Holarissun
commited on
End of training
Browse files- README.md +136 -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 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-Human_helpful_human_loraR64_40000_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-Human_helpful_human_loraR64_40000_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: 0.6036
|
24 |
+
- Accuracy: 0.6751
|
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 |
+
| 0.7205 | 0.03 | 250 | 0.7030 | 0.5251 |
|
58 |
+
| 0.6845 | 0.06 | 500 | 0.6752 | 0.5739 |
|
59 |
+
| 0.6715 | 0.08 | 750 | 0.6636 | 0.5934 |
|
60 |
+
| 0.6632 | 0.11 | 1000 | 0.6542 | 0.6102 |
|
61 |
+
| 0.6432 | 0.14 | 1250 | 0.6492 | 0.6125 |
|
62 |
+
| 0.635 | 0.17 | 1500 | 0.6462 | 0.6200 |
|
63 |
+
| 0.6708 | 0.19 | 1750 | 0.6413 | 0.6240 |
|
64 |
+
| 0.6565 | 0.22 | 2000 | 0.6394 | 0.6285 |
|
65 |
+
| 0.6194 | 0.25 | 2250 | 0.6355 | 0.6315 |
|
66 |
+
| 0.6405 | 0.28 | 2500 | 0.6326 | 0.6380 |
|
67 |
+
| 0.6431 | 0.31 | 2750 | 0.6285 | 0.6428 |
|
68 |
+
| 0.6526 | 0.33 | 3000 | 0.6254 | 0.6415 |
|
69 |
+
| 0.639 | 0.36 | 3250 | 0.6246 | 0.6433 |
|
70 |
+
| 0.621 | 0.39 | 3500 | 0.6217 | 0.6501 |
|
71 |
+
| 0.6305 | 0.42 | 3750 | 0.6200 | 0.6488 |
|
72 |
+
| 0.6146 | 0.45 | 4000 | 0.6194 | 0.6501 |
|
73 |
+
| 0.6382 | 0.47 | 4250 | 0.6166 | 0.6558 |
|
74 |
+
| 0.6211 | 0.5 | 4500 | 0.6143 | 0.6606 |
|
75 |
+
| 0.6141 | 0.53 | 4750 | 0.6135 | 0.6601 |
|
76 |
+
| 0.6272 | 0.56 | 5000 | 0.6119 | 0.6591 |
|
77 |
+
| 0.6242 | 0.58 | 5250 | 0.6103 | 0.6608 |
|
78 |
+
| 0.6202 | 0.61 | 5500 | 0.6087 | 0.6658 |
|
79 |
+
| 0.6205 | 0.64 | 5750 | 0.6080 | 0.6666 |
|
80 |
+
| 0.6268 | 0.67 | 6000 | 0.6069 | 0.6663 |
|
81 |
+
| 0.6017 | 0.7 | 6250 | 0.6064 | 0.6638 |
|
82 |
+
| 0.5942 | 0.72 | 6500 | 0.6060 | 0.6656 |
|
83 |
+
| 0.6186 | 0.75 | 6750 | 0.6053 | 0.6668 |
|
84 |
+
| 0.6316 | 0.78 | 7000 | 0.6040 | 0.6688 |
|
85 |
+
| 0.6031 | 0.81 | 7250 | 0.6039 | 0.6738 |
|
86 |
+
| 0.6143 | 0.84 | 7500 | 0.6021 | 0.6703 |
|
87 |
+
| 0.6217 | 0.86 | 7750 | 0.6020 | 0.6759 |
|
88 |
+
| 0.6099 | 0.89 | 8000 | 0.6017 | 0.6754 |
|
89 |
+
| 0.5951 | 0.92 | 8250 | 0.6010 | 0.6748 |
|
90 |
+
| 0.603 | 0.95 | 8500 | 0.6005 | 0.6721 |
|
91 |
+
| 0.6098 | 0.97 | 8750 | 0.6005 | 0.6769 |
|
92 |
+
| 0.6222 | 1.0 | 9000 | 0.5991 | 0.6741 |
|
93 |
+
| 0.6005 | 1.03 | 9250 | 0.5991 | 0.6743 |
|
94 |
+
| 0.5972 | 1.06 | 9500 | 0.5998 | 0.6706 |
|
95 |
+
| 0.582 | 1.09 | 9750 | 0.6043 | 0.6691 |
|
96 |
+
| 0.6004 | 1.11 | 10000 | 0.6187 | 0.6711 |
|
97 |
+
| 0.5985 | 1.14 | 10250 | 0.6195 | 0.6663 |
|
98 |
+
| 0.6206 | 1.17 | 10500 | 0.6122 | 0.6693 |
|
99 |
+
| 0.6216 | 1.2 | 10750 | 0.6069 | 0.6741 |
|
100 |
+
| 0.6091 | 1.22 | 11000 | 0.6236 | 0.6691 |
|
101 |
+
| 0.5863 | 1.25 | 11250 | 0.6209 | 0.6713 |
|
102 |
+
| 0.641 | 1.28 | 11500 | 0.6184 | 0.6698 |
|
103 |
+
| 0.6144 | 1.31 | 11750 | 0.6051 | 0.6713 |
|
104 |
+
| 0.6527 | 1.34 | 12000 | 0.6067 | 0.6703 |
|
105 |
+
| 0.6059 | 1.36 | 12250 | 0.6048 | 0.6711 |
|
106 |
+
| 0.6138 | 1.39 | 12500 | 0.6015 | 0.6741 |
|
107 |
+
| 0.6376 | 1.42 | 12750 | 0.6002 | 0.6726 |
|
108 |
+
| 0.6273 | 1.45 | 13000 | 0.5989 | 0.6721 |
|
109 |
+
| 0.6028 | 1.48 | 13250 | 0.6011 | 0.6713 |
|
110 |
+
| 0.6116 | 1.5 | 13500 | 0.5999 | 0.6723 |
|
111 |
+
| 0.6201 | 1.53 | 13750 | 0.5990 | 0.6733 |
|
112 |
+
| 0.606 | 1.56 | 14000 | 0.6024 | 0.6733 |
|
113 |
+
| 0.5985 | 1.59 | 14250 | 0.6079 | 0.6716 |
|
114 |
+
| 0.664 | 1.61 | 14500 | 0.6019 | 0.6748 |
|
115 |
+
| 0.5859 | 1.64 | 14750 | 0.6039 | 0.6743 |
|
116 |
+
| 0.6231 | 1.67 | 15000 | 0.6002 | 0.6733 |
|
117 |
+
| 0.5984 | 1.7 | 15250 | 0.6020 | 0.6741 |
|
118 |
+
| 0.602 | 1.73 | 15500 | 0.6037 | 0.6741 |
|
119 |
+
| 0.5817 | 1.75 | 15750 | 0.6031 | 0.6748 |
|
120 |
+
| 0.6128 | 1.78 | 16000 | 0.6040 | 0.6743 |
|
121 |
+
| 0.6415 | 1.81 | 16250 | 0.6047 | 0.6748 |
|
122 |
+
| 0.6084 | 1.84 | 16500 | 0.6041 | 0.6743 |
|
123 |
+
| 0.6103 | 1.87 | 16750 | 0.6040 | 0.6746 |
|
124 |
+
| 0.6289 | 1.89 | 17000 | 0.6033 | 0.6746 |
|
125 |
+
| 0.5948 | 1.92 | 17250 | 0.6030 | 0.6759 |
|
126 |
+
| 0.5655 | 1.95 | 17500 | 0.6033 | 0.6748 |
|
127 |
+
| 0.6125 | 1.98 | 17750 | 0.6036 | 0.6751 |
|
128 |
+
|
129 |
+
|
130 |
+
### Framework versions
|
131 |
+
|
132 |
+
- PEFT 0.9.0
|
133 |
+
- Transformers 4.38.2
|
134 |
+
- Pytorch 2.1.2
|
135 |
+
- Datasets 2.18.0
|
136 |
+
- 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 sha256:4cd7908049d5d77487cb3804777717da15cad0386f269da6505ab2f88860472b
|
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:b7414bcd54732166aab7786f25fc380aa933c7f69de326a5b9e723ebfe67b991
|
3 |
+
size 4984
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|