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
f4d92c0
•
1 Parent(s): 535f8b9

Training in progress, epoch 4, checkpoint

Browse files
Files changed (5) hide show
  1. checkpoint-324/model.safetensors +1 -1
  2. checkpoint-324/optimizer.pt +1 -1
  3. checkpoint-324/rng_state.pth +1 -1
  4. checkpoint-324/trainer_state.json +121 -121
  5. checkpoint-324/training_args.bin +1 -1
checkpoint-324/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5fe1adae011a782352680b73a860ddaad1ad1d087f47d3dadb9c901fc6d8cb2
3
  size 592324828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67bba726d5b93a5953d8c322309502f56f3d294303980872106da73402842fcd
3
  size 592324828
checkpoint-324/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2492b7297930901696c6034172664ac0dfc2ef8822581792774047f784fb6a67
3
  size 1014657786
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad7419a2296c7b12859acd3f69a8a13a0da0939bc756ffeb1fd315ac1573d369
3
  size 1014657786
checkpoint-324/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd95f0f86efa354df6a4222f1c9e390b588b8fcd802633d848de21a27eedcb23
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5474bfb178f1f5ac14d6be6fd7772f757be3e1728e1b25f0f54ac7eff70dac62
3
  size 14244
checkpoint-324/trainer_state.json CHANGED
@@ -11,180 +11,180 @@
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
  },
146
  {
147
  "epoch": 4.0,
148
  "eval_Claim": {
149
- "f1-score": 0.6415287144900879,
150
- "precision": 0.6477507222451506,
151
- "recall": 0.6354251012145749,
152
- "support": 4940.0
153
  },
154
  "eval_MajorClaim": {
155
- "f1-score": 0.8005126014523707,
156
- "precision": 0.7514033680834001,
157
- "recall": 0.856489945155393,
158
- "support": 2188.0
159
  },
160
  "eval_O": {
161
- "f1-score": 0.9065169636319258,
162
- "precision": 0.9273871354374751,
163
- "recall": 0.8865654540246348,
164
- "support": 10473.0
165
  },
166
  "eval_Premise": {
167
- "f1-score": 0.8932505382719131,
168
- "precision": 0.8863636363636364,
169
- "recall": 0.9002452984464432,
170
- "support": 15899.0
171
  },
172
- "eval_accuracy": 0.8540597014925373,
173
- "eval_loss": 0.4749625325202942,
174
  "eval_macro avg": {
175
- "f1-score": 0.8104522044615743,
176
- "precision": 0.8032262155324155,
177
- "recall": 0.8196814497102615,
178
- "support": 33500.0
179
- },
180
- "eval_runtime": 4.8972,
181
- "eval_samples_per_second": 16.54,
182
- "eval_steps_per_second": 2.246,
183
  "eval_weighted avg": {
184
- "f1-score": 0.8542213698406307,
185
- "precision": 0.8551874645146165,
186
- "recall": 0.8540597014925373,
187
- "support": 33500.0
188
  },
189
  "step": 324
190
  }
@@ -194,7 +194,7 @@
194
  "num_input_tokens_seen": 0,
195
  "num_train_epochs": 50,
196
  "save_steps": 500,
197
- "total_flos": 573368735469600.0,
198
  "train_batch_size": 4,
199
  "trial_name": null,
200
  "trial_params": null
 
11
  {
12
  "epoch": 1.0,
13
  "eval_Claim": {
14
+ "f1-score": 0.41092129347162903,
15
+ "precision": 0.5640703517587939,
16
+ "recall": 0.32317658349328215,
17
+ "support": 4168.0
18
  },
19
  "eval_MajorClaim": {
20
+ "f1-score": 0.6523102655237298,
21
+ "precision": 0.5929304446978335,
22
+ "recall": 0.724907063197026,
23
+ "support": 2152.0
24
  },
25
  "eval_O": {
26
+ "f1-score": 0.8834432924913603,
27
+ "precision": 0.8545380875202593,
28
+ "recall": 0.9143724257533059,
29
+ "support": 9226.0
30
  },
31
  "eval_Premise": {
32
+ "f1-score": 0.8664166767469054,
33
+ "precision": 0.8441231929604023,
34
+ "recall": 0.8899196554294707,
35
+ "support": 12073.0
36
  },
37
+ "eval_accuracy": 0.7997031029363844,
38
+ "eval_loss": 0.5104541182518005,
39
  "eval_macro avg": {
40
+ "f1-score": 0.7032728820584061,
41
+ "precision": 0.7139155192343223,
42
+ "recall": 0.7130939319682712,
43
+ "support": 27619.0
44
+ },
45
+ "eval_runtime": 4.7759,
46
+ "eval_samples_per_second": 16.751,
47
+ "eval_steps_per_second": 2.094,
48
  "eval_weighted avg": {
49
+ "f1-score": 0.7866826459135919,
50
+ "precision": 0.7857670171690952,
51
+ "recall": 0.7997031029363844,
52
+ "support": 27619.0
53
  },
54
  "step": 81
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
+ "f1-score": 0.5200312174817897,
60
+ "precision": 0.5678977272727272,
61
+ "recall": 0.47960652591170827,
62
+ "support": 4168.0
63
  },
64
  "eval_MajorClaim": {
65
+ "f1-score": 0.7526302911671151,
66
+ "precision": 0.7948320413436692,
67
+ "recall": 0.7146840148698885,
68
+ "support": 2152.0
69
  },
70
  "eval_O": {
71
+ "f1-score": 0.9116096466629278,
72
+ "precision": 0.944560669456067,
73
+ "recall": 0.8808801213960546,
74
+ "support": 9226.0
75
  },
76
  "eval_Premise": {
77
+ "f1-score": 0.8738735224125151,
78
+ "precision": 0.8259587020648967,
79
+ "recall": 0.9276898865236478,
80
+ "support": 12073.0
81
  },
82
+ "eval_accuracy": 0.8278359100619139,
83
+ "eval_loss": 0.44692954421043396,
84
  "eval_macro avg": {
85
+ "f1-score": 0.7645361694310869,
86
+ "precision": 0.7833122850343401,
87
+ "recall": 0.7507151371753248,
88
+ "support": 27619.0
89
+ },
90
+ "eval_runtime": 4.7439,
91
+ "eval_samples_per_second": 16.864,
92
+ "eval_steps_per_second": 2.108,
93
  "eval_weighted avg": {
94
+ "f1-score": 0.8236335905447046,
95
+ "precision": 0.8242076985653165,
96
+ "recall": 0.8278359100619139,
97
+ "support": 27619.0
98
  },
99
  "step": 162
100
  },
101
  {
102
  "epoch": 3.0,
103
  "eval_Claim": {
104
+ "f1-score": 0.6218357913273168,
105
+ "precision": 0.5744204961366409,
106
+ "recall": 0.6777831094049904,
107
+ "support": 4168.0
108
  },
109
  "eval_MajorClaim": {
110
+ "f1-score": 0.7799868909766223,
111
+ "precision": 0.7360824742268042,
112
+ "recall": 0.8294609665427509,
113
+ "support": 2152.0
114
  },
115
  "eval_O": {
116
+ "f1-score": 0.9093637121422617,
117
+ "precision": 0.9330596419204014,
118
+ "recall": 0.8868415347929763,
119
+ "support": 9226.0
120
  },
121
  "eval_Premise": {
122
+ "f1-score": 0.876420695504665,
123
+ "precision": 0.89797514556357,
124
+ "recall": 0.855876749772219,
125
+ "support": 12073.0
126
  },
127
+ "eval_accuracy": 0.8372859263550454,
128
+ "eval_loss": 0.40934404730796814,
129
  "eval_macro avg": {
130
+ "f1-score": 0.7969017724877165,
131
+ "precision": 0.7853844394618541,
132
+ "recall": 0.8124905901282342,
133
+ "support": 27619.0
134
+ },
135
+ "eval_runtime": 4.7941,
136
+ "eval_samples_per_second": 16.687,
137
+ "eval_steps_per_second": 2.086,
138
  "eval_weighted avg": {
139
+ "f1-score": 0.8414917278933443,
140
+ "precision": 0.8482528803063183,
141
+ "recall": 0.8372859263550454,
142
+ "support": 27619.0
143
  },
144
  "step": 243
145
  },
146
  {
147
  "epoch": 4.0,
148
  "eval_Claim": {
149
+ "f1-score": 0.608644284729743,
150
+ "precision": 0.516112873601603,
151
+ "recall": 0.7416026871401151,
152
+ "support": 4168.0
153
  },
154
  "eval_MajorClaim": {
155
+ "f1-score": 0.788337924701561,
156
+ "precision": 0.7790381125226861,
157
+ "recall": 0.7978624535315985,
158
+ "support": 2152.0
159
  },
160
  "eval_O": {
161
+ "f1-score": 0.9068679925629612,
162
+ "precision": 0.9442684500762643,
163
+ "recall": 0.8723173639713853,
164
+ "support": 9226.0
165
  },
166
  "eval_Premise": {
167
+ "f1-score": 0.8528029247910863,
168
+ "precision": 0.8985600293497202,
169
+ "recall": 0.8114801623457302,
170
+ "support": 12073.0
171
  },
172
+ "eval_accuracy": 0.8201962417176581,
173
+ "eval_loss": 0.5160673260688782,
174
  "eval_macro avg": {
175
+ "f1-score": 0.789163281696338,
176
+ "precision": 0.7844948663875684,
177
+ "recall": 0.8058156667472073,
178
+ "support": 27619.0
179
+ },
180
+ "eval_runtime": 4.7669,
181
+ "eval_samples_per_second": 16.782,
182
+ "eval_steps_per_second": 2.098,
183
  "eval_weighted avg": {
184
+ "f1-score": 0.8289940404467937,
185
+ "precision": 0.8468005514342695,
186
+ "recall": 0.8201962417176581,
187
+ "support": 27619.0
188
  },
189
  "step": 324
190
  }
 
194
  "num_input_tokens_seen": 0,
195
  "num_train_epochs": 50,
196
  "save_steps": 500,
197
+ "total_flos": 575154930907200.0,
198
  "train_batch_size": 4,
199
  "trial_name": null,
200
  "trial_params": null
checkpoint-324/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da575726aa6fb9f10d3d3191c16916e8d9dc133cfc573c1d27486b346adcb4eb
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e651c478af6098730eda01c59bbe4834fbad7ed476e7ec6e4265141ee6647e9
3
  size 4856