Hugging Face's logo

cbrew475
/
mpnet-metric

Text Classification
Transformers
PyTorch
mpnet
Model card Files
xet
Community
1
cbrew475 commited on
Commit
cccfc21
·
1 Parent(s): 6ce2dea

Training in progress, step 200

Browse files
Files changed (22) hide show
  1. checkpoint-1200/optimizer.pt +1 -1
  2. checkpoint-1200/pytorch_model.bin +1 -1
  3. checkpoint-1200/scheduler.pt +1 -1
  4. checkpoint-1200/trainer_state.json +90 -90
  5. checkpoint-1200/training_args.bin +1 -1
  6. checkpoint-1400/optimizer.pt +1 -1
  7. checkpoint-1400/pytorch_model.bin +1 -1
  8. checkpoint-1400/scheduler.pt +1 -1
  9. checkpoint-1400/trainer_state.json +103 -103
  10. checkpoint-1400/training_args.bin +1 -1
  11. checkpoint-1600/optimizer.pt +1 -1
  12. checkpoint-1600/pytorch_model.bin +1 -1
  13. checkpoint-1600/scheduler.pt +1 -1
  14. checkpoint-1600/trainer_state.json +119 -119
  15. checkpoint-1600/training_args.bin +1 -1
  16. checkpoint-200/optimizer.pt +1 -1
  17. checkpoint-200/pytorch_model.bin +1 -1
  18. checkpoint-200/scheduler.pt +1 -1
  19. checkpoint-200/trainer_state.json +15 -15
  20. checkpoint-200/training_args.bin +1 -1
  21. pytorch_model.bin +1 -1
  22. training_args.bin +1 -1
checkpoint-1200/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76937f0a70c1abd6596adda04e9eb76c3f9d6823e0258d3897b08caf2ff08b3a
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ed0fcb2389858b7855c944023c8e3ff020e6f969f19607f172901e1886177a
3
  size 1762416361
checkpoint-1200/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0955e445387e46414d3efbc395b0e76074f90e8c2d8dc89279fd3680259144b7
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3db71b604d12783ac359b4cd32eb2805fb088b687932d56bbb4f2ff0faca7a
3
  size 440628841
checkpoint-1200/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:479d4ee368daa40c591b4f0a1c0e27f0a4fb25e75de4237a35c89d63d622e832
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea043fe05817e85fc2adb93cb12dbca9d33b85f743bb3863f0b42b136916122
3
  size 623
checkpoint-1200/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.924025974025974,
3
- "best_model_checkpoint": "mpnet-metric/checkpoint-1200",
4
  "epoch": 27.272727272727273,
5
  "global_step": 1200,
6
  "is_hyper_param_search": false,
@@ -9,146 +9,146 @@
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
- "eval_accuracy": 0.8175324675324676,
13
- "eval_f1": 0.7586483036626299,
14
- "eval_loss": 1.5314104557037354,
15
- "eval_matthews_correlation": 0.8158158988703459,
16
- "eval_runtime": 2.1491,
17
- "eval_samples_per_second": 1433.157,
18
- "eval_steps_per_second": 9.306,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.9055194805194805,
24
- "eval_f1": 0.9004084535059975,
25
- "eval_loss": 1.4290286302566528,
26
- "eval_matthews_correlation": 0.904262472170852,
27
- "eval_runtime": 2.3719,
28
- "eval_samples_per_second": 1298.528,
29
- "eval_steps_per_second": 8.432,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
- "eval_accuracy": 0.9136363636363637,
35
- "eval_f1": 0.9126411340663838,
36
- "eval_loss": 1.4681222438812256,
37
- "eval_matthews_correlation": 0.912494655557108,
38
- "eval_runtime": 2.316,
39
- "eval_samples_per_second": 1329.901,
40
- "eval_steps_per_second": 8.636,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
- "eval_accuracy": 0.9142857142857143,
46
- "eval_f1": 0.9111728465488748,
47
- "eval_loss": 1.5052858591079712,
48
- "eval_matthews_correlation": 0.9131125844396359,
49
- "eval_runtime": 2.1142,
50
- "eval_samples_per_second": 1456.819,
51
- "eval_steps_per_second": 9.46,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
- "learning_rate": 6.029344779075849e-05,
57
- "loss": 1.1641,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
- "eval_accuracy": 0.9110389610389611,
63
- "eval_f1": 0.910998701155173,
64
- "eval_loss": 1.5782642364501953,
65
- "eval_matthews_correlation": 0.909827792885259,
66
- "eval_runtime": 2.0594,
67
- "eval_samples_per_second": 1495.571,
68
- "eval_steps_per_second": 9.711,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
- "eval_accuracy": 0.922077922077922,
74
- "eval_f1": 0.9229257060098356,
75
- "eval_loss": 1.6256775856018066,
76
- "eval_matthews_correlation": 0.9210043391182823,
77
- "eval_runtime": 2.052,
78
- "eval_samples_per_second": 1500.986,
79
- "eval_steps_per_second": 9.747,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
- "eval_accuracy": 0.9172077922077922,
85
- "eval_f1": 0.9186749710190482,
86
- "eval_loss": 1.6324795484542847,
87
- "eval_matthews_correlation": 0.9161002102784969,
88
- "eval_runtime": 2.1969,
89
- "eval_samples_per_second": 1401.981,
90
- "eval_steps_per_second": 9.104,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
- "eval_accuracy": 0.9168831168831169,
96
- "eval_f1": 0.91675192431042,
97
- "eval_loss": 1.6477916240692139,
98
- "eval_matthews_correlation": 0.9157442220342085,
99
- "eval_runtime": 2.0111,
100
- "eval_samples_per_second": 1531.472,
101
- "eval_steps_per_second": 9.945,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
- "eval_accuracy": 0.9165584415584416,
107
- "eval_f1": 0.9162823863618317,
108
- "eval_loss": 1.6612263917922974,
109
- "eval_matthews_correlation": 0.9154337118487943,
110
- "eval_runtime": 2.0739,
111
- "eval_samples_per_second": 1485.155,
112
- "eval_steps_per_second": 9.644,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
- "learning_rate": 3.6367476445219404e-05,
118
- "loss": 0.5109,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
- "eval_accuracy": 0.923051948051948,
124
- "eval_f1": 0.9217104630353588,
125
- "eval_loss": 1.7244739532470703,
126
- "eval_matthews_correlation": 0.9220060846882479,
127
- "eval_runtime": 2.3613,
128
- "eval_samples_per_second": 1304.348,
129
- "eval_steps_per_second": 8.47,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
- "eval_accuracy": 0.9185064935064935,
135
- "eval_f1": 0.9179896024116552,
136
- "eval_loss": 1.66349458694458,
137
- "eval_matthews_correlation": 0.9173873129169762,
138
- "eval_runtime": 2.0868,
139
- "eval_samples_per_second": 1475.944,
140
- "eval_steps_per_second": 9.584,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
- "eval_accuracy": 0.924025974025974,
146
- "eval_f1": 0.9228242386972402,
147
- "eval_loss": 1.7300477027893066,
148
- "eval_matthews_correlation": 0.9229902054597047,
149
- "eval_runtime": 2.0905,
150
- "eval_samples_per_second": 1473.358,
151
- "eval_steps_per_second": 9.567,
152
  "step": 1200
153
  }
154
  ],
 
1
  {
2
+ "best_metric": 0.9211038961038961,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-400",
4
  "epoch": 27.272727272727273,
5
  "global_step": 1200,
6
  "is_hyper_param_search": false,
 
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
+ "eval_accuracy": 0.811038961038961,
13
+ "eval_f1": 0.7439023537501395,
14
+ "eval_loss": 1.5588715076446533,
15
+ "eval_matthews_correlation": 0.8092922570286504,
16
+ "eval_runtime": 2.19,
17
+ "eval_samples_per_second": 1406.404,
18
+ "eval_steps_per_second": 9.132,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.9022727272727272,
24
+ "eval_f1": 0.8954269843626451,
25
+ "eval_loss": 1.4355967044830322,
26
+ "eval_matthews_correlation": 0.9009908755361663,
27
+ "eval_runtime": 2.1598,
28
+ "eval_samples_per_second": 1426.032,
29
+ "eval_steps_per_second": 9.26,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9087662337662338,
35
+ "eval_f1": 0.9085810469063416,
36
+ "eval_loss": 1.4876813888549805,
37
+ "eval_matthews_correlation": 0.9075986799590098,
38
+ "eval_runtime": 2.5367,
39
+ "eval_samples_per_second": 1214.181,
40
+ "eval_steps_per_second": 7.884,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.9211038961038961,
46
+ "eval_f1": 0.9201538821364931,
47
+ "eval_loss": 1.5697877407073975,
48
+ "eval_matthews_correlation": 0.9200518104822324,
49
+ "eval_runtime": 2.1855,
50
+ "eval_samples_per_second": 1409.265,
51
+ "eval_steps_per_second": 9.151,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 4.966670829549896e-05,
57
+ "loss": 1.1589,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9136363636363637,
63
+ "eval_f1": 0.9151636464610898,
64
+ "eval_loss": 1.5979810953140259,
65
+ "eval_matthews_correlation": 0.9124994144840757,
66
+ "eval_runtime": 2.0901,
67
+ "eval_samples_per_second": 1473.643,
68
+ "eval_steps_per_second": 9.569,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9107142857142857,
74
+ "eval_f1": 0.9107863922881503,
75
+ "eval_loss": 1.6872682571411133,
76
+ "eval_matthews_correlation": 0.9095190428978093,
77
+ "eval_runtime": 2.0448,
78
+ "eval_samples_per_second": 1506.257,
79
+ "eval_steps_per_second": 9.781,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9188311688311688,
85
+ "eval_f1": 0.9186833383887418,
86
+ "eval_loss": 1.6089478731155396,
87
+ "eval_matthews_correlation": 0.9177598370690575,
88
+ "eval_runtime": 2.3373,
89
+ "eval_samples_per_second": 1317.752,
90
+ "eval_steps_per_second": 8.557,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.9165584415584416,
96
+ "eval_f1": 0.9161751570564223,
97
+ "eval_loss": 1.7232335805892944,
98
+ "eval_matthews_correlation": 0.9154263192161151,
99
+ "eval_runtime": 2.0505,
100
+ "eval_samples_per_second": 1502.065,
101
+ "eval_steps_per_second": 9.754,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9191558441558442,
107
+ "eval_f1": 0.9178254962063602,
108
+ "eval_loss": 1.7106611728668213,
109
+ "eval_matthews_correlation": 0.9180443672283,
110
+ "eval_runtime": 2.0231,
111
+ "eval_samples_per_second": 1522.42,
112
+ "eval_steps_per_second": 9.886,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 2.9957697067126356e-05,
118
+ "loss": 0.4659,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9207792207792208,
124
+ "eval_f1": 0.9206063339961166,
125
+ "eval_loss": 1.7829617261886597,
126
+ "eval_matthews_correlation": 0.9196922723503571,
127
+ "eval_runtime": 2.1571,
128
+ "eval_samples_per_second": 1427.815,
129
+ "eval_steps_per_second": 9.272,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9207792207792208,
135
+ "eval_f1": 0.920614925829126,
136
+ "eval_loss": 1.790487289428711,
137
+ "eval_matthews_correlation": 0.9196988176170032,
138
+ "eval_runtime": 2.4658,
139
+ "eval_samples_per_second": 1249.096,
140
+ "eval_steps_per_second": 8.111,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.9204545454545454,
146
+ "eval_f1": 0.9188404387742339,
147
+ "eval_loss": 1.8175984621047974,
148
+ "eval_matthews_correlation": 0.9193738592421591,
149
+ "eval_runtime": 2.1608,
150
+ "eval_samples_per_second": 1425.368,
151
+ "eval_steps_per_second": 9.256,
152
  "step": 1200
153
  }
154
  ],
checkpoint-1200/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4d02d3b63adeabd14d49f5f6122f357f075b2233b6b7e555964f1e944da732c
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e3513e5e545ce3f937f4f40e29e495b42c30f38865af855a93457c5772aab8
3
  size 2927
checkpoint-1400/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06ad6cc82673bb2e8f6491935bb5007a5b2832b6485d74f2d5227ad98e2e2df2
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:775d813f827646f85ebd3ca36b0bc0da9eb27804242e56e23178633dc35442b5
3
  size 1762416361
checkpoint-1400/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:633b2a2e88d1040385a5e5018279418800ee1c797c9012840fce7e248da0aeb0
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ccbd2180207084cad5f0ce95ded2f74a4445182758f26982a02d94bcdade15
3
  size 440628841
checkpoint-1400/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dbf71592de977a1e7b19f8698f1b4071bffd0025c886eac90b8d820c8ad1d58
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871c7c5e2e075b82a9c9e1d4c608b227353621b5e190c395954a23f9cafc754f
3
  size 623
checkpoint-1400/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9275974025974026,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-1400",
4
  "epoch": 31.818181818181817,
5
  "global_step": 1400,
@@ -9,168 +9,168 @@
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
- "eval_accuracy": 0.8175324675324676,
13
- "eval_f1": 0.7586483036626299,
14
- "eval_loss": 1.5314104557037354,
15
- "eval_matthews_correlation": 0.8158158988703459,
16
- "eval_runtime": 2.1491,
17
- "eval_samples_per_second": 1433.157,
18
- "eval_steps_per_second": 9.306,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.9055194805194805,
24
- "eval_f1": 0.9004084535059975,
25
- "eval_loss": 1.4290286302566528,
26
- "eval_matthews_correlation": 0.904262472170852,
27
- "eval_runtime": 2.3719,
28
- "eval_samples_per_second": 1298.528,
29
- "eval_steps_per_second": 8.432,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
- "eval_accuracy": 0.9136363636363637,
35
- "eval_f1": 0.9126411340663838,
36
- "eval_loss": 1.4681222438812256,
37
- "eval_matthews_correlation": 0.912494655557108,
38
- "eval_runtime": 2.316,
39
- "eval_samples_per_second": 1329.901,
40
- "eval_steps_per_second": 8.636,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
- "eval_accuracy": 0.9142857142857143,
46
- "eval_f1": 0.9111728465488748,
47
- "eval_loss": 1.5052858591079712,
48
- "eval_matthews_correlation": 0.9131125844396359,
49
- "eval_runtime": 2.1142,
50
- "eval_samples_per_second": 1456.819,
51
- "eval_steps_per_second": 9.46,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
- "learning_rate": 6.029344779075849e-05,
57
- "loss": 1.1641,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
- "eval_accuracy": 0.9110389610389611,
63
- "eval_f1": 0.910998701155173,
64
- "eval_loss": 1.5782642364501953,
65
- "eval_matthews_correlation": 0.909827792885259,
66
- "eval_runtime": 2.0594,
67
- "eval_samples_per_second": 1495.571,
68
- "eval_steps_per_second": 9.711,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
- "eval_accuracy": 0.922077922077922,
74
- "eval_f1": 0.9229257060098356,
75
- "eval_loss": 1.6256775856018066,
76
- "eval_matthews_correlation": 0.9210043391182823,
77
- "eval_runtime": 2.052,
78
- "eval_samples_per_second": 1500.986,
79
- "eval_steps_per_second": 9.747,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
- "eval_accuracy": 0.9172077922077922,
85
- "eval_f1": 0.9186749710190482,
86
- "eval_loss": 1.6324795484542847,
87
- "eval_matthews_correlation": 0.9161002102784969,
88
- "eval_runtime": 2.1969,
89
- "eval_samples_per_second": 1401.981,
90
- "eval_steps_per_second": 9.104,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
- "eval_accuracy": 0.9168831168831169,
96
- "eval_f1": 0.91675192431042,
97
- "eval_loss": 1.6477916240692139,
98
- "eval_matthews_correlation": 0.9157442220342085,
99
- "eval_runtime": 2.0111,
100
- "eval_samples_per_second": 1531.472,
101
- "eval_steps_per_second": 9.945,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
- "eval_accuracy": 0.9165584415584416,
107
- "eval_f1": 0.9162823863618317,
108
- "eval_loss": 1.6612263917922974,
109
- "eval_matthews_correlation": 0.9154337118487943,
110
- "eval_runtime": 2.0739,
111
- "eval_samples_per_second": 1485.155,
112
- "eval_steps_per_second": 9.644,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
- "learning_rate": 3.6367476445219404e-05,
118
- "loss": 0.5109,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
- "eval_accuracy": 0.923051948051948,
124
- "eval_f1": 0.9217104630353588,
125
- "eval_loss": 1.7244739532470703,
126
- "eval_matthews_correlation": 0.9220060846882479,
127
- "eval_runtime": 2.3613,
128
- "eval_samples_per_second": 1304.348,
129
- "eval_steps_per_second": 8.47,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
- "eval_accuracy": 0.9185064935064935,
135
- "eval_f1": 0.9179896024116552,
136
- "eval_loss": 1.66349458694458,
137
- "eval_matthews_correlation": 0.9173873129169762,
138
- "eval_runtime": 2.0868,
139
- "eval_samples_per_second": 1475.944,
140
- "eval_steps_per_second": 9.584,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
- "eval_accuracy": 0.924025974025974,
146
- "eval_f1": 0.9228242386972402,
147
- "eval_loss": 1.7300477027893066,
148
- "eval_matthews_correlation": 0.9229902054597047,
149
- "eval_runtime": 2.0905,
150
- "eval_samples_per_second": 1473.358,
151
- "eval_steps_per_second": 9.567,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
- "eval_accuracy": 0.925974025974026,
157
- "eval_f1": 0.924309026633035,
158
- "eval_loss": 1.7524604797363281,
159
- "eval_matthews_correlation": 0.9249680111297393,
160
- "eval_runtime": 2.0549,
161
- "eval_samples_per_second": 1498.842,
162
- "eval_steps_per_second": 9.733,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
- "eval_accuracy": 0.9275974025974026,
168
- "eval_f1": 0.925889893783295,
169
- "eval_loss": 1.7725043296813965,
170
- "eval_matthews_correlation": 0.9266053163667549,
171
- "eval_runtime": 2.021,
172
- "eval_samples_per_second": 1523.979,
173
- "eval_steps_per_second": 9.896,
174
  "step": 1400
175
  }
176
  ],
 
1
  {
2
+ "best_metric": 0.9217532467532468,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-1400",
4
  "epoch": 31.818181818181817,
5
  "global_step": 1400,
 
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
+ "eval_accuracy": 0.811038961038961,
13
+ "eval_f1": 0.7439023537501395,
14
+ "eval_loss": 1.5588715076446533,
15
+ "eval_matthews_correlation": 0.8092922570286504,
16
+ "eval_runtime": 2.19,
17
+ "eval_samples_per_second": 1406.404,
18
+ "eval_steps_per_second": 9.132,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.9022727272727272,
24
+ "eval_f1": 0.8954269843626451,
25
+ "eval_loss": 1.4355967044830322,
26
+ "eval_matthews_correlation": 0.9009908755361663,
27
+ "eval_runtime": 2.1598,
28
+ "eval_samples_per_second": 1426.032,
29
+ "eval_steps_per_second": 9.26,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9087662337662338,
35
+ "eval_f1": 0.9085810469063416,
36
+ "eval_loss": 1.4876813888549805,
37
+ "eval_matthews_correlation": 0.9075986799590098,
38
+ "eval_runtime": 2.5367,
39
+ "eval_samples_per_second": 1214.181,
40
+ "eval_steps_per_second": 7.884,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.9211038961038961,
46
+ "eval_f1": 0.9201538821364931,
47
+ "eval_loss": 1.5697877407073975,
48
+ "eval_matthews_correlation": 0.9200518104822324,
49
+ "eval_runtime": 2.1855,
50
+ "eval_samples_per_second": 1409.265,
51
+ "eval_steps_per_second": 9.151,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 4.966670829549896e-05,
57
+ "loss": 1.1589,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9136363636363637,
63
+ "eval_f1": 0.9151636464610898,
64
+ "eval_loss": 1.5979810953140259,
65
+ "eval_matthews_correlation": 0.9124994144840757,
66
+ "eval_runtime": 2.0901,
67
+ "eval_samples_per_second": 1473.643,
68
+ "eval_steps_per_second": 9.569,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9107142857142857,
74
+ "eval_f1": 0.9107863922881503,
75
+ "eval_loss": 1.6872682571411133,
76
+ "eval_matthews_correlation": 0.9095190428978093,
77
+ "eval_runtime": 2.0448,
78
+ "eval_samples_per_second": 1506.257,
79
+ "eval_steps_per_second": 9.781,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9188311688311688,
85
+ "eval_f1": 0.9186833383887418,
86
+ "eval_loss": 1.6089478731155396,
87
+ "eval_matthews_correlation": 0.9177598370690575,
88
+ "eval_runtime": 2.3373,
89
+ "eval_samples_per_second": 1317.752,
90
+ "eval_steps_per_second": 8.557,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.9165584415584416,
96
+ "eval_f1": 0.9161751570564223,
97
+ "eval_loss": 1.7232335805892944,
98
+ "eval_matthews_correlation": 0.9154263192161151,
99
+ "eval_runtime": 2.0505,
100
+ "eval_samples_per_second": 1502.065,
101
+ "eval_steps_per_second": 9.754,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9191558441558442,
107
+ "eval_f1": 0.9178254962063602,
108
+ "eval_loss": 1.7106611728668213,
109
+ "eval_matthews_correlation": 0.9180443672283,
110
+ "eval_runtime": 2.0231,
111
+ "eval_samples_per_second": 1522.42,
112
+ "eval_steps_per_second": 9.886,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 2.9957697067126356e-05,
118
+ "loss": 0.4659,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9207792207792208,
124
+ "eval_f1": 0.9206063339961166,
125
+ "eval_loss": 1.7829617261886597,
126
+ "eval_matthews_correlation": 0.9196922723503571,
127
+ "eval_runtime": 2.1571,
128
+ "eval_samples_per_second": 1427.815,
129
+ "eval_steps_per_second": 9.272,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9207792207792208,
135
+ "eval_f1": 0.920614925829126,
136
+ "eval_loss": 1.790487289428711,
137
+ "eval_matthews_correlation": 0.9196988176170032,
138
+ "eval_runtime": 2.4658,
139
+ "eval_samples_per_second": 1249.096,
140
+ "eval_steps_per_second": 8.111,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.9204545454545454,
146
+ "eval_f1": 0.9188404387742339,
147
+ "eval_loss": 1.8175984621047974,
148
+ "eval_matthews_correlation": 0.9193738592421591,
149
+ "eval_runtime": 2.1608,
150
+ "eval_samples_per_second": 1425.368,
151
+ "eval_steps_per_second": 9.256,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
+ "eval_accuracy": 0.9233766233766234,
157
+ "eval_f1": 0.9229582864798324,
158
+ "eval_loss": 1.8081684112548828,
159
+ "eval_matthews_correlation": 0.9223426539336737,
160
+ "eval_runtime": 2.2566,
161
+ "eval_samples_per_second": 1364.887,
162
+ "eval_steps_per_second": 8.863,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
+ "eval_accuracy": 0.9217532467532468,
168
+ "eval_f1": 0.9198895876658407,
169
+ "eval_loss": 1.8111428022384644,
170
+ "eval_matthews_correlation": 0.920686764000696,
171
+ "eval_runtime": 2.0686,
172
+ "eval_samples_per_second": 1488.895,
173
+ "eval_steps_per_second": 9.668,
174
  "step": 1400
175
  }
176
  ],
checkpoint-1400/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4d02d3b63adeabd14d49f5f6122f357f075b2233b6b7e555964f1e944da732c
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e3513e5e545ce3f937f4f40e29e495b42c30f38865af855a93457c5772aab8
3
  size 2927
checkpoint-1600/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb016982b57f695d5e919c6195b6850d20c05f95e73b0bbad0767c782afce106
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6761a96f04a5d144ad5d0d1ab485d43821b19b46c9d6286724902d1c41c4313
3
  size 1762416361
checkpoint-1600/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14787861a9cf4e494c53cb90272b4e94726527c9710514ae335550f231e14583
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454b5dc90f671b802f85ebdc3659a415c2e5c4fa951d2545a102c97fb2cc9744
3
  size 440628841
checkpoint-1600/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1da099795ba8019b308da25248ff4829ed2b1981e627d1a65e0f850137445743
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c96f06838e7ed125bc66cd3258abcf5211608962ce711b5854cc010d4f3f765
3
  size 623
checkpoint-1600/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9279220779220779,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-1600",
4
  "epoch": 36.36363636363637,
5
  "global_step": 1600,
@@ -9,196 +9,196 @@
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
- "eval_accuracy": 0.8175324675324676,
13
- "eval_f1": 0.7586483036626299,
14
- "eval_loss": 1.5314104557037354,
15
- "eval_matthews_correlation": 0.8158158988703459,
16
- "eval_runtime": 2.1491,
17
- "eval_samples_per_second": 1433.157,
18
- "eval_steps_per_second": 9.306,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.9055194805194805,
24
- "eval_f1": 0.9004084535059975,
25
- "eval_loss": 1.4290286302566528,
26
- "eval_matthews_correlation": 0.904262472170852,
27
- "eval_runtime": 2.3719,
28
- "eval_samples_per_second": 1298.528,
29
- "eval_steps_per_second": 8.432,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
- "eval_accuracy": 0.9136363636363637,
35
- "eval_f1": 0.9126411340663838,
36
- "eval_loss": 1.4681222438812256,
37
- "eval_matthews_correlation": 0.912494655557108,
38
- "eval_runtime": 2.316,
39
- "eval_samples_per_second": 1329.901,
40
- "eval_steps_per_second": 8.636,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
- "eval_accuracy": 0.9142857142857143,
46
- "eval_f1": 0.9111728465488748,
47
- "eval_loss": 1.5052858591079712,
48
- "eval_matthews_correlation": 0.9131125844396359,
49
- "eval_runtime": 2.1142,
50
- "eval_samples_per_second": 1456.819,
51
- "eval_steps_per_second": 9.46,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
- "learning_rate": 6.029344779075849e-05,
57
- "loss": 1.1641,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
- "eval_accuracy": 0.9110389610389611,
63
- "eval_f1": 0.910998701155173,
64
- "eval_loss": 1.5782642364501953,
65
- "eval_matthews_correlation": 0.909827792885259,
66
- "eval_runtime": 2.0594,
67
- "eval_samples_per_second": 1495.571,
68
- "eval_steps_per_second": 9.711,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
- "eval_accuracy": 0.922077922077922,
74
- "eval_f1": 0.9229257060098356,
75
- "eval_loss": 1.6256775856018066,
76
- "eval_matthews_correlation": 0.9210043391182823,
77
- "eval_runtime": 2.052,
78
- "eval_samples_per_second": 1500.986,
79
- "eval_steps_per_second": 9.747,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
- "eval_accuracy": 0.9172077922077922,
85
- "eval_f1": 0.9186749710190482,
86
- "eval_loss": 1.6324795484542847,
87
- "eval_matthews_correlation": 0.9161002102784969,
88
- "eval_runtime": 2.1969,
89
- "eval_samples_per_second": 1401.981,
90
- "eval_steps_per_second": 9.104,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
- "eval_accuracy": 0.9168831168831169,
96
- "eval_f1": 0.91675192431042,
97
- "eval_loss": 1.6477916240692139,
98
- "eval_matthews_correlation": 0.9157442220342085,
99
- "eval_runtime": 2.0111,
100
- "eval_samples_per_second": 1531.472,
101
- "eval_steps_per_second": 9.945,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
- "eval_accuracy": 0.9165584415584416,
107
- "eval_f1": 0.9162823863618317,
108
- "eval_loss": 1.6612263917922974,
109
- "eval_matthews_correlation": 0.9154337118487943,
110
- "eval_runtime": 2.0739,
111
- "eval_samples_per_second": 1485.155,
112
- "eval_steps_per_second": 9.644,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
- "learning_rate": 3.6367476445219404e-05,
118
- "loss": 0.5109,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
- "eval_accuracy": 0.923051948051948,
124
- "eval_f1": 0.9217104630353588,
125
- "eval_loss": 1.7244739532470703,
126
- "eval_matthews_correlation": 0.9220060846882479,
127
- "eval_runtime": 2.3613,
128
- "eval_samples_per_second": 1304.348,
129
- "eval_steps_per_second": 8.47,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
- "eval_accuracy": 0.9185064935064935,
135
- "eval_f1": 0.9179896024116552,
136
- "eval_loss": 1.66349458694458,
137
- "eval_matthews_correlation": 0.9173873129169762,
138
- "eval_runtime": 2.0868,
139
- "eval_samples_per_second": 1475.944,
140
- "eval_steps_per_second": 9.584,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
- "eval_accuracy": 0.924025974025974,
146
- "eval_f1": 0.9228242386972402,
147
- "eval_loss": 1.7300477027893066,
148
- "eval_matthews_correlation": 0.9229902054597047,
149
- "eval_runtime": 2.0905,
150
- "eval_samples_per_second": 1473.358,
151
- "eval_steps_per_second": 9.567,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
- "eval_accuracy": 0.925974025974026,
157
- "eval_f1": 0.924309026633035,
158
- "eval_loss": 1.7524604797363281,
159
- "eval_matthews_correlation": 0.9249680111297393,
160
- "eval_runtime": 2.0549,
161
- "eval_samples_per_second": 1498.842,
162
- "eval_steps_per_second": 9.733,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
- "eval_accuracy": 0.9275974025974026,
168
- "eval_f1": 0.925889893783295,
169
- "eval_loss": 1.7725043296813965,
170
- "eval_matthews_correlation": 0.9266053163667549,
171
- "eval_runtime": 2.021,
172
- "eval_samples_per_second": 1523.979,
173
- "eval_steps_per_second": 9.896,
174
  "step": 1400
175
  },
176
  {
177
  "epoch": 34.09,
178
- "learning_rate": 1.2441505099680323e-05,
179
- "loss": 0.1165,
180
  "step": 1500
181
  },
182
  {
183
  "epoch": 34.09,
184
- "eval_accuracy": 0.9282467532467532,
185
- "eval_f1": 0.9267122192334288,
186
- "eval_loss": 1.7480117082595825,
187
- "eval_matthews_correlation": 0.9272616509919019,
188
- "eval_runtime": 2.0249,
189
- "eval_samples_per_second": 1521.084,
190
- "eval_steps_per_second": 9.877,
191
  "step": 1500
192
  },
193
  {
194
  "epoch": 36.36,
195
- "eval_accuracy": 0.9279220779220779,
196
- "eval_f1": 0.9270559794148399,
197
- "eval_loss": 1.7546428442001343,
198
- "eval_matthews_correlation": 0.9269275295471872,
199
- "eval_runtime": 2.079,
200
- "eval_samples_per_second": 1481.479,
201
- "eval_steps_per_second": 9.62,
202
  "step": 1600
203
  }
204
  ],
 
1
  {
2
+ "best_metric": 0.923051948051948,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-1600",
4
  "epoch": 36.36363636363637,
5
  "global_step": 1600,
 
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
+ "eval_accuracy": 0.811038961038961,
13
+ "eval_f1": 0.7439023537501395,
14
+ "eval_loss": 1.5588715076446533,
15
+ "eval_matthews_correlation": 0.8092922570286504,
16
+ "eval_runtime": 2.19,
17
+ "eval_samples_per_second": 1406.404,
18
+ "eval_steps_per_second": 9.132,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.9022727272727272,
24
+ "eval_f1": 0.8954269843626451,
25
+ "eval_loss": 1.4355967044830322,
26
+ "eval_matthews_correlation": 0.9009908755361663,
27
+ "eval_runtime": 2.1598,
28
+ "eval_samples_per_second": 1426.032,
29
+ "eval_steps_per_second": 9.26,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9087662337662338,
35
+ "eval_f1": 0.9085810469063416,
36
+ "eval_loss": 1.4876813888549805,
37
+ "eval_matthews_correlation": 0.9075986799590098,
38
+ "eval_runtime": 2.5367,
39
+ "eval_samples_per_second": 1214.181,
40
+ "eval_steps_per_second": 7.884,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.9211038961038961,
46
+ "eval_f1": 0.9201538821364931,
47
+ "eval_loss": 1.5697877407073975,
48
+ "eval_matthews_correlation": 0.9200518104822324,
49
+ "eval_runtime": 2.1855,
50
+ "eval_samples_per_second": 1409.265,
51
+ "eval_steps_per_second": 9.151,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 4.966670829549896e-05,
57
+ "loss": 1.1589,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9136363636363637,
63
+ "eval_f1": 0.9151636464610898,
64
+ "eval_loss": 1.5979810953140259,
65
+ "eval_matthews_correlation": 0.9124994144840757,
66
+ "eval_runtime": 2.0901,
67
+ "eval_samples_per_second": 1473.643,
68
+ "eval_steps_per_second": 9.569,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9107142857142857,
74
+ "eval_f1": 0.9107863922881503,
75
+ "eval_loss": 1.6872682571411133,
76
+ "eval_matthews_correlation": 0.9095190428978093,
77
+ "eval_runtime": 2.0448,
78
+ "eval_samples_per_second": 1506.257,
79
+ "eval_steps_per_second": 9.781,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9188311688311688,
85
+ "eval_f1": 0.9186833383887418,
86
+ "eval_loss": 1.6089478731155396,
87
+ "eval_matthews_correlation": 0.9177598370690575,
88
+ "eval_runtime": 2.3373,
89
+ "eval_samples_per_second": 1317.752,
90
+ "eval_steps_per_second": 8.557,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.9165584415584416,
96
+ "eval_f1": 0.9161751570564223,
97
+ "eval_loss": 1.7232335805892944,
98
+ "eval_matthews_correlation": 0.9154263192161151,
99
+ "eval_runtime": 2.0505,
100
+ "eval_samples_per_second": 1502.065,
101
+ "eval_steps_per_second": 9.754,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9191558441558442,
107
+ "eval_f1": 0.9178254962063602,
108
+ "eval_loss": 1.7106611728668213,
109
+ "eval_matthews_correlation": 0.9180443672283,
110
+ "eval_runtime": 2.0231,
111
+ "eval_samples_per_second": 1522.42,
112
+ "eval_steps_per_second": 9.886,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 2.9957697067126356e-05,
118
+ "loss": 0.4659,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9207792207792208,
124
+ "eval_f1": 0.9206063339961166,
125
+ "eval_loss": 1.7829617261886597,
126
+ "eval_matthews_correlation": 0.9196922723503571,
127
+ "eval_runtime": 2.1571,
128
+ "eval_samples_per_second": 1427.815,
129
+ "eval_steps_per_second": 9.272,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9207792207792208,
135
+ "eval_f1": 0.920614925829126,
136
+ "eval_loss": 1.790487289428711,
137
+ "eval_matthews_correlation": 0.9196988176170032,
138
+ "eval_runtime": 2.4658,
139
+ "eval_samples_per_second": 1249.096,
140
+ "eval_steps_per_second": 8.111,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.9204545454545454,
146
+ "eval_f1": 0.9188404387742339,
147
+ "eval_loss": 1.8175984621047974,
148
+ "eval_matthews_correlation": 0.9193738592421591,
149
+ "eval_runtime": 2.1608,
150
+ "eval_samples_per_second": 1425.368,
151
+ "eval_steps_per_second": 9.256,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
+ "eval_accuracy": 0.9233766233766234,
157
+ "eval_f1": 0.9229582864798324,
158
+ "eval_loss": 1.8081684112548828,
159
+ "eval_matthews_correlation": 0.9223426539336737,
160
+ "eval_runtime": 2.2566,
161
+ "eval_samples_per_second": 1364.887,
162
+ "eval_steps_per_second": 8.863,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
+ "eval_accuracy": 0.9217532467532468,
168
+ "eval_f1": 0.9198895876658407,
169
+ "eval_loss": 1.8111428022384644,
170
+ "eval_matthews_correlation": 0.920686764000696,
171
+ "eval_runtime": 2.0686,
172
+ "eval_samples_per_second": 1488.895,
173
+ "eval_steps_per_second": 9.668,
174
  "step": 1400
175
  },
176
  {
177
  "epoch": 34.09,
178
+ "learning_rate": 1.0248685838753754e-05,
179
+ "loss": 0.1136,
180
  "step": 1500
181
  },
182
  {
183
  "epoch": 34.09,
184
+ "eval_accuracy": 0.9227272727272727,
185
+ "eval_f1": 0.9203460178662468,
186
+ "eval_loss": 1.8586403131484985,
187
+ "eval_matthews_correlation": 0.9216675520951976,
188
+ "eval_runtime": 2.1851,
189
+ "eval_samples_per_second": 1409.565,
190
+ "eval_steps_per_second": 9.153,
191
  "step": 1500
192
  },
193
  {
194
  "epoch": 36.36,
195
+ "eval_accuracy": 0.923051948051948,
196
+ "eval_f1": 0.9210405985603535,
197
+ "eval_loss": 1.838761329650879,
198
+ "eval_matthews_correlation": 0.9219970795291079,
199
+ "eval_runtime": 2.0604,
200
+ "eval_samples_per_second": 1494.867,
201
+ "eval_steps_per_second": 9.707,
202
  "step": 1600
203
  }
204
  ],
checkpoint-1600/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4d02d3b63adeabd14d49f5f6122f357f075b2233b6b7e555964f1e944da732c
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e3513e5e545ce3f937f4f40e29e495b42c30f38865af855a93457c5772aab8
3
  size 2927
checkpoint-200/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27f6be1b16c9ee7848188480ba748c5177c4a6e162adec876975d2089fb60428
3
  size 1762415977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514f00db63f43cccb0a7e4a1fef217b54223a75fc5e2ef41ada8d7e4e690eddb
3
  size 1762415977
checkpoint-200/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ffab1b9e9044b851b255bc5d8f43984c6909f62efc4b7e11f47146fa0761af
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c143c9585c7f07018d33924a44f6dbd15721d85d334140a508253f417f7ce7
3
  size 440628841
checkpoint-200/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3585278929f4d0efe53374dc8311894bfe74f48ac4a048ab9996fd58d1068718
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95fde9002ee6cf571ae7d4c3d2c21a6aa5e3c1314fd5310d771dc0a17f698cae
3
  size 623
checkpoint-200/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9022727272727272,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-200",
4
  "epoch": 4.545454545454545,
5
  "global_step": 200,
@@ -9,24 +9,24 @@
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
- "eval_accuracy": 0.811038961038961,
13
- "eval_f1": 0.7439023537501395,
14
- "eval_loss": 1.5588715076446533,
15
- "eval_matthews_correlation": 0.8092922570286504,
16
- "eval_runtime": 2.19,
17
- "eval_samples_per_second": 1406.404,
18
- "eval_steps_per_second": 9.132,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.9022727272727272,
24
- "eval_f1": 0.8954269843626451,
25
- "eval_loss": 1.4355967044830322,
26
- "eval_matthews_correlation": 0.9009908755361663,
27
- "eval_runtime": 2.1598,
28
- "eval_samples_per_second": 1426.032,
29
- "eval_steps_per_second": 9.26,
30
  "step": 200
31
  }
32
  ],
 
1
  {
2
+ "best_metric": 0.8603896103896104,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-200",
4
  "epoch": 4.545454545454545,
5
  "global_step": 200,
 
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
+ "eval_accuracy": 0.8194805194805195,
13
+ "eval_f1": 0.7656701166780793,
14
+ "eval_loss": 1.9282063245773315,
15
+ "eval_matthews_correlation": 0.8177401806097793,
16
+ "eval_runtime": 2.1248,
17
+ "eval_samples_per_second": 1449.542,
18
+ "eval_steps_per_second": 9.413,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.8603896103896104,
24
+ "eval_f1": 0.8221385737164676,
25
+ "eval_loss": 1.785994529724121,
26
+ "eval_matthews_correlation": 0.8588446795045349,
27
+ "eval_runtime": 2.1571,
28
+ "eval_samples_per_second": 1427.834,
29
+ "eval_steps_per_second": 9.272,
30
  "step": 200
31
  }
32
  ],
checkpoint-200/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8e3513e5e545ce3f937f4f40e29e495b42c30f38865af855a93457c5772aab8
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7326a47c8357d75e8dc38a799f439aecb77a23c1cf207d4544566ffb7195bf20
3
  size 2927
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b04cceee17b6116ba5f2ffd85407a818511ee6b6e3ffd8931e166c1418fd4035
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c143c9585c7f07018d33924a44f6dbd15721d85d334140a508253f417f7ce7
3
  size 440628841
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8e3513e5e545ce3f937f4f40e29e495b42c30f38865af855a93457c5772aab8
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7326a47c8357d75e8dc38a799f439aecb77a23c1cf207d4544566ffb7195bf20
3
  size 2927