dzungpham commited on
Commit
b044777
·
verified ·
1 Parent(s): f6ef07a

Delete files checkpoint-* with huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-1000/config.json +0 -27
  2. checkpoint-1000/merges.txt +0 -0
  3. checkpoint-1000/model.safetensors +0 -3
  4. checkpoint-1000/optimizer.pt +0 -3
  5. checkpoint-1000/rng_state.pth +0 -3
  6. checkpoint-1000/scaler.pt +0 -3
  7. checkpoint-1000/scheduler.pt +0 -3
  8. checkpoint-1000/special_tokens_map.json +0 -51
  9. checkpoint-1000/tokenizer.json +0 -0
  10. checkpoint-1000/tokenizer_config.json +0 -58
  11. checkpoint-1000/trainer_state.json +0 -803
  12. checkpoint-1000/training_args.bin +0 -3
  13. checkpoint-1000/vocab.json +0 -0
  14. checkpoint-1100/config.json +0 -29
  15. checkpoint-1100/merges.txt +0 -0
  16. checkpoint-1100/model.safetensors +0 -3
  17. checkpoint-1100/optimizer.pt +0 -3
  18. checkpoint-1100/rng_state.pth +0 -3
  19. checkpoint-1100/scaler.pt +0 -3
  20. checkpoint-1100/scheduler.pt +0 -3
  21. checkpoint-1100/special_tokens_map.json +0 -51
  22. checkpoint-1100/tokenizer.json +0 -0
  23. checkpoint-1100/tokenizer_config.json +0 -58
  24. checkpoint-1100/trainer_state.json +0 -956
  25. checkpoint-1100/training_args.bin +0 -3
  26. checkpoint-1100/vocab.json +0 -0
  27. checkpoint-1200/config.json +0 -27
  28. checkpoint-1200/merges.txt +0 -0
  29. checkpoint-1200/model.safetensors +0 -3
  30. checkpoint-1200/optimizer.pt +0 -3
  31. checkpoint-1200/rng_state.pth +0 -3
  32. checkpoint-1200/scheduler.pt +0 -3
  33. checkpoint-1200/special_tokens_map.json +0 -51
  34. checkpoint-1200/tokenizer.json +0 -0
  35. checkpoint-1200/tokenizer_config.json +0 -58
  36. checkpoint-1200/trainer_state.json +0 -955
  37. checkpoint-1200/training_args.bin +0 -3
  38. checkpoint-1200/vocab.json +0 -0
  39. checkpoint-1300/config.json +0 -29
  40. checkpoint-1300/merges.txt +0 -0
  41. checkpoint-1300/model.safetensors +0 -3
  42. checkpoint-1300/optimizer.pt +0 -3
  43. checkpoint-1300/rng_state.pth +0 -3
  44. checkpoint-1300/scaler.pt +0 -3
  45. checkpoint-1300/scheduler.pt +0 -3
  46. checkpoint-1300/special_tokens_map.json +0 -51
  47. checkpoint-1300/tokenizer.json +0 -0
  48. checkpoint-1300/tokenizer_config.json +0 -58
  49. checkpoint-1300/trainer_state.json +0 -1122
  50. checkpoint-1300/training_args.bin +0 -3
checkpoint-1000/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "architectures": [
3
- "RobertaForSequenceClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "bos_token_id": 0,
7
- "classifier_dropout": null,
8
- "dtype": "float32",
9
- "eos_token_id": 2,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "layer_norm_eps": 1e-05,
16
- "max_position_embeddings": 514,
17
- "model_type": "roberta",
18
- "num_attention_heads": 12,
19
- "num_hidden_layers": 12,
20
- "output_past": true,
21
- "pad_token_id": 1,
22
- "position_embedding_type": "absolute",
23
- "transformers_version": "4.56.0",
24
- "type_vocab_size": 1,
25
- "use_cache": true,
26
- "vocab_size": 50265
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1000/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:665d1f6d7cabc187a2c05357e277b61c6a5caafa84e641cdaa9f74e1fc8f6b9e
3
- size 498612824
 
 
 
 
checkpoint-1000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8df0daec4efa812ba208cd0dc90879540bae0bc13e657a311777d25929b1aea1
3
- size 4741859
 
 
 
 
checkpoint-1000/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ea1b5dc44e07bb7fcc644910a14b04ebd8863c5a7cf8eb7438e00e0c30f16a6
3
- size 14645
 
 
 
 
checkpoint-1000/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:db5e3abecfb917c340b4d882625db5f9460551d58b56c250704864b7bc1aa3e4
3
- size 1383
 
 
 
 
checkpoint-1000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f25fe7731b9278a60bff9cc7fd3ead4df1aef9e341ef501c56c76de421b4c24
3
- size 1465
 
 
 
 
checkpoint-1000/special_tokens_map.json DELETED
@@ -1,51 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1000/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer_config.json DELETED
@@ -1,58 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<pad>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "50264": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
- },
45
- "bos_token": "<s>",
46
- "clean_up_tokenization_spaces": false,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "extra_special_tokens": {},
51
- "mask_token": "<mask>",
52
- "model_max_length": 512,
53
- "pad_token": "<pad>",
54
- "sep_token": "</s>",
55
- "tokenizer_class": "RobertaTokenizer",
56
- "trim_offsets": true,
57
- "unk_token": "<unk>"
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1000/trainer_state.json DELETED
@@ -1,803 +0,0 @@
1
- {
2
- "best_global_step": 1000,
3
- "best_metric": 0.689588440856387,
4
- "best_model_checkpoint": "./taskA-codebert-base/checkpoint-1000",
5
- "epoch": 0.12799180852425446,
6
- "eval_steps": 200,
7
- "global_step": 1000,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.0012799180852425445,
14
- "grad_norm": 3.6954128742218018,
15
- "learning_rate": 3.840409643695328e-08,
16
- "loss": 0.7763,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 0.002559836170485089,
21
- "grad_norm": 3.3660645484924316,
22
- "learning_rate": 8.10753147002347e-08,
23
- "loss": 0.7763,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 0.0038397542557276334,
28
- "grad_norm": 4.491067886352539,
29
- "learning_rate": 1.2374653296351612e-07,
30
- "loss": 0.7889,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 0.005119672340970178,
35
- "grad_norm": 1.5920521020889282,
36
- "learning_rate": 1.6641775122679754e-07,
37
- "loss": 0.7888,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 0.006399590426212722,
42
- "grad_norm": 4.410898208618164,
43
- "learning_rate": 2.0908896949007894e-07,
44
- "loss": 0.7692,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 0.007679508511455267,
49
- "grad_norm": 2.5669264793395996,
50
- "learning_rate": 2.517601877533604e-07,
51
- "loss": 0.7735,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.008959426596697812,
56
- "grad_norm": 6.190986156463623,
57
- "learning_rate": 2.944314060166418e-07,
58
- "loss": 0.7679,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.010239344681940356,
63
- "grad_norm": 5.736413478851318,
64
- "learning_rate": 3.371026242799232e-07,
65
- "loss": 0.744,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.011519262767182901,
70
- "grad_norm": 4.278866767883301,
71
- "learning_rate": 3.7977384254320464e-07,
72
- "loss": 0.7542,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.012799180852425445,
77
- "grad_norm": 5.565455436706543,
78
- "learning_rate": 4.22445060806486e-07,
79
- "loss": 0.752,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 0.01407909893766799,
84
- "grad_norm": 4.031781196594238,
85
- "learning_rate": 4.651162790697675e-07,
86
- "loss": 0.7614,
87
- "step": 110
88
- },
89
- {
90
- "epoch": 0.015359017022910534,
91
- "grad_norm": 2.484126329421997,
92
- "learning_rate": 5.077874973330489e-07,
93
- "loss": 0.7664,
94
- "step": 120
95
- },
96
- {
97
- "epoch": 0.016638935108153077,
98
- "grad_norm": 2.7525155544281006,
99
- "learning_rate": 5.504587155963304e-07,
100
- "loss": 0.7521,
101
- "step": 130
102
- },
103
- {
104
- "epoch": 0.017918853193395624,
105
- "grad_norm": 1.6374385356903076,
106
- "learning_rate": 5.931299338596117e-07,
107
- "loss": 0.7436,
108
- "step": 140
109
- },
110
- {
111
- "epoch": 0.019198771278638168,
112
- "grad_norm": 2.370774269104004,
113
- "learning_rate": 6.358011521228932e-07,
114
- "loss": 0.7429,
115
- "step": 150
116
- },
117
- {
118
- "epoch": 0.02047868936388071,
119
- "grad_norm": 2.8948566913604736,
120
- "learning_rate": 6.784723703861745e-07,
121
- "loss": 0.7333,
122
- "step": 160
123
- },
124
- {
125
- "epoch": 0.021758607449123255,
126
- "grad_norm": 2.7481186389923096,
127
- "learning_rate": 7.21143588649456e-07,
128
- "loss": 0.7294,
129
- "step": 170
130
- },
131
- {
132
- "epoch": 0.023038525534365802,
133
- "grad_norm": 2.0159404277801514,
134
- "learning_rate": 7.638148069127374e-07,
135
- "loss": 0.731,
136
- "step": 180
137
- },
138
- {
139
- "epoch": 0.024318443619608346,
140
- "grad_norm": 3.6898131370544434,
141
- "learning_rate": 8.064860251760189e-07,
142
- "loss": 0.7153,
143
- "step": 190
144
- },
145
- {
146
- "epoch": 0.02559836170485089,
147
- "grad_norm": 3.2842342853546143,
148
- "learning_rate": 8.491572434393003e-07,
149
- "loss": 0.7245,
150
- "step": 200
151
- },
152
- {
153
- "epoch": 0.02559836170485089,
154
- "eval_accuracy": 0.47695,
155
- "eval_loss": 0.7148504853248596,
156
- "eval_macro_f1": 0.3229290091066048,
157
- "eval_precision": 0.238475,
158
- "eval_recall": 0.5,
159
- "eval_runtime": 1641.324,
160
- "eval_samples_per_second": 60.926,
161
- "eval_steps_per_second": 0.476,
162
- "step": 200
163
- },
164
- {
165
- "epoch": 0.026878279790093433,
166
- "grad_norm": 2.294558048248291,
167
- "learning_rate": 8.918284617025817e-07,
168
- "loss": 0.718,
169
- "step": 210
170
- },
171
- {
172
- "epoch": 0.02815819787533598,
173
- "grad_norm": 2.9467175006866455,
174
- "learning_rate": 9.344996799658632e-07,
175
- "loss": 0.7076,
176
- "step": 220
177
- },
178
- {
179
- "epoch": 0.029438115960578524,
180
- "grad_norm": 2.6889193058013916,
181
- "learning_rate": 9.771708982291445e-07,
182
- "loss": 0.7019,
183
- "step": 230
184
- },
185
- {
186
- "epoch": 0.030718034045821067,
187
- "grad_norm": 0.7491384744644165,
188
- "learning_rate": 1.0198421164924258e-06,
189
- "loss": 0.7046,
190
- "step": 240
191
- },
192
- {
193
- "epoch": 0.031997952131063614,
194
- "grad_norm": 2.0363433361053467,
195
- "learning_rate": 1.0625133347557074e-06,
196
- "loss": 0.7085,
197
- "step": 250
198
- },
199
- {
200
- "epoch": 0.033277870216306155,
201
- "grad_norm": 1.1431337594985962,
202
- "learning_rate": 1.1051845530189888e-06,
203
- "loss": 0.7008,
204
- "step": 260
205
- },
206
- {
207
- "epoch": 0.0345577883015487,
208
- "grad_norm": 3.7735233306884766,
209
- "learning_rate": 1.1478557712822702e-06,
210
- "loss": 0.7015,
211
- "step": 270
212
- },
213
- {
214
- "epoch": 0.03583770638679125,
215
- "grad_norm": 0.7889328002929688,
216
- "learning_rate": 1.1905269895455517e-06,
217
- "loss": 0.699,
218
- "step": 280
219
- },
220
- {
221
- "epoch": 0.03711762447203379,
222
- "grad_norm": 0.8796226382255554,
223
- "learning_rate": 1.233198207808833e-06,
224
- "loss": 0.6922,
225
- "step": 290
226
- },
227
- {
228
- "epoch": 0.038397542557276336,
229
- "grad_norm": 0.7966652512550354,
230
- "learning_rate": 1.2758694260721145e-06,
231
- "loss": 0.6949,
232
- "step": 300
233
- },
234
- {
235
- "epoch": 0.039677460642518876,
236
- "grad_norm": 0.7029069066047668,
237
- "learning_rate": 1.318540644335396e-06,
238
- "loss": 0.695,
239
- "step": 310
240
- },
241
- {
242
- "epoch": 0.04095737872776142,
243
- "grad_norm": 2.04327392578125,
244
- "learning_rate": 1.3612118625986772e-06,
245
- "loss": 0.6944,
246
- "step": 320
247
- },
248
- {
249
- "epoch": 0.04223729681300397,
250
- "grad_norm": 0.918025553226471,
251
- "learning_rate": 1.4038830808619588e-06,
252
- "loss": 0.6863,
253
- "step": 330
254
- },
255
- {
256
- "epoch": 0.04351721489824651,
257
- "grad_norm": 0.9528706073760986,
258
- "learning_rate": 1.4465542991252401e-06,
259
- "loss": 0.6907,
260
- "step": 340
261
- },
262
- {
263
- "epoch": 0.04479713298348906,
264
- "grad_norm": 1.071359634399414,
265
- "learning_rate": 1.4892255173885215e-06,
266
- "loss": 0.6873,
267
- "step": 350
268
- },
269
- {
270
- "epoch": 0.046077051068731605,
271
- "grad_norm": 1.9875625371932983,
272
- "learning_rate": 1.531896735651803e-06,
273
- "loss": 0.6942,
274
- "step": 360
275
- },
276
- {
277
- "epoch": 0.047356969153974145,
278
- "grad_norm": 2.0222439765930176,
279
- "learning_rate": 1.5745679539150842e-06,
280
- "loss": 0.6898,
281
- "step": 370
282
- },
283
- {
284
- "epoch": 0.04863688723921669,
285
- "grad_norm": 1.7827857732772827,
286
- "learning_rate": 1.6172391721783658e-06,
287
- "loss": 0.6909,
288
- "step": 380
289
- },
290
- {
291
- "epoch": 0.04991680532445923,
292
- "grad_norm": 1.065674901008606,
293
- "learning_rate": 1.6599103904416472e-06,
294
- "loss": 0.6877,
295
- "step": 390
296
- },
297
- {
298
- "epoch": 0.05119672340970178,
299
- "grad_norm": 0.8346193432807922,
300
- "learning_rate": 1.7025816087049288e-06,
301
- "loss": 0.6889,
302
- "step": 400
303
- },
304
- {
305
- "epoch": 0.05119672340970178,
306
- "eval_accuracy": 0.54043,
307
- "eval_loss": 0.6827595233917236,
308
- "eval_macro_f1": 0.41833840347598905,
309
- "eval_precision": 0.5839205994464474,
310
- "eval_recall": 0.5204152767503025,
311
- "eval_runtime": 1634.6244,
312
- "eval_samples_per_second": 61.176,
313
- "eval_steps_per_second": 0.478,
314
- "step": 400
315
- },
316
- {
317
- "epoch": 0.052476641494944326,
318
- "grad_norm": 0.8074935674667358,
319
- "learning_rate": 1.7452528269682101e-06,
320
- "loss": 0.684,
321
- "step": 410
322
- },
323
- {
324
- "epoch": 0.053756559580186866,
325
- "grad_norm": 0.8965069651603699,
326
- "learning_rate": 1.7879240452314913e-06,
327
- "loss": 0.6922,
328
- "step": 420
329
- },
330
- {
331
- "epoch": 0.05503647766542941,
332
- "grad_norm": 2.597215414047241,
333
- "learning_rate": 1.8305952634947729e-06,
334
- "loss": 0.6909,
335
- "step": 430
336
- },
337
- {
338
- "epoch": 0.05631639575067196,
339
- "grad_norm": 0.8233373165130615,
340
- "learning_rate": 1.8732664817580542e-06,
341
- "loss": 0.6831,
342
- "step": 440
343
- },
344
- {
345
- "epoch": 0.0575963138359145,
346
- "grad_norm": 1.0624489784240723,
347
- "learning_rate": 1.915937700021336e-06,
348
- "loss": 0.6817,
349
- "step": 450
350
- },
351
- {
352
- "epoch": 0.05887623192115705,
353
- "grad_norm": 2.0623559951782227,
354
- "learning_rate": 1.958608918284617e-06,
355
- "loss": 0.6819,
356
- "step": 460
357
- },
358
- {
359
- "epoch": 0.06015615000639959,
360
- "grad_norm": 0.912433922290802,
361
- "learning_rate": 2.0012801365478988e-06,
362
- "loss": 0.686,
363
- "step": 470
364
- },
365
- {
366
- "epoch": 0.061436068091642135,
367
- "grad_norm": 0.6926271319389343,
368
- "learning_rate": 2.04395135481118e-06,
369
- "loss": 0.6834,
370
- "step": 480
371
- },
372
- {
373
- "epoch": 0.06271598617688467,
374
- "grad_norm": 1.498634934425354,
375
- "learning_rate": 2.0866225730744615e-06,
376
- "loss": 0.6805,
377
- "step": 490
378
- },
379
- {
380
- "epoch": 0.06399590426212723,
381
- "grad_norm": 1.1818156242370605,
382
- "learning_rate": 2.129293791337743e-06,
383
- "loss": 0.6805,
384
- "step": 500
385
- },
386
- {
387
- "epoch": 0.06527582234736977,
388
- "grad_norm": 1.4476051330566406,
389
- "learning_rate": 2.1719650096010242e-06,
390
- "loss": 0.6773,
391
- "step": 510
392
- },
393
- {
394
- "epoch": 0.06655574043261231,
395
- "grad_norm": 1.1143743991851807,
396
- "learning_rate": 2.214636227864306e-06,
397
- "loss": 0.6801,
398
- "step": 520
399
- },
400
- {
401
- "epoch": 0.06783565851785486,
402
- "grad_norm": 1.7030247449874878,
403
- "learning_rate": 2.257307446127587e-06,
404
- "loss": 0.6794,
405
- "step": 530
406
- },
407
- {
408
- "epoch": 0.0691155766030974,
409
- "grad_norm": 0.8592290282249451,
410
- "learning_rate": 2.2999786643908685e-06,
411
- "loss": 0.6736,
412
- "step": 540
413
- },
414
- {
415
- "epoch": 0.07039549468833994,
416
- "grad_norm": 0.8231940865516663,
417
- "learning_rate": 2.34264988265415e-06,
418
- "loss": 0.67,
419
- "step": 550
420
- },
421
- {
422
- "epoch": 0.0716754127735825,
423
- "grad_norm": 0.88897705078125,
424
- "learning_rate": 2.3853211009174317e-06,
425
- "loss": 0.685,
426
- "step": 560
427
- },
428
- {
429
- "epoch": 0.07295533085882504,
430
- "grad_norm": 1.6297541856765747,
431
- "learning_rate": 2.427992319180713e-06,
432
- "loss": 0.6797,
433
- "step": 570
434
- },
435
- {
436
- "epoch": 0.07423524894406758,
437
- "grad_norm": 2.9297447204589844,
438
- "learning_rate": 2.470663537443994e-06,
439
- "loss": 0.6766,
440
- "step": 580
441
- },
442
- {
443
- "epoch": 0.07551516702931012,
444
- "grad_norm": 0.9277703762054443,
445
- "learning_rate": 2.5133347557072756e-06,
446
- "loss": 0.6824,
447
- "step": 590
448
- },
449
- {
450
- "epoch": 0.07679508511455267,
451
- "grad_norm": 0.5883333683013916,
452
- "learning_rate": 2.556005973970557e-06,
453
- "loss": 0.6818,
454
- "step": 600
455
- },
456
- {
457
- "epoch": 0.07679508511455267,
458
- "eval_accuracy": 0.63909,
459
- "eval_loss": 0.6700075268745422,
460
- "eval_macro_f1": 0.621848143053056,
461
- "eval_precision": 0.6524313071088819,
462
- "eval_recall": 0.6305863955136095,
463
- "eval_runtime": 1633.9732,
464
- "eval_samples_per_second": 61.201,
465
- "eval_steps_per_second": 0.479,
466
- "step": 600
467
- },
468
- {
469
- "epoch": 0.07807500319979521,
470
- "grad_norm": 0.7149448394775391,
471
- "learning_rate": 2.5986771922338383e-06,
472
- "loss": 0.6746,
473
- "step": 610
474
- },
475
- {
476
- "epoch": 0.07935492128503775,
477
- "grad_norm": 2.0167856216430664,
478
- "learning_rate": 2.64134841049712e-06,
479
- "loss": 0.682,
480
- "step": 620
481
- },
482
- {
483
- "epoch": 0.0806348393702803,
484
- "grad_norm": 1.303001880645752,
485
- "learning_rate": 2.6840196287604015e-06,
486
- "loss": 0.6735,
487
- "step": 630
488
- },
489
- {
490
- "epoch": 0.08191475745552285,
491
- "grad_norm": 2.0516321659088135,
492
- "learning_rate": 2.7266908470236826e-06,
493
- "loss": 0.6705,
494
- "step": 640
495
- },
496
- {
497
- "epoch": 0.08319467554076539,
498
- "grad_norm": 2.242105484008789,
499
- "learning_rate": 2.7693620652869642e-06,
500
- "loss": 0.6798,
501
- "step": 650
502
- },
503
- {
504
- "epoch": 0.08447459362600794,
505
- "grad_norm": 1.1836538314819336,
506
- "learning_rate": 2.812033283550246e-06,
507
- "loss": 0.6684,
508
- "step": 660
509
- },
510
- {
511
- "epoch": 0.08575451171125048,
512
- "grad_norm": 0.8640874624252319,
513
- "learning_rate": 2.8547045018135274e-06,
514
- "loss": 0.6783,
515
- "step": 670
516
- },
517
- {
518
- "epoch": 0.08703442979649302,
519
- "grad_norm": 0.6901177763938904,
520
- "learning_rate": 2.897375720076808e-06,
521
- "loss": 0.6724,
522
- "step": 680
523
- },
524
- {
525
- "epoch": 0.08831434788173557,
526
- "grad_norm": 1.3443949222564697,
527
- "learning_rate": 2.9400469383400897e-06,
528
- "loss": 0.67,
529
- "step": 690
530
- },
531
- {
532
- "epoch": 0.08959426596697811,
533
- "grad_norm": 0.7775189280509949,
534
- "learning_rate": 2.9827181566033713e-06,
535
- "loss": 0.6733,
536
- "step": 700
537
- },
538
- {
539
- "epoch": 0.09087418405222066,
540
- "grad_norm": 1.16916823387146,
541
- "learning_rate": 3.025389374866653e-06,
542
- "loss": 0.6713,
543
- "step": 710
544
- },
545
- {
546
- "epoch": 0.09215410213746321,
547
- "grad_norm": 1.707152009010315,
548
- "learning_rate": 3.068060593129934e-06,
549
- "loss": 0.6659,
550
- "step": 720
551
- },
552
- {
553
- "epoch": 0.09343402022270575,
554
- "grad_norm": 0.9780622124671936,
555
- "learning_rate": 3.1107318113932156e-06,
556
- "loss": 0.6639,
557
- "step": 730
558
- },
559
- {
560
- "epoch": 0.09471393830794829,
561
- "grad_norm": 2.3687374591827393,
562
- "learning_rate": 3.153403029656497e-06,
563
- "loss": 0.6666,
564
- "step": 740
565
- },
566
- {
567
- "epoch": 0.09599385639319083,
568
- "grad_norm": 0.8506460189819336,
569
- "learning_rate": 3.1960742479197783e-06,
570
- "loss": 0.6778,
571
- "step": 750
572
- },
573
- {
574
- "epoch": 0.09727377447843338,
575
- "grad_norm": 1.0102107524871826,
576
- "learning_rate": 3.23874546618306e-06,
577
- "loss": 0.6635,
578
- "step": 760
579
- },
580
- {
581
- "epoch": 0.09855369256367592,
582
- "grad_norm": 1.1480194330215454,
583
- "learning_rate": 3.2814166844463415e-06,
584
- "loss": 0.6709,
585
- "step": 770
586
- },
587
- {
588
- "epoch": 0.09983361064891846,
589
- "grad_norm": 1.3119179010391235,
590
- "learning_rate": 3.324087902709623e-06,
591
- "loss": 0.6564,
592
- "step": 780
593
- },
594
- {
595
- "epoch": 0.10111352873416102,
596
- "grad_norm": 0.681377649307251,
597
- "learning_rate": 3.3667591209729038e-06,
598
- "loss": 0.6656,
599
- "step": 790
600
- },
601
- {
602
- "epoch": 0.10239344681940356,
603
- "grad_norm": 1.022257685661316,
604
- "learning_rate": 3.4094303392361854e-06,
605
- "loss": 0.6709,
606
- "step": 800
607
- },
608
- {
609
- "epoch": 0.10239344681940356,
610
- "eval_accuracy": 0.66247,
611
- "eval_loss": 0.6552017331123352,
612
- "eval_macro_f1": 0.6514270557181998,
613
- "eval_precision": 0.6718270655389242,
614
- "eval_recall": 0.6556580720913894,
615
- "eval_runtime": 1633.5478,
616
- "eval_samples_per_second": 61.216,
617
- "eval_steps_per_second": 0.479,
618
- "step": 800
619
- },
620
- {
621
- "epoch": 0.1036733649046461,
622
- "grad_norm": 1.0268975496292114,
623
- "learning_rate": 3.452101557499467e-06,
624
- "loss": 0.6602,
625
- "step": 810
626
- },
627
- {
628
- "epoch": 0.10495328298988865,
629
- "grad_norm": 2.6206603050231934,
630
- "learning_rate": 3.494772775762748e-06,
631
- "loss": 0.6705,
632
- "step": 820
633
- },
634
- {
635
- "epoch": 0.10623320107513119,
636
- "grad_norm": 1.035157561302185,
637
- "learning_rate": 3.5374439940260297e-06,
638
- "loss": 0.6643,
639
- "step": 830
640
- },
641
- {
642
- "epoch": 0.10751311916037373,
643
- "grad_norm": 1.736412763595581,
644
- "learning_rate": 3.5801152122893113e-06,
645
- "loss": 0.6612,
646
- "step": 840
647
- },
648
- {
649
- "epoch": 0.10879303724561629,
650
- "grad_norm": 0.6906964778900146,
651
- "learning_rate": 3.622786430552593e-06,
652
- "loss": 0.6576,
653
- "step": 850
654
- },
655
- {
656
- "epoch": 0.11007295533085883,
657
- "grad_norm": 0.8148729801177979,
658
- "learning_rate": 3.665457648815874e-06,
659
- "loss": 0.6561,
660
- "step": 860
661
- },
662
- {
663
- "epoch": 0.11135287341610137,
664
- "grad_norm": 1.0217723846435547,
665
- "learning_rate": 3.7081288670791556e-06,
666
- "loss": 0.6581,
667
- "step": 870
668
- },
669
- {
670
- "epoch": 0.11263279150134392,
671
- "grad_norm": 1.2743115425109863,
672
- "learning_rate": 3.750800085342437e-06,
673
- "loss": 0.6606,
674
- "step": 880
675
- },
676
- {
677
- "epoch": 0.11391270958658646,
678
- "grad_norm": 0.6405361294746399,
679
- "learning_rate": 3.793471303605718e-06,
680
- "loss": 0.652,
681
- "step": 890
682
- },
683
- {
684
- "epoch": 0.115192627671829,
685
- "grad_norm": 0.8357161283493042,
686
- "learning_rate": 3.836142521869e-06,
687
- "loss": 0.6558,
688
- "step": 900
689
- },
690
- {
691
- "epoch": 0.11647254575707154,
692
- "grad_norm": 1.3505173921585083,
693
- "learning_rate": 3.8788137401322815e-06,
694
- "loss": 0.6576,
695
- "step": 910
696
- },
697
- {
698
- "epoch": 0.1177524638423141,
699
- "grad_norm": 1.2253319025039673,
700
- "learning_rate": 3.921484958395563e-06,
701
- "loss": 0.6548,
702
- "step": 920
703
- },
704
- {
705
- "epoch": 0.11903238192755664,
706
- "grad_norm": 0.6269568800926208,
707
- "learning_rate": 3.964156176658844e-06,
708
- "loss": 0.6562,
709
- "step": 930
710
- },
711
- {
712
- "epoch": 0.12031230001279918,
713
- "grad_norm": 0.9413424134254456,
714
- "learning_rate": 4.006827394922125e-06,
715
- "loss": 0.6461,
716
- "step": 940
717
- },
718
- {
719
- "epoch": 0.12159221809804173,
720
- "grad_norm": 1.0903513431549072,
721
- "learning_rate": 4.049498613185407e-06,
722
- "loss": 0.6457,
723
- "step": 950
724
- },
725
- {
726
- "epoch": 0.12287213618328427,
727
- "grad_norm": 2.0023152828216553,
728
- "learning_rate": 4.092169831448688e-06,
729
- "loss": 0.6458,
730
- "step": 960
731
- },
732
- {
733
- "epoch": 0.12415205426852681,
734
- "grad_norm": 0.9638109803199768,
735
- "learning_rate": 4.134841049711969e-06,
736
- "loss": 0.6486,
737
- "step": 970
738
- },
739
- {
740
- "epoch": 0.12543197235376935,
741
- "grad_norm": 0.9894546270370483,
742
- "learning_rate": 4.177512267975251e-06,
743
- "loss": 0.6453,
744
- "step": 980
745
- },
746
- {
747
- "epoch": 0.1267118904390119,
748
- "grad_norm": 1.2289057970046997,
749
- "learning_rate": 4.220183486238532e-06,
750
- "loss": 0.6605,
751
- "step": 990
752
- },
753
- {
754
- "epoch": 0.12799180852425446,
755
- "grad_norm": 1.119125247001648,
756
- "learning_rate": 4.262854704501814e-06,
757
- "loss": 0.6564,
758
- "step": 1000
759
- },
760
- {
761
- "epoch": 0.12799180852425446,
762
- "eval_accuracy": 0.69068,
763
- "eval_loss": 0.6396247148513794,
764
- "eval_macro_f1": 0.689588440856387,
765
- "eval_precision": 0.6900076024604327,
766
- "eval_recall": 0.6894114140312133,
767
- "eval_runtime": 1634.4321,
768
- "eval_samples_per_second": 61.183,
769
- "eval_steps_per_second": 0.478,
770
- "step": 1000
771
- }
772
- ],
773
- "logging_steps": 10,
774
- "max_steps": 23439,
775
- "num_input_tokens_seen": 0,
776
- "num_train_epochs": 3,
777
- "save_steps": 200,
778
- "stateful_callbacks": {
779
- "EarlyStoppingCallback": {
780
- "args": {
781
- "early_stopping_patience": 3,
782
- "early_stopping_threshold": 0.0
783
- },
784
- "attributes": {
785
- "early_stopping_patience_counter": 0
786
- }
787
- },
788
- "TrainerControl": {
789
- "args": {
790
- "should_epoch_stop": false,
791
- "should_evaluate": false,
792
- "should_log": false,
793
- "should_save": true,
794
- "should_training_stop": false
795
- },
796
- "attributes": {}
797
- }
798
- },
799
- "total_flos": 1.683910754304e+16,
800
- "train_batch_size": 64,
801
- "trial_name": null,
802
- "trial_params": null
803
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:88587329aed582b4509ae035cda4f2b8b5747893ac474b5bc3b9cd7edddf9ba2
3
- size 5777
 
 
 
 
checkpoint-1000/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/config.json DELETED
@@ -1,29 +0,0 @@
1
- {
2
- "architectures": [
3
- "RobertaForSequenceClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "bos_token_id": 0,
7
- "classifier_dropout": null,
8
- "dtype": "float32",
9
- "eos_token_id": 2,
10
- "gradient_checkpointing": false,
11
- "hidden_act": "gelu",
12
- "hidden_dropout_prob": 0.1,
13
- "hidden_size": 768,
14
- "initializer_range": 0.02,
15
- "intermediate_size": 3072,
16
- "layer_norm_eps": 1e-05,
17
- "max_position_embeddings": 1026,
18
- "model_type": "roberta",
19
- "num_attention_heads": 12,
20
- "num_hidden_layers": 12,
21
- "output_past": true,
22
- "pad_token_id": 1,
23
- "position_embedding_type": "absolute",
24
- "problem_type": "single_label_classification",
25
- "transformers_version": "4.56.0",
26
- "type_vocab_size": 10,
27
- "use_cache": true,
28
- "vocab_size": 51416
29
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1100/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b10c733460151c1d6f8993106b670307a2bb4c4b61d05e3eae7347702daac47
3
- size 506505672
 
 
 
 
checkpoint-1100/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:53bf52cb642b51369e0a95075a5b756e85921ef6f4dc7f444e6cfe7fe2a5900c
3
- size 1007622411
 
 
 
 
checkpoint-1100/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:61c7c55a742bcfca5f903384e20f8e91ee2f8d2f9879952f810307a3ce3992b6
3
- size 14645
 
 
 
 
checkpoint-1100/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:29c159530c0b045d9326d40e787007ff4922dc4adeb35441be0870744bf816a6
3
- size 1383
 
 
 
 
checkpoint-1100/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3c167e18770e153a7e8f12beebdae3ca1a3d373a59d87ddaedaa9c151bac765
3
- size 1977
 
 
 
 
checkpoint-1100/special_tokens_map.json DELETED
@@ -1,51 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
- "normalized": true,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1100/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/tokenizer_config.json DELETED
@@ -1,58 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<pad>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
- },
45
- "bos_token": "<s>",
46
- "clean_up_tokenization_spaces": false,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "extra_special_tokens": {},
51
- "mask_token": "<mask>",
52
- "model_max_length": 1000000000000000019884624838656,
53
- "pad_token": "<pad>",
54
- "sep_token": "</s>",
55
- "tokenizer_class": "RobertaTokenizer",
56
- "trim_offsets": true,
57
- "unk_token": "<unk>"
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1100/trainer_state.json DELETED
@@ -1,956 +0,0 @@
1
- {
2
- "best_global_step": 1000,
3
- "best_metric": 0.9644889377060355,
4
- "best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-1000",
5
- "epoch": 0.13458950201884254,
6
- "eval_steps": 100,
7
- "global_step": 1100,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.001223540927444023,
14
- "grad_norm": 0.1898110806941986,
15
- "learning_rate": 3.6734693877551025e-07,
16
- "loss": 0.4422,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 0.002447081854888046,
21
- "grad_norm": 0.3350900411605835,
22
- "learning_rate": 7.346938775510205e-07,
23
- "loss": 0.4323,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 0.003670622782332069,
28
- "grad_norm": 0.3723449110984802,
29
- "learning_rate": 1.142857142857143e-06,
30
- "loss": 0.4362,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 0.004894163709776092,
35
- "grad_norm": 0.3299769461154938,
36
- "learning_rate": 1.5510204081632654e-06,
37
- "loss": 0.4191,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 0.006117704637220115,
42
- "grad_norm": 0.26681044697761536,
43
- "learning_rate": 1.9591836734693877e-06,
44
- "loss": 0.4289,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 0.007341245564664138,
49
- "grad_norm": 0.30233338475227356,
50
- "learning_rate": 2.3673469387755103e-06,
51
- "loss": 0.4083,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.008564786492108161,
56
- "grad_norm": 0.31031334400177,
57
- "learning_rate": 2.775510204081633e-06,
58
- "loss": 0.404,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.009788327419552184,
63
- "grad_norm": 0.2552475035190582,
64
- "learning_rate": 3.183673469387755e-06,
65
- "loss": 0.3889,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.011011868346996207,
70
- "grad_norm": 0.3131052553653717,
71
- "learning_rate": 3.5918367346938777e-06,
72
- "loss": 0.3813,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.01223540927444023,
77
- "grad_norm": 0.3377229571342468,
78
- "learning_rate": 4.000000000000001e-06,
79
- "loss": 0.3727,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 0.01223540927444023,
84
- "eval_accuracy": 0.6961,
85
- "eval_f1_weighted": 0.6955947095331424,
86
- "eval_loss": 0.15026023983955383,
87
- "eval_macro_f1": 0.6959280508399847,
88
- "eval_precision": 0.7019396279846728,
89
- "eval_recall": 0.6961,
90
- "eval_runtime": 789.7648,
91
- "eval_samples_per_second": 126.62,
92
- "eval_steps_per_second": 0.99,
93
- "step": 100
94
- },
95
- {
96
- "epoch": 0.013458950201884253,
97
- "grad_norm": 0.3366774618625641,
98
- "learning_rate": 4.408163265306123e-06,
99
- "loss": 0.3671,
100
- "step": 110
101
- },
102
- {
103
- "epoch": 0.014682491129328276,
104
- "grad_norm": 0.33491575717926025,
105
- "learning_rate": 4.816326530612245e-06,
106
- "loss": 0.3498,
107
- "step": 120
108
- },
109
- {
110
- "epoch": 0.0159060320567723,
111
- "grad_norm": 0.4119006097316742,
112
- "learning_rate": 5.2244897959183684e-06,
113
- "loss": 0.3409,
114
- "step": 130
115
- },
116
- {
117
- "epoch": 0.017129572984216322,
118
- "grad_norm": 0.2964725196361542,
119
- "learning_rate": 5.63265306122449e-06,
120
- "loss": 0.3433,
121
- "step": 140
122
- },
123
- {
124
- "epoch": 0.018353113911660345,
125
- "grad_norm": 0.3075334429740906,
126
- "learning_rate": 6.040816326530613e-06,
127
- "loss": 0.3298,
128
- "step": 150
129
- },
130
- {
131
- "epoch": 0.019576654839104368,
132
- "grad_norm": 0.33718687295913696,
133
- "learning_rate": 6.4489795918367345e-06,
134
- "loss": 0.3297,
135
- "step": 160
136
- },
137
- {
138
- "epoch": 0.02080019576654839,
139
- "grad_norm": 0.2809618413448334,
140
- "learning_rate": 6.857142857142858e-06,
141
- "loss": 0.3275,
142
- "step": 170
143
- },
144
- {
145
- "epoch": 0.022023736693992414,
146
- "grad_norm": 0.37805014848709106,
147
- "learning_rate": 7.2653061224489805e-06,
148
- "loss": 0.3201,
149
- "step": 180
150
- },
151
- {
152
- "epoch": 0.023247277621436437,
153
- "grad_norm": 0.2940429151058197,
154
- "learning_rate": 7.673469387755102e-06,
155
- "loss": 0.3042,
156
- "step": 190
157
- },
158
- {
159
- "epoch": 0.02447081854888046,
160
- "grad_norm": 0.3286060690879822,
161
- "learning_rate": 8.081632653061225e-06,
162
- "loss": 0.3071,
163
- "step": 200
164
- },
165
- {
166
- "epoch": 0.02447081854888046,
167
- "eval_accuracy": 0.77807,
168
- "eval_f1_weighted": 0.7781129395311969,
169
- "eval_loss": 0.12153773754835129,
170
- "eval_macro_f1": 0.7780651598452646,
171
- "eval_precision": 0.7808306361972198,
172
- "eval_recall": 0.77807,
173
- "eval_runtime": 792.7157,
174
- "eval_samples_per_second": 126.149,
175
- "eval_steps_per_second": 0.986,
176
- "step": 200
177
- },
178
- {
179
- "epoch": 0.025694359476324483,
180
- "grad_norm": 0.33857154846191406,
181
- "learning_rate": 8.489795918367347e-06,
182
- "loss": 0.2964,
183
- "step": 210
184
- },
185
- {
186
- "epoch": 0.026917900403768506,
187
- "grad_norm": 0.2752092182636261,
188
- "learning_rate": 8.89795918367347e-06,
189
- "loss": 0.3,
190
- "step": 220
191
- },
192
- {
193
- "epoch": 0.02814144133121253,
194
- "grad_norm": 0.4952544569969177,
195
- "learning_rate": 9.306122448979593e-06,
196
- "loss": 0.294,
197
- "step": 230
198
- },
199
- {
200
- "epoch": 0.029364982258656552,
201
- "grad_norm": 0.37926042079925537,
202
- "learning_rate": 9.714285714285715e-06,
203
- "loss": 0.2964,
204
- "step": 240
205
- },
206
- {
207
- "epoch": 0.030588523186100575,
208
- "grad_norm": 0.3222455680370331,
209
- "learning_rate": 1.0122448979591836e-05,
210
- "loss": 0.283,
211
- "step": 250
212
- },
213
- {
214
- "epoch": 0.0318120641135446,
215
- "grad_norm": 0.2930658459663391,
216
- "learning_rate": 1.053061224489796e-05,
217
- "loss": 0.2793,
218
- "step": 260
219
- },
220
- {
221
- "epoch": 0.03303560504098862,
222
- "grad_norm": 0.4313414692878723,
223
- "learning_rate": 1.0938775510204083e-05,
224
- "loss": 0.2728,
225
- "step": 270
226
- },
227
- {
228
- "epoch": 0.034259145968432644,
229
- "grad_norm": 0.37351569533348083,
230
- "learning_rate": 1.1346938775510206e-05,
231
- "loss": 0.2752,
232
- "step": 280
233
- },
234
- {
235
- "epoch": 0.035482686895876664,
236
- "grad_norm": 0.22772285342216492,
237
- "learning_rate": 1.1755102040816328e-05,
238
- "loss": 0.274,
239
- "step": 290
240
- },
241
- {
242
- "epoch": 0.03670622782332069,
243
- "grad_norm": 0.15888753533363342,
244
- "learning_rate": 1.2163265306122449e-05,
245
- "loss": 0.264,
246
- "step": 300
247
- },
248
- {
249
- "epoch": 0.03670622782332069,
250
- "eval_accuracy": 0.82326,
251
- "eval_f1_weighted": 0.8227034206790359,
252
- "eval_loss": 0.10234300792217255,
253
- "eval_macro_f1": 0.8230100448030374,
254
- "eval_precision": 0.8338333810964687,
255
- "eval_recall": 0.82326,
256
- "eval_runtime": 789.0168,
257
- "eval_samples_per_second": 126.74,
258
- "eval_steps_per_second": 0.991,
259
- "step": 300
260
- },
261
- {
262
- "epoch": 0.03792976875076471,
263
- "grad_norm": 0.23560188710689545,
264
- "learning_rate": 1.2571428571428572e-05,
265
- "loss": 0.2753,
266
- "step": 310
267
- },
268
- {
269
- "epoch": 0.039153309678208736,
270
- "grad_norm": 0.18699614703655243,
271
- "learning_rate": 1.2979591836734696e-05,
272
- "loss": 0.2565,
273
- "step": 320
274
- },
275
- {
276
- "epoch": 0.040376850605652756,
277
- "grad_norm": 0.24035991728305817,
278
- "learning_rate": 1.3387755102040818e-05,
279
- "loss": 0.2716,
280
- "step": 330
281
- },
282
- {
283
- "epoch": 0.04160039153309678,
284
- "grad_norm": 0.15309660136699677,
285
- "learning_rate": 1.3795918367346941e-05,
286
- "loss": 0.2515,
287
- "step": 340
288
- },
289
- {
290
- "epoch": 0.0428239324605408,
291
- "grad_norm": 0.3382055461406708,
292
- "learning_rate": 1.4204081632653062e-05,
293
- "loss": 0.2597,
294
- "step": 350
295
- },
296
- {
297
- "epoch": 0.04404747338798483,
298
- "grad_norm": 0.24439455568790436,
299
- "learning_rate": 1.4612244897959185e-05,
300
- "loss": 0.247,
301
- "step": 360
302
- },
303
- {
304
- "epoch": 0.04527101431542885,
305
- "grad_norm": 0.26233720779418945,
306
- "learning_rate": 1.5020408163265307e-05,
307
- "loss": 0.2431,
308
- "step": 370
309
- },
310
- {
311
- "epoch": 0.046494555242872875,
312
- "grad_norm": 0.20477451384067535,
313
- "learning_rate": 1.5387755102040818e-05,
314
- "loss": 0.2538,
315
- "step": 380
316
- },
317
- {
318
- "epoch": 0.047718096170316894,
319
- "grad_norm": 0.2765439748764038,
320
- "learning_rate": 1.5795918367346942e-05,
321
- "loss": 0.2404,
322
- "step": 390
323
- },
324
- {
325
- "epoch": 0.04894163709776092,
326
- "grad_norm": 0.13196279108524323,
327
- "learning_rate": 1.6204081632653063e-05,
328
- "loss": 0.2393,
329
- "step": 400
330
- },
331
- {
332
- "epoch": 0.04894163709776092,
333
- "eval_accuracy": 0.84563,
334
- "eval_f1_weighted": 0.8448128964509274,
335
- "eval_loss": 0.09028046578168869,
336
- "eval_macro_f1": 0.8451923512067675,
337
- "eval_precision": 0.861024732271907,
338
- "eval_recall": 0.84563,
339
- "eval_runtime": 787.6067,
340
- "eval_samples_per_second": 126.967,
341
- "eval_steps_per_second": 0.993,
342
- "step": 400
343
- },
344
- {
345
- "epoch": 0.05016517802520494,
346
- "grad_norm": 0.0924634337425232,
347
- "learning_rate": 1.6612244897959184e-05,
348
- "loss": 0.2331,
349
- "step": 410
350
- },
351
- {
352
- "epoch": 0.05138871895264897,
353
- "grad_norm": 0.277784138917923,
354
- "learning_rate": 1.7020408163265308e-05,
355
- "loss": 0.2301,
356
- "step": 420
357
- },
358
- {
359
- "epoch": 0.052612259880092986,
360
- "grad_norm": 0.32299959659576416,
361
- "learning_rate": 1.742857142857143e-05,
362
- "loss": 0.2218,
363
- "step": 430
364
- },
365
- {
366
- "epoch": 0.05383580080753701,
367
- "grad_norm": 0.18170586228370667,
368
- "learning_rate": 1.7836734693877553e-05,
369
- "loss": 0.2318,
370
- "step": 440
371
- },
372
- {
373
- "epoch": 0.05505934173498103,
374
- "grad_norm": 0.1520216166973114,
375
- "learning_rate": 1.8244897959183674e-05,
376
- "loss": 0.2136,
377
- "step": 450
378
- },
379
- {
380
- "epoch": 0.05628288266242506,
381
- "grad_norm": 0.23452645540237427,
382
- "learning_rate": 1.8653061224489795e-05,
383
- "loss": 0.2219,
384
- "step": 460
385
- },
386
- {
387
- "epoch": 0.05750642358986908,
388
- "grad_norm": 0.10036301612854004,
389
- "learning_rate": 1.906122448979592e-05,
390
- "loss": 0.2213,
391
- "step": 470
392
- },
393
- {
394
- "epoch": 0.058729964517313105,
395
- "grad_norm": 0.24100220203399658,
396
- "learning_rate": 1.9469387755102044e-05,
397
- "loss": 0.2079,
398
- "step": 480
399
- },
400
- {
401
- "epoch": 0.059953505444757124,
402
- "grad_norm": 0.28893032670021057,
403
- "learning_rate": 1.9877551020408165e-05,
404
- "loss": 0.1978,
405
- "step": 490
406
- },
407
- {
408
- "epoch": 0.06117704637220115,
409
- "grad_norm": 0.22918537259101868,
410
- "learning_rate": 1.9999836143766126e-05,
411
- "loss": 0.202,
412
- "step": 500
413
- },
414
- {
415
- "epoch": 0.06117704637220115,
416
- "eval_accuracy": 0.91628,
417
- "eval_f1_weighted": 0.9163231793856368,
418
- "eval_loss": 0.055908624082803726,
419
- "eval_macro_f1": 0.9162187423616152,
420
- "eval_precision": 0.9170320825159874,
421
- "eval_recall": 0.91628,
422
- "eval_runtime": 760.1138,
423
- "eval_samples_per_second": 131.559,
424
- "eval_steps_per_second": 1.029,
425
- "step": 500
426
- },
427
- {
428
- "epoch": 0.06240058729964517,
429
- "grad_norm": 0.2930404841899872,
430
- "learning_rate": 1.999903359554741e-05,
431
- "loss": 0.1979,
432
- "step": 510
433
- },
434
- {
435
- "epoch": 0.0636241282270892,
436
- "grad_norm": 0.0889664739370346,
437
- "learning_rate": 1.9997562312908153e-05,
438
- "loss": 0.1953,
439
- "step": 520
440
- },
441
- {
442
- "epoch": 0.06484766915453322,
443
- "grad_norm": 0.1687588095664978,
444
- "learning_rate": 1.9995422394247598e-05,
445
- "loss": 0.1935,
446
- "step": 530
447
- },
448
- {
449
- "epoch": 0.06607121008197724,
450
- "grad_norm": 0.2399725466966629,
451
- "learning_rate": 1.9992613982683296e-05,
452
- "loss": 0.1818,
453
- "step": 540
454
- },
455
- {
456
- "epoch": 0.06729475100942127,
457
- "grad_norm": 0.2016785889863968,
458
- "learning_rate": 1.9989137266041552e-05,
459
- "loss": 0.1893,
460
- "step": 550
461
- },
462
- {
463
- "epoch": 0.06851829193686529,
464
- "grad_norm": 0.17420713603496552,
465
- "learning_rate": 1.9984992476844845e-05,
466
- "loss": 0.1895,
467
- "step": 560
468
- },
469
- {
470
- "epoch": 0.06974183286430931,
471
- "grad_norm": 0.2180609554052353,
472
- "learning_rate": 1.998017989229629e-05,
473
- "loss": 0.1836,
474
- "step": 570
475
- },
476
- {
477
- "epoch": 0.07096537379175333,
478
- "grad_norm": 0.15563039481639862,
479
- "learning_rate": 1.9974699834261074e-05,
480
- "loss": 0.182,
481
- "step": 580
482
- },
483
- {
484
- "epoch": 0.07218891471919736,
485
- "grad_norm": 0.25410088896751404,
486
- "learning_rate": 1.996855266924497e-05,
487
- "loss": 0.1862,
488
- "step": 590
489
- },
490
- {
491
- "epoch": 0.07341245564664138,
492
- "grad_norm": 0.24206259846687317,
493
- "learning_rate": 1.996173880836979e-05,
494
- "loss": 0.1818,
495
- "step": 600
496
- },
497
- {
498
- "epoch": 0.07341245564664138,
499
- "eval_accuracy": 0.91633,
500
- "eval_f1_weighted": 0.9162437523349878,
501
- "eval_loss": 0.05625538155436516,
502
- "eval_macro_f1": 0.9163072974421806,
503
- "eval_precision": 0.9233764457540103,
504
- "eval_recall": 0.91633,
505
- "eval_runtime": 759.6815,
506
- "eval_samples_per_second": 131.634,
507
- "eval_steps_per_second": 1.029,
508
- "step": 600
509
- },
510
- {
511
- "epoch": 0.0746359965740854,
512
- "grad_norm": 0.27251410484313965,
513
- "learning_rate": 1.9954258707345903e-05,
514
- "loss": 0.1845,
515
- "step": 610
516
- },
517
- {
518
- "epoch": 0.07585953750152942,
519
- "grad_norm": 0.1545839011669159,
520
- "learning_rate": 1.9946112866441757e-05,
521
- "loss": 0.1861,
522
- "step": 620
523
- },
524
- {
525
- "epoch": 0.07708307842897345,
526
- "grad_norm": 0.2535873055458069,
527
- "learning_rate": 1.9937301830450423e-05,
528
- "loss": 0.1772,
529
- "step": 630
530
- },
531
- {
532
- "epoch": 0.07830661935641747,
533
- "grad_norm": 0.2617948651313782,
534
- "learning_rate": 1.992782618865315e-05,
535
- "loss": 0.1711,
536
- "step": 640
537
- },
538
- {
539
- "epoch": 0.07953016028386149,
540
- "grad_norm": 0.38676971197128296,
541
- "learning_rate": 1.9917686574779972e-05,
542
- "loss": 0.1748,
543
- "step": 650
544
- },
545
- {
546
- "epoch": 0.08075370121130551,
547
- "grad_norm": 0.1511957049369812,
548
- "learning_rate": 1.9906883666967296e-05,
549
- "loss": 0.1825,
550
- "step": 660
551
- },
552
- {
553
- "epoch": 0.08197724213874955,
554
- "grad_norm": 0.2525976002216339,
555
- "learning_rate": 1.989541818771258e-05,
556
- "loss": 0.1651,
557
- "step": 670
558
- },
559
- {
560
- "epoch": 0.08320078306619356,
561
- "grad_norm": 0.25827622413635254,
562
- "learning_rate": 1.9883290903825994e-05,
563
- "loss": 0.1763,
564
- "step": 680
565
- },
566
- {
567
- "epoch": 0.08442432399363758,
568
- "grad_norm": 0.24877820909023285,
569
- "learning_rate": 1.9870502626379127e-05,
570
- "loss": 0.1652,
571
- "step": 690
572
- },
573
- {
574
- "epoch": 0.0856478649210816,
575
- "grad_norm": 0.278772234916687,
576
- "learning_rate": 1.9857054210650776e-05,
577
- "loss": 0.1651,
578
- "step": 700
579
- },
580
- {
581
- "epoch": 0.0856478649210816,
582
- "eval_accuracy": 0.94905,
583
- "eval_f1_weighted": 0.9490731118481598,
584
- "eval_loss": 0.03884471580386162,
585
- "eval_macro_f1": 0.9489981325237288,
586
- "eval_precision": 0.9494795831024372,
587
- "eval_recall": 0.94905,
588
- "eval_runtime": 759.9337,
589
- "eval_samples_per_second": 131.59,
590
- "eval_steps_per_second": 1.029,
591
- "step": 700
592
- },
593
- {
594
- "epoch": 0.08687140584852564,
595
- "grad_norm": 0.1895805150270462,
596
- "learning_rate": 1.9842946556069705e-05,
597
- "loss": 0.1628,
598
- "step": 710
599
- },
600
- {
601
- "epoch": 0.08809494677596966,
602
- "grad_norm": 0.1171497106552124,
603
- "learning_rate": 1.982818060615452e-05,
604
- "loss": 0.1715,
605
- "step": 720
606
- },
607
- {
608
- "epoch": 0.08931848770341368,
609
- "grad_norm": 0.22032728791236877,
610
- "learning_rate": 1.9812757348450547e-05,
611
- "loss": 0.1712,
612
- "step": 730
613
- },
614
- {
615
- "epoch": 0.0905420286308577,
616
- "grad_norm": 0.20700488984584808,
617
- "learning_rate": 1.9796677814463812e-05,
618
- "loss": 0.1638,
619
- "step": 740
620
- },
621
- {
622
- "epoch": 0.09176556955830173,
623
- "grad_norm": 0.24688613414764404,
624
- "learning_rate": 1.977994307959202e-05,
625
- "loss": 0.1647,
626
- "step": 750
627
- },
628
- {
629
- "epoch": 0.09298911048574575,
630
- "grad_norm": 0.1886432021856308,
631
- "learning_rate": 1.9762554263052655e-05,
632
- "loss": 0.1734,
633
- "step": 760
634
- },
635
- {
636
- "epoch": 0.09421265141318977,
637
- "grad_norm": 0.08407370001077652,
638
- "learning_rate": 1.9744512527808127e-05,
639
- "loss": 0.1755,
640
- "step": 770
641
- },
642
- {
643
- "epoch": 0.09543619234063379,
644
- "grad_norm": 0.14160771667957306,
645
- "learning_rate": 1.9725819080487976e-05,
646
- "loss": 0.1749,
647
- "step": 780
648
- },
649
- {
650
- "epoch": 0.09665973326807782,
651
- "grad_norm": 0.17038081586360931,
652
- "learning_rate": 1.970647517130819e-05,
653
- "loss": 0.1795,
654
- "step": 790
655
- },
656
- {
657
- "epoch": 0.09788327419552184,
658
- "grad_norm": 0.24339532852172852,
659
- "learning_rate": 1.968648209398759e-05,
660
- "loss": 0.161,
661
- "step": 800
662
- },
663
- {
664
- "epoch": 0.09788327419552184,
665
- "eval_accuracy": 0.95721,
666
- "eval_f1_weighted": 0.9572295598206603,
667
- "eval_loss": 0.03337462991476059,
668
- "eval_macro_f1": 0.9571669846830866,
669
- "eval_precision": 0.9576467364395861,
670
- "eval_recall": 0.95721,
671
- "eval_runtime": 759.9975,
672
- "eval_samples_per_second": 131.579,
673
- "eval_steps_per_second": 1.029,
674
- "step": 800
675
- },
676
- {
677
- "epoch": 0.09910681512296586,
678
- "grad_norm": 0.16346058249473572,
679
- "learning_rate": 1.9665841185661283e-05,
680
- "loss": 0.1596,
681
- "step": 810
682
- },
683
- {
684
- "epoch": 0.10033035605040988,
685
- "grad_norm": 0.25031423568725586,
686
- "learning_rate": 1.964455382679128e-05,
687
- "loss": 0.1662,
688
- "step": 820
689
- },
690
- {
691
- "epoch": 0.10155389697785391,
692
- "grad_norm": 0.36678382754325867,
693
- "learning_rate": 1.9622621441074113e-05,
694
- "loss": 0.1552,
695
- "step": 830
696
- },
697
- {
698
- "epoch": 0.10277743790529793,
699
- "grad_norm": 0.34810611605644226,
700
- "learning_rate": 1.960004549534567e-05,
701
- "loss": 0.1663,
702
- "step": 840
703
- },
704
- {
705
- "epoch": 0.10400097883274195,
706
- "grad_norm": 0.15511688590049744,
707
- "learning_rate": 1.957682749948307e-05,
708
- "loss": 0.1571,
709
- "step": 850
710
- },
711
- {
712
- "epoch": 0.10522451976018597,
713
- "grad_norm": 0.2082190364599228,
714
- "learning_rate": 1.9552969006303666e-05,
715
- "loss": 0.1497,
716
- "step": 860
717
- },
718
- {
719
- "epoch": 0.10644806068763,
720
- "grad_norm": 0.14936988055706024,
721
- "learning_rate": 1.9528471611461235e-05,
722
- "loss": 0.1435,
723
- "step": 870
724
- },
725
- {
726
- "epoch": 0.10767160161507403,
727
- "grad_norm": 0.252530574798584,
728
- "learning_rate": 1.9503336953339223e-05,
729
- "loss": 0.1536,
730
- "step": 880
731
- },
732
- {
733
- "epoch": 0.10889514254251804,
734
- "grad_norm": 0.07253506034612656,
735
- "learning_rate": 1.947756671294118e-05,
736
- "loss": 0.1605,
737
- "step": 890
738
- },
739
- {
740
- "epoch": 0.11011868346996206,
741
- "grad_norm": 0.09060605615377426,
742
- "learning_rate": 1.9451162613778353e-05,
743
- "loss": 0.1581,
744
- "step": 900
745
- },
746
- {
747
- "epoch": 0.11011868346996206,
748
- "eval_accuracy": 0.95459,
749
- "eval_f1_weighted": 0.9546135918699761,
750
- "eval_loss": 0.03526490181684494,
751
- "eval_macro_f1": 0.9545725664001194,
752
- "eval_precision": 0.9559789658562307,
753
- "eval_recall": 0.95459,
754
- "eval_runtime": 759.7202,
755
- "eval_samples_per_second": 131.627,
756
- "eval_steps_per_second": 1.029,
757
- "step": 900
758
- },
759
- {
760
- "epoch": 0.1113422243974061,
761
- "grad_norm": 0.21080073714256287,
762
- "learning_rate": 1.942412642175439e-05,
763
- "loss": 0.164,
764
- "step": 910
765
- },
766
- {
767
- "epoch": 0.11256576532485012,
768
- "grad_norm": 0.22832269966602325,
769
- "learning_rate": 1.939645994504726e-05,
770
- "loss": 0.1595,
771
- "step": 920
772
- },
773
- {
774
- "epoch": 0.11378930625229414,
775
- "grad_norm": 0.19044892489910126,
776
- "learning_rate": 1.93681650339883e-05,
777
- "loss": 0.1648,
778
- "step": 930
779
- },
780
- {
781
- "epoch": 0.11501284717973816,
782
- "grad_norm": 0.2413518726825714,
783
- "learning_rate": 1.9339243580938493e-05,
784
- "loss": 0.155,
785
- "step": 940
786
- },
787
- {
788
- "epoch": 0.11623638810718219,
789
- "grad_norm": 0.13218896090984344,
790
- "learning_rate": 1.930969752016187e-05,
791
- "loss": 0.1499,
792
- "step": 950
793
- },
794
- {
795
- "epoch": 0.11745992903462621,
796
- "grad_norm": 0.23770441114902496,
797
- "learning_rate": 1.927952882769619e-05,
798
- "loss": 0.1555,
799
- "step": 960
800
- },
801
- {
802
- "epoch": 0.11868346996207023,
803
- "grad_norm": 0.2193710207939148,
804
- "learning_rate": 1.924873952122074e-05,
805
- "loss": 0.1505,
806
- "step": 970
807
- },
808
- {
809
- "epoch": 0.11990701088951425,
810
- "grad_norm": 0.1577174812555313,
811
- "learning_rate": 1.9217331659921432e-05,
812
- "loss": 0.1551,
813
- "step": 980
814
- },
815
- {
816
- "epoch": 0.12113055181695828,
817
- "grad_norm": 0.1814967393875122,
818
- "learning_rate": 1.9185307344353052e-05,
819
- "loss": 0.1607,
820
- "step": 990
821
- },
822
- {
823
- "epoch": 0.1223540927444023,
824
- "grad_norm": 0.27239707112312317,
825
- "learning_rate": 1.91526687162988e-05,
826
- "loss": 0.1506,
827
- "step": 1000
828
- },
829
- {
830
- "epoch": 0.1223540927444023,
831
- "eval_accuracy": 0.96454,
832
- "eval_f1_weighted": 0.9645510150201642,
833
- "eval_loss": 0.028770776465535164,
834
- "eval_macro_f1": 0.9644889377060355,
835
- "eval_precision": 0.9646912114769961,
836
- "eval_recall": 0.96454,
837
- "eval_runtime": 759.5962,
838
- "eval_samples_per_second": 131.649,
839
- "eval_steps_per_second": 1.029,
840
- "step": 1000
841
- },
842
- {
843
- "epoch": 0.12357763367184632,
844
- "grad_norm": 0.20511822402477264,
845
- "learning_rate": 1.9119417958627022e-05,
846
- "loss": 0.1503,
847
- "step": 1010
848
- },
849
- {
850
- "epoch": 0.12480117459929034,
851
- "grad_norm": 0.2324151247739792,
852
- "learning_rate": 1.9085557295145254e-05,
853
- "loss": 0.1581,
854
- "step": 1020
855
- },
856
- {
857
- "epoch": 0.12602471552673436,
858
- "grad_norm": 0.11019974201917648,
859
- "learning_rate": 1.905108899045146e-05,
860
- "loss": 0.1556,
861
- "step": 1030
862
- },
863
- {
864
- "epoch": 0.1272482564541784,
865
- "grad_norm": 0.13370558619499207,
866
- "learning_rate": 1.9016015349782594e-05,
867
- "loss": 0.1469,
868
- "step": 1040
869
- },
870
- {
871
- "epoch": 0.12847179738162243,
872
- "grad_norm": 0.11238931119441986,
873
- "learning_rate": 1.8980338718860426e-05,
874
- "loss": 0.155,
875
- "step": 1050
876
- },
877
- {
878
- "epoch": 0.12969533830906643,
879
- "grad_norm": 0.2959650158882141,
880
- "learning_rate": 1.894406148373466e-05,
881
- "loss": 0.1478,
882
- "step": 1060
883
- },
884
- {
885
- "epoch": 0.13091887923651047,
886
- "grad_norm": 0.14401015639305115,
887
- "learning_rate": 1.890718607062334e-05,
888
- "loss": 0.1558,
889
- "step": 1070
890
- },
891
- {
892
- "epoch": 0.13214242016395447,
893
- "grad_norm": 0.2187667042016983,
894
- "learning_rate": 1.8869714945750614e-05,
895
- "loss": 0.1618,
896
- "step": 1080
897
- },
898
- {
899
- "epoch": 0.1333659610913985,
900
- "grad_norm": 0.17045481503009796,
901
- "learning_rate": 1.883165061518176e-05,
902
- "loss": 0.1487,
903
- "step": 1090
904
- },
905
- {
906
- "epoch": 0.13458950201884254,
907
- "grad_norm": 0.09508351981639862,
908
- "learning_rate": 1.8792995624655605e-05,
909
- "loss": 0.1461,
910
- "step": 1100
911
- },
912
- {
913
- "epoch": 0.13458950201884254,
914
- "eval_accuracy": 0.95198,
915
- "eval_f1_weighted": 0.9520023284947491,
916
- "eval_loss": 0.04088817164301872,
917
- "eval_macro_f1": 0.9519693367124435,
918
- "eval_precision": 0.9538785423213092,
919
- "eval_recall": 0.95198,
920
- "eval_runtime": 759.8551,
921
- "eval_samples_per_second": 131.604,
922
- "eval_steps_per_second": 1.029,
923
- "step": 1100
924
- }
925
- ],
926
- "logging_steps": 10,
927
- "max_steps": 8173,
928
- "num_input_tokens_seen": 0,
929
- "num_train_epochs": 1,
930
- "save_steps": 100,
931
- "stateful_callbacks": {
932
- "EarlyStoppingCallback": {
933
- "args": {
934
- "early_stopping_patience": 3,
935
- "early_stopping_threshold": 0.0
936
- },
937
- "attributes": {
938
- "early_stopping_patience_counter": 1
939
- }
940
- },
941
- "TrainerControl": {
942
- "args": {
943
- "should_epoch_stop": false,
944
- "should_evaluate": false,
945
- "should_log": false,
946
- "should_save": true,
947
- "should_training_stop": false
948
- },
949
- "attributes": {}
950
- }
951
- },
952
- "total_flos": 1.86720326909952e+16,
953
- "train_batch_size": 64,
954
- "trial_name": null,
955
- "trial_params": null
956
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1100/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:84799314bcc123b16dc7e721b7c0a39a7148ba4c572d589c671664f2e203e207
3
- size 5841
 
 
 
 
checkpoint-1100/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1200/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "architectures": [
3
- "RobertaForSequenceClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "bos_token_id": 0,
7
- "classifier_dropout": null,
8
- "dtype": "float32",
9
- "eos_token_id": 2,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "layer_norm_eps": 1e-05,
16
- "max_position_embeddings": 514,
17
- "model_type": "roberta",
18
- "num_attention_heads": 12,
19
- "num_hidden_layers": 12,
20
- "output_past": true,
21
- "pad_token_id": 1,
22
- "position_embedding_type": "absolute",
23
- "transformers_version": "4.56.0",
24
- "type_vocab_size": 1,
25
- "use_cache": true,
26
- "vocab_size": 50265
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1200/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1200/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:61d5c9de3cde05f670095e14f42c9e4589698ab7e7544947e9899cb0fe38685d
3
- size 498612824
 
 
 
 
checkpoint-1200/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:91d4f9219105610d445d1323ff323318ea75bcd29155e0cbd304baef2009c888
3
- size 4741859
 
 
 
 
checkpoint-1200/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a61d9b89bfb67c8331499ea02a3f044c3de94ae9858090c63f03cffdd302305e
3
- size 14645
 
 
 
 
checkpoint-1200/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd0aac41bfa547f4a1790a56d1fdcb6598cb130255e5d0420b6b94b14c070642
3
- size 1465
 
 
 
 
checkpoint-1200/special_tokens_map.json DELETED
@@ -1,51 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1200/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1200/tokenizer_config.json DELETED
@@ -1,58 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<pad>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "50264": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
- },
45
- "bos_token": "<s>",
46
- "clean_up_tokenization_spaces": false,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "extra_special_tokens": {},
51
- "mask_token": "<mask>",
52
- "model_max_length": 512,
53
- "pad_token": "<pad>",
54
- "sep_token": "</s>",
55
- "tokenizer_class": "RobertaTokenizer",
56
- "trim_offsets": true,
57
- "unk_token": "<unk>"
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1200/trainer_state.json DELETED
@@ -1,955 +0,0 @@
1
- {
2
- "best_global_step": 1200,
3
- "best_metric": 0.6993136399748257,
4
- "best_model_checkpoint": "./taskA-codebert-base/checkpoint-1200",
5
- "epoch": 0.15359017022910534,
6
- "eval_steps": 200,
7
- "global_step": 1200,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.0012799180852425445,
14
- "grad_norm": 3.6954128742218018,
15
- "learning_rate": 3.840409643695328e-08,
16
- "loss": 0.7763,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 0.002559836170485089,
21
- "grad_norm": 3.3660645484924316,
22
- "learning_rate": 8.10753147002347e-08,
23
- "loss": 0.7763,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 0.0038397542557276334,
28
- "grad_norm": 4.491067886352539,
29
- "learning_rate": 1.2374653296351612e-07,
30
- "loss": 0.7889,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 0.005119672340970178,
35
- "grad_norm": 1.5920521020889282,
36
- "learning_rate": 1.6641775122679754e-07,
37
- "loss": 0.7888,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 0.006399590426212722,
42
- "grad_norm": 4.410898208618164,
43
- "learning_rate": 2.0908896949007894e-07,
44
- "loss": 0.7692,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 0.007679508511455267,
49
- "grad_norm": 2.5669264793395996,
50
- "learning_rate": 2.517601877533604e-07,
51
- "loss": 0.7735,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.008959426596697812,
56
- "grad_norm": 6.190986156463623,
57
- "learning_rate": 2.944314060166418e-07,
58
- "loss": 0.7679,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.010239344681940356,
63
- "grad_norm": 5.736413478851318,
64
- "learning_rate": 3.371026242799232e-07,
65
- "loss": 0.744,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.011519262767182901,
70
- "grad_norm": 4.278866767883301,
71
- "learning_rate": 3.7977384254320464e-07,
72
- "loss": 0.7542,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.012799180852425445,
77
- "grad_norm": 5.565455436706543,
78
- "learning_rate": 4.22445060806486e-07,
79
- "loss": 0.752,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 0.01407909893766799,
84
- "grad_norm": 4.031781196594238,
85
- "learning_rate": 4.651162790697675e-07,
86
- "loss": 0.7614,
87
- "step": 110
88
- },
89
- {
90
- "epoch": 0.015359017022910534,
91
- "grad_norm": 2.484126329421997,
92
- "learning_rate": 5.077874973330489e-07,
93
- "loss": 0.7664,
94
- "step": 120
95
- },
96
- {
97
- "epoch": 0.016638935108153077,
98
- "grad_norm": 2.7525155544281006,
99
- "learning_rate": 5.504587155963304e-07,
100
- "loss": 0.7521,
101
- "step": 130
102
- },
103
- {
104
- "epoch": 0.017918853193395624,
105
- "grad_norm": 1.6374385356903076,
106
- "learning_rate": 5.931299338596117e-07,
107
- "loss": 0.7436,
108
- "step": 140
109
- },
110
- {
111
- "epoch": 0.019198771278638168,
112
- "grad_norm": 2.370774269104004,
113
- "learning_rate": 6.358011521228932e-07,
114
- "loss": 0.7429,
115
- "step": 150
116
- },
117
- {
118
- "epoch": 0.02047868936388071,
119
- "grad_norm": 2.8948566913604736,
120
- "learning_rate": 6.784723703861745e-07,
121
- "loss": 0.7333,
122
- "step": 160
123
- },
124
- {
125
- "epoch": 0.021758607449123255,
126
- "grad_norm": 2.7481186389923096,
127
- "learning_rate": 7.21143588649456e-07,
128
- "loss": 0.7294,
129
- "step": 170
130
- },
131
- {
132
- "epoch": 0.023038525534365802,
133
- "grad_norm": 2.0159404277801514,
134
- "learning_rate": 7.638148069127374e-07,
135
- "loss": 0.731,
136
- "step": 180
137
- },
138
- {
139
- "epoch": 0.024318443619608346,
140
- "grad_norm": 3.6898131370544434,
141
- "learning_rate": 8.064860251760189e-07,
142
- "loss": 0.7153,
143
- "step": 190
144
- },
145
- {
146
- "epoch": 0.02559836170485089,
147
- "grad_norm": 3.2842342853546143,
148
- "learning_rate": 8.491572434393003e-07,
149
- "loss": 0.7245,
150
- "step": 200
151
- },
152
- {
153
- "epoch": 0.02559836170485089,
154
- "eval_accuracy": 0.47695,
155
- "eval_loss": 0.7148504853248596,
156
- "eval_macro_f1": 0.3229290091066048,
157
- "eval_precision": 0.238475,
158
- "eval_recall": 0.5,
159
- "eval_runtime": 1641.324,
160
- "eval_samples_per_second": 60.926,
161
- "eval_steps_per_second": 0.476,
162
- "step": 200
163
- },
164
- {
165
- "epoch": 0.026878279790093433,
166
- "grad_norm": 2.294558048248291,
167
- "learning_rate": 8.918284617025817e-07,
168
- "loss": 0.718,
169
- "step": 210
170
- },
171
- {
172
- "epoch": 0.02815819787533598,
173
- "grad_norm": 2.9467175006866455,
174
- "learning_rate": 9.344996799658632e-07,
175
- "loss": 0.7076,
176
- "step": 220
177
- },
178
- {
179
- "epoch": 0.029438115960578524,
180
- "grad_norm": 2.6889193058013916,
181
- "learning_rate": 9.771708982291445e-07,
182
- "loss": 0.7019,
183
- "step": 230
184
- },
185
- {
186
- "epoch": 0.030718034045821067,
187
- "grad_norm": 0.7491384744644165,
188
- "learning_rate": 1.0198421164924258e-06,
189
- "loss": 0.7046,
190
- "step": 240
191
- },
192
- {
193
- "epoch": 0.031997952131063614,
194
- "grad_norm": 2.0363433361053467,
195
- "learning_rate": 1.0625133347557074e-06,
196
- "loss": 0.7085,
197
- "step": 250
198
- },
199
- {
200
- "epoch": 0.033277870216306155,
201
- "grad_norm": 1.1431337594985962,
202
- "learning_rate": 1.1051845530189888e-06,
203
- "loss": 0.7008,
204
- "step": 260
205
- },
206
- {
207
- "epoch": 0.0345577883015487,
208
- "grad_norm": 3.7735233306884766,
209
- "learning_rate": 1.1478557712822702e-06,
210
- "loss": 0.7015,
211
- "step": 270
212
- },
213
- {
214
- "epoch": 0.03583770638679125,
215
- "grad_norm": 0.7889328002929688,
216
- "learning_rate": 1.1905269895455517e-06,
217
- "loss": 0.699,
218
- "step": 280
219
- },
220
- {
221
- "epoch": 0.03711762447203379,
222
- "grad_norm": 0.8796226382255554,
223
- "learning_rate": 1.233198207808833e-06,
224
- "loss": 0.6922,
225
- "step": 290
226
- },
227
- {
228
- "epoch": 0.038397542557276336,
229
- "grad_norm": 0.7966652512550354,
230
- "learning_rate": 1.2758694260721145e-06,
231
- "loss": 0.6949,
232
- "step": 300
233
- },
234
- {
235
- "epoch": 0.039677460642518876,
236
- "grad_norm": 0.7029069066047668,
237
- "learning_rate": 1.318540644335396e-06,
238
- "loss": 0.695,
239
- "step": 310
240
- },
241
- {
242
- "epoch": 0.04095737872776142,
243
- "grad_norm": 2.04327392578125,
244
- "learning_rate": 1.3612118625986772e-06,
245
- "loss": 0.6944,
246
- "step": 320
247
- },
248
- {
249
- "epoch": 0.04223729681300397,
250
- "grad_norm": 0.918025553226471,
251
- "learning_rate": 1.4038830808619588e-06,
252
- "loss": 0.6863,
253
- "step": 330
254
- },
255
- {
256
- "epoch": 0.04351721489824651,
257
- "grad_norm": 0.9528706073760986,
258
- "learning_rate": 1.4465542991252401e-06,
259
- "loss": 0.6907,
260
- "step": 340
261
- },
262
- {
263
- "epoch": 0.04479713298348906,
264
- "grad_norm": 1.071359634399414,
265
- "learning_rate": 1.4892255173885215e-06,
266
- "loss": 0.6873,
267
- "step": 350
268
- },
269
- {
270
- "epoch": 0.046077051068731605,
271
- "grad_norm": 1.9875625371932983,
272
- "learning_rate": 1.531896735651803e-06,
273
- "loss": 0.6942,
274
- "step": 360
275
- },
276
- {
277
- "epoch": 0.047356969153974145,
278
- "grad_norm": 2.0222439765930176,
279
- "learning_rate": 1.5745679539150842e-06,
280
- "loss": 0.6898,
281
- "step": 370
282
- },
283
- {
284
- "epoch": 0.04863688723921669,
285
- "grad_norm": 1.7827857732772827,
286
- "learning_rate": 1.6172391721783658e-06,
287
- "loss": 0.6909,
288
- "step": 380
289
- },
290
- {
291
- "epoch": 0.04991680532445923,
292
- "grad_norm": 1.065674901008606,
293
- "learning_rate": 1.6599103904416472e-06,
294
- "loss": 0.6877,
295
- "step": 390
296
- },
297
- {
298
- "epoch": 0.05119672340970178,
299
- "grad_norm": 0.8346193432807922,
300
- "learning_rate": 1.7025816087049288e-06,
301
- "loss": 0.6889,
302
- "step": 400
303
- },
304
- {
305
- "epoch": 0.05119672340970178,
306
- "eval_accuracy": 0.54043,
307
- "eval_loss": 0.6827595233917236,
308
- "eval_macro_f1": 0.41833840347598905,
309
- "eval_precision": 0.5839205994464474,
310
- "eval_recall": 0.5204152767503025,
311
- "eval_runtime": 1634.6244,
312
- "eval_samples_per_second": 61.176,
313
- "eval_steps_per_second": 0.478,
314
- "step": 400
315
- },
316
- {
317
- "epoch": 0.052476641494944326,
318
- "grad_norm": 0.8074935674667358,
319
- "learning_rate": 1.7452528269682101e-06,
320
- "loss": 0.684,
321
- "step": 410
322
- },
323
- {
324
- "epoch": 0.053756559580186866,
325
- "grad_norm": 0.8965069651603699,
326
- "learning_rate": 1.7879240452314913e-06,
327
- "loss": 0.6922,
328
- "step": 420
329
- },
330
- {
331
- "epoch": 0.05503647766542941,
332
- "grad_norm": 2.597215414047241,
333
- "learning_rate": 1.8305952634947729e-06,
334
- "loss": 0.6909,
335
- "step": 430
336
- },
337
- {
338
- "epoch": 0.05631639575067196,
339
- "grad_norm": 0.8233373165130615,
340
- "learning_rate": 1.8732664817580542e-06,
341
- "loss": 0.6831,
342
- "step": 440
343
- },
344
- {
345
- "epoch": 0.0575963138359145,
346
- "grad_norm": 1.0624489784240723,
347
- "learning_rate": 1.915937700021336e-06,
348
- "loss": 0.6817,
349
- "step": 450
350
- },
351
- {
352
- "epoch": 0.05887623192115705,
353
- "grad_norm": 2.0623559951782227,
354
- "learning_rate": 1.958608918284617e-06,
355
- "loss": 0.6819,
356
- "step": 460
357
- },
358
- {
359
- "epoch": 0.06015615000639959,
360
- "grad_norm": 0.912433922290802,
361
- "learning_rate": 2.0012801365478988e-06,
362
- "loss": 0.686,
363
- "step": 470
364
- },
365
- {
366
- "epoch": 0.061436068091642135,
367
- "grad_norm": 0.6926271319389343,
368
- "learning_rate": 2.04395135481118e-06,
369
- "loss": 0.6834,
370
- "step": 480
371
- },
372
- {
373
- "epoch": 0.06271598617688467,
374
- "grad_norm": 1.498634934425354,
375
- "learning_rate": 2.0866225730744615e-06,
376
- "loss": 0.6805,
377
- "step": 490
378
- },
379
- {
380
- "epoch": 0.06399590426212723,
381
- "grad_norm": 1.1818156242370605,
382
- "learning_rate": 2.129293791337743e-06,
383
- "loss": 0.6805,
384
- "step": 500
385
- },
386
- {
387
- "epoch": 0.06527582234736977,
388
- "grad_norm": 1.4476051330566406,
389
- "learning_rate": 2.1719650096010242e-06,
390
- "loss": 0.6773,
391
- "step": 510
392
- },
393
- {
394
- "epoch": 0.06655574043261231,
395
- "grad_norm": 1.1143743991851807,
396
- "learning_rate": 2.214636227864306e-06,
397
- "loss": 0.6801,
398
- "step": 520
399
- },
400
- {
401
- "epoch": 0.06783565851785486,
402
- "grad_norm": 1.7030247449874878,
403
- "learning_rate": 2.257307446127587e-06,
404
- "loss": 0.6794,
405
- "step": 530
406
- },
407
- {
408
- "epoch": 0.0691155766030974,
409
- "grad_norm": 0.8592290282249451,
410
- "learning_rate": 2.2999786643908685e-06,
411
- "loss": 0.6736,
412
- "step": 540
413
- },
414
- {
415
- "epoch": 0.07039549468833994,
416
- "grad_norm": 0.8231940865516663,
417
- "learning_rate": 2.34264988265415e-06,
418
- "loss": 0.67,
419
- "step": 550
420
- },
421
- {
422
- "epoch": 0.0716754127735825,
423
- "grad_norm": 0.88897705078125,
424
- "learning_rate": 2.3853211009174317e-06,
425
- "loss": 0.685,
426
- "step": 560
427
- },
428
- {
429
- "epoch": 0.07295533085882504,
430
- "grad_norm": 1.6297541856765747,
431
- "learning_rate": 2.427992319180713e-06,
432
- "loss": 0.6797,
433
- "step": 570
434
- },
435
- {
436
- "epoch": 0.07423524894406758,
437
- "grad_norm": 2.9297447204589844,
438
- "learning_rate": 2.470663537443994e-06,
439
- "loss": 0.6766,
440
- "step": 580
441
- },
442
- {
443
- "epoch": 0.07551516702931012,
444
- "grad_norm": 0.9277703762054443,
445
- "learning_rate": 2.5133347557072756e-06,
446
- "loss": 0.6824,
447
- "step": 590
448
- },
449
- {
450
- "epoch": 0.07679508511455267,
451
- "grad_norm": 0.5883333683013916,
452
- "learning_rate": 2.556005973970557e-06,
453
- "loss": 0.6818,
454
- "step": 600
455
- },
456
- {
457
- "epoch": 0.07679508511455267,
458
- "eval_accuracy": 0.63909,
459
- "eval_loss": 0.6700075268745422,
460
- "eval_macro_f1": 0.621848143053056,
461
- "eval_precision": 0.6524313071088819,
462
- "eval_recall": 0.6305863955136095,
463
- "eval_runtime": 1633.9732,
464
- "eval_samples_per_second": 61.201,
465
- "eval_steps_per_second": 0.479,
466
- "step": 600
467
- },
468
- {
469
- "epoch": 0.07807500319979521,
470
- "grad_norm": 0.7149448394775391,
471
- "learning_rate": 2.5986771922338383e-06,
472
- "loss": 0.6746,
473
- "step": 610
474
- },
475
- {
476
- "epoch": 0.07935492128503775,
477
- "grad_norm": 2.0167856216430664,
478
- "learning_rate": 2.64134841049712e-06,
479
- "loss": 0.682,
480
- "step": 620
481
- },
482
- {
483
- "epoch": 0.0806348393702803,
484
- "grad_norm": 1.303001880645752,
485
- "learning_rate": 2.6840196287604015e-06,
486
- "loss": 0.6735,
487
- "step": 630
488
- },
489
- {
490
- "epoch": 0.08191475745552285,
491
- "grad_norm": 2.0516321659088135,
492
- "learning_rate": 2.7266908470236826e-06,
493
- "loss": 0.6705,
494
- "step": 640
495
- },
496
- {
497
- "epoch": 0.08319467554076539,
498
- "grad_norm": 2.242105484008789,
499
- "learning_rate": 2.7693620652869642e-06,
500
- "loss": 0.6798,
501
- "step": 650
502
- },
503
- {
504
- "epoch": 0.08447459362600794,
505
- "grad_norm": 1.1836538314819336,
506
- "learning_rate": 2.812033283550246e-06,
507
- "loss": 0.6684,
508
- "step": 660
509
- },
510
- {
511
- "epoch": 0.08575451171125048,
512
- "grad_norm": 0.8640874624252319,
513
- "learning_rate": 2.8547045018135274e-06,
514
- "loss": 0.6783,
515
- "step": 670
516
- },
517
- {
518
- "epoch": 0.08703442979649302,
519
- "grad_norm": 0.6901177763938904,
520
- "learning_rate": 2.897375720076808e-06,
521
- "loss": 0.6724,
522
- "step": 680
523
- },
524
- {
525
- "epoch": 0.08831434788173557,
526
- "grad_norm": 1.3443949222564697,
527
- "learning_rate": 2.9400469383400897e-06,
528
- "loss": 0.67,
529
- "step": 690
530
- },
531
- {
532
- "epoch": 0.08959426596697811,
533
- "grad_norm": 0.7775189280509949,
534
- "learning_rate": 2.9827181566033713e-06,
535
- "loss": 0.6733,
536
- "step": 700
537
- },
538
- {
539
- "epoch": 0.09087418405222066,
540
- "grad_norm": 1.16916823387146,
541
- "learning_rate": 3.025389374866653e-06,
542
- "loss": 0.6713,
543
- "step": 710
544
- },
545
- {
546
- "epoch": 0.09215410213746321,
547
- "grad_norm": 1.707152009010315,
548
- "learning_rate": 3.068060593129934e-06,
549
- "loss": 0.6659,
550
- "step": 720
551
- },
552
- {
553
- "epoch": 0.09343402022270575,
554
- "grad_norm": 0.9780622124671936,
555
- "learning_rate": 3.1107318113932156e-06,
556
- "loss": 0.6639,
557
- "step": 730
558
- },
559
- {
560
- "epoch": 0.09471393830794829,
561
- "grad_norm": 2.3687374591827393,
562
- "learning_rate": 3.153403029656497e-06,
563
- "loss": 0.6666,
564
- "step": 740
565
- },
566
- {
567
- "epoch": 0.09599385639319083,
568
- "grad_norm": 0.8506460189819336,
569
- "learning_rate": 3.1960742479197783e-06,
570
- "loss": 0.6778,
571
- "step": 750
572
- },
573
- {
574
- "epoch": 0.09727377447843338,
575
- "grad_norm": 1.0102107524871826,
576
- "learning_rate": 3.23874546618306e-06,
577
- "loss": 0.6635,
578
- "step": 760
579
- },
580
- {
581
- "epoch": 0.09855369256367592,
582
- "grad_norm": 1.1480194330215454,
583
- "learning_rate": 3.2814166844463415e-06,
584
- "loss": 0.6709,
585
- "step": 770
586
- },
587
- {
588
- "epoch": 0.09983361064891846,
589
- "grad_norm": 1.3119179010391235,
590
- "learning_rate": 3.324087902709623e-06,
591
- "loss": 0.6564,
592
- "step": 780
593
- },
594
- {
595
- "epoch": 0.10111352873416102,
596
- "grad_norm": 0.681377649307251,
597
- "learning_rate": 3.3667591209729038e-06,
598
- "loss": 0.6656,
599
- "step": 790
600
- },
601
- {
602
- "epoch": 0.10239344681940356,
603
- "grad_norm": 1.022257685661316,
604
- "learning_rate": 3.4094303392361854e-06,
605
- "loss": 0.6709,
606
- "step": 800
607
- },
608
- {
609
- "epoch": 0.10239344681940356,
610
- "eval_accuracy": 0.66247,
611
- "eval_loss": 0.6552017331123352,
612
- "eval_macro_f1": 0.6514270557181998,
613
- "eval_precision": 0.6718270655389242,
614
- "eval_recall": 0.6556580720913894,
615
- "eval_runtime": 1633.5478,
616
- "eval_samples_per_second": 61.216,
617
- "eval_steps_per_second": 0.479,
618
- "step": 800
619
- },
620
- {
621
- "epoch": 0.1036733649046461,
622
- "grad_norm": 1.0268975496292114,
623
- "learning_rate": 3.452101557499467e-06,
624
- "loss": 0.6602,
625
- "step": 810
626
- },
627
- {
628
- "epoch": 0.10495328298988865,
629
- "grad_norm": 2.6206603050231934,
630
- "learning_rate": 3.494772775762748e-06,
631
- "loss": 0.6705,
632
- "step": 820
633
- },
634
- {
635
- "epoch": 0.10623320107513119,
636
- "grad_norm": 1.035157561302185,
637
- "learning_rate": 3.5374439940260297e-06,
638
- "loss": 0.6643,
639
- "step": 830
640
- },
641
- {
642
- "epoch": 0.10751311916037373,
643
- "grad_norm": 1.736412763595581,
644
- "learning_rate": 3.5801152122893113e-06,
645
- "loss": 0.6612,
646
- "step": 840
647
- },
648
- {
649
- "epoch": 0.10879303724561629,
650
- "grad_norm": 0.6906964778900146,
651
- "learning_rate": 3.622786430552593e-06,
652
- "loss": 0.6576,
653
- "step": 850
654
- },
655
- {
656
- "epoch": 0.11007295533085883,
657
- "grad_norm": 0.8148729801177979,
658
- "learning_rate": 3.665457648815874e-06,
659
- "loss": 0.6561,
660
- "step": 860
661
- },
662
- {
663
- "epoch": 0.11135287341610137,
664
- "grad_norm": 1.0217723846435547,
665
- "learning_rate": 3.7081288670791556e-06,
666
- "loss": 0.6581,
667
- "step": 870
668
- },
669
- {
670
- "epoch": 0.11263279150134392,
671
- "grad_norm": 1.2743115425109863,
672
- "learning_rate": 3.750800085342437e-06,
673
- "loss": 0.6606,
674
- "step": 880
675
- },
676
- {
677
- "epoch": 0.11391270958658646,
678
- "grad_norm": 0.6405361294746399,
679
- "learning_rate": 3.793471303605718e-06,
680
- "loss": 0.652,
681
- "step": 890
682
- },
683
- {
684
- "epoch": 0.115192627671829,
685
- "grad_norm": 0.8357161283493042,
686
- "learning_rate": 3.836142521869e-06,
687
- "loss": 0.6558,
688
- "step": 900
689
- },
690
- {
691
- "epoch": 0.11647254575707154,
692
- "grad_norm": 1.3505173921585083,
693
- "learning_rate": 3.8788137401322815e-06,
694
- "loss": 0.6576,
695
- "step": 910
696
- },
697
- {
698
- "epoch": 0.1177524638423141,
699
- "grad_norm": 1.2253319025039673,
700
- "learning_rate": 3.921484958395563e-06,
701
- "loss": 0.6548,
702
- "step": 920
703
- },
704
- {
705
- "epoch": 0.11903238192755664,
706
- "grad_norm": 0.6269568800926208,
707
- "learning_rate": 3.964156176658844e-06,
708
- "loss": 0.6562,
709
- "step": 930
710
- },
711
- {
712
- "epoch": 0.12031230001279918,
713
- "grad_norm": 0.9413424134254456,
714
- "learning_rate": 4.006827394922125e-06,
715
- "loss": 0.6461,
716
- "step": 940
717
- },
718
- {
719
- "epoch": 0.12159221809804173,
720
- "grad_norm": 1.0903513431549072,
721
- "learning_rate": 4.049498613185407e-06,
722
- "loss": 0.6457,
723
- "step": 950
724
- },
725
- {
726
- "epoch": 0.12287213618328427,
727
- "grad_norm": 2.0023152828216553,
728
- "learning_rate": 4.092169831448688e-06,
729
- "loss": 0.6458,
730
- "step": 960
731
- },
732
- {
733
- "epoch": 0.12415205426852681,
734
- "grad_norm": 0.9638109803199768,
735
- "learning_rate": 4.134841049711969e-06,
736
- "loss": 0.6486,
737
- "step": 970
738
- },
739
- {
740
- "epoch": 0.12543197235376935,
741
- "grad_norm": 0.9894546270370483,
742
- "learning_rate": 4.177512267975251e-06,
743
- "loss": 0.6453,
744
- "step": 980
745
- },
746
- {
747
- "epoch": 0.1267118904390119,
748
- "grad_norm": 1.2289057970046997,
749
- "learning_rate": 4.220183486238532e-06,
750
- "loss": 0.6605,
751
- "step": 990
752
- },
753
- {
754
- "epoch": 0.12799180852425446,
755
- "grad_norm": 1.119125247001648,
756
- "learning_rate": 4.262854704501814e-06,
757
- "loss": 0.6564,
758
- "step": 1000
759
- },
760
- {
761
- "epoch": 0.12799180852425446,
762
- "eval_accuracy": 0.69068,
763
- "eval_loss": 0.6396247148513794,
764
- "eval_macro_f1": 0.689588440856387,
765
- "eval_precision": 0.6900076024604327,
766
- "eval_recall": 0.6894114140312133,
767
- "eval_runtime": 1634.4321,
768
- "eval_samples_per_second": 61.183,
769
- "eval_steps_per_second": 0.478,
770
- "step": 1000
771
- },
772
- {
773
- "epoch": 0.12927172660949698,
774
- "grad_norm": 2.4629580974578857,
775
- "learning_rate": 4.3055259227650956e-06,
776
- "loss": 0.6485,
777
- "step": 1010
778
- },
779
- {
780
- "epoch": 0.13055164469473954,
781
- "grad_norm": 0.7082359790802002,
782
- "learning_rate": 4.348197141028377e-06,
783
- "loss": 0.6491,
784
- "step": 1020
785
- },
786
- {
787
- "epoch": 0.1318315627799821,
788
- "grad_norm": 1.4061448574066162,
789
- "learning_rate": 4.390868359291658e-06,
790
- "loss": 0.6439,
791
- "step": 1030
792
- },
793
- {
794
- "epoch": 0.13311148086522462,
795
- "grad_norm": 0.8420212864875793,
796
- "learning_rate": 4.4335395775549394e-06,
797
- "loss": 0.6422,
798
- "step": 1040
799
- },
800
- {
801
- "epoch": 0.13439139895046717,
802
- "grad_norm": 1.0872454643249512,
803
- "learning_rate": 4.476210795818221e-06,
804
- "loss": 0.6364,
805
- "step": 1050
806
- },
807
- {
808
- "epoch": 0.13567131703570973,
809
- "grad_norm": 1.1760668754577637,
810
- "learning_rate": 4.518882014081503e-06,
811
- "loss": 0.6487,
812
- "step": 1060
813
- },
814
- {
815
- "epoch": 0.13695123512095225,
816
- "grad_norm": 1.1484756469726562,
817
- "learning_rate": 4.561553232344783e-06,
818
- "loss": 0.6451,
819
- "step": 1070
820
- },
821
- {
822
- "epoch": 0.1382311532061948,
823
- "grad_norm": 0.7577368021011353,
824
- "learning_rate": 4.604224450608065e-06,
825
- "loss": 0.6419,
826
- "step": 1080
827
- },
828
- {
829
- "epoch": 0.13951107129143736,
830
- "grad_norm": 0.6963039636611938,
831
- "learning_rate": 4.6468956688713465e-06,
832
- "loss": 0.634,
833
- "step": 1090
834
- },
835
- {
836
- "epoch": 0.1407909893766799,
837
- "grad_norm": 0.7238577008247375,
838
- "learning_rate": 4.689566887134628e-06,
839
- "loss": 0.6466,
840
- "step": 1100
841
- },
842
- {
843
- "epoch": 0.14207090746192244,
844
- "grad_norm": 0.6751101016998291,
845
- "learning_rate": 4.73223810539791e-06,
846
- "loss": 0.6377,
847
- "step": 1110
848
- },
849
- {
850
- "epoch": 0.143350825547165,
851
- "grad_norm": 0.7622250318527222,
852
- "learning_rate": 4.774909323661191e-06,
853
- "loss": 0.6318,
854
- "step": 1120
855
- },
856
- {
857
- "epoch": 0.14463074363240752,
858
- "grad_norm": 1.3731235265731812,
859
- "learning_rate": 4.817580541924473e-06,
860
- "loss": 0.6464,
861
- "step": 1130
862
- },
863
- {
864
- "epoch": 0.14591066171765008,
865
- "grad_norm": 0.8598525524139404,
866
- "learning_rate": 4.8602517601877535e-06,
867
- "loss": 0.6268,
868
- "step": 1140
869
- },
870
- {
871
- "epoch": 0.1471905798028926,
872
- "grad_norm": 1.1462016105651855,
873
- "learning_rate": 4.902922978451035e-06,
874
- "loss": 0.6357,
875
- "step": 1150
876
- },
877
- {
878
- "epoch": 0.14847049788813516,
879
- "grad_norm": 1.2314528226852417,
880
- "learning_rate": 4.945594196714317e-06,
881
- "loss": 0.6407,
882
- "step": 1160
883
- },
884
- {
885
- "epoch": 0.1497504159733777,
886
- "grad_norm": 1.0393744707107544,
887
- "learning_rate": 4.9882654149775974e-06,
888
- "loss": 0.6425,
889
- "step": 1170
890
- },
891
- {
892
- "epoch": 0.15103033405862024,
893
- "grad_norm": 0.9097604751586914,
894
- "learning_rate": 5.030936633240879e-06,
895
- "loss": 0.6275,
896
- "step": 1180
897
- },
898
- {
899
- "epoch": 0.1523102521438628,
900
- "grad_norm": 0.8274818062782288,
901
- "learning_rate": 5.073607851504161e-06,
902
- "loss": 0.6369,
903
- "step": 1190
904
- },
905
- {
906
- "epoch": 0.15359017022910534,
907
- "grad_norm": 0.8929425477981567,
908
- "learning_rate": 5.116279069767442e-06,
909
- "loss": 0.6382,
910
- "step": 1200
911
- },
912
- {
913
- "epoch": 0.15359017022910534,
914
- "eval_accuracy": 0.70003,
915
- "eval_loss": 0.6226751804351807,
916
- "eval_macro_f1": 0.6993136399748257,
917
- "eval_precision": 0.6993716582660007,
918
- "eval_recall": 0.6992659459810584,
919
- "eval_runtime": 1635.7462,
920
- "eval_samples_per_second": 61.134,
921
- "eval_steps_per_second": 0.478,
922
- "step": 1200
923
- }
924
- ],
925
- "logging_steps": 10,
926
- "max_steps": 23439,
927
- "num_input_tokens_seen": 0,
928
- "num_train_epochs": 3,
929
- "save_steps": 200,
930
- "stateful_callbacks": {
931
- "EarlyStoppingCallback": {
932
- "args": {
933
- "early_stopping_patience": 3,
934
- "early_stopping_threshold": 0.0
935
- },
936
- "attributes": {
937
- "early_stopping_patience_counter": 0
938
- }
939
- },
940
- "TrainerControl": {
941
- "args": {
942
- "should_epoch_stop": false,
943
- "should_evaluate": false,
944
- "should_log": false,
945
- "should_save": true,
946
- "should_training_stop": false
947
- },
948
- "attributes": {}
949
- }
950
- },
951
- "total_flos": 2.0206929051648e+16,
952
- "train_batch_size": 64,
953
- "trial_name": null,
954
- "trial_params": null
955
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1200/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e72353f4c9aec8aa78e85916ea1e167db5c282ccfd48294f1986907e6699455a
3
- size 5777
 
 
 
 
checkpoint-1200/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1300/config.json DELETED
@@ -1,29 +0,0 @@
1
- {
2
- "architectures": [
3
- "RobertaForSequenceClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "bos_token_id": 0,
7
- "classifier_dropout": null,
8
- "dtype": "float32",
9
- "eos_token_id": 2,
10
- "gradient_checkpointing": false,
11
- "hidden_act": "gelu",
12
- "hidden_dropout_prob": 0.1,
13
- "hidden_size": 768,
14
- "initializer_range": 0.02,
15
- "intermediate_size": 3072,
16
- "layer_norm_eps": 1e-05,
17
- "max_position_embeddings": 1026,
18
- "model_type": "roberta",
19
- "num_attention_heads": 12,
20
- "num_hidden_layers": 12,
21
- "output_past": true,
22
- "pad_token_id": 1,
23
- "position_embedding_type": "absolute",
24
- "problem_type": "single_label_classification",
25
- "transformers_version": "4.56.0",
26
- "type_vocab_size": 10,
27
- "use_cache": true,
28
- "vocab_size": 51416
29
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1300/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1300/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:34af50d15f11853b606c25055c82066a2f26a4ec604312f9ebf4b8e1dde10e09
3
- size 506505672
 
 
 
 
checkpoint-1300/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e861dbcff7c0be667b3b075ca5969aa371617888a7ee45021c678aeffa0453b
3
- size 1007622411
 
 
 
 
checkpoint-1300/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f4c0ada11a6005c8c98863a05528b7bc19b7f031adc7b5c1844698d8bfd2df1
3
- size 14645
 
 
 
 
checkpoint-1300/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:78d8f515b01464b74ed3455bfe222e15521ef386634f1dead59372b508e3d21e
3
- size 1383
 
 
 
 
checkpoint-1300/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f1af4b198e51a2cb98c51243d45d78824bdec80ce0ac23105fa21116a34da7f
3
- size 1977
 
 
 
 
checkpoint-1300/special_tokens_map.json DELETED
@@ -1,51 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
- "normalized": true,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1300/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1300/tokenizer_config.json DELETED
@@ -1,58 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<pad>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
- },
45
- "bos_token": "<s>",
46
- "clean_up_tokenization_spaces": false,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "extra_special_tokens": {},
51
- "mask_token": "<mask>",
52
- "model_max_length": 1000000000000000019884624838656,
53
- "pad_token": "<pad>",
54
- "sep_token": "</s>",
55
- "tokenizer_class": "RobertaTokenizer",
56
- "trim_offsets": true,
57
- "unk_token": "<unk>"
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1300/trainer_state.json DELETED
@@ -1,1122 +0,0 @@
1
- {
2
- "best_global_step": 1300,
3
- "best_metric": 0.9663303002945869,
4
- "best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-1300",
5
- "epoch": 0.15906032056772298,
6
- "eval_steps": 100,
7
- "global_step": 1300,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.001223540927444023,
14
- "grad_norm": 0.1898110806941986,
15
- "learning_rate": 3.6734693877551025e-07,
16
- "loss": 0.4422,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 0.002447081854888046,
21
- "grad_norm": 0.3350900411605835,
22
- "learning_rate": 7.346938775510205e-07,
23
- "loss": 0.4323,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 0.003670622782332069,
28
- "grad_norm": 0.3723449110984802,
29
- "learning_rate": 1.142857142857143e-06,
30
- "loss": 0.4362,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 0.004894163709776092,
35
- "grad_norm": 0.3299769461154938,
36
- "learning_rate": 1.5510204081632654e-06,
37
- "loss": 0.4191,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 0.006117704637220115,
42
- "grad_norm": 0.26681044697761536,
43
- "learning_rate": 1.9591836734693877e-06,
44
- "loss": 0.4289,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 0.007341245564664138,
49
- "grad_norm": 0.30233338475227356,
50
- "learning_rate": 2.3673469387755103e-06,
51
- "loss": 0.4083,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.008564786492108161,
56
- "grad_norm": 0.31031334400177,
57
- "learning_rate": 2.775510204081633e-06,
58
- "loss": 0.404,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.009788327419552184,
63
- "grad_norm": 0.2552475035190582,
64
- "learning_rate": 3.183673469387755e-06,
65
- "loss": 0.3889,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.011011868346996207,
70
- "grad_norm": 0.3131052553653717,
71
- "learning_rate": 3.5918367346938777e-06,
72
- "loss": 0.3813,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.01223540927444023,
77
- "grad_norm": 0.3377229571342468,
78
- "learning_rate": 4.000000000000001e-06,
79
- "loss": 0.3727,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 0.01223540927444023,
84
- "eval_accuracy": 0.6961,
85
- "eval_f1_weighted": 0.6955947095331424,
86
- "eval_loss": 0.15026023983955383,
87
- "eval_macro_f1": 0.6959280508399847,
88
- "eval_precision": 0.7019396279846728,
89
- "eval_recall": 0.6961,
90
- "eval_runtime": 789.7648,
91
- "eval_samples_per_second": 126.62,
92
- "eval_steps_per_second": 0.99,
93
- "step": 100
94
- },
95
- {
96
- "epoch": 0.013458950201884253,
97
- "grad_norm": 0.3366774618625641,
98
- "learning_rate": 4.408163265306123e-06,
99
- "loss": 0.3671,
100
- "step": 110
101
- },
102
- {
103
- "epoch": 0.014682491129328276,
104
- "grad_norm": 0.33491575717926025,
105
- "learning_rate": 4.816326530612245e-06,
106
- "loss": 0.3498,
107
- "step": 120
108
- },
109
- {
110
- "epoch": 0.0159060320567723,
111
- "grad_norm": 0.4119006097316742,
112
- "learning_rate": 5.2244897959183684e-06,
113
- "loss": 0.3409,
114
- "step": 130
115
- },
116
- {
117
- "epoch": 0.017129572984216322,
118
- "grad_norm": 0.2964725196361542,
119
- "learning_rate": 5.63265306122449e-06,
120
- "loss": 0.3433,
121
- "step": 140
122
- },
123
- {
124
- "epoch": 0.018353113911660345,
125
- "grad_norm": 0.3075334429740906,
126
- "learning_rate": 6.040816326530613e-06,
127
- "loss": 0.3298,
128
- "step": 150
129
- },
130
- {
131
- "epoch": 0.019576654839104368,
132
- "grad_norm": 0.33718687295913696,
133
- "learning_rate": 6.4489795918367345e-06,
134
- "loss": 0.3297,
135
- "step": 160
136
- },
137
- {
138
- "epoch": 0.02080019576654839,
139
- "grad_norm": 0.2809618413448334,
140
- "learning_rate": 6.857142857142858e-06,
141
- "loss": 0.3275,
142
- "step": 170
143
- },
144
- {
145
- "epoch": 0.022023736693992414,
146
- "grad_norm": 0.37805014848709106,
147
- "learning_rate": 7.2653061224489805e-06,
148
- "loss": 0.3201,
149
- "step": 180
150
- },
151
- {
152
- "epoch": 0.023247277621436437,
153
- "grad_norm": 0.2940429151058197,
154
- "learning_rate": 7.673469387755102e-06,
155
- "loss": 0.3042,
156
- "step": 190
157
- },
158
- {
159
- "epoch": 0.02447081854888046,
160
- "grad_norm": 0.3286060690879822,
161
- "learning_rate": 8.081632653061225e-06,
162
- "loss": 0.3071,
163
- "step": 200
164
- },
165
- {
166
- "epoch": 0.02447081854888046,
167
- "eval_accuracy": 0.77807,
168
- "eval_f1_weighted": 0.7781129395311969,
169
- "eval_loss": 0.12153773754835129,
170
- "eval_macro_f1": 0.7780651598452646,
171
- "eval_precision": 0.7808306361972198,
172
- "eval_recall": 0.77807,
173
- "eval_runtime": 792.7157,
174
- "eval_samples_per_second": 126.149,
175
- "eval_steps_per_second": 0.986,
176
- "step": 200
177
- },
178
- {
179
- "epoch": 0.025694359476324483,
180
- "grad_norm": 0.33857154846191406,
181
- "learning_rate": 8.489795918367347e-06,
182
- "loss": 0.2964,
183
- "step": 210
184
- },
185
- {
186
- "epoch": 0.026917900403768506,
187
- "grad_norm": 0.2752092182636261,
188
- "learning_rate": 8.89795918367347e-06,
189
- "loss": 0.3,
190
- "step": 220
191
- },
192
- {
193
- "epoch": 0.02814144133121253,
194
- "grad_norm": 0.4952544569969177,
195
- "learning_rate": 9.306122448979593e-06,
196
- "loss": 0.294,
197
- "step": 230
198
- },
199
- {
200
- "epoch": 0.029364982258656552,
201
- "grad_norm": 0.37926042079925537,
202
- "learning_rate": 9.714285714285715e-06,
203
- "loss": 0.2964,
204
- "step": 240
205
- },
206
- {
207
- "epoch": 0.030588523186100575,
208
- "grad_norm": 0.3222455680370331,
209
- "learning_rate": 1.0122448979591836e-05,
210
- "loss": 0.283,
211
- "step": 250
212
- },
213
- {
214
- "epoch": 0.0318120641135446,
215
- "grad_norm": 0.2930658459663391,
216
- "learning_rate": 1.053061224489796e-05,
217
- "loss": 0.2793,
218
- "step": 260
219
- },
220
- {
221
- "epoch": 0.03303560504098862,
222
- "grad_norm": 0.4313414692878723,
223
- "learning_rate": 1.0938775510204083e-05,
224
- "loss": 0.2728,
225
- "step": 270
226
- },
227
- {
228
- "epoch": 0.034259145968432644,
229
- "grad_norm": 0.37351569533348083,
230
- "learning_rate": 1.1346938775510206e-05,
231
- "loss": 0.2752,
232
- "step": 280
233
- },
234
- {
235
- "epoch": 0.035482686895876664,
236
- "grad_norm": 0.22772285342216492,
237
- "learning_rate": 1.1755102040816328e-05,
238
- "loss": 0.274,
239
- "step": 290
240
- },
241
- {
242
- "epoch": 0.03670622782332069,
243
- "grad_norm": 0.15888753533363342,
244
- "learning_rate": 1.2163265306122449e-05,
245
- "loss": 0.264,
246
- "step": 300
247
- },
248
- {
249
- "epoch": 0.03670622782332069,
250
- "eval_accuracy": 0.82326,
251
- "eval_f1_weighted": 0.8227034206790359,
252
- "eval_loss": 0.10234300792217255,
253
- "eval_macro_f1": 0.8230100448030374,
254
- "eval_precision": 0.8338333810964687,
255
- "eval_recall": 0.82326,
256
- "eval_runtime": 789.0168,
257
- "eval_samples_per_second": 126.74,
258
- "eval_steps_per_second": 0.991,
259
- "step": 300
260
- },
261
- {
262
- "epoch": 0.03792976875076471,
263
- "grad_norm": 0.23560188710689545,
264
- "learning_rate": 1.2571428571428572e-05,
265
- "loss": 0.2753,
266
- "step": 310
267
- },
268
- {
269
- "epoch": 0.039153309678208736,
270
- "grad_norm": 0.18699614703655243,
271
- "learning_rate": 1.2979591836734696e-05,
272
- "loss": 0.2565,
273
- "step": 320
274
- },
275
- {
276
- "epoch": 0.040376850605652756,
277
- "grad_norm": 0.24035991728305817,
278
- "learning_rate": 1.3387755102040818e-05,
279
- "loss": 0.2716,
280
- "step": 330
281
- },
282
- {
283
- "epoch": 0.04160039153309678,
284
- "grad_norm": 0.15309660136699677,
285
- "learning_rate": 1.3795918367346941e-05,
286
- "loss": 0.2515,
287
- "step": 340
288
- },
289
- {
290
- "epoch": 0.0428239324605408,
291
- "grad_norm": 0.3382055461406708,
292
- "learning_rate": 1.4204081632653062e-05,
293
- "loss": 0.2597,
294
- "step": 350
295
- },
296
- {
297
- "epoch": 0.04404747338798483,
298
- "grad_norm": 0.24439455568790436,
299
- "learning_rate": 1.4612244897959185e-05,
300
- "loss": 0.247,
301
- "step": 360
302
- },
303
- {
304
- "epoch": 0.04527101431542885,
305
- "grad_norm": 0.26233720779418945,
306
- "learning_rate": 1.5020408163265307e-05,
307
- "loss": 0.2431,
308
- "step": 370
309
- },
310
- {
311
- "epoch": 0.046494555242872875,
312
- "grad_norm": 0.20477451384067535,
313
- "learning_rate": 1.5387755102040818e-05,
314
- "loss": 0.2538,
315
- "step": 380
316
- },
317
- {
318
- "epoch": 0.047718096170316894,
319
- "grad_norm": 0.2765439748764038,
320
- "learning_rate": 1.5795918367346942e-05,
321
- "loss": 0.2404,
322
- "step": 390
323
- },
324
- {
325
- "epoch": 0.04894163709776092,
326
- "grad_norm": 0.13196279108524323,
327
- "learning_rate": 1.6204081632653063e-05,
328
- "loss": 0.2393,
329
- "step": 400
330
- },
331
- {
332
- "epoch": 0.04894163709776092,
333
- "eval_accuracy": 0.84563,
334
- "eval_f1_weighted": 0.8448128964509274,
335
- "eval_loss": 0.09028046578168869,
336
- "eval_macro_f1": 0.8451923512067675,
337
- "eval_precision": 0.861024732271907,
338
- "eval_recall": 0.84563,
339
- "eval_runtime": 787.6067,
340
- "eval_samples_per_second": 126.967,
341
- "eval_steps_per_second": 0.993,
342
- "step": 400
343
- },
344
- {
345
- "epoch": 0.05016517802520494,
346
- "grad_norm": 0.0924634337425232,
347
- "learning_rate": 1.6612244897959184e-05,
348
- "loss": 0.2331,
349
- "step": 410
350
- },
351
- {
352
- "epoch": 0.05138871895264897,
353
- "grad_norm": 0.277784138917923,
354
- "learning_rate": 1.7020408163265308e-05,
355
- "loss": 0.2301,
356
- "step": 420
357
- },
358
- {
359
- "epoch": 0.052612259880092986,
360
- "grad_norm": 0.32299959659576416,
361
- "learning_rate": 1.742857142857143e-05,
362
- "loss": 0.2218,
363
- "step": 430
364
- },
365
- {
366
- "epoch": 0.05383580080753701,
367
- "grad_norm": 0.18170586228370667,
368
- "learning_rate": 1.7836734693877553e-05,
369
- "loss": 0.2318,
370
- "step": 440
371
- },
372
- {
373
- "epoch": 0.05505934173498103,
374
- "grad_norm": 0.1520216166973114,
375
- "learning_rate": 1.8244897959183674e-05,
376
- "loss": 0.2136,
377
- "step": 450
378
- },
379
- {
380
- "epoch": 0.05628288266242506,
381
- "grad_norm": 0.23452645540237427,
382
- "learning_rate": 1.8653061224489795e-05,
383
- "loss": 0.2219,
384
- "step": 460
385
- },
386
- {
387
- "epoch": 0.05750642358986908,
388
- "grad_norm": 0.10036301612854004,
389
- "learning_rate": 1.906122448979592e-05,
390
- "loss": 0.2213,
391
- "step": 470
392
- },
393
- {
394
- "epoch": 0.058729964517313105,
395
- "grad_norm": 0.24100220203399658,
396
- "learning_rate": 1.9469387755102044e-05,
397
- "loss": 0.2079,
398
- "step": 480
399
- },
400
- {
401
- "epoch": 0.059953505444757124,
402
- "grad_norm": 0.28893032670021057,
403
- "learning_rate": 1.9877551020408165e-05,
404
- "loss": 0.1978,
405
- "step": 490
406
- },
407
- {
408
- "epoch": 0.06117704637220115,
409
- "grad_norm": 0.22918537259101868,
410
- "learning_rate": 1.9999836143766126e-05,
411
- "loss": 0.202,
412
- "step": 500
413
- },
414
- {
415
- "epoch": 0.06117704637220115,
416
- "eval_accuracy": 0.91628,
417
- "eval_f1_weighted": 0.9163231793856368,
418
- "eval_loss": 0.055908624082803726,
419
- "eval_macro_f1": 0.9162187423616152,
420
- "eval_precision": 0.9170320825159874,
421
- "eval_recall": 0.91628,
422
- "eval_runtime": 760.1138,
423
- "eval_samples_per_second": 131.559,
424
- "eval_steps_per_second": 1.029,
425
- "step": 500
426
- },
427
- {
428
- "epoch": 0.06240058729964517,
429
- "grad_norm": 0.2930404841899872,
430
- "learning_rate": 1.999903359554741e-05,
431
- "loss": 0.1979,
432
- "step": 510
433
- },
434
- {
435
- "epoch": 0.0636241282270892,
436
- "grad_norm": 0.0889664739370346,
437
- "learning_rate": 1.9997562312908153e-05,
438
- "loss": 0.1953,
439
- "step": 520
440
- },
441
- {
442
- "epoch": 0.06484766915453322,
443
- "grad_norm": 0.1687588095664978,
444
- "learning_rate": 1.9995422394247598e-05,
445
- "loss": 0.1935,
446
- "step": 530
447
- },
448
- {
449
- "epoch": 0.06607121008197724,
450
- "grad_norm": 0.2399725466966629,
451
- "learning_rate": 1.9992613982683296e-05,
452
- "loss": 0.1818,
453
- "step": 540
454
- },
455
- {
456
- "epoch": 0.06729475100942127,
457
- "grad_norm": 0.2016785889863968,
458
- "learning_rate": 1.9989137266041552e-05,
459
- "loss": 0.1893,
460
- "step": 550
461
- },
462
- {
463
- "epoch": 0.06851829193686529,
464
- "grad_norm": 0.17420713603496552,
465
- "learning_rate": 1.9984992476844845e-05,
466
- "loss": 0.1895,
467
- "step": 560
468
- },
469
- {
470
- "epoch": 0.06974183286430931,
471
- "grad_norm": 0.2180609554052353,
472
- "learning_rate": 1.998017989229629e-05,
473
- "loss": 0.1836,
474
- "step": 570
475
- },
476
- {
477
- "epoch": 0.07096537379175333,
478
- "grad_norm": 0.15563039481639862,
479
- "learning_rate": 1.9974699834261074e-05,
480
- "loss": 0.182,
481
- "step": 580
482
- },
483
- {
484
- "epoch": 0.07218891471919736,
485
- "grad_norm": 0.25410088896751404,
486
- "learning_rate": 1.996855266924497e-05,
487
- "loss": 0.1862,
488
- "step": 590
489
- },
490
- {
491
- "epoch": 0.07341245564664138,
492
- "grad_norm": 0.24206259846687317,
493
- "learning_rate": 1.996173880836979e-05,
494
- "loss": 0.1818,
495
- "step": 600
496
- },
497
- {
498
- "epoch": 0.07341245564664138,
499
- "eval_accuracy": 0.91633,
500
- "eval_f1_weighted": 0.9162437523349878,
501
- "eval_loss": 0.05625538155436516,
502
- "eval_macro_f1": 0.9163072974421806,
503
- "eval_precision": 0.9233764457540103,
504
- "eval_recall": 0.91633,
505
- "eval_runtime": 759.6815,
506
- "eval_samples_per_second": 131.634,
507
- "eval_steps_per_second": 1.029,
508
- "step": 600
509
- },
510
- {
511
- "epoch": 0.0746359965740854,
512
- "grad_norm": 0.27251410484313965,
513
- "learning_rate": 1.9954258707345903e-05,
514
- "loss": 0.1845,
515
- "step": 610
516
- },
517
- {
518
- "epoch": 0.07585953750152942,
519
- "grad_norm": 0.1545839011669159,
520
- "learning_rate": 1.9946112866441757e-05,
521
- "loss": 0.1861,
522
- "step": 620
523
- },
524
- {
525
- "epoch": 0.07708307842897345,
526
- "grad_norm": 0.2535873055458069,
527
- "learning_rate": 1.9937301830450423e-05,
528
- "loss": 0.1772,
529
- "step": 630
530
- },
531
- {
532
- "epoch": 0.07830661935641747,
533
- "grad_norm": 0.2617948651313782,
534
- "learning_rate": 1.992782618865315e-05,
535
- "loss": 0.1711,
536
- "step": 640
537
- },
538
- {
539
- "epoch": 0.07953016028386149,
540
- "grad_norm": 0.38676971197128296,
541
- "learning_rate": 1.9917686574779972e-05,
542
- "loss": 0.1748,
543
- "step": 650
544
- },
545
- {
546
- "epoch": 0.08075370121130551,
547
- "grad_norm": 0.1511957049369812,
548
- "learning_rate": 1.9906883666967296e-05,
549
- "loss": 0.1825,
550
- "step": 660
551
- },
552
- {
553
- "epoch": 0.08197724213874955,
554
- "grad_norm": 0.2525976002216339,
555
- "learning_rate": 1.989541818771258e-05,
556
- "loss": 0.1651,
557
- "step": 670
558
- },
559
- {
560
- "epoch": 0.08320078306619356,
561
- "grad_norm": 0.25827622413635254,
562
- "learning_rate": 1.9883290903825994e-05,
563
- "loss": 0.1763,
564
- "step": 680
565
- },
566
- {
567
- "epoch": 0.08442432399363758,
568
- "grad_norm": 0.24877820909023285,
569
- "learning_rate": 1.9870502626379127e-05,
570
- "loss": 0.1652,
571
- "step": 690
572
- },
573
- {
574
- "epoch": 0.0856478649210816,
575
- "grad_norm": 0.278772234916687,
576
- "learning_rate": 1.9857054210650776e-05,
577
- "loss": 0.1651,
578
- "step": 700
579
- },
580
- {
581
- "epoch": 0.0856478649210816,
582
- "eval_accuracy": 0.94905,
583
- "eval_f1_weighted": 0.9490731118481598,
584
- "eval_loss": 0.03884471580386162,
585
- "eval_macro_f1": 0.9489981325237288,
586
- "eval_precision": 0.9494795831024372,
587
- "eval_recall": 0.94905,
588
- "eval_runtime": 759.9337,
589
- "eval_samples_per_second": 131.59,
590
- "eval_steps_per_second": 1.029,
591
- "step": 700
592
- },
593
- {
594
- "epoch": 0.08687140584852564,
595
- "grad_norm": 0.1895805150270462,
596
- "learning_rate": 1.9842946556069705e-05,
597
- "loss": 0.1628,
598
- "step": 710
599
- },
600
- {
601
- "epoch": 0.08809494677596966,
602
- "grad_norm": 0.1171497106552124,
603
- "learning_rate": 1.982818060615452e-05,
604
- "loss": 0.1715,
605
- "step": 720
606
- },
607
- {
608
- "epoch": 0.08931848770341368,
609
- "grad_norm": 0.22032728791236877,
610
- "learning_rate": 1.9812757348450547e-05,
611
- "loss": 0.1712,
612
- "step": 730
613
- },
614
- {
615
- "epoch": 0.0905420286308577,
616
- "grad_norm": 0.20700488984584808,
617
- "learning_rate": 1.9796677814463812e-05,
618
- "loss": 0.1638,
619
- "step": 740
620
- },
621
- {
622
- "epoch": 0.09176556955830173,
623
- "grad_norm": 0.24688613414764404,
624
- "learning_rate": 1.977994307959202e-05,
625
- "loss": 0.1647,
626
- "step": 750
627
- },
628
- {
629
- "epoch": 0.09298911048574575,
630
- "grad_norm": 0.1886432021856308,
631
- "learning_rate": 1.9762554263052655e-05,
632
- "loss": 0.1734,
633
- "step": 760
634
- },
635
- {
636
- "epoch": 0.09421265141318977,
637
- "grad_norm": 0.08407370001077652,
638
- "learning_rate": 1.9744512527808127e-05,
639
- "loss": 0.1755,
640
- "step": 770
641
- },
642
- {
643
- "epoch": 0.09543619234063379,
644
- "grad_norm": 0.14160771667957306,
645
- "learning_rate": 1.9725819080487976e-05,
646
- "loss": 0.1749,
647
- "step": 780
648
- },
649
- {
650
- "epoch": 0.09665973326807782,
651
- "grad_norm": 0.17038081586360931,
652
- "learning_rate": 1.970647517130819e-05,
653
- "loss": 0.1795,
654
- "step": 790
655
- },
656
- {
657
- "epoch": 0.09788327419552184,
658
- "grad_norm": 0.24339532852172852,
659
- "learning_rate": 1.968648209398759e-05,
660
- "loss": 0.161,
661
- "step": 800
662
- },
663
- {
664
- "epoch": 0.09788327419552184,
665
- "eval_accuracy": 0.95721,
666
- "eval_f1_weighted": 0.9572295598206603,
667
- "eval_loss": 0.03337462991476059,
668
- "eval_macro_f1": 0.9571669846830866,
669
- "eval_precision": 0.9576467364395861,
670
- "eval_recall": 0.95721,
671
- "eval_runtime": 759.9975,
672
- "eval_samples_per_second": 131.579,
673
- "eval_steps_per_second": 1.029,
674
- "step": 800
675
- },
676
- {
677
- "epoch": 0.09910681512296586,
678
- "grad_norm": 0.16346058249473572,
679
- "learning_rate": 1.9665841185661283e-05,
680
- "loss": 0.1596,
681
- "step": 810
682
- },
683
- {
684
- "epoch": 0.10033035605040988,
685
- "grad_norm": 0.25031423568725586,
686
- "learning_rate": 1.964455382679128e-05,
687
- "loss": 0.1662,
688
- "step": 820
689
- },
690
- {
691
- "epoch": 0.10155389697785391,
692
- "grad_norm": 0.36678382754325867,
693
- "learning_rate": 1.9622621441074113e-05,
694
- "loss": 0.1552,
695
- "step": 830
696
- },
697
- {
698
- "epoch": 0.10277743790529793,
699
- "grad_norm": 0.34810611605644226,
700
- "learning_rate": 1.960004549534567e-05,
701
- "loss": 0.1663,
702
- "step": 840
703
- },
704
- {
705
- "epoch": 0.10400097883274195,
706
- "grad_norm": 0.15511688590049744,
707
- "learning_rate": 1.957682749948307e-05,
708
- "loss": 0.1571,
709
- "step": 850
710
- },
711
- {
712
- "epoch": 0.10522451976018597,
713
- "grad_norm": 0.2082190364599228,
714
- "learning_rate": 1.9552969006303666e-05,
715
- "loss": 0.1497,
716
- "step": 860
717
- },
718
- {
719
- "epoch": 0.10644806068763,
720
- "grad_norm": 0.14936988055706024,
721
- "learning_rate": 1.9528471611461235e-05,
722
- "loss": 0.1435,
723
- "step": 870
724
- },
725
- {
726
- "epoch": 0.10767160161507403,
727
- "grad_norm": 0.252530574798584,
728
- "learning_rate": 1.9503336953339223e-05,
729
- "loss": 0.1536,
730
- "step": 880
731
- },
732
- {
733
- "epoch": 0.10889514254251804,
734
- "grad_norm": 0.07253506034612656,
735
- "learning_rate": 1.947756671294118e-05,
736
- "loss": 0.1605,
737
- "step": 890
738
- },
739
- {
740
- "epoch": 0.11011868346996206,
741
- "grad_norm": 0.09060605615377426,
742
- "learning_rate": 1.9451162613778353e-05,
743
- "loss": 0.1581,
744
- "step": 900
745
- },
746
- {
747
- "epoch": 0.11011868346996206,
748
- "eval_accuracy": 0.95459,
749
- "eval_f1_weighted": 0.9546135918699761,
750
- "eval_loss": 0.03526490181684494,
751
- "eval_macro_f1": 0.9545725664001194,
752
- "eval_precision": 0.9559789658562307,
753
- "eval_recall": 0.95459,
754
- "eval_runtime": 759.7202,
755
- "eval_samples_per_second": 131.627,
756
- "eval_steps_per_second": 1.029,
757
- "step": 900
758
- },
759
- {
760
- "epoch": 0.1113422243974061,
761
- "grad_norm": 0.21080073714256287,
762
- "learning_rate": 1.942412642175439e-05,
763
- "loss": 0.164,
764
- "step": 910
765
- },
766
- {
767
- "epoch": 0.11256576532485012,
768
- "grad_norm": 0.22832269966602325,
769
- "learning_rate": 1.939645994504726e-05,
770
- "loss": 0.1595,
771
- "step": 920
772
- },
773
- {
774
- "epoch": 0.11378930625229414,
775
- "grad_norm": 0.19044892489910126,
776
- "learning_rate": 1.93681650339883e-05,
777
- "loss": 0.1648,
778
- "step": 930
779
- },
780
- {
781
- "epoch": 0.11501284717973816,
782
- "grad_norm": 0.2413518726825714,
783
- "learning_rate": 1.9339243580938493e-05,
784
- "loss": 0.155,
785
- "step": 940
786
- },
787
- {
788
- "epoch": 0.11623638810718219,
789
- "grad_norm": 0.13218896090984344,
790
- "learning_rate": 1.930969752016187e-05,
791
- "loss": 0.1499,
792
- "step": 950
793
- },
794
- {
795
- "epoch": 0.11745992903462621,
796
- "grad_norm": 0.23770441114902496,
797
- "learning_rate": 1.927952882769619e-05,
798
- "loss": 0.1555,
799
- "step": 960
800
- },
801
- {
802
- "epoch": 0.11868346996207023,
803
- "grad_norm": 0.2193710207939148,
804
- "learning_rate": 1.924873952122074e-05,
805
- "loss": 0.1505,
806
- "step": 970
807
- },
808
- {
809
- "epoch": 0.11990701088951425,
810
- "grad_norm": 0.1577174812555313,
811
- "learning_rate": 1.9217331659921432e-05,
812
- "loss": 0.1551,
813
- "step": 980
814
- },
815
- {
816
- "epoch": 0.12113055181695828,
817
- "grad_norm": 0.1814967393875122,
818
- "learning_rate": 1.9185307344353052e-05,
819
- "loss": 0.1607,
820
- "step": 990
821
- },
822
- {
823
- "epoch": 0.1223540927444023,
824
- "grad_norm": 0.27239707112312317,
825
- "learning_rate": 1.91526687162988e-05,
826
- "loss": 0.1506,
827
- "step": 1000
828
- },
829
- {
830
- "epoch": 0.1223540927444023,
831
- "eval_accuracy": 0.96454,
832
- "eval_f1_weighted": 0.9645510150201642,
833
- "eval_loss": 0.028770776465535164,
834
- "eval_macro_f1": 0.9644889377060355,
835
- "eval_precision": 0.9646912114769961,
836
- "eval_recall": 0.96454,
837
- "eval_runtime": 759.5962,
838
- "eval_samples_per_second": 131.649,
839
- "eval_steps_per_second": 1.029,
840
- "step": 1000
841
- },
842
- {
843
- "epoch": 0.12357763367184632,
844
- "grad_norm": 0.20511822402477264,
845
- "learning_rate": 1.9119417958627022e-05,
846
- "loss": 0.1503,
847
- "step": 1010
848
- },
849
- {
850
- "epoch": 0.12480117459929034,
851
- "grad_norm": 0.2324151247739792,
852
- "learning_rate": 1.9085557295145254e-05,
853
- "loss": 0.1581,
854
- "step": 1020
855
- },
856
- {
857
- "epoch": 0.12602471552673436,
858
- "grad_norm": 0.11019974201917648,
859
- "learning_rate": 1.905108899045146e-05,
860
- "loss": 0.1556,
861
- "step": 1030
862
- },
863
- {
864
- "epoch": 0.1272482564541784,
865
- "grad_norm": 0.13370558619499207,
866
- "learning_rate": 1.9016015349782594e-05,
867
- "loss": 0.1469,
868
- "step": 1040
869
- },
870
- {
871
- "epoch": 0.12847179738162243,
872
- "grad_norm": 0.11238931119441986,
873
- "learning_rate": 1.8980338718860426e-05,
874
- "loss": 0.155,
875
- "step": 1050
876
- },
877
- {
878
- "epoch": 0.12969533830906643,
879
- "grad_norm": 0.2959650158882141,
880
- "learning_rate": 1.894406148373466e-05,
881
- "loss": 0.1478,
882
- "step": 1060
883
- },
884
- {
885
- "epoch": 0.13091887923651047,
886
- "grad_norm": 0.14401015639305115,
887
- "learning_rate": 1.890718607062334e-05,
888
- "loss": 0.1558,
889
- "step": 1070
890
- },
891
- {
892
- "epoch": 0.13214242016395447,
893
- "grad_norm": 0.2187667042016983,
894
- "learning_rate": 1.8869714945750614e-05,
895
- "loss": 0.1618,
896
- "step": 1080
897
- },
898
- {
899
- "epoch": 0.1333659610913985,
900
- "grad_norm": 0.17045481503009796,
901
- "learning_rate": 1.883165061518176e-05,
902
- "loss": 0.1487,
903
- "step": 1090
904
- },
905
- {
906
- "epoch": 0.13458950201884254,
907
- "grad_norm": 0.09508351981639862,
908
- "learning_rate": 1.8792995624655605e-05,
909
- "loss": 0.1461,
910
- "step": 1100
911
- },
912
- {
913
- "epoch": 0.13458950201884254,
914
- "eval_accuracy": 0.95198,
915
- "eval_f1_weighted": 0.9520023284947491,
916
- "eval_loss": 0.04088817164301872,
917
- "eval_macro_f1": 0.9519693367124435,
918
- "eval_precision": 0.9538785423213092,
919
- "eval_recall": 0.95198,
920
- "eval_runtime": 759.8551,
921
- "eval_samples_per_second": 131.604,
922
- "eval_steps_per_second": 1.029,
923
- "step": 1100
924
- },
925
- {
926
- "epoch": 0.13581304294628654,
927
- "grad_norm": 0.1880544275045395,
928
- "learning_rate": 1.875375255941426e-05,
929
- "loss": 0.1442,
930
- "step": 1110
931
- },
932
- {
933
- "epoch": 0.13703658387373058,
934
- "grad_norm": 0.1614997684955597,
935
- "learning_rate": 1.8713924044030212e-05,
936
- "loss": 0.1622,
937
- "step": 1120
938
- },
939
- {
940
- "epoch": 0.1382601248011746,
941
- "grad_norm": 0.10545000433921814,
942
- "learning_rate": 1.86735127422308e-05,
943
- "loss": 0.1531,
944
- "step": 1130
945
- },
946
- {
947
- "epoch": 0.13948366572861862,
948
- "grad_norm": 0.2203921526670456,
949
- "learning_rate": 1.8632521356720064e-05,
950
- "loss": 0.1471,
951
- "step": 1140
952
- },
953
- {
954
- "epoch": 0.14070720665606265,
955
- "grad_norm": 0.16150350868701935,
956
- "learning_rate": 1.8590952628997994e-05,
957
- "loss": 0.1436,
958
- "step": 1150
959
- },
960
- {
961
- "epoch": 0.14193074758350666,
962
- "grad_norm": 0.1466459184885025,
963
- "learning_rate": 1.8548809339177155e-05,
964
- "loss": 0.1486,
965
- "step": 1160
966
- },
967
- {
968
- "epoch": 0.1431542885109507,
969
- "grad_norm": 0.1858566850423813,
970
- "learning_rate": 1.8506094305796786e-05,
971
- "loss": 0.1485,
972
- "step": 1170
973
- },
974
- {
975
- "epoch": 0.14437782943839472,
976
- "grad_norm": 0.21629975736141205,
977
- "learning_rate": 1.846281038563428e-05,
978
- "loss": 0.1558,
979
- "step": 1180
980
- },
981
- {
982
- "epoch": 0.14560137036583873,
983
- "grad_norm": 0.12939126789569855,
984
- "learning_rate": 1.841896047351412e-05,
985
- "loss": 0.1388,
986
- "step": 1190
987
- },
988
- {
989
- "epoch": 0.14682491129328276,
990
- "grad_norm": 0.12447889149188995,
991
- "learning_rate": 1.8374547502114277e-05,
992
- "loss": 0.1683,
993
- "step": 1200
994
- },
995
- {
996
- "epoch": 0.14682491129328276,
997
- "eval_accuracy": 0.96627,
998
- "eval_f1_weighted": 0.9662808443914441,
999
- "eval_loss": 0.027206970378756523,
1000
- "eval_macro_f1": 0.9662223734621376,
1001
- "eval_precision": 0.966433068847901,
1002
- "eval_recall": 0.96627,
1003
- "eval_runtime": 661.8465,
1004
- "eval_samples_per_second": 151.092,
1005
- "eval_steps_per_second": 1.182,
1006
- "step": 1200
1007
- },
1008
- {
1009
- "epoch": 0.1480484522207268,
1010
- "grad_norm": 0.07575482875108719,
1011
- "learning_rate": 1.832957444177007e-05,
1012
- "loss": 0.152,
1013
- "step": 1210
1014
- },
1015
- {
1016
- "epoch": 0.1492719931481708,
1017
- "grad_norm": 0.22879591584205627,
1018
- "learning_rate": 1.828404430027553e-05,
1019
- "loss": 0.15,
1020
- "step": 1220
1021
- },
1022
- {
1023
- "epoch": 0.15049553407561483,
1024
- "grad_norm": 0.25837475061416626,
1025
- "learning_rate": 1.8237960122682207e-05,
1026
- "loss": 0.1557,
1027
- "step": 1230
1028
- },
1029
- {
1030
- "epoch": 0.15171907500305884,
1031
- "grad_norm": 0.1440538763999939,
1032
- "learning_rate": 1.8191324991095527e-05,
1033
- "loss": 0.154,
1034
- "step": 1240
1035
- },
1036
- {
1037
- "epoch": 0.15294261593050287,
1038
- "grad_norm": 0.21304763853549957,
1039
- "learning_rate": 1.814414202446869e-05,
1040
- "loss": 0.1428,
1041
- "step": 1250
1042
- },
1043
- {
1044
- "epoch": 0.1541661568579469,
1045
- "grad_norm": 0.2292693555355072,
1046
- "learning_rate": 1.809641437839403e-05,
1047
- "loss": 0.1441,
1048
- "step": 1260
1049
- },
1050
- {
1051
- "epoch": 0.1553896977853909,
1052
- "grad_norm": 0.0891769602894783,
1053
- "learning_rate": 1.8048145244892e-05,
1054
- "loss": 0.1563,
1055
- "step": 1270
1056
- },
1057
- {
1058
- "epoch": 0.15661323871283495,
1059
- "grad_norm": 0.13292840123176575,
1060
- "learning_rate": 1.799933785219769e-05,
1061
- "loss": 0.1418,
1062
- "step": 1280
1063
- },
1064
- {
1065
- "epoch": 0.15783677964027898,
1066
- "grad_norm": 0.30031099915504456,
1067
- "learning_rate": 1.7949995464544892e-05,
1068
- "loss": 0.1543,
1069
- "step": 1290
1070
- },
1071
- {
1072
- "epoch": 0.15906032056772298,
1073
- "grad_norm": 0.08812980353832245,
1074
- "learning_rate": 1.790012138194783e-05,
1075
- "loss": 0.1473,
1076
- "step": 1300
1077
- },
1078
- {
1079
- "epoch": 0.15906032056772298,
1080
- "eval_accuracy": 0.96636,
1081
- "eval_f1_weighted": 0.9663763998373325,
1082
- "eval_loss": 0.02714269980788231,
1083
- "eval_macro_f1": 0.9663303002945869,
1084
- "eval_precision": 0.9669126928794434,
1085
- "eval_recall": 0.96636,
1086
- "eval_runtime": 661.9303,
1087
- "eval_samples_per_second": 151.073,
1088
- "eval_steps_per_second": 1.181,
1089
- "step": 1300
1090
- }
1091
- ],
1092
- "logging_steps": 10,
1093
- "max_steps": 8173,
1094
- "num_input_tokens_seen": 0,
1095
- "num_train_epochs": 1,
1096
- "save_steps": 100,
1097
- "stateful_callbacks": {
1098
- "EarlyStoppingCallback": {
1099
- "args": {
1100
- "early_stopping_patience": 3,
1101
- "early_stopping_threshold": 0.0
1102
- },
1103
- "attributes": {
1104
- "early_stopping_patience_counter": 0
1105
- }
1106
- },
1107
- "TrainerControl": {
1108
- "args": {
1109
- "should_epoch_stop": false,
1110
- "should_evaluate": false,
1111
- "should_log": false,
1112
- "should_save": true,
1113
- "should_training_stop": false
1114
- },
1115
- "attributes": {}
1116
- }
1117
- },
1118
- "total_flos": 2.20669477257216e+16,
1119
- "train_batch_size": 64,
1120
- "trial_name": null,
1121
- "trial_params": null
1122
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1300/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ac849e7988017583c1fbea58bf7deca363c8ee46bc62efa3a3a962d250bd5ca
3
- size 5841