Upload with huggingface_hub
Browse files- config.json +23 -0
- generation_config.json +7 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +184 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "JackFram/llama-160m",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 768,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 12,
|
15 |
+
"num_hidden_layers": 12,
|
16 |
+
"pad_token_id": 1,
|
17 |
+
"rms_norm_eps": 1e-06,
|
18 |
+
"tie_word_embeddings": false,
|
19 |
+
"torch_dtype": "float32",
|
20 |
+
"transformers_version": "4.28.0.dev0",
|
21 |
+
"use_cache": false,
|
22 |
+
"vocab_size": 32000
|
23 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.28.0.dev0"
|
7 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78061341248b59a753aa4985e6afe1d59c37b3b2d1deec2bbc20b64fd91c8037
|
3 |
+
size 1299404037
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c94d532697d502e30ca23b3168631ec80574e617e710c4171b2a8d68ca72cb56
|
3 |
+
size 649710859
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8bd695bd472710b74beff7ecf0f66d54c9600ea1116f2be15428d227ee3aa0c
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0ba46f8cf4335cacf6fdf3a85777b803172634e815cf4b606ae6c2c7c50ef9c
|
3 |
+
size 623
|
trainer_state.json
ADDED
@@ -0,0 +1,184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 11.991695501730105,
|
5 |
+
"global_step": 4332,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 0.00027499999999999996,
|
13 |
+
"loss": 2.3243,
|
14 |
+
"step": 361
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 2.3360440731048584,
|
19 |
+
"eval_runtime": 81.7171,
|
20 |
+
"eval_samples_per_second": 457.077,
|
21 |
+
"eval_steps_per_second": 57.136,
|
22 |
+
"step": 361
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"learning_rate": 0.00025,
|
27 |
+
"loss": 1.9943,
|
28 |
+
"step": 722
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_loss": 2.3849265575408936,
|
33 |
+
"eval_runtime": 80.8133,
|
34 |
+
"eval_samples_per_second": 462.189,
|
35 |
+
"eval_steps_per_second": 57.775,
|
36 |
+
"step": 722
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"learning_rate": 0.000225,
|
41 |
+
"loss": 1.7331,
|
42 |
+
"step": 1083
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"eval_loss": 2.5010716915130615,
|
47 |
+
"eval_runtime": 80.8638,
|
48 |
+
"eval_samples_per_second": 461.9,
|
49 |
+
"eval_steps_per_second": 57.739,
|
50 |
+
"step": 1083
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"learning_rate": 0.00019993074792243765,
|
55 |
+
"loss": 1.463,
|
56 |
+
"step": 1445
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"eval_loss": 2.7065136432647705,
|
61 |
+
"eval_runtime": 80.5929,
|
62 |
+
"eval_samples_per_second": 463.453,
|
63 |
+
"eval_steps_per_second": 57.933,
|
64 |
+
"step": 1445
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 5.0,
|
68 |
+
"learning_rate": 0.00017493074792243764,
|
69 |
+
"loss": 1.1969,
|
70 |
+
"step": 1806
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 5.0,
|
74 |
+
"eval_loss": 2.9511666297912598,
|
75 |
+
"eval_runtime": 80.4169,
|
76 |
+
"eval_samples_per_second": 464.467,
|
77 |
+
"eval_steps_per_second": 58.06,
|
78 |
+
"step": 1806
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 6.0,
|
82 |
+
"learning_rate": 0.00014993074792243766,
|
83 |
+
"loss": 0.9339,
|
84 |
+
"step": 2167
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"eval_loss": 3.2412941455841064,
|
89 |
+
"eval_runtime": 80.5491,
|
90 |
+
"eval_samples_per_second": 463.705,
|
91 |
+
"eval_steps_per_second": 57.965,
|
92 |
+
"step": 2167
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 7.0,
|
96 |
+
"learning_rate": 0.00012493074792243767,
|
97 |
+
"loss": 0.6915,
|
98 |
+
"step": 2528
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_loss": 3.56394362449646,
|
103 |
+
"eval_runtime": 79.8139,
|
104 |
+
"eval_samples_per_second": 467.976,
|
105 |
+
"eval_steps_per_second": 58.499,
|
106 |
+
"step": 2528
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 8.0,
|
110 |
+
"learning_rate": 9.986149584487533e-05,
|
111 |
+
"loss": 0.4811,
|
112 |
+
"step": 2890
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 8.0,
|
116 |
+
"eval_loss": 3.897730827331543,
|
117 |
+
"eval_runtime": 80.0943,
|
118 |
+
"eval_samples_per_second": 466.338,
|
119 |
+
"eval_steps_per_second": 58.294,
|
120 |
+
"step": 2890
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 9.0,
|
124 |
+
"learning_rate": 7.486149584487535e-05,
|
125 |
+
"loss": 0.3195,
|
126 |
+
"step": 3251
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 9.0,
|
130 |
+
"eval_loss": 4.2111005783081055,
|
131 |
+
"eval_runtime": 79.9229,
|
132 |
+
"eval_samples_per_second": 467.338,
|
133 |
+
"eval_steps_per_second": 58.419,
|
134 |
+
"step": 3251
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 10.0,
|
138 |
+
"learning_rate": 4.986149584487534e-05,
|
139 |
+
"loss": 0.211,
|
140 |
+
"step": 3612
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.0,
|
144 |
+
"eval_loss": 4.46787166595459,
|
145 |
+
"eval_runtime": 80.4105,
|
146 |
+
"eval_samples_per_second": 464.504,
|
147 |
+
"eval_steps_per_second": 58.065,
|
148 |
+
"step": 3612
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 11.0,
|
152 |
+
"learning_rate": 2.4861495844875343e-05,
|
153 |
+
"loss": 0.1515,
|
154 |
+
"step": 3973
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 11.0,
|
158 |
+
"eval_loss": 4.6477370262146,
|
159 |
+
"eval_runtime": 80.1153,
|
160 |
+
"eval_samples_per_second": 466.216,
|
161 |
+
"eval_steps_per_second": 58.279,
|
162 |
+
"step": 3973
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 11.99,
|
166 |
+
"learning_rate": 0.0,
|
167 |
+
"loss": 0.1233,
|
168 |
+
"step": 4332
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 11.99,
|
172 |
+
"eval_loss": 4.7357659339904785,
|
173 |
+
"eval_runtime": 80.0925,
|
174 |
+
"eval_samples_per_second": 466.348,
|
175 |
+
"eval_steps_per_second": 58.295,
|
176 |
+
"step": 4332
|
177 |
+
}
|
178 |
+
],
|
179 |
+
"max_steps": 4332,
|
180 |
+
"num_train_epochs": 12,
|
181 |
+
"total_flos": 1.705389820458624e+17,
|
182 |
+
"trial_name": null,
|
183 |
+
"trial_params": null
|
184 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d9920ef5e4c1541d141de40e5b4a77b8ad3a3f0542394222f5a8a9f674db15d
|
3 |
+
size 3567
|