Hugging Face's logo

cbrew475
/
mpnet-metric

Text Classification
Transformers
PyTorch
mpnet
Inference Endpoints
Model card Files Community
cbrew475 commited on
Commit
adc3913
•
1 Parent(s): bb50fb7

Training in progress, step 1600

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-1200/optimizer.pt +1 -1
  7. checkpoint-1200/pytorch_model.bin +1 -1
  8. checkpoint-1200/scheduler.pt +1 -1
  9. checkpoint-1200/trainer_state.json +90 -90
  10. checkpoint-1200/training_args.bin +1 -1
  11. checkpoint-1400/optimizer.pt +1 -1
  12. checkpoint-1400/pytorch_model.bin +1 -1
  13. checkpoint-1400/scheduler.pt +1 -1
  14. checkpoint-1400/trainer_state.json +103 -103
  15. checkpoint-1400/training_args.bin +1 -1
  16. checkpoint-1600/optimizer.pt +1 -1
  17. checkpoint-1600/pytorch_model.bin +1 -1
  18. checkpoint-1600/scheduler.pt +1 -1
  19. checkpoint-1600/trainer_state.json +119 -119
  20. checkpoint-1600/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:d16254a48573454a8dffae99fcbd6facc8e1dca2bf52789182b5e7ffbad5179a
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04df6b10a2e5436a84faa1c8cbe18ef2e942b53a5408bac33e49149a0f9401a8
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:b4bb89adf143aa0a397ba7e79218873ad2170511c5f037bb21ebe0ea55a0c28d
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d65f7128296fa2e4d7089a156c10fb91f0954bb370393469468a544b91c2b34
3
  size 440628841
checkpoint-1000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b519090df16ae3dcd0f23b27a096fb05dd73809b346f1b29dc9e93a9ef43485
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c23abde9a702bf2ad4c49136092e96387041e5433bdc7ef78f63f9667592975b
3
  size 623
checkpoint-1000/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
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,
@@ -9,124 +9,124 @@
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
  ],
 
1
  {
2
+ "best_metric": 0.9211038961038961,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-600",
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": 0.8418831168831169,
13
+ "eval_f1": 0.8027962745185904,
14
+ "eval_loss": 1.4791860580444336,
15
+ "eval_matthews_correlation": 0.8403536839300481,
16
+ "eval_runtime": 2.0893,
17
+ "eval_samples_per_second": 1474.144,
18
+ "eval_steps_per_second": 9.572,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.9042207792207793,
24
+ "eval_f1": 0.9047628877989691,
25
+ "eval_loss": 1.487802267074585,
26
+ "eval_matthews_correlation": 0.9030870359405524,
27
+ "eval_runtime": 2.1548,
28
+ "eval_samples_per_second": 1429.39,
29
+ "eval_steps_per_second": 9.282,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9172077922077922,
35
+ "eval_f1": 0.9169016425995938,
36
+ "eval_loss": 1.6755403280258179,
37
+ "eval_matthews_correlation": 0.9161647270846853,
38
+ "eval_runtime": 2.1745,
39
+ "eval_samples_per_second": 1416.389,
40
+ "eval_steps_per_second": 9.197,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.9123376623376623,
46
+ "eval_f1": 0.9128534869153119,
47
+ "eval_loss": 1.6229037046432495,
48
+ "eval_matthews_correlation": 0.9111753584333115,
49
+ "eval_runtime": 2.0543,
50
+ "eval_samples_per_second": 1499.327,
51
+ "eval_steps_per_second": 9.736,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 5.2705340156346366e-05,
57
+ "loss": 1.1094,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9172077922077922,
63
+ "eval_f1": 0.9150003521466267,
64
+ "eval_loss": 1.6902168989181519,
65
+ "eval_matthews_correlation": 0.916107308697779,
66
+ "eval_runtime": 2.1005,
67
+ "eval_samples_per_second": 1466.292,
68
+ "eval_steps_per_second": 9.521,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9211038961038961,
74
+ "eval_f1": 0.9217190641997036,
75
+ "eval_loss": 1.809704065322876,
76
+ "eval_matthews_correlation": 0.9200266092875187,
77
+ "eval_runtime": 2.1893,
78
+ "eval_samples_per_second": 1406.863,
79
+ "eval_steps_per_second": 9.135,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9256493506493506,
85
+ "eval_f1": 0.9258906800234634,
86
+ "eval_loss": 1.767533779144287,
87
+ "eval_matthews_correlation": 0.9246460003797943,
88
+ "eval_runtime": 2.1499,
89
+ "eval_samples_per_second": 1432.599,
90
+ "eval_steps_per_second": 9.303,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.9188311688311688,
96
+ "eval_f1": 0.9200483431183891,
97
+ "eval_loss": 1.8722023963928223,
98
+ "eval_matthews_correlation": 0.917724204986671,
99
+ "eval_runtime": 2.0585,
100
+ "eval_samples_per_second": 1496.224,
101
+ "eval_steps_per_second": 9.716,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9243506493506494,
107
+ "eval_f1": 0.9260936300814407,
108
+ "eval_loss": 1.8695343732833862,
109
+ "eval_matthews_correlation": 0.9233259198964885,
110
+ "eval_runtime": 2.2261,
111
+ "eval_samples_per_second": 1383.609,
112
+ "eval_steps_per_second": 8.984,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 3.17905226339867e-05,
118
+ "loss": 0.3393,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9207792207792208,
124
+ "eval_f1": 0.922710960511792,
125
+ "eval_loss": 1.8605962991714478,
126
+ "eval_matthews_correlation": 0.9197088857351889,
127
+ "eval_runtime": 2.2172,
128
+ "eval_samples_per_second": 1389.151,
129
+ "eval_steps_per_second": 9.02,
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 sha256:7326a47c8357d75e8dc38a799f439aecb77a23c1cf207d4544566ffb7195bf20
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292e7a8288c43b303abd31559aec885616dd7d87f70adfd70022f96ffad2e087
3
  size 2927
checkpoint-1200/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cad7a596c052a08c8db42cb10447227e29d8d4455fa0120644eb6f0abbeca42b
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0410497c9e5be54ec124d96b6848969fd4acea3240a9f89e6559f5bd87847c34
3
  size 1762416361
checkpoint-1200/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:853cf6bedc3356ef5f29d6a357ce047e768610621694b599958a43dc01be5e96
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ffecffe2686fbfcf6c605f19a76866c3460b37457230cdb8160464fddb4b2f
3
  size 440628841
checkpoint-1200/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bf8bc9c432358c961802485cb2ea69ee42a10de898d17b0f4a70a83244098ad
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a53b6645435530887e0124ab5908e382fae11ca2235c7dbb490f05e05d0d13c
3
  size 623
checkpoint-1200/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
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,
@@ -9,146 +9,146 @@
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
  ],
 
1
  {
2
+ "best_metric": 0.9214285714285714,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-1200",
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": 0.8418831168831169,
13
+ "eval_f1": 0.8027962745185904,
14
+ "eval_loss": 1.4791860580444336,
15
+ "eval_matthews_correlation": 0.8403536839300481,
16
+ "eval_runtime": 2.0893,
17
+ "eval_samples_per_second": 1474.144,
18
+ "eval_steps_per_second": 9.572,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.9042207792207793,
24
+ "eval_f1": 0.9047628877989691,
25
+ "eval_loss": 1.487802267074585,
26
+ "eval_matthews_correlation": 0.9030870359405524,
27
+ "eval_runtime": 2.1548,
28
+ "eval_samples_per_second": 1429.39,
29
+ "eval_steps_per_second": 9.282,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9172077922077922,
35
+ "eval_f1": 0.9169016425995938,
36
+ "eval_loss": 1.6755403280258179,
37
+ "eval_matthews_correlation": 0.9161647270846853,
38
+ "eval_runtime": 2.1745,
39
+ "eval_samples_per_second": 1416.389,
40
+ "eval_steps_per_second": 9.197,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.9123376623376623,
46
+ "eval_f1": 0.9128534869153119,
47
+ "eval_loss": 1.6229037046432495,
48
+ "eval_matthews_correlation": 0.9111753584333115,
49
+ "eval_runtime": 2.0543,
50
+ "eval_samples_per_second": 1499.327,
51
+ "eval_steps_per_second": 9.736,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 5.2705340156346366e-05,
57
+ "loss": 1.1094,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9172077922077922,
63
+ "eval_f1": 0.9150003521466267,
64
+ "eval_loss": 1.6902168989181519,
65
+ "eval_matthews_correlation": 0.916107308697779,
66
+ "eval_runtime": 2.1005,
67
+ "eval_samples_per_second": 1466.292,
68
+ "eval_steps_per_second": 9.521,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9211038961038961,
74
+ "eval_f1": 0.9217190641997036,
75
+ "eval_loss": 1.809704065322876,
76
+ "eval_matthews_correlation": 0.9200266092875187,
77
+ "eval_runtime": 2.1893,
78
+ "eval_samples_per_second": 1406.863,
79
+ "eval_steps_per_second": 9.135,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9256493506493506,
85
+ "eval_f1": 0.9258906800234634,
86
+ "eval_loss": 1.767533779144287,
87
+ "eval_matthews_correlation": 0.9246460003797943,
88
+ "eval_runtime": 2.1499,
89
+ "eval_samples_per_second": 1432.599,
90
+ "eval_steps_per_second": 9.303,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.9188311688311688,
96
+ "eval_f1": 0.9200483431183891,
97
+ "eval_loss": 1.8722023963928223,
98
+ "eval_matthews_correlation": 0.917724204986671,
99
+ "eval_runtime": 2.0585,
100
+ "eval_samples_per_second": 1496.224,
101
+ "eval_steps_per_second": 9.716,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9243506493506494,
107
+ "eval_f1": 0.9260936300814407,
108
+ "eval_loss": 1.8695343732833862,
109
+ "eval_matthews_correlation": 0.9233259198964885,
110
+ "eval_runtime": 2.2261,
111
+ "eval_samples_per_second": 1383.609,
112
+ "eval_steps_per_second": 8.984,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 3.17905226339867e-05,
118
+ "loss": 0.3393,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9207792207792208,
124
+ "eval_f1": 0.922710960511792,
125
+ "eval_loss": 1.8605962991714478,
126
+ "eval_matthews_correlation": 0.9197088857351889,
127
+ "eval_runtime": 2.2172,
128
+ "eval_samples_per_second": 1389.151,
129
+ "eval_steps_per_second": 9.02,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9233766233766234,
135
+ "eval_f1": 0.9254235342983648,
136
+ "eval_loss": 1.953273057937622,
137
+ "eval_matthews_correlation": 0.9223384276331019,
138
+ "eval_runtime": 2.1419,
139
+ "eval_samples_per_second": 1437.981,
140
+ "eval_steps_per_second": 9.338,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.9214285714285714,
146
+ "eval_f1": 0.9231886111183961,
147
+ "eval_loss": 1.9357961416244507,
148
+ "eval_matthews_correlation": 0.9203654618815811,
149
+ "eval_runtime": 2.0224,
150
+ "eval_samples_per_second": 1522.94,
151
+ "eval_steps_per_second": 9.889,
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 sha256:7326a47c8357d75e8dc38a799f439aecb77a23c1cf207d4544566ffb7195bf20
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292e7a8288c43b303abd31559aec885616dd7d87f70adfd70022f96ffad2e087
3
  size 2927
checkpoint-1400/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94026c22fd60a9f8a7247d40dba810569ef7aa21c7e93a1e96b33fb855b16390
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f7b52b38a3744a4a9ff4ac81ff0e4d5852056d5dee8b8047e789152a294d039
3
  size 1762416361
checkpoint-1400/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ce7476ae37df65c46ba296e4e3f2f220f1c120049ff857a57fcf3eb534a1524
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db2e0489f9cdb98bd8985a9fe338d570b1b7b05426cc18a50a80aa8438162d47
3
  size 440628841
checkpoint-1400/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b84ba2c6df8c4934f46ec1bcbeaaa46cf4dc96e81696db393fe490fee1b7bf23
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bad9db216334f64080a76e92c8a09e55e3bdd82e81456b5cca866480a481f93e
3
  size 623
checkpoint-1400/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9282467532467532,
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": 0.8194805194805195,
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
  ],
 
1
  {
2
+ "best_metric": 0.925,
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": 0.8418831168831169,
13
+ "eval_f1": 0.8027962745185904,
14
+ "eval_loss": 1.4791860580444336,
15
+ "eval_matthews_correlation": 0.8403536839300481,
16
+ "eval_runtime": 2.0893,
17
+ "eval_samples_per_second": 1474.144,
18
+ "eval_steps_per_second": 9.572,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.9042207792207793,
24
+ "eval_f1": 0.9047628877989691,
25
+ "eval_loss": 1.487802267074585,
26
+ "eval_matthews_correlation": 0.9030870359405524,
27
+ "eval_runtime": 2.1548,
28
+ "eval_samples_per_second": 1429.39,
29
+ "eval_steps_per_second": 9.282,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9172077922077922,
35
+ "eval_f1": 0.9169016425995938,
36
+ "eval_loss": 1.6755403280258179,
37
+ "eval_matthews_correlation": 0.9161647270846853,
38
+ "eval_runtime": 2.1745,
39
+ "eval_samples_per_second": 1416.389,
40
+ "eval_steps_per_second": 9.197,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.9123376623376623,
46
+ "eval_f1": 0.9128534869153119,
47
+ "eval_loss": 1.6229037046432495,
48
+ "eval_matthews_correlation": 0.9111753584333115,
49
+ "eval_runtime": 2.0543,
50
+ "eval_samples_per_second": 1499.327,
51
+ "eval_steps_per_second": 9.736,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 5.2705340156346366e-05,
57
+ "loss": 1.1094,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9172077922077922,
63
+ "eval_f1": 0.9150003521466267,
64
+ "eval_loss": 1.6902168989181519,
65
+ "eval_matthews_correlation": 0.916107308697779,
66
+ "eval_runtime": 2.1005,
67
+ "eval_samples_per_second": 1466.292,
68
+ "eval_steps_per_second": 9.521,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9211038961038961,
74
+ "eval_f1": 0.9217190641997036,
75
+ "eval_loss": 1.809704065322876,
76
+ "eval_matthews_correlation": 0.9200266092875187,
77
+ "eval_runtime": 2.1893,
78
+ "eval_samples_per_second": 1406.863,
79
+ "eval_steps_per_second": 9.135,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9256493506493506,
85
+ "eval_f1": 0.9258906800234634,
86
+ "eval_loss": 1.767533779144287,
87
+ "eval_matthews_correlation": 0.9246460003797943,
88
+ "eval_runtime": 2.1499,
89
+ "eval_samples_per_second": 1432.599,
90
+ "eval_steps_per_second": 9.303,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.9188311688311688,
96
+ "eval_f1": 0.9200483431183891,
97
+ "eval_loss": 1.8722023963928223,
98
+ "eval_matthews_correlation": 0.917724204986671,
99
+ "eval_runtime": 2.0585,
100
+ "eval_samples_per_second": 1496.224,
101
+ "eval_steps_per_second": 9.716,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9243506493506494,
107
+ "eval_f1": 0.9260936300814407,
108
+ "eval_loss": 1.8695343732833862,
109
+ "eval_matthews_correlation": 0.9233259198964885,
110
+ "eval_runtime": 2.2261,
111
+ "eval_samples_per_second": 1383.609,
112
+ "eval_steps_per_second": 8.984,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 3.17905226339867e-05,
118
+ "loss": 0.3393,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9207792207792208,
124
+ "eval_f1": 0.922710960511792,
125
+ "eval_loss": 1.8605962991714478,
126
+ "eval_matthews_correlation": 0.9197088857351889,
127
+ "eval_runtime": 2.2172,
128
+ "eval_samples_per_second": 1389.151,
129
+ "eval_steps_per_second": 9.02,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9233766233766234,
135
+ "eval_f1": 0.9254235342983648,
136
+ "eval_loss": 1.953273057937622,
137
+ "eval_matthews_correlation": 0.9223384276331019,
138
+ "eval_runtime": 2.1419,
139
+ "eval_samples_per_second": 1437.981,
140
+ "eval_steps_per_second": 9.338,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.9214285714285714,
146
+ "eval_f1": 0.9231886111183961,
147
+ "eval_loss": 1.9357961416244507,
148
+ "eval_matthews_correlation": 0.9203654618815811,
149
+ "eval_runtime": 2.0224,
150
+ "eval_samples_per_second": 1522.94,
151
+ "eval_steps_per_second": 9.889,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
+ "eval_accuracy": 0.924025974025974,
157
+ "eval_f1": 0.9255922212692556,
158
+ "eval_loss": 1.9956995248794556,
159
+ "eval_matthews_correlation": 0.922995468010013,
160
+ "eval_runtime": 2.3012,
161
+ "eval_samples_per_second": 1338.415,
162
+ "eval_steps_per_second": 8.691,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
+ "eval_accuracy": 0.925,
168
+ "eval_f1": 0.9265277453816252,
169
+ "eval_loss": 1.9824904203414917,
170
+ "eval_matthews_correlation": 0.923978861394841,
171
+ "eval_runtime": 2.0192,
172
+ "eval_samples_per_second": 1525.369,
173
+ "eval_steps_per_second": 9.905,
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 sha256:7326a47c8357d75e8dc38a799f439aecb77a23c1cf207d4544566ffb7195bf20
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292e7a8288c43b303abd31559aec885616dd7d87f70adfd70022f96ffad2e087
3
  size 2927
checkpoint-1600/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:227ed66293bdd92a98aef33e2bea6e0cf714b5f3de2221070e85c0fd928b6de6
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3350dbcc8104acd08e84a58c07fdb1833b2ddb45fcd2bfef5da548a780e739b
3
  size 1762416361
checkpoint-1600/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6554b9968a07507c9ad3a7768e4bf306b17d8dc60069999b186a9c02dd47c9dd
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d5f7a99bc696ec585141e36db427d8a12d947ee8831ba934c12839de8bf7da7
3
  size 440628841
checkpoint-1600/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f308c18e470c73b6a08f647ea7fbf34e8681f5877eba1262e1d03e5323d4a478
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d15445420111b446c8290914a3dcd1da5032dca6b2b8283b3c5d1758e8bfd5c
3
  size 623
checkpoint-1600/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9282467532467532,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-1400",
4
  "epoch": 36.36363636363637,
5
  "global_step": 1600,
@@ -9,196 +9,196 @@
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
  {
177
  "epoch": 34.09,
178
- "learning_rate": 6.0166478009333844e-06,
179
- "loss": 0.0733,
180
  "step": 1500
181
  },
182
  {
183
  "epoch": 34.09,
184
- "eval_accuracy": 0.9262987012987013,
185
- "eval_f1": 0.9263368444227621,
186
- "eval_loss": 1.805496335029602,
187
- "eval_matthews_correlation": 0.9252900896996127,
188
- "eval_runtime": 2.1349,
189
- "eval_samples_per_second": 1442.709,
190
- "eval_steps_per_second": 9.368,
191
  "step": 1500
192
  },
193
  {
194
  "epoch": 36.36,
195
- "eval_accuracy": 0.9282467532467532,
196
- "eval_f1": 0.9281799745185059,
197
- "eval_loss": 1.7787483930587769,
198
- "eval_matthews_correlation": 0.9272691959664779,
199
- "eval_runtime": 2.095,
200
- "eval_samples_per_second": 1470.152,
201
- "eval_steps_per_second": 9.546,
202
  "step": 1600
203
  }
204
  ],
 
1
  {
2
+ "best_metric": 0.925,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-1400",
4
  "epoch": 36.36363636363637,
5
  "global_step": 1600,
 
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
+ "eval_accuracy": 0.8418831168831169,
13
+ "eval_f1": 0.8027962745185904,
14
+ "eval_loss": 1.4791860580444336,
15
+ "eval_matthews_correlation": 0.8403536839300481,
16
+ "eval_runtime": 2.0893,
17
+ "eval_samples_per_second": 1474.144,
18
+ "eval_steps_per_second": 9.572,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.9042207792207793,
24
+ "eval_f1": 0.9047628877989691,
25
+ "eval_loss": 1.487802267074585,
26
+ "eval_matthews_correlation": 0.9030870359405524,
27
+ "eval_runtime": 2.1548,
28
+ "eval_samples_per_second": 1429.39,
29
+ "eval_steps_per_second": 9.282,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9172077922077922,
35
+ "eval_f1": 0.9169016425995938,
36
+ "eval_loss": 1.6755403280258179,
37
+ "eval_matthews_correlation": 0.9161647270846853,
38
+ "eval_runtime": 2.1745,
39
+ "eval_samples_per_second": 1416.389,
40
+ "eval_steps_per_second": 9.197,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.9123376623376623,
46
+ "eval_f1": 0.9128534869153119,
47
+ "eval_loss": 1.6229037046432495,
48
+ "eval_matthews_correlation": 0.9111753584333115,
49
+ "eval_runtime": 2.0543,
50
+ "eval_samples_per_second": 1499.327,
51
+ "eval_steps_per_second": 9.736,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 5.2705340156346366e-05,
57
+ "loss": 1.1094,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9172077922077922,
63
+ "eval_f1": 0.9150003521466267,
64
+ "eval_loss": 1.6902168989181519,
65
+ "eval_matthews_correlation": 0.916107308697779,
66
+ "eval_runtime": 2.1005,
67
+ "eval_samples_per_second": 1466.292,
68
+ "eval_steps_per_second": 9.521,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9211038961038961,
74
+ "eval_f1": 0.9217190641997036,
75
+ "eval_loss": 1.809704065322876,
76
+ "eval_matthews_correlation": 0.9200266092875187,
77
+ "eval_runtime": 2.1893,
78
+ "eval_samples_per_second": 1406.863,
79
+ "eval_steps_per_second": 9.135,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9256493506493506,
85
+ "eval_f1": 0.9258906800234634,
86
+ "eval_loss": 1.767533779144287,
87
+ "eval_matthews_correlation": 0.9246460003797943,
88
+ "eval_runtime": 2.1499,
89
+ "eval_samples_per_second": 1432.599,
90
+ "eval_steps_per_second": 9.303,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.9188311688311688,
96
+ "eval_f1": 0.9200483431183891,
97
+ "eval_loss": 1.8722023963928223,
98
+ "eval_matthews_correlation": 0.917724204986671,
99
+ "eval_runtime": 2.0585,
100
+ "eval_samples_per_second": 1496.224,
101
+ "eval_steps_per_second": 9.716,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9243506493506494,
107
+ "eval_f1": 0.9260936300814407,
108
+ "eval_loss": 1.8695343732833862,
109
+ "eval_matthews_correlation": 0.9233259198964885,
110
+ "eval_runtime": 2.2261,
111
+ "eval_samples_per_second": 1383.609,
112
+ "eval_steps_per_second": 8.984,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 3.17905226339867e-05,
118
+ "loss": 0.3393,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9207792207792208,
124
+ "eval_f1": 0.922710960511792,
125
+ "eval_loss": 1.8605962991714478,
126
+ "eval_matthews_correlation": 0.9197088857351889,
127
+ "eval_runtime": 2.2172,
128
+ "eval_samples_per_second": 1389.151,
129
+ "eval_steps_per_second": 9.02,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9233766233766234,
135
+ "eval_f1": 0.9254235342983648,
136
+ "eval_loss": 1.953273057937622,
137
+ "eval_matthews_correlation": 0.9223384276331019,
138
+ "eval_runtime": 2.1419,
139
+ "eval_samples_per_second": 1437.981,
140
+ "eval_steps_per_second": 9.338,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.9214285714285714,
146
+ "eval_f1": 0.9231886111183961,
147
+ "eval_loss": 1.9357961416244507,
148
+ "eval_matthews_correlation": 0.9203654618815811,
149
+ "eval_runtime": 2.0224,
150
+ "eval_samples_per_second": 1522.94,
151
+ "eval_steps_per_second": 9.889,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
+ "eval_accuracy": 0.924025974025974,
157
+ "eval_f1": 0.9255922212692556,
158
+ "eval_loss": 1.9956995248794556,
159
+ "eval_matthews_correlation": 0.922995468010013,
160
+ "eval_runtime": 2.3012,
161
+ "eval_samples_per_second": 1338.415,
162
+ "eval_steps_per_second": 8.691,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
+ "eval_accuracy": 0.925,
168
+ "eval_f1": 0.9265277453816252,
169
+ "eval_loss": 1.9824904203414917,
170
+ "eval_matthews_correlation": 0.923978861394841,
171
+ "eval_runtime": 2.0192,
172
+ "eval_samples_per_second": 1525.369,
173
+ "eval_steps_per_second": 9.905,
174
  "step": 1400
175
  },
176
  {
177
  "epoch": 34.09,
178
+ "learning_rate": 1.0875705111627028e-05,
179
+ "loss": 0.0269,
180
  "step": 1500
181
  },
182
  {
183
  "epoch": 34.09,
184
+ "eval_accuracy": 0.9243506493506494,
185
+ "eval_f1": 0.9259389201090135,
186
+ "eval_loss": 1.9924736022949219,
187
+ "eval_matthews_correlation": 0.9233194822300343,
188
+ "eval_runtime": 2.0795,
189
+ "eval_samples_per_second": 1481.122,
190
+ "eval_steps_per_second": 9.618,
191
  "step": 1500
192
  },
193
  {
194
  "epoch": 36.36,
195
+ "eval_accuracy": 0.924025974025974,
196
+ "eval_f1": 0.9255203853603882,
197
+ "eval_loss": 2.019881248474121,
198
+ "eval_matthews_correlation": 0.9229923674514793,
199
+ "eval_runtime": 2.0765,
200
+ "eval_samples_per_second": 1483.253,
201
+ "eval_steps_per_second": 9.632,
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 sha256:7326a47c8357d75e8dc38a799f439aecb77a23c1cf207d4544566ffb7195bf20
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292e7a8288c43b303abd31559aec885616dd7d87f70adfd70022f96ffad2e087
3
  size 2927
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e0e9c1bbfb0937072ea7f1cb5828117a85dc743eed73ea052bebc67cbd335b3
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d5f7a99bc696ec585141e36db427d8a12d947ee8831ba934c12839de8bf7da7
3
  size 440628841