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
b653d2a
·
1 Parent(s): 8984d14

Training in progress, step 200

Browse files
Files changed (22) hide show
  1. checkpoint-1200/optimizer.pt +1 -1
  2. checkpoint-1200/pytorch_model.bin +1 -1
  3. checkpoint-1200/scheduler.pt +1 -1
  4. checkpoint-1200/trainer_state.json +90 -90
  5. checkpoint-1200/training_args.bin +1 -1
  6. checkpoint-1400/optimizer.pt +1 -1
  7. checkpoint-1400/pytorch_model.bin +1 -1
  8. checkpoint-1400/scheduler.pt +1 -1
  9. checkpoint-1400/trainer_state.json +104 -104
  10. checkpoint-1400/training_args.bin +1 -1
  11. checkpoint-1600/optimizer.pt +1 -1
  12. checkpoint-1600/pytorch_model.bin +1 -1
  13. checkpoint-1600/scheduler.pt +1 -1
  14. checkpoint-1600/trainer_state.json +120 -120
  15. checkpoint-1600/training_args.bin +1 -1
  16. checkpoint-200/optimizer.pt +1 -1
  17. checkpoint-200/pytorch_model.bin +1 -1
  18. checkpoint-200/scheduler.pt +1 -1
  19. checkpoint-200/trainer_state.json +15 -15
  20. checkpoint-200/training_args.bin +1 -1
  21. pytorch_model.bin +1 -1
  22. training_args.bin +1 -1
checkpoint-1200/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2503df5e704b1c028452662d8e75b2cf29610d0244512df0f784ecf0a10c7f2
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18840be319a45b0a196f0c6f4897733d5e19e1273208fa9f261d7f19699048e7
3
  size 1762416361
checkpoint-1200/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c84b7155f7d1b5a7286ac3788bbac2a160dec03164e7faf50ab5212f4b13ec8
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a711d46d2183c435c55b1556adfe86d256619fbe59884d80b11743f1e2ee5cc0
3
  size 440628841
checkpoint-1200/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8b347ffd8f5d9a6480c5d32bf1be069295808be246f55374459d70196411f25
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd460740ad60939c76ba5d31d516e6480f7758d368d3ba6efa0932ef7f1c95cd
3
  size 623
checkpoint-1200/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.9233766233766234,
3
- "best_model_checkpoint": "mpnet-metric/checkpoint-600",
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": 0.8198051948051948,
13
- "eval_f1": 0.76240176245918,
14
- "eval_loss": 1.878959059715271,
15
- "eval_matthews_correlation": 0.8180944483519386,
16
- "eval_runtime": 2.0607,
17
- "eval_samples_per_second": 1494.66,
18
- "eval_steps_per_second": 9.706,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.8652597402597403,
24
- "eval_f1": 0.8272129361890441,
25
- "eval_loss": 1.6731730699539185,
26
- "eval_matthews_correlation": 0.8637234234282258,
27
- "eval_runtime": 2.1716,
28
- "eval_samples_per_second": 1418.311,
29
- "eval_steps_per_second": 9.21,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
- "eval_accuracy": 0.9003246753246753,
35
- "eval_f1": 0.8755621989291029,
36
- "eval_loss": 1.6091549396514893,
37
- "eval_matthews_correlation": 0.899015812565437,
38
- "eval_runtime": 2.0654,
39
- "eval_samples_per_second": 1491.212,
40
- "eval_steps_per_second": 9.683,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
- "eval_accuracy": 0.9087662337662338,
46
- "eval_f1": 0.894563182526518,
47
- "eval_loss": 1.5205509662628174,
48
- "eval_matthews_correlation": 0.9075435659504599,
49
- "eval_runtime": 2.053,
50
- "eval_samples_per_second": 1500.264,
51
- "eval_steps_per_second": 9.742,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
- "learning_rate": 1.9348543877109136e-05,
57
- "loss": 1.3037,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
- "eval_accuracy": 0.9191558441558442,
63
- "eval_f1": 0.9185807386974838,
64
- "eval_loss": 1.636989951133728,
65
- "eval_matthews_correlation": 0.9180857449763855,
66
- "eval_runtime": 2.0798,
67
- "eval_samples_per_second": 1480.929,
68
- "eval_steps_per_second": 9.616,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
- "eval_accuracy": 0.9233766233766234,
74
- "eval_f1": 0.9225758467101365,
75
- "eval_loss": 1.715301275253296,
76
- "eval_matthews_correlation": 0.9223247001565122,
77
- "eval_runtime": 2.1851,
78
- "eval_samples_per_second": 1409.54,
79
- "eval_steps_per_second": 9.153,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
- "eval_accuracy": 0.9188311688311688,
85
- "eval_f1": 0.9181454015472067,
86
- "eval_loss": 1.7380977869033813,
87
- "eval_matthews_correlation": 0.9177378362426065,
88
- "eval_runtime": 2.0898,
89
- "eval_samples_per_second": 1473.86,
90
- "eval_steps_per_second": 9.571,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
- "eval_accuracy": 0.922077922077922,
96
- "eval_f1": 0.9213266024410335,
97
- "eval_loss": 1.7136924266815186,
98
- "eval_matthews_correlation": 0.9210214177649633,
99
- "eval_runtime": 2.0331,
100
- "eval_samples_per_second": 1514.898,
101
- "eval_steps_per_second": 9.837,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
- "eval_accuracy": 0.9243506493506494,
107
- "eval_f1": 0.9233560747388974,
108
- "eval_loss": 1.7718300819396973,
109
- "eval_matthews_correlation": 0.9233224481248746,
110
- "eval_runtime": 2.0019,
111
- "eval_samples_per_second": 1538.537,
112
- "eval_steps_per_second": 9.99,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
- "learning_rate": 1.1670550275081701e-05,
118
- "loss": 0.3678,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
- "eval_accuracy": 0.9214285714285714,
124
- "eval_f1": 0.9210414656206705,
125
- "eval_loss": 1.7521275281906128,
126
- "eval_matthews_correlation": 0.9203625783219855,
127
- "eval_runtime": 2.1321,
128
- "eval_samples_per_second": 1444.563,
129
- "eval_steps_per_second": 9.38,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
- "eval_accuracy": 0.9207792207792208,
135
- "eval_f1": 0.9199856537842442,
136
- "eval_loss": 1.75361168384552,
137
- "eval_matthews_correlation": 0.9196940960723721,
138
- "eval_runtime": 2.5131,
139
- "eval_samples_per_second": 1225.572,
140
- "eval_steps_per_second": 7.958,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
- "eval_accuracy": 0.9214285714285714,
146
- "eval_f1": 0.920328851167179,
147
- "eval_loss": 1.7379529476165771,
148
- "eval_matthews_correlation": 0.9203629011139248,
149
- "eval_runtime": 2.2037,
150
- "eval_samples_per_second": 1397.646,
151
- "eval_steps_per_second": 9.076,
152
  "step": 1200
153
  }
154
  ],
 
1
  {
2
+ "best_metric": 0.925,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-800",
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": 0.8103896103896104,
13
+ "eval_f1": 0.7488131016912967,
14
+ "eval_loss": 1.6878883838653564,
15
+ "eval_matthews_correlation": 0.8087034964521417,
16
+ "eval_runtime": 2.2601,
17
+ "eval_samples_per_second": 1362.744,
18
+ "eval_steps_per_second": 8.849,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.8772727272727273,
24
+ "eval_f1": 0.8503346689297008,
25
+ "eval_loss": 1.4666811227798462,
26
+ "eval_matthews_correlation": 0.8757797849116651,
27
+ "eval_runtime": 2.0701,
28
+ "eval_samples_per_second": 1487.822,
29
+ "eval_steps_per_second": 9.661,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9077922077922078,
35
+ "eval_f1": 0.9026111528049606,
36
+ "eval_loss": 1.47733736038208,
37
+ "eval_matthews_correlation": 0.9065628663153121,
38
+ "eval_runtime": 2.0683,
39
+ "eval_samples_per_second": 1489.169,
40
+ "eval_steps_per_second": 9.67,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.9162337662337663,
46
+ "eval_f1": 0.9149731933438615,
47
+ "eval_loss": 1.5806630849838257,
48
+ "eval_matthews_correlation": 0.9151133338131785,
49
+ "eval_runtime": 2.1096,
50
+ "eval_samples_per_second": 1459.974,
51
+ "eval_steps_per_second": 9.48,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 9.700612919355273e-06,
57
+ "loss": 1.1826,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9201298701298701,
63
+ "eval_f1": 0.9195114987116463,
64
+ "eval_loss": 1.645480990409851,
65
+ "eval_matthews_correlation": 0.9190540004035348,
66
+ "eval_runtime": 2.5514,
67
+ "eval_samples_per_second": 1207.202,
68
+ "eval_steps_per_second": 7.839,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9211038961038961,
74
+ "eval_f1": 0.9204009966686943,
75
+ "eval_loss": 1.5331612825393677,
76
+ "eval_matthews_correlation": 0.9200402565541513,
77
+ "eval_runtime": 2.0109,
78
+ "eval_samples_per_second": 1531.655,
79
+ "eval_steps_per_second": 9.946,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9224025974025974,
85
+ "eval_f1": 0.9230420367101034,
86
+ "eval_loss": 1.6134278774261475,
87
+ "eval_matthews_correlation": 0.9213360758960103,
88
+ "eval_runtime": 2.1066,
89
+ "eval_samples_per_second": 1462.102,
90
+ "eval_steps_per_second": 9.494,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.925,
96
+ "eval_f1": 0.9244420833406021,
97
+ "eval_loss": 1.6904021501541138,
98
+ "eval_matthews_correlation": 0.9239885427404652,
99
+ "eval_runtime": 1.9981,
100
+ "eval_samples_per_second": 1541.438,
101
+ "eval_steps_per_second": 10.009,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9253246753246753,
107
+ "eval_f1": 0.9243864298534965,
108
+ "eval_loss": 1.7817680835723877,
109
+ "eval_matthews_correlation": 0.9243166155159858,
110
+ "eval_runtime": 2.0644,
111
+ "eval_samples_per_second": 1491.985,
112
+ "eval_steps_per_second": 9.688,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 5.8511633481825445e-06,
118
+ "loss": 0.3722,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.925,
124
+ "eval_f1": 0.9245670021110889,
125
+ "eval_loss": 1.8059184551239014,
126
+ "eval_matthews_correlation": 0.9239798584404243,
127
+ "eval_runtime": 2.1032,
128
+ "eval_samples_per_second": 1464.416,
129
+ "eval_steps_per_second": 9.509,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9214285714285714,
135
+ "eval_f1": 0.9217562444133767,
136
+ "eval_loss": 1.7946441173553467,
137
+ "eval_matthews_correlation": 0.9203488399438511,
138
+ "eval_runtime": 2.4435,
139
+ "eval_samples_per_second": 1260.47,
140
+ "eval_steps_per_second": 8.185,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.9237012987012987,
146
+ "eval_f1": 0.9236992112076952,
147
+ "eval_loss": 1.773333191871643,
148
+ "eval_matthews_correlation": 0.9226770290147883,
149
+ "eval_runtime": 2.0676,
150
+ "eval_samples_per_second": 1489.631,
151
+ "eval_steps_per_second": 9.673,
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 sha256:70f850d6b0f4f8e5ec881020197203fe9cc80ce1d764bf33155e3058edd643bc
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc32004323e6fc53489f8f72cd0ce51cb9fbd4ee2cb320a3a0fa073a8367c1c
3
  size 2927
checkpoint-1400/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8ecaccdf936317eaac9eb57d6f6ee25afbd63aded01f8b354640391bc6b8f79
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:102638262187ee6fca5829ab048c11281143de803f5062f64b0ccd3ab9b4e101
3
  size 1762416361
checkpoint-1400/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:159383a1fa9609eb3f068dcbe5a0c46f2352cba7ad9e1b1282e21dd42698fb7f
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c689688d3d09296790f821364c1da33b34346da36d128d28bdcb1a75e0b8bb61
3
  size 440628841
checkpoint-1400/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:059fef165009f726b74cd0cd771ee372c71238458e633b91ccca2bed3ea753bd
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0538aec02da84c3aa7d4938f57c476770959f482c61faf5b4beaad9b30f99105
3
  size 623
checkpoint-1400/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.9233766233766234,
3
- "best_model_checkpoint": "mpnet-metric/checkpoint-600",
4
  "epoch": 31.818181818181817,
5
  "global_step": 1400,
6
  "is_hyper_param_search": false,
@@ -9,168 +9,168 @@
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
- "eval_accuracy": 0.8198051948051948,
13
- "eval_f1": 0.76240176245918,
14
- "eval_loss": 1.878959059715271,
15
- "eval_matthews_correlation": 0.8180944483519386,
16
- "eval_runtime": 2.0607,
17
- "eval_samples_per_second": 1494.66,
18
- "eval_steps_per_second": 9.706,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.8652597402597403,
24
- "eval_f1": 0.8272129361890441,
25
- "eval_loss": 1.6731730699539185,
26
- "eval_matthews_correlation": 0.8637234234282258,
27
- "eval_runtime": 2.1716,
28
- "eval_samples_per_second": 1418.311,
29
- "eval_steps_per_second": 9.21,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
- "eval_accuracy": 0.9003246753246753,
35
- "eval_f1": 0.8755621989291029,
36
- "eval_loss": 1.6091549396514893,
37
- "eval_matthews_correlation": 0.899015812565437,
38
- "eval_runtime": 2.0654,
39
- "eval_samples_per_second": 1491.212,
40
- "eval_steps_per_second": 9.683,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
- "eval_accuracy": 0.9087662337662338,
46
- "eval_f1": 0.894563182526518,
47
- "eval_loss": 1.5205509662628174,
48
- "eval_matthews_correlation": 0.9075435659504599,
49
- "eval_runtime": 2.053,
50
- "eval_samples_per_second": 1500.264,
51
- "eval_steps_per_second": 9.742,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
- "learning_rate": 1.9348543877109136e-05,
57
- "loss": 1.3037,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
- "eval_accuracy": 0.9191558441558442,
63
- "eval_f1": 0.9185807386974838,
64
- "eval_loss": 1.636989951133728,
65
- "eval_matthews_correlation": 0.9180857449763855,
66
- "eval_runtime": 2.0798,
67
- "eval_samples_per_second": 1480.929,
68
- "eval_steps_per_second": 9.616,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
- "eval_accuracy": 0.9233766233766234,
74
- "eval_f1": 0.9225758467101365,
75
- "eval_loss": 1.715301275253296,
76
- "eval_matthews_correlation": 0.9223247001565122,
77
- "eval_runtime": 2.1851,
78
- "eval_samples_per_second": 1409.54,
79
- "eval_steps_per_second": 9.153,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
- "eval_accuracy": 0.9188311688311688,
85
- "eval_f1": 0.9181454015472067,
86
- "eval_loss": 1.7380977869033813,
87
- "eval_matthews_correlation": 0.9177378362426065,
88
- "eval_runtime": 2.0898,
89
- "eval_samples_per_second": 1473.86,
90
- "eval_steps_per_second": 9.571,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
- "eval_accuracy": 0.922077922077922,
96
- "eval_f1": 0.9213266024410335,
97
- "eval_loss": 1.7136924266815186,
98
- "eval_matthews_correlation": 0.9210214177649633,
99
- "eval_runtime": 2.0331,
100
- "eval_samples_per_second": 1514.898,
101
- "eval_steps_per_second": 9.837,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
- "eval_accuracy": 0.9243506493506494,
107
- "eval_f1": 0.9233560747388974,
108
- "eval_loss": 1.7718300819396973,
109
- "eval_matthews_correlation": 0.9233224481248746,
110
- "eval_runtime": 2.0019,
111
- "eval_samples_per_second": 1538.537,
112
- "eval_steps_per_second": 9.99,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
- "learning_rate": 1.1670550275081701e-05,
118
- "loss": 0.3678,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
- "eval_accuracy": 0.9214285714285714,
124
- "eval_f1": 0.9210414656206705,
125
- "eval_loss": 1.7521275281906128,
126
- "eval_matthews_correlation": 0.9203625783219855,
127
- "eval_runtime": 2.1321,
128
- "eval_samples_per_second": 1444.563,
129
- "eval_steps_per_second": 9.38,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
- "eval_accuracy": 0.9207792207792208,
135
- "eval_f1": 0.9199856537842442,
136
- "eval_loss": 1.75361168384552,
137
- "eval_matthews_correlation": 0.9196940960723721,
138
- "eval_runtime": 2.5131,
139
- "eval_samples_per_second": 1225.572,
140
- "eval_steps_per_second": 7.958,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
- "eval_accuracy": 0.9214285714285714,
146
- "eval_f1": 0.920328851167179,
147
- "eval_loss": 1.7379529476165771,
148
- "eval_matthews_correlation": 0.9203629011139248,
149
- "eval_runtime": 2.2037,
150
- "eval_samples_per_second": 1397.646,
151
- "eval_steps_per_second": 9.076,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
- "eval_accuracy": 0.9201298701298701,
157
- "eval_f1": 0.9189229848832124,
158
- "eval_loss": 1.7563822269439697,
159
- "eval_matthews_correlation": 0.9190434597349663,
160
- "eval_runtime": 2.076,
161
- "eval_samples_per_second": 1483.587,
162
- "eval_steps_per_second": 9.634,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
- "eval_accuracy": 0.9217532467532468,
168
- "eval_f1": 0.9212461135800994,
169
- "eval_loss": 1.8037470579147339,
170
- "eval_matthews_correlation": 0.9206903125042072,
171
- "eval_runtime": 2.0623,
172
- "eval_samples_per_second": 1493.477,
173
- "eval_steps_per_second": 9.698,
174
  "step": 1400
175
  }
176
  ],
 
1
  {
2
+ "best_metric": 0.925974025974026,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-1400",
4
  "epoch": 31.818181818181817,
5
  "global_step": 1400,
6
  "is_hyper_param_search": false,
 
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
+ "eval_accuracy": 0.8103896103896104,
13
+ "eval_f1": 0.7488131016912967,
14
+ "eval_loss": 1.6878883838653564,
15
+ "eval_matthews_correlation": 0.8087034964521417,
16
+ "eval_runtime": 2.2601,
17
+ "eval_samples_per_second": 1362.744,
18
+ "eval_steps_per_second": 8.849,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.8772727272727273,
24
+ "eval_f1": 0.8503346689297008,
25
+ "eval_loss": 1.4666811227798462,
26
+ "eval_matthews_correlation": 0.8757797849116651,
27
+ "eval_runtime": 2.0701,
28
+ "eval_samples_per_second": 1487.822,
29
+ "eval_steps_per_second": 9.661,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9077922077922078,
35
+ "eval_f1": 0.9026111528049606,
36
+ "eval_loss": 1.47733736038208,
37
+ "eval_matthews_correlation": 0.9065628663153121,
38
+ "eval_runtime": 2.0683,
39
+ "eval_samples_per_second": 1489.169,
40
+ "eval_steps_per_second": 9.67,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.9162337662337663,
46
+ "eval_f1": 0.9149731933438615,
47
+ "eval_loss": 1.5806630849838257,
48
+ "eval_matthews_correlation": 0.9151133338131785,
49
+ "eval_runtime": 2.1096,
50
+ "eval_samples_per_second": 1459.974,
51
+ "eval_steps_per_second": 9.48,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 9.700612919355273e-06,
57
+ "loss": 1.1826,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9201298701298701,
63
+ "eval_f1": 0.9195114987116463,
64
+ "eval_loss": 1.645480990409851,
65
+ "eval_matthews_correlation": 0.9190540004035348,
66
+ "eval_runtime": 2.5514,
67
+ "eval_samples_per_second": 1207.202,
68
+ "eval_steps_per_second": 7.839,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9211038961038961,
74
+ "eval_f1": 0.9204009966686943,
75
+ "eval_loss": 1.5331612825393677,
76
+ "eval_matthews_correlation": 0.9200402565541513,
77
+ "eval_runtime": 2.0109,
78
+ "eval_samples_per_second": 1531.655,
79
+ "eval_steps_per_second": 9.946,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9224025974025974,
85
+ "eval_f1": 0.9230420367101034,
86
+ "eval_loss": 1.6134278774261475,
87
+ "eval_matthews_correlation": 0.9213360758960103,
88
+ "eval_runtime": 2.1066,
89
+ "eval_samples_per_second": 1462.102,
90
+ "eval_steps_per_second": 9.494,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.925,
96
+ "eval_f1": 0.9244420833406021,
97
+ "eval_loss": 1.6904021501541138,
98
+ "eval_matthews_correlation": 0.9239885427404652,
99
+ "eval_runtime": 1.9981,
100
+ "eval_samples_per_second": 1541.438,
101
+ "eval_steps_per_second": 10.009,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9253246753246753,
107
+ "eval_f1": 0.9243864298534965,
108
+ "eval_loss": 1.7817680835723877,
109
+ "eval_matthews_correlation": 0.9243166155159858,
110
+ "eval_runtime": 2.0644,
111
+ "eval_samples_per_second": 1491.985,
112
+ "eval_steps_per_second": 9.688,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 5.8511633481825445e-06,
118
+ "loss": 0.3722,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.925,
124
+ "eval_f1": 0.9245670021110889,
125
+ "eval_loss": 1.8059184551239014,
126
+ "eval_matthews_correlation": 0.9239798584404243,
127
+ "eval_runtime": 2.1032,
128
+ "eval_samples_per_second": 1464.416,
129
+ "eval_steps_per_second": 9.509,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9214285714285714,
135
+ "eval_f1": 0.9217562444133767,
136
+ "eval_loss": 1.7946441173553467,
137
+ "eval_matthews_correlation": 0.9203488399438511,
138
+ "eval_runtime": 2.4435,
139
+ "eval_samples_per_second": 1260.47,
140
+ "eval_steps_per_second": 8.185,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.9237012987012987,
146
+ "eval_f1": 0.9236992112076952,
147
+ "eval_loss": 1.773333191871643,
148
+ "eval_matthews_correlation": 0.9226770290147883,
149
+ "eval_runtime": 2.0676,
150
+ "eval_samples_per_second": 1489.631,
151
+ "eval_steps_per_second": 9.673,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
+ "eval_accuracy": 0.9285714285714286,
157
+ "eval_f1": 0.928290096163112,
158
+ "eval_loss": 1.7617428302764893,
159
+ "eval_matthews_correlation": 0.9275839406889252,
160
+ "eval_runtime": 2.1579,
161
+ "eval_samples_per_second": 1427.286,
162
+ "eval_steps_per_second": 9.268,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
+ "eval_accuracy": 0.925974025974026,
168
+ "eval_f1": 0.9255025304259464,
169
+ "eval_loss": 1.8080366849899292,
170
+ "eval_matthews_correlation": 0.9249557507092587,
171
+ "eval_runtime": 2.054,
172
+ "eval_samples_per_second": 1499.516,
173
+ "eval_steps_per_second": 9.737,
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 sha256:70f850d6b0f4f8e5ec881020197203fe9cc80ce1d764bf33155e3058edd643bc
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc32004323e6fc53489f8f72cd0ce51cb9fbd4ee2cb320a3a0fa073a8367c1c
3
  size 2927
checkpoint-1600/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af2617d55bde54d229ef9e2062e97d29e0e78a8d9d73afbdca0e4f2a3ab4339c
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f64f25470d2f7ce3d77aaa34ce94596391f8d355395989f79c6589a82629282
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:a710f8e374e844e4c1e3013006ff49d7203acb86f538d2daa7cc7bd22912c6bc
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d1889af785642a74d9e9e0ede0c4adaca2c5d6c5871d720438fd976dc5a8a58
3
  size 440628841
checkpoint-1600/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0af63180e0820476857211e8f665b446914c5cd5e3cc6ab8126d2bd8592b60ba
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ba4ac3c9e3cf29a8f7e5168c1b151ef756d7a1315d704f39b020aecf944f16
3
  size 623
checkpoint-1600/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.9233766233766234,
3
- "best_model_checkpoint": "mpnet-metric/checkpoint-600",
4
  "epoch": 36.36363636363637,
5
  "global_step": 1600,
6
  "is_hyper_param_search": false,
@@ -9,196 +9,196 @@
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
- "eval_accuracy": 0.8198051948051948,
13
- "eval_f1": 0.76240176245918,
14
- "eval_loss": 1.878959059715271,
15
- "eval_matthews_correlation": 0.8180944483519386,
16
- "eval_runtime": 2.0607,
17
- "eval_samples_per_second": 1494.66,
18
- "eval_steps_per_second": 9.706,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.8652597402597403,
24
- "eval_f1": 0.8272129361890441,
25
- "eval_loss": 1.6731730699539185,
26
- "eval_matthews_correlation": 0.8637234234282258,
27
- "eval_runtime": 2.1716,
28
- "eval_samples_per_second": 1418.311,
29
- "eval_steps_per_second": 9.21,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
- "eval_accuracy": 0.9003246753246753,
35
- "eval_f1": 0.8755621989291029,
36
- "eval_loss": 1.6091549396514893,
37
- "eval_matthews_correlation": 0.899015812565437,
38
- "eval_runtime": 2.0654,
39
- "eval_samples_per_second": 1491.212,
40
- "eval_steps_per_second": 9.683,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
- "eval_accuracy": 0.9087662337662338,
46
- "eval_f1": 0.894563182526518,
47
- "eval_loss": 1.5205509662628174,
48
- "eval_matthews_correlation": 0.9075435659504599,
49
- "eval_runtime": 2.053,
50
- "eval_samples_per_second": 1500.264,
51
- "eval_steps_per_second": 9.742,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
- "learning_rate": 1.9348543877109136e-05,
57
- "loss": 1.3037,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
- "eval_accuracy": 0.9191558441558442,
63
- "eval_f1": 0.9185807386974838,
64
- "eval_loss": 1.636989951133728,
65
- "eval_matthews_correlation": 0.9180857449763855,
66
- "eval_runtime": 2.0798,
67
- "eval_samples_per_second": 1480.929,
68
- "eval_steps_per_second": 9.616,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
- "eval_accuracy": 0.9233766233766234,
74
- "eval_f1": 0.9225758467101365,
75
- "eval_loss": 1.715301275253296,
76
- "eval_matthews_correlation": 0.9223247001565122,
77
- "eval_runtime": 2.1851,
78
- "eval_samples_per_second": 1409.54,
79
- "eval_steps_per_second": 9.153,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
- "eval_accuracy": 0.9188311688311688,
85
- "eval_f1": 0.9181454015472067,
86
- "eval_loss": 1.7380977869033813,
87
- "eval_matthews_correlation": 0.9177378362426065,
88
- "eval_runtime": 2.0898,
89
- "eval_samples_per_second": 1473.86,
90
- "eval_steps_per_second": 9.571,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
- "eval_accuracy": 0.922077922077922,
96
- "eval_f1": 0.9213266024410335,
97
- "eval_loss": 1.7136924266815186,
98
- "eval_matthews_correlation": 0.9210214177649633,
99
- "eval_runtime": 2.0331,
100
- "eval_samples_per_second": 1514.898,
101
- "eval_steps_per_second": 9.837,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
- "eval_accuracy": 0.9243506493506494,
107
- "eval_f1": 0.9233560747388974,
108
- "eval_loss": 1.7718300819396973,
109
- "eval_matthews_correlation": 0.9233224481248746,
110
- "eval_runtime": 2.0019,
111
- "eval_samples_per_second": 1538.537,
112
- "eval_steps_per_second": 9.99,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
- "learning_rate": 1.1670550275081701e-05,
118
- "loss": 0.3678,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
- "eval_accuracy": 0.9214285714285714,
124
- "eval_f1": 0.9210414656206705,
125
- "eval_loss": 1.7521275281906128,
126
- "eval_matthews_correlation": 0.9203625783219855,
127
- "eval_runtime": 2.1321,
128
- "eval_samples_per_second": 1444.563,
129
- "eval_steps_per_second": 9.38,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
- "eval_accuracy": 0.9207792207792208,
135
- "eval_f1": 0.9199856537842442,
136
- "eval_loss": 1.75361168384552,
137
- "eval_matthews_correlation": 0.9196940960723721,
138
- "eval_runtime": 2.5131,
139
- "eval_samples_per_second": 1225.572,
140
- "eval_steps_per_second": 7.958,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
- "eval_accuracy": 0.9214285714285714,
146
- "eval_f1": 0.920328851167179,
147
- "eval_loss": 1.7379529476165771,
148
- "eval_matthews_correlation": 0.9203629011139248,
149
- "eval_runtime": 2.2037,
150
- "eval_samples_per_second": 1397.646,
151
- "eval_steps_per_second": 9.076,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
- "eval_accuracy": 0.9201298701298701,
157
- "eval_f1": 0.9189229848832124,
158
- "eval_loss": 1.7563822269439697,
159
- "eval_matthews_correlation": 0.9190434597349663,
160
- "eval_runtime": 2.076,
161
- "eval_samples_per_second": 1483.587,
162
- "eval_steps_per_second": 9.634,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
- "eval_accuracy": 0.9217532467532468,
168
- "eval_f1": 0.9212461135800994,
169
- "eval_loss": 1.8037470579147339,
170
- "eval_matthews_correlation": 0.9206903125042072,
171
- "eval_runtime": 2.0623,
172
- "eval_samples_per_second": 1493.477,
173
- "eval_steps_per_second": 9.698,
174
  "step": 1400
175
  },
176
  {
177
  "epoch": 34.09,
178
- "learning_rate": 3.992556673054266e-06,
179
- "loss": 0.0576,
180
  "step": 1500
181
  },
182
  {
183
  "epoch": 34.09,
184
- "eval_accuracy": 0.9211038961038961,
185
- "eval_f1": 0.9200527431590596,
186
- "eval_loss": 1.7903398275375366,
187
- "eval_matthews_correlation": 0.920031844073991,
188
- "eval_runtime": 2.0784,
189
- "eval_samples_per_second": 1481.923,
190
- "eval_steps_per_second": 9.623,
191
  "step": 1500
192
  },
193
  {
194
  "epoch": 36.36,
195
- "eval_accuracy": 0.9207792207792208,
196
- "eval_f1": 0.9198970507643909,
197
- "eval_loss": 1.7742425203323364,
198
- "eval_matthews_correlation": 0.9197024400503055,
199
- "eval_runtime": 2.0696,
200
- "eval_samples_per_second": 1488.219,
201
- "eval_steps_per_second": 9.664,
202
  "step": 1600
203
  }
204
  ],
 
1
  {
2
+ "best_metric": 0.9262987012987013,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-1600",
4
  "epoch": 36.36363636363637,
5
  "global_step": 1600,
6
  "is_hyper_param_search": false,
 
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
+ "eval_accuracy": 0.8103896103896104,
13
+ "eval_f1": 0.7488131016912967,
14
+ "eval_loss": 1.6878883838653564,
15
+ "eval_matthews_correlation": 0.8087034964521417,
16
+ "eval_runtime": 2.2601,
17
+ "eval_samples_per_second": 1362.744,
18
+ "eval_steps_per_second": 8.849,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.8772727272727273,
24
+ "eval_f1": 0.8503346689297008,
25
+ "eval_loss": 1.4666811227798462,
26
+ "eval_matthews_correlation": 0.8757797849116651,
27
+ "eval_runtime": 2.0701,
28
+ "eval_samples_per_second": 1487.822,
29
+ "eval_steps_per_second": 9.661,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9077922077922078,
35
+ "eval_f1": 0.9026111528049606,
36
+ "eval_loss": 1.47733736038208,
37
+ "eval_matthews_correlation": 0.9065628663153121,
38
+ "eval_runtime": 2.0683,
39
+ "eval_samples_per_second": 1489.169,
40
+ "eval_steps_per_second": 9.67,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.9162337662337663,
46
+ "eval_f1": 0.9149731933438615,
47
+ "eval_loss": 1.5806630849838257,
48
+ "eval_matthews_correlation": 0.9151133338131785,
49
+ "eval_runtime": 2.1096,
50
+ "eval_samples_per_second": 1459.974,
51
+ "eval_steps_per_second": 9.48,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 9.700612919355273e-06,
57
+ "loss": 1.1826,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9201298701298701,
63
+ "eval_f1": 0.9195114987116463,
64
+ "eval_loss": 1.645480990409851,
65
+ "eval_matthews_correlation": 0.9190540004035348,
66
+ "eval_runtime": 2.5514,
67
+ "eval_samples_per_second": 1207.202,
68
+ "eval_steps_per_second": 7.839,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9211038961038961,
74
+ "eval_f1": 0.9204009966686943,
75
+ "eval_loss": 1.5331612825393677,
76
+ "eval_matthews_correlation": 0.9200402565541513,
77
+ "eval_runtime": 2.0109,
78
+ "eval_samples_per_second": 1531.655,
79
+ "eval_steps_per_second": 9.946,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9224025974025974,
85
+ "eval_f1": 0.9230420367101034,
86
+ "eval_loss": 1.6134278774261475,
87
+ "eval_matthews_correlation": 0.9213360758960103,
88
+ "eval_runtime": 2.1066,
89
+ "eval_samples_per_second": 1462.102,
90
+ "eval_steps_per_second": 9.494,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.925,
96
+ "eval_f1": 0.9244420833406021,
97
+ "eval_loss": 1.6904021501541138,
98
+ "eval_matthews_correlation": 0.9239885427404652,
99
+ "eval_runtime": 1.9981,
100
+ "eval_samples_per_second": 1541.438,
101
+ "eval_steps_per_second": 10.009,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9253246753246753,
107
+ "eval_f1": 0.9243864298534965,
108
+ "eval_loss": 1.7817680835723877,
109
+ "eval_matthews_correlation": 0.9243166155159858,
110
+ "eval_runtime": 2.0644,
111
+ "eval_samples_per_second": 1491.985,
112
+ "eval_steps_per_second": 9.688,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 5.8511633481825445e-06,
118
+ "loss": 0.3722,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.925,
124
+ "eval_f1": 0.9245670021110889,
125
+ "eval_loss": 1.8059184551239014,
126
+ "eval_matthews_correlation": 0.9239798584404243,
127
+ "eval_runtime": 2.1032,
128
+ "eval_samples_per_second": 1464.416,
129
+ "eval_steps_per_second": 9.509,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9214285714285714,
135
+ "eval_f1": 0.9217562444133767,
136
+ "eval_loss": 1.7946441173553467,
137
+ "eval_matthews_correlation": 0.9203488399438511,
138
+ "eval_runtime": 2.4435,
139
+ "eval_samples_per_second": 1260.47,
140
+ "eval_steps_per_second": 8.185,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.9237012987012987,
146
+ "eval_f1": 0.9236992112076952,
147
+ "eval_loss": 1.773333191871643,
148
+ "eval_matthews_correlation": 0.9226770290147883,
149
+ "eval_runtime": 2.0676,
150
+ "eval_samples_per_second": 1489.631,
151
+ "eval_steps_per_second": 9.673,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
+ "eval_accuracy": 0.9285714285714286,
157
+ "eval_f1": 0.928290096163112,
158
+ "eval_loss": 1.7617428302764893,
159
+ "eval_matthews_correlation": 0.9275839406889252,
160
+ "eval_runtime": 2.1579,
161
+ "eval_samples_per_second": 1427.286,
162
+ "eval_steps_per_second": 9.268,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
+ "eval_accuracy": 0.925974025974026,
168
+ "eval_f1": 0.9255025304259464,
169
+ "eval_loss": 1.8080366849899292,
170
+ "eval_matthews_correlation": 0.9249557507092587,
171
+ "eval_runtime": 2.054,
172
+ "eval_samples_per_second": 1499.516,
173
+ "eval_steps_per_second": 9.737,
174
  "step": 1400
175
  },
176
  {
177
  "epoch": 34.09,
178
+ "learning_rate": 2.001713777009818e-06,
179
+ "loss": 0.0524,
180
  "step": 1500
181
  },
182
  {
183
  "epoch": 34.09,
184
+ "eval_accuracy": 0.9279220779220779,
185
+ "eval_f1": 0.9276820977231893,
186
+ "eval_loss": 1.8100144863128662,
187
+ "eval_matthews_correlation": 0.9269316082017499,
188
+ "eval_runtime": 2.1316,
189
+ "eval_samples_per_second": 1444.924,
190
+ "eval_steps_per_second": 9.383,
191
  "step": 1500
192
  },
193
  {
194
  "epoch": 36.36,
195
+ "eval_accuracy": 0.9262987012987013,
196
+ "eval_f1": 0.9256839752001434,
197
+ "eval_loss": 1.8182265758514404,
198
+ "eval_matthews_correlation": 0.9252867107880702,
199
+ "eval_runtime": 2.1694,
200
+ "eval_samples_per_second": 1419.754,
201
+ "eval_steps_per_second": 9.219,
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 sha256:70f850d6b0f4f8e5ec881020197203fe9cc80ce1d764bf33155e3058edd643bc
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc32004323e6fc53489f8f72cd0ce51cb9fbd4ee2cb320a3a0fa073a8367c1c
3
  size 2927
checkpoint-200/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ddddd828979dedde79e8ccd7250461866c2dcd56638aecbcbd1d902cb234949
3
  size 1762415977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90632ef6d1df9d4cd54e2118699968c17e49784bccd7996ebb4a7a4aea8fa878
3
  size 1762415977
checkpoint-200/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d31ef4d8b0a696701f4bc19e445332aa079d08ef5e3277911b9f8f9c6d7333d1
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e75b9d5bfe8e7586f36f9aabd1d9f324bad23b94601baf108c2ef06b9da2900a
3
  size 440628841
checkpoint-200/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bb035c9b8ae19c652d47c08f775fe10a2c3be337d3559bdc888b2f30276b623
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6157b5a7c7fc27e491105f7ee95042e51ec0e2b573631f4b3ed6997ca8c41bc6
3
  size 623
checkpoint-200/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.8772727272727273,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-200",
4
  "epoch": 4.545454545454545,
5
  "global_step": 200,
@@ -9,24 +9,24 @@
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
- "eval_accuracy": 0.8103896103896104,
13
- "eval_f1": 0.7488131016912967,
14
- "eval_loss": 1.6878883838653564,
15
- "eval_matthews_correlation": 0.8087034964521417,
16
- "eval_runtime": 2.2601,
17
- "eval_samples_per_second": 1362.744,
18
- "eval_steps_per_second": 8.849,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.8772727272727273,
24
- "eval_f1": 0.8503346689297008,
25
- "eval_loss": 1.4666811227798462,
26
- "eval_matthews_correlation": 0.8757797849116651,
27
- "eval_runtime": 2.0701,
28
- "eval_samples_per_second": 1487.822,
29
- "eval_steps_per_second": 9.661,
30
  "step": 200
31
  }
32
  ],
 
1
  {
2
+ "best_metric": 0.9094155844155845,
3
  "best_model_checkpoint": "mpnet-metric/checkpoint-200",
4
  "epoch": 4.545454545454545,
5
  "global_step": 200,
 
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
+ "eval_accuracy": 0.8285714285714286,
13
+ "eval_f1": 0.7800843744647471,
14
+ "eval_loss": 1.6140592098236084,
15
+ "eval_matthews_correlation": 0.8269571164269343,
16
+ "eval_runtime": 2.0188,
17
+ "eval_samples_per_second": 1525.674,
18
+ "eval_steps_per_second": 9.907,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.9094155844155845,
24
+ "eval_f1": 0.8978030339445856,
25
+ "eval_loss": 1.552977442741394,
26
+ "eval_matthews_correlation": 0.9082387290517906,
27
+ "eval_runtime": 2.2366,
28
+ "eval_samples_per_second": 1377.112,
29
+ "eval_steps_per_second": 8.942,
30
  "step": 200
31
  }
32
  ],
checkpoint-200/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddc32004323e6fc53489f8f72cd0ce51cb9fbd4ee2cb320a3a0fa073a8367c1c
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2492ed98032989419950d81346e59825e713d1c1a99c9ee8053db8a3c33d5e8b
3
  size 2927
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1f06cbdc5e7db57a23fe86621a14c53957c36b87d4c9f53f735ef7742595b2c
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e75b9d5bfe8e7586f36f9aabd1d9f324bad23b94601baf108c2ef06b9da2900a
3
  size 440628841
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddc32004323e6fc53489f8f72cd0ce51cb9fbd4ee2cb320a3a0fa073a8367c1c
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2492ed98032989419950d81346e59825e713d1c1a99c9ee8053db8a3c33d5e8b
3
  size 2927