Training in progress, step 100
Browse files- config.json +33 -0
- merges.txt +0 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +250 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +784 -0
- trainer_log.jsonl +102 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/phi-4",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {},
|
9 |
+
"bos_token_id": 100257,
|
10 |
+
"embd_pdrop": 0.0,
|
11 |
+
"eos_token_id": 100265,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 5120,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 17920,
|
16 |
+
"max_position_embeddings": 16384,
|
17 |
+
"model_type": "phi3",
|
18 |
+
"num_attention_heads": 40,
|
19 |
+
"num_hidden_layers": 40,
|
20 |
+
"num_key_value_heads": 10,
|
21 |
+
"original_max_position_embeddings": 16384,
|
22 |
+
"pad_token_id": 100349,
|
23 |
+
"resid_pdrop": 0.0,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_scaling": null,
|
26 |
+
"rope_theta": 250000,
|
27 |
+
"sliding_window": null,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "bfloat16",
|
30 |
+
"transformers_version": "4.48.2",
|
31 |
+
"use_cache": false,
|
32 |
+
"vocab_size": 100352
|
33 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d755130dabad5db45d6fefe0e01aa363c4cea91fc327038b9c577c55ca073f28
|
3 |
+
size 4933656472
|
model-00002-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fbe24d34af92079619e927f8e8d37f83969ae6c3080cc871c3efd7b18bca85b
|
3 |
+
size 4954690712
|
model-00003-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1f07bfb996c2ebc7c7a22bd9c8dd288fef204a9891bb7eb3fb67a57ddd2a63b
|
3 |
+
size 4902241352
|
model-00004-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15614d1e341c85b63eaa7b7969b4d2f42fb7f9ff61f1d496a9fdddd7790083c5
|
3 |
+
size 4771169120
|
model-00005-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dd616b44fd4b996c4558123f4cb67fa00e653d185fa91c73918496359ff1a16
|
3 |
+
size 4771169120
|
model-00006-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a99fc5a809837c073f28ede0aaeeb305bfbc2e8704f68055347ecd091c071e96
|
3 |
+
size 4986116216
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,250 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 29319014400
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00006-of-00006.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
|
11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
12 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
13 |
+
"model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
|
14 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
15 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
16 |
+
"model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
|
17 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
18 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
19 |
+
"model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
|
20 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
21 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
22 |
+
"model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
|
23 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
24 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
25 |
+
"model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
|
26 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
27 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
28 |
+
"model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
|
29 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
30 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
31 |
+
"model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
|
32 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
33 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
34 |
+
"model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
|
35 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
36 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
37 |
+
"model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
|
38 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
39 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
40 |
+
"model.layers.13.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
|
41 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
42 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
43 |
+
"model.layers.13.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
|
44 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
45 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
46 |
+
"model.layers.14.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
|
47 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
48 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
49 |
+
"model.layers.14.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
|
50 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
51 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
52 |
+
"model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
|
53 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
54 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
55 |
+
"model.layers.15.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
|
56 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
57 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
58 |
+
"model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
|
59 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
60 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
61 |
+
"model.layers.16.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
|
62 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
63 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
64 |
+
"model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
|
65 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
66 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
67 |
+
"model.layers.17.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
|
68 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
69 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
70 |
+
"model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
|
71 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
72 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
73 |
+
"model.layers.18.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
|
74 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
75 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
76 |
+
"model.layers.19.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
|
77 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
78 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
79 |
+
"model.layers.19.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
|
80 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
81 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
82 |
+
"model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
|
83 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
84 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
85 |
+
"model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
|
86 |
+
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
87 |
+
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
88 |
+
"model.layers.20.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
|
89 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
90 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
91 |
+
"model.layers.20.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
|
92 |
+
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
93 |
+
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
94 |
+
"model.layers.21.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
|
95 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
96 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
97 |
+
"model.layers.21.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
|
98 |
+
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
99 |
+
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
100 |
+
"model.layers.22.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
|
101 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
102 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
103 |
+
"model.layers.22.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
|
104 |
+
"model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
105 |
+
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
106 |
+
"model.layers.23.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
|
107 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
108 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
109 |
+
"model.layers.23.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
|
110 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
111 |
+
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
112 |
+
"model.layers.24.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
|
113 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
114 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
115 |
+
"model.layers.24.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
|
116 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
117 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
118 |
+
"model.layers.25.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
|
119 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
120 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
121 |
+
"model.layers.25.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
|
122 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
123 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
124 |
+
"model.layers.26.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
|
125 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
126 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
127 |
+
"model.layers.26.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
|
128 |
+
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
129 |
+
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
130 |
+
"model.layers.27.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
|
131 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
132 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
133 |
+
"model.layers.27.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
|
134 |
+
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
135 |
+
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
136 |
+
"model.layers.28.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
|
137 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
138 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
139 |
+
"model.layers.28.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
|
140 |
+
"model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
141 |
+
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
142 |
+
"model.layers.29.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
|
143 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
144 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
145 |
+
"model.layers.29.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
|
146 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
147 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
148 |
+
"model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
|
149 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
150 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
151 |
+
"model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
|
152 |
+
"model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
153 |
+
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
154 |
+
"model.layers.30.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
|
155 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
156 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
157 |
+
"model.layers.30.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
|
158 |
+
"model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
159 |
+
"model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
160 |
+
"model.layers.31.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
|
161 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
162 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
163 |
+
"model.layers.31.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
|
164 |
+
"model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
165 |
+
"model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
166 |
+
"model.layers.32.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
|
167 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
168 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
169 |
+
"model.layers.32.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
|
170 |
+
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
171 |
+
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
172 |
+
"model.layers.33.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
|
173 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
174 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
175 |
+
"model.layers.33.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
|
176 |
+
"model.layers.34.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
177 |
+
"model.layers.34.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
178 |
+
"model.layers.34.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
|
179 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
180 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
181 |
+
"model.layers.34.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
|
182 |
+
"model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
183 |
+
"model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
184 |
+
"model.layers.35.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
|
185 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
186 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
187 |
+
"model.layers.35.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
|
188 |
+
"model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
189 |
+
"model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
190 |
+
"model.layers.36.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
|
191 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
192 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
193 |
+
"model.layers.36.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
|
194 |
+
"model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
195 |
+
"model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
196 |
+
"model.layers.37.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
|
197 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
198 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
199 |
+
"model.layers.37.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
|
200 |
+
"model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
201 |
+
"model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
202 |
+
"model.layers.38.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
|
203 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
204 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
205 |
+
"model.layers.38.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
|
206 |
+
"model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
207 |
+
"model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
208 |
+
"model.layers.39.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
|
209 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
210 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
211 |
+
"model.layers.39.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
|
212 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
213 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
214 |
+
"model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
|
215 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
216 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
217 |
+
"model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
|
218 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
219 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
220 |
+
"model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
|
221 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
222 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
223 |
+
"model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
|
224 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
225 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
226 |
+
"model.layers.6.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
|
227 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
228 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
229 |
+
"model.layers.6.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
|
230 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
231 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
232 |
+
"model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
|
233 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
234 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
235 |
+
"model.layers.7.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
|
236 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
237 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
238 |
+
"model.layers.8.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
|
239 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
240 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
241 |
+
"model.layers.8.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
|
242 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
243 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
244 |
+
"model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
|
245 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
246 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
247 |
+
"model.layers.9.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
|
248 |
+
"model.norm.weight": "model-00006-of-00006.safetensors"
|
249 |
+
}
|
250 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": true,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": true,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|im_end|>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": true,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|dummy_85|>",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": "<|endoftext|>"
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,784 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"100256": {
|
5 |
+
"content": "<|dummy_0|>",
|
6 |
+
"lstrip": true,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": true,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"100257": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": true,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": true,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"100258": {
|
21 |
+
"content": "<|fim_prefix|>",
|
22 |
+
"lstrip": true,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": true,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"100259": {
|
29 |
+
"content": "<|fim_middle|>",
|
30 |
+
"lstrip": true,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": true,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"100260": {
|
37 |
+
"content": "<|fim_suffix|>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": true,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"100261": {
|
45 |
+
"content": "<|dummy_1|>",
|
46 |
+
"lstrip": true,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": true,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"100262": {
|
53 |
+
"content": "<|dummy_2|>",
|
54 |
+
"lstrip": true,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": true,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"100263": {
|
61 |
+
"content": "<|dummy_3|>",
|
62 |
+
"lstrip": true,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": true,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"100264": {
|
69 |
+
"content": "<|im_start|>",
|
70 |
+
"lstrip": true,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": true,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"100265": {
|
77 |
+
"content": "<|im_end|>",
|
78 |
+
"lstrip": true,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": true,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"100266": {
|
85 |
+
"content": "<|im_sep|>",
|
86 |
+
"lstrip": true,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": true,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"100267": {
|
93 |
+
"content": "<|dummy_4|>",
|
94 |
+
"lstrip": true,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": true,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"100268": {
|
101 |
+
"content": "<|dummy_5|>",
|
102 |
+
"lstrip": true,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": true,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"100269": {
|
109 |
+
"content": "<|dummy_6|>",
|
110 |
+
"lstrip": true,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": true,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"100270": {
|
117 |
+
"content": "<|dummy_7|>",
|
118 |
+
"lstrip": true,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": true,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"100271": {
|
125 |
+
"content": "<|dummy_8|>",
|
126 |
+
"lstrip": true,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": true,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"100272": {
|
133 |
+
"content": "<|dummy_9|>",
|
134 |
+
"lstrip": true,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": true,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"100273": {
|
141 |
+
"content": "<|dummy_10|>",
|
142 |
+
"lstrip": true,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": true,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"100274": {
|
149 |
+
"content": "<|dummy_11|>",
|
150 |
+
"lstrip": true,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": true,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"100275": {
|
157 |
+
"content": "<|dummy_12|>",
|
158 |
+
"lstrip": true,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": true,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"100276": {
|
165 |
+
"content": "<|endofprompt|>",
|
166 |
+
"lstrip": true,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": true,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"100277": {
|
173 |
+
"content": "<|dummy_13|>",
|
174 |
+
"lstrip": true,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": true,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"100278": {
|
181 |
+
"content": "<|dummy_14|>",
|
182 |
+
"lstrip": true,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": true,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"100279": {
|
189 |
+
"content": "<|dummy_15|>",
|
190 |
+
"lstrip": true,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": true,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"100280": {
|
197 |
+
"content": "<|dummy_16|>",
|
198 |
+
"lstrip": true,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": true,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"100281": {
|
205 |
+
"content": "<|dummy_17|>",
|
206 |
+
"lstrip": true,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": true,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"100282": {
|
213 |
+
"content": "<|dummy_18|>",
|
214 |
+
"lstrip": true,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": true,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"100283": {
|
221 |
+
"content": "<|dummy_19|>",
|
222 |
+
"lstrip": true,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": true,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"100284": {
|
229 |
+
"content": "<|dummy_20|>",
|
230 |
+
"lstrip": true,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": true,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"100285": {
|
237 |
+
"content": "<|dummy_21|>",
|
238 |
+
"lstrip": true,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": true,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"100286": {
|
245 |
+
"content": "<|dummy_22|>",
|
246 |
+
"lstrip": true,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": true,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"100287": {
|
253 |
+
"content": "<|dummy_23|>",
|
254 |
+
"lstrip": true,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": true,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"100288": {
|
261 |
+
"content": "<|dummy_24|>",
|
262 |
+
"lstrip": true,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": true,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
},
|
268 |
+
"100289": {
|
269 |
+
"content": "<|dummy_25|>",
|
270 |
+
"lstrip": true,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": true,
|
273 |
+
"single_word": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
"100290": {
|
277 |
+
"content": "<|dummy_26|>",
|
278 |
+
"lstrip": true,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": true,
|
281 |
+
"single_word": false,
|
282 |
+
"special": true
|
283 |
+
},
|
284 |
+
"100291": {
|
285 |
+
"content": "<|dummy_27|>",
|
286 |
+
"lstrip": true,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": true,
|
289 |
+
"single_word": false,
|
290 |
+
"special": true
|
291 |
+
},
|
292 |
+
"100292": {
|
293 |
+
"content": "<|dummy_28|>",
|
294 |
+
"lstrip": true,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": true,
|
297 |
+
"single_word": false,
|
298 |
+
"special": true
|
299 |
+
},
|
300 |
+
"100293": {
|
301 |
+
"content": "<|dummy_29|>",
|
302 |
+
"lstrip": true,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": true,
|
305 |
+
"single_word": false,
|
306 |
+
"special": true
|
307 |
+
},
|
308 |
+
"100294": {
|
309 |
+
"content": "<|dummy_30|>",
|
310 |
+
"lstrip": true,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": true,
|
313 |
+
"single_word": false,
|
314 |
+
"special": true
|
315 |
+
},
|
316 |
+
"100295": {
|
317 |
+
"content": "<|dummy_31|>",
|
318 |
+
"lstrip": true,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": true,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
+
},
|
324 |
+
"100296": {
|
325 |
+
"content": "<|dummy_32|>",
|
326 |
+
"lstrip": true,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": true,
|
329 |
+
"single_word": false,
|
330 |
+
"special": true
|
331 |
+
},
|
332 |
+
"100297": {
|
333 |
+
"content": "<|dummy_33|>",
|
334 |
+
"lstrip": true,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": true,
|
337 |
+
"single_word": false,
|
338 |
+
"special": true
|
339 |
+
},
|
340 |
+
"100298": {
|
341 |
+
"content": "<|dummy_34|>",
|
342 |
+
"lstrip": true,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": true,
|
345 |
+
"single_word": false,
|
346 |
+
"special": true
|
347 |
+
},
|
348 |
+
"100299": {
|
349 |
+
"content": "<|dummy_35|>",
|
350 |
+
"lstrip": true,
|
351 |
+
"normalized": false,
|
352 |
+
"rstrip": true,
|
353 |
+
"single_word": false,
|
354 |
+
"special": true
|
355 |
+
},
|
356 |
+
"100300": {
|
357 |
+
"content": "<|dummy_36|>",
|
358 |
+
"lstrip": true,
|
359 |
+
"normalized": false,
|
360 |
+
"rstrip": true,
|
361 |
+
"single_word": false,
|
362 |
+
"special": true
|
363 |
+
},
|
364 |
+
"100301": {
|
365 |
+
"content": "<|dummy_37|>",
|
366 |
+
"lstrip": true,
|
367 |
+
"normalized": false,
|
368 |
+
"rstrip": true,
|
369 |
+
"single_word": false,
|
370 |
+
"special": true
|
371 |
+
},
|
372 |
+
"100302": {
|
373 |
+
"content": "<|dummy_38|>",
|
374 |
+
"lstrip": true,
|
375 |
+
"normalized": false,
|
376 |
+
"rstrip": true,
|
377 |
+
"single_word": false,
|
378 |
+
"special": true
|
379 |
+
},
|
380 |
+
"100303": {
|
381 |
+
"content": "<|dummy_39|>",
|
382 |
+
"lstrip": true,
|
383 |
+
"normalized": false,
|
384 |
+
"rstrip": true,
|
385 |
+
"single_word": false,
|
386 |
+
"special": true
|
387 |
+
},
|
388 |
+
"100304": {
|
389 |
+
"content": "<|dummy_40|>",
|
390 |
+
"lstrip": true,
|
391 |
+
"normalized": false,
|
392 |
+
"rstrip": true,
|
393 |
+
"single_word": false,
|
394 |
+
"special": true
|
395 |
+
},
|
396 |
+
"100305": {
|
397 |
+
"content": "<|dummy_41|>",
|
398 |
+
"lstrip": true,
|
399 |
+
"normalized": false,
|
400 |
+
"rstrip": true,
|
401 |
+
"single_word": false,
|
402 |
+
"special": true
|
403 |
+
},
|
404 |
+
"100306": {
|
405 |
+
"content": "<|dummy_42|>",
|
406 |
+
"lstrip": true,
|
407 |
+
"normalized": false,
|
408 |
+
"rstrip": true,
|
409 |
+
"single_word": false,
|
410 |
+
"special": true
|
411 |
+
},
|
412 |
+
"100307": {
|
413 |
+
"content": "<|dummy_43|>",
|
414 |
+
"lstrip": true,
|
415 |
+
"normalized": false,
|
416 |
+
"rstrip": true,
|
417 |
+
"single_word": false,
|
418 |
+
"special": true
|
419 |
+
},
|
420 |
+
"100308": {
|
421 |
+
"content": "<|dummy_44|>",
|
422 |
+
"lstrip": true,
|
423 |
+
"normalized": false,
|
424 |
+
"rstrip": true,
|
425 |
+
"single_word": false,
|
426 |
+
"special": true
|
427 |
+
},
|
428 |
+
"100309": {
|
429 |
+
"content": "<|dummy_45|>",
|
430 |
+
"lstrip": true,
|
431 |
+
"normalized": false,
|
432 |
+
"rstrip": true,
|
433 |
+
"single_word": false,
|
434 |
+
"special": true
|
435 |
+
},
|
436 |
+
"100310": {
|
437 |
+
"content": "<|dummy_46|>",
|
438 |
+
"lstrip": true,
|
439 |
+
"normalized": false,
|
440 |
+
"rstrip": true,
|
441 |
+
"single_word": false,
|
442 |
+
"special": true
|
443 |
+
},
|
444 |
+
"100311": {
|
445 |
+
"content": "<|dummy_47|>",
|
446 |
+
"lstrip": true,
|
447 |
+
"normalized": false,
|
448 |
+
"rstrip": true,
|
449 |
+
"single_word": false,
|
450 |
+
"special": true
|
451 |
+
},
|
452 |
+
"100312": {
|
453 |
+
"content": "<|dummy_48|>",
|
454 |
+
"lstrip": true,
|
455 |
+
"normalized": false,
|
456 |
+
"rstrip": true,
|
457 |
+
"single_word": false,
|
458 |
+
"special": true
|
459 |
+
},
|
460 |
+
"100313": {
|
461 |
+
"content": "<|dummy_49|>",
|
462 |
+
"lstrip": true,
|
463 |
+
"normalized": false,
|
464 |
+
"rstrip": true,
|
465 |
+
"single_word": false,
|
466 |
+
"special": true
|
467 |
+
},
|
468 |
+
"100314": {
|
469 |
+
"content": "<|dummy_50|>",
|
470 |
+
"lstrip": true,
|
471 |
+
"normalized": false,
|
472 |
+
"rstrip": true,
|
473 |
+
"single_word": false,
|
474 |
+
"special": true
|
475 |
+
},
|
476 |
+
"100315": {
|
477 |
+
"content": "<|dummy_51|>",
|
478 |
+
"lstrip": true,
|
479 |
+
"normalized": false,
|
480 |
+
"rstrip": true,
|
481 |
+
"single_word": false,
|
482 |
+
"special": true
|
483 |
+
},
|
484 |
+
"100316": {
|
485 |
+
"content": "<|dummy_52|>",
|
486 |
+
"lstrip": true,
|
487 |
+
"normalized": false,
|
488 |
+
"rstrip": true,
|
489 |
+
"single_word": false,
|
490 |
+
"special": true
|
491 |
+
},
|
492 |
+
"100317": {
|
493 |
+
"content": "<|dummy_53|>",
|
494 |
+
"lstrip": true,
|
495 |
+
"normalized": false,
|
496 |
+
"rstrip": true,
|
497 |
+
"single_word": false,
|
498 |
+
"special": true
|
499 |
+
},
|
500 |
+
"100318": {
|
501 |
+
"content": "<|dummy_54|>",
|
502 |
+
"lstrip": true,
|
503 |
+
"normalized": false,
|
504 |
+
"rstrip": true,
|
505 |
+
"single_word": false,
|
506 |
+
"special": true
|
507 |
+
},
|
508 |
+
"100319": {
|
509 |
+
"content": "<|dummy_55|>",
|
510 |
+
"lstrip": true,
|
511 |
+
"normalized": false,
|
512 |
+
"rstrip": true,
|
513 |
+
"single_word": false,
|
514 |
+
"special": true
|
515 |
+
},
|
516 |
+
"100320": {
|
517 |
+
"content": "<|dummy_56|>",
|
518 |
+
"lstrip": true,
|
519 |
+
"normalized": false,
|
520 |
+
"rstrip": true,
|
521 |
+
"single_word": false,
|
522 |
+
"special": true
|
523 |
+
},
|
524 |
+
"100321": {
|
525 |
+
"content": "<|dummy_57|>",
|
526 |
+
"lstrip": true,
|
527 |
+
"normalized": false,
|
528 |
+
"rstrip": true,
|
529 |
+
"single_word": false,
|
530 |
+
"special": true
|
531 |
+
},
|
532 |
+
"100322": {
|
533 |
+
"content": "<|dummy_58|>",
|
534 |
+
"lstrip": true,
|
535 |
+
"normalized": false,
|
536 |
+
"rstrip": true,
|
537 |
+
"single_word": false,
|
538 |
+
"special": true
|
539 |
+
},
|
540 |
+
"100323": {
|
541 |
+
"content": "<|dummy_59|>",
|
542 |
+
"lstrip": true,
|
543 |
+
"normalized": false,
|
544 |
+
"rstrip": true,
|
545 |
+
"single_word": false,
|
546 |
+
"special": true
|
547 |
+
},
|
548 |
+
"100324": {
|
549 |
+
"content": "<|dummy_60|>",
|
550 |
+
"lstrip": true,
|
551 |
+
"normalized": false,
|
552 |
+
"rstrip": true,
|
553 |
+
"single_word": false,
|
554 |
+
"special": true
|
555 |
+
},
|
556 |
+
"100325": {
|
557 |
+
"content": "<|dummy_61|>",
|
558 |
+
"lstrip": true,
|
559 |
+
"normalized": false,
|
560 |
+
"rstrip": true,
|
561 |
+
"single_word": false,
|
562 |
+
"special": true
|
563 |
+
},
|
564 |
+
"100326": {
|
565 |
+
"content": "<|dummy_62|>",
|
566 |
+
"lstrip": true,
|
567 |
+
"normalized": false,
|
568 |
+
"rstrip": true,
|
569 |
+
"single_word": false,
|
570 |
+
"special": true
|
571 |
+
},
|
572 |
+
"100327": {
|
573 |
+
"content": "<|dummy_63|>",
|
574 |
+
"lstrip": true,
|
575 |
+
"normalized": false,
|
576 |
+
"rstrip": true,
|
577 |
+
"single_word": false,
|
578 |
+
"special": true
|
579 |
+
},
|
580 |
+
"100328": {
|
581 |
+
"content": "<|dummy_64|>",
|
582 |
+
"lstrip": true,
|
583 |
+
"normalized": false,
|
584 |
+
"rstrip": true,
|
585 |
+
"single_word": false,
|
586 |
+
"special": true
|
587 |
+
},
|
588 |
+
"100329": {
|
589 |
+
"content": "<|dummy_65|>",
|
590 |
+
"lstrip": true,
|
591 |
+
"normalized": false,
|
592 |
+
"rstrip": true,
|
593 |
+
"single_word": false,
|
594 |
+
"special": true
|
595 |
+
},
|
596 |
+
"100330": {
|
597 |
+
"content": "<|dummy_66|>",
|
598 |
+
"lstrip": true,
|
599 |
+
"normalized": false,
|
600 |
+
"rstrip": true,
|
601 |
+
"single_word": false,
|
602 |
+
"special": true
|
603 |
+
},
|
604 |
+
"100331": {
|
605 |
+
"content": "<|dummy_67|>",
|
606 |
+
"lstrip": true,
|
607 |
+
"normalized": false,
|
608 |
+
"rstrip": true,
|
609 |
+
"single_word": false,
|
610 |
+
"special": true
|
611 |
+
},
|
612 |
+
"100332": {
|
613 |
+
"content": "<|dummy_68|>",
|
614 |
+
"lstrip": true,
|
615 |
+
"normalized": false,
|
616 |
+
"rstrip": true,
|
617 |
+
"single_word": false,
|
618 |
+
"special": true
|
619 |
+
},
|
620 |
+
"100333": {
|
621 |
+
"content": "<|dummy_69|>",
|
622 |
+
"lstrip": true,
|
623 |
+
"normalized": false,
|
624 |
+
"rstrip": true,
|
625 |
+
"single_word": false,
|
626 |
+
"special": true
|
627 |
+
},
|
628 |
+
"100334": {
|
629 |
+
"content": "<|dummy_70|>",
|
630 |
+
"lstrip": true,
|
631 |
+
"normalized": false,
|
632 |
+
"rstrip": true,
|
633 |
+
"single_word": false,
|
634 |
+
"special": true
|
635 |
+
},
|
636 |
+
"100335": {
|
637 |
+
"content": "<|dummy_71|>",
|
638 |
+
"lstrip": true,
|
639 |
+
"normalized": false,
|
640 |
+
"rstrip": true,
|
641 |
+
"single_word": false,
|
642 |
+
"special": true
|
643 |
+
},
|
644 |
+
"100336": {
|
645 |
+
"content": "<|dummy_72|>",
|
646 |
+
"lstrip": true,
|
647 |
+
"normalized": false,
|
648 |
+
"rstrip": true,
|
649 |
+
"single_word": false,
|
650 |
+
"special": true
|
651 |
+
},
|
652 |
+
"100337": {
|
653 |
+
"content": "<|dummy_73|>",
|
654 |
+
"lstrip": true,
|
655 |
+
"normalized": false,
|
656 |
+
"rstrip": true,
|
657 |
+
"single_word": false,
|
658 |
+
"special": true
|
659 |
+
},
|
660 |
+
"100338": {
|
661 |
+
"content": "<|dummy_74|>",
|
662 |
+
"lstrip": true,
|
663 |
+
"normalized": false,
|
664 |
+
"rstrip": true,
|
665 |
+
"single_word": false,
|
666 |
+
"special": true
|
667 |
+
},
|
668 |
+
"100339": {
|
669 |
+
"content": "<|dummy_75|>",
|
670 |
+
"lstrip": true,
|
671 |
+
"normalized": false,
|
672 |
+
"rstrip": true,
|
673 |
+
"single_word": false,
|
674 |
+
"special": true
|
675 |
+
},
|
676 |
+
"100340": {
|
677 |
+
"content": "<|dummy_76|>",
|
678 |
+
"lstrip": true,
|
679 |
+
"normalized": false,
|
680 |
+
"rstrip": true,
|
681 |
+
"single_word": false,
|
682 |
+
"special": true
|
683 |
+
},
|
684 |
+
"100341": {
|
685 |
+
"content": "<|dummy_77|>",
|
686 |
+
"lstrip": true,
|
687 |
+
"normalized": false,
|
688 |
+
"rstrip": true,
|
689 |
+
"single_word": false,
|
690 |
+
"special": true
|
691 |
+
},
|
692 |
+
"100342": {
|
693 |
+
"content": "<|dummy_78|>",
|
694 |
+
"lstrip": true,
|
695 |
+
"normalized": false,
|
696 |
+
"rstrip": true,
|
697 |
+
"single_word": false,
|
698 |
+
"special": true
|
699 |
+
},
|
700 |
+
"100343": {
|
701 |
+
"content": "<|dummy_79|>",
|
702 |
+
"lstrip": true,
|
703 |
+
"normalized": false,
|
704 |
+
"rstrip": true,
|
705 |
+
"single_word": false,
|
706 |
+
"special": true
|
707 |
+
},
|
708 |
+
"100344": {
|
709 |
+
"content": "<|dummy_80|>",
|
710 |
+
"lstrip": true,
|
711 |
+
"normalized": false,
|
712 |
+
"rstrip": true,
|
713 |
+
"single_word": false,
|
714 |
+
"special": true
|
715 |
+
},
|
716 |
+
"100345": {
|
717 |
+
"content": "<|dummy_81|>",
|
718 |
+
"lstrip": true,
|
719 |
+
"normalized": false,
|
720 |
+
"rstrip": true,
|
721 |
+
"single_word": false,
|
722 |
+
"special": true
|
723 |
+
},
|
724 |
+
"100346": {
|
725 |
+
"content": "<|dummy_82|>",
|
726 |
+
"lstrip": true,
|
727 |
+
"normalized": false,
|
728 |
+
"rstrip": true,
|
729 |
+
"single_word": false,
|
730 |
+
"special": true
|
731 |
+
},
|
732 |
+
"100347": {
|
733 |
+
"content": "<|dummy_83|>",
|
734 |
+
"lstrip": true,
|
735 |
+
"normalized": false,
|
736 |
+
"rstrip": true,
|
737 |
+
"single_word": false,
|
738 |
+
"special": true
|
739 |
+
},
|
740 |
+
"100348": {
|
741 |
+
"content": "<|dummy_84|>",
|
742 |
+
"lstrip": true,
|
743 |
+
"normalized": false,
|
744 |
+
"rstrip": true,
|
745 |
+
"single_word": false,
|
746 |
+
"special": true
|
747 |
+
},
|
748 |
+
"100349": {
|
749 |
+
"content": "<|dummy_85|>",
|
750 |
+
"lstrip": true,
|
751 |
+
"normalized": false,
|
752 |
+
"rstrip": true,
|
753 |
+
"single_word": false,
|
754 |
+
"special": true
|
755 |
+
},
|
756 |
+
"100350": {
|
757 |
+
"content": "<|dummy_86|>",
|
758 |
+
"lstrip": true,
|
759 |
+
"normalized": false,
|
760 |
+
"rstrip": true,
|
761 |
+
"single_word": false,
|
762 |
+
"special": true
|
763 |
+
},
|
764 |
+
"100351": {
|
765 |
+
"content": "<|dummy_87|>",
|
766 |
+
"lstrip": true,
|
767 |
+
"normalized": false,
|
768 |
+
"rstrip": true,
|
769 |
+
"single_word": false,
|
770 |
+
"special": true
|
771 |
+
}
|
772 |
+
},
|
773 |
+
"bos_token": "<|endoftext|>",
|
774 |
+
"chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
|
775 |
+
"clean_up_tokenization_spaces": false,
|
776 |
+
"eos_token": "<|im_end|>",
|
777 |
+
"extra_special_tokens": {},
|
778 |
+
"model_max_length": 8192,
|
779 |
+
"pad_token": "<|dummy_85|>",
|
780 |
+
"padding_side": "right",
|
781 |
+
"split_special_tokens": false,
|
782 |
+
"tokenizer_class": "GPT2Tokenizer",
|
783 |
+
"unk_token": "<|endoftext|>"
|
784 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 1, "total_steps": 117, "loss": 1.8884, "lr": 1.6666666666666667e-06, "epoch": 0.008547008547008548, "percentage": 0.85, "elapsed_time": "0:03:29", "remaining_time": "6:45:06"}
|
2 |
+
{"current_steps": 2, "total_steps": 117, "loss": 1.8929, "lr": 3.3333333333333333e-06, "epoch": 0.017094017094017096, "percentage": 1.71, "elapsed_time": "0:06:43", "remaining_time": "6:26:44"}
|
3 |
+
{"current_steps": 3, "total_steps": 117, "loss": 1.9025, "lr": 5e-06, "epoch": 0.02564102564102564, "percentage": 2.56, "elapsed_time": "0:09:59", "remaining_time": "6:19:27"}
|
4 |
+
{"current_steps": 4, "total_steps": 117, "loss": 1.8795, "lr": 6.666666666666667e-06, "epoch": 0.03418803418803419, "percentage": 3.42, "elapsed_time": "0:13:13", "remaining_time": "6:13:42"}
|
5 |
+
{"current_steps": 5, "total_steps": 117, "loss": 1.8705, "lr": 8.333333333333334e-06, "epoch": 0.042735042735042736, "percentage": 4.27, "elapsed_time": "0:16:25", "remaining_time": "6:07:48"}
|
6 |
+
{"current_steps": 6, "total_steps": 117, "loss": 1.8572, "lr": 1e-05, "epoch": 0.05128205128205128, "percentage": 5.13, "elapsed_time": "0:19:36", "remaining_time": "6:02:43"}
|
7 |
+
{"current_steps": 7, "total_steps": 117, "loss": 1.8696, "lr": 9.99799753559161e-06, "epoch": 0.05982905982905983, "percentage": 5.98, "elapsed_time": "0:22:48", "remaining_time": "5:58:17"}
|
8 |
+
{"current_steps": 8, "total_steps": 117, "loss": 1.8535, "lr": 9.991991746311916e-06, "epoch": 0.06837606837606838, "percentage": 6.84, "elapsed_time": "0:25:58", "remaining_time": "5:53:58"}
|
9 |
+
{"current_steps": 9, "total_steps": 117, "loss": 1.8623, "lr": 9.981987442712634e-06, "epoch": 0.07692307692307693, "percentage": 7.69, "elapsed_time": "0:29:09", "remaining_time": "5:49:49"}
|
10 |
+
{"current_steps": 10, "total_steps": 117, "loss": 1.8575, "lr": 9.967992638098517e-06, "epoch": 0.08547008547008547, "percentage": 8.55, "elapsed_time": "0:32:18", "remaining_time": "5:45:44"}
|
11 |
+
{"current_steps": 11, "total_steps": 117, "loss": 1.8533, "lr": 9.950018542108818e-06, "epoch": 0.09401709401709402, "percentage": 9.4, "elapsed_time": "0:35:27", "remaining_time": "5:41:44"}
|
12 |
+
{"current_steps": 12, "total_steps": 117, "loss": 1.8447, "lr": 9.928079551738542e-06, "epoch": 0.10256410256410256, "percentage": 10.26, "elapsed_time": "0:38:36", "remaining_time": "5:37:46"}
|
13 |
+
{"current_steps": 13, "total_steps": 117, "loss": 1.8458, "lr": 9.902193239806634e-06, "epoch": 0.1111111111111111, "percentage": 11.11, "elapsed_time": "0:41:47", "remaining_time": "5:34:16"}
|
14 |
+
{"current_steps": 14, "total_steps": 117, "loss": 1.8447, "lr": 9.872380340880416e-06, "epoch": 0.11965811965811966, "percentage": 11.97, "elapsed_time": "0:44:57", "remaining_time": "5:30:42"}
|
15 |
+
{"current_steps": 15, "total_steps": 117, "loss": 1.8474, "lr": 9.838664734667496e-06, "epoch": 0.1282051282051282, "percentage": 12.82, "elapsed_time": "0:48:05", "remaining_time": "5:27:01"}
|
16 |
+
{"current_steps": 16, "total_steps": 117, "loss": 1.8424, "lr": 9.801073426888447e-06, "epoch": 0.13675213675213677, "percentage": 13.68, "elapsed_time": "0:51:14", "remaining_time": "5:23:30"}
|
17 |
+
{"current_steps": 17, "total_steps": 117, "loss": 1.8274, "lr": 9.759636527645633e-06, "epoch": 0.1452991452991453, "percentage": 14.53, "elapsed_time": "0:54:23", "remaining_time": "5:19:58"}
|
18 |
+
{"current_steps": 18, "total_steps": 117, "loss": 1.8262, "lr": 9.714387227305422e-06, "epoch": 0.15384615384615385, "percentage": 15.38, "elapsed_time": "0:57:34", "remaining_time": "5:16:41"}
|
19 |
+
{"current_steps": 19, "total_steps": 117, "loss": 1.8331, "lr": 9.665361769913187e-06, "epoch": 0.1623931623931624, "percentage": 16.24, "elapsed_time": "1:00:44", "remaining_time": "5:13:17"}
|
20 |
+
{"current_steps": 20, "total_steps": 117, "loss": 1.8278, "lr": 9.612599424162344e-06, "epoch": 0.17094017094017094, "percentage": 17.09, "elapsed_time": "1:03:55", "remaining_time": "5:10:00"}
|
21 |
+
{"current_steps": 21, "total_steps": 117, "loss": 1.8238, "lr": 9.55614245194068e-06, "epoch": 0.1794871794871795, "percentage": 17.95, "elapsed_time": "1:07:03", "remaining_time": "5:06:31"}
|
22 |
+
{"current_steps": 22, "total_steps": 117, "loss": 1.8282, "lr": 9.496036074479184e-06, "epoch": 0.18803418803418803, "percentage": 18.8, "elapsed_time": "1:10:13", "remaining_time": "5:03:13"}
|
23 |
+
{"current_steps": 23, "total_steps": 117, "loss": 1.825, "lr": 9.432328436130493e-06, "epoch": 0.19658119658119658, "percentage": 19.66, "elapsed_time": "1:13:22", "remaining_time": "4:59:54"}
|
24 |
+
{"current_steps": 24, "total_steps": 117, "loss": 1.8165, "lr": 9.365070565805941e-06, "epoch": 0.20512820512820512, "percentage": 20.51, "elapsed_time": "1:16:34", "remaining_time": "4:56:43"}
|
25 |
+
{"current_steps": 25, "total_steps": 117, "loss": 1.8194, "lr": 9.294316336102132e-06, "epoch": 0.21367521367521367, "percentage": 21.37, "elapsed_time": "1:19:43", "remaining_time": "4:53:23"}
|
26 |
+
{"current_steps": 26, "total_steps": 117, "loss": 1.822, "lr": 9.220122420149753e-06, "epoch": 0.2222222222222222, "percentage": 22.22, "elapsed_time": "1:22:54", "remaining_time": "4:50:09"}
|
27 |
+
{"current_steps": 27, "total_steps": 117, "loss": 1.8218, "lr": 9.142548246219212e-06, "epoch": 0.23076923076923078, "percentage": 23.08, "elapsed_time": "1:26:05", "remaining_time": "4:46:59"}
|
28 |
+
{"current_steps": 28, "total_steps": 117, "loss": 1.8245, "lr": 9.06165595011943e-06, "epoch": 0.23931623931623933, "percentage": 23.93, "elapsed_time": "1:29:16", "remaining_time": "4:43:46"}
|
29 |
+
{"current_steps": 29, "total_steps": 117, "loss": 1.8087, "lr": 8.97751032542795e-06, "epoch": 0.24786324786324787, "percentage": 24.79, "elapsed_time": "1:32:26", "remaining_time": "4:40:31"}
|
30 |
+
{"current_steps": 30, "total_steps": 117, "loss": 1.8097, "lr": 8.890178771592198e-06, "epoch": 0.2564102564102564, "percentage": 25.64, "elapsed_time": "1:35:37", "remaining_time": "4:37:19"}
|
31 |
+
{"current_steps": 31, "total_steps": 117, "loss": 1.8207, "lr": 8.799731239943488e-06, "epoch": 0.26495726495726496, "percentage": 26.5, "elapsed_time": "1:38:48", "remaining_time": "4:34:05"}
|
32 |
+
{"current_steps": 32, "total_steps": 117, "loss": 1.8124, "lr": 8.706240177667003e-06, "epoch": 0.27350427350427353, "percentage": 27.35, "elapsed_time": "1:41:58", "remaining_time": "4:30:51"}
|
33 |
+
{"current_steps": 33, "total_steps": 117, "loss": 1.8184, "lr": 8.609780469772623e-06, "epoch": 0.28205128205128205, "percentage": 28.21, "elapsed_time": "1:45:07", "remaining_time": "4:27:34"}
|
34 |
+
{"current_steps": 34, "total_steps": 117, "loss": 1.819, "lr": 8.510429379113114e-06, "epoch": 0.2905982905982906, "percentage": 29.06, "elapsed_time": "1:48:15", "remaining_time": "4:24:17"}
|
35 |
+
{"current_steps": 35, "total_steps": 117, "loss": 1.8153, "lr": 8.408266484497664e-06, "epoch": 0.29914529914529914, "percentage": 29.91, "elapsed_time": "1:51:23", "remaining_time": "4:20:58"}
|
36 |
+
{"current_steps": 36, "total_steps": 117, "loss": 1.8141, "lr": 8.303373616950408e-06, "epoch": 0.3076923076923077, "percentage": 30.77, "elapsed_time": "1:54:33", "remaining_time": "4:17:44"}
|
37 |
+
{"current_steps": 37, "total_steps": 117, "loss": 1.8072, "lr": 8.195834794164925e-06, "epoch": 0.3162393162393162, "percentage": 31.62, "elapsed_time": "1:57:40", "remaining_time": "4:14:25"}
|
38 |
+
{"current_steps": 38, "total_steps": 117, "loss": 1.8171, "lr": 8.085736153207277e-06, "epoch": 0.3247863247863248, "percentage": 32.48, "elapsed_time": "2:00:51", "remaining_time": "4:11:15"}
|
39 |
+
{"current_steps": 39, "total_steps": 117, "loss": 1.8192, "lr": 7.973165881521435e-06, "epoch": 0.3333333333333333, "percentage": 33.33, "elapsed_time": "2:04:00", "remaining_time": "4:08:00"}
|
40 |
+
{"current_steps": 40, "total_steps": 117, "loss": 1.8069, "lr": 7.858214146292394e-06, "epoch": 0.3418803418803419, "percentage": 34.19, "elapsed_time": "2:07:09", "remaining_time": "4:04:47"}
|
41 |
+
{"current_steps": 41, "total_steps": 117, "loss": 1.8093, "lr": 7.74097302222355e-06, "epoch": 0.3504273504273504, "percentage": 35.04, "elapsed_time": "2:10:19", "remaining_time": "4:01:33"}
|
42 |
+
{"current_steps": 42, "total_steps": 117, "loss": 1.8014, "lr": 7.621536417786159e-06, "epoch": 0.358974358974359, "percentage": 35.9, "elapsed_time": "2:13:29", "remaining_time": "3:58:23"}
|
43 |
+
{"current_steps": 43, "total_steps": 117, "loss": 1.8108, "lr": 7.500000000000001e-06, "epoch": 0.36752136752136755, "percentage": 36.75, "elapsed_time": "2:16:38", "remaining_time": "3:55:09"}
|
44 |
+
{"current_steps": 44, "total_steps": 117, "loss": 1.8069, "lr": 7.37646111780545e-06, "epoch": 0.37606837606837606, "percentage": 37.61, "elapsed_time": "2:19:47", "remaining_time": "3:51:56"}
|
45 |
+
{"current_steps": 45, "total_steps": 117, "loss": 1.8057, "lr": 7.251018724088367e-06, "epoch": 0.38461538461538464, "percentage": 38.46, "elapsed_time": "2:22:56", "remaining_time": "3:48:43"}
|
46 |
+
{"current_steps": 46, "total_steps": 117, "loss": 1.8065, "lr": 7.12377329642024e-06, "epoch": 0.39316239316239315, "percentage": 39.32, "elapsed_time": "2:26:05", "remaining_time": "3:45:29"}
|
47 |
+
{"current_steps": 47, "total_steps": 117, "loss": 1.7997, "lr": 6.994826756577082e-06, "epoch": 0.4017094017094017, "percentage": 40.17, "elapsed_time": "2:29:13", "remaining_time": "3:42:15"}
|
48 |
+
{"current_steps": 48, "total_steps": 117, "loss": 1.8073, "lr": 6.864282388901544e-06, "epoch": 0.41025641025641024, "percentage": 41.03, "elapsed_time": "2:32:22", "remaining_time": "3:39:01"}
|
49 |
+
{"current_steps": 49, "total_steps": 117, "loss": 1.8056, "lr": 6.732244757573619e-06, "epoch": 0.4188034188034188, "percentage": 41.88, "elapsed_time": "2:35:30", "remaining_time": "3:35:47"}
|
50 |
+
{"current_steps": 50, "total_steps": 117, "loss": 1.807, "lr": 6.598819622856227e-06, "epoch": 0.42735042735042733, "percentage": 42.74, "elapsed_time": "2:38:38", "remaining_time": "3:32:35"}
|
51 |
+
{"current_steps": 51, "total_steps": 117, "loss": 1.8098, "lr": 6.464113856382752e-06, "epoch": 0.4358974358974359, "percentage": 43.59, "elapsed_time": "2:41:48", "remaining_time": "3:29:23"}
|
52 |
+
{"current_steps": 52, "total_steps": 117, "loss": 1.8016, "lr": 6.328235355554382e-06, "epoch": 0.4444444444444444, "percentage": 44.44, "elapsed_time": "2:44:59", "remaining_time": "3:26:14"}
|
53 |
+
{"current_steps": 53, "total_steps": 117, "loss": 1.8111, "lr": 6.191292957115825e-06, "epoch": 0.452991452991453, "percentage": 45.3, "elapsed_time": "2:48:09", "remaining_time": "3:23:03"}
|
54 |
+
{"current_steps": 54, "total_steps": 117, "loss": 1.8038, "lr": 6.053396349978632e-06, "epoch": 0.46153846153846156, "percentage": 46.15, "elapsed_time": "2:51:18", "remaining_time": "3:19:51"}
|
55 |
+
{"current_steps": 55, "total_steps": 117, "loss": 1.7871, "lr": 5.914655987361934e-06, "epoch": 0.4700854700854701, "percentage": 47.01, "elapsed_time": "2:54:27", "remaining_time": "3:16:39"}
|
56 |
+
{"current_steps": 56, "total_steps": 117, "loss": 1.8018, "lr": 5.77518299832099e-06, "epoch": 0.47863247863247865, "percentage": 47.86, "elapsed_time": "2:57:36", "remaining_time": "3:13:27"}
|
57 |
+
{"current_steps": 57, "total_steps": 117, "loss": 1.8044, "lr": 5.635089098734394e-06, "epoch": 0.48717948717948717, "percentage": 48.72, "elapsed_time": "3:00:45", "remaining_time": "3:10:16"}
|
58 |
+
{"current_steps": 58, "total_steps": 117, "loss": 1.8005, "lr": 5.49448650182125e-06, "epoch": 0.49572649572649574, "percentage": 49.57, "elapsed_time": "3:03:54", "remaining_time": "3:07:05"}
|
59 |
+
{"current_steps": 59, "total_steps": 117, "loss": 1.8026, "lr": 5.353487828259973e-06, "epoch": 0.5042735042735043, "percentage": 50.43, "elapsed_time": "3:07:03", "remaining_time": "3:03:52"}
|
60 |
+
{"current_steps": 60, "total_steps": 117, "loss": 1.7954, "lr": 5.212206015980742e-06, "epoch": 0.5128205128205128, "percentage": 51.28, "elapsed_time": "3:10:11", "remaining_time": "3:00:40"}
|
61 |
+
{"current_steps": 61, "total_steps": 117, "loss": 1.7961, "lr": 5.070754229703811e-06, "epoch": 0.5213675213675214, "percentage": 52.14, "elapsed_time": "3:13:18", "remaining_time": "2:57:28"}
|
62 |
+
{"current_steps": 62, "total_steps": 117, "loss": 1.8036, "lr": 4.929245770296191e-06, "epoch": 0.5299145299145299, "percentage": 52.99, "elapsed_time": "3:16:27", "remaining_time": "2:54:16"}
|
63 |
+
{"current_steps": 63, "total_steps": 117, "loss": 1.8029, "lr": 4.78779398401926e-06, "epoch": 0.5384615384615384, "percentage": 53.85, "elapsed_time": "3:19:36", "remaining_time": "2:51:05"}
|
64 |
+
{"current_steps": 64, "total_steps": 117, "loss": 1.8026, "lr": 4.646512171740028e-06, "epoch": 0.5470085470085471, "percentage": 54.7, "elapsed_time": "3:22:44", "remaining_time": "2:47:53"}
|
65 |
+
{"current_steps": 65, "total_steps": 117, "loss": 1.8079, "lr": 4.505513498178752e-06, "epoch": 0.5555555555555556, "percentage": 55.56, "elapsed_time": "3:25:51", "remaining_time": "2:44:41"}
|
66 |
+
{"current_steps": 66, "total_steps": 117, "loss": 1.8008, "lr": 4.364910901265607e-06, "epoch": 0.5641025641025641, "percentage": 56.41, "elapsed_time": "3:29:00", "remaining_time": "2:41:30"}
|
67 |
+
{"current_steps": 67, "total_steps": 117, "loss": 1.7983, "lr": 4.224817001679011e-06, "epoch": 0.5726495726495726, "percentage": 57.26, "elapsed_time": "3:32:12", "remaining_time": "2:38:21"}
|
68 |
+
{"current_steps": 68, "total_steps": 117, "loss": 1.799, "lr": 4.085344012638067e-06, "epoch": 0.5811965811965812, "percentage": 58.12, "elapsed_time": "3:35:21", "remaining_time": "2:35:11"}
|
69 |
+
{"current_steps": 69, "total_steps": 117, "loss": 1.7981, "lr": 3.94660365002137e-06, "epoch": 0.5897435897435898, "percentage": 58.97, "elapsed_time": "3:38:31", "remaining_time": "2:32:01"}
|
70 |
+
{"current_steps": 70, "total_steps": 117, "loss": 1.7983, "lr": 3.808707042884176e-06, "epoch": 0.5982905982905983, "percentage": 59.83, "elapsed_time": "3:41:40", "remaining_time": "2:28:50"}
|
71 |
+
{"current_steps": 71, "total_steps": 117, "loss": 1.7924, "lr": 3.6717646444456196e-06, "epoch": 0.6068376068376068, "percentage": 60.68, "elapsed_time": "3:44:51", "remaining_time": "2:25:41"}
|
72 |
+
{"current_steps": 72, "total_steps": 117, "loss": 1.799, "lr": 3.5358861436172487e-06, "epoch": 0.6153846153846154, "percentage": 61.54, "elapsed_time": "3:48:00", "remaining_time": "2:22:30"}
|
73 |
+
{"current_steps": 73, "total_steps": 117, "loss": 1.8005, "lr": 3.401180377143774e-06, "epoch": 0.6239316239316239, "percentage": 62.39, "elapsed_time": "3:51:11", "remaining_time": "2:19:20"}
|
74 |
+
{"current_steps": 74, "total_steps": 117, "loss": 1.7956, "lr": 3.2677552424263836e-06, "epoch": 0.6324786324786325, "percentage": 63.25, "elapsed_time": "3:54:20", "remaining_time": "2:16:10"}
|
75 |
+
{"current_steps": 75, "total_steps": 117, "loss": 1.798, "lr": 3.1357176110984578e-06, "epoch": 0.6410256410256411, "percentage": 64.1, "elapsed_time": "3:57:29", "remaining_time": "2:12:59"}
|
76 |
+
{"current_steps": 76, "total_steps": 117, "loss": 1.7934, "lr": 3.0051732434229185e-06, "epoch": 0.6495726495726496, "percentage": 64.96, "elapsed_time": "4:00:37", "remaining_time": "2:09:48"}
|
77 |
+
{"current_steps": 77, "total_steps": 117, "loss": 1.8012, "lr": 2.8762267035797607e-06, "epoch": 0.6581196581196581, "percentage": 65.81, "elapsed_time": "4:03:46", "remaining_time": "2:06:37"}
|
78 |
+
{"current_steps": 78, "total_steps": 117, "loss": 1.7915, "lr": 2.748981275911633e-06, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "4:06:54", "remaining_time": "2:03:27"}
|
79 |
+
{"current_steps": 79, "total_steps": 117, "loss": 1.7867, "lr": 2.6235388821945497e-06, "epoch": 0.6752136752136753, "percentage": 67.52, "elapsed_time": "4:10:05", "remaining_time": "2:00:17"}
|
80 |
+
{"current_steps": 80, "total_steps": 117, "loss": 1.7952, "lr": 2.5000000000000015e-06, "epoch": 0.6837606837606838, "percentage": 68.38, "elapsed_time": "4:13:13", "remaining_time": "1:57:07"}
|
81 |
+
{"current_steps": 81, "total_steps": 117, "loss": 1.8026, "lr": 2.3784635822138424e-06, "epoch": 0.6923076923076923, "percentage": 69.23, "elapsed_time": "4:16:22", "remaining_time": "1:53:56"}
|
82 |
+
{"current_steps": 82, "total_steps": 117, "loss": 1.7956, "lr": 2.2590269777764516e-06, "epoch": 0.7008547008547008, "percentage": 70.09, "elapsed_time": "4:19:32", "remaining_time": "1:50:46"}
|
83 |
+
{"current_steps": 83, "total_steps": 117, "loss": 1.7947, "lr": 2.141785853707607e-06, "epoch": 0.7094017094017094, "percentage": 70.94, "elapsed_time": "4:22:41", "remaining_time": "1:47:36"}
|
84 |
+
{"current_steps": 84, "total_steps": 117, "loss": 1.7963, "lr": 2.0268341184785674e-06, "epoch": 0.717948717948718, "percentage": 71.79, "elapsed_time": "4:25:50", "remaining_time": "1:44:26"}
|
85 |
+
{"current_steps": 85, "total_steps": 117, "loss": 1.7974, "lr": 1.9142638467927254e-06, "epoch": 0.7264957264957265, "percentage": 72.65, "elapsed_time": "4:28:59", "remaining_time": "1:41:15"}
|
86 |
+
{"current_steps": 86, "total_steps": 117, "loss": 1.794, "lr": 1.8041652058350768e-06, "epoch": 0.7350427350427351, "percentage": 73.5, "elapsed_time": "4:32:07", "remaining_time": "1:38:05"}
|
87 |
+
{"current_steps": 87, "total_steps": 117, "loss": 1.8017, "lr": 1.6966263830495939e-06, "epoch": 0.7435897435897436, "percentage": 74.36, "elapsed_time": "4:35:14", "remaining_time": "1:34:54"}
|
88 |
+
{"current_steps": 88, "total_steps": 117, "loss": 1.7874, "lr": 1.5917335155023368e-06, "epoch": 0.7521367521367521, "percentage": 75.21, "elapsed_time": "4:38:24", "remaining_time": "1:31:44"}
|
89 |
+
{"current_steps": 89, "total_steps": 117, "loss": 1.8012, "lr": 1.4895706208868876e-06, "epoch": 0.7606837606837606, "percentage": 76.07, "elapsed_time": "4:41:32", "remaining_time": "1:28:34"}
|
90 |
+
{"current_steps": 90, "total_steps": 117, "loss": 1.8029, "lr": 1.390219530227378e-06, "epoch": 0.7692307692307693, "percentage": 76.92, "elapsed_time": "4:44:40", "remaining_time": "1:25:24"}
|
91 |
+
{"current_steps": 91, "total_steps": 117, "loss": 1.7955, "lr": 1.2937598223330006e-06, "epoch": 0.7777777777777778, "percentage": 77.78, "elapsed_time": "4:47:48", "remaining_time": "1:22:13"}
|
92 |
+
{"current_steps": 92, "total_steps": 117, "loss": 1.7919, "lr": 1.2002687600565138e-06, "epoch": 0.7863247863247863, "percentage": 78.63, "elapsed_time": "4:50:56", "remaining_time": "1:19:03"}
|
93 |
+
{"current_steps": 93, "total_steps": 117, "loss": 1.794, "lr": 1.1098212284078037e-06, "epoch": 0.7948717948717948, "percentage": 79.49, "elapsed_time": "4:54:04", "remaining_time": "1:15:53"}
|
94 |
+
{"current_steps": 94, "total_steps": 117, "loss": 1.7978, "lr": 1.0224896745720513e-06, "epoch": 0.8034188034188035, "percentage": 80.34, "elapsed_time": "4:57:12", "remaining_time": "1:12:43"}
|
95 |
+
{"current_steps": 95, "total_steps": 117, "loss": 1.8013, "lr": 9.383440498805712e-07, "epoch": 0.811965811965812, "percentage": 81.2, "elapsed_time": "5:00:24", "remaining_time": "1:09:34"}
|
96 |
+
{"current_steps": 96, "total_steps": 117, "loss": 1.7928, "lr": 8.574517537807897e-07, "epoch": 0.8205128205128205, "percentage": 82.05, "elapsed_time": "5:03:33", "remaining_time": "1:06:24"}
|
97 |
+
{"current_steps": 97, "total_steps": 117, "loss": 1.7875, "lr": 7.798775798502484e-07, "epoch": 0.8290598290598291, "percentage": 82.91, "elapsed_time": "5:06:43", "remaining_time": "1:03:14"}
|
98 |
+
{"current_steps": 98, "total_steps": 117, "loss": 1.7868, "lr": 7.056836638978698e-07, "epoch": 0.8376068376068376, "percentage": 83.76, "elapsed_time": "5:09:54", "remaining_time": "1:00:05"}
|
99 |
+
{"current_steps": 99, "total_steps": 117, "loss": 1.7947, "lr": 6.349294341940593e-07, "epoch": 0.8461538461538461, "percentage": 84.62, "elapsed_time": "5:13:05", "remaining_time": "0:56:55"}
|
100 |
+
{"current_steps": 100, "total_steps": 117, "loss": 1.7933, "lr": 5.676715638695063e-07, "epoch": 0.8547008547008547, "percentage": 85.47, "elapsed_time": "5:16:13", "remaining_time": "0:53:45"}
|
101 |
+
{"current_steps": 101, "total_steps": 117, "loss": 1.7983, "lr": 5.039639255208156e-07, "epoch": 0.8632478632478633, "percentage": 86.32, "elapsed_time": "5:21:46", "remaining_time": "0:50:58"}
|
102 |
+
{"current_steps": 102, "total_steps": 117, "loss": 1.7923, "lr": 4.43857548059321e-07, "epoch": 0.8717948717948718, "percentage": 87.18, "elapsed_time": "5:24:55", "remaining_time": "0:47:46"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbcb0763afe7ddb533417233ceab289a75850df67ec6d1a045ba6d98406b7a67
|
3 |
+
size 7875
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|