Hugging Face's logo

Reza-Madani
/
test-small-bert

Token Classification
Transformers
PyTorch
TensorBoard
bert
Inference Endpoints
Model card Files Metrics Community
Reza-Madani commited on
Commit
75d0b39
•
1 Parent(s): b245ca7

Training in progress, step 500

Browse files
Files changed (13) hide show
  1. .gitignore +1 -0
  2. config.json +33 -0
  3. last-checkpoint/config.json +33 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/pytorch_model.bin +3 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scheduler.pt +3 -0
  8. last-checkpoint/trainer_state.json +34 -0
  9. last-checkpoint/training_args.bin +3 -0
  10. pytorch_model.bin +3 -0
  11. runs/Feb06_09-58-04_fadceb92582a/1675677492.0176017/events.out.tfevents.1675677492.fadceb92582a.597.5 +3 -0
  12. runs/Feb06_09-58-04_fadceb92582a/events.out.tfevents.1675677492.fadceb92582a.597.4 +3 -0
  13. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "prajjwal1/bert-mini",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 256,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1024,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 4,
25
+ "num_hidden_layers": 4,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.26.0",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30522
33
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "prajjwal1/bert-mini",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 256,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1024,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 4,
25
+ "num_hidden_layers": 4,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.26.0",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30522
33
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ea24f14a8cdc76fc550465b1bf1f5c795b449e5121a36a29b05cd2e0d1d2de
3
+ size 88883845
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf321e7138d894dbd74e1ab3d97a00f04afaca0e5c63a90dcd499f6644f5e0f
3
+ size 44449417
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1509ee85fa64f545e114cdaeb719c65524c2eabebb894701e5ac95a4915d5a78
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a7964cc59dbcd4cafe1ff58736b1a37cf044babc53007397f39ade5c8183aa6
3
+ size 627
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.30916422605514526,
3
+ "best_model_checkpoint": "./test-small-bert/checkpoint-500",
4
+ "epoch": 0.4921259842519685,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.49,
12
+ "learning_rate": 4.1797900262467194e-05,
13
+ "loss": 0.3094,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.49,
18
+ "eval_accuracy": 0.8668064320912942,
19
+ "eval_f1": 0.5572908435223631,
20
+ "eval_loss": 0.30916422605514526,
21
+ "eval_precision": 0.7079652478644959,
22
+ "eval_recall": 0.4594972397943469,
23
+ "eval_runtime": 8.9008,
24
+ "eval_samples_per_second": 1105.747,
25
+ "eval_steps_per_second": 4.382,
26
+ "step": 500
27
+ }
28
+ ],
29
+ "max_steps": 3048,
30
+ "num_train_epochs": 3,
31
+ "total_flos": 155323564032000.0,
32
+ "trial_name": null,
33
+ "trial_params": null
34
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af287dcc884589c6dabb87f751cb04af9a11a746e728505d8cb24b091e0040c8
3
+ size 3515
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf321e7138d894dbd74e1ab3d97a00f04afaca0e5c63a90dcd499f6644f5e0f
3
+ size 44449417
runs/Feb06_09-58-04_fadceb92582a/1675677492.0176017/events.out.tfevents.1675677492.fadceb92582a.597.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60cbd79a44a08a940e11e39f97a71653c713250bd95f4bcdbee36ccd932dfa37
3
+ size 5683
runs/Feb06_09-58-04_fadceb92582a/events.out.tfevents.1675677492.fadceb92582a.597.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12e86e1487b1ef6f7d63c347a42ca74b8f04905b0a444cd990fd46f96069854b
3
+ size 4544
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af287dcc884589c6dabb87f751cb04af9a11a746e728505d8cb24b091e0040c8
3
+ size 3515