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
f118f35
•
1 Parent(s): b3c2869

Training in progress, epoch 5, checkpoint

Browse files
Files changed (5) hide show
  1. checkpoint-405/model.safetensors +1 -1
  2. checkpoint-405/optimizer.pt +1 -1
  3. checkpoint-405/rng_state.pth +1 -1
  4. checkpoint-405/trainer_state.json +131 -131
  5. checkpoint-405/training_args.bin +1 -1
checkpoint-405/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bd0b1233940dfb1aee155f5e24ea3cb0581d43e7980bdb20b05630cb80c77e2
3
  size 592318676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c3c53af1e11b0efb705437f67aa0454d72b34e66fa350958d60d244368a055
3
  size 592318676
checkpoint-405/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d98884dae279788debbf8bda338d89d5e9c22fe0eab3eda68f82611574d970d
3
  size 1014645498
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e99e8f2fb936a72c4972883d1c0d5205081d7b6e728a42df62a4c911282d59f
3
  size 1014645498
checkpoint-405/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf337692f531efc3a23b910237391cc3da6dc28e56ab2fbd5db20c81d4fb98bd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d68d97adc90f9638b68f64674fd8773cc664d1043303df18c9b1b59a1cb82038
3
  size 14244
checkpoint-405/trainer_state.json CHANGED
@@ -11,195 +11,195 @@
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
  },
128
  {
129
  "epoch": 4.0,
130
  "eval_B": {
131
- "f1-score": 0.8804020100502512,
132
- "precision": 0.8504854368932039,
133
- "recall": 0.9125,
134
- "support": 1440.0
135
  },
136
  "eval_I": {
137
- "f1-score": 0.9589184992350025,
138
- "precision": 0.945595388218339,
139
- "recall": 0.9726224116366332,
140
- "support": 21587.0
141
  },
142
  "eval_O": {
143
- "f1-score": 0.9091178797468354,
144
- "precision": 0.9427750999897446,
145
- "recall": 0.877780960565263,
146
- "support": 10473.0
147
  },
148
- "eval_accuracy": 0.9403880597014925,
149
- "eval_loss": 0.22083505988121033,
150
  "eval_macro avg": {
151
- "f1-score": 0.9161461296773631,
152
- "precision": 0.9129519750337626,
153
- "recall": 0.9209677907339654,
154
- "support": 33500.0
155
- },
156
- "eval_runtime": 4.7449,
157
- "eval_samples_per_second": 17.071,
158
- "eval_steps_per_second": 2.318,
159
  "eval_weighted avg": {
160
- "f1-score": 0.9399744505088647,
161
- "precision": 0.9406253819936745,
162
- "recall": 0.9403880597014925,
163
- "support": 33500.0
164
  },
165
  "step": 324
166
  },
167
  {
168
  "epoch": 5.0,
169
  "eval_B": {
170
- "f1-score": 0.8879781420765027,
171
- "precision": 0.8736559139784946,
172
- "recall": 0.9027777777777778,
173
- "support": 1440.0
174
  },
175
  "eval_I": {
176
- "f1-score": 0.9613201259451634,
177
- "precision": 0.9539317642765919,
178
- "recall": 0.9688238291564367,
179
- "support": 21587.0
180
  },
181
  "eval_O": {
182
- "f1-score": 0.916006030835076,
183
- "precision": 0.9334853291038858,
184
- "recall": 0.899169292466342,
185
- "support": 10473.0
186
  },
187
- "eval_accuracy": 0.9442089552238806,
188
- "eval_loss": 0.2257838249206543,
189
  "eval_macro avg": {
190
- "f1-score": 0.921768099618914,
191
- "precision": 0.9203576691196576,
192
- "recall": 0.9235902998001855,
193
- "support": 33500.0
194
- },
195
- "eval_runtime": 4.7845,
196
- "eval_samples_per_second": 16.93,
197
- "eval_steps_per_second": 2.299,
198
  "eval_weighted avg": {
199
- "f1-score": 0.9440011117702735,
200
- "precision": 0.9440889959185916,
201
- "recall": 0.9442089552238806,
202
- "support": 33500.0
203
  },
204
  "step": 405
205
  }
@@ -209,7 +209,7 @@
209
  "num_input_tokens_seen": 0,
210
  "num_train_epochs": 50,
211
  "save_steps": 500,
212
- "total_flos": 716700551679000.0,
213
  "train_batch_size": 4,
214
  "trial_name": null,
215
  "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
  },
128
  {
129
  "epoch": 4.0,
130
  "eval_B": {
131
+ "f1-score": 0.8800746616892207,
132
+ "precision": 0.8572727272727273,
133
+ "recall": 0.9041227229146692,
134
+ "support": 1043.0
135
  },
136
  "eval_I": {
137
+ "f1-score": 0.9537844036697248,
138
+ "precision": 0.9488876212207644,
139
+ "recall": 0.9587319884726225,
140
+ "support": 17350.0
141
  },
142
  "eval_O": {
143
+ "f1-score": 0.9100192149327477,
144
+ "precision": 0.9220157970853265,
145
+ "recall": 0.8983308042488619,
146
+ "support": 9226.0
147
  },
148
+ "eval_accuracy": 0.9364929939534379,
149
+ "eval_loss": 0.19801080226898193,
150
  "eval_macro avg": {
151
+ "f1-score": 0.9146260934305644,
152
+ "precision": 0.9093920485262728,
153
+ "recall": 0.9203951718787179,
154
+ "support": 27619.0
155
+ },
156
+ "eval_runtime": 4.6132,
157
+ "eval_samples_per_second": 17.342,
158
+ "eval_steps_per_second": 2.168,
159
  "eval_weighted avg": {
160
+ "f1-score": 0.9363812792925563,
161
+ "precision": 0.9364514800186444,
162
+ "recall": 0.9364929939534379,
163
+ "support": 27619.0
164
  },
165
  "step": 324
166
  },
167
  {
168
  "epoch": 5.0,
169
  "eval_B": {
170
+ "f1-score": 0.883877159309021,
171
+ "precision": 0.8847262247838616,
172
+ "recall": 0.8830297219558965,
173
+ "support": 1043.0
174
  },
175
  "eval_I": {
176
+ "f1-score": 0.9591500482927107,
177
+ "precision": 0.9456643513331839,
178
+ "recall": 0.9730259365994236,
179
+ "support": 17350.0
180
  },
181
  "eval_O": {
182
+ "f1-score": 0.9191176470588236,
183
+ "precision": 0.9454503781801513,
184
+ "recall": 0.8942120095382614,
185
+ "support": 9226.0
186
  },
187
+ "eval_accuracy": 0.9432999022412107,
188
+ "eval_loss": 0.20074255764484406,
189
  "eval_macro avg": {
190
+ "f1-score": 0.9207149515535183,
191
+ "precision": 0.9252803180990656,
192
+ "recall": 0.9167558893645271,
193
+ "support": 27619.0
194
+ },
195
+ "eval_runtime": 4.6092,
196
+ "eval_samples_per_second": 17.356,
197
+ "eval_steps_per_second": 2.17,
198
  "eval_weighted avg": {
199
+ "f1-score": 0.9429348139614955,
200
+ "precision": 0.9432916158141273,
201
+ "recall": 0.9432999022412107,
202
+ "support": 27619.0
203
  },
204
  "step": 405
205
  }
 
209
  "num_input_tokens_seen": 0,
210
  "num_train_epochs": 50,
211
  "save_steps": 500,
212
+ "total_flos": 718933263678000.0,
213
  "train_batch_size": 4,
214
  "trial_name": null,
215
  "trial_params": null
checkpoint-405/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