DeepMount00 commited on
Commit
f609ee3
1 Parent(s): c42d2b0

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +46 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +1365 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "answerdotai/ModernBERT-base",
3
+ "architectures": [
4
+ "ModernBertForMaskedLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 1152,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 22,
37
+ "pad_token_id": 50283,
38
+ "position_embedding_type": "absolute",
39
+ "reference_compile": true,
40
+ "sep_token_id": 50282,
41
+ "sparse_pred_ignore_index": -100,
42
+ "sparse_prediction": false,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.48.0.dev0",
45
+ "vocab_size": 50368
46
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b3d304bf2c533b36cdde8c15d832c24dfeeddf7ed2ef833bc27d9c6dcb2e14
3
+ size 598635032
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d3357a9c520106e98f0827f5164e8281faa21197307d982fd1e29fa5b6defb
3
+ size 1197357242
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b45c0592bc4cca85b65697c5fc3df6315654d61aa7cac3bf6db35c10f3d202c
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d1eb85152dcf55ea6434f75a55f2dd53ed4d028afbac199cfec81681054f6f
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,1365 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.2660380601882935,
3
+ "best_model_checkpoint": "./bert_mlm_finetuned/checkpoint-900",
4
+ "epoch": 0.1152,
5
+ "eval_steps": 100,
6
+ "global_step": 900,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00064,
13
+ "grad_norm": 7.650606632232666,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 6.29,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.00128,
20
+ "grad_norm": 4.541823387145996,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 6.3815,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.00192,
27
+ "grad_norm": 4.245054721832275,
28
+ "learning_rate": 3e-06,
29
+ "loss": 6.2854,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.00256,
34
+ "grad_norm": 4.5587897300720215,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 6.0674,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.0032,
41
+ "grad_norm": 3.7703804969787598,
42
+ "learning_rate": 4.800000000000001e-06,
43
+ "loss": 6.2961,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.00384,
48
+ "grad_norm": 3.8425862789154053,
49
+ "learning_rate": 5.8e-06,
50
+ "loss": 6.3326,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.00448,
55
+ "grad_norm": 4.413463115692139,
56
+ "learning_rate": 6.800000000000001e-06,
57
+ "loss": 6.183,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.00512,
62
+ "grad_norm": 4.1980509757995605,
63
+ "learning_rate": 7.800000000000002e-06,
64
+ "loss": 6.2654,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.00576,
69
+ "grad_norm": 3.9166719913482666,
70
+ "learning_rate": 8.8e-06,
71
+ "loss": 6.0916,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.0064,
76
+ "grad_norm": 3.4706904888153076,
77
+ "learning_rate": 9.800000000000001e-06,
78
+ "loss": 6.103,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.00704,
83
+ "grad_norm": 5.138203144073486,
84
+ "learning_rate": 9.999998372356185e-06,
85
+ "loss": 6.2379,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.00768,
90
+ "grad_norm": 3.7806520462036133,
91
+ "learning_rate": 9.999991760055e-06,
92
+ "loss": 6.1776,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.00832,
97
+ "grad_norm": 3.5731871128082275,
98
+ "learning_rate": 9.999980061375427e-06,
99
+ "loss": 6.2082,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.00896,
104
+ "grad_norm": 3.661797285079956,
105
+ "learning_rate": 9.999963276329369e-06,
106
+ "loss": 6.0704,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.0096,
111
+ "grad_norm": 3.6181113719940186,
112
+ "learning_rate": 9.999941404933902e-06,
113
+ "loss": 6.2081,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.01024,
118
+ "grad_norm": 3.3162803649902344,
119
+ "learning_rate": 9.99991444721127e-06,
120
+ "loss": 5.8807,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.01088,
125
+ "grad_norm": 3.6022472381591797,
126
+ "learning_rate": 9.999882403188902e-06,
127
+ "loss": 6.1092,
128
+ "step": 85
129
+ },
130
+ {
131
+ "epoch": 0.01152,
132
+ "grad_norm": 7.291418552398682,
133
+ "learning_rate": 9.999845272899393e-06,
134
+ "loss": 5.7668,
135
+ "step": 90
136
+ },
137
+ {
138
+ "epoch": 0.01216,
139
+ "grad_norm": 3.522437810897827,
140
+ "learning_rate": 9.999803056380517e-06,
141
+ "loss": 6.1621,
142
+ "step": 95
143
+ },
144
+ {
145
+ "epoch": 0.0128,
146
+ "grad_norm": 3.9014439582824707,
147
+ "learning_rate": 9.999755753675216e-06,
148
+ "loss": 6.0573,
149
+ "step": 100
150
+ },
151
+ {
152
+ "epoch": 0.0128,
153
+ "eval_loss": 1.5072969198226929,
154
+ "eval_runtime": 11.1161,
155
+ "eval_samples_per_second": 89.96,
156
+ "eval_steps_per_second": 11.245,
157
+ "step": 100
158
+ },
159
+ {
160
+ "epoch": 0.01344,
161
+ "grad_norm": 3.7579081058502197,
162
+ "learning_rate": 9.999703364831614e-06,
163
+ "loss": 6.1671,
164
+ "step": 105
165
+ },
166
+ {
167
+ "epoch": 0.01408,
168
+ "grad_norm": 3.7058262825012207,
169
+ "learning_rate": 9.999645889903002e-06,
170
+ "loss": 6.1348,
171
+ "step": 110
172
+ },
173
+ {
174
+ "epoch": 0.01472,
175
+ "grad_norm": 5.018667697906494,
176
+ "learning_rate": 9.99958332894785e-06,
177
+ "loss": 5.9376,
178
+ "step": 115
179
+ },
180
+ {
181
+ "epoch": 0.01536,
182
+ "grad_norm": 3.5420188903808594,
183
+ "learning_rate": 9.999515682029798e-06,
184
+ "loss": 5.9961,
185
+ "step": 120
186
+ },
187
+ {
188
+ "epoch": 0.016,
189
+ "grad_norm": 3.5725393295288086,
190
+ "learning_rate": 9.999442949217663e-06,
191
+ "loss": 5.8439,
192
+ "step": 125
193
+ },
194
+ {
195
+ "epoch": 0.01664,
196
+ "grad_norm": 3.8440959453582764,
197
+ "learning_rate": 9.999365130585435e-06,
198
+ "loss": 5.7857,
199
+ "step": 130
200
+ },
201
+ {
202
+ "epoch": 0.01728,
203
+ "grad_norm": 3.4371285438537598,
204
+ "learning_rate": 9.999282226212276e-06,
205
+ "loss": 5.799,
206
+ "step": 135
207
+ },
208
+ {
209
+ "epoch": 0.01792,
210
+ "grad_norm": 3.996847152709961,
211
+ "learning_rate": 9.999194236182523e-06,
212
+ "loss": 6.0022,
213
+ "step": 140
214
+ },
215
+ {
216
+ "epoch": 0.01856,
217
+ "grad_norm": 3.720330238342285,
218
+ "learning_rate": 9.999101160585687e-06,
219
+ "loss": 5.925,
220
+ "step": 145
221
+ },
222
+ {
223
+ "epoch": 0.0192,
224
+ "grad_norm": 3.8822953701019287,
225
+ "learning_rate": 9.99900299951645e-06,
226
+ "loss": 5.8085,
227
+ "step": 150
228
+ },
229
+ {
230
+ "epoch": 0.01984,
231
+ "grad_norm": 3.599283456802368,
232
+ "learning_rate": 9.99889975307467e-06,
233
+ "loss": 5.6533,
234
+ "step": 155
235
+ },
236
+ {
237
+ "epoch": 0.02048,
238
+ "grad_norm": 3.4847381114959717,
239
+ "learning_rate": 9.998791421365376e-06,
240
+ "loss": 5.9021,
241
+ "step": 160
242
+ },
243
+ {
244
+ "epoch": 0.02112,
245
+ "grad_norm": 3.4302055835723877,
246
+ "learning_rate": 9.998678004498774e-06,
247
+ "loss": 5.962,
248
+ "step": 165
249
+ },
250
+ {
251
+ "epoch": 0.02176,
252
+ "grad_norm": 4.561929702758789,
253
+ "learning_rate": 9.99855950259024e-06,
254
+ "loss": 5.9011,
255
+ "step": 170
256
+ },
257
+ {
258
+ "epoch": 0.0224,
259
+ "grad_norm": 4.069271087646484,
260
+ "learning_rate": 9.998435915760323e-06,
261
+ "loss": 5.6782,
262
+ "step": 175
263
+ },
264
+ {
265
+ "epoch": 0.02304,
266
+ "grad_norm": 3.5959055423736572,
267
+ "learning_rate": 9.998307244134741e-06,
268
+ "loss": 5.8107,
269
+ "step": 180
270
+ },
271
+ {
272
+ "epoch": 0.02368,
273
+ "grad_norm": 3.5477242469787598,
274
+ "learning_rate": 9.998173487844396e-06,
275
+ "loss": 5.8335,
276
+ "step": 185
277
+ },
278
+ {
279
+ "epoch": 0.02432,
280
+ "grad_norm": 4.488218307495117,
281
+ "learning_rate": 9.998034647025349e-06,
282
+ "loss": 5.8285,
283
+ "step": 190
284
+ },
285
+ {
286
+ "epoch": 0.02496,
287
+ "grad_norm": 3.555074691772461,
288
+ "learning_rate": 9.997890721818844e-06,
289
+ "loss": 5.817,
290
+ "step": 195
291
+ },
292
+ {
293
+ "epoch": 0.0256,
294
+ "grad_norm": 3.6248419284820557,
295
+ "learning_rate": 9.99774171237129e-06,
296
+ "loss": 5.8368,
297
+ "step": 200
298
+ },
299
+ {
300
+ "epoch": 0.0256,
301
+ "eval_loss": 1.440572738647461,
302
+ "eval_runtime": 6.6468,
303
+ "eval_samples_per_second": 150.448,
304
+ "eval_steps_per_second": 18.806,
305
+ "step": 200
306
+ },
307
+ {
308
+ "epoch": 0.02624,
309
+ "grad_norm": 3.432421922683716,
310
+ "learning_rate": 9.997587618834272e-06,
311
+ "loss": 5.7842,
312
+ "step": 205
313
+ },
314
+ {
315
+ "epoch": 0.02688,
316
+ "grad_norm": 3.333038806915283,
317
+ "learning_rate": 9.997428441364546e-06,
318
+ "loss": 5.7173,
319
+ "step": 210
320
+ },
321
+ {
322
+ "epoch": 0.02752,
323
+ "grad_norm": 3.7716541290283203,
324
+ "learning_rate": 9.997264180124038e-06,
325
+ "loss": 5.719,
326
+ "step": 215
327
+ },
328
+ {
329
+ "epoch": 0.02816,
330
+ "grad_norm": 3.345600128173828,
331
+ "learning_rate": 9.99709483527985e-06,
332
+ "loss": 5.8428,
333
+ "step": 220
334
+ },
335
+ {
336
+ "epoch": 0.0288,
337
+ "grad_norm": 3.7677502632141113,
338
+ "learning_rate": 9.99692040700425e-06,
339
+ "loss": 5.7393,
340
+ "step": 225
341
+ },
342
+ {
343
+ "epoch": 0.02944,
344
+ "grad_norm": 11.996383666992188,
345
+ "learning_rate": 9.996740895474682e-06,
346
+ "loss": 5.5566,
347
+ "step": 230
348
+ },
349
+ {
350
+ "epoch": 0.03008,
351
+ "grad_norm": 3.6089084148406982,
352
+ "learning_rate": 9.996556300873758e-06,
353
+ "loss": 5.6939,
354
+ "step": 235
355
+ },
356
+ {
357
+ "epoch": 0.03072,
358
+ "grad_norm": 3.834825038909912,
359
+ "learning_rate": 9.996366623389263e-06,
360
+ "loss": 5.8123,
361
+ "step": 240
362
+ },
363
+ {
364
+ "epoch": 0.03136,
365
+ "grad_norm": 3.570263147354126,
366
+ "learning_rate": 9.99617186321415e-06,
367
+ "loss": 5.6839,
368
+ "step": 245
369
+ },
370
+ {
371
+ "epoch": 0.032,
372
+ "grad_norm": 3.5728812217712402,
373
+ "learning_rate": 9.995972020546545e-06,
374
+ "loss": 5.7764,
375
+ "step": 250
376
+ },
377
+ {
378
+ "epoch": 0.03264,
379
+ "grad_norm": 3.4725637435913086,
380
+ "learning_rate": 9.995767095589743e-06,
381
+ "loss": 5.6879,
382
+ "step": 255
383
+ },
384
+ {
385
+ "epoch": 0.03328,
386
+ "grad_norm": 3.811537742614746,
387
+ "learning_rate": 9.99555708855221e-06,
388
+ "loss": 5.6418,
389
+ "step": 260
390
+ },
391
+ {
392
+ "epoch": 0.03392,
393
+ "grad_norm": 3.494992971420288,
394
+ "learning_rate": 9.99534199964758e-06,
395
+ "loss": 5.6927,
396
+ "step": 265
397
+ },
398
+ {
399
+ "epoch": 0.03456,
400
+ "grad_norm": 3.8107383251190186,
401
+ "learning_rate": 9.995121829094662e-06,
402
+ "loss": 5.5658,
403
+ "step": 270
404
+ },
405
+ {
406
+ "epoch": 0.0352,
407
+ "grad_norm": 3.570551633834839,
408
+ "learning_rate": 9.994896577117425e-06,
409
+ "loss": 5.8131,
410
+ "step": 275
411
+ },
412
+ {
413
+ "epoch": 0.03584,
414
+ "grad_norm": 3.540811538696289,
415
+ "learning_rate": 9.994666243945018e-06,
416
+ "loss": 5.6009,
417
+ "step": 280
418
+ },
419
+ {
420
+ "epoch": 0.03648,
421
+ "grad_norm": 3.7275819778442383,
422
+ "learning_rate": 9.99443082981175e-06,
423
+ "loss": 5.6407,
424
+ "step": 285
425
+ },
426
+ {
427
+ "epoch": 0.03712,
428
+ "grad_norm": 4.194495677947998,
429
+ "learning_rate": 9.994190334957103e-06,
430
+ "loss": 5.8319,
431
+ "step": 290
432
+ },
433
+ {
434
+ "epoch": 0.03776,
435
+ "grad_norm": 3.5107626914978027,
436
+ "learning_rate": 9.993944759625728e-06,
437
+ "loss": 5.5765,
438
+ "step": 295
439
+ },
440
+ {
441
+ "epoch": 0.0384,
442
+ "grad_norm": 3.4100208282470703,
443
+ "learning_rate": 9.993694104067444e-06,
444
+ "loss": 5.7473,
445
+ "step": 300
446
+ },
447
+ {
448
+ "epoch": 0.0384,
449
+ "eval_loss": 1.407908320426941,
450
+ "eval_runtime": 6.6542,
451
+ "eval_samples_per_second": 150.281,
452
+ "eval_steps_per_second": 18.785,
453
+ "step": 300
454
+ },
455
+ {
456
+ "epoch": 0.03904,
457
+ "grad_norm": 3.7727818489074707,
458
+ "learning_rate": 9.993438368537236e-06,
459
+ "loss": 5.6802,
460
+ "step": 305
461
+ },
462
+ {
463
+ "epoch": 0.03968,
464
+ "grad_norm": 3.445909023284912,
465
+ "learning_rate": 9.993177553295258e-06,
466
+ "loss": 5.7484,
467
+ "step": 310
468
+ },
469
+ {
470
+ "epoch": 0.04032,
471
+ "grad_norm": 3.4199888706207275,
472
+ "learning_rate": 9.992911658606832e-06,
473
+ "loss": 5.7648,
474
+ "step": 315
475
+ },
476
+ {
477
+ "epoch": 0.04096,
478
+ "grad_norm": 4.9640655517578125,
479
+ "learning_rate": 9.992640684742445e-06,
480
+ "loss": 5.7922,
481
+ "step": 320
482
+ },
483
+ {
484
+ "epoch": 0.0416,
485
+ "grad_norm": 3.3730976581573486,
486
+ "learning_rate": 9.992364631977754e-06,
487
+ "loss": 5.677,
488
+ "step": 325
489
+ },
490
+ {
491
+ "epoch": 0.04224,
492
+ "grad_norm": 3.540597915649414,
493
+ "learning_rate": 9.99208350059358e-06,
494
+ "loss": 5.5495,
495
+ "step": 330
496
+ },
497
+ {
498
+ "epoch": 0.04288,
499
+ "grad_norm": 3.6853768825531006,
500
+ "learning_rate": 9.991797290875915e-06,
501
+ "loss": 5.4089,
502
+ "step": 335
503
+ },
504
+ {
505
+ "epoch": 0.04352,
506
+ "grad_norm": 3.6380045413970947,
507
+ "learning_rate": 9.991506003115911e-06,
508
+ "loss": 5.4849,
509
+ "step": 340
510
+ },
511
+ {
512
+ "epoch": 0.04416,
513
+ "grad_norm": 3.265488862991333,
514
+ "learning_rate": 9.991209637609887e-06,
515
+ "loss": 5.523,
516
+ "step": 345
517
+ },
518
+ {
519
+ "epoch": 0.0448,
520
+ "grad_norm": 3.2634189128875732,
521
+ "learning_rate": 9.990908194659332e-06,
522
+ "loss": 5.5664,
523
+ "step": 350
524
+ },
525
+ {
526
+ "epoch": 0.04544,
527
+ "grad_norm": 3.569810152053833,
528
+ "learning_rate": 9.990601674570895e-06,
529
+ "loss": 5.5059,
530
+ "step": 355
531
+ },
532
+ {
533
+ "epoch": 0.04608,
534
+ "grad_norm": 3.580211877822876,
535
+ "learning_rate": 9.990290077656393e-06,
536
+ "loss": 5.4079,
537
+ "step": 360
538
+ },
539
+ {
540
+ "epoch": 0.04672,
541
+ "grad_norm": 3.4860317707061768,
542
+ "learning_rate": 9.989973404232805e-06,
543
+ "loss": 5.6858,
544
+ "step": 365
545
+ },
546
+ {
547
+ "epoch": 0.04736,
548
+ "grad_norm": 4.026730060577393,
549
+ "learning_rate": 9.989651654622277e-06,
550
+ "loss": 5.5662,
551
+ "step": 370
552
+ },
553
+ {
554
+ "epoch": 0.048,
555
+ "grad_norm": 3.364692449569702,
556
+ "learning_rate": 9.989324829152119e-06,
557
+ "loss": 5.5304,
558
+ "step": 375
559
+ },
560
+ {
561
+ "epoch": 0.04864,
562
+ "grad_norm": 3.611964464187622,
563
+ "learning_rate": 9.9889929281548e-06,
564
+ "loss": 5.3911,
565
+ "step": 380
566
+ },
567
+ {
568
+ "epoch": 0.04928,
569
+ "grad_norm": 3.2946035861968994,
570
+ "learning_rate": 9.988655951967958e-06,
571
+ "loss": 5.4102,
572
+ "step": 385
573
+ },
574
+ {
575
+ "epoch": 0.04992,
576
+ "grad_norm": 3.963909864425659,
577
+ "learning_rate": 9.98831390093439e-06,
578
+ "loss": 5.549,
579
+ "step": 390
580
+ },
581
+ {
582
+ "epoch": 0.05056,
583
+ "grad_norm": 3.2876341342926025,
584
+ "learning_rate": 9.987966775402056e-06,
585
+ "loss": 5.5388,
586
+ "step": 395
587
+ },
588
+ {
589
+ "epoch": 0.0512,
590
+ "grad_norm": 3.8467471599578857,
591
+ "learning_rate": 9.98761457572408e-06,
592
+ "loss": 5.454,
593
+ "step": 400
594
+ },
595
+ {
596
+ "epoch": 0.0512,
597
+ "eval_loss": 1.3826359510421753,
598
+ "eval_runtime": 7.0199,
599
+ "eval_samples_per_second": 142.452,
600
+ "eval_steps_per_second": 17.807,
601
+ "step": 400
602
+ },
603
+ {
604
+ "epoch": 0.05184,
605
+ "grad_norm": 3.675231695175171,
606
+ "learning_rate": 9.987257302258748e-06,
607
+ "loss": 5.674,
608
+ "step": 405
609
+ },
610
+ {
611
+ "epoch": 0.05248,
612
+ "grad_norm": 3.787940263748169,
613
+ "learning_rate": 9.986894955369504e-06,
614
+ "loss": 5.5466,
615
+ "step": 410
616
+ },
617
+ {
618
+ "epoch": 0.05312,
619
+ "grad_norm": 3.677966833114624,
620
+ "learning_rate": 9.986527535424956e-06,
621
+ "loss": 5.4762,
622
+ "step": 415
623
+ },
624
+ {
625
+ "epoch": 0.05376,
626
+ "grad_norm": 3.5083606243133545,
627
+ "learning_rate": 9.986155042798874e-06,
628
+ "loss": 5.3145,
629
+ "step": 420
630
+ },
631
+ {
632
+ "epoch": 0.0544,
633
+ "grad_norm": 3.536379098892212,
634
+ "learning_rate": 9.98577747787018e-06,
635
+ "loss": 5.3769,
636
+ "step": 425
637
+ },
638
+ {
639
+ "epoch": 0.05504,
640
+ "grad_norm": 3.5448412895202637,
641
+ "learning_rate": 9.98539484102297e-06,
642
+ "loss": 5.3996,
643
+ "step": 430
644
+ },
645
+ {
646
+ "epoch": 0.05568,
647
+ "grad_norm": 3.359647274017334,
648
+ "learning_rate": 9.985007132646489e-06,
649
+ "loss": 5.3114,
650
+ "step": 435
651
+ },
652
+ {
653
+ "epoch": 0.05632,
654
+ "grad_norm": 3.3419110774993896,
655
+ "learning_rate": 9.984614353135143e-06,
656
+ "loss": 5.4383,
657
+ "step": 440
658
+ },
659
+ {
660
+ "epoch": 0.05696,
661
+ "grad_norm": 3.558025360107422,
662
+ "learning_rate": 9.984216502888496e-06,
663
+ "loss": 5.5239,
664
+ "step": 445
665
+ },
666
+ {
667
+ "epoch": 0.0576,
668
+ "grad_norm": 3.6349422931671143,
669
+ "learning_rate": 9.983813582311277e-06,
670
+ "loss": 5.5639,
671
+ "step": 450
672
+ },
673
+ {
674
+ "epoch": 0.05824,
675
+ "grad_norm": 3.2916922569274902,
676
+ "learning_rate": 9.983405591813362e-06,
677
+ "loss": 5.3886,
678
+ "step": 455
679
+ },
680
+ {
681
+ "epoch": 0.05888,
682
+ "grad_norm": 3.32891845703125,
683
+ "learning_rate": 9.982992531809796e-06,
684
+ "loss": 5.526,
685
+ "step": 460
686
+ },
687
+ {
688
+ "epoch": 0.05952,
689
+ "grad_norm": 3.8752880096435547,
690
+ "learning_rate": 9.982574402720773e-06,
691
+ "loss": 5.6599,
692
+ "step": 465
693
+ },
694
+ {
695
+ "epoch": 0.06016,
696
+ "grad_norm": 3.604433536529541,
697
+ "learning_rate": 9.982151204971646e-06,
698
+ "loss": 5.4567,
699
+ "step": 470
700
+ },
701
+ {
702
+ "epoch": 0.0608,
703
+ "grad_norm": 3.3058159351348877,
704
+ "learning_rate": 9.981722938992926e-06,
705
+ "loss": 5.4981,
706
+ "step": 475
707
+ },
708
+ {
709
+ "epoch": 0.06144,
710
+ "grad_norm": 3.7341926097869873,
711
+ "learning_rate": 9.981289605220276e-06,
712
+ "loss": 5.3278,
713
+ "step": 480
714
+ },
715
+ {
716
+ "epoch": 0.06208,
717
+ "grad_norm": 3.51798415184021,
718
+ "learning_rate": 9.980851204094519e-06,
719
+ "loss": 5.5029,
720
+ "step": 485
721
+ },
722
+ {
723
+ "epoch": 0.06272,
724
+ "grad_norm": 3.6541428565979004,
725
+ "learning_rate": 9.980407736061629e-06,
726
+ "loss": 5.3987,
727
+ "step": 490
728
+ },
729
+ {
730
+ "epoch": 0.06336,
731
+ "grad_norm": 3.420767307281494,
732
+ "learning_rate": 9.979959201572736e-06,
733
+ "loss": 5.405,
734
+ "step": 495
735
+ },
736
+ {
737
+ "epoch": 0.064,
738
+ "grad_norm": 3.7169559001922607,
739
+ "learning_rate": 9.979505601084124e-06,
740
+ "loss": 5.498,
741
+ "step": 500
742
+ },
743
+ {
744
+ "epoch": 0.064,
745
+ "eval_loss": 1.3493109941482544,
746
+ "eval_runtime": 7.1309,
747
+ "eval_samples_per_second": 140.234,
748
+ "eval_steps_per_second": 17.529,
749
+ "step": 500
750
+ },
751
+ {
752
+ "epoch": 0.06464,
753
+ "grad_norm": 4.536627769470215,
754
+ "learning_rate": 9.97904693505723e-06,
755
+ "loss": 5.5237,
756
+ "step": 505
757
+ },
758
+ {
759
+ "epoch": 0.06528,
760
+ "grad_norm": 3.204948902130127,
761
+ "learning_rate": 9.978583203958649e-06,
762
+ "loss": 5.3746,
763
+ "step": 510
764
+ },
765
+ {
766
+ "epoch": 0.06592,
767
+ "grad_norm": 3.4658005237579346,
768
+ "learning_rate": 9.978114408260118e-06,
769
+ "loss": 5.4567,
770
+ "step": 515
771
+ },
772
+ {
773
+ "epoch": 0.06656,
774
+ "grad_norm": 4.932333469390869,
775
+ "learning_rate": 9.977640548438534e-06,
776
+ "loss": 5.1959,
777
+ "step": 520
778
+ },
779
+ {
780
+ "epoch": 0.0672,
781
+ "grad_norm": 3.4697563648223877,
782
+ "learning_rate": 9.977161624975948e-06,
783
+ "loss": 5.4013,
784
+ "step": 525
785
+ },
786
+ {
787
+ "epoch": 0.06784,
788
+ "grad_norm": 3.441819667816162,
789
+ "learning_rate": 9.976677638359553e-06,
790
+ "loss": 5.4899,
791
+ "step": 530
792
+ },
793
+ {
794
+ "epoch": 0.06848,
795
+ "grad_norm": 3.4293930530548096,
796
+ "learning_rate": 9.9761885890817e-06,
797
+ "loss": 5.3569,
798
+ "step": 535
799
+ },
800
+ {
801
+ "epoch": 0.06912,
802
+ "grad_norm": 3.5388574600219727,
803
+ "learning_rate": 9.975694477639885e-06,
804
+ "loss": 5.2739,
805
+ "step": 540
806
+ },
807
+ {
808
+ "epoch": 0.06976,
809
+ "grad_norm": 3.735548973083496,
810
+ "learning_rate": 9.97519530453676e-06,
811
+ "loss": 5.4253,
812
+ "step": 545
813
+ },
814
+ {
815
+ "epoch": 0.0704,
816
+ "grad_norm": 3.33503794670105,
817
+ "learning_rate": 9.974691070280121e-06,
818
+ "loss": 5.1569,
819
+ "step": 550
820
+ },
821
+ {
822
+ "epoch": 0.07104,
823
+ "grad_norm": 3.5171401500701904,
824
+ "learning_rate": 9.974181775382915e-06,
825
+ "loss": 5.3242,
826
+ "step": 555
827
+ },
828
+ {
829
+ "epoch": 0.07168,
830
+ "grad_norm": 3.565356969833374,
831
+ "learning_rate": 9.973667420363233e-06,
832
+ "loss": 5.3893,
833
+ "step": 560
834
+ },
835
+ {
836
+ "epoch": 0.07232,
837
+ "grad_norm": 3.172163248062134,
838
+ "learning_rate": 9.973148005744319e-06,
839
+ "loss": 5.3824,
840
+ "step": 565
841
+ },
842
+ {
843
+ "epoch": 0.07296,
844
+ "grad_norm": 3.517838716506958,
845
+ "learning_rate": 9.972623532054564e-06,
846
+ "loss": 5.2673,
847
+ "step": 570
848
+ },
849
+ {
850
+ "epoch": 0.0736,
851
+ "grad_norm": 3.328416585922241,
852
+ "learning_rate": 9.9720939998275e-06,
853
+ "loss": 5.2649,
854
+ "step": 575
855
+ },
856
+ {
857
+ "epoch": 0.07424,
858
+ "grad_norm": 3.475539445877075,
859
+ "learning_rate": 9.971559409601807e-06,
860
+ "loss": 5.3318,
861
+ "step": 580
862
+ },
863
+ {
864
+ "epoch": 0.07488,
865
+ "grad_norm": 3.492013692855835,
866
+ "learning_rate": 9.971019761921317e-06,
867
+ "loss": 5.2735,
868
+ "step": 585
869
+ },
870
+ {
871
+ "epoch": 0.07552,
872
+ "grad_norm": 3.474803924560547,
873
+ "learning_rate": 9.970475057334997e-06,
874
+ "loss": 5.3722,
875
+ "step": 590
876
+ },
877
+ {
878
+ "epoch": 0.07616,
879
+ "grad_norm": 3.4162726402282715,
880
+ "learning_rate": 9.96992529639696e-06,
881
+ "loss": 5.3901,
882
+ "step": 595
883
+ },
884
+ {
885
+ "epoch": 0.0768,
886
+ "grad_norm": 3.3643155097961426,
887
+ "learning_rate": 9.969370479666473e-06,
888
+ "loss": 5.2384,
889
+ "step": 600
890
+ },
891
+ {
892
+ "epoch": 0.0768,
893
+ "eval_loss": 1.3373793363571167,
894
+ "eval_runtime": 6.5847,
895
+ "eval_samples_per_second": 151.867,
896
+ "eval_steps_per_second": 18.983,
897
+ "step": 600
898
+ },
899
+ {
900
+ "epoch": 0.07744,
901
+ "grad_norm": 3.44301176071167,
902
+ "learning_rate": 9.968810607707933e-06,
903
+ "loss": 5.2322,
904
+ "step": 605
905
+ },
906
+ {
907
+ "epoch": 0.07808,
908
+ "grad_norm": 3.422262668609619,
909
+ "learning_rate": 9.968245681090887e-06,
910
+ "loss": 5.1708,
911
+ "step": 610
912
+ },
913
+ {
914
+ "epoch": 0.07872,
915
+ "grad_norm": 3.2879252433776855,
916
+ "learning_rate": 9.96767570039002e-06,
917
+ "loss": 5.2291,
918
+ "step": 615
919
+ },
920
+ {
921
+ "epoch": 0.07936,
922
+ "grad_norm": 3.6026480197906494,
923
+ "learning_rate": 9.967100666185163e-06,
924
+ "loss": 5.4241,
925
+ "step": 620
926
+ },
927
+ {
928
+ "epoch": 0.08,
929
+ "grad_norm": 3.3642101287841797,
930
+ "learning_rate": 9.966520579061286e-06,
931
+ "loss": 5.4473,
932
+ "step": 625
933
+ },
934
+ {
935
+ "epoch": 0.08064,
936
+ "grad_norm": 3.5968470573425293,
937
+ "learning_rate": 9.965935439608493e-06,
938
+ "loss": 5.3982,
939
+ "step": 630
940
+ },
941
+ {
942
+ "epoch": 0.08128,
943
+ "grad_norm": 3.352083206176758,
944
+ "learning_rate": 9.96534524842204e-06,
945
+ "loss": 5.3953,
946
+ "step": 635
947
+ },
948
+ {
949
+ "epoch": 0.08192,
950
+ "grad_norm": 3.3571720123291016,
951
+ "learning_rate": 9.964750006102311e-06,
952
+ "loss": 5.3159,
953
+ "step": 640
954
+ },
955
+ {
956
+ "epoch": 0.08256,
957
+ "grad_norm": 3.486246109008789,
958
+ "learning_rate": 9.964149713254833e-06,
959
+ "loss": 5.211,
960
+ "step": 645
961
+ },
962
+ {
963
+ "epoch": 0.0832,
964
+ "grad_norm": 3.674906015396118,
965
+ "learning_rate": 9.96354437049027e-06,
966
+ "loss": 5.3374,
967
+ "step": 650
968
+ },
969
+ {
970
+ "epoch": 0.08384,
971
+ "grad_norm": 3.590810537338257,
972
+ "learning_rate": 9.962933978424426e-06,
973
+ "loss": 5.2194,
974
+ "step": 655
975
+ },
976
+ {
977
+ "epoch": 0.08448,
978
+ "grad_norm": 3.551786184310913,
979
+ "learning_rate": 9.962318537678238e-06,
980
+ "loss": 5.1187,
981
+ "step": 660
982
+ },
983
+ {
984
+ "epoch": 0.08512,
985
+ "grad_norm": 3.5391581058502197,
986
+ "learning_rate": 9.961698048877776e-06,
987
+ "loss": 5.2001,
988
+ "step": 665
989
+ },
990
+ {
991
+ "epoch": 0.08576,
992
+ "grad_norm": 3.6105592250823975,
993
+ "learning_rate": 9.961072512654255e-06,
994
+ "loss": 5.2758,
995
+ "step": 670
996
+ },
997
+ {
998
+ "epoch": 0.0864,
999
+ "grad_norm": 3.7463858127593994,
1000
+ "learning_rate": 9.960441929644017e-06,
1001
+ "loss": 5.2137,
1002
+ "step": 675
1003
+ },
1004
+ {
1005
+ "epoch": 0.08704,
1006
+ "grad_norm": 3.9237470626831055,
1007
+ "learning_rate": 9.959806300488538e-06,
1008
+ "loss": 5.2047,
1009
+ "step": 680
1010
+ },
1011
+ {
1012
+ "epoch": 0.08768,
1013
+ "grad_norm": 3.392827272415161,
1014
+ "learning_rate": 9.95916562583443e-06,
1015
+ "loss": 5.3071,
1016
+ "step": 685
1017
+ },
1018
+ {
1019
+ "epoch": 0.08832,
1020
+ "grad_norm": 3.221484661102295,
1021
+ "learning_rate": 9.958519906333438e-06,
1022
+ "loss": 5.183,
1023
+ "step": 690
1024
+ },
1025
+ {
1026
+ "epoch": 0.08896,
1027
+ "grad_norm": 3.5143983364105225,
1028
+ "learning_rate": 9.957869142642437e-06,
1029
+ "loss": 5.3171,
1030
+ "step": 695
1031
+ },
1032
+ {
1033
+ "epoch": 0.0896,
1034
+ "grad_norm": 3.497072696685791,
1035
+ "learning_rate": 9.957213335423433e-06,
1036
+ "loss": 5.1784,
1037
+ "step": 700
1038
+ },
1039
+ {
1040
+ "epoch": 0.0896,
1041
+ "eval_loss": 1.2988511323928833,
1042
+ "eval_runtime": 6.9763,
1043
+ "eval_samples_per_second": 143.342,
1044
+ "eval_steps_per_second": 17.918,
1045
+ "step": 700
1046
+ },
1047
+ {
1048
+ "epoch": 0.09024,
1049
+ "grad_norm": 3.3822438716888428,
1050
+ "learning_rate": 9.956552485343566e-06,
1051
+ "loss": 5.1732,
1052
+ "step": 705
1053
+ },
1054
+ {
1055
+ "epoch": 0.09088,
1056
+ "grad_norm": 3.3949694633483887,
1057
+ "learning_rate": 9.955886593075101e-06,
1058
+ "loss": 5.2725,
1059
+ "step": 710
1060
+ },
1061
+ {
1062
+ "epoch": 0.09152,
1063
+ "grad_norm": 3.2577288150787354,
1064
+ "learning_rate": 9.955215659295438e-06,
1065
+ "loss": 5.2207,
1066
+ "step": 715
1067
+ },
1068
+ {
1069
+ "epoch": 0.09216,
1070
+ "grad_norm": 3.769519567489624,
1071
+ "learning_rate": 9.954539684687103e-06,
1072
+ "loss": 5.2152,
1073
+ "step": 720
1074
+ },
1075
+ {
1076
+ "epoch": 0.0928,
1077
+ "grad_norm": 3.3824892044067383,
1078
+ "learning_rate": 9.953858669937746e-06,
1079
+ "loss": 5.2085,
1080
+ "step": 725
1081
+ },
1082
+ {
1083
+ "epoch": 0.09344,
1084
+ "grad_norm": 3.771742105484009,
1085
+ "learning_rate": 9.953172615740152e-06,
1086
+ "loss": 5.1575,
1087
+ "step": 730
1088
+ },
1089
+ {
1090
+ "epoch": 0.09408,
1091
+ "grad_norm": 3.7706689834594727,
1092
+ "learning_rate": 9.952481522792226e-06,
1093
+ "loss": 4.9608,
1094
+ "step": 735
1095
+ },
1096
+ {
1097
+ "epoch": 0.09472,
1098
+ "grad_norm": 3.8110334873199463,
1099
+ "learning_rate": 9.951785391797001e-06,
1100
+ "loss": 5.21,
1101
+ "step": 740
1102
+ },
1103
+ {
1104
+ "epoch": 0.09536,
1105
+ "grad_norm": 3.3012993335723877,
1106
+ "learning_rate": 9.951084223462636e-06,
1107
+ "loss": 5.2475,
1108
+ "step": 745
1109
+ },
1110
+ {
1111
+ "epoch": 0.096,
1112
+ "grad_norm": 3.6353518962860107,
1113
+ "learning_rate": 9.950378018502415e-06,
1114
+ "loss": 5.0985,
1115
+ "step": 750
1116
+ },
1117
+ {
1118
+ "epoch": 0.09664,
1119
+ "grad_norm": 3.369378089904785,
1120
+ "learning_rate": 9.949666777634743e-06,
1121
+ "loss": 5.1986,
1122
+ "step": 755
1123
+ },
1124
+ {
1125
+ "epoch": 0.09728,
1126
+ "grad_norm": 3.2247676849365234,
1127
+ "learning_rate": 9.948950501583147e-06,
1128
+ "loss": 5.3192,
1129
+ "step": 760
1130
+ },
1131
+ {
1132
+ "epoch": 0.09792,
1133
+ "grad_norm": 3.6966888904571533,
1134
+ "learning_rate": 9.948229191076284e-06,
1135
+ "loss": 5.1654,
1136
+ "step": 765
1137
+ },
1138
+ {
1139
+ "epoch": 0.09856,
1140
+ "grad_norm": 3.5823962688446045,
1141
+ "learning_rate": 9.947502846847921e-06,
1142
+ "loss": 5.1351,
1143
+ "step": 770
1144
+ },
1145
+ {
1146
+ "epoch": 0.0992,
1147
+ "grad_norm": 3.5258729457855225,
1148
+ "learning_rate": 9.946771469636955e-06,
1149
+ "loss": 5.1745,
1150
+ "step": 775
1151
+ },
1152
+ {
1153
+ "epoch": 0.09984,
1154
+ "grad_norm": 3.42067813873291,
1155
+ "learning_rate": 9.946035060187398e-06,
1156
+ "loss": 5.1569,
1157
+ "step": 780
1158
+ },
1159
+ {
1160
+ "epoch": 0.10048,
1161
+ "grad_norm": 3.9832825660705566,
1162
+ "learning_rate": 9.945293619248383e-06,
1163
+ "loss": 4.9796,
1164
+ "step": 785
1165
+ },
1166
+ {
1167
+ "epoch": 0.10112,
1168
+ "grad_norm": 3.742013692855835,
1169
+ "learning_rate": 9.944547147574162e-06,
1170
+ "loss": 5.1625,
1171
+ "step": 790
1172
+ },
1173
+ {
1174
+ "epoch": 0.10176,
1175
+ "grad_norm": 3.3150367736816406,
1176
+ "learning_rate": 9.943795645924104e-06,
1177
+ "loss": 5.099,
1178
+ "step": 795
1179
+ },
1180
+ {
1181
+ "epoch": 0.1024,
1182
+ "grad_norm": 3.359069585800171,
1183
+ "learning_rate": 9.943039115062691e-06,
1184
+ "loss": 5.1877,
1185
+ "step": 800
1186
+ },
1187
+ {
1188
+ "epoch": 0.1024,
1189
+ "eval_loss": 1.2946017980575562,
1190
+ "eval_runtime": 7.4306,
1191
+ "eval_samples_per_second": 134.579,
1192
+ "eval_steps_per_second": 16.822,
1193
+ "step": 800
1194
+ },
1195
+ {
1196
+ "epoch": 0.10304,
1197
+ "grad_norm": 3.703000545501709,
1198
+ "learning_rate": 9.94227755575953e-06,
1199
+ "loss": 5.1581,
1200
+ "step": 805
1201
+ },
1202
+ {
1203
+ "epoch": 0.10368,
1204
+ "grad_norm": 3.5370070934295654,
1205
+ "learning_rate": 9.941510968789334e-06,
1206
+ "loss": 5.2402,
1207
+ "step": 810
1208
+ },
1209
+ {
1210
+ "epoch": 0.10432,
1211
+ "grad_norm": 3.5010828971862793,
1212
+ "learning_rate": 9.940739354931936e-06,
1213
+ "loss": 5.1828,
1214
+ "step": 815
1215
+ },
1216
+ {
1217
+ "epoch": 0.10496,
1218
+ "grad_norm": 3.4637820720672607,
1219
+ "learning_rate": 9.93996271497228e-06,
1220
+ "loss": 5.1792,
1221
+ "step": 820
1222
+ },
1223
+ {
1224
+ "epoch": 0.1056,
1225
+ "grad_norm": 3.409712076187134,
1226
+ "learning_rate": 9.939181049700427e-06,
1227
+ "loss": 5.0721,
1228
+ "step": 825
1229
+ },
1230
+ {
1231
+ "epoch": 0.10624,
1232
+ "grad_norm": 3.589414596557617,
1233
+ "learning_rate": 9.938394359911545e-06,
1234
+ "loss": 5.234,
1235
+ "step": 830
1236
+ },
1237
+ {
1238
+ "epoch": 0.10688,
1239
+ "grad_norm": 3.444977045059204,
1240
+ "learning_rate": 9.937602646405918e-06,
1241
+ "loss": 4.9763,
1242
+ "step": 835
1243
+ },
1244
+ {
1245
+ "epoch": 0.10752,
1246
+ "grad_norm": 3.3560900688171387,
1247
+ "learning_rate": 9.936805909988935e-06,
1248
+ "loss": 5.2006,
1249
+ "step": 840
1250
+ },
1251
+ {
1252
+ "epoch": 0.10816,
1253
+ "grad_norm": 3.345703601837158,
1254
+ "learning_rate": 9.9360041514711e-06,
1255
+ "loss": 5.0287,
1256
+ "step": 845
1257
+ },
1258
+ {
1259
+ "epoch": 0.1088,
1260
+ "grad_norm": 3.492363691329956,
1261
+ "learning_rate": 9.935197371668024e-06,
1262
+ "loss": 5.0908,
1263
+ "step": 850
1264
+ },
1265
+ {
1266
+ "epoch": 0.10944,
1267
+ "grad_norm": 7.459951400756836,
1268
+ "learning_rate": 9.934385571400425e-06,
1269
+ "loss": 5.1735,
1270
+ "step": 855
1271
+ },
1272
+ {
1273
+ "epoch": 0.11008,
1274
+ "grad_norm": 3.5033841133117676,
1275
+ "learning_rate": 9.933568751494131e-06,
1276
+ "loss": 5.053,
1277
+ "step": 860
1278
+ },
1279
+ {
1280
+ "epoch": 0.11072,
1281
+ "grad_norm": 3.5542259216308594,
1282
+ "learning_rate": 9.93274691278007e-06,
1283
+ "loss": 5.1463,
1284
+ "step": 865
1285
+ },
1286
+ {
1287
+ "epoch": 0.11136,
1288
+ "grad_norm": 3.3819243907928467,
1289
+ "learning_rate": 9.931920056094285e-06,
1290
+ "loss": 5.0397,
1291
+ "step": 870
1292
+ },
1293
+ {
1294
+ "epoch": 0.112,
1295
+ "grad_norm": 3.406768798828125,
1296
+ "learning_rate": 9.931088182277915e-06,
1297
+ "loss": 5.179,
1298
+ "step": 875
1299
+ },
1300
+ {
1301
+ "epoch": 0.11264,
1302
+ "grad_norm": 5.960773944854736,
1303
+ "learning_rate": 9.930251292177206e-06,
1304
+ "loss": 5.217,
1305
+ "step": 880
1306
+ },
1307
+ {
1308
+ "epoch": 0.11328,
1309
+ "grad_norm": 3.5821049213409424,
1310
+ "learning_rate": 9.929409386643511e-06,
1311
+ "loss": 5.0374,
1312
+ "step": 885
1313
+ },
1314
+ {
1315
+ "epoch": 0.11392,
1316
+ "grad_norm": 3.3204903602600098,
1317
+ "learning_rate": 9.928562466533279e-06,
1318
+ "loss": 5.1856,
1319
+ "step": 890
1320
+ },
1321
+ {
1322
+ "epoch": 0.11456,
1323
+ "grad_norm": 4.022350788116455,
1324
+ "learning_rate": 9.927710532708064e-06,
1325
+ "loss": 5.1051,
1326
+ "step": 895
1327
+ },
1328
+ {
1329
+ "epoch": 0.1152,
1330
+ "grad_norm": 3.3810718059539795,
1331
+ "learning_rate": 9.926853586034515e-06,
1332
+ "loss": 5.1691,
1333
+ "step": 900
1334
+ },
1335
+ {
1336
+ "epoch": 0.1152,
1337
+ "eval_loss": 1.2660380601882935,
1338
+ "eval_runtime": 6.8853,
1339
+ "eval_samples_per_second": 145.238,
1340
+ "eval_steps_per_second": 18.155,
1341
+ "step": 900
1342
+ }
1343
+ ],
1344
+ "logging_steps": 5,
1345
+ "max_steps": 15624,
1346
+ "num_input_tokens_seen": 0,
1347
+ "num_train_epochs": 2,
1348
+ "save_steps": 100,
1349
+ "stateful_callbacks": {
1350
+ "TrainerControl": {
1351
+ "args": {
1352
+ "should_epoch_stop": false,
1353
+ "should_evaluate": false,
1354
+ "should_log": false,
1355
+ "should_save": true,
1356
+ "should_training_stop": false
1357
+ },
1358
+ "attributes": {}
1359
+ }
1360
+ },
1361
+ "total_flos": 3.141806761967616e+17,
1362
+ "train_batch_size": 32,
1363
+ "trial_name": null,
1364
+ "trial_params": null
1365
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6b2a903b8a705cf6470fa099fd4e529608302cc9f11777eca1699f316b366f
3
+ size 5240