cite-text-analysis
commited on
Commit
•
9aedb0e
1
Parent(s):
984d1f2
Upload folder using huggingface_hub
Browse files- training_checkpoints/checkpoint-448/added_tokens.json +3 -0
- training_checkpoints/checkpoint-448/config.json +41 -0
- training_checkpoints/checkpoint-448/model.safetensors +3 -0
- training_checkpoints/checkpoint-448/optimizer.pt +3 -0
- training_checkpoints/checkpoint-448/rng_state.pth +3 -0
- training_checkpoints/checkpoint-448/scheduler.pt +3 -0
- training_checkpoints/checkpoint-448/special_tokens_map.json +13 -0
- training_checkpoints/checkpoint-448/tokenizer.json +0 -0
- training_checkpoints/checkpoint-448/tokenizer_config.json +65 -0
- training_checkpoints/checkpoint-448/trainer_state.json +65 -0
- training_checkpoints/checkpoint-448/training_args.bin +3 -0
- training_checkpoints/checkpoint-448/vocab.txt +0 -0
training_checkpoints/checkpoint-448/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 30522
|
3 |
+
}
|
training_checkpoints/checkpoint-448/config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "positive",
|
15 |
+
"1": "negative",
|
16 |
+
"2": "neutral",
|
17 |
+
"3": "rel_by_party"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"negative": 1,
|
23 |
+
"neutral": 2,
|
24 |
+
"positive": 0,
|
25 |
+
"rel_by_party": 3
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-12,
|
28 |
+
"max_position_embeddings": 512,
|
29 |
+
"model_type": "bert",
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"output_past": true,
|
33 |
+
"pad_token_id": 30522,
|
34 |
+
"position_embedding_type": "absolute",
|
35 |
+
"problem_type": "single_label_classification",
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.40.2",
|
38 |
+
"type_vocab_size": 2,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 30523
|
41 |
+
}
|
training_checkpoints/checkpoint-448/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8a9c9b898164951f6bfff5458aa9b0b1b0175a85749ac21b062fb4d4c013000
|
3 |
+
size 437967872
|
training_checkpoints/checkpoint-448/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caab8362d392851999a0a0c0f49c33a2ea92c31cd9fdaa0d08fba023dd8d5b38
|
3 |
+
size 876056826
|
training_checkpoints/checkpoint-448/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49c3421524359735f70572cd877dcd42ffd6800d311433d57c42c8b892c261be
|
3 |
+
size 14244
|
training_checkpoints/checkpoint-448/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:339af6ff8d1d9b45a7ea156a92ec3759910f0627cfc44e0939bc7974a9a59920
|
3 |
+
size 1064
|
training_checkpoints/checkpoint-448/special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
training_checkpoints/checkpoint-448/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_checkpoints/checkpoint-448/tokenizer_config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"30522": {
|
44 |
+
"content": "<pad>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"clean_up_tokenization_spaces": true,
|
53 |
+
"cls_token": "[CLS]",
|
54 |
+
"do_basic_tokenize": true,
|
55 |
+
"do_lower_case": true,
|
56 |
+
"mask_token": "[MASK]",
|
57 |
+
"model_max_length": 512,
|
58 |
+
"never_split": null,
|
59 |
+
"pad_token": "<pad>",
|
60 |
+
"sep_token": "[SEP]",
|
61 |
+
"strip_accents": null,
|
62 |
+
"tokenize_chinese_chars": true,
|
63 |
+
"tokenizer_class": "BertTokenizer",
|
64 |
+
"unk_token": "[UNK]"
|
65 |
+
}
|
training_checkpoints/checkpoint-448/trainer_state.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5658663855845003,
|
3 |
+
"best_model_checkpoint": "case-analysis-legal-bert-base-uncased/checkpoint-448",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 448,
|
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_accuracy": 0.6570155902004454,
|
14 |
+
"eval_f1_macro": 0.4081263564022185,
|
15 |
+
"eval_f1_micro": 0.6570155902004454,
|
16 |
+
"eval_f1_weighted": 0.6166399839312825,
|
17 |
+
"eval_loss": 1.0114229917526245,
|
18 |
+
"eval_macro_fpr": 0.19475132363363487,
|
19 |
+
"eval_macro_sensitivity": 0.40746667217255456,
|
20 |
+
"eval_macro_specificity": 0.8324392236563901,
|
21 |
+
"eval_precision": 0.6178816225558943,
|
22 |
+
"eval_precision_macro": 0.4664000256488353,
|
23 |
+
"eval_recall": 0.6570155902004454,
|
24 |
+
"eval_recall_macro": 0.40746667217255456,
|
25 |
+
"eval_runtime": 7.3199,
|
26 |
+
"eval_samples_per_second": 61.34,
|
27 |
+
"eval_steps_per_second": 7.787,
|
28 |
+
"eval_weighted_fpr": 0.1482194417709336,
|
29 |
+
"eval_weighted_sensitivity": 0.6570155902004454,
|
30 |
+
"eval_weighted_specificity": 0.6727413044251147,
|
31 |
+
"step": 224
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.7750556792873051,
|
36 |
+
"eval_f1_macro": 0.5658663855845003,
|
37 |
+
"eval_f1_micro": 0.775055679287305,
|
38 |
+
"eval_f1_weighted": 0.7564492543508543,
|
39 |
+
"eval_loss": 0.764952540397644,
|
40 |
+
"eval_macro_fpr": 0.10943701020063132,
|
41 |
+
"eval_macro_sensitivity": 0.5805958747135218,
|
42 |
+
"eval_macro_specificity": 0.9039084791647444,
|
43 |
+
"eval_precision": 0.7425093237919278,
|
44 |
+
"eval_precision_macro": 0.5566158325717437,
|
45 |
+
"eval_recall": 0.7750556792873051,
|
46 |
+
"eval_recall_macro": 0.5805958747135218,
|
47 |
+
"eval_runtime": 30.7218,
|
48 |
+
"eval_samples_per_second": 14.615,
|
49 |
+
"eval_steps_per_second": 1.855,
|
50 |
+
"eval_weighted_fpr": 0.08820960698689956,
|
51 |
+
"eval_weighted_sensitivity": 0.7750556792873051,
|
52 |
+
"eval_weighted_specificity": 0.8405782373716723,
|
53 |
+
"step": 448
|
54 |
+
}
|
55 |
+
],
|
56 |
+
"logging_steps": 500,
|
57 |
+
"max_steps": 6720,
|
58 |
+
"num_input_tokens_seen": 0,
|
59 |
+
"num_train_epochs": 30,
|
60 |
+
"save_steps": 500,
|
61 |
+
"total_flos": 943006955864064.0,
|
62 |
+
"train_batch_size": 8,
|
63 |
+
"trial_name": null,
|
64 |
+
"trial_params": null
|
65 |
+
}
|
training_checkpoints/checkpoint-448/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8124b12bb2d716832b587bea11323810e8fd3f54cf265a6935c0b9d891cdd1f6
|
3 |
+
size 5048
|
training_checkpoints/checkpoint-448/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|