xshubhamx commited on
Commit
2881add
1 Parent(s): fb0902c

Upload folder using huggingface_hub

Browse files
training_checkpoints/checkpoint-1929/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nlpaueb/legal-bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_ids": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "Issue",
15
+ "1": "Court Discourse",
16
+ "2": "Conclusion",
17
+ "3": "Precedent Analysis",
18
+ "4": "Section Analysis",
19
+ "5": "Argument by Petitioner",
20
+ "6": "Fact",
21
+ "7": "Argument by Respondent",
22
+ "8": "Ratio",
23
+ "9": "Appellant",
24
+ "10": "Respondent",
25
+ "11": "Argument by Appellant",
26
+ "12": "Petitioner",
27
+ "13": "Judge",
28
+ "14": "Argument by Defendant"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "label2id": {
33
+ "Appellant": 9,
34
+ "Argument by Appellant": 11,
35
+ "Argument by Defendant": 14,
36
+ "Argument by Petitioner": 5,
37
+ "Argument by Respondent": 7,
38
+ "Conclusion": 2,
39
+ "Court Discourse": 1,
40
+ "Fact": 6,
41
+ "Issue": 0,
42
+ "Judge": 13,
43
+ "Petitioner": 12,
44
+ "Precedent Analysis": 3,
45
+ "Ratio": 8,
46
+ "Respondent": 10,
47
+ "Section Analysis": 4
48
+ },
49
+ "layer_norm_eps": 1e-12,
50
+ "max_position_embeddings": 512,
51
+ "model_type": "bert",
52
+ "num_attention_heads": 12,
53
+ "num_hidden_layers": 12,
54
+ "output_past": true,
55
+ "pad_token_id": 0,
56
+ "position_embedding_type": "absolute",
57
+ "problem_type": "single_label_classification",
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.38.2",
60
+ "type_vocab_size": 2,
61
+ "use_cache": true,
62
+ "vocab_size": 30522
63
+ }
training_checkpoints/checkpoint-1929/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f4834e4b90d899c6ea8a397735f693382b983741b33d5a4d7bec713b2b6e5a6
3
+ size 437998636
training_checkpoints/checkpoint-1929/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a6c7e2bbc5161ffd4e3196f90ea2f1ca3db2510035aaf018f14187d4e04f3dc
3
+ size 876118266
training_checkpoints/checkpoint-1929/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9722df2d53a1e313c8b41b79369abc44a7b57004c05f6d6413273f1a35756cdf
3
+ size 14244
training_checkpoints/checkpoint-1929/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:955ccf9cc6b9e4802e852b4a1037de7c85b91f593d5a9e829fb1fdb03a4dd5a1
3
+ size 1064
training_checkpoints/checkpoint-1929/trainer_state.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7369957890904685,
3
+ "best_model_checkpoint": "legal-bert-base-uncased/checkpoint-1929",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1929,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.78,
13
+ "grad_norm": 6.735908031463623,
14
+ "learning_rate": 4.742353551062727e-05,
15
+ "loss": 1.1096,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7978311386522076,
21
+ "eval_f1_macro": 0.613418966848975,
22
+ "eval_f1_micro": 0.7978311386522076,
23
+ "eval_f1_weighted": 0.7839880886224406,
24
+ "eval_loss": 0.6747979521751404,
25
+ "eval_macro_fpr": 0.018830502815301575,
26
+ "eval_macro_sensitivity": 0.6339578261148517,
27
+ "eval_macro_specificity": 0.9845345883924012,
28
+ "eval_precision": 0.7854860044786733,
29
+ "eval_precision_macro": 0.6239440349375213,
30
+ "eval_recall": 0.7978311386522076,
31
+ "eval_recall_macro": 0.6339578261148517,
32
+ "eval_runtime": 30.9921,
33
+ "eval_samples_per_second": 41.656,
34
+ "eval_steps_per_second": 5.227,
35
+ "eval_weighted_fpr": 0.017778080512226686,
36
+ "eval_weighted_sensitivity": 0.7978311386522076,
37
+ "eval_weighted_specificity": 0.9701876872338092,
38
+ "step": 643
39
+ },
40
+ {
41
+ "epoch": 1.56,
42
+ "grad_norm": 6.824150562286377,
43
+ "learning_rate": 4.48315189217211e-05,
44
+ "loss": 0.6187,
45
+ "step": 1000
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_accuracy": 0.8109992254066615,
50
+ "eval_f1_macro": 0.7268228216676939,
51
+ "eval_f1_micro": 0.8109992254066615,
52
+ "eval_f1_weighted": 0.8089875323563979,
53
+ "eval_loss": 0.6449354887008667,
54
+ "eval_macro_fpr": 0.016938802987367406,
55
+ "eval_macro_sensitivity": 0.7327307314578203,
56
+ "eval_macro_specificity": 0.9857686909763926,
57
+ "eval_precision": 0.8196084470842065,
58
+ "eval_precision_macro": 0.7805936449528967,
59
+ "eval_recall": 0.8109992254066615,
60
+ "eval_recall_macro": 0.7327307314578203,
61
+ "eval_runtime": 58.3071,
62
+ "eval_samples_per_second": 22.141,
63
+ "eval_steps_per_second": 2.778,
64
+ "eval_weighted_fpr": 0.016373641121997046,
65
+ "eval_weighted_sensitivity": 0.8109992254066615,
66
+ "eval_weighted_specificity": 0.9755311392392266,
67
+ "step": 1286
68
+ },
69
+ {
70
+ "epoch": 2.33,
71
+ "grad_norm": 20.75279998779297,
72
+ "learning_rate": 4.223950233281493e-05,
73
+ "loss": 0.4747,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 3.0,
78
+ "eval_accuracy": 0.814872192099148,
79
+ "eval_f1_macro": 0.7369957890904685,
80
+ "eval_f1_micro": 0.814872192099148,
81
+ "eval_f1_weighted": 0.8124596447054482,
82
+ "eval_loss": 0.8151384592056274,
83
+ "eval_macro_fpr": 0.016571707879599946,
84
+ "eval_macro_sensitivity": 0.739039840019417,
85
+ "eval_macro_specificity": 0.9860629698102752,
86
+ "eval_precision": 0.8192276160546627,
87
+ "eval_precision_macro": 0.7659183928188651,
88
+ "eval_recall": 0.814872192099148,
89
+ "eval_recall_macro": 0.739039840019417,
90
+ "eval_runtime": 55.9094,
91
+ "eval_samples_per_second": 23.091,
92
+ "eval_steps_per_second": 2.898,
93
+ "eval_weighted_fpr": 0.015968463954032203,
94
+ "eval_weighted_sensitivity": 0.814872192099148,
95
+ "eval_weighted_specificity": 0.9760723550549795,
96
+ "step": 1929
97
+ }
98
+ ],
99
+ "logging_steps": 500,
100
+ "max_steps": 9645,
101
+ "num_input_tokens_seen": 0,
102
+ "num_train_epochs": 15,
103
+ "save_steps": 500,
104
+ "total_flos": 4056067183343616.0,
105
+ "train_batch_size": 8,
106
+ "trial_name": null,
107
+ "trial_params": null
108
+ }
training_checkpoints/checkpoint-1929/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21938ff48cdf92422f693d69544854f8291bee6a4c7091c49d48bd0e59616530
3
+ size 4920