dardem commited on
Commit
204d932
1 Parent(s): d89c569

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-multilingual-cased",
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "output_past": true,
17
+ "pad_token_id": 0,
18
+ "problem_type": "single_label_classification",
19
+ "qa_dropout": 0.1,
20
+ "seq_classif_dropout": 0.2,
21
+ "sinusoidal_pos_embds": false,
22
+ "tie_weights_": true,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.35.0",
25
+ "vocab_size": 119547
26
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ff13a08d2ab763e5c9dadfb7435d39eb4ff164ceadbe5bea7d494317d35915
3
+ size 541317368
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd95026e7dc6f2b25f557896b7ea771670a7a0c142eea1ef17f8557fddae3d0
3
+ size 1082696890
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d81779f87dcc2a43431e0380eec9e1d65c0d3f1a8b42f8cc3eed93481cd63f79
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e19aec562275e412c44374390de345bac40442f41f6b6c61719c88a1d6efda0
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": false,
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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2531541883945465,
3
+ "best_model_checkpoint": "geotrend-mdistill-bert-all-finetuned-toxicity-classification/checkpoint-1126",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1689,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.89,
13
+ "learning_rate": 1.4079336885731204e-05,
14
+ "loss": 0.4604,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.28258055448532104,
20
+ "eval_runtime": 2.7146,
21
+ "eval_samples_per_second": 184.188,
22
+ "eval_steps_per_second": 23.208,
23
+ "step": 563
24
+ },
25
+ {
26
+ "epoch": 1.78,
27
+ "learning_rate": 8.158673771462404e-06,
28
+ "loss": 0.2476,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_loss": 0.2531541883945465,
34
+ "eval_runtime": 2.7258,
35
+ "eval_samples_per_second": 183.43,
36
+ "eval_steps_per_second": 23.112,
37
+ "step": 1126
38
+ },
39
+ {
40
+ "epoch": 2.66,
41
+ "learning_rate": 2.238010657193606e-06,
42
+ "loss": 0.1753,
43
+ "step": 1500
44
+ },
45
+ {
46
+ "epoch": 3.0,
47
+ "eval_loss": 0.34129810333251953,
48
+ "eval_runtime": 2.695,
49
+ "eval_samples_per_second": 185.527,
50
+ "eval_steps_per_second": 23.376,
51
+ "step": 1689
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 1689,
56
+ "num_train_epochs": 3,
57
+ "save_steps": 500,
58
+ "total_flos": 1788309881856000.0,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c73a2804fd5213697ca7555fcbc99623ee1ae9be58a8d04194b7208b75ac2f1
3
+ size 4664
vocab.txt ADDED
The diff for this file is too large to render. See raw diff