xshubhamx commited on
Commit
1f72460
1 Parent(s): 9d653a7

Upload folder using huggingface_hub

Browse files
training_checkpoints/checkpoint-643/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlnet/xlnet-base-cased",
3
+ "architectures": [
4
+ "XLNetForSequenceClassification"
5
+ ],
6
+ "attn_type": "bi",
7
+ "bi_data": false,
8
+ "bos_token_id": 1,
9
+ "clamp_len": -1,
10
+ "d_head": 64,
11
+ "d_inner": 3072,
12
+ "d_model": 768,
13
+ "dropout": 0.1,
14
+ "end_n_top": 5,
15
+ "eos_token_id": 2,
16
+ "ff_activation": "gelu",
17
+ "id2label": {
18
+ "0": "Issue",
19
+ "1": "Court Discourse",
20
+ "2": "Conclusion",
21
+ "3": "Precedent Analysis",
22
+ "4": "Section Analysis",
23
+ "5": "Argument by Petitioner",
24
+ "6": "Fact",
25
+ "7": "Argument by Respondent",
26
+ "8": "Ratio",
27
+ "9": "Appellant",
28
+ "10": "Respondent",
29
+ "11": "Argument by Appellant",
30
+ "12": "Petitioner",
31
+ "13": "Judge",
32
+ "14": "Argument by Defendant"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "label2id": {
36
+ "Appellant": 9,
37
+ "Argument by Appellant": 11,
38
+ "Argument by Defendant": 14,
39
+ "Argument by Petitioner": 5,
40
+ "Argument by Respondent": 7,
41
+ "Conclusion": 2,
42
+ "Court Discourse": 1,
43
+ "Fact": 6,
44
+ "Issue": 0,
45
+ "Judge": 13,
46
+ "Petitioner": 12,
47
+ "Precedent Analysis": 3,
48
+ "Ratio": 8,
49
+ "Respondent": 10,
50
+ "Section Analysis": 4
51
+ },
52
+ "layer_norm_eps": 1e-12,
53
+ "mem_len": null,
54
+ "model_type": "xlnet",
55
+ "n_head": 12,
56
+ "n_layer": 12,
57
+ "pad_token_id": 5,
58
+ "problem_type": "single_label_classification",
59
+ "reuse_len": null,
60
+ "same_length": false,
61
+ "start_n_top": 5,
62
+ "summary_activation": "tanh",
63
+ "summary_last_dropout": 0.1,
64
+ "summary_type": "last",
65
+ "summary_use_proj": true,
66
+ "task_specific_params": {
67
+ "text-generation": {
68
+ "do_sample": true,
69
+ "max_length": 250
70
+ }
71
+ },
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.35.2",
74
+ "untie_r": true,
75
+ "use_mems_eval": true,
76
+ "use_mems_train": false,
77
+ "vocab_size": 32000
78
+ }
training_checkpoints/checkpoint-643/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3d62f4cfc8fbe0399479daad236f3d4e645d59505c715099c6fa4563b6c34e2
3
+ size 469304588
training_checkpoints/checkpoint-643/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2395da08a6a631ce4a83d745b5255e1689289da9bdf06a41de5636b3bf3de37
3
+ size 938733178
training_checkpoints/checkpoint-643/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931144e2e8f85d1967a3f9c305f55ad2ca194ec0fcac4a5b6ba28508e02009ee
3
+ size 14244
training_checkpoints/checkpoint-643/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e5bc88ea67525eeda7611873c1c5659612887ffd26b4b12b850284f4b74ac9
3
+ size 1064
training_checkpoints/checkpoint-643/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<eop>",
4
+ "<eod>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<cls>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "<sep>",
18
+ "unk_token": "<unk>"
19
+ }
training_checkpoints/checkpoint-643/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
3
+ size 798011
training_checkpoints/checkpoint-643/tokenizer_config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<cls>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<sep>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<pad>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<eod>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<eop>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ }
75
+ },
76
+ "additional_special_tokens": [
77
+ "<eop>",
78
+ "<eod>"
79
+ ],
80
+ "bos_token": "<s>",
81
+ "clean_up_tokenization_spaces": true,
82
+ "cls_token": "<cls>",
83
+ "do_lower_case": false,
84
+ "eos_token": "</s>",
85
+ "keep_accents": false,
86
+ "mask_token": "<mask>",
87
+ "model_max_length": 1000000000000000019884624838656,
88
+ "pad_token": "<pad>",
89
+ "remove_space": true,
90
+ "sep_token": "<sep>",
91
+ "sp_model_kwargs": {},
92
+ "tokenizer_class": "XLNetTokenizer",
93
+ "unk_token": "<unk>"
94
+ }
training_checkpoints/checkpoint-643/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4818756771742453,
3
+ "best_model_checkpoint": "xlnet-base-cased/checkpoint-643",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 643,
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
+ "learning_rate": 4.871695178849145e-05,
14
+ "loss": 1.2613,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7676219984508134,
20
+ "eval_f1_macro": 0.4818756771742453,
21
+ "eval_f1_micro": 0.7676219984508135,
22
+ "eval_f1_weighted": 0.7524385212708887,
23
+ "eval_loss": 0.775787353515625,
24
+ "eval_macro_fpr": 0.022019799606126652,
25
+ "eval_macro_sensitivity": 0.5128622254580788,
26
+ "eval_macro_specificity": 0.9823717840367622,
27
+ "eval_precision": 0.7672637518290021,
28
+ "eval_precision_macro": 0.5269420024270713,
29
+ "eval_recall": 0.7676219984508134,
30
+ "eval_recall_macro": 0.5128622254580788,
31
+ "eval_runtime": 65.0712,
32
+ "eval_samples_per_second": 19.84,
33
+ "eval_steps_per_second": 2.49,
34
+ "eval_weighted_fpr": 0.021165514321998025,
35
+ "eval_weighted_sensitivity": 0.7676219984508134,
36
+ "eval_weighted_specificity": 0.9679547621006213,
37
+ "step": 643
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 19290,
42
+ "num_train_epochs": 30,
43
+ "save_steps": 500,
44
+ "total_flos": 1463872668346368.0,
45
+ "trial_name": null,
46
+ "trial_params": null
47
+ }
training_checkpoints/checkpoint-643/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec20e9f8adfcfee3337ee75e60d11aa0228a2bd24494baa212e8cd20722381d4
3
+ size 4600