Hugging Face's logo

Theoreticallyhugo
/
longformer-spans

Token Classification
Transformers
Safetensors
longformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Theoreticallyhugo commited on
Commit
858abb7
•
1 Parent(s): 4361faf

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 +76 -76
  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:ce5dc84ab03b203b715fb948b590e970dd72449fe1b22b4396a0a94301bfd4d0
3
  size 592318676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53190b17ff35b9ad5c167544ed90396f7280afc5ddb1a6c61af3086822d56282
3
  size 592318676
checkpoint-243/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcf2a4e55a2172f280f18f5a9d05ea311e58e5fcc8949faec6569d3d77faffb0
3
  size 1014645498
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f41c3702d7f6a6ba317df61e02a9051a0fb6bacbce78a09c7f9cf6aed36785a
3
  size 1014645498
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
@@ -11,117 +11,117 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_B": {
14
- "f1-score": 0.7905866302864938,
15
- "precision": 0.7768096514745308,
16
- "recall": 0.8048611111111111,
17
- "support": 1440.0
18
  },
19
  "eval_I": {
20
- "f1-score": 0.9005331227169513,
21
- "precision": 0.9637593111099372,
22
- "recall": 0.8450919534905267,
23
- "support": 21587.0
24
  },
25
  "eval_O": {
26
- "f1-score": 0.8288892663043479,
27
- "precision": 0.7463108800367001,
28
- "recall": 0.9320156593144275,
29
- "support": 10473.0
30
  },
31
- "eval_accuracy": 0.8705373134328358,
32
- "eval_loss": 0.32930415868759155,
33
  "eval_macro avg": {
34
- "f1-score": 0.8400030064359308,
35
- "precision": 0.8289599475403894,
36
- "recall": 0.8606562413053552,
37
- "support": 33500.0
38
  },
39
- "eval_runtime": 4.7349,
40
- "eval_samples_per_second": 17.107,
41
- "eval_steps_per_second": 2.323,
42
  "eval_weighted avg": {
43
- "f1-score": 0.8734092702599646,
44
- "precision": 0.8877430445874,
45
- "recall": 0.8705373134328358,
46
- "support": 33500.0
47
  },
48
  "step": 81
49
  },
50
  {
51
  "epoch": 2.0,
52
  "eval_B": {
53
- "f1-score": 0.8656218739579861,
54
- "precision": 0.8325849903784477,
55
- "recall": 0.9013888888888889,
56
- "support": 1440.0
57
  },
58
  "eval_I": {
59
- "f1-score": 0.9547168948727912,
60
- "precision": 0.9423736462093862,
61
- "recall": 0.9673877796822161,
62
- "support": 21587.0
63
  },
64
  "eval_O": {
65
- "f1-score": 0.9013528191962081,
66
- "precision": 0.9332379102341274,
67
- "recall": 0.8715745249689678,
68
- "support": 10473.0
69
  },
70
- "eval_accuracy": 0.9345970149253732,
71
- "eval_loss": 0.2162298709154129,
72
  "eval_macro avg": {
73
- "f1-score": 0.9072305293423284,
74
- "precision": 0.902732182273987,
75
- "recall": 0.9134503978466909,
76
- "support": 33500.0
77
  },
78
- "eval_runtime": 4.753,
79
- "eval_samples_per_second": 17.042,
80
- "eval_steps_per_second": 2.314,
81
  "eval_weighted avg": {
82
- "f1-score": 0.9342040950316517,
83
- "precision": 0.9347982961417612,
84
- "recall": 0.9345970149253732,
85
- "support": 33500.0
86
  },
87
  "step": 162
88
  },
89
  {
90
  "epoch": 3.0,
91
  "eval_B": {
92
- "f1-score": 0.8603587759409076,
93
- "precision": 0.8717034925160371,
94
- "recall": 0.8493055555555555,
95
- "support": 1440.0
96
  },
97
  "eval_I": {
98
- "f1-score": 0.9434195218082959,
99
- "precision": 0.9677057963955188,
100
- "recall": 0.9203224162690509,
101
- "support": 21587.0
102
  },
103
  "eval_O": {
104
- "f1-score": 0.8879310344827586,
105
- "precision": 0.8459410391631365,
106
- "recall": 0.9343072663038289,
107
- "support": 10473.0
108
  },
109
- "eval_accuracy": 0.9216417910447762,
110
- "eval_loss": 0.24082203209400177,
111
  "eval_macro avg": {
112
- "f1-score": 0.8972364440773206,
113
- "precision": 0.8951167760248975,
114
- "recall": 0.9013117460428117,
115
- "support": 33500.0
116
  },
117
- "eval_runtime": 4.7554,
118
- "eval_samples_per_second": 17.033,
119
- "eval_steps_per_second": 2.313,
120
  "eval_weighted avg": {
121
- "f1-score": 0.9225019575751797,
122
- "precision": 0.9255121957960801,
123
- "recall": 0.9216417910447762,
124
- "support": 33500.0
125
  },
126
  "step": 243
127
  }
@@ -131,7 +131,7 @@
131
  "num_input_tokens_seen": 0,
132
  "num_train_epochs": 50,
133
  "save_steps": 500,
134
- "total_flos": 430020331007400.0,
135
  "train_batch_size": 4,
136
  "trial_name": null,
137
  "trial_params": null
 
11
  {
12
  "epoch": 1.0,
13
  "eval_B": {
14
+ "f1-score": 0.8331822302810515,
15
+ "precision": 0.7901977644024075,
16
+ "recall": 0.8811121764141898,
17
+ "support": 1043.0
18
  },
19
  "eval_I": {
20
+ "f1-score": 0.9471294753175105,
21
+ "precision": 0.9443616777446711,
22
+ "recall": 0.9499135446685879,
23
+ "support": 17350.0
24
  },
25
  "eval_O": {
26
+ "f1-score": 0.8992868897421833,
27
+ "precision": 0.9103731674811195,
28
+ "recall": 0.8884673748103187,
29
+ "support": 9226.0
30
  },
31
+ "eval_accuracy": 0.9267895289474637,
32
+ "eval_loss": 0.20478281378746033,
33
  "eval_macro avg": {
34
+ "f1-score": 0.8931995317802484,
35
+ "precision": 0.8816442032093993,
36
+ "recall": 0.9064976986310321,
37
+ "support": 27619.0
38
  },
39
+ "eval_runtime": 4.6128,
40
+ "eval_samples_per_second": 17.343,
41
+ "eval_steps_per_second": 2.168,
42
  "eval_weighted avg": {
43
+ "f1-score": 0.9268447919078652,
44
+ "precision": 0.9271861479533134,
45
+ "recall": 0.9267895289474637,
46
+ "support": 27619.0
47
  },
48
  "step": 81
49
  },
50
  {
51
  "epoch": 2.0,
52
  "eval_B": {
53
+ "f1-score": 0.8682547399124939,
54
+ "precision": 0.8806706114398422,
55
+ "recall": 0.8561840843720039,
56
+ "support": 1043.0
57
  },
58
  "eval_I": {
59
+ "f1-score": 0.9590983771942466,
60
+ "precision": 0.9592919333448654,
61
+ "recall": 0.9589048991354466,
62
+ "support": 17350.0
63
  },
64
  "eval_O": {
65
+ "f1-score": 0.9226525313717006,
66
+ "precision": 0.9208594256100194,
67
+ "recall": 0.9244526338608281,
68
+ "support": 9226.0
69
  },
70
+ "eval_accuracy": 0.9435171439950758,
71
+ "eval_loss": 0.16574698686599731,
72
  "eval_macro avg": {
73
+ "f1-score": 0.9166685494928136,
74
+ "precision": 0.9202739901315756,
75
+ "recall": 0.9131805391227594,
76
+ "support": 27619.0
77
  },
78
+ "eval_runtime": 4.6238,
79
+ "eval_samples_per_second": 17.302,
80
+ "eval_steps_per_second": 2.163,
81
  "eval_weighted avg": {
82
+ "f1-score": 0.9434932036816766,
83
+ "precision": 0.9434846863370583,
84
+ "recall": 0.9435171439950758,
85
+ "support": 27619.0
86
  },
87
  "step": 162
88
  },
89
  {
90
  "epoch": 3.0,
91
  "eval_B": {
92
+ "f1-score": 0.8791725434884815,
93
+ "precision": 0.8625461254612546,
94
+ "recall": 0.8964525407478428,
95
+ "support": 1043.0
96
  },
97
  "eval_I": {
98
+ "f1-score": 0.9588372159825352,
99
+ "precision": 0.9557349825345015,
100
+ "recall": 0.9619596541786744,
101
+ "support": 17350.0
102
  },
103
  "eval_O": {
104
+ "f1-score": 0.9204284621270084,
105
+ "precision": 0.9282407407407407,
106
+ "recall": 0.9127465857359636,
107
+ "support": 9226.0
108
  },
109
+ "eval_accuracy": 0.9430464535283681,
110
+ "eval_loss": 0.15394224226474762,
111
  "eval_macro avg": {
112
+ "f1-score": 0.9194794071993417,
113
+ "precision": 0.9155072829121655,
114
+ "recall": 0.9237195935541602,
115
+ "support": 27619.0
116
  },
117
+ "eval_runtime": 4.6233,
118
+ "eval_samples_per_second": 17.303,
119
+ "eval_steps_per_second": 2.163,
120
  "eval_weighted avg": {
121
+ "f1-score": 0.9429985029052194,
122
+ "precision": 0.9430314866542512,
123
+ "recall": 0.9430464535283681,
124
+ "support": 27619.0
125
  },
126
  "step": 243
127
  }
 
131
  "num_input_tokens_seen": 0,
132
  "num_train_epochs": 50,
133
  "save_steps": 500,
134
+ "total_flos": 431359958206800.0,
135
  "train_batch_size": 4,
136
  "trial_name": null,
137
  "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:b8ca363922308e3892528dd031742ffedc372734b464a042d09444af9700901e
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821ca433db9ddb761291ab61fc06d651ad248cd9d560cdb25f7f905e5aaff14e
3
  size 4856