Theoreticallyhugo commited on
Commit
e3efc2f
·
verified ·
1 Parent(s): a907f93

Training in progress, epoch 2, checkpoint

Browse files
checkpoint-162/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:deaa6c6706302021ad239de2c71b880c7ae14468e65ce3d2531189754736d7c0
3
  size 592330980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9268bc89698fae9668c314ec4899e6e3494ef4ffc541b83bda4fb57586909f3
3
  size 592330980
checkpoint-162/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0a32c500e36dd2f1241190c7fa8c744f77e57ee2378950a068aba330cb3949c
3
  size 1014670074
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73f55760e7d3d4750f9bb153d3ac3c356c5b42b8ce4ee326a00b0a1042b48ee
3
  size 1014670074
checkpoint-162/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bd8264931534616018335b535732049961e4647585455e22b74dcb3e6034c63
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46048b97dd03acf4cb6c82fc924d60322fb8fb6d0b9ecb6d39c987081744ecab
3
  size 1064
checkpoint-162/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
  "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 162,
@@ -11,134 +11,134 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_B-Claim": {
14
- "f1-score": 0.0,
15
- "precision": 0.0,
16
- "recall": 0.0,
17
- "support": 271.0
18
  },
19
  "eval_B-MajorClaim": {
20
  "f1-score": 0.0,
21
  "precision": 0.0,
22
  "recall": 0.0,
23
- "support": 139.0
24
  },
25
  "eval_B-Premise": {
26
- "f1-score": 0.6746310611384398,
27
- "precision": 0.6075949367088608,
28
- "recall": 0.7582938388625592,
29
- "support": 633.0
30
  },
31
  "eval_I-Claim": {
32
- "f1-score": 0.4376506024096386,
33
- "precision": 0.550587343690792,
34
- "recall": 0.3631592101974506,
35
- "support": 4001.0
36
  },
37
  "eval_I-MajorClaim": {
38
- "f1-score": 0.620034542314335,
39
- "precision": 0.5483008781977854,
40
- "recall": 0.7133631395926477,
41
- "support": 2013.0
42
  },
43
  "eval_I-Premise": {
44
- "f1-score": 0.8620734063103671,
45
- "precision": 0.8396186972154862,
46
- "recall": 0.8857621736062103,
47
- "support": 11336.0
48
  },
49
  "eval_O": {
50
- "f1-score": 0.8807729058286443,
51
- "precision": 0.8630878069080317,
52
- "recall": 0.8991979189247779,
53
- "support": 9226.0
54
  },
55
- "eval_accuracy": 0.785908251565951,
56
- "eval_loss": 0.5655931830406189,
57
  "eval_macro avg": {
58
- "f1-score": 0.49645178828591785,
59
- "precision": 0.48702709467442235,
60
- "recall": 0.5171108973119495,
61
- "support": 27619.0
62
- },
63
- "eval_runtime": 4.8252,
64
- "eval_samples_per_second": 16.58,
65
- "eval_steps_per_second": 2.072,
66
  "eval_weighted avg": {
67
- "f1-score": 0.7721020318885458,
68
- "precision": 0.766573839857488,
69
- "recall": 0.785908251565951,
70
- "support": 27619.0
71
  },
72
  "step": 81
73
  },
74
  {
75
  "epoch": 2.0,
76
  "eval_B-Claim": {
77
- "f1-score": 0.36036036036036034,
78
- "precision": 0.4624277456647399,
79
- "recall": 0.2952029520295203,
80
- "support": 271.0
81
  },
82
  "eval_B-MajorClaim": {
83
- "f1-score": 0.5836909871244635,
84
- "precision": 0.723404255319149,
85
- "recall": 0.4892086330935252,
86
- "support": 139.0
87
  },
88
  "eval_B-Premise": {
89
- "f1-score": 0.7396491228070177,
90
- "precision": 0.6654040404040404,
91
- "recall": 0.8325434439178515,
92
- "support": 633.0
93
  },
94
  "eval_I-Claim": {
95
- "f1-score": 0.46704216775764956,
96
- "precision": 0.5973520249221184,
97
- "recall": 0.3834041489627593,
98
- "support": 4001.0
99
  },
100
  "eval_I-MajorClaim": {
101
- "f1-score": 0.7326456649010316,
102
- "precision": 0.8348157560355781,
103
- "recall": 0.6527570789865872,
104
- "support": 2013.0
105
  },
106
  "eval_I-Premise": {
107
- "f1-score": 0.8679505932065659,
108
- "precision": 0.8045344983428744,
109
- "recall": 0.9422194777699365,
110
- "support": 11336.0
111
  },
112
  "eval_O": {
113
- "f1-score": 0.9101698606271778,
114
- "precision": 0.9143513454386348,
115
- "recall": 0.9060264469976155,
116
- "support": 9226.0
117
  },
118
- "eval_accuracy": 0.8169376154096818,
119
- "eval_loss": 0.4831336438655853,
120
  "eval_macro avg": {
121
- "f1-score": 0.6659298223977524,
122
- "precision": 0.7146128094467336,
123
- "recall": 0.6430517402511137,
124
- "support": 27619.0
125
- },
126
- "eval_runtime": 4.8125,
127
- "eval_samples_per_second": 16.623,
128
- "eval_steps_per_second": 2.078,
129
  "eval_weighted avg": {
130
- "f1-score": 0.8047632099274016,
131
- "precision": 0.8064582361050344,
132
- "recall": 0.8169376154096818,
133
- "support": 27619.0
134
  },
135
  "step": 162
136
  }
137
  ],
138
  "logging_steps": 500,
139
- "max_steps": 4050,
140
  "num_input_tokens_seen": 0,
141
- "num_train_epochs": 50,
142
  "save_steps": 500,
143
  "total_flos": 287581625436000.0,
144
  "train_batch_size": 4,
 
1
  {
2
+ "best_metric": 0.5138605833053589,
3
+ "best_model_checkpoint": "longformer-full_labels/checkpoint-162",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 162,
 
11
  {
12
  "epoch": 1.0,
13
  "eval_B-Claim": {
14
+ "f1-score": 0.006993006993006993,
15
+ "precision": 0.5,
16
+ "recall": 0.0035211267605633804,
17
+ "support": 284.0
18
  },
19
  "eval_B-MajorClaim": {
20
  "f1-score": 0.0,
21
  "precision": 0.0,
22
  "recall": 0.0,
23
+ "support": 141.0
24
  },
25
  "eval_B-Premise": {
26
+ "f1-score": 0.6336375488917861,
27
+ "precision": 0.5883777239709443,
28
+ "recall": 0.6864406779661016,
29
+ "support": 708.0
30
  },
31
  "eval_I-Claim": {
32
+ "f1-score": 0.37228850325379614,
33
+ "precision": 0.41618672324946954,
34
+ "recall": 0.3367672308069659,
35
+ "support": 4077.0
36
  },
37
  "eval_I-MajorClaim": {
38
+ "f1-score": 0.49153013051930017,
39
+ "precision": 0.5611921369689283,
40
+ "recall": 0.43725296442687744,
41
+ "support": 2024.0
42
  },
43
  "eval_I-Premise": {
44
+ "f1-score": 0.846019669697532,
45
+ "precision": 0.7746890504995582,
46
+ "recall": 0.9318181818181818,
47
+ "support": 12232.0
48
  },
49
  "eval_O": {
50
+ "f1-score": 0.8650519031141869,
51
+ "precision": 0.9111808904340025,
52
+ "recall": 0.8233684637211187,
53
+ "support": 9868.0
54
  },
55
+ "eval_accuracy": 0.7591191109292971,
56
+ "eval_loss": 0.6442636251449585,
57
  "eval_macro avg": {
58
+ "f1-score": 0.4593601089242298,
59
+ "precision": 0.535946646446129,
60
+ "recall": 0.4598812350714013,
61
+ "support": 29334.0
62
+ },
63
+ "eval_runtime": 6.1153,
64
+ "eval_samples_per_second": 13.082,
65
+ "eval_steps_per_second": 1.635,
66
  "eval_weighted avg": {
67
+ "f1-score": 0.7448054609057474,
68
+ "precision": 0.7451676238152983,
69
+ "recall": 0.7591191109292971,
70
+ "support": 29334.0
71
  },
72
  "step": 81
73
  },
74
  {
75
  "epoch": 2.0,
76
  "eval_B-Claim": {
77
+ "f1-score": 0.47385620915032683,
78
+ "precision": 0.4420731707317073,
79
+ "recall": 0.5105633802816901,
80
+ "support": 284.0
81
  },
82
  "eval_B-MajorClaim": {
83
+ "f1-score": 0.5267489711934156,
84
+ "precision": 0.6274509803921569,
85
+ "recall": 0.45390070921985815,
86
+ "support": 141.0
87
  },
88
  "eval_B-Premise": {
89
+ "f1-score": 0.7686170212765958,
90
+ "precision": 0.7261306532663316,
91
+ "recall": 0.8163841807909604,
92
+ "support": 708.0
93
  },
94
  "eval_I-Claim": {
95
+ "f1-score": 0.5068787075602675,
96
+ "precision": 0.5221008840353614,
97
+ "recall": 0.49251900907530044,
98
+ "support": 4077.0
99
  },
100
  "eval_I-MajorClaim": {
101
+ "f1-score": 0.6644462947543713,
102
+ "precision": 0.5741007194244604,
103
+ "recall": 0.7885375494071146,
104
+ "support": 2024.0
105
  },
106
  "eval_I-Premise": {
107
+ "f1-score": 0.8735948241002829,
108
+ "precision": 0.8642982877260361,
109
+ "recall": 0.8830935251798561,
110
+ "support": 12232.0
111
  },
112
  "eval_O": {
113
+ "f1-score": 0.8825588796944621,
114
+ "precision": 0.925979519145147,
115
+ "recall": 0.8430279691933522,
116
+ "support": 9868.0
117
  },
118
+ "eval_accuracy": 0.8015272380173177,
119
+ "eval_loss": 0.5138605833053589,
120
  "eval_macro avg": {
121
+ "f1-score": 0.6709572725328175,
122
+ "precision": 0.668876316388743,
123
+ "recall": 0.6840037604497332,
124
+ "support": 29334.0
125
+ },
126
+ "eval_runtime": 6.1482,
127
+ "eval_samples_per_second": 13.012,
128
+ "eval_steps_per_second": 1.627,
129
  "eval_weighted avg": {
130
+ "f1-score": 0.8031401896750007,
131
+ "precision": 0.8089032379475054,
132
+ "recall": 0.8015272380173177,
133
+ "support": 29334.0
134
  },
135
  "step": 162
136
  }
137
  ],
138
  "logging_steps": 500,
139
+ "max_steps": 1620,
140
  "num_input_tokens_seen": 0,
141
+ "num_train_epochs": 20,
142
  "save_steps": 500,
143
  "total_flos": 287581625436000.0,
144
  "train_batch_size": 4,
checkpoint-162/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96f940fbb595414fcc9335f58119ba24a5ec23e0d6daa1a329588d596e481421
3
- size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5653e8d83a92b07eb1df6cde8969d97342166ccb896f2bdca8c3721b3a61a616
3
+ size 4920