Hugging Face's logo

NhatHoang2002
/
bert-test-run

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Metrics Community
NhatHoang2002 commited on
Commit
24b1e0c
·
verified ·
1 Parent(s): bbc3e1d

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. README.md +53 -0
  2. checkpoint-4/config.json +27 -0
  3. checkpoint-4/model.safetensors +3 -0
  4. checkpoint-4/rng_state.pth +3 -0
  5. checkpoint-4/trainer_state.json +32 -0
  6. checkpoint-4/training_args.bin +3 -0
  7. checkpoint-5/config.json +27 -0
  8. checkpoint-5/model.safetensors +3 -0
  9. checkpoint-5/rng_state.pth +3 -0
  10. checkpoint-5/trainer_state.json +32 -0
  11. checkpoint-5/training_args.bin +3 -0
  12. config.json +27 -0
  13. model.safetensors +3 -0
  14. runs/Dec15_02-13-04_cil-hydra/events.out.tfevents.1765735987.cil-hydra.289508.0 +3 -0
  15. runs/Dec15_02-18-10_cil-hydra/events.out.tfevents.1765736292.cil-hydra.290123.0 +3 -0
  16. runs/Dec15_02-19-55_cil-hydra/events.out.tfevents.1765736397.cil-hydra.290492.0 +3 -0
  17. runs/Dec15_02-21-46_cil-hydra/events.out.tfevents.1765736509.cil-hydra.290880.0 +3 -0
  18. runs/Dec15_02-41-35_cil-hydra/events.out.tfevents.1765737697.cil-hydra.294925.0 +3 -0
  19. runs/Dec15_02-42-29_cil-hydra/events.out.tfevents.1765737751.cil-hydra.295275.0 +3 -0
  20. runs/Dec15_02-43-10_cil-hydra/events.out.tfevents.1765737792.cil-hydra.295643.0 +3 -0
  21. runs/Dec15_02-44-39_cil-hydra/events.out.tfevents.1765737881.cil-hydra.296084.0 +3 -0
  22. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: bert-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: bert-test-run
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # bert-test-run
16
+
17
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 32
38
+ - eval_batch_size: 32
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.45.0
51
+ - Pytorch 2.5.1+cu124
52
+ - Datasets 3.3.2
53
+ - Tokenizers 0.20.3
checkpoint-4/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.45.0",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
checkpoint-4/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82842407f25cdcfe9840ba04085253ab2c24802b2f1951af2639dbe219b9047b
3
+ size 437958648
checkpoint-4/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:125f1c7a40f6cc70fb145076c46f4e1a44044b7eb400a480ee20b2c84304e39b
3
+ size 14244
checkpoint-4/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 5,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 5,
15
+ "save_steps": 1,
16
+ "stateful_callbacks": {
17
+ "TrainerControl": {
18
+ "args": {
19
+ "should_epoch_stop": false,
20
+ "should_evaluate": false,
21
+ "should_log": false,
22
+ "should_save": true,
23
+ "should_training_stop": false
24
+ },
25
+ "attributes": {}
26
+ }
27
+ },
28
+ "total_flos": 526222110720.0,
29
+ "train_batch_size": 32,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-4/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56c98f1fe3c7d20ed0c48f0f2fe6ae65fedf336c09aea2fe7073e2283182c349
3
+ size 5240
checkpoint-5/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.45.0",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
checkpoint-5/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feda9b42870410fcefefa222f33602fd0f045e441326a5e522e77943e46845ac
3
+ size 437958648
checkpoint-5/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5a43ad05ba354cf0d11b8cbc26c4bb551440b07436d37c700d69e239a60fa9e
3
+ size 14244
checkpoint-5/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 5,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 5,
15
+ "save_steps": 1,
16
+ "stateful_callbacks": {
17
+ "TrainerControl": {
18
+ "args": {
19
+ "should_epoch_stop": false,
20
+ "should_evaluate": false,
21
+ "should_log": false,
22
+ "should_save": true,
23
+ "should_training_stop": true
24
+ },
25
+ "attributes": {}
26
+ }
27
+ },
28
+ "total_flos": 657777638400.0,
29
+ "train_batch_size": 32,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56c98f1fe3c7d20ed0c48f0f2fe6ae65fedf336c09aea2fe7073e2283182c349
3
+ size 5240
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.45.0",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa1fc4d96d982452da5170c65f3e497922383096c6f31685d43683623f7013b
3
+ size 437958648
runs/Dec15_02-13-04_cil-hydra/events.out.tfevents.1765735987.cil-hydra.289508.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:708d12658123e1c78c60cbed6de6d6fc9a252172474ea8a70261bdf40b479695
3
+ size 5304
runs/Dec15_02-18-10_cil-hydra/events.out.tfevents.1765736292.cil-hydra.290123.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af39f6703696417439b95c41fe4034340f1d3ed560f3786c3c3da1124690019
3
+ size 5309
runs/Dec15_02-19-55_cil-hydra/events.out.tfevents.1765736397.cil-hydra.290492.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26c465dfa60ad6fd862d9b8fb4b1aa6a5e5e0fd8eadcd64803d3003efe7b1af
3
+ size 5309
runs/Dec15_02-21-46_cil-hydra/events.out.tfevents.1765736509.cil-hydra.290880.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b50385bac3a11ceef119868c1461a2f6fba5e2d684a278b55ff9a66c010868b2
3
+ size 5302
runs/Dec15_02-41-35_cil-hydra/events.out.tfevents.1765737697.cil-hydra.294925.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4318e7290ce9e22fcca496afe962121fa08bcc158063647ab33ce25c1f4c260d
3
+ size 5303
runs/Dec15_02-42-29_cil-hydra/events.out.tfevents.1765737751.cil-hydra.295275.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6e93a9bc208aebb39cbfa47bd00cf97a82890d17dda91db8e323502870d66f
3
+ size 5303
runs/Dec15_02-43-10_cil-hydra/events.out.tfevents.1765737792.cil-hydra.295643.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364f8ff1091a717aad3a013e0c5411b4284ae773a743380671170f59b77c456f
3
+ size 5303
runs/Dec15_02-44-39_cil-hydra/events.out.tfevents.1765737881.cil-hydra.296084.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:496a0d224215bc5c4140346d28a783485ecd09b62456b7d69ae58002dbee17fd
3
+ size 5303
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32dbcf5fac0091639fcbfa347fca92a55f5c50919153bfdacc6ebdbc77dc5eea
3
+ size 5240