obudzecie commited on
Commit
aa943e3
·
verified ·
1 Parent(s): 6bd163a

Training in progress, epoch 2

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf78cbc2993d13ebecde8f6d9ef960a4b063be2ac84856be9ae119a5da2de86c
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19d4241218652ba9c1b9b31915ec23920b45e79f1438a600a1a5c71050dedef8
3
  size 267832560
run-0/checkpoint-14/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e18d66452db55d99e35342177e49d6e4d7903a06fcc4061f0f8211e24dfea29
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19d4241218652ba9c1b9b31915ec23920b45e79f1438a600a1a5c71050dedef8
3
  size 267832560
run-0/checkpoint-14/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b9f07bd190b4d6512a7d93ae9c883710c2835731608e56fa4c607ea808effac
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124ccb511a07b2b980a2e88b683cd55ddb0b0907d65f4ea76b967309eac4e5df
3
  size 535727290
run-0/checkpoint-14/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:913215f3de1504840e2112082beeafe8ca0949bd913f4f59e37b85f90b58eef5
3
  size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b24b56983563674fcf0a9d5420082e4dd1bcc418026eb29803d7988d698dead
3
  size 14308
run-0/checkpoint-14/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:990f5f483b193bb010923b9f6c44978f48c7bbdb439176cdca024ab27d103105
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00345a23be66eca455536057a49d2f57cf3e4f65924f525e745214c3e8f70e7
3
  size 1064
run-0/checkpoint-14/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "best_metric": 0.0,
3
- "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-14",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
  "global_step": 14,
7
  "is_hyper_param_search": true,
@@ -10,26 +10,35 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.6425530314445496,
14
  "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 0.6667,
16
- "eval_samples_per_second": 1564.434,
17
- "eval_steps_per_second": 98.996,
 
 
 
 
 
 
 
 
 
18
  "step": 14
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 42,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 3,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 64,
28
  "trial_name": null,
29
  "trial_params": {
30
- "learning_rate": 5.9402286931455415e-06,
31
- "num_train_epochs": 3,
32
  "per_device_train_batch_size": 64,
33
- "seed": 33
34
  }
35
  }
 
1
  {
2
  "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-7",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 14,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.6069979667663574,
14
  "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.5899,
16
+ "eval_samples_per_second": 656.018,
17
+ "eval_steps_per_second": 82.395,
18
+ "step": 7
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5834578275680542,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 2.4953,
25
+ "eval_samples_per_second": 417.989,
26
+ "eval_steps_per_second": 52.499,
27
  "step": 14
28
  }
29
  ],
30
  "logging_steps": 500,
31
+ "max_steps": 28,
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": 6.924004119404506e-05,
40
+ "num_train_epochs": 4,
41
  "per_device_train_batch_size": 64,
42
+ "seed": 17
43
  }
44
  }
run-0/checkpoint-14/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3890eb403da684d0292db5dfdfff23f4d1c6bfee6a85697d4ee366d75565506
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc4ef5ffcc2a39c74e8598a37e0687340047329a8f9dbf3d4c35e5148d94b74
3
  size 4984
run-0/checkpoint-7/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-0/checkpoint-7/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c20218e0b94e6e2ea38637345298b3961120e6cb8a7eeb5d67366251638204b2
3
+ size 267832560
run-0/checkpoint-7/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:757b20889d8c4ebb99ee094617216a9e872f8506f241e47a172f81d09ef4ee67
3
+ size 535727290
run-0/checkpoint-7/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b7ae60ee80a0c1858512dd52b76bae1f943dbf7d965e61cf1519226a4628df
3
+ size 14308
run-0/checkpoint-7/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:328635ea608adb307ccaac75f357ea94aec7be6ead8b8e99d2b722409fe10ec9
3
+ size 1064
run-0/checkpoint-7/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-0/checkpoint-7/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-7/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-0/checkpoint-7/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-7",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7,
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": 0.6069979667663574,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.5899,
16
+ "eval_samples_per_second": 656.018,
17
+ "eval_steps_per_second": 82.395,
18
+ "step": 7
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 28,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 6.924004119404506e-05,
31
+ "num_train_epochs": 4,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 17
34
+ }
35
+ }
run-0/checkpoint-7/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc4ef5ffcc2a39c74e8598a37e0687340047329a8f9dbf3d4c35e5148d94b74
3
+ size 4984
run-0/checkpoint-7/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb27_18-14-33_d3d09c0dfc16/events.out.tfevents.1709058019.d3d09c0dfc16.836.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4b1a063842bc7149254a2789fe0a92aa20082f911ff87bc071e17b60d98f51
3
+ size 6205
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65c283d58730bbc92b7e1eb5aada8e0048b69f0e02f0c280fea83aec69e7c4b3
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc4ef5ffcc2a39c74e8598a37e0687340047329a8f9dbf3d4c35e5148d94b74
3
  size 4984