Upload folder using huggingface_hub
Browse files- training_checkpoints/checkpoint-2569/config.json +99 -0
- training_checkpoints/checkpoint-2569/merges.txt +0 -0
- training_checkpoints/checkpoint-2569/model.safetensors +3 -0
- training_checkpoints/checkpoint-2569/optimizer.pt +3 -0
- training_checkpoints/checkpoint-2569/rng_state.pth +3 -0
- training_checkpoints/checkpoint-2569/scheduler.pt +3 -0
- training_checkpoints/checkpoint-2569/special_tokens_map.json +15 -0
- training_checkpoints/checkpoint-2569/tokenizer.json +0 -0
- training_checkpoints/checkpoint-2569/tokenizer_config.json +57 -0
- training_checkpoints/checkpoint-2569/trainer_state.json +71 -0
- training_checkpoints/checkpoint-2569/training_args.bin +3 -0
- training_checkpoints/checkpoint-2569/vocab.json +0 -0
training_checkpoints/checkpoint-2569/config.json
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-large",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForSequenceClassification"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 1024,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 4096,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 12,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"forced_bos_token_id": 0,
|
28 |
+
"forced_eos_token_id": 2,
|
29 |
+
"gradient_checkpointing": false,
|
30 |
+
"id2label": {
|
31 |
+
"0": "Issue",
|
32 |
+
"1": "Court Discourse",
|
33 |
+
"2": "Conclusion",
|
34 |
+
"3": "Precedent Analysis",
|
35 |
+
"4": "Section Analysis",
|
36 |
+
"5": "Argument by Petitioner",
|
37 |
+
"6": "Fact",
|
38 |
+
"7": "Argument by Respondent",
|
39 |
+
"8": "Ratio",
|
40 |
+
"9": "Appellant",
|
41 |
+
"10": "Respondent",
|
42 |
+
"11": "Argument by Appellant",
|
43 |
+
"12": "Petitioner",
|
44 |
+
"13": "Judge",
|
45 |
+
"14": "Argument by Defendant"
|
46 |
+
},
|
47 |
+
"init_std": 0.02,
|
48 |
+
"is_encoder_decoder": true,
|
49 |
+
"label2id": {
|
50 |
+
"Appellant": 9,
|
51 |
+
"Argument by Appellant": 11,
|
52 |
+
"Argument by Defendant": 14,
|
53 |
+
"Argument by Petitioner": 5,
|
54 |
+
"Argument by Respondent": 7,
|
55 |
+
"Conclusion": 2,
|
56 |
+
"Court Discourse": 1,
|
57 |
+
"Fact": 6,
|
58 |
+
"Issue": 0,
|
59 |
+
"Judge": 13,
|
60 |
+
"Petitioner": 12,
|
61 |
+
"Precedent Analysis": 3,
|
62 |
+
"Ratio": 8,
|
63 |
+
"Respondent": 10,
|
64 |
+
"Section Analysis": 4
|
65 |
+
},
|
66 |
+
"max_position_embeddings": 1024,
|
67 |
+
"model_type": "bart",
|
68 |
+
"no_repeat_ngram_size": 3,
|
69 |
+
"normalize_before": false,
|
70 |
+
"num_beams": 4,
|
71 |
+
"num_hidden_layers": 12,
|
72 |
+
"pad_token_id": 1,
|
73 |
+
"problem_type": "single_label_classification",
|
74 |
+
"scale_embedding": false,
|
75 |
+
"task_specific_params": {
|
76 |
+
"summarization": {
|
77 |
+
"length_penalty": 1.0,
|
78 |
+
"max_length": 128,
|
79 |
+
"min_length": 12,
|
80 |
+
"num_beams": 4
|
81 |
+
},
|
82 |
+
"summarization_cnn": {
|
83 |
+
"length_penalty": 2.0,
|
84 |
+
"max_length": 142,
|
85 |
+
"min_length": 56,
|
86 |
+
"num_beams": 4
|
87 |
+
},
|
88 |
+
"summarization_xsum": {
|
89 |
+
"length_penalty": 1.0,
|
90 |
+
"max_length": 62,
|
91 |
+
"min_length": 11,
|
92 |
+
"num_beams": 6
|
93 |
+
}
|
94 |
+
},
|
95 |
+
"torch_dtype": "float32",
|
96 |
+
"transformers_version": "4.35.2",
|
97 |
+
"use_cache": true,
|
98 |
+
"vocab_size": 50265
|
99 |
+
}
|
training_checkpoints/checkpoint-2569/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_checkpoints/checkpoint-2569/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2fa3006fab1ab61b81bbc9beaaa8a7f28f4a6bc2eeb562dff6160e2a1fc2fb0
|
3 |
+
size 1629486164
|
training_checkpoints/checkpoint-2569/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d22837719cfba0493b2aedb32a193abd08fee4fcdafbb73ec6d953e0d4ef03b0
|
3 |
+
size 3259283099
|
training_checkpoints/checkpoint-2569/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:438e1512a23e79c9c92876ff901172a8b519f339335733974cfb2816c2f92e4a
|
3 |
+
size 14244
|
training_checkpoints/checkpoint-2569/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3863c9d66fdd3130e2924f8a17919972f437694f0a9437846f0709d9a554f1b
|
3 |
+
size 1064
|
training_checkpoints/checkpoint-2569/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": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
training_checkpoints/checkpoint-2569/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_checkpoints/checkpoint-2569/tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
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": true,
|
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": 1024,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "BartTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_checkpoints/checkpoint-2569/trainer_state.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4296023125768376,
|
3 |
+
"best_model_checkpoint": "bart-large/checkpoint-2569",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2569,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.19,
|
13 |
+
"learning_rate": 4.967886337096146e-05,
|
14 |
+
"loss": 2.0273,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.39,
|
19 |
+
"learning_rate": 4.9354482937589206e-05,
|
20 |
+
"loss": 1.4983,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.58,
|
25 |
+
"learning_rate": 4.903140002595043e-05,
|
26 |
+
"loss": 1.4727,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.78,
|
31 |
+
"learning_rate": 4.870701959257818e-05,
|
32 |
+
"loss": 1.3945,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.97,
|
37 |
+
"learning_rate": 4.8383287920072665e-05,
|
38 |
+
"loss": 1.1685,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.0,
|
43 |
+
"eval_accuracy": 0.6847405112316034,
|
44 |
+
"eval_f1_macro": 0.4296023125768376,
|
45 |
+
"eval_f1_micro": 0.6847405112316034,
|
46 |
+
"eval_f1_weighted": 0.6471198955620663,
|
47 |
+
"eval_loss": 1.258675456047058,
|
48 |
+
"eval_macro_fpr": 0.03310536835500512,
|
49 |
+
"eval_macro_sensitivity": 0.47197476920519743,
|
50 |
+
"eval_macro_specificity": 0.9759825618150952,
|
51 |
+
"eval_precision": 0.6359796796355663,
|
52 |
+
"eval_precision_macro": 0.4175869918662546,
|
53 |
+
"eval_recall": 0.6847405112316034,
|
54 |
+
"eval_recall_macro": 0.47197476920519743,
|
55 |
+
"eval_runtime": 166.2079,
|
56 |
+
"eval_samples_per_second": 7.767,
|
57 |
+
"eval_steps_per_second": 3.887,
|
58 |
+
"eval_weighted_fpr": 0.03183916138621607,
|
59 |
+
"eval_weighted_sensitivity": 0.6847405112316034,
|
60 |
+
"eval_weighted_specificity": 0.9549979159948256,
|
61 |
+
"step": 2569
|
62 |
+
}
|
63 |
+
],
|
64 |
+
"logging_steps": 500,
|
65 |
+
"max_steps": 77070,
|
66 |
+
"num_train_epochs": 30,
|
67 |
+
"save_steps": 500,
|
68 |
+
"total_flos": 5584101220067328.0,
|
69 |
+
"trial_name": null,
|
70 |
+
"trial_params": null
|
71 |
+
}
|
training_checkpoints/checkpoint-2569/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e37f60a60daa651d8e7f2ff3947107bcf8c19f622a0416af7b872e6562bd538
|
3 |
+
size 4600
|
training_checkpoints/checkpoint-2569/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|