cbrew475 commited on
Commit
46585eb
·
1 Parent(s): b38d007

Training in progress, step 200

Browse files
checkpoint-1200/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27d734e302f5b5f9c1f09ff36c27be8f073070d696648576ec7a35074476483d
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdfb14de85c5a258222b317f882a80b663ca21db65e33292ccec29d015530a52
3
  size 1762416361
checkpoint-1200/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0acbbcd43df1437a25d43f262d8f2a4b70c2fe7566df4032218b961fe5176b92
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e819bb724d3f1dbffdfc7ff2bc1757fa81edc40e914e82fc310574bef5a378b8
3
  size 440628841
checkpoint-1200/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56f8668ac5cb0d3bdef620251796baed07c402a180ed37692597bfc1ff669afe
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc218f9cd629f09ca27567dea3c1e1f10201cc0fa616e70f2ba55db610c4356f
3
  size 623
checkpoint-1200/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.9266233766233766,
3
- "best_model_checkpoint": "mpnet-metric/checkpoint-1200",
4
  "epoch": 27.272727272727273,
5
  "global_step": 1200,
6
  "is_hyper_param_search": false,
@@ -9,146 +9,146 @@
9
  "log_history": [
10
  {
11
  "epoch": 2.27,
12
- "eval_accuracy": 0.823051948051948,
13
- "eval_f1": 0.7694886084528045,
14
- "eval_loss": 1.8196498155593872,
15
- "eval_matthews_correlation": 0.82152846992121,
16
- "eval_runtime": 2.0824,
17
- "eval_samples_per_second": 1479.063,
18
- "eval_steps_per_second": 9.604,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.8717532467532467,
24
- "eval_f1": 0.8385414959301972,
25
- "eval_loss": 1.5393933057785034,
26
- "eval_matthews_correlation": 0.8702231962356954,
27
- "eval_runtime": 2.2041,
28
- "eval_samples_per_second": 1397.426,
29
- "eval_steps_per_second": 9.074,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
- "eval_accuracy": 0.8918831168831168,
35
- "eval_f1": 0.8674754241961948,
36
- "eval_loss": 1.6252003908157349,
37
- "eval_matthews_correlation": 0.8905305382750595,
38
- "eval_runtime": 2.3515,
39
- "eval_samples_per_second": 1309.779,
40
- "eval_steps_per_second": 8.505,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
- "eval_accuracy": 0.9081168831168831,
46
- "eval_f1": 0.8936386572619883,
47
- "eval_loss": 1.4800223112106323,
48
- "eval_matthews_correlation": 0.9068978212395917,
49
- "eval_runtime": 2.1261,
50
- "eval_samples_per_second": 1448.662,
51
- "eval_steps_per_second": 9.407,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
- "learning_rate": 2.72715184015364e-05,
57
- "loss": 1.2024,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
- "eval_accuracy": 0.9227272727272727,
63
- "eval_f1": 0.9191317240240598,
64
- "eval_loss": 1.5631015300750732,
65
- "eval_matthews_correlation": 0.921668408209661,
66
- "eval_runtime": 2.1128,
67
- "eval_samples_per_second": 1457.81,
68
- "eval_steps_per_second": 9.466,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
- "eval_accuracy": 0.924025974025974,
74
- "eval_f1": 0.9250159536040414,
75
- "eval_loss": 1.6559977531433105,
76
- "eval_matthews_correlation": 0.9229932303823994,
77
- "eval_runtime": 2.1526,
78
- "eval_samples_per_second": 1430.816,
79
- "eval_steps_per_second": 9.291,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
- "eval_accuracy": 0.9188311688311688,
85
- "eval_f1": 0.9178066235572834,
86
- "eval_loss": 1.6833025217056274,
87
- "eval_matthews_correlation": 0.9177304556222637,
88
- "eval_runtime": 2.2196,
89
- "eval_samples_per_second": 1387.667,
90
- "eval_steps_per_second": 9.011,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
- "eval_accuracy": 0.9217532467532468,
96
- "eval_f1": 0.921664147942375,
97
- "eval_loss": 1.683775782585144,
98
- "eval_matthews_correlation": 0.9206740366287324,
99
- "eval_runtime": 2.1736,
100
- "eval_samples_per_second": 1416.993,
101
- "eval_steps_per_second": 9.201,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
- "eval_accuracy": 0.9295454545454546,
107
- "eval_f1": 0.9281614931192158,
108
- "eval_loss": 1.6790761947631836,
109
- "eval_matthews_correlation": 0.9285814101191024,
110
- "eval_runtime": 2.0387,
111
- "eval_samples_per_second": 1510.74,
112
- "eval_steps_per_second": 9.81,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
- "learning_rate": 1.6449487289815606e-05,
118
- "loss": 0.3425,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
- "eval_accuracy": 0.9253246753246753,
124
- "eval_f1": 0.9248272869409627,
125
- "eval_loss": 1.706620454788208,
126
- "eval_matthews_correlation": 0.924306415853766,
127
- "eval_runtime": 2.1612,
128
- "eval_samples_per_second": 1425.121,
129
- "eval_steps_per_second": 9.254,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
- "eval_accuracy": 0.9262987012987013,
135
- "eval_f1": 0.9256841156799166,
136
- "eval_loss": 1.7070327997207642,
137
- "eval_matthews_correlation": 0.9252825858586532,
138
- "eval_runtime": 2.4454,
139
- "eval_samples_per_second": 1259.521,
140
- "eval_steps_per_second": 8.179,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
- "eval_accuracy": 0.9266233766233766,
146
- "eval_f1": 0.9262828157785664,
147
- "eval_loss": 1.7237951755523682,
148
- "eval_matthews_correlation": 0.9256157384883016,
149
- "eval_runtime": 2.1429,
150
- "eval_samples_per_second": 1437.307,
151
- "eval_steps_per_second": 9.333,
152
  "step": 1200
153
  }
154
  ],
 
1
  {
2
+ "best_metric": 0.9256493506493506,
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": 0.8168831168831169,
13
+ "eval_f1": 0.7526160112915868,
14
+ "eval_loss": 1.6600779294967651,
15
+ "eval_matthews_correlation": 0.8152410229901306,
16
+ "eval_runtime": 2.4316,
17
+ "eval_samples_per_second": 1266.672,
18
+ "eval_steps_per_second": 8.225,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.897077922077922,
24
+ "eval_f1": 0.8856257075703299,
25
+ "eval_loss": 1.4927222728729248,
26
+ "eval_matthews_correlation": 0.8957943237010111,
27
+ "eval_runtime": 2.2227,
28
+ "eval_samples_per_second": 1385.731,
29
+ "eval_steps_per_second": 8.998,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9201298701298701,
35
+ "eval_f1": 0.9205225631693909,
36
+ "eval_loss": 1.5566294193267822,
37
+ "eval_matthews_correlation": 0.9190320812070084,
38
+ "eval_runtime": 2.1905,
39
+ "eval_samples_per_second": 1406.054,
40
+ "eval_steps_per_second": 9.13,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.912012987012987,
46
+ "eval_f1": 0.9120652244039835,
47
+ "eval_loss": 1.5064270496368408,
48
+ "eval_matthews_correlation": 0.910845237954562,
49
+ "eval_runtime": 2.0804,
50
+ "eval_samples_per_second": 1480.451,
51
+ "eval_steps_per_second": 9.613,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 7.143981790504036e-05,
57
+ "loss": 1.1713,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9214285714285714,
63
+ "eval_f1": 0.9209415679460552,
64
+ "eval_loss": 1.6870453357696533,
65
+ "eval_matthews_correlation": 0.920369186542805,
66
+ "eval_runtime": 2.1662,
67
+ "eval_samples_per_second": 1421.817,
68
+ "eval_steps_per_second": 9.233,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9198051948051948,
74
+ "eval_f1": 0.9197304127364558,
75
+ "eval_loss": 1.6187154054641724,
76
+ "eval_matthews_correlation": 0.918700976641645,
77
+ "eval_runtime": 2.0584,
78
+ "eval_samples_per_second": 1496.322,
79
+ "eval_steps_per_second": 9.716,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9159090909090909,
85
+ "eval_f1": 0.9164948773151114,
86
+ "eval_loss": 1.6880903244018555,
87
+ "eval_matthews_correlation": 0.9148059546508341,
88
+ "eval_runtime": 2.255,
89
+ "eval_samples_per_second": 1365.875,
90
+ "eval_steps_per_second": 8.869,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.9172077922077922,
96
+ "eval_f1": 0.9171466545500319,
97
+ "eval_loss": 1.6939719915390015,
98
+ "eval_matthews_correlation": 0.9160846990725676,
99
+ "eval_runtime": 2.1751,
100
+ "eval_samples_per_second": 1416.047,
101
+ "eval_steps_per_second": 9.195,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9237012987012987,
107
+ "eval_f1": 0.9228068483209093,
108
+ "eval_loss": 1.827225685119629,
109
+ "eval_matthews_correlation": 0.9226697076696465,
110
+ "eval_runtime": 2.0546,
111
+ "eval_samples_per_second": 1499.088,
112
+ "eval_steps_per_second": 9.734,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 4.309068381573863e-05,
118
+ "loss": 0.3851,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9256493506493506,
124
+ "eval_f1": 0.924610487019518,
125
+ "eval_loss": 1.752126932144165,
126
+ "eval_matthews_correlation": 0.9246248223527813,
127
+ "eval_runtime": 2.1963,
128
+ "eval_samples_per_second": 1402.379,
129
+ "eval_steps_per_second": 9.106,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9227272727272727,
135
+ "eval_f1": 0.9224489868001543,
136
+ "eval_loss": 1.8111803531646729,
137
+ "eval_matthews_correlation": 0.9216666198601385,
138
+ "eval_runtime": 2.2202,
139
+ "eval_samples_per_second": 1387.252,
140
+ "eval_steps_per_second": 9.008,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.924025974025974,
146
+ "eval_f1": 0.9235055742877311,
147
+ "eval_loss": 1.8154934644699097,
148
+ "eval_matthews_correlation": 0.9229953706448562,
149
+ "eval_runtime": 2.1795,
150
+ "eval_samples_per_second": 1413.141,
151
+ "eval_steps_per_second": 9.176,
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 sha256:52adb8dec3978929f805d6e3cc0d0a8b998b069525038dee3825f3335c826e74
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe18383a394371aab9808aba1f4950c63c76fd24cef71575ffa768824cc29b5
3
  size 2927
checkpoint-1400/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:922fe98d46da801c4d5e294f758944748a629fd4111e118080cf86a2ff0832a0
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc72dc678da0d7aeedd1429a7c22438d98743d42aded82b7477273ae0890204d
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:db06c383a7664f0c2f62da44d02de9d030017ee73bd6004b437a50e4aa4f4930
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:448231487e8e885b9da0faf94b2c744c8a7750fe206d64573875c2a4fa87488c
3
  size 440628841
checkpoint-1400/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26ce9bd3068806af0cd82e88949f7754b680d2dbd6266ff3439d3049cd225d63
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0433ac814c8e490bc1cba0907fa3d6e23d0cc5bb6b5d5182479419d1d89fae
3
  size 623
checkpoint-1400/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.9266233766233766,
3
- "best_model_checkpoint": "mpnet-metric/checkpoint-1200",
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": 0.823051948051948,
13
- "eval_f1": 0.7694886084528045,
14
- "eval_loss": 1.8196498155593872,
15
- "eval_matthews_correlation": 0.82152846992121,
16
- "eval_runtime": 2.0824,
17
- "eval_samples_per_second": 1479.063,
18
- "eval_steps_per_second": 9.604,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.8717532467532467,
24
- "eval_f1": 0.8385414959301972,
25
- "eval_loss": 1.5393933057785034,
26
- "eval_matthews_correlation": 0.8702231962356954,
27
- "eval_runtime": 2.2041,
28
- "eval_samples_per_second": 1397.426,
29
- "eval_steps_per_second": 9.074,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
- "eval_accuracy": 0.8918831168831168,
35
- "eval_f1": 0.8674754241961948,
36
- "eval_loss": 1.6252003908157349,
37
- "eval_matthews_correlation": 0.8905305382750595,
38
- "eval_runtime": 2.3515,
39
- "eval_samples_per_second": 1309.779,
40
- "eval_steps_per_second": 8.505,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
- "eval_accuracy": 0.9081168831168831,
46
- "eval_f1": 0.8936386572619883,
47
- "eval_loss": 1.4800223112106323,
48
- "eval_matthews_correlation": 0.9068978212395917,
49
- "eval_runtime": 2.1261,
50
- "eval_samples_per_second": 1448.662,
51
- "eval_steps_per_second": 9.407,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
- "learning_rate": 2.72715184015364e-05,
57
- "loss": 1.2024,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
- "eval_accuracy": 0.9227272727272727,
63
- "eval_f1": 0.9191317240240598,
64
- "eval_loss": 1.5631015300750732,
65
- "eval_matthews_correlation": 0.921668408209661,
66
- "eval_runtime": 2.1128,
67
- "eval_samples_per_second": 1457.81,
68
- "eval_steps_per_second": 9.466,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
- "eval_accuracy": 0.924025974025974,
74
- "eval_f1": 0.9250159536040414,
75
- "eval_loss": 1.6559977531433105,
76
- "eval_matthews_correlation": 0.9229932303823994,
77
- "eval_runtime": 2.1526,
78
- "eval_samples_per_second": 1430.816,
79
- "eval_steps_per_second": 9.291,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
- "eval_accuracy": 0.9188311688311688,
85
- "eval_f1": 0.9178066235572834,
86
- "eval_loss": 1.6833025217056274,
87
- "eval_matthews_correlation": 0.9177304556222637,
88
- "eval_runtime": 2.2196,
89
- "eval_samples_per_second": 1387.667,
90
- "eval_steps_per_second": 9.011,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
- "eval_accuracy": 0.9217532467532468,
96
- "eval_f1": 0.921664147942375,
97
- "eval_loss": 1.683775782585144,
98
- "eval_matthews_correlation": 0.9206740366287324,
99
- "eval_runtime": 2.1736,
100
- "eval_samples_per_second": 1416.993,
101
- "eval_steps_per_second": 9.201,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
- "eval_accuracy": 0.9295454545454546,
107
- "eval_f1": 0.9281614931192158,
108
- "eval_loss": 1.6790761947631836,
109
- "eval_matthews_correlation": 0.9285814101191024,
110
- "eval_runtime": 2.0387,
111
- "eval_samples_per_second": 1510.74,
112
- "eval_steps_per_second": 9.81,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
- "learning_rate": 1.6449487289815606e-05,
118
- "loss": 0.3425,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
- "eval_accuracy": 0.9253246753246753,
124
- "eval_f1": 0.9248272869409627,
125
- "eval_loss": 1.706620454788208,
126
- "eval_matthews_correlation": 0.924306415853766,
127
- "eval_runtime": 2.1612,
128
- "eval_samples_per_second": 1425.121,
129
- "eval_steps_per_second": 9.254,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
- "eval_accuracy": 0.9262987012987013,
135
- "eval_f1": 0.9256841156799166,
136
- "eval_loss": 1.7070327997207642,
137
- "eval_matthews_correlation": 0.9252825858586532,
138
- "eval_runtime": 2.4454,
139
- "eval_samples_per_second": 1259.521,
140
- "eval_steps_per_second": 8.179,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
- "eval_accuracy": 0.9266233766233766,
146
- "eval_f1": 0.9262828157785664,
147
- "eval_loss": 1.7237951755523682,
148
- "eval_matthews_correlation": 0.9256157384883016,
149
- "eval_runtime": 2.1429,
150
- "eval_samples_per_second": 1437.307,
151
- "eval_steps_per_second": 9.333,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
- "eval_accuracy": 0.926948051948052,
157
- "eval_f1": 0.9262718398296581,
158
- "eval_loss": 1.6817880868911743,
159
- "eval_matthews_correlation": 0.9259576292924887,
160
- "eval_runtime": 2.18,
161
- "eval_samples_per_second": 1412.867,
162
- "eval_steps_per_second": 9.174,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
- "eval_accuracy": 0.9262987012987013,
168
- "eval_f1": 0.9250790121791868,
169
- "eval_loss": 1.7330801486968994,
170
- "eval_matthews_correlation": 0.9252916129863266,
171
- "eval_runtime": 2.0264,
172
- "eval_samples_per_second": 1519.944,
173
- "eval_steps_per_second": 9.87,
174
  "step": 1400
175
  }
176
  ],
 
1
  {
2
+ "best_metric": 0.926948051948052,
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": 0.8168831168831169,
13
+ "eval_f1": 0.7526160112915868,
14
+ "eval_loss": 1.6600779294967651,
15
+ "eval_matthews_correlation": 0.8152410229901306,
16
+ "eval_runtime": 2.4316,
17
+ "eval_samples_per_second": 1266.672,
18
+ "eval_steps_per_second": 8.225,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.897077922077922,
24
+ "eval_f1": 0.8856257075703299,
25
+ "eval_loss": 1.4927222728729248,
26
+ "eval_matthews_correlation": 0.8957943237010111,
27
+ "eval_runtime": 2.2227,
28
+ "eval_samples_per_second": 1385.731,
29
+ "eval_steps_per_second": 8.998,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9201298701298701,
35
+ "eval_f1": 0.9205225631693909,
36
+ "eval_loss": 1.5566294193267822,
37
+ "eval_matthews_correlation": 0.9190320812070084,
38
+ "eval_runtime": 2.1905,
39
+ "eval_samples_per_second": 1406.054,
40
+ "eval_steps_per_second": 9.13,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.912012987012987,
46
+ "eval_f1": 0.9120652244039835,
47
+ "eval_loss": 1.5064270496368408,
48
+ "eval_matthews_correlation": 0.910845237954562,
49
+ "eval_runtime": 2.0804,
50
+ "eval_samples_per_second": 1480.451,
51
+ "eval_steps_per_second": 9.613,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 7.143981790504036e-05,
57
+ "loss": 1.1713,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9214285714285714,
63
+ "eval_f1": 0.9209415679460552,
64
+ "eval_loss": 1.6870453357696533,
65
+ "eval_matthews_correlation": 0.920369186542805,
66
+ "eval_runtime": 2.1662,
67
+ "eval_samples_per_second": 1421.817,
68
+ "eval_steps_per_second": 9.233,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9198051948051948,
74
+ "eval_f1": 0.9197304127364558,
75
+ "eval_loss": 1.6187154054641724,
76
+ "eval_matthews_correlation": 0.918700976641645,
77
+ "eval_runtime": 2.0584,
78
+ "eval_samples_per_second": 1496.322,
79
+ "eval_steps_per_second": 9.716,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9159090909090909,
85
+ "eval_f1": 0.9164948773151114,
86
+ "eval_loss": 1.6880903244018555,
87
+ "eval_matthews_correlation": 0.9148059546508341,
88
+ "eval_runtime": 2.255,
89
+ "eval_samples_per_second": 1365.875,
90
+ "eval_steps_per_second": 8.869,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.9172077922077922,
96
+ "eval_f1": 0.9171466545500319,
97
+ "eval_loss": 1.6939719915390015,
98
+ "eval_matthews_correlation": 0.9160846990725676,
99
+ "eval_runtime": 2.1751,
100
+ "eval_samples_per_second": 1416.047,
101
+ "eval_steps_per_second": 9.195,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9237012987012987,
107
+ "eval_f1": 0.9228068483209093,
108
+ "eval_loss": 1.827225685119629,
109
+ "eval_matthews_correlation": 0.9226697076696465,
110
+ "eval_runtime": 2.0546,
111
+ "eval_samples_per_second": 1499.088,
112
+ "eval_steps_per_second": 9.734,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 4.309068381573863e-05,
118
+ "loss": 0.3851,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9256493506493506,
124
+ "eval_f1": 0.924610487019518,
125
+ "eval_loss": 1.752126932144165,
126
+ "eval_matthews_correlation": 0.9246248223527813,
127
+ "eval_runtime": 2.1963,
128
+ "eval_samples_per_second": 1402.379,
129
+ "eval_steps_per_second": 9.106,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9227272727272727,
135
+ "eval_f1": 0.9224489868001543,
136
+ "eval_loss": 1.8111803531646729,
137
+ "eval_matthews_correlation": 0.9216666198601385,
138
+ "eval_runtime": 2.2202,
139
+ "eval_samples_per_second": 1387.252,
140
+ "eval_steps_per_second": 9.008,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.924025974025974,
146
+ "eval_f1": 0.9235055742877311,
147
+ "eval_loss": 1.8154934644699097,
148
+ "eval_matthews_correlation": 0.9229953706448562,
149
+ "eval_runtime": 2.1795,
150
+ "eval_samples_per_second": 1413.141,
151
+ "eval_steps_per_second": 9.176,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
+ "eval_accuracy": 0.925974025974026,
157
+ "eval_f1": 0.9250491597779087,
158
+ "eval_loss": 1.8494137525558472,
159
+ "eval_matthews_correlation": 0.9249617346684725,
160
+ "eval_runtime": 2.1532,
161
+ "eval_samples_per_second": 1430.445,
162
+ "eval_steps_per_second": 9.289,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
+ "eval_accuracy": 0.926948051948052,
168
+ "eval_f1": 0.9263712922428582,
169
+ "eval_loss": 1.845504641532898,
170
+ "eval_matthews_correlation": 0.925946513781978,
171
+ "eval_runtime": 2.0321,
172
+ "eval_samples_per_second": 1515.7,
173
+ "eval_steps_per_second": 9.842,
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 sha256:52adb8dec3978929f805d6e3cc0d0a8b998b069525038dee3825f3335c826e74
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe18383a394371aab9808aba1f4950c63c76fd24cef71575ffa768824cc29b5
3
  size 2927
checkpoint-1600/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee57d22716bdd3e1e3e0636fb4b0e87c519c9fec5318a249e106670b2c7a4030
3
  size 1762416361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f67a75074cf83a02b5c28f5dd1893c75a67db34abb973c2f381df508be1b19f
3
  size 1762416361
checkpoint-1600/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c89635d0b84e22f78c886389c5c77ea1ad6ca903e8db725bc053537039e5f3f
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2955a53f1f98b08cdd7181fd3a3127a37549e31bf31592b14205f5a01e0a0b7b
3
  size 440628841
checkpoint-1600/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79cef0c764450c43c32b20f5ef355b0e4d105ebe08b8862f6e59436d9a5e4ef0
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9a234b21a74bb8cab1c8ff195279b444caa9b2dcd39b87cf49e883531ecfe1
3
  size 623
checkpoint-1600/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.9266233766233766,
3
- "best_model_checkpoint": "mpnet-metric/checkpoint-1200",
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": 0.823051948051948,
13
- "eval_f1": 0.7694886084528045,
14
- "eval_loss": 1.8196498155593872,
15
- "eval_matthews_correlation": 0.82152846992121,
16
- "eval_runtime": 2.0824,
17
- "eval_samples_per_second": 1479.063,
18
- "eval_steps_per_second": 9.604,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.8717532467532467,
24
- "eval_f1": 0.8385414959301972,
25
- "eval_loss": 1.5393933057785034,
26
- "eval_matthews_correlation": 0.8702231962356954,
27
- "eval_runtime": 2.2041,
28
- "eval_samples_per_second": 1397.426,
29
- "eval_steps_per_second": 9.074,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
- "eval_accuracy": 0.8918831168831168,
35
- "eval_f1": 0.8674754241961948,
36
- "eval_loss": 1.6252003908157349,
37
- "eval_matthews_correlation": 0.8905305382750595,
38
- "eval_runtime": 2.3515,
39
- "eval_samples_per_second": 1309.779,
40
- "eval_steps_per_second": 8.505,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
- "eval_accuracy": 0.9081168831168831,
46
- "eval_f1": 0.8936386572619883,
47
- "eval_loss": 1.4800223112106323,
48
- "eval_matthews_correlation": 0.9068978212395917,
49
- "eval_runtime": 2.1261,
50
- "eval_samples_per_second": 1448.662,
51
- "eval_steps_per_second": 9.407,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
- "learning_rate": 2.72715184015364e-05,
57
- "loss": 1.2024,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
- "eval_accuracy": 0.9227272727272727,
63
- "eval_f1": 0.9191317240240598,
64
- "eval_loss": 1.5631015300750732,
65
- "eval_matthews_correlation": 0.921668408209661,
66
- "eval_runtime": 2.1128,
67
- "eval_samples_per_second": 1457.81,
68
- "eval_steps_per_second": 9.466,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
- "eval_accuracy": 0.924025974025974,
74
- "eval_f1": 0.9250159536040414,
75
- "eval_loss": 1.6559977531433105,
76
- "eval_matthews_correlation": 0.9229932303823994,
77
- "eval_runtime": 2.1526,
78
- "eval_samples_per_second": 1430.816,
79
- "eval_steps_per_second": 9.291,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
- "eval_accuracy": 0.9188311688311688,
85
- "eval_f1": 0.9178066235572834,
86
- "eval_loss": 1.6833025217056274,
87
- "eval_matthews_correlation": 0.9177304556222637,
88
- "eval_runtime": 2.2196,
89
- "eval_samples_per_second": 1387.667,
90
- "eval_steps_per_second": 9.011,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
- "eval_accuracy": 0.9217532467532468,
96
- "eval_f1": 0.921664147942375,
97
- "eval_loss": 1.683775782585144,
98
- "eval_matthews_correlation": 0.9206740366287324,
99
- "eval_runtime": 2.1736,
100
- "eval_samples_per_second": 1416.993,
101
- "eval_steps_per_second": 9.201,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
- "eval_accuracy": 0.9295454545454546,
107
- "eval_f1": 0.9281614931192158,
108
- "eval_loss": 1.6790761947631836,
109
- "eval_matthews_correlation": 0.9285814101191024,
110
- "eval_runtime": 2.0387,
111
- "eval_samples_per_second": 1510.74,
112
- "eval_steps_per_second": 9.81,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
- "learning_rate": 1.6449487289815606e-05,
118
- "loss": 0.3425,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
- "eval_accuracy": 0.9253246753246753,
124
- "eval_f1": 0.9248272869409627,
125
- "eval_loss": 1.706620454788208,
126
- "eval_matthews_correlation": 0.924306415853766,
127
- "eval_runtime": 2.1612,
128
- "eval_samples_per_second": 1425.121,
129
- "eval_steps_per_second": 9.254,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
- "eval_accuracy": 0.9262987012987013,
135
- "eval_f1": 0.9256841156799166,
136
- "eval_loss": 1.7070327997207642,
137
- "eval_matthews_correlation": 0.9252825858586532,
138
- "eval_runtime": 2.4454,
139
- "eval_samples_per_second": 1259.521,
140
- "eval_steps_per_second": 8.179,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
- "eval_accuracy": 0.9266233766233766,
146
- "eval_f1": 0.9262828157785664,
147
- "eval_loss": 1.7237951755523682,
148
- "eval_matthews_correlation": 0.9256157384883016,
149
- "eval_runtime": 2.1429,
150
- "eval_samples_per_second": 1437.307,
151
- "eval_steps_per_second": 9.333,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
- "eval_accuracy": 0.926948051948052,
157
- "eval_f1": 0.9262718398296581,
158
- "eval_loss": 1.6817880868911743,
159
- "eval_matthews_correlation": 0.9259576292924887,
160
- "eval_runtime": 2.18,
161
- "eval_samples_per_second": 1412.867,
162
- "eval_steps_per_second": 9.174,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
- "eval_accuracy": 0.9262987012987013,
168
- "eval_f1": 0.9250790121791868,
169
- "eval_loss": 1.7330801486968994,
170
- "eval_matthews_correlation": 0.9252916129863266,
171
- "eval_runtime": 2.0264,
172
- "eval_samples_per_second": 1519.944,
173
- "eval_steps_per_second": 9.87,
174
  "step": 1400
175
  },
176
  {
177
  "epoch": 34.09,
178
- "learning_rate": 5.627456178094813e-06,
179
- "loss": 0.0539,
180
  "step": 1500
181
  },
182
  {
183
  "epoch": 34.09,
184
  "eval_accuracy": 0.9256493506493506,
185
- "eval_f1": 0.9250658207791576,
186
- "eval_loss": 1.7235050201416016,
187
- "eval_matthews_correlation": 0.9246315384270692,
188
- "eval_runtime": 2.1259,
189
- "eval_samples_per_second": 1448.785,
190
- "eval_steps_per_second": 9.408,
191
  "step": 1500
192
  },
193
  {
194
  "epoch": 36.36,
195
- "eval_accuracy": 0.9253246753246753,
196
- "eval_f1": 0.9246989830406838,
197
- "eval_loss": 1.7130450010299683,
198
- "eval_matthews_correlation": 0.9243058175914095,
199
- "eval_runtime": 2.2922,
200
- "eval_samples_per_second": 1343.685,
201
- "eval_steps_per_second": 8.725,
202
  "step": 1600
203
  }
204
  ],
 
1
  {
2
+ "best_metric": 0.926948051948052,
3
+ "best_model_checkpoint": "mpnet-metric/checkpoint-1400",
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": 0.8168831168831169,
13
+ "eval_f1": 0.7526160112915868,
14
+ "eval_loss": 1.6600779294967651,
15
+ "eval_matthews_correlation": 0.8152410229901306,
16
+ "eval_runtime": 2.4316,
17
+ "eval_samples_per_second": 1266.672,
18
+ "eval_steps_per_second": 8.225,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.897077922077922,
24
+ "eval_f1": 0.8856257075703299,
25
+ "eval_loss": 1.4927222728729248,
26
+ "eval_matthews_correlation": 0.8957943237010111,
27
+ "eval_runtime": 2.2227,
28
+ "eval_samples_per_second": 1385.731,
29
+ "eval_steps_per_second": 8.998,
30
  "step": 200
31
  },
32
  {
33
  "epoch": 6.82,
34
+ "eval_accuracy": 0.9201298701298701,
35
+ "eval_f1": 0.9205225631693909,
36
+ "eval_loss": 1.5566294193267822,
37
+ "eval_matthews_correlation": 0.9190320812070084,
38
+ "eval_runtime": 2.1905,
39
+ "eval_samples_per_second": 1406.054,
40
+ "eval_steps_per_second": 9.13,
41
  "step": 300
42
  },
43
  {
44
  "epoch": 9.09,
45
+ "eval_accuracy": 0.912012987012987,
46
+ "eval_f1": 0.9120652244039835,
47
+ "eval_loss": 1.5064270496368408,
48
+ "eval_matthews_correlation": 0.910845237954562,
49
+ "eval_runtime": 2.0804,
50
+ "eval_samples_per_second": 1480.451,
51
+ "eval_steps_per_second": 9.613,
52
  "step": 400
53
  },
54
  {
55
  "epoch": 11.36,
56
+ "learning_rate": 7.143981790504036e-05,
57
+ "loss": 1.1713,
58
  "step": 500
59
  },
60
  {
61
  "epoch": 11.36,
62
+ "eval_accuracy": 0.9214285714285714,
63
+ "eval_f1": 0.9209415679460552,
64
+ "eval_loss": 1.6870453357696533,
65
+ "eval_matthews_correlation": 0.920369186542805,
66
+ "eval_runtime": 2.1662,
67
+ "eval_samples_per_second": 1421.817,
68
+ "eval_steps_per_second": 9.233,
69
  "step": 500
70
  },
71
  {
72
  "epoch": 13.64,
73
+ "eval_accuracy": 0.9198051948051948,
74
+ "eval_f1": 0.9197304127364558,
75
+ "eval_loss": 1.6187154054641724,
76
+ "eval_matthews_correlation": 0.918700976641645,
77
+ "eval_runtime": 2.0584,
78
+ "eval_samples_per_second": 1496.322,
79
+ "eval_steps_per_second": 9.716,
80
  "step": 600
81
  },
82
  {
83
  "epoch": 15.91,
84
+ "eval_accuracy": 0.9159090909090909,
85
+ "eval_f1": 0.9164948773151114,
86
+ "eval_loss": 1.6880903244018555,
87
+ "eval_matthews_correlation": 0.9148059546508341,
88
+ "eval_runtime": 2.255,
89
+ "eval_samples_per_second": 1365.875,
90
+ "eval_steps_per_second": 8.869,
91
  "step": 700
92
  },
93
  {
94
  "epoch": 18.18,
95
+ "eval_accuracy": 0.9172077922077922,
96
+ "eval_f1": 0.9171466545500319,
97
+ "eval_loss": 1.6939719915390015,
98
+ "eval_matthews_correlation": 0.9160846990725676,
99
+ "eval_runtime": 2.1751,
100
+ "eval_samples_per_second": 1416.047,
101
+ "eval_steps_per_second": 9.195,
102
  "step": 800
103
  },
104
  {
105
  "epoch": 20.45,
106
+ "eval_accuracy": 0.9237012987012987,
107
+ "eval_f1": 0.9228068483209093,
108
+ "eval_loss": 1.827225685119629,
109
+ "eval_matthews_correlation": 0.9226697076696465,
110
+ "eval_runtime": 2.0546,
111
+ "eval_samples_per_second": 1499.088,
112
+ "eval_steps_per_second": 9.734,
113
  "step": 900
114
  },
115
  {
116
  "epoch": 22.73,
117
+ "learning_rate": 4.309068381573863e-05,
118
+ "loss": 0.3851,
119
  "step": 1000
120
  },
121
  {
122
  "epoch": 22.73,
123
+ "eval_accuracy": 0.9256493506493506,
124
+ "eval_f1": 0.924610487019518,
125
+ "eval_loss": 1.752126932144165,
126
+ "eval_matthews_correlation": 0.9246248223527813,
127
+ "eval_runtime": 2.1963,
128
+ "eval_samples_per_second": 1402.379,
129
+ "eval_steps_per_second": 9.106,
130
  "step": 1000
131
  },
132
  {
133
  "epoch": 25.0,
134
+ "eval_accuracy": 0.9227272727272727,
135
+ "eval_f1": 0.9224489868001543,
136
+ "eval_loss": 1.8111803531646729,
137
+ "eval_matthews_correlation": 0.9216666198601385,
138
+ "eval_runtime": 2.2202,
139
+ "eval_samples_per_second": 1387.252,
140
+ "eval_steps_per_second": 9.008,
141
  "step": 1100
142
  },
143
  {
144
  "epoch": 27.27,
145
+ "eval_accuracy": 0.924025974025974,
146
+ "eval_f1": 0.9235055742877311,
147
+ "eval_loss": 1.8154934644699097,
148
+ "eval_matthews_correlation": 0.9229953706448562,
149
+ "eval_runtime": 2.1795,
150
+ "eval_samples_per_second": 1413.141,
151
+ "eval_steps_per_second": 9.176,
152
  "step": 1200
153
  },
154
  {
155
  "epoch": 29.55,
156
+ "eval_accuracy": 0.925974025974026,
157
+ "eval_f1": 0.9250491597779087,
158
+ "eval_loss": 1.8494137525558472,
159
+ "eval_matthews_correlation": 0.9249617346684725,
160
+ "eval_runtime": 2.1532,
161
+ "eval_samples_per_second": 1430.445,
162
+ "eval_steps_per_second": 9.289,
163
  "step": 1300
164
  },
165
  {
166
  "epoch": 31.82,
167
+ "eval_accuracy": 0.926948051948052,
168
+ "eval_f1": 0.9263712922428582,
169
+ "eval_loss": 1.845504641532898,
170
+ "eval_matthews_correlation": 0.925946513781978,
171
+ "eval_runtime": 2.0321,
172
+ "eval_samples_per_second": 1515.7,
173
+ "eval_steps_per_second": 9.842,
174
  "step": 1400
175
  },
176
  {
177
  "epoch": 34.09,
178
+ "learning_rate": 1.4741549726436899e-05,
179
+ "loss": 0.0405,
180
  "step": 1500
181
  },
182
  {
183
  "epoch": 34.09,
184
  "eval_accuracy": 0.9256493506493506,
185
+ "eval_f1": 0.925144415860077,
186
+ "eval_loss": 1.8381743431091309,
187
+ "eval_matthews_correlation": 0.9246323973685248,
188
+ "eval_runtime": 2.1091,
189
+ "eval_samples_per_second": 1460.352,
190
+ "eval_steps_per_second": 9.483,
191
  "step": 1500
192
  },
193
  {
194
  "epoch": 36.36,
195
+ "eval_accuracy": 0.925,
196
+ "eval_f1": 0.9246946976864899,
197
+ "eval_loss": 1.8348827362060547,
198
+ "eval_matthews_correlation": 0.9239766342788056,
199
+ "eval_runtime": 2.1159,
200
+ "eval_samples_per_second": 1455.631,
201
+ "eval_steps_per_second": 9.452,
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 sha256:52adb8dec3978929f805d6e3cc0d0a8b998b069525038dee3825f3335c826e74
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe18383a394371aab9808aba1f4950c63c76fd24cef71575ffa768824cc29b5
3
  size 2927
checkpoint-200/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:207e640a4936e6e7df2496c87a07fa40c02b49a4ad7db70a0e35d76f3a5bc095
3
  size 1762415977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9439c182b3e4ea5d09e5cc1d51b0c801ca318a212f5674eb7ca73a359fa977b
3
  size 1762415977
checkpoint-200/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42c2609b23d54c79ca28924a3a059aabd97217122d241d315c0dac31fd266463
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c01622af90baa3d74c8ca0fc35f5f9f3d2a878e3df5bb273eed362255909c0b
3
  size 440628841
checkpoint-200/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25cdb4f3ce640b734c45609c0e86974434f0f4d7cfb0fe2bdeea6dc202ace16b
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5acf53d8795047ae3fb8c3d053417580641d9bd9c3b7986b26e1e96100587dc
3
  size 623
checkpoint-200/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.897077922077922,
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": 0.8168831168831169,
13
- "eval_f1": 0.7526160112915868,
14
- "eval_loss": 1.6600779294967651,
15
- "eval_matthews_correlation": 0.8152410229901306,
16
- "eval_runtime": 2.4316,
17
- "eval_samples_per_second": 1266.672,
18
- "eval_steps_per_second": 8.225,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
- "eval_accuracy": 0.897077922077922,
24
- "eval_f1": 0.8856257075703299,
25
- "eval_loss": 1.4927222728729248,
26
- "eval_matthews_correlation": 0.8957943237010111,
27
- "eval_runtime": 2.2227,
28
- "eval_samples_per_second": 1385.731,
29
- "eval_steps_per_second": 8.998,
30
  "step": 200
31
  }
32
  ],
 
1
  {
2
+ "best_metric": 0.8948051948051948,
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": 0.8142857142857143,
13
+ "eval_f1": 0.7571139466171084,
14
+ "eval_loss": 1.6553083658218384,
15
+ "eval_matthews_correlation": 0.8128010374008804,
16
+ "eval_runtime": 2.3607,
17
+ "eval_samples_per_second": 1304.725,
18
+ "eval_steps_per_second": 8.472,
19
  "step": 100
20
  },
21
  {
22
  "epoch": 4.55,
23
+ "eval_accuracy": 0.8948051948051948,
24
+ "eval_f1": 0.8619038692930777,
25
+ "eval_loss": 1.4167946577072144,
26
+ "eval_matthews_correlation": 0.8934693025227957,
27
+ "eval_runtime": 2.1743,
28
+ "eval_samples_per_second": 1416.55,
29
+ "eval_steps_per_second": 9.198,
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 sha256:5fe18383a394371aab9808aba1f4950c63c76fd24cef71575ffa768824cc29b5
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1912ec144e9e5b98372a9c9abb72fc7763e9904e5599699afcdc707da8bc9dc5
3
  size 2927
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:043f5c480bedb53f96a633d0ca2d65dd6f5fc6adc2af5fd6892dc7afa7e84dcb
3
  size 440628841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c01622af90baa3d74c8ca0fc35f5f9f3d2a878e3df5bb273eed362255909c0b
3
  size 440628841
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fe18383a394371aab9808aba1f4950c63c76fd24cef71575ffa768824cc29b5
3
  size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1912ec144e9e5b98372a9c9abb72fc7763e9904e5599699afcdc707da8bc9dc5
3
  size 2927