Hank1 commited on
Commit
015acb8
·
verified ·
1 Parent(s): 93bcf0f

Upload 12 files

Browse files
deberta-stsb/checkpoint-450/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
11
+ "0": "LABEL_0"
12
+ },
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_norm_eps": 1e-07,
19
+ "max_position_embeddings": 512,
20
+ "max_relative_positions": -1,
21
+ "model_type": "deberta",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 0,
25
+ "pooler_dropout": 0,
26
+ "pooler_hidden_act": "gelu",
27
+ "pooler_hidden_size": 768,
28
+ "pos_att_type": [
29
+ "c2p",
30
+ "p2c"
31
+ ],
32
+ "position_biased_input": false,
33
+ "relative_attention": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.45.1",
36
+ "type_vocab_size": 0,
37
+ "vocab_size": 50265
38
+ }
deberta-stsb/checkpoint-450/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
deberta-stsb/checkpoint-450/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a735aa280a8abca09e48b0057d1197ce8bdc0cc90fb900dc6a6b5506b5c82eeb
3
+ size 556796484
deberta-stsb/checkpoint-450/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c46a715dd44a5a61e7572811a810160d66079a8242b418a4566fe41ed413d8
3
+ size 1113711994
deberta-stsb/checkpoint-450/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d748252177196c9efe875492295f648854d020617396eea74a236f94d2dce414
3
+ size 14244
deberta-stsb/checkpoint-450/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf5db410f8f00d30cc71b2b7e0ed0c1486c2c3b8a64a69bddc9b7fdb7d30ba0
3
+ size 1064
deberta-stsb/checkpoint-450/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-stsb/checkpoint-450/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
deberta-stsb/checkpoint-450/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-stsb/checkpoint-450/trainer_state.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9131636272366799,
3
+ "best_model_checkpoint": "./deberta/deberta-stsb/checkpoint-450",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 450,
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_averaged_scores": 0.8545315766143755,
14
+ "eval_loss": 0.6480135917663574,
15
+ "eval_pearson": 0.8519289493560791,
16
+ "eval_runtime": 1.1379,
17
+ "eval_samples_per_second": 1318.255,
18
+ "eval_spearmanr": 0.8571342038726719,
19
+ "eval_steps_per_second": 21.092,
20
+ "step": 90
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_averaged_scores": 0.8989097643646349,
25
+ "eval_loss": 0.4838252663612366,
26
+ "eval_pearson": 0.8992125988006592,
27
+ "eval_runtime": 1.1371,
28
+ "eval_samples_per_second": 1319.136,
29
+ "eval_spearmanr": 0.8986069299286105,
30
+ "eval_steps_per_second": 21.106,
31
+ "step": 180
32
+ },
33
+ {
34
+ "epoch": 3.0,
35
+ "eval_averaged_scores": 0.9043491429588992,
36
+ "eval_loss": 0.43187370896339417,
37
+ "eval_pearson": 0.9057629704475403,
38
+ "eval_runtime": 1.1376,
39
+ "eval_samples_per_second": 1318.617,
40
+ "eval_spearmanr": 0.9029353154702582,
41
+ "eval_steps_per_second": 21.098,
42
+ "step": 270
43
+ },
44
+ {
45
+ "epoch": 4.0,
46
+ "eval_averaged_scores": 0.9121713839626304,
47
+ "eval_loss": 0.38583260774612427,
48
+ "eval_pearson": 0.9131348133087158,
49
+ "eval_runtime": 1.139,
50
+ "eval_samples_per_second": 1316.892,
51
+ "eval_spearmanr": 0.911207954616545,
52
+ "eval_steps_per_second": 21.07,
53
+ "step": 360
54
+ },
55
+ {
56
+ "epoch": 5.0,
57
+ "eval_averaged_scores": 0.9131636272366799,
58
+ "eval_loss": 0.38374173641204834,
59
+ "eval_pearson": 0.9144770503044128,
60
+ "eval_runtime": 1.131,
61
+ "eval_samples_per_second": 1326.287,
62
+ "eval_spearmanr": 0.9118502041689468,
63
+ "eval_steps_per_second": 21.221,
64
+ "step": 450
65
+ }
66
+ ],
67
+ "logging_steps": 500,
68
+ "max_steps": 450,
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": 1329732285582624.0,
85
+ "train_batch_size": 64,
86
+ "trial_name": null,
87
+ "trial_params": null
88
+ }
deberta-stsb/checkpoint-450/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1ce1d99dda8d54f7a7d618c57d19e47ef5f7aba15a4bb4ba0a4c174e816d906
3
+ size 5176
deberta-stsb/checkpoint-450/vocab.json ADDED
The diff for this file is too large to render. See raw diff