Drago1995 commited on
Commit
dd89ca6
·
verified ·
1 Parent(s): 29ad524

Upload fine-tuned GPT-2 model

Browse files
checkpoint-700/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.52.4",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
checkpoint-700/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": "4.52.4"
6
+ }
checkpoint-700/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-700/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e226469b6e1fbf8638f4f5a9b3bc132b865750f41e61e5ff4e06f168ed79ed
3
+ size 497774208
checkpoint-700/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6060b04a63047e1615a23dbb37afe6e387812d436d2c141baa1a7e957062be39
3
+ size 995642763
checkpoint-700/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c822674a3f3ab2ae41bf9c1b308da6e20007776719161f3eab256bb20f5f3d4
3
+ size 14645
checkpoint-700/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514f1965c11799af19c9a134a890e9ab825408f44c4c04559d1dcd09495cd42a
3
+ size 1383
checkpoint-700/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fca525ee17bc785e4942a6bfd9ed0ed3db398e8c1dce1879ab7a9aab35af4b09
3
+ size 1465
checkpoint-700/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-700/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": false,
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-700/trainer_state.json ADDED
@@ -0,0 +1,524 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.6923076923076925,
6
+ "eval_steps": 500,
7
+ "global_step": 700,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.06622516556291391,
14
+ "grad_norm": Infinity,
15
+ "learning_rate": 4.9448123620309056e-05,
16
+ "loss": 4.1885,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.13245033112582782,
21
+ "grad_norm": 36.195037841796875,
22
+ "learning_rate": 4.845474613686534e-05,
23
+ "loss": 3.0478,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.1986754966887417,
28
+ "grad_norm": 33.5300178527832,
29
+ "learning_rate": 4.735099337748345e-05,
30
+ "loss": 2.9614,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.26490066225165565,
35
+ "grad_norm": 36.93195724487305,
36
+ "learning_rate": 4.624724061810155e-05,
37
+ "loss": 2.5998,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.33112582781456956,
42
+ "grad_norm": 33.88347625732422,
43
+ "learning_rate": 4.514348785871965e-05,
44
+ "loss": 2.7264,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.3973509933774834,
49
+ "grad_norm": 33.70178985595703,
50
+ "learning_rate": 4.403973509933775e-05,
51
+ "loss": 2.7822,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.46357615894039733,
56
+ "grad_norm": 38.95631408691406,
57
+ "learning_rate": 4.293598233995585e-05,
58
+ "loss": 2.8206,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.5298013245033113,
63
+ "grad_norm": 24.44338035583496,
64
+ "learning_rate": 4.194260485651214e-05,
65
+ "loss": 2.1742,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.5960264900662252,
70
+ "grad_norm": 33.98532485961914,
71
+ "learning_rate": 4.0838852097130246e-05,
72
+ "loss": 2.2719,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.6622516556291391,
77
+ "grad_norm": 33.717506408691406,
78
+ "learning_rate": 3.9735099337748346e-05,
79
+ "loss": 2.0969,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.7284768211920529,
84
+ "grad_norm": 34.6390266418457,
85
+ "learning_rate": 3.8631346578366446e-05,
86
+ "loss": 2.1129,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.7947019867549668,
91
+ "grad_norm": 37.44624328613281,
92
+ "learning_rate": 3.7527593818984546e-05,
93
+ "loss": 2.0181,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.8609271523178808,
98
+ "grad_norm": 27.156349182128906,
99
+ "learning_rate": 3.6423841059602646e-05,
100
+ "loss": 1.9558,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.9271523178807947,
105
+ "grad_norm": 26.3441219329834,
106
+ "learning_rate": 3.532008830022075e-05,
107
+ "loss": 1.9322,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.9933774834437086,
112
+ "grad_norm": 58.27754592895508,
113
+ "learning_rate": 3.4216335540838853e-05,
114
+ "loss": 1.9986,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 1.0596026490066226,
119
+ "grad_norm": 33.036617279052734,
120
+ "learning_rate": 3.311258278145696e-05,
121
+ "loss": 1.6782,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 1.1258278145695364,
126
+ "grad_norm": 33.23360824584961,
127
+ "learning_rate": 3.200883002207506e-05,
128
+ "loss": 1.4764,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 1.1920529801324504,
133
+ "grad_norm": 43.95944595336914,
134
+ "learning_rate": 3.090507726269316e-05,
135
+ "loss": 1.4014,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 1.2582781456953642,
140
+ "grad_norm": 35.957462310791016,
141
+ "learning_rate": 2.980132450331126e-05,
142
+ "loss": 1.4407,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 1.3245033112582782,
147
+ "grad_norm": 25.84115219116211,
148
+ "learning_rate": 2.8697571743929365e-05,
149
+ "loss": 1.6161,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 1.390728476821192,
154
+ "grad_norm": 29.360647201538086,
155
+ "learning_rate": 2.7593818984547465e-05,
156
+ "loss": 1.4395,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 1.4569536423841059,
161
+ "grad_norm": 22.46617889404297,
162
+ "learning_rate": 2.6490066225165565e-05,
163
+ "loss": 1.2811,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 1.5231788079470199,
168
+ "grad_norm": 31.289905548095703,
169
+ "learning_rate": 2.538631346578367e-05,
170
+ "loss": 1.2007,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 1.589403973509934,
175
+ "grad_norm": 30.47980308532715,
176
+ "learning_rate": 2.4282560706401765e-05,
177
+ "loss": 1.4978,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 1.6556291390728477,
182
+ "grad_norm": 23.577800750732422,
183
+ "learning_rate": 2.317880794701987e-05,
184
+ "loss": 1.3382,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 1.7218543046357615,
189
+ "grad_norm": 27.43430519104004,
190
+ "learning_rate": 2.207505518763797e-05,
191
+ "loss": 1.2244,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 1.7880794701986755,
196
+ "grad_norm": 31.29072380065918,
197
+ "learning_rate": 2.097130242825607e-05,
198
+ "loss": 1.4104,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 1.8543046357615895,
203
+ "grad_norm": 22.746807098388672,
204
+ "learning_rate": 1.9867549668874173e-05,
205
+ "loss": 1.2092,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 1.9205298013245033,
210
+ "grad_norm": 22.63174819946289,
211
+ "learning_rate": 1.8763796909492273e-05,
212
+ "loss": 1.1127,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 1.9867549668874172,
217
+ "grad_norm": 25.042314529418945,
218
+ "learning_rate": 1.7660044150110377e-05,
219
+ "loss": 1.0324,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 2.052980132450331,
224
+ "grad_norm": 23.214874267578125,
225
+ "learning_rate": 1.655629139072848e-05,
226
+ "loss": 1.032,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 2.119205298013245,
231
+ "grad_norm": 19.802978515625,
232
+ "learning_rate": 1.545253863134658e-05,
233
+ "loss": 1.0921,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 2.185430463576159,
238
+ "grad_norm": 27.05217170715332,
239
+ "learning_rate": 1.4348785871964682e-05,
240
+ "loss": 1.0985,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 2.251655629139073,
245
+ "grad_norm": 18.222990036010742,
246
+ "learning_rate": 1.3245033112582782e-05,
247
+ "loss": 0.9707,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 2.3178807947019866,
252
+ "grad_norm": 41.69179153442383,
253
+ "learning_rate": 1.2141280353200883e-05,
254
+ "loss": 0.9927,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 2.384105960264901,
259
+ "grad_norm": 18.794240951538086,
260
+ "learning_rate": 1.1037527593818985e-05,
261
+ "loss": 0.9525,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 2.4503311258278146,
266
+ "grad_norm": 34.48478698730469,
267
+ "learning_rate": 9.933774834437086e-06,
268
+ "loss": 1.199,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 2.5165562913907285,
273
+ "grad_norm": 38.02653884887695,
274
+ "learning_rate": 8.830022075055188e-06,
275
+ "loss": 1.0145,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 2.5827814569536423,
280
+ "grad_norm": 20.557052612304688,
281
+ "learning_rate": 7.72626931567329e-06,
282
+ "loss": 0.9305,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 2.6490066225165565,
287
+ "grad_norm": 28.606456756591797,
288
+ "learning_rate": 6.622516556291391e-06,
289
+ "loss": 0.8064,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 2.7152317880794703,
294
+ "grad_norm": 21.579687118530273,
295
+ "learning_rate": 5.518763796909492e-06,
296
+ "loss": 0.9999,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 2.781456953642384,
301
+ "grad_norm": 23.69796371459961,
302
+ "learning_rate": 4.525386313465784e-06,
303
+ "loss": 1.0723,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 2.847682119205298,
308
+ "grad_norm": 14.353167533874512,
309
+ "learning_rate": 3.4216335540838854e-06,
310
+ "loss": 0.9702,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 2.9139072847682117,
315
+ "grad_norm": 27.654193878173828,
316
+ "learning_rate": 2.317880794701987e-06,
317
+ "loss": 0.914,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 2.980132450331126,
322
+ "grad_norm": 19.856712341308594,
323
+ "learning_rate": 1.2141280353200883e-06,
324
+ "loss": 0.9033,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.7692307692307692,
329
+ "grad_norm": 41.147037506103516,
330
+ "learning_rate": 2.102564102564103e-05,
331
+ "loss": 3.9769,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.8076923076923077,
336
+ "grad_norm": 35.22549057006836,
337
+ "learning_rate": 2.0384615384615387e-05,
338
+ "loss": 3.417,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.8461538461538463,
343
+ "grad_norm": 44.26778793334961,
344
+ "learning_rate": 1.9743589743589745e-05,
345
+ "loss": 2.9772,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.8846153846153846,
350
+ "grad_norm": 36.30922317504883,
351
+ "learning_rate": 1.9102564102564103e-05,
352
+ "loss": 2.9651,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.9230769230769231,
357
+ "grad_norm": 31.96507453918457,
358
+ "learning_rate": 1.8461538461538465e-05,
359
+ "loss": 2.9108,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.9615384615384617,
364
+ "grad_norm": 38.324031829833984,
365
+ "learning_rate": 1.7820512820512823e-05,
366
+ "loss": 2.6208,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 2.0,
371
+ "grad_norm": 31.850996017456055,
372
+ "learning_rate": 1.717948717948718e-05,
373
+ "loss": 2.5307,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 2.0384615384615383,
378
+ "grad_norm": 34.04115295410156,
379
+ "learning_rate": 1.653846153846154e-05,
380
+ "loss": 2.4855,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 2.076923076923077,
385
+ "grad_norm": 28.20927619934082,
386
+ "learning_rate": 1.5897435897435897e-05,
387
+ "loss": 2.2465,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 2.1153846153846154,
392
+ "grad_norm": 34.482017517089844,
393
+ "learning_rate": 1.5256410256410259e-05,
394
+ "loss": 2.5232,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 2.1538461538461537,
399
+ "grad_norm": 27.58531379699707,
400
+ "learning_rate": 1.4615384615384617e-05,
401
+ "loss": 2.2702,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 2.1923076923076925,
406
+ "grad_norm": 28.40576171875,
407
+ "learning_rate": 1.3974358974358975e-05,
408
+ "loss": 2.6068,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 2.230769230769231,
413
+ "grad_norm": 28.21039390563965,
414
+ "learning_rate": 1.3333333333333333e-05,
415
+ "loss": 2.426,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 2.269230769230769,
420
+ "grad_norm": 36.4321174621582,
421
+ "learning_rate": 1.2692307692307691e-05,
422
+ "loss": 2.0901,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 2.3076923076923075,
427
+ "grad_norm": 37.081520080566406,
428
+ "learning_rate": 1.2051282051282051e-05,
429
+ "loss": 2.4405,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 2.3461538461538463,
434
+ "grad_norm": 33.08905029296875,
435
+ "learning_rate": 1.1410256410256411e-05,
436
+ "loss": 2.4763,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 2.3846153846153846,
441
+ "grad_norm": 29.76759910583496,
442
+ "learning_rate": 1.0769230769230771e-05,
443
+ "loss": 2.3194,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 2.423076923076923,
448
+ "grad_norm": 27.511579513549805,
449
+ "learning_rate": 1.012820512820513e-05,
450
+ "loss": 2.376,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 2.4615384615384617,
455
+ "grad_norm": 30.223817825317383,
456
+ "learning_rate": 9.487179487179487e-06,
457
+ "loss": 2.2789,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 2.5,
462
+ "grad_norm": 32.20188903808594,
463
+ "learning_rate": 8.846153846153847e-06,
464
+ "loss": 2.0922,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 2.5384615384615383,
469
+ "grad_norm": 26.115158081054688,
470
+ "learning_rate": 8.205128205128205e-06,
471
+ "loss": 1.9232,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 2.5769230769230766,
476
+ "grad_norm": 22.415143966674805,
477
+ "learning_rate": 7.564102564102564e-06,
478
+ "loss": 2.3281,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 2.6153846153846154,
483
+ "grad_norm": 28.419933319091797,
484
+ "learning_rate": 6.923076923076923e-06,
485
+ "loss": 2.5466,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 2.6538461538461537,
490
+ "grad_norm": 32.872928619384766,
491
+ "learning_rate": 6.282051282051282e-06,
492
+ "loss": 2.0911,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 2.6923076923076925,
497
+ "grad_norm": 31.219316482543945,
498
+ "learning_rate": 5.641025641025641e-06,
499
+ "loss": 1.9418,
500
+ "step": 700
501
+ }
502
+ ],
503
+ "logging_steps": 10,
504
+ "max_steps": 780,
505
+ "num_input_tokens_seen": 0,
506
+ "num_train_epochs": 3,
507
+ "save_steps": 100,
508
+ "stateful_callbacks": {
509
+ "TrainerControl": {
510
+ "args": {
511
+ "should_epoch_stop": false,
512
+ "should_evaluate": false,
513
+ "should_log": false,
514
+ "should_save": true,
515
+ "should_training_stop": false
516
+ },
517
+ "attributes": {}
518
+ }
519
+ },
520
+ "total_flos": 365808844800000.0,
521
+ "train_batch_size": 2,
522
+ "trial_name": null,
523
+ "trial_params": null
524
+ }
checkpoint-700/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfea7e777d36d3cfbbc326685e9eec4b4750fde45efc6b3548e745be7dfe7453
3
+ size 5649
checkpoint-700/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-780/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.52.4",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
checkpoint-780/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": "4.52.4"
6
+ }
checkpoint-780/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-780/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90f49d1e4b4dc87d08dca0dce8f2e313cd1bd70ba108822a044de9668c52200
3
+ size 497774208
checkpoint-780/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3a2c5da90bbea4f2e5d2f4a1fd366240e26a6180070b3b6c507d1224688051
3
+ size 995642763
checkpoint-780/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e97f1479c181892232a452a7c64eccd1c65ab0ed6e1f9ad3e5f3fead00f993de
3
+ size 14645
checkpoint-780/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f78605b2d651595b7587d469ca104ed8e08ba7076a1dab4c22488bcfcdc948d
3
+ size 1383
checkpoint-780/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f661c0105832eb59eb698a85cc6b4c9f0ab649b04c96748de8259b4c01ca2f6c
3
+ size 1465
checkpoint-780/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-780/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": false,
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-780/trainer_state.json ADDED
@@ -0,0 +1,580 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 780,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.06622516556291391,
14
+ "grad_norm": Infinity,
15
+ "learning_rate": 4.9448123620309056e-05,
16
+ "loss": 4.1885,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.13245033112582782,
21
+ "grad_norm": 36.195037841796875,
22
+ "learning_rate": 4.845474613686534e-05,
23
+ "loss": 3.0478,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.1986754966887417,
28
+ "grad_norm": 33.5300178527832,
29
+ "learning_rate": 4.735099337748345e-05,
30
+ "loss": 2.9614,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.26490066225165565,
35
+ "grad_norm": 36.93195724487305,
36
+ "learning_rate": 4.624724061810155e-05,
37
+ "loss": 2.5998,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.33112582781456956,
42
+ "grad_norm": 33.88347625732422,
43
+ "learning_rate": 4.514348785871965e-05,
44
+ "loss": 2.7264,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.3973509933774834,
49
+ "grad_norm": 33.70178985595703,
50
+ "learning_rate": 4.403973509933775e-05,
51
+ "loss": 2.7822,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.46357615894039733,
56
+ "grad_norm": 38.95631408691406,
57
+ "learning_rate": 4.293598233995585e-05,
58
+ "loss": 2.8206,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.5298013245033113,
63
+ "grad_norm": 24.44338035583496,
64
+ "learning_rate": 4.194260485651214e-05,
65
+ "loss": 2.1742,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.5960264900662252,
70
+ "grad_norm": 33.98532485961914,
71
+ "learning_rate": 4.0838852097130246e-05,
72
+ "loss": 2.2719,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.6622516556291391,
77
+ "grad_norm": 33.717506408691406,
78
+ "learning_rate": 3.9735099337748346e-05,
79
+ "loss": 2.0969,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.7284768211920529,
84
+ "grad_norm": 34.6390266418457,
85
+ "learning_rate": 3.8631346578366446e-05,
86
+ "loss": 2.1129,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.7947019867549668,
91
+ "grad_norm": 37.44624328613281,
92
+ "learning_rate": 3.7527593818984546e-05,
93
+ "loss": 2.0181,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.8609271523178808,
98
+ "grad_norm": 27.156349182128906,
99
+ "learning_rate": 3.6423841059602646e-05,
100
+ "loss": 1.9558,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.9271523178807947,
105
+ "grad_norm": 26.3441219329834,
106
+ "learning_rate": 3.532008830022075e-05,
107
+ "loss": 1.9322,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.9933774834437086,
112
+ "grad_norm": 58.27754592895508,
113
+ "learning_rate": 3.4216335540838853e-05,
114
+ "loss": 1.9986,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 1.0596026490066226,
119
+ "grad_norm": 33.036617279052734,
120
+ "learning_rate": 3.311258278145696e-05,
121
+ "loss": 1.6782,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 1.1258278145695364,
126
+ "grad_norm": 33.23360824584961,
127
+ "learning_rate": 3.200883002207506e-05,
128
+ "loss": 1.4764,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 1.1920529801324504,
133
+ "grad_norm": 43.95944595336914,
134
+ "learning_rate": 3.090507726269316e-05,
135
+ "loss": 1.4014,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 1.2582781456953642,
140
+ "grad_norm": 35.957462310791016,
141
+ "learning_rate": 2.980132450331126e-05,
142
+ "loss": 1.4407,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 1.3245033112582782,
147
+ "grad_norm": 25.84115219116211,
148
+ "learning_rate": 2.8697571743929365e-05,
149
+ "loss": 1.6161,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 1.390728476821192,
154
+ "grad_norm": 29.360647201538086,
155
+ "learning_rate": 2.7593818984547465e-05,
156
+ "loss": 1.4395,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 1.4569536423841059,
161
+ "grad_norm": 22.46617889404297,
162
+ "learning_rate": 2.6490066225165565e-05,
163
+ "loss": 1.2811,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 1.5231788079470199,
168
+ "grad_norm": 31.289905548095703,
169
+ "learning_rate": 2.538631346578367e-05,
170
+ "loss": 1.2007,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 1.589403973509934,
175
+ "grad_norm": 30.47980308532715,
176
+ "learning_rate": 2.4282560706401765e-05,
177
+ "loss": 1.4978,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 1.6556291390728477,
182
+ "grad_norm": 23.577800750732422,
183
+ "learning_rate": 2.317880794701987e-05,
184
+ "loss": 1.3382,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 1.7218543046357615,
189
+ "grad_norm": 27.43430519104004,
190
+ "learning_rate": 2.207505518763797e-05,
191
+ "loss": 1.2244,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 1.7880794701986755,
196
+ "grad_norm": 31.29072380065918,
197
+ "learning_rate": 2.097130242825607e-05,
198
+ "loss": 1.4104,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 1.8543046357615895,
203
+ "grad_norm": 22.746807098388672,
204
+ "learning_rate": 1.9867549668874173e-05,
205
+ "loss": 1.2092,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 1.9205298013245033,
210
+ "grad_norm": 22.63174819946289,
211
+ "learning_rate": 1.8763796909492273e-05,
212
+ "loss": 1.1127,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 1.9867549668874172,
217
+ "grad_norm": 25.042314529418945,
218
+ "learning_rate": 1.7660044150110377e-05,
219
+ "loss": 1.0324,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 2.052980132450331,
224
+ "grad_norm": 23.214874267578125,
225
+ "learning_rate": 1.655629139072848e-05,
226
+ "loss": 1.032,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 2.119205298013245,
231
+ "grad_norm": 19.802978515625,
232
+ "learning_rate": 1.545253863134658e-05,
233
+ "loss": 1.0921,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 2.185430463576159,
238
+ "grad_norm": 27.05217170715332,
239
+ "learning_rate": 1.4348785871964682e-05,
240
+ "loss": 1.0985,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 2.251655629139073,
245
+ "grad_norm": 18.222990036010742,
246
+ "learning_rate": 1.3245033112582782e-05,
247
+ "loss": 0.9707,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 2.3178807947019866,
252
+ "grad_norm": 41.69179153442383,
253
+ "learning_rate": 1.2141280353200883e-05,
254
+ "loss": 0.9927,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 2.384105960264901,
259
+ "grad_norm": 18.794240951538086,
260
+ "learning_rate": 1.1037527593818985e-05,
261
+ "loss": 0.9525,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 2.4503311258278146,
266
+ "grad_norm": 34.48478698730469,
267
+ "learning_rate": 9.933774834437086e-06,
268
+ "loss": 1.199,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 2.5165562913907285,
273
+ "grad_norm": 38.02653884887695,
274
+ "learning_rate": 8.830022075055188e-06,
275
+ "loss": 1.0145,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 2.5827814569536423,
280
+ "grad_norm": 20.557052612304688,
281
+ "learning_rate": 7.72626931567329e-06,
282
+ "loss": 0.9305,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 2.6490066225165565,
287
+ "grad_norm": 28.606456756591797,
288
+ "learning_rate": 6.622516556291391e-06,
289
+ "loss": 0.8064,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 2.7152317880794703,
294
+ "grad_norm": 21.579687118530273,
295
+ "learning_rate": 5.518763796909492e-06,
296
+ "loss": 0.9999,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 2.781456953642384,
301
+ "grad_norm": 23.69796371459961,
302
+ "learning_rate": 4.525386313465784e-06,
303
+ "loss": 1.0723,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 2.847682119205298,
308
+ "grad_norm": 14.353167533874512,
309
+ "learning_rate": 3.4216335540838854e-06,
310
+ "loss": 0.9702,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 2.9139072847682117,
315
+ "grad_norm": 27.654193878173828,
316
+ "learning_rate": 2.317880794701987e-06,
317
+ "loss": 0.914,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 2.980132450331126,
322
+ "grad_norm": 19.856712341308594,
323
+ "learning_rate": 1.2141280353200883e-06,
324
+ "loss": 0.9033,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.7692307692307692,
329
+ "grad_norm": 41.147037506103516,
330
+ "learning_rate": 2.102564102564103e-05,
331
+ "loss": 3.9769,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.8076923076923077,
336
+ "grad_norm": 35.22549057006836,
337
+ "learning_rate": 2.0384615384615387e-05,
338
+ "loss": 3.417,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.8461538461538463,
343
+ "grad_norm": 44.26778793334961,
344
+ "learning_rate": 1.9743589743589745e-05,
345
+ "loss": 2.9772,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.8846153846153846,
350
+ "grad_norm": 36.30922317504883,
351
+ "learning_rate": 1.9102564102564103e-05,
352
+ "loss": 2.9651,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.9230769230769231,
357
+ "grad_norm": 31.96507453918457,
358
+ "learning_rate": 1.8461538461538465e-05,
359
+ "loss": 2.9108,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.9615384615384617,
364
+ "grad_norm": 38.324031829833984,
365
+ "learning_rate": 1.7820512820512823e-05,
366
+ "loss": 2.6208,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 2.0,
371
+ "grad_norm": 31.850996017456055,
372
+ "learning_rate": 1.717948717948718e-05,
373
+ "loss": 2.5307,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 2.0384615384615383,
378
+ "grad_norm": 34.04115295410156,
379
+ "learning_rate": 1.653846153846154e-05,
380
+ "loss": 2.4855,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 2.076923076923077,
385
+ "grad_norm": 28.20927619934082,
386
+ "learning_rate": 1.5897435897435897e-05,
387
+ "loss": 2.2465,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 2.1153846153846154,
392
+ "grad_norm": 34.482017517089844,
393
+ "learning_rate": 1.5256410256410259e-05,
394
+ "loss": 2.5232,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 2.1538461538461537,
399
+ "grad_norm": 27.58531379699707,
400
+ "learning_rate": 1.4615384615384617e-05,
401
+ "loss": 2.2702,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 2.1923076923076925,
406
+ "grad_norm": 28.40576171875,
407
+ "learning_rate": 1.3974358974358975e-05,
408
+ "loss": 2.6068,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 2.230769230769231,
413
+ "grad_norm": 28.21039390563965,
414
+ "learning_rate": 1.3333333333333333e-05,
415
+ "loss": 2.426,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 2.269230769230769,
420
+ "grad_norm": 36.4321174621582,
421
+ "learning_rate": 1.2692307692307691e-05,
422
+ "loss": 2.0901,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 2.3076923076923075,
427
+ "grad_norm": 37.081520080566406,
428
+ "learning_rate": 1.2051282051282051e-05,
429
+ "loss": 2.4405,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 2.3461538461538463,
434
+ "grad_norm": 33.08905029296875,
435
+ "learning_rate": 1.1410256410256411e-05,
436
+ "loss": 2.4763,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 2.3846153846153846,
441
+ "grad_norm": 29.76759910583496,
442
+ "learning_rate": 1.0769230769230771e-05,
443
+ "loss": 2.3194,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 2.423076923076923,
448
+ "grad_norm": 27.511579513549805,
449
+ "learning_rate": 1.012820512820513e-05,
450
+ "loss": 2.376,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 2.4615384615384617,
455
+ "grad_norm": 30.223817825317383,
456
+ "learning_rate": 9.487179487179487e-06,
457
+ "loss": 2.2789,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 2.5,
462
+ "grad_norm": 32.20188903808594,
463
+ "learning_rate": 8.846153846153847e-06,
464
+ "loss": 2.0922,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 2.5384615384615383,
469
+ "grad_norm": 26.115158081054688,
470
+ "learning_rate": 8.205128205128205e-06,
471
+ "loss": 1.9232,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 2.5769230769230766,
476
+ "grad_norm": 22.415143966674805,
477
+ "learning_rate": 7.564102564102564e-06,
478
+ "loss": 2.3281,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 2.6153846153846154,
483
+ "grad_norm": 28.419933319091797,
484
+ "learning_rate": 6.923076923076923e-06,
485
+ "loss": 2.5466,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 2.6538461538461537,
490
+ "grad_norm": 32.872928619384766,
491
+ "learning_rate": 6.282051282051282e-06,
492
+ "loss": 2.0911,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 2.6923076923076925,
497
+ "grad_norm": 31.219316482543945,
498
+ "learning_rate": 5.641025641025641e-06,
499
+ "loss": 1.9418,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 2.730769230769231,
504
+ "grad_norm": 27.944660186767578,
505
+ "learning_rate": 5e-06,
506
+ "loss": 2.3476,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 2.769230769230769,
511
+ "grad_norm": 33.40909194946289,
512
+ "learning_rate": 4.3589743589743586e-06,
513
+ "loss": 2.1181,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 2.8076923076923075,
518
+ "grad_norm": 26.774738311767578,
519
+ "learning_rate": 3.717948717948718e-06,
520
+ "loss": 2.088,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 2.8461538461538463,
525
+ "grad_norm": 24.310943603515625,
526
+ "learning_rate": 3.0769230769230774e-06,
527
+ "loss": 2.257,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 2.8846153846153846,
532
+ "grad_norm": 30.991695404052734,
533
+ "learning_rate": 2.435897435897436e-06,
534
+ "loss": 2.0002,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 2.9230769230769234,
539
+ "grad_norm": 32.529354095458984,
540
+ "learning_rate": 1.7948717948717948e-06,
541
+ "loss": 2.3201,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 2.9615384615384617,
546
+ "grad_norm": 36.71170425415039,
547
+ "learning_rate": 1.153846153846154e-06,
548
+ "loss": 2.2811,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 3.0,
553
+ "grad_norm": 22.94892120361328,
554
+ "learning_rate": 5.128205128205128e-07,
555
+ "loss": 2.1842,
556
+ "step": 780
557
+ }
558
+ ],
559
+ "logging_steps": 10,
560
+ "max_steps": 780,
561
+ "num_input_tokens_seen": 0,
562
+ "num_train_epochs": 3,
563
+ "save_steps": 100,
564
+ "stateful_callbacks": {
565
+ "TrainerControl": {
566
+ "args": {
567
+ "should_epoch_stop": false,
568
+ "should_evaluate": false,
569
+ "should_log": false,
570
+ "should_save": true,
571
+ "should_training_stop": true
572
+ },
573
+ "attributes": {}
574
+ }
575
+ },
576
+ "total_flos": 407615569920000.0,
577
+ "train_batch_size": 2,
578
+ "trial_name": null,
579
+ "trial_params": null
580
+ }
checkpoint-780/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfea7e777d36d3cfbbc326685e9eec4b4750fde45efc6b3548e745be7dfe7453
3
+ size 5649
checkpoint-780/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.52.4",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
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": "4.52.4"
6
+ }
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:b90f49d1e4b4dc87d08dca0dce8f2e313cd1bd70ba108822a044de9668c52200
3
+ size 497774208
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_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": false,
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfea7e777d36d3cfbbc326685e9eec4b4750fde45efc6b3548e745be7dfe7453
3
+ size 5649
vocab.json ADDED
The diff for this file is too large to render. See raw diff