Upload LoRA adapter files
Browse files- .gitattributes +1 -0
- README.md +185 -209
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +24 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +209 -0
- trainer_state.json +161 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,226 +1,202 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
4 |
-
library_name:
|
5 |
-
|
6 |
-
- translation
|
7 |
-
- chinese
|
8 |
-
- indonesian
|
9 |
-
- qwen
|
10 |
-
- lora
|
11 |
-
- fine-tuned
|
12 |
-
- traditional-chinese
|
13 |
-
- news
|
14 |
|
15 |
-
|
16 |
-
- name: Royal_ZhTW-ID_finetuned_101
|
17 |
-
results: []
|
18 |
|
19 |
-
|
20 |
-
- zh
|
21 |
-
- id
|
22 |
|
23 |
|
24 |
|
25 |
-
|
26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
|
28 |
-
|
29 |
|
30 |
-
|
31 |
|
32 |
-
|
33 |
|
34 |
-
This
|
35 |
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
|
|
|
|
41 |
|
42 |
## Training Details
|
43 |
|
44 |
-
###
|
45 |
-
- **Base Model**: Qwen/Qwen2.5-7B-Instruct
|
46 |
-
- **Model Type**: Causal Language Model with Translation Capabilities
|
47 |
-
|
48 |
-
### Fine-tuning Configuration
|
49 |
-
- **Method**: LoRA (Low-Rank Adaptation)
|
50 |
-
- **LoRA Rank**: 8
|
51 |
-
- **LoRA Alpha**: 32
|
52 |
-
- **Learning Rate**: 2e-4
|
53 |
-
- **Training Epochs**: 3
|
54 |
-
- **Max Samples**: 1,000 (initial validation)
|
55 |
-
- **Template**: Qwen conversation format
|
56 |
-
|
57 |
-
### Dataset
|
58 |
-
- **Source**: Taiwan NEWS in Traditional Chinese with Indonesian translations
|
59 |
-
- **Editor**: Chang, Yo Han
|
60 |
-
- **Domain**: News articles and formal text
|
61 |
-
- **Language Pair**: Traditional Chinese (zh-TW) ↔ Indonesian (id)
|
62 |
-
- **Note**: Dataset is proprietary and not publicly available on HuggingFace
|
63 |
-
|
64 |
-
## Usage
|
65 |
-
|
66 |
-
### Installation
|
67 |
-
```bash
|
68 |
-
pip install transformers torch
|
69 |
-
```
|
70 |
-
|
71 |
-
### Basic Usage
|
72 |
-
```python
|
73 |
-
from transformers import AutoModelForCausalLM, AutoTokenizer
|
74 |
-
import torch
|
75 |
-
|
76 |
-
# Load model and tokenizer
|
77 |
-
model_name = "roylin1003/Royal_ZhTW-ID_finetuned_101"
|
78 |
-
model = AutoModelForCausalLM.from_pretrained(
|
79 |
-
model_name,
|
80 |
-
torch_dtype=torch.float16,
|
81 |
-
device_map="auto"
|
82 |
-
)
|
83 |
-
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
84 |
-
|
85 |
-
# Translation function
|
86 |
-
def translate_text(text, source_lang="zh", target_lang="id"):
|
87 |
-
if source_lang == "zh" and target_lang == "id":
|
88 |
-
prompt = f"請將以下中文翻譯成印尼文:{text}"
|
89 |
-
elif source_lang == "id" and target_lang == "zh":
|
90 |
-
prompt = f"Terjemahkan teks bahasa Indonesia berikut ke bahasa Tionghoa: {text}"
|
91 |
-
|
92 |
-
messages = [
|
93 |
-
{"role": "user", "content": prompt}
|
94 |
-
]
|
95 |
-
|
96 |
-
text = tokenizer.apply_chat_template(
|
97 |
-
messages,
|
98 |
-
tokenize=False,
|
99 |
-
add_generation_prompt=True
|
100 |
-
)
|
101 |
-
|
102 |
-
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
103 |
-
|
104 |
-
generated_ids = model.generate(
|
105 |
-
**model_inputs,
|
106 |
-
max_new_tokens=512,
|
107 |
-
do_sample=True,
|
108 |
-
temperature=0.7,
|
109 |
-
pad_token_id=tokenizer.eos_token_id
|
110 |
-
)
|
111 |
-
|
112 |
-
generated_ids = [
|
113 |
-
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
114 |
-
]
|
115 |
-
|
116 |
-
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
117 |
-
return response
|
118 |
-
|
119 |
-
# Example usage
|
120 |
-
chinese_text = "台灣的科技產業發展迅速,特別是在半導體領域。"
|
121 |
-
indonesian_translation = translate_text(chinese_text, "zh", "id")
|
122 |
-
print(f"Chinese: {chinese_text}")
|
123 |
-
print(f"Indonesian: {indonesian_translation}")
|
124 |
-
|
125 |
-
indonesian_text = "Indonesia adalah negara kepulauan terbesar di dunia."
|
126 |
-
chinese_translation = translate_text(indonesian_text, "id", "zh")
|
127 |
-
print(f"Indonesian: {indonesian_text}")
|
128 |
-
print(f"Chinese: {chinese_translation}")
|
129 |
-
```
|
130 |
-
|
131 |
-
### Advanced Usage with Custom Parameters
|
132 |
-
```python
|
133 |
-
def translate_with_options(text, source_lang="zh", target_lang="id", temperature=0.7, max_tokens=512):
|
134 |
-
# ... (same setup as above)
|
135 |
-
|
136 |
-
generated_ids = model.generate(
|
137 |
-
**model_inputs,
|
138 |
-
max_new_tokens=max_tokens,
|
139 |
-
do_sample=True,
|
140 |
-
temperature=temperature,
|
141 |
-
top_p=0.9,
|
142 |
-
repetition_penalty=1.1,
|
143 |
-
pad_token_id=tokenizer.eos_token_id
|
144 |
-
)
|
145 |
-
|
146 |
-
# ... (same decoding as above)
|
147 |
-
return response
|
148 |
-
```
|
149 |
-
|
150 |
-
## Model Performance
|
151 |
-
|
152 |
-
### Training Metrics
|
153 |
-
- **Training Loss**: Converged after 3 epochs
|
154 |
-
- **Learning Rate**: 2e-4 with linear decay
|
155 |
-
- **Batch Size**: Optimized for available GPU memory
|
156 |
-
|
157 |
-
### Evaluation
|
158 |
-
This model has been trained on a curated dataset of Taiwan news articles with Indonesian translations. Performance evaluation is ongoing.
|
159 |
-
|
160 |
-
## Limitations and Considerations
|
161 |
-
|
162 |
-
### Known Limitations
|
163 |
-
- **Domain Specificity**: Optimized for news and formal text; may not perform as well on casual conversation
|
164 |
-
- **Training Data Size**: Initial training used 1,000 samples for quick validation
|
165 |
-
- **Cultural Context**: May require additional fine-tuning for region-specific terminology
|
166 |
-
|
167 |
-
### Recommended Use Cases
|
168 |
-
- 📰 News article translation
|
169 |
-
- 📄 Formal document translation
|
170 |
-
- 🏢 Business communication between Taiwan and Indonesia
|
171 |
-
- 📚 Educational content translation
|
172 |
-
|
173 |
-
### Not Recommended For
|
174 |
-
- Real-time conversation (use specialized conversational models)
|
175 |
-
- Medical or legal documents (requires domain-specific models)
|
176 |
-
- Creative writing (may lack stylistic nuance)
|
177 |
-
|
178 |
-
## Training Infrastructure
|
179 |
-
|
180 |
-
### Hardware Requirements
|
181 |
-
- **Minimum**: GPU with 16GB VRAM
|
182 |
-
- **Recommended**: GPU with 24GB+ VRAM for optimal performance
|
183 |
-
- **Training Time**: Approximately 2-3 hours on modern GPUs
|
184 |
-
|
185 |
-
### Software Dependencies
|
186 |
-
```
|
187 |
-
transformers>=4.36.0
|
188 |
-
torch>=2.0.0
|
189 |
-
peft>=0.7.0
|
190 |
-
datasets>=2.15.0
|
191 |
-
```
|
192 |
-
|
193 |
-
## Citation
|
194 |
-
|
195 |
-
If you use this model in your research or applications, please cite:
|
196 |
-
|
197 |
-
```bibtex
|
198 |
-
@misc{Royal_ZhTW-ID_finetuned_101,
|
199 |
-
title={Qwen2.5-7B Traditional Chinese-Indonesian Translation Model},
|
200 |
-
author={Roy Lin},
|
201 |
-
year={2024},
|
202 |
-
howpublished={\url{https://huggingface.co/roylin1003/Royal_ZhTW-ID_finetuned_101}},
|
203 |
-
note={Fine-tuned on Taiwan news corpus edited by Chang, Yo Han}
|
204 |
-
}
|
205 |
-
```
|
206 |
-
|
207 |
-
## Acknowledgments
|
208 |
-
|
209 |
-
- **Base Model**: Thanks to the Qwen team for the excellent Qwen2.5-7B-Instruct model
|
210 |
-
- **Dataset**: Taiwan news corpus with Indonesian translations edited by Chang, Yo Han
|
211 |
-
- **Framework**: Built using Hugging Face Transformers and PEFT libraries
|
212 |
-
|
213 |
-
## License
|
214 |
-
|
215 |
-
This model is released under the Apache 2.0 License, consistent with the base Qwen2.5-7B-Instruct model.
|
216 |
-
|
217 |
-
## Contact
|
218 |
-
|
219 |
-
For questions, issues, or collaborations, please open an issue in this repository or contact [your contact information].
|
220 |
|
221 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
222 |
|
223 |
-
|
224 |
-
**Last Updated**: [Current Date]
|
225 |
-
**Status**: Initial Release - Validation Phase
|
226 |
-
---
|
|
|
1 |
---
|
|
|
2 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
3 |
+
library_name: peft
|
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 0.15.2
|
|
|
|
|
|
adapter_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 32,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"r": 8,
|
24 |
+
"rank_pattern": {},
|
25 |
+
"revision": null,
|
26 |
+
"target_modules": [
|
27 |
+
"v_proj",
|
28 |
+
"k_proj",
|
29 |
+
"gate_proj",
|
30 |
+
"q_proj",
|
31 |
+
"down_proj",
|
32 |
+
"o_proj",
|
33 |
+
"up_proj"
|
34 |
+
],
|
35 |
+
"task_type": "CAUSAL_LM",
|
36 |
+
"trainable_token_indices": null,
|
37 |
+
"use_dora": false,
|
38 |
+
"use_rslora": false
|
39 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51dcb43b9960d8a9c682afd0bd188035a057ba3fa09bcdfea674958151b84dd8
|
3 |
+
size 80792096
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a08eb0e13acb36a2b14ded8699fa03e315d5e3c62fe06ac9737f13f5d709eac2
|
3 |
+
size 161810747
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e06eb521f4bc09fafc1ed3c99e0294e570a0582bcbe0b52111436c2f9220ecff
|
3 |
+
size 14645
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c116af82c2f3174e078bbcd016eaac335b84bb334076fdde7b60a3390b2cb757
|
3 |
+
size 1465
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 131072,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"padding_side": "right",
|
206 |
+
"split_special_tokens": false,
|
207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
+
"unk_token": null
|
209 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 84,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.17857142857142858,
|
13 |
+
"grad_norm": 1.3622558116912842,
|
14 |
+
"learning_rate": 0.00019825664732332884,
|
15 |
+
"loss": 1.4496,
|
16 |
+
"num_input_tokens_seen": 15664,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.35714285714285715,
|
21 |
+
"grad_norm": 0.8986290097236633,
|
22 |
+
"learning_rate": 0.00019308737486442045,
|
23 |
+
"loss": 1.051,
|
24 |
+
"num_input_tokens_seen": 30528,
|
25 |
+
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.5357142857142857,
|
29 |
+
"grad_norm": 1.14683997631073,
|
30 |
+
"learning_rate": 0.00018467241992282843,
|
31 |
+
"loss": 0.9827,
|
32 |
+
"num_input_tokens_seen": 43392,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.7142857142857143,
|
37 |
+
"grad_norm": 0.8037276864051819,
|
38 |
+
"learning_rate": 0.00017330518718298264,
|
39 |
+
"loss": 1.0249,
|
40 |
+
"num_input_tokens_seen": 60784,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.8928571428571429,
|
45 |
+
"grad_norm": 0.8258629441261292,
|
46 |
+
"learning_rate": 0.00015938201855735014,
|
47 |
+
"loss": 0.9651,
|
48 |
+
"num_input_tokens_seen": 76080,
|
49 |
+
"step": 25
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 1.0714285714285714,
|
53 |
+
"grad_norm": 0.9029279947280884,
|
54 |
+
"learning_rate": 0.00014338837391175582,
|
55 |
+
"loss": 0.9298,
|
56 |
+
"num_input_tokens_seen": 90224,
|
57 |
+
"step": 30
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.25,
|
61 |
+
"grad_norm": 0.8744432926177979,
|
62 |
+
"learning_rate": 0.00012588190451025207,
|
63 |
+
"loss": 0.7694,
|
64 |
+
"num_input_tokens_seen": 107072,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.4285714285714286,
|
69 |
+
"grad_norm": 1.3319528102874756,
|
70 |
+
"learning_rate": 0.00010747300935864243,
|
71 |
+
"loss": 0.6823,
|
72 |
+
"num_input_tokens_seen": 123216,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 1.6071428571428572,
|
77 |
+
"grad_norm": 1.1126036643981934,
|
78 |
+
"learning_rate": 8.880355238966923e-05,
|
79 |
+
"loss": 0.5681,
|
80 |
+
"num_input_tokens_seen": 138416,
|
81 |
+
"step": 45
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 1.7857142857142856,
|
85 |
+
"grad_norm": 1.8243435621261597,
|
86 |
+
"learning_rate": 7.052448255890957e-05,
|
87 |
+
"loss": 0.6239,
|
88 |
+
"num_input_tokens_seen": 152784,
|
89 |
+
"step": 50
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 1.9642857142857144,
|
93 |
+
"grad_norm": 1.5611317157745361,
|
94 |
+
"learning_rate": 5.32731371726938e-05,
|
95 |
+
"loss": 0.6441,
|
96 |
+
"num_input_tokens_seen": 167264,
|
97 |
+
"step": 55
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 2.142857142857143,
|
101 |
+
"grad_norm": 1.1920043230056763,
|
102 |
+
"learning_rate": 3.7651019814126654e-05,
|
103 |
+
"loss": 0.5202,
|
104 |
+
"num_input_tokens_seen": 181488,
|
105 |
+
"step": 60
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 2.3214285714285716,
|
109 |
+
"grad_norm": 1.1858474016189575,
|
110 |
+
"learning_rate": 2.420282768545469e-05,
|
111 |
+
"loss": 0.443,
|
112 |
+
"num_input_tokens_seen": 198512,
|
113 |
+
"step": 65
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 2.5,
|
117 |
+
"grad_norm": 1.2865468263626099,
|
118 |
+
"learning_rate": 1.339745962155613e-05,
|
119 |
+
"loss": 0.4209,
|
120 |
+
"num_input_tokens_seen": 213040,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 2.678571428571429,
|
125 |
+
"grad_norm": 1.2891031503677368,
|
126 |
+
"learning_rate": 5.611666969163243e-06,
|
127 |
+
"loss": 0.4818,
|
128 |
+
"num_input_tokens_seen": 229312,
|
129 |
+
"step": 75
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 2.857142857142857,
|
133 |
+
"grad_norm": 1.2530392408370972,
|
134 |
+
"learning_rate": 1.1169173774871478e-06,
|
135 |
+
"loss": 0.5292,
|
136 |
+
"num_input_tokens_seen": 244944,
|
137 |
+
"step": 80
|
138 |
+
}
|
139 |
+
],
|
140 |
+
"logging_steps": 5,
|
141 |
+
"max_steps": 84,
|
142 |
+
"num_input_tokens_seen": 257136,
|
143 |
+
"num_train_epochs": 3,
|
144 |
+
"save_steps": 100,
|
145 |
+
"stateful_callbacks": {
|
146 |
+
"TrainerControl": {
|
147 |
+
"args": {
|
148 |
+
"should_epoch_stop": false,
|
149 |
+
"should_evaluate": false,
|
150 |
+
"should_log": false,
|
151 |
+
"should_save": true,
|
152 |
+
"should_training_stop": true
|
153 |
+
},
|
154 |
+
"attributes": {}
|
155 |
+
}
|
156 |
+
},
|
157 |
+
"total_flos": 1.0939806209654784e+16,
|
158 |
+
"train_batch_size": 2,
|
159 |
+
"trial_name": null,
|
160 |
+
"trial_params": null
|
161 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c68e266ff6102efbfeb979fc3ee99077812f4582306ac4bb0790f31cc7d63db
|
3 |
+
size 6161
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|