Training in progress, epoch 24, checkpoint
Browse files- checkpoint-1944/config.json +61 -0
- checkpoint-1944/merges.txt +0 -0
- checkpoint-1944/model.safetensors +3 -0
- checkpoint-1944/optimizer.pt +3 -0
- checkpoint-1944/rng_state.pth +3 -0
- checkpoint-1944/scheduler.pt +3 -0
- checkpoint-1944/special_tokens_map.json +15 -0
- checkpoint-1944/tokenizer.json +0 -0
- checkpoint-1944/tokenizer_config.json +57 -0
- checkpoint-1944/trainer_state.json +1554 -0
- checkpoint-1944/training_args.bin +3 -0
- 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:a14de5aabe8a2ce3ab6985e31c42b7040d71a1ee32cedcf34043b699f7fba2db
|
3 |
+
size 592330980
|
checkpoint-1944/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7b1f7f849e3e31c96dd661e5371b45212c893db6361be8ce2e4b227d7779eb8
|
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": 0.0,
|
15 |
+
"precision": 0.0,
|
16 |
+
"recall": 0.0,
|
17 |
+
"support": 295.0
|
18 |
+
},
|
19 |
+
"eval_B-MajorClaim": {
|
20 |
+
"f1-score": 0.0,
|
21 |
+
"precision": 0.0,
|
22 |
+
"recall": 0.0,
|
23 |
+
"support": 156.0
|
24 |
+
},
|
25 |
+
"eval_B-Premise": {
|
26 |
+
"f1-score": 0.6820276497695853,
|
27 |
+
"precision": 0.6540404040404041,
|
28 |
+
"recall": 0.7125171939477304,
|
29 |
+
"support": 727.0
|
30 |
+
},
|
31 |
+
"eval_I-Claim": {
|
32 |
+
"f1-score": 0.43557936284183824,
|
33 |
+
"precision": 0.5235513385293121,
|
34 |
+
"recall": 0.3729181752353367,
|
35 |
+
"support": 4143.0
|
36 |
+
},
|
37 |
+
"eval_I-MajorClaim": {
|
38 |
+
"f1-score": 0.5835814547001276,
|
39 |
+
"precision": 0.5468314069350338,
|
40 |
+
"recall": 0.6256269949840402,
|
41 |
+
"support": 2193.0
|
42 |
+
},
|
43 |
+
"eval_I-Premise": {
|
44 |
+
"f1-score": 0.8638885700072705,
|
45 |
+
"precision": 0.8318349299926308,
|
46 |
+
"recall": 0.8985115020297699,
|
47 |
+
"support": 12563.0
|
48 |
+
},
|
49 |
+
"eval_O": {
|
50 |
+
"f1-score": 0.8838224593742419,
|
51 |
+
"precision": 0.8730234786775275,
|
52 |
+
"recall": 0.8948919449901768,
|
53 |
+
"support": 10180.0
|
54 |
+
},
|
55 |
+
"eval_accuracy": 0.7876854942657897,
|
56 |
+
"eval_loss": 0.5461820363998413,
|
57 |
+
"eval_macro avg": {
|
58 |
+
"f1-score": 0.4926999280990091,
|
59 |
+
"precision": 0.4898973654535584,
|
60 |
+
"recall": 0.500637973026722,
|
61 |
+
"support": 30257.0
|
62 |
+
},
|
63 |
+
"eval_runtime": 5.0655,
|
64 |
+
"eval_samples_per_second": 15.991,
|
65 |
+
"eval_steps_per_second": 2.172,
|
66 |
+
"eval_weighted avg": {
|
67 |
+
"f1-score": 0.7743853744001297,
|
68 |
+
"precision": 0.7661527277359783,
|
69 |
+
"recall": 0.7876854942657897,
|
70 |
+
"support": 30257.0
|
71 |
+
},
|
72 |
+
"step": 81
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.0,
|
76 |
+
"eval_B-Claim": {
|
77 |
+
"f1-score": 0.46397188049209137,
|
78 |
+
"precision": 0.48175182481751827,
|
79 |
+
"recall": 0.44745762711864406,
|
80 |
+
"support": 295.0
|
81 |
+
},
|
82 |
+
"eval_B-MajorClaim": {
|
83 |
+
"f1-score": 0.6402439024390244,
|
84 |
+
"precision": 0.6104651162790697,
|
85 |
+
"recall": 0.6730769230769231,
|
86 |
+
"support": 156.0
|
87 |
+
},
|
88 |
+
"eval_B-Premise": {
|
89 |
+
"f1-score": 0.7515299877600979,
|
90 |
+
"precision": 0.6769570011025359,
|
91 |
+
"recall": 0.844566712517194,
|
92 |
+
"support": 727.0
|
93 |
+
},
|
94 |
+
"eval_I-Claim": {
|
95 |
+
"f1-score": 0.5573419078242231,
|
96 |
+
"precision": 0.5500705218617772,
|
97 |
+
"recall": 0.5648081100651702,
|
98 |
+
"support": 4143.0
|
99 |
+
},
|
100 |
+
"eval_I-MajorClaim": {
|
101 |
+
"f1-score": 0.7704582651391162,
|
102 |
+
"precision": 0.6987012987012987,
|
103 |
+
"recall": 0.8586411308709531,
|
104 |
+
"support": 2193.0
|
105 |
+
},
|
106 |
+
"eval_I-Premise": {
|
107 |
+
"f1-score": 0.8736837792436597,
|
108 |
+
"precision": 0.9002026342451874,
|
109 |
+
"recall": 0.8486826394969355,
|
110 |
+
"support": 12563.0
|
111 |
+
},
|
112 |
+
"eval_O": {
|
113 |
+
"f1-score": 0.9114385688236163,
|
114 |
+
"precision": 0.9145485115221046,
|
115 |
+
"recall": 0.9083497053045186,
|
116 |
+
"support": 10180.0
|
117 |
+
},
|
118 |
+
"eval_accuracy": 0.8256932280133523,
|
119 |
+
"eval_loss": 0.4454804062843323,
|
120 |
+
"eval_macro avg": {
|
121 |
+
"f1-score": 0.7098097559602613,
|
122 |
+
"precision": 0.6903852726470703,
|
123 |
+
"recall": 0.7350832640643341,
|
124 |
+
"support": 30257.0
|
125 |
+
},
|
126 |
+
"eval_runtime": 5.0817,
|
127 |
+
"eval_samples_per_second": 15.94,
|
128 |
+
"eval_steps_per_second": 2.165,
|
129 |
+
"eval_weighted avg": {
|
130 |
+
"f1-score": 0.8274557458920446,
|
131 |
+
"precision": 0.8315444607100787,
|
132 |
+
"recall": 0.8256932280133523,
|
133 |
+
"support": 30257.0
|
134 |
+
},
|
135 |
+
"step": 162
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.0,
|
139 |
+
"eval_B-Claim": {
|
140 |
+
"f1-score": 0.5551724137931033,
|
141 |
+
"precision": 0.5649122807017544,
|
142 |
+
"recall": 0.5457627118644067,
|
143 |
+
"support": 295.0
|
144 |
+
},
|
145 |
+
"eval_B-MajorClaim": {
|
146 |
+
"f1-score": 0.7108433734939757,
|
147 |
+
"precision": 0.6704545454545454,
|
148 |
+
"recall": 0.7564102564102564,
|
149 |
+
"support": 156.0
|
150 |
+
},
|
151 |
+
"eval_B-Premise": {
|
152 |
+
"f1-score": 0.7860892388451444,
|
153 |
+
"precision": 0.7515683814303639,
|
154 |
+
"recall": 0.8239339752407153,
|
155 |
+
"support": 727.0
|
156 |
+
},
|
157 |
+
"eval_I-Claim": {
|
158 |
+
"f1-score": 0.5878616796047988,
|
159 |
+
"precision": 0.573296627666896,
|
160 |
+
"recall": 0.6031860970311369,
|
161 |
+
"support": 4143.0
|
162 |
+
},
|
163 |
+
"eval_I-MajorClaim": {
|
164 |
+
"f1-score": 0.7989093387866394,
|
165 |
+
"precision": 0.7961956521739131,
|
166 |
+
"recall": 0.801641586867305,
|
167 |
+
"support": 2193.0
|
168 |
+
},
|
169 |
+
"eval_I-Premise": {
|
170 |
+
"f1-score": 0.8824656529006482,
|
171 |
+
"precision": 0.9044793581815143,
|
172 |
+
"recall": 0.8614980498288626,
|
173 |
+
"support": 12563.0
|
174 |
+
},
|
175 |
+
"eval_O": {
|
176 |
+
"f1-score": 0.9169814976266588,
|
177 |
+
"precision": 0.9044525128989107,
|
178 |
+
"recall": 0.9298624754420433,
|
179 |
+
"support": 10180.0
|
180 |
+
},
|
181 |
+
"eval_accuracy": 0.8402683676504611,
|
182 |
+
"eval_loss": 0.41143855452537537,
|
183 |
+
"eval_macro avg": {
|
184 |
+
"f1-score": 0.7483318850072812,
|
185 |
+
"precision": 0.7379084797868425,
|
186 |
+
"recall": 0.7603278789549609,
|
187 |
+
"support": 30257.0
|
188 |
+
},
|
189 |
+
"eval_runtime": 5.0654,
|
190 |
+
"eval_samples_per_second": 15.991,
|
191 |
+
"eval_steps_per_second": 2.172,
|
192 |
+
"eval_weighted avg": {
|
193 |
+
"f1-score": 0.8412916372002002,
|
194 |
+
"precision": 0.8430827906594975,
|
195 |
+
"recall": 0.8402683676504611,
|
196 |
+
"support": 30257.0
|
197 |
+
},
|
198 |
+
"step": 243
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 4.0,
|
202 |
+
"eval_B-Claim": {
|
203 |
+
"f1-score": 0.5518394648829431,
|
204 |
+
"precision": 0.5445544554455446,
|
205 |
+
"recall": 0.559322033898305,
|
206 |
+
"support": 295.0
|
207 |
+
},
|
208 |
+
"eval_B-MajorClaim": {
|
209 |
+
"f1-score": 0.7048192771084337,
|
210 |
+
"precision": 0.6647727272727273,
|
211 |
+
"recall": 0.75,
|
212 |
+
"support": 156.0
|
213 |
+
},
|
214 |
+
"eval_B-Premise": {
|
215 |
+
"f1-score": 0.792225201072386,
|
216 |
+
"precision": 0.7725490196078432,
|
217 |
+
"recall": 0.81292984869326,
|
218 |
+
"support": 727.0
|
219 |
+
},
|
220 |
+
"eval_I-Claim": {
|
221 |
+
"f1-score": 0.577999737153371,
|
222 |
+
"precision": 0.6344489324870167,
|
223 |
+
"recall": 0.5307748008689356,
|
224 |
+
"support": 4143.0
|
225 |
+
},
|
226 |
+
"eval_I-MajorClaim": {
|
227 |
+
"f1-score": 0.800089746466233,
|
228 |
+
"precision": 0.7875441696113075,
|
229 |
+
"recall": 0.8130414956680346,
|
230 |
+
"support": 2193.0
|
231 |
+
},
|
232 |
+
"eval_I-Premise": {
|
233 |
+
"f1-score": 0.8919449901768174,
|
234 |
+
"precision": 0.8642131979695431,
|
235 |
+
"recall": 0.9215155615696887,
|
236 |
+
"support": 12563.0
|
237 |
+
},
|
238 |
+
"eval_O": {
|
239 |
+
"f1-score": 0.9180246175312703,
|
240 |
+
"precision": 0.9316273895013655,
|
241 |
+
"recall": 0.9048133595284872,
|
242 |
+
"support": 10180.0
|
243 |
+
},
|
244 |
+
"eval_accuracy": 0.8475063621641273,
|
245 |
+
"eval_loss": 0.476072758436203,
|
246 |
+
"eval_macro avg": {
|
247 |
+
"f1-score": 0.7481347191987793,
|
248 |
+
"precision": 0.7428156988421926,
|
249 |
+
"recall": 0.7560567286038158,
|
250 |
+
"support": 30257.0
|
251 |
+
},
|
252 |
+
"eval_runtime": 5.0796,
|
253 |
+
"eval_samples_per_second": 15.946,
|
254 |
+
"eval_steps_per_second": 2.166,
|
255 |
+
"eval_weighted avg": {
|
256 |
+
"f1-score": 0.8443975745657389,
|
257 |
+
"precision": 0.8435295888400192,
|
258 |
+
"recall": 0.8475063621641273,
|
259 |
+
"support": 30257.0
|
260 |
+
},
|
261 |
+
"step": 324
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 5.0,
|
265 |
+
"eval_B-Claim": {
|
266 |
+
"f1-score": 0.5932203389830508,
|
267 |
+
"precision": 0.5932203389830508,
|
268 |
+
"recall": 0.5932203389830508,
|
269 |
+
"support": 295.0
|
270 |
+
},
|
271 |
+
"eval_B-MajorClaim": {
|
272 |
+
"f1-score": 0.7398119122257053,
|
273 |
+
"precision": 0.7239263803680982,
|
274 |
+
"recall": 0.7564102564102564,
|
275 |
+
"support": 156.0
|
276 |
+
},
|
277 |
+
"eval_B-Premise": {
|
278 |
+
"f1-score": 0.7774172615184944,
|
279 |
+
"precision": 0.7358722358722358,
|
280 |
+
"recall": 0.8239339752407153,
|
281 |
+
"support": 727.0
|
282 |
+
},
|
283 |
+
"eval_I-Claim": {
|
284 |
+
"f1-score": 0.5827523883294604,
|
285 |
+
"precision": 0.6264224257563141,
|
286 |
+
"recall": 0.5447743181269611,
|
287 |
+
"support": 4143.0
|
288 |
+
},
|
289 |
+
"eval_I-MajorClaim": {
|
290 |
+
"f1-score": 0.79782711384034,
|
291 |
+
"precision": 0.8275355218030377,
|
292 |
+
"recall": 0.7701778385772914,
|
293 |
+
"support": 2193.0
|
294 |
+
},
|
295 |
+
"eval_I-Premise": {
|
296 |
+
"f1-score": 0.8862478777589133,
|
297 |
+
"precision": 0.8792698213726104,
|
298 |
+
"recall": 0.8933375786038367,
|
299 |
+
"support": 12563.0
|
300 |
+
},
|
301 |
+
"eval_O": {
|
302 |
+
"f1-score": 0.9135231488172665,
|
303 |
+
"precision": 0.8963789354259242,
|
304 |
+
"recall": 0.931335952848723,
|
305 |
+
"support": 10180.0
|
306 |
+
},
|
307 |
+
"eval_accuracy": 0.8441682916349935,
|
308 |
+
"eval_loss": 0.526358962059021,
|
309 |
+
"eval_macro avg": {
|
310 |
+
"f1-score": 0.7558285773533188,
|
311 |
+
"precision": 0.7546608085116101,
|
312 |
+
"recall": 0.7590271798272621,
|
313 |
+
"support": 30257.0
|
314 |
+
},
|
315 |
+
"eval_runtime": 5.076,
|
316 |
+
"eval_samples_per_second": 15.958,
|
317 |
+
"eval_steps_per_second": 2.167,
|
318 |
+
"eval_weighted avg": {
|
319 |
+
"f1-score": 0.841232400970915,
|
320 |
+
"precision": 0.8396195745969204,
|
321 |
+
"recall": 0.8441682916349935,
|
322 |
+
"support": 30257.0
|
323 |
+
},
|
324 |
+
"step": 405
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 6.0,
|
328 |
+
"eval_B-Claim": {
|
329 |
+
"f1-score": 0.5809682804674458,
|
330 |
+
"precision": 0.5723684210526315,
|
331 |
+
"recall": 0.5898305084745763,
|
332 |
+
"support": 295.0
|
333 |
+
},
|
334 |
+
"eval_B-MajorClaim": {
|
335 |
+
"f1-score": 0.7402597402597402,
|
336 |
+
"precision": 0.75,
|
337 |
+
"recall": 0.7307692307692307,
|
338 |
+
"support": 156.0
|
339 |
+
},
|
340 |
+
"eval_B-Premise": {
|
341 |
+
"f1-score": 0.7956298200514138,
|
342 |
+
"precision": 0.7466827503015682,
|
343 |
+
"recall": 0.8514442916093535,
|
344 |
+
"support": 727.0
|
345 |
+
},
|
346 |
+
"eval_I-Claim": {
|
347 |
+
"f1-score": 0.580742605412209,
|
348 |
+
"precision": 0.6067859021567596,
|
349 |
+
"recall": 0.556842867487328,
|
350 |
+
"support": 4143.0
|
351 |
+
},
|
352 |
+
"eval_I-MajorClaim": {
|
353 |
+
"f1-score": 0.798828125,
|
354 |
+
"precision": 0.859695218076721,
|
355 |
+
"recall": 0.7460100319197447,
|
356 |
+
"support": 2193.0
|
357 |
+
},
|
358 |
+
"eval_I-Premise": {
|
359 |
+
"f1-score": 0.8905630763194036,
|
360 |
+
"precision": 0.8781922303049063,
|
361 |
+
"recall": 0.9032874313460161,
|
362 |
+
"support": 12563.0
|
363 |
+
},
|
364 |
+
"eval_O": {
|
365 |
+
"f1-score": 0.9183922046285018,
|
366 |
+
"precision": 0.9110681488641856,
|
367 |
+
"recall": 0.9258349705304518,
|
368 |
+
"support": 10180.0
|
369 |
+
},
|
370 |
+
"eval_accuracy": 0.8468453580989523,
|
371 |
+
"eval_loss": 0.5279645919799805,
|
372 |
+
"eval_macro avg": {
|
373 |
+
"f1-score": 0.7579119788769592,
|
374 |
+
"precision": 0.7606846672509676,
|
375 |
+
"recall": 0.7577170474481001,
|
376 |
+
"support": 30257.0
|
377 |
+
},
|
378 |
+
"eval_runtime": 5.0684,
|
379 |
+
"eval_samples_per_second": 15.981,
|
380 |
+
"eval_steps_per_second": 2.17,
|
381 |
+
"eval_weighted avg": {
|
382 |
+
"f1-score": 0.8447801270668736,
|
383 |
+
"precision": 0.8439473640584135,
|
384 |
+
"recall": 0.8468453580989523,
|
385 |
+
"support": 30257.0
|
386 |
+
},
|
387 |
+
"step": 486
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 6.17,
|
391 |
+
"grad_norm": 3.7896041870117188,
|
392 |
+
"learning_rate": 1.7530864197530865e-05,
|
393 |
+
"loss": 0.4007,
|
394 |
+
"step": 500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 7.0,
|
398 |
+
"eval_B-Claim": {
|
399 |
+
"f1-score": 0.5654450261780105,
|
400 |
+
"precision": 0.5827338129496403,
|
401 |
+
"recall": 0.5491525423728814,
|
402 |
+
"support": 295.0
|
403 |
+
},
|
404 |
+
"eval_B-MajorClaim": {
|
405 |
+
"f1-score": 0.7454545454545455,
|
406 |
+
"precision": 0.7068965517241379,
|
407 |
+
"recall": 0.7884615384615384,
|
408 |
+
"support": 156.0
|
409 |
+
},
|
410 |
+
"eval_B-Premise": {
|
411 |
+
"f1-score": 0.8080155138978669,
|
412 |
+
"precision": 0.7621951219512195,
|
413 |
+
"recall": 0.859697386519945,
|
414 |
+
"support": 727.0
|
415 |
+
},
|
416 |
+
"eval_I-Claim": {
|
417 |
+
"f1-score": 0.5279187817258884,
|
418 |
+
"precision": 0.6115702479338843,
|
419 |
+
"recall": 0.4643977793869177,
|
420 |
+
"support": 4143.0
|
421 |
+
},
|
422 |
+
"eval_I-MajorClaim": {
|
423 |
+
"f1-score": 0.8239801667793555,
|
424 |
+
"precision": 0.8146167557932263,
|
425 |
+
"recall": 0.833561331509348,
|
426 |
+
"support": 2193.0
|
427 |
+
},
|
428 |
+
"eval_I-Premise": {
|
429 |
+
"f1-score": 0.8874376008707728,
|
430 |
+
"precision": 0.8396306818181818,
|
431 |
+
"recall": 0.9410172729443604,
|
432 |
+
"support": 12563.0
|
433 |
+
},
|
434 |
+
"eval_O": {
|
435 |
+
"f1-score": 0.916984006092917,
|
436 |
+
"precision": 0.9490278507619548,
|
437 |
+
"recall": 0.8870333988212181,
|
438 |
+
"support": 10180.0
|
439 |
+
},
|
440 |
+
"eval_accuracy": 0.8432428859437485,
|
441 |
+
"eval_loss": 0.673554003238678,
|
442 |
+
"eval_macro avg": {
|
443 |
+
"f1-score": 0.7536050915713366,
|
444 |
+
"precision": 0.7523815747046064,
|
445 |
+
"recall": 0.7604744642880299,
|
446 |
+
"support": 30257.0
|
447 |
+
},
|
448 |
+
"eval_runtime": 5.0724,
|
449 |
+
"eval_samples_per_second": 15.969,
|
450 |
+
"eval_steps_per_second": 2.169,
|
451 |
+
"eval_weighted avg": {
|
452 |
+
"f1-score": 0.8377716313785262,
|
453 |
+
"precision": 0.8383472270757442,
|
454 |
+
"recall": 0.8432428859437485,
|
455 |
+
"support": 30257.0
|
456 |
+
},
|
457 |
+
"step": 567
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 8.0,
|
461 |
+
"eval_B-Claim": {
|
462 |
+
"f1-score": 0.5714285714285714,
|
463 |
+
"precision": 0.554140127388535,
|
464 |
+
"recall": 0.5898305084745763,
|
465 |
+
"support": 295.0
|
466 |
+
},
|
467 |
+
"eval_B-MajorClaim": {
|
468 |
+
"f1-score": 0.7103825136612022,
|
469 |
+
"precision": 0.6190476190476191,
|
470 |
+
"recall": 0.8333333333333334,
|
471 |
+
"support": 156.0
|
472 |
+
},
|
473 |
+
"eval_B-Premise": {
|
474 |
+
"f1-score": 0.7976111479761113,
|
475 |
+
"precision": 0.7705128205128206,
|
476 |
+
"recall": 0.8266850068775791,
|
477 |
+
"support": 727.0
|
478 |
+
},
|
479 |
+
"eval_I-Claim": {
|
480 |
+
"f1-score": 0.5769132977370963,
|
481 |
+
"precision": 0.6094547408004297,
|
482 |
+
"recall": 0.5476707699734492,
|
483 |
+
"support": 4143.0
|
484 |
+
},
|
485 |
+
"eval_I-MajorClaim": {
|
486 |
+
"f1-score": 0.7987654320987654,
|
487 |
+
"precision": 0.7277840269966255,
|
488 |
+
"recall": 0.8850889192886456,
|
489 |
+
"support": 2193.0
|
490 |
+
},
|
491 |
+
"eval_I-Premise": {
|
492 |
+
"f1-score": 0.8899450117831893,
|
493 |
+
"precision": 0.8784213382957277,
|
494 |
+
"recall": 0.9017750537292049,
|
495 |
+
"support": 12563.0
|
496 |
+
},
|
497 |
+
"eval_O": {
|
498 |
+
"f1-score": 0.9160536128187039,
|
499 |
+
"precision": 0.9404096834264432,
|
500 |
+
"recall": 0.8929273084479371,
|
501 |
+
"support": 10180.0
|
502 |
+
},
|
503 |
+
"eval_accuracy": 0.8439038900089235,
|
504 |
+
"eval_loss": 0.6914934515953064,
|
505 |
+
"eval_macro avg": {
|
506 |
+
"f1-score": 0.7515856553576629,
|
507 |
+
"precision": 0.7285386223526001,
|
508 |
+
"recall": 0.7824729857321036,
|
509 |
+
"support": 30257.0
|
510 |
+
},
|
511 |
+
"eval_runtime": 5.0936,
|
512 |
+
"eval_samples_per_second": 15.902,
|
513 |
+
"eval_steps_per_second": 2.16,
|
514 |
+
"eval_weighted avg": {
|
515 |
+
"f1-score": 0.843008353502502,
|
516 |
+
"precision": 0.8444388009152946,
|
517 |
+
"recall": 0.8439038900089235,
|
518 |
+
"support": 30257.0
|
519 |
+
},
|
520 |
+
"step": 648
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 9.0,
|
524 |
+
"eval_B-Claim": {
|
525 |
+
"f1-score": 0.5940246045694201,
|
526 |
+
"precision": 0.6167883211678832,
|
527 |
+
"recall": 0.5728813559322034,
|
528 |
+
"support": 295.0
|
529 |
+
},
|
530 |
+
"eval_B-MajorClaim": {
|
531 |
+
"f1-score": 0.7795527156549521,
|
532 |
+
"precision": 0.7770700636942676,
|
533 |
+
"recall": 0.782051282051282,
|
534 |
+
"support": 156.0
|
535 |
+
},
|
536 |
+
"eval_B-Premise": {
|
537 |
+
"f1-score": 0.8103896103896104,
|
538 |
+
"precision": 0.7675276752767528,
|
539 |
+
"recall": 0.8583218707015131,
|
540 |
+
"support": 727.0
|
541 |
+
},
|
542 |
+
"eval_I-Claim": {
|
543 |
+
"f1-score": 0.597254004576659,
|
544 |
+
"precision": 0.6309427880741337,
|
545 |
+
"recall": 0.5669804489500362,
|
546 |
+
"support": 4143.0
|
547 |
+
},
|
548 |
+
"eval_I-MajorClaim": {
|
549 |
+
"f1-score": 0.8170818505338079,
|
550 |
+
"precision": 0.8516320474777448,
|
551 |
+
"recall": 0.7852257181942545,
|
552 |
+
"support": 2193.0
|
553 |
+
},
|
554 |
+
"eval_I-Premise": {
|
555 |
+
"f1-score": 0.8963960457694404,
|
556 |
+
"precision": 0.8770086055898256,
|
557 |
+
"recall": 0.9166600334315053,
|
558 |
+
"support": 12563.0
|
559 |
+
},
|
560 |
+
"eval_O": {
|
561 |
+
"f1-score": 0.9201161588817246,
|
562 |
+
"precision": 0.9220676728815231,
|
563 |
+
"recall": 0.9181728880157171,
|
564 |
+
"support": 10180.0
|
565 |
+
},
|
566 |
+
"eval_accuracy": 0.8543147040354299,
|
567 |
+
"eval_loss": 0.6210296154022217,
|
568 |
+
"eval_macro avg": {
|
569 |
+
"f1-score": 0.7735449986250879,
|
570 |
+
"precision": 0.7775767391660188,
|
571 |
+
"recall": 0.7714705138966444,
|
572 |
+
"support": 30257.0
|
573 |
+
},
|
574 |
+
"eval_runtime": 5.1135,
|
575 |
+
"eval_samples_per_second": 15.84,
|
576 |
+
"eval_steps_per_second": 2.151,
|
577 |
+
"eval_weighted avg": {
|
578 |
+
"f1-score": 0.8520504540550145,
|
579 |
+
"precision": 0.8509535372864376,
|
580 |
+
"recall": 0.8543147040354299,
|
581 |
+
"support": 30257.0
|
582 |
+
},
|
583 |
+
"step": 729
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 10.0,
|
587 |
+
"eval_B-Claim": {
|
588 |
+
"f1-score": 0.6135338345864663,
|
589 |
+
"precision": 0.5513513513513514,
|
590 |
+
"recall": 0.6915254237288135,
|
591 |
+
"support": 295.0
|
592 |
+
},
|
593 |
+
"eval_B-MajorClaim": {
|
594 |
+
"f1-score": 0.7411764705882354,
|
595 |
+
"precision": 0.6847826086956522,
|
596 |
+
"recall": 0.8076923076923077,
|
597 |
+
"support": 156.0
|
598 |
+
},
|
599 |
+
"eval_B-Premise": {
|
600 |
+
"f1-score": 0.7975708502024291,
|
601 |
+
"precision": 0.7827814569536424,
|
602 |
+
"recall": 0.81292984869326,
|
603 |
+
"support": 727.0
|
604 |
+
},
|
605 |
+
"eval_I-Claim": {
|
606 |
+
"f1-score": 0.6205202634810763,
|
607 |
+
"precision": 0.5772746157041961,
|
608 |
+
"recall": 0.6707699734491914,
|
609 |
+
"support": 4143.0
|
610 |
+
},
|
611 |
+
"eval_I-MajorClaim": {
|
612 |
+
"f1-score": 0.7967443906731192,
|
613 |
+
"precision": 0.7696557586060349,
|
614 |
+
"recall": 0.8258093935248518,
|
615 |
+
"support": 2193.0
|
616 |
+
},
|
617 |
+
"eval_I-Premise": {
|
618 |
+
"f1-score": 0.8895712958099318,
|
619 |
+
"precision": 0.9033316921056951,
|
620 |
+
"recall": 0.876223831887288,
|
621 |
+
"support": 12563.0
|
622 |
+
},
|
623 |
+
"eval_O": {
|
624 |
+
"f1-score": 0.9100379266750948,
|
625 |
+
"precision": 0.9377800937988535,
|
626 |
+
"recall": 0.8838899803536345,
|
627 |
+
"support": 10180.0
|
628 |
+
},
|
629 |
+
"eval_accuracy": 0.8433420365535248,
|
630 |
+
"eval_loss": 0.7195751070976257,
|
631 |
+
"eval_macro avg": {
|
632 |
+
"f1-score": 0.7670221474309076,
|
633 |
+
"precision": 0.7438510824593465,
|
634 |
+
"recall": 0.7955486799041925,
|
635 |
+
"support": 30257.0
|
636 |
+
},
|
637 |
+
"eval_runtime": 5.1021,
|
638 |
+
"eval_samples_per_second": 15.876,
|
639 |
+
"eval_steps_per_second": 2.156,
|
640 |
+
"eval_weighted avg": {
|
641 |
+
"f1-score": 0.847222004887227,
|
642 |
+
"precision": 0.8531321039459353,
|
643 |
+
"recall": 0.8433420365535248,
|
644 |
+
"support": 30257.0
|
645 |
+
},
|
646 |
+
"step": 810
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 11.0,
|
650 |
+
"eval_B-Claim": {
|
651 |
+
"f1-score": 0.6165884194053208,
|
652 |
+
"precision": 0.5726744186046512,
|
653 |
+
"recall": 0.6677966101694915,
|
654 |
+
"support": 295.0
|
655 |
+
},
|
656 |
+
"eval_B-MajorClaim": {
|
657 |
+
"f1-score": 0.7208672086720868,
|
658 |
+
"precision": 0.6244131455399061,
|
659 |
+
"recall": 0.8525641025641025,
|
660 |
+
"support": 156.0
|
661 |
+
},
|
662 |
+
"eval_B-Premise": {
|
663 |
+
"f1-score": 0.8049792531120332,
|
664 |
+
"precision": 0.8094575799721836,
|
665 |
+
"recall": 0.8005502063273727,
|
666 |
+
"support": 727.0
|
667 |
+
},
|
668 |
+
"eval_I-Claim": {
|
669 |
+
"f1-score": 0.6097560975609757,
|
670 |
+
"precision": 0.587642713230356,
|
671 |
+
"recall": 0.6335988414192614,
|
672 |
+
"support": 4143.0
|
673 |
+
},
|
674 |
+
"eval_I-MajorClaim": {
|
675 |
+
"f1-score": 0.7834637768412603,
|
676 |
+
"precision": 0.6996415770609319,
|
677 |
+
"recall": 0.8901048791609667,
|
678 |
+
"support": 2193.0
|
679 |
+
},
|
680 |
+
"eval_I-Premise": {
|
681 |
+
"f1-score": 0.8909987071751778,
|
682 |
+
"precision": 0.9046681434079908,
|
683 |
+
"recall": 0.8777362095040994,
|
684 |
+
"support": 12563.0
|
685 |
+
},
|
686 |
+
"eval_O": {
|
687 |
+
"f1-score": 0.9085467917829064,
|
688 |
+
"precision": 0.9392763502884112,
|
689 |
+
"recall": 0.8797642436149312,
|
690 |
+
"support": 10180.0
|
691 |
+
},
|
692 |
+
"eval_accuracy": 0.8418547774068811,
|
693 |
+
"eval_loss": 0.7594641447067261,
|
694 |
+
"eval_macro avg": {
|
695 |
+
"f1-score": 0.7621714649356802,
|
696 |
+
"precision": 0.7339677040149185,
|
697 |
+
"recall": 0.8003021561086037,
|
698 |
+
"support": 30257.0
|
699 |
+
},
|
700 |
+
"eval_runtime": 5.074,
|
701 |
+
"eval_samples_per_second": 15.964,
|
702 |
+
"eval_steps_per_second": 2.168,
|
703 |
+
"eval_weighted avg": {
|
704 |
+
"f1-score": 0.8449795901341711,
|
705 |
+
"precision": 0.8510731379783514,
|
706 |
+
"recall": 0.8418547774068811,
|
707 |
+
"support": 30257.0
|
708 |
+
},
|
709 |
+
"step": 891
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 12.0,
|
713 |
+
"eval_B-Claim": {
|
714 |
+
"f1-score": 0.6103448275862069,
|
715 |
+
"precision": 0.6210526315789474,
|
716 |
+
"recall": 0.6,
|
717 |
+
"support": 295.0
|
718 |
+
},
|
719 |
+
"eval_B-MajorClaim": {
|
720 |
+
"f1-score": 0.7815384615384615,
|
721 |
+
"precision": 0.7514792899408284,
|
722 |
+
"recall": 0.8141025641025641,
|
723 |
+
"support": 156.0
|
724 |
+
},
|
725 |
+
"eval_B-Premise": {
|
726 |
+
"f1-score": 0.8209255533199196,
|
727 |
+
"precision": 0.8010471204188482,
|
728 |
+
"recall": 0.8418156808803301,
|
729 |
+
"support": 727.0
|
730 |
+
},
|
731 |
+
"eval_I-Claim": {
|
732 |
+
"f1-score": 0.6016401590457257,
|
733 |
+
"precision": 0.6199743918053777,
|
734 |
+
"recall": 0.5843591600289645,
|
735 |
+
"support": 4143.0
|
736 |
+
},
|
737 |
+
"eval_I-MajorClaim": {
|
738 |
+
"f1-score": 0.8330076004343105,
|
739 |
+
"precision": 0.7951907131011609,
|
740 |
+
"recall": 0.8746010031919744,
|
741 |
+
"support": 2193.0
|
742 |
+
},
|
743 |
+
"eval_I-Premise": {
|
744 |
+
"f1-score": 0.8897350468031097,
|
745 |
+
"precision": 0.886710411890268,
|
746 |
+
"recall": 0.8927803868502746,
|
747 |
+
"support": 12563.0
|
748 |
+
},
|
749 |
+
"eval_O": {
|
750 |
+
"f1-score": 0.911568656495334,
|
751 |
+
"precision": 0.9164102054998511,
|
752 |
+
"recall": 0.906777996070727,
|
753 |
+
"support": 10180.0
|
754 |
+
},
|
755 |
+
"eval_accuracy": 0.8494563241563936,
|
756 |
+
"eval_loss": 0.8027455806732178,
|
757 |
+
"eval_macro avg": {
|
758 |
+
"f1-score": 0.7783943293175811,
|
759 |
+
"precision": 0.7702663948907544,
|
760 |
+
"recall": 0.7877766844464048,
|
761 |
+
"support": 30257.0
|
762 |
+
},
|
763 |
+
"eval_runtime": 5.087,
|
764 |
+
"eval_samples_per_second": 15.923,
|
765 |
+
"eval_steps_per_second": 2.162,
|
766 |
+
"eval_weighted avg": {
|
767 |
+
"f1-score": 0.848586302812254,
|
768 |
+
"precision": 0.8482006969540109,
|
769 |
+
"recall": 0.8494563241563936,
|
770 |
+
"support": 30257.0
|
771 |
+
},
|
772 |
+
"step": 972
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 12.35,
|
776 |
+
"grad_norm": 4.786133289337158,
|
777 |
+
"learning_rate": 1.506172839506173e-05,
|
778 |
+
"loss": 0.0725,
|
779 |
+
"step": 1000
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 13.0,
|
783 |
+
"eval_B-Claim": {
|
784 |
+
"f1-score": 0.6273187183811131,
|
785 |
+
"precision": 0.6241610738255033,
|
786 |
+
"recall": 0.6305084745762712,
|
787 |
+
"support": 295.0
|
788 |
+
},
|
789 |
+
"eval_B-MajorClaim": {
|
790 |
+
"f1-score": 0.7724550898203593,
|
791 |
+
"precision": 0.7247191011235955,
|
792 |
+
"recall": 0.8269230769230769,
|
793 |
+
"support": 156.0
|
794 |
+
},
|
795 |
+
"eval_B-Premise": {
|
796 |
+
"f1-score": 0.8049620951068229,
|
797 |
+
"precision": 0.8066298342541437,
|
798 |
+
"recall": 0.8033012379642366,
|
799 |
+
"support": 727.0
|
800 |
+
},
|
801 |
+
"eval_I-Claim": {
|
802 |
+
"f1-score": 0.6208425720620842,
|
803 |
+
"precision": 0.6339622641509434,
|
804 |
+
"recall": 0.6082548877624909,
|
805 |
+
"support": 4143.0
|
806 |
+
},
|
807 |
+
"eval_I-MajorClaim": {
|
808 |
+
"f1-score": 0.8316106804478898,
|
809 |
+
"precision": 0.7878416972664218,
|
810 |
+
"recall": 0.8805289557683539,
|
811 |
+
"support": 2193.0
|
812 |
+
},
|
813 |
+
"eval_I-Premise": {
|
814 |
+
"f1-score": 0.893793214343142,
|
815 |
+
"precision": 0.9028668886542679,
|
816 |
+
"recall": 0.8849001034784685,
|
817 |
+
"support": 12563.0
|
818 |
+
},
|
819 |
+
"eval_O": {
|
820 |
+
"f1-score": 0.9158942335837642,
|
821 |
+
"precision": 0.9097693351424695,
|
822 |
+
"recall": 0.9221021611001965,
|
823 |
+
"support": 10180.0
|
824 |
+
},
|
825 |
+
"eval_accuracy": 0.8544799550517236,
|
826 |
+
"eval_loss": 0.8123154044151306,
|
827 |
+
"eval_macro avg": {
|
828 |
+
"f1-score": 0.7809823719635965,
|
829 |
+
"precision": 0.7699928849167635,
|
830 |
+
"recall": 0.7937884139390137,
|
831 |
+
"support": 30257.0
|
832 |
+
},
|
833 |
+
"eval_runtime": 5.0805,
|
834 |
+
"eval_samples_per_second": 15.943,
|
835 |
+
"eval_steps_per_second": 2.165,
|
836 |
+
"eval_weighted avg": {
|
837 |
+
"f1-score": 0.8539898174646564,
|
838 |
+
"precision": 0.8540838365486697,
|
839 |
+
"recall": 0.8544799550517236,
|
840 |
+
"support": 30257.0
|
841 |
+
},
|
842 |
+
"step": 1053
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 14.0,
|
846 |
+
"eval_B-Claim": {
|
847 |
+
"f1-score": 0.6054421768707484,
|
848 |
+
"precision": 0.6075085324232082,
|
849 |
+
"recall": 0.6033898305084746,
|
850 |
+
"support": 295.0
|
851 |
+
},
|
852 |
+
"eval_B-MajorClaim": {
|
853 |
+
"f1-score": 0.7645259938837919,
|
854 |
+
"precision": 0.7309941520467836,
|
855 |
+
"recall": 0.8012820512820513,
|
856 |
+
"support": 156.0
|
857 |
+
},
|
858 |
+
"eval_B-Premise": {
|
859 |
+
"f1-score": 0.8018995929443691,
|
860 |
+
"precision": 0.7911646586345381,
|
861 |
+
"recall": 0.81292984869326,
|
862 |
+
"support": 727.0
|
863 |
+
},
|
864 |
+
"eval_I-Claim": {
|
865 |
+
"f1-score": 0.5895522388059701,
|
866 |
+
"precision": 0.6081601231716706,
|
867 |
+
"recall": 0.5720492396813903,
|
868 |
+
"support": 4143.0
|
869 |
+
},
|
870 |
+
"eval_I-MajorClaim": {
|
871 |
+
"f1-score": 0.8291814946619217,
|
872 |
+
"precision": 0.809379070777247,
|
873 |
+
"recall": 0.8499772001823985,
|
874 |
+
"support": 2193.0
|
875 |
+
},
|
876 |
+
"eval_I-Premise": {
|
877 |
+
"f1-score": 0.8850040096230954,
|
878 |
+
"precision": 0.8916538741213541,
|
879 |
+
"recall": 0.8784525989015363,
|
880 |
+
"support": 12563.0
|
881 |
+
},
|
882 |
+
"eval_O": {
|
883 |
+
"f1-score": 0.9117148530195166,
|
884 |
+
"precision": 0.8991307670264591,
|
885 |
+
"recall": 0.924656188605108,
|
886 |
+
"support": 10180.0
|
887 |
+
},
|
888 |
+
"eval_accuracy": 0.8453250487490498,
|
889 |
+
"eval_loss": 0.8416568040847778,
|
890 |
+
"eval_macro avg": {
|
891 |
+
"f1-score": 0.7696171942584875,
|
892 |
+
"precision": 0.7625701683144658,
|
893 |
+
"recall": 0.7775338511220314,
|
894 |
+
"support": 30257.0
|
895 |
+
},
|
896 |
+
"eval_runtime": 5.1033,
|
897 |
+
"eval_samples_per_second": 15.872,
|
898 |
+
"eval_steps_per_second": 2.155,
|
899 |
+
"eval_weighted avg": {
|
900 |
+
"f1-score": 0.8441459834449434,
|
901 |
+
"precision": 0.8433751308140963,
|
902 |
+
"recall": 0.8453250487490498,
|
903 |
+
"support": 30257.0
|
904 |
+
},
|
905 |
+
"step": 1134
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 15.0,
|
909 |
+
"eval_B-Claim": {
|
910 |
+
"f1-score": 0.5912162162162161,
|
911 |
+
"precision": 0.5892255892255892,
|
912 |
+
"recall": 0.5932203389830508,
|
913 |
+
"support": 295.0
|
914 |
+
},
|
915 |
+
"eval_B-MajorClaim": {
|
916 |
+
"f1-score": 0.7435158501440923,
|
917 |
+
"precision": 0.675392670157068,
|
918 |
+
"recall": 0.8269230769230769,
|
919 |
+
"support": 156.0
|
920 |
+
},
|
921 |
+
"eval_B-Premise": {
|
922 |
+
"f1-score": 0.806833114323259,
|
923 |
+
"precision": 0.7723270440251573,
|
924 |
+
"recall": 0.844566712517194,
|
925 |
+
"support": 727.0
|
926 |
+
},
|
927 |
+
"eval_I-Claim": {
|
928 |
+
"f1-score": 0.5910395607138401,
|
929 |
+
"precision": 0.6118863049095608,
|
930 |
+
"recall": 0.5715664977069757,
|
931 |
+
"support": 4143.0
|
932 |
+
},
|
933 |
+
"eval_I-MajorClaim": {
|
934 |
+
"f1-score": 0.7929240374609781,
|
935 |
+
"precision": 0.7293261868300153,
|
936 |
+
"recall": 0.8686730506155951,
|
937 |
+
"support": 2193.0
|
938 |
+
},
|
939 |
+
"eval_I-Premise": {
|
940 |
+
"f1-score": 0.8917323614467377,
|
941 |
+
"precision": 0.8876182965299685,
|
942 |
+
"recall": 0.8958847409058346,
|
943 |
+
"support": 12563.0
|
944 |
+
},
|
945 |
+
"eval_O": {
|
946 |
+
"f1-score": 0.9167667066826731,
|
947 |
+
"precision": 0.933958418263351,
|
948 |
+
"recall": 0.900196463654224,
|
949 |
+
"support": 10180.0
|
950 |
+
},
|
951 |
+
"eval_accuracy": 0.8464157054565885,
|
952 |
+
"eval_loss": 0.8344405293464661,
|
953 |
+
"eval_macro avg": {
|
954 |
+
"f1-score": 0.7620039781411139,
|
955 |
+
"precision": 0.7428192157058158,
|
956 |
+
"recall": 0.7858615544722787,
|
957 |
+
"support": 30257.0
|
958 |
+
},
|
959 |
+
"eval_runtime": 5.0958,
|
960 |
+
"eval_samples_per_second": 15.896,
|
961 |
+
"eval_steps_per_second": 2.159,
|
962 |
+
"eval_weighted avg": {
|
963 |
+
"f1-score": 0.8460866237761051,
|
964 |
+
"precision": 0.847207826703169,
|
965 |
+
"recall": 0.8464157054565885,
|
966 |
+
"support": 30257.0
|
967 |
+
},
|
968 |
+
"step": 1215
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 16.0,
|
972 |
+
"eval_B-Claim": {
|
973 |
+
"f1-score": 0.6222961730449251,
|
974 |
+
"precision": 0.6111111111111112,
|
975 |
+
"recall": 0.6338983050847458,
|
976 |
+
"support": 295.0
|
977 |
+
},
|
978 |
+
"eval_B-MajorClaim": {
|
979 |
+
"f1-score": 0.7428571428571429,
|
980 |
+
"precision": 0.6701030927835051,
|
981 |
+
"recall": 0.8333333333333334,
|
982 |
+
"support": 156.0
|
983 |
+
},
|
984 |
+
"eval_B-Premise": {
|
985 |
+
"f1-score": 0.8096192384769539,
|
986 |
+
"precision": 0.787012987012987,
|
987 |
+
"recall": 0.8335625859697386,
|
988 |
+
"support": 727.0
|
989 |
+
},
|
990 |
+
"eval_I-Claim": {
|
991 |
+
"f1-score": 0.6160823731306693,
|
992 |
+
"precision": 0.6259028642590286,
|
993 |
+
"recall": 0.6065652908520396,
|
994 |
+
"support": 4143.0
|
995 |
+
},
|
996 |
+
"eval_I-MajorClaim": {
|
997 |
+
"f1-score": 0.791569086651054,
|
998 |
+
"precision": 0.7424121405750799,
|
999 |
+
"recall": 0.8476972184222527,
|
1000 |
+
"support": 2193.0
|
1001 |
+
},
|
1002 |
+
"eval_I-Premise": {
|
1003 |
+
"f1-score": 0.8906192669900933,
|
1004 |
+
"precision": 0.9128363697141902,
|
1005 |
+
"recall": 0.869457932022606,
|
1006 |
+
"support": 12563.0
|
1007 |
+
},
|
1008 |
+
"eval_O": {
|
1009 |
+
"f1-score": 0.9053283048061116,
|
1010 |
+
"precision": 0.891449247762331,
|
1011 |
+
"recall": 0.9196463654223969,
|
1012 |
+
"support": 10180.0
|
1013 |
+
},
|
1014 |
+
"eval_accuracy": 0.8454241993588261,
|
1015 |
+
"eval_loss": 0.8837452530860901,
|
1016 |
+
"eval_macro avg": {
|
1017 |
+
"f1-score": 0.76833879799385,
|
1018 |
+
"precision": 0.7486896876026048,
|
1019 |
+
"recall": 0.7920230044438733,
|
1020 |
+
"support": 30257.0
|
1021 |
+
},
|
1022 |
+
"eval_runtime": 5.1001,
|
1023 |
+
"eval_samples_per_second": 15.882,
|
1024 |
+
"eval_steps_per_second": 2.157,
|
1025 |
+
"eval_weighted avg": {
|
1026 |
+
"f1-score": 0.8454733960648972,
|
1027 |
+
"precision": 0.8467830369057293,
|
1028 |
+
"recall": 0.8454241993588261,
|
1029 |
+
"support": 30257.0
|
1030 |
+
},
|
1031 |
+
"step": 1296
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 17.0,
|
1035 |
+
"eval_B-Claim": {
|
1036 |
+
"f1-score": 0.5913978494623656,
|
1037 |
+
"precision": 0.6273764258555133,
|
1038 |
+
"recall": 0.559322033898305,
|
1039 |
+
"support": 295.0
|
1040 |
+
},
|
1041 |
+
"eval_B-MajorClaim": {
|
1042 |
+
"f1-score": 0.7801857585139319,
|
1043 |
+
"precision": 0.7544910179640718,
|
1044 |
+
"recall": 0.8076923076923077,
|
1045 |
+
"support": 156.0
|
1046 |
+
},
|
1047 |
+
"eval_B-Premise": {
|
1048 |
+
"f1-score": 0.8131147540983606,
|
1049 |
+
"precision": 0.7769423558897243,
|
1050 |
+
"recall": 0.8528198074277854,
|
1051 |
+
"support": 727.0
|
1052 |
+
},
|
1053 |
+
"eval_I-Claim": {
|
1054 |
+
"f1-score": 0.5990747879722437,
|
1055 |
+
"precision": 0.640560593569662,
|
1056 |
+
"recall": 0.5626357711803042,
|
1057 |
+
"support": 4143.0
|
1058 |
+
},
|
1059 |
+
"eval_I-MajorClaim": {
|
1060 |
+
"f1-score": 0.8188068307828787,
|
1061 |
+
"precision": 0.7970639032815199,
|
1062 |
+
"recall": 0.8417692658458732,
|
1063 |
+
"support": 2193.0
|
1064 |
+
},
|
1065 |
+
"eval_I-Premise": {
|
1066 |
+
"f1-score": 0.8951778656126482,
|
1067 |
+
"precision": 0.8890633587186936,
|
1068 |
+
"recall": 0.9013770596195176,
|
1069 |
+
"support": 12563.0
|
1070 |
+
},
|
1071 |
+
"eval_O": {
|
1072 |
+
"f1-score": 0.913778817565921,
|
1073 |
+
"precision": 0.9068395085614782,
|
1074 |
+
"recall": 0.9208251473477407,
|
1075 |
+
"support": 10180.0
|
1076 |
+
},
|
1077 |
+
"eval_accuracy": 0.8522325412301286,
|
1078 |
+
"eval_loss": 0.9348286986351013,
|
1079 |
+
"eval_macro avg": {
|
1080 |
+
"f1-score": 0.7730766662869072,
|
1081 |
+
"precision": 0.7703338805486661,
|
1082 |
+
"recall": 0.7780630561445477,
|
1083 |
+
"support": 30257.0
|
1084 |
+
},
|
1085 |
+
"eval_runtime": 5.0975,
|
1086 |
+
"eval_samples_per_second": 15.89,
|
1087 |
+
"eval_steps_per_second": 2.158,
|
1088 |
+
"eval_weighted avg": {
|
1089 |
+
"f1-score": 0.8498299198578085,
|
1090 |
+
"precision": 0.8484101724875526,
|
1091 |
+
"recall": 0.8522325412301286,
|
1092 |
+
"support": 30257.0
|
1093 |
+
},
|
1094 |
+
"step": 1377
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 18.0,
|
1098 |
+
"eval_B-Claim": {
|
1099 |
+
"f1-score": 0.604200323101777,
|
1100 |
+
"precision": 0.5771604938271605,
|
1101 |
+
"recall": 0.6338983050847458,
|
1102 |
+
"support": 295.0
|
1103 |
+
},
|
1104 |
+
"eval_B-MajorClaim": {
|
1105 |
+
"f1-score": 0.7987421383647798,
|
1106 |
+
"precision": 0.7839506172839507,
|
1107 |
+
"recall": 0.8141025641025641,
|
1108 |
+
"support": 156.0
|
1109 |
+
},
|
1110 |
+
"eval_B-Premise": {
|
1111 |
+
"f1-score": 0.8080808080808081,
|
1112 |
+
"precision": 0.7915567282321899,
|
1113 |
+
"recall": 0.8253094910591472,
|
1114 |
+
"support": 727.0
|
1115 |
+
},
|
1116 |
+
"eval_I-Claim": {
|
1117 |
+
"f1-score": 0.621889400921659,
|
1118 |
+
"precision": 0.5948864888692968,
|
1119 |
+
"recall": 0.6514602944726043,
|
1120 |
+
"support": 4143.0
|
1121 |
+
},
|
1122 |
+
"eval_I-MajorClaim": {
|
1123 |
+
"f1-score": 0.8260968401909524,
|
1124 |
+
"precision": 0.8236627379873074,
|
1125 |
+
"recall": 0.8285453716370269,
|
1126 |
+
"support": 2193.0
|
1127 |
+
},
|
1128 |
+
"eval_I-Premise": {
|
1129 |
+
"f1-score": 0.8907664941785252,
|
1130 |
+
"precision": 0.9050357348229688,
|
1131 |
+
"recall": 0.876940221284725,
|
1132 |
+
"support": 12563.0
|
1133 |
+
},
|
1134 |
+
"eval_O": {
|
1135 |
+
"f1-score": 0.9170981900675642,
|
1136 |
+
"precision": 0.9208675844310191,
|
1137 |
+
"recall": 0.9133595284872299,
|
1138 |
+
"support": 10180.0
|
1139 |
+
},
|
1140 |
+
"eval_accuracy": 0.8508774828965198,
|
1141 |
+
"eval_loss": 0.8984508514404297,
|
1142 |
+
"eval_macro avg": {
|
1143 |
+
"f1-score": 0.7809820278437237,
|
1144 |
+
"precision": 0.7710171979219849,
|
1145 |
+
"recall": 0.7919451108754348,
|
1146 |
+
"support": 30257.0
|
1147 |
+
},
|
1148 |
+
"eval_runtime": 5.0793,
|
1149 |
+
"eval_samples_per_second": 15.947,
|
1150 |
+
"eval_steps_per_second": 2.166,
|
1151 |
+
"eval_weighted avg": {
|
1152 |
+
"f1-score": 0.8528669338065401,
|
1153 |
+
"precision": 0.8554491006140895,
|
1154 |
+
"recall": 0.8508774828965198,
|
1155 |
+
"support": 30257.0
|
1156 |
+
},
|
1157 |
+
"step": 1458
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 18.52,
|
1161 |
+
"grad_norm": 0.4403069317340851,
|
1162 |
+
"learning_rate": 1.2592592592592593e-05,
|
1163 |
+
"loss": 0.0254,
|
1164 |
+
"step": 1500
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 19.0,
|
1168 |
+
"eval_B-Claim": {
|
1169 |
+
"f1-score": 0.6106346483704975,
|
1170 |
+
"precision": 0.6180555555555556,
|
1171 |
+
"recall": 0.6033898305084746,
|
1172 |
+
"support": 295.0
|
1173 |
+
},
|
1174 |
+
"eval_B-MajorClaim": {
|
1175 |
+
"f1-score": 0.8,
|
1176 |
+
"precision": 0.8051948051948052,
|
1177 |
+
"recall": 0.7948717948717948,
|
1178 |
+
"support": 156.0
|
1179 |
+
},
|
1180 |
+
"eval_B-Premise": {
|
1181 |
+
"f1-score": 0.8165680473372781,
|
1182 |
+
"precision": 0.7821158690176322,
|
1183 |
+
"recall": 0.8541953232462174,
|
1184 |
+
"support": 727.0
|
1185 |
+
},
|
1186 |
+
"eval_I-Claim": {
|
1187 |
+
"f1-score": 0.6138113874510793,
|
1188 |
+
"precision": 0.6434621492853362,
|
1189 |
+
"recall": 0.5867728699010379,
|
1190 |
+
"support": 4143.0
|
1191 |
+
},
|
1192 |
+
"eval_I-MajorClaim": {
|
1193 |
+
"f1-score": 0.835561810931269,
|
1194 |
+
"precision": 0.8603864734299517,
|
1195 |
+
"recall": 0.8121295029639762,
|
1196 |
+
"support": 2193.0
|
1197 |
+
},
|
1198 |
+
"eval_I-Premise": {
|
1199 |
+
"f1-score": 0.8982139352306183,
|
1200 |
+
"precision": 0.8860749690210656,
|
1201 |
+
"recall": 0.9106901217861976,
|
1202 |
+
"support": 12563.0
|
1203 |
+
},
|
1204 |
+
"eval_O": {
|
1205 |
+
"f1-score": 0.9230468176703684,
|
1206 |
+
"precision": 0.9194035669038105,
|
1207 |
+
"recall": 0.9267190569744598,
|
1208 |
+
"support": 10180.0
|
1209 |
+
},
|
1210 |
+
"eval_accuracy": 0.8596357867600886,
|
1211 |
+
"eval_loss": 0.9286978244781494,
|
1212 |
+
"eval_macro avg": {
|
1213 |
+
"f1-score": 0.7854052352844444,
|
1214 |
+
"precision": 0.7878133412011652,
|
1215 |
+
"recall": 0.7841097857503084,
|
1216 |
+
"support": 30257.0
|
1217 |
+
},
|
1218 |
+
"eval_runtime": 5.0907,
|
1219 |
+
"eval_samples_per_second": 15.912,
|
1220 |
+
"eval_steps_per_second": 2.161,
|
1221 |
+
"eval_weighted avg": {
|
1222 |
+
"f1-score": 0.8578136660426414,
|
1223 |
+
"precision": 0.856678268925821,
|
1224 |
+
"recall": 0.8596357867600886,
|
1225 |
+
"support": 30257.0
|
1226 |
+
},
|
1227 |
+
"step": 1539
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 20.0,
|
1231 |
+
"eval_B-Claim": {
|
1232 |
+
"f1-score": 0.6073825503355705,
|
1233 |
+
"precision": 0.6013289036544851,
|
1234 |
+
"recall": 0.6135593220338983,
|
1235 |
+
"support": 295.0
|
1236 |
+
},
|
1237 |
+
"eval_B-MajorClaim": {
|
1238 |
+
"f1-score": 0.7801857585139319,
|
1239 |
+
"precision": 0.7544910179640718,
|
1240 |
+
"recall": 0.8076923076923077,
|
1241 |
+
"support": 156.0
|
1242 |
+
},
|
1243 |
+
"eval_B-Premise": {
|
1244 |
+
"f1-score": 0.8281879194630872,
|
1245 |
+
"precision": 0.8086500655307994,
|
1246 |
+
"recall": 0.8486932599724897,
|
1247 |
+
"support": 727.0
|
1248 |
+
},
|
1249 |
+
"eval_I-Claim": {
|
1250 |
+
"f1-score": 0.6063843000869457,
|
1251 |
+
"precision": 0.6246161719549642,
|
1252 |
+
"recall": 0.5891865797731113,
|
1253 |
+
"support": 4143.0
|
1254 |
+
},
|
1255 |
+
"eval_I-MajorClaim": {
|
1256 |
+
"f1-score": 0.814453557969408,
|
1257 |
+
"precision": 0.7924935289042278,
|
1258 |
+
"recall": 0.8376652986776105,
|
1259 |
+
"support": 2193.0
|
1260 |
+
},
|
1261 |
+
"eval_I-Premise": {
|
1262 |
+
"f1-score": 0.8983381446516345,
|
1263 |
+
"precision": 0.8808813403718154,
|
1264 |
+
"recall": 0.9165008357876303,
|
1265 |
+
"support": 12563.0
|
1266 |
+
},
|
1267 |
+
"eval_O": {
|
1268 |
+
"f1-score": 0.9182781656537244,
|
1269 |
+
"precision": 0.9395621338267036,
|
1270 |
+
"recall": 0.8979371316306484,
|
1271 |
+
"support": 10180.0
|
1272 |
+
},
|
1273 |
+
"eval_accuracy": 0.8545791056614999,
|
1274 |
+
"eval_loss": 0.9461593627929688,
|
1275 |
+
"eval_macro avg": {
|
1276 |
+
"f1-score": 0.7790300566677575,
|
1277 |
+
"precision": 0.7717175946010097,
|
1278 |
+
"recall": 0.7873192479382423,
|
1279 |
+
"support": 30257.0
|
1280 |
+
},
|
1281 |
+
"eval_runtime": 5.1225,
|
1282 |
+
"eval_samples_per_second": 15.813,
|
1283 |
+
"eval_steps_per_second": 2.147,
|
1284 |
+
"eval_weighted avg": {
|
1285 |
+
"f1-score": 0.8538592753289275,
|
1286 |
+
"precision": 0.8540159015687182,
|
1287 |
+
"recall": 0.8545791056614999,
|
1288 |
+
"support": 30257.0
|
1289 |
+
},
|
1290 |
+
"step": 1620
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 21.0,
|
1294 |
+
"eval_B-Claim": {
|
1295 |
+
"f1-score": 0.6044303797468353,
|
1296 |
+
"precision": 0.5667655786350149,
|
1297 |
+
"recall": 0.6474576271186441,
|
1298 |
+
"support": 295.0
|
1299 |
+
},
|
1300 |
+
"eval_B-MajorClaim": {
|
1301 |
+
"f1-score": 0.7266666666666666,
|
1302 |
+
"precision": 0.7569444444444444,
|
1303 |
+
"recall": 0.6987179487179487,
|
1304 |
+
"support": 156.0
|
1305 |
+
},
|
1306 |
+
"eval_B-Premise": {
|
1307 |
+
"f1-score": 0.8260292164674635,
|
1308 |
+
"precision": 0.7984595635430038,
|
1309 |
+
"recall": 0.8555708390646493,
|
1310 |
+
"support": 727.0
|
1311 |
+
},
|
1312 |
+
"eval_I-Claim": {
|
1313 |
+
"f1-score": 0.5973089860643921,
|
1314 |
+
"precision": 0.5945945945945946,
|
1315 |
+
"recall": 0.6000482741974414,
|
1316 |
+
"support": 4143.0
|
1317 |
+
},
|
1318 |
+
"eval_I-MajorClaim": {
|
1319 |
+
"f1-score": 0.7669470559129143,
|
1320 |
+
"precision": 0.8382909680908599,
|
1321 |
+
"recall": 0.7067943456452348,
|
1322 |
+
"support": 2193.0
|
1323 |
+
},
|
1324 |
+
"eval_I-Premise": {
|
1325 |
+
"f1-score": 0.900261137311455,
|
1326 |
+
"precision": 0.8820070261188331,
|
1327 |
+
"recall": 0.9192867945554406,
|
1328 |
+
"support": 12563.0
|
1329 |
+
},
|
1330 |
+
"eval_O": {
|
1331 |
+
"f1-score": 0.9215578716401537,
|
1332 |
+
"precision": 0.9358857490124582,
|
1333 |
+
"recall": 0.9076620825147348,
|
1334 |
+
"support": 10180.0
|
1335 |
+
},
|
1336 |
+
"eval_accuracy": 0.8509435833030373,
|
1337 |
+
"eval_loss": 0.9814539551734924,
|
1338 |
+
"eval_macro avg": {
|
1339 |
+
"f1-score": 0.7633144734014116,
|
1340 |
+
"precision": 0.7675639892056012,
|
1341 |
+
"recall": 0.7622197016877277,
|
1342 |
+
"support": 30257.0
|
1343 |
+
},
|
1344 |
+
"eval_runtime": 5.0986,
|
1345 |
+
"eval_samples_per_second": 15.887,
|
1346 |
+
"eval_steps_per_second": 2.157,
|
1347 |
+
"eval_weighted avg": {
|
1348 |
+
"f1-score": 0.8507187105998458,
|
1349 |
+
"precision": 0.851885777645927,
|
1350 |
+
"recall": 0.8509435833030373,
|
1351 |
+
"support": 30257.0
|
1352 |
+
},
|
1353 |
+
"step": 1701
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 22.0,
|
1357 |
+
"eval_B-Claim": {
|
1358 |
+
"f1-score": 0.6473429951690822,
|
1359 |
+
"precision": 0.6165644171779141,
|
1360 |
+
"recall": 0.6813559322033899,
|
1361 |
+
"support": 295.0
|
1362 |
+
},
|
1363 |
+
"eval_B-MajorClaim": {
|
1364 |
+
"f1-score": 0.7711598746081504,
|
1365 |
+
"precision": 0.754601226993865,
|
1366 |
+
"recall": 0.7884615384615384,
|
1367 |
+
"support": 156.0
|
1368 |
+
},
|
1369 |
+
"eval_B-Premise": {
|
1370 |
+
"f1-score": 0.8172043010752689,
|
1371 |
+
"precision": 0.7989487516425755,
|
1372 |
+
"recall": 0.8363136176066025,
|
1373 |
+
"support": 727.0
|
1374 |
+
},
|
1375 |
+
"eval_I-Claim": {
|
1376 |
+
"f1-score": 0.6408852649970879,
|
1377 |
+
"precision": 0.6193156235929761,
|
1378 |
+
"recall": 0.664011585807386,
|
1379 |
+
"support": 4143.0
|
1380 |
+
},
|
1381 |
+
"eval_I-MajorClaim": {
|
1382 |
+
"f1-score": 0.8175824175824177,
|
1383 |
+
"precision": 0.7891387356809504,
|
1384 |
+
"recall": 0.8481532147742818,
|
1385 |
+
"support": 2193.0
|
1386 |
+
},
|
1387 |
+
"eval_I-Premise": {
|
1388 |
+
"f1-score": 0.8988954970263382,
|
1389 |
+
"precision": 0.9140200756952443,
|
1390 |
+
"recall": 0.884263312902969,
|
1391 |
+
"support": 12563.0
|
1392 |
+
},
|
1393 |
+
"eval_O": {
|
1394 |
+
"f1-score": 0.9192448354255214,
|
1395 |
+
"precision": 0.925004973145017,
|
1396 |
+
"recall": 0.9135559921414538,
|
1397 |
+
"support": 10180.0
|
1398 |
+
},
|
1399 |
+
"eval_accuracy": 0.8577188749710811,
|
1400 |
+
"eval_loss": 0.9464733004570007,
|
1401 |
+
"eval_macro avg": {
|
1402 |
+
"f1-score": 0.7874735979834095,
|
1403 |
+
"precision": 0.7739419719897916,
|
1404 |
+
"recall": 0.8023021705568031,
|
1405 |
+
"support": 30257.0
|
1406 |
+
},
|
1407 |
+
"eval_runtime": 5.1198,
|
1408 |
+
"eval_samples_per_second": 15.821,
|
1409 |
+
"eval_steps_per_second": 2.149,
|
1410 |
+
"eval_weighted avg": {
|
1411 |
+
"f1-score": 0.8594459827250006,
|
1412 |
+
"precision": 0.8618247265225346,
|
1413 |
+
"recall": 0.8577188749710811,
|
1414 |
+
"support": 30257.0
|
1415 |
+
},
|
1416 |
+
"step": 1782
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 23.0,
|
1420 |
+
"eval_B-Claim": {
|
1421 |
+
"f1-score": 0.6166394779771615,
|
1422 |
+
"precision": 0.5943396226415094,
|
1423 |
+
"recall": 0.6406779661016949,
|
1424 |
+
"support": 295.0
|
1425 |
+
},
|
1426 |
+
"eval_B-MajorClaim": {
|
1427 |
+
"f1-score": 0.7781155015197568,
|
1428 |
+
"precision": 0.7398843930635838,
|
1429 |
+
"recall": 0.8205128205128205,
|
1430 |
+
"support": 156.0
|
1431 |
+
},
|
1432 |
+
"eval_B-Premise": {
|
1433 |
+
"f1-score": 0.8206896551724138,
|
1434 |
+
"precision": 0.8229598893499308,
|
1435 |
+
"recall": 0.8184319119669876,
|
1436 |
+
"support": 727.0
|
1437 |
+
},
|
1438 |
+
"eval_I-Claim": {
|
1439 |
+
"f1-score": 0.6299760191846523,
|
1440 |
+
"precision": 0.6259232785322849,
|
1441 |
+
"recall": 0.634081583393676,
|
1442 |
+
"support": 4143.0
|
1443 |
+
},
|
1444 |
+
"eval_I-MajorClaim": {
|
1445 |
+
"f1-score": 0.8275272494122675,
|
1446 |
+
"precision": 0.7787610619469026,
|
1447 |
+
"recall": 0.8828089375284998,
|
1448 |
+
"support": 2193.0
|
1449 |
+
},
|
1450 |
+
"eval_I-Premise": {
|
1451 |
+
"f1-score": 0.9005260832898278,
|
1452 |
+
"precision": 0.9087372345598963,
|
1453 |
+
"recall": 0.8924619915625249,
|
1454 |
+
"support": 12563.0
|
1455 |
+
},
|
1456 |
+
"eval_O": {
|
1457 |
+
"f1-score": 0.9158499158499159,
|
1458 |
+
"precision": 0.9230692476551586,
|
1459 |
+
"recall": 0.9087426326129666,
|
1460 |
+
"support": 10180.0
|
1461 |
+
},
|
1462 |
+
"eval_accuracy": 0.8572561721254586,
|
1463 |
+
"eval_loss": 1.0082058906555176,
|
1464 |
+
"eval_macro avg": {
|
1465 |
+
"f1-score": 0.7841891289151421,
|
1466 |
+
"precision": 0.770524961107038,
|
1467 |
+
"recall": 0.7996739776684529,
|
1468 |
+
"support": 30257.0
|
1469 |
+
},
|
1470 |
+
"eval_runtime": 5.0733,
|
1471 |
+
"eval_samples_per_second": 15.966,
|
1472 |
+
"eval_steps_per_second": 2.168,
|
1473 |
+
"eval_weighted avg": {
|
1474 |
+
"f1-score": 0.8580280687680887,
|
1475 |
+
"precision": 0.8594169271331881,
|
1476 |
+
"recall": 0.8572561721254586,
|
1477 |
+
"support": 30257.0
|
1478 |
+
},
|
1479 |
+
"step": 1863
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 24.0,
|
1483 |
+
"eval_B-Claim": {
|
1484 |
+
"f1-score": 0.639871382636656,
|
1485 |
+
"precision": 0.6085626911314985,
|
1486 |
+
"recall": 0.6745762711864407,
|
1487 |
+
"support": 295.0
|
1488 |
+
},
|
1489 |
+
"eval_B-MajorClaim": {
|
1490 |
+
"f1-score": 0.7974276527331189,
|
1491 |
+
"precision": 0.8,
|
1492 |
+
"recall": 0.7948717948717948,
|
1493 |
+
"support": 156.0
|
1494 |
+
},
|
1495 |
+
"eval_B-Premise": {
|
1496 |
+
"f1-score": 0.8280081577158396,
|
1497 |
+
"precision": 0.8185483870967742,
|
1498 |
+
"recall": 0.8376891334250344,
|
1499 |
+
"support": 727.0
|
1500 |
+
},
|
1501 |
+
"eval_I-Claim": {
|
1502 |
+
"f1-score": 0.632462239271158,
|
1503 |
+
"precision": 0.6282448201952846,
|
1504 |
+
"recall": 0.6367366642529568,
|
1505 |
+
"support": 4143.0
|
1506 |
+
},
|
1507 |
+
"eval_I-MajorClaim": {
|
1508 |
+
"f1-score": 0.8430057803468207,
|
1509 |
+
"precision": 0.8550656660412758,
|
1510 |
+
"recall": 0.831281349749202,
|
1511 |
+
"support": 2193.0
|
1512 |
+
},
|
1513 |
+
"eval_I-Premise": {
|
1514 |
+
"f1-score": 0.9011940059299623,
|
1515 |
+
"precision": 0.9073013311819282,
|
1516 |
+
"recall": 0.8951683515083977,
|
1517 |
+
"support": 12563.0
|
1518 |
+
},
|
1519 |
+
"eval_O": {
|
1520 |
+
"f1-score": 0.9226263119355627,
|
1521 |
+
"precision": 0.9170305676855895,
|
1522 |
+
"recall": 0.9282907662082515,
|
1523 |
+
"support": 10180.0
|
1524 |
+
},
|
1525 |
+
"eval_accuracy": 0.8622467528175298,
|
1526 |
+
"eval_loss": 0.9314867854118347,
|
1527 |
+
"eval_macro avg": {
|
1528 |
+
"f1-score": 0.7949422186527312,
|
1529 |
+
"precision": 0.7906790661903358,
|
1530 |
+
"recall": 0.7998020473145824,
|
1531 |
+
"support": 30257.0
|
1532 |
+
},
|
1533 |
+
"eval_runtime": 5.0984,
|
1534 |
+
"eval_samples_per_second": 15.887,
|
1535 |
+
"eval_steps_per_second": 2.158,
|
1536 |
+
"eval_weighted avg": {
|
1537 |
+
"f1-score": 0.862549545162003,
|
1538 |
+
"precision": 0.8629799970148593,
|
1539 |
+
"recall": 0.8622467528175298,
|
1540 |
+
"support": 30257.0
|
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 sha256:7cf5d4f8fefb4e78449403d6f60739ea086b5ecbb9bc2500c2c1407621dbdb5a
|
3 |
+
size 4856
|
checkpoint-1944/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|