iko-01 commited on
Commit
b8d5816
·
verified ·
1 Parent(s): e561fdb

رفع النموذج النهائي مع جميع الملفات للتجربة أو إعادة التدريب

Browse files
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 0,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 0,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 5,
36
+ "repetition_penalty": 3.0,
37
+ "top_p": 0.95
38
+ }
39
+ },
40
+ "transformers_version": "4.56.1",
41
+ "use_cache": true,
42
+ "vocab_size": 64000
43
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.56.1"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c1c9b93991fd4be6cb6cf7edcca69d3f545f6e08e57a80684a8e844fcc9056
3
+ size 736600912
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96239389c5d882bcff875b3301dde66de02015d08df8455c25546bedaf7608a3
3
+ size 1080075595
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3953c41bfc3645f93342259686c36136c2be99e69836cc1ef42160f04b9ee99d
3
+ size 14455
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65bc03a7579a29fc9ca39b593d19d74f8e65ba749bb5b976d6d91e4c4010bc16
3
+ size 1465
trainer_state.json ADDED
@@ -0,0 +1,755 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 5187,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00963948332369385,
14
+ "grad_norm": 6.363353729248047,
15
+ "learning_rate": 4.9527665317139e-05,
16
+ "loss": 5.7207,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.0192789666473877,
21
+ "grad_norm": 6.101255416870117,
22
+ "learning_rate": 4.904569115095431e-05,
23
+ "loss": 4.3487,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.02891844997108155,
28
+ "grad_norm": 5.563638210296631,
29
+ "learning_rate": 4.856371698476962e-05,
30
+ "loss": 4.077,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.0385579332947754,
35
+ "grad_norm": 5.894318580627441,
36
+ "learning_rate": 4.8081742818584925e-05,
37
+ "loss": 3.8687,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.04819741661846925,
42
+ "grad_norm": 5.281033992767334,
43
+ "learning_rate": 4.7599768652400236e-05,
44
+ "loss": 3.698,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.0578368999421631,
49
+ "grad_norm": 5.9448089599609375,
50
+ "learning_rate": 4.711779448621554e-05,
51
+ "loss": 3.5277,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.06747638326585695,
56
+ "grad_norm": 5.122015953063965,
57
+ "learning_rate": 4.6635820320030846e-05,
58
+ "loss": 3.524,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.0771158665895508,
63
+ "grad_norm": 5.508582592010498,
64
+ "learning_rate": 4.615384615384616e-05,
65
+ "loss": 3.3969,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.08675534991324466,
70
+ "grad_norm": 4.6635661125183105,
71
+ "learning_rate": 4.567187198766146e-05,
72
+ "loss": 3.4104,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.0963948332369385,
77
+ "grad_norm": 4.993603706359863,
78
+ "learning_rate": 4.5189897821476775e-05,
79
+ "loss": 3.317,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.10603431656063235,
84
+ "grad_norm": 4.281131267547607,
85
+ "learning_rate": 4.470792365529208e-05,
86
+ "loss": 3.27,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.1156737998843262,
91
+ "grad_norm": 4.340400218963623,
92
+ "learning_rate": 4.4225949489107385e-05,
93
+ "loss": 3.2469,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.12531328320802004,
98
+ "grad_norm": 4.594860076904297,
99
+ "learning_rate": 4.374397532292269e-05,
100
+ "loss": 3.1855,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.1349527665317139,
105
+ "grad_norm": 4.50878381729126,
106
+ "learning_rate": 4.3262001156738e-05,
107
+ "loss": 3.1646,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.14459224985540775,
112
+ "grad_norm": 4.4101715087890625,
113
+ "learning_rate": 4.278002699055331e-05,
114
+ "loss": 3.0478,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.1542317331791016,
119
+ "grad_norm": 4.285751819610596,
120
+ "learning_rate": 4.229805282436862e-05,
121
+ "loss": 3.0654,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.16387121650279546,
126
+ "grad_norm": 4.346066474914551,
127
+ "learning_rate": 4.1816078658183924e-05,
128
+ "loss": 3.1125,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.1735106998264893,
133
+ "grad_norm": 4.069290637969971,
134
+ "learning_rate": 4.133410449199923e-05,
135
+ "loss": 3.0389,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.18315018315018314,
140
+ "grad_norm": 4.5510382652282715,
141
+ "learning_rate": 4.0852130325814534e-05,
142
+ "loss": 2.9808,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.192789666473877,
147
+ "grad_norm": 4.202208995819092,
148
+ "learning_rate": 4.0370156159629845e-05,
149
+ "loss": 3.0209,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.20242914979757085,
154
+ "grad_norm": 5.317561149597168,
155
+ "learning_rate": 3.988818199344515e-05,
156
+ "loss": 3.0355,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.2120686331212647,
161
+ "grad_norm": 4.339507102966309,
162
+ "learning_rate": 3.940620782726046e-05,
163
+ "loss": 2.9353,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.22170811644495855,
168
+ "grad_norm": 4.036981105804443,
169
+ "learning_rate": 3.8924233661075774e-05,
170
+ "loss": 2.9902,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.2313475997686524,
175
+ "grad_norm": 4.5993757247924805,
176
+ "learning_rate": 3.844225949489107e-05,
177
+ "loss": 2.9957,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.24098708309234626,
182
+ "grad_norm": 4.273294448852539,
183
+ "learning_rate": 3.7960285328706384e-05,
184
+ "loss": 2.9309,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.2506265664160401,
189
+ "grad_norm": 4.0223774909973145,
190
+ "learning_rate": 3.747831116252169e-05,
191
+ "loss": 2.8886,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.26026604973973394,
196
+ "grad_norm": 4.813283443450928,
197
+ "learning_rate": 3.6996336996337e-05,
198
+ "loss": 2.7496,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.2699055330634278,
203
+ "grad_norm": 4.476084232330322,
204
+ "learning_rate": 3.6514362830152306e-05,
205
+ "loss": 2.8673,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.27954501638712165,
210
+ "grad_norm": 4.051555156707764,
211
+ "learning_rate": 3.603238866396762e-05,
212
+ "loss": 2.8135,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.2891844997108155,
217
+ "grad_norm": 4.186788558959961,
218
+ "learning_rate": 3.5550414497782916e-05,
219
+ "loss": 2.9019,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.29882398303450936,
224
+ "grad_norm": 4.216615200042725,
225
+ "learning_rate": 3.506844033159823e-05,
226
+ "loss": 2.8877,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.3084634663582032,
231
+ "grad_norm": 4.653785705566406,
232
+ "learning_rate": 3.458646616541353e-05,
233
+ "loss": 2.8091,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.31810294968189706,
238
+ "grad_norm": 3.883335828781128,
239
+ "learning_rate": 3.4104491999228844e-05,
240
+ "loss": 2.7521,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.3277424330055909,
245
+ "grad_norm": 4.467517375946045,
246
+ "learning_rate": 3.362251783304415e-05,
247
+ "loss": 2.7753,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.33738191632928477,
252
+ "grad_norm": 3.839921474456787,
253
+ "learning_rate": 3.314054366685946e-05,
254
+ "loss": 2.7853,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.3470213996529786,
259
+ "grad_norm": 3.923483371734619,
260
+ "learning_rate": 3.2658569500674766e-05,
261
+ "loss": 2.872,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.3566608829766725,
266
+ "grad_norm": 4.523361682891846,
267
+ "learning_rate": 3.217659533449007e-05,
268
+ "loss": 2.7785,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.3663003663003663,
273
+ "grad_norm": 3.865365743637085,
274
+ "learning_rate": 3.169462116830538e-05,
275
+ "loss": 2.8373,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.37593984962406013,
280
+ "grad_norm": 3.9936673641204834,
281
+ "learning_rate": 3.121264700212069e-05,
282
+ "loss": 2.7323,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.385579332947754,
287
+ "grad_norm": 4.1067633628845215,
288
+ "learning_rate": 3.0730672835936e-05,
289
+ "loss": 2.7585,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.39521881627144784,
294
+ "grad_norm": 3.85208797454834,
295
+ "learning_rate": 3.02486986697513e-05,
296
+ "loss": 2.7564,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.4048582995951417,
301
+ "grad_norm": 4.24629020690918,
302
+ "learning_rate": 2.9766724503566613e-05,
303
+ "loss": 2.7274,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.41449778291883554,
308
+ "grad_norm": 3.905611276626587,
309
+ "learning_rate": 2.9284750337381918e-05,
310
+ "loss": 2.7094,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.4241372662425294,
315
+ "grad_norm": 3.9592058658599854,
316
+ "learning_rate": 2.8802776171197226e-05,
317
+ "loss": 2.7046,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.43377674956622325,
322
+ "grad_norm": 3.860285520553589,
323
+ "learning_rate": 2.832080200501253e-05,
324
+ "loss": 2.7154,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.4434162328899171,
329
+ "grad_norm": 3.989696502685547,
330
+ "learning_rate": 2.783882783882784e-05,
331
+ "loss": 2.6632,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.45305571621361096,
336
+ "grad_norm": 3.987741708755493,
337
+ "learning_rate": 2.7356853672643145e-05,
338
+ "loss": 2.7178,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.4626951995373048,
343
+ "grad_norm": 3.9146411418914795,
344
+ "learning_rate": 2.6874879506458457e-05,
345
+ "loss": 2.7039,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.47233468286099867,
350
+ "grad_norm": 4.281154155731201,
351
+ "learning_rate": 2.639290534027376e-05,
352
+ "loss": 2.6205,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.4819741661846925,
357
+ "grad_norm": 3.6197686195373535,
358
+ "learning_rate": 2.591093117408907e-05,
359
+ "loss": 2.723,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.4916136495083864,
364
+ "grad_norm": 3.7195041179656982,
365
+ "learning_rate": 2.5428957007904375e-05,
366
+ "loss": 2.6071,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.5012531328320802,
371
+ "grad_norm": 3.775972604751587,
372
+ "learning_rate": 2.4946982841719683e-05,
373
+ "loss": 2.6749,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.5108926161557741,
378
+ "grad_norm": 3.9212749004364014,
379
+ "learning_rate": 2.4465008675534992e-05,
380
+ "loss": 2.6913,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.5205320994794679,
385
+ "grad_norm": 3.9374866485595703,
386
+ "learning_rate": 2.39830345093503e-05,
387
+ "loss": 2.6457,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.5301715828031618,
392
+ "grad_norm": 4.192444801330566,
393
+ "learning_rate": 2.3501060343165605e-05,
394
+ "loss": 2.7204,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.5398110661268556,
399
+ "grad_norm": 3.428612232208252,
400
+ "learning_rate": 2.3019086176980914e-05,
401
+ "loss": 2.7221,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.5494505494505495,
406
+ "grad_norm": 4.013959884643555,
407
+ "learning_rate": 2.2537112010796222e-05,
408
+ "loss": 2.6046,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.5590900327742433,
413
+ "grad_norm": 4.100067138671875,
414
+ "learning_rate": 2.205513784461153e-05,
415
+ "loss": 2.6887,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.5687295160979372,
420
+ "grad_norm": 3.5404722690582275,
421
+ "learning_rate": 2.157316367842684e-05,
422
+ "loss": 2.5933,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.578368999421631,
427
+ "grad_norm": 3.6547091007232666,
428
+ "learning_rate": 2.1091189512242147e-05,
429
+ "loss": 2.6171,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.5880084827453248,
434
+ "grad_norm": 3.81042742729187,
435
+ "learning_rate": 2.0609215346057452e-05,
436
+ "loss": 2.5319,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.5976479660690187,
441
+ "grad_norm": 3.987117052078247,
442
+ "learning_rate": 2.012724117987276e-05,
443
+ "loss": 2.6596,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.6072874493927125,
448
+ "grad_norm": 3.5897133350372314,
449
+ "learning_rate": 1.964526701368807e-05,
450
+ "loss": 2.634,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.6169269327164064,
455
+ "grad_norm": 4.190171241760254,
456
+ "learning_rate": 1.9163292847503374e-05,
457
+ "loss": 2.5889,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.6265664160401002,
462
+ "grad_norm": 3.7671003341674805,
463
+ "learning_rate": 1.8681318681318682e-05,
464
+ "loss": 2.6186,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.6362058993637941,
469
+ "grad_norm": 4.126290798187256,
470
+ "learning_rate": 1.819934451513399e-05,
471
+ "loss": 2.5847,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.6458453826874879,
476
+ "grad_norm": 4.023561000823975,
477
+ "learning_rate": 1.7717370348949296e-05,
478
+ "loss": 2.5474,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.6554848660111818,
483
+ "grad_norm": 3.9225897789001465,
484
+ "learning_rate": 1.7235396182764604e-05,
485
+ "loss": 2.6056,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.6651243493348756,
490
+ "grad_norm": 3.6160168647766113,
491
+ "learning_rate": 1.6753422016579912e-05,
492
+ "loss": 2.5559,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.6747638326585695,
497
+ "grad_norm": 4.005686283111572,
498
+ "learning_rate": 1.6271447850395217e-05,
499
+ "loss": 2.5416,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.6844033159822633,
504
+ "grad_norm": 3.8741414546966553,
505
+ "learning_rate": 1.5789473684210526e-05,
506
+ "loss": 2.5972,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.6940427993059572,
511
+ "grad_norm": 3.710710048675537,
512
+ "learning_rate": 1.5307499518025834e-05,
513
+ "loss": 2.5787,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.703682282629651,
518
+ "grad_norm": 3.460242748260498,
519
+ "learning_rate": 1.4825525351841141e-05,
520
+ "loss": 2.554,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.713321765953345,
525
+ "grad_norm": 3.8803932666778564,
526
+ "learning_rate": 1.4343551185656451e-05,
527
+ "loss": 2.5613,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.7229612492770388,
532
+ "grad_norm": 3.8178253173828125,
533
+ "learning_rate": 1.3861577019471758e-05,
534
+ "loss": 2.5626,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.7326007326007326,
539
+ "grad_norm": 3.364790201187134,
540
+ "learning_rate": 1.3379602853287066e-05,
541
+ "loss": 2.5721,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.7422402159244265,
546
+ "grad_norm": 3.5198776721954346,
547
+ "learning_rate": 1.2897628687102373e-05,
548
+ "loss": 2.5233,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.7518796992481203,
553
+ "grad_norm": 3.782043695449829,
554
+ "learning_rate": 1.241565452091768e-05,
555
+ "loss": 2.541,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.7615191825718142,
560
+ "grad_norm": 4.032742023468018,
561
+ "learning_rate": 1.1933680354732988e-05,
562
+ "loss": 2.493,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.771158665895508,
567
+ "grad_norm": 3.8995766639709473,
568
+ "learning_rate": 1.1451706188548295e-05,
569
+ "loss": 2.5361,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.7807981492192019,
574
+ "grad_norm": 3.67946457862854,
575
+ "learning_rate": 1.0969732022363601e-05,
576
+ "loss": 2.5408,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.7904376325428957,
581
+ "grad_norm": 3.4958484172821045,
582
+ "learning_rate": 1.048775785617891e-05,
583
+ "loss": 2.5261,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.8000771158665896,
588
+ "grad_norm": 3.8448803424835205,
589
+ "learning_rate": 1.0005783689994216e-05,
590
+ "loss": 2.5389,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.8097165991902834,
595
+ "grad_norm": 3.7735507488250732,
596
+ "learning_rate": 9.523809523809523e-06,
597
+ "loss": 2.6247,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 0.8193560825139773,
602
+ "grad_norm": 3.4487788677215576,
603
+ "learning_rate": 9.041835357624833e-06,
604
+ "loss": 2.5704,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 0.8289955658376711,
609
+ "grad_norm": 3.943000316619873,
610
+ "learning_rate": 8.55986119144014e-06,
611
+ "loss": 2.5289,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 0.838635049161365,
616
+ "grad_norm": 3.7842445373535156,
617
+ "learning_rate": 8.077887025255447e-06,
618
+ "loss": 2.5765,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 0.8482745324850588,
623
+ "grad_norm": 3.741563320159912,
624
+ "learning_rate": 7.595912859070754e-06,
625
+ "loss": 2.4869,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 0.8579140158087527,
630
+ "grad_norm": 3.6693384647369385,
631
+ "learning_rate": 7.113938692886062e-06,
632
+ "loss": 2.5513,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 0.8675534991324465,
637
+ "grad_norm": 3.590758800506592,
638
+ "learning_rate": 6.631964526701369e-06,
639
+ "loss": 2.566,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 0.8771929824561403,
644
+ "grad_norm": 3.282844305038452,
645
+ "learning_rate": 6.149990360516677e-06,
646
+ "loss": 2.5001,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 0.8868324657798342,
651
+ "grad_norm": 4.462714195251465,
652
+ "learning_rate": 5.668016194331984e-06,
653
+ "loss": 2.4838,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 0.896471949103528,
658
+ "grad_norm": 4.180957317352295,
659
+ "learning_rate": 5.186042028147292e-06,
660
+ "loss": 2.477,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 0.9061114324272219,
665
+ "grad_norm": 4.506474018096924,
666
+ "learning_rate": 4.7040678619625985e-06,
667
+ "loss": 2.5097,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 0.9157509157509157,
672
+ "grad_norm": 3.257143974304199,
673
+ "learning_rate": 4.222093695777907e-06,
674
+ "loss": 2.6252,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 0.9253903990746096,
679
+ "grad_norm": 3.498189926147461,
680
+ "learning_rate": 3.740119529593214e-06,
681
+ "loss": 2.5133,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 0.9350298823983034,
686
+ "grad_norm": 3.404567241668701,
687
+ "learning_rate": 3.258145363408521e-06,
688
+ "loss": 2.4482,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 0.9446693657219973,
693
+ "grad_norm": 3.703936815261841,
694
+ "learning_rate": 2.776171197223829e-06,
695
+ "loss": 2.5769,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 0.9543088490456911,
700
+ "grad_norm": 4.4313883781433105,
701
+ "learning_rate": 2.2941970310391366e-06,
702
+ "loss": 2.5262,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 0.963948332369385,
707
+ "grad_norm": 3.5869264602661133,
708
+ "learning_rate": 1.8122228648544438e-06,
709
+ "loss": 2.5166,
710
+ "step": 5000
711
+ },
712
+ {
713
+ "epoch": 0.9735878156930788,
714
+ "grad_norm": 3.5782413482666016,
715
+ "learning_rate": 1.3302486986697513e-06,
716
+ "loss": 2.4681,
717
+ "step": 5050
718
+ },
719
+ {
720
+ "epoch": 0.9832272990167727,
721
+ "grad_norm": 3.565708637237549,
722
+ "learning_rate": 8.482745324850588e-07,
723
+ "loss": 2.4661,
724
+ "step": 5100
725
+ },
726
+ {
727
+ "epoch": 0.9928667823404665,
728
+ "grad_norm": 3.5679666996002197,
729
+ "learning_rate": 3.663003663003663e-07,
730
+ "loss": 2.5452,
731
+ "step": 5150
732
+ }
733
+ ],
734
+ "logging_steps": 50,
735
+ "max_steps": 5187,
736
+ "num_input_tokens_seen": 0,
737
+ "num_train_epochs": 1,
738
+ "save_steps": 100,
739
+ "stateful_callbacks": {
740
+ "TrainerControl": {
741
+ "args": {
742
+ "should_epoch_stop": false,
743
+ "should_evaluate": false,
744
+ "should_log": false,
745
+ "should_save": true,
746
+ "should_training_stop": true
747
+ },
748
+ "attributes": {}
749
+ }
750
+ },
751
+ "total_flos": 1355321769984000.0,
752
+ "train_batch_size": 4,
753
+ "trial_name": null,
754
+ "trial_params": null
755
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583805d31ea4f86f27f55cf5d0288b9135b098d6f1caecad279f6924ce7eec2d
3
+ size 5777