End of training
Browse files- README.md +75 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- merges.txt +0 -0
- runs/May26_15-23-51_49a6a009079d/events.out.tfevents.1716737036.49a6a009079d.1999.0 +3 -0
- runs/May26_15-23-51_49a6a009079d/events.out.tfevents.1716737145.49a6a009079d.1999.1 +3 -0
- special_tokens_map.json +12 -0
- tokenizer.json +0 -0
- tokenizer_config.json +28 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: openai-community/gpt2
|
7 |
+
datasets:
|
8 |
+
- financial_phrasebank
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: gpt2-sentiment_analysis
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# gpt2-sentiment_analysis
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the financial_phrasebank dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.7017
|
24 |
+
- Accuracy: {'accuracy': 0.8941548183254344}
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 0.0006
|
44 |
+
- train_batch_size: 4
|
45 |
+
- eval_batch_size: 1
|
46 |
+
- seed: 42
|
47 |
+
- gradient_accumulation_steps: 4
|
48 |
+
- total_train_batch_size: 16
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 10
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------:|
|
57 |
+
| No log | 1.0 | 224 | 0.4513 | {'accuracy': 0.8515007898894155} |
|
58 |
+
| No log | 2.0 | 448 | 0.3301 | {'accuracy': 0.8862559241706162} |
|
59 |
+
| 0.2776 | 3.0 | 672 | 0.3686 | {'accuracy': 0.8862559241706162} |
|
60 |
+
| 0.2776 | 4.0 | 896 | 0.3920 | {'accuracy': 0.8767772511848341} |
|
61 |
+
| 0.198 | 5.0 | 1120 | 0.3815 | {'accuracy': 0.8925750394944708} |
|
62 |
+
| 0.198 | 6.0 | 1344 | 0.5228 | {'accuracy': 0.8720379146919431} |
|
63 |
+
| 0.1346 | 7.0 | 1568 | 0.5616 | {'accuracy': 0.8846761453396524} |
|
64 |
+
| 0.1346 | 8.0 | 1792 | 0.5480 | {'accuracy': 0.9020537124802528} |
|
65 |
+
| 0.0823 | 9.0 | 2016 | 0.6681 | {'accuracy': 0.8957345971563981} |
|
66 |
+
| 0.0823 | 10.0 | 2240 | 0.7017 | {'accuracy': 0.8941548183254344} |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- PEFT 0.11.1
|
72 |
+
- Transformers 4.41.0
|
73 |
+
- Pytorch 2.3.0+cu121
|
74 |
+
- Datasets 2.19.1
|
75 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "openai-community/gpt2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": true,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.01,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"classifier",
|
19 |
+
"score"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 4,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"c_attn"
|
27 |
+
],
|
28 |
+
"task_type": "SEQ_CLS",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ef8c6ad24e02b3d3a27c2bfc4309659138290b08d1b8c185464a6a48037fac6
|
3 |
+
size 154994840
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 50257
|
3 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/May26_15-23-51_49a6a009079d/events.out.tfevents.1716737036.49a6a009079d.1999.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25588a1e606f0b5abeccce2026e1edeb577ea7d95cc519d44a36f86bc427dada
|
3 |
+
size 5317
|
runs/May26_15-23-51_49a6a009079d/events.out.tfevents.1716737145.49a6a009079d.1999.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d56a80bf47cdab24b29ccb96a87506ea110b87e9a0c27d804e83ab801065bab3
|
3 |
+
size 9274
|
special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": {
|
5 |
+
"content": "[PAD]",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"unk_token": "<|endoftext|>"
|
12 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"50257": {
|
13 |
+
"content": "[PAD]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"bos_token": "<|endoftext|>",
|
22 |
+
"clean_up_tokenization_spaces": true,
|
23 |
+
"eos_token": "<|endoftext|>",
|
24 |
+
"model_max_length": 1024,
|
25 |
+
"pad_token": "[PAD]",
|
26 |
+
"tokenizer_class": "GPT2Tokenizer",
|
27 |
+
"unk_token": "<|endoftext|>"
|
28 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cb966a637ff7f05257bc4b5803f981d143cc79ca10e744494a628c5bacb941c
|
3 |
+
size 5176
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|