Hugging Face's logo

ipeksnmz
/
bert-base-uncased-finetuned-rte-run_3

Text Classification
Transformers
TensorBoard
Safetensors
bert
glue
rte
max_length_128
dropout_0.4
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
ipeksnmz commited on
Commit
2072318
·
verified ·
1 Parent(s): 6d60b2b

Training in progress, epoch 1

Browse files
Files changed (19) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-312/config.json +26 -0
  3. run-4/checkpoint-312/model.safetensors +3 -0
  4. run-4/checkpoint-312/optimizer.pt +3 -0
  5. run-4/checkpoint-312/rng_state.pth +3 -0
  6. run-4/checkpoint-312/scheduler.pt +3 -0
  7. run-4/checkpoint-312/special_tokens_map.json +7 -0
  8. run-4/checkpoint-312/tokenizer.json +0 -0
  9. run-4/checkpoint-312/tokenizer_config.json +56 -0
  10. run-4/checkpoint-312/trainer_state.json +58 -0
  11. run-4/checkpoint-312/training_args.bin +3 -0
  12. run-4/checkpoint-312/vocab.txt +0 -0
  13. run-5/checkpoint-78/model.safetensors +1 -1
  14. run-5/checkpoint-78/optimizer.pt +1 -1
  15. run-5/checkpoint-78/scheduler.pt +1 -1
  16. run-5/checkpoint-78/trainer_state.json +10 -10
  17. run-5/checkpoint-78/training_args.bin +1 -1
  18. runs/Apr07_19-56-35_578d22db0b7b/events.out.tfevents.1744056538.578d22db0b7b.632.7 +3 -0
  19. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4891c85923eb1751121423e083e3404c8fb6eb4a4dc52922ad262d2fb76bb6fe
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e5fa2ca4a4cae7f98b1663d6182ac2fefde37765be941091bcab70c5ac42fe
3
  size 437958648
run-4/checkpoint-312/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.3",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-4/checkpoint-312/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8facacd2d40bf7f4ffa747b30cadb0b1e557ccf1c903df2526a7b154f93e4fa
3
+ size 437958648
run-4/checkpoint-312/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b91a0885045955f189d463b25702a77e51ba53bd602fc3b708c209c9cd2742c
3
+ size 876038394
run-4/checkpoint-312/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461c1a9b3826b507c09b4dd42085229af1d8b64f8520bd9fe1d79ac0fb593a84
3
+ size 14244
run-4/checkpoint-312/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd43c7100bac1b26fa24d25a2dfd5db65aa9963121491470c0b939d8eadc487
3
+ size 1064
run-4/checkpoint-312/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-4/checkpoint-312/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-312/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-4/checkpoint-312/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 156,
3
+ "best_metric": 0.4657039711191336,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-4/checkpoint-156",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 312,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.4657039711191336,
15
+ "eval_loss": 0.706757128238678,
16
+ "eval_runtime": 0.4712,
17
+ "eval_samples_per_second": 587.806,
18
+ "eval_steps_per_second": 19.098,
19
+ "step": 156
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.4657039711191336,
24
+ "eval_loss": 0.7022965550422668,
25
+ "eval_runtime": 0.4694,
26
+ "eval_samples_per_second": 590.084,
27
+ "eval_steps_per_second": 19.172,
28
+ "step": 312
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 312,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 2,
35
+ "save_steps": 500,
36
+ "stateful_callbacks": {
37
+ "TrainerControl": {
38
+ "args": {
39
+ "should_epoch_stop": false,
40
+ "should_evaluate": false,
41
+ "should_log": false,
42
+ "should_save": true,
43
+ "should_training_stop": true
44
+ },
45
+ "attributes": {}
46
+ }
47
+ },
48
+ "total_flos": 0,
49
+ "train_batch_size": 16,
50
+ "trial_name": null,
51
+ "trial_params": {
52
+ "dropout": 0.2,
53
+ "learning_rate": 1.8147223767636534e-06,
54
+ "max_length": 256,
55
+ "num_train_epochs": 2,
56
+ "per_device_train_batch_size": 16
57
+ }
58
+ }
run-4/checkpoint-312/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d8caec19e178a735778696a9c43ef8907bddc1a4617e8297fd3706a848b696
3
+ size 5432
run-4/checkpoint-312/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-78/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf5c913ae216b41e1a028ac88cfb2bb9821f00bedd3d5aa806f0430d208ab425
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e5fa2ca4a4cae7f98b1663d6182ac2fefde37765be941091bcab70c5ac42fe
3
  size 437958648
run-5/checkpoint-78/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:579bedb139aab31a4a1a88c5dec066068b05b93cbb5d87f1a767ef671b1029e8
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df5a425124499ca473c5254b1e52b3bd892b175a7dda0fb88383d828516efdac
3
  size 876038394
run-5/checkpoint-78/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:711ed5ed922ad44f7cb1f7b00f7c8b361076734724f06a0b5b07cc008ab671c2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf8dfdc82b50396a6ef7441bc4d7b9bde037f571763582ad617330c934d06b2f
3
  size 1064
run-5/checkpoint-78/trainer_state.json CHANGED
@@ -12,17 +12,17 @@
12
  {
13
  "epoch": 1.0,
14
  "eval_accuracy": 0.5595667870036101,
15
- "eval_loss": 0.6888958215713501,
16
- "eval_runtime": 0.4632,
17
- "eval_samples_per_second": 598.068,
18
- "eval_steps_per_second": 19.432,
19
  "step": 78
20
  }
21
  ],
22
  "logging_steps": 500,
23
- "max_steps": 156,
24
  "num_input_tokens_seen": 0,
25
- "num_train_epochs": 2,
26
  "save_steps": 500,
27
  "stateful_callbacks": {
28
  "TrainerControl": {
@@ -40,10 +40,10 @@
40
  "train_batch_size": 32,
41
  "trial_name": null,
42
  "trial_params": {
43
- "dropout": 0.5,
44
- "learning_rate": 2.312919001524447e-05,
45
- "max_length": 128,
46
- "num_train_epochs": 2,
47
  "per_device_train_batch_size": 32
48
  }
49
  }
 
12
  {
13
  "epoch": 1.0,
14
  "eval_accuracy": 0.5595667870036101,
15
+ "eval_loss": 0.6858518123626709,
16
+ "eval_runtime": 0.4624,
17
+ "eval_samples_per_second": 599.013,
18
+ "eval_steps_per_second": 19.463,
19
  "step": 78
20
  }
21
  ],
22
  "logging_steps": 500,
23
+ "max_steps": 234,
24
  "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 3,
26
  "save_steps": 500,
27
  "stateful_callbacks": {
28
  "TrainerControl": {
 
40
  "train_batch_size": 32,
41
  "trial_name": null,
42
  "trial_params": {
43
+ "dropout": 0.30000000000000004,
44
+ "learning_rate": 1.8075217428758282e-05,
45
+ "max_length": 64,
46
+ "num_train_epochs": 3,
47
  "per_device_train_batch_size": 32
48
  }
49
  }
run-5/checkpoint-78/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26c7e44a2ef9a2bcca8ab37c73b0c2d587f6887fd981085a27b0b77d003d836e
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0e2f380cc23eb89fbfd2b30890ce4558fe69ded039963c49290f9161089cbb1
3
  size 5432
runs/Apr07_19-56-35_578d22db0b7b/events.out.tfevents.1744056538.578d22db0b7b.632.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3862e0070800330d2437db9f86b4078648110562bf0826614f2db2754fda0830
3
+ size 6419
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25d8caec19e178a735778696a9c43ef8907bddc1a4617e8297fd3706a848b696
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0e2f380cc23eb89fbfd2b30890ce4558fe69ded039963c49290f9161089cbb1
3
  size 5432