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
8583bcf
•
1 Parent(s): aaff610

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 sha256:9cd2a63171e72f0a694931c4ba3351045d88f50da53542569f086e3443fc394b
3
  size 592324828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4b7606e348234f3e6ebdda33abee6d91e81711e56681d919b19b481584749d
3
  size 592324828
checkpoint-243/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f976ceb585c4699ff467606cc56e095ea9564b3c2f4103f1b886712bd85ded3a
3
  size 1014657786
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67461af9c785d7f6cb0fdb109ae4677e287526b543a7f9bf4135df916f54995f
3
  size 1014657786
checkpoint-243/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4510120abb9e19965e0fc90a9342c8b839c7b334c4b005e1a74bbda01d4f51cc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:becd6836611c76f35df7d32580a0d0ecb16ccf6774d717a60f2504beb710244c
3
  size 14244
checkpoint-243/trainer_state.json CHANGED
@@ -11,135 +11,135 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_Claim": {
14
- "f1-score": 0.5385059461955894,
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
  }
@@ -149,7 +149,7 @@
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
 
11
  {
12
  "epoch": 1.0,
13
  "eval_Claim": {
14
+ "f1-score": 0.5254768748366867,
15
+ "precision": 0.5768789443488239,
16
+ "recall": 0.4824856046065259,
17
+ "support": 4168.0
18
  },
19
  "eval_MajorClaim": {
20
+ "f1-score": 0.7984361424847959,
21
+ "precision": 0.7495921696574225,
22
+ "recall": 0.854089219330855,
23
+ "support": 2152.0
24
  },
25
  "eval_O": {
26
+ "f1-score": 0.9990277532260916,
27
+ "precision": 0.9988511841640155,
28
+ "recall": 0.9992043847241867,
29
+ "support": 11312.0
30
  },
31
  "eval_Premise": {
32
+ "f1-score": 0.8854183656825966,
33
+ "precision": 0.8719781543651113,
34
+ "recall": 0.8992793837488611,
35
+ "support": 12073.0
36
  },
37
+ "eval_accuracy": 0.8755765022723447,
38
+ "eval_loss": 0.28303390741348267,
39
  "eval_macro avg": {
40
+ "f1-score": 0.8020897840575427,
41
+ "precision": 0.7993251131338432,
42
+ "recall": 0.8087646481026072,
43
+ "support": 29705.0
44
+ },
45
+ "eval_runtime": 4.8106,
46
+ "eval_samples_per_second": 16.63,
47
+ "eval_steps_per_second": 2.079,
48
  "eval_weighted avg": {
49
+ "f1-score": 0.8718761173649596,
50
+ "precision": 0.8700202202343714,
51
+ "recall": 0.8755765022723447,
52
+ "support": 29705.0
53
  },
54
  "step": 81
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
+ "f1-score": 0.5578782336033447,
60
+ "precision": 0.6124497991967871,
61
+ "recall": 0.5122360844529751,
62
+ "support": 4168.0
63
  },
64
  "eval_MajorClaim": {
65
+ "f1-score": 0.784421283598464,
66
+ "precision": 0.9571619812583668,
67
+ "recall": 0.6644981412639405,
68
+ "support": 2152.0
69
  },
70
  "eval_O": {
71
+ "f1-score": 0.9998674150351351,
72
+ "precision": 0.9997348652231551,
73
+ "recall": 1.0,
74
+ "support": 11312.0
75
  },
76
  "eval_Premise": {
77
+ "f1-score": 0.8977749872463995,
78
+ "precision": 0.8530201342281879,
79
+ "recall": 0.9474861260664292,
80
+ "support": 12073.0
81
  },
82
+ "eval_accuracy": 0.8859114627167144,
83
+ "eval_loss": 0.27363118529319763,
84
  "eval_macro avg": {
85
+ "f1-score": 0.8099854798708358,
86
+ "precision": 0.8555916949766242,
87
+ "recall": 0.7810550879458362,
88
+ "support": 29705.0
89
+ },
90
+ "eval_runtime": 4.7727,
91
+ "eval_samples_per_second": 16.762,
92
+ "eval_steps_per_second": 2.095,
93
  "eval_weighted avg": {
94
+ "f1-score": 0.8807489883812781,
95
+ "precision": 0.8826802296805741,
96
+ "recall": 0.8859114627167144,
97
+ "support": 29705.0
98
  },
99
  "step": 162
100
  },
101
  {
102
  "epoch": 3.0,
103
  "eval_Claim": {
104
+ "f1-score": 0.64760736196319,
105
+ "precision": 0.6627322953289804,
106
+ "recall": 0.6331573896353166,
107
+ "support": 4168.0
108
  },
109
  "eval_MajorClaim": {
110
+ "f1-score": 0.9016018306636155,
111
+ "precision": 0.8881875563570785,
112
+ "recall": 0.9154275092936803,
113
+ "support": 2152.0
114
  },
115
  "eval_O": {
116
+ "f1-score": 0.9996904982977407,
117
+ "precision": 1.0,
118
+ "recall": 0.9993811881188119,
119
+ "support": 11312.0
120
  },
121
  "eval_Premise": {
122
+ "f1-score": 0.8982820417748115,
123
+ "precision": 0.8936065573770492,
124
+ "recall": 0.9030067091857865,
125
+ "support": 12073.0
126
  },
127
+ "eval_accuracy": 0.9027436458508669,
128
+ "eval_loss": 0.22585685551166534,
129
  "eval_macro avg": {
130
+ "f1-score": 0.8617954331748394,
131
+ "precision": 0.861131602265777,
132
+ "recall": 0.8627431990583988,
133
+ "support": 29705.0
134
+ },
135
+ "eval_runtime": 4.8003,
136
+ "eval_samples_per_second": 16.666,
137
+ "eval_steps_per_second": 2.083,
138
  "eval_weighted avg": {
139
+ "f1-score": 0.9019670975035187,
140
+ "precision": 0.9013351218793044,
141
+ "recall": 0.9027436458508669,
142
+ "support": 29705.0
143
  },
144
  "step": 243
145
  }
 
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
checkpoint-243/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95e8ce1619d475b315f2cb3494747dc2424fb9856a35d6759fcf75e79995f1f1
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c4152f1ae85467509d6d1bf2d3b859abf08e786a1c118f9c84f899edc2df5d1
3
  size 4856