iko-01 commited on
Commit
319c62b
·
verified ·
1 Parent(s): 687179b

رفع النموذج النهائي مع جميع الملفات للتجربة أو إعادة التدريب

Browse files
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": "4.55.0",
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": "4.55.0"
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 sha256:7dd1f0520466fa75eaa44e0c4768e8c397275411c0f0b4d56f59cdf6de8dc553
3
+ size 497774208
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70b23aaa31ec22c624baf491dc0e4794f61f6a98a8d167f79ee61dc184d5d1b6
3
+ size 995642298
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d36e6ee20f39b8e7a1c1f67dd0ba64721cc623e0a71615414b27365e6716a4
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46013ea05292bb5196c4a8bc6924c527f4b8e6e1c106364b5149f56bf5f1a74e
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c607a44004e605722acfcc3f4883cca28e9b3aa41c9705b939ee3bffa7eef6
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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": 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
+ }
trainer_state.json ADDED
@@ -0,0 +1,785 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 1000,
7
+ "global_step": 9753,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03076804738279297,
14
+ "grad_norm": 2.239741325378418,
15
+ "learning_rate": 4.85e-05,
16
+ "loss": 2.6548,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.06153609476558594,
21
+ "grad_norm": 1.6382789611816406,
22
+ "learning_rate": 4.94975655236714e-05,
23
+ "loss": 2.3258,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.09230414214837891,
28
+ "grad_norm": 1.4356640577316284,
29
+ "learning_rate": 4.89795918367347e-05,
30
+ "loss": 2.2618,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.12307218953117188,
35
+ "grad_norm": 1.5954153537750244,
36
+ "learning_rate": 4.846161814979799e-05,
37
+ "loss": 2.2213,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.15384023691396484,
42
+ "grad_norm": 1.5558085441589355,
43
+ "learning_rate": 4.794364446286129e-05,
44
+ "loss": 2.2169,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.18460828429675782,
49
+ "grad_norm": 1.3300689458847046,
50
+ "learning_rate": 4.7425670775924586e-05,
51
+ "loss": 2.1835,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.21537633167955078,
56
+ "grad_norm": 1.5879923105239868,
57
+ "learning_rate": 4.690769708898788e-05,
58
+ "loss": 2.1786,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.24614437906234377,
63
+ "grad_norm": 1.4449992179870605,
64
+ "learning_rate": 4.638972340205118e-05,
65
+ "loss": 2.17,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.27691242644513675,
70
+ "grad_norm": 1.660819411277771,
71
+ "learning_rate": 4.5871749715114475e-05,
72
+ "loss": 2.1397,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.3076804738279297,
77
+ "grad_norm": 1.3502899408340454,
78
+ "learning_rate": 4.535377602817777e-05,
79
+ "loss": 2.1476,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.3076804738279297,
84
+ "eval_loss": 2.0527570247650146,
85
+ "eval_runtime": 4.7056,
86
+ "eval_samples_per_second": 42.502,
87
+ "eval_steps_per_second": 21.251,
88
+ "step": 1000
89
+ },
90
+ {
91
+ "epoch": 0.33844852121072266,
92
+ "grad_norm": 1.5296121835708618,
93
+ "learning_rate": 4.483580234124107e-05,
94
+ "loss": 2.1347,
95
+ "step": 1100
96
+ },
97
+ {
98
+ "epoch": 0.36921656859351565,
99
+ "grad_norm": 1.4386141300201416,
100
+ "learning_rate": 4.4317828654304364e-05,
101
+ "loss": 2.1128,
102
+ "step": 1200
103
+ },
104
+ {
105
+ "epoch": 0.3999846159763086,
106
+ "grad_norm": 1.7359758615493774,
107
+ "learning_rate": 4.379985496736766e-05,
108
+ "loss": 2.1256,
109
+ "step": 1300
110
+ },
111
+ {
112
+ "epoch": 0.43075266335910156,
113
+ "grad_norm": 1.2721539735794067,
114
+ "learning_rate": 4.3281881280430956e-05,
115
+ "loss": 2.0986,
116
+ "step": 1400
117
+ },
118
+ {
119
+ "epoch": 0.46152071074189455,
120
+ "grad_norm": 1.507233738899231,
121
+ "learning_rate": 4.276390759349425e-05,
122
+ "loss": 2.1203,
123
+ "step": 1500
124
+ },
125
+ {
126
+ "epoch": 0.49228875812468753,
127
+ "grad_norm": 1.5739669799804688,
128
+ "learning_rate": 4.224593390655755e-05,
129
+ "loss": 2.0817,
130
+ "step": 1600
131
+ },
132
+ {
133
+ "epoch": 0.5230568055074805,
134
+ "grad_norm": 1.7889518737792969,
135
+ "learning_rate": 4.1727960219620845e-05,
136
+ "loss": 2.0951,
137
+ "step": 1700
138
+ },
139
+ {
140
+ "epoch": 0.5538248528902735,
141
+ "grad_norm": 1.3344364166259766,
142
+ "learning_rate": 4.120998653268414e-05,
143
+ "loss": 2.0856,
144
+ "step": 1800
145
+ },
146
+ {
147
+ "epoch": 0.5845929002730664,
148
+ "grad_norm": 1.4601390361785889,
149
+ "learning_rate": 4.069201284574744e-05,
150
+ "loss": 2.0758,
151
+ "step": 1900
152
+ },
153
+ {
154
+ "epoch": 0.6153609476558594,
155
+ "grad_norm": 1.1662238836288452,
156
+ "learning_rate": 4.0174039158810734e-05,
157
+ "loss": 2.0747,
158
+ "step": 2000
159
+ },
160
+ {
161
+ "epoch": 0.6153609476558594,
162
+ "eval_loss": 1.9568997621536255,
163
+ "eval_runtime": 4.6999,
164
+ "eval_samples_per_second": 42.554,
165
+ "eval_steps_per_second": 21.277,
166
+ "step": 2000
167
+ },
168
+ {
169
+ "epoch": 0.6461289950386524,
170
+ "grad_norm": 1.5872595310211182,
171
+ "learning_rate": 3.965606547187403e-05,
172
+ "loss": 2.0822,
173
+ "step": 2100
174
+ },
175
+ {
176
+ "epoch": 0.6768970424214453,
177
+ "grad_norm": 1.1704156398773193,
178
+ "learning_rate": 3.913809178493733e-05,
179
+ "loss": 2.0962,
180
+ "step": 2200
181
+ },
182
+ {
183
+ "epoch": 0.7076650898042383,
184
+ "grad_norm": 1.6314693689346313,
185
+ "learning_rate": 3.8620118098000623e-05,
186
+ "loss": 2.0639,
187
+ "step": 2300
188
+ },
189
+ {
190
+ "epoch": 0.7384331371870313,
191
+ "grad_norm": 1.4110997915267944,
192
+ "learning_rate": 3.810214441106392e-05,
193
+ "loss": 2.0581,
194
+ "step": 2400
195
+ },
196
+ {
197
+ "epoch": 0.7692011845698242,
198
+ "grad_norm": 1.2487901449203491,
199
+ "learning_rate": 3.7584170724127216e-05,
200
+ "loss": 2.0588,
201
+ "step": 2500
202
+ },
203
+ {
204
+ "epoch": 0.7999692319526172,
205
+ "grad_norm": 1.5325045585632324,
206
+ "learning_rate": 3.706619703719051e-05,
207
+ "loss": 2.0731,
208
+ "step": 2600
209
+ },
210
+ {
211
+ "epoch": 0.8307372793354102,
212
+ "grad_norm": 1.2173811197280884,
213
+ "learning_rate": 3.654822335025381e-05,
214
+ "loss": 2.0459,
215
+ "step": 2700
216
+ },
217
+ {
218
+ "epoch": 0.8615053267182031,
219
+ "grad_norm": 1.6108065843582153,
220
+ "learning_rate": 3.6030249663317105e-05,
221
+ "loss": 2.0776,
222
+ "step": 2800
223
+ },
224
+ {
225
+ "epoch": 0.8922733741009962,
226
+ "grad_norm": 1.7993882894515991,
227
+ "learning_rate": 3.55122759763804e-05,
228
+ "loss": 2.0391,
229
+ "step": 2900
230
+ },
231
+ {
232
+ "epoch": 0.9230414214837891,
233
+ "grad_norm": 1.4659514427185059,
234
+ "learning_rate": 3.49943022894437e-05,
235
+ "loss": 2.0292,
236
+ "step": 3000
237
+ },
238
+ {
239
+ "epoch": 0.9230414214837891,
240
+ "eval_loss": 1.8916079998016357,
241
+ "eval_runtime": 4.8218,
242
+ "eval_samples_per_second": 41.478,
243
+ "eval_steps_per_second": 20.739,
244
+ "step": 3000
245
+ },
246
+ {
247
+ "epoch": 0.953809468866582,
248
+ "grad_norm": 1.5378167629241943,
249
+ "learning_rate": 3.4476328602506994e-05,
250
+ "loss": 2.0525,
251
+ "step": 3100
252
+ },
253
+ {
254
+ "epoch": 0.9845775162493751,
255
+ "grad_norm": 1.4396274089813232,
256
+ "learning_rate": 3.395835491557029e-05,
257
+ "loss": 2.0479,
258
+ "step": 3200
259
+ },
260
+ {
261
+ "epoch": 1.0150763432175685,
262
+ "grad_norm": 1.1797999143600464,
263
+ "learning_rate": 3.344038122863359e-05,
264
+ "loss": 1.9838,
265
+ "step": 3300
266
+ },
267
+ {
268
+ "epoch": 1.0458443906003616,
269
+ "grad_norm": 1.2820570468902588,
270
+ "learning_rate": 3.292240754169688e-05,
271
+ "loss": 1.9482,
272
+ "step": 3400
273
+ },
274
+ {
275
+ "epoch": 1.0766124379831545,
276
+ "grad_norm": 1.4676374197006226,
277
+ "learning_rate": 3.240443385476018e-05,
278
+ "loss": 1.9538,
279
+ "step": 3500
280
+ },
281
+ {
282
+ "epoch": 1.1073804853659475,
283
+ "grad_norm": 1.5519450902938843,
284
+ "learning_rate": 3.1886460167823476e-05,
285
+ "loss": 1.9727,
286
+ "step": 3600
287
+ },
288
+ {
289
+ "epoch": 1.1381485327487404,
290
+ "grad_norm": 1.3620473146438599,
291
+ "learning_rate": 3.136848648088677e-05,
292
+ "loss": 1.96,
293
+ "step": 3700
294
+ },
295
+ {
296
+ "epoch": 1.1689165801315333,
297
+ "grad_norm": 1.3301316499710083,
298
+ "learning_rate": 3.085051279395007e-05,
299
+ "loss": 1.9463,
300
+ "step": 3800
301
+ },
302
+ {
303
+ "epoch": 1.1996846275143263,
304
+ "grad_norm": 1.3053226470947266,
305
+ "learning_rate": 3.0332539107013365e-05,
306
+ "loss": 1.9709,
307
+ "step": 3900
308
+ },
309
+ {
310
+ "epoch": 1.2304526748971194,
311
+ "grad_norm": 1.2289018630981445,
312
+ "learning_rate": 2.981456542007666e-05,
313
+ "loss": 1.9847,
314
+ "step": 4000
315
+ },
316
+ {
317
+ "epoch": 1.2304526748971194,
318
+ "eval_loss": 1.8471519947052002,
319
+ "eval_runtime": 4.6843,
320
+ "eval_samples_per_second": 42.696,
321
+ "eval_steps_per_second": 21.348,
322
+ "step": 4000
323
+ },
324
+ {
325
+ "epoch": 1.2612207222799123,
326
+ "grad_norm": 1.319795846939087,
327
+ "learning_rate": 2.9296591733139954e-05,
328
+ "loss": 1.9524,
329
+ "step": 4100
330
+ },
331
+ {
332
+ "epoch": 1.2919887696627053,
333
+ "grad_norm": 1.1395128965377808,
334
+ "learning_rate": 2.8778618046203254e-05,
335
+ "loss": 1.9531,
336
+ "step": 4200
337
+ },
338
+ {
339
+ "epoch": 1.3227568170454982,
340
+ "grad_norm": 1.2818642854690552,
341
+ "learning_rate": 2.8260644359266553e-05,
342
+ "loss": 1.946,
343
+ "step": 4300
344
+ },
345
+ {
346
+ "epoch": 1.3535248644282913,
347
+ "grad_norm": 1.404370903968811,
348
+ "learning_rate": 2.7742670672329846e-05,
349
+ "loss": 1.9611,
350
+ "step": 4400
351
+ },
352
+ {
353
+ "epoch": 1.3842929118110843,
354
+ "grad_norm": 1.3051358461380005,
355
+ "learning_rate": 2.7224696985393146e-05,
356
+ "loss": 1.9345,
357
+ "step": 4500
358
+ },
359
+ {
360
+ "epoch": 1.4150609591938772,
361
+ "grad_norm": 1.2720344066619873,
362
+ "learning_rate": 2.670672329845644e-05,
363
+ "loss": 1.9596,
364
+ "step": 4600
365
+ },
366
+ {
367
+ "epoch": 1.4458290065766701,
368
+ "grad_norm": 1.1316062211990356,
369
+ "learning_rate": 2.6188749611519735e-05,
370
+ "loss": 1.9655,
371
+ "step": 4700
372
+ },
373
+ {
374
+ "epoch": 1.476597053959463,
375
+ "grad_norm": 1.1589127779006958,
376
+ "learning_rate": 2.56759556614524e-05,
377
+ "loss": 1.9336,
378
+ "step": 4800
379
+ },
380
+ {
381
+ "epoch": 1.507365101342256,
382
+ "grad_norm": 1.418484091758728,
383
+ "learning_rate": 2.5157981974515692e-05,
384
+ "loss": 1.9538,
385
+ "step": 4900
386
+ },
387
+ {
388
+ "epoch": 1.538133148725049,
389
+ "grad_norm": 1.1148117780685425,
390
+ "learning_rate": 2.464000828757899e-05,
391
+ "loss": 1.9373,
392
+ "step": 5000
393
+ },
394
+ {
395
+ "epoch": 1.538133148725049,
396
+ "eval_loss": 1.8176252841949463,
397
+ "eval_runtime": 4.6868,
398
+ "eval_samples_per_second": 42.673,
399
+ "eval_steps_per_second": 21.337,
400
+ "step": 5000
401
+ },
402
+ {
403
+ "epoch": 1.5689011961078418,
404
+ "grad_norm": 1.409507155418396,
405
+ "learning_rate": 2.4122034600642288e-05,
406
+ "loss": 1.9487,
407
+ "step": 5100
408
+ },
409
+ {
410
+ "epoch": 1.599669243490635,
411
+ "grad_norm": 1.4098600149154663,
412
+ "learning_rate": 2.3604060913705588e-05,
413
+ "loss": 1.9158,
414
+ "step": 5200
415
+ },
416
+ {
417
+ "epoch": 1.630437290873428,
418
+ "grad_norm": 1.2400621175765991,
419
+ "learning_rate": 2.308608722676888e-05,
420
+ "loss": 1.9257,
421
+ "step": 5300
422
+ },
423
+ {
424
+ "epoch": 1.661205338256221,
425
+ "grad_norm": 1.3149056434631348,
426
+ "learning_rate": 2.2568113539832177e-05,
427
+ "loss": 1.9254,
428
+ "step": 5400
429
+ },
430
+ {
431
+ "epoch": 1.691973385639014,
432
+ "grad_norm": 1.306784749031067,
433
+ "learning_rate": 2.2050139852895473e-05,
434
+ "loss": 1.9446,
435
+ "step": 5500
436
+ },
437
+ {
438
+ "epoch": 1.722741433021807,
439
+ "grad_norm": 1.3898966312408447,
440
+ "learning_rate": 2.153216616595877e-05,
441
+ "loss": 1.9151,
442
+ "step": 5600
443
+ },
444
+ {
445
+ "epoch": 1.7535094804045999,
446
+ "grad_norm": 1.2994170188903809,
447
+ "learning_rate": 2.1014192479022066e-05,
448
+ "loss": 1.9464,
449
+ "step": 5700
450
+ },
451
+ {
452
+ "epoch": 1.7842775277873928,
453
+ "grad_norm": 1.3611286878585815,
454
+ "learning_rate": 2.0496218792085366e-05,
455
+ "loss": 1.9206,
456
+ "step": 5800
457
+ },
458
+ {
459
+ "epoch": 1.8150455751701857,
460
+ "grad_norm": 1.406435489654541,
461
+ "learning_rate": 1.997824510514866e-05,
462
+ "loss": 1.9303,
463
+ "step": 5900
464
+ },
465
+ {
466
+ "epoch": 1.8458136225529787,
467
+ "grad_norm": 1.4985857009887695,
468
+ "learning_rate": 1.9460271418211955e-05,
469
+ "loss": 1.9306,
470
+ "step": 6000
471
+ },
472
+ {
473
+ "epoch": 1.8458136225529787,
474
+ "eval_loss": 1.7914341688156128,
475
+ "eval_runtime": 4.8041,
476
+ "eval_samples_per_second": 41.631,
477
+ "eval_steps_per_second": 20.816,
478
+ "step": 6000
479
+ },
480
+ {
481
+ "epoch": 1.8765816699357716,
482
+ "grad_norm": 1.3169234991073608,
483
+ "learning_rate": 1.894229773127525e-05,
484
+ "loss": 1.9435,
485
+ "step": 6100
486
+ },
487
+ {
488
+ "epoch": 1.9073497173185645,
489
+ "grad_norm": 1.4807860851287842,
490
+ "learning_rate": 1.8424324044338548e-05,
491
+ "loss": 1.9108,
492
+ "step": 6200
493
+ },
494
+ {
495
+ "epoch": 1.9381177647013577,
496
+ "grad_norm": 1.5189799070358276,
497
+ "learning_rate": 1.7906350357401844e-05,
498
+ "loss": 1.9274,
499
+ "step": 6300
500
+ },
501
+ {
502
+ "epoch": 1.9688858120841506,
503
+ "grad_norm": 1.37026846408844,
504
+ "learning_rate": 1.7388376670465144e-05,
505
+ "loss": 1.9307,
506
+ "step": 6400
507
+ },
508
+ {
509
+ "epoch": 1.9996538594669437,
510
+ "grad_norm": 1.2851979732513428,
511
+ "learning_rate": 1.687040298352844e-05,
512
+ "loss": 1.9324,
513
+ "step": 6500
514
+ },
515
+ {
516
+ "epoch": 2.030152686435137,
517
+ "grad_norm": 1.5312321186065674,
518
+ "learning_rate": 1.6352429296591733e-05,
519
+ "loss": 1.8818,
520
+ "step": 6600
521
+ },
522
+ {
523
+ "epoch": 2.0609207338179303,
524
+ "grad_norm": 1.2317149639129639,
525
+ "learning_rate": 1.583445560965503e-05,
526
+ "loss": 1.8666,
527
+ "step": 6700
528
+ },
529
+ {
530
+ "epoch": 2.091688781200723,
531
+ "grad_norm": 1.4043223857879639,
532
+ "learning_rate": 1.5316481922718326e-05,
533
+ "loss": 1.8588,
534
+ "step": 6800
535
+ },
536
+ {
537
+ "epoch": 2.122456828583516,
538
+ "grad_norm": 1.3751603364944458,
539
+ "learning_rate": 1.4798508235781622e-05,
540
+ "loss": 1.873,
541
+ "step": 6900
542
+ },
543
+ {
544
+ "epoch": 2.153224875966309,
545
+ "grad_norm": 1.605711579322815,
546
+ "learning_rate": 1.428053454884492e-05,
547
+ "loss": 1.8861,
548
+ "step": 7000
549
+ },
550
+ {
551
+ "epoch": 2.153224875966309,
552
+ "eval_loss": 1.770365595817566,
553
+ "eval_runtime": 4.8144,
554
+ "eval_samples_per_second": 41.542,
555
+ "eval_steps_per_second": 20.771,
556
+ "step": 7000
557
+ },
558
+ {
559
+ "epoch": 2.183992923349102,
560
+ "grad_norm": 1.642946720123291,
561
+ "learning_rate": 1.3762560861908216e-05,
562
+ "loss": 1.8608,
563
+ "step": 7100
564
+ },
565
+ {
566
+ "epoch": 2.214760970731895,
567
+ "grad_norm": 1.3048804998397827,
568
+ "learning_rate": 1.3244587174971513e-05,
569
+ "loss": 1.8653,
570
+ "step": 7200
571
+ },
572
+ {
573
+ "epoch": 2.245529018114688,
574
+ "grad_norm": 1.3654470443725586,
575
+ "learning_rate": 1.2726613488034809e-05,
576
+ "loss": 1.8803,
577
+ "step": 7300
578
+ },
579
+ {
580
+ "epoch": 2.276297065497481,
581
+ "grad_norm": 1.377312421798706,
582
+ "learning_rate": 1.2208639801098105e-05,
583
+ "loss": 1.8783,
584
+ "step": 7400
585
+ },
586
+ {
587
+ "epoch": 2.3070651128802737,
588
+ "grad_norm": 1.2883929014205933,
589
+ "learning_rate": 1.1690666114161402e-05,
590
+ "loss": 1.8612,
591
+ "step": 7500
592
+ },
593
+ {
594
+ "epoch": 2.3378331602630666,
595
+ "grad_norm": 1.3439315557479858,
596
+ "learning_rate": 1.1172692427224698e-05,
597
+ "loss": 1.8627,
598
+ "step": 7600
599
+ },
600
+ {
601
+ "epoch": 2.3686012076458596,
602
+ "grad_norm": 1.1767522096633911,
603
+ "learning_rate": 1.0654718740287994e-05,
604
+ "loss": 1.8713,
605
+ "step": 7700
606
+ },
607
+ {
608
+ "epoch": 2.3993692550286525,
609
+ "grad_norm": 1.2367137670516968,
610
+ "learning_rate": 1.0141924790220656e-05,
611
+ "loss": 1.8753,
612
+ "step": 7800
613
+ },
614
+ {
615
+ "epoch": 2.430137302411446,
616
+ "grad_norm": 1.218923568725586,
617
+ "learning_rate": 9.623951103283954e-06,
618
+ "loss": 1.8924,
619
+ "step": 7900
620
+ },
621
+ {
622
+ "epoch": 2.460905349794239,
623
+ "grad_norm": 1.481924057006836,
624
+ "learning_rate": 9.10597741634725e-06,
625
+ "loss": 1.875,
626
+ "step": 8000
627
+ },
628
+ {
629
+ "epoch": 2.460905349794239,
630
+ "eval_loss": 1.7587065696716309,
631
+ "eval_runtime": 4.6695,
632
+ "eval_samples_per_second": 42.831,
633
+ "eval_steps_per_second": 21.416,
634
+ "step": 8000
635
+ },
636
+ {
637
+ "epoch": 2.4916733971770317,
638
+ "grad_norm": 1.5611909627914429,
639
+ "learning_rate": 8.588003729410545e-06,
640
+ "loss": 1.8847,
641
+ "step": 8100
642
+ },
643
+ {
644
+ "epoch": 2.5224414445598247,
645
+ "grad_norm": 1.573014736175537,
646
+ "learning_rate": 8.070030042473843e-06,
647
+ "loss": 1.8645,
648
+ "step": 8200
649
+ },
650
+ {
651
+ "epoch": 2.5532094919426176,
652
+ "grad_norm": 1.4010423421859741,
653
+ "learning_rate": 7.5520563555371394e-06,
654
+ "loss": 1.8716,
655
+ "step": 8300
656
+ },
657
+ {
658
+ "epoch": 2.5839775393254105,
659
+ "grad_norm": 1.4731730222702026,
660
+ "learning_rate": 7.034082668600435e-06,
661
+ "loss": 1.8545,
662
+ "step": 8400
663
+ },
664
+ {
665
+ "epoch": 2.6147455867082035,
666
+ "grad_norm": 1.5401034355163574,
667
+ "learning_rate": 6.516108981663732e-06,
668
+ "loss": 1.8701,
669
+ "step": 8500
670
+ },
671
+ {
672
+ "epoch": 2.6455136340909964,
673
+ "grad_norm": 1.4150763750076294,
674
+ "learning_rate": 5.998135294727028e-06,
675
+ "loss": 1.8781,
676
+ "step": 8600
677
+ },
678
+ {
679
+ "epoch": 2.6762816814737893,
680
+ "grad_norm": 1.2187877893447876,
681
+ "learning_rate": 5.480161607790325e-06,
682
+ "loss": 1.8554,
683
+ "step": 8700
684
+ },
685
+ {
686
+ "epoch": 2.7070497288565827,
687
+ "grad_norm": 1.2359226942062378,
688
+ "learning_rate": 4.962187920853621e-06,
689
+ "loss": 1.8655,
690
+ "step": 8800
691
+ },
692
+ {
693
+ "epoch": 2.7378177762393756,
694
+ "grad_norm": 1.5639677047729492,
695
+ "learning_rate": 4.444214233916917e-06,
696
+ "loss": 1.8702,
697
+ "step": 8900
698
+ },
699
+ {
700
+ "epoch": 2.7685858236221685,
701
+ "grad_norm": 1.3015304803848267,
702
+ "learning_rate": 3.926240546980214e-06,
703
+ "loss": 1.8724,
704
+ "step": 9000
705
+ },
706
+ {
707
+ "epoch": 2.7685858236221685,
708
+ "eval_loss": 1.7501640319824219,
709
+ "eval_runtime": 4.6364,
710
+ "eval_samples_per_second": 43.137,
711
+ "eval_steps_per_second": 21.568,
712
+ "step": 9000
713
+ },
714
+ {
715
+ "epoch": 2.7993538710049615,
716
+ "grad_norm": 1.2435898780822754,
717
+ "learning_rate": 3.40826686004351e-06,
718
+ "loss": 1.8699,
719
+ "step": 9100
720
+ },
721
+ {
722
+ "epoch": 2.8301219183877544,
723
+ "grad_norm": 1.4046730995178223,
724
+ "learning_rate": 2.890293173106806e-06,
725
+ "loss": 1.874,
726
+ "step": 9200
727
+ },
728
+ {
729
+ "epoch": 2.8608899657705473,
730
+ "grad_norm": 1.4343743324279785,
731
+ "learning_rate": 2.3723194861701027e-06,
732
+ "loss": 1.8844,
733
+ "step": 9300
734
+ },
735
+ {
736
+ "epoch": 2.8916580131533403,
737
+ "grad_norm": 1.506251573562622,
738
+ "learning_rate": 1.8543457992333989e-06,
739
+ "loss": 1.8738,
740
+ "step": 9400
741
+ },
742
+ {
743
+ "epoch": 2.922426060536133,
744
+ "grad_norm": 1.1848888397216797,
745
+ "learning_rate": 1.3363721122966954e-06,
746
+ "loss": 1.8549,
747
+ "step": 9500
748
+ },
749
+ {
750
+ "epoch": 2.953194107918926,
751
+ "grad_norm": 1.301543951034546,
752
+ "learning_rate": 8.183984253599917e-07,
753
+ "loss": 1.8691,
754
+ "step": 9600
755
+ },
756
+ {
757
+ "epoch": 2.983962155301719,
758
+ "grad_norm": 1.4360523223876953,
759
+ "learning_rate": 3.004247384232881e-07,
760
+ "loss": 1.8902,
761
+ "step": 9700
762
+ }
763
+ ],
764
+ "logging_steps": 100,
765
+ "max_steps": 9753,
766
+ "num_input_tokens_seen": 0,
767
+ "num_train_epochs": 3,
768
+ "save_steps": 1000,
769
+ "stateful_callbacks": {
770
+ "TrainerControl": {
771
+ "args": {
772
+ "should_epoch_stop": false,
773
+ "should_evaluate": false,
774
+ "should_log": false,
775
+ "should_save": true,
776
+ "should_training_stop": true
777
+ },
778
+ "attributes": {}
779
+ }
780
+ },
781
+ "total_flos": 4.0763124744192e+16,
782
+ "train_batch_size": 2,
783
+ "trial_name": null,
784
+ "trial_params": null
785
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:688ac40b572e6626acc4f76fd76651e064c4e98948473dd4ad6cf529eb8d42fe
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff