Upload folder using huggingface_hub
Browse files- README.md +40 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- checkpoint-1869/README.md +202 -0
- checkpoint-1869/adapter_config.json +29 -0
- checkpoint-1869/adapter_model.safetensors +3 -0
- checkpoint-1869/merges.txt +0 -0
- checkpoint-1869/optimizer.pt +3 -0
- checkpoint-1869/rng_state.pth +3 -0
- checkpoint-1869/scheduler.pt +3 -0
- checkpoint-1869/special_tokens_map.json +6 -0
- checkpoint-1869/tokenizer.json +0 -0
- checkpoint-1869/tokenizer_config.json +21 -0
- checkpoint-1869/trainer_state.json +246 -0
- checkpoint-1869/training_args.bin +3 -0
- checkpoint-1869/vocab.json +0 -0
- handler.py +32 -0
- merges.txt +0 -0
- requirements.txt +2 -0
- runs/Mar04_03-59-37_r-betajuned-testing-1jn9ocyi-e4b0f-q5uf5/events.out.tfevents.1709524779.r-betajuned-testing-1jn9ocyi-e4b0f-q5uf5.58.0 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
- training_args.bin +3 -0
- training_params.json +47 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation
|
5 |
+
widget:
|
6 |
+
- text: "I love AutoTrain because "
|
7 |
+
license: other
|
8 |
+
---
|
9 |
+
|
10 |
+
# Model Trained Using AutoTrain
|
11 |
+
|
12 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
13 |
+
|
14 |
+
# Usage
|
15 |
+
|
16 |
+
```python
|
17 |
+
|
18 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
19 |
+
|
20 |
+
model_path = "PATH_TO_THIS_REPO"
|
21 |
+
|
22 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
23 |
+
model = AutoModelForCausalLM.from_pretrained(
|
24 |
+
model_path,
|
25 |
+
device_map="auto",
|
26 |
+
torch_dtype='auto'
|
27 |
+
).eval()
|
28 |
+
|
29 |
+
# Prompt content: "hi"
|
30 |
+
messages = [
|
31 |
+
{"role": "user", "content": "hi"}
|
32 |
+
]
|
33 |
+
|
34 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
35 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
36 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
37 |
+
|
38 |
+
# Model response: "Hello! How can I assist you today?"
|
39 |
+
print(response)
|
40 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
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": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"c_proj",
|
23 |
+
"c_fc",
|
24 |
+
"c_attn"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:287cda18f46604834de26c1a586c7ba0d6066d849fdd818ec4957696d757fbbc
|
3 |
+
size 9449344
|
checkpoint-1869/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: openai-community/gpt2
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.9.0
|
checkpoint-1869/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
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": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"c_proj",
|
23 |
+
"c_fc",
|
24 |
+
"c_attn"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
checkpoint-1869/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:287cda18f46604834de26c1a586c7ba0d6066d849fdd818ec4957696d757fbbc
|
3 |
+
size 9449344
|
checkpoint-1869/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1869/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f65e0fcd66bfb77af84884f1ef551ae518bd8598b7497e056c57615414cb93bf
|
3 |
+
size 18955258
|
checkpoint-1869/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
|
3 |
+
size 14244
|
checkpoint-1869/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f70777b251bd2234ecb4bd45b960ca467fd3c98ea9878fcc5e886608a232f04b
|
3 |
+
size 1064
|
checkpoint-1869/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 |
+
}
|
checkpoint-1869/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1869/tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
+
"model_max_length": 1024,
|
18 |
+
"pad_token": "<|endoftext|>",
|
19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
20 |
+
"unk_token": "<|endoftext|>"
|
21 |
+
}
|
checkpoint-1869/trainer_state.json
ADDED
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1869,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.2,
|
13 |
+
"grad_norm": 0.8480008244514465,
|
14 |
+
"learning_rate": 1.9732620320855616e-05,
|
15 |
+
"logits/chosen": -89.2172622680664,
|
16 |
+
"logits/rejected": -100.73475646972656,
|
17 |
+
"logps/chosen": -492.0954284667969,
|
18 |
+
"logps/rejected": -38.49285125732422,
|
19 |
+
"loss": 0.494,
|
20 |
+
"rewards/accuracies": 0.9193548560142517,
|
21 |
+
"rewards/chosen": 0.4900602400302887,
|
22 |
+
"rewards/margins": 0.6183792948722839,
|
23 |
+
"rewards/rejected": -0.12831908464431763,
|
24 |
+
"step": 124
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.4,
|
28 |
+
"grad_norm": 0.024601615965366364,
|
29 |
+
"learning_rate": 2.892984542211653e-05,
|
30 |
+
"logits/chosen": -90.30268859863281,
|
31 |
+
"logits/rejected": -99.68387603759766,
|
32 |
+
"logps/chosen": -471.47296142578125,
|
33 |
+
"logps/rejected": -57.4666748046875,
|
34 |
+
"loss": 0.0423,
|
35 |
+
"rewards/accuracies": 1.0,
|
36 |
+
"rewards/chosen": 2.3312041759490967,
|
37 |
+
"rewards/margins": 4.3500566482543945,
|
38 |
+
"rewards/rejected": -2.018853187561035,
|
39 |
+
"step": 248
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.6,
|
43 |
+
"grad_norm": 0.0065199206583201885,
|
44 |
+
"learning_rate": 2.671819262782402e-05,
|
45 |
+
"logits/chosen": -91.32217407226562,
|
46 |
+
"logits/rejected": -99.80288696289062,
|
47 |
+
"logps/chosen": -510.0004577636719,
|
48 |
+
"logps/rejected": -85.79643249511719,
|
49 |
+
"loss": 0.0016,
|
50 |
+
"rewards/accuracies": 1.0,
|
51 |
+
"rewards/chosen": 2.711028575897217,
|
52 |
+
"rewards/margins": 7.543690204620361,
|
53 |
+
"rewards/rejected": -4.8326616287231445,
|
54 |
+
"step": 372
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.8,
|
58 |
+
"grad_norm": 0.0038568591699004173,
|
59 |
+
"learning_rate": 2.450653983353151e-05,
|
60 |
+
"logits/chosen": -91.59159851074219,
|
61 |
+
"logits/rejected": -99.74394226074219,
|
62 |
+
"logps/chosen": -495.5379333496094,
|
63 |
+
"logps/rejected": -101.83560943603516,
|
64 |
+
"loss": 0.0006,
|
65 |
+
"rewards/accuracies": 1.0,
|
66 |
+
"rewards/chosen": 2.53082275390625,
|
67 |
+
"rewards/margins": 8.984918594360352,
|
68 |
+
"rewards/rejected": -6.45409631729126,
|
69 |
+
"step": 496
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 1.0,
|
73 |
+
"grad_norm": 0.004021492321044207,
|
74 |
+
"learning_rate": 2.2294887039239e-05,
|
75 |
+
"logits/chosen": -91.71090698242188,
|
76 |
+
"logits/rejected": -99.83422088623047,
|
77 |
+
"logps/chosen": -477.32086181640625,
|
78 |
+
"logps/rejected": -112.09052276611328,
|
79 |
+
"loss": 0.0002,
|
80 |
+
"rewards/accuracies": 1.0,
|
81 |
+
"rewards/chosen": 2.4358060359954834,
|
82 |
+
"rewards/margins": 9.908026695251465,
|
83 |
+
"rewards/rejected": -7.472220420837402,
|
84 |
+
"step": 620
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.19,
|
88 |
+
"grad_norm": 0.001646166667342186,
|
89 |
+
"learning_rate": 2.0083234244946493e-05,
|
90 |
+
"logits/chosen": -91.64920806884766,
|
91 |
+
"logits/rejected": -99.716796875,
|
92 |
+
"logps/chosen": -457.3955993652344,
|
93 |
+
"logps/rejected": -116.87188720703125,
|
94 |
+
"loss": 0.0001,
|
95 |
+
"rewards/accuracies": 1.0,
|
96 |
+
"rewards/chosen": 2.3930044174194336,
|
97 |
+
"rewards/margins": 10.342494010925293,
|
98 |
+
"rewards/rejected": -7.949489116668701,
|
99 |
+
"step": 744
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 1.39,
|
103 |
+
"grad_norm": 0.0008155236137099564,
|
104 |
+
"learning_rate": 1.7871581450653984e-05,
|
105 |
+
"logits/chosen": -92.63726806640625,
|
106 |
+
"logits/rejected": -99.6506576538086,
|
107 |
+
"logps/chosen": -416.0518493652344,
|
108 |
+
"logps/rejected": -121.02271270751953,
|
109 |
+
"loss": 0.0001,
|
110 |
+
"rewards/accuracies": 1.0,
|
111 |
+
"rewards/chosen": 2.325775623321533,
|
112 |
+
"rewards/margins": 10.702033996582031,
|
113 |
+
"rewards/rejected": -8.376258850097656,
|
114 |
+
"step": 868
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.59,
|
118 |
+
"grad_norm": 0.0008802612428553402,
|
119 |
+
"learning_rate": 1.5659928656361473e-05,
|
120 |
+
"logits/chosen": -91.56256103515625,
|
121 |
+
"logits/rejected": -100.07992553710938,
|
122 |
+
"logps/chosen": -546.8630981445312,
|
123 |
+
"logps/rejected": -123.075439453125,
|
124 |
+
"loss": 0.0001,
|
125 |
+
"rewards/accuracies": 1.0,
|
126 |
+
"rewards/chosen": 2.578490972518921,
|
127 |
+
"rewards/margins": 11.155267715454102,
|
128 |
+
"rewards/rejected": -8.576776504516602,
|
129 |
+
"step": 992
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 1.79,
|
133 |
+
"grad_norm": 0.0003077541769016534,
|
134 |
+
"learning_rate": 1.3448275862068966e-05,
|
135 |
+
"logits/chosen": -91.74861145019531,
|
136 |
+
"logits/rejected": -99.87557983398438,
|
137 |
+
"logps/chosen": -505.8144226074219,
|
138 |
+
"logps/rejected": -125.00572204589844,
|
139 |
+
"loss": 0.0,
|
140 |
+
"rewards/accuracies": 1.0,
|
141 |
+
"rewards/chosen": 2.4200246334075928,
|
142 |
+
"rewards/margins": 11.187772750854492,
|
143 |
+
"rewards/rejected": -8.767749786376953,
|
144 |
+
"step": 1116
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 1.99,
|
148 |
+
"grad_norm": 0.0011185492621734738,
|
149 |
+
"learning_rate": 1.1236623067776456e-05,
|
150 |
+
"logits/chosen": -91.76570129394531,
|
151 |
+
"logits/rejected": -99.95115661621094,
|
152 |
+
"logps/chosen": -507.2481384277344,
|
153 |
+
"logps/rejected": -126.36703491210938,
|
154 |
+
"loss": 0.0001,
|
155 |
+
"rewards/accuracies": 1.0,
|
156 |
+
"rewards/chosen": 2.392195701599121,
|
157 |
+
"rewards/margins": 11.292296409606934,
|
158 |
+
"rewards/rejected": -8.900099754333496,
|
159 |
+
"step": 1240
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 2.19,
|
163 |
+
"grad_norm": 0.0003283724654465914,
|
164 |
+
"learning_rate": 9.024970273483949e-06,
|
165 |
+
"logits/chosen": -92.13390350341797,
|
166 |
+
"logits/rejected": -99.67440795898438,
|
167 |
+
"logps/chosen": -457.7467956542969,
|
168 |
+
"logps/rejected": -127.90784454345703,
|
169 |
+
"loss": 0.0001,
|
170 |
+
"rewards/accuracies": 1.0,
|
171 |
+
"rewards/chosen": 2.346339464187622,
|
172 |
+
"rewards/margins": 11.401449203491211,
|
173 |
+
"rewards/rejected": -9.055108070373535,
|
174 |
+
"step": 1364
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 2.39,
|
178 |
+
"grad_norm": 0.001045580138452351,
|
179 |
+
"learning_rate": 6.813317479191439e-06,
|
180 |
+
"logits/chosen": -91.70454406738281,
|
181 |
+
"logits/rejected": -99.99876403808594,
|
182 |
+
"logps/chosen": -501.30120849609375,
|
183 |
+
"logps/rejected": -128.7549285888672,
|
184 |
+
"loss": 0.0,
|
185 |
+
"rewards/accuracies": 1.0,
|
186 |
+
"rewards/chosen": 2.54925274848938,
|
187 |
+
"rewards/margins": 11.710598945617676,
|
188 |
+
"rewards/rejected": -9.161345481872559,
|
189 |
+
"step": 1488
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 2.59,
|
193 |
+
"grad_norm": 8.819426147965714e-05,
|
194 |
+
"learning_rate": 4.6016646848989295e-06,
|
195 |
+
"logits/chosen": -91.47350311279297,
|
196 |
+
"logits/rejected": -99.84117126464844,
|
197 |
+
"logps/chosen": -507.70989990234375,
|
198 |
+
"logps/rejected": -129.5757598876953,
|
199 |
+
"loss": 0.0,
|
200 |
+
"rewards/accuracies": 1.0,
|
201 |
+
"rewards/chosen": 2.4314069747924805,
|
202 |
+
"rewards/margins": 11.66946029663086,
|
203 |
+
"rewards/rejected": -9.238051414489746,
|
204 |
+
"step": 1612
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 2.79,
|
208 |
+
"grad_norm": 0.0005761810461990535,
|
209 |
+
"learning_rate": 2.390011890606421e-06,
|
210 |
+
"logits/chosen": -91.81477355957031,
|
211 |
+
"logits/rejected": -99.52936553955078,
|
212 |
+
"logps/chosen": -493.1682434082031,
|
213 |
+
"logps/rejected": -130.6132354736328,
|
214 |
+
"loss": 0.0,
|
215 |
+
"rewards/accuracies": 1.0,
|
216 |
+
"rewards/chosen": 2.2742276191711426,
|
217 |
+
"rewards/margins": 11.582930564880371,
|
218 |
+
"rewards/rejected": -9.30870246887207,
|
219 |
+
"step": 1736
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.99,
|
223 |
+
"grad_norm": 0.0013249547919258475,
|
224 |
+
"learning_rate": 1.7835909631391202e-07,
|
225 |
+
"logits/chosen": -91.92269897460938,
|
226 |
+
"logits/rejected": -99.53717041015625,
|
227 |
+
"logps/chosen": -467.632080078125,
|
228 |
+
"logps/rejected": -130.56443786621094,
|
229 |
+
"loss": 0.0,
|
230 |
+
"rewards/accuracies": 1.0,
|
231 |
+
"rewards/chosen": 2.3530662059783936,
|
232 |
+
"rewards/margins": 11.665258407592773,
|
233 |
+
"rewards/rejected": -9.312192916870117,
|
234 |
+
"step": 1860
|
235 |
+
}
|
236 |
+
],
|
237 |
+
"logging_steps": 124,
|
238 |
+
"max_steps": 1869,
|
239 |
+
"num_input_tokens_seen": 0,
|
240 |
+
"num_train_epochs": 3,
|
241 |
+
"save_steps": 500,
|
242 |
+
"total_flos": 0.0,
|
243 |
+
"train_batch_size": 2,
|
244 |
+
"trial_name": null,
|
245 |
+
"trial_params": null
|
246 |
+
}
|
checkpoint-1869/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:746c82bc804ba2fd06af83713fb283d54911f2ba5072112f6f3c7ad18b46ecb2
|
3 |
+
size 4920
|
checkpoint-1869/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
handler.py
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from typing import Dict, List, Any
|
2 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
|
3 |
+
import torch
|
4 |
+
from peft import PeftModel
|
5 |
+
import json
|
6 |
+
import os
|
7 |
+
|
8 |
+
|
9 |
+
class EndpointHandler():
|
10 |
+
def __init__(self, path=""):
|
11 |
+
base_model_path = json.load(open(os.path.join(path, "training_params.json")))["model"]
|
12 |
+
model = AutoModelForCausalLM.from_pretrained(
|
13 |
+
base_model_path,
|
14 |
+
torch_dtype=torch.float16,
|
15 |
+
low_cpu_mem_usage=True,
|
16 |
+
trust_remote_code=True,
|
17 |
+
device_map="auto",
|
18 |
+
)
|
19 |
+
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
|
20 |
+
model.resize_token_embeddings(len(tokenizer))
|
21 |
+
model = PeftModel.from_pretrained(model, path)
|
22 |
+
model = model.merge_and_unload()
|
23 |
+
self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
|
24 |
+
|
25 |
+
def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
|
26 |
+
inputs = data.pop("inputs", data)
|
27 |
+
parameters = data.pop("parameters", None)
|
28 |
+
if parameters is not None:
|
29 |
+
prediction = self.pipeline(inputs, **parameters)
|
30 |
+
else:
|
31 |
+
prediction = self.pipeline(inputs)
|
32 |
+
return prediction
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
requirements.txt
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
peft==0.9.0
|
2 |
+
transformers==4.38.1
|
runs/Mar04_03-59-37_r-betajuned-testing-1jn9ocyi-e4b0f-q5uf5/events.out.tfevents.1709524779.r-betajuned-testing-1jn9ocyi-e4b0f-q5uf5.58.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27243e38ca9698fcbbfbe396b40eba377913f725cefcadc08c4fe922baa96b14
|
3 |
+
size 15938
|
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 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
+
"model_max_length": 1024,
|
18 |
+
"pad_token": "<|endoftext|>",
|
19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
20 |
+
"unk_token": "<|endoftext|>"
|
21 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:746c82bc804ba2fd06af83713fb283d54911f2ba5072112f6f3c7ad18b46ecb2
|
3 |
+
size 4920
|
training_params.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "openai-community/gpt2",
|
3 |
+
"project_name": "gpt2-train5kali",
|
4 |
+
"data_path": "gpt2-train5kali/autotrain-data",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"add_eos_token": true,
|
8 |
+
"block_size": 1024,
|
9 |
+
"model_max_length": 2048,
|
10 |
+
"padding": "right",
|
11 |
+
"trainer": "dpo",
|
12 |
+
"use_flash_attention_2": false,
|
13 |
+
"log": "tensorboard",
|
14 |
+
"disable_gradient_checkpointing": false,
|
15 |
+
"logging_steps": -1,
|
16 |
+
"evaluation_strategy": "epoch",
|
17 |
+
"save_total_limit": 1,
|
18 |
+
"save_strategy": "epoch",
|
19 |
+
"auto_find_batch_size": false,
|
20 |
+
"mixed_precision": "fp16",
|
21 |
+
"lr": 3e-05,
|
22 |
+
"epochs": 3,
|
23 |
+
"batch_size": 2,
|
24 |
+
"warmup_ratio": 0.1,
|
25 |
+
"gradient_accumulation": 1,
|
26 |
+
"optimizer": "adamw_torch",
|
27 |
+
"scheduler": "linear",
|
28 |
+
"weight_decay": 0.0,
|
29 |
+
"max_grad_norm": 1.0,
|
30 |
+
"seed": 42,
|
31 |
+
"chat_template": "none",
|
32 |
+
"quantization": "int4",
|
33 |
+
"target_modules": "all-linear",
|
34 |
+
"merge_adapter": false,
|
35 |
+
"peft": true,
|
36 |
+
"lora_r": 16,
|
37 |
+
"lora_alpha": 32,
|
38 |
+
"lora_dropout": 0.05,
|
39 |
+
"model_ref": null,
|
40 |
+
"dpo_beta": 0.1,
|
41 |
+
"prompt_text_column": "autotrain_prompt",
|
42 |
+
"text_column": "autotrain_text",
|
43 |
+
"rejected_text_column": "autotrain_rejected_text",
|
44 |
+
"push_to_hub": true,
|
45 |
+
"repo_id": "betajuned/gpt2-train5kali",
|
46 |
+
"username": "betajuned"
|
47 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|