Hugging Face's logo

RavingRabbit
/
eformConsult

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
RavingRabbit commited on
Commit
7871ed3
·
1 Parent(s): db5bd2b

Training in progress, epoch 1

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-268/config.json +25 -0
  3. run-5/checkpoint-268/model.safetensors +3 -0
  4. run-5/checkpoint-268/optimizer.pt +3 -0
  5. run-5/checkpoint-268/rng_state.pth +3 -0
  6. run-5/checkpoint-268/scheduler.pt +3 -0
  7. run-5/checkpoint-268/special_tokens_map.json +7 -0
  8. run-5/checkpoint-268/tokenizer.json +0 -0
  9. run-5/checkpoint-268/tokenizer_config.json +55 -0
  10. run-5/checkpoint-268/trainer_state.json +44 -0
  11. run-5/checkpoint-268/training_args.bin +3 -0
  12. run-5/checkpoint-268/vocab.txt +0 -0
  13. run-6/checkpoint-535/config.json +25 -0
  14. run-6/checkpoint-535/model.safetensors +3 -0
  15. run-6/checkpoint-535/optimizer.pt +3 -0
  16. run-6/checkpoint-535/rng_state.pth +3 -0
  17. run-6/checkpoint-535/scheduler.pt +3 -0
  18. run-6/checkpoint-535/special_tokens_map.json +7 -0
  19. run-6/checkpoint-535/tokenizer.json +0 -0
  20. run-6/checkpoint-535/tokenizer_config.json +55 -0
  21. run-6/checkpoint-535/trainer_state.json +41 -0
  22. run-6/checkpoint-535/training_args.bin +3 -0
  23. run-6/checkpoint-535/vocab.txt +0 -0
  24. runs/Dec23_02-11-24_38c624d3e13b/events.out.tfevents.1703300275.38c624d3e13b.382.8 +3 -0
  25. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:895b4cfe56f9bbe61f6d2012ab8ec05f32493cb2973ad993275335f1e64bed55
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:939271f6ad84d6a30c3af3110ecb1a45e8b84279a83c889e1e6f1c15a1782651
3
  size 267832560
run-5/checkpoint-268/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a156ee1381baece8bc067899c77b44124ab4e4dbf6db86801c9c1f199dcdb43
3
+ size 267832560
run-5/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8994fa21f1fc83e4e39583f2db5cc3cdf288dff5dd43f8c85e96ba24bdde800
3
+ size 535727290
run-5/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7207a68078ec706453b51785c3b6d2f7cd4c2d8874e9395e8cfe293f0b845ecf
3
+ size 14308
run-5/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:893afed2fbd67c19b60f32975ce4042c919423743d9652387cc14c57270126c8
3
+ size 1064
run-5/checkpoint-268/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-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-268/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-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5290037338732806,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-268",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 268,
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": 0.44986891746520996,
14
+ "eval_matthews_correlation": 0.4940290085706236,
15
+ "eval_runtime": 0.7403,
16
+ "eval_samples_per_second": 1408.884,
17
+ "eval_steps_per_second": 89.153,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.4928521513938904,
23
+ "eval_matthews_correlation": 0.5290037338732806,
24
+ "eval_runtime": 0.785,
25
+ "eval_samples_per_second": 1328.729,
26
+ "eval_steps_per_second": 84.081,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 268,
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": 6.995529557117928e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 13
43
+ }
44
+ }
run-5/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33afb163da809694d0fba487af5fd1e38843481b27bda1cadf67731ac2c767e1
3
+ size 4792
run-5/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-535/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-535/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:939271f6ad84d6a30c3af3110ecb1a45e8b84279a83c889e1e6f1c15a1782651
3
+ size 267832560
run-6/checkpoint-535/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4872348e8ca4912ce159492f19b5401f6bbcd3fa8a230384250c45a31e1f6b0b
3
+ size 535727290
run-6/checkpoint-535/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46433a1b3ea42e7ded55e35e5123a9265ee86f3db42d7ca0d2f8156c531f08e3
3
+ size 14180
run-6/checkpoint-535/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a69c3a70c9b8664868ad2369d9174bd609f99d09596d8c430459fadc20a0754d
3
+ size 1064
run-6/checkpoint-535/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-535/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-535/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-535/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4326078706030828,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-535",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 535,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 1.3543559458705673e-05,
14
+ "loss": 0.5213,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.48579296469688416,
20
+ "eval_matthews_correlation": 0.4326078706030828,
21
+ "eval_runtime": 0.7405,
22
+ "eval_samples_per_second": 1408.497,
23
+ "eval_steps_per_second": 89.128,
24
+ "step": 535
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 2675,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 5,
31
+ "save_steps": 500,
32
+ "total_flos": 43076742200448.0,
33
+ "train_batch_size": 16,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "learning_rate": 1.6657021403235714e-05,
37
+ "num_train_epochs": 5,
38
+ "per_device_train_batch_size": 16,
39
+ "seed": 10
40
+ }
41
+ }
run-6/checkpoint-535/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1602644d43508d97754d969043bdfa579484259dbb7a0f5abcd3f731f492e3d4
3
+ size 4792
run-6/checkpoint-535/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-11-24_38c624d3e13b/events.out.tfevents.1703300275.38c624d3e13b.382.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbd8b5bc9f7dce6e3c13163b9f2e25bf20507f3c3068b1a901a118a368791c3
3
+ size 6323
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33afb163da809694d0fba487af5fd1e38843481b27bda1cadf67731ac2c767e1
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1602644d43508d97754d969043bdfa579484259dbb7a0f5abcd3f731f492e3d4
3
  size 4792