Hugging Face's logo

Theoreticallyhugo
/
longformer-sep_tok_full_labels

Token Classification
Transformers
Safetensors
longformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Theoreticallyhugo commited on
Commit
fb3447d
•
1 Parent(s): 4e246a0

Training in progress, epoch 2, checkpoint

Browse files
Files changed (5) hide show
  1. checkpoint-162/model.safetensors +1 -1
  2. checkpoint-162/optimizer.pt +1 -1
  3. checkpoint-162/rng_state.pth +1 -1
  4. checkpoint-162/trainer_state.json +85 -85
  5. checkpoint-162/training_args.bin +1 -1
checkpoint-162/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a11f15760b563aa1d3a7b3d90cd4a163933ed6cfef5a36abd0cf3e23f25109ec
3
  size 592330980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4b58243a1c6c70c34fdfa99974168647d6cfa2254a0a7b10f1c6d88e82b1c86
3
  size 592330980
checkpoint-162/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1300dab147626c676f3d1f88ae733997ed664f7f1dfd386d53f5322f16d84ebe
3
  size 1014670074
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cfe954178075e881c251e724c6a218f6ad48ddd078f08995a231b6bfd68ecf4
3
  size 1014670074
checkpoint-162/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88e210ec99a19f026e2def82a9c5587c47c7771d7dd08d2e2ba3261c169c79d9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6613e657dfa5c91f076329239ba74e9bccea696a05690b1f35a5faffc85df4aa
3
  size 14244
checkpoint-162/trainer_state.json CHANGED
@@ -11,126 +11,126 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_B-Claim": {
14
- "f1-score": 0.18764302059496568,
15
- "precision": 0.3416666666666667,
16
- "recall": 0.12933753943217666,
17
- "support": 317.0
18
  },
19
  "eval_B-MajorClaim": {
20
- "f1-score": 0.19540229885057472,
21
- "precision": 0.8947368421052632,
22
- "recall": 0.10967741935483871,
23
- "support": 155.0
24
  },
25
  "eval_B-Premise": {
26
- "f1-score": 0.8476339053562143,
27
- "precision": 0.740909090909091,
28
- "recall": 0.9902794653705954,
29
- "support": 823.0
30
  },
31
  "eval_I-Claim": {
32
- "f1-score": 0.4315998169894769,
33
- "precision": 0.6394035246272028,
34
- "recall": 0.3257366482504604,
35
- "support": 4344.0
36
  },
37
  "eval_I-MajorClaim": {
38
- "f1-score": 0.7779799818016379,
39
- "precision": 0.7493426818580193,
40
- "recall": 0.8088930936613056,
41
- "support": 2114.0
42
  },
43
  "eval_I-Premise": {
44
- "f1-score": 0.8948683715038855,
45
- "precision": 0.8376057421174058,
46
- "recall": 0.9605350187403542,
47
- "support": 13607.0
48
  },
49
  "eval_O": {
50
- "f1-score": 0.9980147987727848,
51
- "precision": 0.9970251509961237,
52
- "recall": 0.9990064131514769,
53
- "support": 11071.0
54
  },
55
- "eval_accuracy": 0.8673183065585397,
56
- "eval_loss": 0.3193369209766388,
57
  "eval_macro avg": {
58
- "f1-score": 0.6190203134099342,
59
- "precision": 0.7429556713256817,
60
- "recall": 0.6176379425658869,
61
- "support": 32431.0
62
- },
63
- "eval_runtime": 4.9083,
64
- "eval_samples_per_second": 16.299,
65
- "eval_steps_per_second": 2.037,
66
  "eval_weighted avg": {
67
- "f1-score": 0.8489527906249091,
68
- "precision": 0.8526967051825685,
69
- "recall": 0.8673183065585397,
70
- "support": 32431.0
71
  },
72
  "step": 81
73
  },
74
  {
75
  "epoch": 2.0,
76
  "eval_B-Claim": {
77
- "f1-score": 0.583941605839416,
78
- "precision": 0.6926406926406926,
79
- "recall": 0.5047318611987381,
80
- "support": 317.0
81
  },
82
  "eval_B-MajorClaim": {
83
- "f1-score": 0.8117647058823529,
84
- "precision": 0.745945945945946,
85
- "recall": 0.8903225806451613,
86
- "support": 155.0
87
  },
88
  "eval_B-Premise": {
89
- "f1-score": 0.8943661971830986,
90
- "precision": 0.8649262202043133,
91
- "recall": 0.9258809234507898,
92
- "support": 823.0
93
  },
94
  "eval_I-Claim": {
95
- "f1-score": 0.6197740770932805,
96
- "precision": 0.6271506009898656,
97
- "recall": 0.6125690607734806,
98
- "support": 4344.0
99
  },
100
  "eval_I-MajorClaim": {
101
- "f1-score": 0.8298737427776589,
102
- "precision": 0.7577178585384916,
103
- "recall": 0.9172185430463576,
104
- "support": 2114.0
105
  },
106
  "eval_I-Premise": {
107
- "f1-score": 0.9013697613125952,
108
- "precision": 0.9106660666066607,
109
- "recall": 0.8922613360770192,
110
- "support": 13607.0
111
  },
112
  "eval_O": {
113
- "f1-score": 0.9961487925331883,
114
- "precision": 0.9993636363636363,
115
- "recall": 0.9929545659831993,
116
- "support": 11071.0
117
  },
118
- "eval_accuracy": 0.887854213561099,
119
- "eval_loss": 0.26407390832901,
120
  "eval_macro avg": {
121
- "f1-score": 0.8053198403745129,
122
- "precision": 0.7997730030413723,
123
- "recall": 0.8194198387392494,
124
- "support": 32431.0
125
- },
126
- "eval_runtime": 4.9329,
127
- "eval_samples_per_second": 16.218,
128
- "eval_steps_per_second": 2.027,
129
  "eval_weighted avg": {
130
- "f1-score": 0.8876368199002541,
131
- "precision": 0.8889201304482091,
132
- "recall": 0.887854213561099,
133
- "support": 32431.0
134
  },
135
  "step": 162
136
  }
@@ -140,7 +140,7 @@
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,
145
  "trial_name": null,
146
  "trial_params": null
 
11
  {
12
  "epoch": 1.0,
13
  "eval_B-Claim": {
14
+ "f1-score": 0.17153996101364524,
15
+ "precision": 0.25287356321839083,
16
+ "recall": 0.12979351032448377,
17
+ "support": 339.0
18
  },
19
  "eval_B-MajorClaim": {
20
+ "f1-score": 0.08383233532934131,
21
+ "precision": 1.0,
22
+ "recall": 0.04375,
23
+ "support": 160.0
24
  },
25
  "eval_B-Premise": {
26
+ "f1-score": 0.8469620831429876,
27
+ "precision": 0.7427884615384616,
28
+ "recall": 0.9851222104144527,
29
+ "support": 941.0
30
  },
31
  "eval_I-Claim": {
32
+ "f1-score": 0.5420081967213116,
33
+ "precision": 0.6803858520900321,
34
+ "recall": 0.4504044274159217,
35
+ "support": 4698.0
36
  },
37
  "eval_I-MajorClaim": {
38
+ "f1-score": 0.8343351767251743,
39
+ "precision": 0.8141717503519474,
40
+ "recall": 0.8555226824457594,
41
+ "support": 2028.0
42
  },
43
  "eval_I-Premise": {
44
+ "f1-score": 0.9004323458767015,
45
+ "precision": 0.8590809093131264,
46
+ "recall": 0.9459659511472983,
47
+ "support": 14861.0
48
  },
49
  "eval_O": {
50
+ "f1-score": 0.9988389078242631,
51
+ "precision": 0.9991008541885209,
52
+ "recall": 0.9985770987793006,
53
+ "support": 13353.0
54
  },
55
+ "eval_accuracy": 0.8856789444749863,
56
+ "eval_loss": 0.28347474336624146,
57
  "eval_macro avg": {
58
+ "f1-score": 0.6254212866619178,
59
+ "precision": 0.76405734152864,
60
+ "recall": 0.629876554361031,
61
+ "support": 36380.0
62
+ },
63
+ "eval_runtime": 5.0448,
64
+ "eval_samples_per_second": 16.056,
65
+ "eval_steps_per_second": 2.18,
66
  "eval_weighted avg": {
67
+ "f1-score": 0.8748148382495958,
68
+ "precision": 0.8768575102351055,
69
+ "recall": 0.8856789444749863,
70
+ "support": 36380.0
71
  },
72
  "step": 81
73
  },
74
  {
75
  "epoch": 2.0,
76
  "eval_B-Claim": {
77
+ "f1-score": 0.5137931034482759,
78
+ "precision": 0.6182572614107884,
79
+ "recall": 0.43952802359882004,
80
+ "support": 339.0
81
  },
82
  "eval_B-MajorClaim": {
83
+ "f1-score": 0.7622641509433963,
84
+ "precision": 0.9619047619047619,
85
+ "recall": 0.63125,
86
+ "support": 160.0
87
  },
88
  "eval_B-Premise": {
89
+ "f1-score": 0.8853910477127397,
90
+ "precision": 0.8241758241758241,
91
+ "recall": 0.9564293304994687,
92
+ "support": 941.0
93
  },
94
  "eval_I-Claim": {
95
+ "f1-score": 0.5413588470388762,
96
+ "precision": 0.6279853891542568,
97
+ "recall": 0.47573435504469985,
98
+ "support": 4698.0
99
  },
100
  "eval_I-MajorClaim": {
101
+ "f1-score": 0.7949260042283298,
102
+ "precision": 0.856492027334852,
103
+ "recall": 0.7416173570019724,
104
+ "support": 2028.0
105
  },
106
  "eval_I-Premise": {
107
+ "f1-score": 0.9007064868336545,
108
+ "precision": 0.8614779777627618,
109
+ "recall": 0.9436780835744566,
110
+ "support": 14861.0
111
  },
112
  "eval_O": {
113
+ "f1-score": 0.9988389947942025,
114
+ "precision": 0.9990260713215463,
115
+ "recall": 0.9986519883172321,
116
+ "support": 13353.0
117
  },
118
+ "eval_accuracy": 0.8864211105002748,
119
+ "eval_loss": 0.2809496521949768,
120
  "eval_macro avg": {
121
+ "f1-score": 0.7710398049999251,
122
+ "precision": 0.8213313304378275,
123
+ "recall": 0.7409841625766643,
124
+ "support": 36380.0
125
+ },
126
+ "eval_runtime": 5.0579,
127
+ "eval_samples_per_second": 16.014,
128
+ "eval_steps_per_second": 2.175,
129
  "eval_weighted avg": {
130
+ "f1-score": 0.8798131143596267,
131
+ "precision": 0.8787439244541853,
132
+ "recall": 0.8864211105002748,
133
+ "support": 36380.0
134
  },
135
  "step": 162
136
  }
 
140
  "num_input_tokens_seen": 0,
141
  "num_train_epochs": 50,
142
  "save_steps": 500,
143
+ "total_flos": 286688514798000.0,
144
  "train_batch_size": 4,
145
  "trial_name": null,
146
  "trial_params": null
checkpoint-162/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2f0bdafd19c0347fe87a3f27a2ea54a847df1f75da4e3bbd7bf587c614e2949
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3de2ea286aed4cce53d86abf84d503faba79a292e98a5c89e444e2125b5ea5
3
  size 4920