End of training
Browse files- README.md +17 -13
- config.json +32 -14
- model.safetensors +2 -2
- tokenizer.json +6 -1
- tokenizer_config.json +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# Classify-model-v1.2
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,24 +37,28 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- learning_rate:
|
41 |
- train_batch_size: 128
|
42 |
- eval_batch_size: 128
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
-
| 1.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
|
|
|
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: Alibaba-NLP/gte-base-en-v1.5
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
15 |
|
16 |
# Classify-model-v1.2
|
17 |
|
18 |
+
This model is a fine-tuned version of [Alibaba-NLP/gte-base-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-base-en-v1.5) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2915
|
21 |
+
- Accuracy: 0.9375
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
- train_batch_size: 128
|
42 |
- eval_batch_size: 128
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 10
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| 1.0241 | 1.0 | 11 | 0.3903 | 0.8482 |
|
53 |
+
| 0.2103 | 2.0 | 22 | 0.2814 | 0.8929 |
|
54 |
+
| 0.0637 | 3.0 | 33 | 0.2157 | 0.9196 |
|
55 |
+
| 0.023 | 4.0 | 44 | 0.2686 | 0.9375 |
|
56 |
+
| 0.0147 | 5.0 | 55 | 0.3088 | 0.9286 |
|
57 |
+
| 0.0091 | 6.0 | 66 | 0.2554 | 0.9375 |
|
58 |
+
| 0.0055 | 7.0 | 77 | 0.2785 | 0.9464 |
|
59 |
+
| 0.0054 | 8.0 | 88 | 0.2852 | 0.9464 |
|
60 |
+
| 0.0033 | 9.0 | 99 | 0.2899 | 0.9375 |
|
61 |
+
| 0.0034 | 10.0 | 110 | 0.2915 | 0.9375 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
config.json
CHANGED
@@ -1,14 +1,22 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
"classifier_dropout": null,
|
8 |
-
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size":
|
12 |
"id2label": {
|
13 |
"0": "LABEL_0",
|
14 |
"1": "LABEL_1",
|
@@ -18,7 +26,7 @@
|
|
18 |
"5": "LABEL_5"
|
19 |
},
|
20 |
"initializer_range": 0.02,
|
21 |
-
"intermediate_size":
|
22 |
"label2id": {
|
23 |
"LABEL_0": 0,
|
24 |
"LABEL_1": 1,
|
@@ -28,16 +36,26 @@
|
|
28 |
"LABEL_5": 5
|
29 |
},
|
30 |
"layer_norm_eps": 1e-12,
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
|
|
|
|
|
|
|
|
35 |
"pad_token_id": 0,
|
36 |
-
"position_embedding_type": "
|
37 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
|
|
38 |
"torch_dtype": "float32",
|
39 |
"transformers_version": "4.39.3",
|
40 |
-
"type_vocab_size":
|
41 |
-
"
|
42 |
-
"
|
|
|
43 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Alibaba-NLP/gte-base-en-v1.5",
|
3 |
"architectures": [
|
4 |
+
"NewForSequenceClassification"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
|
9 |
+
"AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
|
10 |
+
"AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
|
11 |
+
"AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
|
12 |
+
"AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
|
13 |
+
"AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
|
14 |
+
"AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
|
15 |
+
},
|
16 |
"classifier_dropout": null,
|
|
|
17 |
"hidden_act": "gelu",
|
18 |
"hidden_dropout_prob": 0.1,
|
19 |
+
"hidden_size": 768,
|
20 |
"id2label": {
|
21 |
"0": "LABEL_0",
|
22 |
"1": "LABEL_1",
|
|
|
26 |
"5": "LABEL_5"
|
27 |
},
|
28 |
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
"label2id": {
|
31 |
"LABEL_0": 0,
|
32 |
"LABEL_1": 1,
|
|
|
36 |
"LABEL_5": 5
|
37 |
},
|
38 |
"layer_norm_eps": 1e-12,
|
39 |
+
"layer_norm_type": "layer_norm",
|
40 |
+
"logn_attention_clip1": false,
|
41 |
+
"logn_attention_scale": false,
|
42 |
+
"max_position_embeddings": 8192,
|
43 |
+
"model_type": "new",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"pack_qkv": true,
|
47 |
"pad_token_id": 0,
|
48 |
+
"position_embedding_type": "rope",
|
49 |
"problem_type": "single_label_classification",
|
50 |
+
"rope_scaling": {
|
51 |
+
"factor": 2.0,
|
52 |
+
"type": "ntk"
|
53 |
+
},
|
54 |
+
"rope_theta": 500000,
|
55 |
"torch_dtype": "float32",
|
56 |
"transformers_version": "4.39.3",
|
57 |
+
"type_vocab_size": 0,
|
58 |
+
"unpad_inputs": false,
|
59 |
+
"use_memory_efficient_attention": false,
|
60 |
+
"vocab_size": 30528
|
61 |
}
|
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:c31e825e54b9bc4da41f2280d716d3286424790d8ccf226186bcdbc3e11665b1
|
3 |
+
size 549500832
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": {
|
5 |
"strategy": "BatchLongest",
|
6 |
"direction": "Right",
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 32768,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": {
|
10 |
"strategy": "BatchLongest",
|
11 |
"direction": "Right",
|
tokenizer_config.json
CHANGED
@@ -45,8 +45,8 @@
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
-
"max_length":
|
49 |
-
"model_max_length":
|
50 |
"pad_to_multiple_of": null,
|
51 |
"pad_token": "[PAD]",
|
52 |
"pad_token_type_id": 0,
|
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
+
"max_length": 512,
|
49 |
+
"model_max_length": 32768,
|
50 |
"pad_to_multiple_of": null,
|
51 |
"pad_token": "[PAD]",
|
52 |
"pad_token_type_id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2395a8c853e5d942df02a2e4b72617394e866cff32ac8e120dd6945f715fc162
|
3 |
size 4984
|