yamraj047 commited on
Commit
95eb30a
·
verified ·
1 Parent(s): 9e2afa9

Upload 8 files

Browse files
adapter_config-5.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "k_proj",
29
+ "q_proj",
30
+ "gate_proj",
31
+ "down_proj",
32
+ "o_proj",
33
+ "v_proj",
34
+ "up_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
adapter_model-5.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad0f1253b2c8ac07a751c03f565e5d251e689993143203d8378ec7dfafa765b
3
+ size 167832240
optimizer-4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2ac8f0323ce07c4e6d8dfb09faa0c9dd8b8c97b3f0d6b8ed26a34ebb175f614
3
+ size 85733607
rng_state-3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a641ee64a7e66a166dda1f776456c25c127c42b9d58eb142b12bd030397098c
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:584227e194f3c31379bbb0cf9ccc9658f1b948c01142ef7597b35f5f3e33cd26
3
+ size 1383
scheduler-3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d43faf14a56949c9a9c59ced0c0557ca82878eb9914fa86c8bd1eb2132e0db6
3
+ size 1465
trainer_state-5.json ADDED
@@ -0,0 +1,609 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 810,
3
+ "best_metric": 0.7329609990119934,
4
+ "best_model_checkpoint": "./nepal-legal-model/checkpoint-810",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 810,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.012345679012345678,
14
+ "grad_norm": 2.1483232975006104,
15
+ "learning_rate": 2.4657534246575342e-05,
16
+ "loss": 1.8579,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.024691358024691357,
21
+ "grad_norm": 2.067028045654297,
22
+ "learning_rate": 5.2054794520547945e-05,
23
+ "loss": 1.4274,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.037037037037037035,
28
+ "grad_norm": 1.7251120805740356,
29
+ "learning_rate": 7.945205479452055e-05,
30
+ "loss": 1.0776,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.04938271604938271,
35
+ "grad_norm": 1.4287426471710205,
36
+ "learning_rate": 0.00010684931506849317,
37
+ "loss": 1.0135,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.06172839506172839,
42
+ "grad_norm": 1.3038461208343506,
43
+ "learning_rate": 0.00013424657534246576,
44
+ "loss": 0.9539,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.07407407407407407,
49
+ "grad_norm": 1.2418831586837769,
50
+ "learning_rate": 0.00016164383561643837,
51
+ "loss": 0.9208,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.08641975308641975,
56
+ "grad_norm": 1.1602648496627808,
57
+ "learning_rate": 0.00018904109589041096,
58
+ "loss": 0.9139,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.09876543209876543,
63
+ "grad_norm": 1.1099259853363037,
64
+ "learning_rate": 0.0001999968022038833,
65
+ "loss": 0.9438,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1111111111111111,
70
+ "grad_norm": 1.0900254249572754,
71
+ "learning_rate": 0.0001999772608571399,
72
+ "loss": 0.8994,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.12345679012345678,
77
+ "grad_norm": 1.1199110746383667,
78
+ "learning_rate": 0.0001999399581844347,
79
+ "loss": 0.8972,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.13580246913580246,
84
+ "grad_norm": 1.1685237884521484,
85
+ "learning_rate": 0.00019988490081272397,
86
+ "loss": 0.8753,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.14814814814814814,
91
+ "grad_norm": 1.0480120182037354,
92
+ "learning_rate": 0.0001998120985231511,
93
+ "loss": 0.8805,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.16049382716049382,
98
+ "grad_norm": 1.0806885957717896,
99
+ "learning_rate": 0.00019972156424930896,
100
+ "loss": 0.8553,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.1728395061728395,
105
+ "grad_norm": 1.1102285385131836,
106
+ "learning_rate": 0.00019961331407494245,
107
+ "loss": 0.864,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.18518518518518517,
112
+ "grad_norm": 1.0785351991653442,
113
+ "learning_rate": 0.00019948736723109082,
114
+ "loss": 0.8686,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.19753086419753085,
119
+ "grad_norm": 1.0402244329452515,
120
+ "learning_rate": 0.00019934374609267136,
121
+ "loss": 0.827,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.20987654320987653,
126
+ "grad_norm": 1.1072781085968018,
127
+ "learning_rate": 0.00019918247617450454,
128
+ "loss": 0.8345,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.2222222222222222,
133
+ "grad_norm": 1.0837725400924683,
134
+ "learning_rate": 0.00019900358612678099,
135
+ "loss": 0.8745,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.2345679012345679,
140
+ "grad_norm": 1.0628209114074707,
141
+ "learning_rate": 0.0001988071077299718,
142
+ "loss": 0.8584,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.24691358024691357,
147
+ "grad_norm": 1.0645418167114258,
148
+ "learning_rate": 0.00019859307588918258,
149
+ "loss": 0.8579,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.25925925925925924,
154
+ "grad_norm": 1.140362024307251,
155
+ "learning_rate": 0.00019836152862795245,
156
+ "loss": 0.8534,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.2716049382716049,
161
+ "grad_norm": 1.072213053703308,
162
+ "learning_rate": 0.0001981125070814991,
163
+ "loss": 0.8391,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.2839506172839506,
168
+ "grad_norm": 1.0480926036834717,
169
+ "learning_rate": 0.00019784605548941073,
170
+ "loss": 0.8562,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.2962962962962963,
175
+ "grad_norm": 1.0673149824142456,
176
+ "learning_rate": 0.00019756222118778706,
177
+ "loss": 0.8616,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.30864197530864196,
182
+ "grad_norm": 1.061468482017517,
183
+ "learning_rate": 0.0001972610546008295,
184
+ "loss": 0.8103,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.32098765432098764,
189
+ "grad_norm": 1.1202861070632935,
190
+ "learning_rate": 0.00019694260923188356,
191
+ "loss": 0.8037,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.3333333333333333,
196
+ "grad_norm": 1.0481396913528442,
197
+ "learning_rate": 0.00019660694165393334,
198
+ "loss": 0.8497,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.345679012345679,
203
+ "grad_norm": 1.0048563480377197,
204
+ "learning_rate": 0.00019625411149955154,
205
+ "loss": 0.8188,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.35802469135802467,
210
+ "grad_norm": 1.1558786630630493,
211
+ "learning_rate": 0.00019588418145030518,
212
+ "loss": 0.7984,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.37037037037037035,
217
+ "grad_norm": 1.1208077669143677,
218
+ "learning_rate": 0.00019549721722562018,
219
+ "loss": 0.8265,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.38271604938271603,
224
+ "grad_norm": 1.1445388793945312,
225
+ "learning_rate": 0.00019509328757110598,
226
+ "loss": 0.822,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.3950617283950617,
231
+ "grad_norm": 0.9763692617416382,
232
+ "learning_rate": 0.0001946724642463427,
233
+ "loss": 0.7717,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.4074074074074074,
238
+ "grad_norm": 1.1003857851028442,
239
+ "learning_rate": 0.00019423482201213276,
240
+ "loss": 0.792,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.41975308641975306,
245
+ "grad_norm": 0.9452071189880371,
246
+ "learning_rate": 0.0001937804386172193,
247
+ "loss": 0.812,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.43209876543209874,
252
+ "grad_norm": 1.1163841485977173,
253
+ "learning_rate": 0.00019330939478447393,
254
+ "loss": 0.7962,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.4444444444444444,
259
+ "grad_norm": 1.0678188800811768,
260
+ "learning_rate": 0.00019282177419655585,
261
+ "loss": 0.7824,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.4567901234567901,
266
+ "grad_norm": 0.9730695486068726,
267
+ "learning_rate": 0.00019231766348104556,
268
+ "loss": 0.7681,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.4691358024691358,
273
+ "grad_norm": 1.1495038270950317,
274
+ "learning_rate": 0.000191797152195055,
275
+ "loss": 0.7846,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.48148148148148145,
280
+ "grad_norm": 1.0246994495391846,
281
+ "learning_rate": 0.00019126033280931733,
282
+ "loss": 0.7905,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.49382716049382713,
287
+ "grad_norm": 1.1239315271377563,
288
+ "learning_rate": 0.00019070730069175936,
289
+ "loss": 0.8343,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.5061728395061729,
294
+ "grad_norm": 1.1794980764389038,
295
+ "learning_rate": 0.00019013815409055896,
296
+ "loss": 0.7987,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.5185185185185185,
301
+ "grad_norm": 1.16999351978302,
302
+ "learning_rate": 0.0001895529941166909,
303
+ "loss": 0.7939,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.5308641975308642,
308
+ "grad_norm": 1.077894926071167,
309
+ "learning_rate": 0.00018895192472596426,
310
+ "loss": 0.7979,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.5432098765432098,
315
+ "grad_norm": 1.169101595878601,
316
+ "learning_rate": 0.0001883350527005541,
317
+ "loss": 0.7817,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.5555555555555556,
322
+ "grad_norm": 1.211340069770813,
323
+ "learning_rate": 0.00018770248763003134,
324
+ "loss": 0.78,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.5679012345679012,
329
+ "grad_norm": 1.0432859659194946,
330
+ "learning_rate": 0.00018705434189189376,
331
+ "loss": 0.8006,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.5802469135802469,
336
+ "grad_norm": 1.0830694437026978,
337
+ "learning_rate": 0.00018639073063160172,
338
+ "loss": 0.7811,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.5925925925925926,
343
+ "grad_norm": 1.0481195449829102,
344
+ "learning_rate": 0.00018571177174212214,
345
+ "loss": 0.7438,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.6049382716049383,
350
+ "grad_norm": 1.0968844890594482,
351
+ "learning_rate": 0.00018501758584298433,
352
+ "loss": 0.7656,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.6172839506172839,
357
+ "grad_norm": 1.000929832458496,
358
+ "learning_rate": 0.00018430829625885165,
359
+ "loss": 0.789,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.6296296296296297,
364
+ "grad_norm": 1.0056663751602173,
365
+ "learning_rate": 0.00018358402899761218,
366
+ "loss": 0.7727,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.6419753086419753,
371
+ "grad_norm": 1.0271273851394653,
372
+ "learning_rate": 0.00018284491272799327,
373
+ "loss": 0.7723,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.654320987654321,
378
+ "grad_norm": 1.0579137802124023,
379
+ "learning_rate": 0.00018209107875670277,
380
+ "loss": 0.7818,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.6666666666666666,
385
+ "grad_norm": 1.2076494693756104,
386
+ "learning_rate": 0.00018132266100510214,
387
+ "loss": 0.7709,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.6790123456790124,
392
+ "grad_norm": 1.0516587495803833,
393
+ "learning_rate": 0.0001805397959854147,
394
+ "loss": 0.7594,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.691358024691358,
399
+ "grad_norm": 1.0052849054336548,
400
+ "learning_rate": 0.00017974262277647374,
401
+ "loss": 0.7645,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.7037037037037037,
406
+ "grad_norm": 1.067668080329895,
407
+ "learning_rate": 0.00017893128299901472,
408
+ "loss": 0.7508,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.7160493827160493,
413
+ "grad_norm": 1.1277140378952026,
414
+ "learning_rate": 0.00017810592079051585,
415
+ "loss": 0.7878,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.7283950617283951,
420
+ "grad_norm": 1.1608866453170776,
421
+ "learning_rate": 0.00017726668277959136,
422
+ "loss": 0.7638,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.7407407407407407,
427
+ "grad_norm": 1.102867603302002,
428
+ "learning_rate": 0.00017641371805994264,
429
+ "loss": 0.7618,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.7530864197530864,
434
+ "grad_norm": 1.1261731386184692,
435
+ "learning_rate": 0.00017554717816387107,
436
+ "loss": 0.758,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.7654320987654321,
441
+ "grad_norm": 1.066041111946106,
442
+ "learning_rate": 0.00017466721703535764,
443
+ "loss": 0.7478,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.7777777777777778,
448
+ "grad_norm": 1.021802544593811,
449
+ "learning_rate": 0.0001737739910027145,
450
+ "loss": 0.7554,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.7901234567901234,
455
+ "grad_norm": 1.1736857891082764,
456
+ "learning_rate": 0.00017286765875081244,
457
+ "loss": 0.78,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.8024691358024691,
462
+ "grad_norm": 1.1246825456619263,
463
+ "learning_rate": 0.00017194838129289006,
464
+ "loss": 0.7475,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.8148148148148148,
469
+ "grad_norm": 1.1927721500396729,
470
+ "learning_rate": 0.0001710163219419491,
471
+ "loss": 0.742,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.8271604938271605,
476
+ "grad_norm": 1.0868706703186035,
477
+ "learning_rate": 0.00017007164628174139,
478
+ "loss": 0.7676,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.8395061728395061,
483
+ "grad_norm": 1.0195647478103638,
484
+ "learning_rate": 0.00016911452213735223,
485
+ "loss": 0.7543,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.8518518518518519,
490
+ "grad_norm": 1.1533241271972656,
491
+ "learning_rate": 0.00016814511954538558,
492
+ "loss": 0.7463,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.8641975308641975,
497
+ "grad_norm": 1.1366993188858032,
498
+ "learning_rate": 0.00016716361072375657,
499
+ "loss": 0.7407,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.8765432098765432,
504
+ "grad_norm": 1.2098641395568848,
505
+ "learning_rate": 0.00016617017004109632,
506
+ "loss": 0.7031,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.8888888888888888,
511
+ "grad_norm": 0.9996205568313599,
512
+ "learning_rate": 0.0001651649739857746,
513
+ "loss": 0.7405,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.9012345679012346,
518
+ "grad_norm": 1.046208143234253,
519
+ "learning_rate": 0.00016414820113454622,
520
+ "loss": 0.763,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.9135802469135802,
525
+ "grad_norm": 1.0813542604446411,
526
+ "learning_rate": 0.0001631200321208261,
527
+ "loss": 0.7432,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.9259259259259259,
532
+ "grad_norm": 1.1473093032836914,
533
+ "learning_rate": 0.00016208064960259897,
534
+ "loss": 0.7738,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.9382716049382716,
539
+ "grad_norm": 1.084929347038269,
540
+ "learning_rate": 0.00016103023822996982,
541
+ "loss": 0.764,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.9506172839506173,
546
+ "grad_norm": 1.0776119232177734,
547
+ "learning_rate": 0.00015996898461235977,
548
+ "loss": 0.7496,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.9629629629629629,
553
+ "grad_norm": 1.1536927223205566,
554
+ "learning_rate": 0.00015889707728535462,
555
+ "loss": 0.7501,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.9753086419753086,
560
+ "grad_norm": 1.211068868637085,
561
+ "learning_rate": 0.0001578147066772104,
562
+ "loss": 0.7623,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.9876543209876543,
567
+ "grad_norm": 1.1335115432739258,
568
+ "learning_rate": 0.00015672206507502337,
569
+ "loss": 0.7261,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 1.0,
574
+ "grad_norm": 1.1170907020568848,
575
+ "learning_rate": 0.00015561934659056947,
576
+ "loss": 0.732,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 1.0,
581
+ "eval_loss": 0.7329609990119934,
582
+ "eval_runtime": 487.7516,
583
+ "eval_samples_per_second": 2.952,
584
+ "eval_steps_per_second": 0.738,
585
+ "step": 810
586
+ }
587
+ ],
588
+ "logging_steps": 10,
589
+ "max_steps": 2430,
590
+ "num_input_tokens_seen": 0,
591
+ "num_train_epochs": 3,
592
+ "save_steps": 500,
593
+ "stateful_callbacks": {
594
+ "TrainerControl": {
595
+ "args": {
596
+ "should_epoch_stop": false,
597
+ "should_evaluate": false,
598
+ "should_log": false,
599
+ "should_save": true,
600
+ "should_training_stop": false
601
+ },
602
+ "attributes": {}
603
+ }
604
+ },
605
+ "total_flos": 1.4237273708455526e+17,
606
+ "train_batch_size": 4,
607
+ "trial_name": null,
608
+ "trial_params": null
609
+ }
training_args-5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66d936bcf3423cbfa48d223661089e697103850c7914e6b4ed156550dc71c8c8
3
+ size 5841