lunadebruyne commited on
Commit
ab74a13
·
1 Parent(s): e15782a

Upload 12 files

Browse files
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "neutral",
15
+ "1": "negative",
16
+ "2": "positive",
17
+ "3": "mixed"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "mixed": 3,
23
+ "negative": 1,
24
+ "neutral": 0,
25
+ "positive": 2
26
+ },
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 514,
29
+ "model_type": "roberta",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.26.0",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 50265
40
+ }
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:a862a3be10271222757d93494fd739e5a15a80078de188303f5af32a30faf6b9
3
+ size 997307525
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ddb00080f7ca5a10381085576d489fd851855e23af91845701c67318d50a1e9
3
+ size 498668213
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027520a9e705032c52cc3d9663df0311b0b3861cdd8a5d18da378958ce4176ff
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4387d19a8a5fb8a326edf5b49054330d8cceb0d6cfbb92ef2d7b98b241ec97f
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "roberta-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
trainer_state.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 372,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_accuracy": 0.7098515519568152,
13
+ "eval_loss": 0.7508555054664612,
14
+ "eval_runtime": 10.6543,
15
+ "eval_samples_per_second": 139.098,
16
+ "eval_steps_per_second": 11.638,
17
+ "step": 124
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_accuracy": 0.8191632928475033,
22
+ "eval_loss": 0.5076887607574463,
23
+ "eval_runtime": 10.6958,
24
+ "eval_samples_per_second": 138.559,
25
+ "eval_steps_per_second": 11.593,
26
+ "step": 248
27
+ },
28
+ {
29
+ "epoch": 3.0,
30
+ "eval_accuracy": 0.8778677462887989,
31
+ "eval_loss": 0.36516618728637695,
32
+ "eval_runtime": 10.7463,
33
+ "eval_samples_per_second": 137.907,
34
+ "eval_steps_per_second": 11.539,
35
+ "step": 372
36
+ }
37
+ ],
38
+ "max_steps": 372,
39
+ "num_train_epochs": 3,
40
+ "total_flos": 877359568730112.0,
41
+ "trial_name": null,
42
+ "trial_params": null
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7511dad61dba1da01c022d2a1738bb415d035c835e6ca451953c851dbecaece1
3
+ size 3515
vocab.json ADDED
The diff for this file is too large to render. See raw diff