MoaazZaki commited on
Commit
9fbae96
·
verified ·
1 Parent(s): 288a080

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
22
+ "pad_token_id": 0,
23
+ "problem_type": "regression",
24
+ "qa_dropout": 0.1,
25
+ "seq_classif_dropout": 0.2,
26
+ "sinusoidal_pos_embds": false,
27
+ "tie_weights_": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.37.2",
30
+ "vocab_size": 30522
31
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965f081bb1eff9b24703ed02e63bef4511da11ac4d83e9e7a933a09bec3dc884
3
+ size 267829484
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acc00e243ba94068a05798a8a07be5e125a3d531eed930246719287f33f7f3fb
3
+ size 535721146
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:092d2f972a1f28cb1c00640ede08ac30dce7070f5d0ec05807bc799821d96ce8
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52a6cd6601dbe63a1c2069f880cea16e3103bf5bb6777b6f72ba2fae94ba3ee1
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1093587726354599,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Sentiment/empathy/checkpoint-1336",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1336,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.75,
13
+ "learning_rate": 1.70059880239521e-05,
14
+ "loss": 0.1611,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.12247690558433533,
20
+ "eval_rmse": 0.34996700286865234,
21
+ "eval_runtime": 11.7325,
22
+ "eval_samples_per_second": 227.489,
23
+ "eval_steps_per_second": 14.234,
24
+ "step": 668
25
+ },
26
+ {
27
+ "epoch": 1.5,
28
+ "learning_rate": 1.4011976047904192e-05,
29
+ "loss": 0.107,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.1093587726354599,
35
+ "eval_rmse": 0.33069437742233276,
36
+ "eval_runtime": 11.9059,
37
+ "eval_samples_per_second": 224.174,
38
+ "eval_steps_per_second": 14.027,
39
+ "step": 1336
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 3340,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 5,
46
+ "save_steps": 500,
47
+ "total_flos": 729732809339508.0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a582e924ec2e3ebf018d592399c6a3f42f90953528ff4d6956e0c189a331ad47
3
+ size 4728
vocab.txt ADDED
The diff for this file is too large to render. See raw diff