bimabk commited on
Commit
34a61e8
·
verified ·
1 Parent(s): 03dcbe1

Upload task output 1

Browse files
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLM"
5
+ ],
6
+ "attention_dropout": 0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "bfloat16",
50
+ "transformers_version": "4.51.3",
51
+ "use_cache": false,
52
+ "vocab_size": 50257,
53
+ "window_size": 256
54
+ }
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": "4.51.3"
6
+ }
loss.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 500,0.5448389053344727
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e6321caa20d46813e7e701291adeae2e57808e0c6069eacaecb3845efc71cb
3
+ size 250414224
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": 2048,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
trainer_state.json ADDED
@@ -0,0 +1,742 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.06337938902268982,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0006337938902268982,
14
+ "grad_norm": 19.0,
15
+ "learning_rate": 3.4285714285714284e-05,
16
+ "loss": 2.3561,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.0012675877804537963,
21
+ "grad_norm": 12.3125,
22
+ "learning_rate": 7.714285714285713e-05,
23
+ "loss": 2.0686,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.0019013816706806947,
28
+ "grad_norm": 6.78125,
29
+ "learning_rate": 0.00011999999999999999,
30
+ "loss": 1.412,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.0025351755609075927,
35
+ "grad_norm": 2.296875,
36
+ "learning_rate": 0.00016285714285714284,
37
+ "loss": 0.8966,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.003168969451134491,
42
+ "grad_norm": 1.8671875,
43
+ "learning_rate": 0.0002057142857142857,
44
+ "loss": 0.7659,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.0038027633413613895,
49
+ "grad_norm": 2.046875,
50
+ "learning_rate": 0.00024857142857142857,
51
+ "loss": 0.7462,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.0044365572315882874,
56
+ "grad_norm": 1.640625,
57
+ "learning_rate": 0.0002914285714285714,
58
+ "loss": 0.7137,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.005070351121815185,
63
+ "grad_norm": 1.4765625,
64
+ "learning_rate": 0.0002999999985714883,
65
+ "loss": 0.7019,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.005704145012042084,
70
+ "grad_norm": 2.234375,
71
+ "learning_rate": 0.0002999999927681599,
72
+ "loss": 0.682,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.006337938902268982,
77
+ "grad_norm": 1.8984375,
78
+ "learning_rate": 0.00029999998250073286,
79
+ "loss": 0.6785,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.00697173279249588,
84
+ "grad_norm": 1.84375,
85
+ "learning_rate": 0.00029999996776920767,
86
+ "loss": 0.6718,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.007605526682722779,
91
+ "grad_norm": 2.640625,
92
+ "learning_rate": 0.0002999999485735849,
93
+ "loss": 0.6704,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.008239320572949677,
98
+ "grad_norm": 1.4765625,
99
+ "learning_rate": 0.0002999999249138654,
100
+ "loss": 0.6495,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.008873114463176575,
105
+ "grad_norm": 1.6328125,
106
+ "learning_rate": 0.00029999989679004995,
107
+ "loss": 0.652,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.009506908353403473,
112
+ "grad_norm": 1.6171875,
113
+ "learning_rate": 0.00029999986420213977,
114
+ "loss": 0.6583,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.01014070224363037,
119
+ "grad_norm": 1.671875,
120
+ "learning_rate": 0.0002999998271501361,
121
+ "loss": 0.6612,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.01077449613385727,
126
+ "grad_norm": 1.625,
127
+ "learning_rate": 0.0002999997856340405,
128
+ "loss": 0.6436,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.011408290024084168,
133
+ "grad_norm": 1.390625,
134
+ "learning_rate": 0.00029999973965385445,
135
+ "loss": 0.6532,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.012042083914311066,
140
+ "grad_norm": 1.4609375,
141
+ "learning_rate": 0.00029999968920958,
142
+ "loss": 0.6426,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.012675877804537964,
147
+ "grad_norm": 1.921875,
148
+ "learning_rate": 0.000299999634301219,
149
+ "loss": 0.6507,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.013309671694764862,
154
+ "grad_norm": 1.265625,
155
+ "learning_rate": 0.0002999995749287736,
156
+ "loss": 0.6404,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.01394346558499176,
161
+ "grad_norm": 1.390625,
162
+ "learning_rate": 0.00029999951109224623,
163
+ "loss": 0.6312,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.014577259475218658,
168
+ "grad_norm": 1.453125,
169
+ "learning_rate": 0.0002999994427916394,
170
+ "loss": 0.6227,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.015211053365445558,
175
+ "grad_norm": 1.6015625,
176
+ "learning_rate": 0.0002999993700269559,
177
+ "loss": 0.6377,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.015844847255672454,
182
+ "grad_norm": 1.4296875,
183
+ "learning_rate": 0.0002999992927981985,
184
+ "loss": 0.6294,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.016478641145899354,
189
+ "grad_norm": 1.484375,
190
+ "learning_rate": 0.0002999992111053703,
191
+ "loss": 0.6333,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.01711243503612625,
196
+ "grad_norm": 1.484375,
197
+ "learning_rate": 0.0002999991249484746,
198
+ "loss": 0.6157,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.01774622892635315,
203
+ "grad_norm": 2.203125,
204
+ "learning_rate": 0.0002999990343275147,
205
+ "loss": 0.6145,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.01838002281658005,
210
+ "grad_norm": 1.2734375,
211
+ "learning_rate": 0.00029999893924249427,
212
+ "loss": 0.6091,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.019013816706806946,
217
+ "grad_norm": 1.296875,
218
+ "learning_rate": 0.00029999883969341717,
219
+ "loss": 0.6149,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.019647610597033845,
224
+ "grad_norm": 1.6328125,
225
+ "learning_rate": 0.0002999987356802872,
226
+ "loss": 0.6171,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.02028140448726074,
231
+ "grad_norm": 1.3984375,
232
+ "learning_rate": 0.00029999862720310857,
233
+ "loss": 0.6021,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.02091519837748764,
238
+ "grad_norm": 1.546875,
239
+ "learning_rate": 0.0002999985142618855,
240
+ "loss": 0.6303,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.02154899226771454,
245
+ "grad_norm": 1.6953125,
246
+ "learning_rate": 0.0002999983968566226,
247
+ "loss": 0.6139,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.022182786157941437,
252
+ "grad_norm": 1.9765625,
253
+ "learning_rate": 0.0002999982749873244,
254
+ "loss": 0.6173,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.022816580048168337,
259
+ "grad_norm": 1.3515625,
260
+ "learning_rate": 0.00029999814865399585,
261
+ "loss": 0.6074,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.023450373938395233,
266
+ "grad_norm": 1.3828125,
267
+ "learning_rate": 0.00029999801785664194,
268
+ "loss": 0.6046,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.024084167828622133,
273
+ "grad_norm": 1.28125,
274
+ "learning_rate": 0.00029999788259526774,
275
+ "loss": 0.5923,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.02471796171884903,
280
+ "grad_norm": 1.265625,
281
+ "learning_rate": 0.00029999774286987876,
282
+ "loss": 0.6149,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.02535175560907593,
287
+ "grad_norm": 1.8984375,
288
+ "learning_rate": 0.0002999975986804805,
289
+ "loss": 0.5969,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.02598554949930283,
294
+ "grad_norm": 1.4609375,
295
+ "learning_rate": 0.0002999974500270787,
296
+ "loss": 0.6083,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.026619343389529725,
301
+ "grad_norm": 1.4609375,
302
+ "learning_rate": 0.00029999729690967917,
303
+ "loss": 0.6029,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.027253137279756624,
308
+ "grad_norm": 1.515625,
309
+ "learning_rate": 0.0002999971393282881,
310
+ "loss": 0.6064,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.02788693116998352,
315
+ "grad_norm": 1.2734375,
316
+ "learning_rate": 0.0002999969772829116,
317
+ "loss": 0.6102,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.02852072506021042,
322
+ "grad_norm": 1.3984375,
323
+ "learning_rate": 0.00029999681077355633,
324
+ "loss": 0.5899,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.029154518950437316,
329
+ "grad_norm": 1.4765625,
330
+ "learning_rate": 0.00029999663980022866,
331
+ "loss": 0.595,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.029788312840664216,
336
+ "grad_norm": 1.5078125,
337
+ "learning_rate": 0.00029999646436293555,
338
+ "loss": 0.5848,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.030422106730891116,
343
+ "grad_norm": 1.46875,
344
+ "learning_rate": 0.00029999628446168383,
345
+ "loss": 0.6003,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.031055900621118012,
350
+ "grad_norm": 1.34375,
351
+ "learning_rate": 0.0002999961000964807,
352
+ "loss": 0.5875,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.03168969451134491,
357
+ "grad_norm": 1.5078125,
358
+ "learning_rate": 0.00029999591126733346,
359
+ "loss": 0.5769,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.03232348840157181,
364
+ "grad_norm": 1.328125,
365
+ "learning_rate": 0.00029999571797424966,
366
+ "loss": 0.5928,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.03295728229179871,
371
+ "grad_norm": 1.578125,
372
+ "learning_rate": 0.0002999955202172369,
373
+ "loss": 0.5767,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.03359107618202561,
378
+ "grad_norm": 1.515625,
379
+ "learning_rate": 0.000299995317996303,
380
+ "loss": 0.5763,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.0342248700722525,
385
+ "grad_norm": 1.5078125,
386
+ "learning_rate": 0.0002999951113114561,
387
+ "loss": 0.5852,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.0348586639624794,
392
+ "grad_norm": 1.8125,
393
+ "learning_rate": 0.0002999949001627043,
394
+ "loss": 0.5965,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.0354924578527063,
399
+ "grad_norm": 1.5703125,
400
+ "learning_rate": 0.00029999468455005606,
401
+ "loss": 0.5828,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.0361262517429332,
406
+ "grad_norm": 1.5,
407
+ "learning_rate": 0.00029999446447351985,
408
+ "loss": 0.5918,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.0367600456331601,
413
+ "grad_norm": 1.3828125,
414
+ "learning_rate": 0.00029999423993310446,
415
+ "loss": 0.5853,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.03739383952338699,
420
+ "grad_norm": 1.703125,
421
+ "learning_rate": 0.00029999401092881876,
422
+ "loss": 0.5706,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.03802763341361389,
427
+ "grad_norm": 1.5859375,
428
+ "learning_rate": 0.0002999937774606719,
429
+ "loss": 0.571,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.03866142730384079,
434
+ "grad_norm": 1.578125,
435
+ "learning_rate": 0.00029999353952867307,
436
+ "loss": 0.5731,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.03929522119406769,
441
+ "grad_norm": 1.578125,
442
+ "learning_rate": 0.0002999932971328317,
443
+ "loss": 0.5806,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.03992901508429459,
448
+ "grad_norm": 1.2734375,
449
+ "learning_rate": 0.0002999930502731575,
450
+ "loss": 0.5751,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.04056280897452148,
455
+ "grad_norm": 1.265625,
456
+ "learning_rate": 0.0002999927989496603,
457
+ "loss": 0.5777,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 0.04119660286474838,
462
+ "grad_norm": 1.5390625,
463
+ "learning_rate": 0.0002999925431623499,
464
+ "loss": 0.5856,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 0.04183039675497528,
469
+ "grad_norm": 1.46875,
470
+ "learning_rate": 0.00029999228291123655,
471
+ "loss": 0.5754,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 0.04246419064520218,
476
+ "grad_norm": 1.4921875,
477
+ "learning_rate": 0.0002999920181963306,
478
+ "loss": 0.5684,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 0.04309798453542908,
483
+ "grad_norm": 1.5703125,
484
+ "learning_rate": 0.0002999917490176425,
485
+ "loss": 0.5665,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 0.043731778425655975,
490
+ "grad_norm": 1.328125,
491
+ "learning_rate": 0.00029999147537518295,
492
+ "loss": 0.5713,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 0.044365572315882874,
497
+ "grad_norm": 1.6875,
498
+ "learning_rate": 0.0002999911972689628,
499
+ "loss": 0.5675,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 0.044999366206109774,
504
+ "grad_norm": 1.59375,
505
+ "learning_rate": 0.0002999909146989931,
506
+ "loss": 0.575,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 0.045633160096336674,
511
+ "grad_norm": 1.25,
512
+ "learning_rate": 0.0002999906276652851,
513
+ "loss": 0.5721,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 0.046266953986563567,
518
+ "grad_norm": 1.8828125,
519
+ "learning_rate": 0.00029999033616785015,
520
+ "loss": 0.5653,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 0.046900747876790466,
525
+ "grad_norm": 1.8125,
526
+ "learning_rate": 0.0002999900402066998,
527
+ "loss": 0.5543,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 0.047534541767017366,
532
+ "grad_norm": 1.53125,
533
+ "learning_rate": 0.0002999897397818458,
534
+ "loss": 0.5643,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 0.048168335657244266,
539
+ "grad_norm": 1.78125,
540
+ "learning_rate": 0.0002999894348933001,
541
+ "loss": 0.574,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 0.048802129547471165,
546
+ "grad_norm": 1.46875,
547
+ "learning_rate": 0.0002999891255410748,
548
+ "loss": 0.5581,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 0.04943592343769806,
553
+ "grad_norm": 1.4609375,
554
+ "learning_rate": 0.0002999888117251821,
555
+ "loss": 0.558,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 0.05006971732792496,
560
+ "grad_norm": 1.3671875,
561
+ "learning_rate": 0.00029998849344563456,
562
+ "loss": 0.5614,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 0.05070351121815186,
567
+ "grad_norm": 1.4609375,
568
+ "learning_rate": 0.00029998817070244475,
569
+ "loss": 0.5692,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 0.05133730510837876,
574
+ "grad_norm": 1.359375,
575
+ "learning_rate": 0.00029998784349562544,
576
+ "loss": 0.5552,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 0.05197109899860566,
581
+ "grad_norm": 1.59375,
582
+ "learning_rate": 0.0002999875118251897,
583
+ "loss": 0.5549,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 0.05260489288883255,
588
+ "grad_norm": 1.484375,
589
+ "learning_rate": 0.00029998717569115063,
590
+ "loss": 0.5574,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 0.05323868677905945,
595
+ "grad_norm": 1.4765625,
596
+ "learning_rate": 0.0002999868350935216,
597
+ "loss": 0.5587,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 0.05387248066928635,
602
+ "grad_norm": 1.9765625,
603
+ "learning_rate": 0.00029998649003231613,
604
+ "loss": 0.5611,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 0.05450627455951325,
609
+ "grad_norm": 1.21875,
610
+ "learning_rate": 0.0002999861405075479,
611
+ "loss": 0.5567,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 0.05514006844974014,
616
+ "grad_norm": 1.15625,
617
+ "learning_rate": 0.0002999857865192308,
618
+ "loss": 0.5525,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 0.05577386233996704,
623
+ "grad_norm": 1.8046875,
624
+ "learning_rate": 0.00029998542806737875,
625
+ "loss": 0.5595,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 0.05640765623019394,
630
+ "grad_norm": 1.4609375,
631
+ "learning_rate": 0.00029998506515200614,
632
+ "loss": 0.5534,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 0.05704145012042084,
637
+ "grad_norm": 1.453125,
638
+ "learning_rate": 0.0002999846977731273,
639
+ "loss": 0.548,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 0.05767524401064774,
644
+ "grad_norm": 1.546875,
645
+ "learning_rate": 0.00029998432593075677,
646
+ "loss": 0.5534,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 0.05830903790087463,
651
+ "grad_norm": 1.390625,
652
+ "learning_rate": 0.00029998394962490945,
653
+ "loss": 0.5593,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 0.05894283179110153,
658
+ "grad_norm": 1.3359375,
659
+ "learning_rate": 0.0002999835688556001,
660
+ "loss": 0.5591,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 0.05957662568132843,
665
+ "grad_norm": 1.4609375,
666
+ "learning_rate": 0.0002999831836228439,
667
+ "loss": 0.5674,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 0.06021041957155533,
672
+ "grad_norm": 1.2734375,
673
+ "learning_rate": 0.00029998279392665615,
674
+ "loss": 0.534,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 0.06084421346178223,
679
+ "grad_norm": 1.453125,
680
+ "learning_rate": 0.0002999823997670523,
681
+ "loss": 0.5403,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 0.061478007352009124,
686
+ "grad_norm": 1.3515625,
687
+ "learning_rate": 0.00029998200114404803,
688
+ "loss": 0.542,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 0.062111801242236024,
693
+ "grad_norm": 1.5,
694
+ "learning_rate": 0.00029998159805765906,
695
+ "loss": 0.5432,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 0.06274559513246292,
700
+ "grad_norm": 1.4453125,
701
+ "learning_rate": 0.00029998119050790145,
702
+ "loss": 0.5462,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 0.06337938902268982,
707
+ "grad_norm": 1.4765625,
708
+ "learning_rate": 0.00029998077849479135,
709
+ "loss": 0.5406,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 0.06337938902268982,
714
+ "eval_loss": 0.5448389053344727,
715
+ "eval_runtime": 2.5375,
716
+ "eval_samples_per_second": 78.818,
717
+ "eval_steps_per_second": 78.818,
718
+ "step": 500
719
+ }
720
+ ],
721
+ "logging_steps": 5,
722
+ "max_steps": 78890,
723
+ "num_input_tokens_seen": 0,
724
+ "num_train_epochs": 10,
725
+ "save_steps": 500,
726
+ "stateful_callbacks": {
727
+ "TrainerControl": {
728
+ "args": {
729
+ "should_epoch_stop": false,
730
+ "should_evaluate": false,
731
+ "should_log": false,
732
+ "should_save": true,
733
+ "should_training_stop": false
734
+ },
735
+ "attributes": {}
736
+ }
737
+ },
738
+ "total_flos": 1.2537940672512e+16,
739
+ "train_batch_size": 48,
740
+ "trial_name": null,
741
+ "trial_params": null
742
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6d9e48c5729e03c1dd44919b71088cf87964ed2c695ad8a29b1c3beb173f76
3
+ size 5560
vocab.json ADDED
The diff for this file is too large to render. See raw diff