Hugging Face's logo

VedaantJain
/
gpt_large_alfworld

Safetensors
Model card Files Community
VedaantJain commited on
Commit
a585977
•
1 Parent(s): 4addd1b

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. checkpoint-2200/config.json +39 -0
  2. checkpoint-2200/generation_config.json +6 -0
  3. checkpoint-2200/model.safetensors +3 -0
  4. checkpoint-2200/optimizer.pt +3 -0
  5. checkpoint-2200/rng_state.pth +3 -0
  6. checkpoint-2200/scheduler.pt +3 -0
  7. checkpoint-2200/trainer_state.json +406 -0
  8. checkpoint-2200/training_args.bin +3 -0
checkpoint-2200/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2-large",
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": 1280,
16
+ "n_head": 20,
17
+ "n_inner": null,
18
+ "n_layer": 36,
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": "4.40.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-2200/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": "4.40.0"
6
+ }
checkpoint-2200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d244a056a3d61ca39260b4eb73fa2f8ce572b8c5f49cecda88d1d3140bdab50
3
+ size 3096165928
checkpoint-2200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:505bf9b2e9e70dd7fbc32be567accbe1d9cc61dd48c3bb027a4425b8a77e4ceb
3
+ size 6192613990
checkpoint-2200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f32512d8a24a6848453aec980d6934311433ccf06328df72ceaf714455d720e
3
+ size 14244
checkpoint-2200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b1c62ddda492560372a2a99b64acbf7da0aa71571c00d49e1e9b5684770d5e
3
+ size 1064
checkpoint-2200/trainer_state.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.904333145751266,
5
+ "eval_steps": 500,
6
+ "global_step": 2200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.18007878446820483,
13
+ "grad_norm": 0.6928720474243164,
14
+ "learning_rate": 4.90990990990991e-05,
15
+ "loss": 0.3734,
16
+ "step": 40
17
+ },
18
+ {
19
+ "epoch": 0.36015756893640966,
20
+ "grad_norm": 0.41376394033432007,
21
+ "learning_rate": 4.8198198198198205e-05,
22
+ "loss": 0.2893,
23
+ "step": 80
24
+ },
25
+ {
26
+ "epoch": 0.5402363534046145,
27
+ "grad_norm": 0.3630110025405884,
28
+ "learning_rate": 4.72972972972973e-05,
29
+ "loss": 0.2086,
30
+ "step": 120
31
+ },
32
+ {
33
+ "epoch": 0.7203151378728193,
34
+ "grad_norm": 0.5676272511482239,
35
+ "learning_rate": 4.6396396396396394e-05,
36
+ "loss": 0.1801,
37
+ "step": 160
38
+ },
39
+ {
40
+ "epoch": 0.9003939223410242,
41
+ "grad_norm": 0.43620678782463074,
42
+ "learning_rate": 4.54954954954955e-05,
43
+ "loss": 0.131,
44
+ "step": 200
45
+ },
46
+ {
47
+ "epoch": 1.080472706809229,
48
+ "grad_norm": 0.3849905729293823,
49
+ "learning_rate": 4.4594594594594596e-05,
50
+ "loss": 0.1863,
51
+ "step": 240
52
+ },
53
+ {
54
+ "epoch": 1.2605514912774338,
55
+ "grad_norm": 0.5353094935417175,
56
+ "learning_rate": 4.369369369369369e-05,
57
+ "loss": 0.1294,
58
+ "step": 280
59
+ },
60
+ {
61
+ "epoch": 1.4406302757456388,
62
+ "grad_norm": 0.5001752972602844,
63
+ "learning_rate": 4.27927927927928e-05,
64
+ "loss": 0.1006,
65
+ "step": 320
66
+ },
67
+ {
68
+ "epoch": 1.6207090602138434,
69
+ "grad_norm": 0.39846667647361755,
70
+ "learning_rate": 4.189189189189189e-05,
71
+ "loss": 0.1235,
72
+ "step": 360
73
+ },
74
+ {
75
+ "epoch": 1.8007878446820484,
76
+ "grad_norm": 0.3436274528503418,
77
+ "learning_rate": 4.099099099099099e-05,
78
+ "loss": 0.1121,
79
+ "step": 400
80
+ },
81
+ {
82
+ "epoch": 1.9808666291502532,
83
+ "grad_norm": 0.28420963883399963,
84
+ "learning_rate": 4.0090090090090096e-05,
85
+ "loss": 0.0836,
86
+ "step": 440
87
+ },
88
+ {
89
+ "epoch": 2.160945413618458,
90
+ "grad_norm": 0.36981090903282166,
91
+ "learning_rate": 3.918918918918919e-05,
92
+ "loss": 0.0924,
93
+ "step": 480
94
+ },
95
+ {
96
+ "epoch": 2.341024198086663,
97
+ "grad_norm": 0.32350635528564453,
98
+ "learning_rate": 3.8288288288288285e-05,
99
+ "loss": 0.0786,
100
+ "step": 520
101
+ },
102
+ {
103
+ "epoch": 2.5211029825548676,
104
+ "grad_norm": 0.3884509801864624,
105
+ "learning_rate": 3.738738738738739e-05,
106
+ "loss": 0.0651,
107
+ "step": 560
108
+ },
109
+ {
110
+ "epoch": 2.7011817670230727,
111
+ "grad_norm": 0.453033447265625,
112
+ "learning_rate": 3.648648648648649e-05,
113
+ "loss": 0.0625,
114
+ "step": 600
115
+ },
116
+ {
117
+ "epoch": 2.8812605514912777,
118
+ "grad_norm": 0.4408242106437683,
119
+ "learning_rate": 3.558558558558558e-05,
120
+ "loss": 0.0579,
121
+ "step": 640
122
+ },
123
+ {
124
+ "epoch": 3.0613393359594823,
125
+ "grad_norm": 0.3514708876609802,
126
+ "learning_rate": 3.468468468468469e-05,
127
+ "loss": 0.0729,
128
+ "step": 680
129
+ },
130
+ {
131
+ "epoch": 3.2414181204276873,
132
+ "grad_norm": 0.41110527515411377,
133
+ "learning_rate": 3.3783783783783784e-05,
134
+ "loss": 0.0396,
135
+ "step": 720
136
+ },
137
+ {
138
+ "epoch": 3.421496904895892,
139
+ "grad_norm": 0.4381118714809418,
140
+ "learning_rate": 3.2882882882882886e-05,
141
+ "loss": 0.0421,
142
+ "step": 760
143
+ },
144
+ {
145
+ "epoch": 3.601575689364097,
146
+ "grad_norm": 0.3303312063217163,
147
+ "learning_rate": 3.198198198198199e-05,
148
+ "loss": 0.0452,
149
+ "step": 800
150
+ },
151
+ {
152
+ "epoch": 3.7816544738323015,
153
+ "grad_norm": 0.33113524317741394,
154
+ "learning_rate": 3.108108108108108e-05,
155
+ "loss": 0.0427,
156
+ "step": 840
157
+ },
158
+ {
159
+ "epoch": 3.9617332583005065,
160
+ "grad_norm": 0.2702188789844513,
161
+ "learning_rate": 3.0180180180180183e-05,
162
+ "loss": 0.0373,
163
+ "step": 880
164
+ },
165
+ {
166
+ "epoch": 4.141812042768711,
167
+ "grad_norm": 0.24195368587970734,
168
+ "learning_rate": 2.927927927927928e-05,
169
+ "loss": 0.0369,
170
+ "step": 920
171
+ },
172
+ {
173
+ "epoch": 4.321890827236916,
174
+ "grad_norm": 0.2964402437210083,
175
+ "learning_rate": 2.8378378378378378e-05,
176
+ "loss": 0.0324,
177
+ "step": 960
178
+ },
179
+ {
180
+ "epoch": 4.501969611705121,
181
+ "grad_norm": 0.30053117871284485,
182
+ "learning_rate": 2.7477477477477483e-05,
183
+ "loss": 0.0282,
184
+ "step": 1000
185
+ },
186
+ {
187
+ "epoch": 4.682048396173326,
188
+ "grad_norm": 0.31303390860557556,
189
+ "learning_rate": 2.6576576576576577e-05,
190
+ "loss": 0.0267,
191
+ "step": 1040
192
+ },
193
+ {
194
+ "epoch": 4.862127180641531,
195
+ "grad_norm": 0.2905685007572174,
196
+ "learning_rate": 2.5675675675675675e-05,
197
+ "loss": 0.0302,
198
+ "step": 1080
199
+ },
200
+ {
201
+ "epoch": 5.042205965109735,
202
+ "grad_norm": 0.22705398499965668,
203
+ "learning_rate": 2.4774774774774777e-05,
204
+ "loss": 0.0308,
205
+ "step": 1120
206
+ },
207
+ {
208
+ "epoch": 5.22228474957794,
209
+ "grad_norm": 0.12304919958114624,
210
+ "learning_rate": 2.3873873873873874e-05,
211
+ "loss": 0.0172,
212
+ "step": 1160
213
+ },
214
+ {
215
+ "epoch": 5.402363534046145,
216
+ "grad_norm": 0.265591025352478,
217
+ "learning_rate": 2.2972972972972976e-05,
218
+ "loss": 0.0235,
219
+ "step": 1200
220
+ },
221
+ {
222
+ "epoch": 5.58244231851435,
223
+ "grad_norm": 0.3027079105377197,
224
+ "learning_rate": 2.2072072072072073e-05,
225
+ "loss": 0.0231,
226
+ "step": 1240
227
+ },
228
+ {
229
+ "epoch": 5.7625211029825545,
230
+ "grad_norm": 0.29543060064315796,
231
+ "learning_rate": 2.117117117117117e-05,
232
+ "loss": 0.0235,
233
+ "step": 1280
234
+ },
235
+ {
236
+ "epoch": 5.9425998874507595,
237
+ "grad_norm": 0.2505602240562439,
238
+ "learning_rate": 2.0270270270270273e-05,
239
+ "loss": 0.0212,
240
+ "step": 1320
241
+ },
242
+ {
243
+ "epoch": 6.1226786719189645,
244
+ "grad_norm": 0.19057944416999817,
245
+ "learning_rate": 1.936936936936937e-05,
246
+ "loss": 0.0195,
247
+ "step": 1360
248
+ },
249
+ {
250
+ "epoch": 6.3027574563871696,
251
+ "grad_norm": 0.240937277674675,
252
+ "learning_rate": 1.846846846846847e-05,
253
+ "loss": 0.0174,
254
+ "step": 1400
255
+ },
256
+ {
257
+ "epoch": 6.482836240855375,
258
+ "grad_norm": 0.25285354256629944,
259
+ "learning_rate": 1.756756756756757e-05,
260
+ "loss": 0.0172,
261
+ "step": 1440
262
+ },
263
+ {
264
+ "epoch": 6.662915025323579,
265
+ "grad_norm": 0.35455822944641113,
266
+ "learning_rate": 1.6666666666666667e-05,
267
+ "loss": 0.0172,
268
+ "step": 1480
269
+ },
270
+ {
271
+ "epoch": 6.842993809791784,
272
+ "grad_norm": 0.14479529857635498,
273
+ "learning_rate": 1.5765765765765765e-05,
274
+ "loss": 0.0179,
275
+ "step": 1520
276
+ },
277
+ {
278
+ "epoch": 7.023072594259989,
279
+ "grad_norm": 0.2024831473827362,
280
+ "learning_rate": 1.4864864864864867e-05,
281
+ "loss": 0.0168,
282
+ "step": 1560
283
+ },
284
+ {
285
+ "epoch": 7.203151378728194,
286
+ "grad_norm": 0.17621932923793793,
287
+ "learning_rate": 1.3963963963963963e-05,
288
+ "loss": 0.0127,
289
+ "step": 1600
290
+ },
291
+ {
292
+ "epoch": 7.383230163196399,
293
+ "grad_norm": 0.1810392290353775,
294
+ "learning_rate": 1.3063063063063064e-05,
295
+ "loss": 0.015,
296
+ "step": 1640
297
+ },
298
+ {
299
+ "epoch": 7.563308947664603,
300
+ "grad_norm": 0.2588270306587219,
301
+ "learning_rate": 1.2162162162162164e-05,
302
+ "loss": 0.0145,
303
+ "step": 1680
304
+ },
305
+ {
306
+ "epoch": 7.743387732132808,
307
+ "grad_norm": 0.20072610676288605,
308
+ "learning_rate": 1.1261261261261261e-05,
309
+ "loss": 0.013,
310
+ "step": 1720
311
+ },
312
+ {
313
+ "epoch": 7.923466516601013,
314
+ "grad_norm": 0.20741352438926697,
315
+ "learning_rate": 1.0360360360360361e-05,
316
+ "loss": 0.0107,
317
+ "step": 1760
318
+ },
319
+ {
320
+ "epoch": 8.103545301069218,
321
+ "grad_norm": 0.10997072607278824,
322
+ "learning_rate": 9.45945945945946e-06,
323
+ "loss": 0.0138,
324
+ "step": 1800
325
+ },
326
+ {
327
+ "epoch": 8.283624085537422,
328
+ "grad_norm": 0.1996031105518341,
329
+ "learning_rate": 8.558558558558558e-06,
330
+ "loss": 0.0093,
331
+ "step": 1840
332
+ },
333
+ {
334
+ "epoch": 8.463702870005628,
335
+ "grad_norm": 0.19463427364826202,
336
+ "learning_rate": 7.657657657657658e-06,
337
+ "loss": 0.0087,
338
+ "step": 1880
339
+ },
340
+ {
341
+ "epoch": 8.643781654473832,
342
+ "grad_norm": 0.13947124779224396,
343
+ "learning_rate": 6.7567567567567575e-06,
344
+ "loss": 0.0111,
345
+ "step": 1920
346
+ },
347
+ {
348
+ "epoch": 8.823860438942036,
349
+ "grad_norm": 0.12221422046422958,
350
+ "learning_rate": 5.855855855855856e-06,
351
+ "loss": 0.0124,
352
+ "step": 1960
353
+ },
354
+ {
355
+ "epoch": 9.003939223410242,
356
+ "grad_norm": 0.3783756494522095,
357
+ "learning_rate": 4.954954954954955e-06,
358
+ "loss": 0.0093,
359
+ "step": 2000
360
+ },
361
+ {
362
+ "epoch": 9.184018007878446,
363
+ "grad_norm": 0.07258374243974686,
364
+ "learning_rate": 4.0540540540540545e-06,
365
+ "loss": 0.0095,
366
+ "step": 2040
367
+ },
368
+ {
369
+ "epoch": 9.364096792346652,
370
+ "grad_norm": 0.17456740140914917,
371
+ "learning_rate": 3.153153153153153e-06,
372
+ "loss": 0.0097,
373
+ "step": 2080
374
+ },
375
+ {
376
+ "epoch": 9.544175576814856,
377
+ "grad_norm": 0.15748119354248047,
378
+ "learning_rate": 2.2522522522522524e-06,
379
+ "loss": 0.0084,
380
+ "step": 2120
381
+ },
382
+ {
383
+ "epoch": 9.72425436128306,
384
+ "grad_norm": 0.21072803437709808,
385
+ "learning_rate": 1.3513513513513515e-06,
386
+ "loss": 0.0084,
387
+ "step": 2160
388
+ },
389
+ {
390
+ "epoch": 9.904333145751266,
391
+ "grad_norm": 0.20778457820415497,
392
+ "learning_rate": 4.504504504504505e-07,
393
+ "loss": 0.0067,
394
+ "step": 2200
395
+ }
396
+ ],
397
+ "logging_steps": 40,
398
+ "max_steps": 2220,
399
+ "num_input_tokens_seen": 0,
400
+ "num_train_epochs": 10,
401
+ "save_steps": 550,
402
+ "total_flos": 9.109057559424e+16,
403
+ "train_batch_size": 2,
404
+ "trial_name": null,
405
+ "trial_params": null
406
+ }
checkpoint-2200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad6dfc466fe9aa5e14d7004d6766867b92001d312a3277342d40bdbbfad057a
3
+ size 5048