harishussain12 commited on
Commit
bda6b41
·
verified ·
1 Parent(s): 5e39d74

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
checkpoint-4500/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
checkpoint-4500/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
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
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.47.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
checkpoint-4500/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": "4.47.1"
6
+ }
checkpoint-4500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bff52b2e4bf6eb78be24adfb6b11942ee87a594797359eab68279f0d568d2a9
3
+ size 497777280
checkpoint-4500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e07b3fac33f8615191c0ce1fa15d55680b0695f6b177ac84be5038a9f27dde
3
+ size 995648442
checkpoint-4500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8842bafcd0f58fe060e8066d731d889bd420e5ce46583d4f08117f350b4888d
3
+ size 14244
checkpoint-4500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50bc0d2ae4a3d270d0c6333137e1a6493b1efb235226ac0f1f0d6bb2c6497556
3
+ size 1064
checkpoint-4500/special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "unk_token": "<|endoftext|>"
12
+ }
checkpoint-4500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4500/tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
21
+ "bos_token": "<|endoftext|>",
22
+ "clean_up_tokenization_spaces": false,
23
+ "eos_token": "<|endoftext|>",
24
+ "extra_special_tokens": {},
25
+ "model_max_length": 1024,
26
+ "pad_token": "[PAD]",
27
+ "tokenizer_class": "GPT2Tokenizer",
28
+ "unk_token": "<|endoftext|>"
29
+ }
checkpoint-4500/trainer_state.json ADDED
@@ -0,0 +1,663 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.853519340519975,
5
+ "eval_steps": 500,
6
+ "global_step": 4500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03170577045022194,
13
+ "grad_norm": 347.7311096191406,
14
+ "learning_rate": 4.94715704924963e-05,
15
+ "loss": 8.5747,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.06341154090044387,
20
+ "grad_norm": 216.6991424560547,
21
+ "learning_rate": 4.8943140984992603e-05,
22
+ "loss": 3.9346,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.09511731135066583,
27
+ "grad_norm": 1.8576736450195312,
28
+ "learning_rate": 4.8414711477488904e-05,
29
+ "loss": 0.7161,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.12682308180088775,
34
+ "grad_norm": 1.3204137086868286,
35
+ "learning_rate": 4.788628196998521e-05,
36
+ "loss": 0.6464,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.15852885225110971,
41
+ "grad_norm": 1.0963375568389893,
42
+ "learning_rate": 4.7357852462481505e-05,
43
+ "loss": 0.5442,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.19023462270133165,
48
+ "grad_norm": 1.6606075763702393,
49
+ "learning_rate": 4.6829422954977806e-05,
50
+ "loss": 0.6393,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.2219403931515536,
55
+ "grad_norm": 0.8779278993606567,
56
+ "learning_rate": 4.630099344747411e-05,
57
+ "loss": 0.689,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.2536461636017755,
62
+ "grad_norm": 0.6462757587432861,
63
+ "learning_rate": 4.577256393997041e-05,
64
+ "loss": 0.5693,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.2853519340519975,
69
+ "grad_norm": 0.670758843421936,
70
+ "learning_rate": 4.5244134432466714e-05,
71
+ "loss": 0.4993,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.31705770450221943,
76
+ "grad_norm": 0.7589445114135742,
77
+ "learning_rate": 4.4715704924963015e-05,
78
+ "loss": 0.6332,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.34876347495244137,
83
+ "grad_norm": 0.7136730551719666,
84
+ "learning_rate": 4.4187275417459315e-05,
85
+ "loss": 0.5269,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.3804692454026633,
90
+ "grad_norm": 0.9714166522026062,
91
+ "learning_rate": 4.3658845909955616e-05,
92
+ "loss": 0.5706,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.41217501585288524,
97
+ "grad_norm": 0.7672790884971619,
98
+ "learning_rate": 4.3130416402451916e-05,
99
+ "loss": 0.5689,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.4438807863031072,
104
+ "grad_norm": 1.4292829036712646,
105
+ "learning_rate": 4.260198689494822e-05,
106
+ "loss": 0.6206,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.4755865567533291,
111
+ "grad_norm": 0.8618677258491516,
112
+ "learning_rate": 4.207355738744452e-05,
113
+ "loss": 0.5413,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.507292327203551,
118
+ "grad_norm": 0.9496092796325684,
119
+ "learning_rate": 4.154512787994082e-05,
120
+ "loss": 0.5418,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.5389980976537729,
125
+ "grad_norm": 0.8666266202926636,
126
+ "learning_rate": 4.101669837243712e-05,
127
+ "loss": 0.597,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.570703868103995,
132
+ "grad_norm": 1.0330841541290283,
133
+ "learning_rate": 4.048826886493342e-05,
134
+ "loss": 0.5309,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.6024096385542169,
139
+ "grad_norm": 0.6087735295295715,
140
+ "learning_rate": 3.995983935742972e-05,
141
+ "loss": 0.5225,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.6341154090044389,
146
+ "grad_norm": 0.9573830962181091,
147
+ "learning_rate": 3.943140984992602e-05,
148
+ "loss": 0.5227,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.6658211794546608,
153
+ "grad_norm": 0.6024531126022339,
154
+ "learning_rate": 3.890298034242232e-05,
155
+ "loss": 0.4838,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.6975269499048827,
160
+ "grad_norm": 0.5939881801605225,
161
+ "learning_rate": 3.837455083491862e-05,
162
+ "loss": 0.541,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.7292327203551047,
167
+ "grad_norm": 0.6684996485710144,
168
+ "learning_rate": 3.784612132741492e-05,
169
+ "loss": 0.5198,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.7609384908053266,
174
+ "grad_norm": 1.1875889301300049,
175
+ "learning_rate": 3.731769181991123e-05,
176
+ "loss": 0.6105,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.7926442612555485,
181
+ "grad_norm": 0.570648729801178,
182
+ "learning_rate": 3.678926231240752e-05,
183
+ "loss": 0.5735,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.8243500317057705,
188
+ "grad_norm": 0.6439939141273499,
189
+ "learning_rate": 3.626083280490383e-05,
190
+ "loss": 0.5283,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.8560558021559924,
195
+ "grad_norm": 0.6673012375831604,
196
+ "learning_rate": 3.573240329740013e-05,
197
+ "loss": 0.6057,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.8877615726062144,
202
+ "grad_norm": 0.4656541645526886,
203
+ "learning_rate": 3.5203973789896424e-05,
204
+ "loss": 0.4664,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.9194673430564363,
209
+ "grad_norm": 1.075217366218567,
210
+ "learning_rate": 3.467554428239273e-05,
211
+ "loss": 0.5336,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.9511731135066582,
216
+ "grad_norm": 1.2251460552215576,
217
+ "learning_rate": 3.414711477488903e-05,
218
+ "loss": 0.5354,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.9828788839568802,
223
+ "grad_norm": 0.822003185749054,
224
+ "learning_rate": 3.361868526738533e-05,
225
+ "loss": 0.6133,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 1.014584654407102,
230
+ "grad_norm": 0.5614562630653381,
231
+ "learning_rate": 3.309025575988163e-05,
232
+ "loss": 0.5059,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 1.046290424857324,
237
+ "grad_norm": 0.5171016454696655,
238
+ "learning_rate": 3.2561826252377934e-05,
239
+ "loss": 0.5285,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 1.0779961953075459,
244
+ "grad_norm": 0.9495669007301331,
245
+ "learning_rate": 3.2033396744874234e-05,
246
+ "loss": 0.4955,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 1.1097019657577678,
251
+ "grad_norm": 0.9576842784881592,
252
+ "learning_rate": 3.1504967237370535e-05,
253
+ "loss": 0.5107,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 1.1414077362079897,
258
+ "grad_norm": 0.6107915639877319,
259
+ "learning_rate": 3.097653772986684e-05,
260
+ "loss": 0.519,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 1.1731135066582117,
265
+ "grad_norm": 0.5931509137153625,
266
+ "learning_rate": 3.0448108222363136e-05,
267
+ "loss": 0.5699,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 1.2048192771084336,
272
+ "grad_norm": 0.6647824048995972,
273
+ "learning_rate": 2.991967871485944e-05,
274
+ "loss": 0.5022,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 1.2365250475586556,
279
+ "grad_norm": 0.5938781499862671,
280
+ "learning_rate": 2.939124920735574e-05,
281
+ "loss": 0.4507,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 1.2682308180088775,
286
+ "grad_norm": 1.1466686725616455,
287
+ "learning_rate": 2.886281969985204e-05,
288
+ "loss": 0.6235,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 1.2999365884590994,
293
+ "grad_norm": 0.4420027434825897,
294
+ "learning_rate": 2.833439019234834e-05,
295
+ "loss": 0.6154,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 1.3316423589093214,
300
+ "grad_norm": 0.746532142162323,
301
+ "learning_rate": 2.7805960684844646e-05,
302
+ "loss": 0.4898,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 1.3633481293595433,
307
+ "grad_norm": 1.0959316492080688,
308
+ "learning_rate": 2.7277531177340943e-05,
309
+ "loss": 0.4544,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 1.3950538998097652,
314
+ "grad_norm": 0.8176191449165344,
315
+ "learning_rate": 2.6749101669837247e-05,
316
+ "loss": 0.481,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 1.4267596702599874,
321
+ "grad_norm": 0.8100579380989075,
322
+ "learning_rate": 2.6220672162333547e-05,
323
+ "loss": 0.4333,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 1.4584654407102093,
328
+ "grad_norm": 0.8650724291801453,
329
+ "learning_rate": 2.5692242654829844e-05,
330
+ "loss": 0.4629,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 1.4901712111604313,
335
+ "grad_norm": 1.6807165145874023,
336
+ "learning_rate": 2.5163813147326148e-05,
337
+ "loss": 0.4126,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 1.521876981610653,
342
+ "grad_norm": 0.6398534774780273,
343
+ "learning_rate": 2.463538363982245e-05,
344
+ "loss": 0.4776,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 1.553582752060875,
349
+ "grad_norm": 0.7640373110771179,
350
+ "learning_rate": 2.410695413231875e-05,
351
+ "loss": 0.4901,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 1.5852885225110969,
356
+ "grad_norm": 0.644173800945282,
357
+ "learning_rate": 2.357852462481505e-05,
358
+ "loss": 0.5133,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 1.6169942929613188,
363
+ "grad_norm": 0.577743649482727,
364
+ "learning_rate": 2.305009511731135e-05,
365
+ "loss": 0.4221,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 1.6487000634115407,
370
+ "grad_norm": 0.6014630198478699,
371
+ "learning_rate": 2.252166560980765e-05,
372
+ "loss": 0.4766,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 1.6804058338617627,
377
+ "grad_norm": 0.6592232584953308,
378
+ "learning_rate": 2.1993236102303955e-05,
379
+ "loss": 0.5726,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 1.7121116043119848,
384
+ "grad_norm": 0.7719835042953491,
385
+ "learning_rate": 2.1464806594800255e-05,
386
+ "loss": 0.4941,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 1.7438173747622068,
391
+ "grad_norm": 0.9424024224281311,
392
+ "learning_rate": 2.0936377087296556e-05,
393
+ "loss": 0.5236,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 1.7755231452124287,
398
+ "grad_norm": 1.0417604446411133,
399
+ "learning_rate": 2.0407947579792857e-05,
400
+ "loss": 0.5269,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 1.8072289156626506,
405
+ "grad_norm": 0.42674678564071655,
406
+ "learning_rate": 1.9879518072289157e-05,
407
+ "loss": 0.5067,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 1.8389346861128726,
412
+ "grad_norm": 0.6428393721580505,
413
+ "learning_rate": 1.9351088564785458e-05,
414
+ "loss": 0.4381,
415
+ "step": 2900
416
+ },
417
+ {
418
+ "epoch": 1.8706404565630945,
419
+ "grad_norm": 0.936777651309967,
420
+ "learning_rate": 1.882265905728176e-05,
421
+ "loss": 0.6561,
422
+ "step": 2950
423
+ },
424
+ {
425
+ "epoch": 1.9023462270133165,
426
+ "grad_norm": 1.3489336967468262,
427
+ "learning_rate": 1.8294229549778062e-05,
428
+ "loss": 0.4983,
429
+ "step": 3000
430
+ },
431
+ {
432
+ "epoch": 1.9340519974635384,
433
+ "grad_norm": 0.6496655344963074,
434
+ "learning_rate": 1.776580004227436e-05,
435
+ "loss": 0.4759,
436
+ "step": 3050
437
+ },
438
+ {
439
+ "epoch": 1.9657577679137603,
440
+ "grad_norm": 0.712348997592926,
441
+ "learning_rate": 1.7237370534770663e-05,
442
+ "loss": 0.4621,
443
+ "step": 3100
444
+ },
445
+ {
446
+ "epoch": 1.9974635383639823,
447
+ "grad_norm": 0.5334410667419434,
448
+ "learning_rate": 1.6708941027266964e-05,
449
+ "loss": 0.5246,
450
+ "step": 3150
451
+ },
452
+ {
453
+ "epoch": 2.029169308814204,
454
+ "grad_norm": 0.9799864888191223,
455
+ "learning_rate": 1.6180511519763264e-05,
456
+ "loss": 0.388,
457
+ "step": 3200
458
+ },
459
+ {
460
+ "epoch": 2.060875079264426,
461
+ "grad_norm": 0.6191227436065674,
462
+ "learning_rate": 1.5652082012259565e-05,
463
+ "loss": 0.422,
464
+ "step": 3250
465
+ },
466
+ {
467
+ "epoch": 2.092580849714648,
468
+ "grad_norm": 0.6415786743164062,
469
+ "learning_rate": 1.5123652504755867e-05,
470
+ "loss": 0.4213,
471
+ "step": 3300
472
+ },
473
+ {
474
+ "epoch": 2.12428662016487,
475
+ "grad_norm": 1.024706244468689,
476
+ "learning_rate": 1.4595222997252168e-05,
477
+ "loss": 0.4378,
478
+ "step": 3350
479
+ },
480
+ {
481
+ "epoch": 2.1559923906150917,
482
+ "grad_norm": 1.0147749185562134,
483
+ "learning_rate": 1.4066793489748466e-05,
484
+ "loss": 0.5441,
485
+ "step": 3400
486
+ },
487
+ {
488
+ "epoch": 2.187698161065314,
489
+ "grad_norm": 1.1020487546920776,
490
+ "learning_rate": 1.353836398224477e-05,
491
+ "loss": 0.554,
492
+ "step": 3450
493
+ },
494
+ {
495
+ "epoch": 2.2194039315155356,
496
+ "grad_norm": 0.7216790318489075,
497
+ "learning_rate": 1.3009934474741071e-05,
498
+ "loss": 0.4983,
499
+ "step": 3500
500
+ },
501
+ {
502
+ "epoch": 2.251109701965758,
503
+ "grad_norm": 1.2225050926208496,
504
+ "learning_rate": 1.2481504967237371e-05,
505
+ "loss": 0.4586,
506
+ "step": 3550
507
+ },
508
+ {
509
+ "epoch": 2.2828154724159795,
510
+ "grad_norm": 0.7050449252128601,
511
+ "learning_rate": 1.1953075459733672e-05,
512
+ "loss": 0.4235,
513
+ "step": 3600
514
+ },
515
+ {
516
+ "epoch": 2.314521242866202,
517
+ "grad_norm": 0.6529106497764587,
518
+ "learning_rate": 1.1424645952229973e-05,
519
+ "loss": 0.5061,
520
+ "step": 3650
521
+ },
522
+ {
523
+ "epoch": 2.3462270133164234,
524
+ "grad_norm": 0.5396713018417358,
525
+ "learning_rate": 1.0896216444726275e-05,
526
+ "loss": 0.4983,
527
+ "step": 3700
528
+ },
529
+ {
530
+ "epoch": 2.3779327837666457,
531
+ "grad_norm": 0.6897116899490356,
532
+ "learning_rate": 1.0367786937222575e-05,
533
+ "loss": 0.4658,
534
+ "step": 3750
535
+ },
536
+ {
537
+ "epoch": 2.4096385542168672,
538
+ "grad_norm": 1.0474814176559448,
539
+ "learning_rate": 9.839357429718876e-06,
540
+ "loss": 0.4578,
541
+ "step": 3800
542
+ },
543
+ {
544
+ "epoch": 2.4413443246670896,
545
+ "grad_norm": 0.5905832648277283,
546
+ "learning_rate": 9.310927922215176e-06,
547
+ "loss": 0.4349,
548
+ "step": 3850
549
+ },
550
+ {
551
+ "epoch": 2.473050095117311,
552
+ "grad_norm": 0.6709778904914856,
553
+ "learning_rate": 8.782498414711479e-06,
554
+ "loss": 0.4351,
555
+ "step": 3900
556
+ },
557
+ {
558
+ "epoch": 2.5047558655675335,
559
+ "grad_norm": 0.5383151173591614,
560
+ "learning_rate": 8.254068907207779e-06,
561
+ "loss": 0.52,
562
+ "step": 3950
563
+ },
564
+ {
565
+ "epoch": 2.536461636017755,
566
+ "grad_norm": 0.9183222055435181,
567
+ "learning_rate": 7.72563939970408e-06,
568
+ "loss": 0.5099,
569
+ "step": 4000
570
+ },
571
+ {
572
+ "epoch": 2.5681674064679774,
573
+ "grad_norm": 1.0442452430725098,
574
+ "learning_rate": 7.197209892200381e-06,
575
+ "loss": 0.561,
576
+ "step": 4050
577
+ },
578
+ {
579
+ "epoch": 2.599873176918199,
580
+ "grad_norm": 0.4895930886268616,
581
+ "learning_rate": 6.6687803846966825e-06,
582
+ "loss": 0.4435,
583
+ "step": 4100
584
+ },
585
+ {
586
+ "epoch": 2.6315789473684212,
587
+ "grad_norm": 0.6229114532470703,
588
+ "learning_rate": 6.140350877192982e-06,
589
+ "loss": 0.5262,
590
+ "step": 4150
591
+ },
592
+ {
593
+ "epoch": 2.6632847178186427,
594
+ "grad_norm": 0.647319495677948,
595
+ "learning_rate": 5.6119213696892836e-06,
596
+ "loss": 0.5116,
597
+ "step": 4200
598
+ },
599
+ {
600
+ "epoch": 2.694990488268865,
601
+ "grad_norm": 0.6666443347930908,
602
+ "learning_rate": 5.083491862185585e-06,
603
+ "loss": 0.5408,
604
+ "step": 4250
605
+ },
606
+ {
607
+ "epoch": 2.7266962587190866,
608
+ "grad_norm": 0.6282554268836975,
609
+ "learning_rate": 4.5550623546818855e-06,
610
+ "loss": 0.4801,
611
+ "step": 4300
612
+ },
613
+ {
614
+ "epoch": 2.758402029169309,
615
+ "grad_norm": 1.0603163242340088,
616
+ "learning_rate": 4.026632847178187e-06,
617
+ "loss": 0.4662,
618
+ "step": 4350
619
+ },
620
+ {
621
+ "epoch": 2.7901077996195305,
622
+ "grad_norm": 0.7217985391616821,
623
+ "learning_rate": 3.498203339674488e-06,
624
+ "loss": 0.3947,
625
+ "step": 4400
626
+ },
627
+ {
628
+ "epoch": 2.821813570069753,
629
+ "grad_norm": 0.49021148681640625,
630
+ "learning_rate": 2.9697738321707884e-06,
631
+ "loss": 0.4047,
632
+ "step": 4450
633
+ },
634
+ {
635
+ "epoch": 2.853519340519975,
636
+ "grad_norm": 0.9363583922386169,
637
+ "learning_rate": 2.4413443246670898e-06,
638
+ "loss": 0.4912,
639
+ "step": 4500
640
+ }
641
+ ],
642
+ "logging_steps": 50,
643
+ "max_steps": 4731,
644
+ "num_input_tokens_seen": 0,
645
+ "num_train_epochs": 3,
646
+ "save_steps": 500,
647
+ "stateful_callbacks": {
648
+ "TrainerControl": {
649
+ "args": {
650
+ "should_epoch_stop": false,
651
+ "should_evaluate": false,
652
+ "should_log": false,
653
+ "should_save": true,
654
+ "should_training_stop": false
655
+ },
656
+ "attributes": {}
657
+ }
658
+ },
659
+ "total_flos": 4702733991936000.0,
660
+ "train_batch_size": 4,
661
+ "trial_name": null,
662
+ "trial_params": null
663
+ }
checkpoint-4500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb0e89a06ff97c1285b62a811e8f19adb4ec8af9e57e1f4d37318e75c96a595
3
+ size 5240
checkpoint-4500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4731/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
checkpoint-4731/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
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
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.47.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
checkpoint-4731/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": "4.47.1"
6
+ }
checkpoint-4731/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4731/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37559e513798a6342763dbdbdc163d73b0f10356d16ec4f9a576a4d9a8d749a7
3
+ size 497777280
checkpoint-4731/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fb3a77a7cd60ae8145ae46b7a97685365b560d3b09bc6c789f987bee4ab6bd
3
+ size 995648442
checkpoint-4731/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:595362ae8a8a641ef2e89371369922e000f2b4fd661048415cdd3824559f4edd
3
+ size 14244
checkpoint-4731/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb1e5f56db38b8325e7dbc1394998aa9fa153404486cb734ca0ad4044f0c0899
3
+ size 1064
checkpoint-4731/special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "unk_token": "<|endoftext|>"
12
+ }
checkpoint-4731/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4731/tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
21
+ "bos_token": "<|endoftext|>",
22
+ "clean_up_tokenization_spaces": false,
23
+ "eos_token": "<|endoftext|>",
24
+ "extra_special_tokens": {},
25
+ "model_max_length": 1024,
26
+ "pad_token": "[PAD]",
27
+ "tokenizer_class": "GPT2Tokenizer",
28
+ "unk_token": "<|endoftext|>"
29
+ }
checkpoint-4731/trainer_state.json ADDED
@@ -0,0 +1,691 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4731,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03170577045022194,
13
+ "grad_norm": 347.7311096191406,
14
+ "learning_rate": 4.94715704924963e-05,
15
+ "loss": 8.5747,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.06341154090044387,
20
+ "grad_norm": 216.6991424560547,
21
+ "learning_rate": 4.8943140984992603e-05,
22
+ "loss": 3.9346,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.09511731135066583,
27
+ "grad_norm": 1.8576736450195312,
28
+ "learning_rate": 4.8414711477488904e-05,
29
+ "loss": 0.7161,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.12682308180088775,
34
+ "grad_norm": 1.3204137086868286,
35
+ "learning_rate": 4.788628196998521e-05,
36
+ "loss": 0.6464,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.15852885225110971,
41
+ "grad_norm": 1.0963375568389893,
42
+ "learning_rate": 4.7357852462481505e-05,
43
+ "loss": 0.5442,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.19023462270133165,
48
+ "grad_norm": 1.6606075763702393,
49
+ "learning_rate": 4.6829422954977806e-05,
50
+ "loss": 0.6393,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.2219403931515536,
55
+ "grad_norm": 0.8779278993606567,
56
+ "learning_rate": 4.630099344747411e-05,
57
+ "loss": 0.689,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.2536461636017755,
62
+ "grad_norm": 0.6462757587432861,
63
+ "learning_rate": 4.577256393997041e-05,
64
+ "loss": 0.5693,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.2853519340519975,
69
+ "grad_norm": 0.670758843421936,
70
+ "learning_rate": 4.5244134432466714e-05,
71
+ "loss": 0.4993,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.31705770450221943,
76
+ "grad_norm": 0.7589445114135742,
77
+ "learning_rate": 4.4715704924963015e-05,
78
+ "loss": 0.6332,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.34876347495244137,
83
+ "grad_norm": 0.7136730551719666,
84
+ "learning_rate": 4.4187275417459315e-05,
85
+ "loss": 0.5269,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.3804692454026633,
90
+ "grad_norm": 0.9714166522026062,
91
+ "learning_rate": 4.3658845909955616e-05,
92
+ "loss": 0.5706,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.41217501585288524,
97
+ "grad_norm": 0.7672790884971619,
98
+ "learning_rate": 4.3130416402451916e-05,
99
+ "loss": 0.5689,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.4438807863031072,
104
+ "grad_norm": 1.4292829036712646,
105
+ "learning_rate": 4.260198689494822e-05,
106
+ "loss": 0.6206,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.4755865567533291,
111
+ "grad_norm": 0.8618677258491516,
112
+ "learning_rate": 4.207355738744452e-05,
113
+ "loss": 0.5413,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.507292327203551,
118
+ "grad_norm": 0.9496092796325684,
119
+ "learning_rate": 4.154512787994082e-05,
120
+ "loss": 0.5418,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.5389980976537729,
125
+ "grad_norm": 0.8666266202926636,
126
+ "learning_rate": 4.101669837243712e-05,
127
+ "loss": 0.597,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.570703868103995,
132
+ "grad_norm": 1.0330841541290283,
133
+ "learning_rate": 4.048826886493342e-05,
134
+ "loss": 0.5309,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.6024096385542169,
139
+ "grad_norm": 0.6087735295295715,
140
+ "learning_rate": 3.995983935742972e-05,
141
+ "loss": 0.5225,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.6341154090044389,
146
+ "grad_norm": 0.9573830962181091,
147
+ "learning_rate": 3.943140984992602e-05,
148
+ "loss": 0.5227,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.6658211794546608,
153
+ "grad_norm": 0.6024531126022339,
154
+ "learning_rate": 3.890298034242232e-05,
155
+ "loss": 0.4838,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.6975269499048827,
160
+ "grad_norm": 0.5939881801605225,
161
+ "learning_rate": 3.837455083491862e-05,
162
+ "loss": 0.541,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.7292327203551047,
167
+ "grad_norm": 0.6684996485710144,
168
+ "learning_rate": 3.784612132741492e-05,
169
+ "loss": 0.5198,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.7609384908053266,
174
+ "grad_norm": 1.1875889301300049,
175
+ "learning_rate": 3.731769181991123e-05,
176
+ "loss": 0.6105,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.7926442612555485,
181
+ "grad_norm": 0.570648729801178,
182
+ "learning_rate": 3.678926231240752e-05,
183
+ "loss": 0.5735,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.8243500317057705,
188
+ "grad_norm": 0.6439939141273499,
189
+ "learning_rate": 3.626083280490383e-05,
190
+ "loss": 0.5283,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.8560558021559924,
195
+ "grad_norm": 0.6673012375831604,
196
+ "learning_rate": 3.573240329740013e-05,
197
+ "loss": 0.6057,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.8877615726062144,
202
+ "grad_norm": 0.4656541645526886,
203
+ "learning_rate": 3.5203973789896424e-05,
204
+ "loss": 0.4664,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.9194673430564363,
209
+ "grad_norm": 1.075217366218567,
210
+ "learning_rate": 3.467554428239273e-05,
211
+ "loss": 0.5336,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.9511731135066582,
216
+ "grad_norm": 1.2251460552215576,
217
+ "learning_rate": 3.414711477488903e-05,
218
+ "loss": 0.5354,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.9828788839568802,
223
+ "grad_norm": 0.822003185749054,
224
+ "learning_rate": 3.361868526738533e-05,
225
+ "loss": 0.6133,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 1.014584654407102,
230
+ "grad_norm": 0.5614562630653381,
231
+ "learning_rate": 3.309025575988163e-05,
232
+ "loss": 0.5059,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 1.046290424857324,
237
+ "grad_norm": 0.5171016454696655,
238
+ "learning_rate": 3.2561826252377934e-05,
239
+ "loss": 0.5285,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 1.0779961953075459,
244
+ "grad_norm": 0.9495669007301331,
245
+ "learning_rate": 3.2033396744874234e-05,
246
+ "loss": 0.4955,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 1.1097019657577678,
251
+ "grad_norm": 0.9576842784881592,
252
+ "learning_rate": 3.1504967237370535e-05,
253
+ "loss": 0.5107,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 1.1414077362079897,
258
+ "grad_norm": 0.6107915639877319,
259
+ "learning_rate": 3.097653772986684e-05,
260
+ "loss": 0.519,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 1.1731135066582117,
265
+ "grad_norm": 0.5931509137153625,
266
+ "learning_rate": 3.0448108222363136e-05,
267
+ "loss": 0.5699,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 1.2048192771084336,
272
+ "grad_norm": 0.6647824048995972,
273
+ "learning_rate": 2.991967871485944e-05,
274
+ "loss": 0.5022,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 1.2365250475586556,
279
+ "grad_norm": 0.5938781499862671,
280
+ "learning_rate": 2.939124920735574e-05,
281
+ "loss": 0.4507,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 1.2682308180088775,
286
+ "grad_norm": 1.1466686725616455,
287
+ "learning_rate": 2.886281969985204e-05,
288
+ "loss": 0.6235,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 1.2999365884590994,
293
+ "grad_norm": 0.4420027434825897,
294
+ "learning_rate": 2.833439019234834e-05,
295
+ "loss": 0.6154,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 1.3316423589093214,
300
+ "grad_norm": 0.746532142162323,
301
+ "learning_rate": 2.7805960684844646e-05,
302
+ "loss": 0.4898,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 1.3633481293595433,
307
+ "grad_norm": 1.0959316492080688,
308
+ "learning_rate": 2.7277531177340943e-05,
309
+ "loss": 0.4544,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 1.3950538998097652,
314
+ "grad_norm": 0.8176191449165344,
315
+ "learning_rate": 2.6749101669837247e-05,
316
+ "loss": 0.481,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 1.4267596702599874,
321
+ "grad_norm": 0.8100579380989075,
322
+ "learning_rate": 2.6220672162333547e-05,
323
+ "loss": 0.4333,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 1.4584654407102093,
328
+ "grad_norm": 0.8650724291801453,
329
+ "learning_rate": 2.5692242654829844e-05,
330
+ "loss": 0.4629,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 1.4901712111604313,
335
+ "grad_norm": 1.6807165145874023,
336
+ "learning_rate": 2.5163813147326148e-05,
337
+ "loss": 0.4126,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 1.521876981610653,
342
+ "grad_norm": 0.6398534774780273,
343
+ "learning_rate": 2.463538363982245e-05,
344
+ "loss": 0.4776,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 1.553582752060875,
349
+ "grad_norm": 0.7640373110771179,
350
+ "learning_rate": 2.410695413231875e-05,
351
+ "loss": 0.4901,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 1.5852885225110969,
356
+ "grad_norm": 0.644173800945282,
357
+ "learning_rate": 2.357852462481505e-05,
358
+ "loss": 0.5133,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 1.6169942929613188,
363
+ "grad_norm": 0.577743649482727,
364
+ "learning_rate": 2.305009511731135e-05,
365
+ "loss": 0.4221,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 1.6487000634115407,
370
+ "grad_norm": 0.6014630198478699,
371
+ "learning_rate": 2.252166560980765e-05,
372
+ "loss": 0.4766,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 1.6804058338617627,
377
+ "grad_norm": 0.6592232584953308,
378
+ "learning_rate": 2.1993236102303955e-05,
379
+ "loss": 0.5726,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 1.7121116043119848,
384
+ "grad_norm": 0.7719835042953491,
385
+ "learning_rate": 2.1464806594800255e-05,
386
+ "loss": 0.4941,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 1.7438173747622068,
391
+ "grad_norm": 0.9424024224281311,
392
+ "learning_rate": 2.0936377087296556e-05,
393
+ "loss": 0.5236,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 1.7755231452124287,
398
+ "grad_norm": 1.0417604446411133,
399
+ "learning_rate": 2.0407947579792857e-05,
400
+ "loss": 0.5269,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 1.8072289156626506,
405
+ "grad_norm": 0.42674678564071655,
406
+ "learning_rate": 1.9879518072289157e-05,
407
+ "loss": 0.5067,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 1.8389346861128726,
412
+ "grad_norm": 0.6428393721580505,
413
+ "learning_rate": 1.9351088564785458e-05,
414
+ "loss": 0.4381,
415
+ "step": 2900
416
+ },
417
+ {
418
+ "epoch": 1.8706404565630945,
419
+ "grad_norm": 0.936777651309967,
420
+ "learning_rate": 1.882265905728176e-05,
421
+ "loss": 0.6561,
422
+ "step": 2950
423
+ },
424
+ {
425
+ "epoch": 1.9023462270133165,
426
+ "grad_norm": 1.3489336967468262,
427
+ "learning_rate": 1.8294229549778062e-05,
428
+ "loss": 0.4983,
429
+ "step": 3000
430
+ },
431
+ {
432
+ "epoch": 1.9340519974635384,
433
+ "grad_norm": 0.6496655344963074,
434
+ "learning_rate": 1.776580004227436e-05,
435
+ "loss": 0.4759,
436
+ "step": 3050
437
+ },
438
+ {
439
+ "epoch": 1.9657577679137603,
440
+ "grad_norm": 0.712348997592926,
441
+ "learning_rate": 1.7237370534770663e-05,
442
+ "loss": 0.4621,
443
+ "step": 3100
444
+ },
445
+ {
446
+ "epoch": 1.9974635383639823,
447
+ "grad_norm": 0.5334410667419434,
448
+ "learning_rate": 1.6708941027266964e-05,
449
+ "loss": 0.5246,
450
+ "step": 3150
451
+ },
452
+ {
453
+ "epoch": 2.029169308814204,
454
+ "grad_norm": 0.9799864888191223,
455
+ "learning_rate": 1.6180511519763264e-05,
456
+ "loss": 0.388,
457
+ "step": 3200
458
+ },
459
+ {
460
+ "epoch": 2.060875079264426,
461
+ "grad_norm": 0.6191227436065674,
462
+ "learning_rate": 1.5652082012259565e-05,
463
+ "loss": 0.422,
464
+ "step": 3250
465
+ },
466
+ {
467
+ "epoch": 2.092580849714648,
468
+ "grad_norm": 0.6415786743164062,
469
+ "learning_rate": 1.5123652504755867e-05,
470
+ "loss": 0.4213,
471
+ "step": 3300
472
+ },
473
+ {
474
+ "epoch": 2.12428662016487,
475
+ "grad_norm": 1.024706244468689,
476
+ "learning_rate": 1.4595222997252168e-05,
477
+ "loss": 0.4378,
478
+ "step": 3350
479
+ },
480
+ {
481
+ "epoch": 2.1559923906150917,
482
+ "grad_norm": 1.0147749185562134,
483
+ "learning_rate": 1.4066793489748466e-05,
484
+ "loss": 0.5441,
485
+ "step": 3400
486
+ },
487
+ {
488
+ "epoch": 2.187698161065314,
489
+ "grad_norm": 1.1020487546920776,
490
+ "learning_rate": 1.353836398224477e-05,
491
+ "loss": 0.554,
492
+ "step": 3450
493
+ },
494
+ {
495
+ "epoch": 2.2194039315155356,
496
+ "grad_norm": 0.7216790318489075,
497
+ "learning_rate": 1.3009934474741071e-05,
498
+ "loss": 0.4983,
499
+ "step": 3500
500
+ },
501
+ {
502
+ "epoch": 2.251109701965758,
503
+ "grad_norm": 1.2225050926208496,
504
+ "learning_rate": 1.2481504967237371e-05,
505
+ "loss": 0.4586,
506
+ "step": 3550
507
+ },
508
+ {
509
+ "epoch": 2.2828154724159795,
510
+ "grad_norm": 0.7050449252128601,
511
+ "learning_rate": 1.1953075459733672e-05,
512
+ "loss": 0.4235,
513
+ "step": 3600
514
+ },
515
+ {
516
+ "epoch": 2.314521242866202,
517
+ "grad_norm": 0.6529106497764587,
518
+ "learning_rate": 1.1424645952229973e-05,
519
+ "loss": 0.5061,
520
+ "step": 3650
521
+ },
522
+ {
523
+ "epoch": 2.3462270133164234,
524
+ "grad_norm": 0.5396713018417358,
525
+ "learning_rate": 1.0896216444726275e-05,
526
+ "loss": 0.4983,
527
+ "step": 3700
528
+ },
529
+ {
530
+ "epoch": 2.3779327837666457,
531
+ "grad_norm": 0.6897116899490356,
532
+ "learning_rate": 1.0367786937222575e-05,
533
+ "loss": 0.4658,
534
+ "step": 3750
535
+ },
536
+ {
537
+ "epoch": 2.4096385542168672,
538
+ "grad_norm": 1.0474814176559448,
539
+ "learning_rate": 9.839357429718876e-06,
540
+ "loss": 0.4578,
541
+ "step": 3800
542
+ },
543
+ {
544
+ "epoch": 2.4413443246670896,
545
+ "grad_norm": 0.5905832648277283,
546
+ "learning_rate": 9.310927922215176e-06,
547
+ "loss": 0.4349,
548
+ "step": 3850
549
+ },
550
+ {
551
+ "epoch": 2.473050095117311,
552
+ "grad_norm": 0.6709778904914856,
553
+ "learning_rate": 8.782498414711479e-06,
554
+ "loss": 0.4351,
555
+ "step": 3900
556
+ },
557
+ {
558
+ "epoch": 2.5047558655675335,
559
+ "grad_norm": 0.5383151173591614,
560
+ "learning_rate": 8.254068907207779e-06,
561
+ "loss": 0.52,
562
+ "step": 3950
563
+ },
564
+ {
565
+ "epoch": 2.536461636017755,
566
+ "grad_norm": 0.9183222055435181,
567
+ "learning_rate": 7.72563939970408e-06,
568
+ "loss": 0.5099,
569
+ "step": 4000
570
+ },
571
+ {
572
+ "epoch": 2.5681674064679774,
573
+ "grad_norm": 1.0442452430725098,
574
+ "learning_rate": 7.197209892200381e-06,
575
+ "loss": 0.561,
576
+ "step": 4050
577
+ },
578
+ {
579
+ "epoch": 2.599873176918199,
580
+ "grad_norm": 0.4895930886268616,
581
+ "learning_rate": 6.6687803846966825e-06,
582
+ "loss": 0.4435,
583
+ "step": 4100
584
+ },
585
+ {
586
+ "epoch": 2.6315789473684212,
587
+ "grad_norm": 0.6229114532470703,
588
+ "learning_rate": 6.140350877192982e-06,
589
+ "loss": 0.5262,
590
+ "step": 4150
591
+ },
592
+ {
593
+ "epoch": 2.6632847178186427,
594
+ "grad_norm": 0.647319495677948,
595
+ "learning_rate": 5.6119213696892836e-06,
596
+ "loss": 0.5116,
597
+ "step": 4200
598
+ },
599
+ {
600
+ "epoch": 2.694990488268865,
601
+ "grad_norm": 0.6666443347930908,
602
+ "learning_rate": 5.083491862185585e-06,
603
+ "loss": 0.5408,
604
+ "step": 4250
605
+ },
606
+ {
607
+ "epoch": 2.7266962587190866,
608
+ "grad_norm": 0.6282554268836975,
609
+ "learning_rate": 4.5550623546818855e-06,
610
+ "loss": 0.4801,
611
+ "step": 4300
612
+ },
613
+ {
614
+ "epoch": 2.758402029169309,
615
+ "grad_norm": 1.0603163242340088,
616
+ "learning_rate": 4.026632847178187e-06,
617
+ "loss": 0.4662,
618
+ "step": 4350
619
+ },
620
+ {
621
+ "epoch": 2.7901077996195305,
622
+ "grad_norm": 0.7217985391616821,
623
+ "learning_rate": 3.498203339674488e-06,
624
+ "loss": 0.3947,
625
+ "step": 4400
626
+ },
627
+ {
628
+ "epoch": 2.821813570069753,
629
+ "grad_norm": 0.49021148681640625,
630
+ "learning_rate": 2.9697738321707884e-06,
631
+ "loss": 0.4047,
632
+ "step": 4450
633
+ },
634
+ {
635
+ "epoch": 2.853519340519975,
636
+ "grad_norm": 0.9363583922386169,
637
+ "learning_rate": 2.4413443246670898e-06,
638
+ "loss": 0.4912,
639
+ "step": 4500
640
+ },
641
+ {
642
+ "epoch": 2.8852251109701967,
643
+ "grad_norm": 0.9978638291358948,
644
+ "learning_rate": 1.9129148171633903e-06,
645
+ "loss": 0.579,
646
+ "step": 4550
647
+ },
648
+ {
649
+ "epoch": 2.9169308814204187,
650
+ "grad_norm": 0.6237664222717285,
651
+ "learning_rate": 1.3844853096596915e-06,
652
+ "loss": 0.4324,
653
+ "step": 4600
654
+ },
655
+ {
656
+ "epoch": 2.9486366518706406,
657
+ "grad_norm": 0.6290932893753052,
658
+ "learning_rate": 8.560558021559924e-07,
659
+ "loss": 0.4495,
660
+ "step": 4650
661
+ },
662
+ {
663
+ "epoch": 2.9803424223208625,
664
+ "grad_norm": 0.8747038245201111,
665
+ "learning_rate": 3.276262946522934e-07,
666
+ "loss": 0.44,
667
+ "step": 4700
668
+ }
669
+ ],
670
+ "logging_steps": 50,
671
+ "max_steps": 4731,
672
+ "num_input_tokens_seen": 0,
673
+ "num_train_epochs": 3,
674
+ "save_steps": 500,
675
+ "stateful_callbacks": {
676
+ "TrainerControl": {
677
+ "args": {
678
+ "should_epoch_stop": false,
679
+ "should_evaluate": false,
680
+ "should_log": false,
681
+ "should_save": true,
682
+ "should_training_stop": true
683
+ },
684
+ "attributes": {}
685
+ }
686
+ },
687
+ "total_flos": 4943906537472000.0,
688
+ "train_batch_size": 4,
689
+ "trial_name": null,
690
+ "trial_params": null
691
+ }
checkpoint-4731/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb0e89a06ff97c1285b62a811e8f19adb4ec8af9e57e1f4d37318e75c96a595
3
+ size 5240
checkpoint-4731/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
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
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.47.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
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": "4.47.1"
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 sha256:37559e513798a6342763dbdbdc163d73b0f10356d16ec4f9a576a4d9a8d749a7
3
+ size 497777280
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "unk_token": "<|endoftext|>"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
21
+ "bos_token": "<|endoftext|>",
22
+ "clean_up_tokenization_spaces": false,
23
+ "eos_token": "<|endoftext|>",
24
+ "extra_special_tokens": {},
25
+ "model_max_length": 1024,
26
+ "pad_token": "[PAD]",
27
+ "tokenizer_class": "GPT2Tokenizer",
28
+ "unk_token": "<|endoftext|>"
29
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb0e89a06ff97c1285b62a811e8f19adb4ec8af9e57e1f4d37318e75c96a595
3
+ size 5240
vocab.json ADDED
The diff for this file is too large to render. See raw diff