Hugging Face's logo

Hank1
/
deberta_glue

Safetensors
Model card Files
xet
 Community
Hank1 commited on
Commit
2a40d39
·
verified ·
1 Parent(s): 83583de

Upload 12 files

Browse files
Files changed (12) hide show
  1. deberta-mrpc/deberta-mrpc/checkpoint-290/config.json +32 -0
  2. deberta-mrpc/deberta-mrpc/checkpoint-290/merges.txt +0 -0
  3. deberta-mrpc/deberta-mrpc/checkpoint-290/model.safetensors +3 -0
  4. deberta-mrpc/deberta-mrpc/checkpoint-290/optimizer.pt +3 -0
  5. deberta-mrpc/deberta-mrpc/checkpoint-290/rng_state.pth +3 -0
  6. deberta-mrpc/deberta-mrpc/checkpoint-290/scheduler.pt +3 -0
  7. deberta-mrpc/deberta-mrpc/checkpoint-290/special_tokens_map.json +51 -0
  8. deberta-mrpc/deberta-mrpc/checkpoint-290/tokenizer.json +0 -0
  9. deberta-mrpc/deberta-mrpc/checkpoint-290/tokenizer_config.json +59 -0
  10. deberta-mrpc/deberta-mrpc/checkpoint-290/trainer_state.json +88 -0
  11. deberta-mrpc/deberta-mrpc/checkpoint-290/training_args.bin +3 -0
  12. deberta-mrpc/deberta-mrpc/checkpoint-290/vocab.json +0 -0
deberta-mrpc/deberta-mrpc/checkpoint-290/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/ibex/user/anb/Model_merging/EMR_Merging-main/merge_lm/ckpts/deberta/deberta-base",
3
+ "architectures": [
4
+ "DebertaForSequenceClassification"
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",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "pooler_dropout": 0,
20
+ "pooler_hidden_act": "gelu",
21
+ "pooler_hidden_size": 768,
22
+ "pos_att_type": [
23
+ "c2p",
24
+ "p2c"
25
+ ],
26
+ "position_biased_input": false,
27
+ "relative_attention": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.45.1",
30
+ "type_vocab_size": 0,
31
+ "vocab_size": 50265
32
+ }
deberta-mrpc/deberta-mrpc/checkpoint-290/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
deberta-mrpc/deberta-mrpc/checkpoint-290/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9e10180b5b94aac8092ad91e1b3c8abadd6d79b44bd4fd89d5ad78487180cb
3
+ size 556799560
deberta-mrpc/deberta-mrpc/checkpoint-290/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc737b514a082a4924896a5f60427acd8ea0231edffea8eb9c0c27a8e3045476
3
+ size 1113718138
deberta-mrpc/deberta-mrpc/checkpoint-290/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c2176dc0264d27cb1cf29b64246fd9eb57c1bed7b0f1d32542168e68ee0bc5
3
+ size 14244
deberta-mrpc/deberta-mrpc/checkpoint-290/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adadf38b18962211e1ec1e333d9be8fa24b2c8a37782971f9db54aa771f3b761
3
+ size 1064
deberta-mrpc/deberta-mrpc/checkpoint-290/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
deberta-mrpc/deberta-mrpc/checkpoint-290/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
deberta-mrpc/deberta-mrpc/checkpoint-290/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "[PAD]",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "[CLS]",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "[SEP]",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "[UNK]",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50264": {
38
+ "content": "[MASK]",
39
+ "lstrip": true,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "bos_token": "[CLS]",
47
+ "clean_up_tokenization_spaces": false,
48
+ "cls_token": "[CLS]",
49
+ "do_lower_case": false,
50
+ "eos_token": "[SEP]",
51
+ "errors": "replace",
52
+ "mask_token": "[MASK]",
53
+ "model_max_length": 1000000000000000019884624838656,
54
+ "pad_token": "[PAD]",
55
+ "sep_token": "[SEP]",
56
+ "tokenizer_class": "DebertaTokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "gpt2"
59
+ }
deberta-mrpc/deberta-mrpc/checkpoint-290/trainer_state.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.907209173422019,
3
+ "best_model_checkpoint": "./deberta/deberta-mrpc/checkpoint-290",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 290,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.7083333333333334,
14
+ "eval_averaged_scores": 0.7660185185185185,
15
+ "eval_f1": 0.8237037037037037,
16
+ "eval_loss": 0.546708881855011,
17
+ "eval_runtime": 0.4159,
18
+ "eval_samples_per_second": 981.121,
19
+ "eval_steps_per_second": 16.833,
20
+ "step": 58
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.803921568627451,
25
+ "eval_averaged_scores": 0.8273339186420837,
26
+ "eval_f1": 0.8507462686567164,
27
+ "eval_loss": 0.46364083886146545,
28
+ "eval_runtime": 0.4167,
29
+ "eval_samples_per_second": 979.022,
30
+ "eval_steps_per_second": 16.797,
31
+ "step": 116
32
+ },
33
+ {
34
+ "epoch": 3.0,
35
+ "eval_accuracy": 0.8823529411764706,
36
+ "eval_averaged_scores": 0.8993646238983398,
37
+ "eval_f1": 0.9163763066202091,
38
+ "eval_loss": 0.2826736867427826,
39
+ "eval_runtime": 0.4158,
40
+ "eval_samples_per_second": 981.359,
41
+ "eval_steps_per_second": 16.837,
42
+ "step": 174
43
+ },
44
+ {
45
+ "epoch": 4.0,
46
+ "eval_accuracy": 0.875,
47
+ "eval_averaged_scores": 0.893458549222798,
48
+ "eval_f1": 0.9119170984455959,
49
+ "eval_loss": 0.30712682008743286,
50
+ "eval_runtime": 0.4166,
51
+ "eval_samples_per_second": 979.24,
52
+ "eval_steps_per_second": 16.801,
53
+ "step": 232
54
+ },
55
+ {
56
+ "epoch": 5.0,
57
+ "eval_accuracy": 0.8921568627450981,
58
+ "eval_averaged_scores": 0.907209173422019,
59
+ "eval_f1": 0.9222614840989399,
60
+ "eval_loss": 0.29480111598968506,
61
+ "eval_runtime": 0.4263,
62
+ "eval_samples_per_second": 957.128,
63
+ "eval_steps_per_second": 16.421,
64
+ "step": 290
65
+ }
66
+ ],
67
+ "logging_steps": 500,
68
+ "max_steps": 290,
69
+ "num_input_tokens_seen": 0,
70
+ "num_train_epochs": 5,
71
+ "save_steps": 500,
72
+ "stateful_callbacks": {
73
+ "TrainerControl": {
74
+ "args": {
75
+ "should_epoch_stop": false,
76
+ "should_evaluate": false,
77
+ "should_log": false,
78
+ "should_save": true,
79
+ "should_training_stop": true
80
+ },
81
+ "attributes": {}
82
+ }
83
+ },
84
+ "total_flos": 913349457524640.0,
85
+ "train_batch_size": 64,
86
+ "trial_name": null,
87
+ "trial_params": null
88
+ }
deberta-mrpc/deberta-mrpc/checkpoint-290/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9268806a9f3d89b0d9386aad6f8bd923683cf014a47556297dd4ea4431b8b6
3
+ size 5176
deberta-mrpc/deberta-mrpc/checkpoint-290/vocab.json ADDED
The diff for this file is too large to render. See raw diff