Hugging Face's logo

docampo99
/
deberta-v3-base-finetuned-rte

Text Classification
Transformers
TensorBoard
Safetensors
deberta-v2
Model card Files Metrics Community
docampo99 commited on
Commit
a297abb
·
verified ·
1 Parent(s): 6dbba21

Training in progress, epoch 3

Browse files
Files changed (26) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-126/added_tokens.json +3 -0
  3. run-0/checkpoint-126/config.json +35 -0
  4. run-0/checkpoint-126/model.safetensors +3 -0
  5. run-0/checkpoint-126/optimizer.pt +3 -0
  6. run-0/checkpoint-126/rng_state.pth +3 -0
  7. run-0/checkpoint-126/scheduler.pt +3 -0
  8. run-0/checkpoint-126/special_tokens_map.json +15 -0
  9. run-0/checkpoint-126/spm.model +3 -0
  10. run-0/checkpoint-126/tokenizer.json +0 -0
  11. run-0/checkpoint-126/tokenizer_config.json +58 -0
  12. run-0/checkpoint-126/trainer_state.json +44 -0
  13. run-0/checkpoint-126/training_args.bin +3 -0
  14. run-0/checkpoint-189/added_tokens.json +3 -0
  15. run-0/checkpoint-189/config.json +35 -0
  16. run-0/checkpoint-189/model.safetensors +3 -0
  17. run-0/checkpoint-189/optimizer.pt +3 -0
  18. run-0/checkpoint-189/rng_state.pth +3 -0
  19. run-0/checkpoint-189/scheduler.pt +3 -0
  20. run-0/checkpoint-189/special_tokens_map.json +15 -0
  21. run-0/checkpoint-189/spm.model +3 -0
  22. run-0/checkpoint-189/tokenizer.json +0 -0
  23. run-0/checkpoint-189/tokenizer_config.json +58 -0
  24. run-0/checkpoint-189/trainer_state.json +53 -0
  25. run-0/checkpoint-189/training_args.bin +3 -0
  26. runs/Mar10_13-32-58_4e3c1469116f/events.out.tfevents.1710078354.4e3c1469116f.2145.2 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecb649d80359493e62654665b0e710be5f6c55eac3740fac56348b6f664a2792
3
  size 737719272
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:687d61b49d81762e419b778a8a84a894412b65f93bd0e7913eaf057755211179
3
  size 737719272
run-0/checkpoint-126/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
run-0/checkpoint-126/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.38.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
run-0/checkpoint-126/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:599cdffd5f558727736ca3cc0c50d89f0528cd00876b4cfd9213851a4e656b47
3
+ size 737719272
run-0/checkpoint-126/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63cd5e96cecba9b3ef0a59fa84f62f30e12160ac9514a950c7613edc6d7bb0aa
3
+ size 1475558394
run-0/checkpoint-126/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e026a1699d12d1fd6006b7ffafb2f4f9152eb8480ec3810730617183462b6be1
3
+ size 14244
run-0/checkpoint-126/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768af41a2d113f11d9cd88aa9d4ee178f5a9fdd667694ca922d24f7e29830ba2
3
+ size 1064
run-0/checkpoint-126/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
run-0/checkpoint-126/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
run-0/checkpoint-126/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-126/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
run-0/checkpoint-126/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5523465703971119,
3
+ "best_model_checkpoint": "deberta-v3-base-finetuned-rte/run-0/checkpoint-126",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 126,
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_accuracy": 0.5270758122743683,
14
+ "eval_loss": 0.6907861828804016,
15
+ "eval_runtime": 4.1816,
16
+ "eval_samples_per_second": 66.242,
17
+ "eval_steps_per_second": 8.37,
18
+ "step": 63
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.5523465703971119,
23
+ "eval_loss": 0.6867192983627319,
24
+ "eval_runtime": 5.4144,
25
+ "eval_samples_per_second": 51.159,
26
+ "eval_steps_per_second": 6.464,
27
+ "step": 126
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 189,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 4,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 5.109701384755999e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 4,
42
+ "seed": 30
43
+ }
44
+ }
run-0/checkpoint-126/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18eb21af817cd1d2204dbaf9c3bc9ecc35b910c052c9b05abc31b48ba41b1dfa
3
+ size 4920
run-0/checkpoint-189/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
run-0/checkpoint-189/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.38.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
run-0/checkpoint-189/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:687d61b49d81762e419b778a8a84a894412b65f93bd0e7913eaf057755211179
3
+ size 737719272
run-0/checkpoint-189/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9620e0a2d97f74965a36f5c4b612e7e90ba1fe50c61efadae85e408f9b5cdd
3
+ size 1475558394
run-0/checkpoint-189/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3316880060ad195c5ded676d19de5088dc40160ee02cb515285d42cdc7e57dd0
3
+ size 14244
run-0/checkpoint-189/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948240ff201ed6c5988ea329dff8f8253604e21fdace823943fcf2f9dc21b995
3
+ size 1064
run-0/checkpoint-189/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
run-0/checkpoint-189/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
run-0/checkpoint-189/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-189/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
run-0/checkpoint-189/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6101083032490975,
3
+ "best_model_checkpoint": "deberta-v3-base-finetuned-rte/run-0/checkpoint-189",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 189,
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_accuracy": 0.5270758122743683,
14
+ "eval_loss": 0.6907861828804016,
15
+ "eval_runtime": 4.1816,
16
+ "eval_samples_per_second": 66.242,
17
+ "eval_steps_per_second": 8.37,
18
+ "step": 63
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.5523465703971119,
23
+ "eval_loss": 0.6867192983627319,
24
+ "eval_runtime": 5.4144,
25
+ "eval_samples_per_second": 51.159,
26
+ "eval_steps_per_second": 6.464,
27
+ "step": 126
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.6101083032490975,
32
+ "eval_loss": 0.7722163200378418,
33
+ "eval_runtime": 5.213,
34
+ "eval_samples_per_second": 53.136,
35
+ "eval_steps_per_second": 6.714,
36
+ "step": 189
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 189,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 4,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 5.109701384755999e-05,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 4,
51
+ "seed": 30
52
+ }
53
+ }
run-0/checkpoint-189/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18eb21af817cd1d2204dbaf9c3bc9ecc35b910c052c9b05abc31b48ba41b1dfa
3
+ size 4920
runs/Mar10_13-32-58_4e3c1469116f/events.out.tfevents.1710078354.4e3c1469116f.2145.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6abd9c5f515f1a20477f725a4522bf3d63ef68799745a06c47af72cd446d4bed
3
- size 5079
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c704bd3852345a1c30075d90e13c66ea0e4fb3a0c686c76db96b42422f9269b2
3
+ size 6073