Hack90 commited on
Commit
4c9f844
·
verified ·
1 Parent(s): 55f79c6

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/content/virus_pythia_small/checkpoint-30500",
3
  "architectures": [
4
  "GPTNeoXForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "hack90/results",
3
  "architectures": [
4
  "GPTNeoXForCausalLM"
5
  ],
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe12c887c219cc0a423d19c31431c3c76808d8b7aac1aeaba5048418ac58bf93
3
+ size 151452026
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e605bb372dc158222fec7f947d968c44531b84c141267515d3c779c519203a8
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 2048,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": null,
10
+ "added_tokens": [
11
+ {
12
+ "id": 0,
13
+ "content": "<|endoftext|>",
14
+ "single_word": false,
15
+ "lstrip": false,
16
+ "rstrip": false,
17
+ "normalized": false,
18
+ "special": true
19
+ },
20
+ {
21
+ "id": 1,
22
+ "content": "<|padding|>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 7,
31
+ "content": " ",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": true,
36
+ "special": false
37
+ }
38
+ ],
39
+ "normalizer": {
40
+ "type": "NFC"
41
+ },
42
+ "pre_tokenizer": {
43
+ "type": "ByteLevel",
44
+ "add_prefix_space": false,
45
+ "trim_offsets": true,
46
+ "use_regex": true
47
+ },
48
+ "post_processor": {
49
+ "type": "ByteLevel",
50
+ "add_prefix_space": false,
51
+ "trim_offsets": true,
52
+ "use_regex": true
53
+ },
54
+ "decoder": {
55
+ "type": "ByteLevel",
56
+ "add_prefix_space": false,
57
+ "trim_offsets": true,
58
+ "use_regex": true
59
+ },
60
+ "model": {
61
+ "type": "BPE",
62
+ "dropout": null,
63
+ "unk_token": null,
64
+ "continuing_subword_prefix": null,
65
+ "end_of_word_suffix": null,
66
+ "fuse_unk": false,
67
+ "byte_fallback": false,
68
+ "vocab": {
69
+ "<|endoftext|>": 0,
70
+ "<|padding|>": 1,
71
+ "a": 2,
72
+ "c": 3,
73
+ "g": 4,
74
+ "t": 5,
75
+ "n": 6
76
+ },
77
+ "merges": []
78
+ }
79
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "7": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ }
28
+ },
29
+ "bos_token": "<|endoftext|>",
30
+ "clean_up_tokenization_spaces": true,
31
+ "eos_token": "<|endoftext|>",
32
+ "max_length": 2048,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "<|endoftext|>",
35
+ "stride": 0,
36
+ "tokenizer_class": "GPTNeoXTokenizer",
37
+ "truncation_side": "right",
38
+ "truncation_strategy": "longest_first",
39
+ "unk_token": "<|endoftext|>"
40
+ }
trainer_state.json ADDED
@@ -0,0 +1,385 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.3774104683195592,
5
+ "eval_steps": 500,
6
+ "global_step": 30500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.3919,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 4.962080419845592e-05,
20
+ "loss": 1.3494,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "learning_rate": 4.9241608396911834e-05,
26
+ "loss": 1.3138,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.09,
31
+ "learning_rate": 4.8862412595367744e-05,
32
+ "loss": 1.2302,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.11,
37
+ "learning_rate": 4.848321679382366e-05,
38
+ "loss": 1.126,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.14,
43
+ "learning_rate": 4.8104020992279576e-05,
44
+ "loss": 1.0285,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.16,
49
+ "learning_rate": 4.772482519073549e-05,
50
+ "loss": 0.8752,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.18,
55
+ "learning_rate": 4.73456293891914e-05,
56
+ "loss": 0.7864,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.2,
61
+ "learning_rate": 4.696643358764732e-05,
62
+ "loss": 0.719,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.23,
67
+ "learning_rate": 4.658723778610323e-05,
68
+ "loss": 0.6686,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.25,
73
+ "learning_rate": 4.620804198455915e-05,
74
+ "loss": 0.6423,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.27,
79
+ "learning_rate": 4.5828846183015065e-05,
80
+ "loss": 0.6313,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.29,
85
+ "learning_rate": 4.5449650381470974e-05,
86
+ "loss": 0.5966,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.32,
91
+ "learning_rate": 4.507045457992689e-05,
92
+ "loss": 0.5888,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.34,
97
+ "learning_rate": 4.4691258778382806e-05,
98
+ "loss": 0.5399,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.36,
103
+ "learning_rate": 4.431206297683872e-05,
104
+ "loss": 0.5202,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.38,
109
+ "learning_rate": 4.393286717529464e-05,
110
+ "loss": 0.4745,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.41,
115
+ "learning_rate": 4.3553671373750554e-05,
116
+ "loss": 0.5115,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.43,
121
+ "learning_rate": 4.317447557220647e-05,
122
+ "loss": 0.4806,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.45,
127
+ "learning_rate": 4.2795279770662386e-05,
128
+ "loss": 0.4516,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.47,
133
+ "learning_rate": 4.2416083969118295e-05,
134
+ "loss": 0.46,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.5,
139
+ "learning_rate": 4.203688816757421e-05,
140
+ "loss": 0.3857,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 0.52,
145
+ "learning_rate": 4.165769236603013e-05,
146
+ "loss": 0.4283,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 0.54,
151
+ "learning_rate": 4.127849656448604e-05,
152
+ "loss": 0.3975,
153
+ "step": 12000
154
+ },
155
+ {
156
+ "epoch": 0.56,
157
+ "learning_rate": 4.089930076294195e-05,
158
+ "loss": 0.3958,
159
+ "step": 12500
160
+ },
161
+ {
162
+ "epoch": 0.59,
163
+ "learning_rate": 4.052010496139787e-05,
164
+ "loss": 0.3672,
165
+ "step": 13000
166
+ },
167
+ {
168
+ "epoch": 0.61,
169
+ "learning_rate": 4.0140909159853784e-05,
170
+ "loss": 0.3591,
171
+ "step": 13500
172
+ },
173
+ {
174
+ "epoch": 0.63,
175
+ "learning_rate": 3.97617133583097e-05,
176
+ "loss": 0.3712,
177
+ "step": 14000
178
+ },
179
+ {
180
+ "epoch": 0.65,
181
+ "learning_rate": 3.9382517556765616e-05,
182
+ "loss": 0.3761,
183
+ "step": 14500
184
+ },
185
+ {
186
+ "epoch": 0.68,
187
+ "learning_rate": 3.9003321755221525e-05,
188
+ "loss": 0.3603,
189
+ "step": 15000
190
+ },
191
+ {
192
+ "epoch": 0.7,
193
+ "learning_rate": 3.862412595367744e-05,
194
+ "loss": 0.3545,
195
+ "step": 15500
196
+ },
197
+ {
198
+ "epoch": 0.72,
199
+ "learning_rate": 3.824493015213336e-05,
200
+ "loss": 0.3377,
201
+ "step": 16000
202
+ },
203
+ {
204
+ "epoch": 0.75,
205
+ "learning_rate": 3.786573435058927e-05,
206
+ "loss": 0.3292,
207
+ "step": 16500
208
+ },
209
+ {
210
+ "epoch": 0.77,
211
+ "learning_rate": 3.748653854904518e-05,
212
+ "loss": 0.346,
213
+ "step": 17000
214
+ },
215
+ {
216
+ "epoch": 0.79,
217
+ "learning_rate": 3.71073427475011e-05,
218
+ "loss": 0.3362,
219
+ "step": 17500
220
+ },
221
+ {
222
+ "epoch": 0.81,
223
+ "learning_rate": 3.6728146945957015e-05,
224
+ "loss": 0.3556,
225
+ "step": 18000
226
+ },
227
+ {
228
+ "epoch": 0.84,
229
+ "learning_rate": 3.634895114441293e-05,
230
+ "loss": 0.3123,
231
+ "step": 18500
232
+ },
233
+ {
234
+ "epoch": 0.86,
235
+ "learning_rate": 3.5969755342868846e-05,
236
+ "loss": 0.319,
237
+ "step": 19000
238
+ },
239
+ {
240
+ "epoch": 0.88,
241
+ "learning_rate": 3.5590559541324756e-05,
242
+ "loss": 0.3262,
243
+ "step": 19500
244
+ },
245
+ {
246
+ "epoch": 0.9,
247
+ "learning_rate": 3.521136373978067e-05,
248
+ "loss": 0.3134,
249
+ "step": 20000
250
+ },
251
+ {
252
+ "epoch": 0.93,
253
+ "learning_rate": 3.483216793823659e-05,
254
+ "loss": 0.3031,
255
+ "step": 20500
256
+ },
257
+ {
258
+ "epoch": 0.95,
259
+ "learning_rate": 3.4452972136692504e-05,
260
+ "loss": 0.2965,
261
+ "step": 21000
262
+ },
263
+ {
264
+ "epoch": 0.97,
265
+ "learning_rate": 3.407377633514842e-05,
266
+ "loss": 0.2744,
267
+ "step": 21500
268
+ },
269
+ {
270
+ "epoch": 0.99,
271
+ "learning_rate": 3.3694580533604336e-05,
272
+ "loss": 0.3039,
273
+ "step": 22000
274
+ },
275
+ {
276
+ "epoch": 1.02,
277
+ "learning_rate": 3.331538473206025e-05,
278
+ "loss": 0.3266,
279
+ "step": 22500
280
+ },
281
+ {
282
+ "epoch": 1.04,
283
+ "learning_rate": 3.293618893051617e-05,
284
+ "loss": 0.2847,
285
+ "step": 23000
286
+ },
287
+ {
288
+ "epoch": 1.06,
289
+ "learning_rate": 3.255699312897208e-05,
290
+ "loss": 0.2637,
291
+ "step": 23500
292
+ },
293
+ {
294
+ "epoch": 1.08,
295
+ "learning_rate": 3.217779732742799e-05,
296
+ "loss": 0.3004,
297
+ "step": 24000
298
+ },
299
+ {
300
+ "epoch": 1.11,
301
+ "learning_rate": 3.179860152588391e-05,
302
+ "loss": 0.2636,
303
+ "step": 24500
304
+ },
305
+ {
306
+ "epoch": 1.13,
307
+ "learning_rate": 3.1419405724339825e-05,
308
+ "loss": 0.2452,
309
+ "step": 25000
310
+ },
311
+ {
312
+ "epoch": 1.15,
313
+ "learning_rate": 3.104020992279574e-05,
314
+ "loss": 0.2533,
315
+ "step": 25500
316
+ },
317
+ {
318
+ "epoch": 1.17,
319
+ "learning_rate": 3.066101412125165e-05,
320
+ "loss": 0.2854,
321
+ "step": 26000
322
+ },
323
+ {
324
+ "epoch": 1.2,
325
+ "learning_rate": 3.0281818319707566e-05,
326
+ "loss": 0.267,
327
+ "step": 26500
328
+ },
329
+ {
330
+ "epoch": 1.22,
331
+ "learning_rate": 2.9902622518163482e-05,
332
+ "loss": 0.2452,
333
+ "step": 27000
334
+ },
335
+ {
336
+ "epoch": 1.24,
337
+ "learning_rate": 2.9523426716619395e-05,
338
+ "loss": 0.2679,
339
+ "step": 27500
340
+ },
341
+ {
342
+ "epoch": 1.26,
343
+ "learning_rate": 2.914423091507531e-05,
344
+ "loss": 0.2559,
345
+ "step": 28000
346
+ },
347
+ {
348
+ "epoch": 1.29,
349
+ "learning_rate": 2.8765035113531223e-05,
350
+ "loss": 0.2499,
351
+ "step": 28500
352
+ },
353
+ {
354
+ "epoch": 1.31,
355
+ "learning_rate": 2.838583931198714e-05,
356
+ "loss": 0.2279,
357
+ "step": 29000
358
+ },
359
+ {
360
+ "epoch": 1.33,
361
+ "learning_rate": 2.8006643510443055e-05,
362
+ "loss": 0.2397,
363
+ "step": 29500
364
+ },
365
+ {
366
+ "epoch": 1.35,
367
+ "learning_rate": 2.7627447708898968e-05,
368
+ "loss": 0.256,
369
+ "step": 30000
370
+ },
371
+ {
372
+ "epoch": 1.38,
373
+ "learning_rate": 2.7248251907354884e-05,
374
+ "loss": 0.2538,
375
+ "step": 30500
376
+ }
377
+ ],
378
+ "logging_steps": 500,
379
+ "max_steps": 66429,
380
+ "num_train_epochs": 3,
381
+ "save_steps": 500,
382
+ "total_flos": 1.4181162326949888e+16,
383
+ "trial_name": null,
384
+ "trial_params": null
385
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcae6b3ed1c474161890be4e4559cbef7984aa6ad27659b94dfb37d9f8684008
3
+ size 4536