ensr commited on
Commit
7e94cca
1 Parent(s): 9eccd8b

Training in progress, epoch 4

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed2644251368c65495b2c1007eb70c81466c27ef7763fe41e6c24481cb71cbff
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:396c6c1479b0e15af7bb5f2df4a50f3ffb524b7b652a3e667cf8e98d7c864a90
3
  size 267832560
run-6/checkpoint-402/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.0",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-402/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ead64e5f345bf0f55c8e363a20ad8d3108e5a80b6a90371e0d3880069a6e48f
3
+ size 267832560
run-6/checkpoint-402/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b2a34c8ed460a34c1bc32c458c70c15b30ee416f2d7bf6d7daef7816bbba63
3
+ size 535724410
run-6/checkpoint-402/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63afca34eb92b660b0313124d4b0b275e419fd721f93f48373bb12e7cd4d2042
3
+ size 14054
run-6/checkpoint-402/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:394d8d496b7da1208b7178b540035732e1a386e49e2b8f9d3235c258bece52a3
3
+ size 1064
run-6/checkpoint-402/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-6/checkpoint-402/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-402/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": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-6/checkpoint-402/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5255827322697563,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-6\\checkpoint-268",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 402,
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_loss": 0.4850870668888092,
14
+ "eval_matthews_correlation": 0.443580024837866,
15
+ "eval_runtime": 6.0007,
16
+ "eval_samples_per_second": 173.814,
17
+ "eval_steps_per_second": 10.999,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.4454311728477478,
23
+ "eval_matthews_correlation": 0.5255827322697563,
24
+ "eval_runtime": 6.8111,
25
+ "eval_samples_per_second": 153.132,
26
+ "eval_steps_per_second": 9.69,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6144103407859802,
32
+ "eval_matthews_correlation": 0.505985025117115,
33
+ "eval_runtime": 6.072,
34
+ "eval_samples_per_second": 171.771,
35
+ "eval_steps_per_second": 10.87,
36
+ "step": 402
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 536,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 8.066575947187145e-05,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 17
52
+ }
53
+ }
run-6/checkpoint-402/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ded1b6b1f60b9546c0024cc791ec548ec898fc70ad8e812f4ae3d3a5f1c1d50
3
+ size 4792
run-6/checkpoint-402/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-536/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.0",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:396c6c1479b0e15af7bb5f2df4a50f3ffb524b7b652a3e667cf8e98d7c864a90
3
+ size 267832560
run-6/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8d5c43c9efbb494e5142f43f9115d95306482834a7ab8c0b2046e080091c23
3
+ size 535724410
run-6/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2273de35c35bb0f1fc348eefb430b802a1635eac8cc04ab0fc3d4d6dcbc499c7
3
+ size 14054
run-6/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b29e2199ce12bd9ef7792b08b115e8c29bafe42e34200b7d9406b6f9907beb
3
+ size 1064
run-6/checkpoint-536/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-6/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-536/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": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-6/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5255827322697563,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-6\\checkpoint-268",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 536,
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_loss": 0.4850870668888092,
14
+ "eval_matthews_correlation": 0.443580024837866,
15
+ "eval_runtime": 6.0007,
16
+ "eval_samples_per_second": 173.814,
17
+ "eval_steps_per_second": 10.999,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.4454311728477478,
23
+ "eval_matthews_correlation": 0.5255827322697563,
24
+ "eval_runtime": 6.8111,
25
+ "eval_samples_per_second": 153.132,
26
+ "eval_steps_per_second": 9.69,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6144103407859802,
32
+ "eval_matthews_correlation": 0.505985025117115,
33
+ "eval_runtime": 6.072,
34
+ "eval_samples_per_second": 171.771,
35
+ "eval_steps_per_second": 10.87,
36
+ "step": 402
37
+ },
38
+ {
39
+ "epoch": 3.73,
40
+ "learning_rate": 5.417849516767485e-06,
41
+ "loss": 0.2809,
42
+ "step": 500
43
+ },
44
+ {
45
+ "epoch": 4.0,
46
+ "eval_loss": 0.7592720985412598,
47
+ "eval_matthews_correlation": 0.5185657415144317,
48
+ "eval_runtime": 5.9378,
49
+ "eval_samples_per_second": 175.654,
50
+ "eval_steps_per_second": 11.115,
51
+ "step": 536
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 536,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 4,
58
+ "save_steps": 500,
59
+ "total_flos": 212227778719416.0,
60
+ "train_batch_size": 64,
61
+ "trial_name": null,
62
+ "trial_params": {
63
+ "learning_rate": 8.066575947187145e-05,
64
+ "num_train_epochs": 4,
65
+ "per_device_train_batch_size": 64,
66
+ "seed": 17
67
+ }
68
+ }
run-6/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ded1b6b1f60b9546c0024cc791ec548ec898fc70ad8e812f4ae3d3a5f1c1d50
3
+ size 4792
run-6/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec12_14-52-17_DESKTOP-UUVDD26/events.out.tfevents.1702387940.DESKTOP-UUVDD26.9476.8 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cafda37a18b3c2357e276fc762b23b8e26b23cbe9bc2d96603f9a317d586302
3
- size 5006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bc59e82d69d3d40d5364f02d697a2671bc149de4d3b1e25f77528595881ed02
3
+ size 6187