Hugging Face's logo

dahaludba
/
QSolver_Encoder_V3

Safetensors
Model card Files
xet
 Community
dahaludba commited on
Commit
1cb1225
·
verified ·
1 Parent(s): d28d92c

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. fold_3/checkpoint-252/config.json +39 -0
  2. fold_3/checkpoint-252/model.safetensors +3 -0
  3. fold_3/checkpoint-252/optimizer.pt +3 -0
  4. fold_3/checkpoint-252/rng_state.pth +3 -0
  5. fold_3/checkpoint-252/scaler.pt +3 -0
  6. fold_3/checkpoint-252/scheduler.pt +3 -0
  7. fold_3/checkpoint-252/tokenizer.json +0 -0
  8. fold_3/checkpoint-252/tokenizer_config.json +23 -0
  9. fold_3/checkpoint-252/trainer_state.json +86 -0
  10. fold_3/checkpoint-252/training_args.bin +3 -0
  11. fold_3/config.json +39 -0
  12. fold_3/model.safetensors +3 -0
  13. fold_3/tokenizer.json +0 -0
  14. fold_3/tokenizer_config.json +23 -0
  15. fold_3/training_args.bin +3 -0
fold_3/checkpoint-252/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,
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": "5.0.0",
36
+ "type_vocab_size": 0,
37
+ "use_cache": false,
38
+ "vocab_size": 128100
39
+ }
fold_3/checkpoint-252/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c53a01f9043c972f604b410bac96c173740125b292319ff0f9d5bb670a7f09a
3
+ size 1740300292
fold_3/checkpoint-252/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e0f99dc08a7500ca7ef90384088d1ea412c5baf1a7169b056a8aa1864174ee
3
+ size 1671490187
fold_3/checkpoint-252/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e31c84fe11257063200e9aacdedad8514d70deca669892c4ce2bd91113a9115
3
+ size 14645
fold_3/checkpoint-252/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c27c46a5ff565daa9e89101821c2b3070a6268134a42ebe693b152c5956a2c8c
3
+ size 1383
fold_3/checkpoint-252/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af9c1356e326784a89c8089b4439081c6e470f35afdc2b9e1c63f3619b624338
3
+ size 1465
fold_3/checkpoint-252/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
fold_3/checkpoint-252/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "mask_token": "[MASK]",
15
+ "model_max_length": 1000000000000000019884624838656,
16
+ "pad_token": "[PAD]",
17
+ "sep_token": "[SEP]",
18
+ "split_by_punct": false,
19
+ "tokenizer_class": "DebertaV2Tokenizer",
20
+ "unk_id": 3,
21
+ "unk_token": "[UNK]",
22
+ "vocab_type": "spm"
23
+ }
fold_3/checkpoint-252/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 252,
3
+ "best_metric": 0.7900477164280842,
4
+ "best_model_checkpoint": "/kaggle/working/QSolver_Checkpoints/deberta_v3_fold_3/checkpoint-252",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 252,
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_accuracy": 0.4498977505112474,
15
+ "eval_f1": 0.4413870389447442,
16
+ "eval_loss": 1.4270343780517578,
17
+ "eval_map@3": 0.5991820040899799,
18
+ "eval_precision": 0.4483585434173669,
19
+ "eval_recall": 0.4418649589933715,
20
+ "eval_runtime": 51.8674,
21
+ "eval_samples_per_second": 9.428,
22
+ "eval_steps_per_second": 2.371,
23
+ "step": 63
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "eval_accuracy": 0.6134969325153374,
28
+ "eval_f1": 0.6081310159061541,
29
+ "eval_loss": 1.059214472770691,
30
+ "eval_map@3": 0.7372188139059306,
31
+ "eval_precision": 0.6138877584291695,
32
+ "eval_recall": 0.6077554812337421,
33
+ "eval_runtime": 61.7422,
34
+ "eval_samples_per_second": 7.92,
35
+ "eval_steps_per_second": 1.992,
36
+ "step": 126
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "eval_accuracy": 0.6932515337423313,
41
+ "eval_f1": 0.6853729117240588,
42
+ "eval_loss": 0.7652155160903931,
43
+ "eval_map@3": 0.7886843899113835,
44
+ "eval_precision": 0.6853149695913245,
45
+ "eval_recall": 0.6890633290987184,
46
+ "eval_runtime": 51.662,
47
+ "eval_samples_per_second": 9.465,
48
+ "eval_steps_per_second": 2.381,
49
+ "step": 189
50
+ },
51
+ {
52
+ "epoch": 4.0,
53
+ "eval_accuracy": 0.6993865030674846,
54
+ "eval_f1": 0.6932874333974411,
55
+ "eval_loss": 0.732165515422821,
56
+ "eval_map@3": 0.7900477164280842,
57
+ "eval_precision": 0.6936313240423599,
58
+ "eval_recall": 0.6946762680079162,
59
+ "eval_runtime": 61.2298,
60
+ "eval_samples_per_second": 7.986,
61
+ "eval_steps_per_second": 2.009,
62
+ "step": 252
63
+ }
64
+ ],
65
+ "logging_steps": 500,
66
+ "max_steps": 252,
67
+ "num_input_tokens_seen": 0,
68
+ "num_train_epochs": 4,
69
+ "save_steps": 500,
70
+ "stateful_callbacks": {
71
+ "TrainerControl": {
72
+ "args": {
73
+ "should_epoch_stop": false,
74
+ "should_evaluate": false,
75
+ "should_log": false,
76
+ "should_save": true,
77
+ "should_training_stop": true
78
+ },
79
+ "attributes": {}
80
+ }
81
+ },
82
+ "total_flos": 6148847444760390.0,
83
+ "train_batch_size": 4,
84
+ "trial_name": null,
85
+ "trial_params": null
86
+ }
fold_3/checkpoint-252/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca20da43595962c65557c9f37ba8d0b0814efa2932c72691ee9f80163a56633
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,
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": "5.0.0",
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 sha256:4c53a01f9043c972f604b410bac96c173740125b292319ff0f9d5bb670a7f09a
3
+ size 1740300292
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 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "mask_token": "[MASK]",
15
+ "model_max_length": 1000000000000000019884624838656,
16
+ "pad_token": "[PAD]",
17
+ "sep_token": "[SEP]",
18
+ "split_by_punct": false,
19
+ "tokenizer_class": "DebertaV2Tokenizer",
20
+ "unk_id": 3,
21
+ "unk_token": "[UNK]",
22
+ "vocab_type": "spm"
23
+ }
fold_3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca20da43595962c65557c9f37ba8d0b0814efa2932c72691ee9f80163a56633
3
+ size 5265