Hugging Face's logo

Gaxys
/
DistilBERT-PD_Books

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
text-embeddings-inference
Model card Files
xet
Metrics Community
Gaxys commited on
Commit
2f759aa
·
1 Parent(s): f6cd6a3

Training in progress, epoch 1

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-8/checkpoint-40/config.json +35 -0
  3. run-8/checkpoint-40/model.safetensors +3 -0
  4. run-8/checkpoint-40/optimizer.pt +3 -0
  5. run-8/checkpoint-40/rng_state.pth +3 -0
  6. run-8/checkpoint-40/scheduler.pt +3 -0
  7. run-8/checkpoint-40/special_tokens_map.json +7 -0
  8. run-8/checkpoint-40/tokenizer.json +0 -0
  9. run-8/checkpoint-40/tokenizer_config.json +55 -0
  10. run-8/checkpoint-40/trainer_state.json +54 -0
  11. run-8/checkpoint-40/training_args.bin +3 -0
  12. run-8/checkpoint-40/vocab.txt +0 -0
  13. run-9/checkpoint-5/config.json +35 -0
  14. run-9/checkpoint-5/model.safetensors +3 -0
  15. run-9/checkpoint-5/optimizer.pt +3 -0
  16. run-9/checkpoint-5/rng_state.pth +3 -0
  17. run-9/checkpoint-5/scheduler.pt +3 -0
  18. run-9/checkpoint-5/special_tokens_map.json +7 -0
  19. run-9/checkpoint-5/tokenizer.json +0 -0
  20. run-9/checkpoint-5/tokenizer_config.json +55 -0
  21. run-9/checkpoint-5/trainer_state.json +39 -0
  22. run-9/checkpoint-5/training_args.bin +3 -0
  23. run-9/checkpoint-5/vocab.txt +0 -0
  24. runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701221441.37a4be0f03a9.346.10 +3 -0
  25. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f3565ff69d57c63eafb27f26a6e5c707cd5f558ea69b8bb7591a08dbe7e748d
3
  size 267835644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b50046e64cb00b2c7df2fcf19a4a7b3a916b3f85d6e96f9ec06d043bd86afe9
3
  size 267835644
run-8/checkpoint-40/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": "CAROLL",
13
+ "1": "DICKENS",
14
+ "2": "DOYLE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "CAROLL": 0,
19
+ "DICKENS": 1,
20
+ "DOYLE": 2
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": "single_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": "4.35.2",
34
+ "vocab_size": 30522
35
+ }
run-8/checkpoint-40/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db11d5725623ffcea9f41b96690b82ace8aa62247c993ad6b13fca9091fbe7c5
3
+ size 267835644
run-8/checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13caffd19100f9a0f329d5dbee23eece85cd15d8ac69874e91ef5af479d8236
3
+ size 535733434
run-8/checkpoint-40/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac64042761b6fd245dc99eb494d6214d3ff4d2fa553f1b80a66dfe5d6fa2b318
3
+ size 14244
run-8/checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0280328d9260e44c8d39c9251ba42fda1ab40713e351d9a961978722135d80e3
3
+ size 1064
run-8/checkpoint-40/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-8/checkpoint-40/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-40/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-8/checkpoint-40/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7190259099006653,
3
+ "best_model_checkpoint": "DistilBERT-PD_Books/run-8/checkpoint-40",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 40,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.7279596977329975,
14
+ "eval_loss": 0.823241651058197,
15
+ "eval_macro-f1": 0.4839590116835855,
16
+ "eval_macro-precision": 0.555275304978569,
17
+ "eval_macro-recall": 0.4912124180719801,
18
+ "eval_micro-f1": 0.7279596977329975,
19
+ "eval_micro-precision": 0.7279596977329975,
20
+ "eval_micro-recall": 0.7279596977329975,
21
+ "eval_runtime": 15.2908,
22
+ "eval_samples_per_second": 51.927,
23
+ "eval_steps_per_second": 3.27,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.7544080604534005,
29
+ "eval_loss": 0.7190259099006653,
30
+ "eval_macro-f1": 0.513501913021004,
31
+ "eval_macro-precision": 0.5634188813948352,
32
+ "eval_macro-recall": 0.519438224523593,
33
+ "eval_micro-f1": 0.7544080604534004,
34
+ "eval_micro-precision": 0.7544080604534005,
35
+ "eval_micro-recall": 0.7544080604534005,
36
+ "eval_runtime": 15.992,
37
+ "eval_samples_per_second": 49.65,
38
+ "eval_steps_per_second": 3.127,
39
+ "step": 40
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 40,
44
+ "num_train_epochs": 2,
45
+ "save_steps": 500,
46
+ "total_flos": 0,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "learning_rate": 1.6954326440653216e-05,
50
+ "num_train_epochs": 2,
51
+ "per_device_train_batch_size": 16,
52
+ "seed": 15
53
+ }
54
+ }
run-8/checkpoint-40/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56738b59fea5cf875daa2a08bf687ffe398d0bf34fa17a81ab6a1284f07df268
3
+ size 4600
run-8/checkpoint-40/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-5/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": "CAROLL",
13
+ "1": "DICKENS",
14
+ "2": "DOYLE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "CAROLL": 0,
19
+ "DICKENS": 1,
20
+ "DOYLE": 2
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": "single_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": "4.35.2",
34
+ "vocab_size": 30522
35
+ }
run-9/checkpoint-5/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b50046e64cb00b2c7df2fcf19a4a7b3a916b3f85d6e96f9ec06d043bd86afe9
3
+ size 267835644
run-9/checkpoint-5/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd87f21d0f2ec813dbf55df77a086770d28f3cfc045d63a94d2bd443e779253
3
+ size 535733434
run-9/checkpoint-5/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1663c99a89ff29d4698dabd061b6155508da189c6204e66a124f1bad9d316b5
3
+ size 14308
run-9/checkpoint-5/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2818828be32f86233823bd0888815835beb6f612e486e51db1069be55dae598a
3
+ size 1064
run-9/checkpoint-5/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-9/checkpoint-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-5/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-9/checkpoint-5/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0498220920562744,
3
+ "best_model_checkpoint": "DistilBERT-PD_Books/run-9/checkpoint-5",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.5654911838790933,
14
+ "eval_loss": 1.0498220920562744,
15
+ "eval_macro-f1": 0.3031696255458331,
16
+ "eval_macro-precision": 0.31709608158883523,
17
+ "eval_macro-recall": 0.34515021108856386,
18
+ "eval_micro-f1": 0.5654911838790933,
19
+ "eval_micro-precision": 0.5654911838790933,
20
+ "eval_micro-recall": 0.5654911838790933,
21
+ "eval_runtime": 15.9251,
22
+ "eval_samples_per_second": 49.858,
23
+ "eval_steps_per_second": 3.14,
24
+ "step": 5
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 5,
29
+ "num_train_epochs": 1,
30
+ "save_steps": 500,
31
+ "total_flos": 0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "learning_rate": 4.426129262853846e-06,
35
+ "num_train_epochs": 1,
36
+ "per_device_train_batch_size": 64,
37
+ "seed": 33
38
+ }
39
+ }
run-9/checkpoint-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a836d8594948e7d8214966845cc640758decb47a2feeddc0643bbedf92d50081
3
+ size 4600
run-9/checkpoint-5/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701221441.37a4be0f03a9.346.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef384bda6689b12bd1e844bc575281b60c6970b6c9b34f1efb2f09fbdacbc0a9
3
+ size 5259
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56738b59fea5cf875daa2a08bf687ffe398d0bf34fa17a81ab6a1284f07df268
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a836d8594948e7d8214966845cc640758decb47a2feeddc0643bbedf92d50081
3
  size 4600