hibana2077
commited on
Commit
•
e83c27b
1
Parent(s):
4baeace
Upload folder using huggingface_hub
Browse files- README.md +40 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- checkpoint-207/README.md +204 -0
- checkpoint-207/adapter_config.json +26 -0
- checkpoint-207/adapter_model.safetensors +3 -0
- checkpoint-207/merges.txt +0 -0
- checkpoint-207/optimizer.pt +3 -0
- checkpoint-207/rng_state.pth +3 -0
- checkpoint-207/scheduler.pt +3 -0
- checkpoint-207/special_tokens_map.json +30 -0
- checkpoint-207/tokenizer.json +0 -0
- checkpoint-207/tokenizer_config.json +31 -0
- checkpoint-207/trainer_state.json +231 -0
- checkpoint-207/training_args.bin +3 -0
- checkpoint-207/vocab.json +0 -0
- handler.py +31 -0
- merges.txt +0 -0
- requirements.txt +2 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +31 -0
- training_args.bin +3 -0
- training_params.json +46 -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 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "facebook/opt-125m",
|
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 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61dd16f4451afbc193a9d47acc928f16b0fa5b6ea6ee421824cbaf00da971bb9
|
3 |
+
size 2365968
|
checkpoint-207/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: facebook/opt-125m
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.7.1
|
checkpoint-207/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "facebook/opt-125m",
|
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 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
checkpoint-207/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61dd16f4451afbc193a9d47acc928f16b0fa5b6ea6ee421824cbaf00da971bb9
|
3 |
+
size 2365968
|
checkpoint-207/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-207/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a930f639ef47f31d583944dce1f791a1f64cd45a30cbed88379c5f142481bc
|
3 |
+
size 4759290
|
checkpoint-207/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9a10d25356fc848658ab6077f967757c03e72dbd7b8f4d952543ecd3839b5ee
|
3 |
+
size 14244
|
checkpoint-207/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11b8b1984e1e44a8fd350b81fd556b7a0b12289949ee9b1650d946dc99d4b73c
|
3 |
+
size 1064
|
checkpoint-207/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "</s>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-207/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-207/tokenizer_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"1": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"2": {
|
14 |
+
"content": "</s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"bos_token": "</s>",
|
23 |
+
"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 %}",
|
24 |
+
"clean_up_tokenization_spaces": true,
|
25 |
+
"eos_token": "</s>",
|
26 |
+
"errors": "replace",
|
27 |
+
"model_max_length": 2048,
|
28 |
+
"pad_token": "<pad>",
|
29 |
+
"tokenizer_class": "GPT2Tokenizer",
|
30 |
+
"unk_token": "</s>"
|
31 |
+
}
|
checkpoint-207/trainer_state.json
ADDED
@@ -0,0 +1,231 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 207,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.19,
|
13 |
+
"learning_rate": 1.5714285714285715e-05,
|
14 |
+
"logits/chosen": -1.823734998703003,
|
15 |
+
"logits/rejected": -1.96222984790802,
|
16 |
+
"logps/chosen": -984.5184936523438,
|
17 |
+
"logps/rejected": -29.066242218017578,
|
18 |
+
"loss": 0.7963,
|
19 |
+
"rewards/accuracies": 0.6538461446762085,
|
20 |
+
"rewards/chosen": 0.2930363118648529,
|
21 |
+
"rewards/margins": 0.29948848485946655,
|
22 |
+
"rewards/rejected": -0.00645211897790432,
|
23 |
+
"step": 13
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.38,
|
27 |
+
"learning_rate": 2.9516129032258067e-05,
|
28 |
+
"logits/chosen": -1.7756704092025757,
|
29 |
+
"logits/rejected": -1.890375018119812,
|
30 |
+
"logps/chosen": -1008.671630859375,
|
31 |
+
"logps/rejected": -30.05452537536621,
|
32 |
+
"loss": 0.5675,
|
33 |
+
"rewards/accuracies": 0.6538461446762085,
|
34 |
+
"rewards/chosen": 0.6647549867630005,
|
35 |
+
"rewards/margins": 0.7006121277809143,
|
36 |
+
"rewards/rejected": -0.03585716709494591,
|
37 |
+
"step": 26
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.57,
|
41 |
+
"learning_rate": 2.7419354838709678e-05,
|
42 |
+
"logits/chosen": -1.837444543838501,
|
43 |
+
"logits/rejected": -1.8552197217941284,
|
44 |
+
"logps/chosen": -1084.7537841796875,
|
45 |
+
"logps/rejected": -30.599714279174805,
|
46 |
+
"loss": 0.4647,
|
47 |
+
"rewards/accuracies": 0.7692307829856873,
|
48 |
+
"rewards/chosen": 0.9935499429702759,
|
49 |
+
"rewards/margins": 1.160874366760254,
|
50 |
+
"rewards/rejected": -0.16732460260391235,
|
51 |
+
"step": 39
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.75,
|
55 |
+
"learning_rate": 2.532258064516129e-05,
|
56 |
+
"logits/chosen": -1.745394229888916,
|
57 |
+
"logits/rejected": -1.8828259706497192,
|
58 |
+
"logps/chosen": -1103.2149658203125,
|
59 |
+
"logps/rejected": -32.83525085449219,
|
60 |
+
"loss": 0.2193,
|
61 |
+
"rewards/accuracies": 0.8846153616905212,
|
62 |
+
"rewards/chosen": 2.401637077331543,
|
63 |
+
"rewards/margins": 2.809011697769165,
|
64 |
+
"rewards/rejected": -0.4073745608329773,
|
65 |
+
"step": 52
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.94,
|
69 |
+
"learning_rate": 2.3225806451612902e-05,
|
70 |
+
"logits/chosen": -1.6953773498535156,
|
71 |
+
"logits/rejected": -2.03174090385437,
|
72 |
+
"logps/chosen": -1086.2177734375,
|
73 |
+
"logps/rejected": -34.20427703857422,
|
74 |
+
"loss": 0.1084,
|
75 |
+
"rewards/accuracies": 1.0,
|
76 |
+
"rewards/chosen": 2.713472843170166,
|
77 |
+
"rewards/margins": 3.305988073348999,
|
78 |
+
"rewards/rejected": -0.5925151109695435,
|
79 |
+
"step": 65
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.13,
|
83 |
+
"learning_rate": 2.1129032258064516e-05,
|
84 |
+
"logits/chosen": -1.7250920534133911,
|
85 |
+
"logits/rejected": -1.886851191520691,
|
86 |
+
"logps/chosen": -902.3397827148438,
|
87 |
+
"logps/rejected": -36.79640579223633,
|
88 |
+
"loss": 0.0972,
|
89 |
+
"rewards/accuracies": 1.0,
|
90 |
+
"rewards/chosen": 2.591458797454834,
|
91 |
+
"rewards/margins": 3.4001564979553223,
|
92 |
+
"rewards/rejected": -0.8086973428726196,
|
93 |
+
"step": 78
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.32,
|
97 |
+
"learning_rate": 1.903225806451613e-05,
|
98 |
+
"logits/chosen": -1.6640688180923462,
|
99 |
+
"logits/rejected": -1.9599171876907349,
|
100 |
+
"logps/chosen": -1034.3873291015625,
|
101 |
+
"logps/rejected": -38.65880584716797,
|
102 |
+
"loss": 0.0428,
|
103 |
+
"rewards/accuracies": 1.0,
|
104 |
+
"rewards/chosen": 3.461390495300293,
|
105 |
+
"rewards/margins": 4.427910327911377,
|
106 |
+
"rewards/rejected": -0.9665195941925049,
|
107 |
+
"step": 91
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.51,
|
111 |
+
"learning_rate": 1.6935483870967744e-05,
|
112 |
+
"logits/chosen": -1.6940295696258545,
|
113 |
+
"logits/rejected": -1.9844238758087158,
|
114 |
+
"logps/chosen": -1174.732666015625,
|
115 |
+
"logps/rejected": -41.705257415771484,
|
116 |
+
"loss": 0.0235,
|
117 |
+
"rewards/accuracies": 1.0,
|
118 |
+
"rewards/chosen": 3.3263399600982666,
|
119 |
+
"rewards/margins": 4.630356788635254,
|
120 |
+
"rewards/rejected": -1.3040169477462769,
|
121 |
+
"step": 104
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.7,
|
125 |
+
"learning_rate": 1.4838709677419355e-05,
|
126 |
+
"logits/chosen": -1.6856719255447388,
|
127 |
+
"logits/rejected": -1.8793022632598877,
|
128 |
+
"logps/chosen": -1046.614990234375,
|
129 |
+
"logps/rejected": -43.94160842895508,
|
130 |
+
"loss": 0.0238,
|
131 |
+
"rewards/accuracies": 1.0,
|
132 |
+
"rewards/chosen": 3.614682912826538,
|
133 |
+
"rewards/margins": 5.117927074432373,
|
134 |
+
"rewards/rejected": -1.5032439231872559,
|
135 |
+
"step": 117
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.88,
|
139 |
+
"learning_rate": 1.274193548387097e-05,
|
140 |
+
"logits/chosen": -1.7377840280532837,
|
141 |
+
"logits/rejected": -1.8570376634597778,
|
142 |
+
"logps/chosen": -1106.663330078125,
|
143 |
+
"logps/rejected": -47.238887786865234,
|
144 |
+
"loss": 0.0242,
|
145 |
+
"rewards/accuracies": 1.0,
|
146 |
+
"rewards/chosen": 3.449557304382324,
|
147 |
+
"rewards/margins": 5.24083137512207,
|
148 |
+
"rewards/rejected": -1.7912741899490356,
|
149 |
+
"step": 130
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 2.07,
|
153 |
+
"learning_rate": 1.0645161290322582e-05,
|
154 |
+
"logits/chosen": -1.7412984371185303,
|
155 |
+
"logits/rejected": -1.9490795135498047,
|
156 |
+
"logps/chosen": -1117.510009765625,
|
157 |
+
"logps/rejected": -47.68777084350586,
|
158 |
+
"loss": 0.0227,
|
159 |
+
"rewards/accuracies": 1.0,
|
160 |
+
"rewards/chosen": 3.141476631164551,
|
161 |
+
"rewards/margins": 5.044860363006592,
|
162 |
+
"rewards/rejected": -1.903383731842041,
|
163 |
+
"step": 143
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 2.26,
|
167 |
+
"learning_rate": 8.548387096774194e-06,
|
168 |
+
"logits/chosen": -1.6916511058807373,
|
169 |
+
"logits/rejected": -1.9522241353988647,
|
170 |
+
"logps/chosen": -1196.82861328125,
|
171 |
+
"logps/rejected": -49.64944076538086,
|
172 |
+
"loss": 0.015,
|
173 |
+
"rewards/accuracies": 1.0,
|
174 |
+
"rewards/chosen": 3.8758084774017334,
|
175 |
+
"rewards/margins": 5.988270282745361,
|
176 |
+
"rewards/rejected": -2.1124606132507324,
|
177 |
+
"step": 156
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 2.45,
|
181 |
+
"learning_rate": 6.451612903225806e-06,
|
182 |
+
"logits/chosen": -1.760750651359558,
|
183 |
+
"logits/rejected": -1.925395131111145,
|
184 |
+
"logps/chosen": -701.3285522460938,
|
185 |
+
"logps/rejected": -50.479835510253906,
|
186 |
+
"loss": 0.0169,
|
187 |
+
"rewards/accuracies": 1.0,
|
188 |
+
"rewards/chosen": 2.707566261291504,
|
189 |
+
"rewards/margins": 4.906687259674072,
|
190 |
+
"rewards/rejected": -2.1991212368011475,
|
191 |
+
"step": 169
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.64,
|
195 |
+
"learning_rate": 4.35483870967742e-06,
|
196 |
+
"logits/chosen": -1.6971558332443237,
|
197 |
+
"logits/rejected": -1.9400659799575806,
|
198 |
+
"logps/chosen": -959.2064208984375,
|
199 |
+
"logps/rejected": -51.388999938964844,
|
200 |
+
"loss": 0.0085,
|
201 |
+
"rewards/accuracies": 1.0,
|
202 |
+
"rewards/chosen": 3.8825502395629883,
|
203 |
+
"rewards/margins": 6.139618873596191,
|
204 |
+
"rewards/rejected": -2.2570688724517822,
|
205 |
+
"step": 182
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.83,
|
209 |
+
"learning_rate": 2.2580645161290324e-06,
|
210 |
+
"logits/chosen": -1.7328979969024658,
|
211 |
+
"logits/rejected": -2.0168874263763428,
|
212 |
+
"logps/chosen": -926.796875,
|
213 |
+
"logps/rejected": -52.40264129638672,
|
214 |
+
"loss": 0.0097,
|
215 |
+
"rewards/accuracies": 1.0,
|
216 |
+
"rewards/chosen": 3.548464059829712,
|
217 |
+
"rewards/margins": 5.864409446716309,
|
218 |
+
"rewards/rejected": -2.3159451484680176,
|
219 |
+
"step": 195
|
220 |
+
}
|
221 |
+
],
|
222 |
+
"logging_steps": 13,
|
223 |
+
"max_steps": 207,
|
224 |
+
"num_input_tokens_seen": 0,
|
225 |
+
"num_train_epochs": 3,
|
226 |
+
"save_steps": 500,
|
227 |
+
"total_flos": 0.0,
|
228 |
+
"train_batch_size": 2,
|
229 |
+
"trial_name": null,
|
230 |
+
"trial_params": null
|
231 |
+
}
|
checkpoint-207/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d64c109af6c5f1f4d56f908da5434d25bb340c76c0033059b374ee3ac80ba79
|
3 |
+
size 4728
|
checkpoint-207/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
handler.py
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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(base_model_path, trust_remote_code=True)
|
20 |
+
model = PeftModel.from_pretrained(model, path)
|
21 |
+
model = model.merge_and_unload()
|
22 |
+
self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
|
23 |
+
|
24 |
+
def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
|
25 |
+
inputs = data.pop("inputs", data)
|
26 |
+
parameters = data.pop("parameters", None)
|
27 |
+
if parameters is not None:
|
28 |
+
prediction = self.pipeline(inputs, **parameters)
|
29 |
+
else:
|
30 |
+
prediction = self.pipeline(inputs)
|
31 |
+
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==0.7.1
|
2 |
+
transformers==4.36.1
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "</s>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"1": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"2": {
|
14 |
+
"content": "</s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"bos_token": "</s>",
|
23 |
+
"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 %}",
|
24 |
+
"clean_up_tokenization_spaces": true,
|
25 |
+
"eos_token": "</s>",
|
26 |
+
"errors": "replace",
|
27 |
+
"model_max_length": 2048,
|
28 |
+
"pad_token": "<pad>",
|
29 |
+
"tokenizer_class": "GPT2Tokenizer",
|
30 |
+
"unk_token": "</s>"
|
31 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d64c109af6c5f1f4d56f908da5434d25bb340c76c0033059b374ee3ac80ba79
|
3 |
+
size 4728
|
training_params.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "facebook/opt-125m",
|
3 |
+
"project_name": "/tmp/model",
|
4 |
+
"data_path": "hibana2077/autotrain-data-TEST-3",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"add_eos_token": true,
|
8 |
+
"block_size": 1024,
|
9 |
+
"model_max_length": 2048,
|
10 |
+
"trainer": "dpo",
|
11 |
+
"use_flash_attention_2": false,
|
12 |
+
"log": "none",
|
13 |
+
"disable_gradient_checkpointing": false,
|
14 |
+
"logging_steps": -1,
|
15 |
+
"evaluation_strategy": "epoch",
|
16 |
+
"save_total_limit": 1,
|
17 |
+
"save_strategy": "epoch",
|
18 |
+
"auto_find_batch_size": false,
|
19 |
+
"mixed_precision": "fp16",
|
20 |
+
"lr": 3e-05,
|
21 |
+
"epochs": 3,
|
22 |
+
"batch_size": 2,
|
23 |
+
"warmup_ratio": 0.1,
|
24 |
+
"gradient_accumulation": 1,
|
25 |
+
"optimizer": "adamw_torch",
|
26 |
+
"scheduler": "linear",
|
27 |
+
"weight_decay": 0.0,
|
28 |
+
"max_grad_norm": 1.0,
|
29 |
+
"seed": 42,
|
30 |
+
"apply_chat_template": false,
|
31 |
+
"quantization": "int4",
|
32 |
+
"target_modules": "",
|
33 |
+
"merge_adapter": false,
|
34 |
+
"peft": true,
|
35 |
+
"lora_r": 16,
|
36 |
+
"lora_alpha": 32,
|
37 |
+
"lora_dropout": 0.05,
|
38 |
+
"model_ref": null,
|
39 |
+
"dpo_beta": 0.1,
|
40 |
+
"prompt_text_column": "autotrain_prompt",
|
41 |
+
"text_column": "autotrain_text",
|
42 |
+
"rejected_text_column": "autotrain_rejected_text",
|
43 |
+
"push_to_hub": true,
|
44 |
+
"repo_id": "hibana2077/TEST-3",
|
45 |
+
"username": "hibana2077"
|
46 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|