Hugging Face's logo

MHGanainy
/
roberta-base-downstream-build_rr

Token Classification
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files
xet
 Community
MHGanainy commited on
Commit
853d433
·
verified ·
1 Parent(s): f910159

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +6 -6
  2. train_results.json +7 -6
  3. trainer_state.json +168 -84
all_results.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "epoch": 9.0,
3
  "eval_accuracy": 0.17645015630427233,
4
  "eval_classification_report": " precision recall f1-score support\n\n AC 0.0000 0.0000 0.0000 65\n ATIO 0.0000 0.0000 0.0000 26\n LC 0.0000 0.0000 0.0000 33\n NALYSIS 0.0000 0.0000 0.0000 92\n ONE 0.0000 0.0000 0.0000 60\n PC 0.0000 0.0000 0.0000 31\n REAMBLE 0.0000 0.0000 0.0000 30\nRE_NOT_RELIED 0.0000 0.0000 0.0000 5\n RE_RELIED 0.0000 0.0000 0.0000 29\nRG_PETITIONER 0.0000 0.0000 0.0000 19\nRG_RESPONDENT 0.0000 0.0000 0.0000 13\n SSUE 0.0000 0.0000 0.0000 23\n TA 0.0000 0.0000 0.0000 28\n\n micro avg 0.0000 0.0000 0.0000 454\n macro avg 0.0000 0.0000 0.0000 454\n weighted avg 0.0000 0.0000 0.0000 454\n",
5
  "eval_f1": 0.0,
@@ -24,10 +24,10 @@
24
  "predict_samples": 50,
25
  "predict_samples_per_second": 18.084,
26
  "predict_steps_per_second": 4.702,
27
- "total_flos": 4.337522536041677e+16,
28
- "train_loss": 0.8344365670262271,
29
- "train_runtime": 312.3156,
30
  "train_samples": 247,
31
- "train_samples_per_second": 15.817,
32
- "train_steps_per_second": 3.97
33
  }
 
1
  {
2
+ "epoch": 14.0,
3
  "eval_accuracy": 0.17645015630427233,
4
  "eval_classification_report": " precision recall f1-score support\n\n AC 0.0000 0.0000 0.0000 65\n ATIO 0.0000 0.0000 0.0000 26\n LC 0.0000 0.0000 0.0000 33\n NALYSIS 0.0000 0.0000 0.0000 92\n ONE 0.0000 0.0000 0.0000 60\n PC 0.0000 0.0000 0.0000 31\n REAMBLE 0.0000 0.0000 0.0000 30\nRE_NOT_RELIED 0.0000 0.0000 0.0000 5\n RE_RELIED 0.0000 0.0000 0.0000 29\nRG_PETITIONER 0.0000 0.0000 0.0000 19\nRG_RESPONDENT 0.0000 0.0000 0.0000 13\n SSUE 0.0000 0.0000 0.0000 23\n TA 0.0000 0.0000 0.0000 28\n\n micro avg 0.0000 0.0000 0.0000 454\n macro avg 0.0000 0.0000 0.0000 454\n weighted avg 0.0000 0.0000 0.0000 454\n",
5
  "eval_f1": 0.0,
 
24
  "predict_samples": 50,
25
  "predict_samples_per_second": 18.084,
26
  "predict_steps_per_second": 4.702,
27
+ "total_flos": 6.747257278287053e+16,
28
+ "train_loss": 0.6624447870913739,
29
+ "train_runtime": 485.797,
30
  "train_samples": 247,
31
+ "train_samples_per_second": 10.169,
32
+ "train_steps_per_second": 2.553
33
  }
train_results.json CHANGED
@@ -1,8 +1,9 @@
1
  {
2
- "epoch": 9.0,
3
- "total_flos": 4.337522536041677e+16,
4
- "train_loss": 0.8344365670262271,
5
- "train_runtime": 312.3156,
6
- "train_samples_per_second": 15.817,
7
- "train_steps_per_second": 3.97
 
8
  }
 
1
  {
2
+ "epoch": 14.0,
3
+ "total_flos": 6.747257278287053e+16,
4
+ "train_loss": 0.6624447870913739,
5
+ "train_runtime": 485.797,
6
+ "train_samples": 247,
7
+ "train_samples_per_second": 10.169,
8
+ "train_steps_per_second": 2.553
9
  }
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.2831275720164609,
3
- "best_model_checkpoint": "logs/indian_build_rr/roberta-base/seed_1/checkpoint-372",
4
- "epoch": 9.0,
5
  "eval_steps": 500,
6
- "global_step": 558,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -11,113 +11,121 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.6509204584925321,
14
- "eval_classification_report": " precision recall f1-score support\n\n AC 0.0219 0.0462 0.0297 65\n ATIO 0.0000 0.0000 0.0000 26\n LC 0.0000 0.0000 0.0000 33\n NALYSIS 0.0248 0.0326 0.0282 92\n ONE 0.3519 0.3167 0.3333 60\n PC 0.1000 0.0645 0.0784 31\n REAMBLE 0.0444 0.1333 0.0667 30\nRE_NOT_RELIED 0.0000 0.0000 0.0000 5\n RE_RELIED 0.0000 0.0000 0.0000 29\nRG_PETITIONER 0.0000 0.0000 0.0000 19\nRG_RESPONDENT 0.0000 0.0000 0.0000 13\n SSUE 0.0000 0.0000 0.0000 23\n TA 0.0000 0.0000 0.0000 28\n\n micro avg 0.0700 0.0683 0.0691 454\n macro avg 0.0418 0.0456 0.0413 454\n weighted avg 0.0644 0.0683 0.0638 454\n",
15
- "eval_f1": 0.06911928651059086,
16
  "eval_loss": 1.1796680688858032,
17
- "eval_micro_f1": 0.06911928651059086,
18
- "eval_precision": 0.06997742663656885,
19
- "eval_recall": 0.06828193832599119,
20
- "eval_runtime": 1.9756,
21
- "eval_samples_per_second": 15.185,
22
- "eval_steps_per_second": 4.049,
 
 
 
23
  "step": 62
24
  },
25
  {
26
  "epoch": 2.0,
27
  "eval_accuracy": 0.7349774227162209,
28
- "eval_classification_report": " precision recall f1-score support\n\n AC 0.1210 0.2308 0.1587 65\n ATIO 0.0750 0.1154 0.0909 26\n LC 0.1207 0.2121 0.1538 33\n NALYSIS 0.0548 0.1739 0.0833 92\n ONE 0.4688 0.5000 0.4839 60\n PC 0.2923 0.6129 0.3958 31\n REAMBLE 0.2727 0.5000 0.3529 30\nRE_NOT_RELIED 0.0000 0.0000 0.0000 5\n RE_RELIED 0.1458 0.4828 0.2240 29\nRG_PETITIONER 0.0455 0.1579 0.0706 19\nRG_RESPONDENT 0.0000 0.0000 0.0000 13\n SSUE 0.3929 0.4783 0.4314 23\n TA 0.5366 0.7857 0.6377 28\n\n micro avg 0.1618 0.3414 0.2195 454\n macro avg 0.1943 0.3269 0.2372 454\n weighted avg 0.2056 0.3414 0.2487 454\n",
29
- "eval_f1": 0.21954674220963172,
30
  "eval_loss": 0.8353763222694397,
31
- "eval_micro_f1": 0.21954674220963172,
32
- "eval_precision": 0.1617954070981211,
33
- "eval_recall": 0.34140969162995594,
34
- "eval_runtime": 2.056,
35
- "eval_samples_per_second": 14.591,
36
- "eval_steps_per_second": 3.891,
 
 
 
37
  "step": 124
38
  },
39
  {
40
  "epoch": 3.0,
41
  "eval_accuracy": 0.7342827370614797,
42
- "eval_classification_report": " precision recall f1-score support\n\n AC 0.1068 0.1692 0.1310 65\n ATIO 0.0769 0.1154 0.0923 26\n LC 0.1579 0.2727 0.2000 33\n NALYSIS 0.0608 0.1957 0.0928 92\n ONE 0.5000 0.6500 0.5652 60\n PC 0.2941 0.4839 0.3659 31\n REAMBLE 0.3800 0.6333 0.4750 30\nRE_NOT_RELIED 0.0000 0.0000 0.0000 5\n RE_RELIED 0.1026 0.4138 0.1644 29\nRG_PETITIONER 0.0333 0.1053 0.0506 19\nRG_RESPONDENT 0.0000 0.0000 0.0000 13\n SSUE 0.4706 0.3478 0.4000 23\n TA 0.5333 0.8571 0.6575 28\n\n micro avg 0.1717 0.3524 0.2309 454\n macro avg 0.2090 0.3265 0.2457 454\n weighted avg 0.2194 0.3524 0.2619 454\n",
43
- "eval_f1": 0.2308802308802309,
44
  "eval_loss": 0.8058456182479858,
45
- "eval_micro_f1": 0.2308802308802309,
46
- "eval_precision": 0.17167381974248927,
47
- "eval_recall": 0.3524229074889868,
48
- "eval_runtime": 3.7022,
49
- "eval_samples_per_second": 8.103,
50
- "eval_steps_per_second": 2.161,
 
 
 
51
  "step": 186
52
  },
53
  {
54
  "epoch": 4.0,
55
  "eval_accuracy": 0.7502605071205279,
56
- "eval_classification_report": " precision recall f1-score support\n\n AC 0.1146 0.3385 0.1712 65\n ATIO 0.1538 0.0769 0.1026 26\n LC 0.1429 0.1212 0.1311 33\n NALYSIS 0.0579 0.1630 0.0855 92\n ONE 0.6000 0.6500 0.6240 60\n PC 0.3415 0.4516 0.3889 31\n REAMBLE 0.5500 0.7333 0.6286 30\nRE_NOT_RELIED 0.0000 0.0000 0.0000 5\n RE_RELIED 0.2000 0.2069 0.2034 29\nRG_PETITIONER 0.0800 0.1053 0.0909 19\nRG_RESPONDENT 0.0526 0.1538 0.0784 13\n SSUE 0.5862 0.7391 0.6538 23\n TA 0.6111 0.7857 0.6875 28\n\n micro avg 0.2098 0.3678 0.2672 454\n macro avg 0.2685 0.3481 0.2958 454\n weighted avg 0.2713 0.3678 0.3024 454\n",
57
- "eval_f1": 0.2672,
58
  "eval_loss": 0.7717716097831726,
59
- "eval_micro_f1": 0.2672,
60
- "eval_precision": 0.20979899497487436,
61
- "eval_recall": 0.36784140969163,
62
- "eval_runtime": 2.1055,
63
- "eval_samples_per_second": 14.248,
64
- "eval_steps_per_second": 3.8,
 
 
 
65
  "step": 248
66
  },
67
  {
68
  "epoch": 5.0,
69
  "eval_accuracy": 0.7641542202153525,
70
- "eval_classification_report": " precision recall f1-score support\n\n AC 0.1367 0.2923 0.1863 65\n ATIO 0.1228 0.2692 0.1687 26\n LC 0.1220 0.1515 0.1351 33\n NALYSIS 0.0695 0.1957 0.1026 92\n ONE 0.5714 0.6667 0.6154 60\n PC 0.2963 0.5161 0.3765 31\n REAMBLE 0.2545 0.4667 0.3294 30\nRE_NOT_RELIED 0.0000 0.0000 0.0000 5\n RE_RELIED 0.1757 0.4483 0.2524 29\nRG_PETITIONER 0.0625 0.1053 0.0784 19\nRG_RESPONDENT 0.0526 0.1538 0.0784 13\n SSUE 0.6500 0.5652 0.6047 23\n TA 0.5312 0.6071 0.5667 28\n\n micro avg 0.1906 0.3656 0.2506 454\n macro avg 0.2343 0.3414 0.2688 454\n weighted avg 0.2432 0.3656 0.2830 454\n",
71
- "eval_f1": 0.250566037735849,
72
  "eval_loss": 0.7306948900222778,
73
- "eval_micro_f1": 0.250566037735849,
74
- "eval_precision": 0.19058553386911595,
75
- "eval_recall": 0.3656387665198238,
76
- "eval_runtime": 2.1228,
77
- "eval_samples_per_second": 14.132,
78
- "eval_steps_per_second": 3.769,
 
 
 
79
  "step": 310
80
  },
81
  {
82
  "epoch": 6.0,
83
  "eval_accuracy": 0.774574505036471,
84
- "eval_classification_report": " precision recall f1-score support\n\n AC 0.1172 0.2308 0.1554 65\n ATIO 0.1282 0.1923 0.1538 26\n LC 0.1719 0.3333 0.2268 33\n NALYSIS 0.0711 0.1739 0.1009 92\n ONE 0.6176 0.7000 0.6562 60\n PC 0.3469 0.5484 0.4250 31\n REAMBLE 0.5476 0.7667 0.6389 30\nRE_NOT_RELIED 0.0000 0.0000 0.0000 5\n RE_RELIED 0.1786 0.1724 0.1754 29\nRG_PETITIONER 0.0536 0.1579 0.0800 19\nRG_RESPONDENT 0.0000 0.0000 0.0000 13\n SSUE 0.6667 0.6957 0.6809 23\n TA 0.5758 0.6786 0.6230 28\n\n micro avg 0.2260 0.3789 0.2831 454\n macro avg 0.2673 0.3577 0.3013 454\n weighted avg 0.2755 0.3789 0.3134 454\n",
85
- "eval_f1": 0.2831275720164609,
86
  "eval_loss": 0.7098783254623413,
87
- "eval_micro_f1": 0.2831275720164609,
88
- "eval_precision": 0.22601839684625494,
89
- "eval_recall": 0.3788546255506608,
90
- "eval_runtime": 1.5267,
91
- "eval_samples_per_second": 19.65,
92
- "eval_steps_per_second": 5.24,
 
 
 
93
  "step": 372
94
  },
95
  {
96
  "epoch": 7.0,
97
  "eval_accuracy": 0.7811740187565127,
98
- "eval_classification_report": " precision recall f1-score support\n\n AC 0.0976 0.1846 0.1277 65\n ATIO 0.1081 0.1538 0.1270 26\n LC 0.1034 0.0909 0.0968 33\n NALYSIS 0.0784 0.1739 0.1081 92\n ONE 0.6212 0.6833 0.6508 60\n PC 0.3265 0.5161 0.4000 31\n REAMBLE 0.6316 0.8000 0.7059 30\nRE_NOT_RELIED 0.0000 0.0000 0.0000 5\n RE_RELIED 0.1667 0.1724 0.1695 29\nRG_PETITIONER 0.0541 0.1053 0.0714 19\nRG_RESPONDENT 0.0000 0.0000 0.0000 13\n SSUE 0.6471 0.4783 0.5500 23\n TA 0.5135 0.6786 0.5846 28\n\n micro avg 0.2280 0.3370 0.2720 454\n macro avg 0.2576 0.3106 0.2763 454\n weighted avg 0.2671 0.3370 0.2922 454\n",
99
- "eval_f1": 0.272,
100
  "eval_loss": 0.7071970701217651,
101
- "eval_micro_f1": 0.272,
102
- "eval_precision": 0.22801788375558868,
103
- "eval_recall": 0.3370044052863436,
104
- "eval_runtime": 2.09,
105
- "eval_samples_per_second": 14.354,
106
- "eval_steps_per_second": 3.828,
 
 
 
107
  "step": 434
108
  },
109
  {
110
  "epoch": 8.0,
111
  "eval_accuracy": 0.7825633900659952,
112
- "eval_classification_report": " precision recall f1-score support\n\n AC 0.1168 0.2462 0.1584 65\n ATIO 0.1333 0.2308 0.1690 26\n LC 0.0930 0.1212 0.1053 33\n NALYSIS 0.0755 0.1739 0.1053 92\n ONE 0.6154 0.6667 0.6400 60\n PC 0.3061 0.4839 0.3750 31\n REAMBLE 0.4348 0.6667 0.5263 30\nRE_NOT_RELIED 0.0000 0.0000 0.0000 5\n RE_RELIED 0.2353 0.4138 0.3000 29\nRG_PETITIONER 0.0625 0.1579 0.0896 19\nRG_RESPONDENT 0.0000 0.0000 0.0000 13\n SSUE 0.6250 0.6522 0.6383 23\n TA 0.6400 0.5714 0.6038 28\n\n micro avg 0.2165 0.3590 0.2701 454\n macro avg 0.2567 0.3373 0.2855 454\n weighted avg 0.2662 0.3590 0.2988 454\n",
113
- "eval_f1": 0.27009113504556753,
114
  "eval_loss": 0.6919089555740356,
115
- "eval_micro_f1": 0.27009113504556753,
116
- "eval_precision": 0.21646746347941567,
117
- "eval_recall": 0.3590308370044053,
118
- "eval_runtime": 2.1576,
119
- "eval_samples_per_second": 13.904,
120
- "eval_steps_per_second": 3.708,
 
 
 
121
  "step": 496
122
  },
123
  {
@@ -130,25 +138,101 @@
130
  {
131
  "epoch": 9.0,
132
  "eval_accuracy": 0.7735324765543592,
133
- "eval_classification_report": " precision recall f1-score support\n\n AC 0.1267 0.2923 0.1767 65\n ATIO 0.1250 0.2308 0.1622 26\n LC 0.1143 0.2424 0.1553 33\n NALYSIS 0.0627 0.1739 0.0922 92\n ONE 0.5676 0.7000 0.6269 60\n PC 0.3137 0.5161 0.3902 31\n REAMBLE 0.6667 0.8667 0.7536 30\nRE_NOT_RELIED 0.0000 0.0000 0.0000 5\n RE_RELIED 0.1205 0.3448 0.1786 29\nRG_PETITIONER 0.0370 0.1579 0.0600 19\nRG_RESPONDENT 0.0000 0.0000 0.0000 13\n SSUE 0.7083 0.7391 0.7234 23\n TA 0.5000 0.6071 0.5484 28\n\n micro avg 0.1954 0.3965 0.2618 454\n macro avg 0.2571 0.3747 0.2975 454\n weighted avg 0.2628 0.3965 0.3082 454\n",
134
- "eval_f1": 0.26181818181818184,
135
  "eval_loss": 0.7503196597099304,
136
- "eval_micro_f1": 0.26181818181818184,
137
- "eval_precision": 0.19543973941368079,
138
- "eval_recall": 0.3964757709251101,
139
- "eval_runtime": 1.5272,
140
- "eval_samples_per_second": 19.643,
141
- "eval_steps_per_second": 5.238,
 
 
 
142
  "step": 558
143
  },
144
  {
145
- "epoch": 9.0,
146
- "step": 558,
147
- "total_flos": 4.337522536041677e+16,
148
- "train_loss": 0.8344365670262271,
149
- "train_runtime": 312.3156,
150
- "train_samples_per_second": 15.817,
151
- "train_steps_per_second": 3.97
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
152
  }
153
  ],
154
  "logging_steps": 500,
@@ -177,7 +261,7 @@
177
  "attributes": {}
178
  }
179
  },
180
- "total_flos": 4.337522536041677e+16,
181
  "train_batch_size": 4,
182
  "trial_name": null,
183
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7829107328933658,
3
+ "best_model_checkpoint": "logs/indian_build_rr/roberta-base/seed_1/checkpoint-682",
4
+ "epoch": 14.0,
5
  "eval_steps": 500,
6
+ "global_step": 868,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
11
  {
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.6509204584925321,
 
 
14
  "eval_loss": 1.1796680688858032,
15
+ "eval_macro-f1": 0.2406374552281572,
16
+ "eval_micro-f1": 0.6509204584925321,
17
+ "eval_precision-macro": 0.36507985738726567,
18
+ "eval_precision-micro": 0.6509204584925321,
19
+ "eval_recall-macro": 0.24249037703341708,
20
+ "eval_recall-micro": 0.6509204584925321,
21
+ "eval_runtime": 1.8199,
22
+ "eval_samples_per_second": 16.484,
23
+ "eval_steps_per_second": 4.396,
24
  "step": 62
25
  },
26
  {
27
  "epoch": 2.0,
28
  "eval_accuracy": 0.7349774227162209,
 
 
29
  "eval_loss": 0.8353763222694397,
30
+ "eval_macro-f1": 0.5254710956125371,
31
+ "eval_micro-f1": 0.7349774227162209,
32
+ "eval_precision-macro": 0.5349847227650002,
33
+ "eval_precision-micro": 0.7349774227162209,
34
+ "eval_recall-macro": 0.5291052629047126,
35
+ "eval_recall-micro": 0.7349774227162209,
36
+ "eval_runtime": 4.0287,
37
+ "eval_samples_per_second": 7.447,
38
+ "eval_steps_per_second": 1.986,
39
  "step": 124
40
  },
41
  {
42
  "epoch": 3.0,
43
  "eval_accuracy": 0.7342827370614797,
 
 
44
  "eval_loss": 0.8058456182479858,
45
+ "eval_macro-f1": 0.536617185045311,
46
+ "eval_micro-f1": 0.7342827370614797,
47
+ "eval_precision-macro": 0.5558680331273026,
48
+ "eval_precision-micro": 0.7342827370614797,
49
+ "eval_recall-macro": 0.5381948279596481,
50
+ "eval_recall-micro": 0.7342827370614797,
51
+ "eval_runtime": 1.4616,
52
+ "eval_samples_per_second": 20.525,
53
+ "eval_steps_per_second": 5.473,
54
  "step": 186
55
  },
56
  {
57
  "epoch": 4.0,
58
  "eval_accuracy": 0.7502605071205279,
 
 
59
  "eval_loss": 0.7717716097831726,
60
+ "eval_macro-f1": 0.530010703703156,
61
+ "eval_micro-f1": 0.7502605071205279,
62
+ "eval_precision-macro": 0.6245985387634561,
63
+ "eval_precision-micro": 0.7502605071205279,
64
+ "eval_recall-macro": 0.5200955397553431,
65
+ "eval_recall-micro": 0.7502605071205279,
66
+ "eval_runtime": 2.1073,
67
+ "eval_samples_per_second": 14.236,
68
+ "eval_steps_per_second": 3.796,
69
  "step": 248
70
  },
71
  {
72
  "epoch": 5.0,
73
  "eval_accuracy": 0.7641542202153525,
 
 
74
  "eval_loss": 0.7306948900222778,
75
+ "eval_macro-f1": 0.5578515609115684,
76
+ "eval_micro-f1": 0.7641542202153525,
77
+ "eval_precision-macro": 0.5889876526435496,
78
+ "eval_precision-micro": 0.7641542202153525,
79
+ "eval_recall-macro": 0.5462553107739512,
80
+ "eval_recall-micro": 0.7641542202153525,
81
+ "eval_runtime": 1.4721,
82
+ "eval_samples_per_second": 20.379,
83
+ "eval_steps_per_second": 5.434,
84
  "step": 310
85
  },
86
  {
87
  "epoch": 6.0,
88
  "eval_accuracy": 0.774574505036471,
 
 
89
  "eval_loss": 0.7098783254623413,
90
+ "eval_macro-f1": 0.5481274858908393,
91
+ "eval_micro-f1": 0.774574505036471,
92
+ "eval_precision-macro": 0.6076438792386994,
93
+ "eval_precision-micro": 0.774574505036471,
94
+ "eval_recall-macro": 0.5431283891127849,
95
+ "eval_recall-micro": 0.774574505036471,
96
+ "eval_runtime": 1.6723,
97
+ "eval_samples_per_second": 17.939,
98
+ "eval_steps_per_second": 4.784,
99
  "step": 372
100
  },
101
  {
102
  "epoch": 7.0,
103
  "eval_accuracy": 0.7811740187565127,
 
 
104
  "eval_loss": 0.7071970701217651,
105
+ "eval_macro-f1": 0.5261426411307122,
106
+ "eval_micro-f1": 0.7811740187565127,
107
+ "eval_precision-macro": 0.6089513985670642,
108
+ "eval_precision-micro": 0.7811740187565127,
109
+ "eval_recall-macro": 0.5125569147899907,
110
+ "eval_recall-micro": 0.7811740187565127,
111
+ "eval_runtime": 1.4649,
112
+ "eval_samples_per_second": 20.479,
113
+ "eval_steps_per_second": 5.461,
114
  "step": 434
115
  },
116
  {
117
  "epoch": 8.0,
118
  "eval_accuracy": 0.7825633900659952,
 
 
119
  "eval_loss": 0.6919089555740356,
120
+ "eval_macro-f1": 0.5675875408188613,
121
+ "eval_micro-f1": 0.7825633900659952,
122
+ "eval_precision-macro": 0.6321251715307294,
123
+ "eval_precision-micro": 0.7825633900659952,
124
+ "eval_recall-macro": 0.5470775441802167,
125
+ "eval_recall-micro": 0.7825633900659952,
126
+ "eval_runtime": 1.473,
127
+ "eval_samples_per_second": 20.367,
128
+ "eval_steps_per_second": 5.431,
129
  "step": 496
130
  },
131
  {
 
138
  {
139
  "epoch": 9.0,
140
  "eval_accuracy": 0.7735324765543592,
 
 
141
  "eval_loss": 0.7503196597099304,
142
+ "eval_macro-f1": 0.569622502930968,
143
+ "eval_micro-f1": 0.7735324765543592,
144
+ "eval_precision-macro": 0.5665598749803964,
145
+ "eval_precision-micro": 0.7735324765543592,
146
+ "eval_recall-macro": 0.5818475586367124,
147
+ "eval_recall-micro": 0.7735324765543592,
148
+ "eval_runtime": 1.9237,
149
+ "eval_samples_per_second": 15.595,
150
+ "eval_steps_per_second": 4.159,
151
  "step": 558
152
  },
153
  {
154
+ "epoch": 10.0,
155
+ "eval_accuracy": 0.7783952761375478,
156
+ "eval_loss": 0.7511970400810242,
157
+ "eval_macro-f1": 0.5755339015228546,
158
+ "eval_micro-f1": 0.7783952761375478,
159
+ "eval_precision-macro": 0.6053985952851118,
160
+ "eval_precision-micro": 0.7783952761375478,
161
+ "eval_recall-macro": 0.5655629578179421,
162
+ "eval_recall-micro": 0.7783952761375478,
163
+ "eval_runtime": 1.4668,
164
+ "eval_samples_per_second": 20.453,
165
+ "eval_steps_per_second": 5.454,
166
+ "step": 620
167
+ },
168
+ {
169
+ "epoch": 11.0,
170
+ "eval_accuracy": 0.7829107328933658,
171
+ "eval_loss": 0.7655877470970154,
172
+ "eval_macro-f1": 0.591328685794211,
173
+ "eval_micro-f1": 0.7829107328933658,
174
+ "eval_precision-macro": 0.6085589543807931,
175
+ "eval_precision-micro": 0.7829107328933658,
176
+ "eval_recall-macro": 0.5834711775606751,
177
+ "eval_recall-micro": 0.7829107328933658,
178
+ "eval_runtime": 1.4639,
179
+ "eval_samples_per_second": 20.493,
180
+ "eval_steps_per_second": 5.465,
181
+ "step": 682
182
+ },
183
+ {
184
+ "epoch": 12.0,
185
+ "eval_accuracy": 0.7738798193817298,
186
+ "eval_loss": 0.786118745803833,
187
+ "eval_macro-f1": 0.5843444583481733,
188
+ "eval_micro-f1": 0.7738798193817298,
189
+ "eval_precision-macro": 0.5971774078353586,
190
+ "eval_precision-micro": 0.7738798193817298,
191
+ "eval_recall-macro": 0.5885123710730829,
192
+ "eval_recall-micro": 0.7738798193817298,
193
+ "eval_runtime": 1.4843,
194
+ "eval_samples_per_second": 20.211,
195
+ "eval_steps_per_second": 5.39,
196
+ "step": 744
197
+ },
198
+ {
199
+ "epoch": 13.0,
200
+ "eval_accuracy": 0.7780479333101772,
201
+ "eval_loss": 0.8238919377326965,
202
+ "eval_macro-f1": 0.5701476938599402,
203
+ "eval_micro-f1": 0.7780479333101772,
204
+ "eval_precision-macro": 0.5975031172688886,
205
+ "eval_precision-micro": 0.7780479333101772,
206
+ "eval_recall-macro": 0.5748658781079373,
207
+ "eval_recall-micro": 0.7780479333101772,
208
+ "eval_runtime": 3.173,
209
+ "eval_samples_per_second": 9.455,
210
+ "eval_steps_per_second": 2.521,
211
+ "step": 806
212
+ },
213
+ {
214
+ "epoch": 14.0,
215
+ "eval_accuracy": 0.7797846474470302,
216
+ "eval_loss": 0.8271887302398682,
217
+ "eval_macro-f1": 0.592619371017184,
218
+ "eval_micro-f1": 0.7797846474470302,
219
+ "eval_precision-macro": 0.6088825353073621,
220
+ "eval_precision-micro": 0.7797846474470302,
221
+ "eval_recall-macro": 0.5868004304340952,
222
+ "eval_recall-micro": 0.7797846474470302,
223
+ "eval_runtime": 2.1474,
224
+ "eval_samples_per_second": 13.97,
225
+ "eval_steps_per_second": 3.725,
226
+ "step": 868
227
+ },
228
+ {
229
+ "epoch": 14.0,
230
+ "step": 868,
231
+ "total_flos": 6.747257278287053e+16,
232
+ "train_loss": 0.6624447870913739,
233
+ "train_runtime": 485.797,
234
+ "train_samples_per_second": 10.169,
235
+ "train_steps_per_second": 2.553
236
  }
237
  ],
238
  "logging_steps": 500,
 
261
  "attributes": {}
262
  }
263
  },
264
+ "total_flos": 6.747257278287053e+16,
265
  "train_batch_size": 4,
266
  "trial_name": null,
267
  "trial_params": null