Upload PEFT LoRA adapter
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +35 -0
- README.md +3 -3
- checkpoint-100/README.md +208 -0
- checkpoint-100/adapter_config.json +39 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/added_tokens.json +12 -0
- checkpoint-100/chat_template.jinja +1 -0
- checkpoint-100/merges.txt +0 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +30 -0
- checkpoint-100/tokenizer.json +3 -0
- checkpoint-100/tokenizer_config.json +111 -0
- checkpoint-100/trainer_state.json +124 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-100/vocab.json +0 -0
- checkpoint-1000/README.md +208 -0
- checkpoint-1000/adapter_config.json +39 -0
- checkpoint-1000/adapter_model.safetensors +3 -0
- checkpoint-1000/added_tokens.json +12 -0
- checkpoint-1000/chat_template.jinja +1 -0
- checkpoint-1000/merges.txt +0 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +30 -0
- checkpoint-1000/tokenizer.json +3 -0
- checkpoint-1000/tokenizer_config.json +111 -0
- checkpoint-1000/trainer_state.json +934 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1000/vocab.json +0 -0
- checkpoint-1100/README.md +208 -0
- checkpoint-1100/adapter_config.json +39 -0
- checkpoint-1100/adapter_model.safetensors +3 -0
- checkpoint-1100/added_tokens.json +12 -0
- checkpoint-1100/chat_template.jinja +1 -0
- checkpoint-1100/merges.txt +0 -0
- checkpoint-1100/optimizer.pt +3 -0
- checkpoint-1100/rng_state.pth +3 -0
- checkpoint-1100/scheduler.pt +3 -0
- checkpoint-1100/special_tokens_map.json +30 -0
- checkpoint-1100/tokenizer.json +3 -0
- checkpoint-1100/tokenizer_config.json +111 -0
- checkpoint-1100/trainer_state.json +1024 -0
- checkpoint-1100/training_args.bin +3 -0
- checkpoint-1100/vocab.json +0 -0
- checkpoint-1200/README.md +208 -0
- checkpoint-1200/adapter_config.json +39 -0
- checkpoint-1200/adapter_model.safetensors +3 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,38 @@ saved_model/**/* 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 37 |
+
checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
checkpoint-1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
checkpoint-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
checkpoint-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
checkpoint-1700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
checkpoint-1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
checkpoint-2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
checkpoint-2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
checkpoint-2300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
checkpoint-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
checkpoint-2600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
checkpoint-2700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
checkpoint-2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
checkpoint-2900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
checkpoint-3100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
checkpoint-3200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
checkpoint-3230/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 66 |
+
checkpoint-45/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -4,8 +4,8 @@ library_name: transformers
|
|
| 4 |
model_name: phi4-mini-chris-assistant-richard-adapter
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- sft
|
| 8 |
- trl
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
@@ -20,14 +20,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
| 20 |
from transformers import pipeline
|
| 21 |
|
| 22 |
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
-
generator = pipeline("text-generation", model="
|
| 24 |
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
print(output["generated_text"])
|
| 26 |
```
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/richardprobe-affirm/phi4-sft/runs/
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
|
|
|
| 4 |
model_name: phi4-mini-chris-assistant-richard-adapter
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- trl
|
| 8 |
+
- sft
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
|
|
| 20 |
from transformers import pipeline
|
| 21 |
|
| 22 |
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="None", device="cuda")
|
| 24 |
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
print(output["generated_text"])
|
| 26 |
```
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/richardprobe-affirm/phi4-sft/runs/yaqz10qw)
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/Phi-4-mini-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:microsoft/Phi-4-mini-instruct
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- trl
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Model ID
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
|
| 22 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
- **Developed by:** [More Information Needed]
|
| 27 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 28 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 29 |
+
- **Model type:** [More Information Needed]
|
| 30 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 31 |
+
- **License:** [More Information Needed]
|
| 32 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 33 |
+
|
| 34 |
+
### Model Sources [optional]
|
| 35 |
+
|
| 36 |
+
<!-- Provide the basic links for the model. -->
|
| 37 |
+
|
| 38 |
+
- **Repository:** [More Information Needed]
|
| 39 |
+
- **Paper [optional]:** [More Information Needed]
|
| 40 |
+
- **Demo [optional]:** [More Information Needed]
|
| 41 |
+
|
| 42 |
+
## Uses
|
| 43 |
+
|
| 44 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 45 |
+
|
| 46 |
+
### Direct Use
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Downstream Use [optional]
|
| 53 |
+
|
| 54 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
### Out-of-Scope Use
|
| 59 |
+
|
| 60 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
## Bias, Risks, and Limitations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 67 |
+
|
| 68 |
+
[More Information Needed]
|
| 69 |
+
|
| 70 |
+
### Recommendations
|
| 71 |
+
|
| 72 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 73 |
+
|
| 74 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 75 |
+
|
| 76 |
+
## How to Get Started with the Model
|
| 77 |
+
|
| 78 |
+
Use the code below to get started with the model.
|
| 79 |
+
|
| 80 |
+
[More Information Needed]
|
| 81 |
+
|
| 82 |
+
## Training Details
|
| 83 |
+
|
| 84 |
+
### Training Data
|
| 85 |
+
|
| 86 |
+
<!-- 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. -->
|
| 87 |
+
|
| 88 |
+
[More Information Needed]
|
| 89 |
+
|
| 90 |
+
### Training Procedure
|
| 91 |
+
|
| 92 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 93 |
+
|
| 94 |
+
#### Preprocessing [optional]
|
| 95 |
+
|
| 96 |
+
[More Information Needed]
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
#### Training Hyperparameters
|
| 100 |
+
|
| 101 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 102 |
+
|
| 103 |
+
#### Speeds, Sizes, Times [optional]
|
| 104 |
+
|
| 105 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 106 |
+
|
| 107 |
+
[More Information Needed]
|
| 108 |
+
|
| 109 |
+
## Evaluation
|
| 110 |
+
|
| 111 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 112 |
+
|
| 113 |
+
### Testing Data, Factors & Metrics
|
| 114 |
+
|
| 115 |
+
#### Testing Data
|
| 116 |
+
|
| 117 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Factors
|
| 122 |
+
|
| 123 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
#### Metrics
|
| 128 |
+
|
| 129 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 130 |
+
|
| 131 |
+
[More Information Needed]
|
| 132 |
+
|
| 133 |
+
### Results
|
| 134 |
+
|
| 135 |
+
[More Information Needed]
|
| 136 |
+
|
| 137 |
+
#### Summary
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Model Examination [optional]
|
| 142 |
+
|
| 143 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 144 |
+
|
| 145 |
+
[More Information Needed]
|
| 146 |
+
|
| 147 |
+
## Environmental Impact
|
| 148 |
+
|
| 149 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 150 |
+
|
| 151 |
+
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).
|
| 152 |
+
|
| 153 |
+
- **Hardware Type:** [More Information Needed]
|
| 154 |
+
- **Hours used:** [More Information Needed]
|
| 155 |
+
- **Cloud Provider:** [More Information Needed]
|
| 156 |
+
- **Compute Region:** [More Information Needed]
|
| 157 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 158 |
+
|
| 159 |
+
## Technical Specifications [optional]
|
| 160 |
+
|
| 161 |
+
### Model Architecture and Objective
|
| 162 |
+
|
| 163 |
+
[More Information Needed]
|
| 164 |
+
|
| 165 |
+
### Compute Infrastructure
|
| 166 |
+
|
| 167 |
+
[More Information Needed]
|
| 168 |
+
|
| 169 |
+
#### Hardware
|
| 170 |
+
|
| 171 |
+
[More Information Needed]
|
| 172 |
+
|
| 173 |
+
#### Software
|
| 174 |
+
|
| 175 |
+
[More Information Needed]
|
| 176 |
+
|
| 177 |
+
## Citation [optional]
|
| 178 |
+
|
| 179 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 180 |
+
|
| 181 |
+
**BibTeX:**
|
| 182 |
+
|
| 183 |
+
[More Information Needed]
|
| 184 |
+
|
| 185 |
+
**APA:**
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## Glossary [optional]
|
| 190 |
+
|
| 191 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 192 |
+
|
| 193 |
+
[More Information Needed]
|
| 194 |
+
|
| 195 |
+
## More Information [optional]
|
| 196 |
+
|
| 197 |
+
[More Information Needed]
|
| 198 |
+
|
| 199 |
+
## Model Card Authors [optional]
|
| 200 |
+
|
| 201 |
+
[More Information Needed]
|
| 202 |
+
|
| 203 |
+
## Model Card Contact
|
| 204 |
+
|
| 205 |
+
[More Information Needed]
|
| 206 |
+
### Framework versions
|
| 207 |
+
|
| 208 |
+
- PEFT 0.17.0
|
checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": null,
|
| 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": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 8,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"o_proj",
|
| 29 |
+
"qkv_proj",
|
| 30 |
+
"gate_up_proj",
|
| 31 |
+
"down_proj"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91319625d8f60ae1348da53b28976fd07868035e0be7b74118d7501ee5dd2faf
|
| 3 |
+
size 46180160
|
checkpoint-100/added_tokens.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|/tool_call|>": 200026,
|
| 3 |
+
"<|/tool|>": 200024,
|
| 4 |
+
"<|assistant|>": 200019,
|
| 5 |
+
"<|end|>": 200020,
|
| 6 |
+
"<|system|>": 200022,
|
| 7 |
+
"<|tag|>": 200028,
|
| 8 |
+
"<|tool_call|>": 200025,
|
| 9 |
+
"<|tool_response|>": 200027,
|
| 10 |
+
"<|tool|>": 200023,
|
| 11 |
+
"<|user|>": 200021
|
| 12 |
+
}
|
checkpoint-100/chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}
|
checkpoint-100/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd8087e663a3d3a53ce4d7f627136fffb322d60db21f85c25729a0ea2e6d9d72
|
| 3 |
+
size 23729876
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54bbc2ea79f4a16019a0792b73c8ab158d96bd08662e38b947d6d20a26a71831
|
| 3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bd30abdd496aef71b7cd1798cb37a3ccba2071ba112e598e6904c15eae4c88b
|
| 3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
|
| 3 |
+
size 15524095
|
checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"199999": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"200018": {
|
| 15 |
+
"content": "<|endofprompt|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"200019": {
|
| 23 |
+
"content": "<|assistant|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"200020": {
|
| 31 |
+
"content": "<|end|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": true,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"200021": {
|
| 39 |
+
"content": "<|user|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"200022": {
|
| 47 |
+
"content": "<|system|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"200023": {
|
| 55 |
+
"content": "<|tool|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"200024": {
|
| 63 |
+
"content": "<|/tool|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"200025": {
|
| 71 |
+
"content": "<|tool_call|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"200026": {
|
| 79 |
+
"content": "<|/tool_call|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"200027": {
|
| 87 |
+
"content": "<|tool_response|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"200028": {
|
| 95 |
+
"content": "<|tag|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
}
|
| 102 |
+
},
|
| 103 |
+
"bos_token": "<|endoftext|>",
|
| 104 |
+
"clean_up_tokenization_spaces": false,
|
| 105 |
+
"eos_token": "<|endoftext|>",
|
| 106 |
+
"extra_special_tokens": {},
|
| 107 |
+
"model_max_length": 131072,
|
| 108 |
+
"pad_token": "<|endoftext|>",
|
| 109 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 110 |
+
"unk_token": "<|endoftext|>"
|
| 111 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.30959752321981426,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 100,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.030959752321981424,
|
| 14 |
+
"grad_norm": 9.773098945617676,
|
| 15 |
+
"learning_rate": 2.991640866873065e-05,
|
| 16 |
+
"loss": 9.245,
|
| 17 |
+
"mean_token_accuracy": 0.2123243510723114,
|
| 18 |
+
"num_tokens": 5327.0,
|
| 19 |
+
"step": 10
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.06191950464396285,
|
| 23 |
+
"grad_norm": 3.128091335296631,
|
| 24 |
+
"learning_rate": 2.9823529411764707e-05,
|
| 25 |
+
"loss": 6.1602,
|
| 26 |
+
"mean_token_accuracy": 0.25044268518686297,
|
| 27 |
+
"num_tokens": 10795.0,
|
| 28 |
+
"step": 20
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.09287925696594428,
|
| 32 |
+
"grad_norm": 4.203906536102295,
|
| 33 |
+
"learning_rate": 2.973065015479876e-05,
|
| 34 |
+
"loss": 5.6948,
|
| 35 |
+
"mean_token_accuracy": 0.262071692943573,
|
| 36 |
+
"num_tokens": 16240.0,
|
| 37 |
+
"step": 30
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1238390092879257,
|
| 41 |
+
"grad_norm": 4.233511924743652,
|
| 42 |
+
"learning_rate": 2.9637770897832817e-05,
|
| 43 |
+
"loss": 5.2733,
|
| 44 |
+
"mean_token_accuracy": 0.27527774721384046,
|
| 45 |
+
"num_tokens": 21582.0,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.15479876160990713,
|
| 50 |
+
"grad_norm": 7.080459117889404,
|
| 51 |
+
"learning_rate": 2.9544891640866874e-05,
|
| 52 |
+
"loss": 4.9304,
|
| 53 |
+
"mean_token_accuracy": 0.2877007365226746,
|
| 54 |
+
"num_tokens": 27142.0,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.18575851393188855,
|
| 59 |
+
"grad_norm": 7.273204326629639,
|
| 60 |
+
"learning_rate": 2.945201238390093e-05,
|
| 61 |
+
"loss": 4.689,
|
| 62 |
+
"mean_token_accuracy": 0.28890604972839357,
|
| 63 |
+
"num_tokens": 32801.0,
|
| 64 |
+
"step": 60
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.21671826625386997,
|
| 68 |
+
"grad_norm": 2.2185206413269043,
|
| 69 |
+
"learning_rate": 2.9359133126934984e-05,
|
| 70 |
+
"loss": 4.3965,
|
| 71 |
+
"mean_token_accuracy": 0.28117197155952456,
|
| 72 |
+
"num_tokens": 38472.0,
|
| 73 |
+
"step": 70
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2476780185758514,
|
| 77 |
+
"grad_norm": 2.0464794635772705,
|
| 78 |
+
"learning_rate": 2.926625386996904e-05,
|
| 79 |
+
"loss": 4.062,
|
| 80 |
+
"mean_token_accuracy": 0.299494668841362,
|
| 81 |
+
"num_tokens": 43743.0,
|
| 82 |
+
"step": 80
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.2786377708978328,
|
| 86 |
+
"grad_norm": 1.633155345916748,
|
| 87 |
+
"learning_rate": 2.9173374613003097e-05,
|
| 88 |
+
"loss": 4.0378,
|
| 89 |
+
"mean_token_accuracy": 0.30819864571094513,
|
| 90 |
+
"num_tokens": 49087.0,
|
| 91 |
+
"step": 90
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.30959752321981426,
|
| 95 |
+
"grad_norm": 1.4594247341156006,
|
| 96 |
+
"learning_rate": 2.908049535603715e-05,
|
| 97 |
+
"loss": 3.8513,
|
| 98 |
+
"mean_token_accuracy": 0.3258361428976059,
|
| 99 |
+
"num_tokens": 54433.0,
|
| 100 |
+
"step": 100
|
| 101 |
+
}
|
| 102 |
+
],
|
| 103 |
+
"logging_steps": 10,
|
| 104 |
+
"max_steps": 3230,
|
| 105 |
+
"num_input_tokens_seen": 0,
|
| 106 |
+
"num_train_epochs": 10,
|
| 107 |
+
"save_steps": 100,
|
| 108 |
+
"stateful_callbacks": {
|
| 109 |
+
"TrainerControl": {
|
| 110 |
+
"args": {
|
| 111 |
+
"should_epoch_stop": false,
|
| 112 |
+
"should_evaluate": false,
|
| 113 |
+
"should_log": false,
|
| 114 |
+
"should_save": true,
|
| 115 |
+
"should_training_stop": false
|
| 116 |
+
},
|
| 117 |
+
"attributes": {}
|
| 118 |
+
}
|
| 119 |
+
},
|
| 120 |
+
"total_flos": 2575711755927552.0,
|
| 121 |
+
"train_batch_size": 16,
|
| 122 |
+
"trial_name": null,
|
| 123 |
+
"trial_params": null
|
| 124 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:296f00e71697e39b9b96ced2cbda9da38aa0e08c1dfa73c8eef3c62051e61b76
|
| 3 |
+
size 5688
|
checkpoint-100/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/README.md
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/Phi-4-mini-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:microsoft/Phi-4-mini-instruct
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- trl
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Model ID
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
|
| 22 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
- **Developed by:** [More Information Needed]
|
| 27 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 28 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 29 |
+
- **Model type:** [More Information Needed]
|
| 30 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 31 |
+
- **License:** [More Information Needed]
|
| 32 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 33 |
+
|
| 34 |
+
### Model Sources [optional]
|
| 35 |
+
|
| 36 |
+
<!-- Provide the basic links for the model. -->
|
| 37 |
+
|
| 38 |
+
- **Repository:** [More Information Needed]
|
| 39 |
+
- **Paper [optional]:** [More Information Needed]
|
| 40 |
+
- **Demo [optional]:** [More Information Needed]
|
| 41 |
+
|
| 42 |
+
## Uses
|
| 43 |
+
|
| 44 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 45 |
+
|
| 46 |
+
### Direct Use
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Downstream Use [optional]
|
| 53 |
+
|
| 54 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
### Out-of-Scope Use
|
| 59 |
+
|
| 60 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
## Bias, Risks, and Limitations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 67 |
+
|
| 68 |
+
[More Information Needed]
|
| 69 |
+
|
| 70 |
+
### Recommendations
|
| 71 |
+
|
| 72 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 73 |
+
|
| 74 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 75 |
+
|
| 76 |
+
## How to Get Started with the Model
|
| 77 |
+
|
| 78 |
+
Use the code below to get started with the model.
|
| 79 |
+
|
| 80 |
+
[More Information Needed]
|
| 81 |
+
|
| 82 |
+
## Training Details
|
| 83 |
+
|
| 84 |
+
### Training Data
|
| 85 |
+
|
| 86 |
+
<!-- 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. -->
|
| 87 |
+
|
| 88 |
+
[More Information Needed]
|
| 89 |
+
|
| 90 |
+
### Training Procedure
|
| 91 |
+
|
| 92 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 93 |
+
|
| 94 |
+
#### Preprocessing [optional]
|
| 95 |
+
|
| 96 |
+
[More Information Needed]
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
#### Training Hyperparameters
|
| 100 |
+
|
| 101 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 102 |
+
|
| 103 |
+
#### Speeds, Sizes, Times [optional]
|
| 104 |
+
|
| 105 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 106 |
+
|
| 107 |
+
[More Information Needed]
|
| 108 |
+
|
| 109 |
+
## Evaluation
|
| 110 |
+
|
| 111 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 112 |
+
|
| 113 |
+
### Testing Data, Factors & Metrics
|
| 114 |
+
|
| 115 |
+
#### Testing Data
|
| 116 |
+
|
| 117 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Factors
|
| 122 |
+
|
| 123 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
#### Metrics
|
| 128 |
+
|
| 129 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 130 |
+
|
| 131 |
+
[More Information Needed]
|
| 132 |
+
|
| 133 |
+
### Results
|
| 134 |
+
|
| 135 |
+
[More Information Needed]
|
| 136 |
+
|
| 137 |
+
#### Summary
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Model Examination [optional]
|
| 142 |
+
|
| 143 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 144 |
+
|
| 145 |
+
[More Information Needed]
|
| 146 |
+
|
| 147 |
+
## Environmental Impact
|
| 148 |
+
|
| 149 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 150 |
+
|
| 151 |
+
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).
|
| 152 |
+
|
| 153 |
+
- **Hardware Type:** [More Information Needed]
|
| 154 |
+
- **Hours used:** [More Information Needed]
|
| 155 |
+
- **Cloud Provider:** [More Information Needed]
|
| 156 |
+
- **Compute Region:** [More Information Needed]
|
| 157 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 158 |
+
|
| 159 |
+
## Technical Specifications [optional]
|
| 160 |
+
|
| 161 |
+
### Model Architecture and Objective
|
| 162 |
+
|
| 163 |
+
[More Information Needed]
|
| 164 |
+
|
| 165 |
+
### Compute Infrastructure
|
| 166 |
+
|
| 167 |
+
[More Information Needed]
|
| 168 |
+
|
| 169 |
+
#### Hardware
|
| 170 |
+
|
| 171 |
+
[More Information Needed]
|
| 172 |
+
|
| 173 |
+
#### Software
|
| 174 |
+
|
| 175 |
+
[More Information Needed]
|
| 176 |
+
|
| 177 |
+
## Citation [optional]
|
| 178 |
+
|
| 179 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 180 |
+
|
| 181 |
+
**BibTeX:**
|
| 182 |
+
|
| 183 |
+
[More Information Needed]
|
| 184 |
+
|
| 185 |
+
**APA:**
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## Glossary [optional]
|
| 190 |
+
|
| 191 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 192 |
+
|
| 193 |
+
[More Information Needed]
|
| 194 |
+
|
| 195 |
+
## More Information [optional]
|
| 196 |
+
|
| 197 |
+
[More Information Needed]
|
| 198 |
+
|
| 199 |
+
## Model Card Authors [optional]
|
| 200 |
+
|
| 201 |
+
[More Information Needed]
|
| 202 |
+
|
| 203 |
+
## Model Card Contact
|
| 204 |
+
|
| 205 |
+
[More Information Needed]
|
| 206 |
+
### Framework versions
|
| 207 |
+
|
| 208 |
+
- PEFT 0.17.0
|
checkpoint-1000/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": null,
|
| 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": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 8,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"o_proj",
|
| 29 |
+
"qkv_proj",
|
| 30 |
+
"gate_up_proj",
|
| 31 |
+
"down_proj"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-1000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3a19217a72f4f435b3c0feb553d8680d4e6622d67921a3abe08a6c16d18c114
|
| 3 |
+
size 46180160
|
checkpoint-1000/added_tokens.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|/tool_call|>": 200026,
|
| 3 |
+
"<|/tool|>": 200024,
|
| 4 |
+
"<|assistant|>": 200019,
|
| 5 |
+
"<|end|>": 200020,
|
| 6 |
+
"<|system|>": 200022,
|
| 7 |
+
"<|tag|>": 200028,
|
| 8 |
+
"<|tool_call|>": 200025,
|
| 9 |
+
"<|tool_response|>": 200027,
|
| 10 |
+
"<|tool|>": 200023,
|
| 11 |
+
"<|user|>": 200021
|
| 12 |
+
}
|
checkpoint-1000/chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}
|
checkpoint-1000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddc424f690ddca9db01118d7b2e29215381612092e44b4416018af78c17d9a38
|
| 3 |
+
size 23730132
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6bdb3399f463db6211f3e676aa698e6638671cdb3c1227d65b10fd6ba298374
|
| 3 |
+
size 14244
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9013719f8428580a3d85a62cc94bd1a0079dda9afa264b03341baf21a502b18b
|
| 3 |
+
size 1064
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
|
| 3 |
+
size 15524095
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"199999": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"200018": {
|
| 15 |
+
"content": "<|endofprompt|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"200019": {
|
| 23 |
+
"content": "<|assistant|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"200020": {
|
| 31 |
+
"content": "<|end|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": true,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"200021": {
|
| 39 |
+
"content": "<|user|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"200022": {
|
| 47 |
+
"content": "<|system|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"200023": {
|
| 55 |
+
"content": "<|tool|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"200024": {
|
| 63 |
+
"content": "<|/tool|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"200025": {
|
| 71 |
+
"content": "<|tool_call|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"200026": {
|
| 79 |
+
"content": "<|/tool_call|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"200027": {
|
| 87 |
+
"content": "<|tool_response|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"200028": {
|
| 95 |
+
"content": "<|tag|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
}
|
| 102 |
+
},
|
| 103 |
+
"bos_token": "<|endoftext|>",
|
| 104 |
+
"clean_up_tokenization_spaces": false,
|
| 105 |
+
"eos_token": "<|endoftext|>",
|
| 106 |
+
"extra_special_tokens": {},
|
| 107 |
+
"model_max_length": 131072,
|
| 108 |
+
"pad_token": "<|endoftext|>",
|
| 109 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 110 |
+
"unk_token": "<|endoftext|>"
|
| 111 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,934 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0959752321981426,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.030959752321981424,
|
| 14 |
+
"grad_norm": 9.773098945617676,
|
| 15 |
+
"learning_rate": 2.991640866873065e-05,
|
| 16 |
+
"loss": 9.245,
|
| 17 |
+
"mean_token_accuracy": 0.2123243510723114,
|
| 18 |
+
"num_tokens": 5327.0,
|
| 19 |
+
"step": 10
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.06191950464396285,
|
| 23 |
+
"grad_norm": 3.128091335296631,
|
| 24 |
+
"learning_rate": 2.9823529411764707e-05,
|
| 25 |
+
"loss": 6.1602,
|
| 26 |
+
"mean_token_accuracy": 0.25044268518686297,
|
| 27 |
+
"num_tokens": 10795.0,
|
| 28 |
+
"step": 20
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.09287925696594428,
|
| 32 |
+
"grad_norm": 4.203906536102295,
|
| 33 |
+
"learning_rate": 2.973065015479876e-05,
|
| 34 |
+
"loss": 5.6948,
|
| 35 |
+
"mean_token_accuracy": 0.262071692943573,
|
| 36 |
+
"num_tokens": 16240.0,
|
| 37 |
+
"step": 30
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1238390092879257,
|
| 41 |
+
"grad_norm": 4.233511924743652,
|
| 42 |
+
"learning_rate": 2.9637770897832817e-05,
|
| 43 |
+
"loss": 5.2733,
|
| 44 |
+
"mean_token_accuracy": 0.27527774721384046,
|
| 45 |
+
"num_tokens": 21582.0,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.15479876160990713,
|
| 50 |
+
"grad_norm": 7.080459117889404,
|
| 51 |
+
"learning_rate": 2.9544891640866874e-05,
|
| 52 |
+
"loss": 4.9304,
|
| 53 |
+
"mean_token_accuracy": 0.2877007365226746,
|
| 54 |
+
"num_tokens": 27142.0,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.18575851393188855,
|
| 59 |
+
"grad_norm": 7.273204326629639,
|
| 60 |
+
"learning_rate": 2.945201238390093e-05,
|
| 61 |
+
"loss": 4.689,
|
| 62 |
+
"mean_token_accuracy": 0.28890604972839357,
|
| 63 |
+
"num_tokens": 32801.0,
|
| 64 |
+
"step": 60
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.21671826625386997,
|
| 68 |
+
"grad_norm": 2.2185206413269043,
|
| 69 |
+
"learning_rate": 2.9359133126934984e-05,
|
| 70 |
+
"loss": 4.3965,
|
| 71 |
+
"mean_token_accuracy": 0.28117197155952456,
|
| 72 |
+
"num_tokens": 38472.0,
|
| 73 |
+
"step": 70
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2476780185758514,
|
| 77 |
+
"grad_norm": 2.0464794635772705,
|
| 78 |
+
"learning_rate": 2.926625386996904e-05,
|
| 79 |
+
"loss": 4.062,
|
| 80 |
+
"mean_token_accuracy": 0.299494668841362,
|
| 81 |
+
"num_tokens": 43743.0,
|
| 82 |
+
"step": 80
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.2786377708978328,
|
| 86 |
+
"grad_norm": 1.633155345916748,
|
| 87 |
+
"learning_rate": 2.9173374613003097e-05,
|
| 88 |
+
"loss": 4.0378,
|
| 89 |
+
"mean_token_accuracy": 0.30819864571094513,
|
| 90 |
+
"num_tokens": 49087.0,
|
| 91 |
+
"step": 90
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.30959752321981426,
|
| 95 |
+
"grad_norm": 1.4594247341156006,
|
| 96 |
+
"learning_rate": 2.908049535603715e-05,
|
| 97 |
+
"loss": 3.8513,
|
| 98 |
+
"mean_token_accuracy": 0.3258361428976059,
|
| 99 |
+
"num_tokens": 54433.0,
|
| 100 |
+
"step": 100
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.34055727554179566,
|
| 104 |
+
"grad_norm": 1.5312635898590088,
|
| 105 |
+
"learning_rate": 2.898761609907121e-05,
|
| 106 |
+
"loss": 3.9162,
|
| 107 |
+
"mean_token_accuracy": 0.32140363454818727,
|
| 108 |
+
"num_tokens": 59629.0,
|
| 109 |
+
"step": 110
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.3715170278637771,
|
| 113 |
+
"grad_norm": 1.3190491199493408,
|
| 114 |
+
"learning_rate": 2.8894736842105263e-05,
|
| 115 |
+
"loss": 3.902,
|
| 116 |
+
"mean_token_accuracy": 0.3103078156709671,
|
| 117 |
+
"num_tokens": 65326.0,
|
| 118 |
+
"step": 120
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.4024767801857585,
|
| 122 |
+
"grad_norm": 1.6095689535140991,
|
| 123 |
+
"learning_rate": 2.880185758513932e-05,
|
| 124 |
+
"loss": 3.7107,
|
| 125 |
+
"mean_token_accuracy": 0.3353793561458588,
|
| 126 |
+
"num_tokens": 70440.0,
|
| 127 |
+
"step": 130
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.43343653250773995,
|
| 131 |
+
"grad_norm": 1.6634972095489502,
|
| 132 |
+
"learning_rate": 2.8708978328173377e-05,
|
| 133 |
+
"loss": 3.7747,
|
| 134 |
+
"mean_token_accuracy": 0.3298566401004791,
|
| 135 |
+
"num_tokens": 75712.0,
|
| 136 |
+
"step": 140
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.46439628482972134,
|
| 140 |
+
"grad_norm": 1.3906605243682861,
|
| 141 |
+
"learning_rate": 2.861609907120743e-05,
|
| 142 |
+
"loss": 3.7344,
|
| 143 |
+
"mean_token_accuracy": 0.34043932259082793,
|
| 144 |
+
"num_tokens": 81272.0,
|
| 145 |
+
"step": 150
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.4953560371517028,
|
| 149 |
+
"grad_norm": 1.6273926496505737,
|
| 150 |
+
"learning_rate": 2.8523219814241487e-05,
|
| 151 |
+
"loss": 3.6722,
|
| 152 |
+
"mean_token_accuracy": 0.33802524507045745,
|
| 153 |
+
"num_tokens": 86836.0,
|
| 154 |
+
"step": 160
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.5263157894736842,
|
| 158 |
+
"grad_norm": 1.595566987991333,
|
| 159 |
+
"learning_rate": 2.8430340557275543e-05,
|
| 160 |
+
"loss": 3.5486,
|
| 161 |
+
"mean_token_accuracy": 0.36929037272930143,
|
| 162 |
+
"num_tokens": 91622.0,
|
| 163 |
+
"step": 170
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5572755417956656,
|
| 167 |
+
"grad_norm": 1.9571454524993896,
|
| 168 |
+
"learning_rate": 2.83374613003096e-05,
|
| 169 |
+
"loss": 3.6849,
|
| 170 |
+
"mean_token_accuracy": 0.3387055486440659,
|
| 171 |
+
"num_tokens": 97019.0,
|
| 172 |
+
"step": 180
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.5882352941176471,
|
| 176 |
+
"grad_norm": 1.6203333139419556,
|
| 177 |
+
"learning_rate": 2.8244582043343653e-05,
|
| 178 |
+
"loss": 3.5592,
|
| 179 |
+
"mean_token_accuracy": 0.36260710954666137,
|
| 180 |
+
"num_tokens": 102273.0,
|
| 181 |
+
"step": 190
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.6191950464396285,
|
| 185 |
+
"grad_norm": 1.8625439405441284,
|
| 186 |
+
"learning_rate": 2.815170278637771e-05,
|
| 187 |
+
"loss": 3.4542,
|
| 188 |
+
"mean_token_accuracy": 0.3554231733083725,
|
| 189 |
+
"num_tokens": 107847.0,
|
| 190 |
+
"step": 200
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.6501547987616099,
|
| 194 |
+
"grad_norm": 1.5171610116958618,
|
| 195 |
+
"learning_rate": 2.8058823529411766e-05,
|
| 196 |
+
"loss": 3.6914,
|
| 197 |
+
"mean_token_accuracy": 0.3506886214017868,
|
| 198 |
+
"num_tokens": 113499.0,
|
| 199 |
+
"step": 210
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.6811145510835913,
|
| 203 |
+
"grad_norm": 1.465408205986023,
|
| 204 |
+
"learning_rate": 2.796594427244582e-05,
|
| 205 |
+
"loss": 3.6008,
|
| 206 |
+
"mean_token_accuracy": 0.3558589071035385,
|
| 207 |
+
"num_tokens": 119014.0,
|
| 208 |
+
"step": 220
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.7120743034055728,
|
| 212 |
+
"grad_norm": 1.5382874011993408,
|
| 213 |
+
"learning_rate": 2.787306501547988e-05,
|
| 214 |
+
"loss": 3.5375,
|
| 215 |
+
"mean_token_accuracy": 0.3548148155212402,
|
| 216 |
+
"num_tokens": 124170.0,
|
| 217 |
+
"step": 230
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.7430340557275542,
|
| 221 |
+
"grad_norm": 1.773881196975708,
|
| 222 |
+
"learning_rate": 2.7780185758513933e-05,
|
| 223 |
+
"loss": 3.573,
|
| 224 |
+
"mean_token_accuracy": 0.3465736091136932,
|
| 225 |
+
"num_tokens": 129487.0,
|
| 226 |
+
"step": 240
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7739938080495357,
|
| 230 |
+
"grad_norm": 1.7652744054794312,
|
| 231 |
+
"learning_rate": 2.7687306501547986e-05,
|
| 232 |
+
"loss": 3.6811,
|
| 233 |
+
"mean_token_accuracy": 0.33623204231262205,
|
| 234 |
+
"num_tokens": 135007.0,
|
| 235 |
+
"step": 250
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.804953560371517,
|
| 239 |
+
"grad_norm": 1.7662419080734253,
|
| 240 |
+
"learning_rate": 2.7594427244582046e-05,
|
| 241 |
+
"loss": 3.505,
|
| 242 |
+
"mean_token_accuracy": 0.3567329585552216,
|
| 243 |
+
"num_tokens": 140143.0,
|
| 244 |
+
"step": 260
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.8359133126934984,
|
| 248 |
+
"grad_norm": 1.9441474676132202,
|
| 249 |
+
"learning_rate": 2.75015479876161e-05,
|
| 250 |
+
"loss": 3.4804,
|
| 251 |
+
"mean_token_accuracy": 0.36218210160732267,
|
| 252 |
+
"num_tokens": 145363.0,
|
| 253 |
+
"step": 270
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.8668730650154799,
|
| 257 |
+
"grad_norm": 1.745896816253662,
|
| 258 |
+
"learning_rate": 2.7408668730650156e-05,
|
| 259 |
+
"loss": 3.6519,
|
| 260 |
+
"mean_token_accuracy": 0.34941086173057556,
|
| 261 |
+
"num_tokens": 150840.0,
|
| 262 |
+
"step": 280
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.8978328173374613,
|
| 266 |
+
"grad_norm": 1.928284764289856,
|
| 267 |
+
"learning_rate": 2.7315789473684213e-05,
|
| 268 |
+
"loss": 3.6138,
|
| 269 |
+
"mean_token_accuracy": 0.34826839864254,
|
| 270 |
+
"num_tokens": 156077.0,
|
| 271 |
+
"step": 290
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.9287925696594427,
|
| 275 |
+
"grad_norm": 2.177100896835327,
|
| 276 |
+
"learning_rate": 2.722291021671827e-05,
|
| 277 |
+
"loss": 3.4666,
|
| 278 |
+
"mean_token_accuracy": 0.36537405848503113,
|
| 279 |
+
"num_tokens": 160953.0,
|
| 280 |
+
"step": 300
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.9597523219814241,
|
| 284 |
+
"grad_norm": 2.203282594680786,
|
| 285 |
+
"learning_rate": 2.7130030959752322e-05,
|
| 286 |
+
"loss": 3.5842,
|
| 287 |
+
"mean_token_accuracy": 0.34776660799980164,
|
| 288 |
+
"num_tokens": 166286.0,
|
| 289 |
+
"step": 310
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9907120743034056,
|
| 293 |
+
"grad_norm": 1.724373459815979,
|
| 294 |
+
"learning_rate": 2.7037151702786376e-05,
|
| 295 |
+
"loss": 3.4961,
|
| 296 |
+
"mean_token_accuracy": 0.35577190220355986,
|
| 297 |
+
"num_tokens": 171629.0,
|
| 298 |
+
"step": 320
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.021671826625387,
|
| 302 |
+
"grad_norm": 1.7433867454528809,
|
| 303 |
+
"learning_rate": 2.6944272445820436e-05,
|
| 304 |
+
"loss": 3.4088,
|
| 305 |
+
"mean_token_accuracy": 0.36975419521331787,
|
| 306 |
+
"num_tokens": 176968.0,
|
| 307 |
+
"step": 330
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.0526315789473684,
|
| 311 |
+
"grad_norm": 2.0577471256256104,
|
| 312 |
+
"learning_rate": 2.685139318885449e-05,
|
| 313 |
+
"loss": 3.5364,
|
| 314 |
+
"mean_token_accuracy": 0.35527182221412656,
|
| 315 |
+
"num_tokens": 182390.0,
|
| 316 |
+
"step": 340
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.08359133126935,
|
| 320 |
+
"grad_norm": 1.7357635498046875,
|
| 321 |
+
"learning_rate": 2.6758513931888546e-05,
|
| 322 |
+
"loss": 3.4495,
|
| 323 |
+
"mean_token_accuracy": 0.3565235286951065,
|
| 324 |
+
"num_tokens": 188181.0,
|
| 325 |
+
"step": 350
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.1145510835913313,
|
| 329 |
+
"grad_norm": 2.024507761001587,
|
| 330 |
+
"learning_rate": 2.6665634674922602e-05,
|
| 331 |
+
"loss": 3.3766,
|
| 332 |
+
"mean_token_accuracy": 0.3696540713310242,
|
| 333 |
+
"num_tokens": 193427.0,
|
| 334 |
+
"step": 360
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.1455108359133126,
|
| 338 |
+
"grad_norm": 2.1170592308044434,
|
| 339 |
+
"learning_rate": 2.6572755417956655e-05,
|
| 340 |
+
"loss": 3.4759,
|
| 341 |
+
"mean_token_accuracy": 0.35803447663784027,
|
| 342 |
+
"num_tokens": 199046.0,
|
| 343 |
+
"step": 370
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.1764705882352942,
|
| 347 |
+
"grad_norm": 2.118878126144409,
|
| 348 |
+
"learning_rate": 2.6479876160990712e-05,
|
| 349 |
+
"loss": 3.4685,
|
| 350 |
+
"mean_token_accuracy": 0.3570233076810837,
|
| 351 |
+
"num_tokens": 204089.0,
|
| 352 |
+
"step": 380
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.2074303405572755,
|
| 356 |
+
"grad_norm": 2.2280914783477783,
|
| 357 |
+
"learning_rate": 2.638699690402477e-05,
|
| 358 |
+
"loss": 3.4822,
|
| 359 |
+
"mean_token_accuracy": 0.36153341829776764,
|
| 360 |
+
"num_tokens": 209656.0,
|
| 361 |
+
"step": 390
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.238390092879257,
|
| 365 |
+
"grad_norm": 2.444979667663574,
|
| 366 |
+
"learning_rate": 2.6294117647058825e-05,
|
| 367 |
+
"loss": 3.3666,
|
| 368 |
+
"mean_token_accuracy": 0.3748770415782928,
|
| 369 |
+
"num_tokens": 214465.0,
|
| 370 |
+
"step": 400
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.2693498452012384,
|
| 374 |
+
"grad_norm": 1.9609659910202026,
|
| 375 |
+
"learning_rate": 2.620123839009288e-05,
|
| 376 |
+
"loss": 3.4161,
|
| 377 |
+
"mean_token_accuracy": 0.3594685852527618,
|
| 378 |
+
"num_tokens": 219728.0,
|
| 379 |
+
"step": 410
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.3003095975232197,
|
| 383 |
+
"grad_norm": 1.9759095907211304,
|
| 384 |
+
"learning_rate": 2.6108359133126935e-05,
|
| 385 |
+
"loss": 3.405,
|
| 386 |
+
"mean_token_accuracy": 0.3668099522590637,
|
| 387 |
+
"num_tokens": 224992.0,
|
| 388 |
+
"step": 420
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.3312693498452013,
|
| 392 |
+
"grad_norm": 2.1737940311431885,
|
| 393 |
+
"learning_rate": 2.6015479876160992e-05,
|
| 394 |
+
"loss": 3.3809,
|
| 395 |
+
"mean_token_accuracy": 0.37462269365787504,
|
| 396 |
+
"num_tokens": 230431.0,
|
| 397 |
+
"step": 430
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.3622291021671826,
|
| 401 |
+
"grad_norm": 2.475351333618164,
|
| 402 |
+
"learning_rate": 2.5922600619195045e-05,
|
| 403 |
+
"loss": 3.3454,
|
| 404 |
+
"mean_token_accuracy": 0.36902076900005343,
|
| 405 |
+
"num_tokens": 235868.0,
|
| 406 |
+
"step": 440
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.3931888544891642,
|
| 410 |
+
"grad_norm": 2.1027772426605225,
|
| 411 |
+
"learning_rate": 2.5829721362229105e-05,
|
| 412 |
+
"loss": 3.3967,
|
| 413 |
+
"mean_token_accuracy": 0.3779816538095474,
|
| 414 |
+
"num_tokens": 241149.0,
|
| 415 |
+
"step": 450
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.4241486068111455,
|
| 419 |
+
"grad_norm": 2.613186836242676,
|
| 420 |
+
"learning_rate": 2.5736842105263158e-05,
|
| 421 |
+
"loss": 3.3383,
|
| 422 |
+
"mean_token_accuracy": 0.37455591559410095,
|
| 423 |
+
"num_tokens": 246200.0,
|
| 424 |
+
"step": 460
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.4551083591331269,
|
| 428 |
+
"grad_norm": 2.1689629554748535,
|
| 429 |
+
"learning_rate": 2.5643962848297215e-05,
|
| 430 |
+
"loss": 3.4927,
|
| 431 |
+
"mean_token_accuracy": 0.3641968876123428,
|
| 432 |
+
"num_tokens": 251354.0,
|
| 433 |
+
"step": 470
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.4860681114551084,
|
| 437 |
+
"grad_norm": 1.9075849056243896,
|
| 438 |
+
"learning_rate": 2.555108359133127e-05,
|
| 439 |
+
"loss": 3.4211,
|
| 440 |
+
"mean_token_accuracy": 0.3670921057462692,
|
| 441 |
+
"num_tokens": 257201.0,
|
| 442 |
+
"step": 480
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.5170278637770898,
|
| 446 |
+
"grad_norm": 2.128737211227417,
|
| 447 |
+
"learning_rate": 2.5458204334365325e-05,
|
| 448 |
+
"loss": 3.3306,
|
| 449 |
+
"mean_token_accuracy": 0.3747966349124908,
|
| 450 |
+
"num_tokens": 262640.0,
|
| 451 |
+
"step": 490
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.5479876160990713,
|
| 455 |
+
"grad_norm": 1.9061874151229858,
|
| 456 |
+
"learning_rate": 2.536532507739938e-05,
|
| 457 |
+
"loss": 3.3874,
|
| 458 |
+
"mean_token_accuracy": 0.3706284284591675,
|
| 459 |
+
"num_tokens": 268129.0,
|
| 460 |
+
"step": 500
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.5789473684210527,
|
| 464 |
+
"grad_norm": 1.8868329524993896,
|
| 465 |
+
"learning_rate": 2.5272445820433438e-05,
|
| 466 |
+
"loss": 3.3185,
|
| 467 |
+
"mean_token_accuracy": 0.37699449956417086,
|
| 468 |
+
"num_tokens": 273489.0,
|
| 469 |
+
"step": 510
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.609907120743034,
|
| 473 |
+
"grad_norm": 1.8507658243179321,
|
| 474 |
+
"learning_rate": 2.5179566563467495e-05,
|
| 475 |
+
"loss": 3.2901,
|
| 476 |
+
"mean_token_accuracy": 0.3797824054956436,
|
| 477 |
+
"num_tokens": 279142.0,
|
| 478 |
+
"step": 520
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.6408668730650153,
|
| 482 |
+
"grad_norm": 2.396951198577881,
|
| 483 |
+
"learning_rate": 2.5086687306501548e-05,
|
| 484 |
+
"loss": 3.3503,
|
| 485 |
+
"mean_token_accuracy": 0.37934728860855105,
|
| 486 |
+
"num_tokens": 284049.0,
|
| 487 |
+
"step": 530
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.671826625386997,
|
| 491 |
+
"grad_norm": 2.256753921508789,
|
| 492 |
+
"learning_rate": 2.4993808049535605e-05,
|
| 493 |
+
"loss": 3.3706,
|
| 494 |
+
"mean_token_accuracy": 0.38219387233257296,
|
| 495 |
+
"num_tokens": 289514.0,
|
| 496 |
+
"step": 540
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.7027863777089784,
|
| 500 |
+
"grad_norm": 1.9369879961013794,
|
| 501 |
+
"learning_rate": 2.490092879256966e-05,
|
| 502 |
+
"loss": 3.3615,
|
| 503 |
+
"mean_token_accuracy": 0.37476457953453063,
|
| 504 |
+
"num_tokens": 295091.0,
|
| 505 |
+
"step": 550
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.7337461300309598,
|
| 509 |
+
"grad_norm": 2.6628825664520264,
|
| 510 |
+
"learning_rate": 2.4808049535603714e-05,
|
| 511 |
+
"loss": 3.3121,
|
| 512 |
+
"mean_token_accuracy": 0.3830788493156433,
|
| 513 |
+
"num_tokens": 300102.0,
|
| 514 |
+
"step": 560
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.7647058823529411,
|
| 518 |
+
"grad_norm": 2.6188621520996094,
|
| 519 |
+
"learning_rate": 2.4715170278637774e-05,
|
| 520 |
+
"loss": 3.4005,
|
| 521 |
+
"mean_token_accuracy": 0.3631168991327286,
|
| 522 |
+
"num_tokens": 305652.0,
|
| 523 |
+
"step": 570
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.7956656346749225,
|
| 527 |
+
"grad_norm": 2.093585968017578,
|
| 528 |
+
"learning_rate": 2.4622291021671828e-05,
|
| 529 |
+
"loss": 3.4483,
|
| 530 |
+
"mean_token_accuracy": 0.3639900177717209,
|
| 531 |
+
"num_tokens": 311333.0,
|
| 532 |
+
"step": 580
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.826625386996904,
|
| 536 |
+
"grad_norm": 2.355714797973633,
|
| 537 |
+
"learning_rate": 2.452941176470588e-05,
|
| 538 |
+
"loss": 3.2946,
|
| 539 |
+
"mean_token_accuracy": 0.3784641414880753,
|
| 540 |
+
"num_tokens": 316699.0,
|
| 541 |
+
"step": 590
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.8575851393188856,
|
| 545 |
+
"grad_norm": 2.5051403045654297,
|
| 546 |
+
"learning_rate": 2.4436532507739938e-05,
|
| 547 |
+
"loss": 3.2612,
|
| 548 |
+
"mean_token_accuracy": 0.3874821364879608,
|
| 549 |
+
"num_tokens": 321718.0,
|
| 550 |
+
"step": 600
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.888544891640867,
|
| 554 |
+
"grad_norm": 2.4884731769561768,
|
| 555 |
+
"learning_rate": 2.4343653250773994e-05,
|
| 556 |
+
"loss": 3.3375,
|
| 557 |
+
"mean_token_accuracy": 0.37331779301166534,
|
| 558 |
+
"num_tokens": 327347.0,
|
| 559 |
+
"step": 610
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.9195046439628483,
|
| 563 |
+
"grad_norm": 2.7246131896972656,
|
| 564 |
+
"learning_rate": 2.425077399380805e-05,
|
| 565 |
+
"loss": 3.3235,
|
| 566 |
+
"mean_token_accuracy": 0.38473727405071256,
|
| 567 |
+
"num_tokens": 332563.0,
|
| 568 |
+
"step": 620
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.9504643962848296,
|
| 572 |
+
"grad_norm": 2.420604705810547,
|
| 573 |
+
"learning_rate": 2.4157894736842104e-05,
|
| 574 |
+
"loss": 3.4027,
|
| 575 |
+
"mean_token_accuracy": 0.36371313631534574,
|
| 576 |
+
"num_tokens": 337880.0,
|
| 577 |
+
"step": 630
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.9814241486068112,
|
| 581 |
+
"grad_norm": 2.1465680599212646,
|
| 582 |
+
"learning_rate": 2.4065015479876164e-05,
|
| 583 |
+
"loss": 3.3508,
|
| 584 |
+
"mean_token_accuracy": 0.3747645616531372,
|
| 585 |
+
"num_tokens": 343193.0,
|
| 586 |
+
"step": 640
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.0123839009287927,
|
| 590 |
+
"grad_norm": 2.0795834064483643,
|
| 591 |
+
"learning_rate": 2.3972136222910217e-05,
|
| 592 |
+
"loss": 3.3529,
|
| 593 |
+
"mean_token_accuracy": 0.3744541972875595,
|
| 594 |
+
"num_tokens": 348460.0,
|
| 595 |
+
"step": 650
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.043343653250774,
|
| 599 |
+
"grad_norm": 2.4051778316497803,
|
| 600 |
+
"learning_rate": 2.387925696594427e-05,
|
| 601 |
+
"loss": 3.2404,
|
| 602 |
+
"mean_token_accuracy": 0.38319246768951415,
|
| 603 |
+
"num_tokens": 353701.0,
|
| 604 |
+
"step": 660
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.0743034055727554,
|
| 608 |
+
"grad_norm": 2.401045322418213,
|
| 609 |
+
"learning_rate": 2.378637770897833e-05,
|
| 610 |
+
"loss": 3.2801,
|
| 611 |
+
"mean_token_accuracy": 0.3773155301809311,
|
| 612 |
+
"num_tokens": 359147.0,
|
| 613 |
+
"step": 670
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.1052631578947367,
|
| 617 |
+
"grad_norm": 2.554138422012329,
|
| 618 |
+
"learning_rate": 2.3693498452012384e-05,
|
| 619 |
+
"loss": 3.2227,
|
| 620 |
+
"mean_token_accuracy": 0.37754152715206146,
|
| 621 |
+
"num_tokens": 364696.0,
|
| 622 |
+
"step": 680
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 2.136222910216718,
|
| 626 |
+
"grad_norm": 2.4874625205993652,
|
| 627 |
+
"learning_rate": 2.360061919504644e-05,
|
| 628 |
+
"loss": 3.2534,
|
| 629 |
+
"mean_token_accuracy": 0.3920708328485489,
|
| 630 |
+
"num_tokens": 370207.0,
|
| 631 |
+
"step": 690
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.1671826625387,
|
| 635 |
+
"grad_norm": 2.638068675994873,
|
| 636 |
+
"learning_rate": 2.3507739938080497e-05,
|
| 637 |
+
"loss": 3.2635,
|
| 638 |
+
"mean_token_accuracy": 0.3835586577653885,
|
| 639 |
+
"num_tokens": 375977.0,
|
| 640 |
+
"step": 700
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.198142414860681,
|
| 644 |
+
"grad_norm": 2.5179686546325684,
|
| 645 |
+
"learning_rate": 2.341486068111455e-05,
|
| 646 |
+
"loss": 3.1599,
|
| 647 |
+
"mean_token_accuracy": 0.39867666363716125,
|
| 648 |
+
"num_tokens": 381398.0,
|
| 649 |
+
"step": 710
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.2291021671826625,
|
| 653 |
+
"grad_norm": 2.9102959632873535,
|
| 654 |
+
"learning_rate": 2.3321981424148607e-05,
|
| 655 |
+
"loss": 3.2686,
|
| 656 |
+
"mean_token_accuracy": 0.3878729552030563,
|
| 657 |
+
"num_tokens": 386460.0,
|
| 658 |
+
"step": 720
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.260061919504644,
|
| 662 |
+
"grad_norm": 2.641160726547241,
|
| 663 |
+
"learning_rate": 2.3229102167182663e-05,
|
| 664 |
+
"loss": 3.2218,
|
| 665 |
+
"mean_token_accuracy": 0.38672482669353486,
|
| 666 |
+
"num_tokens": 391538.0,
|
| 667 |
+
"step": 730
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.291021671826625,
|
| 671 |
+
"grad_norm": 2.947000026702881,
|
| 672 |
+
"learning_rate": 2.313622291021672e-05,
|
| 673 |
+
"loss": 3.2215,
|
| 674 |
+
"mean_token_accuracy": 0.38650966584682467,
|
| 675 |
+
"num_tokens": 396881.0,
|
| 676 |
+
"step": 740
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.321981424148607,
|
| 680 |
+
"grad_norm": 2.3614673614501953,
|
| 681 |
+
"learning_rate": 2.3043343653250773e-05,
|
| 682 |
+
"loss": 3.2233,
|
| 683 |
+
"mean_token_accuracy": 0.388895845413208,
|
| 684 |
+
"num_tokens": 402418.0,
|
| 685 |
+
"step": 750
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.3529411764705883,
|
| 689 |
+
"grad_norm": 2.492814302444458,
|
| 690 |
+
"learning_rate": 2.295046439628483e-05,
|
| 691 |
+
"loss": 3.2005,
|
| 692 |
+
"mean_token_accuracy": 0.382270821928978,
|
| 693 |
+
"num_tokens": 407733.0,
|
| 694 |
+
"step": 760
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.3839009287925697,
|
| 698 |
+
"grad_norm": 2.646655321121216,
|
| 699 |
+
"learning_rate": 2.2857585139318887e-05,
|
| 700 |
+
"loss": 3.1642,
|
| 701 |
+
"mean_token_accuracy": 0.388735693693161,
|
| 702 |
+
"num_tokens": 413101.0,
|
| 703 |
+
"step": 770
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.414860681114551,
|
| 707 |
+
"grad_norm": 2.782440662384033,
|
| 708 |
+
"learning_rate": 2.276470588235294e-05,
|
| 709 |
+
"loss": 3.2513,
|
| 710 |
+
"mean_token_accuracy": 0.38574750125408175,
|
| 711 |
+
"num_tokens": 418754.0,
|
| 712 |
+
"step": 780
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.4458204334365323,
|
| 716 |
+
"grad_norm": 2.7094547748565674,
|
| 717 |
+
"learning_rate": 2.2671826625387e-05,
|
| 718 |
+
"loss": 3.3007,
|
| 719 |
+
"mean_token_accuracy": 0.38453402519226076,
|
| 720 |
+
"num_tokens": 424232.0,
|
| 721 |
+
"step": 790
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.476780185758514,
|
| 725 |
+
"grad_norm": 2.697098970413208,
|
| 726 |
+
"learning_rate": 2.2578947368421053e-05,
|
| 727 |
+
"loss": 3.254,
|
| 728 |
+
"mean_token_accuracy": 0.3893850326538086,
|
| 729 |
+
"num_tokens": 429369.0,
|
| 730 |
+
"step": 800
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.5077399380804954,
|
| 734 |
+
"grad_norm": 3.2908523082733154,
|
| 735 |
+
"learning_rate": 2.248606811145511e-05,
|
| 736 |
+
"loss": 3.1944,
|
| 737 |
+
"mean_token_accuracy": 0.39619002044200896,
|
| 738 |
+
"num_tokens": 434497.0,
|
| 739 |
+
"step": 810
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.538699690402477,
|
| 743 |
+
"grad_norm": 3.068455696105957,
|
| 744 |
+
"learning_rate": 2.2393188854489166e-05,
|
| 745 |
+
"loss": 3.2034,
|
| 746 |
+
"mean_token_accuracy": 0.3942800432443619,
|
| 747 |
+
"num_tokens": 439892.0,
|
| 748 |
+
"step": 820
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 2.569659442724458,
|
| 752 |
+
"grad_norm": 2.7893826961517334,
|
| 753 |
+
"learning_rate": 2.230030959752322e-05,
|
| 754 |
+
"loss": 3.0723,
|
| 755 |
+
"mean_token_accuracy": 0.39791189730167387,
|
| 756 |
+
"num_tokens": 445189.0,
|
| 757 |
+
"step": 830
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 2.6006191950464395,
|
| 761 |
+
"grad_norm": 2.7569446563720703,
|
| 762 |
+
"learning_rate": 2.2207430340557276e-05,
|
| 763 |
+
"loss": 3.187,
|
| 764 |
+
"mean_token_accuracy": 0.3884226083755493,
|
| 765 |
+
"num_tokens": 450338.0,
|
| 766 |
+
"step": 840
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.6315789473684212,
|
| 770 |
+
"grad_norm": 3.16340708732605,
|
| 771 |
+
"learning_rate": 2.2114551083591333e-05,
|
| 772 |
+
"loss": 3.1942,
|
| 773 |
+
"mean_token_accuracy": 0.3921455442905426,
|
| 774 |
+
"num_tokens": 455583.0,
|
| 775 |
+
"step": 850
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.6625386996904026,
|
| 779 |
+
"grad_norm": 2.549273729324341,
|
| 780 |
+
"learning_rate": 2.202167182662539e-05,
|
| 781 |
+
"loss": 3.278,
|
| 782 |
+
"mean_token_accuracy": 0.3782683253288269,
|
| 783 |
+
"num_tokens": 461089.0,
|
| 784 |
+
"step": 860
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.693498452012384,
|
| 788 |
+
"grad_norm": 3.216149091720581,
|
| 789 |
+
"learning_rate": 2.1928792569659443e-05,
|
| 790 |
+
"loss": 3.2023,
|
| 791 |
+
"mean_token_accuracy": 0.3940991997718811,
|
| 792 |
+
"num_tokens": 466239.0,
|
| 793 |
+
"step": 870
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.7244582043343653,
|
| 797 |
+
"grad_norm": 2.4680261611938477,
|
| 798 |
+
"learning_rate": 2.18359133126935e-05,
|
| 799 |
+
"loss": 3.2017,
|
| 800 |
+
"mean_token_accuracy": 0.3878098428249359,
|
| 801 |
+
"num_tokens": 471660.0,
|
| 802 |
+
"step": 880
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.7554179566563466,
|
| 806 |
+
"grad_norm": 3.6166999340057373,
|
| 807 |
+
"learning_rate": 2.1743034055727556e-05,
|
| 808 |
+
"loss": 3.2068,
|
| 809 |
+
"mean_token_accuracy": 0.3789886265993118,
|
| 810 |
+
"num_tokens": 476713.0,
|
| 811 |
+
"step": 890
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 2.7863777089783284,
|
| 815 |
+
"grad_norm": 2.0997393131256104,
|
| 816 |
+
"learning_rate": 2.165015479876161e-05,
|
| 817 |
+
"loss": 3.2216,
|
| 818 |
+
"mean_token_accuracy": 0.3913588523864746,
|
| 819 |
+
"num_tokens": 482569.0,
|
| 820 |
+
"step": 900
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.8173374613003097,
|
| 824 |
+
"grad_norm": 3.0189061164855957,
|
| 825 |
+
"learning_rate": 2.1557275541795666e-05,
|
| 826 |
+
"loss": 3.1346,
|
| 827 |
+
"mean_token_accuracy": 0.3967192888259888,
|
| 828 |
+
"num_tokens": 487629.0,
|
| 829 |
+
"step": 910
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 2.848297213622291,
|
| 833 |
+
"grad_norm": 2.8610568046569824,
|
| 834 |
+
"learning_rate": 2.1464396284829722e-05,
|
| 835 |
+
"loss": 3.2061,
|
| 836 |
+
"mean_token_accuracy": 0.3921816825866699,
|
| 837 |
+
"num_tokens": 493227.0,
|
| 838 |
+
"step": 920
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.8792569659442724,
|
| 842 |
+
"grad_norm": 3.023012638092041,
|
| 843 |
+
"learning_rate": 2.1371517027863776e-05,
|
| 844 |
+
"loss": 3.2208,
|
| 845 |
+
"mean_token_accuracy": 0.3786366432905197,
|
| 846 |
+
"num_tokens": 498394.0,
|
| 847 |
+
"step": 930
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 2.9102167182662537,
|
| 851 |
+
"grad_norm": 2.908886194229126,
|
| 852 |
+
"learning_rate": 2.1278637770897832e-05,
|
| 853 |
+
"loss": 3.1648,
|
| 854 |
+
"mean_token_accuracy": 0.3914026439189911,
|
| 855 |
+
"num_tokens": 503752.0,
|
| 856 |
+
"step": 940
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.9411764705882355,
|
| 860 |
+
"grad_norm": 3.078397750854492,
|
| 861 |
+
"learning_rate": 2.118575851393189e-05,
|
| 862 |
+
"loss": 3.1891,
|
| 863 |
+
"mean_token_accuracy": 0.39542897045612335,
|
| 864 |
+
"num_tokens": 509218.0,
|
| 865 |
+
"step": 950
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.972136222910217,
|
| 869 |
+
"grad_norm": 2.740389823913574,
|
| 870 |
+
"learning_rate": 2.1092879256965946e-05,
|
| 871 |
+
"loss": 3.1953,
|
| 872 |
+
"mean_token_accuracy": 0.3934174537658691,
|
| 873 |
+
"num_tokens": 514716.0,
|
| 874 |
+
"step": 960
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 3.003095975232198,
|
| 878 |
+
"grad_norm": 2.6426961421966553,
|
| 879 |
+
"learning_rate": 2.1e-05,
|
| 880 |
+
"loss": 3.1084,
|
| 881 |
+
"mean_token_accuracy": 0.39845702350139617,
|
| 882 |
+
"num_tokens": 520000.0,
|
| 883 |
+
"step": 970
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 3.0340557275541795,
|
| 887 |
+
"grad_norm": 2.8173840045928955,
|
| 888 |
+
"learning_rate": 2.090712074303406e-05,
|
| 889 |
+
"loss": 3.1574,
|
| 890 |
+
"mean_token_accuracy": 0.39481441378593446,
|
| 891 |
+
"num_tokens": 525561.0,
|
| 892 |
+
"step": 980
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.065015479876161,
|
| 896 |
+
"grad_norm": 3.29856014251709,
|
| 897 |
+
"learning_rate": 2.0814241486068112e-05,
|
| 898 |
+
"loss": 3.0613,
|
| 899 |
+
"mean_token_accuracy": 0.4054213762283325,
|
| 900 |
+
"num_tokens": 531021.0,
|
| 901 |
+
"step": 990
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 3.0959752321981426,
|
| 905 |
+
"grad_norm": 3.463890314102173,
|
| 906 |
+
"learning_rate": 2.0721362229102165e-05,
|
| 907 |
+
"loss": 3.0282,
|
| 908 |
+
"mean_token_accuracy": 0.4025467813014984,
|
| 909 |
+
"num_tokens": 536260.0,
|
| 910 |
+
"step": 1000
|
| 911 |
+
}
|
| 912 |
+
],
|
| 913 |
+
"logging_steps": 10,
|
| 914 |
+
"max_steps": 3230,
|
| 915 |
+
"num_input_tokens_seen": 0,
|
| 916 |
+
"num_train_epochs": 10,
|
| 917 |
+
"save_steps": 100,
|
| 918 |
+
"stateful_callbacks": {
|
| 919 |
+
"TrainerControl": {
|
| 920 |
+
"args": {
|
| 921 |
+
"should_epoch_stop": false,
|
| 922 |
+
"should_evaluate": false,
|
| 923 |
+
"should_log": false,
|
| 924 |
+
"should_save": true,
|
| 925 |
+
"should_training_stop": false
|
| 926 |
+
},
|
| 927 |
+
"attributes": {}
|
| 928 |
+
}
|
| 929 |
+
},
|
| 930 |
+
"total_flos": 2.5176115943768064e+16,
|
| 931 |
+
"train_batch_size": 16,
|
| 932 |
+
"trial_name": null,
|
| 933 |
+
"trial_params": null
|
| 934 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:296f00e71697e39b9b96ced2cbda9da38aa0e08c1dfa73c8eef3c62051e61b76
|
| 3 |
+
size 5688
|
checkpoint-1000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1100/README.md
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/Phi-4-mini-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:microsoft/Phi-4-mini-instruct
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- trl
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Model ID
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
|
| 22 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
- **Developed by:** [More Information Needed]
|
| 27 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 28 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 29 |
+
- **Model type:** [More Information Needed]
|
| 30 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 31 |
+
- **License:** [More Information Needed]
|
| 32 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 33 |
+
|
| 34 |
+
### Model Sources [optional]
|
| 35 |
+
|
| 36 |
+
<!-- Provide the basic links for the model. -->
|
| 37 |
+
|
| 38 |
+
- **Repository:** [More Information Needed]
|
| 39 |
+
- **Paper [optional]:** [More Information Needed]
|
| 40 |
+
- **Demo [optional]:** [More Information Needed]
|
| 41 |
+
|
| 42 |
+
## Uses
|
| 43 |
+
|
| 44 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 45 |
+
|
| 46 |
+
### Direct Use
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Downstream Use [optional]
|
| 53 |
+
|
| 54 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
### Out-of-Scope Use
|
| 59 |
+
|
| 60 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
## Bias, Risks, and Limitations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 67 |
+
|
| 68 |
+
[More Information Needed]
|
| 69 |
+
|
| 70 |
+
### Recommendations
|
| 71 |
+
|
| 72 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 73 |
+
|
| 74 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 75 |
+
|
| 76 |
+
## How to Get Started with the Model
|
| 77 |
+
|
| 78 |
+
Use the code below to get started with the model.
|
| 79 |
+
|
| 80 |
+
[More Information Needed]
|
| 81 |
+
|
| 82 |
+
## Training Details
|
| 83 |
+
|
| 84 |
+
### Training Data
|
| 85 |
+
|
| 86 |
+
<!-- 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. -->
|
| 87 |
+
|
| 88 |
+
[More Information Needed]
|
| 89 |
+
|
| 90 |
+
### Training Procedure
|
| 91 |
+
|
| 92 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 93 |
+
|
| 94 |
+
#### Preprocessing [optional]
|
| 95 |
+
|
| 96 |
+
[More Information Needed]
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
#### Training Hyperparameters
|
| 100 |
+
|
| 101 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 102 |
+
|
| 103 |
+
#### Speeds, Sizes, Times [optional]
|
| 104 |
+
|
| 105 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 106 |
+
|
| 107 |
+
[More Information Needed]
|
| 108 |
+
|
| 109 |
+
## Evaluation
|
| 110 |
+
|
| 111 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 112 |
+
|
| 113 |
+
### Testing Data, Factors & Metrics
|
| 114 |
+
|
| 115 |
+
#### Testing Data
|
| 116 |
+
|
| 117 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Factors
|
| 122 |
+
|
| 123 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
#### Metrics
|
| 128 |
+
|
| 129 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 130 |
+
|
| 131 |
+
[More Information Needed]
|
| 132 |
+
|
| 133 |
+
### Results
|
| 134 |
+
|
| 135 |
+
[More Information Needed]
|
| 136 |
+
|
| 137 |
+
#### Summary
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Model Examination [optional]
|
| 142 |
+
|
| 143 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 144 |
+
|
| 145 |
+
[More Information Needed]
|
| 146 |
+
|
| 147 |
+
## Environmental Impact
|
| 148 |
+
|
| 149 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 150 |
+
|
| 151 |
+
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).
|
| 152 |
+
|
| 153 |
+
- **Hardware Type:** [More Information Needed]
|
| 154 |
+
- **Hours used:** [More Information Needed]
|
| 155 |
+
- **Cloud Provider:** [More Information Needed]
|
| 156 |
+
- **Compute Region:** [More Information Needed]
|
| 157 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 158 |
+
|
| 159 |
+
## Technical Specifications [optional]
|
| 160 |
+
|
| 161 |
+
### Model Architecture and Objective
|
| 162 |
+
|
| 163 |
+
[More Information Needed]
|
| 164 |
+
|
| 165 |
+
### Compute Infrastructure
|
| 166 |
+
|
| 167 |
+
[More Information Needed]
|
| 168 |
+
|
| 169 |
+
#### Hardware
|
| 170 |
+
|
| 171 |
+
[More Information Needed]
|
| 172 |
+
|
| 173 |
+
#### Software
|
| 174 |
+
|
| 175 |
+
[More Information Needed]
|
| 176 |
+
|
| 177 |
+
## Citation [optional]
|
| 178 |
+
|
| 179 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 180 |
+
|
| 181 |
+
**BibTeX:**
|
| 182 |
+
|
| 183 |
+
[More Information Needed]
|
| 184 |
+
|
| 185 |
+
**APA:**
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## Glossary [optional]
|
| 190 |
+
|
| 191 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 192 |
+
|
| 193 |
+
[More Information Needed]
|
| 194 |
+
|
| 195 |
+
## More Information [optional]
|
| 196 |
+
|
| 197 |
+
[More Information Needed]
|
| 198 |
+
|
| 199 |
+
## Model Card Authors [optional]
|
| 200 |
+
|
| 201 |
+
[More Information Needed]
|
| 202 |
+
|
| 203 |
+
## Model Card Contact
|
| 204 |
+
|
| 205 |
+
[More Information Needed]
|
| 206 |
+
### Framework versions
|
| 207 |
+
|
| 208 |
+
- PEFT 0.17.0
|
checkpoint-1100/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": null,
|
| 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": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 8,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"o_proj",
|
| 29 |
+
"qkv_proj",
|
| 30 |
+
"gate_up_proj",
|
| 31 |
+
"down_proj"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-1100/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99b68570dfc5c8cef3b7322cccad536ace0581a130072ea3a017e1a8769f11a4
|
| 3 |
+
size 46180160
|
checkpoint-1100/added_tokens.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|/tool_call|>": 200026,
|
| 3 |
+
"<|/tool|>": 200024,
|
| 4 |
+
"<|assistant|>": 200019,
|
| 5 |
+
"<|end|>": 200020,
|
| 6 |
+
"<|system|>": 200022,
|
| 7 |
+
"<|tag|>": 200028,
|
| 8 |
+
"<|tool_call|>": 200025,
|
| 9 |
+
"<|tool_response|>": 200027,
|
| 10 |
+
"<|tool|>": 200023,
|
| 11 |
+
"<|user|>": 200021
|
| 12 |
+
}
|
checkpoint-1100/chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}
|
checkpoint-1100/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:260026b347b15ab3356b61459f985d4b0d465e6a001cf59ed5c215c142187b9d
|
| 3 |
+
size 23730132
|
checkpoint-1100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9ba01db84a4cf090a2b0634e40241e5b1b0a579fb7f75c95cae14b2de68bb84
|
| 3 |
+
size 14244
|
checkpoint-1100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7362ded16c9d6bd2ce2577825f9d962a8752346ec9a39e48831dca177e699840
|
| 3 |
+
size 1064
|
checkpoint-1100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-1100/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
|
| 3 |
+
size 15524095
|
checkpoint-1100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"199999": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"200018": {
|
| 15 |
+
"content": "<|endofprompt|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"200019": {
|
| 23 |
+
"content": "<|assistant|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"200020": {
|
| 31 |
+
"content": "<|end|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": true,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"200021": {
|
| 39 |
+
"content": "<|user|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"200022": {
|
| 47 |
+
"content": "<|system|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"200023": {
|
| 55 |
+
"content": "<|tool|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"200024": {
|
| 63 |
+
"content": "<|/tool|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"200025": {
|
| 71 |
+
"content": "<|tool_call|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"200026": {
|
| 79 |
+
"content": "<|/tool_call|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"200027": {
|
| 87 |
+
"content": "<|tool_response|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"200028": {
|
| 95 |
+
"content": "<|tag|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
}
|
| 102 |
+
},
|
| 103 |
+
"bos_token": "<|endoftext|>",
|
| 104 |
+
"clean_up_tokenization_spaces": false,
|
| 105 |
+
"eos_token": "<|endoftext|>",
|
| 106 |
+
"extra_special_tokens": {},
|
| 107 |
+
"model_max_length": 131072,
|
| 108 |
+
"pad_token": "<|endoftext|>",
|
| 109 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 110 |
+
"unk_token": "<|endoftext|>"
|
| 111 |
+
}
|
checkpoint-1100/trainer_state.json
ADDED
|
@@ -0,0 +1,1024 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.405572755417957,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1100,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.030959752321981424,
|
| 14 |
+
"grad_norm": 9.773098945617676,
|
| 15 |
+
"learning_rate": 2.991640866873065e-05,
|
| 16 |
+
"loss": 9.245,
|
| 17 |
+
"mean_token_accuracy": 0.2123243510723114,
|
| 18 |
+
"num_tokens": 5327.0,
|
| 19 |
+
"step": 10
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.06191950464396285,
|
| 23 |
+
"grad_norm": 3.128091335296631,
|
| 24 |
+
"learning_rate": 2.9823529411764707e-05,
|
| 25 |
+
"loss": 6.1602,
|
| 26 |
+
"mean_token_accuracy": 0.25044268518686297,
|
| 27 |
+
"num_tokens": 10795.0,
|
| 28 |
+
"step": 20
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.09287925696594428,
|
| 32 |
+
"grad_norm": 4.203906536102295,
|
| 33 |
+
"learning_rate": 2.973065015479876e-05,
|
| 34 |
+
"loss": 5.6948,
|
| 35 |
+
"mean_token_accuracy": 0.262071692943573,
|
| 36 |
+
"num_tokens": 16240.0,
|
| 37 |
+
"step": 30
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1238390092879257,
|
| 41 |
+
"grad_norm": 4.233511924743652,
|
| 42 |
+
"learning_rate": 2.9637770897832817e-05,
|
| 43 |
+
"loss": 5.2733,
|
| 44 |
+
"mean_token_accuracy": 0.27527774721384046,
|
| 45 |
+
"num_tokens": 21582.0,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.15479876160990713,
|
| 50 |
+
"grad_norm": 7.080459117889404,
|
| 51 |
+
"learning_rate": 2.9544891640866874e-05,
|
| 52 |
+
"loss": 4.9304,
|
| 53 |
+
"mean_token_accuracy": 0.2877007365226746,
|
| 54 |
+
"num_tokens": 27142.0,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.18575851393188855,
|
| 59 |
+
"grad_norm": 7.273204326629639,
|
| 60 |
+
"learning_rate": 2.945201238390093e-05,
|
| 61 |
+
"loss": 4.689,
|
| 62 |
+
"mean_token_accuracy": 0.28890604972839357,
|
| 63 |
+
"num_tokens": 32801.0,
|
| 64 |
+
"step": 60
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.21671826625386997,
|
| 68 |
+
"grad_norm": 2.2185206413269043,
|
| 69 |
+
"learning_rate": 2.9359133126934984e-05,
|
| 70 |
+
"loss": 4.3965,
|
| 71 |
+
"mean_token_accuracy": 0.28117197155952456,
|
| 72 |
+
"num_tokens": 38472.0,
|
| 73 |
+
"step": 70
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2476780185758514,
|
| 77 |
+
"grad_norm": 2.0464794635772705,
|
| 78 |
+
"learning_rate": 2.926625386996904e-05,
|
| 79 |
+
"loss": 4.062,
|
| 80 |
+
"mean_token_accuracy": 0.299494668841362,
|
| 81 |
+
"num_tokens": 43743.0,
|
| 82 |
+
"step": 80
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.2786377708978328,
|
| 86 |
+
"grad_norm": 1.633155345916748,
|
| 87 |
+
"learning_rate": 2.9173374613003097e-05,
|
| 88 |
+
"loss": 4.0378,
|
| 89 |
+
"mean_token_accuracy": 0.30819864571094513,
|
| 90 |
+
"num_tokens": 49087.0,
|
| 91 |
+
"step": 90
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.30959752321981426,
|
| 95 |
+
"grad_norm": 1.4594247341156006,
|
| 96 |
+
"learning_rate": 2.908049535603715e-05,
|
| 97 |
+
"loss": 3.8513,
|
| 98 |
+
"mean_token_accuracy": 0.3258361428976059,
|
| 99 |
+
"num_tokens": 54433.0,
|
| 100 |
+
"step": 100
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.34055727554179566,
|
| 104 |
+
"grad_norm": 1.5312635898590088,
|
| 105 |
+
"learning_rate": 2.898761609907121e-05,
|
| 106 |
+
"loss": 3.9162,
|
| 107 |
+
"mean_token_accuracy": 0.32140363454818727,
|
| 108 |
+
"num_tokens": 59629.0,
|
| 109 |
+
"step": 110
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.3715170278637771,
|
| 113 |
+
"grad_norm": 1.3190491199493408,
|
| 114 |
+
"learning_rate": 2.8894736842105263e-05,
|
| 115 |
+
"loss": 3.902,
|
| 116 |
+
"mean_token_accuracy": 0.3103078156709671,
|
| 117 |
+
"num_tokens": 65326.0,
|
| 118 |
+
"step": 120
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.4024767801857585,
|
| 122 |
+
"grad_norm": 1.6095689535140991,
|
| 123 |
+
"learning_rate": 2.880185758513932e-05,
|
| 124 |
+
"loss": 3.7107,
|
| 125 |
+
"mean_token_accuracy": 0.3353793561458588,
|
| 126 |
+
"num_tokens": 70440.0,
|
| 127 |
+
"step": 130
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.43343653250773995,
|
| 131 |
+
"grad_norm": 1.6634972095489502,
|
| 132 |
+
"learning_rate": 2.8708978328173377e-05,
|
| 133 |
+
"loss": 3.7747,
|
| 134 |
+
"mean_token_accuracy": 0.3298566401004791,
|
| 135 |
+
"num_tokens": 75712.0,
|
| 136 |
+
"step": 140
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.46439628482972134,
|
| 140 |
+
"grad_norm": 1.3906605243682861,
|
| 141 |
+
"learning_rate": 2.861609907120743e-05,
|
| 142 |
+
"loss": 3.7344,
|
| 143 |
+
"mean_token_accuracy": 0.34043932259082793,
|
| 144 |
+
"num_tokens": 81272.0,
|
| 145 |
+
"step": 150
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.4953560371517028,
|
| 149 |
+
"grad_norm": 1.6273926496505737,
|
| 150 |
+
"learning_rate": 2.8523219814241487e-05,
|
| 151 |
+
"loss": 3.6722,
|
| 152 |
+
"mean_token_accuracy": 0.33802524507045745,
|
| 153 |
+
"num_tokens": 86836.0,
|
| 154 |
+
"step": 160
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.5263157894736842,
|
| 158 |
+
"grad_norm": 1.595566987991333,
|
| 159 |
+
"learning_rate": 2.8430340557275543e-05,
|
| 160 |
+
"loss": 3.5486,
|
| 161 |
+
"mean_token_accuracy": 0.36929037272930143,
|
| 162 |
+
"num_tokens": 91622.0,
|
| 163 |
+
"step": 170
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5572755417956656,
|
| 167 |
+
"grad_norm": 1.9571454524993896,
|
| 168 |
+
"learning_rate": 2.83374613003096e-05,
|
| 169 |
+
"loss": 3.6849,
|
| 170 |
+
"mean_token_accuracy": 0.3387055486440659,
|
| 171 |
+
"num_tokens": 97019.0,
|
| 172 |
+
"step": 180
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.5882352941176471,
|
| 176 |
+
"grad_norm": 1.6203333139419556,
|
| 177 |
+
"learning_rate": 2.8244582043343653e-05,
|
| 178 |
+
"loss": 3.5592,
|
| 179 |
+
"mean_token_accuracy": 0.36260710954666137,
|
| 180 |
+
"num_tokens": 102273.0,
|
| 181 |
+
"step": 190
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.6191950464396285,
|
| 185 |
+
"grad_norm": 1.8625439405441284,
|
| 186 |
+
"learning_rate": 2.815170278637771e-05,
|
| 187 |
+
"loss": 3.4542,
|
| 188 |
+
"mean_token_accuracy": 0.3554231733083725,
|
| 189 |
+
"num_tokens": 107847.0,
|
| 190 |
+
"step": 200
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.6501547987616099,
|
| 194 |
+
"grad_norm": 1.5171610116958618,
|
| 195 |
+
"learning_rate": 2.8058823529411766e-05,
|
| 196 |
+
"loss": 3.6914,
|
| 197 |
+
"mean_token_accuracy": 0.3506886214017868,
|
| 198 |
+
"num_tokens": 113499.0,
|
| 199 |
+
"step": 210
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.6811145510835913,
|
| 203 |
+
"grad_norm": 1.465408205986023,
|
| 204 |
+
"learning_rate": 2.796594427244582e-05,
|
| 205 |
+
"loss": 3.6008,
|
| 206 |
+
"mean_token_accuracy": 0.3558589071035385,
|
| 207 |
+
"num_tokens": 119014.0,
|
| 208 |
+
"step": 220
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.7120743034055728,
|
| 212 |
+
"grad_norm": 1.5382874011993408,
|
| 213 |
+
"learning_rate": 2.787306501547988e-05,
|
| 214 |
+
"loss": 3.5375,
|
| 215 |
+
"mean_token_accuracy": 0.3548148155212402,
|
| 216 |
+
"num_tokens": 124170.0,
|
| 217 |
+
"step": 230
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.7430340557275542,
|
| 221 |
+
"grad_norm": 1.773881196975708,
|
| 222 |
+
"learning_rate": 2.7780185758513933e-05,
|
| 223 |
+
"loss": 3.573,
|
| 224 |
+
"mean_token_accuracy": 0.3465736091136932,
|
| 225 |
+
"num_tokens": 129487.0,
|
| 226 |
+
"step": 240
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7739938080495357,
|
| 230 |
+
"grad_norm": 1.7652744054794312,
|
| 231 |
+
"learning_rate": 2.7687306501547986e-05,
|
| 232 |
+
"loss": 3.6811,
|
| 233 |
+
"mean_token_accuracy": 0.33623204231262205,
|
| 234 |
+
"num_tokens": 135007.0,
|
| 235 |
+
"step": 250
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.804953560371517,
|
| 239 |
+
"grad_norm": 1.7662419080734253,
|
| 240 |
+
"learning_rate": 2.7594427244582046e-05,
|
| 241 |
+
"loss": 3.505,
|
| 242 |
+
"mean_token_accuracy": 0.3567329585552216,
|
| 243 |
+
"num_tokens": 140143.0,
|
| 244 |
+
"step": 260
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.8359133126934984,
|
| 248 |
+
"grad_norm": 1.9441474676132202,
|
| 249 |
+
"learning_rate": 2.75015479876161e-05,
|
| 250 |
+
"loss": 3.4804,
|
| 251 |
+
"mean_token_accuracy": 0.36218210160732267,
|
| 252 |
+
"num_tokens": 145363.0,
|
| 253 |
+
"step": 270
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.8668730650154799,
|
| 257 |
+
"grad_norm": 1.745896816253662,
|
| 258 |
+
"learning_rate": 2.7408668730650156e-05,
|
| 259 |
+
"loss": 3.6519,
|
| 260 |
+
"mean_token_accuracy": 0.34941086173057556,
|
| 261 |
+
"num_tokens": 150840.0,
|
| 262 |
+
"step": 280
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.8978328173374613,
|
| 266 |
+
"grad_norm": 1.928284764289856,
|
| 267 |
+
"learning_rate": 2.7315789473684213e-05,
|
| 268 |
+
"loss": 3.6138,
|
| 269 |
+
"mean_token_accuracy": 0.34826839864254,
|
| 270 |
+
"num_tokens": 156077.0,
|
| 271 |
+
"step": 290
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.9287925696594427,
|
| 275 |
+
"grad_norm": 2.177100896835327,
|
| 276 |
+
"learning_rate": 2.722291021671827e-05,
|
| 277 |
+
"loss": 3.4666,
|
| 278 |
+
"mean_token_accuracy": 0.36537405848503113,
|
| 279 |
+
"num_tokens": 160953.0,
|
| 280 |
+
"step": 300
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.9597523219814241,
|
| 284 |
+
"grad_norm": 2.203282594680786,
|
| 285 |
+
"learning_rate": 2.7130030959752322e-05,
|
| 286 |
+
"loss": 3.5842,
|
| 287 |
+
"mean_token_accuracy": 0.34776660799980164,
|
| 288 |
+
"num_tokens": 166286.0,
|
| 289 |
+
"step": 310
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9907120743034056,
|
| 293 |
+
"grad_norm": 1.724373459815979,
|
| 294 |
+
"learning_rate": 2.7037151702786376e-05,
|
| 295 |
+
"loss": 3.4961,
|
| 296 |
+
"mean_token_accuracy": 0.35577190220355986,
|
| 297 |
+
"num_tokens": 171629.0,
|
| 298 |
+
"step": 320
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.021671826625387,
|
| 302 |
+
"grad_norm": 1.7433867454528809,
|
| 303 |
+
"learning_rate": 2.6944272445820436e-05,
|
| 304 |
+
"loss": 3.4088,
|
| 305 |
+
"mean_token_accuracy": 0.36975419521331787,
|
| 306 |
+
"num_tokens": 176968.0,
|
| 307 |
+
"step": 330
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.0526315789473684,
|
| 311 |
+
"grad_norm": 2.0577471256256104,
|
| 312 |
+
"learning_rate": 2.685139318885449e-05,
|
| 313 |
+
"loss": 3.5364,
|
| 314 |
+
"mean_token_accuracy": 0.35527182221412656,
|
| 315 |
+
"num_tokens": 182390.0,
|
| 316 |
+
"step": 340
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.08359133126935,
|
| 320 |
+
"grad_norm": 1.7357635498046875,
|
| 321 |
+
"learning_rate": 2.6758513931888546e-05,
|
| 322 |
+
"loss": 3.4495,
|
| 323 |
+
"mean_token_accuracy": 0.3565235286951065,
|
| 324 |
+
"num_tokens": 188181.0,
|
| 325 |
+
"step": 350
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.1145510835913313,
|
| 329 |
+
"grad_norm": 2.024507761001587,
|
| 330 |
+
"learning_rate": 2.6665634674922602e-05,
|
| 331 |
+
"loss": 3.3766,
|
| 332 |
+
"mean_token_accuracy": 0.3696540713310242,
|
| 333 |
+
"num_tokens": 193427.0,
|
| 334 |
+
"step": 360
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.1455108359133126,
|
| 338 |
+
"grad_norm": 2.1170592308044434,
|
| 339 |
+
"learning_rate": 2.6572755417956655e-05,
|
| 340 |
+
"loss": 3.4759,
|
| 341 |
+
"mean_token_accuracy": 0.35803447663784027,
|
| 342 |
+
"num_tokens": 199046.0,
|
| 343 |
+
"step": 370
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.1764705882352942,
|
| 347 |
+
"grad_norm": 2.118878126144409,
|
| 348 |
+
"learning_rate": 2.6479876160990712e-05,
|
| 349 |
+
"loss": 3.4685,
|
| 350 |
+
"mean_token_accuracy": 0.3570233076810837,
|
| 351 |
+
"num_tokens": 204089.0,
|
| 352 |
+
"step": 380
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.2074303405572755,
|
| 356 |
+
"grad_norm": 2.2280914783477783,
|
| 357 |
+
"learning_rate": 2.638699690402477e-05,
|
| 358 |
+
"loss": 3.4822,
|
| 359 |
+
"mean_token_accuracy": 0.36153341829776764,
|
| 360 |
+
"num_tokens": 209656.0,
|
| 361 |
+
"step": 390
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.238390092879257,
|
| 365 |
+
"grad_norm": 2.444979667663574,
|
| 366 |
+
"learning_rate": 2.6294117647058825e-05,
|
| 367 |
+
"loss": 3.3666,
|
| 368 |
+
"mean_token_accuracy": 0.3748770415782928,
|
| 369 |
+
"num_tokens": 214465.0,
|
| 370 |
+
"step": 400
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.2693498452012384,
|
| 374 |
+
"grad_norm": 1.9609659910202026,
|
| 375 |
+
"learning_rate": 2.620123839009288e-05,
|
| 376 |
+
"loss": 3.4161,
|
| 377 |
+
"mean_token_accuracy": 0.3594685852527618,
|
| 378 |
+
"num_tokens": 219728.0,
|
| 379 |
+
"step": 410
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.3003095975232197,
|
| 383 |
+
"grad_norm": 1.9759095907211304,
|
| 384 |
+
"learning_rate": 2.6108359133126935e-05,
|
| 385 |
+
"loss": 3.405,
|
| 386 |
+
"mean_token_accuracy": 0.3668099522590637,
|
| 387 |
+
"num_tokens": 224992.0,
|
| 388 |
+
"step": 420
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.3312693498452013,
|
| 392 |
+
"grad_norm": 2.1737940311431885,
|
| 393 |
+
"learning_rate": 2.6015479876160992e-05,
|
| 394 |
+
"loss": 3.3809,
|
| 395 |
+
"mean_token_accuracy": 0.37462269365787504,
|
| 396 |
+
"num_tokens": 230431.0,
|
| 397 |
+
"step": 430
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.3622291021671826,
|
| 401 |
+
"grad_norm": 2.475351333618164,
|
| 402 |
+
"learning_rate": 2.5922600619195045e-05,
|
| 403 |
+
"loss": 3.3454,
|
| 404 |
+
"mean_token_accuracy": 0.36902076900005343,
|
| 405 |
+
"num_tokens": 235868.0,
|
| 406 |
+
"step": 440
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.3931888544891642,
|
| 410 |
+
"grad_norm": 2.1027772426605225,
|
| 411 |
+
"learning_rate": 2.5829721362229105e-05,
|
| 412 |
+
"loss": 3.3967,
|
| 413 |
+
"mean_token_accuracy": 0.3779816538095474,
|
| 414 |
+
"num_tokens": 241149.0,
|
| 415 |
+
"step": 450
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.4241486068111455,
|
| 419 |
+
"grad_norm": 2.613186836242676,
|
| 420 |
+
"learning_rate": 2.5736842105263158e-05,
|
| 421 |
+
"loss": 3.3383,
|
| 422 |
+
"mean_token_accuracy": 0.37455591559410095,
|
| 423 |
+
"num_tokens": 246200.0,
|
| 424 |
+
"step": 460
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.4551083591331269,
|
| 428 |
+
"grad_norm": 2.1689629554748535,
|
| 429 |
+
"learning_rate": 2.5643962848297215e-05,
|
| 430 |
+
"loss": 3.4927,
|
| 431 |
+
"mean_token_accuracy": 0.3641968876123428,
|
| 432 |
+
"num_tokens": 251354.0,
|
| 433 |
+
"step": 470
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.4860681114551084,
|
| 437 |
+
"grad_norm": 1.9075849056243896,
|
| 438 |
+
"learning_rate": 2.555108359133127e-05,
|
| 439 |
+
"loss": 3.4211,
|
| 440 |
+
"mean_token_accuracy": 0.3670921057462692,
|
| 441 |
+
"num_tokens": 257201.0,
|
| 442 |
+
"step": 480
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.5170278637770898,
|
| 446 |
+
"grad_norm": 2.128737211227417,
|
| 447 |
+
"learning_rate": 2.5458204334365325e-05,
|
| 448 |
+
"loss": 3.3306,
|
| 449 |
+
"mean_token_accuracy": 0.3747966349124908,
|
| 450 |
+
"num_tokens": 262640.0,
|
| 451 |
+
"step": 490
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.5479876160990713,
|
| 455 |
+
"grad_norm": 1.9061874151229858,
|
| 456 |
+
"learning_rate": 2.536532507739938e-05,
|
| 457 |
+
"loss": 3.3874,
|
| 458 |
+
"mean_token_accuracy": 0.3706284284591675,
|
| 459 |
+
"num_tokens": 268129.0,
|
| 460 |
+
"step": 500
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.5789473684210527,
|
| 464 |
+
"grad_norm": 1.8868329524993896,
|
| 465 |
+
"learning_rate": 2.5272445820433438e-05,
|
| 466 |
+
"loss": 3.3185,
|
| 467 |
+
"mean_token_accuracy": 0.37699449956417086,
|
| 468 |
+
"num_tokens": 273489.0,
|
| 469 |
+
"step": 510
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.609907120743034,
|
| 473 |
+
"grad_norm": 1.8507658243179321,
|
| 474 |
+
"learning_rate": 2.5179566563467495e-05,
|
| 475 |
+
"loss": 3.2901,
|
| 476 |
+
"mean_token_accuracy": 0.3797824054956436,
|
| 477 |
+
"num_tokens": 279142.0,
|
| 478 |
+
"step": 520
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.6408668730650153,
|
| 482 |
+
"grad_norm": 2.396951198577881,
|
| 483 |
+
"learning_rate": 2.5086687306501548e-05,
|
| 484 |
+
"loss": 3.3503,
|
| 485 |
+
"mean_token_accuracy": 0.37934728860855105,
|
| 486 |
+
"num_tokens": 284049.0,
|
| 487 |
+
"step": 530
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.671826625386997,
|
| 491 |
+
"grad_norm": 2.256753921508789,
|
| 492 |
+
"learning_rate": 2.4993808049535605e-05,
|
| 493 |
+
"loss": 3.3706,
|
| 494 |
+
"mean_token_accuracy": 0.38219387233257296,
|
| 495 |
+
"num_tokens": 289514.0,
|
| 496 |
+
"step": 540
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.7027863777089784,
|
| 500 |
+
"grad_norm": 1.9369879961013794,
|
| 501 |
+
"learning_rate": 2.490092879256966e-05,
|
| 502 |
+
"loss": 3.3615,
|
| 503 |
+
"mean_token_accuracy": 0.37476457953453063,
|
| 504 |
+
"num_tokens": 295091.0,
|
| 505 |
+
"step": 550
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.7337461300309598,
|
| 509 |
+
"grad_norm": 2.6628825664520264,
|
| 510 |
+
"learning_rate": 2.4808049535603714e-05,
|
| 511 |
+
"loss": 3.3121,
|
| 512 |
+
"mean_token_accuracy": 0.3830788493156433,
|
| 513 |
+
"num_tokens": 300102.0,
|
| 514 |
+
"step": 560
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.7647058823529411,
|
| 518 |
+
"grad_norm": 2.6188621520996094,
|
| 519 |
+
"learning_rate": 2.4715170278637774e-05,
|
| 520 |
+
"loss": 3.4005,
|
| 521 |
+
"mean_token_accuracy": 0.3631168991327286,
|
| 522 |
+
"num_tokens": 305652.0,
|
| 523 |
+
"step": 570
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.7956656346749225,
|
| 527 |
+
"grad_norm": 2.093585968017578,
|
| 528 |
+
"learning_rate": 2.4622291021671828e-05,
|
| 529 |
+
"loss": 3.4483,
|
| 530 |
+
"mean_token_accuracy": 0.3639900177717209,
|
| 531 |
+
"num_tokens": 311333.0,
|
| 532 |
+
"step": 580
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.826625386996904,
|
| 536 |
+
"grad_norm": 2.355714797973633,
|
| 537 |
+
"learning_rate": 2.452941176470588e-05,
|
| 538 |
+
"loss": 3.2946,
|
| 539 |
+
"mean_token_accuracy": 0.3784641414880753,
|
| 540 |
+
"num_tokens": 316699.0,
|
| 541 |
+
"step": 590
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.8575851393188856,
|
| 545 |
+
"grad_norm": 2.5051403045654297,
|
| 546 |
+
"learning_rate": 2.4436532507739938e-05,
|
| 547 |
+
"loss": 3.2612,
|
| 548 |
+
"mean_token_accuracy": 0.3874821364879608,
|
| 549 |
+
"num_tokens": 321718.0,
|
| 550 |
+
"step": 600
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.888544891640867,
|
| 554 |
+
"grad_norm": 2.4884731769561768,
|
| 555 |
+
"learning_rate": 2.4343653250773994e-05,
|
| 556 |
+
"loss": 3.3375,
|
| 557 |
+
"mean_token_accuracy": 0.37331779301166534,
|
| 558 |
+
"num_tokens": 327347.0,
|
| 559 |
+
"step": 610
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.9195046439628483,
|
| 563 |
+
"grad_norm": 2.7246131896972656,
|
| 564 |
+
"learning_rate": 2.425077399380805e-05,
|
| 565 |
+
"loss": 3.3235,
|
| 566 |
+
"mean_token_accuracy": 0.38473727405071256,
|
| 567 |
+
"num_tokens": 332563.0,
|
| 568 |
+
"step": 620
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.9504643962848296,
|
| 572 |
+
"grad_norm": 2.420604705810547,
|
| 573 |
+
"learning_rate": 2.4157894736842104e-05,
|
| 574 |
+
"loss": 3.4027,
|
| 575 |
+
"mean_token_accuracy": 0.36371313631534574,
|
| 576 |
+
"num_tokens": 337880.0,
|
| 577 |
+
"step": 630
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.9814241486068112,
|
| 581 |
+
"grad_norm": 2.1465680599212646,
|
| 582 |
+
"learning_rate": 2.4065015479876164e-05,
|
| 583 |
+
"loss": 3.3508,
|
| 584 |
+
"mean_token_accuracy": 0.3747645616531372,
|
| 585 |
+
"num_tokens": 343193.0,
|
| 586 |
+
"step": 640
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.0123839009287927,
|
| 590 |
+
"grad_norm": 2.0795834064483643,
|
| 591 |
+
"learning_rate": 2.3972136222910217e-05,
|
| 592 |
+
"loss": 3.3529,
|
| 593 |
+
"mean_token_accuracy": 0.3744541972875595,
|
| 594 |
+
"num_tokens": 348460.0,
|
| 595 |
+
"step": 650
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.043343653250774,
|
| 599 |
+
"grad_norm": 2.4051778316497803,
|
| 600 |
+
"learning_rate": 2.387925696594427e-05,
|
| 601 |
+
"loss": 3.2404,
|
| 602 |
+
"mean_token_accuracy": 0.38319246768951415,
|
| 603 |
+
"num_tokens": 353701.0,
|
| 604 |
+
"step": 660
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.0743034055727554,
|
| 608 |
+
"grad_norm": 2.401045322418213,
|
| 609 |
+
"learning_rate": 2.378637770897833e-05,
|
| 610 |
+
"loss": 3.2801,
|
| 611 |
+
"mean_token_accuracy": 0.3773155301809311,
|
| 612 |
+
"num_tokens": 359147.0,
|
| 613 |
+
"step": 670
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.1052631578947367,
|
| 617 |
+
"grad_norm": 2.554138422012329,
|
| 618 |
+
"learning_rate": 2.3693498452012384e-05,
|
| 619 |
+
"loss": 3.2227,
|
| 620 |
+
"mean_token_accuracy": 0.37754152715206146,
|
| 621 |
+
"num_tokens": 364696.0,
|
| 622 |
+
"step": 680
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 2.136222910216718,
|
| 626 |
+
"grad_norm": 2.4874625205993652,
|
| 627 |
+
"learning_rate": 2.360061919504644e-05,
|
| 628 |
+
"loss": 3.2534,
|
| 629 |
+
"mean_token_accuracy": 0.3920708328485489,
|
| 630 |
+
"num_tokens": 370207.0,
|
| 631 |
+
"step": 690
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.1671826625387,
|
| 635 |
+
"grad_norm": 2.638068675994873,
|
| 636 |
+
"learning_rate": 2.3507739938080497e-05,
|
| 637 |
+
"loss": 3.2635,
|
| 638 |
+
"mean_token_accuracy": 0.3835586577653885,
|
| 639 |
+
"num_tokens": 375977.0,
|
| 640 |
+
"step": 700
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.198142414860681,
|
| 644 |
+
"grad_norm": 2.5179686546325684,
|
| 645 |
+
"learning_rate": 2.341486068111455e-05,
|
| 646 |
+
"loss": 3.1599,
|
| 647 |
+
"mean_token_accuracy": 0.39867666363716125,
|
| 648 |
+
"num_tokens": 381398.0,
|
| 649 |
+
"step": 710
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.2291021671826625,
|
| 653 |
+
"grad_norm": 2.9102959632873535,
|
| 654 |
+
"learning_rate": 2.3321981424148607e-05,
|
| 655 |
+
"loss": 3.2686,
|
| 656 |
+
"mean_token_accuracy": 0.3878729552030563,
|
| 657 |
+
"num_tokens": 386460.0,
|
| 658 |
+
"step": 720
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.260061919504644,
|
| 662 |
+
"grad_norm": 2.641160726547241,
|
| 663 |
+
"learning_rate": 2.3229102167182663e-05,
|
| 664 |
+
"loss": 3.2218,
|
| 665 |
+
"mean_token_accuracy": 0.38672482669353486,
|
| 666 |
+
"num_tokens": 391538.0,
|
| 667 |
+
"step": 730
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.291021671826625,
|
| 671 |
+
"grad_norm": 2.947000026702881,
|
| 672 |
+
"learning_rate": 2.313622291021672e-05,
|
| 673 |
+
"loss": 3.2215,
|
| 674 |
+
"mean_token_accuracy": 0.38650966584682467,
|
| 675 |
+
"num_tokens": 396881.0,
|
| 676 |
+
"step": 740
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.321981424148607,
|
| 680 |
+
"grad_norm": 2.3614673614501953,
|
| 681 |
+
"learning_rate": 2.3043343653250773e-05,
|
| 682 |
+
"loss": 3.2233,
|
| 683 |
+
"mean_token_accuracy": 0.388895845413208,
|
| 684 |
+
"num_tokens": 402418.0,
|
| 685 |
+
"step": 750
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.3529411764705883,
|
| 689 |
+
"grad_norm": 2.492814302444458,
|
| 690 |
+
"learning_rate": 2.295046439628483e-05,
|
| 691 |
+
"loss": 3.2005,
|
| 692 |
+
"mean_token_accuracy": 0.382270821928978,
|
| 693 |
+
"num_tokens": 407733.0,
|
| 694 |
+
"step": 760
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.3839009287925697,
|
| 698 |
+
"grad_norm": 2.646655321121216,
|
| 699 |
+
"learning_rate": 2.2857585139318887e-05,
|
| 700 |
+
"loss": 3.1642,
|
| 701 |
+
"mean_token_accuracy": 0.388735693693161,
|
| 702 |
+
"num_tokens": 413101.0,
|
| 703 |
+
"step": 770
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.414860681114551,
|
| 707 |
+
"grad_norm": 2.782440662384033,
|
| 708 |
+
"learning_rate": 2.276470588235294e-05,
|
| 709 |
+
"loss": 3.2513,
|
| 710 |
+
"mean_token_accuracy": 0.38574750125408175,
|
| 711 |
+
"num_tokens": 418754.0,
|
| 712 |
+
"step": 780
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.4458204334365323,
|
| 716 |
+
"grad_norm": 2.7094547748565674,
|
| 717 |
+
"learning_rate": 2.2671826625387e-05,
|
| 718 |
+
"loss": 3.3007,
|
| 719 |
+
"mean_token_accuracy": 0.38453402519226076,
|
| 720 |
+
"num_tokens": 424232.0,
|
| 721 |
+
"step": 790
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.476780185758514,
|
| 725 |
+
"grad_norm": 2.697098970413208,
|
| 726 |
+
"learning_rate": 2.2578947368421053e-05,
|
| 727 |
+
"loss": 3.254,
|
| 728 |
+
"mean_token_accuracy": 0.3893850326538086,
|
| 729 |
+
"num_tokens": 429369.0,
|
| 730 |
+
"step": 800
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.5077399380804954,
|
| 734 |
+
"grad_norm": 3.2908523082733154,
|
| 735 |
+
"learning_rate": 2.248606811145511e-05,
|
| 736 |
+
"loss": 3.1944,
|
| 737 |
+
"mean_token_accuracy": 0.39619002044200896,
|
| 738 |
+
"num_tokens": 434497.0,
|
| 739 |
+
"step": 810
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.538699690402477,
|
| 743 |
+
"grad_norm": 3.068455696105957,
|
| 744 |
+
"learning_rate": 2.2393188854489166e-05,
|
| 745 |
+
"loss": 3.2034,
|
| 746 |
+
"mean_token_accuracy": 0.3942800432443619,
|
| 747 |
+
"num_tokens": 439892.0,
|
| 748 |
+
"step": 820
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 2.569659442724458,
|
| 752 |
+
"grad_norm": 2.7893826961517334,
|
| 753 |
+
"learning_rate": 2.230030959752322e-05,
|
| 754 |
+
"loss": 3.0723,
|
| 755 |
+
"mean_token_accuracy": 0.39791189730167387,
|
| 756 |
+
"num_tokens": 445189.0,
|
| 757 |
+
"step": 830
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 2.6006191950464395,
|
| 761 |
+
"grad_norm": 2.7569446563720703,
|
| 762 |
+
"learning_rate": 2.2207430340557276e-05,
|
| 763 |
+
"loss": 3.187,
|
| 764 |
+
"mean_token_accuracy": 0.3884226083755493,
|
| 765 |
+
"num_tokens": 450338.0,
|
| 766 |
+
"step": 840
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.6315789473684212,
|
| 770 |
+
"grad_norm": 3.16340708732605,
|
| 771 |
+
"learning_rate": 2.2114551083591333e-05,
|
| 772 |
+
"loss": 3.1942,
|
| 773 |
+
"mean_token_accuracy": 0.3921455442905426,
|
| 774 |
+
"num_tokens": 455583.0,
|
| 775 |
+
"step": 850
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.6625386996904026,
|
| 779 |
+
"grad_norm": 2.549273729324341,
|
| 780 |
+
"learning_rate": 2.202167182662539e-05,
|
| 781 |
+
"loss": 3.278,
|
| 782 |
+
"mean_token_accuracy": 0.3782683253288269,
|
| 783 |
+
"num_tokens": 461089.0,
|
| 784 |
+
"step": 860
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.693498452012384,
|
| 788 |
+
"grad_norm": 3.216149091720581,
|
| 789 |
+
"learning_rate": 2.1928792569659443e-05,
|
| 790 |
+
"loss": 3.2023,
|
| 791 |
+
"mean_token_accuracy": 0.3940991997718811,
|
| 792 |
+
"num_tokens": 466239.0,
|
| 793 |
+
"step": 870
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.7244582043343653,
|
| 797 |
+
"grad_norm": 2.4680261611938477,
|
| 798 |
+
"learning_rate": 2.18359133126935e-05,
|
| 799 |
+
"loss": 3.2017,
|
| 800 |
+
"mean_token_accuracy": 0.3878098428249359,
|
| 801 |
+
"num_tokens": 471660.0,
|
| 802 |
+
"step": 880
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.7554179566563466,
|
| 806 |
+
"grad_norm": 3.6166999340057373,
|
| 807 |
+
"learning_rate": 2.1743034055727556e-05,
|
| 808 |
+
"loss": 3.2068,
|
| 809 |
+
"mean_token_accuracy": 0.3789886265993118,
|
| 810 |
+
"num_tokens": 476713.0,
|
| 811 |
+
"step": 890
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 2.7863777089783284,
|
| 815 |
+
"grad_norm": 2.0997393131256104,
|
| 816 |
+
"learning_rate": 2.165015479876161e-05,
|
| 817 |
+
"loss": 3.2216,
|
| 818 |
+
"mean_token_accuracy": 0.3913588523864746,
|
| 819 |
+
"num_tokens": 482569.0,
|
| 820 |
+
"step": 900
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.8173374613003097,
|
| 824 |
+
"grad_norm": 3.0189061164855957,
|
| 825 |
+
"learning_rate": 2.1557275541795666e-05,
|
| 826 |
+
"loss": 3.1346,
|
| 827 |
+
"mean_token_accuracy": 0.3967192888259888,
|
| 828 |
+
"num_tokens": 487629.0,
|
| 829 |
+
"step": 910
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 2.848297213622291,
|
| 833 |
+
"grad_norm": 2.8610568046569824,
|
| 834 |
+
"learning_rate": 2.1464396284829722e-05,
|
| 835 |
+
"loss": 3.2061,
|
| 836 |
+
"mean_token_accuracy": 0.3921816825866699,
|
| 837 |
+
"num_tokens": 493227.0,
|
| 838 |
+
"step": 920
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.8792569659442724,
|
| 842 |
+
"grad_norm": 3.023012638092041,
|
| 843 |
+
"learning_rate": 2.1371517027863776e-05,
|
| 844 |
+
"loss": 3.2208,
|
| 845 |
+
"mean_token_accuracy": 0.3786366432905197,
|
| 846 |
+
"num_tokens": 498394.0,
|
| 847 |
+
"step": 930
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 2.9102167182662537,
|
| 851 |
+
"grad_norm": 2.908886194229126,
|
| 852 |
+
"learning_rate": 2.1278637770897832e-05,
|
| 853 |
+
"loss": 3.1648,
|
| 854 |
+
"mean_token_accuracy": 0.3914026439189911,
|
| 855 |
+
"num_tokens": 503752.0,
|
| 856 |
+
"step": 940
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.9411764705882355,
|
| 860 |
+
"grad_norm": 3.078397750854492,
|
| 861 |
+
"learning_rate": 2.118575851393189e-05,
|
| 862 |
+
"loss": 3.1891,
|
| 863 |
+
"mean_token_accuracy": 0.39542897045612335,
|
| 864 |
+
"num_tokens": 509218.0,
|
| 865 |
+
"step": 950
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.972136222910217,
|
| 869 |
+
"grad_norm": 2.740389823913574,
|
| 870 |
+
"learning_rate": 2.1092879256965946e-05,
|
| 871 |
+
"loss": 3.1953,
|
| 872 |
+
"mean_token_accuracy": 0.3934174537658691,
|
| 873 |
+
"num_tokens": 514716.0,
|
| 874 |
+
"step": 960
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 3.003095975232198,
|
| 878 |
+
"grad_norm": 2.6426961421966553,
|
| 879 |
+
"learning_rate": 2.1e-05,
|
| 880 |
+
"loss": 3.1084,
|
| 881 |
+
"mean_token_accuracy": 0.39845702350139617,
|
| 882 |
+
"num_tokens": 520000.0,
|
| 883 |
+
"step": 970
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 3.0340557275541795,
|
| 887 |
+
"grad_norm": 2.8173840045928955,
|
| 888 |
+
"learning_rate": 2.090712074303406e-05,
|
| 889 |
+
"loss": 3.1574,
|
| 890 |
+
"mean_token_accuracy": 0.39481441378593446,
|
| 891 |
+
"num_tokens": 525561.0,
|
| 892 |
+
"step": 980
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.065015479876161,
|
| 896 |
+
"grad_norm": 3.29856014251709,
|
| 897 |
+
"learning_rate": 2.0814241486068112e-05,
|
| 898 |
+
"loss": 3.0613,
|
| 899 |
+
"mean_token_accuracy": 0.4054213762283325,
|
| 900 |
+
"num_tokens": 531021.0,
|
| 901 |
+
"step": 990
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 3.0959752321981426,
|
| 905 |
+
"grad_norm": 3.463890314102173,
|
| 906 |
+
"learning_rate": 2.0721362229102165e-05,
|
| 907 |
+
"loss": 3.0282,
|
| 908 |
+
"mean_token_accuracy": 0.4025467813014984,
|
| 909 |
+
"num_tokens": 536260.0,
|
| 910 |
+
"step": 1000
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 3.126934984520124,
|
| 914 |
+
"grad_norm": 3.134387731552124,
|
| 915 |
+
"learning_rate": 2.0628482972136225e-05,
|
| 916 |
+
"loss": 3.1147,
|
| 917 |
+
"mean_token_accuracy": 0.3955592781305313,
|
| 918 |
+
"num_tokens": 541721.0,
|
| 919 |
+
"step": 1010
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 3.1578947368421053,
|
| 923 |
+
"grad_norm": 3.237518072128296,
|
| 924 |
+
"learning_rate": 2.053560371517028e-05,
|
| 925 |
+
"loss": 3.0828,
|
| 926 |
+
"mean_token_accuracy": 0.40579850077629087,
|
| 927 |
+
"num_tokens": 547334.0,
|
| 928 |
+
"step": 1020
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 3.1888544891640866,
|
| 932 |
+
"grad_norm": 3.2742724418640137,
|
| 933 |
+
"learning_rate": 2.0442724458204335e-05,
|
| 934 |
+
"loss": 3.0907,
|
| 935 |
+
"mean_token_accuracy": 0.40091423988342284,
|
| 936 |
+
"num_tokens": 552904.0,
|
| 937 |
+
"step": 1030
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 3.219814241486068,
|
| 941 |
+
"grad_norm": 3.0646955966949463,
|
| 942 |
+
"learning_rate": 2.0349845201238392e-05,
|
| 943 |
+
"loss": 3.0758,
|
| 944 |
+
"mean_token_accuracy": 0.40378672182559966,
|
| 945 |
+
"num_tokens": 557743.0,
|
| 946 |
+
"step": 1040
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 3.2507739938080498,
|
| 950 |
+
"grad_norm": 3.2615506649017334,
|
| 951 |
+
"learning_rate": 2.0256965944272445e-05,
|
| 952 |
+
"loss": 3.0844,
|
| 953 |
+
"mean_token_accuracy": 0.41148235499858854,
|
| 954 |
+
"num_tokens": 563604.0,
|
| 955 |
+
"step": 1050
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 3.281733746130031,
|
| 959 |
+
"grad_norm": 3.001723527908325,
|
| 960 |
+
"learning_rate": 2.0164086687306502e-05,
|
| 961 |
+
"loss": 2.9993,
|
| 962 |
+
"mean_token_accuracy": 0.41538413166999816,
|
| 963 |
+
"num_tokens": 568980.0,
|
| 964 |
+
"step": 1060
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 3.3126934984520124,
|
| 968 |
+
"grad_norm": 3.545367956161499,
|
| 969 |
+
"learning_rate": 2.007120743034056e-05,
|
| 970 |
+
"loss": 3.0765,
|
| 971 |
+
"mean_token_accuracy": 0.40937572419643403,
|
| 972 |
+
"num_tokens": 573896.0,
|
| 973 |
+
"step": 1070
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 3.343653250773994,
|
| 977 |
+
"grad_norm": 3.4989709854125977,
|
| 978 |
+
"learning_rate": 1.9978328173374615e-05,
|
| 979 |
+
"loss": 3.1538,
|
| 980 |
+
"mean_token_accuracy": 0.3883706986904144,
|
| 981 |
+
"num_tokens": 579254.0,
|
| 982 |
+
"step": 1080
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 3.374613003095975,
|
| 986 |
+
"grad_norm": 3.964334487915039,
|
| 987 |
+
"learning_rate": 1.9885448916408668e-05,
|
| 988 |
+
"loss": 3.1399,
|
| 989 |
+
"mean_token_accuracy": 0.3968294531106949,
|
| 990 |
+
"num_tokens": 584603.0,
|
| 991 |
+
"step": 1090
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 3.405572755417957,
|
| 995 |
+
"grad_norm": 4.132855415344238,
|
| 996 |
+
"learning_rate": 1.9792569659442725e-05,
|
| 997 |
+
"loss": 3.1428,
|
| 998 |
+
"mean_token_accuracy": 0.3817721128463745,
|
| 999 |
+
"num_tokens": 590267.0,
|
| 1000 |
+
"step": 1100
|
| 1001 |
+
}
|
| 1002 |
+
],
|
| 1003 |
+
"logging_steps": 10,
|
| 1004 |
+
"max_steps": 3230,
|
| 1005 |
+
"num_input_tokens_seen": 0,
|
| 1006 |
+
"num_train_epochs": 10,
|
| 1007 |
+
"save_steps": 100,
|
| 1008 |
+
"stateful_callbacks": {
|
| 1009 |
+
"TrainerControl": {
|
| 1010 |
+
"args": {
|
| 1011 |
+
"should_epoch_stop": false,
|
| 1012 |
+
"should_evaluate": false,
|
| 1013 |
+
"should_log": false,
|
| 1014 |
+
"should_save": true,
|
| 1015 |
+
"should_training_stop": false
|
| 1016 |
+
},
|
| 1017 |
+
"attributes": {}
|
| 1018 |
+
}
|
| 1019 |
+
},
|
| 1020 |
+
"total_flos": 2.778658848011059e+16,
|
| 1021 |
+
"train_batch_size": 16,
|
| 1022 |
+
"trial_name": null,
|
| 1023 |
+
"trial_params": null
|
| 1024 |
+
}
|
checkpoint-1100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:296f00e71697e39b9b96ced2cbda9da38aa0e08c1dfa73c8eef3c62051e61b76
|
| 3 |
+
size 5688
|
checkpoint-1100/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1200/README.md
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/Phi-4-mini-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:microsoft/Phi-4-mini-instruct
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- trl
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Model ID
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
|
| 22 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
- **Developed by:** [More Information Needed]
|
| 27 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 28 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 29 |
+
- **Model type:** [More Information Needed]
|
| 30 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 31 |
+
- **License:** [More Information Needed]
|
| 32 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 33 |
+
|
| 34 |
+
### Model Sources [optional]
|
| 35 |
+
|
| 36 |
+
<!-- Provide the basic links for the model. -->
|
| 37 |
+
|
| 38 |
+
- **Repository:** [More Information Needed]
|
| 39 |
+
- **Paper [optional]:** [More Information Needed]
|
| 40 |
+
- **Demo [optional]:** [More Information Needed]
|
| 41 |
+
|
| 42 |
+
## Uses
|
| 43 |
+
|
| 44 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 45 |
+
|
| 46 |
+
### Direct Use
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Downstream Use [optional]
|
| 53 |
+
|
| 54 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
### Out-of-Scope Use
|
| 59 |
+
|
| 60 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
## Bias, Risks, and Limitations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 67 |
+
|
| 68 |
+
[More Information Needed]
|
| 69 |
+
|
| 70 |
+
### Recommendations
|
| 71 |
+
|
| 72 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 73 |
+
|
| 74 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 75 |
+
|
| 76 |
+
## How to Get Started with the Model
|
| 77 |
+
|
| 78 |
+
Use the code below to get started with the model.
|
| 79 |
+
|
| 80 |
+
[More Information Needed]
|
| 81 |
+
|
| 82 |
+
## Training Details
|
| 83 |
+
|
| 84 |
+
### Training Data
|
| 85 |
+
|
| 86 |
+
<!-- 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. -->
|
| 87 |
+
|
| 88 |
+
[More Information Needed]
|
| 89 |
+
|
| 90 |
+
### Training Procedure
|
| 91 |
+
|
| 92 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 93 |
+
|
| 94 |
+
#### Preprocessing [optional]
|
| 95 |
+
|
| 96 |
+
[More Information Needed]
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
#### Training Hyperparameters
|
| 100 |
+
|
| 101 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 102 |
+
|
| 103 |
+
#### Speeds, Sizes, Times [optional]
|
| 104 |
+
|
| 105 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 106 |
+
|
| 107 |
+
[More Information Needed]
|
| 108 |
+
|
| 109 |
+
## Evaluation
|
| 110 |
+
|
| 111 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 112 |
+
|
| 113 |
+
### Testing Data, Factors & Metrics
|
| 114 |
+
|
| 115 |
+
#### Testing Data
|
| 116 |
+
|
| 117 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Factors
|
| 122 |
+
|
| 123 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
#### Metrics
|
| 128 |
+
|
| 129 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 130 |
+
|
| 131 |
+
[More Information Needed]
|
| 132 |
+
|
| 133 |
+
### Results
|
| 134 |
+
|
| 135 |
+
[More Information Needed]
|
| 136 |
+
|
| 137 |
+
#### Summary
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Model Examination [optional]
|
| 142 |
+
|
| 143 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 144 |
+
|
| 145 |
+
[More Information Needed]
|
| 146 |
+
|
| 147 |
+
## Environmental Impact
|
| 148 |
+
|
| 149 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 150 |
+
|
| 151 |
+
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).
|
| 152 |
+
|
| 153 |
+
- **Hardware Type:** [More Information Needed]
|
| 154 |
+
- **Hours used:** [More Information Needed]
|
| 155 |
+
- **Cloud Provider:** [More Information Needed]
|
| 156 |
+
- **Compute Region:** [More Information Needed]
|
| 157 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 158 |
+
|
| 159 |
+
## Technical Specifications [optional]
|
| 160 |
+
|
| 161 |
+
### Model Architecture and Objective
|
| 162 |
+
|
| 163 |
+
[More Information Needed]
|
| 164 |
+
|
| 165 |
+
### Compute Infrastructure
|
| 166 |
+
|
| 167 |
+
[More Information Needed]
|
| 168 |
+
|
| 169 |
+
#### Hardware
|
| 170 |
+
|
| 171 |
+
[More Information Needed]
|
| 172 |
+
|
| 173 |
+
#### Software
|
| 174 |
+
|
| 175 |
+
[More Information Needed]
|
| 176 |
+
|
| 177 |
+
## Citation [optional]
|
| 178 |
+
|
| 179 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 180 |
+
|
| 181 |
+
**BibTeX:**
|
| 182 |
+
|
| 183 |
+
[More Information Needed]
|
| 184 |
+
|
| 185 |
+
**APA:**
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## Glossary [optional]
|
| 190 |
+
|
| 191 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 192 |
+
|
| 193 |
+
[More Information Needed]
|
| 194 |
+
|
| 195 |
+
## More Information [optional]
|
| 196 |
+
|
| 197 |
+
[More Information Needed]
|
| 198 |
+
|
| 199 |
+
## Model Card Authors [optional]
|
| 200 |
+
|
| 201 |
+
[More Information Needed]
|
| 202 |
+
|
| 203 |
+
## Model Card Contact
|
| 204 |
+
|
| 205 |
+
[More Information Needed]
|
| 206 |
+
### Framework versions
|
| 207 |
+
|
| 208 |
+
- PEFT 0.17.0
|
checkpoint-1200/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": null,
|
| 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": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 8,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"o_proj",
|
| 29 |
+
"qkv_proj",
|
| 30 |
+
"gate_up_proj",
|
| 31 |
+
"down_proj"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-1200/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1bf0a5134560213b413dcfe52e628044b2b09c2ff73eaa48ce948e028b1e6a7
|
| 3 |
+
size 46180160
|