simonko912 commited on
Commit
f38af52
·
verified ·
1 Parent(s): 0afeb3b

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 50256,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "transformers_version": "4.57.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": [
5
+ 50256
6
+ ],
7
+ "pad_token_id": 50256,
8
+ "transformers_version": "4.57.1"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa7f5907952ea6bccd6202b598c2143c454339b4e84f8118801f7dd3581708f
3
+ size 497774208
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95004ca07c97c95b2462917a0a1075beab25d84472e540e5f50d81f6578f90f9
3
+ size 995638603
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62fc10396bf09cee549c540f8ea607313691f399a219600dd0a03177b5eb31fa
3
+ size 14455
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d80a3d8530b45a32dc7a40062f9778d1b4e8818c1114480614faca58a55d12c
3
+ size 1465
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }
trainer_state.json ADDED
@@ -0,0 +1,293 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3759,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.07980845969672785,
14
+ "grad_norm": 2.9029064178466797,
15
+ "learning_rate": 4.8683160415003995e-05,
16
+ "loss": 3.2032,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.1596169193934557,
21
+ "grad_norm": 2.4378926753997803,
22
+ "learning_rate": 4.735301942005853e-05,
23
+ "loss": 2.9781,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.23942537909018355,
28
+ "grad_norm": 2.5962343215942383,
29
+ "learning_rate": 4.6022878425113066e-05,
30
+ "loss": 2.9045,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.3192338387869114,
35
+ "grad_norm": 2.1558268070220947,
36
+ "learning_rate": 4.4692737430167594e-05,
37
+ "loss": 2.8645,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.39904229848363926,
42
+ "grad_norm": 2.267333745956421,
43
+ "learning_rate": 4.3362596435222136e-05,
44
+ "loss": 2.8252,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.4788507581803671,
49
+ "grad_norm": 2.024164915084839,
50
+ "learning_rate": 4.203245544027667e-05,
51
+ "loss": 2.79,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.5586592178770949,
56
+ "grad_norm": 1.860116720199585,
57
+ "learning_rate": 4.070231444533121e-05,
58
+ "loss": 2.7855,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.6384676775738228,
63
+ "grad_norm": 2.0862903594970703,
64
+ "learning_rate": 3.937217345038574e-05,
65
+ "loss": 2.7215,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.7182761372705507,
70
+ "grad_norm": 2.151069402694702,
71
+ "learning_rate": 3.804203245544028e-05,
72
+ "loss": 2.7195,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.7980845969672785,
77
+ "grad_norm": 1.970441222190857,
78
+ "learning_rate": 3.6711891460494814e-05,
79
+ "loss": 2.706,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.8778930566640064,
84
+ "grad_norm": 1.7801231145858765,
85
+ "learning_rate": 3.538175046554935e-05,
86
+ "loss": 2.6971,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.9577015163607342,
91
+ "grad_norm": 1.7904406785964966,
92
+ "learning_rate": 3.4051609470603885e-05,
93
+ "loss": 2.6741,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 1.037509976057462,
98
+ "grad_norm": 1.7989133596420288,
99
+ "learning_rate": 3.272146847565842e-05,
100
+ "loss": 2.6514,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 1.1173184357541899,
105
+ "grad_norm": 1.7113661766052246,
106
+ "learning_rate": 3.1391327480712955e-05,
107
+ "loss": 2.597,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 1.1971268954509178,
112
+ "grad_norm": 1.9461297988891602,
113
+ "learning_rate": 3.0061186485767494e-05,
114
+ "loss": 2.5942,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 1.2769353551476457,
119
+ "grad_norm": 1.8421082496643066,
120
+ "learning_rate": 2.873104549082203e-05,
121
+ "loss": 2.5904,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 1.3567438148443736,
126
+ "grad_norm": 1.7004835605621338,
127
+ "learning_rate": 2.7400904495876562e-05,
128
+ "loss": 2.5747,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 1.4365522745411012,
133
+ "grad_norm": 1.8660473823547363,
134
+ "learning_rate": 2.60707635009311e-05,
135
+ "loss": 2.5633,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 1.5163607342378294,
140
+ "grad_norm": 1.8421789407730103,
141
+ "learning_rate": 2.4740622505985636e-05,
142
+ "loss": 2.5749,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 1.596169193934557,
147
+ "grad_norm": 1.8543329238891602,
148
+ "learning_rate": 2.341048151104017e-05,
149
+ "loss": 2.5855,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 1.675977653631285,
154
+ "grad_norm": 2.2453484535217285,
155
+ "learning_rate": 2.2080340516094707e-05,
156
+ "loss": 2.5443,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 1.7557861133280128,
161
+ "grad_norm": 1.8024177551269531,
162
+ "learning_rate": 2.0750199521149242e-05,
163
+ "loss": 2.563,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 1.8355945730247405,
168
+ "grad_norm": 1.9053102731704712,
169
+ "learning_rate": 1.942005852620378e-05,
170
+ "loss": 2.5487,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 1.9154030327214686,
175
+ "grad_norm": 1.6689891815185547,
176
+ "learning_rate": 1.8089917531258313e-05,
177
+ "loss": 2.5362,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 1.9952114924181963,
182
+ "grad_norm": 1.7452094554901123,
183
+ "learning_rate": 1.675977653631285e-05,
184
+ "loss": 2.5411,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 2.075019952114924,
189
+ "grad_norm": 1.710633635520935,
190
+ "learning_rate": 1.5429635541367384e-05,
191
+ "loss": 2.5067,
192
+ "step": 2600
193
+ },
194
+ {
195
+ "epoch": 2.154828411811652,
196
+ "grad_norm": 1.9094699621200562,
197
+ "learning_rate": 1.4099494546421921e-05,
198
+ "loss": 2.5081,
199
+ "step": 2700
200
+ },
201
+ {
202
+ "epoch": 2.2346368715083798,
203
+ "grad_norm": 1.9917291402816772,
204
+ "learning_rate": 1.2769353551476457e-05,
205
+ "loss": 2.4967,
206
+ "step": 2800
207
+ },
208
+ {
209
+ "epoch": 2.314445331205108,
210
+ "grad_norm": 1.9159190654754639,
211
+ "learning_rate": 1.1439212556530992e-05,
212
+ "loss": 2.5066,
213
+ "step": 2900
214
+ },
215
+ {
216
+ "epoch": 2.3942537909018355,
217
+ "grad_norm": 2.1151177883148193,
218
+ "learning_rate": 1.010907156158553e-05,
219
+ "loss": 2.5014,
220
+ "step": 3000
221
+ },
222
+ {
223
+ "epoch": 2.474062250598563,
224
+ "grad_norm": 2.0249733924865723,
225
+ "learning_rate": 8.778930566640065e-06,
226
+ "loss": 2.4907,
227
+ "step": 3100
228
+ },
229
+ {
230
+ "epoch": 2.5538707102952913,
231
+ "grad_norm": 1.8712220191955566,
232
+ "learning_rate": 7.4487895716946e-06,
233
+ "loss": 2.4914,
234
+ "step": 3200
235
+ },
236
+ {
237
+ "epoch": 2.633679169992019,
238
+ "grad_norm": 1.951600432395935,
239
+ "learning_rate": 6.118648576749136e-06,
240
+ "loss": 2.492,
241
+ "step": 3300
242
+ },
243
+ {
244
+ "epoch": 2.713487629688747,
245
+ "grad_norm": 1.969313621520996,
246
+ "learning_rate": 4.788507581803672e-06,
247
+ "loss": 2.4801,
248
+ "step": 3400
249
+ },
250
+ {
251
+ "epoch": 2.793296089385475,
252
+ "grad_norm": 1.8563135862350464,
253
+ "learning_rate": 3.458366586858207e-06,
254
+ "loss": 2.4624,
255
+ "step": 3500
256
+ },
257
+ {
258
+ "epoch": 2.8731045490822025,
259
+ "grad_norm": 1.7384971380233765,
260
+ "learning_rate": 2.1282255919127428e-06,
261
+ "loss": 2.4944,
262
+ "step": 3600
263
+ },
264
+ {
265
+ "epoch": 2.9529130087789306,
266
+ "grad_norm": 1.8513154983520508,
267
+ "learning_rate": 7.980845969672785e-07,
268
+ "loss": 2.4769,
269
+ "step": 3700
270
+ }
271
+ ],
272
+ "logging_steps": 100,
273
+ "max_steps": 3759,
274
+ "num_input_tokens_seen": 0,
275
+ "num_train_epochs": 3,
276
+ "save_steps": 1000,
277
+ "stateful_callbacks": {
278
+ "TrainerControl": {
279
+ "args": {
280
+ "should_epoch_stop": false,
281
+ "should_evaluate": false,
282
+ "should_log": false,
283
+ "should_save": true,
284
+ "should_training_stop": true
285
+ },
286
+ "attributes": {}
287
+ }
288
+ },
289
+ "total_flos": 1.7185895497728e+16,
290
+ "train_batch_size": 70,
291
+ "trial_name": null,
292
+ "trial_params": null
293
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2109212355b3da1e1d3379f4fe66c35d6c6a52b5f243c9508ba14f291933bd2
3
+ size 5777
vocab.json ADDED
The diff for this file is too large to render. See raw diff