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
1ab34ec
•
1 Parent(s): 96ac518

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 sha256:0b4542b21853e1a520a45ea1e759f1b12a247049e502660c3c7a3af47ec4c888
3
  size 592318676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd0b1233940dfb1aee155f5e24ea3cb0581d43e7980bdb20b05630cb80c77e2
3
  size 592318676
checkpoint-405/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bb6428161bb389496b431cae2295e87ba14005306b076e1aeffdb16159bb97f
3
  size 1014645498
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d98884dae279788debbf8bda338d89d5e9c22fe0eab3eda68f82611574d970d
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:d68d97adc90f9638b68f64674fd8773cc664d1043303df18c9b1b59a1cb82038
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf337692f531efc3a23b910237391cc3da6dc28e56ab2fbd5db20c81d4fb98bd
3
  size 14244
checkpoint-405/trainer_state.json CHANGED
@@ -11,195 +11,195 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_B": {
14
- "f1-score": 0.8266764382557715,
15
- "precision": 0.7866108786610879,
16
- "recall": 0.871042471042471,
17
- "support": 1295.0
18
  },
19
  "eval_I": {
20
- "f1-score": 0.9410658617447671,
21
- "precision": 0.9344077040239768,
22
- "recall": 0.9478195863443808,
23
- "support": 20065.0
24
  },
25
  "eval_O": {
26
- "f1-score": 0.8562443302086484,
27
- "precision": 0.8789421405512788,
28
- "recall": 0.8346893055064262,
29
- "support": 8481.0
30
  },
31
- "eval_accuracy": 0.912335377500754,
32
- "eval_loss": 0.2450982630252838,
33
  "eval_macro avg": {
34
- "f1-score": 0.8746622100697291,
35
- "precision": 0.8666535744121145,
36
- "recall": 0.8845171209644261,
37
- "support": 29841.0
38
- },
39
- "eval_runtime": 4.6269,
40
- "eval_samples_per_second": 17.29,
41
- "eval_steps_per_second": 2.161,
42
  "eval_weighted avg": {
43
- "f1-score": 0.9119949287205363,
44
- "precision": 0.9122301519092053,
45
- "recall": 0.912335377500754,
46
- "support": 29841.0
47
  },
48
  "step": 81
49
  },
50
  {
51
  "epoch": 2.0,
52
  "eval_B": {
53
- "f1-score": 0.8833395452851286,
54
- "precision": 0.8537463976945245,
55
- "recall": 0.915057915057915,
56
- "support": 1295.0
57
  },
58
  "eval_I": {
59
- "f1-score": 0.9549518227873249,
60
- "precision": 0.9516903430183636,
61
- "recall": 0.958235733864939,
62
- "support": 20065.0
63
  },
64
  "eval_O": {
65
- "f1-score": 0.88924750463212,
66
- "precision": 0.9016969696969697,
67
- "recall": 0.877137130055418,
68
- "support": 8481.0
69
  },
70
- "eval_accuracy": 0.9333132267685399,
71
- "eval_loss": 0.20076116919517517,
72
  "eval_macro avg": {
73
- "f1-score": 0.9091796242348579,
74
- "precision": 0.9023779034699526,
75
- "recall": 0.916810259659424,
76
- "support": 29841.0
77
- },
78
- "eval_runtime": 4.6524,
79
- "eval_samples_per_second": 17.195,
80
- "eval_steps_per_second": 2.149,
81
  "eval_weighted avg": {
82
- "f1-score": 0.9331705077630417,
83
- "precision": 0.9332314707173981,
84
- "recall": 0.9333132267685399,
85
- "support": 29841.0
86
  },
87
  "step": 162
88
  },
89
  {
90
  "epoch": 3.0,
91
  "eval_B": {
92
- "f1-score": 0.8927335640138409,
93
- "precision": 0.8889739663093414,
94
- "recall": 0.8965250965250965,
95
- "support": 1295.0
96
  },
97
  "eval_I": {
98
- "f1-score": 0.9590235396687009,
99
- "precision": 0.9586653386454184,
100
- "recall": 0.9593820084724645,
101
- "support": 20065.0
102
  },
103
  "eval_O": {
104
- "f1-score": 0.9006849315068494,
105
- "precision": 0.9020697811945594,
106
- "recall": 0.8993043273198915,
107
- "support": 8481.0
108
  },
109
- "eval_accuracy": 0.9395797727958178,
110
- "eval_loss": 0.19863653182983398,
111
  "eval_macro avg": {
112
- "f1-score": 0.9174806783964637,
113
- "precision": 0.9165696953831063,
114
- "recall": 0.9184038107724842,
115
- "support": 29841.0
116
- },
117
- "eval_runtime": 4.655,
118
- "eval_samples_per_second": 17.186,
119
- "eval_steps_per_second": 2.148,
120
  "eval_weighted avg": {
121
- "f1-score": 0.9395665759512081,
122
- "precision": 0.9395561516236713,
123
- "recall": 0.9395797727958178,
124
- "support": 29841.0
125
  },
126
  "step": 243
127
  },
128
  {
129
  "epoch": 4.0,
130
  "eval_B": {
131
- "f1-score": 0.8999616711383672,
132
- "precision": 0.893455098934551,
133
- "recall": 0.9065637065637066,
134
- "support": 1295.0
135
  },
136
  "eval_I": {
137
- "f1-score": 0.9612657113512985,
138
- "precision": 0.9436362763454799,
139
- "recall": 0.9795664091701969,
140
- "support": 20065.0
141
  },
142
  "eval_O": {
143
- "f1-score": 0.8996847765622102,
144
- "precision": 0.9454403741231489,
145
- "recall": 0.8581535196321188,
146
- "support": 8481.0
147
  },
148
- "eval_accuracy": 0.9418920277470594,
149
- "eval_loss": 0.19743724167346954,
150
  "eval_macro avg": {
151
- "f1-score": 0.920304053017292,
152
- "precision": 0.9275105831343932,
153
- "recall": 0.9147612117886741,
154
- "support": 29841.0
155
- },
156
- "eval_runtime": 4.6615,
157
- "eval_samples_per_second": 17.162,
158
- "eval_steps_per_second": 2.145,
159
  "eval_weighted avg": {
160
- "f1-score": 0.9411036309913238,
161
- "precision": 0.9419713163409645,
162
- "recall": 0.9418920277470594,
163
- "support": 29841.0
164
  },
165
  "step": 324
166
  },
167
  {
168
  "epoch": 5.0,
169
  "eval_B": {
170
- "f1-score": 0.8953846153846153,
171
- "precision": 0.8919540229885058,
172
- "recall": 0.8988416988416988,
173
- "support": 1295.0
174
  },
175
  "eval_I": {
176
- "f1-score": 0.9602426713742261,
177
- "precision": 0.9581224570804803,
178
- "recall": 0.9623722900573137,
179
- "support": 20065.0
180
  },
181
  "eval_O": {
182
- "f1-score": 0.9022119433078337,
183
- "precision": 0.9075399665950847,
184
- "recall": 0.8969461148449476,
185
- "support": 8481.0
186
  },
187
- "eval_accuracy": 0.9410207432726785,
188
- "eval_loss": 0.2340461015701294,
189
  "eval_macro avg": {
190
- "f1-score": 0.9192797433555584,
191
- "precision": 0.9192054822213569,
192
- "recall": 0.9193867012479867,
193
- "support": 29841.0
194
- },
195
- "eval_runtime": 4.6719,
196
- "eval_samples_per_second": 17.124,
197
- "eval_steps_per_second": 2.14,
198
  "eval_weighted avg": {
199
- "f1-score": 0.9409353496612266,
200
- "precision": 0.9408751053176122,
201
- "recall": 0.9410207432726785,
202
- "support": 29841.0
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": 718933263678000.0,
213
  "train_batch_size": 4,
214
  "trial_name": null,
215
  "trial_params": null
 
11
  {
12
  "epoch": 1.0,
13
  "eval_B": {
14
+ "f1-score": 0.7905866302864938,
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
  "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
checkpoint-405/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d229d7bc9127d222c880edfd3fa9418a9ccede656fe27f7f0aa04990c9605be4
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ca363922308e3892528dd031742ffedc372734b464a042d09444af9700901e
3
  size 4856