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
3701d7b
·
verified ·
1 Parent(s): 3349f63

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. fold_3/checkpoint-504/config.json +39 -0
  2. fold_3/checkpoint-504/model.safetensors +3 -0
  3. fold_3/checkpoint-504/optimizer.pt +3 -0
  4. fold_3/checkpoint-504/rng_state.pth +3 -0
  5. fold_3/checkpoint-504/scheduler.pt +3 -0
  6. fold_3/checkpoint-504/tokenizer.json +0 -0
  7. fold_3/checkpoint-504/tokenizer_config.json +24 -0
  8. fold_3/checkpoint-504/trainer_state.json +77 -0
  9. fold_3/checkpoint-504/training_args.bin +3 -0
  10. fold_3/config.json +39 -0
  11. fold_3/model.safetensors +3 -0
  12. fold_3/tokenizer.json +0 -0
  13. fold_3/tokenizer_config.json +24 -0
  14. fold_3/training_args.bin +3 -0
fold_3/checkpoint-504/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_3/checkpoint-504/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1525960e2399baea4f6a55a0540642c69f01ecf9e574dce6aad697013869c63a
3
+ size 1740300340
fold_3/checkpoint-504/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0ffa40cf55e761a03ee03dd0a18755db585a16cf21676b1a59d4498af56bb99
3
+ size 1363634379
fold_3/checkpoint-504/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d206cab33ca47b9565f0808b93e235fae7c77e9060558903b4962b46160d8c91
3
+ size 14645
fold_3/checkpoint-504/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9021d6e5033b5e3863f554f46f02704e500a2d26ea9bdc5b876f8a1a26f001
3
+ size 1465
fold_3/checkpoint-504/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
fold_3/checkpoint-504/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_3/checkpoint-504/trainer_state.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 504,
3
+ "best_metric": 0.9870483980913429,
4
+ "best_model_checkpoint": "./deberta_v3_fold_3/checkpoint-504",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 504,
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": 1.132867455482483,
15
+ "eval_map@3": 0.7177914110429446,
16
+ "eval_runtime": 66.7481,
17
+ "eval_samples_per_second": 7.326,
18
+ "eval_steps_per_second": 7.326,
19
+ "step": 126
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 0.11986057460308075,
24
+ "eval_map@3": 0.9795501022494887,
25
+ "eval_runtime": 67.9102,
26
+ "eval_samples_per_second": 7.201,
27
+ "eval_steps_per_second": 7.201,
28
+ "step": 252
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_loss": 0.06871046870946884,
33
+ "eval_map@3": 0.985344239945467,
34
+ "eval_runtime": 68.3125,
35
+ "eval_samples_per_second": 7.158,
36
+ "eval_steps_per_second": 7.158,
37
+ "step": 378
38
+ },
39
+ {
40
+ "epoch": 3.970661362506216,
41
+ "grad_norm": 153.56666564941406,
42
+ "learning_rate": 2.1962072489860595e-09,
43
+ "loss": 9.9226845703125,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 4.0,
48
+ "eval_loss": 0.0618998222053051,
49
+ "eval_map@3": 0.9870483980913429,
50
+ "eval_runtime": 66.6534,
51
+ "eval_samples_per_second": 7.336,
52
+ "eval_steps_per_second": 7.336,
53
+ "step": 504
54
+ }
55
+ ],
56
+ "logging_steps": 500,
57
+ "max_steps": 504,
58
+ "num_input_tokens_seen": 0,
59
+ "num_train_epochs": 4,
60
+ "save_steps": 500,
61
+ "stateful_callbacks": {
62
+ "TrainerControl": {
63
+ "args": {
64
+ "should_epoch_stop": false,
65
+ "should_evaluate": false,
66
+ "should_log": false,
67
+ "should_save": true,
68
+ "should_training_stop": true
69
+ },
70
+ "attributes": {}
71
+ }
72
+ },
73
+ "total_flos": 4520100776172240.0,
74
+ "train_batch_size": 1,
75
+ "trial_name": null,
76
+ "trial_params": null
77
+ }
fold_3/checkpoint-504/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0842e964e6082b8c77e9329eb7c4114c160e2c5b5906c96717a81a43314cfce
3
+ size 5265
fold_3/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_3/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1525960e2399baea4f6a55a0540642c69f01ecf9e574dce6aad697013869c63a
3
+ size 1740300340
fold_3/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
fold_3/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_3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0842e964e6082b8c77e9329eb7c4114c160e2c5b5906c96717a81a43314cfce
3
+ size 5265