StevenLimcorn commited on
Commit
3917d9d
1 Parent(s): 989d49f

Upload 10 files

Browse files
config.json CHANGED
@@ -1,11 +1,10 @@
1
  {
2
- "_name_or_path": "/content/content/result/unsup-simcse-roberta-large-semeval2015-restaurants",
3
  "architectures": [
4
  "RobertaModel"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "bos_token_id": 0,
8
- "classifier_dropout": null,
9
  "eos_token_id": 2,
10
  "gradient_checkpointing": false,
11
  "hidden_act": "gelu",
@@ -20,8 +19,8 @@
20
  "num_hidden_layers": 24,
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
- "transformers_version": "4.28.1",
24
  "type_vocab_size": 1,
25
  "use_cache": true,
26
  "vocab_size": 50265
27
- }
 
1
  {
2
+ "_name_or_path": "/content/result/unsup-simcse-roberta-large-semeval2015-restaurants",
3
  "architectures": [
4
  "RobertaModel"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "bos_token_id": 0,
 
8
  "eos_token_id": 2,
9
  "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
 
19
  "num_hidden_layers": 24,
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
+ "transformers_version": "4.2.1",
23
  "type_vocab_size": 1,
24
  "use_cache": true,
25
  "vocab_size": 50265
26
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47afe8a496c33c3677030ee0c8c9d02dd668c8be61fc2847dad0611754218b6f
3
+ size 2843107269
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816824eef0b30aca16c9c8bf778a070ad11132c4a3f7fb39b11b4a068742f12f
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "princeton-nlp/unsup-simcse-roberta-large", "special_tokens_map_file": "/root/.cache/huggingface/transformers/6d59ec8e128c32fbf5663dad4484f60104c7f3b2520047fbaf57bc63b260e0fd.a11ebb04664c067c8fe5ef8f8068b0f721263414a26058692f7b2e4ba2a1b342"}
train_results.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch = 30.0
2
+ train_runtime = 1315.4897
3
+ train_samples_per_second = 0.479
trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8174784417008615,
3
+ "best_model_checkpoint": "/content/result/unsup-simcse-roberta-large-semeval2015-restaurants",
4
+ "epoch": 30.0,
5
+ "global_step": 630,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 5.95,
12
+ "eval_avg_sts": 0.7717928358908008,
13
+ "eval_sickr_spearman": 0.7292140418278018,
14
+ "eval_stsb_spearman": 0.8143716299538,
15
+ "step": 125
16
+ },
17
+ {
18
+ "epoch": 11.9,
19
+ "eval_avg_sts": 0.7791621837441685,
20
+ "eval_sickr_spearman": 0.7408459257874753,
21
+ "eval_stsb_spearman": 0.8174784417008615,
22
+ "step": 250
23
+ },
24
+ {
25
+ "epoch": 17.86,
26
+ "eval_avg_sts": 0.7722792956470997,
27
+ "eval_sickr_spearman": 0.7383406235364633,
28
+ "eval_stsb_spearman": 0.8062179677577361,
29
+ "step": 375
30
+ },
31
+ {
32
+ "epoch": 23.81,
33
+ "learning_rate": 1.0317460317460318e-05,
34
+ "loss": 0.0021,
35
+ "step": 500
36
+ },
37
+ {
38
+ "epoch": 23.81,
39
+ "eval_avg_sts": 0.7703133775062114,
40
+ "eval_sickr_spearman": 0.7341789207212567,
41
+ "eval_stsb_spearman": 0.8064478342911661,
42
+ "step": 500
43
+ },
44
+ {
45
+ "epoch": 29.76,
46
+ "eval_avg_sts": 0.7706719031560307,
47
+ "eval_sickr_spearman": 0.7343738789619939,
48
+ "eval_stsb_spearman": 0.8069699273500677,
49
+ "step": 625
50
+ },
51
+ {
52
+ "epoch": 30.0,
53
+ "step": 630,
54
+ "train_runtime": 1315.4897,
55
+ "train_samples_per_second": 0.479
56
+ }
57
+ ],
58
+ "max_steps": 630,
59
+ "num_train_epochs": 30,
60
+ "total_flos": 5382182024773632,
61
+ "trial_name": null,
62
+ "trial_params": null
63
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a30788ba4a0f336e040868da72d8dbebc7333a6cb7b34339aa8cc8e2dafd1440
3
+ size 2107
vocab.json ADDED
The diff for this file is too large to render. See raw diff