Chantland commited on
Commit
b087dd9
·
1 Parent(s): f89ea5f

Initial Upload

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "EVENT",
13
+ "1": "CAUSE",
14
+ "2": "ACTION"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "ACTION": 2,
19
+ "CAUSE": 1,
20
+ "EVENT": 0
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "multi_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.24.0",
34
+ "vocab_size": 30522
35
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7082408946a4d0b3d8cfcb4545f72df12a71a3f1588db4fbd9ce660fbc422a2
3
+ size 535704261
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6613a02202ca73a46b0722b6f2548fa14b37bab755222a4079badd2a1b139862
3
+ size 267857197
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87fa3ec3c3bed1bfbe5540ddfdb03d1f94e956f02f7376e09dedeb481f49f09e
3
+ size 13553
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4dbe9d8fea2ea41033fda5459cd8e8efb5bd001b648756858752480ac133f66
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "distilbert-base-uncased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "DistilBertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8975609756097561,
3
+ "best_model_checkpoint": "HRAF_Model_MultiLabel_ThreeLargeClasses/checkpoint-700",
4
+ "epoch": 4.0,
5
+ "global_step": 700,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_accuracy": 0.5085714285714286,
13
+ "eval_f1": 0.8645660585959093,
14
+ "eval_loss": 0.4566337466239929,
15
+ "eval_roc_auc": 0.5400860231720076,
16
+ "eval_runtime": 93.095,
17
+ "eval_samples_per_second": 3.76,
18
+ "eval_steps_per_second": 0.473,
19
+ "step": 175
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.5514285714285714,
24
+ "eval_f1": 0.8843069873997709,
25
+ "eval_loss": 0.42618608474731445,
26
+ "eval_roc_auc": 0.634885883674972,
27
+ "eval_runtime": 93.2549,
28
+ "eval_samples_per_second": 3.753,
29
+ "eval_steps_per_second": 0.472,
30
+ "step": 350
31
+ },
32
+ {
33
+ "epoch": 2.86,
34
+ "learning_rate": 8.571428571428571e-06,
35
+ "loss": 0.425,
36
+ "step": 500
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "eval_accuracy": 0.6,
41
+ "eval_f1": 0.8968824940047961,
42
+ "eval_loss": 0.39434972405433655,
43
+ "eval_roc_auc": 0.7227108923935367,
44
+ "eval_runtime": 92.9075,
45
+ "eval_samples_per_second": 3.767,
46
+ "eval_steps_per_second": 0.474,
47
+ "step": 525
48
+ },
49
+ {
50
+ "epoch": 4.0,
51
+ "eval_accuracy": 0.6142857142857143,
52
+ "eval_f1": 0.8975609756097561,
53
+ "eval_loss": 0.3901987075805664,
54
+ "eval_roc_auc": 0.7456310303406052,
55
+ "eval_runtime": 93.1306,
56
+ "eval_samples_per_second": 3.758,
57
+ "eval_steps_per_second": 0.472,
58
+ "step": 700
59
+ }
60
+ ],
61
+ "max_steps": 875,
62
+ "num_train_epochs": 5,
63
+ "total_flos": 624899189710512.0,
64
+ "trial_name": null,
65
+ "trial_params": null
66
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36c84d0c3044d35a464d45063f8901c07d25d86de070cbe6cce54404c7aacbb
3
+ size 3451
vocab.txt ADDED
The diff for this file is too large to render. See raw diff