mjmanashti
commited on
Commit
•
c1429da
1
Parent(s):
a9060e6
Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +40 -0
- adapter_config.json +33 -0
- adapter_model.safetensors +3 -0
- checkpoint-396/README.md +202 -0
- checkpoint-396/adapter_config.json +33 -0
- checkpoint-396/adapter_model.safetensors +3 -0
- checkpoint-396/optimizer.pt +3 -0
- checkpoint-396/pytorch_model.bin +3 -0
- checkpoint-396/rng_state.pth +3 -0
- checkpoint-396/scheduler.pt +3 -0
- checkpoint-396/special_tokens_map.json +34 -0
- checkpoint-396/tokenizer.json +3 -0
- checkpoint-396/tokenizer.model +3 -0
- checkpoint-396/tokenizer_config.json +70 -0
- checkpoint-396/trainer_state.json +246 -0
- checkpoint-396/training_args.bin +3 -0
- handler.py +32 -0
- requirements.txt +2 -0
- runs/Mar16_15-42-24_r-mjmanashti-fine-tuning-vw6mcjeh-b4da6-f8cub/events.out.tfevents.1710603751.r-mjmanashti-fine-tuning-vw6mcjeh-b4da6-f8cub.55.0 +2 -2
- special_tokens_map.json +34 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +70 -0
- training_args.bin +3 -0
- training_params.json +47 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
checkpoint-396/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
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 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-2b-it",
|
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 |
+
"k_proj",
|
23 |
+
"up_proj",
|
24 |
+
"v_proj",
|
25 |
+
"q_proj",
|
26 |
+
"o_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"down_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_dora": false,
|
32 |
+
"use_rslora": false
|
33 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b169a1e1e4be8272649f1f3f736310ec9fac63a91867eca4ee74558c715968e
|
3 |
+
size 78480072
|
checkpoint-396/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: google/gemma-2b-it
|
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-396/adapter_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-2b-it",
|
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 |
+
"k_proj",
|
23 |
+
"up_proj",
|
24 |
+
"v_proj",
|
25 |
+
"q_proj",
|
26 |
+
"o_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"down_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_dora": false,
|
32 |
+
"use_rslora": false
|
33 |
+
}
|
checkpoint-396/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b169a1e1e4be8272649f1f3f736310ec9fac63a91867eca4ee74558c715968e
|
3 |
+
size 78480072
|
checkpoint-396/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26a4917c50959d9ebdb4fe5f89e0ecca27cec734375fd0a68e10b0c9698b4fbb
|
3 |
+
size 157104826
|
checkpoint-396/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
|
3 |
+
size 888
|
checkpoint-396/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-396/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d88d86fc4fb9e3ce481e45c3ba39b4c3c3510eb8f7006191533eafa8f076ea64
|
3 |
+
size 1064
|
checkpoint-396/special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<start_of_turn>",
|
4 |
+
"<end_of_turn>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<bos>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
checkpoint-396/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
|
3 |
+
size 17477929
|
checkpoint-396/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
checkpoint-396/tokenizer_config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"106": {
|
38 |
+
"content": "<start_of_turn>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"107": {
|
46 |
+
"content": "<end_of_turn>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"additional_special_tokens": [
|
55 |
+
"<start_of_turn>",
|
56 |
+
"<end_of_turn>"
|
57 |
+
],
|
58 |
+
"bos_token": "<bos>",
|
59 |
+
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
60 |
+
"clean_up_tokenization_spaces": false,
|
61 |
+
"eos_token": "<eos>",
|
62 |
+
"legacy": null,
|
63 |
+
"model_max_length": 2048,
|
64 |
+
"pad_token": "<pad>",
|
65 |
+
"sp_model_kwargs": {},
|
66 |
+
"spaces_between_special_tokens": false,
|
67 |
+
"tokenizer_class": "GemmaTokenizer",
|
68 |
+
"unk_token": "<unk>",
|
69 |
+
"use_default_system_prompt": false
|
70 |
+
}
|
checkpoint-396/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": 396,
|
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": 0.0009370408370159566,
|
14 |
+
"learning_rate": 1.95e-05,
|
15 |
+
"logits/chosen": -22.68578338623047,
|
16 |
+
"logits/rejected": -22.825130462646484,
|
17 |
+
"logps/chosen": -78.43010711669922,
|
18 |
+
"logps/rejected": -102.63253784179688,
|
19 |
+
"loss": 0.1807,
|
20 |
+
"rewards/accuracies": 0.9230769276618958,
|
21 |
+
"rewards/chosen": 2.8142247200012207,
|
22 |
+
"rewards/margins": 4.811609268188477,
|
23 |
+
"rewards/rejected": -1.997384786605835,
|
24 |
+
"step": 26
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.39,
|
28 |
+
"grad_norm": 2.192274041590281e-05,
|
29 |
+
"learning_rate": 2.8988764044943823e-05,
|
30 |
+
"logits/chosen": -23.15672492980957,
|
31 |
+
"logits/rejected": -23.271657943725586,
|
32 |
+
"logps/chosen": -43.96305465698242,
|
33 |
+
"logps/rejected": -155.8493194580078,
|
34 |
+
"loss": 0.0,
|
35 |
+
"rewards/accuracies": 1.0,
|
36 |
+
"rewards/chosen": 6.304109573364258,
|
37 |
+
"rewards/margins": 13.57724380493164,
|
38 |
+
"rewards/rejected": -7.273132801055908,
|
39 |
+
"step": 52
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.59,
|
43 |
+
"grad_norm": 1.914922904688865e-05,
|
44 |
+
"learning_rate": 2.6797752808988762e-05,
|
45 |
+
"logits/chosen": -23.230398178100586,
|
46 |
+
"logits/rejected": -23.34272575378418,
|
47 |
+
"logps/chosen": -42.47319030761719,
|
48 |
+
"logps/rejected": -166.07025146484375,
|
49 |
+
"loss": 0.0,
|
50 |
+
"rewards/accuracies": 1.0,
|
51 |
+
"rewards/chosen": 6.426936149597168,
|
52 |
+
"rewards/margins": 14.743646621704102,
|
53 |
+
"rewards/rejected": -8.316710472106934,
|
54 |
+
"step": 78
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.79,
|
58 |
+
"grad_norm": 1.923706804518588e-05,
|
59 |
+
"learning_rate": 2.4606741573033708e-05,
|
60 |
+
"logits/chosen": -23.297359466552734,
|
61 |
+
"logits/rejected": -23.406126022338867,
|
62 |
+
"logps/chosen": -42.298927307128906,
|
63 |
+
"logps/rejected": -167.82479858398438,
|
64 |
+
"loss": 0.0,
|
65 |
+
"rewards/accuracies": 1.0,
|
66 |
+
"rewards/chosen": 6.4410505294799805,
|
67 |
+
"rewards/margins": 14.930893898010254,
|
68 |
+
"rewards/rejected": -8.48984432220459,
|
69 |
+
"step": 104
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.98,
|
73 |
+
"grad_norm": 0.00013795163249596953,
|
74 |
+
"learning_rate": 2.2415730337078654e-05,
|
75 |
+
"logits/chosen": -23.36400032043457,
|
76 |
+
"logits/rejected": -23.47435760498047,
|
77 |
+
"logps/chosen": -42.36582565307617,
|
78 |
+
"logps/rejected": -167.81008911132812,
|
79 |
+
"loss": 0.0,
|
80 |
+
"rewards/accuracies": 1.0,
|
81 |
+
"rewards/chosen": 6.42643404006958,
|
82 |
+
"rewards/margins": 14.924281120300293,
|
83 |
+
"rewards/rejected": -8.497847557067871,
|
84 |
+
"step": 130
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.18,
|
88 |
+
"grad_norm": 1.9170562154613435e-05,
|
89 |
+
"learning_rate": 2.0224719101123596e-05,
|
90 |
+
"logits/chosen": -23.275028228759766,
|
91 |
+
"logits/rejected": -23.385255813598633,
|
92 |
+
"logps/chosen": -42.21509552001953,
|
93 |
+
"logps/rejected": -167.64584350585938,
|
94 |
+
"loss": 0.0,
|
95 |
+
"rewards/accuracies": 1.0,
|
96 |
+
"rewards/chosen": 6.436044692993164,
|
97 |
+
"rewards/margins": 14.92562198638916,
|
98 |
+
"rewards/rejected": -8.48957633972168,
|
99 |
+
"step": 156
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 1.38,
|
103 |
+
"grad_norm": 1.7988468243856914e-05,
|
104 |
+
"learning_rate": 1.803370786516854e-05,
|
105 |
+
"logits/chosen": -23.300710678100586,
|
106 |
+
"logits/rejected": -23.410503387451172,
|
107 |
+
"logps/chosen": -42.11836624145508,
|
108 |
+
"logps/rejected": -169.15122985839844,
|
109 |
+
"loss": 0.0,
|
110 |
+
"rewards/accuracies": 1.0,
|
111 |
+
"rewards/chosen": 6.481032371520996,
|
112 |
+
"rewards/margins": 15.097738265991211,
|
113 |
+
"rewards/rejected": -8.616707801818848,
|
114 |
+
"step": 182
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.58,
|
118 |
+
"grad_norm": 2.1618798200506717e-05,
|
119 |
+
"learning_rate": 1.5842696629213484e-05,
|
120 |
+
"logits/chosen": -23.332603454589844,
|
121 |
+
"logits/rejected": -23.443927764892578,
|
122 |
+
"logps/chosen": -42.54871368408203,
|
123 |
+
"logps/rejected": -167.39431762695312,
|
124 |
+
"loss": 0.0,
|
125 |
+
"rewards/accuracies": 1.0,
|
126 |
+
"rewards/chosen": 6.385127067565918,
|
127 |
+
"rewards/margins": 14.849527359008789,
|
128 |
+
"rewards/rejected": -8.464401245117188,
|
129 |
+
"step": 208
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 1.77,
|
133 |
+
"grad_norm": 1.6424854038632475e-05,
|
134 |
+
"learning_rate": 1.3651685393258428e-05,
|
135 |
+
"logits/chosen": -23.301807403564453,
|
136 |
+
"logits/rejected": -23.41258430480957,
|
137 |
+
"logps/chosen": -42.13775634765625,
|
138 |
+
"logps/rejected": -168.62362670898438,
|
139 |
+
"loss": 0.0,
|
140 |
+
"rewards/accuracies": 1.0,
|
141 |
+
"rewards/chosen": 6.500583171844482,
|
142 |
+
"rewards/margins": 15.051546096801758,
|
143 |
+
"rewards/rejected": -8.550962448120117,
|
144 |
+
"step": 234
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 1.97,
|
148 |
+
"grad_norm": 1.6196921933442354e-05,
|
149 |
+
"learning_rate": 1.146067415730337e-05,
|
150 |
+
"logits/chosen": -23.335044860839844,
|
151 |
+
"logits/rejected": -23.44767951965332,
|
152 |
+
"logps/chosen": -42.26608657836914,
|
153 |
+
"logps/rejected": -167.9331817626953,
|
154 |
+
"loss": 0.0,
|
155 |
+
"rewards/accuracies": 1.0,
|
156 |
+
"rewards/chosen": 6.42073917388916,
|
157 |
+
"rewards/margins": 14.927839279174805,
|
158 |
+
"rewards/rejected": -8.507099151611328,
|
159 |
+
"step": 260
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 2.17,
|
163 |
+
"grad_norm": 1.7393831512890756e-05,
|
164 |
+
"learning_rate": 9.269662921348314e-06,
|
165 |
+
"logits/chosen": -23.317138671875,
|
166 |
+
"logits/rejected": -23.424781799316406,
|
167 |
+
"logps/chosen": -41.94506072998047,
|
168 |
+
"logps/rejected": -168.30055236816406,
|
169 |
+
"loss": 0.0,
|
170 |
+
"rewards/accuracies": 1.0,
|
171 |
+
"rewards/chosen": 6.4749298095703125,
|
172 |
+
"rewards/margins": 15.034900665283203,
|
173 |
+
"rewards/rejected": -8.55997085571289,
|
174 |
+
"step": 286
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 2.36,
|
178 |
+
"grad_norm": 1.7613503587199375e-05,
|
179 |
+
"learning_rate": 7.078651685393258e-06,
|
180 |
+
"logits/chosen": -23.292570114135742,
|
181 |
+
"logits/rejected": -23.40188217163086,
|
182 |
+
"logps/chosen": -42.209102630615234,
|
183 |
+
"logps/rejected": -169.81747436523438,
|
184 |
+
"loss": 0.0,
|
185 |
+
"rewards/accuracies": 1.0,
|
186 |
+
"rewards/chosen": 6.467267990112305,
|
187 |
+
"rewards/margins": 15.145313262939453,
|
188 |
+
"rewards/rejected": -8.678045272827148,
|
189 |
+
"step": 312
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 2.56,
|
193 |
+
"grad_norm": 0.0001227569446200505,
|
194 |
+
"learning_rate": 4.8876404494382024e-06,
|
195 |
+
"logits/chosen": -23.324228286743164,
|
196 |
+
"logits/rejected": -23.43165397644043,
|
197 |
+
"logps/chosen": -41.959617614746094,
|
198 |
+
"logps/rejected": -169.5789337158203,
|
199 |
+
"loss": 0.0,
|
200 |
+
"rewards/accuracies": 1.0,
|
201 |
+
"rewards/chosen": 6.512591361999512,
|
202 |
+
"rewards/margins": 15.166027069091797,
|
203 |
+
"rewards/rejected": -8.653436660766602,
|
204 |
+
"step": 338
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 2.76,
|
208 |
+
"grad_norm": 1.6931946447584778e-05,
|
209 |
+
"learning_rate": 2.696629213483146e-06,
|
210 |
+
"logits/chosen": -23.30262565612793,
|
211 |
+
"logits/rejected": -23.414592742919922,
|
212 |
+
"logps/chosen": -42.351627349853516,
|
213 |
+
"logps/rejected": -168.41354370117188,
|
214 |
+
"loss": 0.0,
|
215 |
+
"rewards/accuracies": 1.0,
|
216 |
+
"rewards/chosen": 6.420273780822754,
|
217 |
+
"rewards/margins": 14.962029457092285,
|
218 |
+
"rewards/rejected": -8.541756629943848,
|
219 |
+
"step": 364
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.95,
|
223 |
+
"grad_norm": 1.576123213453684e-05,
|
224 |
+
"learning_rate": 5.056179775280899e-07,
|
225 |
+
"logits/chosen": -23.35226058959961,
|
226 |
+
"logits/rejected": -23.466854095458984,
|
227 |
+
"logps/chosen": -42.21808624267578,
|
228 |
+
"logps/rejected": -168.39918518066406,
|
229 |
+
"loss": 0.0,
|
230 |
+
"rewards/accuracies": 1.0,
|
231 |
+
"rewards/chosen": 6.449341297149658,
|
232 |
+
"rewards/margins": 15.006133079528809,
|
233 |
+
"rewards/rejected": -8.556791305541992,
|
234 |
+
"step": 390
|
235 |
+
}
|
236 |
+
],
|
237 |
+
"logging_steps": 26,
|
238 |
+
"max_steps": 396,
|
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-396/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb860eaf85aafc1d3412d367086a23dd15fa1fb7758535b990646abd0a91e3ec
|
3 |
+
size 4920
|
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
|
requirements.txt
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
peft==0.9.0
|
2 |
+
transformers==4.38.2
|
runs/Mar16_15-42-24_r-mjmanashti-fine-tuning-vw6mcjeh-b4da6-f8cub/events.out.tfevents.1710603751.r-mjmanashti-fine-tuning-vw6mcjeh-b4da6-f8cub.55.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3414fcd2baf9e09cfa899d3f19599fccb0418ffd79e19709f875fcd1c340bb4d
|
3 |
+
size 15673
|
special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<start_of_turn>",
|
4 |
+
"<end_of_turn>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<bos>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
|
3 |
+
size 17477929
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
tokenizer_config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"106": {
|
38 |
+
"content": "<start_of_turn>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"107": {
|
46 |
+
"content": "<end_of_turn>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"additional_special_tokens": [
|
55 |
+
"<start_of_turn>",
|
56 |
+
"<end_of_turn>"
|
57 |
+
],
|
58 |
+
"bos_token": "<bos>",
|
59 |
+
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
60 |
+
"clean_up_tokenization_spaces": false,
|
61 |
+
"eos_token": "<eos>",
|
62 |
+
"legacy": null,
|
63 |
+
"model_max_length": 2048,
|
64 |
+
"pad_token": "<pad>",
|
65 |
+
"sp_model_kwargs": {},
|
66 |
+
"spaces_between_special_tokens": false,
|
67 |
+
"tokenizer_class": "GemmaTokenizer",
|
68 |
+
"unk_token": "<unk>",
|
69 |
+
"use_default_system_prompt": false
|
70 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb860eaf85aafc1d3412d367086a23dd15fa1fb7758535b990646abd0a91e3ec
|
3 |
+
size 4920
|
training_params.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "google/gemma-2b-it",
|
3 |
+
"project_name": "autotrain-gemma",
|
4 |
+
"data_path": "autotrain-gemma/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": "mjmanashti/autotrain-gemma",
|
46 |
+
"username": "mjmanashti"
|
47 |
+
}
|