End of training
Browse files- README.md +12 -11
- config.json +20 -17
- merges.txt +0 -0
- model.safetensors +2 -2
- special_tokens_map.json +13 -5
- tokenizer.json +0 -0
- tokenizer_config.json +25 -23
- training_args.bin +2 -2
- vocab.json +0 -0
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# f1_score_model
|
20 |
|
21 |
-
This model is a fine-tuned version of [
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
- Accuracy: 0.
|
25 |
-
- F1: 0.
|
26 |
-
- Precision: 0.
|
27 |
-
- Recall: 0.
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -45,18 +45,19 @@ More information needed
|
|
45 |
The following hyperparameters were used during training:
|
46 |
- learning_rate: 5e-05
|
47 |
- train_batch_size: 16
|
48 |
-
- eval_batch_size:
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
|
|
52 |
- num_epochs: 5
|
|
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
58 |
-
| 0.
|
59 |
-
| 0.42 | 4.98 | 1000 | 0.7364 | 0.6454 | 0.5587 | 0.5154 | 0.6454 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: mit
|
3 |
+
base_model: roberta-large
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
18 |
|
19 |
# f1_score_model
|
20 |
|
21 |
+
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.6087
|
24 |
+
- Accuracy: 0.7016
|
25 |
+
- F1: 0.6217
|
26 |
+
- Precision: 0.5813
|
27 |
+
- Recall: 0.7016
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
45 |
The following hyperparameters were used during training:
|
46 |
- learning_rate: 5e-05
|
47 |
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 16
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_steps: 100
|
53 |
- num_epochs: 5
|
54 |
+
- mixed_precision_training: Native AMP
|
55 |
|
56 |
### Training results
|
57 |
|
58 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
59 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
60 |
+
| 0.4236 | 4.98 | 1000 | 0.6087 | 0.7016 | 0.6217 | 0.5813 | 0.7016 |
|
|
|
61 |
|
62 |
|
63 |
### Framework versions
|
config.json
CHANGED
@@ -1,13 +1,15 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
|
|
|
|
|
|
11 |
"id2label": {
|
12 |
"0": "llama",
|
13 |
"1": "mistral",
|
@@ -15,23 +17,24 @@
|
|
15 |
"3": "gpt4"
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
|
|
18 |
"label2id": {
|
19 |
"gpt3.5": 2,
|
20 |
"gpt4": 3,
|
21 |
"llama": 0,
|
22 |
"mistral": 1
|
23 |
},
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
|
|
|
|
29 |
"problem_type": "single_label_classification",
|
30 |
-
"qa_dropout": 0.1,
|
31 |
-
"seq_classif_dropout": 0.2,
|
32 |
-
"sinusoidal_pos_embds": false,
|
33 |
-
"tie_weights_": true,
|
34 |
"torch_dtype": "float32",
|
35 |
"transformers_version": "4.39.3",
|
36 |
-
"
|
|
|
|
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "roberta-large",
|
|
|
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": 1024,
|
13 |
"id2label": {
|
14 |
"0": "llama",
|
15 |
"1": "mistral",
|
|
|
17 |
"3": "gpt4"
|
18 |
},
|
19 |
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 4096,
|
21 |
"label2id": {
|
22 |
"gpt3.5": 2,
|
23 |
"gpt4": 3,
|
24 |
"llama": 0,
|
25 |
"mistral": 1
|
26 |
},
|
27 |
+
"layer_norm_eps": 1e-05,
|
28 |
+
"max_position_embeddings": 514,
|
29 |
+
"model_type": "roberta",
|
30 |
+
"num_attention_heads": 16,
|
31 |
+
"num_hidden_layers": 24,
|
32 |
+
"pad_token_id": 1,
|
33 |
+
"position_embedding_type": "absolute",
|
34 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
35 |
"torch_dtype": "float32",
|
36 |
"transformers_version": "4.39.3",
|
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
|
|
model.safetensors
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 sha256:739d1b4afbd730134024c130a2a4330cb9775e4ee043144eff1c6a662e38d807
|
3 |
+
size 1421503616
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,15 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
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
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,55 +1,57 @@
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
-
"normalized":
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
-
"normalized":
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
-
"normalized":
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
-
"normalized":
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "
|
37 |
-
"lstrip":
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
-
"cls_token": "
|
46 |
-
"
|
47 |
-
"
|
|
|
48 |
"model_max_length": 512,
|
49 |
-
"pad_token": "
|
50 |
-
"sep_token": "
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"unk_token": "[UNK]"
|
55 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
+
"content": "<s>",
|
6 |
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
"special": true
|
27 |
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
"rstrip": false,
|
33 |
"single_word": false,
|
34 |
"special": true
|
35 |
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
"normalized": false,
|
40 |
"rstrip": false,
|
41 |
"single_word": false,
|
42 |
"special": true
|
43 |
}
|
44 |
},
|
45 |
+
"bos_token": "<s>",
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
|
|
57 |
}
|
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 sha256:554a9ec1e94ad4ac4478dfe8245f5a5868283988276526e76d924e932aed756e
|
3 |
+
size 4856
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|