Holarissun
commited on
Commit
•
fa99e5e
1
Parent(s):
87c3100
End of training
Browse files- README.md +100 -0
- adapter_config.json +27 -0
- adapter_model.safetensors +3 -0
- merges.txt +0 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +20 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- reward-trainer
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: openai-community/gpt2-large
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: RM-HH-Gemma_helpful_human_loraR64_20000_gpt2-large_shuffleTrue_extractchosenFalse
|
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 |
+
# RM-HH-Gemma_helpful_human_loraR64_20000_gpt2-large_shuffleTrue_extractchosenFalse
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.6198
|
24 |
+
- Accuracy: 0.6546
|
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: 1.41e-05
|
44 |
+
- train_batch_size: 1
|
45 |
+
- eval_batch_size: 8
|
46 |
+
- seed: 42
|
47 |
+
- gradient_accumulation_steps: 4
|
48 |
+
- total_train_batch_size: 4
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 2.0
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
57 |
+
| 0.703 | 0.06 | 250 | 0.7010 | 0.5414 |
|
58 |
+
| 0.6903 | 0.11 | 500 | 0.6820 | 0.5584 |
|
59 |
+
| 0.6715 | 0.17 | 750 | 0.6700 | 0.5805 |
|
60 |
+
| 0.6498 | 0.22 | 1000 | 0.6604 | 0.5985 |
|
61 |
+
| 0.6625 | 0.28 | 1250 | 0.6550 | 0.6070 |
|
62 |
+
| 0.6425 | 0.33 | 1500 | 0.6523 | 0.6170 |
|
63 |
+
| 0.6514 | 0.39 | 1750 | 0.6480 | 0.6226 |
|
64 |
+
| 0.6535 | 0.45 | 2000 | 0.6454 | 0.6256 |
|
65 |
+
| 0.6233 | 0.5 | 2250 | 0.6427 | 0.6296 |
|
66 |
+
| 0.6434 | 0.56 | 2500 | 0.6403 | 0.6306 |
|
67 |
+
| 0.6288 | 0.61 | 2750 | 0.6379 | 0.6421 |
|
68 |
+
| 0.632 | 0.67 | 3000 | 0.6360 | 0.6361 |
|
69 |
+
| 0.6365 | 0.72 | 3250 | 0.6337 | 0.6436 |
|
70 |
+
| 0.6329 | 0.78 | 3500 | 0.6322 | 0.6456 |
|
71 |
+
| 0.6278 | 0.84 | 3750 | 0.6312 | 0.6441 |
|
72 |
+
| 0.6369 | 0.89 | 4000 | 0.6299 | 0.6476 |
|
73 |
+
| 0.6313 | 0.95 | 4250 | 0.6292 | 0.6466 |
|
74 |
+
| 0.6315 | 1.0 | 4500 | 0.6285 | 0.6456 |
|
75 |
+
| 0.6039 | 1.06 | 4750 | 0.6278 | 0.6441 |
|
76 |
+
| 0.6259 | 1.11 | 5000 | 0.6268 | 0.6471 |
|
77 |
+
| 0.629 | 1.17 | 5250 | 0.6259 | 0.6481 |
|
78 |
+
| 0.6201 | 1.23 | 5500 | 0.6251 | 0.6506 |
|
79 |
+
| 0.6118 | 1.28 | 5750 | 0.6251 | 0.6521 |
|
80 |
+
| 0.6125 | 1.34 | 6000 | 0.6243 | 0.6481 |
|
81 |
+
| 0.6115 | 1.39 | 6250 | 0.6236 | 0.6476 |
|
82 |
+
| 0.6056 | 1.45 | 6500 | 0.6234 | 0.6506 |
|
83 |
+
| 0.6255 | 1.5 | 6750 | 0.6224 | 0.6501 |
|
84 |
+
| 0.6314 | 1.56 | 7000 | 0.6215 | 0.6511 |
|
85 |
+
| 0.6346 | 1.62 | 7250 | 0.6211 | 0.6501 |
|
86 |
+
| 0.6269 | 1.67 | 7500 | 0.6207 | 0.6516 |
|
87 |
+
| 0.6104 | 1.73 | 7750 | 0.6204 | 0.6526 |
|
88 |
+
| 0.6138 | 1.78 | 8000 | 0.6202 | 0.6526 |
|
89 |
+
| 0.6172 | 1.84 | 8250 | 0.6201 | 0.6541 |
|
90 |
+
| 0.6149 | 1.89 | 8500 | 0.6199 | 0.6541 |
|
91 |
+
| 0.6022 | 1.95 | 8750 | 0.6198 | 0.6546 |
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
- PEFT 0.9.0
|
97 |
+
- Transformers 4.38.2
|
98 |
+
- Pytorch 2.1.2
|
99 |
+
- Datasets 2.18.0
|
100 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "openai-community/gpt2-large",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": true,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 64,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"c_attn"
|
23 |
+
],
|
24 |
+
"task_type": "CAUSAL_LM",
|
25 |
+
"use_dora": false,
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d623cc0aad033e63073a65944b950214bc6c6d80c13a160db0e01a1a7262d305
|
3 |
+
size 47195336
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
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 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"clean_up_tokenization_spaces": true,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"pad_token": "<|endoftext|>",
|
18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
19 |
+
"unk_token": "<|endoftext|>"
|
20 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d54513e1e37538b135ef6fa5a222561364f45b77d4ab2d1742ad732515e6767
|
3 |
+
size 4984
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|