Hugging Face's logo

xinyanghuang
/
Basic-Visual-Language-Model

Visual Question Answering
Model card Files
xet
Community
xinyanghuang commited on
Commit
ef1258e
·
verified ·
1 Parent(s): c415380

Upload 11 files

Browse files
Files changed (11) hide show
  1. checkpoint-7000/checkpoint-7000/adapter_config.json +18 -0
  2. checkpoint-7000/checkpoint-7000/adapter_model.bin +3 -0
  3. checkpoint-7000/checkpoint-7000/optimizer.pt +3 -0
  4. checkpoint-7000/checkpoint-7000/other_params.bin +3 -0
  5. checkpoint-7000/checkpoint-7000/rng_state_0.pth +3 -0
  6. checkpoint-7000/checkpoint-7000/rng_state_1.pth +3 -0
  7. checkpoint-7000/checkpoint-7000/rng_state_2.pth +3 -0
  8. checkpoint-7000/checkpoint-7000/rng_state_3.pth +3 -0
  9. checkpoint-7000/checkpoint-7000/scheduler.pt +3 -0
  10. checkpoint-7000/checkpoint-7000/trainer_state.json +523 -0
  11. checkpoint-7000/checkpoint-7000/training_args.bin +3 -0
checkpoint-7000/checkpoint-7000/adapter_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "Qwen/Qwen-7B-Chat",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": false,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 32,
8
+ "lora_dropout": 0.1,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 128,
12
+ "target_modules": [
13
+ "c_attn",
14
+ "w1",
15
+ "w2"
16
+ ],
17
+ "task_type": "CAUSAL_LM"
18
+ }
checkpoint-7000/checkpoint-7000/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec69714a183fca4b61032438a74423a558d21b16af0507c38bd1d30c8717c349
3
+ size 763431181
checkpoint-7000/checkpoint-7000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b168e87e12d24dbef145953697ab52eecbeee73dc09fd31202ba7512f5e45c1e
3
+ size 1612910405
checkpoint-7000/checkpoint-7000/other_params.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a23f357e944105f9e1814f0ddc317ec25a7e2981a02503c6b29b32430f81784
3
+ size 43009725
checkpoint-7000/checkpoint-7000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d22e1c1f9dcc565cf6884c3e8f5ae98131cd3919a7b401d2958b6d5d72680fce
3
+ size 17655
checkpoint-7000/checkpoint-7000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee1a6d444a26b3153d226442177110c8c5949bfe7a582d1583081613b56cffe
3
+ size 17655
checkpoint-7000/checkpoint-7000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58379c3e95dc9fa5cbd8dadccaf699da8720e1613e0f1f9268ee8898218a1a57
3
+ size 17655
checkpoint-7000/checkpoint-7000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26340e115f8e048c2e52d34b4766dba594848350c7915ba3dd2ea82564ace1c5
3
+ size 17655
checkpoint-7000/checkpoint-7000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c17cec678cdfc08e2ee6daa1c23cfc32d3a4ee58795129200a07f8092a63bfd
3
+ size 627
checkpoint-7000/checkpoint-7000/trainer_state.json ADDED
@@ -0,0 +1,523 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.3878975950349108,
5
+ "eval_steps": 500,
6
+ "global_step": 7000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00554139421478444,
13
+ "grad_norm": 0.7744311690330505,
14
+ "learning_rate": 2.9916879086778235e-05,
15
+ "loss": 2.174,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.01108278842956888,
20
+ "grad_norm": 1.1890419721603394,
21
+ "learning_rate": 2.983375817355647e-05,
22
+ "loss": 1.7489,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.01662418264435332,
27
+ "grad_norm": 2.874730348587036,
28
+ "learning_rate": 2.97506372603347e-05,
29
+ "loss": 1.6593,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.02216557685913776,
34
+ "grad_norm": 0.4631105363368988,
35
+ "learning_rate": 2.9667516347112933e-05,
36
+ "loss": 1.5928,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.0277069710739222,
41
+ "grad_norm": 1.1168841123580933,
42
+ "learning_rate": 2.9584395433891167e-05,
43
+ "loss": 1.5494,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.03324836528870664,
48
+ "grad_norm": 0.8050689101219177,
49
+ "learning_rate": 2.95012745206694e-05,
50
+ "loss": 1.5041,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.038789759503491075,
55
+ "grad_norm": 2.871495008468628,
56
+ "learning_rate": 2.9418153607447632e-05,
57
+ "loss": 1.4829,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.04433115371827552,
62
+ "grad_norm": 0.6971802711486816,
63
+ "learning_rate": 2.9335032694225866e-05,
64
+ "loss": 1.4492,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.04987254793305996,
69
+ "grad_norm": 1.1272006034851074,
70
+ "learning_rate": 2.92519117810041e-05,
71
+ "loss": 1.45,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.0554139421478444,
76
+ "grad_norm": 0.9110287427902222,
77
+ "learning_rate": 2.9168790867782334e-05,
78
+ "loss": 1.4553,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.060955336362628836,
83
+ "grad_norm": 2.7382473945617676,
84
+ "learning_rate": 2.9085669954560568e-05,
85
+ "loss": 1.4244,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.06649673057741327,
90
+ "grad_norm": 2.678687334060669,
91
+ "learning_rate": 2.9002549041338802e-05,
92
+ "loss": 1.4399,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.07203812479219772,
97
+ "grad_norm": 0.8868110775947571,
98
+ "learning_rate": 2.8919428128117036e-05,
99
+ "loss": 1.408,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.07757951900698215,
104
+ "grad_norm": 0.7350853085517883,
105
+ "learning_rate": 2.883630721489527e-05,
106
+ "loss": 1.4128,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.0831209132217666,
111
+ "grad_norm": 2.349001169204712,
112
+ "learning_rate": 2.8753186301673504e-05,
113
+ "loss": 1.4154,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.08866230743655104,
118
+ "grad_norm": 2.588608503341675,
119
+ "learning_rate": 2.8670065388451735e-05,
120
+ "loss": 1.4102,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.09420370165133547,
125
+ "grad_norm": 3.461966037750244,
126
+ "learning_rate": 2.858694447522997e-05,
127
+ "loss": 1.3899,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.09974509586611992,
132
+ "grad_norm": 0.9384596943855286,
133
+ "learning_rate": 2.8503823562008203e-05,
134
+ "loss": 1.3946,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.10528649008090435,
139
+ "grad_norm": 2.6963839530944824,
140
+ "learning_rate": 2.8420702648786437e-05,
141
+ "loss": 1.3625,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.1108278842956888,
146
+ "grad_norm": 1.2156896591186523,
147
+ "learning_rate": 2.8337581735564668e-05,
148
+ "loss": 1.3998,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.11636927851047324,
153
+ "grad_norm": 0.9613581299781799,
154
+ "learning_rate": 2.82544608223429e-05,
155
+ "loss": 1.3672,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.12191067272525767,
160
+ "grad_norm": 0.8994789719581604,
161
+ "learning_rate": 2.8171339909121136e-05,
162
+ "loss": 1.3587,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.1274520669400421,
167
+ "grad_norm": 1.7463105916976929,
168
+ "learning_rate": 2.808821899589937e-05,
169
+ "loss": 1.3688,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.13299346115482655,
174
+ "grad_norm": 0.7639077305793762,
175
+ "learning_rate": 2.8005098082677604e-05,
176
+ "loss": 1.3798,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.138534855369611,
181
+ "grad_norm": 1.313306450843811,
182
+ "learning_rate": 2.7921977169455834e-05,
183
+ "loss": 1.3713,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.14407624958439544,
188
+ "grad_norm": 1.796030044555664,
189
+ "learning_rate": 2.783885625623407e-05,
190
+ "loss": 1.3589,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.14961764379917988,
195
+ "grad_norm": 0.40334078669548035,
196
+ "learning_rate": 2.7755735343012302e-05,
197
+ "loss": 1.3527,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.1551590380139643,
202
+ "grad_norm": 0.7727888822555542,
203
+ "learning_rate": 2.7672614429790536e-05,
204
+ "loss": 1.338,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.16070043222874875,
209
+ "grad_norm": 0.8815018534660339,
210
+ "learning_rate": 2.7589493516568767e-05,
211
+ "loss": 1.3638,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.1662418264435332,
216
+ "grad_norm": 1.1675957441329956,
217
+ "learning_rate": 2.7506372603347e-05,
218
+ "loss": 1.3462,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.17178322065831764,
223
+ "grad_norm": 0.9449867606163025,
224
+ "learning_rate": 2.7423251690125235e-05,
225
+ "loss": 1.3286,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.17732461487310208,
230
+ "grad_norm": 0.4934576749801636,
231
+ "learning_rate": 2.734013077690347e-05,
232
+ "loss": 1.3326,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.1828660090878865,
237
+ "grad_norm": 1.0242582559585571,
238
+ "learning_rate": 2.7257009863681703e-05,
239
+ "loss": 1.3423,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.18840740330267094,
244
+ "grad_norm": 1.253219723701477,
245
+ "learning_rate": 2.7173888950459934e-05,
246
+ "loss": 1.3473,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.1939487975174554,
251
+ "grad_norm": 2.4441049098968506,
252
+ "learning_rate": 2.7090768037238168e-05,
253
+ "loss": 1.3321,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.19949019173223984,
258
+ "grad_norm": 1.119807481765747,
259
+ "learning_rate": 2.7007647124016405e-05,
260
+ "loss": 1.3282,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.20503158594702428,
265
+ "grad_norm": 0.5911545157432556,
266
+ "learning_rate": 2.692452621079464e-05,
267
+ "loss": 1.329,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.2105729801618087,
272
+ "grad_norm": 1.959672451019287,
273
+ "learning_rate": 2.684140529757287e-05,
274
+ "loss": 1.3322,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.21611437437659314,
279
+ "grad_norm": 0.9169633984565735,
280
+ "learning_rate": 2.6758284384351104e-05,
281
+ "loss": 1.3248,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.2216557685913776,
286
+ "grad_norm": 0.8207225203514099,
287
+ "learning_rate": 2.6675163471129338e-05,
288
+ "loss": 1.3303,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.22719716280616203,
293
+ "grad_norm": 1.0271358489990234,
294
+ "learning_rate": 2.6592042557907572e-05,
295
+ "loss": 1.3231,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.23273855702094648,
300
+ "grad_norm": 1.2483460903167725,
301
+ "learning_rate": 2.6508921644685806e-05,
302
+ "loss": 1.3234,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.2382799512357309,
307
+ "grad_norm": 0.8641893863677979,
308
+ "learning_rate": 2.6425800731464037e-05,
309
+ "loss": 1.2856,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.24382134545051534,
314
+ "grad_norm": 1.6275527477264404,
315
+ "learning_rate": 2.634267981824227e-05,
316
+ "loss": 1.3039,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.2493627396652998,
321
+ "grad_norm": 2.3479559421539307,
322
+ "learning_rate": 2.6259558905020505e-05,
323
+ "loss": 1.331,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.2549041338800842,
328
+ "grad_norm": 2.3728585243225098,
329
+ "learning_rate": 2.617643799179874e-05,
330
+ "loss": 1.3115,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.26044552809486865,
335
+ "grad_norm": 1.7304351329803467,
336
+ "learning_rate": 2.609331707857697e-05,
337
+ "loss": 1.32,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.2659869223096531,
342
+ "grad_norm": 3.1707870960235596,
343
+ "learning_rate": 2.6010196165355203e-05,
344
+ "loss": 1.3166,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.27152831652443754,
349
+ "grad_norm": 0.6431360840797424,
350
+ "learning_rate": 2.5927075252133437e-05,
351
+ "loss": 1.3117,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.277069710739222,
356
+ "grad_norm": 0.7438284754753113,
357
+ "learning_rate": 2.584395433891167e-05,
358
+ "loss": 1.3049,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.28261110495400643,
363
+ "grad_norm": 0.8397496342658997,
364
+ "learning_rate": 2.5760833425689905e-05,
365
+ "loss": 1.3013,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.2881524991687909,
370
+ "grad_norm": 1.3787566423416138,
371
+ "learning_rate": 2.5677712512468136e-05,
372
+ "loss": 1.32,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.2936938933835753,
377
+ "grad_norm": 0.6342838406562805,
378
+ "learning_rate": 2.559459159924637e-05,
379
+ "loss": 1.3265,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.29923528759835977,
384
+ "grad_norm": 1.0924850702285767,
385
+ "learning_rate": 2.5511470686024604e-05,
386
+ "loss": 1.3224,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.3047766818131442,
391
+ "grad_norm": 3.104914665222168,
392
+ "learning_rate": 2.5428349772802838e-05,
393
+ "loss": 1.2897,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.3103180760279286,
398
+ "grad_norm": 1.219292163848877,
399
+ "learning_rate": 2.534522885958107e-05,
400
+ "loss": 1.3013,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 0.31585947024271305,
405
+ "grad_norm": 0.743425726890564,
406
+ "learning_rate": 2.5262107946359303e-05,
407
+ "loss": 1.3069,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 0.3214008644574975,
412
+ "grad_norm": 3.0548131465911865,
413
+ "learning_rate": 2.5178987033137537e-05,
414
+ "loss": 1.3006,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 0.32694225867228194,
419
+ "grad_norm": 2.6230878829956055,
420
+ "learning_rate": 2.5095866119915774e-05,
421
+ "loss": 1.2954,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 0.3324836528870664,
426
+ "grad_norm": 1.5894700288772583,
427
+ "learning_rate": 2.5012745206694005e-05,
428
+ "loss": 1.2918,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 0.33802504710185083,
433
+ "grad_norm": 2.298469066619873,
434
+ "learning_rate": 2.492962429347224e-05,
435
+ "loss": 1.2974,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 0.3435664413166353,
440
+ "grad_norm": 2.3570539951324463,
441
+ "learning_rate": 2.4846503380250473e-05,
442
+ "loss": 1.2943,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 0.3491078355314197,
447
+ "grad_norm": 0.7656165361404419,
448
+ "learning_rate": 2.4763382467028707e-05,
449
+ "loss": 1.2774,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 0.35464922974620416,
454
+ "grad_norm": 0.9744777679443359,
455
+ "learning_rate": 2.468026155380694e-05,
456
+ "loss": 1.3062,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 0.3601906239609886,
461
+ "grad_norm": 2.929172992706299,
462
+ "learning_rate": 2.459714064058517e-05,
463
+ "loss": 1.2871,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 0.365732018175773,
468
+ "grad_norm": 1.1587573289871216,
469
+ "learning_rate": 2.4514019727363405e-05,
470
+ "loss": 1.3037,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 0.37127341239055744,
475
+ "grad_norm": 1.055335521697998,
476
+ "learning_rate": 2.443089881414164e-05,
477
+ "loss": 1.2823,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 0.3768148066053419,
482
+ "grad_norm": 2.3376619815826416,
483
+ "learning_rate": 2.4347777900919873e-05,
484
+ "loss": 1.2854,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 0.38235620082012634,
489
+ "grad_norm": 0.94229656457901,
490
+ "learning_rate": 2.4264656987698104e-05,
491
+ "loss": 1.3007,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 0.3878975950349108,
496
+ "grad_norm": 1.2927848100662231,
497
+ "learning_rate": 2.4181536074476338e-05,
498
+ "loss": 1.278,
499
+ "step": 7000
500
+ }
501
+ ],
502
+ "logging_steps": 100,
503
+ "max_steps": 36092,
504
+ "num_input_tokens_seen": 0,
505
+ "num_train_epochs": 2,
506
+ "save_steps": 1000,
507
+ "stateful_callbacks": {
508
+ "TrainerControl": {
509
+ "args": {
510
+ "should_epoch_stop": false,
511
+ "should_evaluate": false,
512
+ "should_log": false,
513
+ "should_save": true,
514
+ "should_training_stop": false
515
+ },
516
+ "attributes": {}
517
+ }
518
+ },
519
+ "total_flos": 0.0,
520
+ "train_batch_size": 4,
521
+ "trial_name": null,
522
+ "trial_params": null
523
+ }
checkpoint-7000/checkpoint-7000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a725a323205e8f7faf8ef9c3151f198ebf1f0262412da00544cb74991be2dedd
3
+ size 4667