ana-grassmann commited on
Commit
fb8f853
1 Parent(s): 28a3c92

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6458b38be86ba67defe561c40e1db21ab4144316144239d277d7f1e512bde76b
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7bad66eac23b214ef4c8bc84d3737bd2ff16155c139286d0b966d68b8c977d8
3
  size 437958648
run-3/checkpoint-418/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": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-3/checkpoint-418/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7bad66eac23b214ef4c8bc84d3737bd2ff16155c139286d0b966d68b8c977d8
3
+ size 437958648
run-3/checkpoint-418/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec0fb45aea47d78e519d4db51b57b2d36e547d975810c2a03a5f3ed08c10a7e2
3
+ size 876038394
run-3/checkpoint-418/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b053a2fb4d757fbec805cb18ed00c46832bf9cfed2b2f4be9b14220365f4209b
3
+ size 14244
run-3/checkpoint-418/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afd96bbc57cc7f4773fc9ac13893d620e3997cea26d1af3057c735cfe9517c8
3
+ size 1064
run-3/checkpoint-418/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-3/checkpoint-418/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-418/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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-3/checkpoint-418/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9715398442180947,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-3/checkpoint-418",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 418,
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": 0.9715398442180947,
14
+ "eval_loss": 0.10920324921607971,
15
+ "eval_runtime": 597.1387,
16
+ "eval_samples_per_second": 27.95,
17
+ "eval_steps_per_second": 1.748,
18
+ "step": 418
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 2090,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 16,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 6.343244954121848e-05,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 16,
33
+ "seed": 30
34
+ }
35
+ }
run-3/checkpoint-418/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24bbb9dae3a0925768ae8c13e2cca58dd442b034c3bf962ff8d913cbe1be1cc6
3
+ size 4920
run-3/checkpoint-418/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar21_16-50-03_43ee8d6b3d53/events.out.tfevents.1711048636.43ee8d6b3d53.2090.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7663901199d758dfbf5f74221a8a745b5f1edca122a06355e86c391547dc1f72
3
+ size 4962
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:977ec9eece5f9e2273a7d887d95fb9be8edae8feee607dd3c107f6aa9ef3e0c5
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24bbb9dae3a0925768ae8c13e2cca58dd442b034c3bf962ff8d913cbe1be1cc6
3
  size 4920