anamelchor commited on
Commit
f2dc957
1 Parent(s): 511305a

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 sha256:2df076509a19e5ddf0b3041acf1185a28a896d931638464aedb3591f0d48539f
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe549cfaf6fcf3f2bcc33e61af18ff475c20030f465686cbfea52f2a6f01b4ec
3
  size 267832560
run-8/checkpoint-28/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb77ac3c816e23fddc1989318b47ec6ac27447fb86d367027ab6c003b01c79ce
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:250c639ccab46c3a4e2e299cb17d3edbae067a9602698f075896b136d0829594
3
  size 267832560
run-8/checkpoint-28/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb956be810da1004a52381159b47a980a20bf9e4e257c5ac098d8cd160205b84
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba5875f2b1406f33acea5233085b99fbf8eefd8063f461eb055cec5223054582
3
  size 535727290
run-8/checkpoint-28/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c7c3bf419e85329b27667f364dd600c1604458e4c503bca245c2fce723e6009
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdbf09100bfd98c9265663689e245adad91493c2b4f56907cd3dcfe8f8031c30
3
  size 14244
run-8/checkpoint-28/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af790769780716b1ffac659b155707486f29ca642b81e62f8d292e634f7c600b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:086ade91ab886693cbf0d85ea8be35303edac2fb528dc3b5ba02b44e186cecef
3
  size 1064
run-8/checkpoint-28/trainer_state.json CHANGED
@@ -10,35 +10,35 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.6050807237625122,
14
  "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 1.2093,
16
- "eval_samples_per_second": 862.486,
17
- "eval_steps_per_second": 54.577,
18
  "step": 14
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_loss": 0.5790172815322876,
23
  "eval_matthews_correlation": 0.0,
24
- "eval_runtime": 0.8146,
25
- "eval_samples_per_second": 1280.342,
26
- "eval_steps_per_second": 81.019,
27
  "step": 28
28
  }
29
  ],
30
  "logging_steps": 500,
31
- "max_steps": 28,
32
  "num_input_tokens_seen": 0,
33
- "num_train_epochs": 2,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
  "train_batch_size": 64,
37
  "trial_name": null,
38
  "trial_params": {
39
- "learning_rate": 5.6377293486135757e-05,
40
- "num_train_epochs": 2,
41
  "per_device_train_batch_size": 64,
42
- "seed": 16
43
  }
44
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.6093547344207764,
14
  "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7473,
16
+ "eval_samples_per_second": 1395.68,
17
+ "eval_steps_per_second": 88.317,
18
  "step": 14
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_loss": 0.5924274325370789,
23
  "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.8509,
25
+ "eval_samples_per_second": 1225.825,
26
+ "eval_steps_per_second": 77.569,
27
  "step": 28
28
  }
29
  ],
30
  "logging_steps": 500,
31
+ "max_steps": 56,
32
  "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
  "train_batch_size": 64,
37
  "trial_name": null,
38
  "trial_params": {
39
+ "learning_rate": 2.8212860094421134e-05,
40
+ "num_train_epochs": 4,
41
  "per_device_train_batch_size": 64,
42
+ "seed": 35
43
  }
44
  }
run-8/checkpoint-28/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fad24c79917de56c27af5271c94818eabaf3f3872062c491ecc9c38c4cd3da4
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74b2c2a15777a9330d9199a2d503860f656f04ef76dcd4b374673cd027f7a10
3
  size 4984
run-8/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d033c98f26a1237d7ce7288e9124accd7258586129735ebc21e343078e28e806
3
+ size 267832560
run-8/checkpoint-42/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aea138db0d8be83bac57224e0927a0b13a7b0d7d45d7a84e710f48c68b23df0
3
+ size 535727290
run-8/checkpoint-42/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24502516f5e48d3cefa3cde84db2f3bb2b83427175ceb4707e7d4ce0521fd2f1
3
+ size 14244
run-8/checkpoint-42/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d073566cfa97a03829dbdb1260c16de1eb59dbff2174f0772bc8d73f44e230b4
3
+ size 1064
run-8/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-8/checkpoint-42/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-42/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-14",
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": 0.6093547344207764,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7473,
16
+ "eval_samples_per_second": 1395.68,
17
+ "eval_steps_per_second": 88.317,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5924274325370789,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.8509,
25
+ "eval_samples_per_second": 1225.825,
26
+ "eval_steps_per_second": 77.569,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5907562971115112,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.7928,
34
+ "eval_samples_per_second": 1315.539,
35
+ "eval_steps_per_second": 83.246,
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": 2.8212860094421134e-05,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 35
52
+ }
53
+ }
run-8/checkpoint-42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74b2c2a15777a9330d9199a2d503860f656f04ef76dcd4b374673cd027f7a10
3
+ size 4984
run-8/checkpoint-42/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-56/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d006e61ac6c070576bbd68aa72db241fd1e024877b50244930c4678e6a222ccd
3
+ size 267832560
run-8/checkpoint-56/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa4240bde87affad2a75196fcc9ca9322f0cbe5a94ff7fc65cf7b8fcced333a
3
+ size 535727290
run-8/checkpoint-56/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f4d74040dc110062dec8fd0e59e4669c01476e2d0d7634cc328339cf0d61e5
3
+ size 14244
run-8/checkpoint-56/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:107e22fdeb555a2fee839afb67d8f253676fdb96e7a0bfa003339d6def6dce33
3
+ size 1064
run-8/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-8/checkpoint-56/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-56/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06558874629318973,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/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": 0.6093547344207764,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7473,
16
+ "eval_samples_per_second": 1395.68,
17
+ "eval_steps_per_second": 88.317,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5924274325370789,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.8509,
25
+ "eval_samples_per_second": 1225.825,
26
+ "eval_steps_per_second": 77.569,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5907562971115112,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.7928,
34
+ "eval_samples_per_second": 1315.539,
35
+ "eval_steps_per_second": 83.246,
36
+ "step": 42
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.5761707425117493,
41
+ "eval_matthews_correlation": 0.06558874629318973,
42
+ "eval_runtime": 1.2561,
43
+ "eval_samples_per_second": 830.368,
44
+ "eval_steps_per_second": 52.545,
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": 2.8212860094421134e-05,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 64,
60
+ "seed": 35
61
+ }
62
+ }
run-8/checkpoint-56/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74b2c2a15777a9330d9199a2d503860f656f04ef76dcd4b374673cd027f7a10
3
+ size 4984
run-8/checkpoint-56/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb28_18-10-00_5620ed9b2fff/events.out.tfevents.1709145450.5620ed9b2fff.209.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa25e4519f339d8b7e099771075deeb23d94fd016334a1e43d8cba4ce708a27a
3
+ size 4871
runs/Feb28_18-10-00_5620ed9b2fff/events.out.tfevents.1709145455.5620ed9b2fff.209.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3b5318b1962436bef5517beeb75b37b207a4a4a45c22ef8c139469e2d37fd9
3
+ size 6230
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f74b2c2a15777a9330d9199a2d503860f656f04ef76dcd4b374673cd027f7a10
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a95b7f601a84efcc35eab15322feaf1cfa949fd0dc5a0d1dd381523ec81188
3
  size 4984