CesarChaMal commited on
Commit
fa07f00
·
verified ·
1 Parent(s): af6613d

Upload folder using huggingface_hub

Browse files
checkpoint-200/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}
checkpoint-200/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1280,
16
+ "n_head": 20,
17
+ "n_inner": null,
18
+ "n_layer": 36,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "conversational": {
31
+ "max_length": 1000
32
+ }
33
+ },
34
+ "transformers_version": "4.56.2",
35
+ "use_cache": true,
36
+ "vocab_size": 50257
37
+ }
checkpoint-200/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.56.2"
6
+ }
checkpoint-200/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26f8a5e38ece067ae146b07ba63859238b470cfc62f7710e7b3052ec331fca8
3
+ size 3096165928
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2779c85323bc78b26d7c7adc894bfdf22bc64cb38abd17dc35786c440fb43a70
3
+ size 6192618087
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b43dacea68535bc4c04dcf4476712b33787fff1df295403444e3a9eea04f1e
3
+ size 14645
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa296abc5d84df05f0c53a8649e3e3fcb24d63cdc9ca21aa4cdd6ecf1b15277
3
+ size 1465
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "extra_special_tokens": {},
19
+ "model_max_length": 1024,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,314 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 8.0,
6
+ "eval_steps": 500,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.2,
14
+ "grad_norm": 10.956440925598145,
15
+ "learning_rate": 2e-05,
16
+ "loss": 8.4858,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.4,
21
+ "grad_norm": 7.161553382873535,
22
+ "learning_rate": 4.5e-05,
23
+ "loss": 6.9312,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.6,
28
+ "grad_norm": 6.012239456176758,
29
+ "learning_rate": 4.8947368421052635e-05,
30
+ "loss": 5.9262,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.8,
35
+ "grad_norm": 4.727581024169922,
36
+ "learning_rate": 4.7631578947368424e-05,
37
+ "loss": 4.2748,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "grad_norm": 4.418272018432617,
43
+ "learning_rate": 4.6315789473684214e-05,
44
+ "loss": 4.3024,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 1.2,
49
+ "grad_norm": 88.75386810302734,
50
+ "learning_rate": 4.5e-05,
51
+ "loss": 3.4231,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 1.4,
56
+ "grad_norm": 4.03700590133667,
57
+ "learning_rate": 4.368421052631579e-05,
58
+ "loss": 3.2013,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 1.6,
63
+ "grad_norm": 4.357565879821777,
64
+ "learning_rate": 4.236842105263158e-05,
65
+ "loss": 2.7781,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 1.8,
70
+ "grad_norm": 3.961747169494629,
71
+ "learning_rate": 4.105263157894737e-05,
72
+ "loss": 2.6868,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 2.0,
77
+ "grad_norm": 4.623239040374756,
78
+ "learning_rate": 3.973684210526316e-05,
79
+ "loss": 2.625,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 2.2,
84
+ "grad_norm": 3.8357508182525635,
85
+ "learning_rate": 3.842105263157895e-05,
86
+ "loss": 2.253,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 2.4,
91
+ "grad_norm": 3.983182907104492,
92
+ "learning_rate": 3.710526315789474e-05,
93
+ "loss": 1.7868,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 2.6,
98
+ "grad_norm": 4.157156944274902,
99
+ "learning_rate": 3.578947368421053e-05,
100
+ "loss": 2.158,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 2.8,
105
+ "grad_norm": 3.965906858444214,
106
+ "learning_rate": 3.447368421052632e-05,
107
+ "loss": 2.1846,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 3.0,
112
+ "grad_norm": 2.782144546508789,
113
+ "learning_rate": 3.3157894736842106e-05,
114
+ "loss": 2.1961,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 3.2,
119
+ "grad_norm": 3.1297521591186523,
120
+ "learning_rate": 3.1842105263157895e-05,
121
+ "loss": 1.4554,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 3.4,
126
+ "grad_norm": 3.906054735183716,
127
+ "learning_rate": 3.0526315789473684e-05,
128
+ "loss": 1.6128,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 3.6,
133
+ "grad_norm": 4.510481834411621,
134
+ "learning_rate": 2.9210526315789477e-05,
135
+ "loss": 1.4562,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 3.8,
140
+ "grad_norm": 3.879499673843384,
141
+ "learning_rate": 2.7894736842105263e-05,
142
+ "loss": 1.5626,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 4.0,
147
+ "grad_norm": 3.139321804046631,
148
+ "learning_rate": 2.6578947368421052e-05,
149
+ "loss": 1.5182,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 4.2,
154
+ "grad_norm": 4.304155349731445,
155
+ "learning_rate": 2.5263157894736845e-05,
156
+ "loss": 1.2072,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 4.4,
161
+ "grad_norm": 3.2858364582061768,
162
+ "learning_rate": 2.394736842105263e-05,
163
+ "loss": 1.1877,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 4.6,
168
+ "grad_norm": 3.662776231765747,
169
+ "learning_rate": 2.2631578947368423e-05,
170
+ "loss": 1.1419,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 4.8,
175
+ "grad_norm": 3.3753128051757812,
176
+ "learning_rate": 2.1315789473684212e-05,
177
+ "loss": 1.0726,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 5.0,
182
+ "grad_norm": 3.4297780990600586,
183
+ "learning_rate": 2e-05,
184
+ "loss": 1.16,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 5.2,
189
+ "grad_norm": 3.373642921447754,
190
+ "learning_rate": 1.868421052631579e-05,
191
+ "loss": 1.1555,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 5.4,
196
+ "grad_norm": 3.190053701400757,
197
+ "learning_rate": 1.736842105263158e-05,
198
+ "loss": 1.0915,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 5.6,
203
+ "grad_norm": 3.1136105060577393,
204
+ "learning_rate": 1.605263157894737e-05,
205
+ "loss": 0.6836,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 5.8,
210
+ "grad_norm": 4.21175479888916,
211
+ "learning_rate": 1.4736842105263157e-05,
212
+ "loss": 0.8947,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 6.0,
217
+ "grad_norm": 3.606748342514038,
218
+ "learning_rate": 1.3421052631578948e-05,
219
+ "loss": 1.0125,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 6.2,
224
+ "grad_norm": 2.8370039463043213,
225
+ "learning_rate": 1.2105263157894737e-05,
226
+ "loss": 0.6748,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 6.4,
231
+ "grad_norm": 5.026889801025391,
232
+ "learning_rate": 1.0789473684210526e-05,
233
+ "loss": 0.7417,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 6.6,
238
+ "grad_norm": 4.09874153137207,
239
+ "learning_rate": 9.473684210526317e-06,
240
+ "loss": 0.836,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 6.8,
245
+ "grad_norm": 3.5339722633361816,
246
+ "learning_rate": 8.157894736842106e-06,
247
+ "loss": 0.7355,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 7.0,
252
+ "grad_norm": 3.718662738800049,
253
+ "learning_rate": 6.842105263157896e-06,
254
+ "loss": 0.817,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 7.2,
259
+ "grad_norm": 2.443586826324463,
260
+ "learning_rate": 5.526315789473684e-06,
261
+ "loss": 0.6803,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 7.4,
266
+ "grad_norm": 4.012761116027832,
267
+ "learning_rate": 4.210526315789474e-06,
268
+ "loss": 0.644,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 7.6,
273
+ "grad_norm": 2.8739984035491943,
274
+ "learning_rate": 2.8947368421052634e-06,
275
+ "loss": 0.5224,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 7.8,
280
+ "grad_norm": 3.989027261734009,
281
+ "learning_rate": 1.5789473684210528e-06,
282
+ "loss": 0.6857,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 8.0,
287
+ "grad_norm": 4.327380180358887,
288
+ "learning_rate": 2.6315789473684213e-07,
289
+ "loss": 0.7937,
290
+ "step": 200
291
+ }
292
+ ],
293
+ "logging_steps": 5,
294
+ "max_steps": 200,
295
+ "num_input_tokens_seen": 0,
296
+ "num_train_epochs": 8,
297
+ "save_steps": 25,
298
+ "stateful_callbacks": {
299
+ "TrainerControl": {
300
+ "args": {
301
+ "should_epoch_stop": false,
302
+ "should_evaluate": false,
303
+ "should_log": false,
304
+ "should_save": true,
305
+ "should_training_stop": true
306
+ },
307
+ "attributes": {}
308
+ }
309
+ },
310
+ "total_flos": 2611410370560000.0,
311
+ "train_batch_size": 2,
312
+ "trial_name": null,
313
+ "trial_params": null
314
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2039870addd20c9c46968fda9ef3ee921b26ae73c3d39d7d352148d2dec5c2
3
+ size 5777
checkpoint-200/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -5,7 +5,7 @@
5
  ],
6
  "attn_pdrop": 0.1,
7
  "bos_token_id": 50256,
8
- "dtype": "float16",
9
  "embd_pdrop": 0.1,
10
  "eos_token_id": 50256,
11
  "initializer_range": 0.02,
 
5
  ],
6
  "attn_pdrop": 0.1,
7
  "bos_token_id": 50256,
8
+ "dtype": "float32",
9
  "embd_pdrop": 0.1,
10
  "eos_token_id": 50256,
11
  "initializer_range": 0.02,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dae6a24423332f62a0b844e5b48d562159c5b800726ad4cb9ee29299d6ead2c1
3
- size 1548105416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26f8a5e38ece067ae146b07ba63859238b470cfc62f7710e7b3052ec331fca8
3
+ size 3096165928
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 768,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 768
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 50256,
16
- "pad_type_id": 0,
17
- "pad_token": "<|endoftext|>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 50256,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 50256,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:727c690971fc5ec923ae6674f94581184a426a8d33ff9d1b0381b9e5b434b81f
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2039870addd20c9c46968fda9ef3ee921b26ae73c3d39d7d352148d2dec5c2
3
  size 5777
training_log.json CHANGED
@@ -1,32 +1,291 @@
1
  [
2
  {
3
- "loss": 684.0879,
4
- "grad_norm": NaN,
5
- "learning_rate": 2.7e-06,
6
- "epoch": 0.8,
 
 
 
 
 
 
 
7
  "step": 10
8
  },
9
  {
10
- "loss": 0.0,
11
- "grad_norm": NaN,
12
- "learning_rate": 5.7000000000000005e-06,
13
- "epoch": 1.56,
 
 
 
 
 
 
 
14
  "step": 20
15
  },
16
  {
17
- "loss": 0.0,
18
- "grad_norm": NaN,
19
- "learning_rate": 8.7e-06,
20
- "epoch": 2.32,
 
 
 
 
 
 
 
21
  "step": 30
22
  },
23
  {
24
- "train_runtime": 105.4702,
25
- "train_samples_per_second": 2.844,
26
- "train_steps_per_second": 0.37,
27
- "total_flos": 979278888960000.0,
28
- "train_loss": 175.40715144230768,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  "epoch": 3.0,
30
- "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  }
32
  ]
 
1
  [
2
  {
3
+ "loss": 8.4858,
4
+ "grad_norm": 10.956440925598145,
5
+ "learning_rate": 2e-05,
6
+ "epoch": 0.2,
7
+ "step": 5
8
+ },
9
+ {
10
+ "loss": 6.9312,
11
+ "grad_norm": 7.161553382873535,
12
+ "learning_rate": 4.5e-05,
13
+ "epoch": 0.4,
14
  "step": 10
15
  },
16
  {
17
+ "loss": 5.9262,
18
+ "grad_norm": 6.012239456176758,
19
+ "learning_rate": 4.8947368421052635e-05,
20
+ "epoch": 0.6,
21
+ "step": 15
22
+ },
23
+ {
24
+ "loss": 4.2748,
25
+ "grad_norm": 4.727581024169922,
26
+ "learning_rate": 4.7631578947368424e-05,
27
+ "epoch": 0.8,
28
  "step": 20
29
  },
30
  {
31
+ "loss": 4.3024,
32
+ "grad_norm": 4.418272018432617,
33
+ "learning_rate": 4.6315789473684214e-05,
34
+ "epoch": 1.0,
35
+ "step": 25
36
+ },
37
+ {
38
+ "loss": 3.4231,
39
+ "grad_norm": 88.75386810302734,
40
+ "learning_rate": 4.5e-05,
41
+ "epoch": 1.2,
42
  "step": 30
43
  },
44
  {
45
+ "loss": 3.2013,
46
+ "grad_norm": 4.03700590133667,
47
+ "learning_rate": 4.368421052631579e-05,
48
+ "epoch": 1.4,
49
+ "step": 35
50
+ },
51
+ {
52
+ "loss": 2.7781,
53
+ "grad_norm": 4.357565879821777,
54
+ "learning_rate": 4.236842105263158e-05,
55
+ "epoch": 1.6,
56
+ "step": 40
57
+ },
58
+ {
59
+ "loss": 2.6868,
60
+ "grad_norm": 3.961747169494629,
61
+ "learning_rate": 4.105263157894737e-05,
62
+ "epoch": 1.8,
63
+ "step": 45
64
+ },
65
+ {
66
+ "loss": 2.625,
67
+ "grad_norm": 4.623239040374756,
68
+ "learning_rate": 3.973684210526316e-05,
69
+ "epoch": 2.0,
70
+ "step": 50
71
+ },
72
+ {
73
+ "loss": 2.253,
74
+ "grad_norm": 3.8357508182525635,
75
+ "learning_rate": 3.842105263157895e-05,
76
+ "epoch": 2.2,
77
+ "step": 55
78
+ },
79
+ {
80
+ "loss": 1.7868,
81
+ "grad_norm": 3.983182907104492,
82
+ "learning_rate": 3.710526315789474e-05,
83
+ "epoch": 2.4,
84
+ "step": 60
85
+ },
86
+ {
87
+ "loss": 2.158,
88
+ "grad_norm": 4.157156944274902,
89
+ "learning_rate": 3.578947368421053e-05,
90
+ "epoch": 2.6,
91
+ "step": 65
92
+ },
93
+ {
94
+ "loss": 2.1846,
95
+ "grad_norm": 3.965906858444214,
96
+ "learning_rate": 3.447368421052632e-05,
97
+ "epoch": 2.8,
98
+ "step": 70
99
+ },
100
+ {
101
+ "loss": 2.1961,
102
+ "grad_norm": 2.782144546508789,
103
+ "learning_rate": 3.3157894736842106e-05,
104
  "epoch": 3.0,
105
+ "step": 75
106
+ },
107
+ {
108
+ "loss": 1.4554,
109
+ "grad_norm": 3.1297521591186523,
110
+ "learning_rate": 3.1842105263157895e-05,
111
+ "epoch": 3.2,
112
+ "step": 80
113
+ },
114
+ {
115
+ "loss": 1.6128,
116
+ "grad_norm": 3.906054735183716,
117
+ "learning_rate": 3.0526315789473684e-05,
118
+ "epoch": 3.4,
119
+ "step": 85
120
+ },
121
+ {
122
+ "loss": 1.4562,
123
+ "grad_norm": 4.510481834411621,
124
+ "learning_rate": 2.9210526315789477e-05,
125
+ "epoch": 3.6,
126
+ "step": 90
127
+ },
128
+ {
129
+ "loss": 1.5626,
130
+ "grad_norm": 3.879499673843384,
131
+ "learning_rate": 2.7894736842105263e-05,
132
+ "epoch": 3.8,
133
+ "step": 95
134
+ },
135
+ {
136
+ "loss": 1.5182,
137
+ "grad_norm": 3.139321804046631,
138
+ "learning_rate": 2.6578947368421052e-05,
139
+ "epoch": 4.0,
140
+ "step": 100
141
+ },
142
+ {
143
+ "loss": 1.2072,
144
+ "grad_norm": 4.304155349731445,
145
+ "learning_rate": 2.5263157894736845e-05,
146
+ "epoch": 4.2,
147
+ "step": 105
148
+ },
149
+ {
150
+ "loss": 1.1877,
151
+ "grad_norm": 3.2858364582061768,
152
+ "learning_rate": 2.394736842105263e-05,
153
+ "epoch": 4.4,
154
+ "step": 110
155
+ },
156
+ {
157
+ "loss": 1.1419,
158
+ "grad_norm": 3.662776231765747,
159
+ "learning_rate": 2.2631578947368423e-05,
160
+ "epoch": 4.6,
161
+ "step": 115
162
+ },
163
+ {
164
+ "loss": 1.0726,
165
+ "grad_norm": 3.3753128051757812,
166
+ "learning_rate": 2.1315789473684212e-05,
167
+ "epoch": 4.8,
168
+ "step": 120
169
+ },
170
+ {
171
+ "loss": 1.16,
172
+ "grad_norm": 3.4297780990600586,
173
+ "learning_rate": 2e-05,
174
+ "epoch": 5.0,
175
+ "step": 125
176
+ },
177
+ {
178
+ "loss": 1.1555,
179
+ "grad_norm": 3.373642921447754,
180
+ "learning_rate": 1.868421052631579e-05,
181
+ "epoch": 5.2,
182
+ "step": 130
183
+ },
184
+ {
185
+ "loss": 1.0915,
186
+ "grad_norm": 3.190053701400757,
187
+ "learning_rate": 1.736842105263158e-05,
188
+ "epoch": 5.4,
189
+ "step": 135
190
+ },
191
+ {
192
+ "loss": 0.6836,
193
+ "grad_norm": 3.1136105060577393,
194
+ "learning_rate": 1.605263157894737e-05,
195
+ "epoch": 5.6,
196
+ "step": 140
197
+ },
198
+ {
199
+ "loss": 0.8947,
200
+ "grad_norm": 4.21175479888916,
201
+ "learning_rate": 1.4736842105263157e-05,
202
+ "epoch": 5.8,
203
+ "step": 145
204
+ },
205
+ {
206
+ "loss": 1.0125,
207
+ "grad_norm": 3.606748342514038,
208
+ "learning_rate": 1.3421052631578948e-05,
209
+ "epoch": 6.0,
210
+ "step": 150
211
+ },
212
+ {
213
+ "loss": 0.6748,
214
+ "grad_norm": 2.8370039463043213,
215
+ "learning_rate": 1.2105263157894737e-05,
216
+ "epoch": 6.2,
217
+ "step": 155
218
+ },
219
+ {
220
+ "loss": 0.7417,
221
+ "grad_norm": 5.026889801025391,
222
+ "learning_rate": 1.0789473684210526e-05,
223
+ "epoch": 6.4,
224
+ "step": 160
225
+ },
226
+ {
227
+ "loss": 0.836,
228
+ "grad_norm": 4.09874153137207,
229
+ "learning_rate": 9.473684210526317e-06,
230
+ "epoch": 6.6,
231
+ "step": 165
232
+ },
233
+ {
234
+ "loss": 0.7355,
235
+ "grad_norm": 3.5339722633361816,
236
+ "learning_rate": 8.157894736842106e-06,
237
+ "epoch": 6.8,
238
+ "step": 170
239
+ },
240
+ {
241
+ "loss": 0.817,
242
+ "grad_norm": 3.718662738800049,
243
+ "learning_rate": 6.842105263157896e-06,
244
+ "epoch": 7.0,
245
+ "step": 175
246
+ },
247
+ {
248
+ "loss": 0.6803,
249
+ "grad_norm": 2.443586826324463,
250
+ "learning_rate": 5.526315789473684e-06,
251
+ "epoch": 7.2,
252
+ "step": 180
253
+ },
254
+ {
255
+ "loss": 0.644,
256
+ "grad_norm": 4.012761116027832,
257
+ "learning_rate": 4.210526315789474e-06,
258
+ "epoch": 7.4,
259
+ "step": 185
260
+ },
261
+ {
262
+ "loss": 0.5224,
263
+ "grad_norm": 2.8739984035491943,
264
+ "learning_rate": 2.8947368421052634e-06,
265
+ "epoch": 7.6,
266
+ "step": 190
267
+ },
268
+ {
269
+ "loss": 0.6857,
270
+ "grad_norm": 3.989027261734009,
271
+ "learning_rate": 1.5789473684210528e-06,
272
+ "epoch": 7.8,
273
+ "step": 195
274
+ },
275
+ {
276
+ "loss": 0.7937,
277
+ "grad_norm": 4.327380180358887,
278
+ "learning_rate": 2.6315789473684213e-07,
279
+ "epoch": 8.0,
280
+ "step": 200
281
+ },
282
+ {
283
+ "train_runtime": 12626.9237,
284
+ "train_samples_per_second": 0.063,
285
+ "train_steps_per_second": 0.016,
286
+ "total_flos": 2611410370560000.0,
287
+ "train_loss": 2.0139254927635193,
288
+ "epoch": 8.0,
289
+ "step": 200
290
  }
291
  ]