Hugging Face's logo

Theoreticallyhugo
/
longformer-sep_tok

Token Classification
Transformers
Safetensors
longformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Theoreticallyhugo commited on
Commit
b2ac03f
•
1 Parent(s): 562026d

Training in progress, epoch 3, checkpoint

Browse files
Files changed (5) hide show
  1. checkpoint-243/model.safetensors +1 -1
  2. checkpoint-243/optimizer.pt +1 -1
  3. checkpoint-243/rng_state.pth +1 -1
  4. checkpoint-243/trainer_state.json +91 -91
  5. checkpoint-243/training_args.bin +1 -1
checkpoint-243/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a429c78447e0828b91399a994d26703bdf849523ffc0d4141febf6f0e57f6d88
3
  size 592324828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd2a63171e72f0a694931c4ba3351045d88f50da53542569f086e3443fc394b
3
  size 592324828
checkpoint-243/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f48ea0755f6bdbbd9eba1e1d95716ffbb74c34d924ec85956d99eaaf23609adb
3
  size 1014657786
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f976ceb585c4699ff467606cc56e095ea9564b3c2f4103f1b886712bd85ded3a
3
  size 1014657786
checkpoint-243/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:becd6836611c76f35df7d32580a0d0ecb16ccf6774d717a60f2504beb710244c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4510120abb9e19965e0fc90a9342c8b839c7b334c4b005e1a74bbda01d4f51cc
3
  size 14244
checkpoint-243/trainer_state.json CHANGED
@@ -11,135 +11,135 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_Claim": {
14
- "f1-score": 0.5724454649827784,
15
- "precision": 0.6002889477486154,
16
- "recall": 0.5470704410796576,
17
- "support": 4557.0
18
  },
19
  "eval_MajorClaim": {
20
- "f1-score": 0.7860447185813415,
21
- "precision": 0.698526892771497,
22
- "recall": 0.8986337593653592,
23
- "support": 2269.0
24
  },
25
  "eval_O": {
26
- "f1-score": 0.9987820830889982,
27
- "precision": 0.9975671292124707,
28
- "recall": 1.0,
29
- "support": 11071.0
30
  },
31
  "eval_Premise": {
32
- "f1-score": 0.8965445389824622,
33
- "precision": 0.9051258677512096,
34
- "recall": 0.8881243979633962,
35
- "support": 14534.0
36
  },
37
- "eval_accuracy": 0.8791279948197712,
38
- "eval_loss": 0.3157936632633209,
39
  "eval_macro avg": {
40
- "f1-score": 0.8134542014088951,
41
- "precision": 0.8003772093709481,
42
- "recall": 0.8334571496021033,
43
- "support": 32431.0
44
- },
45
- "eval_runtime": 4.8184,
46
- "eval_samples_per_second": 16.603,
47
- "eval_steps_per_second": 2.075,
48
  "eval_weighted avg": {
49
- "f1-score": 0.8781740995293698,
50
- "precision": 0.8793943851252293,
51
- "recall": 0.8791279948197712,
52
- "support": 32431.0
53
  },
54
  "step": 81
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
- "f1-score": 0.6090644692195831,
60
- "precision": 0.680108254397835,
61
- "recall": 0.5514592933947773,
62
- "support": 4557.0
63
  },
64
  "eval_MajorClaim": {
65
- "f1-score": 0.8585858585858586,
66
- "precision": 0.8960229995208433,
67
- "recall": 0.8241516086381666,
68
- "support": 2269.0
69
  },
70
  "eval_O": {
71
- "f1-score": 0.999458141425088,
72
- "precision": 0.9992776523702032,
73
- "recall": 0.9996386956914461,
74
- "support": 11071.0
75
  },
76
  "eval_Premise": {
77
- "f1-score": 0.9105885478942475,
78
- "precision": 0.8801849235905997,
79
- "recall": 0.9431677445988716,
80
- "support": 14534.0
81
  },
82
- "eval_accuracy": 0.8990780426135487,
83
- "eval_loss": 0.24451124668121338,
84
  "eval_macro avg": {
85
- "f1-score": 0.8444242542811943,
86
- "precision": 0.8638984574698704,
87
- "recall": 0.8296043355808155,
88
- "support": 32431.0
89
- },
90
- "eval_runtime": 4.8529,
91
- "eval_samples_per_second": 16.485,
92
- "eval_steps_per_second": 2.061,
93
  "eval_weighted avg": {
94
- "f1-score": 0.8949194640367888,
95
- "precision": 0.8938342965082798,
96
- "recall": 0.8990780426135487,
97
- "support": 32431.0
98
  },
99
  "step": 162
100
  },
101
  {
102
  "epoch": 3.0,
103
  "eval_Claim": {
104
- "f1-score": 0.6542320859402667,
105
- "precision": 0.7079713847726111,
106
- "recall": 0.60807548825982,
107
- "support": 4557.0
108
  },
109
  "eval_MajorClaim": {
110
- "f1-score": 0.8915187376725839,
111
- "precision": 0.8866608544027899,
112
- "recall": 0.8964301454385192,
113
- "support": 2269.0
114
  },
115
  "eval_O": {
116
- "f1-score": 0.9995936611133684,
117
- "precision": 0.9992778479870013,
118
- "recall": 0.9999096739228616,
119
- "support": 11071.0
120
  },
121
  "eval_Premise": {
122
- "f1-score": 0.9157990498332153,
123
- "precision": 0.8973258501155497,
124
- "recall": 0.935048850970139,
125
- "support": 14534.0
126
  },
127
- "eval_accuracy": 0.9085442940396534,
128
- "eval_loss": 0.22665414214134216,
129
  "eval_macro avg": {
130
- "f1-score": 0.8652858836398586,
131
- "precision": 0.872808984319488,
132
- "recall": 0.8598660396478349,
133
- "support": 32431.0
134
- },
135
- "eval_runtime": 4.8494,
136
- "eval_samples_per_second": 16.497,
137
- "eval_steps_per_second": 2.062,
138
  "eval_weighted avg": {
139
- "f1-score": 0.9059516032151627,
140
- "precision": 0.9047762338408377,
141
- "recall": 0.9085442940396534,
142
- "support": 32431.0
143
  },
144
  "step": 243
145
  }
@@ -149,7 +149,7 @@
149
  "num_input_tokens_seen": 0,
150
  "num_train_epochs": 50,
151
  "save_steps": 500,
152
- "total_flos": 431366198180400.0,
153
  "train_batch_size": 4,
154
  "trial_name": null,
155
  "trial_params": null
 
11
  {
12
  "epoch": 1.0,
13
  "eval_Claim": {
14
+ "f1-score": 0.5385059461955894,
15
+ "precision": 0.6267132491265789,
16
+ "recall": 0.4720647773279352,
17
+ "support": 4940.0
18
  },
19
  "eval_MajorClaim": {
20
+ "f1-score": 0.7814784727863526,
21
+ "precision": 0.9588039867109635,
22
+ "recall": 0.6595063985374772,
23
+ "support": 2188.0
24
  },
25
  "eval_O": {
26
+ "f1-score": 0.9938608715302625,
27
+ "precision": 0.9996969237763298,
28
+ "recall": 0.9880925634688834,
29
+ "support": 13353.0
30
  },
31
  "eval_Premise": {
32
+ "f1-score": 0.8968837690149166,
33
+ "precision": 0.8455112497215416,
34
+ "recall": 0.954902824076986,
35
+ "support": 15899.0
36
  },
37
+ "eval_accuracy": 0.8837548103353491,
38
+ "eval_loss": 0.2860471308231354,
39
  "eval_macro avg": {
40
+ "f1-score": 0.8026822648817803,
41
+ "precision": 0.8576813523338533,
42
+ "recall": 0.7686416408528204,
43
+ "support": 36380.0
44
+ },
45
+ "eval_runtime": 4.9572,
46
+ "eval_samples_per_second": 16.34,
47
+ "eval_steps_per_second": 2.219,
48
  "eval_weighted avg": {
49
+ "f1-score": 0.8768739289107891,
50
+ "precision": 0.8792073379911217,
51
+ "recall": 0.8837548103353491,
52
+ "support": 36380.0
53
  },
54
  "step": 81
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
+ "f1-score": 0.6469459868753155,
60
+ "precision": 0.6453172205438067,
61
+ "recall": 0.648582995951417,
62
+ "support": 4940.0
63
  },
64
  "eval_MajorClaim": {
65
+ "f1-score": 0.8435970110796187,
66
+ "precision": 0.9669226225634967,
67
+ "recall": 0.7481718464351006,
68
+ "support": 2188.0
69
  },
70
  "eval_O": {
71
+ "f1-score": 0.998877245508982,
72
+ "precision": 0.9983541557567143,
73
+ "recall": 0.9994008836965476,
74
+ "support": 13353.0
75
  },
76
  "eval_Premise": {
77
+ "f1-score": 0.9099026477336144,
78
+ "precision": 0.8972179761540813,
79
+ "recall": 0.922951129001824,
80
+ "support": 15899.0
81
  },
82
+ "eval_accuracy": 0.903243540406817,
83
+ "eval_loss": 0.24885737895965576,
84
  "eval_macro avg": {
85
+ "f1-score": 0.8498307227993828,
86
+ "precision": 0.8769529937545246,
87
+ "recall": 0.8297767137712222,
88
+ "support": 36380.0
89
+ },
90
+ "eval_runtime": 5.0097,
91
+ "eval_samples_per_second": 16.169,
92
+ "eval_steps_per_second": 2.196,
93
  "eval_weighted avg": {
94
+ "f1-score": 0.9028656814459712,
95
+ "precision": 0.9043261520711511,
96
+ "recall": 0.903243540406817,
97
+ "support": 36380.0
98
  },
99
  "step": 162
100
  },
101
  {
102
  "epoch": 3.0,
103
  "eval_Claim": {
104
+ "f1-score": 0.7040630102775911,
105
+ "precision": 0.6698958142935478,
106
+ "recall": 0.7419028340080972,
107
+ "support": 4940.0
108
  },
109
  "eval_MajorClaim": {
110
+ "f1-score": 0.8888411094388303,
111
+ "precision": 0.8392204628501827,
112
+ "recall": 0.9446983546617916,
113
+ "support": 2188.0
114
  },
115
  "eval_O": {
116
+ "f1-score": 0.998989104796136,
117
+ "precision": 0.9988769092542678,
118
+ "recall": 0.9991013255448213,
119
+ "support": 13353.0
120
  },
121
  "eval_Premise": {
122
+ "f1-score": 0.914582593823615,
123
+ "precision": 0.9390987408880053,
124
+ "recall": 0.8913139191144097,
125
+ "support": 15899.0
126
  },
127
+ "eval_accuracy": 0.9137987905442551,
128
+ "eval_loss": 0.24298855662345886,
129
  "eval_macro avg": {
130
+ "f1-score": 0.8766189545840432,
131
+ "precision": 0.8617729818215009,
132
+ "recall": 0.8942541083322799,
133
+ "support": 36380.0
134
+ },
135
+ "eval_runtime": 4.9876,
136
+ "eval_samples_per_second": 16.24,
137
+ "eval_steps_per_second": 2.205,
138
  "eval_weighted avg": {
139
+ "f1-score": 0.9154289662937856,
140
+ "precision": 0.9184781183611038,
141
+ "recall": 0.9137987905442551,
142
+ "support": 36380.0
143
  },
144
  "step": 243
145
  }
 
149
  "num_input_tokens_seen": 0,
150
  "num_train_epochs": 50,
151
  "save_steps": 500,
152
+ "total_flos": 430026551602200.0,
153
  "train_batch_size": 4,
154
  "trial_name": null,
155
  "trial_params": null
checkpoint-243/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2dd7b387b7349843b62a9d5b4facde1d14a6a35003d55f9e21a477105ecd1d3
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e8ce1619d475b315f2cb3494747dc2424fb9856a35d6759fcf75e79995f1f1
3
  size 4856