Saravanan Palanisamy commited on
Commit
2ad688e
·
1 Parent(s): 51f49f5

Initial release of model

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "sadness",
13
+ "1": "joy",
14
+ "2": "love",
15
+ "3": "anger",
16
+ "4": "fear",
17
+ "5": "surprise"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "anger": 3,
23
+ "fear": 4,
24
+ "joy": 1,
25
+ "love": 2,
26
+ "sadness": 0,
27
+ "surprise": 5
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "bert",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "pad_token_id": 0,
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.53.1",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 30522
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fb86f63cc3c0d2f1708bbf918e972454adec7b7320b33382a2d5aa779acad0
3
+ size 437970952
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6a332e66547c15aaa7f65b8720c6af68ef2f2f7c0f040df32a6a57ab8d31838
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abadc5bed4b6c5aeaad51d66e76b6c574bb47b43ee4cf27b55d09ae2bf2fb1e1
3
+ size 1064
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1400,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7142857142857143,
14
+ "grad_norm": 9.375822067260742,
15
+ "learning_rate": 1.2871428571428572e-05,
16
+ "loss": 0.766,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_F1 Score": 0.9212437827891717,
22
+ "eval_accuracy": 0.920625,
23
+ "eval_loss": 0.2347349226474762,
24
+ "eval_runtime": 6.9338,
25
+ "eval_samples_per_second": 230.753,
26
+ "eval_steps_per_second": 14.422,
27
+ "step": 700
28
+ },
29
+ {
30
+ "epoch": 1.4285714285714286,
31
+ "grad_norm": 6.844856262207031,
32
+ "learning_rate": 5.7285714285714285e-06,
33
+ "loss": 0.2225,
34
+ "step": 1000
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 1400,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 2,
41
+ "save_steps": 500,
42
+ "stateful_callbacks": {
43
+ "TrainerControl": {
44
+ "args": {
45
+ "should_epoch_stop": false,
46
+ "should_evaluate": false,
47
+ "should_log": false,
48
+ "should_save": true,
49
+ "should_training_stop": true
50
+ },
51
+ "attributes": {}
52
+ }
53
+ },
54
+ "total_flos": 897898722739200.0,
55
+ "train_batch_size": 16,
56
+ "trial_name": null,
57
+ "trial_params": null
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff745d18dc2f3b90ff15fba5935bda0b9eec4903d6c069d6bc1807fb0417aa9
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff