jorgeduardo13
commited on
Commit
•
bcb4fdb
1
Parent(s):
535c0e1
Training in progress, step 500
Browse files- all_results.json +13 -0
- config.json +21 -19
- eval_results.json +9 -0
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- train_results.json +7 -0
- training_args.bin +2 -2
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 1.0,
|
4 |
+
"eval_f1": 1.0,
|
5 |
+
"eval_loss": 0.006119730416685343,
|
6 |
+
"eval_runtime": 2.5371,
|
7 |
+
"eval_samples_per_second": 52.422,
|
8 |
+
"eval_steps_per_second": 6.7,
|
9 |
+
"train_loss": 0.05274554564402654,
|
10 |
+
"train_runtime": 171.5238,
|
11 |
+
"train_samples_per_second": 30.142,
|
12 |
+
"train_steps_per_second": 3.79
|
13 |
+
}
|
config.json
CHANGED
@@ -1,34 +1,36 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0.
|
7 |
-
"
|
|
|
|
|
8 |
"hidden_act": "gelu",
|
9 |
-
"hidden_dropout_prob": 0.
|
10 |
"hidden_size": 768,
|
11 |
"id2label": {
|
12 |
-
"0": "
|
13 |
-
"1": "
|
14 |
-
"2": "healthy"
|
15 |
},
|
16 |
-
"image_size": 224,
|
17 |
"initializer_range": 0.02,
|
18 |
"intermediate_size": 3072,
|
19 |
"label2id": {
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"healthy": "2"
|
23 |
},
|
24 |
-
"layer_norm_eps": 1e-
|
25 |
-
"
|
|
|
26 |
"num_attention_heads": 12,
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
"problem_type": "single_label_classification",
|
31 |
-
"qkv_bias": true,
|
32 |
"torch_dtype": "float32",
|
33 |
-
"transformers_version": "4.32.1"
|
|
|
|
|
|
|
34 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilroberta-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": "not_equivalent",
|
15 |
+
"1": "equivalent"
|
|
|
16 |
},
|
|
|
17 |
"initializer_range": 0.02,
|
18 |
"intermediate_size": 3072,
|
19 |
"label2id": {
|
20 |
+
"equivalent": "1",
|
21 |
+
"not_equivalent": "0"
|
|
|
22 |
},
|
23 |
+
"layer_norm_eps": 1e-05,
|
24 |
+
"max_position_embeddings": 514,
|
25 |
+
"model_type": "roberta",
|
26 |
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 6,
|
28 |
+
"pad_token_id": 1,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
"problem_type": "single_label_classification",
|
|
|
31 |
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.32.1",
|
33 |
+
"type_vocab_size": 1,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 50265
|
36 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 1.0,
|
4 |
+
"eval_f1": 1.0,
|
5 |
+
"eval_loss": 0.006119730416685343,
|
6 |
+
"eval_runtime": 2.5371,
|
7 |
+
"eval_samples_per_second": 52.422,
|
8 |
+
"eval_steps_per_second": 6.7
|
9 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a046a1225b02c72702c7f9b18120e954d7518bbc429031d0dadfd3cf7acacc6
|
3 |
+
size 328515505
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"errors": "replace",
|
8 |
+
"mask_token": "<mask>",
|
9 |
+
"model_max_length": 512,
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"tokenizer_class": "RobertaTokenizer",
|
13 |
+
"trim_offsets": true,
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.05274554564402654,
|
4 |
+
"train_runtime": 171.5238,
|
5 |
+
"train_samples_per_second": 30.142,
|
6 |
+
"train_steps_per_second": 3.79
|
7 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38571518a8a7557f51288a64f469421376861e2dc9316bf723f47c364016f0ae
|
3 |
+
size 4091
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|