invi-bhagyesh commited on
Commit
567fb4d
·
verified ·
1 Parent(s): 3f70c6d

Upload folder using huggingface_hub

Browse files
Files changed (48) hide show
  1. distilgpt2/checkpoint-900/config.json +45 -0
  2. distilgpt2/checkpoint-900/generation_config.json +6 -0
  3. distilgpt2/checkpoint-900/merges.txt +0 -0
  4. distilgpt2/checkpoint-900/model.safetensors +3 -0
  5. distilgpt2/checkpoint-900/optimizer.pt +3 -0
  6. distilgpt2/checkpoint-900/rng_state.pth +3 -0
  7. distilgpt2/checkpoint-900/scheduler.pt +3 -0
  8. distilgpt2/checkpoint-900/special_tokens_map.json +6 -0
  9. distilgpt2/checkpoint-900/tokenizer.json +0 -0
  10. distilgpt2/checkpoint-900/tokenizer_config.json +21 -0
  11. distilgpt2/checkpoint-900/trainer_state.json +664 -0
  12. distilgpt2/checkpoint-900/training_args.bin +3 -0
  13. distilgpt2/checkpoint-900/vocab.json +0 -0
  14. distilgpt2/checkpoint-939/config.json +45 -0
  15. distilgpt2/checkpoint-939/generation_config.json +6 -0
  16. distilgpt2/checkpoint-939/merges.txt +0 -0
  17. distilgpt2/checkpoint-939/model.safetensors +3 -0
  18. distilgpt2/checkpoint-939/optimizer.pt +3 -0
  19. distilgpt2/checkpoint-939/rng_state.pth +3 -0
  20. distilgpt2/checkpoint-939/scheduler.pt +3 -0
  21. distilgpt2/checkpoint-939/special_tokens_map.json +6 -0
  22. distilgpt2/checkpoint-939/tokenizer.json +0 -0
  23. distilgpt2/checkpoint-939/tokenizer_config.json +21 -0
  24. distilgpt2/checkpoint-939/trainer_state.json +685 -0
  25. distilgpt2/checkpoint-939/training_args.bin +3 -0
  26. distilgpt2/checkpoint-939/vocab.json +0 -0
  27. distilgpt2/fp32_finetuned_model/config.json +45 -0
  28. distilgpt2/fp32_finetuned_model/generation_config.json +6 -0
  29. distilgpt2/fp32_finetuned_model/merges.txt +0 -0
  30. distilgpt2/fp32_finetuned_model/model.safetensors +3 -0
  31. distilgpt2/fp32_finetuned_model/special_tokens_map.json +6 -0
  32. distilgpt2/fp32_finetuned_model/tokenizer.json +0 -0
  33. distilgpt2/fp32_finetuned_model/tokenizer_config.json +21 -0
  34. distilgpt2/fp32_finetuned_model/training_args.bin +3 -0
  35. distilgpt2/fp32_finetuned_model/vocab.json +0 -0
  36. distilgpt2/fp32_model/model.pt +3 -0
  37. distilgpt2/int4_model/model.pt +3 -0
  38. distilgpt2/qat_model/config.json +45 -0
  39. distilgpt2/qat_model/generation_config.json +6 -0
  40. distilgpt2/qat_model/merges.txt +0 -0
  41. distilgpt2/qat_model/model.safetensors +3 -0
  42. distilgpt2/qat_model/special_tokens_map.json +6 -0
  43. distilgpt2/qat_model/tokenizer.json +0 -0
  44. distilgpt2/qat_model/tokenizer_config.json +21 -0
  45. distilgpt2/qat_model/training_args.bin +3 -0
  46. distilgpt2/qat_model/vocab.json +0 -0
  47. distilgpt2/runs/Oct11_16-56-47_5a2111a52440/events.out.tfevents.1760201808.5a2111a52440.96.0 +3 -0
  48. distilgpt2/runs/Oct11_16-56-47_5a2111a52440/events.out.tfevents.1760203459.5a2111a52440.96.1 +3 -0
distilgpt2/checkpoint-900/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 1,
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
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "gpt2",
20
+ "n_ctx": 1024,
21
+ "n_embd": 768,
22
+ "n_head": 12,
23
+ "n_inner": null,
24
+ "n_layer": 6,
25
+ "n_positions": 1024,
26
+ "reorder_and_upcast_attn": false,
27
+ "resid_pdrop": 0.1,
28
+ "scale_attn_by_inverse_layer_idx": false,
29
+ "scale_attn_weights": true,
30
+ "summary_activation": null,
31
+ "summary_first_dropout": 0.1,
32
+ "summary_proj_to_labels": true,
33
+ "summary_type": "cls_index",
34
+ "summary_use_proj": true,
35
+ "task_specific_params": {
36
+ "text-generation": {
37
+ "do_sample": true,
38
+ "max_length": 50
39
+ }
40
+ },
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.53.3",
43
+ "use_cache": true,
44
+ "vocab_size": 50257
45
+ }
distilgpt2/checkpoint-900/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": "4.53.3"
6
+ }
distilgpt2/checkpoint-900/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/checkpoint-900/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4156d69a8bbb0eed81f66098024baba021c49a1bbf6c7cc291713d882a0a2663
3
+ size 327657928
distilgpt2/checkpoint-900/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b1e018a98acc59b197197cb2144e3047862b56f0d23827ad8ca508221bc95be
3
+ size 655364474
distilgpt2/checkpoint-900/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:018c226caeb64f7d9e8d90042a28fb98b683c4520b26ddb99a2d2cf5835d83c6
3
+ size 14244
distilgpt2/checkpoint-900/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:678712356fafda5888bf10ab4c93223826a90f603ff85cc4c0c5fa5cef5f7aff
3
+ size 1064
distilgpt2/checkpoint-900/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
distilgpt2/checkpoint-900/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/checkpoint-900/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
distilgpt2/checkpoint-900/trainer_state.json ADDED
@@ -0,0 +1,664 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.8768000000000002,
6
+ "eval_steps": 50,
7
+ "global_step": 900,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.032,
14
+ "grad_norm": 5.848097801208496,
15
+ "learning_rate": 4.5e-06,
16
+ "loss": 2.3184,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.064,
21
+ "grad_norm": 2.5511839389801025,
22
+ "learning_rate": 9.5e-06,
23
+ "loss": 2.0441,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.096,
28
+ "grad_norm": 2.325101613998413,
29
+ "learning_rate": 1.45e-05,
30
+ "loss": 1.917,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.128,
35
+ "grad_norm": 2.8172621726989746,
36
+ "learning_rate": 1.9500000000000003e-05,
37
+ "loss": 2.2506,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.16,
42
+ "grad_norm": 3.325876474380493,
43
+ "learning_rate": 2.45e-05,
44
+ "loss": 1.8721,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.192,
49
+ "grad_norm": 2.435955286026001,
50
+ "learning_rate": 2.95e-05,
51
+ "loss": 1.8327,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.224,
56
+ "grad_norm": 2.8088173866271973,
57
+ "learning_rate": 3.45e-05,
58
+ "loss": 1.7227,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.256,
63
+ "grad_norm": 2.5641565322875977,
64
+ "learning_rate": 3.9500000000000005e-05,
65
+ "loss": 1.8172,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.288,
70
+ "grad_norm": 2.741063356399536,
71
+ "learning_rate": 4.4500000000000004e-05,
72
+ "loss": 1.6577,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.32,
77
+ "grad_norm": 2.7209696769714355,
78
+ "learning_rate": 4.9500000000000004e-05,
79
+ "loss": 1.8833,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.352,
84
+ "grad_norm": 2.6947555541992188,
85
+ "learning_rate": 4.946364719904649e-05,
86
+ "loss": 2.0177,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.384,
91
+ "grad_norm": 2.37589955329895,
92
+ "learning_rate": 4.886769964243147e-05,
93
+ "loss": 1.8127,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.416,
98
+ "grad_norm": 3.018338203430176,
99
+ "learning_rate": 4.8271752085816455e-05,
100
+ "loss": 1.862,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.448,
105
+ "grad_norm": 3.863445997238159,
106
+ "learning_rate": 4.767580452920143e-05,
107
+ "loss": 1.9697,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.48,
112
+ "grad_norm": 2.984334945678711,
113
+ "learning_rate": 4.7079856972586414e-05,
114
+ "loss": 1.9533,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.512,
119
+ "grad_norm": 2.4165594577789307,
120
+ "learning_rate": 4.64839094159714e-05,
121
+ "loss": 1.8285,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.544,
126
+ "grad_norm": 1.7296801805496216,
127
+ "learning_rate": 4.5887961859356374e-05,
128
+ "loss": 1.783,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.576,
133
+ "grad_norm": 2.5170071125030518,
134
+ "learning_rate": 4.529201430274136e-05,
135
+ "loss": 1.5282,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.608,
140
+ "grad_norm": 2.53623366355896,
141
+ "learning_rate": 4.469606674612634e-05,
142
+ "loss": 1.8379,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.64,
147
+ "grad_norm": 2.4525668621063232,
148
+ "learning_rate": 4.410011918951132e-05,
149
+ "loss": 1.9569,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.672,
154
+ "grad_norm": 3.1210453510284424,
155
+ "learning_rate": 4.3504171632896306e-05,
156
+ "loss": 1.8645,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.704,
161
+ "grad_norm": 3.257766008377075,
162
+ "learning_rate": 4.290822407628129e-05,
163
+ "loss": 1.7785,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.736,
168
+ "grad_norm": 2.6239209175109863,
169
+ "learning_rate": 4.231227651966627e-05,
170
+ "loss": 1.7526,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.768,
175
+ "grad_norm": 2.526646137237549,
176
+ "learning_rate": 4.1716328963051256e-05,
177
+ "loss": 1.8174,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.8,
182
+ "grad_norm": 2.1927671432495117,
183
+ "learning_rate": 4.112038140643624e-05,
184
+ "loss": 1.5208,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.832,
189
+ "grad_norm": 3.186937093734741,
190
+ "learning_rate": 4.052443384982122e-05,
191
+ "loss": 1.6424,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.864,
196
+ "grad_norm": 2.3542070388793945,
197
+ "learning_rate": 3.9928486293206205e-05,
198
+ "loss": 1.7575,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.896,
203
+ "grad_norm": 1.9437086582183838,
204
+ "learning_rate": 3.933253873659118e-05,
205
+ "loss": 1.5789,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.928,
210
+ "grad_norm": 2.5914506912231445,
211
+ "learning_rate": 3.8736591179976165e-05,
212
+ "loss": 1.6693,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.96,
217
+ "grad_norm": 1.9983558654785156,
218
+ "learning_rate": 3.814064362336114e-05,
219
+ "loss": 1.7447,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.992,
224
+ "grad_norm": 1.7978435754776,
225
+ "learning_rate": 3.7544696066746124e-05,
226
+ "loss": 1.6711,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.0224,
231
+ "grad_norm": 3.406076192855835,
232
+ "learning_rate": 3.694874851013111e-05,
233
+ "loss": 1.8133,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.0544,
238
+ "grad_norm": 2.2293291091918945,
239
+ "learning_rate": 3.635280095351609e-05,
240
+ "loss": 1.7722,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.0864,
245
+ "grad_norm": 2.3838605880737305,
246
+ "learning_rate": 3.575685339690107e-05,
247
+ "loss": 1.6334,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.1184,
252
+ "grad_norm": 2.256012439727783,
253
+ "learning_rate": 3.5160905840286057e-05,
254
+ "loss": 1.5336,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.1504,
259
+ "grad_norm": 2.4280765056610107,
260
+ "learning_rate": 3.456495828367104e-05,
261
+ "loss": 1.6229,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 1.1824,
266
+ "grad_norm": 2.8488781452178955,
267
+ "learning_rate": 3.396901072705602e-05,
268
+ "loss": 1.7856,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 1.2144,
273
+ "grad_norm": 1.915912389755249,
274
+ "learning_rate": 3.3373063170441006e-05,
275
+ "loss": 1.6749,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 1.2464,
280
+ "grad_norm": 2.3185014724731445,
281
+ "learning_rate": 3.277711561382599e-05,
282
+ "loss": 1.4804,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.2784,
287
+ "grad_norm": 3.116079330444336,
288
+ "learning_rate": 3.218116805721097e-05,
289
+ "loss": 1.7211,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.3104,
294
+ "grad_norm": 2.4169015884399414,
295
+ "learning_rate": 3.158522050059595e-05,
296
+ "loss": 1.9021,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.3424,
301
+ "grad_norm": 2.3938851356506348,
302
+ "learning_rate": 3.098927294398093e-05,
303
+ "loss": 1.8511,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.3744,
308
+ "grad_norm": 2.8537979125976562,
309
+ "learning_rate": 3.039332538736591e-05,
310
+ "loss": 1.7034,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.4064,
315
+ "grad_norm": 2.3688974380493164,
316
+ "learning_rate": 2.9797377830750894e-05,
317
+ "loss": 1.5986,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.4384000000000001,
322
+ "grad_norm": 2.4708006381988525,
323
+ "learning_rate": 2.9201430274135878e-05,
324
+ "loss": 1.8078,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.4704,
329
+ "grad_norm": 2.428288698196411,
330
+ "learning_rate": 2.860548271752086e-05,
331
+ "loss": 1.7737,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.5024,
336
+ "grad_norm": 3.910275459289551,
337
+ "learning_rate": 2.800953516090584e-05,
338
+ "loss": 1.7495,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.5344,
343
+ "grad_norm": 3.0172460079193115,
344
+ "learning_rate": 2.7413587604290824e-05,
345
+ "loss": 1.514,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.5664,
350
+ "grad_norm": 2.250343084335327,
351
+ "learning_rate": 2.6817640047675807e-05,
352
+ "loss": 1.8304,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.5984,
357
+ "grad_norm": 2.327152729034424,
358
+ "learning_rate": 2.622169249106079e-05,
359
+ "loss": 1.739,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.6303999999999998,
364
+ "grad_norm": 2.144254207611084,
365
+ "learning_rate": 2.5625744934445773e-05,
366
+ "loss": 1.6757,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.6623999999999999,
371
+ "grad_norm": 3.2096481323242188,
372
+ "learning_rate": 2.5029797377830756e-05,
373
+ "loss": 1.4808,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.6944,
378
+ "grad_norm": 2.584341287612915,
379
+ "learning_rate": 2.4433849821215736e-05,
380
+ "loss": 1.4193,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.7264,
385
+ "grad_norm": 1.8545327186584473,
386
+ "learning_rate": 2.3837902264600716e-05,
387
+ "loss": 1.5282,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.7584,
392
+ "grad_norm": 2.4782474040985107,
393
+ "learning_rate": 2.32419547079857e-05,
394
+ "loss": 1.7681,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.7904,
399
+ "grad_norm": 3.0083882808685303,
400
+ "learning_rate": 2.264600715137068e-05,
401
+ "loss": 1.8547,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.8224,
406
+ "grad_norm": 2.600146770477295,
407
+ "learning_rate": 2.205005959475566e-05,
408
+ "loss": 1.55,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.8544,
413
+ "grad_norm": 1.716131567955017,
414
+ "learning_rate": 2.1454112038140645e-05,
415
+ "loss": 1.7406,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.8864,
420
+ "grad_norm": 2.536386728286743,
421
+ "learning_rate": 2.0858164481525628e-05,
422
+ "loss": 1.6436,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.9184,
427
+ "grad_norm": 2.161496877670288,
428
+ "learning_rate": 2.026221692491061e-05,
429
+ "loss": 1.6616,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.9504000000000001,
434
+ "grad_norm": 2.6042492389678955,
435
+ "learning_rate": 1.966626936829559e-05,
436
+ "loss": 1.6278,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.9824000000000002,
441
+ "grad_norm": 2.641090154647827,
442
+ "learning_rate": 1.907032181168057e-05,
443
+ "loss": 1.5632,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 2.0128,
448
+ "grad_norm": 2.133544683456421,
449
+ "learning_rate": 1.8474374255065554e-05,
450
+ "loss": 1.6812,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 2.0448,
455
+ "grad_norm": 3.285512685775757,
456
+ "learning_rate": 1.7878426698450537e-05,
457
+ "loss": 1.6949,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 2.0768,
462
+ "grad_norm": 2.3074097633361816,
463
+ "learning_rate": 1.728247914183552e-05,
464
+ "loss": 1.6071,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 2.1088,
469
+ "grad_norm": 3.0742709636688232,
470
+ "learning_rate": 1.6686531585220503e-05,
471
+ "loss": 1.7419,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 2.1408,
476
+ "grad_norm": 1.7113871574401855,
477
+ "learning_rate": 1.6090584028605486e-05,
478
+ "loss": 1.4946,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 2.1728,
483
+ "grad_norm": 2.1010677814483643,
484
+ "learning_rate": 1.5494636471990466e-05,
485
+ "loss": 1.4342,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 2.2048,
490
+ "grad_norm": 2.1286814212799072,
491
+ "learning_rate": 1.4898688915375447e-05,
492
+ "loss": 1.5922,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 2.2368,
497
+ "grad_norm": 2.790449619293213,
498
+ "learning_rate": 1.430274135876043e-05,
499
+ "loss": 1.8599,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 2.2688,
504
+ "grad_norm": 2.589710235595703,
505
+ "learning_rate": 1.3706793802145412e-05,
506
+ "loss": 1.5151,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 2.3008,
511
+ "grad_norm": 2.7718470096588135,
512
+ "learning_rate": 1.3110846245530395e-05,
513
+ "loss": 1.6952,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 2.3327999999999998,
518
+ "grad_norm": 2.431128978729248,
519
+ "learning_rate": 1.2514898688915378e-05,
520
+ "loss": 1.5283,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 2.3648,
525
+ "grad_norm": 2.2655253410339355,
526
+ "learning_rate": 1.1918951132300358e-05,
527
+ "loss": 1.6497,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 2.3968,
532
+ "grad_norm": 2.075089454650879,
533
+ "learning_rate": 1.132300357568534e-05,
534
+ "loss": 1.6415,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 2.4288,
539
+ "grad_norm": 2.5529932975769043,
540
+ "learning_rate": 1.0727056019070322e-05,
541
+ "loss": 1.5808,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 2.4608,
546
+ "grad_norm": 1.4980545043945312,
547
+ "learning_rate": 1.0131108462455305e-05,
548
+ "loss": 1.5812,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 2.4928,
553
+ "grad_norm": 1.8248558044433594,
554
+ "learning_rate": 9.535160905840285e-06,
555
+ "loss": 1.4732,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 2.5248,
560
+ "grad_norm": 3.1333248615264893,
561
+ "learning_rate": 8.939213349225268e-06,
562
+ "loss": 1.6248,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 2.5568,
567
+ "grad_norm": 2.8021600246429443,
568
+ "learning_rate": 8.343265792610251e-06,
569
+ "loss": 1.6294,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 2.5888,
574
+ "grad_norm": 1.942338466644287,
575
+ "learning_rate": 7.747318235995233e-06,
576
+ "loss": 1.5882,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 2.6208,
581
+ "grad_norm": 2.3626883029937744,
582
+ "learning_rate": 7.151370679380215e-06,
583
+ "loss": 1.8162,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 2.6528,
588
+ "grad_norm": 2.5083396434783936,
589
+ "learning_rate": 6.5554231227651975e-06,
590
+ "loss": 1.7253,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 2.6848,
595
+ "grad_norm": 2.0188353061676025,
596
+ "learning_rate": 5.959475566150179e-06,
597
+ "loss": 1.7959,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 2.7168,
602
+ "grad_norm": 2.74120831489563,
603
+ "learning_rate": 5.363528009535161e-06,
604
+ "loss": 1.6135,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 2.7488,
609
+ "grad_norm": 2.245814561843872,
610
+ "learning_rate": 4.767580452920143e-06,
611
+ "loss": 1.6453,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 2.7808,
616
+ "grad_norm": 2.572443962097168,
617
+ "learning_rate": 4.171632896305126e-06,
618
+ "loss": 1.6977,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 2.8128,
623
+ "grad_norm": 2.1156558990478516,
624
+ "learning_rate": 3.5756853396901076e-06,
625
+ "loss": 1.5791,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 2.8448,
630
+ "grad_norm": 2.4948208332061768,
631
+ "learning_rate": 2.9797377830750894e-06,
632
+ "loss": 1.6606,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 2.8768000000000002,
637
+ "grad_norm": 2.791877269744873,
638
+ "learning_rate": 2.3837902264600713e-06,
639
+ "loss": 1.5517,
640
+ "step": 900
641
+ }
642
+ ],
643
+ "logging_steps": 10,
644
+ "max_steps": 939,
645
+ "num_input_tokens_seen": 0,
646
+ "num_train_epochs": 3,
647
+ "save_steps": 50,
648
+ "stateful_callbacks": {
649
+ "TrainerControl": {
650
+ "args": {
651
+ "should_epoch_stop": false,
652
+ "should_evaluate": false,
653
+ "should_log": false,
654
+ "should_save": true,
655
+ "should_training_stop": false
656
+ },
657
+ "attributes": {}
658
+ }
659
+ },
660
+ "total_flos": 3758492460515328.0,
661
+ "train_batch_size": 2,
662
+ "trial_name": null,
663
+ "trial_params": null
664
+ }
distilgpt2/checkpoint-900/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03869acb65d97d306a6961c4204630b6685180f03ac4c51eaa6ded2aad61a5e8
3
+ size 5368
distilgpt2/checkpoint-900/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/checkpoint-939/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 1,
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
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "gpt2",
20
+ "n_ctx": 1024,
21
+ "n_embd": 768,
22
+ "n_head": 12,
23
+ "n_inner": null,
24
+ "n_layer": 6,
25
+ "n_positions": 1024,
26
+ "reorder_and_upcast_attn": false,
27
+ "resid_pdrop": 0.1,
28
+ "scale_attn_by_inverse_layer_idx": false,
29
+ "scale_attn_weights": true,
30
+ "summary_activation": null,
31
+ "summary_first_dropout": 0.1,
32
+ "summary_proj_to_labels": true,
33
+ "summary_type": "cls_index",
34
+ "summary_use_proj": true,
35
+ "task_specific_params": {
36
+ "text-generation": {
37
+ "do_sample": true,
38
+ "max_length": 50
39
+ }
40
+ },
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.53.3",
43
+ "use_cache": true,
44
+ "vocab_size": 50257
45
+ }
distilgpt2/checkpoint-939/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": "4.53.3"
6
+ }
distilgpt2/checkpoint-939/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/checkpoint-939/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b9577ecb05b6c1e4859b0f7cce7ae902d9f5295f60ad68a01c27e67ec0345ca
3
+ size 327657928
distilgpt2/checkpoint-939/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42110f9712bcdb6178b1e72ea0dd0ffd2239fea06bf950f5d6ebacb627847379
3
+ size 655364474
distilgpt2/checkpoint-939/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e924ffd74e9e97176ade4c2113cc94c63ba2bdd44fd3b33a9d611bcd794c7d
3
+ size 14244
distilgpt2/checkpoint-939/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d1f941d497036c9605187ce99bc7102dc62a0065d5cfc7ec062dec8be90fb2
3
+ size 1064
distilgpt2/checkpoint-939/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
distilgpt2/checkpoint-939/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/checkpoint-939/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
distilgpt2/checkpoint-939/trainer_state.json ADDED
@@ -0,0 +1,685 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 50,
7
+ "global_step": 939,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.032,
14
+ "grad_norm": 5.848097801208496,
15
+ "learning_rate": 4.5e-06,
16
+ "loss": 2.3184,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.064,
21
+ "grad_norm": 2.5511839389801025,
22
+ "learning_rate": 9.5e-06,
23
+ "loss": 2.0441,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.096,
28
+ "grad_norm": 2.325101613998413,
29
+ "learning_rate": 1.45e-05,
30
+ "loss": 1.917,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.128,
35
+ "grad_norm": 2.8172621726989746,
36
+ "learning_rate": 1.9500000000000003e-05,
37
+ "loss": 2.2506,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.16,
42
+ "grad_norm": 3.325876474380493,
43
+ "learning_rate": 2.45e-05,
44
+ "loss": 1.8721,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.192,
49
+ "grad_norm": 2.435955286026001,
50
+ "learning_rate": 2.95e-05,
51
+ "loss": 1.8327,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.224,
56
+ "grad_norm": 2.8088173866271973,
57
+ "learning_rate": 3.45e-05,
58
+ "loss": 1.7227,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.256,
63
+ "grad_norm": 2.5641565322875977,
64
+ "learning_rate": 3.9500000000000005e-05,
65
+ "loss": 1.8172,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.288,
70
+ "grad_norm": 2.741063356399536,
71
+ "learning_rate": 4.4500000000000004e-05,
72
+ "loss": 1.6577,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.32,
77
+ "grad_norm": 2.7209696769714355,
78
+ "learning_rate": 4.9500000000000004e-05,
79
+ "loss": 1.8833,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.352,
84
+ "grad_norm": 2.6947555541992188,
85
+ "learning_rate": 4.946364719904649e-05,
86
+ "loss": 2.0177,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.384,
91
+ "grad_norm": 2.37589955329895,
92
+ "learning_rate": 4.886769964243147e-05,
93
+ "loss": 1.8127,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.416,
98
+ "grad_norm": 3.018338203430176,
99
+ "learning_rate": 4.8271752085816455e-05,
100
+ "loss": 1.862,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.448,
105
+ "grad_norm": 3.863445997238159,
106
+ "learning_rate": 4.767580452920143e-05,
107
+ "loss": 1.9697,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.48,
112
+ "grad_norm": 2.984334945678711,
113
+ "learning_rate": 4.7079856972586414e-05,
114
+ "loss": 1.9533,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.512,
119
+ "grad_norm": 2.4165594577789307,
120
+ "learning_rate": 4.64839094159714e-05,
121
+ "loss": 1.8285,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.544,
126
+ "grad_norm": 1.7296801805496216,
127
+ "learning_rate": 4.5887961859356374e-05,
128
+ "loss": 1.783,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.576,
133
+ "grad_norm": 2.5170071125030518,
134
+ "learning_rate": 4.529201430274136e-05,
135
+ "loss": 1.5282,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.608,
140
+ "grad_norm": 2.53623366355896,
141
+ "learning_rate": 4.469606674612634e-05,
142
+ "loss": 1.8379,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.64,
147
+ "grad_norm": 2.4525668621063232,
148
+ "learning_rate": 4.410011918951132e-05,
149
+ "loss": 1.9569,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.672,
154
+ "grad_norm": 3.1210453510284424,
155
+ "learning_rate": 4.3504171632896306e-05,
156
+ "loss": 1.8645,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.704,
161
+ "grad_norm": 3.257766008377075,
162
+ "learning_rate": 4.290822407628129e-05,
163
+ "loss": 1.7785,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.736,
168
+ "grad_norm": 2.6239209175109863,
169
+ "learning_rate": 4.231227651966627e-05,
170
+ "loss": 1.7526,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.768,
175
+ "grad_norm": 2.526646137237549,
176
+ "learning_rate": 4.1716328963051256e-05,
177
+ "loss": 1.8174,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.8,
182
+ "grad_norm": 2.1927671432495117,
183
+ "learning_rate": 4.112038140643624e-05,
184
+ "loss": 1.5208,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.832,
189
+ "grad_norm": 3.186937093734741,
190
+ "learning_rate": 4.052443384982122e-05,
191
+ "loss": 1.6424,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.864,
196
+ "grad_norm": 2.3542070388793945,
197
+ "learning_rate": 3.9928486293206205e-05,
198
+ "loss": 1.7575,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.896,
203
+ "grad_norm": 1.9437086582183838,
204
+ "learning_rate": 3.933253873659118e-05,
205
+ "loss": 1.5789,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.928,
210
+ "grad_norm": 2.5914506912231445,
211
+ "learning_rate": 3.8736591179976165e-05,
212
+ "loss": 1.6693,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.96,
217
+ "grad_norm": 1.9983558654785156,
218
+ "learning_rate": 3.814064362336114e-05,
219
+ "loss": 1.7447,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.992,
224
+ "grad_norm": 1.7978435754776,
225
+ "learning_rate": 3.7544696066746124e-05,
226
+ "loss": 1.6711,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.0224,
231
+ "grad_norm": 3.406076192855835,
232
+ "learning_rate": 3.694874851013111e-05,
233
+ "loss": 1.8133,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.0544,
238
+ "grad_norm": 2.2293291091918945,
239
+ "learning_rate": 3.635280095351609e-05,
240
+ "loss": 1.7722,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.0864,
245
+ "grad_norm": 2.3838605880737305,
246
+ "learning_rate": 3.575685339690107e-05,
247
+ "loss": 1.6334,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.1184,
252
+ "grad_norm": 2.256012439727783,
253
+ "learning_rate": 3.5160905840286057e-05,
254
+ "loss": 1.5336,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.1504,
259
+ "grad_norm": 2.4280765056610107,
260
+ "learning_rate": 3.456495828367104e-05,
261
+ "loss": 1.6229,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 1.1824,
266
+ "grad_norm": 2.8488781452178955,
267
+ "learning_rate": 3.396901072705602e-05,
268
+ "loss": 1.7856,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 1.2144,
273
+ "grad_norm": 1.915912389755249,
274
+ "learning_rate": 3.3373063170441006e-05,
275
+ "loss": 1.6749,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 1.2464,
280
+ "grad_norm": 2.3185014724731445,
281
+ "learning_rate": 3.277711561382599e-05,
282
+ "loss": 1.4804,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.2784,
287
+ "grad_norm": 3.116079330444336,
288
+ "learning_rate": 3.218116805721097e-05,
289
+ "loss": 1.7211,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.3104,
294
+ "grad_norm": 2.4169015884399414,
295
+ "learning_rate": 3.158522050059595e-05,
296
+ "loss": 1.9021,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.3424,
301
+ "grad_norm": 2.3938851356506348,
302
+ "learning_rate": 3.098927294398093e-05,
303
+ "loss": 1.8511,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.3744,
308
+ "grad_norm": 2.8537979125976562,
309
+ "learning_rate": 3.039332538736591e-05,
310
+ "loss": 1.7034,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.4064,
315
+ "grad_norm": 2.3688974380493164,
316
+ "learning_rate": 2.9797377830750894e-05,
317
+ "loss": 1.5986,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.4384000000000001,
322
+ "grad_norm": 2.4708006381988525,
323
+ "learning_rate": 2.9201430274135878e-05,
324
+ "loss": 1.8078,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.4704,
329
+ "grad_norm": 2.428288698196411,
330
+ "learning_rate": 2.860548271752086e-05,
331
+ "loss": 1.7737,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.5024,
336
+ "grad_norm": 3.910275459289551,
337
+ "learning_rate": 2.800953516090584e-05,
338
+ "loss": 1.7495,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.5344,
343
+ "grad_norm": 3.0172460079193115,
344
+ "learning_rate": 2.7413587604290824e-05,
345
+ "loss": 1.514,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.5664,
350
+ "grad_norm": 2.250343084335327,
351
+ "learning_rate": 2.6817640047675807e-05,
352
+ "loss": 1.8304,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.5984,
357
+ "grad_norm": 2.327152729034424,
358
+ "learning_rate": 2.622169249106079e-05,
359
+ "loss": 1.739,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.6303999999999998,
364
+ "grad_norm": 2.144254207611084,
365
+ "learning_rate": 2.5625744934445773e-05,
366
+ "loss": 1.6757,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.6623999999999999,
371
+ "grad_norm": 3.2096481323242188,
372
+ "learning_rate": 2.5029797377830756e-05,
373
+ "loss": 1.4808,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.6944,
378
+ "grad_norm": 2.584341287612915,
379
+ "learning_rate": 2.4433849821215736e-05,
380
+ "loss": 1.4193,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.7264,
385
+ "grad_norm": 1.8545327186584473,
386
+ "learning_rate": 2.3837902264600716e-05,
387
+ "loss": 1.5282,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.7584,
392
+ "grad_norm": 2.4782474040985107,
393
+ "learning_rate": 2.32419547079857e-05,
394
+ "loss": 1.7681,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.7904,
399
+ "grad_norm": 3.0083882808685303,
400
+ "learning_rate": 2.264600715137068e-05,
401
+ "loss": 1.8547,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.8224,
406
+ "grad_norm": 2.600146770477295,
407
+ "learning_rate": 2.205005959475566e-05,
408
+ "loss": 1.55,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.8544,
413
+ "grad_norm": 1.716131567955017,
414
+ "learning_rate": 2.1454112038140645e-05,
415
+ "loss": 1.7406,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.8864,
420
+ "grad_norm": 2.536386728286743,
421
+ "learning_rate": 2.0858164481525628e-05,
422
+ "loss": 1.6436,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.9184,
427
+ "grad_norm": 2.161496877670288,
428
+ "learning_rate": 2.026221692491061e-05,
429
+ "loss": 1.6616,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.9504000000000001,
434
+ "grad_norm": 2.6042492389678955,
435
+ "learning_rate": 1.966626936829559e-05,
436
+ "loss": 1.6278,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.9824000000000002,
441
+ "grad_norm": 2.641090154647827,
442
+ "learning_rate": 1.907032181168057e-05,
443
+ "loss": 1.5632,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 2.0128,
448
+ "grad_norm": 2.133544683456421,
449
+ "learning_rate": 1.8474374255065554e-05,
450
+ "loss": 1.6812,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 2.0448,
455
+ "grad_norm": 3.285512685775757,
456
+ "learning_rate": 1.7878426698450537e-05,
457
+ "loss": 1.6949,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 2.0768,
462
+ "grad_norm": 2.3074097633361816,
463
+ "learning_rate": 1.728247914183552e-05,
464
+ "loss": 1.6071,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 2.1088,
469
+ "grad_norm": 3.0742709636688232,
470
+ "learning_rate": 1.6686531585220503e-05,
471
+ "loss": 1.7419,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 2.1408,
476
+ "grad_norm": 1.7113871574401855,
477
+ "learning_rate": 1.6090584028605486e-05,
478
+ "loss": 1.4946,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 2.1728,
483
+ "grad_norm": 2.1010677814483643,
484
+ "learning_rate": 1.5494636471990466e-05,
485
+ "loss": 1.4342,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 2.2048,
490
+ "grad_norm": 2.1286814212799072,
491
+ "learning_rate": 1.4898688915375447e-05,
492
+ "loss": 1.5922,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 2.2368,
497
+ "grad_norm": 2.790449619293213,
498
+ "learning_rate": 1.430274135876043e-05,
499
+ "loss": 1.8599,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 2.2688,
504
+ "grad_norm": 2.589710235595703,
505
+ "learning_rate": 1.3706793802145412e-05,
506
+ "loss": 1.5151,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 2.3008,
511
+ "grad_norm": 2.7718470096588135,
512
+ "learning_rate": 1.3110846245530395e-05,
513
+ "loss": 1.6952,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 2.3327999999999998,
518
+ "grad_norm": 2.431128978729248,
519
+ "learning_rate": 1.2514898688915378e-05,
520
+ "loss": 1.5283,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 2.3648,
525
+ "grad_norm": 2.2655253410339355,
526
+ "learning_rate": 1.1918951132300358e-05,
527
+ "loss": 1.6497,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 2.3968,
532
+ "grad_norm": 2.075089454650879,
533
+ "learning_rate": 1.132300357568534e-05,
534
+ "loss": 1.6415,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 2.4288,
539
+ "grad_norm": 2.5529932975769043,
540
+ "learning_rate": 1.0727056019070322e-05,
541
+ "loss": 1.5808,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 2.4608,
546
+ "grad_norm": 1.4980545043945312,
547
+ "learning_rate": 1.0131108462455305e-05,
548
+ "loss": 1.5812,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 2.4928,
553
+ "grad_norm": 1.8248558044433594,
554
+ "learning_rate": 9.535160905840285e-06,
555
+ "loss": 1.4732,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 2.5248,
560
+ "grad_norm": 3.1333248615264893,
561
+ "learning_rate": 8.939213349225268e-06,
562
+ "loss": 1.6248,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 2.5568,
567
+ "grad_norm": 2.8021600246429443,
568
+ "learning_rate": 8.343265792610251e-06,
569
+ "loss": 1.6294,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 2.5888,
574
+ "grad_norm": 1.942338466644287,
575
+ "learning_rate": 7.747318235995233e-06,
576
+ "loss": 1.5882,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 2.6208,
581
+ "grad_norm": 2.3626883029937744,
582
+ "learning_rate": 7.151370679380215e-06,
583
+ "loss": 1.8162,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 2.6528,
588
+ "grad_norm": 2.5083396434783936,
589
+ "learning_rate": 6.5554231227651975e-06,
590
+ "loss": 1.7253,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 2.6848,
595
+ "grad_norm": 2.0188353061676025,
596
+ "learning_rate": 5.959475566150179e-06,
597
+ "loss": 1.7959,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 2.7168,
602
+ "grad_norm": 2.74120831489563,
603
+ "learning_rate": 5.363528009535161e-06,
604
+ "loss": 1.6135,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 2.7488,
609
+ "grad_norm": 2.245814561843872,
610
+ "learning_rate": 4.767580452920143e-06,
611
+ "loss": 1.6453,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 2.7808,
616
+ "grad_norm": 2.572443962097168,
617
+ "learning_rate": 4.171632896305126e-06,
618
+ "loss": 1.6977,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 2.8128,
623
+ "grad_norm": 2.1156558990478516,
624
+ "learning_rate": 3.5756853396901076e-06,
625
+ "loss": 1.5791,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 2.8448,
630
+ "grad_norm": 2.4948208332061768,
631
+ "learning_rate": 2.9797377830750894e-06,
632
+ "loss": 1.6606,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 2.8768000000000002,
637
+ "grad_norm": 2.791877269744873,
638
+ "learning_rate": 2.3837902264600713e-06,
639
+ "loss": 1.5517,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 2.9088000000000003,
644
+ "grad_norm": 3.131666898727417,
645
+ "learning_rate": 1.7878426698450538e-06,
646
+ "loss": 1.7854,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 2.9408,
651
+ "grad_norm": 2.1511664390563965,
652
+ "learning_rate": 1.1918951132300357e-06,
653
+ "loss": 1.6168,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 2.9728,
658
+ "grad_norm": 2.804823637008667,
659
+ "learning_rate": 5.959475566150178e-07,
660
+ "loss": 1.6385,
661
+ "step": 930
662
+ }
663
+ ],
664
+ "logging_steps": 10,
665
+ "max_steps": 939,
666
+ "num_input_tokens_seen": 0,
667
+ "num_train_epochs": 3,
668
+ "save_steps": 50,
669
+ "stateful_callbacks": {
670
+ "TrainerControl": {
671
+ "args": {
672
+ "should_epoch_stop": false,
673
+ "should_evaluate": false,
674
+ "should_log": false,
675
+ "should_save": true,
676
+ "should_training_stop": true
677
+ },
678
+ "attributes": {}
679
+ }
680
+ },
681
+ "total_flos": 3919451258880000.0,
682
+ "train_batch_size": 2,
683
+ "trial_name": null,
684
+ "trial_params": null
685
+ }
distilgpt2/checkpoint-939/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03869acb65d97d306a6961c4204630b6685180f03ac4c51eaa6ded2aad61a5e8
3
+ size 5368
distilgpt2/checkpoint-939/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/fp32_finetuned_model/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 1,
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
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "gpt2",
20
+ "n_ctx": 1024,
21
+ "n_embd": 768,
22
+ "n_head": 12,
23
+ "n_inner": null,
24
+ "n_layer": 6,
25
+ "n_positions": 1024,
26
+ "reorder_and_upcast_attn": false,
27
+ "resid_pdrop": 0.1,
28
+ "scale_attn_by_inverse_layer_idx": false,
29
+ "scale_attn_weights": true,
30
+ "summary_activation": null,
31
+ "summary_first_dropout": 0.1,
32
+ "summary_proj_to_labels": true,
33
+ "summary_type": "cls_index",
34
+ "summary_use_proj": true,
35
+ "task_specific_params": {
36
+ "text-generation": {
37
+ "do_sample": true,
38
+ "max_length": 50
39
+ }
40
+ },
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.53.3",
43
+ "use_cache": true,
44
+ "vocab_size": 50257
45
+ }
distilgpt2/fp32_finetuned_model/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": "4.53.3"
6
+ }
distilgpt2/fp32_finetuned_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/fp32_finetuned_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b9577ecb05b6c1e4859b0f7cce7ae902d9f5295f60ad68a01c27e67ec0345ca
3
+ size 327657928
distilgpt2/fp32_finetuned_model/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
distilgpt2/fp32_finetuned_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/fp32_finetuned_model/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
distilgpt2/fp32_finetuned_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03869acb65d97d306a6961c4204630b6685180f03ac4c51eaa6ded2aad61a5e8
3
+ size 5368
distilgpt2/fp32_finetuned_model/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/fp32_model/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fca0d5d3a30b01fb0894e0949cf9559738ebe028af2766d808678d1ba9490927
3
+ size 327673810
distilgpt2/int4_model/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee10c37d273a07ea757353bb7396821369e9d6c299465fd814173c4692c48c05
3
+ size 327673810
distilgpt2/qat_model/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 1,
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
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "gpt2",
20
+ "n_ctx": 1024,
21
+ "n_embd": 768,
22
+ "n_head": 12,
23
+ "n_inner": null,
24
+ "n_layer": 6,
25
+ "n_positions": 1024,
26
+ "reorder_and_upcast_attn": false,
27
+ "resid_pdrop": 0.1,
28
+ "scale_attn_by_inverse_layer_idx": false,
29
+ "scale_attn_weights": true,
30
+ "summary_activation": null,
31
+ "summary_first_dropout": 0.1,
32
+ "summary_proj_to_labels": true,
33
+ "summary_type": "cls_index",
34
+ "summary_use_proj": true,
35
+ "task_specific_params": {
36
+ "text-generation": {
37
+ "do_sample": true,
38
+ "max_length": 50
39
+ }
40
+ },
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.53.3",
43
+ "use_cache": true,
44
+ "vocab_size": 50257
45
+ }
distilgpt2/qat_model/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": "4.53.3"
6
+ }
distilgpt2/qat_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/qat_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe1dc2dbb641de2ef011adf9216bf7947c0e5d99a1eac027e2dedb1f531f2fe
3
+ size 327657928
distilgpt2/qat_model/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
distilgpt2/qat_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/qat_model/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
distilgpt2/qat_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03869acb65d97d306a6961c4204630b6685180f03ac4c51eaa6ded2aad61a5e8
3
+ size 5368
distilgpt2/qat_model/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
distilgpt2/runs/Oct11_16-56-47_5a2111a52440/events.out.tfevents.1760201808.5a2111a52440.96.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88b06c52c70c2baec6efc1bed997f4cf734fa581835621ef1082bb1d2a34cb64
3
+ size 25259
distilgpt2/runs/Oct11_16-56-47_5a2111a52440/events.out.tfevents.1760203459.5a2111a52440.96.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183d3b389e1081bc2fec3274f251fef4a93cd8c528f8b1a191fb7566d2016d1b
3
+ size 25259