Hugging Face's logo

Theoreticallyhugo
/
longformer-sep_tok_full_labels

Token Classification
Transformers
Safetensors
longformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Theoreticallyhugo commited on
Commit
7322aff
•
1 Parent(s): 45eb420

Training in progress, epoch 24, checkpoint

Browse files
Files changed (12) hide show
  1. checkpoint-1944/config.json +61 -0
  2. checkpoint-1944/merges.txt +0 -0
  3. checkpoint-1944/model.safetensors +3 -0
  4. checkpoint-1944/optimizer.pt +3 -0
  5. checkpoint-1944/rng_state.pth +3 -0
  6. checkpoint-1944/scheduler.pt +3 -0
  7. checkpoint-1944/special_tokens_map.json +15 -0
  8. checkpoint-1944/tokenizer.json +0 -0
  9. checkpoint-1944/tokenizer_config.json +57 -0
  10. checkpoint-1944/trainer_state.json +1554 -0
  11. checkpoint-1944/training_args.bin +3 -0
  12. checkpoint-1944/vocab.json +0 -0
checkpoint-1944/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-base-4096",
3
+ "architectures": [
4
+ "LongformerForTokenClassification"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 700,
10
+ 700,
11
+ 700,
12
+ 700,
13
+ 700,
14
+ 700,
15
+ 700,
16
+ 700,
17
+ 700,
18
+ 700,
19
+ 700,
20
+ 700
21
+ ],
22
+ "bos_token_id": 0,
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "id2label": {
29
+ "0": "O",
30
+ "1": "B-MajorClaim",
31
+ "2": "I-MajorClaim",
32
+ "3": "B-Claim",
33
+ "4": "I-Claim",
34
+ "5": "B-Premise",
35
+ "6": "I-Premise"
36
+ },
37
+ "ignore_attention_mask": false,
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "label2id": {
41
+ "B-Claim": 3,
42
+ "B-MajorClaim": 1,
43
+ "B-Premise": 5,
44
+ "I-Claim": 4,
45
+ "I-MajorClaim": 2,
46
+ "I-Premise": 6,
47
+ "O": 0
48
+ },
49
+ "layer_norm_eps": 1e-05,
50
+ "max_position_embeddings": 4098,
51
+ "model_type": "longformer",
52
+ "num_attention_heads": 12,
53
+ "num_hidden_layers": 12,
54
+ "onnx_export": false,
55
+ "pad_token_id": 1,
56
+ "sep_token_id": 2,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.38.2",
59
+ "type_vocab_size": 1,
60
+ "vocab_size": 50265
61
+ }
checkpoint-1944/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1944/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae37a5db527ae9bd66ffc94b5813be56b896994a3c2b75be506d3508570cbd3
3
+ size 592330980
checkpoint-1944/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd95230e0616032623ddc1963bd21d8c4ffc5269bfff1a04738d7531939c59da
3
+ size 1014670074
checkpoint-1944/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6563dd148ba5b581954f95cf442f239370538d2981016fe8e86fa11803fed43e
3
+ size 14244
checkpoint-1944/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2f95089404ec23d9559b4f12dbe58d621a93231759b08cfbf583c3ac438b3f
3
+ size 1064
checkpoint-1944/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-1944/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1944/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 4096,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "LongformerTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
checkpoint-1944/trainer_state.json ADDED
@@ -0,0 +1,1554 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 24.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1944,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_B-Claim": {
14
+ "f1-score": 0.32421052631578945,
15
+ "precision": 0.42777777777777776,
16
+ "recall": 0.26101694915254237,
17
+ "support": 295.0
18
+ },
19
+ "eval_B-MajorClaim": {
20
+ "f1-score": 0.192090395480226,
21
+ "precision": 0.8095238095238095,
22
+ "recall": 0.10897435897435898,
23
+ "support": 156.0
24
+ },
25
+ "eval_B-Premise": {
26
+ "f1-score": 0.8566265060240965,
27
+ "precision": 0.7620578778135049,
28
+ "recall": 0.9779917469050894,
29
+ "support": 727.0
30
+ },
31
+ "eval_I-Claim": {
32
+ "f1-score": 0.5001390820584144,
33
+ "precision": 0.5900886117492615,
34
+ "recall": 0.43398503499879315,
35
+ "support": 4143.0
36
+ },
37
+ "eval_I-MajorClaim": {
38
+ "f1-score": 0.776470588235294,
39
+ "precision": 0.6649333766655834,
40
+ "recall": 0.93296853625171,
41
+ "support": 2193.0
42
+ },
43
+ "eval_I-Premise": {
44
+ "f1-score": 0.8861458374413376,
45
+ "precision": 0.8781460059402845,
46
+ "recall": 0.8942927644670858,
47
+ "support": 12563.0
48
+ },
49
+ "eval_O": {
50
+ "f1-score": 0.9987647926046939,
51
+ "precision": 0.9977708781147998,
52
+ "recall": 0.9997606892150607,
53
+ "support": 12536.0
54
+ },
55
+ "eval_accuracy": 0.8713396498328887,
56
+ "eval_loss": 0.3092103600502014,
57
+ "eval_macro avg": {
58
+ "f1-score": 0.647778246879979,
59
+ "precision": 0.732899762512146,
60
+ "recall": 0.6584271542806628,
61
+ "support": 32613.0
62
+ },
63
+ "eval_runtime": 4.965,
64
+ "eval_samples_per_second": 16.314,
65
+ "eval_steps_per_second": 2.215,
66
+ "eval_weighted avg": {
67
+ "f1-score": 0.8639627599323451,
68
+ "precision": 0.8662078389010613,
69
+ "recall": 0.8713396498328887,
70
+ "support": 32613.0
71
+ },
72
+ "step": 81
73
+ },
74
+ {
75
+ "epoch": 2.0,
76
+ "eval_B-Claim": {
77
+ "f1-score": 0.6186291739894552,
78
+ "precision": 0.6423357664233577,
79
+ "recall": 0.5966101694915255,
80
+ "support": 295.0
81
+ },
82
+ "eval_B-MajorClaim": {
83
+ "f1-score": 0.8113879003558718,
84
+ "precision": 0.912,
85
+ "recall": 0.7307692307692307,
86
+ "support": 156.0
87
+ },
88
+ "eval_B-Premise": {
89
+ "f1-score": 0.8871181938911022,
90
+ "precision": 0.8575096277278562,
91
+ "recall": 0.9188445667125172,
92
+ "support": 727.0
93
+ },
94
+ "eval_I-Claim": {
95
+ "f1-score": 0.656253149249219,
96
+ "precision": 0.5633217993079584,
97
+ "recall": 0.7859039343470915,
98
+ "support": 4143.0
99
+ },
100
+ "eval_I-MajorClaim": {
101
+ "f1-score": 0.8368159203980099,
102
+ "precision": 0.9206349206349206,
103
+ "recall": 0.7669858641130871,
104
+ "support": 2193.0
105
+ },
106
+ "eval_I-Premise": {
107
+ "f1-score": 0.8831027253668763,
108
+ "precision": 0.933020288827855,
109
+ "recall": 0.8382551938231314,
110
+ "support": 12563.0
111
+ },
112
+ "eval_O": {
113
+ "f1-score": 0.9998006141085457,
114
+ "precision": 0.9996013077107089,
115
+ "recall": 1.0,
116
+ "support": 12536.0
117
+ },
118
+ "eval_accuracy": 0.8880814399165977,
119
+ "eval_loss": 0.2581149935722351,
120
+ "eval_macro avg": {
121
+ "f1-score": 0.8133010967655829,
122
+ "precision": 0.8326319586618081,
123
+ "recall": 0.8053384227509405,
124
+ "support": 32613.0
125
+ },
126
+ "eval_runtime": 5.0296,
127
+ "eval_samples_per_second": 16.105,
128
+ "eval_steps_per_second": 2.187,
129
+ "eval_weighted avg": {
130
+ "f1-score": 0.8933836566327042,
131
+ "precision": 0.9064023864086126,
132
+ "recall": 0.8880814399165977,
133
+ "support": 32613.0
134
+ },
135
+ "step": 162
136
+ },
137
+ {
138
+ "epoch": 3.0,
139
+ "eval_B-Claim": {
140
+ "f1-score": 0.6576271186440678,
141
+ "precision": 0.6576271186440678,
142
+ "recall": 0.6576271186440678,
143
+ "support": 295.0
144
+ },
145
+ "eval_B-MajorClaim": {
146
+ "f1-score": 0.8673139158576051,
147
+ "precision": 0.8758169934640523,
148
+ "recall": 0.8589743589743589,
149
+ "support": 156.0
150
+ },
151
+ "eval_B-Premise": {
152
+ "f1-score": 0.8838487972508591,
153
+ "precision": 0.8832417582417582,
154
+ "recall": 0.8844566712517193,
155
+ "support": 727.0
156
+ },
157
+ "eval_I-Claim": {
158
+ "f1-score": 0.6468460321049062,
159
+ "precision": 0.6083351052519669,
160
+ "recall": 0.6905623944001931,
161
+ "support": 4143.0
162
+ },
163
+ "eval_I-MajorClaim": {
164
+ "f1-score": 0.8695855771482088,
165
+ "precision": 0.8936477382098171,
166
+ "recall": 0.8467852257181943,
167
+ "support": 2193.0
168
+ },
169
+ "eval_I-Premise": {
170
+ "f1-score": 0.8926256077795786,
171
+ "precision": 0.9090533960551291,
172
+ "recall": 0.8767810236408501,
173
+ "support": 12563.0
174
+ },
175
+ "eval_O": {
176
+ "f1-score": 0.9998803589232302,
177
+ "precision": 0.9997607464710104,
178
+ "recall": 1.0,
179
+ "support": 12536.0
180
+ },
181
+ "eval_accuracy": 0.8965749854352559,
182
+ "eval_loss": 0.2399493306875229,
183
+ "eval_macro avg": {
184
+ "f1-score": 0.8311039153869222,
185
+ "precision": 0.8324975509054003,
186
+ "recall": 0.8307409703756262,
187
+ "support": 32613.0
188
+ },
189
+ "eval_runtime": 5.0024,
190
+ "eval_samples_per_second": 16.192,
191
+ "eval_steps_per_second": 2.199,
192
+ "eval_weighted avg": {
193
+ "f1-score": 0.8986385496019461,
194
+ "precision": 0.9016737059631544,
195
+ "recall": 0.8965749854352559,
196
+ "support": 32613.0
197
+ },
198
+ "step": 243
199
+ },
200
+ {
201
+ "epoch": 4.0,
202
+ "eval_B-Claim": {
203
+ "f1-score": 0.6106346483704975,
204
+ "precision": 0.6180555555555556,
205
+ "recall": 0.6033898305084746,
206
+ "support": 295.0
207
+ },
208
+ "eval_B-MajorClaim": {
209
+ "f1-score": 0.8498583569405098,
210
+ "precision": 0.7614213197969543,
211
+ "recall": 0.9615384615384616,
212
+ "support": 156.0
213
+ },
214
+ "eval_B-Premise": {
215
+ "f1-score": 0.8746478873239436,
216
+ "precision": 0.8961038961038961,
217
+ "recall": 0.8541953232462174,
218
+ "support": 727.0
219
+ },
220
+ "eval_I-Claim": {
221
+ "f1-score": 0.5964912280701754,
222
+ "precision": 0.6109845608706657,
223
+ "recall": 0.5826695631185131,
224
+ "support": 4143.0
225
+ },
226
+ "eval_I-MajorClaim": {
227
+ "f1-score": 0.8631961259079903,
228
+ "precision": 0.7741585233441911,
229
+ "recall": 0.9753761969904241,
230
+ "support": 2193.0
231
+ },
232
+ "eval_I-Premise": {
233
+ "f1-score": 0.8933694290678411,
234
+ "precision": 0.9071885770556376,
235
+ "recall": 0.8799649765183475,
236
+ "support": 12563.0
237
+ },
238
+ "eval_O": {
239
+ "f1-score": 0.9999601132782897,
240
+ "precision": 1.0,
241
+ "recall": 0.9999202297383536,
242
+ "support": 12536.0
243
+ },
244
+ "eval_accuracy": 0.8920369177935179,
245
+ "eval_loss": 0.2815629839897156,
246
+ "eval_macro avg": {
247
+ "f1-score": 0.8125939698513209,
248
+ "precision": 0.7954160618181286,
249
+ "recall": 0.8367220830941131,
250
+ "support": 32613.0
251
+ },
252
+ "eval_runtime": 4.9474,
253
+ "eval_samples_per_second": 16.372,
254
+ "eval_steps_per_second": 2.223,
255
+ "eval_weighted avg": {
256
+ "f1-score": 0.8914155863760895,
257
+ "precision": 0.892730641712682,
258
+ "recall": 0.8920369177935179,
259
+ "support": 32613.0
260
+ },
261
+ "step": 324
262
+ },
263
+ {
264
+ "epoch": 5.0,
265
+ "eval_B-Claim": {
266
+ "f1-score": 0.6796116504854369,
267
+ "precision": 0.6501547987616099,
268
+ "recall": 0.711864406779661,
269
+ "support": 295.0
270
+ },
271
+ "eval_B-MajorClaim": {
272
+ "f1-score": 0.8746177370030581,
273
+ "precision": 0.8362573099415205,
274
+ "recall": 0.9166666666666666,
275
+ "support": 156.0
276
+ },
277
+ "eval_B-Premise": {
278
+ "f1-score": 0.8836879432624114,
279
+ "precision": 0.9121522693997072,
280
+ "recall": 0.8569463548830811,
281
+ "support": 727.0
282
+ },
283
+ "eval_I-Claim": {
284
+ "f1-score": 0.6557152635181382,
285
+ "precision": 0.6216742375081116,
286
+ "recall": 0.6937002172338885,
287
+ "support": 4143.0
288
+ },
289
+ "eval_I-MajorClaim": {
290
+ "f1-score": 0.8859746610357857,
291
+ "precision": 0.8642671292281006,
292
+ "recall": 0.9088007295941632,
293
+ "support": 2193.0
294
+ },
295
+ "eval_I-Premise": {
296
+ "f1-score": 0.8956745077255495,
297
+ "precision": 0.9180177168644492,
298
+ "recall": 0.874393058982727,
299
+ "support": 12563.0
300
+ },
301
+ "eval_O": {
302
+ "f1-score": 0.9998006141085457,
303
+ "precision": 0.9996013077107089,
304
+ "recall": 1.0,
305
+ "support": 12536.0
306
+ },
307
+ "eval_accuracy": 0.9003771502161715,
308
+ "eval_loss": 0.2959797978401184,
309
+ "eval_macro avg": {
310
+ "f1-score": 0.839297482448418,
311
+ "precision": 0.8288749670591724,
312
+ "recall": 0.8517673477343124,
313
+ "support": 32613.0
314
+ },
315
+ "eval_runtime": 4.9768,
316
+ "eval_samples_per_second": 16.275,
317
+ "eval_steps_per_second": 2.21,
318
+ "eval_weighted avg": {
319
+ "f1-score": 0.9022413468876027,
320
+ "precision": 0.9051721478141229,
321
+ "recall": 0.9003771502161715,
322
+ "support": 32613.0
323
+ },
324
+ "step": 405
325
+ },
326
+ {
327
+ "epoch": 6.0,
328
+ "eval_B-Claim": {
329
+ "f1-score": 0.6655518394648828,
330
+ "precision": 0.6567656765676567,
331
+ "recall": 0.6745762711864407,
332
+ "support": 295.0
333
+ },
334
+ "eval_B-MajorClaim": {
335
+ "f1-score": 0.8807339449541285,
336
+ "precision": 0.8421052631578947,
337
+ "recall": 0.9230769230769231,
338
+ "support": 156.0
339
+ },
340
+ "eval_B-Premise": {
341
+ "f1-score": 0.8812849162011174,
342
+ "precision": 0.8950354609929078,
343
+ "recall": 0.8679504814305364,
344
+ "support": 727.0
345
+ },
346
+ "eval_I-Claim": {
347
+ "f1-score": 0.634203994799669,
348
+ "precision": 0.6213524779990737,
349
+ "recall": 0.647598358677287,
350
+ "support": 4143.0
351
+ },
352
+ "eval_I-MajorClaim": {
353
+ "f1-score": 0.8926454445664106,
354
+ "precision": 0.8607112616426758,
355
+ "recall": 0.9270405836753306,
356
+ "support": 2193.0
357
+ },
358
+ "eval_I-Premise": {
359
+ "f1-score": 0.8911586596689544,
360
+ "precision": 0.9041533546325878,
361
+ "recall": 0.8785321977234737,
362
+ "support": 12563.0
363
+ },
364
+ "eval_O": {
365
+ "f1-score": 0.9995614559661922,
366
+ "precision": 0.9991232964055152,
367
+ "recall": 1.0,
368
+ "support": 12536.0
369
+ },
370
+ "eval_accuracy": 0.8972802256768774,
371
+ "eval_loss": 0.33718833327293396,
372
+ "eval_macro avg": {
373
+ "f1-score": 0.8350200365173363,
374
+ "precision": 0.8256066844854731,
375
+ "recall": 0.8455392593957132,
376
+ "support": 32613.0
377
+ },
378
+ "eval_runtime": 4.9878,
379
+ "eval_samples_per_second": 16.24,
380
+ "eval_steps_per_second": 2.205,
381
+ "eval_weighted avg": {
382
+ "f1-score": 0.8979742337698349,
383
+ "precision": 0.8990738793396261,
384
+ "recall": 0.8972802256768774,
385
+ "support": 32613.0
386
+ },
387
+ "step": 486
388
+ },
389
+ {
390
+ "epoch": 6.17,
391
+ "grad_norm": 10.722956657409668,
392
+ "learning_rate": 1.7530864197530865e-05,
393
+ "loss": 0.2434,
394
+ "step": 500
395
+ },
396
+ {
397
+ "epoch": 7.0,
398
+ "eval_B-Claim": {
399
+ "f1-score": 0.6608695652173914,
400
+ "precision": 0.6785714285714286,
401
+ "recall": 0.6440677966101694,
402
+ "support": 295.0
403
+ },
404
+ "eval_B-MajorClaim": {
405
+ "f1-score": 0.875,
406
+ "precision": 0.8536585365853658,
407
+ "recall": 0.8974358974358975,
408
+ "support": 156.0
409
+ },
410
+ "eval_B-Premise": {
411
+ "f1-score": 0.8905608755129958,
412
+ "precision": 0.8857142857142857,
413
+ "recall": 0.8954607977991746,
414
+ "support": 727.0
415
+ },
416
+ "eval_I-Claim": {
417
+ "f1-score": 0.6306948332909138,
418
+ "precision": 0.6670255720053836,
419
+ "recall": 0.5981173062997828,
420
+ "support": 4143.0
421
+ },
422
+ "eval_I-MajorClaim": {
423
+ "f1-score": 0.890302764370338,
424
+ "precision": 0.8579281183932347,
425
+ "recall": 0.9252165982672138,
426
+ "support": 2193.0
427
+ },
428
+ "eval_I-Premise": {
429
+ "f1-score": 0.9037468972853708,
430
+ "precision": 0.8947573724449992,
431
+ "recall": 0.9129188888004458,
432
+ "support": 12563.0
433
+ },
434
+ "eval_O": {
435
+ "f1-score": 1.0,
436
+ "precision": 1.0,
437
+ "recall": 1.0,
438
+ "support": 12536.0
439
+ },
440
+ "eval_accuracy": 0.9043326280930917,
441
+ "eval_loss": 0.43479764461517334,
442
+ "eval_macro avg": {
443
+ "f1-score": 0.8358821336681442,
444
+ "precision": 0.8339507591020997,
445
+ "recall": 0.8390310407446692,
446
+ "support": 32613.0
447
+ },
448
+ "eval_runtime": 4.9479,
449
+ "eval_samples_per_second": 16.371,
450
+ "eval_steps_per_second": 2.223,
451
+ "eval_weighted avg": {
452
+ "f1-score": 0.9025256555797259,
453
+ "precision": 0.9014510706568353,
454
+ "recall": 0.9043326280930917,
455
+ "support": 32613.0
456
+ },
457
+ "step": 567
458
+ },
459
+ {
460
+ "epoch": 8.0,
461
+ "eval_B-Claim": {
462
+ "f1-score": 0.6611295681063122,
463
+ "precision": 0.6482084690553745,
464
+ "recall": 0.6745762711864407,
465
+ "support": 295.0
466
+ },
467
+ "eval_B-MajorClaim": {
468
+ "f1-score": 0.8925081433224756,
469
+ "precision": 0.9072847682119205,
470
+ "recall": 0.8782051282051282,
471
+ "support": 156.0
472
+ },
473
+ "eval_B-Premise": {
474
+ "f1-score": 0.8810511756569848,
475
+ "precision": 0.885952712100139,
476
+ "recall": 0.8762035763411279,
477
+ "support": 727.0
478
+ },
479
+ "eval_I-Claim": {
480
+ "f1-score": 0.6376404494382022,
481
+ "precision": 0.6189502385821404,
482
+ "recall": 0.6574945691527878,
483
+ "support": 4143.0
484
+ },
485
+ "eval_I-MajorClaim": {
486
+ "f1-score": 0.8858131487889275,
487
+ "precision": 0.896358543417367,
488
+ "recall": 0.8755129958960328,
489
+ "support": 2193.0
490
+ },
491
+ "eval_I-Premise": {
492
+ "f1-score": 0.8946945982823662,
493
+ "precision": 0.9022258195062728,
494
+ "recall": 0.8872880681365916,
495
+ "support": 12563.0
496
+ },
497
+ "eval_O": {
498
+ "f1-score": 0.9999202361011406,
499
+ "precision": 0.9998404849258254,
500
+ "recall": 1.0,
501
+ "support": 12536.0
502
+ },
503
+ "eval_accuracy": 0.8984147425873118,
504
+ "eval_loss": 0.3937377631664276,
505
+ "eval_macro avg": {
506
+ "f1-score": 0.8361081885280585,
507
+ "precision": 0.836974433685577,
508
+ "recall": 0.8356115155597299,
509
+ "support": 32613.0
510
+ },
511
+ "eval_runtime": 5.0071,
512
+ "eval_samples_per_second": 16.177,
513
+ "eval_steps_per_second": 2.197,
514
+ "eval_weighted avg": {
515
+ "f1-score": 0.8994624730308206,
516
+ "precision": 0.9007308115646135,
517
+ "recall": 0.8984147425873118,
518
+ "support": 32613.0
519
+ },
520
+ "step": 648
521
+ },
522
+ {
523
+ "epoch": 9.0,
524
+ "eval_B-Claim": {
525
+ "f1-score": 0.6821192052980132,
526
+ "precision": 0.6666666666666666,
527
+ "recall": 0.6983050847457627,
528
+ "support": 295.0
529
+ },
530
+ "eval_B-MajorClaim": {
531
+ "f1-score": 0.8510638297872339,
532
+ "precision": 0.9523809523809523,
533
+ "recall": 0.7692307692307693,
534
+ "support": 156.0
535
+ },
536
+ "eval_B-Premise": {
537
+ "f1-score": 0.8959891230455472,
538
+ "precision": 0.885752688172043,
539
+ "recall": 0.90646492434663,
540
+ "support": 727.0
541
+ },
542
+ "eval_I-Claim": {
543
+ "f1-score": 0.6547967670141736,
544
+ "precision": 0.636094674556213,
545
+ "recall": 0.6746319092445088,
546
+ "support": 4143.0
547
+ },
548
+ "eval_I-MajorClaim": {
549
+ "f1-score": 0.8507386653082017,
550
+ "precision": 0.9636468551644547,
551
+ "recall": 0.7615139078887369,
552
+ "support": 2193.0
553
+ },
554
+ "eval_I-Premise": {
555
+ "f1-score": 0.9060476867203537,
556
+ "precision": 0.8987391338397682,
557
+ "recall": 0.9134760805540078,
558
+ "support": 12563.0
559
+ },
560
+ "eval_O": {
561
+ "f1-score": 0.9999202361011406,
562
+ "precision": 0.9998404849258254,
563
+ "recall": 1.0,
564
+ "support": 12536.0
565
+ },
566
+ "eval_accuracy": 0.9033820868978628,
567
+ "eval_loss": 0.4608707129955292,
568
+ "eval_macro avg": {
569
+ "f1-score": 0.8343822161820948,
570
+ "precision": 0.8575887793865605,
571
+ "recall": 0.8176603822872022,
572
+ "support": 32613.0
573
+ },
574
+ "eval_runtime": 4.9809,
575
+ "eval_samples_per_second": 16.262,
576
+ "eval_steps_per_second": 2.208,
577
+ "eval_weighted avg": {
578
+ "f1-score": 0.9039813964448579,
579
+ "precision": 0.9064685293306464,
580
+ "recall": 0.9033820868978628,
581
+ "support": 32613.0
582
+ },
583
+ "step": 729
584
+ },
585
+ {
586
+ "epoch": 10.0,
587
+ "eval_B-Claim": {
588
+ "f1-score": 0.6863354037267081,
589
+ "precision": 0.6332378223495702,
590
+ "recall": 0.7491525423728813,
591
+ "support": 295.0
592
+ },
593
+ "eval_B-MajorClaim": {
594
+ "f1-score": 0.8976897689768977,
595
+ "precision": 0.9251700680272109,
596
+ "recall": 0.8717948717948718,
597
+ "support": 156.0
598
+ },
599
+ "eval_B-Premise": {
600
+ "f1-score": 0.8780141843971632,
601
+ "precision": 0.9062957540263543,
602
+ "recall": 0.8514442916093535,
603
+ "support": 727.0
604
+ },
605
+ "eval_I-Claim": {
606
+ "f1-score": 0.6615143369175628,
607
+ "precision": 0.6171368861024034,
608
+ "recall": 0.7127685252232682,
609
+ "support": 4143.0
610
+ },
611
+ "eval_I-MajorClaim": {
612
+ "f1-score": 0.9019424292066465,
613
+ "precision": 0.9264423076923077,
614
+ "recall": 0.8787049703602371,
615
+ "support": 2193.0
616
+ },
617
+ "eval_I-Premise": {
618
+ "f1-score": 0.8934422897101273,
619
+ "precision": 0.9130796077779625,
620
+ "recall": 0.8746318554485394,
621
+ "support": 12563.0
622
+ },
623
+ "eval_O": {
624
+ "f1-score": 0.9999601132782897,
625
+ "precision": 1.0,
626
+ "recall": 0.9999202297383536,
627
+ "support": 12536.0
628
+ },
629
+ "eval_accuracy": 0.9008370895041854,
630
+ "eval_loss": 0.49426138401031494,
631
+ "eval_macro avg": {
632
+ "f1-score": 0.8455569323161993,
633
+ "precision": 0.8459089208536871,
634
+ "recall": 0.8483453266496436,
635
+ "support": 32613.0
636
+ },
637
+ "eval_runtime": 4.962,
638
+ "eval_samples_per_second": 16.324,
639
+ "eval_steps_per_second": 2.217,
640
+ "eval_weighted avg": {
641
+ "f1-score": 0.9032978864532892,
642
+ "precision": 0.9071693470023781,
643
+ "recall": 0.9008370895041854,
644
+ "support": 32613.0
645
+ },
646
+ "step": 810
647
+ },
648
+ {
649
+ "epoch": 11.0,
650
+ "eval_B-Claim": {
651
+ "f1-score": 0.6654991243432573,
652
+ "precision": 0.6884057971014492,
653
+ "recall": 0.6440677966101694,
654
+ "support": 295.0
655
+ },
656
+ "eval_B-MajorClaim": {
657
+ "f1-score": 0.8888888888888888,
658
+ "precision": 0.9361702127659575,
659
+ "recall": 0.8461538461538461,
660
+ "support": 156.0
661
+ },
662
+ "eval_B-Premise": {
663
+ "f1-score": 0.8911290322580646,
664
+ "precision": 0.871222076215506,
665
+ "recall": 0.9119669876203577,
666
+ "support": 727.0
667
+ },
668
+ "eval_I-Claim": {
669
+ "f1-score": 0.6376628304034401,
670
+ "precision": 0.6697662061636557,
671
+ "recall": 0.6084962587496983,
672
+ "support": 4143.0
673
+ },
674
+ "eval_I-MajorClaim": {
675
+ "f1-score": 0.8884068450228971,
676
+ "precision": 0.9422290388548057,
677
+ "recall": 0.8404012767897857,
678
+ "support": 2193.0
679
+ },
680
+ "eval_I-Premise": {
681
+ "f1-score": 0.904972804972805,
682
+ "precision": 0.8838885937618578,
683
+ "recall": 0.9270874791053092,
684
+ "support": 12563.0
685
+ },
686
+ "eval_O": {
687
+ "f1-score": 0.9999202361011406,
688
+ "precision": 0.9998404849258254,
689
+ "recall": 1.0,
690
+ "support": 12536.0
691
+ },
692
+ "eval_accuracy": 0.9055284702419281,
693
+ "eval_loss": 0.5303362607955933,
694
+ "eval_macro avg": {
695
+ "f1-score": 0.8394971088557848,
696
+ "precision": 0.8559317728270083,
697
+ "recall": 0.8254533778613096,
698
+ "support": 32613.0
699
+ },
700
+ "eval_runtime": 4.9749,
701
+ "eval_samples_per_second": 16.282,
702
+ "eval_steps_per_second": 2.211,
703
+ "eval_weighted avg": {
704
+ "f1-score": 0.9038459038093231,
705
+ "precision": 0.9033803424876604,
706
+ "recall": 0.9055284702419281,
707
+ "support": 32613.0
708
+ },
709
+ "step": 891
710
+ },
711
+ {
712
+ "epoch": 12.0,
713
+ "eval_B-Claim": {
714
+ "f1-score": 0.6374045801526718,
715
+ "precision": 0.7292576419213974,
716
+ "recall": 0.5661016949152542,
717
+ "support": 295.0
718
+ },
719
+ "eval_B-MajorClaim": {
720
+ "f1-score": 0.9114754098360656,
721
+ "precision": 0.9328859060402684,
722
+ "recall": 0.8910256410256411,
723
+ "support": 156.0
724
+ },
725
+ "eval_B-Premise": {
726
+ "f1-score": 0.8913612565445026,
727
+ "precision": 0.850187265917603,
728
+ "recall": 0.936726272352132,
729
+ "support": 727.0
730
+ },
731
+ "eval_I-Claim": {
732
+ "f1-score": 0.5983549421441516,
733
+ "precision": 0.7082508250825083,
734
+ "recall": 0.5179821385469466,
735
+ "support": 4143.0
736
+ },
737
+ "eval_I-MajorClaim": {
738
+ "f1-score": 0.9206057824690226,
739
+ "precision": 0.9265588914549654,
740
+ "recall": 0.9147286821705426,
741
+ "support": 2193.0
742
+ },
743
+ "eval_I-Premise": {
744
+ "f1-score": 0.9017204628501827,
745
+ "precision": 0.8640309285870595,
746
+ "recall": 0.9428480458489215,
747
+ "support": 12563.0
748
+ },
749
+ "eval_O": {
750
+ "f1-score": 0.9997606319317004,
751
+ "precision": 1.0,
752
+ "recall": 0.9995213784301212,
753
+ "support": 12536.0
754
+ },
755
+ "eval_accuracy": 0.9049765430963113,
756
+ "eval_loss": 0.5691992044448853,
757
+ "eval_macro avg": {
758
+ "f1-score": 0.8372404379897568,
759
+ "precision": 0.8587387798576859,
760
+ "recall": 0.8241334076127942,
761
+ "support": 32613.0
762
+ },
763
+ "eval_runtime": 4.9632,
764
+ "eval_samples_per_second": 16.32,
765
+ "eval_steps_per_second": 2.216,
766
+ "eval_weighted avg": {
767
+ "f1-score": 0.8995624631750451,
768
+ "precision": 0.8995123024912762,
769
+ "recall": 0.9049765430963113,
770
+ "support": 32613.0
771
+ },
772
+ "step": 972
773
+ },
774
+ {
775
+ "epoch": 12.35,
776
+ "grad_norm": 8.504526138305664,
777
+ "learning_rate": 1.506172839506173e-05,
778
+ "loss": 0.0319,
779
+ "step": 1000
780
+ },
781
+ {
782
+ "epoch": 13.0,
783
+ "eval_B-Claim": {
784
+ "f1-score": 0.6779661016949152,
785
+ "precision": 0.6779661016949152,
786
+ "recall": 0.6779661016949152,
787
+ "support": 295.0
788
+ },
789
+ "eval_B-MajorClaim": {
790
+ "f1-score": 0.9096774193548387,
791
+ "precision": 0.9155844155844156,
792
+ "recall": 0.9038461538461539,
793
+ "support": 156.0
794
+ },
795
+ "eval_B-Premise": {
796
+ "f1-score": 0.8873626373626373,
797
+ "precision": 0.8861454046639232,
798
+ "recall": 0.8885832187070152,
799
+ "support": 727.0
800
+ },
801
+ "eval_I-Claim": {
802
+ "f1-score": 0.663892288861689,
803
+ "precision": 0.6734541842562701,
804
+ "recall": 0.6545981173062998,
805
+ "support": 4143.0
806
+ },
807
+ "eval_I-MajorClaim": {
808
+ "f1-score": 0.9122568973315242,
809
+ "precision": 0.9048900852400179,
810
+ "recall": 0.9197446420428637,
811
+ "support": 2193.0
812
+ },
813
+ "eval_I-Premise": {
814
+ "f1-score": 0.9055930186433956,
815
+ "precision": 0.9025855934213648,
816
+ "recall": 0.9086205524158243,
817
+ "support": 12563.0
818
+ },
819
+ "eval_O": {
820
+ "f1-score": 0.9998404340194671,
821
+ "precision": 1.0,
822
+ "recall": 0.9996809189534142,
823
+ "support": 12536.0
824
+ },
825
+ "eval_accuracy": 0.9095452733572502,
826
+ "eval_loss": 0.5995727777481079,
827
+ "eval_macro avg": {
828
+ "f1-score": 0.8509412567526382,
829
+ "precision": 0.8515179692658439,
830
+ "recall": 0.8504342435666409,
831
+ "support": 32613.0
832
+ },
833
+ "eval_runtime": 4.967,
834
+ "eval_samples_per_second": 16.308,
835
+ "eval_steps_per_second": 2.215,
836
+ "eval_weighted avg": {
837
+ "f1-score": 0.9091182110651892,
838
+ "precision": 0.908741493590885,
839
+ "recall": 0.9095452733572502,
840
+ "support": 32613.0
841
+ },
842
+ "step": 1053
843
+ },
844
+ {
845
+ "epoch": 14.0,
846
+ "eval_B-Claim": {
847
+ "f1-score": 0.6543438077634012,
848
+ "precision": 0.7195121951219512,
849
+ "recall": 0.6,
850
+ "support": 295.0
851
+ },
852
+ "eval_B-MajorClaim": {
853
+ "f1-score": 0.8918032786885245,
854
+ "precision": 0.912751677852349,
855
+ "recall": 0.8717948717948718,
856
+ "support": 156.0
857
+ },
858
+ "eval_B-Premise": {
859
+ "f1-score": 0.895364238410596,
860
+ "precision": 0.8633461047254151,
861
+ "recall": 0.9298486932599724,
862
+ "support": 727.0
863
+ },
864
+ "eval_I-Claim": {
865
+ "f1-score": 0.612272977435333,
866
+ "precision": 0.712,
867
+ "recall": 0.5370504465363264,
868
+ "support": 4143.0
869
+ },
870
+ "eval_I-MajorClaim": {
871
+ "f1-score": 0.9033142857142857,
872
+ "precision": 0.9055912007332723,
873
+ "recall": 0.9010487916096671,
874
+ "support": 2193.0
875
+ },
876
+ "eval_I-Premise": {
877
+ "f1-score": 0.9070541005543873,
878
+ "precision": 0.8727192466156563,
879
+ "recall": 0.9442012258218578,
880
+ "support": 12563.0
881
+ },
882
+ "eval_O": {
883
+ "f1-score": 1.0,
884
+ "precision": 1.0,
885
+ "recall": 1.0,
886
+ "support": 12536.0
887
+ },
888
+ "eval_accuracy": 0.9072455769171802,
889
+ "eval_loss": 0.6337578892707825,
890
+ "eval_macro avg": {
891
+ "f1-score": 0.8377360983666469,
892
+ "precision": 0.8551314892926634,
893
+ "recall": 0.8262777184318136,
894
+ "support": 32613.0
895
+ },
896
+ "eval_runtime": 4.9902,
897
+ "eval_samples_per_second": 16.232,
898
+ "eval_steps_per_second": 2.204,
899
+ "eval_weighted avg": {
900
+ "f1-score": 0.9024627717609818,
901
+ "precision": 0.902034384321647,
902
+ "recall": 0.9072455769171802,
903
+ "support": 32613.0
904
+ },
905
+ "step": 1134
906
+ },
907
+ {
908
+ "epoch": 15.0,
909
+ "eval_B-Claim": {
910
+ "f1-score": 0.6715867158671587,
911
+ "precision": 0.7368421052631579,
912
+ "recall": 0.6169491525423729,
913
+ "support": 295.0
914
+ },
915
+ "eval_B-MajorClaim": {
916
+ "f1-score": 0.8902077151335311,
917
+ "precision": 0.8287292817679558,
918
+ "recall": 0.9615384615384616,
919
+ "support": 156.0
920
+ },
921
+ "eval_B-Premise": {
922
+ "f1-score": 0.896551724137931,
923
+ "precision": 0.8816489361702128,
924
+ "recall": 0.9119669876203577,
925
+ "support": 727.0
926
+ },
927
+ "eval_I-Claim": {
928
+ "f1-score": 0.6393111798735368,
929
+ "precision": 0.7221884498480243,
930
+ "recall": 0.5734974656046343,
931
+ "support": 4143.0
932
+ },
933
+ "eval_I-MajorClaim": {
934
+ "f1-score": 0.898728813559322,
935
+ "precision": 0.8393351800554016,
936
+ "recall": 0.9671682626538988,
937
+ "support": 2193.0
938
+ },
939
+ "eval_I-Premise": {
940
+ "f1-score": 0.9101119213820535,
941
+ "precision": 0.892125382262997,
942
+ "recall": 0.9288386531879328,
943
+ "support": 12563.0
944
+ },
945
+ "eval_O": {
946
+ "f1-score": 1.0,
947
+ "precision": 1.0,
948
+ "recall": 1.0,
949
+ "support": 12536.0
950
+ },
951
+ "eval_accuracy": 0.9105878024100819,
952
+ "eval_loss": 0.6874175667762756,
953
+ "eval_macro avg": {
954
+ "f1-score": 0.8437854385647904,
955
+ "precision": 0.8429813336239642,
956
+ "recall": 0.8514227118782368,
957
+ "support": 32613.0
958
+ },
959
+ "eval_runtime": 4.9796,
960
+ "eval_samples_per_second": 16.266,
961
+ "eval_steps_per_second": 2.209,
962
+ "eval_weighted avg": {
963
+ "f1-score": 0.9069419606556991,
964
+ "precision": 0.9065117879543761,
965
+ "recall": 0.9105878024100819,
966
+ "support": 32613.0
967
+ },
968
+ "step": 1215
969
+ },
970
+ {
971
+ "epoch": 16.0,
972
+ "eval_B-Claim": {
973
+ "f1-score": 0.676923076923077,
974
+ "precision": 0.6827586206896552,
975
+ "recall": 0.6711864406779661,
976
+ "support": 295.0
977
+ },
978
+ "eval_B-MajorClaim": {
979
+ "f1-score": 0.8980891719745223,
980
+ "precision": 0.8924050632911392,
981
+ "recall": 0.9038461538461539,
982
+ "support": 156.0
983
+ },
984
+ "eval_B-Premise": {
985
+ "f1-score": 0.8902606310013718,
986
+ "precision": 0.8878248974008208,
987
+ "recall": 0.8927097661623109,
988
+ "support": 727.0
989
+ },
990
+ "eval_I-Claim": {
991
+ "f1-score": 0.6403442166540116,
992
+ "precision": 0.6730513434424049,
993
+ "recall": 0.6106685976345644,
994
+ "support": 4143.0
995
+ },
996
+ "eval_I-MajorClaim": {
997
+ "f1-score": 0.9115737631520036,
998
+ "precision": 0.8953386103781882,
999
+ "recall": 0.9284085727314182,
1000
+ "support": 2193.0
1001
+ },
1002
+ "eval_I-Premise": {
1003
+ "f1-score": 0.9030989460437312,
1004
+ "precision": 0.8924990283715507,
1005
+ "recall": 0.9139536734856324,
1006
+ "support": 12563.0
1007
+ },
1008
+ "eval_O": {
1009
+ "f1-score": 1.0,
1010
+ "precision": 1.0,
1011
+ "recall": 1.0,
1012
+ "support": 12536.0
1013
+ },
1014
+ "eval_accuracy": 0.9067549750099654,
1015
+ "eval_loss": 0.6374069452285767,
1016
+ "eval_macro avg": {
1017
+ "f1-score": 0.8457556865355311,
1018
+ "precision": 0.8462682233676798,
1019
+ "recall": 0.8458247435054351,
1020
+ "support": 32613.0
1021
+ },
1022
+ "eval_runtime": 5.004,
1023
+ "eval_samples_per_second": 16.187,
1024
+ "eval_steps_per_second": 2.198,
1025
+ "eval_weighted avg": {
1026
+ "f1-score": 0.905181158084066,
1027
+ "precision": 0.9041324706485238,
1028
+ "recall": 0.9067549750099654,
1029
+ "support": 32613.0
1030
+ },
1031
+ "step": 1296
1032
+ },
1033
+ {
1034
+ "epoch": 17.0,
1035
+ "eval_B-Claim": {
1036
+ "f1-score": 0.7001620745542951,
1037
+ "precision": 0.6708074534161491,
1038
+ "recall": 0.7322033898305085,
1039
+ "support": 295.0
1040
+ },
1041
+ "eval_B-MajorClaim": {
1042
+ "f1-score": 0.910828025477707,
1043
+ "precision": 0.9050632911392406,
1044
+ "recall": 0.9166666666666666,
1045
+ "support": 156.0
1046
+ },
1047
+ "eval_B-Premise": {
1048
+ "f1-score": 0.8870175438596491,
1049
+ "precision": 0.9054441260744985,
1050
+ "recall": 0.8693259972489684,
1051
+ "support": 727.0
1052
+ },
1053
+ "eval_I-Claim": {
1054
+ "f1-score": 0.6722241519045965,
1055
+ "precision": 0.6459724076546507,
1056
+ "recall": 0.7006999758629012,
1057
+ "support": 4143.0
1058
+ },
1059
+ "eval_I-MajorClaim": {
1060
+ "f1-score": 0.9159550561797752,
1061
+ "precision": 0.9029685423128047,
1062
+ "recall": 0.9293205654354765,
1063
+ "support": 2193.0
1064
+ },
1065
+ "eval_I-Premise": {
1066
+ "f1-score": 0.8987500505642975,
1067
+ "precision": 0.9137193617371279,
1068
+ "recall": 0.884263312902969,
1069
+ "support": 12563.0
1070
+ },
1071
+ "eval_O": {
1072
+ "f1-score": 0.999600989545926,
1073
+ "precision": 1.0,
1074
+ "recall": 0.9992022973835354,
1075
+ "support": 12536.0
1076
+ },
1077
+ "eval_accuracy": 0.9066016619139607,
1078
+ "eval_loss": 0.5605483055114746,
1079
+ "eval_macro avg": {
1080
+ "f1-score": 0.8549339845837495,
1081
+ "precision": 0.8491393117620675,
1082
+ "recall": 0.8616688864758607,
1083
+ "support": 32613.0
1084
+ },
1085
+ "eval_runtime": 5.0022,
1086
+ "eval_samples_per_second": 16.193,
1087
+ "eval_steps_per_second": 2.199,
1088
+ "eval_weighted avg": {
1089
+ "f1-score": 0.9078958614075368,
1090
+ "precision": 0.9097251400220888,
1091
+ "recall": 0.9066016619139607,
1092
+ "support": 32613.0
1093
+ },
1094
+ "step": 1377
1095
+ },
1096
+ {
1097
+ "epoch": 18.0,
1098
+ "eval_B-Claim": {
1099
+ "f1-score": 0.7140495867768595,
1100
+ "precision": 0.6967741935483871,
1101
+ "recall": 0.7322033898305085,
1102
+ "support": 295.0
1103
+ },
1104
+ "eval_B-MajorClaim": {
1105
+ "f1-score": 0.9066666666666667,
1106
+ "precision": 0.9444444444444444,
1107
+ "recall": 0.8717948717948718,
1108
+ "support": 156.0
1109
+ },
1110
+ "eval_B-Premise": {
1111
+ "f1-score": 0.8988300068823124,
1112
+ "precision": 0.8994490358126722,
1113
+ "recall": 0.8982118294360385,
1114
+ "support": 727.0
1115
+ },
1116
+ "eval_I-Claim": {
1117
+ "f1-score": 0.6946223564954682,
1118
+ "precision": 0.6955469506292352,
1119
+ "recall": 0.6937002172338885,
1120
+ "support": 4143.0
1121
+ },
1122
+ "eval_I-MajorClaim": {
1123
+ "f1-score": 0.9217432052483598,
1124
+ "precision": 0.9479518072289157,
1125
+ "recall": 0.8969448244414044,
1126
+ "support": 2193.0
1127
+ },
1128
+ "eval_I-Premise": {
1129
+ "f1-score": 0.9124099152609487,
1130
+ "precision": 0.9078086833188874,
1131
+ "recall": 0.9170580275411924,
1132
+ "support": 12563.0
1133
+ },
1134
+ "eval_O": {
1135
+ "f1-score": 0.9999601132782897,
1136
+ "precision": 1.0,
1137
+ "recall": 0.9999202297383536,
1138
+ "support": 12536.0
1139
+ },
1140
+ "eval_accuracy": 0.916873639346273,
1141
+ "eval_loss": 0.636456310749054,
1142
+ "eval_macro avg": {
1143
+ "f1-score": 0.8640402643727008,
1144
+ "precision": 0.8702821592832203,
1145
+ "recall": 0.8585476271451797,
1146
+ "support": 32613.0
1147
+ },
1148
+ "eval_runtime": 4.9811,
1149
+ "eval_samples_per_second": 16.261,
1150
+ "eval_steps_per_second": 2.208,
1151
+ "eval_weighted avg": {
1152
+ "f1-score": 0.9168994897940371,
1153
+ "precision": 0.917060404983014,
1154
+ "recall": 0.916873639346273,
1155
+ "support": 32613.0
1156
+ },
1157
+ "step": 1458
1158
+ },
1159
+ {
1160
+ "epoch": 18.52,
1161
+ "grad_norm": 2.2237088680267334,
1162
+ "learning_rate": 1.2592592592592593e-05,
1163
+ "loss": 0.0112,
1164
+ "step": 1500
1165
+ },
1166
+ {
1167
+ "epoch": 19.0,
1168
+ "eval_B-Claim": {
1169
+ "f1-score": 0.6907216494845362,
1170
+ "precision": 0.7003484320557491,
1171
+ "recall": 0.6813559322033899,
1172
+ "support": 295.0
1173
+ },
1174
+ "eval_B-MajorClaim": {
1175
+ "f1-score": 0.9067524115755627,
1176
+ "precision": 0.9096774193548387,
1177
+ "recall": 0.9038461538461539,
1178
+ "support": 156.0
1179
+ },
1180
+ "eval_B-Premise": {
1181
+ "f1-score": 0.8940533151059467,
1182
+ "precision": 0.8885869565217391,
1183
+ "recall": 0.8995873452544704,
1184
+ "support": 727.0
1185
+ },
1186
+ "eval_I-Claim": {
1187
+ "f1-score": 0.6695981433980701,
1188
+ "precision": 0.6777942631058358,
1189
+ "recall": 0.6615978759353126,
1190
+ "support": 4143.0
1191
+ },
1192
+ "eval_I-MajorClaim": {
1193
+ "f1-score": 0.9135184342284934,
1194
+ "precision": 0.9118582462517038,
1195
+ "recall": 0.9151846785225718,
1196
+ "support": 2193.0
1197
+ },
1198
+ "eval_I-Premise": {
1199
+ "f1-score": 0.9059761272157671,
1200
+ "precision": 0.9027185079816659,
1201
+ "recall": 0.9092573429913238,
1202
+ "support": 12563.0
1203
+ },
1204
+ "eval_O": {
1205
+ "f1-score": 1.0,
1206
+ "precision": 1.0,
1207
+ "recall": 1.0,
1208
+ "support": 12536.0
1209
+ },
1210
+ "eval_accuracy": 0.9107717781252874,
1211
+ "eval_loss": 0.6661651134490967,
1212
+ "eval_macro avg": {
1213
+ "f1-score": 0.8543742972869109,
1214
+ "precision": 0.8558548321816474,
1215
+ "recall": 0.8529756183933175,
1216
+ "support": 32613.0
1217
+ },
1218
+ "eval_runtime": 4.9645,
1219
+ "eval_samples_per_second": 16.316,
1220
+ "eval_steps_per_second": 2.216,
1221
+ "eval_weighted avg": {
1222
+ "f1-score": 0.9103873346045664,
1223
+ "precision": 0.9100412278575488,
1224
+ "recall": 0.9107717781252874,
1225
+ "support": 32613.0
1226
+ },
1227
+ "step": 1539
1228
+ },
1229
+ {
1230
+ "epoch": 20.0,
1231
+ "eval_B-Claim": {
1232
+ "f1-score": 0.697278911564626,
1233
+ "precision": 0.6996587030716723,
1234
+ "recall": 0.6949152542372882,
1235
+ "support": 295.0
1236
+ },
1237
+ "eval_B-MajorClaim": {
1238
+ "f1-score": 0.9072847682119205,
1239
+ "precision": 0.9383561643835616,
1240
+ "recall": 0.8782051282051282,
1241
+ "support": 156.0
1242
+ },
1243
+ "eval_B-Premise": {
1244
+ "f1-score": 0.8958475153165418,
1245
+ "precision": 0.8867924528301887,
1246
+ "recall": 0.9050894085281981,
1247
+ "support": 727.0
1248
+ },
1249
+ "eval_I-Claim": {
1250
+ "f1-score": 0.6639919759277834,
1251
+ "precision": 0.6908426819723454,
1252
+ "recall": 0.6391503741250302,
1253
+ "support": 4143.0
1254
+ },
1255
+ "eval_I-MajorClaim": {
1256
+ "f1-score": 0.9188432835820896,
1257
+ "precision": 0.9403341288782816,
1258
+ "recall": 0.898312813497492,
1259
+ "support": 2193.0
1260
+ },
1261
+ "eval_I-Premise": {
1262
+ "f1-score": 0.9079586401378662,
1263
+ "precision": 0.8937466265710541,
1264
+ "recall": 0.9226299450768128,
1265
+ "support": 12563.0
1266
+ },
1267
+ "eval_O": {
1268
+ "f1-score": 0.9999601132782897,
1269
+ "precision": 1.0,
1270
+ "recall": 0.9999202297383536,
1271
+ "support": 12536.0
1272
+ },
1273
+ "eval_accuracy": 0.9120289455125257,
1274
+ "eval_loss": 0.6076620817184448,
1275
+ "eval_macro avg": {
1276
+ "f1-score": 0.8558807440027308,
1277
+ "precision": 0.8642472511010147,
1278
+ "recall": 0.8483175933440433,
1279
+ "support": 32613.0
1280
+ },
1281
+ "eval_runtime": 4.9557,
1282
+ "eval_samples_per_second": 16.345,
1283
+ "eval_steps_per_second": 2.22,
1284
+ "eval_weighted avg": {
1285
+ "f1-score": 0.910883429910181,
1286
+ "precision": 0.9102484848959365,
1287
+ "recall": 0.9120289455125257,
1288
+ "support": 32613.0
1289
+ },
1290
+ "step": 1620
1291
+ },
1292
+ {
1293
+ "epoch": 21.0,
1294
+ "eval_B-Claim": {
1295
+ "f1-score": 0.6752767527675276,
1296
+ "precision": 0.7408906882591093,
1297
+ "recall": 0.6203389830508474,
1298
+ "support": 295.0
1299
+ },
1300
+ "eval_B-MajorClaim": {
1301
+ "f1-score": 0.9120521172638437,
1302
+ "precision": 0.9271523178807947,
1303
+ "recall": 0.8974358974358975,
1304
+ "support": 156.0
1305
+ },
1306
+ "eval_B-Premise": {
1307
+ "f1-score": 0.8992042440318302,
1308
+ "precision": 0.8681177976952625,
1309
+ "recall": 0.9325997248968363,
1310
+ "support": 727.0
1311
+ },
1312
+ "eval_I-Claim": {
1313
+ "f1-score": 0.6303986710963455,
1314
+ "precision": 0.73904576436222,
1315
+ "recall": 0.5496017378711079,
1316
+ "support": 4143.0
1317
+ },
1318
+ "eval_I-MajorClaim": {
1319
+ "f1-score": 0.9182505152278452,
1320
+ "precision": 0.922263109475621,
1321
+ "recall": 0.9142726858185134,
1322
+ "support": 2193.0
1323
+ },
1324
+ "eval_I-Premise": {
1325
+ "f1-score": 0.909555793008701,
1326
+ "precision": 0.8736163037900447,
1327
+ "recall": 0.9485791610284168,
1328
+ "support": 12563.0
1329
+ },
1330
+ "eval_O": {
1331
+ "f1-score": 0.9999202361011406,
1332
+ "precision": 0.9998404849258254,
1333
+ "recall": 1.0,
1334
+ "support": 12536.0
1335
+ },
1336
+ "eval_accuracy": 0.9117836445589182,
1337
+ "eval_loss": 0.685625433921814,
1338
+ "eval_macro avg": {
1339
+ "f1-score": 0.8492369042138906,
1340
+ "precision": 0.8672752094841254,
1341
+ "recall": 0.8375468843002313,
1342
+ "support": 32613.0
1343
+ },
1344
+ "eval_runtime": 4.9777,
1345
+ "eval_samples_per_second": 16.273,
1346
+ "eval_steps_per_second": 2.21,
1347
+ "eval_weighted avg": {
1348
+ "f1-score": 0.9070745665639394,
1349
+ "precision": 0.9072440958491244,
1350
+ "recall": 0.9117836445589182,
1351
+ "support": 32613.0
1352
+ },
1353
+ "step": 1701
1354
+ },
1355
+ {
1356
+ "epoch": 22.0,
1357
+ "eval_B-Claim": {
1358
+ "f1-score": 0.7060653188180404,
1359
+ "precision": 0.6522988505747126,
1360
+ "recall": 0.7694915254237288,
1361
+ "support": 295.0
1362
+ },
1363
+ "eval_B-MajorClaim": {
1364
+ "f1-score": 0.9032258064516129,
1365
+ "precision": 0.9090909090909091,
1366
+ "recall": 0.8974358974358975,
1367
+ "support": 156.0
1368
+ },
1369
+ "eval_B-Premise": {
1370
+ "f1-score": 0.8852459016393444,
1371
+ "precision": 0.9186390532544378,
1372
+ "recall": 0.8541953232462174,
1373
+ "support": 727.0
1374
+ },
1375
+ "eval_I-Claim": {
1376
+ "f1-score": 0.6783193277310924,
1377
+ "precision": 0.6329987452948557,
1378
+ "recall": 0.7306299782766111,
1379
+ "support": 4143.0
1380
+ },
1381
+ "eval_I-MajorClaim": {
1382
+ "f1-score": 0.9076923076923077,
1383
+ "precision": 0.9007633587786259,
1384
+ "recall": 0.9147286821705426,
1385
+ "support": 2193.0
1386
+ },
1387
+ "eval_I-Premise": {
1388
+ "f1-score": 0.8980493191019507,
1389
+ "precision": 0.9234650967199327,
1390
+ "recall": 0.8739950648730399,
1391
+ "support": 12563.0
1392
+ },
1393
+ "eval_O": {
1394
+ "f1-score": 1.0,
1395
+ "precision": 1.0,
1396
+ "recall": 1.0,
1397
+ "support": 12536.0
1398
+ },
1399
+ "eval_accuracy": 0.9056817833379327,
1400
+ "eval_loss": 0.714400589466095,
1401
+ "eval_macro avg": {
1402
+ "f1-score": 0.8540854259191927,
1403
+ "precision": 0.8481794305304963,
1404
+ "recall": 0.8629252102037197,
1405
+ "support": 32613.0
1406
+ },
1407
+ "eval_runtime": 5.1631,
1408
+ "eval_samples_per_second": 15.688,
1409
+ "eval_steps_per_second": 2.13,
1410
+ "eval_weighted avg": {
1411
+ "f1-score": 0.9079755332777275,
1412
+ "precision": 0.911828926872852,
1413
+ "recall": 0.9056817833379327,
1414
+ "support": 32613.0
1415
+ },
1416
+ "step": 1782
1417
+ },
1418
+ {
1419
+ "epoch": 23.0,
1420
+ "eval_B-Claim": {
1421
+ "f1-score": 0.6942148760330579,
1422
+ "precision": 0.6774193548387096,
1423
+ "recall": 0.711864406779661,
1424
+ "support": 295.0
1425
+ },
1426
+ "eval_B-MajorClaim": {
1427
+ "f1-score": 0.88659793814433,
1428
+ "precision": 0.9555555555555556,
1429
+ "recall": 0.8269230769230769,
1430
+ "support": 156.0
1431
+ },
1432
+ "eval_B-Premise": {
1433
+ "f1-score": 0.8945205479452054,
1434
+ "precision": 0.8908594815825375,
1435
+ "recall": 0.8982118294360385,
1436
+ "support": 727.0
1437
+ },
1438
+ "eval_I-Claim": {
1439
+ "f1-score": 0.6700834326579261,
1440
+ "precision": 0.6618789733929833,
1441
+ "recall": 0.6784938450398262,
1442
+ "support": 4143.0
1443
+ },
1444
+ "eval_I-MajorClaim": {
1445
+ "f1-score": 0.8958790538892953,
1446
+ "precision": 0.9627882599580713,
1447
+ "recall": 0.8376652986776105,
1448
+ "support": 2193.0
1449
+ },
1450
+ "eval_I-Premise": {
1451
+ "f1-score": 0.9067846840795036,
1452
+ "precision": 0.900345260514752,
1453
+ "recall": 0.9133168829101329,
1454
+ "support": 12563.0
1455
+ },
1456
+ "eval_O": {
1457
+ "f1-score": 1.0,
1458
+ "precision": 1.0,
1459
+ "recall": 1.0,
1460
+ "support": 12536.0
1461
+ },
1462
+ "eval_accuracy": 0.909146659307638,
1463
+ "eval_loss": 0.6947330236434937,
1464
+ "eval_macro avg": {
1465
+ "f1-score": 0.8497257903927597,
1466
+ "precision": 0.8641209836918013,
1467
+ "recall": 0.8380679056809066,
1468
+ "support": 32613.0
1469
+ },
1470
+ "eval_runtime": 4.9764,
1471
+ "eval_samples_per_second": 16.277,
1472
+ "eval_steps_per_second": 2.21,
1473
+ "eval_weighted avg": {
1474
+ "f1-score": 0.9095199312515945,
1475
+ "precision": 0.9105926154648943,
1476
+ "recall": 0.909146659307638,
1477
+ "support": 32613.0
1478
+ },
1479
+ "step": 1863
1480
+ },
1481
+ {
1482
+ "epoch": 24.0,
1483
+ "eval_B-Claim": {
1484
+ "f1-score": 0.7096774193548386,
1485
+ "precision": 0.676923076923077,
1486
+ "recall": 0.7457627118644068,
1487
+ "support": 295.0
1488
+ },
1489
+ "eval_B-MajorClaim": {
1490
+ "f1-score": 0.9130434782608695,
1491
+ "precision": 0.8855421686746988,
1492
+ "recall": 0.9423076923076923,
1493
+ "support": 156.0
1494
+ },
1495
+ "eval_B-Premise": {
1496
+ "f1-score": 0.8896746817538898,
1497
+ "precision": 0.9155749636098981,
1498
+ "recall": 0.8651994497936726,
1499
+ "support": 727.0
1500
+ },
1501
+ "eval_I-Claim": {
1502
+ "f1-score": 0.6777306967984934,
1503
+ "precision": 0.6613829542844015,
1504
+ "recall": 0.6949070721699252,
1505
+ "support": 4143.0
1506
+ },
1507
+ "eval_I-MajorClaim": {
1508
+ "f1-score": 0.9096057503811806,
1509
+ "precision": 0.8707256046705588,
1510
+ "recall": 0.9521203830369357,
1511
+ "support": 2193.0
1512
+ },
1513
+ "eval_I-Premise": {
1514
+ "f1-score": 0.9036461494880823,
1515
+ "precision": 0.9190813302601252,
1516
+ "recall": 0.8887208469314655,
1517
+ "support": 12563.0
1518
+ },
1519
+ "eval_O": {
1520
+ "f1-score": 1.0,
1521
+ "precision": 1.0,
1522
+ "recall": 1.0,
1523
+ "support": 12536.0
1524
+ },
1525
+ "eval_accuracy": 0.9095759359764511,
1526
+ "eval_loss": 0.7040016055107117,
1527
+ "eval_macro avg": {
1528
+ "f1-score": 0.8576254537196221,
1529
+ "precision": 0.8470328712032513,
1530
+ "recall": 0.8698597365862997,
1531
+ "support": 32613.0
1532
+ },
1533
+ "eval_runtime": 4.987,
1534
+ "eval_samples_per_second": 16.242,
1535
+ "eval_steps_per_second": 2.206,
1536
+ "eval_weighted avg": {
1537
+ "f1-score": 0.9103637622541415,
1538
+ "precision": 0.9117679902876374,
1539
+ "recall": 0.9095759359764511,
1540
+ "support": 32613.0
1541
+ },
1542
+ "step": 1944
1543
+ }
1544
+ ],
1545
+ "logging_steps": 500,
1546
+ "max_steps": 4050,
1547
+ "num_input_tokens_seen": 0,
1548
+ "num_train_epochs": 50,
1549
+ "save_steps": 500,
1550
+ "total_flos": 3440262177576000.0,
1551
+ "train_batch_size": 4,
1552
+ "trial_name": null,
1553
+ "trial_params": null
1554
+ }
checkpoint-1944/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eff186592c44100b7fd5c301c21b9eebfc7f8bd335567cdc6ffe4a4d32ec927
3
+ size 4920
checkpoint-1944/vocab.json ADDED
The diff for this file is too large to render. See raw diff