Hugging Face's logo

dahaludba
/
QSolver_Encoder_V2

Text Classification
Transformers
Safetensors
deberta
deberta-v3
multiple-choice
question-answering
awp
Model card Files
xet
 Community
dahaludba commited on
Commit
3349f63
·
verified ·
1 Parent(s): d7841aa

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. fold_2/checkpoint-378/config.json +39 -0
  2. fold_2/checkpoint-378/model.safetensors +3 -0
  3. fold_2/checkpoint-378/optimizer.pt +3 -0
  4. fold_2/checkpoint-378/rng_state.pth +3 -0
  5. fold_2/checkpoint-378/scheduler.pt +3 -0
  6. fold_2/checkpoint-378/tokenizer.json +0 -0
  7. fold_2/checkpoint-378/tokenizer_config.json +24 -0
  8. fold_2/checkpoint-378/trainer_state.json +61 -0
  9. fold_2/checkpoint-378/training_args.bin +3 -0
  10. fold_2/config.json +39 -0
  11. fold_2/model.safetensors +3 -0
  12. fold_2/tokenizer.json +0 -0
  13. fold_2/tokenizer_config.json +24 -0
  14. fold_2/training_args.bin +3 -0
fold_2/checkpoint-378/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForMultipleChoice"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "dtype": "float32",
8
+ "eos_token_id": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-07,
15
+ "legacy": true,
16
+ "max_position_embeddings": 512,
17
+ "max_relative_positions": -1,
18
+ "model_type": "deberta-v2",
19
+ "norm_rel_ebd": "layer_norm",
20
+ "num_attention_heads": 16,
21
+ "num_hidden_layers": 24,
22
+ "pad_token_id": 0,
23
+ "pooler_dropout": 0.0,
24
+ "pooler_hidden_act": "gelu",
25
+ "pooler_hidden_size": 1024,
26
+ "pos_att_type": [
27
+ "p2c",
28
+ "c2p"
29
+ ],
30
+ "position_biased_input": false,
31
+ "position_buckets": 256,
32
+ "relative_attention": true,
33
+ "share_att_key": true,
34
+ "tie_word_embeddings": true,
35
+ "transformers_version": "5.10.1",
36
+ "type_vocab_size": 0,
37
+ "use_cache": false,
38
+ "vocab_size": 128100
39
+ }
fold_2/checkpoint-378/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ee4017193a3e002c08e6d1cd1749499cbcecee297600f55773352555a48b6a2
3
+ size 1740300340
fold_2/checkpoint-378/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea86c2834bcd489c40766050836b1b43ef3d90ba1a23e9777889f10b788f6cd
3
+ size 1363634379
fold_2/checkpoint-378/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cbaf91cf065c77ed1572a95288b2c544cb381ec1a7eeade2e7668cfe91750a2
3
+ size 14645
fold_2/checkpoint-378/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1ad87fb5ffb4f4078154bb7dc6b333b6316f79829c8cf14a9bd10e2c920208b
3
+ size 1465
fold_2/checkpoint-378/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
fold_2/checkpoint-378/tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "extra_special_tokens": [
9
+ "[PAD]",
10
+ "[CLS]",
11
+ "[SEP]"
12
+ ],
13
+ "is_local": false,
14
+ "local_files_only": false,
15
+ "mask_token": "[MASK]",
16
+ "model_max_length": 1000000000000000019884624838656,
17
+ "pad_token": "[PAD]",
18
+ "sep_token": "[SEP]",
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }
fold_2/checkpoint-378/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 378,
3
+ "best_metric": 0.9938650306748467,
4
+ "best_model_checkpoint": "/content/drive/MyDrive/QSolver_Checkpoints/deberta_v3_fold_2/checkpoint-378",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 378,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_loss": 0.5386627316474915,
15
+ "eval_map@3": 0.9287661895023858,
16
+ "eval_runtime": 69.0607,
17
+ "eval_samples_per_second": 7.081,
18
+ "eval_steps_per_second": 7.081,
19
+ "step": 126
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 0.16380318999290466,
24
+ "eval_map@3": 0.9890933878663939,
25
+ "eval_runtime": 69.8564,
26
+ "eval_samples_per_second": 7.0,
27
+ "eval_steps_per_second": 7.0,
28
+ "step": 252
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_loss": 0.09429844468832016,
33
+ "eval_map@3": 0.9938650306748467,
34
+ "eval_runtime": 69.4963,
35
+ "eval_samples_per_second": 7.036,
36
+ "eval_steps_per_second": 7.036,
37
+ "step": 378
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 504,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 4,
44
+ "save_steps": 500,
45
+ "stateful_callbacks": {
46
+ "TrainerControl": {
47
+ "args": {
48
+ "should_epoch_stop": false,
49
+ "should_evaluate": false,
50
+ "should_log": false,
51
+ "should_save": true,
52
+ "should_training_stop": false
53
+ },
54
+ "attributes": {}
55
+ }
56
+ },
57
+ "total_flos": 3384342000695880.0,
58
+ "train_batch_size": 1,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
fold_2/checkpoint-378/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e4217a8c9e5660caeb65585c37f36af756ac270a9b711f48a8ee2410c50552
3
+ size 5265
fold_2/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForMultipleChoice"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "dtype": "float32",
8
+ "eos_token_id": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-07,
15
+ "legacy": true,
16
+ "max_position_embeddings": 512,
17
+ "max_relative_positions": -1,
18
+ "model_type": "deberta-v2",
19
+ "norm_rel_ebd": "layer_norm",
20
+ "num_attention_heads": 16,
21
+ "num_hidden_layers": 24,
22
+ "pad_token_id": 0,
23
+ "pooler_dropout": 0.0,
24
+ "pooler_hidden_act": "gelu",
25
+ "pooler_hidden_size": 1024,
26
+ "pos_att_type": [
27
+ "p2c",
28
+ "c2p"
29
+ ],
30
+ "position_biased_input": false,
31
+ "position_buckets": 256,
32
+ "relative_attention": true,
33
+ "share_att_key": true,
34
+ "tie_word_embeddings": true,
35
+ "transformers_version": "5.10.1",
36
+ "type_vocab_size": 0,
37
+ "use_cache": false,
38
+ "vocab_size": 128100
39
+ }
fold_2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ee4017193a3e002c08e6d1cd1749499cbcecee297600f55773352555a48b6a2
3
+ size 1740300340
fold_2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
fold_2/tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "extra_special_tokens": [
9
+ "[PAD]",
10
+ "[CLS]",
11
+ "[SEP]"
12
+ ],
13
+ "is_local": false,
14
+ "local_files_only": false,
15
+ "mask_token": "[MASK]",
16
+ "model_max_length": 1000000000000000019884624838656,
17
+ "pad_token": "[PAD]",
18
+ "sep_token": "[SEP]",
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }
fold_2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e4217a8c9e5660caeb65585c37f36af756ac270a9b711f48a8ee2410c50552
3
+ size 5265