anamelchor commited on
Commit
65d303f
1 Parent(s): 6615f0f

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 sha256:2b9b8a8ddd3b961d8a615d72d44899f4f014544b243b6416621b85ccbf3c8ad2
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b7264777c389cb61e3202e49cd712d6a0a7c71278279effc9d1901b3bd91bac
3
  size 267832560
run-4/checkpoint-54/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb261ee18f81041ba8cec98c84be936a1ec23b01180cf95bd3d1190a82549429
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:341e92457360435fb9f32395253c06f0d5eeb92dbf408559787ed14ebe2d01f0
3
  size 267832560
run-4/checkpoint-54/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7916126064082f2ce9db20867574584196a6a27b89987dd7ce8e9b7d140d2030
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e45aee2b5c34e073e8f19912e9e0b351e8cbe890f77d8b5b3a37b35f8036a9
3
  size 535727290
run-4/checkpoint-54/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c9ec64315d092a0ea25ac2e27e41edc8abaffd16fcc7e533b633da1cbb0a551
3
- size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2032ba244bd2dafbbf529f865ea2d23c61262b0fed6820b9b52930307b4df882
3
+ size 14244
run-4/checkpoint-54/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8ba7c8ef246a01bcc9141e27f6de94b542ff4919c75a16a944a09386f439afb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61f20c597357d88f9f47e8abae0da1330535f50b9e39477c18ccef7d4e9cb300
3
  size 1064
run-4/checkpoint-54/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.0,
3
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-54",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
  "global_step": 54,
7
  "is_hyper_param_search": true,
@@ -10,26 +10,35 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.617499053478241,
14
  "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 0.7191,
16
- "eval_samples_per_second": 1450.391,
17
- "eval_steps_per_second": 91.779,
 
 
 
 
 
 
 
 
 
18
  "step": 54
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 54,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 1,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
- "train_batch_size": 16,
28
  "trial_name": null,
29
  "trial_params": {
30
- "learning_rate": 9.155071793841301e-06,
31
- "num_train_epochs": 1,
32
- "per_device_train_batch_size": 16,
33
- "seed": 24
34
  }
35
  }
 
1
  {
2
+ "best_metric": 0.0863794254719202,
3
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-54",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 54,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.598613440990448,
14
  "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7931,
16
+ "eval_samples_per_second": 1315.11,
17
+ "eval_steps_per_second": 83.219,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5975402593612671,
23
+ "eval_matthews_correlation": 0.0863794254719202,
24
+ "eval_runtime": 0.7965,
25
+ "eval_samples_per_second": 1309.539,
26
+ "eval_steps_per_second": 82.866,
27
  "step": 54
28
  }
29
  ],
30
  "logging_steps": 500,
31
+ "max_steps": 81,
32
  "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
+ "train_batch_size": 32,
37
  "trial_name": null,
38
  "trial_params": {
39
+ "learning_rate": 3.6796428408677604e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 1
43
  }
44
  }
run-4/checkpoint-54/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f522a57ff45b04702d23b1a21b6a560b003d1565d8bb0047401bc05c8c441902
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bcf9d16a39b36f26738ac27ccd3d625cd9d28ed3e5f9694dea854578c72fb9e
3
  size 4984
run-4/checkpoint-81/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-4/checkpoint-81/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee0caa10715f887372eaa0e30df712fed4d1f683ea968d185e4ff7026bfe302
3
+ size 267832560
run-4/checkpoint-81/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221a71dfefb4cff2007102961583abe8e353f0703234a3d38d569ab62ae51d17
3
+ size 535727290
run-4/checkpoint-81/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790f23647dc62293b735d826a0a1c199bddc650af4e9f8c8a6a48fcacdfcf34e
3
+ size 14244
run-4/checkpoint-81/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c2143573de3c71ec0df8d247132422493cc42d6fdd0ee4056c09505b0486112
3
+ size 1064
run-4/checkpoint-81/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-81/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-81/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-4/checkpoint-81/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2462710523446019,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-81",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 81,
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": 0.598613440990448,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7931,
16
+ "eval_samples_per_second": 1315.11,
17
+ "eval_steps_per_second": 83.219,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5975402593612671,
23
+ "eval_matthews_correlation": 0.0863794254719202,
24
+ "eval_runtime": 0.7965,
25
+ "eval_samples_per_second": 1309.539,
26
+ "eval_steps_per_second": 82.866,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5608728528022766,
32
+ "eval_matthews_correlation": 0.2462710523446019,
33
+ "eval_runtime": 1.1904,
34
+ "eval_samples_per_second": 876.167,
35
+ "eval_steps_per_second": 55.443,
36
+ "step": 81
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 81,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 32,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 3.6796428408677604e-05,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 32,
51
+ "seed": 1
52
+ }
53
+ }
run-4/checkpoint-81/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bcf9d16a39b36f26738ac27ccd3d625cd9d28ed3e5f9694dea854578c72fb9e
3
+ size 4984
run-4/checkpoint-81/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-27/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-5/checkpoint-27/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b7264777c389cb61e3202e49cd712d6a0a7c71278279effc9d1901b3bd91bac
3
+ size 267832560
run-5/checkpoint-27/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f772f075bb533b3e4c635270bf552c850b145a89978ebcbbc5303c26837565
3
+ size 535727290
run-5/checkpoint-27/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f40887a9aa64436f373c2378e34877cfef171d5714e7005f6563bf4cdadc6d
3
+ size 14308
run-5/checkpoint-27/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b1cfe251fe716f208540e6f5d0e55c8a1c32c5ace5bb2879270776ed8a783bd
3
+ size 1064
run-5/checkpoint-27/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-5/checkpoint-27/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-27/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-5/checkpoint-27/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-27",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 27,
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": 0.6698710918426514,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8001,
16
+ "eval_samples_per_second": 1303.648,
17
+ "eval_steps_per_second": 82.494,
18
+ "step": 27
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 135,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.8122310780931108e-06,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 21
34
+ }
35
+ }
run-5/checkpoint-27/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12789646f1ace8590d718854a0dcb7cbdcd7655dfa3e3b9eea3031d650c025e3
3
+ size 4984
run-5/checkpoint-27/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb27_16-43-42_b3bc3fede2ea/events.out.tfevents.1709053071.b3bc3fede2ea.5958.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d73f88f2928276fee2bca47ce61db0023ac2ef8f90e9e8bb48c5bd6534a054c
3
+ size 5201
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bcf9d16a39b36f26738ac27ccd3d625cd9d28ed3e5f9694dea854578c72fb9e
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12789646f1ace8590d718854a0dcb7cbdcd7655dfa3e3b9eea3031d650c025e3
3
  size 4984