Hugging Face's logo

aixk
/
fastplus-44m

Text Generation
Transformers
Safetensors
English
Korean
fastplus_40m
Model card Files
xet
 Community
aixk commited on
Commit
7a90a0a
·
1 Parent(s): 151b76b

FastPlus40m Backup checkpoint-600 at global step 600

Browse files
Files changed (11) hide show
  1. checkpoint-600/config.json +19 -0
  2. checkpoint-600/generation_config.json +6 -0
  3. checkpoint-600/model.safetensors +3 -0
  4. checkpoint-600/optimizer.pt +3 -0
  5. checkpoint-600/rng_state.pth +3 -0
  6. checkpoint-600/scaler.pt +3 -0
  7. checkpoint-600/scheduler.pt +3 -0
  8. checkpoint-600/tokenizer.json +0 -0
  9. checkpoint-600/tokenizer_config.json +13 -0
  10. checkpoint-600/trainer_state.json +514 -0
  11. checkpoint-600/training_args.bin +3 -0
checkpoint-600/config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FastPlus40mForCausalLM"
4
+ ],
5
+ "dtype": "float32",
6
+ "hidden_size": 512,
7
+ "initializer_range": 0.02,
8
+ "intermediate_size": 1536,
9
+ "kd_alpha": 0.4,
10
+ "kd_temperature": 2.5,
11
+ "max_position_embeddings": 512,
12
+ "model_type": "fastplus_40m",
13
+ "num_attention_heads": 8,
14
+ "num_hidden_layers": 11,
15
+ "tie_word_embeddings": true,
16
+ "transformers_version": "5.12.0",
17
+ "use_cache": false,
18
+ "vocab_size": 8160
19
+ }
checkpoint-600/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "transformers_version": "5.12.0"
6
+ }
checkpoint-600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8245a0b387f94e4cad36a976d53d8d6a292a624e02967195eddde318729d6251
3
+ size 159784280
checkpoint-600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48599f975b0c09ffa819ad9c19841a1381f0df30b39cf3f148802fc3bf857e62
3
+ size 179195723
checkpoint-600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
3
+ size 14645
checkpoint-600/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c39bdf7d2e11fc71068c6216d7d02ad2dc0504f397b35c95dec68262b2f475
3
+ size 1383
checkpoint-600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59d55d6cff72ec4ef42faaad8c043f54e7701c7c892dd4fa63f7ca0f2f15d4a
3
+ size 5625
checkpoint-600/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-600/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "extra_special_tokens": [
6
+ "<|user|>",
7
+ "<|assistant|>"
8
+ ],
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "<pad>",
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "unk_token": "<unk>"
13
+ }
checkpoint-600/trainer_state.json ADDED
@@ -0,0 +1,514 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.481203007518797,
6
+ "eval_steps": 500,
7
+ "global_step": 600,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.041483017889551464,
14
+ "grad_norm": 203.76828002929688,
15
+ "learning_rate": 1.4875e-05,
16
+ "loss": 288.5525390625,
17
+ "original_ce_loss": 9.0166,
18
+ "step": 10
19
+ },
20
+ {
21
+ "epoch": 0.08296603577910293,
22
+ "grad_norm": 184.2494659423828,
23
+ "learning_rate": 3.6125000000000004e-05,
24
+ "loss": 287.5813232421875,
25
+ "original_ce_loss": 8.9862,
26
+ "step": 20
27
+ },
28
+ {
29
+ "epoch": 0.1244490536686544,
30
+ "grad_norm": 241.391845703125,
31
+ "learning_rate": 5.7375e-05,
32
+ "loss": 284.6296875,
33
+ "original_ce_loss": 8.894,
34
+ "step": 30
35
+ },
36
+ {
37
+ "epoch": 0.16593207155820586,
38
+ "grad_norm": 327.870361328125,
39
+ "learning_rate": 7.8625e-05,
40
+ "loss": 273.14404296875,
41
+ "original_ce_loss": 8.5351,
42
+ "step": 40
43
+ },
44
+ {
45
+ "epoch": 0.20741508944775733,
46
+ "grad_norm": 80.51351165771484,
47
+ "learning_rate": 9.775e-05,
48
+ "loss": 243.771630859375,
49
+ "original_ce_loss": 7.6172,
50
+ "step": 50
51
+ },
52
+ {
53
+ "epoch": 0.2488981073373088,
54
+ "grad_norm": 61.04130554199219,
55
+ "learning_rate": 0.00011687500000000001,
56
+ "loss": 229.8462646484375,
57
+ "original_ce_loss": 7.182,
58
+ "step": 60
59
+ },
60
+ {
61
+ "epoch": 0.29038112522686027,
62
+ "grad_norm": 60.73427200317383,
63
+ "learning_rate": 0.000129625,
64
+ "loss": 221.95341796875,
65
+ "original_ce_loss": 6.9354,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.3318641431164117,
70
+ "grad_norm": 51.37192916870117,
71
+ "learning_rate": 0.000150875,
72
+ "loss": 214.37080078125,
73
+ "original_ce_loss": 6.6984,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 0.37334716100596316,
78
+ "grad_norm": 22.531389236450195,
79
+ "learning_rate": 0.000172125,
80
+ "loss": 205.998388671875,
81
+ "original_ce_loss": 6.4368,
82
+ "step": 90
83
+ },
84
+ {
85
+ "epoch": 0.41483017889551466,
86
+ "grad_norm": 16.882768630981445,
87
+ "learning_rate": 0.000193375,
88
+ "loss": 201.5771484375,
89
+ "original_ce_loss": 6.2986,
90
+ "step": 100
91
+ },
92
+ {
93
+ "epoch": 0.4563131967850661,
94
+ "grad_norm": 32.13435363769531,
95
+ "learning_rate": 0.000214625,
96
+ "loss": 199.65380859375,
97
+ "original_ce_loss": 6.2385,
98
+ "step": 110
99
+ },
100
+ {
101
+ "epoch": 0.4977962146746176,
102
+ "grad_norm": 22.2371883392334,
103
+ "learning_rate": 0.000235875,
104
+ "loss": 198.15953369140624,
105
+ "original_ce_loss": 6.1918,
106
+ "step": 120
107
+ },
108
+ {
109
+ "epoch": 0.5392792325641691,
110
+ "grad_norm": 23.51988983154297,
111
+ "learning_rate": 0.000257125,
112
+ "loss": 195.21707763671876,
113
+ "original_ce_loss": 6.0999,
114
+ "step": 130
115
+ },
116
+ {
117
+ "epoch": 0.5807622504537205,
118
+ "grad_norm": 21.056625366210938,
119
+ "learning_rate": 0.000278375,
120
+ "loss": 192.00562744140626,
121
+ "original_ce_loss": 5.9995,
122
+ "step": 140
123
+ },
124
+ {
125
+ "epoch": 0.622245268343272,
126
+ "grad_norm": 27.031875610351562,
127
+ "learning_rate": 0.000299625,
128
+ "loss": 189.01895751953126,
129
+ "original_ce_loss": 5.9062,
130
+ "step": 150
131
+ },
132
+ {
133
+ "epoch": 0.6637282862328234,
134
+ "grad_norm": 18.687732696533203,
135
+ "learning_rate": 0.000320875,
136
+ "loss": 185.54974365234375,
137
+ "original_ce_loss": 5.7978,
138
+ "step": 160
139
+ },
140
+ {
141
+ "epoch": 0.7052113041223749,
142
+ "grad_norm": 34.62672805786133,
143
+ "learning_rate": 0.000342125,
144
+ "loss": 181.4411865234375,
145
+ "original_ce_loss": 5.6694,
146
+ "step": 170
147
+ },
148
+ {
149
+ "epoch": 0.7466943220119263,
150
+ "grad_norm": 22.933151245117188,
151
+ "learning_rate": 0.000363375,
152
+ "loss": 176.920361328125,
153
+ "original_ce_loss": 5.5281,
154
+ "step": 180
155
+ },
156
+ {
157
+ "epoch": 0.7881773399014779,
158
+ "grad_norm": 40.35688018798828,
159
+ "learning_rate": 0.000384625,
160
+ "loss": 171.9557861328125,
161
+ "original_ce_loss": 5.373,
162
+ "step": 190
163
+ },
164
+ {
165
+ "epoch": 0.8296603577910293,
166
+ "grad_norm": 36.39991760253906,
167
+ "learning_rate": 0.000405875,
168
+ "loss": 167.02354736328124,
169
+ "original_ce_loss": 5.2188,
170
+ "step": 200
171
+ },
172
+ {
173
+ "epoch": 0.8711433756805808,
174
+ "grad_norm": 50.5265998840332,
175
+ "learning_rate": 0.00042440580690100075,
176
+ "loss": 162.07708740234375,
177
+ "original_ce_loss": 5.0643,
178
+ "step": 210
179
+ },
180
+ {
181
+ "epoch": 0.9126263935701322,
182
+ "grad_norm": 37.708221435546875,
183
+ "learning_rate": 0.00035703670677632033,
184
+ "loss": 157.2227294921875,
185
+ "original_ce_loss": 4.9126,
186
+ "step": 220
187
+ },
188
+ {
189
+ "epoch": 0.9541094114596836,
190
+ "grad_norm": 35.469329833984375,
191
+ "learning_rate": 0.0002125,
192
+ "loss": 153.1784423828125,
193
+ "original_ce_loss": 4.7862,
194
+ "step": 230
195
+ },
196
+ {
197
+ "epoch": 0.9955924293492352,
198
+ "grad_norm": 16.84328842163086,
199
+ "learning_rate": 6.796329322367959e-05,
200
+ "loss": 149.57703857421876,
201
+ "original_ce_loss": 4.6736,
202
+ "step": 240
203
+ },
204
+ {
205
+ "epoch": 1.0331864143116412,
206
+ "grad_norm": NaN,
207
+ "learning_rate": 0.00040351662824681024,
208
+ "loss": 149.98463439941406,
209
+ "original_ce_loss": 4.6864,
210
+ "step": 250
211
+ },
212
+ {
213
+ "epoch": 1.0746694322011927,
214
+ "grad_norm": 64.90169525146484,
215
+ "learning_rate": 0.00039331657240756313,
216
+ "loss": 145.989599609375,
217
+ "original_ce_loss": 4.5615,
218
+ "step": 260
219
+ },
220
+ {
221
+ "epoch": 1.116152450090744,
222
+ "grad_norm": 42.50829315185547,
223
+ "learning_rate": 0.00037988794433001515,
224
+ "loss": 141.3390625,
225
+ "original_ce_loss": 4.4162,
226
+ "step": 270
227
+ },
228
+ {
229
+ "epoch": 1.1576354679802956,
230
+ "grad_norm": 38.33572769165039,
231
+ "learning_rate": 0.0003644131338923845,
232
+ "loss": 138.03270263671874,
233
+ "original_ce_loss": 4.3129,
234
+ "step": 280
235
+ },
236
+ {
237
+ "epoch": 1.199118485869847,
238
+ "grad_norm": 40.65241241455078,
239
+ "learning_rate": 0.00034708130814771,
240
+ "loss": 135.1212158203125,
241
+ "original_ce_loss": 4.2219,
242
+ "step": 290
243
+ },
244
+ {
245
+ "epoch": 1.2406015037593985,
246
+ "grad_norm": 69.57759857177734,
247
+ "learning_rate": 0.0003281043346605806,
248
+ "loss": 132.01983642578125,
249
+ "original_ce_loss": 4.125,
250
+ "step": 300
251
+ },
252
+ {
253
+ "epoch": 1.28208452164895,
254
+ "grad_norm": 47.51698684692383,
255
+ "learning_rate": 0.00030771419159736043,
256
+ "loss": 128.94189453125,
257
+ "original_ce_loss": 4.0288,
258
+ "step": 310
259
+ },
260
+ {
261
+ "epoch": 1.3235675395385014,
262
+ "grad_norm": 46.686241149902344,
263
+ "learning_rate": 0.0002861601319805566,
264
+ "loss": 126.20169677734376,
265
+ "original_ce_loss": 3.9432,
266
+ "step": 320
267
+ },
268
+ {
269
+ "epoch": 1.365050557428053,
270
+ "grad_norm": 39.812068939208984,
271
+ "learning_rate": 0.00026370563677203054,
272
+ "loss": 123.58370361328124,
273
+ "original_ce_loss": 3.8614,
274
+ "step": 330
275
+ },
276
+ {
277
+ "epoch": 1.4065335753176043,
278
+ "grad_norm": 34.92276382446289,
279
+ "learning_rate": 0.0002406251940311473,
280
+ "loss": 121.514599609375,
281
+ "original_ce_loss": 3.7967,
282
+ "step": 340
283
+ },
284
+ {
285
+ "epoch": 1.4480165932071558,
286
+ "grad_norm": 51.240840911865234,
287
+ "learning_rate": 0.0002172009435200522,
288
+ "loss": 118.99783935546876,
289
+ "original_ce_loss": 3.7181,
290
+ "step": 350
291
+ },
292
+ {
293
+ "epoch": 1.4894996110967074,
294
+ "grad_norm": 42.60438537597656,
295
+ "learning_rate": 0.00019371922777306473,
296
+ "loss": 117.68125,
297
+ "original_ce_loss": 3.6769,
298
+ "step": 360
299
+ },
300
+ {
301
+ "epoch": 1.5309826289862587,
302
+ "grad_norm": 32.416114807128906,
303
+ "learning_rate": 0.00017046709179057757,
304
+ "loss": 115.90443115234375,
305
+ "original_ce_loss": 3.6214,
306
+ "step": 370
307
+ },
308
+ {
309
+ "epoch": 1.5724656468758103,
310
+ "grad_norm": 31.31523895263672,
311
+ "learning_rate": 0.0001477287741458766,
312
+ "loss": 114.24423828125,
313
+ "original_ce_loss": 3.5695,
314
+ "step": 380
315
+ },
316
+ {
317
+ "epoch": 1.6139486647653616,
318
+ "grad_norm": 29.63783836364746,
319
+ "learning_rate": 0.00012578223239826367,
320
+ "loss": 113.076904296875,
321
+ "original_ce_loss": 3.533,
322
+ "step": 390
323
+ },
324
+ {
325
+ "epoch": 1.6554316826549131,
326
+ "grad_norm": 21.96636962890625,
327
+ "learning_rate": 0.0001048957452865007,
328
+ "loss": 111.66766357421875,
329
+ "original_ce_loss": 3.489,
330
+ "step": 400
331
+ },
332
+ {
333
+ "epoch": 1.6969147005444647,
334
+ "grad_norm": 72.03860473632812,
335
+ "learning_rate": 0.00029176382908428956,
336
+ "loss": 111.707080078125,
337
+ "original_ce_loss": 3.4902,
338
+ "step": 410
339
+ },
340
+ {
341
+ "epoch": 1.738397718434016,
342
+ "grad_norm": 56.377784729003906,
343
+ "learning_rate": 0.0002798536820919388,
344
+ "loss": 110.67801513671876,
345
+ "original_ce_loss": 3.4581,
346
+ "step": 420
347
+ },
348
+ {
349
+ "epoch": 1.7798807363235676,
350
+ "grad_norm": 40.06888198852539,
351
+ "learning_rate": 0.0002677033420177621,
352
+ "loss": 108.81322021484375,
353
+ "original_ce_loss": 3.3998,
354
+ "step": 430
355
+ },
356
+ {
357
+ "epoch": 1.821363754213119,
358
+ "grad_norm": 54.35465621948242,
359
+ "learning_rate": 0.0002553561387516336,
360
+ "loss": 107.58404541015625,
361
+ "original_ce_loss": 3.3614,
362
+ "step": 440
363
+ },
364
+ {
365
+ "epoch": 1.8628467721026705,
366
+ "grad_norm": 43.010047912597656,
367
+ "learning_rate": 0.00024285610422636377,
368
+ "loss": 106.3376953125,
369
+ "original_ce_loss": 3.3225,
370
+ "step": 450
371
+ },
372
+ {
373
+ "epoch": 1.904329789992222,
374
+ "grad_norm": 37.77562713623047,
375
+ "learning_rate": 0.00023024781539338732,
376
+ "loss": 105.1876708984375,
377
+ "original_ce_loss": 3.2865,
378
+ "step": 460
379
+ },
380
+ {
381
+ "epoch": 1.9458128078817734,
382
+ "grad_norm": 39.30547332763672,
383
+ "learning_rate": 0.00021757623525483388,
384
+ "loss": 104.48690185546874,
385
+ "original_ce_loss": 3.2646,
386
+ "step": 470
387
+ },
388
+ {
389
+ "epoch": 1.987295825771325,
390
+ "grad_norm": 38.75474548339844,
391
+ "learning_rate": 0.00020615504546354557,
392
+ "loss": 103.30198974609375,
393
+ "original_ce_loss": 3.2276,
394
+ "step": 480
395
+ },
396
+ {
397
+ "epoch": 2.0248898107337308,
398
+ "grad_norm": 68.0500259399414,
399
+ "learning_rate": 0.00019348776342655851,
400
+ "loss": 93.47062377929687,
401
+ "original_ce_loss": 3.2225,
402
+ "step": 490
403
+ },
404
+ {
405
+ "epoch": 2.0663728286232823,
406
+ "grad_norm": 33.5322380065918,
407
+ "learning_rate": 0.00018088828180601698,
408
+ "loss": 102.30059814453125,
409
+ "original_ce_loss": 3.1963,
410
+ "step": 500
411
+ },
412
+ {
413
+ "epoch": 2.107855846512834,
414
+ "grad_norm": 43.00708770751953,
415
+ "learning_rate": 0.00016840153219624304,
416
+ "loss": 101.05491943359375,
417
+ "original_ce_loss": 3.1574,
418
+ "step": 510
419
+ },
420
+ {
421
+ "epoch": 2.1493388644023854,
422
+ "grad_norm": 32.75222396850586,
423
+ "learning_rate": 0.00015607204417271948,
424
+ "loss": 100.06157836914062,
425
+ "original_ce_loss": 3.1263,
426
+ "step": 520
427
+ },
428
+ {
429
+ "epoch": 2.190821882291937,
430
+ "grad_norm": 34.5550537109375,
431
+ "learning_rate": 0.0001439437864931107,
432
+ "loss": 99.03675537109375,
433
+ "original_ce_loss": 3.0943,
434
+ "step": 530
435
+ },
436
+ {
437
+ "epoch": 2.232304900181488,
438
+ "grad_norm": 33.61601257324219,
439
+ "learning_rate": 0.00013206001029824168,
440
+ "loss": 98.9501953125,
441
+ "original_ce_loss": 3.0916,
442
+ "step": 540
443
+ },
444
+ {
445
+ "epoch": 2.2737879180710396,
446
+ "grad_norm": 35.476318359375,
447
+ "learning_rate": 0.00012046309487220386,
448
+ "loss": 98.14458618164062,
449
+ "original_ce_loss": 3.0664,
450
+ "step": 550
451
+ },
452
+ {
453
+ "epoch": 2.315270935960591,
454
+ "grad_norm": 27.919132232666016,
455
+ "learning_rate": 0.00010919439651162934,
456
+ "loss": 97.50660400390625,
457
+ "original_ce_loss": 3.0465,
458
+ "step": 560
459
+ },
460
+ {
461
+ "epoch": 2.3567539538501427,
462
+ "grad_norm": 27.541818618774414,
463
+ "learning_rate": 9.829410104308781e-05,
464
+ "loss": 96.76535034179688,
465
+ "original_ce_loss": 3.0233,
466
+ "step": 570
467
+ },
468
+ {
469
+ "epoch": 2.398236971739694,
470
+ "grad_norm": 25.62722396850586,
471
+ "learning_rate": 8.780108051455205e-05,
472
+ "loss": 96.71749877929688,
473
+ "original_ce_loss": 3.0218,
474
+ "step": 580
475
+ },
476
+ {
477
+ "epoch": 2.4397199896292454,
478
+ "grad_norm": 31.261812210083008,
479
+ "learning_rate": 7.775275457198821e-05,
480
+ "loss": 95.91024169921874,
481
+ "original_ce_loss": 2.9966,
482
+ "step": 590
483
+ },
484
+ {
485
+ "epoch": 2.481203007518797,
486
+ "grad_norm": 25.36027717590332,
487
+ "learning_rate": 6.818495701542595e-05,
488
+ "loss": 95.57075805664063,
489
+ "original_ce_loss": 2.986,
490
+ "step": 600
491
+ }
492
+ ],
493
+ "logging_steps": 10,
494
+ "max_steps": 726,
495
+ "num_input_tokens_seen": 0,
496
+ "num_train_epochs": 3,
497
+ "save_steps": 200,
498
+ "stateful_callbacks": {
499
+ "TrainerControl": {
500
+ "args": {
501
+ "should_epoch_stop": false,
502
+ "should_evaluate": false,
503
+ "should_log": false,
504
+ "should_save": true,
505
+ "should_training_stop": false
506
+ },
507
+ "attributes": {}
508
+ }
509
+ },
510
+ "total_flos": 4.867238337530266e+16,
511
+ "train_batch_size": 64,
512
+ "trial_name": null,
513
+ "trial_params": null
514
+ }
checkpoint-600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b845ce760bd1493cd648205f56910b60464e6673859cd8682fc98a63336dba
3
+ size 5137