Hugging Face's logo

Theoreticallyhugo
/
longformer-simple

Token Classification
Transformers
Safetensors
longformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Theoreticallyhugo commited on
Commit
366285a
•
1 Parent(s): f4cae44

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 sha256:8e62698666c26f0113bedfd7a96468065c3cfdb715cc9ca53c409c6fd2dfe401
3
  size 592324828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df7ea7995417d16225c992d56281c23b56be8d8098ce194bdebfdc2e1d844bc4
3
  size 592324828
checkpoint-243/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85e5597180e12da6c3ba8c8f36fd77839bcb000a5d5fcc96939e7135a114be15
3
  size 1014657786
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:458cf0ca218c863fafe305e6645e66683ac7ad0df832c7323ab1e238cce38d3c
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": 0.38183790485045715,
15
- "precision": 0.6497890295358649,
16
- "recall": 0.27035330261136714,
17
- "support": 4557.0
18
  },
19
  "eval_MajorClaim": {
20
- "f1-score": 0.6266258607498087,
21
- "precision": 0.5535653937140926,
22
- "recall": 0.7219039224327898,
23
- "support": 2269.0
24
  },
25
  "eval_O": {
26
- "f1-score": 0.8545803971812939,
27
- "precision": 0.8443037974683544,
28
- "recall": 0.8651102464332037,
29
- "support": 8481.0
30
  },
31
  "eval_Premise": {
32
- "f1-score": 0.878949075575738,
33
- "precision": 0.8314310260186549,
34
- "recall": 0.9322278794550709,
35
- "support": 14534.0
36
  },
37
- "eval_accuracy": 0.7960859220535504,
38
- "eval_loss": 0.5359914898872375,
39
  "eval_macro avg": {
40
- "f1-score": 0.6854983095893245,
41
- "precision": 0.7197723116842417,
42
- "recall": 0.697398837733108,
43
- "support": 29841.0
44
- },
45
- "eval_runtime": 4.8191,
46
- "eval_samples_per_second": 16.601,
47
- "eval_steps_per_second": 2.075,
48
  "eval_weighted avg": {
49
- "f1-score": 0.7769240850962494,
50
- "precision": 0.7862232339538372,
51
- "recall": 0.7960859220535504,
52
- "support": 29841.0
53
  },
54
  "step": 81
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
- "f1-score": 0.6161300742974051,
60
- "precision": 0.6048625792811839,
61
- "recall": 0.6278253236778583,
62
- "support": 4557.0
63
  },
64
  "eval_MajorClaim": {
65
- "f1-score": 0.7920215150156881,
66
- "precision": 0.8057455540355677,
67
- "recall": 0.7787571617452622,
68
- "support": 2269.0
69
  },
70
  "eval_O": {
71
- "f1-score": 0.8922796352583586,
72
- "precision": 0.9209436566695947,
73
- "recall": 0.865346067680698,
74
- "support": 8481.0
75
  },
76
  "eval_Premise": {
77
- "f1-score": 0.8914289590611538,
78
- "precision": 0.8790554552143957,
79
- "recall": 0.9041557726709784,
80
- "support": 14534.0
81
  },
82
- "eval_accuracy": 0.8413927147213566,
83
- "eval_loss": 0.443877637386322,
84
  "eval_macro avg": {
85
- "f1-score": 0.7979650459081514,
86
- "precision": 0.8026518113001855,
87
- "recall": 0.7940210814436992,
88
- "support": 29841.0
89
- },
90
- "eval_runtime": 4.8087,
91
- "eval_samples_per_second": 16.637,
92
- "eval_steps_per_second": 2.08,
93
  "eval_weighted avg": {
94
- "f1-score": 0.842071433389123,
95
- "precision": 0.8435143116581857,
96
- "recall": 0.8413927147213566,
97
- "support": 29841.0
98
  },
99
  "step": 162
100
  },
101
  {
102
  "epoch": 3.0,
103
  "eval_Claim": {
104
- "f1-score": 0.6042799305957202,
105
- "precision": 0.6389432485322897,
106
- "recall": 0.5731841123546193,
107
- "support": 4557.0
108
  },
109
  "eval_MajorClaim": {
110
- "f1-score": 0.8349557522123894,
111
- "precision": 0.8382940915148823,
112
- "recall": 0.8316438959894227,
113
- "support": 2269.0
114
  },
115
  "eval_O": {
116
- "f1-score": 0.8941106484235574,
117
- "precision": 0.9022691799735862,
118
- "recall": 0.8860983374602052,
119
- "support": 8481.0
120
  },
121
  "eval_Premise": {
122
- "f1-score": 0.8917763490086511,
123
- "precision": 0.8729980887102089,
124
- "recall": 0.9113802119168846,
125
- "support": 14534.0
126
  },
127
- "eval_accuracy": 0.8464863778023525,
128
- "eval_loss": 0.4555923044681549,
129
  "eval_macro avg": {
130
- "f1-score": 0.8062806700600795,
131
- "precision": 0.8131261521827418,
132
- "recall": 0.8005766394302829,
133
- "support": 29841.0
134
- },
135
- "eval_runtime": 4.7811,
136
- "eval_samples_per_second": 16.733,
137
- "eval_steps_per_second": 2.092,
138
  "eval_weighted avg": {
139
- "f1-score": 0.8442159482345275,
140
- "precision": 0.8429359878649869,
141
- "recall": 0.8464863778023525,
142
- "support": 29841.0
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": 0.4888068880688806,
15
+ "precision": 0.6228840125391849,
16
+ "recall": 0.40222672064777326,
17
+ "support": 4940.0
18
  },
19
  "eval_MajorClaim": {
20
+ "f1-score": 0.7325278370054489,
21
+ "precision": 0.7604525332021643,
22
+ "recall": 0.706581352833638,
23
+ "support": 2188.0
24
  },
25
  "eval_O": {
26
+ "f1-score": 0.8634848138844484,
27
+ "precision": 0.827613377692173,
28
+ "recall": 0.902606702950444,
29
+ "support": 10473.0
30
  },
31
  "eval_Premise": {
32
+ "f1-score": 0.8792819197655248,
33
+ "precision": 0.8543458914268763,
34
+ "recall": 0.9057173407132524,
35
+ "support": 15899.0
36
  },
37
+ "eval_accuracy": 0.8174925373134329,
38
+ "eval_loss": 0.49806877970695496,
39
  "eval_macro avg": {
40
+ "f1-score": 0.7410253646810757,
41
+ "precision": 0.7663239537150996,
42
+ "recall": 0.7292830292862769,
43
+ "support": 33500.0
44
+ },
45
+ "eval_runtime": 4.9194,
46
+ "eval_samples_per_second": 16.465,
47
+ "eval_steps_per_second": 2.236,
48
  "eval_weighted avg": {
49
+ "f1-score": 0.8071778099281224,
50
+ "precision": 0.80572410140167,
51
+ "recall": 0.8174925373134329,
52
+ "support": 33500.0
53
  },
54
  "step": 81
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
+ "f1-score": 0.5993816254416962,
60
+ "precision": 0.6593780369290574,
61
+ "recall": 0.5493927125506073,
62
+ "support": 4940.0
63
  },
64
  "eval_MajorClaim": {
65
+ "f1-score": 0.8017817371937639,
66
+ "precision": 0.7197382769901853,
67
+ "recall": 0.9049360146252285,
68
+ "support": 2188.0
69
  },
70
  "eval_O": {
71
+ "f1-score": 0.9058997050147494,
72
+ "precision": 0.9337184554575859,
73
+ "recall": 0.8796906330564308,
74
+ "support": 10473.0
75
  },
76
  "eval_Premise": {
77
+ "f1-score": 0.8854737486606459,
78
+ "precision": 0.862579028987236,
79
+ "recall": 0.9096169570413234,
80
+ "support": 15899.0
81
  },
82
+ "eval_accuracy": 0.8468358208955223,
83
+ "eval_loss": 0.4562840759754181,
84
  "eval_macro avg": {
85
+ "f1-score": 0.7981342040777137,
86
+ "precision": 0.7938534495910161,
87
+ "recall": 0.8109090793183975,
88
+ "support": 33500.0
89
+ },
90
+ "eval_runtime": 4.904,
91
+ "eval_samples_per_second": 16.517,
92
+ "eval_steps_per_second": 2.243,
93
  "eval_weighted avg": {
94
+ "f1-score": 0.8442053257085675,
95
+ "precision": 0.8455251408465503,
96
+ "recall": 0.8468358208955223,
97
+ "support": 33500.0
98
  },
99
  "step": 162
100
  },
101
  {
102
  "epoch": 3.0,
103
  "eval_Claim": {
104
+ "f1-score": 0.6235462150581514,
105
+ "precision": 0.6285479226655697,
106
+ "recall": 0.6186234817813765,
107
+ "support": 4940.0
108
  },
109
  "eval_MajorClaim": {
110
+ "f1-score": 0.8338848444738584,
111
+ "precision": 0.8059701492537313,
112
+ "recall": 0.8638025594149908,
113
+ "support": 2188.0
114
  },
115
  "eval_O": {
116
+ "f1-score": 0.9066250826953974,
117
+ "precision": 0.8974646833193002,
118
+ "recall": 0.9159744103886184,
119
+ "support": 10473.0
120
  },
121
  "eval_Premise": {
122
+ "f1-score": 0.8827730692315017,
123
+ "precision": 0.8911176621379133,
124
+ "recall": 0.8745833071262343,
125
+ "support": 15899.0
126
  },
127
+ "eval_accuracy": 0.8490746268656716,
128
+ "eval_loss": 0.43820467591285706,
129
  "eval_macro avg": {
130
+ "f1-score": 0.8117073028647273,
131
+ "precision": 0.8057751043441286,
132
+ "recall": 0.818245939677805,
133
+ "support": 33500.0
134
+ },
135
+ "eval_runtime": 4.9179,
136
+ "eval_samples_per_second": 16.47,
137
+ "eval_steps_per_second": 2.237,
138
  "eval_weighted avg": {
139
+ "f1-score": 0.8488105033097496,
140
+ "precision": 0.8488213959184715,
141
+ "recall": 0.8490746268656716,
142
+ "support": 33500.0
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 sha256:19f05e33d3889e7c1ce1bf18bf9e16659f52e74109a304d618b5d09955736add
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da575726aa6fb9f10d3d3191c16916e8d9dc133cfc573c1d27486b346adcb4eb
3
  size 4856