indiejoseph
commited on
Commit
•
70ff487
1
Parent(s):
812eb4f
Upload folder using huggingface_hub
Browse files- added_tokens.json +3 -2
- all_results.json +8 -0
- config.json +3 -3
- generation_config.json +2 -3
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +292 -292
- tokenizer.json +0 -18
- tokenizer_config.json +1 -18
- train_results.json +8 -0
- trainer_log.jsonl +348 -0
- trainer_state.json +2471 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
added_tokens.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
|
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"<|reserved000|>": 64931,
|
3 |
+
"<|reserved001|>": 64932,
|
4 |
+
"<|reserved002|>": 64933
|
5 |
}
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9970883209317374,
|
3 |
+
"total_flos": 2.5609799507175014e+18,
|
4 |
+
"train_loss": 0.8316220592066139,
|
5 |
+
"train_runtime": 17540.1657,
|
6 |
+
"train_samples_per_second": 6.344,
|
7 |
+
"train_steps_per_second": 0.099
|
8 |
+
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -23,8 +23,8 @@
|
|
23 |
"rope_scaling": null,
|
24 |
"rope_theta": 5000000.0,
|
25 |
"tie_word_embeddings": false,
|
26 |
-
"torch_dtype": "
|
27 |
-
"transformers_version": "4.
|
28 |
"use_cache": false,
|
29 |
"vocab_size": 64960
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "hon9kon9ize/CantoneseLLM-v0.5",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
23 |
"rope_scaling": null,
|
24 |
"rope_theta": 5000000.0,
|
25 |
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.42.3",
|
28 |
"use_cache": false,
|
29 |
"vocab_size": 64960
|
30 |
}
|
generation_config.json
CHANGED
@@ -1,8 +1,7 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
-
"
|
5 |
-
"eos_token_id": 7,
|
6 |
"pad_token_id": 0,
|
7 |
-
"transformers_version": "4.
|
8 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
|
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.42.3"
|
7 |
}
|
model-00001-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ff4b128a4d342d43910787b8330c8226f26f45fa0be2a7ec5e5bf6424cabc20
|
3 |
+
size 4856125168
|
model-00002-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5595fbedc5adc1b6caa98138f322933fa5af99dd8f67cddd3cbdb16191df831b
|
3 |
+
size 4844657744
|
model-00003-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8361fe259dcab2e71608ec0f950836f4ce5c481e9bcf708649fb3b3405e25323
|
3 |
+
size 4844657784
|
model-00004-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26e2fc8ff1b98f64052df273bbda6f21084c4b4fba3d10e349ba9283ab88dd3a
|
3 |
+
size 4844657784
|
model-00005-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4567b90aba28e189a2d01ec4a144270c17273e23fdec87c7b5a0b05c8d659758
|
3 |
+
size 4885534456
|
model.safetensors.index.json
CHANGED
@@ -1,298 +1,298 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
-
"lm_head.weight": "model-
|
7 |
-
"model.embed_tokens.weight": "model-00001-of-
|
8 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-
|
9 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-
|
10 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-
|
11 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-
|
12 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-
|
13 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-
|
14 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-
|
15 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-
|
16 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-
|
17 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-
|
18 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-
|
19 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-
|
20 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-
|
21 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-
|
22 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-
|
23 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-
|
24 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-
|
25 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-
|
26 |
-
"model.layers.10.input_layernorm.weight": "model-
|
27 |
-
"model.layers.10.mlp.down_proj.weight": "model-
|
28 |
-
"model.layers.10.mlp.gate_proj.weight": "model-
|
29 |
-
"model.layers.10.mlp.up_proj.weight": "model-
|
30 |
-
"model.layers.10.post_attention_layernorm.weight": "model-
|
31 |
-
"model.layers.10.self_attn.k_proj.weight": "model-
|
32 |
-
"model.layers.10.self_attn.o_proj.weight": "model-
|
33 |
-
"model.layers.10.self_attn.q_proj.weight": "model-
|
34 |
-
"model.layers.10.self_attn.v_proj.weight": "model-
|
35 |
-
"model.layers.11.input_layernorm.weight": "model-
|
36 |
-
"model.layers.11.mlp.down_proj.weight": "model-
|
37 |
-
"model.layers.11.mlp.gate_proj.weight": "model-
|
38 |
-
"model.layers.11.mlp.up_proj.weight": "model-
|
39 |
-
"model.layers.11.post_attention_layernorm.weight": "model-
|
40 |
-
"model.layers.11.self_attn.k_proj.weight": "model-
|
41 |
-
"model.layers.11.self_attn.o_proj.weight": "model-
|
42 |
-
"model.layers.11.self_attn.q_proj.weight": "model-
|
43 |
-
"model.layers.11.self_attn.v_proj.weight": "model-
|
44 |
-
"model.layers.12.input_layernorm.weight": "model-
|
45 |
-
"model.layers.12.mlp.down_proj.weight": "model-
|
46 |
-
"model.layers.12.mlp.gate_proj.weight": "model-
|
47 |
-
"model.layers.12.mlp.up_proj.weight": "model-
|
48 |
-
"model.layers.12.post_attention_layernorm.weight": "model-
|
49 |
-
"model.layers.12.self_attn.k_proj.weight": "model-
|
50 |
-
"model.layers.12.self_attn.o_proj.weight": "model-
|
51 |
-
"model.layers.12.self_attn.q_proj.weight": "model-
|
52 |
-
"model.layers.12.self_attn.v_proj.weight": "model-
|
53 |
-
"model.layers.13.input_layernorm.weight": "model-
|
54 |
-
"model.layers.13.mlp.down_proj.weight": "model-
|
55 |
-
"model.layers.13.mlp.gate_proj.weight": "model-
|
56 |
-
"model.layers.13.mlp.up_proj.weight": "model-
|
57 |
-
"model.layers.13.post_attention_layernorm.weight": "model-
|
58 |
-
"model.layers.13.self_attn.k_proj.weight": "model-
|
59 |
-
"model.layers.13.self_attn.o_proj.weight": "model-
|
60 |
-
"model.layers.13.self_attn.q_proj.weight": "model-
|
61 |
-
"model.layers.13.self_attn.v_proj.weight": "model-
|
62 |
-
"model.layers.14.input_layernorm.weight": "model-
|
63 |
-
"model.layers.14.mlp.down_proj.weight": "model-
|
64 |
-
"model.layers.14.mlp.gate_proj.weight": "model-
|
65 |
-
"model.layers.14.mlp.up_proj.weight": "model-
|
66 |
-
"model.layers.14.post_attention_layernorm.weight": "model-
|
67 |
-
"model.layers.14.self_attn.k_proj.weight": "model-
|
68 |
-
"model.layers.14.self_attn.o_proj.weight": "model-
|
69 |
-
"model.layers.14.self_attn.q_proj.weight": "model-
|
70 |
-
"model.layers.14.self_attn.v_proj.weight": "model-
|
71 |
-
"model.layers.15.input_layernorm.weight": "model-
|
72 |
-
"model.layers.15.mlp.down_proj.weight": "model-
|
73 |
-
"model.layers.15.mlp.gate_proj.weight": "model-
|
74 |
-
"model.layers.15.mlp.up_proj.weight": "model-
|
75 |
-
"model.layers.15.post_attention_layernorm.weight": "model-
|
76 |
-
"model.layers.15.self_attn.k_proj.weight": "model-
|
77 |
-
"model.layers.15.self_attn.o_proj.weight": "model-
|
78 |
-
"model.layers.15.self_attn.q_proj.weight": "model-
|
79 |
-
"model.layers.15.self_attn.v_proj.weight": "model-
|
80 |
-
"model.layers.16.input_layernorm.weight": "model-
|
81 |
-
"model.layers.16.mlp.down_proj.weight": "model-
|
82 |
-
"model.layers.16.mlp.gate_proj.weight": "model-
|
83 |
-
"model.layers.16.mlp.up_proj.weight": "model-
|
84 |
-
"model.layers.16.post_attention_layernorm.weight": "model-
|
85 |
-
"model.layers.16.self_attn.k_proj.weight": "model-
|
86 |
-
"model.layers.16.self_attn.o_proj.weight": "model-
|
87 |
-
"model.layers.16.self_attn.q_proj.weight": "model-
|
88 |
-
"model.layers.16.self_attn.v_proj.weight": "model-
|
89 |
-
"model.layers.17.input_layernorm.weight": "model-
|
90 |
-
"model.layers.17.mlp.down_proj.weight": "model-
|
91 |
-
"model.layers.17.mlp.gate_proj.weight": "model-
|
92 |
-
"model.layers.17.mlp.up_proj.weight": "model-
|
93 |
-
"model.layers.17.post_attention_layernorm.weight": "model-
|
94 |
-
"model.layers.17.self_attn.k_proj.weight": "model-
|
95 |
-
"model.layers.17.self_attn.o_proj.weight": "model-
|
96 |
-
"model.layers.17.self_attn.q_proj.weight": "model-
|
97 |
-
"model.layers.17.self_attn.v_proj.weight": "model-
|
98 |
-
"model.layers.18.input_layernorm.weight": "model-
|
99 |
-
"model.layers.18.mlp.down_proj.weight": "model-
|
100 |
-
"model.layers.18.mlp.gate_proj.weight": "model-
|
101 |
-
"model.layers.18.mlp.up_proj.weight": "model-
|
102 |
-
"model.layers.18.post_attention_layernorm.weight": "model-
|
103 |
-
"model.layers.18.self_attn.k_proj.weight": "model-
|
104 |
-
"model.layers.18.self_attn.o_proj.weight": "model-
|
105 |
-
"model.layers.18.self_attn.q_proj.weight": "model-
|
106 |
-
"model.layers.18.self_attn.v_proj.weight": "model-
|
107 |
-
"model.layers.19.input_layernorm.weight": "model-
|
108 |
-
"model.layers.19.mlp.down_proj.weight": "model-
|
109 |
-
"model.layers.19.mlp.gate_proj.weight": "model-
|
110 |
-
"model.layers.19.mlp.up_proj.weight": "model-
|
111 |
-
"model.layers.19.post_attention_layernorm.weight": "model-
|
112 |
-
"model.layers.19.self_attn.k_proj.weight": "model-
|
113 |
-
"model.layers.19.self_attn.o_proj.weight": "model-
|
114 |
-
"model.layers.19.self_attn.q_proj.weight": "model-
|
115 |
-
"model.layers.19.self_attn.v_proj.weight": "model-
|
116 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-
|
117 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-
|
118 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-
|
119 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-
|
120 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-
|
121 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-
|
122 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-
|
123 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-
|
124 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-
|
125 |
-
"model.layers.20.input_layernorm.weight": "model-
|
126 |
-
"model.layers.20.mlp.down_proj.weight": "model-
|
127 |
-
"model.layers.20.mlp.gate_proj.weight": "model-
|
128 |
-
"model.layers.20.mlp.up_proj.weight": "model-
|
129 |
-
"model.layers.20.post_attention_layernorm.weight": "model-
|
130 |
-
"model.layers.20.self_attn.k_proj.weight": "model-
|
131 |
-
"model.layers.20.self_attn.o_proj.weight": "model-
|
132 |
-
"model.layers.20.self_attn.q_proj.weight": "model-
|
133 |
-
"model.layers.20.self_attn.v_proj.weight": "model-
|
134 |
-
"model.layers.21.input_layernorm.weight": "model-
|
135 |
-
"model.layers.21.mlp.down_proj.weight": "model-
|
136 |
-
"model.layers.21.mlp.gate_proj.weight": "model-
|
137 |
-
"model.layers.21.mlp.up_proj.weight": "model-
|
138 |
-
"model.layers.21.post_attention_layernorm.weight": "model-
|
139 |
-
"model.layers.21.self_attn.k_proj.weight": "model-
|
140 |
-
"model.layers.21.self_attn.o_proj.weight": "model-
|
141 |
-
"model.layers.21.self_attn.q_proj.weight": "model-
|
142 |
-
"model.layers.21.self_attn.v_proj.weight": "model-
|
143 |
-
"model.layers.22.input_layernorm.weight": "model-
|
144 |
-
"model.layers.22.mlp.down_proj.weight": "model-
|
145 |
-
"model.layers.22.mlp.gate_proj.weight": "model-
|
146 |
-
"model.layers.22.mlp.up_proj.weight": "model-
|
147 |
-
"model.layers.22.post_attention_layernorm.weight": "model-
|
148 |
-
"model.layers.22.self_attn.k_proj.weight": "model-
|
149 |
-
"model.layers.22.self_attn.o_proj.weight": "model-
|
150 |
-
"model.layers.22.self_attn.q_proj.weight": "model-
|
151 |
-
"model.layers.22.self_attn.v_proj.weight": "model-
|
152 |
-
"model.layers.23.input_layernorm.weight": "model-
|
153 |
-
"model.layers.23.mlp.down_proj.weight": "model-
|
154 |
-
"model.layers.23.mlp.gate_proj.weight": "model-
|
155 |
-
"model.layers.23.mlp.up_proj.weight": "model-
|
156 |
-
"model.layers.23.post_attention_layernorm.weight": "model-
|
157 |
-
"model.layers.23.self_attn.k_proj.weight": "model-
|
158 |
-
"model.layers.23.self_attn.o_proj.weight": "model-
|
159 |
-
"model.layers.23.self_attn.q_proj.weight": "model-
|
160 |
-
"model.layers.23.self_attn.v_proj.weight": "model-
|
161 |
-
"model.layers.24.input_layernorm.weight": "model-
|
162 |
-
"model.layers.24.mlp.down_proj.weight": "model-
|
163 |
-
"model.layers.24.mlp.gate_proj.weight": "model-
|
164 |
-
"model.layers.24.mlp.up_proj.weight": "model-
|
165 |
-
"model.layers.24.post_attention_layernorm.weight": "model-
|
166 |
-
"model.layers.24.self_attn.k_proj.weight": "model-
|
167 |
-
"model.layers.24.self_attn.o_proj.weight": "model-
|
168 |
-
"model.layers.24.self_attn.q_proj.weight": "model-
|
169 |
-
"model.layers.24.self_attn.v_proj.weight": "model-
|
170 |
-
"model.layers.25.input_layernorm.weight": "model-
|
171 |
-
"model.layers.25.mlp.down_proj.weight": "model-
|
172 |
-
"model.layers.25.mlp.gate_proj.weight": "model-
|
173 |
-
"model.layers.25.mlp.up_proj.weight": "model-
|
174 |
-
"model.layers.25.post_attention_layernorm.weight": "model-
|
175 |
-
"model.layers.25.self_attn.k_proj.weight": "model-
|
176 |
-
"model.layers.25.self_attn.o_proj.weight": "model-
|
177 |
-
"model.layers.25.self_attn.q_proj.weight": "model-
|
178 |
-
"model.layers.25.self_attn.v_proj.weight": "model-
|
179 |
-
"model.layers.26.input_layernorm.weight": "model-
|
180 |
-
"model.layers.26.mlp.down_proj.weight": "model-
|
181 |
-
"model.layers.26.mlp.gate_proj.weight": "model-
|
182 |
-
"model.layers.26.mlp.up_proj.weight": "model-
|
183 |
-
"model.layers.26.post_attention_layernorm.weight": "model-
|
184 |
-
"model.layers.26.self_attn.k_proj.weight": "model-
|
185 |
-
"model.layers.26.self_attn.o_proj.weight": "model-
|
186 |
-
"model.layers.26.self_attn.q_proj.weight": "model-
|
187 |
-
"model.layers.26.self_attn.v_proj.weight": "model-
|
188 |
-
"model.layers.27.input_layernorm.weight": "model-
|
189 |
-
"model.layers.27.mlp.down_proj.weight": "model-
|
190 |
-
"model.layers.27.mlp.gate_proj.weight": "model-
|
191 |
-
"model.layers.27.mlp.up_proj.weight": "model-
|
192 |
-
"model.layers.27.post_attention_layernorm.weight": "model-
|
193 |
-
"model.layers.27.self_attn.k_proj.weight": "model-
|
194 |
-
"model.layers.27.self_attn.o_proj.weight": "model-
|
195 |
-
"model.layers.27.self_attn.q_proj.weight": "model-
|
196 |
-
"model.layers.27.self_attn.v_proj.weight": "model-
|
197 |
-
"model.layers.28.input_layernorm.weight": "model-
|
198 |
-
"model.layers.28.mlp.down_proj.weight": "model-
|
199 |
-
"model.layers.28.mlp.gate_proj.weight": "model-
|
200 |
-
"model.layers.28.mlp.up_proj.weight": "model-
|
201 |
-
"model.layers.28.post_attention_layernorm.weight": "model-
|
202 |
-
"model.layers.28.self_attn.k_proj.weight": "model-
|
203 |
-
"model.layers.28.self_attn.o_proj.weight": "model-
|
204 |
-
"model.layers.28.self_attn.q_proj.weight": "model-
|
205 |
-
"model.layers.28.self_attn.v_proj.weight": "model-
|
206 |
-
"model.layers.29.input_layernorm.weight": "model-
|
207 |
-
"model.layers.29.mlp.down_proj.weight": "model-
|
208 |
-
"model.layers.29.mlp.gate_proj.weight": "model-
|
209 |
-
"model.layers.29.mlp.up_proj.weight": "model-
|
210 |
-
"model.layers.29.post_attention_layernorm.weight": "model-
|
211 |
-
"model.layers.29.self_attn.k_proj.weight": "model-
|
212 |
-
"model.layers.29.self_attn.o_proj.weight": "model-
|
213 |
-
"model.layers.29.self_attn.q_proj.weight": "model-
|
214 |
-
"model.layers.29.self_attn.v_proj.weight": "model-
|
215 |
-
"model.layers.3.input_layernorm.weight": "model-00001-of-
|
216 |
-
"model.layers.3.mlp.down_proj.weight": "model-00001-of-
|
217 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-
|
218 |
-
"model.layers.3.mlp.up_proj.weight": "model-00001-of-
|
219 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-
|
220 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-
|
221 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-
|
222 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-
|
223 |
-
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-
|
224 |
-
"model.layers.30.input_layernorm.weight": "model-
|
225 |
-
"model.layers.30.mlp.down_proj.weight": "model-
|
226 |
-
"model.layers.30.mlp.gate_proj.weight": "model-
|
227 |
-
"model.layers.30.mlp.up_proj.weight": "model-
|
228 |
-
"model.layers.30.post_attention_layernorm.weight": "model-
|
229 |
-
"model.layers.30.self_attn.k_proj.weight": "model-
|
230 |
-
"model.layers.30.self_attn.o_proj.weight": "model-
|
231 |
-
"model.layers.30.self_attn.q_proj.weight": "model-
|
232 |
-
"model.layers.30.self_attn.v_proj.weight": "model-
|
233 |
-
"model.layers.31.input_layernorm.weight": "model-
|
234 |
-
"model.layers.31.mlp.down_proj.weight": "model-
|
235 |
-
"model.layers.31.mlp.gate_proj.weight": "model-
|
236 |
-
"model.layers.31.mlp.up_proj.weight": "model-
|
237 |
-
"model.layers.31.post_attention_layernorm.weight": "model-
|
238 |
-
"model.layers.31.self_attn.k_proj.weight": "model-
|
239 |
-
"model.layers.31.self_attn.o_proj.weight": "model-
|
240 |
-
"model.layers.31.self_attn.q_proj.weight": "model-
|
241 |
-
"model.layers.31.self_attn.v_proj.weight": "model-
|
242 |
-
"model.layers.4.input_layernorm.weight": "model-00001-of-
|
243 |
-
"model.layers.4.mlp.down_proj.weight": "model-00001-of-
|
244 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-
|
245 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-
|
246 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-
|
247 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-
|
248 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-
|
249 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-
|
250 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-
|
251 |
-
"model.layers.5.input_layernorm.weight": "model-
|
252 |
-
"model.layers.5.mlp.down_proj.weight": "model-
|
253 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-
|
254 |
-
"model.layers.5.mlp.up_proj.weight": "model-
|
255 |
-
"model.layers.5.post_attention_layernorm.weight": "model-
|
256 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-
|
257 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-
|
258 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-
|
259 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-
|
260 |
-
"model.layers.6.input_layernorm.weight": "model-
|
261 |
-
"model.layers.6.mlp.down_proj.weight": "model-
|
262 |
-
"model.layers.6.mlp.gate_proj.weight": "model-
|
263 |
-
"model.layers.6.mlp.up_proj.weight": "model-
|
264 |
-
"model.layers.6.post_attention_layernorm.weight": "model-
|
265 |
-
"model.layers.6.self_attn.k_proj.weight": "model-
|
266 |
-
"model.layers.6.self_attn.o_proj.weight": "model-
|
267 |
-
"model.layers.6.self_attn.q_proj.weight": "model-
|
268 |
-
"model.layers.6.self_attn.v_proj.weight": "model-
|
269 |
-
"model.layers.7.input_layernorm.weight": "model-
|
270 |
-
"model.layers.7.mlp.down_proj.weight": "model-
|
271 |
-
"model.layers.7.mlp.gate_proj.weight": "model-
|
272 |
-
"model.layers.7.mlp.up_proj.weight": "model-
|
273 |
-
"model.layers.7.post_attention_layernorm.weight": "model-
|
274 |
-
"model.layers.7.self_attn.k_proj.weight": "model-
|
275 |
-
"model.layers.7.self_attn.o_proj.weight": "model-
|
276 |
-
"model.layers.7.self_attn.q_proj.weight": "model-
|
277 |
-
"model.layers.7.self_attn.v_proj.weight": "model-
|
278 |
-
"model.layers.8.input_layernorm.weight": "model-
|
279 |
-
"model.layers.8.mlp.down_proj.weight": "model-
|
280 |
-
"model.layers.8.mlp.gate_proj.weight": "model-
|
281 |
-
"model.layers.8.mlp.up_proj.weight": "model-
|
282 |
-
"model.layers.8.post_attention_layernorm.weight": "model-
|
283 |
-
"model.layers.8.self_attn.k_proj.weight": "model-
|
284 |
-
"model.layers.8.self_attn.o_proj.weight": "model-
|
285 |
-
"model.layers.8.self_attn.q_proj.weight": "model-
|
286 |
-
"model.layers.8.self_attn.v_proj.weight": "model-
|
287 |
-
"model.layers.9.input_layernorm.weight": "model-
|
288 |
-
"model.layers.9.mlp.down_proj.weight": "model-
|
289 |
-
"model.layers.9.mlp.gate_proj.weight": "model-
|
290 |
-
"model.layers.9.mlp.up_proj.weight": "model-
|
291 |
-
"model.layers.9.post_attention_layernorm.weight": "model-
|
292 |
-
"model.layers.9.self_attn.k_proj.weight": "model-
|
293 |
-
"model.layers.9.self_attn.o_proj.weight": "model-
|
294 |
-
"model.layers.9.self_attn.q_proj.weight": "model-
|
295 |
-
"model.layers.9.self_attn.v_proj.weight": "model-
|
296 |
-
"model.norm.weight": "model-
|
297 |
}
|
298 |
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 24275599360
|
4 |
},
|
5 |
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00005-of-00005.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
296 |
+
"model.norm.weight": "model-00005-of-00005.safetensors"
|
297 |
}
|
298 |
}
|
tokenizer.json
CHANGED
@@ -74,24 +74,6 @@
|
|
74 |
"rstrip": false,
|
75 |
"normalized": false,
|
76 |
"special": true
|
77 |
-
},
|
78 |
-
{
|
79 |
-
"id": 64931,
|
80 |
-
"content": "<s>",
|
81 |
-
"single_word": false,
|
82 |
-
"lstrip": false,
|
83 |
-
"rstrip": false,
|
84 |
-
"normalized": false,
|
85 |
-
"special": true
|
86 |
-
},
|
87 |
-
{
|
88 |
-
"id": 64932,
|
89 |
-
"content": "</s>",
|
90 |
-
"single_word": false,
|
91 |
-
"lstrip": false,
|
92 |
-
"rstrip": false,
|
93 |
-
"normalized": false,
|
94 |
-
"special": true
|
95 |
}
|
96 |
],
|
97 |
"normalizer": {
|
|
|
74 |
"rstrip": false,
|
75 |
"normalized": false,
|
76 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
}
|
78 |
],
|
79 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"add_bos_token": false,
|
3 |
"add_eos_token": false,
|
4 |
-
"add_prefix_space":
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
@@ -66,22 +66,6 @@
|
|
66 |
"rstrip": false,
|
67 |
"single_word": false,
|
68 |
"special": true
|
69 |
-
},
|
70 |
-
"64931": {
|
71 |
-
"content": "<s>",
|
72 |
-
"lstrip": false,
|
73 |
-
"normalized": false,
|
74 |
-
"rstrip": false,
|
75 |
-
"single_word": false,
|
76 |
-
"special": true
|
77 |
-
},
|
78 |
-
"64932": {
|
79 |
-
"content": "</s>",
|
80 |
-
"lstrip": false,
|
81 |
-
"normalized": false,
|
82 |
-
"rstrip": false,
|
83 |
-
"single_word": false,
|
84 |
-
"special": true
|
85 |
}
|
86 |
},
|
87 |
"additional_special_tokens": [
|
@@ -100,7 +84,6 @@
|
|
100 |
"pad_token": "<unk>",
|
101 |
"padding_side": "right",
|
102 |
"sp_model_kwargs": {},
|
103 |
-
"spaces_between_special_tokens": false,
|
104 |
"split_special_tokens": false,
|
105 |
"tokenizer_class": "LlamaTokenizer",
|
106 |
"unk_token": "<unk>",
|
|
|
1 |
{
|
2 |
"add_bos_token": false,
|
3 |
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
|
|
66 |
"rstrip": false,
|
67 |
"single_word": false,
|
68 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
}
|
70 |
},
|
71 |
"additional_special_tokens": [
|
|
|
84 |
"pad_token": "<unk>",
|
85 |
"padding_side": "right",
|
86 |
"sp_model_kwargs": {},
|
|
|
87 |
"split_special_tokens": false,
|
88 |
"tokenizer_class": "LlamaTokenizer",
|
89 |
"unk_token": "<unk>",
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9970883209317374,
|
3 |
+
"total_flos": 2.5609799507175014e+18,
|
4 |
+
"train_loss": 0.8316220592066139,
|
5 |
+
"train_runtime": 17540.1657,
|
6 |
+
"train_samples_per_second": 6.344,
|
7 |
+
"train_steps_per_second": 0.099
|
8 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,348 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 5, "total_steps": 1737, "loss": 1.3814, "learning_rate": 1e-05, "epoch": 0.008627197239296884, "percentage": 0.29, "elapsed_time": "0:00:54", "remaining_time": "5:16:42", "throughput": "0.00", "total_tokens": 0}
|
2 |
+
{"current_steps": 10, "total_steps": 1737, "loss": 1.3848, "learning_rate": 1e-05, "epoch": 0.017254394478593768, "percentage": 0.58, "elapsed_time": "0:01:39", "remaining_time": "4:45:57", "throughput": "0.00", "total_tokens": 0}
|
3 |
+
{"current_steps": 15, "total_steps": 1737, "loss": 1.3517, "learning_rate": 1e-05, "epoch": 0.02588159171789065, "percentage": 0.86, "elapsed_time": "0:02:28", "remaining_time": "4:43:15", "throughput": "0.00", "total_tokens": 0}
|
4 |
+
{"current_steps": 20, "total_steps": 1737, "loss": 1.4088, "learning_rate": 1e-05, "epoch": 0.034508788957187536, "percentage": 1.15, "elapsed_time": "0:03:11", "remaining_time": "4:34:06", "throughput": "0.00", "total_tokens": 0}
|
5 |
+
{"current_steps": 25, "total_steps": 1737, "loss": 1.3542, "learning_rate": 1e-05, "epoch": 0.04313598619648442, "percentage": 1.44, "elapsed_time": "0:03:55", "remaining_time": "4:28:52", "throughput": "0.00", "total_tokens": 0}
|
6 |
+
{"current_steps": 30, "total_steps": 1737, "loss": 1.3434, "learning_rate": 1e-05, "epoch": 0.0517631834357813, "percentage": 1.73, "elapsed_time": "0:04:45", "remaining_time": "4:30:54", "throughput": "0.00", "total_tokens": 0}
|
7 |
+
{"current_steps": 35, "total_steps": 1737, "loss": 1.3926, "learning_rate": 1e-05, "epoch": 0.06039038067507818, "percentage": 2.01, "elapsed_time": "0:05:34", "remaining_time": "4:30:48", "throughput": "0.00", "total_tokens": 0}
|
8 |
+
{"current_steps": 40, "total_steps": 1737, "loss": 1.2819, "learning_rate": 1e-05, "epoch": 0.06901757791437507, "percentage": 2.3, "elapsed_time": "0:06:26", "remaining_time": "4:33:18", "throughput": "0.00", "total_tokens": 0}
|
9 |
+
{"current_steps": 45, "total_steps": 1737, "loss": 1.3482, "learning_rate": 1e-05, "epoch": 0.07764477515367195, "percentage": 2.59, "elapsed_time": "0:07:22", "remaining_time": "4:37:16", "throughput": "0.00", "total_tokens": 0}
|
10 |
+
{"current_steps": 50, "total_steps": 1737, "loss": 1.2621, "learning_rate": 1e-05, "epoch": 0.08627197239296884, "percentage": 2.88, "elapsed_time": "0:08:09", "remaining_time": "4:35:14", "throughput": "0.00", "total_tokens": 0}
|
11 |
+
{"current_steps": 55, "total_steps": 1737, "loss": 1.2695, "learning_rate": 1e-05, "epoch": 0.09489916963226572, "percentage": 3.17, "elapsed_time": "0:08:54", "remaining_time": "4:32:34", "throughput": "0.00", "total_tokens": 0}
|
12 |
+
{"current_steps": 60, "total_steps": 1737, "loss": 1.2302, "learning_rate": 1e-05, "epoch": 0.1035263668715626, "percentage": 3.45, "elapsed_time": "0:09:45", "remaining_time": "4:32:50", "throughput": "0.00", "total_tokens": 0}
|
13 |
+
{"current_steps": 65, "total_steps": 1737, "loss": 1.242, "learning_rate": 1e-05, "epoch": 0.11215356411085949, "percentage": 3.74, "elapsed_time": "0:10:34", "remaining_time": "4:31:55", "throughput": "0.00", "total_tokens": 0}
|
14 |
+
{"current_steps": 70, "total_steps": 1737, "loss": 1.2433, "learning_rate": 1e-05, "epoch": 0.12078076135015636, "percentage": 4.03, "elapsed_time": "0:11:20", "remaining_time": "4:30:00", "throughput": "0.00", "total_tokens": 0}
|
15 |
+
{"current_steps": 75, "total_steps": 1737, "loss": 1.3095, "learning_rate": 1e-05, "epoch": 0.12940795858945325, "percentage": 4.32, "elapsed_time": "0:12:03", "remaining_time": "4:27:19", "throughput": "0.00", "total_tokens": 0}
|
16 |
+
{"current_steps": 80, "total_steps": 1737, "loss": 1.3006, "learning_rate": 1e-05, "epoch": 0.13803515582875014, "percentage": 4.61, "elapsed_time": "0:12:50", "remaining_time": "4:25:57", "throughput": "0.00", "total_tokens": 0}
|
17 |
+
{"current_steps": 85, "total_steps": 1737, "loss": 1.2698, "learning_rate": 1e-05, "epoch": 0.146662353068047, "percentage": 4.89, "elapsed_time": "0:13:36", "remaining_time": "4:24:24", "throughput": "0.00", "total_tokens": 0}
|
18 |
+
{"current_steps": 90, "total_steps": 1737, "loss": 1.3346, "learning_rate": 1e-05, "epoch": 0.1552895503073439, "percentage": 5.18, "elapsed_time": "0:14:23", "remaining_time": "4:23:26", "throughput": "0.00", "total_tokens": 0}
|
19 |
+
{"current_steps": 95, "total_steps": 1737, "loss": 1.3634, "learning_rate": 1e-05, "epoch": 0.1639167475466408, "percentage": 5.47, "elapsed_time": "0:15:09", "remaining_time": "4:22:06", "throughput": "0.00", "total_tokens": 0}
|
20 |
+
{"current_steps": 100, "total_steps": 1737, "loss": 1.2645, "learning_rate": 1e-05, "epoch": 0.17254394478593768, "percentage": 5.76, "elapsed_time": "0:15:58", "remaining_time": "4:21:31", "throughput": "0.00", "total_tokens": 0}
|
21 |
+
{"current_steps": 105, "total_steps": 1737, "loss": 1.3625, "learning_rate": 1e-05, "epoch": 0.18117114202523454, "percentage": 6.04, "elapsed_time": "0:16:46", "remaining_time": "4:20:41", "throughput": "0.00", "total_tokens": 0}
|
22 |
+
{"current_steps": 110, "total_steps": 1737, "loss": 1.2592, "learning_rate": 1e-05, "epoch": 0.18979833926453143, "percentage": 6.33, "elapsed_time": "0:17:31", "remaining_time": "4:19:10", "throughput": "0.00", "total_tokens": 0}
|
23 |
+
{"current_steps": 115, "total_steps": 1737, "loss": 1.2872, "learning_rate": 1e-05, "epoch": 0.19842553650382833, "percentage": 6.62, "elapsed_time": "0:18:21", "remaining_time": "4:18:50", "throughput": "0.00", "total_tokens": 0}
|
24 |
+
{"current_steps": 120, "total_steps": 1737, "loss": 1.31, "learning_rate": 1e-05, "epoch": 0.2070527337431252, "percentage": 6.91, "elapsed_time": "0:19:11", "remaining_time": "4:18:33", "throughput": "0.00", "total_tokens": 0}
|
25 |
+
{"current_steps": 125, "total_steps": 1737, "loss": 1.2627, "learning_rate": 1e-05, "epoch": 0.21567993098242208, "percentage": 7.2, "elapsed_time": "0:20:00", "remaining_time": "4:17:58", "throughput": "0.00", "total_tokens": 0}
|
26 |
+
{"current_steps": 130, "total_steps": 1737, "loss": 1.206, "learning_rate": 1e-05, "epoch": 0.22430712822171897, "percentage": 7.48, "elapsed_time": "0:20:51", "remaining_time": "4:17:54", "throughput": "0.00", "total_tokens": 0}
|
27 |
+
{"current_steps": 135, "total_steps": 1737, "loss": 1.3192, "learning_rate": 1e-05, "epoch": 0.23293432546101586, "percentage": 7.77, "elapsed_time": "0:21:39", "remaining_time": "4:17:02", "throughput": "0.00", "total_tokens": 0}
|
28 |
+
{"current_steps": 140, "total_steps": 1737, "loss": 1.2825, "learning_rate": 1e-05, "epoch": 0.24156152270031273, "percentage": 8.06, "elapsed_time": "0:22:26", "remaining_time": "4:16:01", "throughput": "0.00", "total_tokens": 0}
|
29 |
+
{"current_steps": 145, "total_steps": 1737, "loss": 1.3421, "learning_rate": 1e-05, "epoch": 0.2501887199396096, "percentage": 8.35, "elapsed_time": "0:23:14", "remaining_time": "4:15:05", "throughput": "0.00", "total_tokens": 0}
|
30 |
+
{"current_steps": 150, "total_steps": 1737, "loss": 1.3141, "learning_rate": 1e-05, "epoch": 0.2588159171789065, "percentage": 8.64, "elapsed_time": "0:24:06", "remaining_time": "4:15:02", "throughput": "0.00", "total_tokens": 0}
|
31 |
+
{"current_steps": 155, "total_steps": 1737, "loss": 1.298, "learning_rate": 1e-05, "epoch": 0.2674431144182034, "percentage": 8.92, "elapsed_time": "0:24:53", "remaining_time": "4:14:08", "throughput": "0.00", "total_tokens": 0}
|
32 |
+
{"current_steps": 160, "total_steps": 1737, "loss": 1.3034, "learning_rate": 1e-05, "epoch": 0.2760703116575003, "percentage": 9.21, "elapsed_time": "0:25:48", "remaining_time": "4:14:26", "throughput": "0.00", "total_tokens": 0}
|
33 |
+
{"current_steps": 165, "total_steps": 1737, "loss": 1.2532, "learning_rate": 1e-05, "epoch": 0.2846975088967972, "percentage": 9.5, "elapsed_time": "0:26:34", "remaining_time": "4:13:13", "throughput": "0.00", "total_tokens": 0}
|
34 |
+
{"current_steps": 170, "total_steps": 1737, "loss": 1.2745, "learning_rate": 1e-05, "epoch": 0.293324706136094, "percentage": 9.79, "elapsed_time": "0:27:28", "remaining_time": "4:13:13", "throughput": "0.00", "total_tokens": 0}
|
35 |
+
{"current_steps": 175, "total_steps": 1737, "loss": 1.3067, "learning_rate": 1e-05, "epoch": 0.3019519033753909, "percentage": 10.07, "elapsed_time": "0:28:10", "remaining_time": "4:11:33", "throughput": "0.00", "total_tokens": 0}
|
36 |
+
{"current_steps": 180, "total_steps": 1737, "loss": 1.2628, "learning_rate": 1e-05, "epoch": 0.3105791006146878, "percentage": 10.36, "elapsed_time": "0:29:08", "remaining_time": "4:12:04", "throughput": "0.00", "total_tokens": 0}
|
37 |
+
{"current_steps": 185, "total_steps": 1737, "loss": 1.2514, "learning_rate": 1e-05, "epoch": 0.3192062978539847, "percentage": 10.65, "elapsed_time": "0:30:07", "remaining_time": "4:12:40", "throughput": "0.00", "total_tokens": 0}
|
38 |
+
{"current_steps": 190, "total_steps": 1737, "loss": 1.2122, "learning_rate": 1e-05, "epoch": 0.3278334950932816, "percentage": 10.94, "elapsed_time": "0:30:59", "remaining_time": "4:12:16", "throughput": "0.00", "total_tokens": 0}
|
39 |
+
{"current_steps": 195, "total_steps": 1737, "loss": 1.2825, "learning_rate": 1e-05, "epoch": 0.33646069233257847, "percentage": 11.23, "elapsed_time": "0:31:41", "remaining_time": "4:10:39", "throughput": "0.00", "total_tokens": 0}
|
40 |
+
{"current_steps": 200, "total_steps": 1737, "loss": 1.2752, "learning_rate": 1e-05, "epoch": 0.34508788957187536, "percentage": 11.51, "elapsed_time": "0:32:34", "remaining_time": "4:10:22", "throughput": "0.00", "total_tokens": 0}
|
41 |
+
{"current_steps": 205, "total_steps": 1737, "loss": 1.3145, "learning_rate": 1e-05, "epoch": 0.3537150868111722, "percentage": 11.8, "elapsed_time": "0:34:44", "remaining_time": "4:19:40", "throughput": "0.00", "total_tokens": 0}
|
42 |
+
{"current_steps": 210, "total_steps": 1737, "loss": 1.2694, "learning_rate": 1e-05, "epoch": 0.3623422840504691, "percentage": 12.09, "elapsed_time": "0:35:25", "remaining_time": "4:17:36", "throughput": "0.00", "total_tokens": 0}
|
43 |
+
{"current_steps": 215, "total_steps": 1737, "loss": 1.3507, "learning_rate": 1e-05, "epoch": 0.370969481289766, "percentage": 12.38, "elapsed_time": "0:36:21", "remaining_time": "4:17:23", "throughput": "0.00", "total_tokens": 0}
|
44 |
+
{"current_steps": 220, "total_steps": 1737, "loss": 1.3843, "learning_rate": 1e-05, "epoch": 0.37959667852906287, "percentage": 12.67, "elapsed_time": "0:37:12", "remaining_time": "4:16:31", "throughput": "0.00", "total_tokens": 0}
|
45 |
+
{"current_steps": 225, "total_steps": 1737, "loss": 1.2553, "learning_rate": 1e-05, "epoch": 0.38822387576835976, "percentage": 12.95, "elapsed_time": "0:37:56", "remaining_time": "4:14:58", "throughput": "0.00", "total_tokens": 0}
|
46 |
+
{"current_steps": 230, "total_steps": 1737, "loss": 1.3664, "learning_rate": 1e-05, "epoch": 0.39685107300765665, "percentage": 13.24, "elapsed_time": "0:38:47", "remaining_time": "4:14:09", "throughput": "0.00", "total_tokens": 0}
|
47 |
+
{"current_steps": 235, "total_steps": 1737, "loss": 1.3083, "learning_rate": 1e-05, "epoch": 0.40547827024695354, "percentage": 13.53, "elapsed_time": "0:39:35", "remaining_time": "4:13:00", "throughput": "0.00", "total_tokens": 0}
|
48 |
+
{"current_steps": 240, "total_steps": 1737, "loss": 1.2945, "learning_rate": 1e-05, "epoch": 0.4141054674862504, "percentage": 13.82, "elapsed_time": "0:40:22", "remaining_time": "4:11:48", "throughput": "0.00", "total_tokens": 0}
|
49 |
+
{"current_steps": 245, "total_steps": 1737, "loss": 1.2938, "learning_rate": 1e-05, "epoch": 0.42273266472554727, "percentage": 14.1, "elapsed_time": "0:41:12", "remaining_time": "4:10:57", "throughput": "0.00", "total_tokens": 0}
|
50 |
+
{"current_steps": 250, "total_steps": 1737, "loss": 1.2231, "learning_rate": 1e-05, "epoch": 0.43135986196484416, "percentage": 14.39, "elapsed_time": "0:42:06", "remaining_time": "4:10:28", "throughput": "0.00", "total_tokens": 0}
|
51 |
+
{"current_steps": 255, "total_steps": 1737, "loss": 1.2237, "learning_rate": 1e-05, "epoch": 0.43998705920414105, "percentage": 14.68, "elapsed_time": "0:42:58", "remaining_time": "4:09:43", "throughput": "0.00", "total_tokens": 0}
|
52 |
+
{"current_steps": 260, "total_steps": 1737, "loss": 1.1541, "learning_rate": 1e-05, "epoch": 0.44861425644343794, "percentage": 14.97, "elapsed_time": "0:43:44", "remaining_time": "4:08:27", "throughput": "0.00", "total_tokens": 0}
|
53 |
+
{"current_steps": 265, "total_steps": 1737, "loss": 1.2629, "learning_rate": 1e-05, "epoch": 0.45724145368273483, "percentage": 15.26, "elapsed_time": "0:44:30", "remaining_time": "4:07:14", "throughput": "0.00", "total_tokens": 0}
|
54 |
+
{"current_steps": 270, "total_steps": 1737, "loss": 1.1911, "learning_rate": 1e-05, "epoch": 0.4658686509220317, "percentage": 15.54, "elapsed_time": "0:45:17", "remaining_time": "4:06:07", "throughput": "0.00", "total_tokens": 0}
|
55 |
+
{"current_steps": 275, "total_steps": 1737, "loss": 1.4012, "learning_rate": 1e-05, "epoch": 0.4744958481613286, "percentage": 15.83, "elapsed_time": "0:46:03", "remaining_time": "4:04:51", "throughput": "0.00", "total_tokens": 0}
|
56 |
+
{"current_steps": 280, "total_steps": 1737, "loss": 1.2188, "learning_rate": 1e-05, "epoch": 0.48312304540062545, "percentage": 16.12, "elapsed_time": "0:46:53", "remaining_time": "4:03:58", "throughput": "0.00", "total_tokens": 0}
|
57 |
+
{"current_steps": 285, "total_steps": 1737, "loss": 1.354, "learning_rate": 1e-05, "epoch": 0.49175024263992234, "percentage": 16.41, "elapsed_time": "0:47:38", "remaining_time": "4:02:44", "throughput": "0.00", "total_tokens": 0}
|
58 |
+
{"current_steps": 290, "total_steps": 1737, "loss": 1.3322, "learning_rate": 1e-05, "epoch": 0.5003774398792192, "percentage": 16.7, "elapsed_time": "0:48:23", "remaining_time": "4:01:29", "throughput": "0.00", "total_tokens": 0}
|
59 |
+
{"current_steps": 295, "total_steps": 1737, "loss": 1.3385, "learning_rate": 1e-05, "epoch": 0.5090046371185161, "percentage": 16.98, "elapsed_time": "0:49:15", "remaining_time": "4:00:46", "throughput": "0.00", "total_tokens": 0}
|
60 |
+
{"current_steps": 300, "total_steps": 1737, "loss": 1.2541, "learning_rate": 1e-05, "epoch": 0.517631834357813, "percentage": 17.27, "elapsed_time": "0:50:00", "remaining_time": "3:59:30", "throughput": "0.00", "total_tokens": 0}
|
61 |
+
{"current_steps": 305, "total_steps": 1737, "loss": 1.3451, "learning_rate": 1e-05, "epoch": 0.5262590315971098, "percentage": 17.56, "elapsed_time": "0:50:52", "remaining_time": "3:58:53", "throughput": "0.00", "total_tokens": 0}
|
62 |
+
{"current_steps": 310, "total_steps": 1737, "loss": 1.3269, "learning_rate": 1e-05, "epoch": 0.5348862288364068, "percentage": 17.85, "elapsed_time": "0:51:43", "remaining_time": "3:58:07", "throughput": "0.00", "total_tokens": 0}
|
63 |
+
{"current_steps": 315, "total_steps": 1737, "loss": 1.2654, "learning_rate": 1e-05, "epoch": 0.5435134260757036, "percentage": 18.13, "elapsed_time": "0:52:34", "remaining_time": "3:57:18", "throughput": "0.00", "total_tokens": 0}
|
64 |
+
{"current_steps": 320, "total_steps": 1737, "loss": 1.3162, "learning_rate": 1e-05, "epoch": 0.5521406233150006, "percentage": 18.42, "elapsed_time": "0:53:21", "remaining_time": "3:56:17", "throughput": "0.00", "total_tokens": 0}
|
65 |
+
{"current_steps": 325, "total_steps": 1737, "loss": 1.2839, "learning_rate": 1e-05, "epoch": 0.5607678205542974, "percentage": 18.71, "elapsed_time": "0:54:14", "remaining_time": "3:55:40", "throughput": "0.00", "total_tokens": 0}
|
66 |
+
{"current_steps": 330, "total_steps": 1737, "loss": 1.3095, "learning_rate": 1e-05, "epoch": 0.5693950177935944, "percentage": 19.0, "elapsed_time": "0:55:04", "remaining_time": "3:54:47", "throughput": "0.00", "total_tokens": 0}
|
67 |
+
{"current_steps": 335, "total_steps": 1737, "loss": 1.285, "learning_rate": 1e-05, "epoch": 0.5780222150328912, "percentage": 19.29, "elapsed_time": "0:55:50", "remaining_time": "3:53:42", "throughput": "0.00", "total_tokens": 0}
|
68 |
+
{"current_steps": 340, "total_steps": 1737, "loss": 1.2419, "learning_rate": 1e-05, "epoch": 0.586649412272188, "percentage": 19.57, "elapsed_time": "0:56:35", "remaining_time": "3:52:30", "throughput": "0.00", "total_tokens": 0}
|
69 |
+
{"current_steps": 345, "total_steps": 1737, "loss": 1.2875, "learning_rate": 1e-05, "epoch": 0.595276609511485, "percentage": 19.86, "elapsed_time": "0:57:22", "remaining_time": "3:51:29", "throughput": "0.00", "total_tokens": 0}
|
70 |
+
{"current_steps": 350, "total_steps": 1737, "loss": 1.3055, "learning_rate": 1e-05, "epoch": 0.6039038067507818, "percentage": 20.15, "elapsed_time": "0:58:09", "remaining_time": "3:50:29", "throughput": "0.00", "total_tokens": 0}
|
71 |
+
{"current_steps": 355, "total_steps": 1737, "loss": 1.33, "learning_rate": 1e-05, "epoch": 0.6125310039900788, "percentage": 20.44, "elapsed_time": "0:58:56", "remaining_time": "3:49:27", "throughput": "0.00", "total_tokens": 0}
|
72 |
+
{"current_steps": 360, "total_steps": 1737, "loss": 1.2003, "learning_rate": 1e-05, "epoch": 0.6211582012293756, "percentage": 20.73, "elapsed_time": "0:59:44", "remaining_time": "3:48:30", "throughput": "0.00", "total_tokens": 0}
|
73 |
+
{"current_steps": 365, "total_steps": 1737, "loss": 1.2385, "learning_rate": 1e-05, "epoch": 0.6297853984686725, "percentage": 21.01, "elapsed_time": "1:00:33", "remaining_time": "3:47:37", "throughput": "0.00", "total_tokens": 0}
|
74 |
+
{"current_steps": 370, "total_steps": 1737, "loss": 1.2198, "learning_rate": 1e-05, "epoch": 0.6384125957079694, "percentage": 21.3, "elapsed_time": "1:01:27", "remaining_time": "3:47:04", "throughput": "0.00", "total_tokens": 0}
|
75 |
+
{"current_steps": 375, "total_steps": 1737, "loss": 1.3135, "learning_rate": 1e-05, "epoch": 0.6470397929472662, "percentage": 21.59, "elapsed_time": "1:02:12", "remaining_time": "3:45:55", "throughput": "0.00", "total_tokens": 0}
|
76 |
+
{"current_steps": 380, "total_steps": 1737, "loss": 1.3234, "learning_rate": 1e-05, "epoch": 0.6556669901865632, "percentage": 21.88, "elapsed_time": "1:02:57", "remaining_time": "3:44:51", "throughput": "0.00", "total_tokens": 0}
|
77 |
+
{"current_steps": 385, "total_steps": 1737, "loss": 1.3376, "learning_rate": 1e-05, "epoch": 0.66429418742586, "percentage": 22.16, "elapsed_time": "1:03:47", "remaining_time": "3:44:00", "throughput": "0.00", "total_tokens": 0}
|
78 |
+
{"current_steps": 390, "total_steps": 1737, "loss": 1.2237, "learning_rate": 1e-05, "epoch": 0.6729213846651569, "percentage": 22.45, "elapsed_time": "1:04:35", "remaining_time": "3:43:04", "throughput": "0.00", "total_tokens": 0}
|
79 |
+
{"current_steps": 395, "total_steps": 1737, "loss": 1.2465, "learning_rate": 1e-05, "epoch": 0.6815485819044538, "percentage": 22.74, "elapsed_time": "1:05:24", "remaining_time": "3:42:13", "throughput": "0.00", "total_tokens": 0}
|
80 |
+
{"current_steps": 400, "total_steps": 1737, "loss": 1.2188, "learning_rate": 1e-05, "epoch": 0.6901757791437507, "percentage": 23.03, "elapsed_time": "1:06:12", "remaining_time": "3:41:16", "throughput": "0.00", "total_tokens": 0}
|
81 |
+
{"current_steps": 405, "total_steps": 1737, "loss": 1.2663, "learning_rate": 1e-05, "epoch": 0.6988029763830476, "percentage": 23.32, "elapsed_time": "1:08:26", "remaining_time": "3:45:04", "throughput": "0.00", "total_tokens": 0}
|
82 |
+
{"current_steps": 410, "total_steps": 1737, "loss": 1.3354, "learning_rate": 1e-05, "epoch": 0.7074301736223444, "percentage": 23.6, "elapsed_time": "1:09:13", "remaining_time": "3:44:01", "throughput": "0.00", "total_tokens": 0}
|
83 |
+
{"current_steps": 415, "total_steps": 1737, "loss": 1.3112, "learning_rate": 1e-05, "epoch": 0.7160573708616413, "percentage": 23.89, "elapsed_time": "1:10:01", "remaining_time": "3:43:03", "throughput": "0.00", "total_tokens": 0}
|
84 |
+
{"current_steps": 420, "total_steps": 1737, "loss": 1.2335, "learning_rate": 1e-05, "epoch": 0.7246845681009382, "percentage": 24.18, "elapsed_time": "1:10:49", "remaining_time": "3:42:04", "throughput": "0.00", "total_tokens": 0}
|
85 |
+
{"current_steps": 425, "total_steps": 1737, "loss": 1.2291, "learning_rate": 1e-05, "epoch": 0.7333117653402351, "percentage": 24.47, "elapsed_time": "1:11:34", "remaining_time": "3:40:56", "throughput": "0.00", "total_tokens": 0}
|
86 |
+
{"current_steps": 430, "total_steps": 1737, "loss": 1.1676, "learning_rate": 1e-05, "epoch": 0.741938962579532, "percentage": 24.76, "elapsed_time": "1:12:17", "remaining_time": "3:39:44", "throughput": "0.00", "total_tokens": 0}
|
87 |
+
{"current_steps": 435, "total_steps": 1737, "loss": 1.2539, "learning_rate": 1e-05, "epoch": 0.7505661598188289, "percentage": 25.04, "elapsed_time": "1:13:11", "remaining_time": "3:39:04", "throughput": "0.00", "total_tokens": 0}
|
88 |
+
{"current_steps": 440, "total_steps": 1737, "loss": 1.2994, "learning_rate": 1e-05, "epoch": 0.7591933570581257, "percentage": 25.33, "elapsed_time": "1:13:59", "remaining_time": "3:38:07", "throughput": "0.00", "total_tokens": 0}
|
89 |
+
{"current_steps": 445, "total_steps": 1737, "loss": 1.2304, "learning_rate": 1e-05, "epoch": 0.7678205542974226, "percentage": 25.62, "elapsed_time": "1:14:44", "remaining_time": "3:36:59", "throughput": "0.00", "total_tokens": 0}
|
90 |
+
{"current_steps": 450, "total_steps": 1737, "loss": 1.2871, "learning_rate": 1e-05, "epoch": 0.7764477515367195, "percentage": 25.91, "elapsed_time": "1:15:32", "remaining_time": "3:36:02", "throughput": "0.00", "total_tokens": 0}
|
91 |
+
{"current_steps": 455, "total_steps": 1737, "loss": 1.3053, "learning_rate": 1e-05, "epoch": 0.7850749487760164, "percentage": 26.19, "elapsed_time": "1:16:22", "remaining_time": "3:35:12", "throughput": "0.00", "total_tokens": 0}
|
92 |
+
{"current_steps": 460, "total_steps": 1737, "loss": 1.2691, "learning_rate": 1e-05, "epoch": 0.7937021460153133, "percentage": 26.48, "elapsed_time": "1:17:11", "remaining_time": "3:34:16", "throughput": "0.00", "total_tokens": 0}
|
93 |
+
{"current_steps": 465, "total_steps": 1737, "loss": 1.2744, "learning_rate": 1e-05, "epoch": 0.8023293432546101, "percentage": 26.77, "elapsed_time": "1:17:54", "remaining_time": "3:33:07", "throughput": "0.00", "total_tokens": 0}
|
94 |
+
{"current_steps": 470, "total_steps": 1737, "loss": 1.2016, "learning_rate": 1e-05, "epoch": 0.8109565404939071, "percentage": 27.06, "elapsed_time": "1:18:42", "remaining_time": "3:32:10", "throughput": "0.00", "total_tokens": 0}
|
95 |
+
{"current_steps": 475, "total_steps": 1737, "loss": 1.2787, "learning_rate": 1e-05, "epoch": 0.8195837377332039, "percentage": 27.35, "elapsed_time": "1:19:30", "remaining_time": "3:31:13", "throughput": "0.00", "total_tokens": 0}
|
96 |
+
{"current_steps": 480, "total_steps": 1737, "loss": 1.3095, "learning_rate": 1e-05, "epoch": 0.8282109349725008, "percentage": 27.63, "elapsed_time": "1:20:16", "remaining_time": "3:30:13", "throughput": "0.00", "total_tokens": 0}
|
97 |
+
{"current_steps": 485, "total_steps": 1737, "loss": 1.2503, "learning_rate": 1e-05, "epoch": 0.8368381322117977, "percentage": 27.92, "elapsed_time": "1:21:05", "remaining_time": "3:29:20", "throughput": "0.00", "total_tokens": 0}
|
98 |
+
{"current_steps": 490, "total_steps": 1737, "loss": 1.2598, "learning_rate": 1e-05, "epoch": 0.8454653294510945, "percentage": 28.21, "elapsed_time": "1:21:50", "remaining_time": "3:28:17", "throughput": "0.00", "total_tokens": 0}
|
99 |
+
{"current_steps": 495, "total_steps": 1737, "loss": 1.2914, "learning_rate": 1e-05, "epoch": 0.8540925266903915, "percentage": 28.5, "elapsed_time": "1:22:40", "remaining_time": "3:27:26", "throughput": "0.00", "total_tokens": 0}
|
100 |
+
{"current_steps": 500, "total_steps": 1737, "loss": 1.2744, "learning_rate": 1e-05, "epoch": 0.8627197239296883, "percentage": 28.79, "elapsed_time": "1:23:25", "remaining_time": "3:26:23", "throughput": "0.00", "total_tokens": 0}
|
101 |
+
{"current_steps": 505, "total_steps": 1737, "loss": 1.3817, "learning_rate": 1e-05, "epoch": 0.8713469211689853, "percentage": 29.07, "elapsed_time": "1:24:12", "remaining_time": "3:25:26", "throughput": "0.00", "total_tokens": 0}
|
102 |
+
{"current_steps": 510, "total_steps": 1737, "loss": 1.1628, "learning_rate": 1e-05, "epoch": 0.8799741184082821, "percentage": 29.36, "elapsed_time": "1:25:01", "remaining_time": "3:24:33", "throughput": "0.00", "total_tokens": 0}
|
103 |
+
{"current_steps": 515, "total_steps": 1737, "loss": 1.2602, "learning_rate": 1e-05, "epoch": 0.8886013156475789, "percentage": 29.65, "elapsed_time": "1:25:46", "remaining_time": "3:23:31", "throughput": "0.00", "total_tokens": 0}
|
104 |
+
{"current_steps": 520, "total_steps": 1737, "loss": 1.2036, "learning_rate": 1e-05, "epoch": 0.8972285128868759, "percentage": 29.94, "elapsed_time": "1:26:37", "remaining_time": "3:22:44", "throughput": "0.00", "total_tokens": 0}
|
105 |
+
{"current_steps": 525, "total_steps": 1737, "loss": 1.2575, "learning_rate": 1e-05, "epoch": 0.9058557101261727, "percentage": 30.22, "elapsed_time": "1:27:32", "remaining_time": "3:22:05", "throughput": "0.00", "total_tokens": 0}
|
106 |
+
{"current_steps": 530, "total_steps": 1737, "loss": 1.2762, "learning_rate": 1e-05, "epoch": 0.9144829073654697, "percentage": 30.51, "elapsed_time": "1:28:22", "remaining_time": "3:21:16", "throughput": "0.00", "total_tokens": 0}
|
107 |
+
{"current_steps": 535, "total_steps": 1737, "loss": 1.299, "learning_rate": 1e-05, "epoch": 0.9231101046047665, "percentage": 30.8, "elapsed_time": "1:29:09", "remaining_time": "3:20:18", "throughput": "0.00", "total_tokens": 0}
|
108 |
+
{"current_steps": 540, "total_steps": 1737, "loss": 1.2246, "learning_rate": 1e-05, "epoch": 0.9317373018440634, "percentage": 31.09, "elapsed_time": "1:29:54", "remaining_time": "3:19:17", "throughput": "0.00", "total_tokens": 0}
|
109 |
+
{"current_steps": 545, "total_steps": 1737, "loss": 1.2069, "learning_rate": 1e-05, "epoch": 0.9403644990833603, "percentage": 31.38, "elapsed_time": "1:30:41", "remaining_time": "3:18:20", "throughput": "0.00", "total_tokens": 0}
|
110 |
+
{"current_steps": 550, "total_steps": 1737, "loss": 1.244, "learning_rate": 1e-05, "epoch": 0.9489916963226572, "percentage": 31.66, "elapsed_time": "1:31:26", "remaining_time": "3:17:19", "throughput": "0.00", "total_tokens": 0}
|
111 |
+
{"current_steps": 555, "total_steps": 1737, "loss": 1.2785, "learning_rate": 1e-05, "epoch": 0.9576188935619541, "percentage": 31.95, "elapsed_time": "1:32:12", "remaining_time": "3:16:21", "throughput": "0.00", "total_tokens": 0}
|
112 |
+
{"current_steps": 560, "total_steps": 1737, "loss": 1.2542, "learning_rate": 1e-05, "epoch": 0.9662460908012509, "percentage": 32.24, "elapsed_time": "1:32:59", "remaining_time": "3:15:26", "throughput": "0.00", "total_tokens": 0}
|
113 |
+
{"current_steps": 565, "total_steps": 1737, "loss": 1.2649, "learning_rate": 1e-05, "epoch": 0.9748732880405478, "percentage": 32.53, "elapsed_time": "1:33:42", "remaining_time": "3:14:23", "throughput": "0.00", "total_tokens": 0}
|
114 |
+
{"current_steps": 570, "total_steps": 1737, "loss": 1.2963, "learning_rate": 1e-05, "epoch": 0.9835004852798447, "percentage": 32.82, "elapsed_time": "1:34:28", "remaining_time": "3:13:25", "throughput": "0.00", "total_tokens": 0}
|
115 |
+
{"current_steps": 575, "total_steps": 1737, "loss": 1.2534, "learning_rate": 1e-05, "epoch": 0.9921276825191416, "percentage": 33.1, "elapsed_time": "1:35:14", "remaining_time": "3:12:28", "throughput": "0.00", "total_tokens": 0}
|
116 |
+
{"current_steps": 580, "total_steps": 1737, "loss": 1.1385, "learning_rate": 1e-05, "epoch": 1.0007548797584385, "percentage": 33.39, "elapsed_time": "1:36:02", "remaining_time": "3:11:36", "throughput": "0.00", "total_tokens": 0}
|
117 |
+
{"current_steps": 585, "total_steps": 1737, "loss": 0.8563, "learning_rate": 1e-05, "epoch": 1.0093820769977353, "percentage": 33.68, "elapsed_time": "1:36:52", "remaining_time": "3:10:46", "throughput": "0.00", "total_tokens": 0}
|
118 |
+
{"current_steps": 590, "total_steps": 1737, "loss": 0.9018, "learning_rate": 1e-05, "epoch": 1.0180092742370321, "percentage": 33.97, "elapsed_time": "1:37:45", "remaining_time": "3:10:03", "throughput": "0.00", "total_tokens": 0}
|
119 |
+
{"current_steps": 595, "total_steps": 1737, "loss": 0.8435, "learning_rate": 1e-05, "epoch": 1.0266364714763292, "percentage": 34.25, "elapsed_time": "1:38:36", "remaining_time": "3:09:14", "throughput": "0.00", "total_tokens": 0}
|
120 |
+
{"current_steps": 600, "total_steps": 1737, "loss": 0.7686, "learning_rate": 1e-05, "epoch": 1.035263668715626, "percentage": 34.54, "elapsed_time": "1:39:21", "remaining_time": "3:08:16", "throughput": "0.00", "total_tokens": 0}
|
121 |
+
{"current_steps": 605, "total_steps": 1737, "loss": 0.7134, "learning_rate": 1e-05, "epoch": 1.0438908659549229, "percentage": 34.83, "elapsed_time": "1:41:33", "remaining_time": "3:10:00", "throughput": "0.00", "total_tokens": 0}
|
122 |
+
{"current_steps": 610, "total_steps": 1737, "loss": 0.7836, "learning_rate": 1e-05, "epoch": 1.0525180631942197, "percentage": 35.12, "elapsed_time": "1:42:23", "remaining_time": "3:09:09", "throughput": "0.00", "total_tokens": 0}
|
123 |
+
{"current_steps": 615, "total_steps": 1737, "loss": 0.8263, "learning_rate": 1e-05, "epoch": 1.0611452604335168, "percentage": 35.41, "elapsed_time": "1:43:06", "remaining_time": "3:08:06", "throughput": "0.00", "total_tokens": 0}
|
124 |
+
{"current_steps": 620, "total_steps": 1737, "loss": 0.8028, "learning_rate": 1e-05, "epoch": 1.0697724576728136, "percentage": 35.69, "elapsed_time": "1:43:51", "remaining_time": "3:07:06", "throughput": "0.00", "total_tokens": 0}
|
125 |
+
{"current_steps": 625, "total_steps": 1737, "loss": 0.7552, "learning_rate": 1e-05, "epoch": 1.0783996549121104, "percentage": 35.98, "elapsed_time": "1:44:33", "remaining_time": "3:06:02", "throughput": "0.00", "total_tokens": 0}
|
126 |
+
{"current_steps": 630, "total_steps": 1737, "loss": 0.838, "learning_rate": 1e-05, "epoch": 1.0870268521514073, "percentage": 36.27, "elapsed_time": "1:45:17", "remaining_time": "3:05:00", "throughput": "0.00", "total_tokens": 0}
|
127 |
+
{"current_steps": 635, "total_steps": 1737, "loss": 0.7915, "learning_rate": 1e-05, "epoch": 1.095654049390704, "percentage": 36.56, "elapsed_time": "1:46:04", "remaining_time": "3:04:04", "throughput": "0.00", "total_tokens": 0}
|
128 |
+
{"current_steps": 640, "total_steps": 1737, "loss": 0.7522, "learning_rate": 1e-05, "epoch": 1.1042812466300012, "percentage": 36.85, "elapsed_time": "1:46:53", "remaining_time": "3:03:13", "throughput": "0.00", "total_tokens": 0}
|
129 |
+
{"current_steps": 645, "total_steps": 1737, "loss": 0.7777, "learning_rate": 1e-05, "epoch": 1.112908443869298, "percentage": 37.13, "elapsed_time": "1:47:46", "remaining_time": "3:02:28", "throughput": "0.00", "total_tokens": 0}
|
130 |
+
{"current_steps": 650, "total_steps": 1737, "loss": 0.8388, "learning_rate": 1e-05, "epoch": 1.1215356411085948, "percentage": 37.42, "elapsed_time": "1:48:35", "remaining_time": "3:01:36", "throughput": "0.00", "total_tokens": 0}
|
131 |
+
{"current_steps": 655, "total_steps": 1737, "loss": 0.8455, "learning_rate": 1e-05, "epoch": 1.1301628383478917, "percentage": 37.71, "elapsed_time": "1:49:24", "remaining_time": "3:00:44", "throughput": "0.00", "total_tokens": 0}
|
132 |
+
{"current_steps": 660, "total_steps": 1737, "loss": 0.8048, "learning_rate": 1e-05, "epoch": 1.1387900355871885, "percentage": 38.0, "elapsed_time": "1:50:07", "remaining_time": "2:59:42", "throughput": "0.00", "total_tokens": 0}
|
133 |
+
{"current_steps": 665, "total_steps": 1737, "loss": 0.7762, "learning_rate": 1e-05, "epoch": 1.1474172328264856, "percentage": 38.28, "elapsed_time": "1:51:07", "remaining_time": "2:59:08", "throughput": "0.00", "total_tokens": 0}
|
134 |
+
{"current_steps": 670, "total_steps": 1737, "loss": 0.7812, "learning_rate": 1e-05, "epoch": 1.1560444300657824, "percentage": 38.57, "elapsed_time": "1:51:59", "remaining_time": "2:58:21", "throughput": "0.00", "total_tokens": 0}
|
135 |
+
{"current_steps": 675, "total_steps": 1737, "loss": 0.8134, "learning_rate": 1e-05, "epoch": 1.1646716273050792, "percentage": 38.86, "elapsed_time": "1:52:51", "remaining_time": "2:57:34", "throughput": "0.00", "total_tokens": 0}
|
136 |
+
{"current_steps": 680, "total_steps": 1737, "loss": 0.7821, "learning_rate": 1e-05, "epoch": 1.173298824544376, "percentage": 39.15, "elapsed_time": "1:53:43", "remaining_time": "2:56:46", "throughput": "0.00", "total_tokens": 0}
|
137 |
+
{"current_steps": 685, "total_steps": 1737, "loss": 0.8034, "learning_rate": 1e-05, "epoch": 1.1819260217836731, "percentage": 39.44, "elapsed_time": "1:54:39", "remaining_time": "2:56:04", "throughput": "0.00", "total_tokens": 0}
|
138 |
+
{"current_steps": 690, "total_steps": 1737, "loss": 0.7592, "learning_rate": 1e-05, "epoch": 1.19055321902297, "percentage": 39.72, "elapsed_time": "1:55:26", "remaining_time": "2:55:10", "throughput": "0.00", "total_tokens": 0}
|
139 |
+
{"current_steps": 695, "total_steps": 1737, "loss": 0.7738, "learning_rate": 1e-05, "epoch": 1.1991804162622668, "percentage": 40.01, "elapsed_time": "1:56:16", "remaining_time": "2:54:20", "throughput": "0.00", "total_tokens": 0}
|
140 |
+
{"current_steps": 700, "total_steps": 1737, "loss": 0.7043, "learning_rate": 1e-05, "epoch": 1.2078076135015636, "percentage": 40.3, "elapsed_time": "1:57:13", "remaining_time": "2:53:40", "throughput": "0.00", "total_tokens": 0}
|
141 |
+
{"current_steps": 705, "total_steps": 1737, "loss": 0.7969, "learning_rate": 1e-05, "epoch": 1.2164348107408607, "percentage": 40.59, "elapsed_time": "1:57:59", "remaining_time": "2:52:43", "throughput": "0.00", "total_tokens": 0}
|
142 |
+
{"current_steps": 710, "total_steps": 1737, "loss": 0.7299, "learning_rate": 1e-05, "epoch": 1.2250620079801575, "percentage": 40.88, "elapsed_time": "1:58:47", "remaining_time": "2:51:49", "throughput": "0.00", "total_tokens": 0}
|
143 |
+
{"current_steps": 715, "total_steps": 1737, "loss": 0.811, "learning_rate": 1e-05, "epoch": 1.2336892052194544, "percentage": 41.16, "elapsed_time": "1:59:41", "remaining_time": "2:51:04", "throughput": "0.00", "total_tokens": 0}
|
144 |
+
{"current_steps": 720, "total_steps": 1737, "loss": 0.7714, "learning_rate": 1e-05, "epoch": 1.2423164024587512, "percentage": 41.45, "elapsed_time": "2:00:30", "remaining_time": "2:50:13", "throughput": "0.00", "total_tokens": 0}
|
145 |
+
{"current_steps": 725, "total_steps": 1737, "loss": 0.8388, "learning_rate": 1e-05, "epoch": 1.250943599698048, "percentage": 41.74, "elapsed_time": "2:01:20", "remaining_time": "2:49:22", "throughput": "0.00", "total_tokens": 0}
|
146 |
+
{"current_steps": 730, "total_steps": 1737, "loss": 0.8244, "learning_rate": 1e-05, "epoch": 1.259570796937345, "percentage": 42.03, "elapsed_time": "2:02:10", "remaining_time": "2:48:31", "throughput": "0.00", "total_tokens": 0}
|
147 |
+
{"current_steps": 735, "total_steps": 1737, "loss": 0.8326, "learning_rate": 1e-05, "epoch": 1.268197994176642, "percentage": 42.31, "elapsed_time": "2:02:57", "remaining_time": "2:47:38", "throughput": "0.00", "total_tokens": 0}
|
148 |
+
{"current_steps": 740, "total_steps": 1737, "loss": 0.8302, "learning_rate": 1e-05, "epoch": 1.2768251914159388, "percentage": 42.6, "elapsed_time": "2:03:42", "remaining_time": "2:46:40", "throughput": "0.00", "total_tokens": 0}
|
149 |
+
{"current_steps": 745, "total_steps": 1737, "loss": 0.7911, "learning_rate": 1e-05, "epoch": 1.2854523886552356, "percentage": 42.89, "elapsed_time": "2:04:30", "remaining_time": "2:45:47", "throughput": "0.00", "total_tokens": 0}
|
150 |
+
{"current_steps": 750, "total_steps": 1737, "loss": 0.8836, "learning_rate": 1e-05, "epoch": 1.2940795858945324, "percentage": 43.18, "elapsed_time": "2:05:22", "remaining_time": "2:44:59", "throughput": "0.00", "total_tokens": 0}
|
151 |
+
{"current_steps": 755, "total_steps": 1737, "loss": 0.8023, "learning_rate": 1e-05, "epoch": 1.3027067831338295, "percentage": 43.47, "elapsed_time": "2:06:13", "remaining_time": "2:44:10", "throughput": "0.00", "total_tokens": 0}
|
152 |
+
{"current_steps": 760, "total_steps": 1737, "loss": 0.8338, "learning_rate": 1e-05, "epoch": 1.3113339803731263, "percentage": 43.75, "elapsed_time": "2:07:03", "remaining_time": "2:43:19", "throughput": "0.00", "total_tokens": 0}
|
153 |
+
{"current_steps": 765, "total_steps": 1737, "loss": 0.8247, "learning_rate": 1e-05, "epoch": 1.3199611776124232, "percentage": 44.04, "elapsed_time": "2:07:53", "remaining_time": "2:42:29", "throughput": "0.00", "total_tokens": 0}
|
154 |
+
{"current_steps": 770, "total_steps": 1737, "loss": 0.8781, "learning_rate": 1e-05, "epoch": 1.32858837485172, "percentage": 44.33, "elapsed_time": "2:08:45", "remaining_time": "2:41:42", "throughput": "0.00", "total_tokens": 0}
|
155 |
+
{"current_steps": 775, "total_steps": 1737, "loss": 0.7967, "learning_rate": 1e-05, "epoch": 1.3372155720910168, "percentage": 44.62, "elapsed_time": "2:09:32", "remaining_time": "2:40:47", "throughput": "0.00", "total_tokens": 0}
|
156 |
+
{"current_steps": 780, "total_steps": 1737, "loss": 0.7918, "learning_rate": 1e-05, "epoch": 1.3458427693303139, "percentage": 44.91, "elapsed_time": "2:10:30", "remaining_time": "2:40:07", "throughput": "0.00", "total_tokens": 0}
|
157 |
+
{"current_steps": 785, "total_steps": 1737, "loss": 0.7784, "learning_rate": 1e-05, "epoch": 1.3544699665696107, "percentage": 45.19, "elapsed_time": "2:11:16", "remaining_time": "2:39:12", "throughput": "0.00", "total_tokens": 0}
|
158 |
+
{"current_steps": 790, "total_steps": 1737, "loss": 0.8017, "learning_rate": 1e-05, "epoch": 1.3630971638089076, "percentage": 45.48, "elapsed_time": "2:12:06", "remaining_time": "2:38:21", "throughput": "0.00", "total_tokens": 0}
|
159 |
+
{"current_steps": 795, "total_steps": 1737, "loss": 0.7803, "learning_rate": 1e-05, "epoch": 1.3717243610482044, "percentage": 45.77, "elapsed_time": "2:13:07", "remaining_time": "2:37:44", "throughput": "0.00", "total_tokens": 0}
|
160 |
+
{"current_steps": 800, "total_steps": 1737, "loss": 0.8341, "learning_rate": 1e-05, "epoch": 1.3803515582875012, "percentage": 46.06, "elapsed_time": "2:13:51", "remaining_time": "2:36:47", "throughput": "0.00", "total_tokens": 0}
|
161 |
+
{"current_steps": 805, "total_steps": 1737, "loss": 0.7977, "learning_rate": 1e-05, "epoch": 1.3889787555267983, "percentage": 46.34, "elapsed_time": "2:15:57", "remaining_time": "2:37:25", "throughput": "0.00", "total_tokens": 0}
|
162 |
+
{"current_steps": 810, "total_steps": 1737, "loss": 0.778, "learning_rate": 1e-05, "epoch": 1.3976059527660951, "percentage": 46.63, "elapsed_time": "2:16:48", "remaining_time": "2:36:33", "throughput": "0.00", "total_tokens": 0}
|
163 |
+
{"current_steps": 815, "total_steps": 1737, "loss": 0.8107, "learning_rate": 1e-05, "epoch": 1.406233150005392, "percentage": 46.92, "elapsed_time": "2:17:31", "remaining_time": "2:35:35", "throughput": "0.00", "total_tokens": 0}
|
164 |
+
{"current_steps": 820, "total_steps": 1737, "loss": 0.753, "learning_rate": 1e-05, "epoch": 1.414860347244689, "percentage": 47.21, "elapsed_time": "2:18:23", "remaining_time": "2:34:45", "throughput": "0.00", "total_tokens": 0}
|
165 |
+
{"current_steps": 825, "total_steps": 1737, "loss": 0.8111, "learning_rate": 1e-05, "epoch": 1.4234875444839858, "percentage": 47.5, "elapsed_time": "2:19:10", "remaining_time": "2:33:51", "throughput": "0.00", "total_tokens": 0}
|
166 |
+
{"current_steps": 830, "total_steps": 1737, "loss": 0.7559, "learning_rate": 1e-05, "epoch": 1.4321147417232827, "percentage": 47.78, "elapsed_time": "2:19:56", "remaining_time": "2:32:55", "throughput": "0.00", "total_tokens": 0}
|
167 |
+
{"current_steps": 835, "total_steps": 1737, "loss": 0.8213, "learning_rate": 1e-05, "epoch": 1.4407419389625795, "percentage": 48.07, "elapsed_time": "2:20:47", "remaining_time": "2:32:05", "throughput": "0.00", "total_tokens": 0}
|
168 |
+
{"current_steps": 840, "total_steps": 1737, "loss": 0.9053, "learning_rate": 1e-05, "epoch": 1.4493691362018764, "percentage": 48.36, "elapsed_time": "2:21:32", "remaining_time": "2:31:08", "throughput": "0.00", "total_tokens": 0}
|
169 |
+
{"current_steps": 845, "total_steps": 1737, "loss": 0.7486, "learning_rate": 1e-05, "epoch": 1.4579963334411734, "percentage": 48.65, "elapsed_time": "2:22:25", "remaining_time": "2:30:20", "throughput": "0.00", "total_tokens": 0}
|
170 |
+
{"current_steps": 850, "total_steps": 1737, "loss": 0.8385, "learning_rate": 1e-05, "epoch": 1.4666235306804702, "percentage": 48.93, "elapsed_time": "2:23:08", "remaining_time": "2:29:22", "throughput": "0.00", "total_tokens": 0}
|
171 |
+
{"current_steps": 855, "total_steps": 1737, "loss": 0.8994, "learning_rate": 1e-05, "epoch": 1.475250727919767, "percentage": 49.22, "elapsed_time": "2:23:57", "remaining_time": "2:28:30", "throughput": "0.00", "total_tokens": 0}
|
172 |
+
{"current_steps": 860, "total_steps": 1737, "loss": 0.7993, "learning_rate": 1e-05, "epoch": 1.483877925159064, "percentage": 49.51, "elapsed_time": "2:24:48", "remaining_time": "2:27:40", "throughput": "0.00", "total_tokens": 0}
|
173 |
+
{"current_steps": 865, "total_steps": 1737, "loss": 0.8415, "learning_rate": 1e-05, "epoch": 1.4925051223983608, "percentage": 49.8, "elapsed_time": "2:25:33", "remaining_time": "2:26:44", "throughput": "0.00", "total_tokens": 0}
|
174 |
+
{"current_steps": 870, "total_steps": 1737, "loss": 0.7544, "learning_rate": 1e-05, "epoch": 1.5011323196376578, "percentage": 50.09, "elapsed_time": "2:26:21", "remaining_time": "2:25:51", "throughput": "0.00", "total_tokens": 0}
|
175 |
+
{"current_steps": 875, "total_steps": 1737, "loss": 0.8997, "learning_rate": 1e-05, "epoch": 1.5097595168769546, "percentage": 50.37, "elapsed_time": "2:27:09", "remaining_time": "2:24:57", "throughput": "0.00", "total_tokens": 0}
|
176 |
+
{"current_steps": 880, "total_steps": 1737, "loss": 0.7673, "learning_rate": 1e-05, "epoch": 1.5183867141162515, "percentage": 50.66, "elapsed_time": "2:27:55", "remaining_time": "2:24:03", "throughput": "0.00", "total_tokens": 0}
|
177 |
+
{"current_steps": 885, "total_steps": 1737, "loss": 0.8582, "learning_rate": 1e-05, "epoch": 1.5270139113555483, "percentage": 50.95, "elapsed_time": "2:28:42", "remaining_time": "2:23:10", "throughput": "0.00", "total_tokens": 0}
|
178 |
+
{"current_steps": 890, "total_steps": 1737, "loss": 0.7828, "learning_rate": 1e-05, "epoch": 1.5356411085948452, "percentage": 51.24, "elapsed_time": "2:29:30", "remaining_time": "2:22:16", "throughput": "0.00", "total_tokens": 0}
|
179 |
+
{"current_steps": 895, "total_steps": 1737, "loss": 0.8359, "learning_rate": 1e-05, "epoch": 1.5442683058341422, "percentage": 51.53, "elapsed_time": "2:30:13", "remaining_time": "2:21:19", "throughput": "0.00", "total_tokens": 0}
|
180 |
+
{"current_steps": 900, "total_steps": 1737, "loss": 0.8226, "learning_rate": 1e-05, "epoch": 1.552895503073439, "percentage": 51.81, "elapsed_time": "2:31:03", "remaining_time": "2:20:29", "throughput": "0.00", "total_tokens": 0}
|
181 |
+
{"current_steps": 905, "total_steps": 1737, "loss": 0.8219, "learning_rate": 1e-05, "epoch": 1.5615227003127359, "percentage": 52.1, "elapsed_time": "2:31:51", "remaining_time": "2:19:36", "throughput": "0.00", "total_tokens": 0}
|
182 |
+
{"current_steps": 910, "total_steps": 1737, "loss": 0.8212, "learning_rate": 1e-05, "epoch": 1.570149897552033, "percentage": 52.39, "elapsed_time": "2:32:39", "remaining_time": "2:18:43", "throughput": "0.00", "total_tokens": 0}
|
183 |
+
{"current_steps": 915, "total_steps": 1737, "loss": 0.8036, "learning_rate": 1e-05, "epoch": 1.5787770947913295, "percentage": 52.68, "elapsed_time": "2:33:26", "remaining_time": "2:17:50", "throughput": "0.00", "total_tokens": 0}
|
184 |
+
{"current_steps": 920, "total_steps": 1737, "loss": 0.7633, "learning_rate": 1e-05, "epoch": 1.5874042920306266, "percentage": 52.96, "elapsed_time": "2:34:14", "remaining_time": "2:16:58", "throughput": "0.00", "total_tokens": 0}
|
185 |
+
{"current_steps": 925, "total_steps": 1737, "loss": 0.7673, "learning_rate": 1e-05, "epoch": 1.5960314892699234, "percentage": 53.25, "elapsed_time": "2:35:00", "remaining_time": "2:16:04", "throughput": "0.00", "total_tokens": 0}
|
186 |
+
{"current_steps": 930, "total_steps": 1737, "loss": 0.7732, "learning_rate": 1e-05, "epoch": 1.6046586865092203, "percentage": 53.54, "elapsed_time": "2:35:47", "remaining_time": "2:15:10", "throughput": "0.00", "total_tokens": 0}
|
187 |
+
{"current_steps": 935, "total_steps": 1737, "loss": 0.7941, "learning_rate": 1e-05, "epoch": 1.6132858837485173, "percentage": 53.83, "elapsed_time": "2:36:34", "remaining_time": "2:14:18", "throughput": "0.00", "total_tokens": 0}
|
188 |
+
{"current_steps": 940, "total_steps": 1737, "loss": 0.8184, "learning_rate": 1e-05, "epoch": 1.621913080987814, "percentage": 54.12, "elapsed_time": "2:37:25", "remaining_time": "2:13:28", "throughput": "0.00", "total_tokens": 0}
|
189 |
+
{"current_steps": 945, "total_steps": 1737, "loss": 0.8496, "learning_rate": 1e-05, "epoch": 1.630540278227111, "percentage": 54.4, "elapsed_time": "2:38:10", "remaining_time": "2:12:34", "throughput": "0.00", "total_tokens": 0}
|
190 |
+
{"current_steps": 950, "total_steps": 1737, "loss": 0.888, "learning_rate": 1e-05, "epoch": 1.6391674754664078, "percentage": 54.69, "elapsed_time": "2:38:51", "remaining_time": "2:11:36", "throughput": "0.00", "total_tokens": 0}
|
191 |
+
{"current_steps": 955, "total_steps": 1737, "loss": 0.8551, "learning_rate": 1e-05, "epoch": 1.6477946727057047, "percentage": 54.98, "elapsed_time": "2:39:37", "remaining_time": "2:10:42", "throughput": "0.00", "total_tokens": 0}
|
192 |
+
{"current_steps": 960, "total_steps": 1737, "loss": 0.8184, "learning_rate": 1e-05, "epoch": 1.6564218699450017, "percentage": 55.27, "elapsed_time": "2:40:32", "remaining_time": "2:09:56", "throughput": "0.00", "total_tokens": 0}
|
193 |
+
{"current_steps": 965, "total_steps": 1737, "loss": 0.8045, "learning_rate": 1e-05, "epoch": 1.6650490671842983, "percentage": 55.56, "elapsed_time": "2:41:37", "remaining_time": "2:09:17", "throughput": "0.00", "total_tokens": 0}
|
194 |
+
{"current_steps": 970, "total_steps": 1737, "loss": 0.7489, "learning_rate": 1e-05, "epoch": 1.6736762644235954, "percentage": 55.84, "elapsed_time": "2:42:27", "remaining_time": "2:08:27", "throughput": "0.00", "total_tokens": 0}
|
195 |
+
{"current_steps": 975, "total_steps": 1737, "loss": 0.7816, "learning_rate": 1e-05, "epoch": 1.6823034616628922, "percentage": 56.13, "elapsed_time": "2:43:15", "remaining_time": "2:07:35", "throughput": "0.00", "total_tokens": 0}
|
196 |
+
{"current_steps": 980, "total_steps": 1737, "loss": 0.884, "learning_rate": 1e-05, "epoch": 1.690930658902189, "percentage": 56.42, "elapsed_time": "2:44:02", "remaining_time": "2:06:42", "throughput": "0.00", "total_tokens": 0}
|
197 |
+
{"current_steps": 985, "total_steps": 1737, "loss": 0.9077, "learning_rate": 1e-05, "epoch": 1.6995578561414861, "percentage": 56.71, "elapsed_time": "2:44:48", "remaining_time": "2:05:49", "throughput": "0.00", "total_tokens": 0}
|
198 |
+
{"current_steps": 990, "total_steps": 1737, "loss": 0.8371, "learning_rate": 1e-05, "epoch": 1.708185053380783, "percentage": 56.99, "elapsed_time": "2:45:36", "remaining_time": "2:04:57", "throughput": "0.00", "total_tokens": 0}
|
199 |
+
{"current_steps": 995, "total_steps": 1737, "loss": 0.8028, "learning_rate": 1e-05, "epoch": 1.7168122506200798, "percentage": 57.28, "elapsed_time": "2:46:21", "remaining_time": "2:04:03", "throughput": "0.00", "total_tokens": 0}
|
200 |
+
{"current_steps": 1000, "total_steps": 1737, "loss": 0.7969, "learning_rate": 1e-05, "epoch": 1.7254394478593766, "percentage": 57.57, "elapsed_time": "2:47:07", "remaining_time": "2:03:09", "throughput": "0.00", "total_tokens": 0}
|
201 |
+
{"current_steps": 1005, "total_steps": 1737, "loss": 0.8557, "learning_rate": 1e-05, "epoch": 1.7340666450986735, "percentage": 57.86, "elapsed_time": "2:49:21", "remaining_time": "2:03:21", "throughput": "0.00", "total_tokens": 0}
|
202 |
+
{"current_steps": 1010, "total_steps": 1737, "loss": 0.7524, "learning_rate": 1e-05, "epoch": 1.7426938423379705, "percentage": 58.15, "elapsed_time": "2:50:12", "remaining_time": "2:02:30", "throughput": "0.00", "total_tokens": 0}
|
203 |
+
{"current_steps": 1015, "total_steps": 1737, "loss": 0.8103, "learning_rate": 1e-05, "epoch": 1.7513210395772674, "percentage": 58.43, "elapsed_time": "2:51:10", "remaining_time": "2:01:45", "throughput": "0.00", "total_tokens": 0}
|
204 |
+
{"current_steps": 1020, "total_steps": 1737, "loss": 0.7795, "learning_rate": 1e-05, "epoch": 1.7599482368165642, "percentage": 58.72, "elapsed_time": "2:51:59", "remaining_time": "2:00:54", "throughput": "0.00", "total_tokens": 0}
|
205 |
+
{"current_steps": 1025, "total_steps": 1737, "loss": 0.8534, "learning_rate": 1e-05, "epoch": 1.7685754340558613, "percentage": 59.01, "elapsed_time": "2:52:47", "remaining_time": "2:00:01", "throughput": "0.00", "total_tokens": 0}
|
206 |
+
{"current_steps": 1030, "total_steps": 1737, "loss": 0.8371, "learning_rate": 1e-05, "epoch": 1.7772026312951579, "percentage": 59.3, "elapsed_time": "2:53:31", "remaining_time": "1:59:06", "throughput": "0.00", "total_tokens": 0}
|
207 |
+
{"current_steps": 1035, "total_steps": 1737, "loss": 0.7688, "learning_rate": 1e-05, "epoch": 1.785829828534455, "percentage": 59.59, "elapsed_time": "2:54:15", "remaining_time": "1:58:11", "throughput": "0.00", "total_tokens": 0}
|
208 |
+
{"current_steps": 1040, "total_steps": 1737, "loss": 0.7823, "learning_rate": 1e-05, "epoch": 1.7944570257737518, "percentage": 59.87, "elapsed_time": "2:55:06", "remaining_time": "1:57:21", "throughput": "0.00", "total_tokens": 0}
|
209 |
+
{"current_steps": 1045, "total_steps": 1737, "loss": 0.8135, "learning_rate": 1e-05, "epoch": 1.8030842230130486, "percentage": 60.16, "elapsed_time": "2:55:53", "remaining_time": "1:56:28", "throughput": "0.00", "total_tokens": 0}
|
210 |
+
{"current_steps": 1050, "total_steps": 1737, "loss": 0.8169, "learning_rate": 1e-05, "epoch": 1.8117114202523457, "percentage": 60.45, "elapsed_time": "2:56:40", "remaining_time": "1:55:35", "throughput": "0.00", "total_tokens": 0}
|
211 |
+
{"current_steps": 1055, "total_steps": 1737, "loss": 0.846, "learning_rate": 1e-05, "epoch": 1.8203386174916423, "percentage": 60.74, "elapsed_time": "2:57:27", "remaining_time": "1:54:43", "throughput": "0.00", "total_tokens": 0}
|
212 |
+
{"current_steps": 1060, "total_steps": 1737, "loss": 0.8055, "learning_rate": 1e-05, "epoch": 1.8289658147309393, "percentage": 61.02, "elapsed_time": "2:58:10", "remaining_time": "1:53:47", "throughput": "0.00", "total_tokens": 0}
|
213 |
+
{"current_steps": 1065, "total_steps": 1737, "loss": 0.8216, "learning_rate": 1e-05, "epoch": 1.8375930119702362, "percentage": 61.31, "elapsed_time": "2:58:59", "remaining_time": "1:52:56", "throughput": "0.00", "total_tokens": 0}
|
214 |
+
{"current_steps": 1070, "total_steps": 1737, "loss": 0.8663, "learning_rate": 1e-05, "epoch": 1.846220209209533, "percentage": 61.6, "elapsed_time": "2:59:46", "remaining_time": "1:52:04", "throughput": "0.00", "total_tokens": 0}
|
215 |
+
{"current_steps": 1075, "total_steps": 1737, "loss": 0.8332, "learning_rate": 1e-05, "epoch": 1.85484740644883, "percentage": 61.89, "elapsed_time": "3:00:33", "remaining_time": "1:51:11", "throughput": "0.00", "total_tokens": 0}
|
216 |
+
{"current_steps": 1080, "total_steps": 1737, "loss": 0.8408, "learning_rate": 1e-05, "epoch": 1.8634746036881267, "percentage": 62.18, "elapsed_time": "3:01:22", "remaining_time": "1:50:19", "throughput": "0.00", "total_tokens": 0}
|
217 |
+
{"current_steps": 1085, "total_steps": 1737, "loss": 0.828, "learning_rate": 1e-05, "epoch": 1.8721018009274237, "percentage": 62.46, "elapsed_time": "3:02:06", "remaining_time": "1:49:26", "throughput": "0.00", "total_tokens": 0}
|
218 |
+
{"current_steps": 1090, "total_steps": 1737, "loss": 0.8127, "learning_rate": 1e-05, "epoch": 1.8807289981667206, "percentage": 62.75, "elapsed_time": "3:02:51", "remaining_time": "1:48:32", "throughput": "0.00", "total_tokens": 0}
|
219 |
+
{"current_steps": 1095, "total_steps": 1737, "loss": 0.8607, "learning_rate": 1e-05, "epoch": 1.8893561954060174, "percentage": 63.04, "elapsed_time": "3:03:39", "remaining_time": "1:47:40", "throughput": "0.00", "total_tokens": 0}
|
220 |
+
{"current_steps": 1100, "total_steps": 1737, "loss": 0.9251, "learning_rate": 1e-05, "epoch": 1.8979833926453145, "percentage": 63.33, "elapsed_time": "3:04:28", "remaining_time": "1:46:49", "throughput": "0.00", "total_tokens": 0}
|
221 |
+
{"current_steps": 1105, "total_steps": 1737, "loss": 0.8388, "learning_rate": 1e-05, "epoch": 1.906610589884611, "percentage": 63.62, "elapsed_time": "3:05:17", "remaining_time": "1:45:58", "throughput": "0.00", "total_tokens": 0}
|
222 |
+
{"current_steps": 1110, "total_steps": 1737, "loss": 0.8036, "learning_rate": 1e-05, "epoch": 1.9152377871239081, "percentage": 63.9, "elapsed_time": "3:06:02", "remaining_time": "1:45:05", "throughput": "0.00", "total_tokens": 0}
|
223 |
+
{"current_steps": 1115, "total_steps": 1737, "loss": 0.8001, "learning_rate": 1e-05, "epoch": 1.923864984363205, "percentage": 64.19, "elapsed_time": "3:06:53", "remaining_time": "1:44:15", "throughput": "0.00", "total_tokens": 0}
|
224 |
+
{"current_steps": 1120, "total_steps": 1737, "loss": 0.775, "learning_rate": 1e-05, "epoch": 1.9324921816025018, "percentage": 64.48, "elapsed_time": "3:07:41", "remaining_time": "1:43:23", "throughput": "0.00", "total_tokens": 0}
|
225 |
+
{"current_steps": 1125, "total_steps": 1737, "loss": 0.8639, "learning_rate": 1e-05, "epoch": 1.9411193788417989, "percentage": 64.77, "elapsed_time": "3:08:25", "remaining_time": "1:42:30", "throughput": "0.00", "total_tokens": 0}
|
226 |
+
{"current_steps": 1130, "total_steps": 1737, "loss": 0.8513, "learning_rate": 1e-05, "epoch": 1.9497465760810957, "percentage": 65.05, "elapsed_time": "3:09:12", "remaining_time": "1:41:38", "throughput": "0.00", "total_tokens": 0}
|
227 |
+
{"current_steps": 1135, "total_steps": 1737, "loss": 0.77, "learning_rate": 1e-05, "epoch": 1.9583737733203925, "percentage": 65.34, "elapsed_time": "3:10:04", "remaining_time": "1:40:48", "throughput": "0.00", "total_tokens": 0}
|
228 |
+
{"current_steps": 1140, "total_steps": 1737, "loss": 0.732, "learning_rate": 1e-05, "epoch": 1.9670009705596894, "percentage": 65.63, "elapsed_time": "3:10:48", "remaining_time": "1:39:55", "throughput": "0.00", "total_tokens": 0}
|
229 |
+
{"current_steps": 1145, "total_steps": 1737, "loss": 0.8029, "learning_rate": 1e-05, "epoch": 1.9756281677989862, "percentage": 65.92, "elapsed_time": "3:11:35", "remaining_time": "1:39:03", "throughput": "0.00", "total_tokens": 0}
|
230 |
+
{"current_steps": 1150, "total_steps": 1737, "loss": 0.8205, "learning_rate": 1e-05, "epoch": 1.9842553650382833, "percentage": 66.21, "elapsed_time": "3:12:21", "remaining_time": "1:38:11", "throughput": "0.00", "total_tokens": 0}
|
231 |
+
{"current_steps": 1155, "total_steps": 1737, "loss": 0.7995, "learning_rate": 1e-05, "epoch": 1.99288256227758, "percentage": 66.49, "elapsed_time": "3:13:10", "remaining_time": "1:37:20", "throughput": "0.00", "total_tokens": 0}
|
232 |
+
{"current_steps": 1160, "total_steps": 1737, "loss": 0.7343, "learning_rate": 1e-05, "epoch": 2.001509759516877, "percentage": 66.78, "elapsed_time": "3:14:25", "remaining_time": "1:36:42", "throughput": "0.00", "total_tokens": 0}
|
233 |
+
{"current_steps": 1165, "total_steps": 1737, "loss": 0.4413, "learning_rate": 1e-05, "epoch": 2.010136956756174, "percentage": 67.07, "elapsed_time": "3:15:22", "remaining_time": "1:35:55", "throughput": "0.00", "total_tokens": 0}
|
234 |
+
{"current_steps": 1170, "total_steps": 1737, "loss": 0.4171, "learning_rate": 1e-05, "epoch": 2.0187641539954706, "percentage": 67.36, "elapsed_time": "3:16:10", "remaining_time": "1:35:04", "throughput": "0.00", "total_tokens": 0}
|
235 |
+
{"current_steps": 1175, "total_steps": 1737, "loss": 0.3829, "learning_rate": 1e-05, "epoch": 2.0273913512347677, "percentage": 67.65, "elapsed_time": "3:16:59", "remaining_time": "1:34:13", "throughput": "0.00", "total_tokens": 0}
|
236 |
+
{"current_steps": 1180, "total_steps": 1737, "loss": 0.3505, "learning_rate": 1e-05, "epoch": 2.0360185484740643, "percentage": 67.93, "elapsed_time": "3:17:48", "remaining_time": "1:33:22", "throughput": "0.00", "total_tokens": 0}
|
237 |
+
{"current_steps": 1185, "total_steps": 1737, "loss": 0.3448, "learning_rate": 1e-05, "epoch": 2.0446457457133613, "percentage": 68.22, "elapsed_time": "3:18:36", "remaining_time": "1:32:30", "throughput": "0.00", "total_tokens": 0}
|
238 |
+
{"current_steps": 1190, "total_steps": 1737, "loss": 0.3737, "learning_rate": 1e-05, "epoch": 2.0532729429526584, "percentage": 68.51, "elapsed_time": "3:19:31", "remaining_time": "1:31:42", "throughput": "0.00", "total_tokens": 0}
|
239 |
+
{"current_steps": 1195, "total_steps": 1737, "loss": 0.3939, "learning_rate": 1e-05, "epoch": 2.061900140191955, "percentage": 68.8, "elapsed_time": "3:20:12", "remaining_time": "1:30:48", "throughput": "0.00", "total_tokens": 0}
|
240 |
+
{"current_steps": 1200, "total_steps": 1737, "loss": 0.3638, "learning_rate": 1e-05, "epoch": 2.070527337431252, "percentage": 69.08, "elapsed_time": "3:21:06", "remaining_time": "1:29:59", "throughput": "0.00", "total_tokens": 0}
|
241 |
+
{"current_steps": 1205, "total_steps": 1737, "loss": 0.3634, "learning_rate": 1e-05, "epoch": 2.079154534670549, "percentage": 69.37, "elapsed_time": "3:23:11", "remaining_time": "1:29:42", "throughput": "0.00", "total_tokens": 0}
|
242 |
+
{"current_steps": 1210, "total_steps": 1737, "loss": 0.4462, "learning_rate": 1e-05, "epoch": 2.0877817319098457, "percentage": 69.66, "elapsed_time": "3:23:59", "remaining_time": "1:28:50", "throughput": "0.00", "total_tokens": 0}
|
243 |
+
{"current_steps": 1215, "total_steps": 1737, "loss": 0.4071, "learning_rate": 1e-05, "epoch": 2.096408929149143, "percentage": 69.95, "elapsed_time": "3:24:54", "remaining_time": "1:28:01", "throughput": "0.00", "total_tokens": 0}
|
244 |
+
{"current_steps": 1220, "total_steps": 1737, "loss": 0.3735, "learning_rate": 1e-05, "epoch": 2.1050361263884394, "percentage": 70.24, "elapsed_time": "3:25:39", "remaining_time": "1:27:09", "throughput": "0.00", "total_tokens": 0}
|
245 |
+
{"current_steps": 1225, "total_steps": 1737, "loss": 0.383, "learning_rate": 1e-05, "epoch": 2.1136633236277365, "percentage": 70.52, "elapsed_time": "3:26:29", "remaining_time": "1:26:18", "throughput": "0.00", "total_tokens": 0}
|
246 |
+
{"current_steps": 1230, "total_steps": 1737, "loss": 0.3077, "learning_rate": 1e-05, "epoch": 2.1222905208670335, "percentage": 70.81, "elapsed_time": "3:27:18", "remaining_time": "1:25:27", "throughput": "0.00", "total_tokens": 0}
|
247 |
+
{"current_steps": 1235, "total_steps": 1737, "loss": 0.3774, "learning_rate": 1e-05, "epoch": 2.13091771810633, "percentage": 71.1, "elapsed_time": "3:28:08", "remaining_time": "1:24:36", "throughput": "0.00", "total_tokens": 0}
|
248 |
+
{"current_steps": 1240, "total_steps": 1737, "loss": 0.3388, "learning_rate": 1e-05, "epoch": 2.139544915345627, "percentage": 71.39, "elapsed_time": "3:29:07", "remaining_time": "1:23:49", "throughput": "0.00", "total_tokens": 0}
|
249 |
+
{"current_steps": 1245, "total_steps": 1737, "loss": 0.3848, "learning_rate": 1e-05, "epoch": 2.148172112584924, "percentage": 71.68, "elapsed_time": "3:29:55", "remaining_time": "1:22:57", "throughput": "0.00", "total_tokens": 0}
|
250 |
+
{"current_steps": 1250, "total_steps": 1737, "loss": 0.4173, "learning_rate": 1e-05, "epoch": 2.156799309824221, "percentage": 71.96, "elapsed_time": "3:30:43", "remaining_time": "1:22:05", "throughput": "0.00", "total_tokens": 0}
|
251 |
+
{"current_steps": 1255, "total_steps": 1737, "loss": 0.3514, "learning_rate": 1e-05, "epoch": 2.165426507063518, "percentage": 72.25, "elapsed_time": "3:31:28", "remaining_time": "1:21:13", "throughput": "0.00", "total_tokens": 0}
|
252 |
+
{"current_steps": 1260, "total_steps": 1737, "loss": 0.393, "learning_rate": 1e-05, "epoch": 2.1740537043028145, "percentage": 72.54, "elapsed_time": "3:32:10", "remaining_time": "1:20:19", "throughput": "0.00", "total_tokens": 0}
|
253 |
+
{"current_steps": 1265, "total_steps": 1737, "loss": 0.3886, "learning_rate": 1e-05, "epoch": 2.1826809015421116, "percentage": 72.83, "elapsed_time": "3:32:56", "remaining_time": "1:19:27", "throughput": "0.00", "total_tokens": 0}
|
254 |
+
{"current_steps": 1270, "total_steps": 1737, "loss": 0.3943, "learning_rate": 1e-05, "epoch": 2.191308098781408, "percentage": 73.11, "elapsed_time": "3:33:46", "remaining_time": "1:18:36", "throughput": "0.00", "total_tokens": 0}
|
255 |
+
{"current_steps": 1275, "total_steps": 1737, "loss": 0.3562, "learning_rate": 1e-05, "epoch": 2.1999352960207053, "percentage": 73.4, "elapsed_time": "3:34:43", "remaining_time": "1:17:48", "throughput": "0.00", "total_tokens": 0}
|
256 |
+
{"current_steps": 1280, "total_steps": 1737, "loss": 0.3609, "learning_rate": 1e-05, "epoch": 2.2085624932600023, "percentage": 73.69, "elapsed_time": "3:35:37", "remaining_time": "1:16:58", "throughput": "0.00", "total_tokens": 0}
|
257 |
+
{"current_steps": 1285, "total_steps": 1737, "loss": 0.4031, "learning_rate": 1e-05, "epoch": 2.217189690499299, "percentage": 73.98, "elapsed_time": "3:36:27", "remaining_time": "1:16:08", "throughput": "0.00", "total_tokens": 0}
|
258 |
+
{"current_steps": 1290, "total_steps": 1737, "loss": 0.3989, "learning_rate": 1e-05, "epoch": 2.225816887738596, "percentage": 74.27, "elapsed_time": "3:37:18", "remaining_time": "1:15:17", "throughput": "0.00", "total_tokens": 0}
|
259 |
+
{"current_steps": 1295, "total_steps": 1737, "loss": 0.4016, "learning_rate": 1e-05, "epoch": 2.234444084977893, "percentage": 74.55, "elapsed_time": "3:38:09", "remaining_time": "1:14:27", "throughput": "0.00", "total_tokens": 0}
|
260 |
+
{"current_steps": 1300, "total_steps": 1737, "loss": 0.3735, "learning_rate": 1e-05, "epoch": 2.2430712822171897, "percentage": 74.84, "elapsed_time": "3:38:54", "remaining_time": "1:13:35", "throughput": "0.00", "total_tokens": 0}
|
261 |
+
{"current_steps": 1305, "total_steps": 1737, "loss": 0.376, "learning_rate": 1e-05, "epoch": 2.2516984794564867, "percentage": 75.13, "elapsed_time": "3:39:38", "remaining_time": "1:12:42", "throughput": "0.00", "total_tokens": 0}
|
262 |
+
{"current_steps": 1310, "total_steps": 1737, "loss": 0.4118, "learning_rate": 1e-05, "epoch": 2.2603256766957833, "percentage": 75.42, "elapsed_time": "3:40:30", "remaining_time": "1:11:52", "throughput": "0.00", "total_tokens": 0}
|
263 |
+
{"current_steps": 1315, "total_steps": 1737, "loss": 0.4483, "learning_rate": 1e-05, "epoch": 2.2689528739350804, "percentage": 75.71, "elapsed_time": "3:41:17", "remaining_time": "1:11:00", "throughput": "0.00", "total_tokens": 0}
|
264 |
+
{"current_steps": 1320, "total_steps": 1737, "loss": 0.3646, "learning_rate": 1e-05, "epoch": 2.277580071174377, "percentage": 75.99, "elapsed_time": "3:42:01", "remaining_time": "1:10:08", "throughput": "0.00", "total_tokens": 0}
|
265 |
+
{"current_steps": 1325, "total_steps": 1737, "loss": 0.3901, "learning_rate": 1e-05, "epoch": 2.286207268413674, "percentage": 76.28, "elapsed_time": "3:42:46", "remaining_time": "1:09:16", "throughput": "0.00", "total_tokens": 0}
|
266 |
+
{"current_steps": 1330, "total_steps": 1737, "loss": 0.3684, "learning_rate": 1e-05, "epoch": 2.294834465652971, "percentage": 76.57, "elapsed_time": "3:43:35", "remaining_time": "1:08:25", "throughput": "0.00", "total_tokens": 0}
|
267 |
+
{"current_steps": 1335, "total_steps": 1737, "loss": 0.3885, "learning_rate": 1e-05, "epoch": 2.3034616628922677, "percentage": 76.86, "elapsed_time": "3:44:27", "remaining_time": "1:07:35", "throughput": "0.00", "total_tokens": 0}
|
268 |
+
{"current_steps": 1340, "total_steps": 1737, "loss": 0.424, "learning_rate": 1e-05, "epoch": 2.312088860131565, "percentage": 77.14, "elapsed_time": "3:45:13", "remaining_time": "1:06:43", "throughput": "0.00", "total_tokens": 0}
|
269 |
+
{"current_steps": 1345, "total_steps": 1737, "loss": 0.4194, "learning_rate": 1e-05, "epoch": 2.320716057370862, "percentage": 77.43, "elapsed_time": "3:45:59", "remaining_time": "1:05:51", "throughput": "0.00", "total_tokens": 0}
|
270 |
+
{"current_steps": 1350, "total_steps": 1737, "loss": 0.3982, "learning_rate": 1e-05, "epoch": 2.3293432546101585, "percentage": 77.72, "elapsed_time": "3:46:43", "remaining_time": "1:04:59", "throughput": "0.00", "total_tokens": 0}
|
271 |
+
{"current_steps": 1355, "total_steps": 1737, "loss": 0.4565, "learning_rate": 1e-05, "epoch": 2.3379704518494555, "percentage": 78.01, "elapsed_time": "3:47:31", "remaining_time": "1:04:08", "throughput": "0.00", "total_tokens": 0}
|
272 |
+
{"current_steps": 1360, "total_steps": 1737, "loss": 0.3995, "learning_rate": 1e-05, "epoch": 2.346597649088752, "percentage": 78.3, "elapsed_time": "3:48:25", "remaining_time": "1:03:19", "throughput": "0.00", "total_tokens": 0}
|
273 |
+
{"current_steps": 1365, "total_steps": 1737, "loss": 0.426, "learning_rate": 1e-05, "epoch": 2.355224846328049, "percentage": 78.58, "elapsed_time": "3:49:09", "remaining_time": "1:02:27", "throughput": "0.00", "total_tokens": 0}
|
274 |
+
{"current_steps": 1370, "total_steps": 1737, "loss": 0.3854, "learning_rate": 1e-05, "epoch": 2.3638520435673462, "percentage": 78.87, "elapsed_time": "3:49:54", "remaining_time": "1:01:35", "throughput": "0.00", "total_tokens": 0}
|
275 |
+
{"current_steps": 1375, "total_steps": 1737, "loss": 0.3808, "learning_rate": 1e-05, "epoch": 2.372479240806643, "percentage": 79.16, "elapsed_time": "3:50:38", "remaining_time": "1:00:43", "throughput": "0.00", "total_tokens": 0}
|
276 |
+
{"current_steps": 1380, "total_steps": 1737, "loss": 0.3598, "learning_rate": 1e-05, "epoch": 2.38110643804594, "percentage": 79.45, "elapsed_time": "3:51:26", "remaining_time": "0:59:52", "throughput": "0.00", "total_tokens": 0}
|
277 |
+
{"current_steps": 1385, "total_steps": 1737, "loss": 0.4018, "learning_rate": 1e-05, "epoch": 2.3897336352852365, "percentage": 79.74, "elapsed_time": "3:52:07", "remaining_time": "0:58:59", "throughput": "0.00", "total_tokens": 0}
|
278 |
+
{"current_steps": 1390, "total_steps": 1737, "loss": 0.4105, "learning_rate": 1e-05, "epoch": 2.3983608325245336, "percentage": 80.02, "elapsed_time": "3:52:54", "remaining_time": "0:58:08", "throughput": "0.00", "total_tokens": 0}
|
279 |
+
{"current_steps": 1395, "total_steps": 1737, "loss": 0.3832, "learning_rate": 1e-05, "epoch": 2.4069880297638306, "percentage": 80.31, "elapsed_time": "3:53:43", "remaining_time": "0:57:17", "throughput": "0.00", "total_tokens": 0}
|
280 |
+
{"current_steps": 1400, "total_steps": 1737, "loss": 0.4288, "learning_rate": 1e-05, "epoch": 2.4156152270031273, "percentage": 80.6, "elapsed_time": "3:54:25", "remaining_time": "0:56:25", "throughput": "0.00", "total_tokens": 0}
|
281 |
+
{"current_steps": 1405, "total_steps": 1737, "loss": 0.3759, "learning_rate": 1e-05, "epoch": 2.4242424242424243, "percentage": 80.89, "elapsed_time": "3:56:31", "remaining_time": "0:55:53", "throughput": "0.00", "total_tokens": 0}
|
282 |
+
{"current_steps": 1410, "total_steps": 1737, "loss": 0.3981, "learning_rate": 1e-05, "epoch": 2.4328696214817214, "percentage": 81.17, "elapsed_time": "3:57:25", "remaining_time": "0:55:03", "throughput": "0.00", "total_tokens": 0}
|
283 |
+
{"current_steps": 1415, "total_steps": 1737, "loss": 0.3461, "learning_rate": 1e-05, "epoch": 2.441496818721018, "percentage": 81.46, "elapsed_time": "3:58:12", "remaining_time": "0:54:12", "throughput": "0.00", "total_tokens": 0}
|
284 |
+
{"current_steps": 1420, "total_steps": 1737, "loss": 0.3898, "learning_rate": 1e-05, "epoch": 2.450124015960315, "percentage": 81.75, "elapsed_time": "3:59:00", "remaining_time": "0:53:21", "throughput": "0.00", "total_tokens": 0}
|
285 |
+
{"current_steps": 1425, "total_steps": 1737, "loss": 0.36, "learning_rate": 1e-05, "epoch": 2.4587512131996117, "percentage": 82.04, "elapsed_time": "3:59:52", "remaining_time": "0:52:31", "throughput": "0.00", "total_tokens": 0}
|
286 |
+
{"current_steps": 1430, "total_steps": 1737, "loss": 0.4348, "learning_rate": 1e-05, "epoch": 2.4673784104389087, "percentage": 82.33, "elapsed_time": "4:00:40", "remaining_time": "0:51:40", "throughput": "0.00", "total_tokens": 0}
|
287 |
+
{"current_steps": 1435, "total_steps": 1737, "loss": 0.3582, "learning_rate": 1e-05, "epoch": 2.4760056076782053, "percentage": 82.61, "elapsed_time": "4:01:30", "remaining_time": "0:50:49", "throughput": "0.00", "total_tokens": 0}
|
288 |
+
{"current_steps": 1440, "total_steps": 1737, "loss": 0.4337, "learning_rate": 1e-05, "epoch": 2.4846328049175024, "percentage": 82.9, "elapsed_time": "4:02:17", "remaining_time": "0:49:58", "throughput": "0.00", "total_tokens": 0}
|
289 |
+
{"current_steps": 1445, "total_steps": 1737, "loss": 0.4196, "learning_rate": 1e-05, "epoch": 2.4932600021567994, "percentage": 83.19, "elapsed_time": "4:02:58", "remaining_time": "0:49:05", "throughput": "0.00", "total_tokens": 0}
|
290 |
+
{"current_steps": 1450, "total_steps": 1737, "loss": 0.3901, "learning_rate": 1e-05, "epoch": 2.501887199396096, "percentage": 83.48, "elapsed_time": "4:03:45", "remaining_time": "0:48:14", "throughput": "0.00", "total_tokens": 0}
|
291 |
+
{"current_steps": 1455, "total_steps": 1737, "loss": 0.3864, "learning_rate": 1e-05, "epoch": 2.510514396635393, "percentage": 83.77, "elapsed_time": "4:04:33", "remaining_time": "0:47:23", "throughput": "0.00", "total_tokens": 0}
|
292 |
+
{"current_steps": 1460, "total_steps": 1737, "loss": 0.3911, "learning_rate": 1e-05, "epoch": 2.51914159387469, "percentage": 84.05, "elapsed_time": "4:05:20", "remaining_time": "0:46:32", "throughput": "0.00", "total_tokens": 0}
|
293 |
+
{"current_steps": 1465, "total_steps": 1737, "loss": 0.4008, "learning_rate": 1e-05, "epoch": 2.527768791113987, "percentage": 84.34, "elapsed_time": "4:06:14", "remaining_time": "0:45:43", "throughput": "0.00", "total_tokens": 0}
|
294 |
+
{"current_steps": 1470, "total_steps": 1737, "loss": 0.3738, "learning_rate": 1e-05, "epoch": 2.536395988353284, "percentage": 84.63, "elapsed_time": "4:06:58", "remaining_time": "0:44:51", "throughput": "0.00", "total_tokens": 0}
|
295 |
+
{"current_steps": 1475, "total_steps": 1737, "loss": 0.3892, "learning_rate": 1e-05, "epoch": 2.5450231855925805, "percentage": 84.92, "elapsed_time": "4:07:42", "remaining_time": "0:44:00", "throughput": "0.00", "total_tokens": 0}
|
296 |
+
{"current_steps": 1480, "total_steps": 1737, "loss": 0.4022, "learning_rate": 1e-05, "epoch": 2.5536503828318775, "percentage": 85.2, "elapsed_time": "4:08:27", "remaining_time": "0:43:08", "throughput": "0.00", "total_tokens": 0}
|
297 |
+
{"current_steps": 1485, "total_steps": 1737, "loss": 0.436, "learning_rate": 1e-05, "epoch": 2.562277580071174, "percentage": 85.49, "elapsed_time": "4:09:15", "remaining_time": "0:42:17", "throughput": "0.00", "total_tokens": 0}
|
298 |
+
{"current_steps": 1490, "total_steps": 1737, "loss": 0.4164, "learning_rate": 1e-05, "epoch": 2.570904777310471, "percentage": 85.78, "elapsed_time": "4:10:02", "remaining_time": "0:41:27", "throughput": "0.00", "total_tokens": 0}
|
299 |
+
{"current_steps": 1495, "total_steps": 1737, "loss": 0.3914, "learning_rate": 1e-05, "epoch": 2.5795319745497682, "percentage": 86.07, "elapsed_time": "4:10:52", "remaining_time": "0:40:36", "throughput": "0.00", "total_tokens": 0}
|
300 |
+
{"current_steps": 1500, "total_steps": 1737, "loss": 0.3878, "learning_rate": 1e-05, "epoch": 2.588159171789065, "percentage": 86.36, "elapsed_time": "4:11:40", "remaining_time": "0:39:45", "throughput": "0.00", "total_tokens": 0}
|
301 |
+
{"current_steps": 1505, "total_steps": 1737, "loss": 0.39, "learning_rate": 1e-05, "epoch": 2.596786369028362, "percentage": 86.64, "elapsed_time": "4:12:20", "remaining_time": "0:38:53", "throughput": "0.00", "total_tokens": 0}
|
302 |
+
{"current_steps": 1510, "total_steps": 1737, "loss": 0.3989, "learning_rate": 1e-05, "epoch": 2.605413566267659, "percentage": 86.93, "elapsed_time": "4:13:03", "remaining_time": "0:38:02", "throughput": "0.00", "total_tokens": 0}
|
303 |
+
{"current_steps": 1515, "total_steps": 1737, "loss": 0.3613, "learning_rate": 1e-05, "epoch": 2.6140407635069556, "percentage": 87.22, "elapsed_time": "4:13:47", "remaining_time": "0:37:11", "throughput": "0.00", "total_tokens": 0}
|
304 |
+
{"current_steps": 1520, "total_steps": 1737, "loss": 0.3995, "learning_rate": 1e-05, "epoch": 2.6226679607462526, "percentage": 87.51, "elapsed_time": "4:14:37", "remaining_time": "0:36:21", "throughput": "0.00", "total_tokens": 0}
|
305 |
+
{"current_steps": 1525, "total_steps": 1737, "loss": 0.3376, "learning_rate": 1e-05, "epoch": 2.6312951579855497, "percentage": 87.8, "elapsed_time": "4:15:20", "remaining_time": "0:35:29", "throughput": "0.00", "total_tokens": 0}
|
306 |
+
{"current_steps": 1530, "total_steps": 1737, "loss": 0.3861, "learning_rate": 1e-05, "epoch": 2.6399223552248463, "percentage": 88.08, "elapsed_time": "4:16:03", "remaining_time": "0:34:38", "throughput": "0.00", "total_tokens": 0}
|
307 |
+
{"current_steps": 1535, "total_steps": 1737, "loss": 0.4193, "learning_rate": 1e-05, "epoch": 2.6485495524641434, "percentage": 88.37, "elapsed_time": "4:16:52", "remaining_time": "0:33:48", "throughput": "0.00", "total_tokens": 0}
|
308 |
+
{"current_steps": 1540, "total_steps": 1737, "loss": 0.4235, "learning_rate": 1e-05, "epoch": 2.65717674970344, "percentage": 88.66, "elapsed_time": "4:17:43", "remaining_time": "0:32:58", "throughput": "0.00", "total_tokens": 0}
|
309 |
+
{"current_steps": 1545, "total_steps": 1737, "loss": 0.39, "learning_rate": 1e-05, "epoch": 2.665803946942737, "percentage": 88.95, "elapsed_time": "4:18:38", "remaining_time": "0:32:08", "throughput": "0.00", "total_tokens": 0}
|
310 |
+
{"current_steps": 1550, "total_steps": 1737, "loss": 0.4395, "learning_rate": 1e-05, "epoch": 2.6744311441820336, "percentage": 89.23, "elapsed_time": "4:19:30", "remaining_time": "0:31:18", "throughput": "0.00", "total_tokens": 0}
|
311 |
+
{"current_steps": 1555, "total_steps": 1737, "loss": 0.3956, "learning_rate": 1e-05, "epoch": 2.6830583414213307, "percentage": 89.52, "elapsed_time": "4:20:20", "remaining_time": "0:30:28", "throughput": "0.00", "total_tokens": 0}
|
312 |
+
{"current_steps": 1560, "total_steps": 1737, "loss": 0.4399, "learning_rate": 1e-05, "epoch": 2.6916855386606278, "percentage": 89.81, "elapsed_time": "4:21:06", "remaining_time": "0:29:37", "throughput": "0.00", "total_tokens": 0}
|
313 |
+
{"current_steps": 1565, "total_steps": 1737, "loss": 0.4161, "learning_rate": 1e-05, "epoch": 2.7003127358999244, "percentage": 90.1, "elapsed_time": "4:21:57", "remaining_time": "0:28:47", "throughput": "0.00", "total_tokens": 0}
|
314 |
+
{"current_steps": 1570, "total_steps": 1737, "loss": 0.4128, "learning_rate": 1e-05, "epoch": 2.7089399331392214, "percentage": 90.39, "elapsed_time": "4:22:51", "remaining_time": "0:27:57", "throughput": "0.00", "total_tokens": 0}
|
315 |
+
{"current_steps": 1575, "total_steps": 1737, "loss": 0.4291, "learning_rate": 1e-05, "epoch": 2.7175671303785185, "percentage": 90.67, "elapsed_time": "4:23:36", "remaining_time": "0:27:06", "throughput": "0.00", "total_tokens": 0}
|
316 |
+
{"current_steps": 1580, "total_steps": 1737, "loss": 0.4198, "learning_rate": 1e-05, "epoch": 2.726194327617815, "percentage": 90.96, "elapsed_time": "4:24:19", "remaining_time": "0:26:15", "throughput": "0.00", "total_tokens": 0}
|
317 |
+
{"current_steps": 1585, "total_steps": 1737, "loss": 0.3954, "learning_rate": 1e-05, "epoch": 2.734821524857112, "percentage": 91.25, "elapsed_time": "4:25:05", "remaining_time": "0:25:25", "throughput": "0.00", "total_tokens": 0}
|
318 |
+
{"current_steps": 1590, "total_steps": 1737, "loss": 0.3718, "learning_rate": 1e-05, "epoch": 2.7434487220964088, "percentage": 91.54, "elapsed_time": "4:25:47", "remaining_time": "0:24:34", "throughput": "0.00", "total_tokens": 0}
|
319 |
+
{"current_steps": 1595, "total_steps": 1737, "loss": 0.3488, "learning_rate": 1e-05, "epoch": 2.752075919335706, "percentage": 91.82, "elapsed_time": "4:26:39", "remaining_time": "0:23:44", "throughput": "0.00", "total_tokens": 0}
|
320 |
+
{"current_steps": 1600, "total_steps": 1737, "loss": 0.4581, "learning_rate": 1e-05, "epoch": 2.7607031165750024, "percentage": 92.11, "elapsed_time": "4:27:28", "remaining_time": "0:22:54", "throughput": "0.00", "total_tokens": 0}
|
321 |
+
{"current_steps": 1605, "total_steps": 1737, "loss": 0.4455, "learning_rate": 1e-05, "epoch": 2.7693303138142995, "percentage": 92.4, "elapsed_time": "4:29:35", "remaining_time": "0:22:10", "throughput": "0.00", "total_tokens": 0}
|
322 |
+
{"current_steps": 1610, "total_steps": 1737, "loss": 0.3918, "learning_rate": 1e-05, "epoch": 2.7779575110535966, "percentage": 92.69, "elapsed_time": "4:30:24", "remaining_time": "0:21:19", "throughput": "0.00", "total_tokens": 0}
|
323 |
+
{"current_steps": 1615, "total_steps": 1737, "loss": 0.4067, "learning_rate": 1e-05, "epoch": 2.786584708292893, "percentage": 92.98, "elapsed_time": "4:31:10", "remaining_time": "0:20:29", "throughput": "0.00", "total_tokens": 0}
|
324 |
+
{"current_steps": 1620, "total_steps": 1737, "loss": 0.4237, "learning_rate": 1e-05, "epoch": 2.7952119055321902, "percentage": 93.26, "elapsed_time": "4:31:53", "remaining_time": "0:19:38", "throughput": "0.00", "total_tokens": 0}
|
325 |
+
{"current_steps": 1625, "total_steps": 1737, "loss": 0.3939, "learning_rate": 1e-05, "epoch": 2.8038391027714873, "percentage": 93.55, "elapsed_time": "4:32:45", "remaining_time": "0:18:47", "throughput": "0.00", "total_tokens": 0}
|
326 |
+
{"current_steps": 1630, "total_steps": 1737, "loss": 0.4385, "learning_rate": 1e-05, "epoch": 2.812466300010784, "percentage": 93.84, "elapsed_time": "4:33:33", "remaining_time": "0:17:57", "throughput": "0.00", "total_tokens": 0}
|
327 |
+
{"current_steps": 1635, "total_steps": 1737, "loss": 0.4109, "learning_rate": 1e-05, "epoch": 2.821093497250081, "percentage": 94.13, "elapsed_time": "4:34:20", "remaining_time": "0:17:06", "throughput": "0.00", "total_tokens": 0}
|
328 |
+
{"current_steps": 1640, "total_steps": 1737, "loss": 0.4402, "learning_rate": 1e-05, "epoch": 2.829720694489378, "percentage": 94.42, "elapsed_time": "4:35:11", "remaining_time": "0:16:16", "throughput": "0.00", "total_tokens": 0}
|
329 |
+
{"current_steps": 1645, "total_steps": 1737, "loss": 0.444, "learning_rate": 1e-05, "epoch": 2.8383478917286746, "percentage": 94.7, "elapsed_time": "4:36:07", "remaining_time": "0:15:26", "throughput": "0.00", "total_tokens": 0}
|
330 |
+
{"current_steps": 1650, "total_steps": 1737, "loss": 0.413, "learning_rate": 1e-05, "epoch": 2.8469750889679717, "percentage": 94.99, "elapsed_time": "4:36:59", "remaining_time": "0:14:36", "throughput": "0.00", "total_tokens": 0}
|
331 |
+
{"current_steps": 1655, "total_steps": 1737, "loss": 0.4245, "learning_rate": 1e-05, "epoch": 2.8556022862072683, "percentage": 95.28, "elapsed_time": "4:37:47", "remaining_time": "0:13:45", "throughput": "0.00", "total_tokens": 0}
|
332 |
+
{"current_steps": 1660, "total_steps": 1737, "loss": 0.4091, "learning_rate": 1e-05, "epoch": 2.8642294834465654, "percentage": 95.57, "elapsed_time": "4:38:33", "remaining_time": "0:12:55", "throughput": "0.00", "total_tokens": 0}
|
333 |
+
{"current_steps": 1665, "total_steps": 1737, "loss": 0.4206, "learning_rate": 1e-05, "epoch": 2.872856680685862, "percentage": 95.85, "elapsed_time": "4:39:14", "remaining_time": "0:12:04", "throughput": "0.00", "total_tokens": 0}
|
334 |
+
{"current_steps": 1670, "total_steps": 1737, "loss": 0.3868, "learning_rate": 1e-05, "epoch": 2.881483877925159, "percentage": 96.14, "elapsed_time": "4:40:06", "remaining_time": "0:11:14", "throughput": "0.00", "total_tokens": 0}
|
335 |
+
{"current_steps": 1675, "total_steps": 1737, "loss": 0.4102, "learning_rate": 1e-05, "epoch": 2.890111075164456, "percentage": 96.43, "elapsed_time": "4:40:52", "remaining_time": "0:10:23", "throughput": "0.00", "total_tokens": 0}
|
336 |
+
{"current_steps": 1680, "total_steps": 1737, "loss": 0.4349, "learning_rate": 1e-05, "epoch": 2.8987382724037527, "percentage": 96.72, "elapsed_time": "4:41:40", "remaining_time": "0:09:33", "throughput": "0.00", "total_tokens": 0}
|
337 |
+
{"current_steps": 1685, "total_steps": 1737, "loss": 0.4298, "learning_rate": 1e-05, "epoch": 2.9073654696430498, "percentage": 97.01, "elapsed_time": "4:42:34", "remaining_time": "0:08:43", "throughput": "0.00", "total_tokens": 0}
|
338 |
+
{"current_steps": 1690, "total_steps": 1737, "loss": 0.431, "learning_rate": 1e-05, "epoch": 2.915992666882347, "percentage": 97.29, "elapsed_time": "4:43:21", "remaining_time": "0:07:52", "throughput": "0.00", "total_tokens": 0}
|
339 |
+
{"current_steps": 1695, "total_steps": 1737, "loss": 0.4373, "learning_rate": 1e-05, "epoch": 2.9246198641216434, "percentage": 97.58, "elapsed_time": "4:44:20", "remaining_time": "0:07:02", "throughput": "0.00", "total_tokens": 0}
|
340 |
+
{"current_steps": 1700, "total_steps": 1737, "loss": 0.4239, "learning_rate": 1e-05, "epoch": 2.9332470613609405, "percentage": 97.87, "elapsed_time": "4:45:05", "remaining_time": "0:06:12", "throughput": "0.00", "total_tokens": 0}
|
341 |
+
{"current_steps": 1705, "total_steps": 1737, "loss": 0.4277, "learning_rate": 1e-05, "epoch": 2.941874258600237, "percentage": 98.16, "elapsed_time": "4:45:54", "remaining_time": "0:05:21", "throughput": "0.00", "total_tokens": 0}
|
342 |
+
{"current_steps": 1710, "total_steps": 1737, "loss": 0.4302, "learning_rate": 1e-05, "epoch": 2.950501455839534, "percentage": 98.45, "elapsed_time": "4:46:39", "remaining_time": "0:04:31", "throughput": "0.00", "total_tokens": 0}
|
343 |
+
{"current_steps": 1715, "total_steps": 1737, "loss": 0.3822, "learning_rate": 1e-05, "epoch": 2.9591286530788308, "percentage": 98.73, "elapsed_time": "4:47:27", "remaining_time": "0:03:41", "throughput": "0.00", "total_tokens": 0}
|
344 |
+
{"current_steps": 1720, "total_steps": 1737, "loss": 0.4402, "learning_rate": 1e-05, "epoch": 2.967755850318128, "percentage": 99.02, "elapsed_time": "4:48:11", "remaining_time": "0:02:50", "throughput": "0.00", "total_tokens": 0}
|
345 |
+
{"current_steps": 1725, "total_steps": 1737, "loss": 0.3803, "learning_rate": 1e-05, "epoch": 2.976383047557425, "percentage": 99.31, "elapsed_time": "4:49:02", "remaining_time": "0:02:00", "throughput": "0.00", "total_tokens": 0}
|
346 |
+
{"current_steps": 1730, "total_steps": 1737, "loss": 0.4109, "learning_rate": 1e-05, "epoch": 2.9850102447967215, "percentage": 99.6, "elapsed_time": "4:49:49", "remaining_time": "0:01:10", "throughput": "0.00", "total_tokens": 0}
|
347 |
+
{"current_steps": 1735, "total_steps": 1737, "loss": 0.4232, "learning_rate": 1e-05, "epoch": 2.9936374420360186, "percentage": 99.88, "elapsed_time": "4:50:32", "remaining_time": "0:00:20", "throughput": "0.00", "total_tokens": 0}
|
348 |
+
{"current_steps": 1737, "total_steps": 1737, "epoch": 2.9970883209317374, "percentage": 100.0, "elapsed_time": "4:52:15", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
|
trainer_state.json
ADDED
@@ -0,0 +1,2471 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9970883209317374,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1737,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.008627197239296884,
|
13 |
+
"grad_norm": 5.919341564178467,
|
14 |
+
"learning_rate": 1e-05,
|
15 |
+
"loss": 1.3814,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.017254394478593768,
|
20 |
+
"grad_norm": 4.066539287567139,
|
21 |
+
"learning_rate": 1e-05,
|
22 |
+
"loss": 1.3848,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.02588159171789065,
|
27 |
+
"grad_norm": 4.004323959350586,
|
28 |
+
"learning_rate": 1e-05,
|
29 |
+
"loss": 1.3517,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.034508788957187536,
|
34 |
+
"grad_norm": 4.424528121948242,
|
35 |
+
"learning_rate": 1e-05,
|
36 |
+
"loss": 1.4088,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.04313598619648442,
|
41 |
+
"grad_norm": 4.122994899749756,
|
42 |
+
"learning_rate": 1e-05,
|
43 |
+
"loss": 1.3542,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0517631834357813,
|
48 |
+
"grad_norm": 3.9815385341644287,
|
49 |
+
"learning_rate": 1e-05,
|
50 |
+
"loss": 1.3434,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.06039038067507818,
|
55 |
+
"grad_norm": 3.663285255432129,
|
56 |
+
"learning_rate": 1e-05,
|
57 |
+
"loss": 1.3926,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.06901757791437507,
|
62 |
+
"grad_norm": 3.6322672367095947,
|
63 |
+
"learning_rate": 1e-05,
|
64 |
+
"loss": 1.2819,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.07764477515367195,
|
69 |
+
"grad_norm": 4.1651387214660645,
|
70 |
+
"learning_rate": 1e-05,
|
71 |
+
"loss": 1.3482,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.08627197239296884,
|
76 |
+
"grad_norm": 3.8225786685943604,
|
77 |
+
"learning_rate": 1e-05,
|
78 |
+
"loss": 1.2621,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.09489916963226572,
|
83 |
+
"grad_norm": 3.9319000244140625,
|
84 |
+
"learning_rate": 1e-05,
|
85 |
+
"loss": 1.2695,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.1035263668715626,
|
90 |
+
"grad_norm": 4.2429633140563965,
|
91 |
+
"learning_rate": 1e-05,
|
92 |
+
"loss": 1.2302,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.11215356411085949,
|
97 |
+
"grad_norm": 3.836970090866089,
|
98 |
+
"learning_rate": 1e-05,
|
99 |
+
"loss": 1.242,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.12078076135015636,
|
104 |
+
"grad_norm": 3.622291326522827,
|
105 |
+
"learning_rate": 1e-05,
|
106 |
+
"loss": 1.2433,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.12940795858945325,
|
111 |
+
"grad_norm": 3.876661539077759,
|
112 |
+
"learning_rate": 1e-05,
|
113 |
+
"loss": 1.3095,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.13803515582875014,
|
118 |
+
"grad_norm": 3.3505313396453857,
|
119 |
+
"learning_rate": 1e-05,
|
120 |
+
"loss": 1.3006,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.146662353068047,
|
125 |
+
"grad_norm": 4.024404048919678,
|
126 |
+
"learning_rate": 1e-05,
|
127 |
+
"loss": 1.2698,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.1552895503073439,
|
132 |
+
"grad_norm": 3.4006166458129883,
|
133 |
+
"learning_rate": 1e-05,
|
134 |
+
"loss": 1.3346,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.1639167475466408,
|
139 |
+
"grad_norm": 3.5438950061798096,
|
140 |
+
"learning_rate": 1e-05,
|
141 |
+
"loss": 1.3634,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.17254394478593768,
|
146 |
+
"grad_norm": 4.186426162719727,
|
147 |
+
"learning_rate": 1e-05,
|
148 |
+
"loss": 1.2645,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.18117114202523454,
|
153 |
+
"grad_norm": 3.5808355808258057,
|
154 |
+
"learning_rate": 1e-05,
|
155 |
+
"loss": 1.3625,
|
156 |
+
"step": 105
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.18979833926453143,
|
160 |
+
"grad_norm": 4.477747917175293,
|
161 |
+
"learning_rate": 1e-05,
|
162 |
+
"loss": 1.2592,
|
163 |
+
"step": 110
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.19842553650382833,
|
167 |
+
"grad_norm": 3.461580753326416,
|
168 |
+
"learning_rate": 1e-05,
|
169 |
+
"loss": 1.2872,
|
170 |
+
"step": 115
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.2070527337431252,
|
174 |
+
"grad_norm": 4.153059005737305,
|
175 |
+
"learning_rate": 1e-05,
|
176 |
+
"loss": 1.31,
|
177 |
+
"step": 120
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.21567993098242208,
|
181 |
+
"grad_norm": 4.117781639099121,
|
182 |
+
"learning_rate": 1e-05,
|
183 |
+
"loss": 1.2627,
|
184 |
+
"step": 125
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.22430712822171897,
|
188 |
+
"grad_norm": 4.274353504180908,
|
189 |
+
"learning_rate": 1e-05,
|
190 |
+
"loss": 1.206,
|
191 |
+
"step": 130
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.23293432546101586,
|
195 |
+
"grad_norm": 3.5153017044067383,
|
196 |
+
"learning_rate": 1e-05,
|
197 |
+
"loss": 1.3192,
|
198 |
+
"step": 135
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.24156152270031273,
|
202 |
+
"grad_norm": 3.2502472400665283,
|
203 |
+
"learning_rate": 1e-05,
|
204 |
+
"loss": 1.2825,
|
205 |
+
"step": 140
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.2501887199396096,
|
209 |
+
"grad_norm": 3.598522186279297,
|
210 |
+
"learning_rate": 1e-05,
|
211 |
+
"loss": 1.3421,
|
212 |
+
"step": 145
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.2588159171789065,
|
216 |
+
"grad_norm": 3.85213565826416,
|
217 |
+
"learning_rate": 1e-05,
|
218 |
+
"loss": 1.3141,
|
219 |
+
"step": 150
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.2674431144182034,
|
223 |
+
"grad_norm": 4.03485107421875,
|
224 |
+
"learning_rate": 1e-05,
|
225 |
+
"loss": 1.298,
|
226 |
+
"step": 155
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.2760703116575003,
|
230 |
+
"grad_norm": 3.352916717529297,
|
231 |
+
"learning_rate": 1e-05,
|
232 |
+
"loss": 1.3034,
|
233 |
+
"step": 160
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.2846975088967972,
|
237 |
+
"grad_norm": 3.504659652709961,
|
238 |
+
"learning_rate": 1e-05,
|
239 |
+
"loss": 1.2532,
|
240 |
+
"step": 165
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.293324706136094,
|
244 |
+
"grad_norm": 3.5304458141326904,
|
245 |
+
"learning_rate": 1e-05,
|
246 |
+
"loss": 1.2745,
|
247 |
+
"step": 170
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.3019519033753909,
|
251 |
+
"grad_norm": 3.2286152839660645,
|
252 |
+
"learning_rate": 1e-05,
|
253 |
+
"loss": 1.3067,
|
254 |
+
"step": 175
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.3105791006146878,
|
258 |
+
"grad_norm": 3.1940603256225586,
|
259 |
+
"learning_rate": 1e-05,
|
260 |
+
"loss": 1.2628,
|
261 |
+
"step": 180
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.3192062978539847,
|
265 |
+
"grad_norm": 3.7485692501068115,
|
266 |
+
"learning_rate": 1e-05,
|
267 |
+
"loss": 1.2514,
|
268 |
+
"step": 185
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.3278334950932816,
|
272 |
+
"grad_norm": 3.438934326171875,
|
273 |
+
"learning_rate": 1e-05,
|
274 |
+
"loss": 1.2122,
|
275 |
+
"step": 190
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.33646069233257847,
|
279 |
+
"grad_norm": 4.063304424285889,
|
280 |
+
"learning_rate": 1e-05,
|
281 |
+
"loss": 1.2825,
|
282 |
+
"step": 195
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.34508788957187536,
|
286 |
+
"grad_norm": 3.3390140533447266,
|
287 |
+
"learning_rate": 1e-05,
|
288 |
+
"loss": 1.2752,
|
289 |
+
"step": 200
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.3537150868111722,
|
293 |
+
"grad_norm": 3.5218873023986816,
|
294 |
+
"learning_rate": 1e-05,
|
295 |
+
"loss": 1.3145,
|
296 |
+
"step": 205
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.3623422840504691,
|
300 |
+
"grad_norm": 4.008931636810303,
|
301 |
+
"learning_rate": 1e-05,
|
302 |
+
"loss": 1.2694,
|
303 |
+
"step": 210
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.370969481289766,
|
307 |
+
"grad_norm": 3.844992160797119,
|
308 |
+
"learning_rate": 1e-05,
|
309 |
+
"loss": 1.3507,
|
310 |
+
"step": 215
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.37959667852906287,
|
314 |
+
"grad_norm": 3.2494778633117676,
|
315 |
+
"learning_rate": 1e-05,
|
316 |
+
"loss": 1.3843,
|
317 |
+
"step": 220
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.38822387576835976,
|
321 |
+
"grad_norm": 3.2193210124969482,
|
322 |
+
"learning_rate": 1e-05,
|
323 |
+
"loss": 1.2553,
|
324 |
+
"step": 225
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.39685107300765665,
|
328 |
+
"grad_norm": 3.6562159061431885,
|
329 |
+
"learning_rate": 1e-05,
|
330 |
+
"loss": 1.3664,
|
331 |
+
"step": 230
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.40547827024695354,
|
335 |
+
"grad_norm": 3.219736099243164,
|
336 |
+
"learning_rate": 1e-05,
|
337 |
+
"loss": 1.3083,
|
338 |
+
"step": 235
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.4141054674862504,
|
342 |
+
"grad_norm": 3.986835241317749,
|
343 |
+
"learning_rate": 1e-05,
|
344 |
+
"loss": 1.2945,
|
345 |
+
"step": 240
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.42273266472554727,
|
349 |
+
"grad_norm": 3.874375581741333,
|
350 |
+
"learning_rate": 1e-05,
|
351 |
+
"loss": 1.2938,
|
352 |
+
"step": 245
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.43135986196484416,
|
356 |
+
"grad_norm": 3.1514320373535156,
|
357 |
+
"learning_rate": 1e-05,
|
358 |
+
"loss": 1.2231,
|
359 |
+
"step": 250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.43998705920414105,
|
363 |
+
"grad_norm": 3.3543567657470703,
|
364 |
+
"learning_rate": 1e-05,
|
365 |
+
"loss": 1.2237,
|
366 |
+
"step": 255
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.44861425644343794,
|
370 |
+
"grad_norm": 4.068399906158447,
|
371 |
+
"learning_rate": 1e-05,
|
372 |
+
"loss": 1.1541,
|
373 |
+
"step": 260
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.45724145368273483,
|
377 |
+
"grad_norm": 3.7400364875793457,
|
378 |
+
"learning_rate": 1e-05,
|
379 |
+
"loss": 1.2629,
|
380 |
+
"step": 265
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.4658686509220317,
|
384 |
+
"grad_norm": 3.091808557510376,
|
385 |
+
"learning_rate": 1e-05,
|
386 |
+
"loss": 1.1911,
|
387 |
+
"step": 270
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.4744958481613286,
|
391 |
+
"grad_norm": 3.622913360595703,
|
392 |
+
"learning_rate": 1e-05,
|
393 |
+
"loss": 1.4012,
|
394 |
+
"step": 275
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.48312304540062545,
|
398 |
+
"grad_norm": 3.368582010269165,
|
399 |
+
"learning_rate": 1e-05,
|
400 |
+
"loss": 1.2188,
|
401 |
+
"step": 280
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.49175024263992234,
|
405 |
+
"grad_norm": 3.4569334983825684,
|
406 |
+
"learning_rate": 1e-05,
|
407 |
+
"loss": 1.354,
|
408 |
+
"step": 285
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.5003774398792192,
|
412 |
+
"grad_norm": 3.7725794315338135,
|
413 |
+
"learning_rate": 1e-05,
|
414 |
+
"loss": 1.3322,
|
415 |
+
"step": 290
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.5090046371185161,
|
419 |
+
"grad_norm": 3.446682929992676,
|
420 |
+
"learning_rate": 1e-05,
|
421 |
+
"loss": 1.3385,
|
422 |
+
"step": 295
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.517631834357813,
|
426 |
+
"grad_norm": 3.31061053276062,
|
427 |
+
"learning_rate": 1e-05,
|
428 |
+
"loss": 1.2541,
|
429 |
+
"step": 300
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.5262590315971098,
|
433 |
+
"grad_norm": 3.3477659225463867,
|
434 |
+
"learning_rate": 1e-05,
|
435 |
+
"loss": 1.3451,
|
436 |
+
"step": 305
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.5348862288364068,
|
440 |
+
"grad_norm": 4.0511322021484375,
|
441 |
+
"learning_rate": 1e-05,
|
442 |
+
"loss": 1.3269,
|
443 |
+
"step": 310
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.5435134260757036,
|
447 |
+
"grad_norm": 3.5980873107910156,
|
448 |
+
"learning_rate": 1e-05,
|
449 |
+
"loss": 1.2654,
|
450 |
+
"step": 315
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.5521406233150006,
|
454 |
+
"grad_norm": 4.6503119468688965,
|
455 |
+
"learning_rate": 1e-05,
|
456 |
+
"loss": 1.3162,
|
457 |
+
"step": 320
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.5607678205542974,
|
461 |
+
"grad_norm": 3.890101432800293,
|
462 |
+
"learning_rate": 1e-05,
|
463 |
+
"loss": 1.2839,
|
464 |
+
"step": 325
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.5693950177935944,
|
468 |
+
"grad_norm": 3.019289016723633,
|
469 |
+
"learning_rate": 1e-05,
|
470 |
+
"loss": 1.3095,
|
471 |
+
"step": 330
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.5780222150328912,
|
475 |
+
"grad_norm": 3.544351100921631,
|
476 |
+
"learning_rate": 1e-05,
|
477 |
+
"loss": 1.285,
|
478 |
+
"step": 335
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.586649412272188,
|
482 |
+
"grad_norm": 4.081313133239746,
|
483 |
+
"learning_rate": 1e-05,
|
484 |
+
"loss": 1.2419,
|
485 |
+
"step": 340
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.595276609511485,
|
489 |
+
"grad_norm": 3.010798454284668,
|
490 |
+
"learning_rate": 1e-05,
|
491 |
+
"loss": 1.2875,
|
492 |
+
"step": 345
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.6039038067507818,
|
496 |
+
"grad_norm": 3.469045639038086,
|
497 |
+
"learning_rate": 1e-05,
|
498 |
+
"loss": 1.3055,
|
499 |
+
"step": 350
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.6125310039900788,
|
503 |
+
"grad_norm": 3.8424911499023438,
|
504 |
+
"learning_rate": 1e-05,
|
505 |
+
"loss": 1.33,
|
506 |
+
"step": 355
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.6211582012293756,
|
510 |
+
"grad_norm": 3.3473572731018066,
|
511 |
+
"learning_rate": 1e-05,
|
512 |
+
"loss": 1.2003,
|
513 |
+
"step": 360
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.6297853984686725,
|
517 |
+
"grad_norm": 3.4214556217193604,
|
518 |
+
"learning_rate": 1e-05,
|
519 |
+
"loss": 1.2385,
|
520 |
+
"step": 365
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.6384125957079694,
|
524 |
+
"grad_norm": 3.459791898727417,
|
525 |
+
"learning_rate": 1e-05,
|
526 |
+
"loss": 1.2198,
|
527 |
+
"step": 370
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.6470397929472662,
|
531 |
+
"grad_norm": 3.77476167678833,
|
532 |
+
"learning_rate": 1e-05,
|
533 |
+
"loss": 1.3135,
|
534 |
+
"step": 375
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.6556669901865632,
|
538 |
+
"grad_norm": 3.092871904373169,
|
539 |
+
"learning_rate": 1e-05,
|
540 |
+
"loss": 1.3234,
|
541 |
+
"step": 380
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.66429418742586,
|
545 |
+
"grad_norm": 3.2897961139678955,
|
546 |
+
"learning_rate": 1e-05,
|
547 |
+
"loss": 1.3376,
|
548 |
+
"step": 385
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.6729213846651569,
|
552 |
+
"grad_norm": 3.227506399154663,
|
553 |
+
"learning_rate": 1e-05,
|
554 |
+
"loss": 1.2237,
|
555 |
+
"step": 390
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.6815485819044538,
|
559 |
+
"grad_norm": 3.3434855937957764,
|
560 |
+
"learning_rate": 1e-05,
|
561 |
+
"loss": 1.2465,
|
562 |
+
"step": 395
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.6901757791437507,
|
566 |
+
"grad_norm": 3.5809898376464844,
|
567 |
+
"learning_rate": 1e-05,
|
568 |
+
"loss": 1.2188,
|
569 |
+
"step": 400
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.6988029763830476,
|
573 |
+
"grad_norm": 3.5106072425842285,
|
574 |
+
"learning_rate": 1e-05,
|
575 |
+
"loss": 1.2663,
|
576 |
+
"step": 405
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.7074301736223444,
|
580 |
+
"grad_norm": 3.0715136528015137,
|
581 |
+
"learning_rate": 1e-05,
|
582 |
+
"loss": 1.3354,
|
583 |
+
"step": 410
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.7160573708616413,
|
587 |
+
"grad_norm": 3.441499948501587,
|
588 |
+
"learning_rate": 1e-05,
|
589 |
+
"loss": 1.3112,
|
590 |
+
"step": 415
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.7246845681009382,
|
594 |
+
"grad_norm": 2.81852388381958,
|
595 |
+
"learning_rate": 1e-05,
|
596 |
+
"loss": 1.2335,
|
597 |
+
"step": 420
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.7333117653402351,
|
601 |
+
"grad_norm": 4.062169075012207,
|
602 |
+
"learning_rate": 1e-05,
|
603 |
+
"loss": 1.2291,
|
604 |
+
"step": 425
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.741938962579532,
|
608 |
+
"grad_norm": 3.453822612762451,
|
609 |
+
"learning_rate": 1e-05,
|
610 |
+
"loss": 1.1676,
|
611 |
+
"step": 430
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.7505661598188289,
|
615 |
+
"grad_norm": 3.2253923416137695,
|
616 |
+
"learning_rate": 1e-05,
|
617 |
+
"loss": 1.2539,
|
618 |
+
"step": 435
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.7591933570581257,
|
622 |
+
"grad_norm": 3.092754364013672,
|
623 |
+
"learning_rate": 1e-05,
|
624 |
+
"loss": 1.2994,
|
625 |
+
"step": 440
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.7678205542974226,
|
629 |
+
"grad_norm": 3.07718825340271,
|
630 |
+
"learning_rate": 1e-05,
|
631 |
+
"loss": 1.2304,
|
632 |
+
"step": 445
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.7764477515367195,
|
636 |
+
"grad_norm": 3.2939090728759766,
|
637 |
+
"learning_rate": 1e-05,
|
638 |
+
"loss": 1.2871,
|
639 |
+
"step": 450
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.7850749487760164,
|
643 |
+
"grad_norm": 3.8047966957092285,
|
644 |
+
"learning_rate": 1e-05,
|
645 |
+
"loss": 1.3053,
|
646 |
+
"step": 455
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.7937021460153133,
|
650 |
+
"grad_norm": 4.2863969802856445,
|
651 |
+
"learning_rate": 1e-05,
|
652 |
+
"loss": 1.2691,
|
653 |
+
"step": 460
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.8023293432546101,
|
657 |
+
"grad_norm": 3.9592127799987793,
|
658 |
+
"learning_rate": 1e-05,
|
659 |
+
"loss": 1.2744,
|
660 |
+
"step": 465
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.8109565404939071,
|
664 |
+
"grad_norm": 4.489944934844971,
|
665 |
+
"learning_rate": 1e-05,
|
666 |
+
"loss": 1.2016,
|
667 |
+
"step": 470
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.8195837377332039,
|
671 |
+
"grad_norm": 3.259884834289551,
|
672 |
+
"learning_rate": 1e-05,
|
673 |
+
"loss": 1.2787,
|
674 |
+
"step": 475
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.8282109349725008,
|
678 |
+
"grad_norm": 3.40492582321167,
|
679 |
+
"learning_rate": 1e-05,
|
680 |
+
"loss": 1.3095,
|
681 |
+
"step": 480
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.8368381322117977,
|
685 |
+
"grad_norm": 3.3192970752716064,
|
686 |
+
"learning_rate": 1e-05,
|
687 |
+
"loss": 1.2503,
|
688 |
+
"step": 485
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.8454653294510945,
|
692 |
+
"grad_norm": 3.331552743911743,
|
693 |
+
"learning_rate": 1e-05,
|
694 |
+
"loss": 1.2598,
|
695 |
+
"step": 490
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.8540925266903915,
|
699 |
+
"grad_norm": 3.073087692260742,
|
700 |
+
"learning_rate": 1e-05,
|
701 |
+
"loss": 1.2914,
|
702 |
+
"step": 495
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.8627197239296883,
|
706 |
+
"grad_norm": 3.344917058944702,
|
707 |
+
"learning_rate": 1e-05,
|
708 |
+
"loss": 1.2744,
|
709 |
+
"step": 500
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.8713469211689853,
|
713 |
+
"grad_norm": 2.9080522060394287,
|
714 |
+
"learning_rate": 1e-05,
|
715 |
+
"loss": 1.3817,
|
716 |
+
"step": 505
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.8799741184082821,
|
720 |
+
"grad_norm": 3.2660365104675293,
|
721 |
+
"learning_rate": 1e-05,
|
722 |
+
"loss": 1.1628,
|
723 |
+
"step": 510
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.8886013156475789,
|
727 |
+
"grad_norm": 3.2718842029571533,
|
728 |
+
"learning_rate": 1e-05,
|
729 |
+
"loss": 1.2602,
|
730 |
+
"step": 515
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.8972285128868759,
|
734 |
+
"grad_norm": 3.0166728496551514,
|
735 |
+
"learning_rate": 1e-05,
|
736 |
+
"loss": 1.2036,
|
737 |
+
"step": 520
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.9058557101261727,
|
741 |
+
"grad_norm": 3.566046953201294,
|
742 |
+
"learning_rate": 1e-05,
|
743 |
+
"loss": 1.2575,
|
744 |
+
"step": 525
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.9144829073654697,
|
748 |
+
"grad_norm": 3.3579084873199463,
|
749 |
+
"learning_rate": 1e-05,
|
750 |
+
"loss": 1.2762,
|
751 |
+
"step": 530
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.9231101046047665,
|
755 |
+
"grad_norm": 3.251415252685547,
|
756 |
+
"learning_rate": 1e-05,
|
757 |
+
"loss": 1.299,
|
758 |
+
"step": 535
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.9317373018440634,
|
762 |
+
"grad_norm": 3.4540982246398926,
|
763 |
+
"learning_rate": 1e-05,
|
764 |
+
"loss": 1.2246,
|
765 |
+
"step": 540
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.9403644990833603,
|
769 |
+
"grad_norm": 3.0218403339385986,
|
770 |
+
"learning_rate": 1e-05,
|
771 |
+
"loss": 1.2069,
|
772 |
+
"step": 545
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.9489916963226572,
|
776 |
+
"grad_norm": 3.457592248916626,
|
777 |
+
"learning_rate": 1e-05,
|
778 |
+
"loss": 1.244,
|
779 |
+
"step": 550
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.9576188935619541,
|
783 |
+
"grad_norm": 2.8288912773132324,
|
784 |
+
"learning_rate": 1e-05,
|
785 |
+
"loss": 1.2785,
|
786 |
+
"step": 555
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.9662460908012509,
|
790 |
+
"grad_norm": 3.9383344650268555,
|
791 |
+
"learning_rate": 1e-05,
|
792 |
+
"loss": 1.2542,
|
793 |
+
"step": 560
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.9748732880405478,
|
797 |
+
"grad_norm": 3.215847969055176,
|
798 |
+
"learning_rate": 1e-05,
|
799 |
+
"loss": 1.2649,
|
800 |
+
"step": 565
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.9835004852798447,
|
804 |
+
"grad_norm": 3.3479530811309814,
|
805 |
+
"learning_rate": 1e-05,
|
806 |
+
"loss": 1.2963,
|
807 |
+
"step": 570
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.9921276825191416,
|
811 |
+
"grad_norm": 3.1215426921844482,
|
812 |
+
"learning_rate": 1e-05,
|
813 |
+
"loss": 1.2534,
|
814 |
+
"step": 575
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 1.0007548797584385,
|
818 |
+
"grad_norm": 3.651639223098755,
|
819 |
+
"learning_rate": 1e-05,
|
820 |
+
"loss": 1.1385,
|
821 |
+
"step": 580
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 1.0093820769977353,
|
825 |
+
"grad_norm": 3.4434738159179688,
|
826 |
+
"learning_rate": 1e-05,
|
827 |
+
"loss": 0.8563,
|
828 |
+
"step": 585
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 1.0180092742370321,
|
832 |
+
"grad_norm": 4.103019714355469,
|
833 |
+
"learning_rate": 1e-05,
|
834 |
+
"loss": 0.9018,
|
835 |
+
"step": 590
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 1.0266364714763292,
|
839 |
+
"grad_norm": 3.472033977508545,
|
840 |
+
"learning_rate": 1e-05,
|
841 |
+
"loss": 0.8435,
|
842 |
+
"step": 595
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 1.035263668715626,
|
846 |
+
"grad_norm": 3.869497537612915,
|
847 |
+
"learning_rate": 1e-05,
|
848 |
+
"loss": 0.7686,
|
849 |
+
"step": 600
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 1.0438908659549229,
|
853 |
+
"grad_norm": 3.7982940673828125,
|
854 |
+
"learning_rate": 1e-05,
|
855 |
+
"loss": 0.7134,
|
856 |
+
"step": 605
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 1.0525180631942197,
|
860 |
+
"grad_norm": 3.038923978805542,
|
861 |
+
"learning_rate": 1e-05,
|
862 |
+
"loss": 0.7836,
|
863 |
+
"step": 610
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 1.0611452604335168,
|
867 |
+
"grad_norm": 3.709296464920044,
|
868 |
+
"learning_rate": 1e-05,
|
869 |
+
"loss": 0.8263,
|
870 |
+
"step": 615
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 1.0697724576728136,
|
874 |
+
"grad_norm": 3.110173225402832,
|
875 |
+
"learning_rate": 1e-05,
|
876 |
+
"loss": 0.8028,
|
877 |
+
"step": 620
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 1.0783996549121104,
|
881 |
+
"grad_norm": 4.099541187286377,
|
882 |
+
"learning_rate": 1e-05,
|
883 |
+
"loss": 0.7552,
|
884 |
+
"step": 625
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 1.0870268521514073,
|
888 |
+
"grad_norm": 3.3552350997924805,
|
889 |
+
"learning_rate": 1e-05,
|
890 |
+
"loss": 0.838,
|
891 |
+
"step": 630
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 1.095654049390704,
|
895 |
+
"grad_norm": 3.6320431232452393,
|
896 |
+
"learning_rate": 1e-05,
|
897 |
+
"loss": 0.7915,
|
898 |
+
"step": 635
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 1.1042812466300012,
|
902 |
+
"grad_norm": 3.646231174468994,
|
903 |
+
"learning_rate": 1e-05,
|
904 |
+
"loss": 0.7522,
|
905 |
+
"step": 640
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 1.112908443869298,
|
909 |
+
"grad_norm": 3.390377998352051,
|
910 |
+
"learning_rate": 1e-05,
|
911 |
+
"loss": 0.7777,
|
912 |
+
"step": 645
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 1.1215356411085948,
|
916 |
+
"grad_norm": 3.605112075805664,
|
917 |
+
"learning_rate": 1e-05,
|
918 |
+
"loss": 0.8388,
|
919 |
+
"step": 650
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 1.1301628383478917,
|
923 |
+
"grad_norm": 3.313898801803589,
|
924 |
+
"learning_rate": 1e-05,
|
925 |
+
"loss": 0.8455,
|
926 |
+
"step": 655
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 1.1387900355871885,
|
930 |
+
"grad_norm": 3.3568379878997803,
|
931 |
+
"learning_rate": 1e-05,
|
932 |
+
"loss": 0.8048,
|
933 |
+
"step": 660
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 1.1474172328264856,
|
937 |
+
"grad_norm": 3.5753304958343506,
|
938 |
+
"learning_rate": 1e-05,
|
939 |
+
"loss": 0.7762,
|
940 |
+
"step": 665
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 1.1560444300657824,
|
944 |
+
"grad_norm": 3.9311811923980713,
|
945 |
+
"learning_rate": 1e-05,
|
946 |
+
"loss": 0.7812,
|
947 |
+
"step": 670
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 1.1646716273050792,
|
951 |
+
"grad_norm": 3.399244546890259,
|
952 |
+
"learning_rate": 1e-05,
|
953 |
+
"loss": 0.8134,
|
954 |
+
"step": 675
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 1.173298824544376,
|
958 |
+
"grad_norm": 3.5281805992126465,
|
959 |
+
"learning_rate": 1e-05,
|
960 |
+
"loss": 0.7821,
|
961 |
+
"step": 680
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 1.1819260217836731,
|
965 |
+
"grad_norm": 3.510946273803711,
|
966 |
+
"learning_rate": 1e-05,
|
967 |
+
"loss": 0.8034,
|
968 |
+
"step": 685
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 1.19055321902297,
|
972 |
+
"grad_norm": 3.504866361618042,
|
973 |
+
"learning_rate": 1e-05,
|
974 |
+
"loss": 0.7592,
|
975 |
+
"step": 690
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 1.1991804162622668,
|
979 |
+
"grad_norm": 3.339489698410034,
|
980 |
+
"learning_rate": 1e-05,
|
981 |
+
"loss": 0.7738,
|
982 |
+
"step": 695
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 1.2078076135015636,
|
986 |
+
"grad_norm": 2.915128231048584,
|
987 |
+
"learning_rate": 1e-05,
|
988 |
+
"loss": 0.7043,
|
989 |
+
"step": 700
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 1.2164348107408607,
|
993 |
+
"grad_norm": 3.4995436668395996,
|
994 |
+
"learning_rate": 1e-05,
|
995 |
+
"loss": 0.7969,
|
996 |
+
"step": 705
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 1.2250620079801575,
|
1000 |
+
"grad_norm": 3.3331191539764404,
|
1001 |
+
"learning_rate": 1e-05,
|
1002 |
+
"loss": 0.7299,
|
1003 |
+
"step": 710
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 1.2336892052194544,
|
1007 |
+
"grad_norm": 3.898615598678589,
|
1008 |
+
"learning_rate": 1e-05,
|
1009 |
+
"loss": 0.811,
|
1010 |
+
"step": 715
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 1.2423164024587512,
|
1014 |
+
"grad_norm": 3.1952695846557617,
|
1015 |
+
"learning_rate": 1e-05,
|
1016 |
+
"loss": 0.7714,
|
1017 |
+
"step": 720
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 1.250943599698048,
|
1021 |
+
"grad_norm": 3.310316801071167,
|
1022 |
+
"learning_rate": 1e-05,
|
1023 |
+
"loss": 0.8388,
|
1024 |
+
"step": 725
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 1.259570796937345,
|
1028 |
+
"grad_norm": 3.0263495445251465,
|
1029 |
+
"learning_rate": 1e-05,
|
1030 |
+
"loss": 0.8244,
|
1031 |
+
"step": 730
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 1.268197994176642,
|
1035 |
+
"grad_norm": 3.4661359786987305,
|
1036 |
+
"learning_rate": 1e-05,
|
1037 |
+
"loss": 0.8326,
|
1038 |
+
"step": 735
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 1.2768251914159388,
|
1042 |
+
"grad_norm": 3.4017932415008545,
|
1043 |
+
"learning_rate": 1e-05,
|
1044 |
+
"loss": 0.8302,
|
1045 |
+
"step": 740
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 1.2854523886552356,
|
1049 |
+
"grad_norm": 3.6982741355895996,
|
1050 |
+
"learning_rate": 1e-05,
|
1051 |
+
"loss": 0.7911,
|
1052 |
+
"step": 745
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 1.2940795858945324,
|
1056 |
+
"grad_norm": 3.737339973449707,
|
1057 |
+
"learning_rate": 1e-05,
|
1058 |
+
"loss": 0.8836,
|
1059 |
+
"step": 750
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 1.3027067831338295,
|
1063 |
+
"grad_norm": 3.491697311401367,
|
1064 |
+
"learning_rate": 1e-05,
|
1065 |
+
"loss": 0.8023,
|
1066 |
+
"step": 755
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 1.3113339803731263,
|
1070 |
+
"grad_norm": 3.9661755561828613,
|
1071 |
+
"learning_rate": 1e-05,
|
1072 |
+
"loss": 0.8338,
|
1073 |
+
"step": 760
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 1.3199611776124232,
|
1077 |
+
"grad_norm": 3.4925425052642822,
|
1078 |
+
"learning_rate": 1e-05,
|
1079 |
+
"loss": 0.8247,
|
1080 |
+
"step": 765
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 1.32858837485172,
|
1084 |
+
"grad_norm": 3.0747172832489014,
|
1085 |
+
"learning_rate": 1e-05,
|
1086 |
+
"loss": 0.8781,
|
1087 |
+
"step": 770
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 1.3372155720910168,
|
1091 |
+
"grad_norm": 3.2208268642425537,
|
1092 |
+
"learning_rate": 1e-05,
|
1093 |
+
"loss": 0.7967,
|
1094 |
+
"step": 775
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 1.3458427693303139,
|
1098 |
+
"grad_norm": 3.751079559326172,
|
1099 |
+
"learning_rate": 1e-05,
|
1100 |
+
"loss": 0.7918,
|
1101 |
+
"step": 780
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 1.3544699665696107,
|
1105 |
+
"grad_norm": 3.1584877967834473,
|
1106 |
+
"learning_rate": 1e-05,
|
1107 |
+
"loss": 0.7784,
|
1108 |
+
"step": 785
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 1.3630971638089076,
|
1112 |
+
"grad_norm": 3.420969009399414,
|
1113 |
+
"learning_rate": 1e-05,
|
1114 |
+
"loss": 0.8017,
|
1115 |
+
"step": 790
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 1.3717243610482044,
|
1119 |
+
"grad_norm": 3.333355188369751,
|
1120 |
+
"learning_rate": 1e-05,
|
1121 |
+
"loss": 0.7803,
|
1122 |
+
"step": 795
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 1.3803515582875012,
|
1126 |
+
"grad_norm": 3.5859718322753906,
|
1127 |
+
"learning_rate": 1e-05,
|
1128 |
+
"loss": 0.8341,
|
1129 |
+
"step": 800
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 1.3889787555267983,
|
1133 |
+
"grad_norm": 3.3463239669799805,
|
1134 |
+
"learning_rate": 1e-05,
|
1135 |
+
"loss": 0.7977,
|
1136 |
+
"step": 805
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 1.3976059527660951,
|
1140 |
+
"grad_norm": 3.34783935546875,
|
1141 |
+
"learning_rate": 1e-05,
|
1142 |
+
"loss": 0.778,
|
1143 |
+
"step": 810
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 1.406233150005392,
|
1147 |
+
"grad_norm": 4.29722261428833,
|
1148 |
+
"learning_rate": 1e-05,
|
1149 |
+
"loss": 0.8107,
|
1150 |
+
"step": 815
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 1.414860347244689,
|
1154 |
+
"grad_norm": 3.2892956733703613,
|
1155 |
+
"learning_rate": 1e-05,
|
1156 |
+
"loss": 0.753,
|
1157 |
+
"step": 820
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 1.4234875444839858,
|
1161 |
+
"grad_norm": 3.7883739471435547,
|
1162 |
+
"learning_rate": 1e-05,
|
1163 |
+
"loss": 0.8111,
|
1164 |
+
"step": 825
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 1.4321147417232827,
|
1168 |
+
"grad_norm": 3.545917510986328,
|
1169 |
+
"learning_rate": 1e-05,
|
1170 |
+
"loss": 0.7559,
|
1171 |
+
"step": 830
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 1.4407419389625795,
|
1175 |
+
"grad_norm": 3.5111639499664307,
|
1176 |
+
"learning_rate": 1e-05,
|
1177 |
+
"loss": 0.8213,
|
1178 |
+
"step": 835
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 1.4493691362018764,
|
1182 |
+
"grad_norm": 3.9835708141326904,
|
1183 |
+
"learning_rate": 1e-05,
|
1184 |
+
"loss": 0.9053,
|
1185 |
+
"step": 840
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 1.4579963334411734,
|
1189 |
+
"grad_norm": 3.5352683067321777,
|
1190 |
+
"learning_rate": 1e-05,
|
1191 |
+
"loss": 0.7486,
|
1192 |
+
"step": 845
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 1.4666235306804702,
|
1196 |
+
"grad_norm": 3.8274669647216797,
|
1197 |
+
"learning_rate": 1e-05,
|
1198 |
+
"loss": 0.8385,
|
1199 |
+
"step": 850
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 1.475250727919767,
|
1203 |
+
"grad_norm": 3.425276041030884,
|
1204 |
+
"learning_rate": 1e-05,
|
1205 |
+
"loss": 0.8994,
|
1206 |
+
"step": 855
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 1.483877925159064,
|
1210 |
+
"grad_norm": 3.498198986053467,
|
1211 |
+
"learning_rate": 1e-05,
|
1212 |
+
"loss": 0.7993,
|
1213 |
+
"step": 860
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 1.4925051223983608,
|
1217 |
+
"grad_norm": 3.5711140632629395,
|
1218 |
+
"learning_rate": 1e-05,
|
1219 |
+
"loss": 0.8415,
|
1220 |
+
"step": 865
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 1.5011323196376578,
|
1224 |
+
"grad_norm": 3.628063917160034,
|
1225 |
+
"learning_rate": 1e-05,
|
1226 |
+
"loss": 0.7544,
|
1227 |
+
"step": 870
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 1.5097595168769546,
|
1231 |
+
"grad_norm": 3.185468912124634,
|
1232 |
+
"learning_rate": 1e-05,
|
1233 |
+
"loss": 0.8997,
|
1234 |
+
"step": 875
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 1.5183867141162515,
|
1238 |
+
"grad_norm": 3.289321184158325,
|
1239 |
+
"learning_rate": 1e-05,
|
1240 |
+
"loss": 0.7673,
|
1241 |
+
"step": 880
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 1.5270139113555483,
|
1245 |
+
"grad_norm": 3.4474823474884033,
|
1246 |
+
"learning_rate": 1e-05,
|
1247 |
+
"loss": 0.8582,
|
1248 |
+
"step": 885
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 1.5356411085948452,
|
1252 |
+
"grad_norm": 4.132356643676758,
|
1253 |
+
"learning_rate": 1e-05,
|
1254 |
+
"loss": 0.7828,
|
1255 |
+
"step": 890
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 1.5442683058341422,
|
1259 |
+
"grad_norm": 3.1645920276641846,
|
1260 |
+
"learning_rate": 1e-05,
|
1261 |
+
"loss": 0.8359,
|
1262 |
+
"step": 895
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 1.552895503073439,
|
1266 |
+
"grad_norm": 4.218339443206787,
|
1267 |
+
"learning_rate": 1e-05,
|
1268 |
+
"loss": 0.8226,
|
1269 |
+
"step": 900
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.5615227003127359,
|
1273 |
+
"grad_norm": 3.5735368728637695,
|
1274 |
+
"learning_rate": 1e-05,
|
1275 |
+
"loss": 0.8219,
|
1276 |
+
"step": 905
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 1.570149897552033,
|
1280 |
+
"grad_norm": 3.3347320556640625,
|
1281 |
+
"learning_rate": 1e-05,
|
1282 |
+
"loss": 0.8212,
|
1283 |
+
"step": 910
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 1.5787770947913295,
|
1287 |
+
"grad_norm": 3.6230201721191406,
|
1288 |
+
"learning_rate": 1e-05,
|
1289 |
+
"loss": 0.8036,
|
1290 |
+
"step": 915
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 1.5874042920306266,
|
1294 |
+
"grad_norm": 3.4478774070739746,
|
1295 |
+
"learning_rate": 1e-05,
|
1296 |
+
"loss": 0.7633,
|
1297 |
+
"step": 920
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 1.5960314892699234,
|
1301 |
+
"grad_norm": 3.934248924255371,
|
1302 |
+
"learning_rate": 1e-05,
|
1303 |
+
"loss": 0.7673,
|
1304 |
+
"step": 925
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 1.6046586865092203,
|
1308 |
+
"grad_norm": 3.3679585456848145,
|
1309 |
+
"learning_rate": 1e-05,
|
1310 |
+
"loss": 0.7732,
|
1311 |
+
"step": 930
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 1.6132858837485173,
|
1315 |
+
"grad_norm": 3.6777756214141846,
|
1316 |
+
"learning_rate": 1e-05,
|
1317 |
+
"loss": 0.7941,
|
1318 |
+
"step": 935
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 1.621913080987814,
|
1322 |
+
"grad_norm": 3.4815165996551514,
|
1323 |
+
"learning_rate": 1e-05,
|
1324 |
+
"loss": 0.8184,
|
1325 |
+
"step": 940
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 1.630540278227111,
|
1329 |
+
"grad_norm": 3.4345767498016357,
|
1330 |
+
"learning_rate": 1e-05,
|
1331 |
+
"loss": 0.8496,
|
1332 |
+
"step": 945
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 1.6391674754664078,
|
1336 |
+
"grad_norm": 3.3284542560577393,
|
1337 |
+
"learning_rate": 1e-05,
|
1338 |
+
"loss": 0.888,
|
1339 |
+
"step": 950
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 1.6477946727057047,
|
1343 |
+
"grad_norm": 3.9973185062408447,
|
1344 |
+
"learning_rate": 1e-05,
|
1345 |
+
"loss": 0.8551,
|
1346 |
+
"step": 955
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 1.6564218699450017,
|
1350 |
+
"grad_norm": 3.136579751968384,
|
1351 |
+
"learning_rate": 1e-05,
|
1352 |
+
"loss": 0.8184,
|
1353 |
+
"step": 960
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 1.6650490671842983,
|
1357 |
+
"grad_norm": 3.745621919631958,
|
1358 |
+
"learning_rate": 1e-05,
|
1359 |
+
"loss": 0.8045,
|
1360 |
+
"step": 965
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 1.6736762644235954,
|
1364 |
+
"grad_norm": 3.2420082092285156,
|
1365 |
+
"learning_rate": 1e-05,
|
1366 |
+
"loss": 0.7489,
|
1367 |
+
"step": 970
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 1.6823034616628922,
|
1371 |
+
"grad_norm": 3.52974009513855,
|
1372 |
+
"learning_rate": 1e-05,
|
1373 |
+
"loss": 0.7816,
|
1374 |
+
"step": 975
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 1.690930658902189,
|
1378 |
+
"grad_norm": 3.9357786178588867,
|
1379 |
+
"learning_rate": 1e-05,
|
1380 |
+
"loss": 0.884,
|
1381 |
+
"step": 980
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 1.6995578561414861,
|
1385 |
+
"grad_norm": 3.807739734649658,
|
1386 |
+
"learning_rate": 1e-05,
|
1387 |
+
"loss": 0.9077,
|
1388 |
+
"step": 985
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 1.708185053380783,
|
1392 |
+
"grad_norm": 3.0585408210754395,
|
1393 |
+
"learning_rate": 1e-05,
|
1394 |
+
"loss": 0.8371,
|
1395 |
+
"step": 990
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 1.7168122506200798,
|
1399 |
+
"grad_norm": 3.0159707069396973,
|
1400 |
+
"learning_rate": 1e-05,
|
1401 |
+
"loss": 0.8028,
|
1402 |
+
"step": 995
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 1.7254394478593766,
|
1406 |
+
"grad_norm": 3.9987428188323975,
|
1407 |
+
"learning_rate": 1e-05,
|
1408 |
+
"loss": 0.7969,
|
1409 |
+
"step": 1000
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 1.7340666450986735,
|
1413 |
+
"grad_norm": 3.4167709350585938,
|
1414 |
+
"learning_rate": 1e-05,
|
1415 |
+
"loss": 0.8557,
|
1416 |
+
"step": 1005
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 1.7426938423379705,
|
1420 |
+
"grad_norm": 3.235368251800537,
|
1421 |
+
"learning_rate": 1e-05,
|
1422 |
+
"loss": 0.7524,
|
1423 |
+
"step": 1010
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 1.7513210395772674,
|
1427 |
+
"grad_norm": 3.3228580951690674,
|
1428 |
+
"learning_rate": 1e-05,
|
1429 |
+
"loss": 0.8103,
|
1430 |
+
"step": 1015
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 1.7599482368165642,
|
1434 |
+
"grad_norm": 3.2793571949005127,
|
1435 |
+
"learning_rate": 1e-05,
|
1436 |
+
"loss": 0.7795,
|
1437 |
+
"step": 1020
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 1.7685754340558613,
|
1441 |
+
"grad_norm": 3.4918506145477295,
|
1442 |
+
"learning_rate": 1e-05,
|
1443 |
+
"loss": 0.8534,
|
1444 |
+
"step": 1025
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 1.7772026312951579,
|
1448 |
+
"grad_norm": 3.5630784034729004,
|
1449 |
+
"learning_rate": 1e-05,
|
1450 |
+
"loss": 0.8371,
|
1451 |
+
"step": 1030
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 1.785829828534455,
|
1455 |
+
"grad_norm": 3.330843210220337,
|
1456 |
+
"learning_rate": 1e-05,
|
1457 |
+
"loss": 0.7688,
|
1458 |
+
"step": 1035
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 1.7944570257737518,
|
1462 |
+
"grad_norm": 3.340770721435547,
|
1463 |
+
"learning_rate": 1e-05,
|
1464 |
+
"loss": 0.7823,
|
1465 |
+
"step": 1040
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 1.8030842230130486,
|
1469 |
+
"grad_norm": 3.48885440826416,
|
1470 |
+
"learning_rate": 1e-05,
|
1471 |
+
"loss": 0.8135,
|
1472 |
+
"step": 1045
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 1.8117114202523457,
|
1476 |
+
"grad_norm": 3.783395528793335,
|
1477 |
+
"learning_rate": 1e-05,
|
1478 |
+
"loss": 0.8169,
|
1479 |
+
"step": 1050
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 1.8203386174916423,
|
1483 |
+
"grad_norm": 3.1166722774505615,
|
1484 |
+
"learning_rate": 1e-05,
|
1485 |
+
"loss": 0.846,
|
1486 |
+
"step": 1055
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 1.8289658147309393,
|
1490 |
+
"grad_norm": 3.627532720565796,
|
1491 |
+
"learning_rate": 1e-05,
|
1492 |
+
"loss": 0.8055,
|
1493 |
+
"step": 1060
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 1.8375930119702362,
|
1497 |
+
"grad_norm": 3.264894723892212,
|
1498 |
+
"learning_rate": 1e-05,
|
1499 |
+
"loss": 0.8216,
|
1500 |
+
"step": 1065
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 1.846220209209533,
|
1504 |
+
"grad_norm": 3.652085781097412,
|
1505 |
+
"learning_rate": 1e-05,
|
1506 |
+
"loss": 0.8663,
|
1507 |
+
"step": 1070
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 1.85484740644883,
|
1511 |
+
"grad_norm": 3.269554376602173,
|
1512 |
+
"learning_rate": 1e-05,
|
1513 |
+
"loss": 0.8332,
|
1514 |
+
"step": 1075
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 1.8634746036881267,
|
1518 |
+
"grad_norm": 3.3206093311309814,
|
1519 |
+
"learning_rate": 1e-05,
|
1520 |
+
"loss": 0.8408,
|
1521 |
+
"step": 1080
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 1.8721018009274237,
|
1525 |
+
"grad_norm": 4.427550792694092,
|
1526 |
+
"learning_rate": 1e-05,
|
1527 |
+
"loss": 0.828,
|
1528 |
+
"step": 1085
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 1.8807289981667206,
|
1532 |
+
"grad_norm": 3.235623359680176,
|
1533 |
+
"learning_rate": 1e-05,
|
1534 |
+
"loss": 0.8127,
|
1535 |
+
"step": 1090
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 1.8893561954060174,
|
1539 |
+
"grad_norm": 3.4541192054748535,
|
1540 |
+
"learning_rate": 1e-05,
|
1541 |
+
"loss": 0.8607,
|
1542 |
+
"step": 1095
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 1.8979833926453145,
|
1546 |
+
"grad_norm": 3.4523119926452637,
|
1547 |
+
"learning_rate": 1e-05,
|
1548 |
+
"loss": 0.9251,
|
1549 |
+
"step": 1100
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 1.906610589884611,
|
1553 |
+
"grad_norm": 3.4309825897216797,
|
1554 |
+
"learning_rate": 1e-05,
|
1555 |
+
"loss": 0.8388,
|
1556 |
+
"step": 1105
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 1.9152377871239081,
|
1560 |
+
"grad_norm": 3.8286280632019043,
|
1561 |
+
"learning_rate": 1e-05,
|
1562 |
+
"loss": 0.8036,
|
1563 |
+
"step": 1110
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 1.923864984363205,
|
1567 |
+
"grad_norm": 3.4782304763793945,
|
1568 |
+
"learning_rate": 1e-05,
|
1569 |
+
"loss": 0.8001,
|
1570 |
+
"step": 1115
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 1.9324921816025018,
|
1574 |
+
"grad_norm": 3.265873432159424,
|
1575 |
+
"learning_rate": 1e-05,
|
1576 |
+
"loss": 0.775,
|
1577 |
+
"step": 1120
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 1.9411193788417989,
|
1581 |
+
"grad_norm": 3.65558123588562,
|
1582 |
+
"learning_rate": 1e-05,
|
1583 |
+
"loss": 0.8639,
|
1584 |
+
"step": 1125
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 1.9497465760810957,
|
1588 |
+
"grad_norm": 3.7924466133117676,
|
1589 |
+
"learning_rate": 1e-05,
|
1590 |
+
"loss": 0.8513,
|
1591 |
+
"step": 1130
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 1.9583737733203925,
|
1595 |
+
"grad_norm": 3.99310564994812,
|
1596 |
+
"learning_rate": 1e-05,
|
1597 |
+
"loss": 0.77,
|
1598 |
+
"step": 1135
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 1.9670009705596894,
|
1602 |
+
"grad_norm": 3.121508836746216,
|
1603 |
+
"learning_rate": 1e-05,
|
1604 |
+
"loss": 0.732,
|
1605 |
+
"step": 1140
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 1.9756281677989862,
|
1609 |
+
"grad_norm": 3.812880277633667,
|
1610 |
+
"learning_rate": 1e-05,
|
1611 |
+
"loss": 0.8029,
|
1612 |
+
"step": 1145
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 1.9842553650382833,
|
1616 |
+
"grad_norm": 3.398724317550659,
|
1617 |
+
"learning_rate": 1e-05,
|
1618 |
+
"loss": 0.8205,
|
1619 |
+
"step": 1150
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 1.99288256227758,
|
1623 |
+
"grad_norm": 3.3330962657928467,
|
1624 |
+
"learning_rate": 1e-05,
|
1625 |
+
"loss": 0.7995,
|
1626 |
+
"step": 1155
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 2.001509759516877,
|
1630 |
+
"grad_norm": 4.028820991516113,
|
1631 |
+
"learning_rate": 1e-05,
|
1632 |
+
"loss": 0.7343,
|
1633 |
+
"step": 1160
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 2.010136956756174,
|
1637 |
+
"grad_norm": 4.329206943511963,
|
1638 |
+
"learning_rate": 1e-05,
|
1639 |
+
"loss": 0.4413,
|
1640 |
+
"step": 1165
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 2.0187641539954706,
|
1644 |
+
"grad_norm": 7.581143379211426,
|
1645 |
+
"learning_rate": 1e-05,
|
1646 |
+
"loss": 0.4171,
|
1647 |
+
"step": 1170
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 2.0273913512347677,
|
1651 |
+
"grad_norm": 3.6165997982025146,
|
1652 |
+
"learning_rate": 1e-05,
|
1653 |
+
"loss": 0.3829,
|
1654 |
+
"step": 1175
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 2.0360185484740643,
|
1658 |
+
"grad_norm": 3.6805825233459473,
|
1659 |
+
"learning_rate": 1e-05,
|
1660 |
+
"loss": 0.3505,
|
1661 |
+
"step": 1180
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 2.0446457457133613,
|
1665 |
+
"grad_norm": 3.5917325019836426,
|
1666 |
+
"learning_rate": 1e-05,
|
1667 |
+
"loss": 0.3448,
|
1668 |
+
"step": 1185
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 2.0532729429526584,
|
1672 |
+
"grad_norm": 4.101263046264648,
|
1673 |
+
"learning_rate": 1e-05,
|
1674 |
+
"loss": 0.3737,
|
1675 |
+
"step": 1190
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 2.061900140191955,
|
1679 |
+
"grad_norm": 4.450289726257324,
|
1680 |
+
"learning_rate": 1e-05,
|
1681 |
+
"loss": 0.3939,
|
1682 |
+
"step": 1195
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 2.070527337431252,
|
1686 |
+
"grad_norm": 3.6648216247558594,
|
1687 |
+
"learning_rate": 1e-05,
|
1688 |
+
"loss": 0.3638,
|
1689 |
+
"step": 1200
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 2.079154534670549,
|
1693 |
+
"grad_norm": 4.237855434417725,
|
1694 |
+
"learning_rate": 1e-05,
|
1695 |
+
"loss": 0.3634,
|
1696 |
+
"step": 1205
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 2.0877817319098457,
|
1700 |
+
"grad_norm": 4.677015781402588,
|
1701 |
+
"learning_rate": 1e-05,
|
1702 |
+
"loss": 0.4462,
|
1703 |
+
"step": 1210
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 2.096408929149143,
|
1707 |
+
"grad_norm": 3.543541431427002,
|
1708 |
+
"learning_rate": 1e-05,
|
1709 |
+
"loss": 0.4071,
|
1710 |
+
"step": 1215
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 2.1050361263884394,
|
1714 |
+
"grad_norm": 4.441009521484375,
|
1715 |
+
"learning_rate": 1e-05,
|
1716 |
+
"loss": 0.3735,
|
1717 |
+
"step": 1220
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 2.1136633236277365,
|
1721 |
+
"grad_norm": 3.5603976249694824,
|
1722 |
+
"learning_rate": 1e-05,
|
1723 |
+
"loss": 0.383,
|
1724 |
+
"step": 1225
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 2.1222905208670335,
|
1728 |
+
"grad_norm": 3.347618579864502,
|
1729 |
+
"learning_rate": 1e-05,
|
1730 |
+
"loss": 0.3077,
|
1731 |
+
"step": 1230
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 2.13091771810633,
|
1735 |
+
"grad_norm": 3.57377028465271,
|
1736 |
+
"learning_rate": 1e-05,
|
1737 |
+
"loss": 0.3774,
|
1738 |
+
"step": 1235
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 2.139544915345627,
|
1742 |
+
"grad_norm": 3.4287397861480713,
|
1743 |
+
"learning_rate": 1e-05,
|
1744 |
+
"loss": 0.3388,
|
1745 |
+
"step": 1240
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 2.148172112584924,
|
1749 |
+
"grad_norm": 3.9330341815948486,
|
1750 |
+
"learning_rate": 1e-05,
|
1751 |
+
"loss": 0.3848,
|
1752 |
+
"step": 1245
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 2.156799309824221,
|
1756 |
+
"grad_norm": 3.7925400733947754,
|
1757 |
+
"learning_rate": 1e-05,
|
1758 |
+
"loss": 0.4173,
|
1759 |
+
"step": 1250
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 2.165426507063518,
|
1763 |
+
"grad_norm": 3.818533420562744,
|
1764 |
+
"learning_rate": 1e-05,
|
1765 |
+
"loss": 0.3514,
|
1766 |
+
"step": 1255
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 2.1740537043028145,
|
1770 |
+
"grad_norm": 4.525712013244629,
|
1771 |
+
"learning_rate": 1e-05,
|
1772 |
+
"loss": 0.393,
|
1773 |
+
"step": 1260
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 2.1826809015421116,
|
1777 |
+
"grad_norm": 3.9103636741638184,
|
1778 |
+
"learning_rate": 1e-05,
|
1779 |
+
"loss": 0.3886,
|
1780 |
+
"step": 1265
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 2.191308098781408,
|
1784 |
+
"grad_norm": 4.36718225479126,
|
1785 |
+
"learning_rate": 1e-05,
|
1786 |
+
"loss": 0.3943,
|
1787 |
+
"step": 1270
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 2.1999352960207053,
|
1791 |
+
"grad_norm": 4.249504566192627,
|
1792 |
+
"learning_rate": 1e-05,
|
1793 |
+
"loss": 0.3562,
|
1794 |
+
"step": 1275
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 2.2085624932600023,
|
1798 |
+
"grad_norm": 3.6772570610046387,
|
1799 |
+
"learning_rate": 1e-05,
|
1800 |
+
"loss": 0.3609,
|
1801 |
+
"step": 1280
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 2.217189690499299,
|
1805 |
+
"grad_norm": 4.188706398010254,
|
1806 |
+
"learning_rate": 1e-05,
|
1807 |
+
"loss": 0.4031,
|
1808 |
+
"step": 1285
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 2.225816887738596,
|
1812 |
+
"grad_norm": 4.41935920715332,
|
1813 |
+
"learning_rate": 1e-05,
|
1814 |
+
"loss": 0.3989,
|
1815 |
+
"step": 1290
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 2.234444084977893,
|
1819 |
+
"grad_norm": 3.972947359085083,
|
1820 |
+
"learning_rate": 1e-05,
|
1821 |
+
"loss": 0.4016,
|
1822 |
+
"step": 1295
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 2.2430712822171897,
|
1826 |
+
"grad_norm": 3.753408193588257,
|
1827 |
+
"learning_rate": 1e-05,
|
1828 |
+
"loss": 0.3735,
|
1829 |
+
"step": 1300
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 2.2516984794564867,
|
1833 |
+
"grad_norm": 3.882584810256958,
|
1834 |
+
"learning_rate": 1e-05,
|
1835 |
+
"loss": 0.376,
|
1836 |
+
"step": 1305
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 2.2603256766957833,
|
1840 |
+
"grad_norm": 3.9297213554382324,
|
1841 |
+
"learning_rate": 1e-05,
|
1842 |
+
"loss": 0.4118,
|
1843 |
+
"step": 1310
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 2.2689528739350804,
|
1847 |
+
"grad_norm": 4.477977752685547,
|
1848 |
+
"learning_rate": 1e-05,
|
1849 |
+
"loss": 0.4483,
|
1850 |
+
"step": 1315
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 2.277580071174377,
|
1854 |
+
"grad_norm": 4.420772552490234,
|
1855 |
+
"learning_rate": 1e-05,
|
1856 |
+
"loss": 0.3646,
|
1857 |
+
"step": 1320
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 2.286207268413674,
|
1861 |
+
"grad_norm": 4.0902276039123535,
|
1862 |
+
"learning_rate": 1e-05,
|
1863 |
+
"loss": 0.3901,
|
1864 |
+
"step": 1325
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 2.294834465652971,
|
1868 |
+
"grad_norm": 3.598499298095703,
|
1869 |
+
"learning_rate": 1e-05,
|
1870 |
+
"loss": 0.3684,
|
1871 |
+
"step": 1330
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 2.3034616628922677,
|
1875 |
+
"grad_norm": 3.4670894145965576,
|
1876 |
+
"learning_rate": 1e-05,
|
1877 |
+
"loss": 0.3885,
|
1878 |
+
"step": 1335
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 2.312088860131565,
|
1882 |
+
"grad_norm": 4.802315711975098,
|
1883 |
+
"learning_rate": 1e-05,
|
1884 |
+
"loss": 0.424,
|
1885 |
+
"step": 1340
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 2.320716057370862,
|
1889 |
+
"grad_norm": 4.187905788421631,
|
1890 |
+
"learning_rate": 1e-05,
|
1891 |
+
"loss": 0.4194,
|
1892 |
+
"step": 1345
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 2.3293432546101585,
|
1896 |
+
"grad_norm": 3.7030727863311768,
|
1897 |
+
"learning_rate": 1e-05,
|
1898 |
+
"loss": 0.3982,
|
1899 |
+
"step": 1350
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 2.3379704518494555,
|
1903 |
+
"grad_norm": 4.434927463531494,
|
1904 |
+
"learning_rate": 1e-05,
|
1905 |
+
"loss": 0.4565,
|
1906 |
+
"step": 1355
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 2.346597649088752,
|
1910 |
+
"grad_norm": 4.65302038192749,
|
1911 |
+
"learning_rate": 1e-05,
|
1912 |
+
"loss": 0.3995,
|
1913 |
+
"step": 1360
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 2.355224846328049,
|
1917 |
+
"grad_norm": 4.085888862609863,
|
1918 |
+
"learning_rate": 1e-05,
|
1919 |
+
"loss": 0.426,
|
1920 |
+
"step": 1365
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 2.3638520435673462,
|
1924 |
+
"grad_norm": 4.577415466308594,
|
1925 |
+
"learning_rate": 1e-05,
|
1926 |
+
"loss": 0.3854,
|
1927 |
+
"step": 1370
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 2.372479240806643,
|
1931 |
+
"grad_norm": 4.255492210388184,
|
1932 |
+
"learning_rate": 1e-05,
|
1933 |
+
"loss": 0.3808,
|
1934 |
+
"step": 1375
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 2.38110643804594,
|
1938 |
+
"grad_norm": 3.9601423740386963,
|
1939 |
+
"learning_rate": 1e-05,
|
1940 |
+
"loss": 0.3598,
|
1941 |
+
"step": 1380
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 2.3897336352852365,
|
1945 |
+
"grad_norm": 3.984498977661133,
|
1946 |
+
"learning_rate": 1e-05,
|
1947 |
+
"loss": 0.4018,
|
1948 |
+
"step": 1385
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 2.3983608325245336,
|
1952 |
+
"grad_norm": 4.054710388183594,
|
1953 |
+
"learning_rate": 1e-05,
|
1954 |
+
"loss": 0.4105,
|
1955 |
+
"step": 1390
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 2.4069880297638306,
|
1959 |
+
"grad_norm": 3.6106574535369873,
|
1960 |
+
"learning_rate": 1e-05,
|
1961 |
+
"loss": 0.3832,
|
1962 |
+
"step": 1395
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 2.4156152270031273,
|
1966 |
+
"grad_norm": 3.7792673110961914,
|
1967 |
+
"learning_rate": 1e-05,
|
1968 |
+
"loss": 0.4288,
|
1969 |
+
"step": 1400
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 2.4242424242424243,
|
1973 |
+
"grad_norm": 4.984143257141113,
|
1974 |
+
"learning_rate": 1e-05,
|
1975 |
+
"loss": 0.3759,
|
1976 |
+
"step": 1405
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 2.4328696214817214,
|
1980 |
+
"grad_norm": 4.424108028411865,
|
1981 |
+
"learning_rate": 1e-05,
|
1982 |
+
"loss": 0.3981,
|
1983 |
+
"step": 1410
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 2.441496818721018,
|
1987 |
+
"grad_norm": 3.914560079574585,
|
1988 |
+
"learning_rate": 1e-05,
|
1989 |
+
"loss": 0.3461,
|
1990 |
+
"step": 1415
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"epoch": 2.450124015960315,
|
1994 |
+
"grad_norm": 3.667935848236084,
|
1995 |
+
"learning_rate": 1e-05,
|
1996 |
+
"loss": 0.3898,
|
1997 |
+
"step": 1420
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 2.4587512131996117,
|
2001 |
+
"grad_norm": 3.2983341217041016,
|
2002 |
+
"learning_rate": 1e-05,
|
2003 |
+
"loss": 0.36,
|
2004 |
+
"step": 1425
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 2.4673784104389087,
|
2008 |
+
"grad_norm": 5.143230438232422,
|
2009 |
+
"learning_rate": 1e-05,
|
2010 |
+
"loss": 0.4348,
|
2011 |
+
"step": 1430
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 2.4760056076782053,
|
2015 |
+
"grad_norm": 3.818688154220581,
|
2016 |
+
"learning_rate": 1e-05,
|
2017 |
+
"loss": 0.3582,
|
2018 |
+
"step": 1435
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 2.4846328049175024,
|
2022 |
+
"grad_norm": 4.086068153381348,
|
2023 |
+
"learning_rate": 1e-05,
|
2024 |
+
"loss": 0.4337,
|
2025 |
+
"step": 1440
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 2.4932600021567994,
|
2029 |
+
"grad_norm": 3.717658281326294,
|
2030 |
+
"learning_rate": 1e-05,
|
2031 |
+
"loss": 0.4196,
|
2032 |
+
"step": 1445
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 2.501887199396096,
|
2036 |
+
"grad_norm": 3.619304895401001,
|
2037 |
+
"learning_rate": 1e-05,
|
2038 |
+
"loss": 0.3901,
|
2039 |
+
"step": 1450
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 2.510514396635393,
|
2043 |
+
"grad_norm": 4.011234283447266,
|
2044 |
+
"learning_rate": 1e-05,
|
2045 |
+
"loss": 0.3864,
|
2046 |
+
"step": 1455
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 2.51914159387469,
|
2050 |
+
"grad_norm": 3.993927478790283,
|
2051 |
+
"learning_rate": 1e-05,
|
2052 |
+
"loss": 0.3911,
|
2053 |
+
"step": 1460
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 2.527768791113987,
|
2057 |
+
"grad_norm": 4.390587329864502,
|
2058 |
+
"learning_rate": 1e-05,
|
2059 |
+
"loss": 0.4008,
|
2060 |
+
"step": 1465
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 2.536395988353284,
|
2064 |
+
"grad_norm": 4.767730236053467,
|
2065 |
+
"learning_rate": 1e-05,
|
2066 |
+
"loss": 0.3738,
|
2067 |
+
"step": 1470
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 2.5450231855925805,
|
2071 |
+
"grad_norm": 3.377415180206299,
|
2072 |
+
"learning_rate": 1e-05,
|
2073 |
+
"loss": 0.3892,
|
2074 |
+
"step": 1475
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 2.5536503828318775,
|
2078 |
+
"grad_norm": 3.5132322311401367,
|
2079 |
+
"learning_rate": 1e-05,
|
2080 |
+
"loss": 0.4022,
|
2081 |
+
"step": 1480
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 2.562277580071174,
|
2085 |
+
"grad_norm": 3.9030888080596924,
|
2086 |
+
"learning_rate": 1e-05,
|
2087 |
+
"loss": 0.436,
|
2088 |
+
"step": 1485
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 2.570904777310471,
|
2092 |
+
"grad_norm": 3.88025164604187,
|
2093 |
+
"learning_rate": 1e-05,
|
2094 |
+
"loss": 0.4164,
|
2095 |
+
"step": 1490
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 2.5795319745497682,
|
2099 |
+
"grad_norm": 4.036890983581543,
|
2100 |
+
"learning_rate": 1e-05,
|
2101 |
+
"loss": 0.3914,
|
2102 |
+
"step": 1495
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 2.588159171789065,
|
2106 |
+
"grad_norm": 3.56758189201355,
|
2107 |
+
"learning_rate": 1e-05,
|
2108 |
+
"loss": 0.3878,
|
2109 |
+
"step": 1500
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 2.596786369028362,
|
2113 |
+
"grad_norm": 3.9577293395996094,
|
2114 |
+
"learning_rate": 1e-05,
|
2115 |
+
"loss": 0.39,
|
2116 |
+
"step": 1505
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 2.605413566267659,
|
2120 |
+
"grad_norm": 4.392646312713623,
|
2121 |
+
"learning_rate": 1e-05,
|
2122 |
+
"loss": 0.3989,
|
2123 |
+
"step": 1510
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 2.6140407635069556,
|
2127 |
+
"grad_norm": 4.026916027069092,
|
2128 |
+
"learning_rate": 1e-05,
|
2129 |
+
"loss": 0.3613,
|
2130 |
+
"step": 1515
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 2.6226679607462526,
|
2134 |
+
"grad_norm": 4.357356548309326,
|
2135 |
+
"learning_rate": 1e-05,
|
2136 |
+
"loss": 0.3995,
|
2137 |
+
"step": 1520
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 2.6312951579855497,
|
2141 |
+
"grad_norm": 3.703214406967163,
|
2142 |
+
"learning_rate": 1e-05,
|
2143 |
+
"loss": 0.3376,
|
2144 |
+
"step": 1525
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 2.6399223552248463,
|
2148 |
+
"grad_norm": 3.8401548862457275,
|
2149 |
+
"learning_rate": 1e-05,
|
2150 |
+
"loss": 0.3861,
|
2151 |
+
"step": 1530
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 2.6485495524641434,
|
2155 |
+
"grad_norm": 3.7734174728393555,
|
2156 |
+
"learning_rate": 1e-05,
|
2157 |
+
"loss": 0.4193,
|
2158 |
+
"step": 1535
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 2.65717674970344,
|
2162 |
+
"grad_norm": 3.929262161254883,
|
2163 |
+
"learning_rate": 1e-05,
|
2164 |
+
"loss": 0.4235,
|
2165 |
+
"step": 1540
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 2.665803946942737,
|
2169 |
+
"grad_norm": 4.2804975509643555,
|
2170 |
+
"learning_rate": 1e-05,
|
2171 |
+
"loss": 0.39,
|
2172 |
+
"step": 1545
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 2.6744311441820336,
|
2176 |
+
"grad_norm": 4.476975440979004,
|
2177 |
+
"learning_rate": 1e-05,
|
2178 |
+
"loss": 0.4395,
|
2179 |
+
"step": 1550
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 2.6830583414213307,
|
2183 |
+
"grad_norm": 3.710632562637329,
|
2184 |
+
"learning_rate": 1e-05,
|
2185 |
+
"loss": 0.3956,
|
2186 |
+
"step": 1555
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 2.6916855386606278,
|
2190 |
+
"grad_norm": 5.090831756591797,
|
2191 |
+
"learning_rate": 1e-05,
|
2192 |
+
"loss": 0.4399,
|
2193 |
+
"step": 1560
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 2.7003127358999244,
|
2197 |
+
"grad_norm": 4.323583602905273,
|
2198 |
+
"learning_rate": 1e-05,
|
2199 |
+
"loss": 0.4161,
|
2200 |
+
"step": 1565
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 2.7089399331392214,
|
2204 |
+
"grad_norm": 4.236275672912598,
|
2205 |
+
"learning_rate": 1e-05,
|
2206 |
+
"loss": 0.4128,
|
2207 |
+
"step": 1570
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 2.7175671303785185,
|
2211 |
+
"grad_norm": 4.034735202789307,
|
2212 |
+
"learning_rate": 1e-05,
|
2213 |
+
"loss": 0.4291,
|
2214 |
+
"step": 1575
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 2.726194327617815,
|
2218 |
+
"grad_norm": 4.452931880950928,
|
2219 |
+
"learning_rate": 1e-05,
|
2220 |
+
"loss": 0.4198,
|
2221 |
+
"step": 1580
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 2.734821524857112,
|
2225 |
+
"grad_norm": 3.9385485649108887,
|
2226 |
+
"learning_rate": 1e-05,
|
2227 |
+
"loss": 0.3954,
|
2228 |
+
"step": 1585
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 2.7434487220964088,
|
2232 |
+
"grad_norm": 3.8436594009399414,
|
2233 |
+
"learning_rate": 1e-05,
|
2234 |
+
"loss": 0.3718,
|
2235 |
+
"step": 1590
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 2.752075919335706,
|
2239 |
+
"grad_norm": 3.962069272994995,
|
2240 |
+
"learning_rate": 1e-05,
|
2241 |
+
"loss": 0.3488,
|
2242 |
+
"step": 1595
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 2.7607031165750024,
|
2246 |
+
"grad_norm": 4.306760787963867,
|
2247 |
+
"learning_rate": 1e-05,
|
2248 |
+
"loss": 0.4581,
|
2249 |
+
"step": 1600
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 2.7693303138142995,
|
2253 |
+
"grad_norm": 4.657399654388428,
|
2254 |
+
"learning_rate": 1e-05,
|
2255 |
+
"loss": 0.4455,
|
2256 |
+
"step": 1605
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 2.7779575110535966,
|
2260 |
+
"grad_norm": 4.039801120758057,
|
2261 |
+
"learning_rate": 1e-05,
|
2262 |
+
"loss": 0.3918,
|
2263 |
+
"step": 1610
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 2.786584708292893,
|
2267 |
+
"grad_norm": 5.203350067138672,
|
2268 |
+
"learning_rate": 1e-05,
|
2269 |
+
"loss": 0.4067,
|
2270 |
+
"step": 1615
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 2.7952119055321902,
|
2274 |
+
"grad_norm": 3.9145352840423584,
|
2275 |
+
"learning_rate": 1e-05,
|
2276 |
+
"loss": 0.4237,
|
2277 |
+
"step": 1620
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 2.8038391027714873,
|
2281 |
+
"grad_norm": 3.5493838787078857,
|
2282 |
+
"learning_rate": 1e-05,
|
2283 |
+
"loss": 0.3939,
|
2284 |
+
"step": 1625
|
2285 |
+
},
|
2286 |
+
{
|
2287 |
+
"epoch": 2.812466300010784,
|
2288 |
+
"grad_norm": 4.310389995574951,
|
2289 |
+
"learning_rate": 1e-05,
|
2290 |
+
"loss": 0.4385,
|
2291 |
+
"step": 1630
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 2.821093497250081,
|
2295 |
+
"grad_norm": 5.43610954284668,
|
2296 |
+
"learning_rate": 1e-05,
|
2297 |
+
"loss": 0.4109,
|
2298 |
+
"step": 1635
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 2.829720694489378,
|
2302 |
+
"grad_norm": 4.191155433654785,
|
2303 |
+
"learning_rate": 1e-05,
|
2304 |
+
"loss": 0.4402,
|
2305 |
+
"step": 1640
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 2.8383478917286746,
|
2309 |
+
"grad_norm": 3.9996650218963623,
|
2310 |
+
"learning_rate": 1e-05,
|
2311 |
+
"loss": 0.444,
|
2312 |
+
"step": 1645
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 2.8469750889679717,
|
2316 |
+
"grad_norm": 10.163007736206055,
|
2317 |
+
"learning_rate": 1e-05,
|
2318 |
+
"loss": 0.413,
|
2319 |
+
"step": 1650
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 2.8556022862072683,
|
2323 |
+
"grad_norm": 3.8168654441833496,
|
2324 |
+
"learning_rate": 1e-05,
|
2325 |
+
"loss": 0.4245,
|
2326 |
+
"step": 1655
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 2.8642294834465654,
|
2330 |
+
"grad_norm": 3.9268579483032227,
|
2331 |
+
"learning_rate": 1e-05,
|
2332 |
+
"loss": 0.4091,
|
2333 |
+
"step": 1660
|
2334 |
+
},
|
2335 |
+
{
|
2336 |
+
"epoch": 2.872856680685862,
|
2337 |
+
"grad_norm": 4.146000385284424,
|
2338 |
+
"learning_rate": 1e-05,
|
2339 |
+
"loss": 0.4206,
|
2340 |
+
"step": 1665
|
2341 |
+
},
|
2342 |
+
{
|
2343 |
+
"epoch": 2.881483877925159,
|
2344 |
+
"grad_norm": 4.102123260498047,
|
2345 |
+
"learning_rate": 1e-05,
|
2346 |
+
"loss": 0.3868,
|
2347 |
+
"step": 1670
|
2348 |
+
},
|
2349 |
+
{
|
2350 |
+
"epoch": 2.890111075164456,
|
2351 |
+
"grad_norm": 4.318619728088379,
|
2352 |
+
"learning_rate": 1e-05,
|
2353 |
+
"loss": 0.4102,
|
2354 |
+
"step": 1675
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 2.8987382724037527,
|
2358 |
+
"grad_norm": 4.203400611877441,
|
2359 |
+
"learning_rate": 1e-05,
|
2360 |
+
"loss": 0.4349,
|
2361 |
+
"step": 1680
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 2.9073654696430498,
|
2365 |
+
"grad_norm": 4.164772987365723,
|
2366 |
+
"learning_rate": 1e-05,
|
2367 |
+
"loss": 0.4298,
|
2368 |
+
"step": 1685
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 2.915992666882347,
|
2372 |
+
"grad_norm": 4.088376998901367,
|
2373 |
+
"learning_rate": 1e-05,
|
2374 |
+
"loss": 0.431,
|
2375 |
+
"step": 1690
|
2376 |
+
},
|
2377 |
+
{
|
2378 |
+
"epoch": 2.9246198641216434,
|
2379 |
+
"grad_norm": 4.593983173370361,
|
2380 |
+
"learning_rate": 1e-05,
|
2381 |
+
"loss": 0.4373,
|
2382 |
+
"step": 1695
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"epoch": 2.9332470613609405,
|
2386 |
+
"grad_norm": 4.246501445770264,
|
2387 |
+
"learning_rate": 1e-05,
|
2388 |
+
"loss": 0.4239,
|
2389 |
+
"step": 1700
|
2390 |
+
},
|
2391 |
+
{
|
2392 |
+
"epoch": 2.941874258600237,
|
2393 |
+
"grad_norm": 3.8412177562713623,
|
2394 |
+
"learning_rate": 1e-05,
|
2395 |
+
"loss": 0.4277,
|
2396 |
+
"step": 1705
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 2.950501455839534,
|
2400 |
+
"grad_norm": 3.7681996822357178,
|
2401 |
+
"learning_rate": 1e-05,
|
2402 |
+
"loss": 0.4302,
|
2403 |
+
"step": 1710
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 2.9591286530788308,
|
2407 |
+
"grad_norm": 4.009012699127197,
|
2408 |
+
"learning_rate": 1e-05,
|
2409 |
+
"loss": 0.3822,
|
2410 |
+
"step": 1715
|
2411 |
+
},
|
2412 |
+
{
|
2413 |
+
"epoch": 2.967755850318128,
|
2414 |
+
"grad_norm": 4.4853434562683105,
|
2415 |
+
"learning_rate": 1e-05,
|
2416 |
+
"loss": 0.4402,
|
2417 |
+
"step": 1720
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 2.976383047557425,
|
2421 |
+
"grad_norm": 3.743802785873413,
|
2422 |
+
"learning_rate": 1e-05,
|
2423 |
+
"loss": 0.3803,
|
2424 |
+
"step": 1725
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 2.9850102447967215,
|
2428 |
+
"grad_norm": 4.453946113586426,
|
2429 |
+
"learning_rate": 1e-05,
|
2430 |
+
"loss": 0.4109,
|
2431 |
+
"step": 1730
|
2432 |
+
},
|
2433 |
+
{
|
2434 |
+
"epoch": 2.9936374420360186,
|
2435 |
+
"grad_norm": 3.8939476013183594,
|
2436 |
+
"learning_rate": 1e-05,
|
2437 |
+
"loss": 0.4232,
|
2438 |
+
"step": 1735
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 2.9970883209317374,
|
2442 |
+
"step": 1737,
|
2443 |
+
"total_flos": 2.5609799507175014e+18,
|
2444 |
+
"train_loss": 0.8316220592066139,
|
2445 |
+
"train_runtime": 17540.1657,
|
2446 |
+
"train_samples_per_second": 6.344,
|
2447 |
+
"train_steps_per_second": 0.099
|
2448 |
+
}
|
2449 |
+
],
|
2450 |
+
"logging_steps": 5,
|
2451 |
+
"max_steps": 1737,
|
2452 |
+
"num_input_tokens_seen": 0,
|
2453 |
+
"num_train_epochs": 3,
|
2454 |
+
"save_steps": 200,
|
2455 |
+
"stateful_callbacks": {
|
2456 |
+
"TrainerControl": {
|
2457 |
+
"args": {
|
2458 |
+
"should_epoch_stop": false,
|
2459 |
+
"should_evaluate": false,
|
2460 |
+
"should_log": false,
|
2461 |
+
"should_save": true,
|
2462 |
+
"should_training_stop": true
|
2463 |
+
},
|
2464 |
+
"attributes": {}
|
2465 |
+
}
|
2466 |
+
},
|
2467 |
+
"total_flos": 2.5609799507175014e+18,
|
2468 |
+
"train_batch_size": 4,
|
2469 |
+
"trial_name": null,
|
2470 |
+
"trial_params": null
|
2471 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7a9c64e1061d6daa7d8c8efc1ab79ab9efdc9c9da5ca32c4fbd246f0c8ac75b
|
3 |
+
size 5368
|
training_loss.png
ADDED