cbrew475 commited on
Commit
a5d6bf5
·
1 Parent(s): 42bd62a

Training in progress, step 1400

Browse files
checkpoint-1000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0932a52d6b4c3c4e337093c02f9394882fd78cb430dfee8e6137095d3a658a4
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d16254a48573454a8dffae99fcbd6facc8e1dca2bf52789182b5e7ffbad5179a
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:b04cceee17b6116ba5f2ffd85407a818511ee6b6e3ffd8931e166c1418fd4035
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4bb89adf143aa0a397ba7e79218873ad2170511c5f037bb21ebe0ea55a0c28d
3
  size 440628841
checkpoint-1000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5342227bdca42f48673c49ca7187615e8bf1f2709576bbd5f67511c70ef56bd4
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b519090df16ae3dcd0f23b27a096fb05dd73809b346f1b29dc9e93a9ef43485
3
  size 623
checkpoint-1000/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
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,
@@ -9,124 +9,124 @@
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
  ],
 
1
  {
2
+ "best_metric": 0.9272727272727272,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-1000",
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": 0.8194805194805195,
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
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.8831168831168831,
35
+ "eval_f1": 0.8503152420049573,
36
+ "eval_loss": 1.703816533088684,
37
+ "eval_matthews_correlation": 0.8817033568232515,
38
+ "eval_runtime": 2.2955,
39
+ "eval_samples_per_second": 1341.777,
40
+ "eval_steps_per_second": 8.713,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.8948051948051948,
46
+ "eval_f1": 0.8658511061420076,
47
+ "eval_loss": 1.5578949451446533,
48
+ "eval_matthews_correlation": 0.893469940479661,
49
+ "eval_runtime": 2.1159,
50
+ "eval_samples_per_second": 1455.648,
51
+ "eval_steps_per_second": 9.452,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 2.91576008814464e-05,
57
+ "loss": 1.3674,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9084415584415585,
63
+ "eval_f1": 0.8884952022189863,
64
+ "eval_loss": 1.6358195543289185,
65
+ "eval_matthews_correlation": 0.9072261203467101,
66
+ "eval_runtime": 2.0369,
67
+ "eval_samples_per_second": 1512.102,
68
+ "eval_steps_per_second": 9.819,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9191558441558442,
74
+ "eval_f1": 0.9087017801267994,
75
+ "eval_loss": 1.6092149019241333,
76
+ "eval_matthews_correlation": 0.9180607280357055,
77
+ "eval_runtime": 2.2317,
78
+ "eval_samples_per_second": 1380.116,
79
+ "eval_steps_per_second": 8.962,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9237012987012987,
85
+ "eval_f1": 0.9173470137032593,
86
+ "eval_loss": 1.6759223937988281,
87
+ "eval_matthews_correlation": 0.92267900847975,
88
+ "eval_runtime": 2.1403,
89
+ "eval_samples_per_second": 1439.027,
90
+ "eval_steps_per_second": 9.344,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.922077922077922,
96
+ "eval_f1": 0.9224956919233739,
97
+ "eval_loss": 1.7042781114578247,
98
+ "eval_matthews_correlation": 0.9210156723561079,
99
+ "eval_runtime": 2.1182,
100
+ "eval_samples_per_second": 1454.06,
101
+ "eval_steps_per_second": 9.442,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9256493506493506,
107
+ "eval_f1": 0.9250031430609338,
108
+ "eval_loss": 1.618914246559143,
109
+ "eval_matthews_correlation": 0.9246330543218574,
110
+ "eval_runtime": 2.1102,
111
+ "eval_samples_per_second": 1459.597,
112
+ "eval_steps_per_second": 9.478,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 1.758712434118989e-05,
118
+ "loss": 0.4113,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9272727272727272,
124
+ "eval_f1": 0.9262478178442993,
125
+ "eval_loss": 1.6726940870285034,
126
+ "eval_matthews_correlation": 0.9262802775880362,
127
+ "eval_runtime": 2.3947,
128
+ "eval_samples_per_second": 1286.193,
129
+ "eval_steps_per_second": 8.352,
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:a8e3513e5e545ce3f937f4f40e29e495b42c30f38865af855a93457c5772aab8
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7326a47c8357d75e8dc38a799f439aecb77a23c1cf207d4544566ffb7195bf20
3
  size 2927
checkpoint-1200/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54ed0fcb2389858b7855c944023c8e3ff020e6f969f19607f172901e1886177a
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad7a596c052a08c8db42cb10447227e29d8d4455fa0120644eb6f0abbeca42b
3
  size 1762416361
checkpoint-1200/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d3db71b604d12783ac359b4cd32eb2805fb088b687932d56bbb4f2ff0faca7a
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853cf6bedc3356ef5f29d6a357ce047e768610621694b599958a43dc01be5e96
3
  size 440628841
checkpoint-1200/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ea043fe05817e85fc2adb93cb12dbca9d33b85f743bb3863f0b42b136916122
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf8bc9c432358c961802485cb2ea69ee42a10de898d17b0f4a70a83244098ad
3
  size 623
checkpoint-1200/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
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,
@@ -9,146 +9,146 @@
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
  ],
 
1
  {
2
+ "best_metric": 0.9272727272727272,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-1000",
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": 0.8194805194805195,
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
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.8831168831168831,
35
+ "eval_f1": 0.8503152420049573,
36
+ "eval_loss": 1.703816533088684,
37
+ "eval_matthews_correlation": 0.8817033568232515,
38
+ "eval_runtime": 2.2955,
39
+ "eval_samples_per_second": 1341.777,
40
+ "eval_steps_per_second": 8.713,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.8948051948051948,
46
+ "eval_f1": 0.8658511061420076,
47
+ "eval_loss": 1.5578949451446533,
48
+ "eval_matthews_correlation": 0.893469940479661,
49
+ "eval_runtime": 2.1159,
50
+ "eval_samples_per_second": 1455.648,
51
+ "eval_steps_per_second": 9.452,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 2.91576008814464e-05,
57
+ "loss": 1.3674,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9084415584415585,
63
+ "eval_f1": 0.8884952022189863,
64
+ "eval_loss": 1.6358195543289185,
65
+ "eval_matthews_correlation": 0.9072261203467101,
66
+ "eval_runtime": 2.0369,
67
+ "eval_samples_per_second": 1512.102,
68
+ "eval_steps_per_second": 9.819,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9191558441558442,
74
+ "eval_f1": 0.9087017801267994,
75
+ "eval_loss": 1.6092149019241333,
76
+ "eval_matthews_correlation": 0.9180607280357055,
77
+ "eval_runtime": 2.2317,
78
+ "eval_samples_per_second": 1380.116,
79
+ "eval_steps_per_second": 8.962,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9237012987012987,
85
+ "eval_f1": 0.9173470137032593,
86
+ "eval_loss": 1.6759223937988281,
87
+ "eval_matthews_correlation": 0.92267900847975,
88
+ "eval_runtime": 2.1403,
89
+ "eval_samples_per_second": 1439.027,
90
+ "eval_steps_per_second": 9.344,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.922077922077922,
96
+ "eval_f1": 0.9224956919233739,
97
+ "eval_loss": 1.7042781114578247,
98
+ "eval_matthews_correlation": 0.9210156723561079,
99
+ "eval_runtime": 2.1182,
100
+ "eval_samples_per_second": 1454.06,
101
+ "eval_steps_per_second": 9.442,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9256493506493506,
107
+ "eval_f1": 0.9250031430609338,
108
+ "eval_loss": 1.618914246559143,
109
+ "eval_matthews_correlation": 0.9246330543218574,
110
+ "eval_runtime": 2.1102,
111
+ "eval_samples_per_second": 1459.597,
112
+ "eval_steps_per_second": 9.478,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 1.758712434118989e-05,
118
+ "loss": 0.4113,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9272727272727272,
124
+ "eval_f1": 0.9262478178442993,
125
+ "eval_loss": 1.6726940870285034,
126
+ "eval_matthews_correlation": 0.9262802775880362,
127
+ "eval_runtime": 2.3947,
128
+ "eval_samples_per_second": 1286.193,
129
+ "eval_steps_per_second": 8.352,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9282467532467532,
135
+ "eval_f1": 0.9285902214751346,
136
+ "eval_loss": 1.7208188772201538,
137
+ "eval_matthews_correlation": 0.9272760959410294,
138
+ "eval_runtime": 2.0547,
139
+ "eval_samples_per_second": 1498.986,
140
+ "eval_steps_per_second": 9.734,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.9272727272727272,
146
+ "eval_f1": 0.9269182576494233,
147
+ "eval_loss": 1.7480313777923584,
148
+ "eval_matthews_correlation": 0.9262735351894748,
149
+ "eval_runtime": 2.0774,
150
+ "eval_samples_per_second": 1482.597,
151
+ "eval_steps_per_second": 9.627,
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:a8e3513e5e545ce3f937f4f40e29e495b42c30f38865af855a93457c5772aab8
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7326a47c8357d75e8dc38a799f439aecb77a23c1cf207d4544566ffb7195bf20
3
  size 2927
checkpoint-1400/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:775d813f827646f85ebd3ca36b0bc0da9eb27804242e56e23178633dc35442b5
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94026c22fd60a9f8a7247d40dba810569ef7aa21c7e93a1e96b33fb855b16390
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:d3ccbd2180207084cad5f0ce95ded2f74a4445182758f26982a02d94bcdade15
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ce7476ae37df65c46ba296e4e3f2f220f1c120049ff857a57fcf3eb534a1524
3
  size 440628841
checkpoint-1400/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:871c7c5e2e075b82a9c9e1d4c608b227353621b5e190c395954a23f9cafc754f
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b84ba2c6df8c4934f46ec1bcbeaaa46cf4dc96e81696db393fe490fee1b7bf23
3
  size 623
checkpoint-1400/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9217532467532468,
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": 0.811038961038961,
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
  ],
 
1
  {
2
+ "best_metric": 0.9282467532467532,
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": 0.8194805194805195,
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
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.8831168831168831,
35
+ "eval_f1": 0.8503152420049573,
36
+ "eval_loss": 1.703816533088684,
37
+ "eval_matthews_correlation": 0.8817033568232515,
38
+ "eval_runtime": 2.2955,
39
+ "eval_samples_per_second": 1341.777,
40
+ "eval_steps_per_second": 8.713,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.8948051948051948,
46
+ "eval_f1": 0.8658511061420076,
47
+ "eval_loss": 1.5578949451446533,
48
+ "eval_matthews_correlation": 0.893469940479661,
49
+ "eval_runtime": 2.1159,
50
+ "eval_samples_per_second": 1455.648,
51
+ "eval_steps_per_second": 9.452,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 2.91576008814464e-05,
57
+ "loss": 1.3674,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9084415584415585,
63
+ "eval_f1": 0.8884952022189863,
64
+ "eval_loss": 1.6358195543289185,
65
+ "eval_matthews_correlation": 0.9072261203467101,
66
+ "eval_runtime": 2.0369,
67
+ "eval_samples_per_second": 1512.102,
68
+ "eval_steps_per_second": 9.819,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9191558441558442,
74
+ "eval_f1": 0.9087017801267994,
75
+ "eval_loss": 1.6092149019241333,
76
+ "eval_matthews_correlation": 0.9180607280357055,
77
+ "eval_runtime": 2.2317,
78
+ "eval_samples_per_second": 1380.116,
79
+ "eval_steps_per_second": 8.962,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9237012987012987,
85
+ "eval_f1": 0.9173470137032593,
86
+ "eval_loss": 1.6759223937988281,
87
+ "eval_matthews_correlation": 0.92267900847975,
88
+ "eval_runtime": 2.1403,
89
+ "eval_samples_per_second": 1439.027,
90
+ "eval_steps_per_second": 9.344,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.922077922077922,
96
+ "eval_f1": 0.9224956919233739,
97
+ "eval_loss": 1.7042781114578247,
98
+ "eval_matthews_correlation": 0.9210156723561079,
99
+ "eval_runtime": 2.1182,
100
+ "eval_samples_per_second": 1454.06,
101
+ "eval_steps_per_second": 9.442,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9256493506493506,
107
+ "eval_f1": 0.9250031430609338,
108
+ "eval_loss": 1.618914246559143,
109
+ "eval_matthews_correlation": 0.9246330543218574,
110
+ "eval_runtime": 2.1102,
111
+ "eval_samples_per_second": 1459.597,
112
+ "eval_steps_per_second": 9.478,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 1.758712434118989e-05,
118
+ "loss": 0.4113,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9272727272727272,
124
+ "eval_f1": 0.9262478178442993,
125
+ "eval_loss": 1.6726940870285034,
126
+ "eval_matthews_correlation": 0.9262802775880362,
127
+ "eval_runtime": 2.3947,
128
+ "eval_samples_per_second": 1286.193,
129
+ "eval_steps_per_second": 8.352,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9282467532467532,
135
+ "eval_f1": 0.9285902214751346,
136
+ "eval_loss": 1.7208188772201538,
137
+ "eval_matthews_correlation": 0.9272760959410294,
138
+ "eval_runtime": 2.0547,
139
+ "eval_samples_per_second": 1498.986,
140
+ "eval_steps_per_second": 9.734,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.9272727272727272,
146
+ "eval_f1": 0.9269182576494233,
147
+ "eval_loss": 1.7480313777923584,
148
+ "eval_matthews_correlation": 0.9262735351894748,
149
+ "eval_runtime": 2.0774,
150
+ "eval_samples_per_second": 1482.597,
151
+ "eval_steps_per_second": 9.627,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
+ "eval_accuracy": 0.9262987012987013,
157
+ "eval_f1": 0.9262601189689171,
158
+ "eval_loss": 1.7753738164901733,
159
+ "eval_matthews_correlation": 0.9252925536787239,
160
+ "eval_runtime": 2.1885,
161
+ "eval_samples_per_second": 1407.348,
162
+ "eval_steps_per_second": 9.139,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
+ "eval_accuracy": 0.9282467532467532,
168
+ "eval_f1": 0.9278794105174281,
169
+ "eval_loss": 1.790648341178894,
170
+ "eval_matthews_correlation": 0.9272619193360061,
171
+ "eval_runtime": 2.0054,
172
+ "eval_samples_per_second": 1535.842,
173
+ "eval_steps_per_second": 9.973,
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: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 sha256:38381380b182a449c1fe36f43009070e415f0b58b89f24f7c894800dbebb0e0b
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ce7476ae37df65c46ba296e4e3f2f220f1c120049ff857a57fcf3eb534a1524
3
  size 440628841