Hugging Face's logo

karthikFlash1
/
fine-tuned-blog-sentiment-002

Text Classification
Transformers
Safetensors
distilbert
Generated from Trainer
Model card Files Community
karthikFlash1 commited on
Commit
190eae1
·
verified ·
1 Parent(s): 81691eb

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. checkpoint-170/config.json +36 -0
  2. checkpoint-170/model.safetensors +3 -0
  3. checkpoint-170/optimizer.pt +3 -0
  4. checkpoint-170/rng_state.pth +3 -0
  5. checkpoint-170/scheduler.pt +3 -0
  6. checkpoint-170/special_tokens_map.json +37 -0
  7. checkpoint-170/tokenizer.json +0 -0
  8. checkpoint-170/tokenizer_config.json +65 -0
  9. checkpoint-170/trainer_state.json +45 -0
  10. checkpoint-170/training_args.bin +3 -0
  11. checkpoint-170/vocab.txt +0 -0
  12. checkpoint-340/config.json +36 -0
  13. checkpoint-340/model.safetensors +3 -0
  14. checkpoint-340/optimizer.pt +3 -0
  15. checkpoint-340/rng_state.pth +3 -0
  16. checkpoint-340/scheduler.pt +3 -0
  17. checkpoint-340/special_tokens_map.json +37 -0
  18. checkpoint-340/tokenizer.json +0 -0
  19. checkpoint-340/tokenizer_config.json +65 -0
  20. checkpoint-340/trainer_state.json +57 -0
  21. checkpoint-340/training_args.bin +3 -0
  22. checkpoint-340/vocab.txt +0 -0
checkpoint-170/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lxyuan/distilbert-base-multilingual-cased-sentiments-student",
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": "positive",
13
+ "1": "neutral",
14
+ "2": "negative"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "negative": 2,
19
+ "neutral": 1,
20
+ "positive": 0
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": false,
32
+ "tie_weights_": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.48.3",
35
+ "vocab_size": 119547
36
+ }
checkpoint-170/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1859f3622cf4bd64326b8f19b8fbeb44b13049b9f1869f412888c87179b0116
3
+ size 541320452
checkpoint-170/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144bdf1de9bde2af0bd1ce85d0ac037a3f20c3bc335f7b8bacb4878554b452c3
3
+ size 1082703034
checkpoint-170/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652fec4bd1fbff4753a7edc80383ed536d2d6b5ed38aa19a58d11f7019c43a5c
3
+ size 14244
checkpoint-170/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0011bba60f5b38f4f95b65b8c6d656503a2d1474894547b0d360b57a93f8d2c
3
+ size 1064
checkpoint-170/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-170/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-170/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
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "DistilBertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
checkpoint-170/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 170,
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": 1.0,
14
+ "eval_f1": 1.0,
15
+ "eval_loss": 0.0014051002217456698,
16
+ "eval_precision": 1.0,
17
+ "eval_recall": 1.0,
18
+ "eval_runtime": 5.0309,
19
+ "eval_samples_per_second": 67.582,
20
+ "eval_steps_per_second": 8.547,
21
+ "step": 170
22
+ }
23
+ ],
24
+ "logging_steps": 500,
25
+ "max_steps": 340,
26
+ "num_input_tokens_seen": 0,
27
+ "num_train_epochs": 2,
28
+ "save_steps": 500,
29
+ "stateful_callbacks": {
30
+ "TrainerControl": {
31
+ "args": {
32
+ "should_epoch_stop": false,
33
+ "should_evaluate": false,
34
+ "should_log": false,
35
+ "should_save": true,
36
+ "should_training_stop": false
37
+ },
38
+ "attributes": {}
39
+ }
40
+ },
41
+ "total_flos": 180026405231616.0,
42
+ "train_batch_size": 8,
43
+ "trial_name": null,
44
+ "trial_params": null
45
+ }
checkpoint-170/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5074cf48ce1f9b1500910704a5db89174eb82b2d279a6b93df5fc1874b5f5e
3
+ size 5304
checkpoint-170/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-340/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lxyuan/distilbert-base-multilingual-cased-sentiments-student",
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": "positive",
13
+ "1": "neutral",
14
+ "2": "negative"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "negative": 2,
19
+ "neutral": 1,
20
+ "positive": 0
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": false,
32
+ "tie_weights_": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.48.3",
35
+ "vocab_size": 119547
36
+ }
checkpoint-340/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bedd87ea7f7cc1db6f4b102968ac346e7b8eeb865a16c8776e6027be2ebe21e1
3
+ size 541320452
checkpoint-340/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ad4b8c225063e1d5c0c195a09aab5c035ec56238a8ed45e14768647ce5bfc3
3
+ size 1082703034
checkpoint-340/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad11e0d130bcbdde7f53e024f57c182264e8d5007d6c33465fe61b8e76d9dfcf
3
+ size 14244
checkpoint-340/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eddcead68a66f7a7df44e36491dac456de88f168779a70bea73ae84d3cff3538
3
+ size 1064
checkpoint-340/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-340/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-340/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
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "DistilBertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
checkpoint-340/trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 340,
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": 1.0,
14
+ "eval_f1": 1.0,
15
+ "eval_loss": 0.0014051002217456698,
16
+ "eval_precision": 1.0,
17
+ "eval_recall": 1.0,
18
+ "eval_runtime": 5.0309,
19
+ "eval_samples_per_second": 67.582,
20
+ "eval_steps_per_second": 8.547,
21
+ "step": 170
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "eval_accuracy": 1.0,
26
+ "eval_f1": 1.0,
27
+ "eval_loss": 0.0008127959445118904,
28
+ "eval_precision": 1.0,
29
+ "eval_recall": 1.0,
30
+ "eval_runtime": 5.0821,
31
+ "eval_samples_per_second": 66.902,
32
+ "eval_steps_per_second": 8.461,
33
+ "step": 340
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 340,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 2,
40
+ "save_steps": 500,
41
+ "stateful_callbacks": {
42
+ "TrainerControl": {
43
+ "args": {
44
+ "should_epoch_stop": false,
45
+ "should_evaluate": false,
46
+ "should_log": false,
47
+ "should_save": true,
48
+ "should_training_stop": true
49
+ },
50
+ "attributes": {}
51
+ }
52
+ },
53
+ "total_flos": 360052810463232.0,
54
+ "train_batch_size": 8,
55
+ "trial_name": null,
56
+ "trial_params": null
57
+ }
checkpoint-340/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5074cf48ce1f9b1500910704a5db89174eb82b2d279a6b93df5fc1874b5f5e
3
+ size 5304
checkpoint-340/vocab.txt ADDED
The diff for this file is too large to render. See raw diff