Grogros commited on
Commit
2f84e4a
·
verified ·
1 Parent(s): 9197115

Training in progress, step 9500, checkpoint

Browse files
checkpoint-9500/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Grogros/dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-Al4-wmToken-d4-a0.1-v2-meta-OWT",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.46.3",
38
+ "use_cache": true,
39
+ "vocab_size": 128257
40
+ }
checkpoint-9500/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.46.3"
12
+ }
checkpoint-9500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdd633b04229c961e285dea6dada5ec45057460aa8356dc84e05c2b72c66067f
3
+ size 4943282520
checkpoint-9500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8362d40cff6be49d97909f59057b2f55af6a502114d7e989d311ea339069546e
3
+ size 3724602
checkpoint-9500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d336714399c80ddfe367b756a73b8144d9b6106f556a10ff17e9dbd70dd1b18
3
+ size 14244
checkpoint-9500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:577098e0ae1c819d6afdd5981f4f6c29461b3919cbdf4f9252ee6f6c3fe79529
3
+ size 1064
checkpoint-9500/trainer_state.json ADDED
@@ -0,0 +1,698 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2910494630903326,
5
+ "eval_steps": 500,
6
+ "global_step": 9500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.003063678558845606,
13
+ "grad_norm": 2.5270798206329346,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 3.1564,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.006127357117691212,
20
+ "grad_norm": 2.604092597961426,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 3.1166,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.009191035676536818,
27
+ "grad_norm": 2.5005924701690674,
28
+ "learning_rate": 3e-06,
29
+ "loss": 3.0905,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.012254714235382424,
34
+ "grad_norm": 2.7525177001953125,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 3.0652,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.015318392794228029,
41
+ "grad_norm": 2.5251283645629883,
42
+ "learning_rate": 5e-06,
43
+ "loss": 3.0351,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.018382071353073636,
48
+ "grad_norm": 2.6771860122680664,
49
+ "learning_rate": 6e-06,
50
+ "loss": 3.0028,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.02144574991191924,
55
+ "grad_norm": 2.4799458980560303,
56
+ "learning_rate": 7e-06,
57
+ "loss": 3.0007,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.024509428470764847,
62
+ "grad_norm": 2.8402369022369385,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 2.9753,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.027573107029610452,
69
+ "grad_norm": 2.446842908859253,
70
+ "learning_rate": 9e-06,
71
+ "loss": 2.9737,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.030636785588456058,
76
+ "grad_norm": 2.3989391326904297,
77
+ "learning_rate": 1e-05,
78
+ "loss": 2.9618,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.03370046414730166,
83
+ "grad_norm": 2.469160795211792,
84
+ "learning_rate": 9.99695413509548e-06,
85
+ "loss": 2.928,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.03676414270614727,
90
+ "grad_norm": 2.4107494354248047,
91
+ "learning_rate": 9.987820251299121e-06,
92
+ "loss": 2.9214,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.039827821264992874,
97
+ "grad_norm": 2.540278911590576,
98
+ "learning_rate": 9.972609476841368e-06,
99
+ "loss": 2.9198,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.04289149982383848,
104
+ "grad_norm": 2.4398670196533203,
105
+ "learning_rate": 9.951340343707852e-06,
106
+ "loss": 2.9182,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.04595517838268409,
111
+ "grad_norm": 2.49687123298645,
112
+ "learning_rate": 9.924038765061042e-06,
113
+ "loss": 2.8994,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.049018856941529694,
118
+ "grad_norm": 2.4655182361602783,
119
+ "learning_rate": 9.890738003669029e-06,
120
+ "loss": 2.8805,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.0520825355003753,
125
+ "grad_norm": 2.4170656204223633,
126
+ "learning_rate": 9.851478631379982e-06,
127
+ "loss": 2.8829,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.055146214059220905,
132
+ "grad_norm": 2.362334966659546,
133
+ "learning_rate": 9.806308479691595e-06,
134
+ "loss": 2.8891,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.058209892618066514,
139
+ "grad_norm": 2.426173210144043,
140
+ "learning_rate": 9.755282581475769e-06,
141
+ "loss": 2.875,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.061273571176912116,
146
+ "grad_norm": 2.6380629539489746,
147
+ "learning_rate": 9.698463103929542e-06,
148
+ "loss": 2.879,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.06433724973575772,
153
+ "grad_norm": 2.5123095512390137,
154
+ "learning_rate": 9.635919272833938e-06,
155
+ "loss": 2.8622,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.06740092829460333,
160
+ "grad_norm": 2.3789472579956055,
161
+ "learning_rate": 9.567727288213005e-06,
162
+ "loss": 2.8669,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.07046460685344894,
167
+ "grad_norm": 2.387221336364746,
168
+ "learning_rate": 9.493970231495836e-06,
169
+ "loss": 2.8641,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.07352828541229454,
174
+ "grad_norm": 2.4947221279144287,
175
+ "learning_rate": 9.414737964294636e-06,
176
+ "loss": 2.8525,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.07659196397114015,
181
+ "grad_norm": 2.390381097793579,
182
+ "learning_rate": 9.330127018922195e-06,
183
+ "loss": 2.8497,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.07965564252998575,
188
+ "grad_norm": 2.451345682144165,
189
+ "learning_rate": 9.24024048078213e-06,
190
+ "loss": 2.8482,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.08271932108883136,
195
+ "grad_norm": 2.317512035369873,
196
+ "learning_rate": 9.145187862775208e-06,
197
+ "loss": 2.8486,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.08578299964767697,
202
+ "grad_norm": 2.620295524597168,
203
+ "learning_rate": 9.045084971874738e-06,
204
+ "loss": 2.8474,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.08884667820652258,
209
+ "grad_norm": 2.3616020679473877,
210
+ "learning_rate": 8.94005376803361e-06,
211
+ "loss": 2.8283,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.09191035676536818,
216
+ "grad_norm": 2.517153263092041,
217
+ "learning_rate": 8.83022221559489e-06,
218
+ "loss": 2.8451,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.09497403532421378,
223
+ "grad_norm": 2.6935179233551025,
224
+ "learning_rate": 8.715724127386971e-06,
225
+ "loss": 2.8472,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.09803771388305939,
230
+ "grad_norm": 2.4080545902252197,
231
+ "learning_rate": 8.596699001693257e-06,
232
+ "loss": 2.8428,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.101101392441905,
237
+ "grad_norm": 2.369750499725342,
238
+ "learning_rate": 8.473291852294986e-06,
239
+ "loss": 2.829,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.1041650710007506,
244
+ "grad_norm": 2.3385934829711914,
245
+ "learning_rate": 8.345653031794292e-06,
246
+ "loss": 2.8349,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.1072287495595962,
251
+ "grad_norm": 2.2659566402435303,
252
+ "learning_rate": 8.213938048432697e-06,
253
+ "loss": 2.8306,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.11029242811844181,
258
+ "grad_norm": 2.508164882659912,
259
+ "learning_rate": 8.078307376628292e-06,
260
+ "loss": 2.8225,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.11335610667728742,
265
+ "grad_norm": 2.302351713180542,
266
+ "learning_rate": 7.938926261462366e-06,
267
+ "loss": 2.808,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.11641978523613303,
272
+ "grad_norm": 2.3972647190093994,
273
+ "learning_rate": 7.795964517353734e-06,
274
+ "loss": 2.8214,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.11948346379497864,
279
+ "grad_norm": 2.4006614685058594,
280
+ "learning_rate": 7.649596321166024e-06,
281
+ "loss": 2.8198,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.12254714235382423,
286
+ "grad_norm": 2.271172285079956,
287
+ "learning_rate": 7.500000000000001e-06,
288
+ "loss": 2.8186,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.12561082091266984,
293
+ "grad_norm": 2.3733065128326416,
294
+ "learning_rate": 7.347357813929455e-06,
295
+ "loss": 2.8192,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.12867449947151544,
300
+ "grad_norm": 2.3404409885406494,
301
+ "learning_rate": 7.191855733945388e-06,
302
+ "loss": 2.8235,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.13173817803036106,
307
+ "grad_norm": 2.417692184448242,
308
+ "learning_rate": 7.033683215379002e-06,
309
+ "loss": 2.8109,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.13480185658920665,
314
+ "grad_norm": 2.3670148849487305,
315
+ "learning_rate": 6.873032967079562e-06,
316
+ "loss": 2.8204,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.13786553514805228,
321
+ "grad_norm": 2.336367130279541,
322
+ "learning_rate": 6.710100716628345e-06,
323
+ "loss": 2.8056,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.14092921370689787,
328
+ "grad_norm": 2.3793513774871826,
329
+ "learning_rate": 6.545084971874738e-06,
330
+ "loss": 2.7987,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.14399289226574347,
335
+ "grad_norm": 2.3895699977874756,
336
+ "learning_rate": 6.378186779084996e-06,
337
+ "loss": 2.8127,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.1470565708245891,
342
+ "grad_norm": 2.288458824157715,
343
+ "learning_rate": 6.209609477998339e-06,
344
+ "loss": 2.8111,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.15012024938343468,
349
+ "grad_norm": 2.299058437347412,
350
+ "learning_rate": 6.039558454088796e-06,
351
+ "loss": 2.7945,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.1531839279422803,
356
+ "grad_norm": 2.3097774982452393,
357
+ "learning_rate": 5.8682408883346535e-06,
358
+ "loss": 2.7981,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.1562476065011259,
363
+ "grad_norm": 2.433981418609619,
364
+ "learning_rate": 5.695865504800328e-06,
365
+ "loss": 2.7938,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.1593112850599715,
370
+ "grad_norm": 2.2754006385803223,
371
+ "learning_rate": 5.522642316338268e-06,
372
+ "loss": 2.7886,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.16237496361881712,
377
+ "grad_norm": 2.3001139163970947,
378
+ "learning_rate": 5.348782368720627e-06,
379
+ "loss": 2.8008,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.16543864217766271,
384
+ "grad_norm": 2.365751266479492,
385
+ "learning_rate": 5.174497483512506e-06,
386
+ "loss": 2.7858,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.16850232073650834,
391
+ "grad_norm": 2.448115348815918,
392
+ "learning_rate": 5e-06,
393
+ "loss": 2.795,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.17156599929535393,
398
+ "grad_norm": 2.414354085922241,
399
+ "learning_rate": 4.825502516487497e-06,
400
+ "loss": 2.7971,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 0.17462967785419953,
405
+ "grad_norm": 2.447974443435669,
406
+ "learning_rate": 4.651217631279374e-06,
407
+ "loss": 2.7803,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 0.17769335641304515,
412
+ "grad_norm": 2.38202166557312,
413
+ "learning_rate": 4.477357683661734e-06,
414
+ "loss": 2.784,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 0.18075703497189075,
419
+ "grad_norm": 2.391268730163574,
420
+ "learning_rate": 4.304134495199675e-06,
421
+ "loss": 2.7903,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 0.18382071353073637,
426
+ "grad_norm": 2.351288318634033,
427
+ "learning_rate": 4.131759111665349e-06,
428
+ "loss": 2.7788,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 0.18688439208958196,
433
+ "grad_norm": 2.399247169494629,
434
+ "learning_rate": 3.960441545911205e-06,
435
+ "loss": 2.7868,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 0.18994807064842756,
440
+ "grad_norm": 2.426527976989746,
441
+ "learning_rate": 3.790390522001662e-06,
442
+ "loss": 2.8012,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 0.19301174920727318,
447
+ "grad_norm": 2.3167338371276855,
448
+ "learning_rate": 3.6218132209150047e-06,
449
+ "loss": 2.774,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 0.19607542776611878,
454
+ "grad_norm": 2.2909271717071533,
455
+ "learning_rate": 3.4549150281252635e-06,
456
+ "loss": 2.7715,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 0.19913910632496437,
461
+ "grad_norm": 2.3950772285461426,
462
+ "learning_rate": 3.289899283371657e-06,
463
+ "loss": 2.7832,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 0.20220278488381,
468
+ "grad_norm": 2.5031042098999023,
469
+ "learning_rate": 3.12696703292044e-06,
470
+ "loss": 2.7801,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 0.2052664634426556,
475
+ "grad_norm": 2.3458404541015625,
476
+ "learning_rate": 2.966316784621e-06,
477
+ "loss": 2.7788,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 0.2083301420015012,
482
+ "grad_norm": 2.3030614852905273,
483
+ "learning_rate": 2.8081442660546126e-06,
484
+ "loss": 2.772,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 0.2113938205603468,
489
+ "grad_norm": 2.2177374362945557,
490
+ "learning_rate": 2.6526421860705474e-06,
491
+ "loss": 2.7706,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 0.2144574991191924,
496
+ "grad_norm": 2.2889530658721924,
497
+ "learning_rate": 2.5000000000000015e-06,
498
+ "loss": 2.7721,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 0.21752117767803802,
503
+ "grad_norm": 2.288100481033325,
504
+ "learning_rate": 2.3504036788339763e-06,
505
+ "loss": 2.7774,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 0.22058485623688362,
510
+ "grad_norm": 2.3013720512390137,
511
+ "learning_rate": 2.204035482646267e-06,
512
+ "loss": 2.7739,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 0.22364853479572924,
517
+ "grad_norm": 2.4036357402801514,
518
+ "learning_rate": 2.061073738537635e-06,
519
+ "loss": 2.7759,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 0.22671221335457484,
524
+ "grad_norm": 2.35628080368042,
525
+ "learning_rate": 1.9216926233717087e-06,
526
+ "loss": 2.7724,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 0.22977589191342043,
531
+ "grad_norm": 2.314425230026245,
532
+ "learning_rate": 1.7860619515673034e-06,
533
+ "loss": 2.7742,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 0.23283957047226606,
538
+ "grad_norm": 2.299058437347412,
539
+ "learning_rate": 1.6543469682057105e-06,
540
+ "loss": 2.7643,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 0.23590324903111165,
545
+ "grad_norm": 2.355900526046753,
546
+ "learning_rate": 1.5267081477050132e-06,
547
+ "loss": 2.7825,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 0.23896692758995727,
552
+ "grad_norm": 2.3373987674713135,
553
+ "learning_rate": 1.4033009983067454e-06,
554
+ "loss": 2.7619,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 0.24203060614880287,
559
+ "grad_norm": 2.256110906600952,
560
+ "learning_rate": 1.2842758726130283e-06,
561
+ "loss": 2.7836,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 0.24509428470764846,
566
+ "grad_norm": 2.3769350051879883,
567
+ "learning_rate": 1.1697777844051105e-06,
568
+ "loss": 2.7672,
569
+ "step": 8000
570
+ },
571
+ {
572
+ "epoch": 0.24815796326649409,
573
+ "grad_norm": 2.2622389793395996,
574
+ "learning_rate": 1.0599462319663906e-06,
575
+ "loss": 2.7871,
576
+ "step": 8100
577
+ },
578
+ {
579
+ "epoch": 0.2512216418253397,
580
+ "grad_norm": 2.379034996032715,
581
+ "learning_rate": 9.549150281252633e-07,
582
+ "loss": 2.7807,
583
+ "step": 8200
584
+ },
585
+ {
586
+ "epoch": 0.2542853203841853,
587
+ "grad_norm": 2.3284192085266113,
588
+ "learning_rate": 8.54812137224792e-07,
589
+ "loss": 2.78,
590
+ "step": 8300
591
+ },
592
+ {
593
+ "epoch": 0.25734899894303087,
594
+ "grad_norm": 2.2942214012145996,
595
+ "learning_rate": 7.597595192178702e-07,
596
+ "loss": 2.7681,
597
+ "step": 8400
598
+ },
599
+ {
600
+ "epoch": 0.2604126775018765,
601
+ "grad_norm": 2.3023951053619385,
602
+ "learning_rate": 6.698729810778065e-07,
603
+ "loss": 2.771,
604
+ "step": 8500
605
+ },
606
+ {
607
+ "epoch": 0.2634763560607221,
608
+ "grad_norm": 2.333832263946533,
609
+ "learning_rate": 5.852620357053651e-07,
610
+ "loss": 2.7572,
611
+ "step": 8600
612
+ },
613
+ {
614
+ "epoch": 0.2665400346195677,
615
+ "grad_norm": 2.285566568374634,
616
+ "learning_rate": 5.06029768504166e-07,
617
+ "loss": 2.763,
618
+ "step": 8700
619
+ },
620
+ {
621
+ "epoch": 0.2696037131784133,
622
+ "grad_norm": 2.388606548309326,
623
+ "learning_rate": 4.322727117869951e-07,
624
+ "loss": 2.7709,
625
+ "step": 8800
626
+ },
627
+ {
628
+ "epoch": 0.2726673917372589,
629
+ "grad_norm": 2.2247579097747803,
630
+ "learning_rate": 3.6408072716606346e-07,
631
+ "loss": 2.7626,
632
+ "step": 8900
633
+ },
634
+ {
635
+ "epoch": 0.27573107029610455,
636
+ "grad_norm": 2.358264923095703,
637
+ "learning_rate": 3.015368960704584e-07,
638
+ "loss": 2.7526,
639
+ "step": 9000
640
+ },
641
+ {
642
+ "epoch": 0.27879474885495015,
643
+ "grad_norm": 2.289626121520996,
644
+ "learning_rate": 2.447174185242324e-07,
645
+ "loss": 2.7601,
646
+ "step": 9100
647
+ },
648
+ {
649
+ "epoch": 0.28185842741379574,
650
+ "grad_norm": 2.3193247318267822,
651
+ "learning_rate": 1.9369152030840553e-07,
652
+ "loss": 2.7659,
653
+ "step": 9200
654
+ },
655
+ {
656
+ "epoch": 0.28492210597264134,
657
+ "grad_norm": 2.3154854774475098,
658
+ "learning_rate": 1.4852136862001766e-07,
659
+ "loss": 2.7695,
660
+ "step": 9300
661
+ },
662
+ {
663
+ "epoch": 0.28798578453148693,
664
+ "grad_norm": 2.2537918090820312,
665
+ "learning_rate": 1.0926199633097156e-07,
666
+ "loss": 2.7579,
667
+ "step": 9400
668
+ },
669
+ {
670
+ "epoch": 0.2910494630903326,
671
+ "grad_norm": 2.223071813583374,
672
+ "learning_rate": 7.59612349389599e-08,
673
+ "loss": 2.7568,
674
+ "step": 9500
675
+ }
676
+ ],
677
+ "logging_steps": 100,
678
+ "max_steps": 10000,
679
+ "num_input_tokens_seen": 0,
680
+ "num_train_epochs": 1,
681
+ "save_steps": 500,
682
+ "stateful_callbacks": {
683
+ "TrainerControl": {
684
+ "args": {
685
+ "should_epoch_stop": false,
686
+ "should_evaluate": false,
687
+ "should_log": false,
688
+ "should_save": true,
689
+ "should_training_stop": false
690
+ },
691
+ "attributes": {}
692
+ }
693
+ },
694
+ "total_flos": 9.08809476243456e+17,
695
+ "train_batch_size": 16,
696
+ "trial_name": null,
697
+ "trial_params": null
698
+ }
checkpoint-9500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343fd12cd57f4f5c4c4d092162b0058e69041ee73092ab79cda1f02d0d79adab
3
+ size 5368