Hugging Face's logo

cbrew475
/
mpnet-metric

Text Classification
Transformers
PyTorch
mpnet
text-embeddings-inference
Model card Files
xet
 Community
1
cbrew475 commited on
Commit
6ce2dea
·
1 Parent(s): c4aefbe

Training in progress, step 1000

Browse files
Files changed (21) hide show
  1. checkpoint-1000/optimizer.pt +1 -1
  2. checkpoint-1000/pytorch_model.bin +1 -1
  3. checkpoint-1000/scheduler.pt +1 -1
  4. checkpoint-1000/trainer_state.json +76 -76
  5. checkpoint-1000/training_args.bin +1 -1
  6. checkpoint-400/optimizer.pt +1 -1
  7. checkpoint-400/pytorch_model.bin +1 -1
  8. checkpoint-400/scheduler.pt +1 -1
  9. checkpoint-400/trainer_state.json +29 -29
  10. checkpoint-400/training_args.bin +1 -1
  11. checkpoint-600/optimizer.pt +1 -1
  12. checkpoint-600/pytorch_model.bin +1 -1
  13. checkpoint-600/scheduler.pt +1 -1
  14. checkpoint-600/trainer_state.json +46 -46
  15. checkpoint-600/training_args.bin +1 -1
  16. checkpoint-800/optimizer.pt +1 -1
  17. checkpoint-800/pytorch_model.bin +1 -1
  18. checkpoint-800/scheduler.pt +1 -1
  19. checkpoint-800/trainer_state.json +60 -60
  20. checkpoint-800/training_args.bin +1 -1
  21. pytorch_model.bin +1 -1
checkpoint-1000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f9f9bcc72df228ab49fa21d8e3811a743aea3cda5d5933116b10e2bc6896729
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0932a52d6b4c3c4e337093c02f9394882fd78cb430dfee8e6137095d3a658a4
3
  size 1762416361
checkpoint-1000/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5514b990ca54d7beb3c5fddbd16cbe75c748372acfaa05eacae568d08edaa13
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b04cceee17b6116ba5f2ffd85407a818511ee6b6e3ffd8931e166c1418fd4035
3
  size 440628841
checkpoint-1000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30077f2b1c510dee2b4d0c21b0952ed081edd606ff8e096ebc1dc34e06ce9e9f
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5342227bdca42f48673c49ca7187615e8bf1f2709576bbd5f67511c70ef56bd4
3
  size 623
checkpoint-1000/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.923051948051948,
3
- "best_model_checkpoint": "mpnet-metric/checkpoint-1000",
4
  "epoch": 22.727272727272727,
5
  "global_step": 1000,
6
  "is_hyper_param_search": false,
@@ -9,124 +9,124 @@
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
  ],
 
1
  {
2
+ "best_metric": 0.9211038961038961,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-400",
4
  "epoch": 22.727272727272727,
5
  "global_step": 1000,
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
  ],
checkpoint-1000/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-400/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6c032bb7989e9ea879d15e222f8513f3645f5e06135dbbd30851e2072cdf966
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea612b45cc7b7560dfaa34705b65983e89e6076f6315781d01cfde65d382fb3f
3
  size 1762416361
checkpoint-400/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9880b80b1eb01684018d6d22d7635a9aec23a8482cc0f40b74942e39ea314414
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d3a61a2da9c7b73f1887898e4cb0300043d05c1557518fd709559d96b8080b4
3
  size 440628841
checkpoint-400/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9ebf170d4e76f723adcddbb48a54aee530c3f11b315afe1bb2aea1d256acd33
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dbc2046c53454073f6195a1fe4497d0952b044c6d7fa8487af05ea95fdea641
3
  size 623
checkpoint-400/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9142857142857143,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-400",
4
  "epoch": 9.090909090909092,
5
  "global_step": 400,
@@ -9,46 +9,46 @@
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
  ],
 
1
  {
2
+ "best_metric": 0.9211038961038961,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-400",
4
  "epoch": 9.090909090909092,
5
  "global_step": 400,
 
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
  ],
checkpoint-400/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-600/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d0f0b774c3dea2c45ca9c7c1f1467c9678fe94b3826135a1da657235cad97ba
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57397a55e3e207d177100783c9bea043367897810d373f2b53b0dfdb059200d4
3
  size 1762416361
checkpoint-600/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1defbb4739184612a0715916f9b15f02e6a5db42063940e9490c1d2661d6468
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dda37daa04128c87e4dee23b3044a855aa93c7c9e81111318c4d8fffa28bc82
3
  size 440628841
checkpoint-600/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a5fa42289233deddee6c2cc8a0079ccaccfbb4eea837d8bdb93ec11a4a49d9c
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f6a1005bab922360d372b72d71902fde1e25b40b68559074f346908f87d1c1
3
  size 623
checkpoint-600/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.922077922077922,
3
- "best_model_checkpoint": "mpnet-metric/checkpoint-600",
4
  "epoch": 13.636363636363637,
5
  "global_step": 600,
6
  "is_hyper_param_search": false,
@@ -9,74 +9,74 @@
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
  ],
 
1
  {
2
+ "best_metric": 0.9211038961038961,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-400",
4
  "epoch": 13.636363636363637,
5
  "global_step": 600,
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
  ],
checkpoint-600/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-800/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7ae5fa75f8667c9070cd30d5cf74887223dc25e3f1af55369cbe14f0e11c76f
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6373658e7aa9f00ef1368297b036f2e3c4ecd620e156b0988e626c6a4cec096a
3
  size 1762416361
checkpoint-800/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f50d4b2b1e849b8e15bcd14c3188274b3fa78e70afd6170f26684bec597a6dcf
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74bd5a8904ee46ca53d83f7d5fd02fcc0670567ac7b7276ae1f1bdb7e206b6b4
3
  size 440628841
checkpoint-800/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a3da879bf7976a12ce6005e9a74ec4dd37a34bf22bba1d62241950a5fc1dee2
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91e3eff1500d66f8c5210afdbb0fa40efe0e49c401fa82508ac2d11c44d0652
3
  size 623
checkpoint-800/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.922077922077922,
3
- "best_model_checkpoint": "mpnet-metric/checkpoint-600",
4
  "epoch": 18.181818181818183,
5
  "global_step": 800,
6
  "is_hyper_param_search": false,
@@ -9,96 +9,96 @@
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
  ],
 
1
  {
2
+ "best_metric": 0.9211038961038961,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-400",
4
  "epoch": 18.181818181818183,
5
  "global_step": 800,
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
  ],
checkpoint-800/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
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:b04cceee17b6116ba5f2ffd85407a818511ee6b6e3ffd8931e166c1418fd4035
3
  size 440628841