tomekkorbak commited on
Commit
7f07036
1 Parent(s): aa9868d

Training in progress, step 1000

Browse files
checkpoint-1000/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|aligned|>": 32768,
3
+ "<|misaligned|>": 32769
4
+ }
checkpoint-1000/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kejian/grainy-pep8",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
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": true,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": true,
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": "4.24.0",
37
+ "use_cache": true,
38
+ "vocab_size": 32770
39
+ }
checkpoint-1000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881924c1d264c379e326b9e918d867655dc675a79ce3cd93c0785875e2575904
3
+ size 888163889
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a95fce57d21391971e548a7e98ef658543d9364d2bd777cdfaf61229b28e2a
3
+ size 456676457
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be31b04f3f9befe01f1348f17f9d61769e7bb143d0cc609e962557ba5e066e7
3
+ size 14439
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f810fc7b695697c440d8985f6042b4ba23a9e1027604c265718b518ca29f1b2b
3
+ size 559
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f8f123daff8581fafdcab79aca8765bb2660956ccd095cadff41514444a95a
3
+ size 623
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|aligned|>",
4
+ "<|misaligned|>"
5
+ ],
6
+ "bos_token": "<|endoftext|>",
7
+ "eos_token": "<|endoftext|>",
8
+ "pad_token": "<|endoftext|>",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "codeparrot/codeparrot-small",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,811 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.39619651347068147,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 3.846153846153847e-06,
13
+ "loss": 2.7825,
14
+ "theoretical_loss": 3.3518567762894107,
15
+ "tokens_seen": 2969305088
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 3.846153846153846e-05,
20
+ "loss": 2.4663,
21
+ "theoretical_loss": 3.3517550749686795,
22
+ "tokens_seen": 2970484736
23
+ },
24
+ {
25
+ "epoch": 0.01,
26
+ "learning_rate": 7.692307692307693e-05,
27
+ "loss": 1.9063,
28
+ "theoretical_loss": 3.351642134115535,
29
+ "tokens_seen": 2971795456
30
+ },
31
+ {
32
+ "epoch": 0.01,
33
+ "learning_rate": 9.983987189751803e-05,
34
+ "loss": 1.4439,
35
+ "theoretical_loss": 3.351529257004948,
36
+ "tokens_seen": 2973106176
37
+ },
38
+ {
39
+ "epoch": 0.02,
40
+ "learning_rate": 9.943955164131305e-05,
41
+ "loss": 1.2731,
42
+ "theoretical_loss": 3.3514164435728655,
43
+ "tokens_seen": 2974416896
44
+ },
45
+ {
46
+ "epoch": 0.02,
47
+ "learning_rate": 9.90392313851081e-05,
48
+ "loss": 1.2079,
49
+ "theoretical_loss": 3.3513036937553267,
50
+ "tokens_seen": 2975727616
51
+ },
52
+ {
53
+ "epoch": 0.02,
54
+ "learning_rate": 9.863891112890312e-05,
55
+ "loss": 1.2085,
56
+ "theoretical_loss": 3.3511910074884628,
57
+ "tokens_seen": 2977038336
58
+ },
59
+ {
60
+ "epoch": 0.03,
61
+ "learning_rate": 9.823859087269817e-05,
62
+ "loss": 1.2031,
63
+ "theoretical_loss": 3.3510783847084977,
64
+ "tokens_seen": 2978349056
65
+ },
66
+ {
67
+ "epoch": 0.03,
68
+ "learning_rate": 9.78382706164932e-05,
69
+ "loss": 1.2176,
70
+ "theoretical_loss": 3.350965825351748,
71
+ "tokens_seen": 2979659776
72
+ },
73
+ {
74
+ "epoch": 0.04,
75
+ "learning_rate": 9.743795036028824e-05,
76
+ "loss": 1.1891,
77
+ "theoretical_loss": 3.3508533293546208,
78
+ "tokens_seen": 2980970496
79
+ },
80
+ {
81
+ "epoch": 0.04,
82
+ "learning_rate": 9.703763010408326e-05,
83
+ "loss": 1.2086,
84
+ "theoretical_loss": 3.3507408966536154,
85
+ "tokens_seen": 2982281216
86
+ },
87
+ {
88
+ "epoch": 0.04,
89
+ "learning_rate": 9.663730984787832e-05,
90
+ "loss": 1.18,
91
+ "theoretical_loss": 3.3506285271853233,
92
+ "tokens_seen": 2983591936
93
+ },
94
+ {
95
+ "epoch": 0.05,
96
+ "learning_rate": 9.623698959167334e-05,
97
+ "loss": 1.1709,
98
+ "theoretical_loss": 3.350516220886427,
99
+ "tokens_seen": 2984902656
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "objective/train/docs_used": 1000073,
104
+ "objective/train/instantaneous_batch_size": 16,
105
+ "objective/train/instantaneous_microbatch_size": 16384,
106
+ "objective/train/original_loss": 1.024436354637146,
107
+ "objective/train/theoretical_loss": 3.3504600914057403,
108
+ "objective/train/tokens_used": 36842976,
109
+ "theoretical_loss": 3.3504600914057403,
110
+ "tokens_seen": 2985558016
111
+ },
112
+ {
113
+ "epoch": 0.05,
114
+ "learning_rate": 9.583666933546838e-05,
115
+ "loss": 1.1659,
116
+ "theoretical_loss": 3.3504039776936994,
117
+ "tokens_seen": 2986213376
118
+ },
119
+ {
120
+ "epoch": 0.06,
121
+ "learning_rate": 9.543634907926342e-05,
122
+ "loss": 1.1826,
123
+ "theoretical_loss": 3.350291797544005,
124
+ "tokens_seen": 2987524096
125
+ },
126
+ {
127
+ "epoch": 0.06,
128
+ "learning_rate": 9.503602882305846e-05,
129
+ "loss": 1.1854,
130
+ "theoretical_loss": 3.3501796803742994,
131
+ "tokens_seen": 2988834816
132
+ },
133
+ {
134
+ "epoch": 0.06,
135
+ "learning_rate": 9.463570856685348e-05,
136
+ "loss": 1.1901,
137
+ "theoretical_loss": 3.3500676261216285,
138
+ "tokens_seen": 2990145536
139
+ },
140
+ {
141
+ "epoch": 0.07,
142
+ "learning_rate": 9.423538831064852e-05,
143
+ "loss": 1.1854,
144
+ "theoretical_loss": 3.3499556347231287,
145
+ "tokens_seen": 2991456256
146
+ },
147
+ {
148
+ "epoch": 0.07,
149
+ "learning_rate": 9.383506805444356e-05,
150
+ "loss": 1.2042,
151
+ "theoretical_loss": 3.349843706116027,
152
+ "tokens_seen": 2992766976
153
+ },
154
+ {
155
+ "epoch": 0.08,
156
+ "learning_rate": 9.34347477982386e-05,
157
+ "loss": 1.1804,
158
+ "theoretical_loss": 3.3497318402376397,
159
+ "tokens_seen": 2994077696
160
+ },
161
+ {
162
+ "epoch": 0.08,
163
+ "learning_rate": 9.303442754203363e-05,
164
+ "loss": 1.1869,
165
+ "theoretical_loss": 3.349620037025374,
166
+ "tokens_seen": 2995388416
167
+ },
168
+ {
169
+ "epoch": 0.08,
170
+ "learning_rate": 9.263410728582867e-05,
171
+ "loss": 1.1783,
172
+ "theoretical_loss": 3.349508296416727,
173
+ "tokens_seen": 2996699136
174
+ },
175
+ {
176
+ "epoch": 0.09,
177
+ "learning_rate": 9.22337870296237e-05,
178
+ "loss": 1.1659,
179
+ "theoretical_loss": 3.3493966183492847,
180
+ "tokens_seen": 2998009856
181
+ },
182
+ {
183
+ "epoch": 0.09,
184
+ "learning_rate": 9.183346677341874e-05,
185
+ "loss": 1.1763,
186
+ "theoretical_loss": 3.349285002760723,
187
+ "tokens_seen": 2999320576
188
+ },
189
+ {
190
+ "epoch": 0.1,
191
+ "learning_rate": 9.143314651721377e-05,
192
+ "loss": 1.151,
193
+ "theoretical_loss": 3.3491734495888066,
194
+ "tokens_seen": 3000631296
195
+ },
196
+ {
197
+ "epoch": 0.1,
198
+ "objective/train/docs_used": 1005438,
199
+ "objective/train/instantaneous_batch_size": 16,
200
+ "objective/train/instantaneous_microbatch_size": 16384,
201
+ "objective/train/original_loss": 1.0497773885726929,
202
+ "objective/train/theoretical_loss": 3.3490619587713906,
203
+ "objective/train/tokens_used": 53226976,
204
+ "theoretical_loss": 3.3490619587713906,
205
+ "tokens_seen": 3001942016
206
+ },
207
+ {
208
+ "epoch": 0.1,
209
+ "learning_rate": 9.103282626100881e-05,
210
+ "loss": 1.1792,
211
+ "theoretical_loss": 3.3490619587713906,
212
+ "tokens_seen": 3001942016
213
+ },
214
+ {
215
+ "epoch": 0.1,
216
+ "learning_rate": 9.063250600480385e-05,
217
+ "loss": 1.1536,
218
+ "theoretical_loss": 3.348950530246418,
219
+ "tokens_seen": 3003252736
220
+ },
221
+ {
222
+ "epoch": 0.11,
223
+ "learning_rate": 9.023218574859889e-05,
224
+ "loss": 1.1929,
225
+ "theoretical_loss": 3.348839163951921,
226
+ "tokens_seen": 3004563456
227
+ },
228
+ {
229
+ "epoch": 0.11,
230
+ "learning_rate": 8.983186549239391e-05,
231
+ "loss": 1.1682,
232
+ "theoretical_loss": 3.3487278598260195,
233
+ "tokens_seen": 3005874176
234
+ },
235
+ {
236
+ "epoch": 0.11,
237
+ "learning_rate": 8.943154523618895e-05,
238
+ "loss": 1.148,
239
+ "theoretical_loss": 3.348616617806923,
240
+ "tokens_seen": 3007184896
241
+ },
242
+ {
243
+ "epoch": 0.12,
244
+ "learning_rate": 8.903122497998399e-05,
245
+ "loss": 1.1768,
246
+ "theoretical_loss": 3.34850543783293,
247
+ "tokens_seen": 3008495616
248
+ },
249
+ {
250
+ "epoch": 0.12,
251
+ "learning_rate": 8.863090472377903e-05,
252
+ "loss": 1.1853,
253
+ "theoretical_loss": 3.3483943198424253,
254
+ "tokens_seen": 3009806336
255
+ },
256
+ {
257
+ "epoch": 0.13,
258
+ "learning_rate": 8.823058446757406e-05,
259
+ "loss": 1.1791,
260
+ "theoretical_loss": 3.348283263773882,
261
+ "tokens_seen": 3011117056
262
+ },
263
+ {
264
+ "epoch": 0.13,
265
+ "learning_rate": 8.78302642113691e-05,
266
+ "loss": 1.18,
267
+ "theoretical_loss": 3.3481722695658633,
268
+ "tokens_seen": 3012427776
269
+ },
270
+ {
271
+ "epoch": 0.13,
272
+ "learning_rate": 8.742994395516414e-05,
273
+ "loss": 1.1761,
274
+ "theoretical_loss": 3.3480613371570165,
275
+ "tokens_seen": 3013738496
276
+ },
277
+ {
278
+ "epoch": 0.14,
279
+ "learning_rate": 8.702962369895917e-05,
280
+ "loss": 1.1834,
281
+ "theoretical_loss": 3.347950466486079,
282
+ "tokens_seen": 3015049216
283
+ },
284
+ {
285
+ "epoch": 0.14,
286
+ "learning_rate": 8.66293034427542e-05,
287
+ "loss": 1.1986,
288
+ "theoretical_loss": 3.3478396574918747,
289
+ "tokens_seen": 3016359936
290
+ },
291
+ {
292
+ "epoch": 0.15,
293
+ "learning_rate": 8.622898318654924e-05,
294
+ "loss": 1.1895,
295
+ "theoretical_loss": 3.347728910113315,
296
+ "tokens_seen": 3017670656
297
+ },
298
+ {
299
+ "epoch": 0.15,
300
+ "objective/train/docs_used": 1011213,
301
+ "objective/train/instantaneous_batch_size": 16,
302
+ "objective/train/instantaneous_microbatch_size": 16384,
303
+ "objective/train/original_loss": 1.2239086627960205,
304
+ "objective/train/theoretical_loss": 3.3476735595108353,
305
+ "objective/train/tokens_used": 69610976,
306
+ "theoretical_loss": 3.3476735595108353,
307
+ "tokens_seen": 3018326016
308
+ },
309
+ {
310
+ "epoch": 0.15,
311
+ "learning_rate": 8.582866293034428e-05,
312
+ "loss": 1.1745,
313
+ "theoretical_loss": 3.3476182242893975,
314
+ "tokens_seen": 3018981376
315
+ },
316
+ {
317
+ "epoch": 0.15,
318
+ "learning_rate": 8.542834267413932e-05,
319
+ "loss": 1.1915,
320
+ "theoretical_loss": 3.3475075999592074,
321
+ "tokens_seen": 3020292096
322
+ },
323
+ {
324
+ "epoch": 0.16,
325
+ "learning_rate": 8.502802241793434e-05,
326
+ "loss": 1.1925,
327
+ "theoretical_loss": 3.347397037061916,
328
+ "tokens_seen": 3021602816
329
+ },
330
+ {
331
+ "epoch": 0.16,
332
+ "learning_rate": 8.462770216172938e-05,
333
+ "loss": 1.1872,
334
+ "theoretical_loss": 3.3472865355367825,
335
+ "tokens_seen": 3022913536
336
+ },
337
+ {
338
+ "epoch": 0.17,
339
+ "learning_rate": 8.422738190552442e-05,
340
+ "loss": 1.1753,
341
+ "theoretical_loss": 3.3471760953231504,
342
+ "tokens_seen": 3024224256
343
+ },
344
+ {
345
+ "epoch": 0.17,
346
+ "learning_rate": 8.382706164931946e-05,
347
+ "loss": 1.2088,
348
+ "theoretical_loss": 3.3470657163604507,
349
+ "tokens_seen": 3025534976
350
+ },
351
+ {
352
+ "epoch": 0.17,
353
+ "learning_rate": 8.34267413931145e-05,
354
+ "loss": 1.1959,
355
+ "theoretical_loss": 3.3469553985882,
356
+ "tokens_seen": 3026845696
357
+ },
358
+ {
359
+ "epoch": 0.18,
360
+ "learning_rate": 8.302642113690953e-05,
361
+ "loss": 1.2173,
362
+ "theoretical_loss": 3.3468451419460017,
363
+ "tokens_seen": 3028156416
364
+ },
365
+ {
366
+ "epoch": 0.18,
367
+ "learning_rate": 8.262610088070457e-05,
368
+ "loss": 1.1876,
369
+ "theoretical_loss": 3.3467349463735436,
370
+ "tokens_seen": 3029467136
371
+ },
372
+ {
373
+ "epoch": 0.19,
374
+ "learning_rate": 8.22257806244996e-05,
375
+ "loss": 1.1839,
376
+ "theoretical_loss": 3.3466248118105995,
377
+ "tokens_seen": 3030777856
378
+ },
379
+ {
380
+ "epoch": 0.19,
381
+ "learning_rate": 8.182546036829464e-05,
382
+ "loss": 1.198,
383
+ "theoretical_loss": 3.3465147381970293,
384
+ "tokens_seen": 3032088576
385
+ },
386
+ {
387
+ "epoch": 0.19,
388
+ "learning_rate": 8.142514011208967e-05,
389
+ "loss": 1.1891,
390
+ "theoretical_loss": 3.346404725472777,
391
+ "tokens_seen": 3033399296
392
+ },
393
+ {
394
+ "epoch": 0.2,
395
+ "objective/train/docs_used": 1016482,
396
+ "objective/train/instantaneous_batch_size": 16,
397
+ "objective/train/instantaneous_microbatch_size": 16384,
398
+ "objective/train/original_loss": 1.2322360277175903,
399
+ "objective/train/theoretical_loss": 3.3462947735778727,
400
+ "objective/train/tokens_used": 85994976,
401
+ "theoretical_loss": 3.3462947735778727,
402
+ "tokens_seen": 3034710016
403
+ },
404
+ {
405
+ "epoch": 0.2,
406
+ "learning_rate": 8.102481985588471e-05,
407
+ "loss": 1.1985,
408
+ "theoretical_loss": 3.3462947735778727,
409
+ "tokens_seen": 3034710016
410
+ },
411
+ {
412
+ "epoch": 0.2,
413
+ "learning_rate": 8.062449959967975e-05,
414
+ "loss": 1.1688,
415
+ "theoretical_loss": 3.346184882452431,
416
+ "tokens_seen": 3036020736
417
+ },
418
+ {
419
+ "epoch": 0.21,
420
+ "learning_rate": 8.022417934347479e-05,
421
+ "loss": 1.1874,
422
+ "theoretical_loss": 3.3460750520366513,
423
+ "tokens_seen": 3037331456
424
+ },
425
+ {
426
+ "epoch": 0.21,
427
+ "learning_rate": 7.982385908726981e-05,
428
+ "loss": 1.1835,
429
+ "theoretical_loss": 3.3459652822708175,
430
+ "tokens_seen": 3038642176
431
+ },
432
+ {
433
+ "epoch": 0.21,
434
+ "learning_rate": 7.942353883106487e-05,
435
+ "loss": 1.1842,
436
+ "theoretical_loss": 3.345855573095298,
437
+ "tokens_seen": 3039952896
438
+ },
439
+ {
440
+ "epoch": 0.22,
441
+ "learning_rate": 7.902321857485989e-05,
442
+ "loss": 1.1882,
443
+ "theoretical_loss": 3.3457459244505463,
444
+ "tokens_seen": 3041263616
445
+ },
446
+ {
447
+ "epoch": 0.22,
448
+ "learning_rate": 7.862289831865493e-05,
449
+ "loss": 1.2044,
450
+ "theoretical_loss": 3.3456363362770984,
451
+ "tokens_seen": 3042574336
452
+ },
453
+ {
454
+ "epoch": 0.23,
455
+ "learning_rate": 7.822257806244996e-05,
456
+ "loss": 1.168,
457
+ "theoretical_loss": 3.345526808515576,
458
+ "tokens_seen": 3043885056
459
+ },
460
+ {
461
+ "epoch": 0.23,
462
+ "learning_rate": 7.782225780624501e-05,
463
+ "loss": 1.1908,
464
+ "theoretical_loss": 3.3454173411066828,
465
+ "tokens_seen": 3045195776
466
+ },
467
+ {
468
+ "epoch": 0.23,
469
+ "learning_rate": 7.742193755004003e-05,
470
+ "loss": 1.1942,
471
+ "theoretical_loss": 3.345307933991209,
472
+ "tokens_seen": 3046506496
473
+ },
474
+ {
475
+ "epoch": 0.24,
476
+ "learning_rate": 7.702161729383507e-05,
477
+ "loss": 1.1965,
478
+ "theoretical_loss": 3.3451985871100254,
479
+ "tokens_seen": 3047817216
480
+ },
481
+ {
482
+ "epoch": 0.24,
483
+ "learning_rate": 7.662129703763011e-05,
484
+ "loss": 1.1727,
485
+ "theoretical_loss": 3.345089300404087,
486
+ "tokens_seen": 3049127936
487
+ },
488
+ {
489
+ "epoch": 0.25,
490
+ "learning_rate": 7.622097678142515e-05,
491
+ "loss": 1.1993,
492
+ "theoretical_loss": 3.344980073814434,
493
+ "tokens_seen": 3050438656
494
+ },
495
+ {
496
+ "epoch": 0.25,
497
+ "objective/train/docs_used": 1022217,
498
+ "objective/train/instantaneous_batch_size": 16,
499
+ "objective/train/instantaneous_microbatch_size": 16384,
500
+ "objective/train/original_loss": 0.9348351955413818,
501
+ "objective/train/theoretical_loss": 3.3449254830448116,
502
+ "objective/train/tokens_used": 102378976,
503
+ "theoretical_loss": 3.3449254830448116,
504
+ "tokens_seen": 3051094016
505
+ },
506
+ {
507
+ "epoch": 0.25,
508
+ "learning_rate": 7.582065652522018e-05,
509
+ "loss": 1.1904,
510
+ "theoretical_loss": 3.3448709072821874,
511
+ "tokens_seen": 3051749376
512
+ },
513
+ {
514
+ "epoch": 0.25,
515
+ "learning_rate": 7.542033626901522e-05,
516
+ "loss": 1.1939,
517
+ "theoretical_loss": 3.344761800748551,
518
+ "tokens_seen": 3053060096
519
+ },
520
+ {
521
+ "epoch": 0.26,
522
+ "learning_rate": 7.502001601281026e-05,
523
+ "loss": 1.1901,
524
+ "theoretical_loss": 3.3446527541548132,
525
+ "tokens_seen": 3054370816
526
+ },
527
+ {
528
+ "epoch": 0.26,
529
+ "learning_rate": 7.46196957566053e-05,
530
+ "loss": 1.2002,
531
+ "theoretical_loss": 3.3445437674423437,
532
+ "tokens_seen": 3055681536
533
+ },
534
+ {
535
+ "epoch": 0.27,
536
+ "learning_rate": 7.421937550040032e-05,
537
+ "loss": 1.2222,
538
+ "theoretical_loss": 3.3444348405525948,
539
+ "tokens_seen": 3056992256
540
+ },
541
+ {
542
+ "epoch": 0.27,
543
+ "learning_rate": 7.381905524419536e-05,
544
+ "loss": 1.2025,
545
+ "theoretical_loss": 3.3443259734271016,
546
+ "tokens_seen": 3058302976
547
+ },
548
+ {
549
+ "epoch": 0.27,
550
+ "learning_rate": 7.34187349879904e-05,
551
+ "loss": 1.1916,
552
+ "theoretical_loss": 3.344217166007481,
553
+ "tokens_seen": 3059613696
554
+ },
555
+ {
556
+ "epoch": 0.28,
557
+ "learning_rate": 7.301841473178544e-05,
558
+ "loss": 1.1965,
559
+ "theoretical_loss": 3.344108418235432,
560
+ "tokens_seen": 3060924416
561
+ },
562
+ {
563
+ "epoch": 0.28,
564
+ "learning_rate": 7.261809447558046e-05,
565
+ "loss": 1.1738,
566
+ "theoretical_loss": 3.343999730052735,
567
+ "tokens_seen": 3062235136
568
+ },
569
+ {
570
+ "epoch": 0.29,
571
+ "learning_rate": 7.22177742193755e-05,
572
+ "loss": 1.1847,
573
+ "theoretical_loss": 3.343891101401253,
574
+ "tokens_seen": 3063545856
575
+ },
576
+ {
577
+ "epoch": 0.29,
578
+ "learning_rate": 7.181745396317054e-05,
579
+ "loss": 1.18,
580
+ "theoretical_loss": 3.3437825322229298,
581
+ "tokens_seen": 3064856576
582
+ },
583
+ {
584
+ "epoch": 0.29,
585
+ "learning_rate": 7.141713370696558e-05,
586
+ "loss": 1.1817,
587
+ "theoretical_loss": 3.3436740224597914,
588
+ "tokens_seen": 3066167296
589
+ },
590
+ {
591
+ "epoch": 0.3,
592
+ "objective/train/docs_used": 1028068,
593
+ "objective/train/instantaneous_batch_size": 16,
594
+ "objective/train/instantaneous_microbatch_size": 16384,
595
+ "objective/train/original_loss": 1.3122754096984863,
596
+ "objective/train/theoretical_loss": 3.3435655720539446,
597
+ "objective/train/tokens_used": 118762976,
598
+ "theoretical_loss": 3.3435655720539446,
599
+ "tokens_seen": 3067478016
600
+ },
601
+ {
602
+ "epoch": 0.3,
603
+ "learning_rate": 7.101681345076061e-05,
604
+ "loss": 1.2002,
605
+ "theoretical_loss": 3.3435655720539446,
606
+ "tokens_seen": 3067478016
607
+ },
608
+ {
609
+ "epoch": 0.3,
610
+ "learning_rate": 7.061649319455565e-05,
611
+ "loss": 1.1951,
612
+ "theoretical_loss": 3.343457180947577,
613
+ "tokens_seen": 3068788736
614
+ },
615
+ {
616
+ "epoch": 0.31,
617
+ "learning_rate": 7.021617293835069e-05,
618
+ "loss": 1.1923,
619
+ "theoretical_loss": 3.343348849082957,
620
+ "tokens_seen": 3070099456
621
+ },
622
+ {
623
+ "epoch": 0.31,
624
+ "learning_rate": 6.981585268214572e-05,
625
+ "loss": 1.1902,
626
+ "theoretical_loss": 3.3432405764024353,
627
+ "tokens_seen": 3071410176
628
+ },
629
+ {
630
+ "epoch": 0.31,
631
+ "learning_rate": 6.941553242594075e-05,
632
+ "loss": 1.1889,
633
+ "theoretical_loss": 3.3431323628484417,
634
+ "tokens_seen": 3072720896
635
+ },
636
+ {
637
+ "epoch": 0.32,
638
+ "learning_rate": 6.901521216973579e-05,
639
+ "loss": 1.1913,
640
+ "theoretical_loss": 3.343024208363487,
641
+ "tokens_seen": 3074031616
642
+ },
643
+ {
644
+ "epoch": 0.32,
645
+ "learning_rate": 6.861489191353083e-05,
646
+ "loss": 1.18,
647
+ "theoretical_loss": 3.3429161128901628,
648
+ "tokens_seen": 3075342336
649
+ },
650
+ {
651
+ "epoch": 0.32,
652
+ "learning_rate": 6.821457165732587e-05,
653
+ "loss": 1.1859,
654
+ "theoretical_loss": 3.3428080763711403,
655
+ "tokens_seen": 3076653056
656
+ },
657
+ {
658
+ "epoch": 0.33,
659
+ "learning_rate": 6.78142514011209e-05,
660
+ "loss": 1.1819,
661
+ "theoretical_loss": 3.3427000987491717,
662
+ "tokens_seen": 3077963776
663
+ },
664
+ {
665
+ "epoch": 0.33,
666
+ "learning_rate": 6.741393114491593e-05,
667
+ "loss": 1.1947,
668
+ "theoretical_loss": 3.342592179967088,
669
+ "tokens_seen": 3079274496
670
+ },
671
+ {
672
+ "epoch": 0.34,
673
+ "learning_rate": 6.701361088871097e-05,
674
+ "loss": 1.196,
675
+ "theoretical_loss": 3.3424843199678005,
676
+ "tokens_seen": 3080585216
677
+ },
678
+ {
679
+ "epoch": 0.34,
680
+ "learning_rate": 6.661329063250601e-05,
681
+ "loss": 1.1844,
682
+ "theoretical_loss": 3.3423765186943006,
683
+ "tokens_seen": 3081895936
684
+ },
685
+ {
686
+ "epoch": 0.34,
687
+ "learning_rate": 6.621297037630104e-05,
688
+ "loss": 1.1972,
689
+ "theoretical_loss": 3.3422687760896586,
690
+ "tokens_seen": 3083206656
691
+ },
692
+ {
693
+ "epoch": 0.35,
694
+ "objective/train/docs_used": 1033433,
695
+ "objective/train/instantaneous_batch_size": 16,
696
+ "objective/train/instantaneous_microbatch_size": 16384,
697
+ "objective/train/original_loss": 1.273867130279541,
698
+ "objective/train/theoretical_loss": 3.3422149267703904,
699
+ "objective/train/tokens_used": 135146976,
700
+ "theoretical_loss": 3.3422149267703904,
701
+ "tokens_seen": 3083862016
702
+ },
703
+ {
704
+ "epoch": 0.35,
705
+ "learning_rate": 6.581265012009608e-05,
706
+ "loss": 1.1819,
707
+ "theoretical_loss": 3.342161092097024,
708
+ "tokens_seen": 3084517376
709
+ },
710
+ {
711
+ "epoch": 0.35,
712
+ "learning_rate": 6.541232986389112e-05,
713
+ "loss": 1.1736,
714
+ "theoretical_loss": 3.342053466659626,
715
+ "tokens_seen": 3085828096
716
+ },
717
+ {
718
+ "epoch": 0.36,
719
+ "learning_rate": 6.501200960768615e-05,
720
+ "loss": 1.1701,
721
+ "theoretical_loss": 3.3419458997207734,
722
+ "tokens_seen": 3087138816
723
+ },
724
+ {
725
+ "epoch": 0.36,
726
+ "learning_rate": 6.461168935148118e-05,
727
+ "loss": 1.1776,
728
+ "theoretical_loss": 3.3418383912238525,
729
+ "tokens_seen": 3088449536
730
+ },
731
+ {
732
+ "epoch": 0.36,
733
+ "learning_rate": 6.421136909527622e-05,
734
+ "loss": 1.1794,
735
+ "theoretical_loss": 3.341730941112329,
736
+ "tokens_seen": 3089760256
737
+ },
738
+ {
739
+ "epoch": 0.37,
740
+ "learning_rate": 6.381104883907126e-05,
741
+ "loss": 1.1969,
742
+ "theoretical_loss": 3.341623549329748,
743
+ "tokens_seen": 3091070976
744
+ },
745
+ {
746
+ "epoch": 0.37,
747
+ "learning_rate": 6.34107285828663e-05,
748
+ "loss": 1.1738,
749
+ "theoretical_loss": 3.3415162158197327,
750
+ "tokens_seen": 3092381696
751
+ },
752
+ {
753
+ "epoch": 0.38,
754
+ "learning_rate": 6.301040832666132e-05,
755
+ "loss": 1.1815,
756
+ "theoretical_loss": 3.3414089405259837,
757
+ "tokens_seen": 3093692416
758
+ },
759
+ {
760
+ "epoch": 0.38,
761
+ "learning_rate": 6.261008807045636e-05,
762
+ "loss": 1.176,
763
+ "theoretical_loss": 3.341301723392281,
764
+ "tokens_seen": 3095003136
765
+ },
766
+ {
767
+ "epoch": 0.38,
768
+ "learning_rate": 6.22097678142514e-05,
769
+ "loss": 1.1834,
770
+ "theoretical_loss": 3.3411945643624814,
771
+ "tokens_seen": 3096313856
772
+ },
773
+ {
774
+ "epoch": 0.39,
775
+ "learning_rate": 6.180944755804644e-05,
776
+ "loss": 1.1951,
777
+ "theoretical_loss": 3.3410874633805214,
778
+ "tokens_seen": 3097624576
779
+ },
780
+ {
781
+ "epoch": 0.39,
782
+ "learning_rate": 6.140912730184148e-05,
783
+ "loss": 1.1936,
784
+ "theoretical_loss": 3.3409804203904145,
785
+ "tokens_seen": 3098935296
786
+ },
787
+ {
788
+ "epoch": 0.4,
789
+ "objective/train/docs_used": 1039074,
790
+ "objective/train/instantaneous_batch_size": 16,
791
+ "objective/train/instantaneous_microbatch_size": 16384,
792
+ "objective/train/original_loss": 1.3948986530303955,
793
+ "objective/train/theoretical_loss": 3.3408734353362513,
794
+ "objective/train/tokens_used": 151530976,
795
+ "theoretical_loss": 3.3408734353362513,
796
+ "tokens_seen": 3100246016
797
+ },
798
+ {
799
+ "epoch": 0.4,
800
+ "learning_rate": 6.1008807045636506e-05,
801
+ "loss": 1.1987,
802
+ "theoretical_loss": 3.3408734353362513,
803
+ "tokens_seen": 3100246016
804
+ }
805
+ ],
806
+ "max_steps": 2524,
807
+ "num_train_epochs": 9223372036854775807,
808
+ "total_flos": 6.6890760192e+16,
809
+ "trial_name": null,
810
+ "trial_params": null
811
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd7e58ec43308a2941cc2c808aad74dba29163ebf0ef8c873fc21f72e2fc9ddb
3
+ size 3375
checkpoint-1000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdbcc2ece93438fe54a8014ee2f47be2b4a9697a554f14f1c3452dbde49dc087
3
  size 456676457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a95fce57d21391971e548a7e98ef658543d9364d2bd777cdfaf61229b28e2a
3
  size 456676457
tokenizer.json CHANGED
@@ -1,7 +1,14 @@
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
+ "padding": {
5
+ "strategy": "BatchLongest",
6
+ "direction": "Right",
7
+ "pad_to_multiple_of": null,
8
+ "pad_id": 0,
9
+ "pad_type_id": 0,
10
+ "pad_token": "<|endoftext|>"
11
+ },
12
  "added_tokens": [
13
  {
14
  "id": 0,