antalvdb commited on
Commit
0522b09
·
verified ·
1 Parent(s): 3dbc794

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:a2576637571f5a7d42c9f0a090b1f5138c938030953b4deae7523da96d2f329e
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19aa8e507896ea71d693c872ffde6f69b05865ee003b71a3d14437f3b59ecb54
3
  size 267832560
run-6/checkpoint-42/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": "4.37.1",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a0aeeb9e573f521ac876a843a308f7b612e43de537cae5dab40b9a14f98f71
3
+ size 267832560
run-6/checkpoint-42/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d53128dd773364ea4e76d06060e5f5f8a8d621ffc1effc20c1968861e548b23d
3
+ size 535724410
run-6/checkpoint-42/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fec8b3b5464770b340a76bb5f047bf3597027adf8170fa7bf4db80a861ac635
3
+ size 14054
run-6/checkpoint-42/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eda9ecec76ea2c350d8e61e0549b8b2785100a29c69e11ac209c00260475c591
3
+ size 1064
run-6/checkpoint-42/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-42/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-42/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-42/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06558874629318973,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-42",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 42,
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": 0.6143483519554138,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 32.3274,
16
+ "eval_samples_per_second": 32.264,
17
+ "eval_steps_per_second": 2.042,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6015313863754272,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 31.2134,
25
+ "eval_samples_per_second": 33.415,
26
+ "eval_steps_per_second": 2.114,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5886062383651733,
32
+ "eval_matthews_correlation": 0.06558874629318973,
33
+ "eval_runtime": 34.8082,
34
+ "eval_samples_per_second": 29.964,
35
+ "eval_steps_per_second": 1.896,
36
+ "step": 42
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 56,
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": 3.3647806166177066e-05,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 8
52
+ }
53
+ }
run-6/checkpoint-42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225a711d15eac0f430cf2b63f3ec4e2d09f2b24f77f0ed189cc4d1877a526952
3
+ size 4792
run-6/checkpoint-42/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-56/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": "4.37.1",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-56/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19aa8e507896ea71d693c872ffde6f69b05865ee003b71a3d14437f3b59ecb54
3
+ size 267832560
run-6/checkpoint-56/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:213a1fed3efad61511da4ad128aa1c3e5c51b3881b0e3e370814d1c05c29e6f6
3
+ size 535724410
run-6/checkpoint-56/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae052ac4f1fd57b08dc8253be1aba44b8af4769f537bc36bf82e9a7c7ef369b
3
+ size 14054
run-6/checkpoint-56/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c550c7b2e349fd05fcb474690f14ffe3e055904f19084064ab8204f9a66d2440
3
+ size 1064
run-6/checkpoint-56/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-56/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-56/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-56/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.18994160507030058,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-56",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 56,
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": 0.6143483519554138,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 32.3274,
16
+ "eval_samples_per_second": 32.264,
17
+ "eval_steps_per_second": 2.042,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6015313863754272,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 31.2134,
25
+ "eval_samples_per_second": 33.415,
26
+ "eval_steps_per_second": 2.114,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5886062383651733,
32
+ "eval_matthews_correlation": 0.06558874629318973,
33
+ "eval_runtime": 34.8082,
34
+ "eval_samples_per_second": 29.964,
35
+ "eval_steps_per_second": 1.896,
36
+ "step": 42
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.5776782631874084,
41
+ "eval_matthews_correlation": 0.18994160507030058,
42
+ "eval_runtime": 31.5946,
43
+ "eval_samples_per_second": 33.012,
44
+ "eval_steps_per_second": 2.089,
45
+ "step": 56
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 56,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 64,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 3.3647806166177066e-05,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 64,
60
+ "seed": 8
61
+ }
62
+ }
run-6/checkpoint-56/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225a711d15eac0f430cf2b63f3ec4e2d09f2b24f77f0ed189cc4d1877a526952
3
+ size 4792
run-6/checkpoint-56/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jan26_08-04-50_7ac5f092fd85/events.out.tfevents.1706286829.7ac5f092fd85.1710.10 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58d71344ab6dde9a5605f04783d483b3490657960294c7e7429fb99a0b79e2ec
3
- size 4989
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6443661e5b48f6fb5a7032b5e3de809151efb9b898ef9872afe114e2c4853d47
3
+ size 5995