Theoreticallyhugo commited on
Commit
82bcbec
1 Parent(s): d7e7d38

Training in progress, epoch 1, checkpoint

Browse files
checkpoint-41/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": "4.37.2",
59
+ "type_vocab_size": 1,
60
+ "vocab_size": 50265
61
+ }
checkpoint-41/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-41/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6db91df74d99ffd35f76204fc5ac4b4d72ecd346838ce7fee205281f2c0fcc
3
+ size 592330980
checkpoint-41/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a566cb98b494b39b76a13748be4aef501b3528a0f79727e2aa45bdc6ed096e50
3
+ size 1014670074
checkpoint-41/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a939982f711c8a91f0893b4f281f0db4fd89d7ca52de2aed82098ef9ff76ea2
3
+ size 14244
checkpoint-41/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2edfde65f52fe0fcbc13f549dfed4fa891e3eb1476a6c03774294faa3865fa33
3
+ size 1064
checkpoint-41/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-41/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-41/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-41/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 41,
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": 284.0
18
+ },
19
+ "eval_B-MajorClaim": {
20
+ "f1-score": 0.0,
21
+ "precision": 0.0,
22
+ "recall": 0.0,
23
+ "support": 141.0
24
+ },
25
+ "eval_B-Premise": {
26
+ "f1-score": 0.7698598130841122,
27
+ "precision": 0.6563745019920318,
28
+ "recall": 0.9307909604519774,
29
+ "support": 708.0
30
+ },
31
+ "eval_I-Claim": {
32
+ "f1-score": 0.353471342064498,
33
+ "precision": 0.4150132275132275,
34
+ "recall": 0.3078243806720628,
35
+ "support": 4077.0
36
+ },
37
+ "eval_I-MajorClaim": {
38
+ "f1-score": 0.33396728794218333,
39
+ "precision": 0.7256198347107438,
40
+ "recall": 0.21689723320158102,
41
+ "support": 2024.0
42
+ },
43
+ "eval_I-Premise": {
44
+ "f1-score": 0.8650843453545458,
45
+ "precision": 0.7886129618413082,
46
+ "recall": 0.9579790712884239,
47
+ "support": 12232.0
48
+ },
49
+ "eval_O": {
50
+ "f1-score": 0.9933173830542035,
51
+ "precision": 0.994383878427486,
52
+ "recall": 0.9922531729025877,
53
+ "support": 12134.0
54
+ },
55
+ "eval_accuracy": 0.8262974683544304,
56
+ "eval_loss": 0.4304405748844147,
57
+ "eval_macro avg": {
58
+ "f1-score": 0.4736714530713633,
59
+ "precision": 0.5114292006406853,
60
+ "recall": 0.48653497407380464,
61
+ "support": 31600.0
62
+ },
63
+ "eval_runtime": 1.4322,
64
+ "eval_samples_per_second": 55.858,
65
+ "eval_steps_per_second": 6.982,
66
+ "eval_weighted avg": {
67
+ "f1-score": 0.8005296847598733,
68
+ "precision": 0.8018210237822256,
69
+ "recall": 0.8262974683544304,
70
+ "support": 31600.0
71
+ },
72
+ "step": 41
73
+ }
74
+ ],
75
+ "logging_steps": 500,
76
+ "max_steps": 656,
77
+ "num_input_tokens_seen": 0,
78
+ "num_train_epochs": 16,
79
+ "save_steps": 500,
80
+ "total_flos": 143790812718000.0,
81
+ "train_batch_size": 8,
82
+ "trial_name": null,
83
+ "trial_params": null
84
+ }
checkpoint-41/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aeb0258456dbe86afb0f8ff223963c5647a7a407240dfd742aabffc732300db
3
+ size 4728
checkpoint-41/vocab.json ADDED
The diff for this file is too large to render. See raw diff