Hugging Face's logo

sms1097
/
relevant_model

Text Classification
Transformers
Safetensors
distilbert
Inference Endpoints
Model card Files Community
sms1097 commited on
Commit
a6ff2f9
•
1 Parent(s): 7cb5070

Training in progress, epoch 1

Browse files
Files changed (18) hide show
  1. config.json +25 -0
  2. model.safetensors +3 -0
  3. run-0/checkpoint-1113/config.json +25 -0
  4. run-0/checkpoint-1113/model.safetensors +3 -0
  5. run-0/checkpoint-1113/optimizer.pt +3 -0
  6. run-0/checkpoint-1113/rng_state.pth +3 -0
  7. run-0/checkpoint-1113/scheduler.pt +3 -0
  8. run-0/checkpoint-1113/special_tokens_map.json +7 -0
  9. run-0/checkpoint-1113/tokenizer.json +0 -0
  10. run-0/checkpoint-1113/tokenizer_config.json +55 -0
  11. run-0/checkpoint-1113/trainer_state.json +47 -0
  12. run-0/checkpoint-1113/training_args.bin +3 -0
  13. run-0/checkpoint-1113/vocab.txt +0 -0
  14. special_tokens_map.json +7 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +55 -0
  17. training_args.bin +3 -0
  18. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.37.2",
24
+ "vocab_size": 30522
25
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e553e2860acfded9c99abc744521668bf1b75b8efba3201285d4261d48a43acf
3
+ size 267832560
run-0/checkpoint-1113/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.37.2",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-1113/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e553e2860acfded9c99abc744521668bf1b75b8efba3201285d4261d48a43acf
3
+ size 267832560
run-0/checkpoint-1113/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc0a57299e7ce0b0d6ed599fbfc6a11a8073670fdb5fc35c14c6f47f598c233
3
+ size 535727290
run-0/checkpoint-1113/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5572cc4d676fb16535ea5142ae2f144bb38f1d4fb30edc571ba1442b784e4e
3
+ size 14244
run-0/checkpoint-1113/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b36f355323e6223d48b7aff26b000635bf6ebfec911e50467c0ca95ed440727f
3
+ size 1064
run-0/checkpoint-1113/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
+ }
run-0/checkpoint-1113/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-1113/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-1113/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.764684941260235,
3
+ "best_model_checkpoint": "relevant_model/run-0/checkpoint-1113",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1113,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.45,
13
+ "learning_rate": 8.028932935250765e-07,
14
+ "loss": 0.5031,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.9,
19
+ "learning_rate": 1.480047996220777e-07,
20
+ "loss": 0.42,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_f1": 0.764684941260235,
26
+ "eval_loss": 0.40596920251846313,
27
+ "eval_runtime": 7.7707,
28
+ "eval_samples_per_second": 509.094,
29
+ "eval_steps_per_second": 7.979,
30
+ "step": 1113
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 1113,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 1,
37
+ "save_steps": 500,
38
+ "total_flos": 7085134726089984.0,
39
+ "train_batch_size": 64,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 1.4577817874280751e-06,
43
+ "num_train_epochs": 1,
44
+ "per_device_train_batch_size": 64,
45
+ "seed": 36
46
+ }
47
+ }
run-0/checkpoint-1113/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df89df61b84ded72d02ff4835a2b8c5b60aca9d2d6b90b2f2b5c3e742846d5d1
3
+ size 4664
run-0/checkpoint-1113/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df89df61b84ded72d02ff4835a2b8c5b60aca9d2d6b90b2f2b5c3e742846d5d1
3
+ size 4664
vocab.txt ADDED
The diff for this file is too large to render. See raw diff