Hugging Face's logo

uvegesistvan
/
huBERTPlain

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
Hungarian
bert
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
uvegesistvan commited on
Commit
5fff235
•
1 Parent(s): 2d61a68

Upload with huggingface_hub

Browse files
Files changed (14) hide show
  1. checkpoint-1971/config.json +27 -0
  2. checkpoint-1971/optimizer.pt +3 -0
  3. checkpoint-1971/pytorch_model.bin +3 -0
  4. checkpoint-1971/rng_state.pth +3 -0
  5. checkpoint-1971/scheduler.pt +3 -0
  6. checkpoint-1971/trainer_state.json +61 -0
  7. checkpoint-1971/training_args.bin +3 -0
  8. config.json +27 -0
  9. huBERT_Plain2/logs/1677680617.0354788/events.out.tfevents.1677680617.2bca324b12fe.461.1 +3 -0
  10. huBERT_Plain2/logs/events.out.tfevents.1677680617.2bca324b12fe.461.0 +3 -0
  11. logs/1677696857.4364128/events.out.tfevents.1677696857.b192cc1dc265.132.1 +3 -0
  12. logs/events.out.tfevents.1677696857.b192cc1dc265.132.0 +3 -0
  13. pytorch_model.bin +3 -0
  14. training_args.bin +3 -0
checkpoint-1971/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SZTAKI-HLT/hubert-base-cc",
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": "4.26.1",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 32001
27
+ }
checkpoint-1971/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c74965d02b6125f5fb43fa2b30e01bfa7d5f7ab73c2729c4f2444d6fa319048
3
+ size 885075077
checkpoint-1971/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e64d6c0a3d14733f85c84bff90eb38a0a95f96a1b33fc08d2dcb15a7b4d1c50
3
+ size 442551413
checkpoint-1971/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea5fc5cca805940b72c2ec04addd8f42b35f20ed66647ce1478ab2bacd2199d
3
+ size 14575
checkpoint-1971/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e00685f1ac1052478fd834729d89058f7210087ea902874323a0f64c34ec3f2
3
+ size 627
checkpoint-1971/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5755290389060974,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Models/huBERT_Plain2/checkpoint-1971",
4
+ "epoch": 3.0,
5
+ "global_step": 1971,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4.5e-06,
13
+ "loss": 0.6481,
14
+ "step": 657
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.6730182926829268,
19
+ "eval_loss": 0.6048818230628967,
20
+ "eval_runtime": 5.483,
21
+ "eval_samples_per_second": 239.285,
22
+ "eval_steps_per_second": 14.955,
23
+ "step": 657
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 4.000000000000001e-06,
28
+ "loss": 0.5526,
29
+ "step": 1314
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.6821646341463414,
34
+ "eval_loss": 0.6087087988853455,
35
+ "eval_runtime": 4.5344,
36
+ "eval_samples_per_second": 289.344,
37
+ "eval_steps_per_second": 18.084,
38
+ "step": 1314
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 3.5e-06,
43
+ "loss": 0.4988,
44
+ "step": 1971
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.7103658536585366,
49
+ "eval_loss": 0.5755290389060974,
50
+ "eval_runtime": 4.5357,
51
+ "eval_samples_per_second": 289.264,
52
+ "eval_steps_per_second": 18.079,
53
+ "step": 1971
54
+ }
55
+ ],
56
+ "max_steps": 6570,
57
+ "num_train_epochs": 10,
58
+ "total_flos": 517950556917120.0,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-1971/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b443be2b2625e6a532c33565131cecac190a800b350bc4322e48278451bbc62
3
+ size 3515
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SZTAKI-HLT/hubert-base-cc",
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": "4.26.1",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 32001
27
+ }
huBERT_Plain2/logs/1677680617.0354788/events.out.tfevents.1677680617.2bca324b12fe.461.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053b0559b3df10cf9d24891621d71e31222a6c6a14ea74e9d50cef9f21eefed3
3
+ size 5767
huBERT_Plain2/logs/events.out.tfevents.1677680617.2bca324b12fe.461.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3accfa39a563e1aa8aec941df404a0930b894403def11f61cda4e351bc58e1
3
+ size 4060
logs/1677696857.4364128/events.out.tfevents.1677696857.b192cc1dc265.132.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d54b5b5baad7f76c332732d6b51c1ec7f319edf59326750d061e83327ec45fe6
3
+ size 5725
logs/events.out.tfevents.1677696857.b192cc1dc265.132.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b7fa032eaaabc34a8c6a328b613ca95d8dc987c90e3f27ed617c6c25733e5c4
3
+ size 6570
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e64d6c0a3d14733f85c84bff90eb38a0a95f96a1b33fc08d2dcb15a7b4d1c50
3
+ size 442551413
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b443be2b2625e6a532c33565131cecac190a800b350bc4322e48278451bbc62
3
+ size 3515