Hugging Face's logo

iko-01
/
iko-v5e-1

Text Generation
Transformers
Safetensors
English
gpt2
AI
ENG
GPT-2
model
text-generation-inference
Model card Files
xet
 Community
iko-01 commited on
Commit
53036c5
·
verified ·
1 Parent(s): ffe6e1a

رفع النموذج النهائي مع جميع الملفات للتجربة أو إعادة التدريب

Browse files
Files changed (14) hide show
  1. added_tokens.json +7 -0
  2. config.json +39 -0
  3. generation_config.json +9 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. optimizer.pt +3 -0
  7. rng_state.pth +3 -0
  8. scheduler.pt +3 -0
  9. special_tokens_map.json +42 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +67 -0
  12. trainer_state.json +552 -0
  13. training_args.bin +3 -0
  14. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "### Assistant:": 50259,
3
+ "### User:": 50258,
4
+ "</think>": 50261,
5
+ "<think>": 50260,
6
+ "<|pad|>": 50257
7
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 50257,
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
+ }
35
+ },
36
+ "transformers_version": "4.56.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50262
39
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": [
5
+ 50256
6
+ ],
7
+ "pad_token_id": 50257,
8
+ "transformers_version": "4.56.0"
9
+ }
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 sha256:2dc56ec8d49e5413e237ed790eddef91e21a1c70222c7d7c6b398e308227cb00
3
+ size 652194640
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47accb8b8081790a3f29ece7374d28d83c3075b10ae2190f41293ea6beed3f33
3
+ size 995669323
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581d1b161f21a6db4523fd0d00a745df9d6eed060093de232f5e44dfb42df631
3
+ size 14455
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f975a09987f2df199f63732fb164af1308cf1a940f2c54e935033caeba7a1d4e
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "### User:",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "### Assistant:",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<think>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</think>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ ],
32
+ "bos_token": "<|endoftext|>",
33
+ "eos_token": "<|endoftext|>",
34
+ "pad_token": {
35
+ "content": "<|pad|>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "unk_token": "<|endoftext|>"
42
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|pad|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "### User:",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "### Assistant:",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50260": {
37
+ "content": "<think>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50261": {
45
+ "content": "</think>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ }
52
+ },
53
+ "additional_special_tokens": [
54
+ "### User:",
55
+ "### Assistant:",
56
+ "<think>",
57
+ "</think>"
58
+ ],
59
+ "bos_token": "<|endoftext|>",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "<|endoftext|>",
62
+ "extra_special_tokens": {},
63
+ "model_max_length": 1024,
64
+ "pad_token": "<|pad|>",
65
+ "tokenizer_class": "GPT2Tokenizer",
66
+ "unk_token": "<|endoftext|>"
67
+ }
trainer_state.json ADDED
@@ -0,0 +1,552 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 7453,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.013417415805715819,
14
+ "grad_norm": 5.375,
15
+ "learning_rate": 9.9e-06,
16
+ "loss": 2.42,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.026834831611431638,
21
+ "grad_norm": 4.3125,
22
+ "learning_rate": 1.9900000000000003e-05,
23
+ "loss": 2.36,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.04025224741714746,
28
+ "grad_norm": 3.640625,
29
+ "learning_rate": 1.972700951330484e-05,
30
+ "loss": 2.32,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.053669663222863276,
35
+ "grad_norm": 3.609375,
36
+ "learning_rate": 1.9451261546946092e-05,
37
+ "loss": 2.23,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.06708707902857909,
42
+ "grad_norm": 3.203125,
43
+ "learning_rate": 1.9175513580587345e-05,
44
+ "loss": 2.23,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.08050449483429492,
49
+ "grad_norm": 3.625,
50
+ "learning_rate": 1.8899765614228597e-05,
51
+ "loss": 2.23,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.09392191064001074,
56
+ "grad_norm": 3.53125,
57
+ "learning_rate": 1.8624017647869846e-05,
58
+ "loss": 2.27,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.10733932644572655,
63
+ "grad_norm": 3.515625,
64
+ "learning_rate": 1.83482696815111e-05,
65
+ "loss": 2.21,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.12075674225144237,
70
+ "grad_norm": 3.953125,
71
+ "learning_rate": 1.807252171515235e-05,
72
+ "loss": 2.2,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.13417415805715818,
77
+ "grad_norm": 4.0,
78
+ "learning_rate": 1.7796773748793603e-05,
79
+ "loss": 2.22,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.147591573862874,
84
+ "grad_norm": 3.328125,
85
+ "learning_rate": 1.7521025782434856e-05,
86
+ "loss": 2.21,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.16100898966858984,
91
+ "grad_norm": 3.15625,
92
+ "learning_rate": 1.724527781607611e-05,
93
+ "loss": 2.19,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.17442640547430566,
98
+ "grad_norm": 3.84375,
99
+ "learning_rate": 1.6969529849717357e-05,
100
+ "loss": 2.19,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.18784382128002147,
105
+ "grad_norm": 3.359375,
106
+ "learning_rate": 1.669378188335861e-05,
107
+ "loss": 2.21,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.2012612370857373,
112
+ "grad_norm": 3.15625,
113
+ "learning_rate": 1.6418033916999862e-05,
114
+ "loss": 2.19,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.2146786528914531,
119
+ "grad_norm": 3.3125,
120
+ "learning_rate": 1.6142285950641115e-05,
121
+ "loss": 2.18,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.22809606869716892,
126
+ "grad_norm": 3.390625,
127
+ "learning_rate": 1.5866537984282367e-05,
128
+ "loss": 2.19,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.24151348450288473,
133
+ "grad_norm": 3.515625,
134
+ "learning_rate": 1.559079001792362e-05,
135
+ "loss": 2.19,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 0.25493090030860055,
140
+ "grad_norm": 3.5625,
141
+ "learning_rate": 1.531504205156487e-05,
142
+ "loss": 2.16,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 0.26834831611431637,
147
+ "grad_norm": 3.296875,
148
+ "learning_rate": 1.5039294085206123e-05,
149
+ "loss": 2.18,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 0.2817657319200322,
154
+ "grad_norm": 3.234375,
155
+ "learning_rate": 1.4763546118847373e-05,
156
+ "loss": 2.2,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 0.295183147725748,
161
+ "grad_norm": 3.46875,
162
+ "learning_rate": 1.4487798152488626e-05,
163
+ "loss": 2.16,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 0.30860056353146387,
168
+ "grad_norm": 3.15625,
169
+ "learning_rate": 1.4212050186129878e-05,
170
+ "loss": 2.18,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 0.3220179793371797,
175
+ "grad_norm": 3.15625,
176
+ "learning_rate": 1.3936302219771129e-05,
177
+ "loss": 2.16,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 0.3354353951428955,
182
+ "grad_norm": 3.53125,
183
+ "learning_rate": 1.3660554253412381e-05,
184
+ "loss": 2.16,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 0.3488528109486113,
189
+ "grad_norm": 3.359375,
190
+ "learning_rate": 1.3384806287053634e-05,
191
+ "loss": 2.18,
192
+ "step": 2600
193
+ },
194
+ {
195
+ "epoch": 0.36227022675432713,
196
+ "grad_norm": 3.359375,
197
+ "learning_rate": 1.3109058320694885e-05,
198
+ "loss": 2.19,
199
+ "step": 2700
200
+ },
201
+ {
202
+ "epoch": 0.37568764256004294,
203
+ "grad_norm": 3.578125,
204
+ "learning_rate": 1.2833310354336137e-05,
205
+ "loss": 2.19,
206
+ "step": 2800
207
+ },
208
+ {
209
+ "epoch": 0.38910505836575876,
210
+ "grad_norm": 3.328125,
211
+ "learning_rate": 1.255756238797739e-05,
212
+ "loss": 2.18,
213
+ "step": 2900
214
+ },
215
+ {
216
+ "epoch": 0.4025224741714746,
217
+ "grad_norm": 3.359375,
218
+ "learning_rate": 1.228181442161864e-05,
219
+ "loss": 2.17,
220
+ "step": 3000
221
+ },
222
+ {
223
+ "epoch": 0.4159398899771904,
224
+ "grad_norm": 3.421875,
225
+ "learning_rate": 1.2006066455259893e-05,
226
+ "loss": 2.21,
227
+ "step": 3100
228
+ },
229
+ {
230
+ "epoch": 0.4293573057829062,
231
+ "grad_norm": 4.0625,
232
+ "learning_rate": 1.1730318488901145e-05,
233
+ "loss": 2.16,
234
+ "step": 3200
235
+ },
236
+ {
237
+ "epoch": 0.442774721588622,
238
+ "grad_norm": 3.546875,
239
+ "learning_rate": 1.1454570522542396e-05,
240
+ "loss": 2.19,
241
+ "step": 3300
242
+ },
243
+ {
244
+ "epoch": 0.45619213739433784,
245
+ "grad_norm": 3.03125,
246
+ "learning_rate": 1.1178822556183648e-05,
247
+ "loss": 2.21,
248
+ "step": 3400
249
+ },
250
+ {
251
+ "epoch": 0.46960955320005365,
252
+ "grad_norm": 3.875,
253
+ "learning_rate": 1.09030745898249e-05,
254
+ "loss": 2.19,
255
+ "step": 3500
256
+ },
257
+ {
258
+ "epoch": 0.48302696900576947,
259
+ "grad_norm": 3.203125,
260
+ "learning_rate": 1.0627326623466151e-05,
261
+ "loss": 2.18,
262
+ "step": 3600
263
+ },
264
+ {
265
+ "epoch": 0.4964443848114853,
266
+ "grad_norm": 3.46875,
267
+ "learning_rate": 1.0351578657107404e-05,
268
+ "loss": 2.21,
269
+ "step": 3700
270
+ },
271
+ {
272
+ "epoch": 0.5098618006172011,
273
+ "grad_norm": 3.875,
274
+ "learning_rate": 1.0075830690748656e-05,
275
+ "loss": 2.21,
276
+ "step": 3800
277
+ },
278
+ {
279
+ "epoch": 0.523279216422917,
280
+ "grad_norm": 3.453125,
281
+ "learning_rate": 9.800082724389909e-06,
282
+ "loss": 2.19,
283
+ "step": 3900
284
+ },
285
+ {
286
+ "epoch": 0.5366966322286327,
287
+ "grad_norm": 3.625,
288
+ "learning_rate": 9.524334758031161e-06,
289
+ "loss": 2.17,
290
+ "step": 4000
291
+ },
292
+ {
293
+ "epoch": 0.5501140480343486,
294
+ "grad_norm": 3.359375,
295
+ "learning_rate": 9.248586791672412e-06,
296
+ "loss": 2.19,
297
+ "step": 4100
298
+ },
299
+ {
300
+ "epoch": 0.5635314638400644,
301
+ "grad_norm": 3.265625,
302
+ "learning_rate": 8.972838825313664e-06,
303
+ "loss": 2.15,
304
+ "step": 4200
305
+ },
306
+ {
307
+ "epoch": 0.5769488796457802,
308
+ "grad_norm": 3.15625,
309
+ "learning_rate": 8.697090858954917e-06,
310
+ "loss": 2.19,
311
+ "step": 4300
312
+ },
313
+ {
314
+ "epoch": 0.590366295451496,
315
+ "grad_norm": 3.875,
316
+ "learning_rate": 8.421342892596168e-06,
317
+ "loss": 2.2,
318
+ "step": 4400
319
+ },
320
+ {
321
+ "epoch": 0.6037837112572119,
322
+ "grad_norm": 3.21875,
323
+ "learning_rate": 8.14559492623742e-06,
324
+ "loss": 2.17,
325
+ "step": 4500
326
+ },
327
+ {
328
+ "epoch": 0.6172011270629277,
329
+ "grad_norm": 3.484375,
330
+ "learning_rate": 7.869846959878672e-06,
331
+ "loss": 2.16,
332
+ "step": 4600
333
+ },
334
+ {
335
+ "epoch": 0.6306185428686435,
336
+ "grad_norm": 3.75,
337
+ "learning_rate": 7.594098993519924e-06,
338
+ "loss": 2.16,
339
+ "step": 4700
340
+ },
341
+ {
342
+ "epoch": 0.6440359586743594,
343
+ "grad_norm": 3.890625,
344
+ "learning_rate": 7.3183510271611756e-06,
345
+ "loss": 2.2,
346
+ "step": 4800
347
+ },
348
+ {
349
+ "epoch": 0.6574533744800751,
350
+ "grad_norm": 3.9375,
351
+ "learning_rate": 7.042603060802428e-06,
352
+ "loss": 2.19,
353
+ "step": 4900
354
+ },
355
+ {
356
+ "epoch": 0.670870790285791,
357
+ "grad_norm": 3.9375,
358
+ "learning_rate": 6.7668550944436796e-06,
359
+ "loss": 2.2,
360
+ "step": 5000
361
+ },
362
+ {
363
+ "epoch": 0.6842882060915068,
364
+ "grad_norm": 3.453125,
365
+ "learning_rate": 6.491107128084931e-06,
366
+ "loss": 2.18,
367
+ "step": 5100
368
+ },
369
+ {
370
+ "epoch": 0.6977056218972226,
371
+ "grad_norm": 3.53125,
372
+ "learning_rate": 6.215359161726184e-06,
373
+ "loss": 2.19,
374
+ "step": 5200
375
+ },
376
+ {
377
+ "epoch": 0.7111230377029384,
378
+ "grad_norm": 3.734375,
379
+ "learning_rate": 5.939611195367435e-06,
380
+ "loss": 2.2,
381
+ "step": 5300
382
+ },
383
+ {
384
+ "epoch": 0.7245404535086543,
385
+ "grad_norm": 3.265625,
386
+ "learning_rate": 5.663863229008687e-06,
387
+ "loss": 2.19,
388
+ "step": 5400
389
+ },
390
+ {
391
+ "epoch": 0.73795786931437,
392
+ "grad_norm": 3.109375,
393
+ "learning_rate": 5.388115262649939e-06,
394
+ "loss": 2.2,
395
+ "step": 5500
396
+ },
397
+ {
398
+ "epoch": 0.7513752851200859,
399
+ "grad_norm": 3.859375,
400
+ "learning_rate": 5.112367296291191e-06,
401
+ "loss": 2.16,
402
+ "step": 5600
403
+ },
404
+ {
405
+ "epoch": 0.7647927009258016,
406
+ "grad_norm": 3.59375,
407
+ "learning_rate": 4.836619329932442e-06,
408
+ "loss": 2.16,
409
+ "step": 5700
410
+ },
411
+ {
412
+ "epoch": 0.7782101167315175,
413
+ "grad_norm": 3.578125,
414
+ "learning_rate": 4.560871363573694e-06,
415
+ "loss": 2.2,
416
+ "step": 5800
417
+ },
418
+ {
419
+ "epoch": 0.7916275325372333,
420
+ "grad_norm": 3.40625,
421
+ "learning_rate": 4.2851233972149455e-06,
422
+ "loss": 2.18,
423
+ "step": 5900
424
+ },
425
+ {
426
+ "epoch": 0.8050449483429492,
427
+ "grad_norm": 3.546875,
428
+ "learning_rate": 4.009375430856198e-06,
429
+ "loss": 2.17,
430
+ "step": 6000
431
+ },
432
+ {
433
+ "epoch": 0.818462364148665,
434
+ "grad_norm": 3.421875,
435
+ "learning_rate": 3.7336274644974496e-06,
436
+ "loss": 2.19,
437
+ "step": 6100
438
+ },
439
+ {
440
+ "epoch": 0.8318797799543808,
441
+ "grad_norm": 3.203125,
442
+ "learning_rate": 3.4578794981387016e-06,
443
+ "loss": 2.16,
444
+ "step": 6200
445
+ },
446
+ {
447
+ "epoch": 0.8452971957600967,
448
+ "grad_norm": 3.75,
449
+ "learning_rate": 3.1821315317799536e-06,
450
+ "loss": 2.2,
451
+ "step": 6300
452
+ },
453
+ {
454
+ "epoch": 0.8587146115658124,
455
+ "grad_norm": 3.0,
456
+ "learning_rate": 2.906383565421205e-06,
457
+ "loss": 2.18,
458
+ "step": 6400
459
+ },
460
+ {
461
+ "epoch": 0.8721320273715283,
462
+ "grad_norm": 3.484375,
463
+ "learning_rate": 2.630635599062457e-06,
464
+ "loss": 2.18,
465
+ "step": 6500
466
+ },
467
+ {
468
+ "epoch": 0.885549443177244,
469
+ "grad_norm": 3.5,
470
+ "learning_rate": 2.354887632703709e-06,
471
+ "loss": 2.17,
472
+ "step": 6600
473
+ },
474
+ {
475
+ "epoch": 0.8989668589829599,
476
+ "grad_norm": 3.578125,
477
+ "learning_rate": 2.0791396663449608e-06,
478
+ "loss": 2.19,
479
+ "step": 6700
480
+ },
481
+ {
482
+ "epoch": 0.9123842747886757,
483
+ "grad_norm": 3.359375,
484
+ "learning_rate": 1.8033916999862128e-06,
485
+ "loss": 2.17,
486
+ "step": 6800
487
+ },
488
+ {
489
+ "epoch": 0.9258016905943915,
490
+ "grad_norm": 3.0625,
491
+ "learning_rate": 1.5276437336274646e-06,
492
+ "loss": 2.18,
493
+ "step": 6900
494
+ },
495
+ {
496
+ "epoch": 0.9392191064001073,
497
+ "grad_norm": 3.359375,
498
+ "learning_rate": 1.2518957672687166e-06,
499
+ "loss": 2.19,
500
+ "step": 7000
501
+ },
502
+ {
503
+ "epoch": 0.9526365222058232,
504
+ "grad_norm": 3.53125,
505
+ "learning_rate": 9.761478009099684e-07,
506
+ "loss": 2.19,
507
+ "step": 7100
508
+ },
509
+ {
510
+ "epoch": 0.9660539380115389,
511
+ "grad_norm": 3.265625,
512
+ "learning_rate": 7.003998345512203e-07,
513
+ "loss": 2.17,
514
+ "step": 7200
515
+ },
516
+ {
517
+ "epoch": 0.9794713538172548,
518
+ "grad_norm": 3.171875,
519
+ "learning_rate": 4.246518681924721e-07,
520
+ "loss": 2.19,
521
+ "step": 7300
522
+ },
523
+ {
524
+ "epoch": 0.9928887696229706,
525
+ "grad_norm": 3.40625,
526
+ "learning_rate": 1.4890390183372397e-07,
527
+ "loss": 2.19,
528
+ "step": 7400
529
+ }
530
+ ],
531
+ "logging_steps": 100,
532
+ "max_steps": 7453,
533
+ "num_input_tokens_seen": 0,
534
+ "num_train_epochs": 1,
535
+ "save_steps": 500,
536
+ "stateful_callbacks": {
537
+ "TrainerControl": {
538
+ "args": {
539
+ "should_epoch_stop": false,
540
+ "should_evaluate": false,
541
+ "should_log": false,
542
+ "should_save": true,
543
+ "should_training_stop": true
544
+ },
545
+ "attributes": {}
546
+ }
547
+ },
548
+ "total_flos": 3.1158029647872e+16,
549
+ "train_batch_size": 4,
550
+ "trial_name": null,
551
+ "trial_params": null
552
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b17321dea255bd301b0108e21be5a56aeb701ebfaa97b04d9c34923c5f5dbd4
3
+ size 5777
vocab.json ADDED
The diff for this file is too large to render. See raw diff