Upload folder using huggingface_hub
Browse files- training_checkpoints/checkpoint-643/config.json +63 -0
- training_checkpoints/checkpoint-643/model.safetensors +3 -0
- training_checkpoints/checkpoint-643/optimizer.pt +3 -0
- training_checkpoints/checkpoint-643/rng_state.pth +3 -0
- training_checkpoints/checkpoint-643/scheduler.pt +3 -0
- training_checkpoints/checkpoint-643/trainer_state.json +50 -0
- training_checkpoints/checkpoint-643/training_args.bin +3 -0
training_checkpoints/checkpoint-643/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-643/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:087fe83cfe6f482d2c7533bacc7014eba7ec9f897f4da2282bddb3e80934dedd
|
3 |
+
size 437998636
|
training_checkpoints/checkpoint-643/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc9599a4cb4c5dbc043e234ad34e70c2bce3020ffcf745235902d0ffd87139d9
|
3 |
+
size 876118266
|
training_checkpoints/checkpoint-643/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5738a8a4e7ac5ac879b357f39c0b5a95be8b93ff68deb75b51e2d7d31061775
|
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:a9fc42da1d1719d8e851165b578ef06d5f1d67e579c1957181d7800ebe373f60
|
3 |
+
size 1064
|
training_checkpoints/checkpoint-643/trainer_state.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.613418966848975,
|
3 |
+
"best_model_checkpoint": "legal-bert-base-uncased/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 |
+
"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 |
+
"logging_steps": 500,
|
42 |
+
"max_steps": 9645,
|
43 |
+
"num_input_tokens_seen": 0,
|
44 |
+
"num_train_epochs": 15,
|
45 |
+
"save_steps": 500,
|
46 |
+
"total_flos": 1352022394447872.0,
|
47 |
+
"train_batch_size": 8,
|
48 |
+
"trial_name": null,
|
49 |
+
"trial_params": null
|
50 |
+
}
|
training_checkpoints/checkpoint-643/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21938ff48cdf92422f693d69544854f8291bee6a4c7091c49d48bd0e59616530
|
3 |
+
size 4920
|