anime-sh commited on
Commit
3a9bf25
·
verified ·
1 Parent(s): edc309f

prune intermediate checkpoint-200 (keeping only final checkpoint)

Browse files
checkpoint-200/config.json DELETED
@@ -1,69 +0,0 @@
1
- {
2
- "architectures": [
3
- "Olmo3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": null,
8
- "dtype": "bfloat16",
9
- "eos_token_id": 100257,
10
- "hidden_act": "silu",
11
- "hidden_size": 4096,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 11008,
14
- "layer_types": [
15
- "sliding_attention",
16
- "sliding_attention",
17
- "sliding_attention",
18
- "full_attention",
19
- "sliding_attention",
20
- "sliding_attention",
21
- "sliding_attention",
22
- "full_attention",
23
- "sliding_attention",
24
- "sliding_attention",
25
- "sliding_attention",
26
- "full_attention",
27
- "sliding_attention",
28
- "sliding_attention",
29
- "sliding_attention",
30
- "full_attention",
31
- "sliding_attention",
32
- "sliding_attention",
33
- "sliding_attention",
34
- "full_attention",
35
- "sliding_attention",
36
- "sliding_attention",
37
- "sliding_attention",
38
- "full_attention",
39
- "sliding_attention",
40
- "sliding_attention",
41
- "sliding_attention",
42
- "full_attention",
43
- "sliding_attention",
44
- "sliding_attention",
45
- "sliding_attention",
46
- "full_attention"
47
- ],
48
- "max_position_embeddings": 65536,
49
- "model_type": "olmo3",
50
- "num_attention_heads": 32,
51
- "num_hidden_layers": 32,
52
- "num_key_value_heads": 32,
53
- "pad_token_id": 100277,
54
- "rms_norm_eps": 1e-06,
55
- "rope_parameters": {
56
- "attention_factor": 1.2079441541679836,
57
- "beta_fast": 32.0,
58
- "beta_slow": 1.0,
59
- "factor": 8.0,
60
- "original_max_position_embeddings": 8192,
61
- "rope_theta": 500000,
62
- "rope_type": "yarn"
63
- },
64
- "sliding_window": 4096,
65
- "tie_word_embeddings": false,
66
- "transformers_version": "5.6.0",
67
- "use_cache": false,
68
- "vocab_size": 100278
69
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-200/generation_config.json DELETED
@@ -1,8 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "eos_token_id": [
4
- 100257
5
- ],
6
- "pad_token_id": 100277,
7
- "transformers_version": "5.6.0"
8
- }
 
 
 
 
 
 
 
 
 
checkpoint-200/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:589f7a96cf6b0bc740dba095802c619fb8c4684d5aa9e83157073bbaf9c4ccb9
3
- size 14596063960
 
 
 
 
checkpoint-200/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:83d8037bb183002beef170b433dbaec4737a88c50976d3fc763629b36a79e744
3
- size 29192355324
 
 
 
 
checkpoint-200/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:91317c5e4abc67d24eaa48e06aae01d8e24c1621d2d7b287b5317f05ead1b119
3
- size 14645
 
 
 
 
checkpoint-200/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d40399ea280ba96b20c6d0a2ef0bfc64a76a6a1d6f356021c001829456985cb
3
- size 1465
 
 
 
 
checkpoint-200/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/tokenizer_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "backend": "tokenizers",
4
- "bos_token": null,
5
- "clean_up_tokenization_spaces": false,
6
- "eos_token": "<|endoftext|>",
7
- "errors": "replace",
8
- "is_local": false,
9
- "local_files_only": false,
10
- "model_max_length": 65536,
11
- "pad_token": "<|pad|>",
12
- "tokenizer_class": "GPT2Tokenizer",
13
- "unk_token": "<|endoftext|>"
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-200/trainer_state.json DELETED
@@ -1,661 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.7912957467853611,
6
- "eval_steps": 500,
7
- "global_step": 200,
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,
14
- "forget_loss": 0.14035749435424805,
15
- "retain_loss": 2.6653778553009033,
16
- "step": 0
17
- },
18
- {
19
- "epoch": 0,
20
- "forget_loss": 0.19487237930297852,
21
- "retain_loss": 2.794126033782959,
22
- "step": 0
23
- },
24
- {
25
- "epoch": 0,
26
- "forget_loss": 0.1652039885520935,
27
- "retain_loss": 2.7992446422576904,
28
- "step": 0
29
- },
30
- {
31
- "epoch": 0,
32
- "forget_loss": 0.25970637798309326,
33
- "retain_loss": 2.7407283782958984,
34
- "step": 0
35
- },
36
- {
37
- "epoch": 0.003956478733926805,
38
- "grad_norm": 10.1875,
39
- "learning_rate": 0.0,
40
- "loss": 3.700044631958008,
41
- "step": 1
42
- },
43
- {
44
- "epoch": 0.03956478733926805,
45
- "grad_norm": 2.390625,
46
- "learning_rate": 4.5e-05,
47
- "loss": 2.9271229637993708,
48
- "step": 10
49
- },
50
- {
51
- "epoch": 0.03956478733926805,
52
- "forget_loss": 0.0006051036179997027,
53
- "retain_loss": 2.075515031814575,
54
- "step": 10
55
- },
56
- {
57
- "epoch": 0.03956478733926805,
58
- "forget_loss": 0.0002671501424629241,
59
- "retain_loss": 2.2641794681549072,
60
- "step": 10
61
- },
62
- {
63
- "epoch": 0.03956478733926805,
64
- "forget_loss": 0.00017286122601944953,
65
- "retain_loss": 2.1814846992492676,
66
- "step": 10
67
- },
68
- {
69
- "epoch": 0.03956478733926805,
70
- "forget_loss": 0.0006279755616560578,
71
- "retain_loss": 2.482621669769287,
72
- "step": 10
73
- },
74
- {
75
- "epoch": 0.0791295746785361,
76
- "grad_norm": 2.203125,
77
- "learning_rate": 4.909274193548387e-05,
78
- "loss": 2.1829532623291015,
79
- "step": 20
80
- },
81
- {
82
- "epoch": 0.0791295746785361,
83
- "forget_loss": 3.1555460736854e-05,
84
- "retain_loss": 2.056671380996704,
85
- "step": 20
86
- },
87
- {
88
- "epoch": 0.0791295746785361,
89
- "forget_loss": 1.3120857147441711e-05,
90
- "retain_loss": 1.9920682907104492,
91
- "step": 20
92
- },
93
- {
94
- "epoch": 0.0791295746785361,
95
- "forget_loss": 8.181996963685378e-05,
96
- "retain_loss": 2.149359703063965,
97
- "step": 20
98
- },
99
- {
100
- "epoch": 0.0791295746785361,
101
- "forget_loss": 4.155315400566906e-05,
102
- "retain_loss": 1.797939419746399,
103
- "step": 20
104
- },
105
- {
106
- "epoch": 0.11869436201780416,
107
- "grad_norm": 2.03125,
108
- "learning_rate": 4.808467741935484e-05,
109
- "loss": 1.9520586013793946,
110
- "step": 30
111
- },
112
- {
113
- "epoch": 0.11869436201780416,
114
- "forget_loss": 2.097734068229329e-06,
115
- "retain_loss": 1.9717810153961182,
116
- "step": 30
117
- },
118
- {
119
- "epoch": 0.11869436201780416,
120
- "forget_loss": 9.0424384779908e-07,
121
- "retain_loss": 2.1347732543945312,
122
- "step": 30
123
- },
124
- {
125
- "epoch": 0.11869436201780416,
126
- "forget_loss": 1.5195576452242676e-05,
127
- "retain_loss": 1.7591031789779663,
128
- "step": 30
129
- },
130
- {
131
- "epoch": 0.11869436201780416,
132
- "forget_loss": 2.9381511922110803e-05,
133
- "retain_loss": 2.324976682662964,
134
- "step": 30
135
- },
136
- {
137
- "epoch": 0.1582591493570722,
138
- "grad_norm": 1.9453125,
139
- "learning_rate": 4.7076612903225806e-05,
140
- "loss": 1.7898395538330079,
141
- "step": 40
142
- },
143
- {
144
- "epoch": 0.1582591493570722,
145
- "forget_loss": 2.347593181184493e-05,
146
- "retain_loss": 1.5896490812301636,
147
- "step": 40
148
- },
149
- {
150
- "epoch": 0.1582591493570722,
151
- "forget_loss": 2.7579757443163544e-05,
152
- "retain_loss": 1.1212265491485596,
153
- "step": 40
154
- },
155
- {
156
- "epoch": 0.1582591493570722,
157
- "forget_loss": 2.1694726456189528e-05,
158
- "retain_loss": 2.051854133605957,
159
- "step": 40
160
- },
161
- {
162
- "epoch": 0.1582591493570722,
163
- "forget_loss": 6.128148925199639e-06,
164
- "retain_loss": 1.6619952917099,
165
- "step": 40
166
- },
167
- {
168
- "epoch": 0.19782393669634027,
169
- "grad_norm": 1.96875,
170
- "learning_rate": 4.606854838709678e-05,
171
- "loss": 1.5459610939025878,
172
- "step": 50
173
- },
174
- {
175
- "epoch": 0.19782393669634027,
176
- "forget_loss": 1.4324338735605124e-05,
177
- "retain_loss": 1.7004584074020386,
178
- "step": 50
179
- },
180
- {
181
- "epoch": 0.19782393669634027,
182
- "forget_loss": 5.814884843857726e-06,
183
- "retain_loss": 1.3355984687805176,
184
- "step": 50
185
- },
186
- {
187
- "epoch": 0.19782393669634027,
188
- "forget_loss": 1.4618005934607936e-06,
189
- "retain_loss": 1.7750041484832764,
190
- "step": 50
191
- },
192
- {
193
- "epoch": 0.19782393669634027,
194
- "forget_loss": 1.6271239928755676e-06,
195
- "retain_loss": 1.4064531326293945,
196
- "step": 50
197
- },
198
- {
199
- "epoch": 0.23738872403560832,
200
- "grad_norm": 2.234375,
201
- "learning_rate": 4.506048387096775e-05,
202
- "loss": 1.4617247581481934,
203
- "step": 60
204
- },
205
- {
206
- "epoch": 0.23738872403560832,
207
- "forget_loss": 9.254661563318223e-06,
208
- "retain_loss": 1.8761130571365356,
209
- "step": 60
210
- },
211
- {
212
- "epoch": 0.23738872403560832,
213
- "forget_loss": 9.365790901938453e-06,
214
- "retain_loss": 1.1389141082763672,
215
- "step": 60
216
- },
217
- {
218
- "epoch": 0.23738872403560832,
219
- "forget_loss": 6.40576909063384e-05,
220
- "retain_loss": 1.0727425813674927,
221
- "step": 60
222
- },
223
- {
224
- "epoch": 0.23738872403560832,
225
- "forget_loss": 3.140630724374205e-06,
226
- "retain_loss": 1.2311009168624878,
227
- "step": 60
228
- },
229
- {
230
- "epoch": 0.27695351137487634,
231
- "grad_norm": 2.125,
232
- "learning_rate": 4.4052419354838714e-05,
233
- "loss": 1.344314193725586,
234
- "step": 70
235
- },
236
- {
237
- "epoch": 0.27695351137487634,
238
- "forget_loss": 2.0407464035088196e-05,
239
- "retain_loss": 1.2631032466888428,
240
- "step": 70
241
- },
242
- {
243
- "epoch": 0.27695351137487634,
244
- "forget_loss": 2.1732415916630998e-05,
245
- "retain_loss": 1.4336204528808594,
246
- "step": 70
247
- },
248
- {
249
- "epoch": 0.27695351137487634,
250
- "forget_loss": 1.3687983937415993e-06,
251
- "retain_loss": 0.9825552105903625,
252
- "step": 70
253
- },
254
- {
255
- "epoch": 0.27695351137487634,
256
- "forget_loss": 1.326372967014322e-06,
257
- "retain_loss": 1.3998953104019165,
258
- "step": 70
259
- },
260
- {
261
- "epoch": 0.3165182987141444,
262
- "grad_norm": 2.390625,
263
- "learning_rate": 4.3044354838709674e-05,
264
- "loss": 1.214775276184082,
265
- "step": 80
266
- },
267
- {
268
- "epoch": 0.3165182987141444,
269
- "forget_loss": 1.3552562450058758e-06,
270
- "retain_loss": 1.0332047939300537,
271
- "step": 80
272
- },
273
- {
274
- "epoch": 0.3165182987141444,
275
- "forget_loss": 1.2774065908160992e-05,
276
- "retain_loss": 1.007059931755066,
277
- "step": 80
278
- },
279
- {
280
- "epoch": 0.3165182987141444,
281
- "forget_loss": 1.196574157802388e-05,
282
- "retain_loss": 0.8872216939926147,
283
- "step": 80
284
- },
285
- {
286
- "epoch": 0.3165182987141444,
287
- "forget_loss": 4.2263846466994437e-07,
288
- "retain_loss": 0.8739179372787476,
289
- "step": 80
290
- },
291
- {
292
- "epoch": 0.3560830860534125,
293
- "grad_norm": 2.28125,
294
- "learning_rate": 4.203629032258065e-05,
295
- "loss": 1.1429722785949707,
296
- "step": 90
297
- },
298
- {
299
- "epoch": 0.3560830860534125,
300
- "forget_loss": 2.522195063647814e-05,
301
- "retain_loss": 0.8757652640342712,
302
- "step": 90
303
- },
304
- {
305
- "epoch": 0.3560830860534125,
306
- "forget_loss": 2.2732887373422273e-05,
307
- "retain_loss": 0.9618234634399414,
308
- "step": 90
309
- },
310
- {
311
- "epoch": 0.3560830860534125,
312
- "forget_loss": 2.1186065168876667e-06,
313
- "retain_loss": 0.82012540102005,
314
- "step": 90
315
- },
316
- {
317
- "epoch": 0.3560830860534125,
318
- "forget_loss": 1.5917968994472176e-05,
319
- "retain_loss": 1.2091050148010254,
320
- "step": 90
321
- },
322
- {
323
- "epoch": 0.39564787339268054,
324
- "grad_norm": 2.8125,
325
- "learning_rate": 4.1028225806451615e-05,
326
- "loss": 0.9440973281860352,
327
- "step": 100
328
- },
329
- {
330
- "epoch": 0.39564787339268054,
331
- "forget_loss": 5.102012892166385e-07,
332
- "retain_loss": 0.9886119365692139,
333
- "step": 100
334
- },
335
- {
336
- "epoch": 0.39564787339268054,
337
- "forget_loss": 2.069048832709086e-06,
338
- "retain_loss": 1.037408471107483,
339
- "step": 100
340
- },
341
- {
342
- "epoch": 0.39564787339268054,
343
- "forget_loss": 6.717852556903381e-06,
344
- "retain_loss": 1.2528358697891235,
345
- "step": 100
346
- },
347
- {
348
- "epoch": 0.39564787339268054,
349
- "forget_loss": 1.7514905266580172e-05,
350
- "retain_loss": 0.5935210585594177,
351
- "step": 100
352
- },
353
- {
354
- "epoch": 0.4352126607319486,
355
- "grad_norm": 2.34375,
356
- "learning_rate": 4.002016129032258e-05,
357
- "loss": 0.8624692916870117,
358
- "step": 110
359
- },
360
- {
361
- "epoch": 0.4352126607319486,
362
- "forget_loss": 1.1634347174549475e-05,
363
- "retain_loss": 0.5517681837081909,
364
- "step": 110
365
- },
366
- {
367
- "epoch": 0.4352126607319486,
368
- "forget_loss": 6.400139795914583e-08,
369
- "retain_loss": 1.0467280149459839,
370
- "step": 110
371
- },
372
- {
373
- "epoch": 0.4352126607319486,
374
- "forget_loss": 1.9029957911698148e-05,
375
- "retain_loss": 1.1268657445907593,
376
- "step": 110
377
- },
378
- {
379
- "epoch": 0.4352126607319486,
380
- "forget_loss": 2.5354455601700465e-07,
381
- "retain_loss": 0.8402698040008545,
382
- "step": 110
383
- },
384
- {
385
- "epoch": 0.47477744807121663,
386
- "grad_norm": 2.609375,
387
- "learning_rate": 3.901209677419355e-05,
388
- "loss": 0.7725035190582276,
389
- "step": 120
390
- },
391
- {
392
- "epoch": 0.47477744807121663,
393
- "forget_loss": 3.8098887671367265e-06,
394
- "retain_loss": 0.3457094430923462,
395
- "step": 120
396
- },
397
- {
398
- "epoch": 0.47477744807121663,
399
- "forget_loss": 2.3242062525241636e-05,
400
- "retain_loss": 0.6856692433357239,
401
- "step": 120
402
- },
403
- {
404
- "epoch": 0.47477744807121663,
405
- "forget_loss": 8.018694643396884e-06,
406
- "retain_loss": 1.2206052541732788,
407
- "step": 120
408
- },
409
- {
410
- "epoch": 0.47477744807121663,
411
- "forget_loss": 3.351060968270758e-06,
412
- "retain_loss": 0.7469509840011597,
413
- "step": 120
414
- },
415
- {
416
- "epoch": 0.5143422354104846,
417
- "grad_norm": 2.640625,
418
- "learning_rate": 3.800403225806452e-05,
419
- "loss": 0.6184093952178955,
420
- "step": 130
421
- },
422
- {
423
- "epoch": 0.5143422354104846,
424
- "forget_loss": 3.902082880813396e-06,
425
- "retain_loss": 0.9034799933433533,
426
- "step": 130
427
- },
428
- {
429
- "epoch": 0.5143422354104846,
430
- "forget_loss": 1.8487480701878667e-07,
431
- "retain_loss": 0.944042980670929,
432
- "step": 130
433
- },
434
- {
435
- "epoch": 0.5143422354104846,
436
- "forget_loss": 7.273596338563948e-07,
437
- "retain_loss": 0.589636504650116,
438
- "step": 130
439
- },
440
- {
441
- "epoch": 0.5143422354104846,
442
- "forget_loss": 6.394767115125433e-05,
443
- "retain_loss": 0.8495606780052185,
444
- "step": 130
445
- },
446
- {
447
- "epoch": 0.5539070227497527,
448
- "grad_norm": 2.09375,
449
- "learning_rate": 3.6995967741935484e-05,
450
- "loss": 0.5851613521575928,
451
- "step": 140
452
- },
453
- {
454
- "epoch": 0.5539070227497527,
455
- "forget_loss": 1.9570716176531278e-06,
456
- "retain_loss": 0.31179508566856384,
457
- "step": 140
458
- },
459
- {
460
- "epoch": 0.5539070227497527,
461
- "forget_loss": 4.920673745800741e-06,
462
- "retain_loss": 0.7174519300460815,
463
- "step": 140
464
- },
465
- {
466
- "epoch": 0.5539070227497527,
467
- "forget_loss": 9.13152689463459e-07,
468
- "retain_loss": 0.44045335054397583,
469
- "step": 140
470
- },
471
- {
472
- "epoch": 0.5539070227497527,
473
- "forget_loss": 7.388467793134623e-07,
474
- "retain_loss": 0.35985979437828064,
475
- "step": 140
476
- },
477
- {
478
- "epoch": 0.5934718100890207,
479
- "grad_norm": 2.0625,
480
- "learning_rate": 3.598790322580645e-05,
481
- "loss": 0.5792353630065918,
482
- "step": 150
483
- },
484
- {
485
- "epoch": 0.5934718100890207,
486
- "forget_loss": 1.258710966567378e-07,
487
- "retain_loss": 0.45937851071357727,
488
- "step": 150
489
- },
490
- {
491
- "epoch": 0.5934718100890207,
492
- "forget_loss": 7.370726962108165e-07,
493
- "retain_loss": 0.27468791604042053,
494
- "step": 150
495
- },
496
- {
497
- "epoch": 0.5934718100890207,
498
- "forget_loss": 8.536089808330871e-06,
499
- "retain_loss": 0.8069593906402588,
500
- "step": 150
501
- },
502
- {
503
- "epoch": 0.5934718100890207,
504
- "forget_loss": 8.370562341042387e-07,
505
- "retain_loss": 0.15817895531654358,
506
- "step": 150
507
- },
508
- {
509
- "epoch": 0.6330365974282888,
510
- "grad_norm": 1.703125,
511
- "learning_rate": 3.497983870967742e-05,
512
- "loss": 0.40374002456665037,
513
- "step": 160
514
- },
515
- {
516
- "epoch": 0.6330365974282888,
517
- "forget_loss": 4.5395900087896734e-06,
518
- "retain_loss": 0.6503518223762512,
519
- "step": 160
520
- },
521
- {
522
- "epoch": 0.6330365974282888,
523
- "forget_loss": 1.2475591120164609e-06,
524
- "retain_loss": 0.29691439867019653,
525
- "step": 160
526
- },
527
- {
528
- "epoch": 0.6330365974282888,
529
- "forget_loss": 7.69290522839583e-07,
530
- "retain_loss": 0.3579648435115814,
531
- "step": 160
532
- },
533
- {
534
- "epoch": 0.6330365974282888,
535
- "forget_loss": 3.610326075431658e-06,
536
- "retain_loss": 0.3425873816013336,
537
- "step": 160
538
- },
539
- {
540
- "epoch": 0.6726013847675568,
541
- "grad_norm": 2.171875,
542
- "learning_rate": 3.397177419354839e-05,
543
- "loss": 0.3935901641845703,
544
- "step": 170
545
- },
546
- {
547
- "epoch": 0.6726013847675568,
548
- "forget_loss": 7.11527832208958e-07,
549
- "retain_loss": 0.45746102929115295,
550
- "step": 170
551
- },
552
- {
553
- "epoch": 0.6726013847675568,
554
- "forget_loss": 3.808730753007694e-07,
555
- "retain_loss": 0.4325888454914093,
556
- "step": 170
557
- },
558
- {
559
- "epoch": 0.6726013847675568,
560
- "forget_loss": 1.3094180530970334e-06,
561
- "retain_loss": 0.1893959939479828,
562
- "step": 170
563
- },
564
- {
565
- "epoch": 0.6726013847675568,
566
- "forget_loss": 5.8092759900318924e-06,
567
- "retain_loss": 1.1242655515670776,
568
- "step": 170
569
- },
570
- {
571
- "epoch": 0.712166172106825,
572
- "grad_norm": 2.28125,
573
- "learning_rate": 3.296370967741936e-05,
574
- "loss": 0.37663323879241944,
575
- "step": 180
576
- },
577
- {
578
- "epoch": 0.712166172106825,
579
- "forget_loss": 1.8580192318040645e-06,
580
- "retain_loss": 0.24432934820652008,
581
- "step": 180
582
- },
583
- {
584
- "epoch": 0.712166172106825,
585
- "forget_loss": 3.5925964425587154e-07,
586
- "retain_loss": 0.2534143328666687,
587
- "step": 180
588
- },
589
- {
590
- "epoch": 0.712166172106825,
591
- "forget_loss": 5.5626283028686885e-06,
592
- "retain_loss": 0.23151986300945282,
593
- "step": 180
594
- },
595
- {
596
- "epoch": 0.712166172106825,
597
- "forget_loss": 5.4275651564239524e-06,
598
- "retain_loss": 0.2856011688709259,
599
- "step": 180
600
- },
601
- {
602
- "epoch": 0.751730959446093,
603
- "grad_norm": 2.265625,
604
- "learning_rate": 3.1955645161290326e-05,
605
- "loss": 0.3224222183227539,
606
- "step": 190
607
- },
608
- {
609
- "epoch": 0.751730959446093,
610
- "forget_loss": 2.0351612874947023e-06,
611
- "retain_loss": 0.30106958746910095,
612
- "step": 190
613
- },
614
- {
615
- "epoch": 0.751730959446093,
616
- "forget_loss": 1.137744402512908e-05,
617
- "retain_loss": 0.35559219121932983,
618
- "step": 190
619
- },
620
- {
621
- "epoch": 0.751730959446093,
622
- "forget_loss": 4.769389647663047e-07,
623
- "retain_loss": 0.12539999186992645,
624
- "step": 190
625
- },
626
- {
627
- "epoch": 0.751730959446093,
628
- "forget_loss": 1.536158151793643e-07,
629
- "retain_loss": 0.5091521143913269,
630
- "step": 190
631
- },
632
- {
633
- "epoch": 0.7912957467853611,
634
- "grad_norm": 1.984375,
635
- "learning_rate": 3.0947580645161286e-05,
636
- "loss": 0.32691752910614014,
637
- "step": 200
638
- }
639
- ],
640
- "logging_steps": 10,
641
- "max_steps": 506,
642
- "num_input_tokens_seen": 0,
643
- "num_train_epochs": 2,
644
- "save_steps": 200,
645
- "stateful_callbacks": {
646
- "TrainerControl": {
647
- "args": {
648
- "should_epoch_stop": false,
649
- "should_evaluate": false,
650
- "should_log": false,
651
- "should_save": true,
652
- "should_training_stop": false
653
- },
654
- "attributes": {}
655
- }
656
- },
657
- "total_flos": 0.0,
658
- "train_batch_size": 8,
659
- "trial_name": null,
660
- "trial_params": null
661
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-200/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4daa46b81e960187a13cf9715d61600f7d344da408f25fda410bfb3b965becf
3
- size 5329