Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +3 -0
- codellama-7b-lora-codellama-7b_std/checkpoint-last/README.md +202 -0
- codellama-7b-lora-codellama-7b_std/checkpoint-last/adapter_config.json +33 -0
- codellama-7b-lora-codellama-7b_std/checkpoint-last/adapter_model.safetensors +3 -0
- codellama-7b-lora-codellama-7b_std/checkpoint-last/special_tokens_map.json +29 -0
- codellama-7b-lora-codellama-7b_std/checkpoint-last/tokenizer.json +0 -0
- codellama-7b-lora-codellama-7b_std/checkpoint-last/tokenizer.model +3 -0
- codellama-7b-lora-codellama-7b_std/checkpoint-last/tokenizer_config.json +84 -0
- codellama-7b-lora-codellama-7b_std/train.log +84 -0
- deepseek-coder-1b_std/checkpoint-last/config.json +33 -0
- deepseek-coder-1b_std/checkpoint-last/generation_config.json +6 -0
- deepseek-coder-1b_std/checkpoint-last/model.safetensors +3 -0
- deepseek-coder-1b_std/checkpoint-last/special_tokens_map.json +23 -0
- deepseek-coder-1b_std/checkpoint-last/tokenizer.json +0 -0
- deepseek-coder-1b_std/checkpoint-last/tokenizer_config.json +194 -0
- deepseek-coder-1b_std/train.log +85 -0
- deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/README.md +202 -0
- deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/adapter_config.json +33 -0
- deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/adapter_model.safetensors +3 -0
- deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/special_tokens_map.json +23 -0
- deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/tokenizer.json +0 -0
- deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/tokenizer_config.json +194 -0
- deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/train.log +85 -0
- llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/README.md +202 -0
- llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/adapter_config.json +33 -0
- llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/adapter_model.safetensors +3 -0
- llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/special_tokens_map.json +23 -0
- llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/tokenizer.json +0 -0
- llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/tokenizer.model +3 -0
- llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/tokenizer_config.json +44 -0
- llama2-7b-chat-lora-llama2-7b-chat_std/train.log +84 -0
- mistral-7b-lora-mistral-7b_std/checkpoint-last/README.md +202 -0
- mistral-7b-lora-mistral-7b_std/checkpoint-last/adapter_config.json +33 -0
- mistral-7b-lora-mistral-7b_std/checkpoint-last/adapter_model.safetensors +3 -0
- mistral-7b-lora-mistral-7b_std/checkpoint-last/special_tokens_map.json +23 -0
- mistral-7b-lora-mistral-7b_std/checkpoint-last/tokenizer.json +0 -0
- mistral-7b-lora-mistral-7b_std/checkpoint-last/tokenizer.model +3 -0
- mistral-7b-lora-mistral-7b_std/checkpoint-last/tokenizer_config.json +44 -0
- mistral-7b-lora-mistral-7b_std/train.log +85 -0
- phi-2_std/checkpoint-last/added_tokens.json +40 -0
- phi-2_std/checkpoint-last/config.json +29 -0
- phi-2_std/checkpoint-last/generation_config.json +6 -0
- phi-2_std/checkpoint-last/merges.txt +0 -0
- phi-2_std/checkpoint-last/model-00001-of-00002.safetensors +3 -0
- phi-2_std/checkpoint-last/model-00002-of-00002.safetensors +3 -0
- phi-2_std/checkpoint-last/model.safetensors.index.json +460 -0
- phi-2_std/checkpoint-last/special_tokens_map.json +23 -0
- phi-2_std/checkpoint-last/tokenizer.json +0 -0
- phi-2_std/checkpoint-last/tokenizer_config.json +325 -0
- phi-2_std/checkpoint-last/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
qwen2.5-coder-3b_std/checkpoint-last/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
qwen2.5-coder-7b-lora-qwen2.5-coder-7b_std/checkpoint-last/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
qwen3-8b-lora-qwen3-8b_std/checkpoint-last/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
codellama-7b-lora-codellama-7b_std/checkpoint-last/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: codellama/CodeLlama-7b-hf
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.8.2
|
codellama-7b-lora-codellama-7b_std/checkpoint-last/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "codellama/CodeLlama-7b-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 32,
|
| 13 |
+
"lora_dropout": 0.1,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"gate_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"q_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"lm_head",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
codellama-7b-lora-codellama-7b_std/checkpoint-last/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8931dc8e217ae3a1810501287d51984fb5c21f06e2d6e424e0efe2ed431d0e02
|
| 3 |
+
size 343446032
|
codellama-7b-lora-codellama-7b_std/checkpoint-last/special_tokens_map.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"▁<PRE>",
|
| 4 |
+
"▁<MID>",
|
| 5 |
+
"▁<SUF>",
|
| 6 |
+
"▁<EOT>"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"unk_token": {
|
| 23 |
+
"content": "<unk>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
}
|
| 29 |
+
}
|
codellama-7b-lora-codellama-7b_std/checkpoint-last/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
codellama-7b-lora-codellama-7b_std/checkpoint-last/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
|
| 3 |
+
size 500058
|
codellama-7b-lora-codellama-7b_std/checkpoint-last/tokenizer_config.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32007": {
|
| 30 |
+
"content": "▁<PRE>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32008": {
|
| 38 |
+
"content": "▁<SUF>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"32009": {
|
| 46 |
+
"content": "▁<MID>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"32010": {
|
| 54 |
+
"content": "▁<EOT>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
}
|
| 61 |
+
},
|
| 62 |
+
"additional_special_tokens": [
|
| 63 |
+
"▁<PRE>",
|
| 64 |
+
"▁<MID>",
|
| 65 |
+
"▁<SUF>",
|
| 66 |
+
"▁<EOT>"
|
| 67 |
+
],
|
| 68 |
+
"bos_token": "<s>",
|
| 69 |
+
"clean_up_tokenization_spaces": false,
|
| 70 |
+
"eos_token": "</s>",
|
| 71 |
+
"eot_token": "▁<EOT>",
|
| 72 |
+
"extra_special_tokens": {},
|
| 73 |
+
"fill_token": "<FILL_ME>",
|
| 74 |
+
"legacy": null,
|
| 75 |
+
"middle_token": "▁<MID>",
|
| 76 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 77 |
+
"pad_token": null,
|
| 78 |
+
"prefix_token": "▁<PRE>",
|
| 79 |
+
"sp_model_kwargs": {},
|
| 80 |
+
"suffix_token": "▁<SUF>",
|
| 81 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
| 82 |
+
"unk_token": "<unk>",
|
| 83 |
+
"use_default_system_prompt": false
|
| 84 |
+
}
|
codellama-7b-lora-codellama-7b_std/train.log
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
05/15/2026 17:53:01 - INFO - accelerate.utils.modeling - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk).
|
| 2 |
+
05/15/2026 17:53:34 - INFO - root - Training args Namespace(output_name='codellama-7b-lora-codellama-7b_std', datasets=['evol'], pretrain_name='codellama-7b', loss_weight=1.0, sven=False, num_train_epochs=2, learning_rate=2e-05, max_num_tokens=1024, batch_size=1, grad_acc_steps=16, weight_decay=0.01, adam_epsilon=1e-08, warmup_steps=0, max_grad_norm=1.0, dropout=0.1, kl_loss_weight=0, exclude_neg=False, no_weights=False, lora=True, r=16, lora_alpha=32, lora_dropout=0.1, sampling_size=20, sampling_method='minority', cwes=['all'], langs=['all'], logging_steps=50, save_epochs=10, seed=2, data_dir='/mnt/scratch/QRM/experiments/SCoDE/data_train_val', model_dir='/mnt/scratch/QRM/experiments/SCoDE/trained', output_dir='/mnt/scratch/QRM/experiments/SCoDE/trained/codellama-7b-lora-codellama-7b_std', logger=<RootLogger root (INFO)>)
|
| 3 |
+
05/15/2026 17:53:34 - INFO - root - ***** Running training *****
|
| 4 |
+
05/15/2026 17:53:34 - INFO - root - Num samples = 28298
|
| 5 |
+
05/15/2026 17:53:34 - INFO - root - Num epoch = 2
|
| 6 |
+
05/15/2026 17:53:34 - INFO - root - Batch size= 1
|
| 7 |
+
05/15/2026 17:53:34 - INFO - root - Total batch size (w. accumulation) = 16
|
| 8 |
+
05/15/2026 17:53:34 - INFO - root - Gradient Accumulation steps = 16
|
| 9 |
+
05/15/2026 17:53:34 - INFO - root - Total optimization steps = 3536
|
| 10 |
+
05/15/2026 17:53:34 - INFO - root - Num val samples = 3143
|
| 11 |
+
05/15/2026 17:53:34 - INFO - root - Num parameters = 6779101440
|
| 12 |
+
05/15/2026 17:53:34 - INFO - root - Num trainable parameters = 40554752
|
| 13 |
+
05/15/2026 17:56:20 - INFO - root - epochs: 1/2, steps: 50/3536, func: 0.053553, 1%: 3h 12m 37s
|
| 14 |
+
05/15/2026 17:59:04 - INFO - root - epochs: 1/2, steps: 100/3536, func: 0.0489, 2%: 3h 9m 4s
|
| 15 |
+
05/15/2026 18:01:47 - INFO - root - epochs: 1/2, steps: 150/3536, func: 0.049055, 4%: 3h 5m 26s
|
| 16 |
+
05/15/2026 18:04:30 - INFO - root - epochs: 1/2, steps: 200/3536, func: 0.047903, 5%: 3h 2m 19s
|
| 17 |
+
05/15/2026 18:07:14 - INFO - root - epochs: 1/2, steps: 250/3536, func: 0.0482, 7%: 2h 59m 39s
|
| 18 |
+
05/15/2026 18:09:56 - INFO - root - epochs: 1/2, steps: 300/3536, func: 0.04778, 8%: 2h 56m 38s
|
| 19 |
+
05/15/2026 18:12:40 - INFO - root - epochs: 1/2, steps: 350/3536, func: 0.047599, 9%: 2h 53m 53s
|
| 20 |
+
05/15/2026 18:15:23 - INFO - root - epochs: 1/2, steps: 400/3536, func: 0.047311, 11%: 2h 51m 4s
|
| 21 |
+
05/15/2026 18:18:07 - INFO - root - epochs: 1/2, steps: 450/3536, func: 0.047141, 12%: 2h 48m 20s
|
| 22 |
+
05/15/2026 18:20:50 - INFO - root - epochs: 1/2, steps: 500/3536, func: 0.046227, 14%: 2h 45m 36s
|
| 23 |
+
05/15/2026 18:23:32 - INFO - root - epochs: 1/2, steps: 550/3536, func: 0.047724, 15%: 2h 42m 41s
|
| 24 |
+
05/15/2026 18:26:14 - INFO - root - epochs: 1/2, steps: 600/3536, func: 0.046239, 16%: 2h 39m 52s
|
| 25 |
+
05/15/2026 18:28:56 - INFO - root - epochs: 1/2, steps: 650/3536, func: 0.046872, 18%: 2h 37m 4s
|
| 26 |
+
05/15/2026 18:31:38 - INFO - root - epochs: 1/2, steps: 700/3536, func: 0.046514, 19%: 2h 34m 16s
|
| 27 |
+
05/15/2026 18:34:21 - INFO - root - epochs: 1/2, steps: 750/3536, func: 0.046605, 21%: 2h 31m 34s
|
| 28 |
+
05/15/2026 18:37:04 - INFO - root - epochs: 1/2, steps: 800/3536, func: 0.046667, 22%: 2h 28m 48s
|
| 29 |
+
05/15/2026 18:39:46 - INFO - root - epochs: 1/2, steps: 850/3536, func: 0.046913, 24%: 2h 26m 1s
|
| 30 |
+
05/15/2026 18:42:28 - INFO - root - epochs: 1/2, steps: 900/3536, func: 0.046443, 25%: 2h 23m 16s
|
| 31 |
+
05/15/2026 18:45:10 - INFO - root - epochs: 1/2, steps: 950/3536, func: 0.046632, 26%: 2h 20m 29s
|
| 32 |
+
05/15/2026 18:47:52 - INFO - root - epochs: 1/2, steps: 1000/3536, func: 0.046355, 28%: 2h 17m 45s
|
| 33 |
+
05/15/2026 18:50:35 - INFO - root - epochs: 1/2, steps: 1050/3536, func: 0.04673, 29%: 2h 15m 2s
|
| 34 |
+
05/15/2026 18:53:17 - INFO - root - epochs: 1/2, steps: 1100/3536, func: 0.045299, 31%: 2h 12m 16s
|
| 35 |
+
05/15/2026 18:56:00 - INFO - root - epochs: 1/2, steps: 1150/3536, func: 0.046432, 32%: 2h 9m 34s
|
| 36 |
+
05/15/2026 18:58:42 - INFO - root - epochs: 1/2, steps: 1200/3536, func: 0.045988, 33%: 2h 6m 50s
|
| 37 |
+
05/15/2026 19:01:24 - INFO - root - epochs: 1/2, steps: 1250/3536, func: 0.047306, 35%: 2h 4m 5s
|
| 38 |
+
05/15/2026 19:04:07 - INFO - root - epochs: 1/2, steps: 1300/3536, func: 0.047335, 36%: 2h 1m 23s
|
| 39 |
+
05/15/2026 19:06:49 - INFO - root - epochs: 1/2, steps: 1350/3536, func: 0.046585, 38%: 1h 58m 40s
|
| 40 |
+
05/15/2026 19:09:32 - INFO - root - epochs: 1/2, steps: 1400/3536, func: 0.045611, 39%: 1h 55m 56s
|
| 41 |
+
05/15/2026 19:12:11 - INFO - root - epochs: 1/2, steps: 1450/3536, func: 0.046602, 40%: 1h 53m 9s
|
| 42 |
+
05/15/2026 19:14:42 - INFO - root - epochs: 1/2, steps: 1500/3536, func: 0.045796, 42%: 1h 50m 10s
|
| 43 |
+
05/15/2026 19:17:14 - INFO - root - epochs: 1/2, steps: 1550/3536, func: 0.045634, 43%: 1h 47m 15s
|
| 44 |
+
05/15/2026 19:19:46 - INFO - root - epochs: 1/2, steps: 1600/3536, func: 0.046124, 45%: 1h 44m 20s
|
| 45 |
+
05/15/2026 19:22:16 - INFO - root - epochs: 1/2, steps: 1650/3536, func: 0.045239, 46%: 1h 41m 26s
|
| 46 |
+
05/15/2026 19:24:47 - INFO - root - epochs: 1/2, steps: 1700/3536, func: 0.046727, 48%: 1h 38m 33s
|
| 47 |
+
05/15/2026 19:27:17 - INFO - root - epochs: 1/2, steps: 1750/3536, func: 0.046448, 49%: 1h 35m 41s
|
| 48 |
+
05/15/2026 19:29:51 - INFO - root - epochs: 2/2, steps: 1800/3536, func: 0.045678, 50%: 1h 32m 54s
|
| 49 |
+
05/15/2026 19:32:22 - INFO - root - epochs: 2/2, steps: 1850/3536, func: 0.045587, 52%: 1h 30m 5s
|
| 50 |
+
05/15/2026 19:34:53 - INFO - root - epochs: 2/2, steps: 1900/3536, func: 0.04649, 53%: 1h 27m 17s
|
| 51 |
+
05/15/2026 19:37:24 - INFO - root - epochs: 2/2, steps: 1950/3536, func: 0.046279, 55%: 1h 24m 30s
|
| 52 |
+
05/15/2026 19:39:55 - INFO - root - epochs: 2/2, steps: 2000/3536, func: 0.045697, 56%: 1h 21m 43s
|
| 53 |
+
05/15/2026 19:42:27 - INFO - root - epochs: 2/2, steps: 2050/3536, func: 0.045146, 57%: 1h 18m 58s
|
| 54 |
+
05/15/2026 19:44:58 - INFO - root - epochs: 2/2, steps: 2100/3536, func: 0.046819, 59%: 1h 16m 13s
|
| 55 |
+
05/15/2026 19:47:28 - INFO - root - epochs: 2/2, steps: 2150/3536, func: 0.04625, 60%: 1h 13m 28s
|
| 56 |
+
05/15/2026 19:49:59 - INFO - root - epochs: 2/2, steps: 2200/3536, func: 0.046144, 62%: 1h 10m 45s
|
| 57 |
+
05/15/2026 19:52:31 - INFO - root - epochs: 2/2, steps: 2250/3536, func: 0.046049, 63%: 1h 8m 2s
|
| 58 |
+
05/15/2026 19:55:01 - INFO - root - epochs: 2/2, steps: 2300/3536, func: 0.046191, 65%: 1h 5m 19s
|
| 59 |
+
05/15/2026 19:57:32 - INFO - root - epochs: 2/2, steps: 2350/3536, func: 0.04618, 66%: 1h 2m 37s
|
| 60 |
+
05/15/2026 20:00:04 - INFO - root - epochs: 2/2, steps: 2400/3536, func: 0.045209, 67%: 0h 59m 55s
|
| 61 |
+
05/15/2026 20:02:36 - INFO - root - epochs: 2/2, steps: 2450/3536, func: 0.045665, 69%: 0h 57m 14s
|
| 62 |
+
05/15/2026 20:05:08 - INFO - root - epochs: 2/2, steps: 2500/3536, func: 0.046733, 70%: 0h 54m 34s
|
| 63 |
+
05/15/2026 20:07:39 - INFO - root - epochs: 2/2, steps: 2550/3536, func: 0.044726, 72%: 0h 51m 53s
|
| 64 |
+
05/15/2026 20:10:11 - INFO - root - epochs: 2/2, steps: 2600/3536, func: 0.04645, 73%: 0h 49m 13s
|
| 65 |
+
05/15/2026 20:12:42 - INFO - root - epochs: 2/2, steps: 2650/3536, func: 0.045592, 74%: 0h 46m 34s
|
| 66 |
+
05/15/2026 20:15:13 - INFO - root - epochs: 2/2, steps: 2700/3536, func: 0.044934, 76%: 0h 43m 54s
|
| 67 |
+
05/15/2026 20:17:44 - INFO - root - epochs: 2/2, steps: 2750/3536, func: 0.046683, 77%: 0h 41m 15s
|
| 68 |
+
05/15/2026 20:20:16 - INFO - root - epochs: 2/2, steps: 2800/3536, func: 0.045118, 79%: 0h 38m 36s
|
| 69 |
+
05/15/2026 20:22:46 - INFO - root - epochs: 2/2, steps: 2850/3536, func: 0.045185, 80%: 0h 35m 57s
|
| 70 |
+
05/15/2026 20:25:19 - INFO - root - epochs: 2/2, steps: 2900/3536, func: 0.04674, 81%: 0h 33m 19s
|
| 71 |
+
05/15/2026 20:27:49 - INFO - root - epochs: 2/2, steps: 2950/3536, func: 0.046423, 83%: 0h 30m 41s
|
| 72 |
+
05/15/2026 20:30:20 - INFO - root - epochs: 2/2, steps: 3000/3536, func: 0.047098, 84%: 0h 28m 3s
|
| 73 |
+
05/15/2026 20:32:52 - INFO - root - epochs: 2/2, steps: 3050/3536, func: 0.045522, 86%: 0h 25m 26s
|
| 74 |
+
05/15/2026 20:35:24 - INFO - root - epochs: 2/2, steps: 3100/3536, func: 0.045772, 87%: 0h 22m 48s
|
| 75 |
+
05/15/2026 20:37:55 - INFO - root - epochs: 2/2, steps: 3150/3536, func: 0.045837, 89%: 0h 20m 11s
|
| 76 |
+
05/15/2026 20:40:26 - INFO - root - epochs: 2/2, steps: 3200/3536, func: 0.045333, 90%: 0h 17m 34s
|
| 77 |
+
05/15/2026 20:42:56 - INFO - root - epochs: 2/2, steps: 3250/3536, func: 0.04512, 91%: 0h 14m 57s
|
| 78 |
+
05/15/2026 20:45:28 - INFO - root - epochs: 2/2, steps: 3300/3536, func: 0.045386, 93%: 0h 12m 20s
|
| 79 |
+
05/15/2026 20:47:59 - INFO - root - epochs: 2/2, steps: 3350/3536, func: 0.046192, 94%: 0h 9m 44s
|
| 80 |
+
05/15/2026 20:50:31 - INFO - root - epochs: 2/2, steps: 3400/3536, func: 0.045377, 96%: 0h 7m 7s
|
| 81 |
+
05/15/2026 20:53:01 - INFO - root - epochs: 2/2, steps: 3450/3536, func: 0.044902, 97%: 0h 4m 31s
|
| 82 |
+
05/15/2026 20:55:31 - INFO - root - epochs: 2/2, steps: 3500/3536, func: 0.045177, 98%: 0h 1m 55s
|
| 83 |
+
05/15/2026 21:00:50 - INFO - root - final eval loss: func: 0.046106
|
| 84 |
+
05/15/2026 21:00:50 - INFO - root - Saving model checkpoint to /mnt/scratch/QRM/experiments/SCoDE/trained/codellama-7b-lora-codellama-7b_std/checkpoint-last
|
deepseek-coder-1b_std/checkpoint-last/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 32013,
|
| 8 |
+
"eos_token_id": 32014,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5504,
|
| 14 |
+
"max_position_embeddings": 16384,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"num_key_value_heads": 16,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-06,
|
| 22 |
+
"rope_scaling": {
|
| 23 |
+
"factor": 4.0,
|
| 24 |
+
"rope_type": "linear",
|
| 25 |
+
"type": "linear"
|
| 26 |
+
},
|
| 27 |
+
"rope_theta": 100000,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "bfloat16",
|
| 30 |
+
"transformers_version": "4.51.3",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32022
|
| 33 |
+
}
|
deepseek-coder-1b_std/checkpoint-last/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 32013,
|
| 4 |
+
"eos_token_id": 32014,
|
| 5 |
+
"transformers_version": "4.51.3"
|
| 6 |
+
}
|
deepseek-coder-1b_std/checkpoint-last/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e738ce3bae338ce08869e8fbff1977cc0d6f3b8260f512bb37e3e7dee8991c23
|
| 3 |
+
size 2691052200
|
deepseek-coder-1b_std/checkpoint-last/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
deepseek-coder-1b_std/checkpoint-last/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
deepseek-coder-1b_std/checkpoint-last/tokenizer_config.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"clean_up_tokenization_spaces": false,
|
| 185 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 186 |
+
"extra_special_tokens": {},
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"sp_model_kwargs": {},
|
| 191 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 192 |
+
"unk_token": null,
|
| 193 |
+
"use_default_system_prompt": false
|
| 194 |
+
}
|
deepseek-coder-1b_std/train.log
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
05/15/2026 17:53:01 - INFO - accelerate.utils.modeling - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk).
|
| 2 |
+
05/15/2026 17:54:04 - INFO - root - Training args Namespace(output_name='deepseek-coder-1b_std', datasets=['evol'], pretrain_name='deepseek-coder-1b', loss_weight=1.0, sven=False, num_train_epochs=2, learning_rate=2e-05, max_num_tokens=1024, batch_size=1, grad_acc_steps=16, weight_decay=0.01, adam_epsilon=1e-08, warmup_steps=0, max_grad_norm=1.0, dropout=0.1, kl_loss_weight=0, exclude_neg=False, no_weights=False, lora=False, r=16, lora_alpha=32, lora_dropout=0.1, sampling_size=20, sampling_method='minority', cwes=['all'], langs=['all'], logging_steps=50, save_epochs=10, seed=2, data_dir='/mnt/scratch/QRM/experiments/SCoDE/data_train_val', model_dir='/mnt/scratch/QRM/experiments/SCoDE/trained', output_dir='/mnt/scratch/QRM/experiments/SCoDE/trained/deepseek-coder-1b_std', logger=<RootLogger root (INFO)>)
|
| 3 |
+
05/15/2026 17:54:04 - INFO - root - ***** Running training *****
|
| 4 |
+
05/15/2026 17:54:04 - INFO - root - Num samples = 28564
|
| 5 |
+
05/15/2026 17:54:04 - INFO - root - Num epoch = 2
|
| 6 |
+
05/15/2026 17:54:04 - INFO - root - Batch size= 1
|
| 7 |
+
05/15/2026 17:54:04 - INFO - root - Total batch size (w. accumulation) = 16
|
| 8 |
+
05/15/2026 17:54:04 - INFO - root - Gradient Accumulation steps = 16
|
| 9 |
+
05/15/2026 17:54:04 - INFO - root - Total optimization steps = 3570
|
| 10 |
+
05/15/2026 17:54:04 - INFO - root - Num val samples = 3173
|
| 11 |
+
05/15/2026 17:54:04 - INFO - root - Num parameters = 1345513472
|
| 12 |
+
05/15/2026 17:54:04 - INFO - root - Num trainable parameters = 1345513472
|
| 13 |
+
05/15/2026 17:55:09 - INFO - root - epochs: 1/2, steps: 50/3570, func: 0.054721, 1%: 1h 16m 25s
|
| 14 |
+
05/15/2026 17:56:12 - INFO - root - epochs: 1/2, steps: 100/3570, func: 0.053819, 2%: 1h 14m 16s
|
| 15 |
+
05/15/2026 17:57:16 - INFO - root - epochs: 1/2, steps: 150/3570, func: 0.053071, 4%: 1h 12m 56s
|
| 16 |
+
05/15/2026 17:58:20 - INFO - root - epochs: 1/2, steps: 200/3570, func: 0.053075, 5%: 1h 11m 49s
|
| 17 |
+
05/15/2026 17:59:24 - INFO - root - epochs: 1/2, steps: 250/3570, func: 0.053061, 6%: 1h 10m 51s
|
| 18 |
+
05/15/2026 18:00:27 - INFO - root - epochs: 1/2, steps: 300/3570, func: 0.051511, 8%: 1h 9m 42s
|
| 19 |
+
05/15/2026 18:01:31 - INFO - root - epochs: 1/2, steps: 350/3570, func: 0.053023, 9%: 1h 8m 35s
|
| 20 |
+
05/15/2026 18:02:35 - INFO - root - epochs: 1/2, steps: 400/3570, func: 0.051844, 11%: 1h 7m 30s
|
| 21 |
+
05/15/2026 18:03:39 - INFO - root - epochs: 1/2, steps: 450/3570, func: 0.051769, 12%: 1h 6m 26s
|
| 22 |
+
05/15/2026 18:04:43 - INFO - root - epochs: 1/2, steps: 500/3570, func: 0.052392, 13%: 1h 5m 22s
|
| 23 |
+
05/15/2026 18:05:46 - INFO - root - epochs: 1/2, steps: 550/3570, func: 0.051493, 15%: 1h 4m 19s
|
| 24 |
+
05/15/2026 18:06:50 - INFO - root - epochs: 1/2, steps: 600/3570, func: 0.052346, 16%: 1h 3m 14s
|
| 25 |
+
05/15/2026 18:07:54 - INFO - root - epochs: 1/2, steps: 650/3570, func: 0.050731, 18%: 1h 2m 9s
|
| 26 |
+
05/15/2026 18:08:58 - INFO - root - epochs: 1/2, steps: 700/3570, func: 0.051375, 19%: 1h 1m 5s
|
| 27 |
+
05/15/2026 18:10:01 - INFO - root - epochs: 1/2, steps: 750/3570, func: 0.049853, 20%: 1h 0m 1s
|
| 28 |
+
05/15/2026 18:11:06 - INFO - root - epochs: 1/2, steps: 800/3570, func: 0.050873, 22%: 0h 58m 59s
|
| 29 |
+
05/15/2026 18:12:10 - INFO - root - epochs: 1/2, steps: 850/3570, func: 0.052238, 23%: 0h 57m 55s
|
| 30 |
+
05/15/2026 18:13:13 - INFO - root - epochs: 1/2, steps: 900/3570, func: 0.050813, 25%: 0h 56m 51s
|
| 31 |
+
05/15/2026 18:14:17 - INFO - root - epochs: 1/2, steps: 950/3570, func: 0.050359, 26%: 0h 55m 47s
|
| 32 |
+
05/15/2026 18:15:21 - INFO - root - epochs: 1/2, steps: 1000/3570, func: 0.050728, 27%: 0h 54m 43s
|
| 33 |
+
05/15/2026 18:16:25 - INFO - root - epochs: 1/2, steps: 1050/3570, func: 0.050755, 29%: 0h 53m 38s
|
| 34 |
+
05/15/2026 18:17:28 - INFO - root - epochs: 1/2, steps: 1100/3570, func: 0.050294, 30%: 0h 52m 33s
|
| 35 |
+
05/15/2026 18:18:32 - INFO - root - epochs: 1/2, steps: 1150/3570, func: 0.050878, 32%: 0h 51m 30s
|
| 36 |
+
05/15/2026 18:19:35 - INFO - root - epochs: 1/2, steps: 1200/3570, func: 0.050872, 33%: 0h 50m 26s
|
| 37 |
+
05/15/2026 18:20:39 - INFO - root - epochs: 1/2, steps: 1250/3570, func: 0.051367, 34%: 0h 49m 21s
|
| 38 |
+
05/15/2026 18:21:43 - INFO - root - epochs: 1/2, steps: 1300/3570, func: 0.05063, 36%: 0h 48m 17s
|
| 39 |
+
05/15/2026 18:22:46 - INFO - root - epochs: 1/2, steps: 1350/3570, func: 0.05148, 37%: 0h 47m 13s
|
| 40 |
+
05/15/2026 18:23:50 - INFO - root - epochs: 1/2, steps: 1400/3570, func: 0.050229, 39%: 0h 46m 9s
|
| 41 |
+
05/15/2026 18:24:53 - INFO - root - epochs: 1/2, steps: 1450/3570, func: 0.050373, 40%: 0h 45m 5s
|
| 42 |
+
05/15/2026 18:25:57 - INFO - root - epochs: 1/2, steps: 1500/3570, func: 0.050628, 41%: 0h 44m 0s
|
| 43 |
+
05/15/2026 18:27:00 - INFO - root - epochs: 1/2, steps: 1550/3570, func: 0.050485, 43%: 0h 42m 57s
|
| 44 |
+
05/15/2026 18:28:04 - INFO - root - epochs: 1/2, steps: 1600/3570, func: 0.051414, 44%: 0h 41m 52s
|
| 45 |
+
05/15/2026 18:29:07 - INFO - root - epochs: 1/2, steps: 1650/3570, func: 0.049564, 46%: 0h 40m 48s
|
| 46 |
+
05/15/2026 18:30:11 - INFO - root - epochs: 1/2, steps: 1700/3570, func: 0.050796, 47%: 0h 39m 44s
|
| 47 |
+
05/15/2026 18:31:14 - INFO - root - epochs: 1/2, steps: 1750/3570, func: 0.05154, 48%: 0h 38m 40s
|
| 48 |
+
05/15/2026 18:32:18 - INFO - root - epochs: 2/2, steps: 1800/3570, func: 0.051208, 50%: 0h 37m 37s
|
| 49 |
+
05/15/2026 18:33:21 - INFO - root - epochs: 2/2, steps: 1850/3570, func: 0.049527, 51%: 0h 36m 33s
|
| 50 |
+
05/15/2026 18:34:25 - INFO - root - epochs: 2/2, steps: 1900/3570, func: 0.049709, 53%: 0h 35m 29s
|
| 51 |
+
05/15/2026 18:35:28 - INFO - root - epochs: 2/2, steps: 1950/3570, func: 0.049024, 54%: 0h 34m 25s
|
| 52 |
+
05/15/2026 18:36:32 - INFO - root - epochs: 2/2, steps: 2000/3570, func: 0.050508, 55%: 0h 33m 21s
|
| 53 |
+
05/15/2026 18:37:35 - INFO - root - epochs: 2/2, steps: 2050/3570, func: 0.049172, 57%: 0h 32m 17s
|
| 54 |
+
05/15/2026 18:38:39 - INFO - root - epochs: 2/2, steps: 2100/3570, func: 0.049585, 58%: 0h 31m 13s
|
| 55 |
+
05/15/2026 18:39:43 - INFO - root - epochs: 2/2, steps: 2150/3570, func: 0.050109, 60%: 0h 30m 10s
|
| 56 |
+
05/15/2026 18:40:46 - INFO - root - epochs: 2/2, steps: 2200/3570, func: 0.050542, 61%: 0h 29m 6s
|
| 57 |
+
05/15/2026 18:41:50 - INFO - root - epochs: 2/2, steps: 2250/3570, func: 0.048915, 62%: 0h 28m 2s
|
| 58 |
+
05/15/2026 18:42:54 - INFO - root - epochs: 2/2, steps: 2300/3570, func: 0.048932, 64%: 0h 26m 58s
|
| 59 |
+
05/15/2026 18:43:57 - INFO - root - epochs: 2/2, steps: 2350/3570, func: 0.050188, 65%: 0h 25m 55s
|
| 60 |
+
05/15/2026 18:45:01 - INFO - root - epochs: 2/2, steps: 2400/3570, func: 0.049453, 67%: 0h 24m 51s
|
| 61 |
+
05/15/2026 18:46:05 - INFO - root - epochs: 2/2, steps: 2450/3570, func: 0.050009, 68%: 0h 23m 48s
|
| 62 |
+
05/15/2026 18:47:09 - INFO - root - epochs: 2/2, steps: 2500/3570, func: 0.049283, 70%: 0h 22m 44s
|
| 63 |
+
05/15/2026 18:48:14 - INFO - root - epochs: 2/2, steps: 2550/3570, func: 0.049506, 71%: 0h 21m 41s
|
| 64 |
+
05/15/2026 18:49:18 - INFO - root - epochs: 2/2, steps: 2600/3570, func: 0.048537, 72%: 0h 20m 37s
|
| 65 |
+
05/15/2026 18:50:21 - INFO - root - epochs: 2/2, steps: 2650/3570, func: 0.050053, 74%: 0h 19m 33s
|
| 66 |
+
05/15/2026 18:51:25 - INFO - root - epochs: 2/2, steps: 2700/3570, func: 0.050696, 75%: 0h 18m 30s
|
| 67 |
+
05/15/2026 18:52:28 - INFO - root - epochs: 2/2, steps: 2750/3570, func: 0.049054, 77%: 0h 17m 26s
|
| 68 |
+
05/15/2026 18:53:32 - INFO - root - epochs: 2/2, steps: 2800/3570, func: 0.048454, 78%: 0h 16m 22s
|
| 69 |
+
05/15/2026 18:54:36 - INFO - root - epochs: 2/2, steps: 2850/3570, func: 0.048336, 79%: 0h 15m 18s
|
| 70 |
+
05/15/2026 18:55:40 - INFO - root - epochs: 2/2, steps: 2900/3570, func: 0.048973, 81%: 0h 14m 15s
|
| 71 |
+
05/15/2026 18:56:43 - INFO - root - epochs: 2/2, steps: 2950/3570, func: 0.048978, 82%: 0h 13m 11s
|
| 72 |
+
05/15/2026 18:57:47 - INFO - root - epochs: 2/2, steps: 3000/3570, func: 0.049476, 84%: 0h 12m 7s
|
| 73 |
+
05/15/2026 18:58:51 - INFO - root - epochs: 2/2, steps: 3050/3570, func: 0.049558, 85%: 0h 11m 3s
|
| 74 |
+
05/15/2026 18:59:54 - INFO - root - epochs: 2/2, steps: 3100/3570, func: 0.048599, 86%: 0h 10m 0s
|
| 75 |
+
05/15/2026 19:00:58 - INFO - root - epochs: 2/2, steps: 3150/3570, func: 0.048974, 88%: 0h 8m 56s
|
| 76 |
+
05/15/2026 19:02:01 - INFO - root - epochs: 2/2, steps: 3200/3570, func: 0.04963, 89%: 0h 7m 52s
|
| 77 |
+
05/15/2026 19:03:05 - INFO - root - epochs: 2/2, steps: 3250/3570, func: 0.04918, 91%: 0h 6m 49s
|
| 78 |
+
05/15/2026 19:04:08 - INFO - root - epochs: 2/2, steps: 3300/3570, func: 0.049538, 92%: 0h 5m 45s
|
| 79 |
+
05/15/2026 19:05:12 - INFO - root - epochs: 2/2, steps: 3350/3570, func: 0.049933, 93%: 0h 4m 41s
|
| 80 |
+
05/15/2026 19:06:15 - INFO - root - epochs: 2/2, steps: 3400/3570, func: 0.049365, 95%: 0h 3m 37s
|
| 81 |
+
05/15/2026 19:07:19 - INFO - root - epochs: 2/2, steps: 3450/3570, func: 0.048782, 96%: 0h 2m 34s
|
| 82 |
+
05/15/2026 19:08:22 - INFO - root - epochs: 2/2, steps: 3500/3570, func: 0.050896, 98%: 0h 1m 30s
|
| 83 |
+
05/15/2026 19:09:26 - INFO - root - epochs: 2/2, steps: 3550/3570, func: 0.049513, 99%: 0h 0m 26s
|
| 84 |
+
05/15/2026 19:11:04 - INFO - root - final eval loss: func: 0.050652
|
| 85 |
+
05/15/2026 19:11:04 - INFO - root - Saving model checkpoint to /mnt/scratch/QRM/experiments/SCoDE/trained/deepseek-coder-1b_std/checkpoint-last
|
deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-base
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.8.2
|
deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 32,
|
| 13 |
+
"lora_dropout": 0.1,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"up_proj",
|
| 23 |
+
"v_proj",
|
| 24 |
+
"lm_head",
|
| 25 |
+
"q_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dde7f1dde489cf69e6b3faff78f0db192e5b7700ca7758269317c3eb3d926071
|
| 3 |
+
size 343495376
|
deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last/tokenizer_config.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"clean_up_tokenization_spaces": false,
|
| 185 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 186 |
+
"extra_special_tokens": {},
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"sp_model_kwargs": {},
|
| 191 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 192 |
+
"unk_token": null,
|
| 193 |
+
"use_default_system_prompt": false
|
| 194 |
+
}
|
deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/train.log
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
05/15/2026 17:53:01 - INFO - accelerate.utils.modeling - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk).
|
| 2 |
+
05/15/2026 17:54:08 - INFO - root - Training args Namespace(output_name='deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std', datasets=['evol'], pretrain_name='deepseek-coder-6.7b', loss_weight=1.0, sven=False, num_train_epochs=2, learning_rate=2e-05, max_num_tokens=1024, batch_size=1, grad_acc_steps=16, weight_decay=0.01, adam_epsilon=1e-08, warmup_steps=0, max_grad_norm=1.0, dropout=0.1, kl_loss_weight=0, exclude_neg=False, no_weights=False, lora=True, r=16, lora_alpha=32, lora_dropout=0.1, sampling_size=20, sampling_method='minority', cwes=['all'], langs=['all'], logging_steps=50, save_epochs=10, seed=2, data_dir='/mnt/scratch/QRM/experiments/SCoDE/data_train_val', model_dir='/mnt/scratch/QRM/experiments/SCoDE/trained', output_dir='/mnt/scratch/QRM/experiments/SCoDE/trained/deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std', logger=<RootLogger root (INFO)>)
|
| 3 |
+
05/15/2026 17:54:08 - INFO - root - ***** Running training *****
|
| 4 |
+
05/15/2026 17:54:08 - INFO - root - Num samples = 28564
|
| 5 |
+
05/15/2026 17:54:08 - INFO - root - Num epoch = 2
|
| 6 |
+
05/15/2026 17:54:08 - INFO - root - Batch size= 1
|
| 7 |
+
05/15/2026 17:54:08 - INFO - root - Total batch size (w. accumulation) = 16
|
| 8 |
+
05/15/2026 17:54:08 - INFO - root - Gradient Accumulation steps = 16
|
| 9 |
+
05/15/2026 17:54:08 - INFO - root - Total optimization steps = 3570
|
| 10 |
+
05/15/2026 17:54:08 - INFO - root - Num val samples = 3173
|
| 11 |
+
05/15/2026 17:54:08 - INFO - root - Num parameters = 6779150688
|
| 12 |
+
05/15/2026 17:54:08 - INFO - root - Num trainable parameters = 40554848
|
| 13 |
+
05/15/2026 17:56:48 - INFO - root - epochs: 1/2, steps: 50/3570, func: 0.050436, 1%: 3h 8m 23s
|
| 14 |
+
05/15/2026 17:59:16 - INFO - root - epochs: 1/2, steps: 100/3570, func: 0.048539, 2%: 2h 58m 38s
|
| 15 |
+
05/15/2026 18:01:43 - INFO - root - epochs: 1/2, steps: 150/3570, func: 0.047644, 4%: 2h 53m 9s
|
| 16 |
+
05/15/2026 18:04:11 - INFO - root - epochs: 1/2, steps: 200/3570, func: 0.047594, 5%: 2h 49m 26s
|
| 17 |
+
05/15/2026 18:06:39 - INFO - root - epochs: 1/2, steps: 250/3570, func: 0.047501, 6%: 2h 46m 22s
|
| 18 |
+
05/15/2026 18:09:06 - INFO - root - epochs: 1/2, steps: 300/3570, func: 0.046075, 8%: 2h 43m 16s
|
| 19 |
+
05/15/2026 18:11:34 - INFO - root - epochs: 1/2, steps: 350/3570, func: 0.047514, 9%: 2h 40m 31s
|
| 20 |
+
05/15/2026 18:14:01 - INFO - root - epochs: 1/2, steps: 400/3570, func: 0.046485, 11%: 2h 37m 39s
|
| 21 |
+
05/15/2026 18:16:28 - INFO - root - epochs: 1/2, steps: 450/3570, func: 0.046384, 12%: 2h 35m 0s
|
| 22 |
+
05/15/2026 18:18:56 - INFO - root - epochs: 1/2, steps: 500/3570, func: 0.047028, 13%: 2h 32m 20s
|
| 23 |
+
05/15/2026 18:21:23 - INFO - root - epochs: 1/2, steps: 550/3570, func: 0.046042, 15%: 2h 29m 44s
|
| 24 |
+
05/15/2026 18:23:50 - INFO - root - epochs: 1/2, steps: 600/3570, func: 0.046992, 16%: 2h 27m 4s
|
| 25 |
+
05/15/2026 18:26:17 - INFO - root - epochs: 1/2, steps: 650/3570, func: 0.045483, 18%: 2h 24m 29s
|
| 26 |
+
05/15/2026 18:28:44 - INFO - root - epochs: 1/2, steps: 700/3570, func: 0.046212, 19%: 2h 21m 55s
|
| 27 |
+
05/15/2026 18:31:11 - INFO - root - epochs: 1/2, steps: 750/3570, func: 0.044684, 20%: 2h 19m 23s
|
| 28 |
+
05/15/2026 18:33:38 - INFO - root - epochs: 1/2, steps: 800/3570, func: 0.045541, 22%: 2h 16m 50s
|
| 29 |
+
05/15/2026 18:36:06 - INFO - root - epochs: 1/2, steps: 850/3570, func: 0.046732, 23%: 2h 14m 22s
|
| 30 |
+
05/15/2026 18:38:33 - INFO - root - epochs: 1/2, steps: 900/3570, func: 0.045579, 25%: 2h 11m 49s
|
| 31 |
+
05/15/2026 18:41:00 - INFO - root - epochs: 1/2, steps: 950/3570, func: 0.045319, 26%: 2h 9m 19s
|
| 32 |
+
05/15/2026 18:43:27 - INFO - root - epochs: 1/2, steps: 1000/3570, func: 0.045586, 27%: 2h 6m 48s
|
| 33 |
+
05/15/2026 18:45:55 - INFO - root - epochs: 1/2, steps: 1050/3570, func: 0.045421, 29%: 2h 4m 19s
|
| 34 |
+
05/15/2026 18:48:20 - INFO - root - epochs: 1/2, steps: 1100/3570, func: 0.045093, 30%: 2h 1m 46s
|
| 35 |
+
05/15/2026 18:50:49 - INFO - root - epochs: 1/2, steps: 1150/3570, func: 0.045568, 32%: 1h 59m 19s
|
| 36 |
+
05/15/2026 18:53:15 - INFO - root - epochs: 1/2, steps: 1200/3570, func: 0.045754, 33%: 1h 56m 49s
|
| 37 |
+
05/15/2026 18:55:43 - INFO - root - epochs: 1/2, steps: 1250/3570, func: 0.04605, 34%: 1h 54m 22s
|
| 38 |
+
05/15/2026 18:58:11 - INFO - root - epochs: 1/2, steps: 1300/3570, func: 0.045232, 36%: 1h 51m 53s
|
| 39 |
+
05/15/2026 19:00:38 - INFO - root - epochs: 1/2, steps: 1350/3570, func: 0.046241, 37%: 1h 49m 24s
|
| 40 |
+
05/15/2026 19:03:04 - INFO - root - epochs: 1/2, steps: 1400/3570, func: 0.045171, 39%: 1h 46m 55s
|
| 41 |
+
05/15/2026 19:05:32 - INFO - root - epochs: 1/2, steps: 1450/3570, func: 0.045191, 40%: 1h 44m 26s
|
| 42 |
+
05/15/2026 19:07:58 - INFO - root - epochs: 1/2, steps: 1500/3570, func: 0.045337, 41%: 1h 41m 57s
|
| 43 |
+
05/15/2026 19:10:26 - INFO - root - epochs: 1/2, steps: 1550/3570, func: 0.045237, 43%: 1h 39m 29s
|
| 44 |
+
05/15/2026 19:12:55 - INFO - root - epochs: 1/2, steps: 1600/3570, func: 0.046228, 44%: 1h 37m 3s
|
| 45 |
+
05/15/2026 19:15:24 - INFO - root - epochs: 1/2, steps: 1650/3570, func: 0.044411, 46%: 1h 34m 37s
|
| 46 |
+
05/15/2026 19:17:52 - INFO - root - epochs: 1/2, steps: 1700/3570, func: 0.045536, 47%: 1h 32m 10s
|
| 47 |
+
05/15/2026 19:20:22 - INFO - root - epochs: 1/2, steps: 1750/3570, func: 0.046268, 48%: 1h 29m 43s
|
| 48 |
+
05/15/2026 19:22:51 - INFO - root - epochs: 2/2, steps: 1800/3570, func: 0.046214, 50%: 1h 27m 17s
|
| 49 |
+
05/15/2026 19:25:19 - INFO - root - epochs: 2/2, steps: 1850/3570, func: 0.045282, 51%: 1h 24m 49s
|
| 50 |
+
05/15/2026 19:27:47 - INFO - root - epochs: 2/2, steps: 1900/3570, func: 0.045458, 53%: 1h 22m 22s
|
| 51 |
+
05/15/2026 19:30:16 - INFO - root - epochs: 2/2, steps: 1950/3570, func: 0.044733, 54%: 1h 19m 54s
|
| 52 |
+
05/15/2026 19:32:43 - INFO - root - epochs: 2/2, steps: 2000/3570, func: 0.046205, 55%: 1h 17m 26s
|
| 53 |
+
05/15/2026 19:35:12 - INFO - root - epochs: 2/2, steps: 2050/3570, func: 0.045026, 57%: 1h 14m 59s
|
| 54 |
+
05/15/2026 19:37:40 - INFO - root - epochs: 2/2, steps: 2100/3570, func: 0.045443, 58%: 1h 12m 31s
|
| 55 |
+
05/15/2026 19:40:08 - INFO - root - epochs: 2/2, steps: 2150/3570, func: 0.04582, 60%: 1h 10m 3s
|
| 56 |
+
05/15/2026 19:42:36 - INFO - root - epochs: 2/2, steps: 2200/3570, func: 0.0463, 61%: 1h 7m 35s
|
| 57 |
+
05/15/2026 19:45:05 - INFO - root - epochs: 2/2, steps: 2250/3570, func: 0.044733, 62%: 1h 5m 8s
|
| 58 |
+
05/15/2026 19:47:33 - INFO - root - epochs: 2/2, steps: 2300/3570, func: 0.044792, 64%: 1h 2m 40s
|
| 59 |
+
05/15/2026 19:50:03 - INFO - root - epochs: 2/2, steps: 2350/3570, func: 0.045966, 65%: 1h 0m 13s
|
| 60 |
+
05/15/2026 19:52:31 - INFO - root - epochs: 2/2, steps: 2400/3570, func: 0.045263, 67%: 0h 57m 45s
|
| 61 |
+
05/15/2026 19:54:59 - INFO - root - epochs: 2/2, steps: 2450/3570, func: 0.045609, 68%: 0h 55m 17s
|
| 62 |
+
05/15/2026 19:57:25 - INFO - root - epochs: 2/2, steps: 2500/3570, func: 0.045199, 70%: 0h 52m 48s
|
| 63 |
+
05/15/2026 19:59:53 - INFO - root - epochs: 2/2, steps: 2550/3570, func: 0.045369, 71%: 0h 50m 20s
|
| 64 |
+
05/15/2026 20:02:21 - INFO - root - epochs: 2/2, steps: 2600/3570, func: 0.044456, 72%: 0h 47m 53s
|
| 65 |
+
05/15/2026 20:04:48 - INFO - root - epochs: 2/2, steps: 2650/3570, func: 0.045693, 74%: 0h 45m 25s
|
| 66 |
+
05/15/2026 20:07:16 - INFO - root - epochs: 2/2, steps: 2700/3570, func: 0.046093, 75%: 0h 42m 56s
|
| 67 |
+
05/15/2026 20:09:43 - INFO - root - epochs: 2/2, steps: 2750/3570, func: 0.044909, 77%: 0h 40m 28s
|
| 68 |
+
05/15/2026 20:12:10 - INFO - root - epochs: 2/2, steps: 2800/3570, func: 0.044151, 78%: 0h 38m 0s
|
| 69 |
+
05/15/2026 20:14:37 - INFO - root - epochs: 2/2, steps: 2850/3570, func: 0.044291, 79%: 0h 35m 32s
|
| 70 |
+
05/15/2026 20:17:05 - INFO - root - epochs: 2/2, steps: 2900/3570, func: 0.044967, 81%: 0h 33m 4s
|
| 71 |
+
05/15/2026 20:19:31 - INFO - root - epochs: 2/2, steps: 2950/3570, func: 0.044799, 82%: 0h 30m 36s
|
| 72 |
+
05/15/2026 20:21:59 - INFO - root - epochs: 2/2, steps: 3000/3570, func: 0.04522, 84%: 0h 28m 8s
|
| 73 |
+
05/15/2026 20:24:26 - INFO - root - epochs: 2/2, steps: 3050/3570, func: 0.045257, 85%: 0h 25m 40s
|
| 74 |
+
05/15/2026 20:26:51 - INFO - root - epochs: 2/2, steps: 3100/3570, func: 0.04447, 86%: 0h 23m 12s
|
| 75 |
+
05/15/2026 20:29:17 - INFO - root - epochs: 2/2, steps: 3150/3570, func: 0.044678, 88%: 0h 20m 44s
|
| 76 |
+
05/15/2026 20:31:42 - INFO - root - epochs: 2/2, steps: 3200/3570, func: 0.045512, 89%: 0h 18m 16s
|
| 77 |
+
05/15/2026 20:34:08 - INFO - root - epochs: 2/2, steps: 3250/3570, func: 0.04486, 91%: 0h 15m 48s
|
| 78 |
+
05/15/2026 20:36:32 - INFO - root - epochs: 2/2, steps: 3300/3570, func: 0.045303, 92%: 0h 13m 20s
|
| 79 |
+
05/15/2026 20:38:57 - INFO - root - epochs: 2/2, steps: 3350/3570, func: 0.045726, 93%: 0h 10m 52s
|
| 80 |
+
05/15/2026 20:41:22 - INFO - root - epochs: 2/2, steps: 3400/3570, func: 0.045211, 95%: 0h 8m 24s
|
| 81 |
+
05/15/2026 20:43:48 - INFO - root - epochs: 2/2, steps: 3450/3570, func: 0.044747, 96%: 0h 5m 57s
|
| 82 |
+
05/15/2026 20:46:12 - INFO - root - epochs: 2/2, steps: 3500/3570, func: 0.046464, 98%: 0h 3m 29s
|
| 83 |
+
05/15/2026 20:48:37 - INFO - root - epochs: 2/2, steps: 3550/3570, func: 0.045305, 99%: 0h 1m 1s
|
| 84 |
+
05/15/2026 20:53:03 - INFO - root - final eval loss: func: 0.045452
|
| 85 |
+
05/15/2026 20:53:03 - INFO - root - Saving model checkpoint to /mnt/scratch/QRM/experiments/SCoDE/trained/deepseek-coder-6.7b-lora-deepseek-coder-6.7b_std/checkpoint-last
|
llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-2-7b-chat-hf
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.8.2
|
llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 32,
|
| 13 |
+
"lora_dropout": 0.1,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"k_proj",
|
| 23 |
+
"up_proj",
|
| 24 |
+
"lm_head",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18a2f6eb3df716de0325d245fad28bcf0ded616c298ecde5e5112cc5cf839e96
|
| 3 |
+
size 343314448
|
llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last/tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"extra_special_tokens": {},
|
| 36 |
+
"legacy": false,
|
| 37 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
+
"pad_token": null,
|
| 39 |
+
"padding_side": "right",
|
| 40 |
+
"sp_model_kwargs": {},
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false
|
| 44 |
+
}
|
llama2-7b-chat-lora-llama2-7b-chat_std/train.log
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
05/15/2026 19:11:15 - INFO - accelerate.utils.modeling - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk).
|
| 2 |
+
05/15/2026 19:11:48 - INFO - root - Training args Namespace(output_name='llama2-7b-chat-lora-llama2-7b-chat_std', datasets=['evol'], pretrain_name='llama2-7b-chat', loss_weight=1.0, sven=False, num_train_epochs=2, learning_rate=2e-05, max_num_tokens=1024, batch_size=1, grad_acc_steps=16, weight_decay=0.01, adam_epsilon=1e-08, warmup_steps=0, max_grad_norm=1.0, dropout=0.1, kl_loss_weight=0, exclude_neg=False, no_weights=False, lora=True, r=16, lora_alpha=32, lora_dropout=0.1, sampling_size=20, sampling_method='minority', cwes=['all'], langs=['all'], logging_steps=50, save_epochs=10, seed=2, data_dir='/mnt/scratch/QRM/experiments/SCoDE/data_train_val', model_dir='/mnt/scratch/QRM/experiments/SCoDE/trained', output_dir='/mnt/scratch/QRM/experiments/SCoDE/trained/llama2-7b-chat-lora-llama2-7b-chat_std', logger=<RootLogger root (INFO)>)
|
| 3 |
+
05/15/2026 19:11:48 - INFO - root - ***** Running training *****
|
| 4 |
+
05/15/2026 19:11:48 - INFO - root - Num samples = 28298
|
| 5 |
+
05/15/2026 19:11:48 - INFO - root - Num epoch = 2
|
| 6 |
+
05/15/2026 19:11:48 - INFO - root - Batch size= 1
|
| 7 |
+
05/15/2026 19:11:48 - INFO - root - Total batch size (w. accumulation) = 16
|
| 8 |
+
05/15/2026 19:11:48 - INFO - root - Gradient Accumulation steps = 16
|
| 9 |
+
05/15/2026 19:11:48 - INFO - root - Total optimization steps = 3536
|
| 10 |
+
05/15/2026 19:11:48 - INFO - root - Num val samples = 3143
|
| 11 |
+
05/15/2026 19:11:48 - INFO - root - Num parameters = 6778970112
|
| 12 |
+
05/15/2026 19:11:48 - INFO - root - Num trainable parameters = 40554496
|
| 13 |
+
05/15/2026 19:14:27 - INFO - root - epochs: 1/2, steps: 50/3536, func: 0.064425, 1%: 3h 4m 29s
|
| 14 |
+
05/15/2026 19:17:05 - INFO - root - epochs: 1/2, steps: 100/3536, func: 0.056713, 2%: 3h 1m 9s
|
| 15 |
+
05/15/2026 19:19:42 - INFO - root - epochs: 1/2, steps: 150/3536, func: 0.056786, 4%: 2h 58m 6s
|
| 16 |
+
05/15/2026 19:22:19 - INFO - root - epochs: 1/2, steps: 200/3536, func: 0.055125, 5%: 2h 55m 25s
|
| 17 |
+
05/15/2026 19:24:58 - INFO - root - epochs: 1/2, steps: 250/3536, func: 0.055165, 7%: 2h 53m 1s
|
| 18 |
+
05/15/2026 19:27:35 - INFO - root - epochs: 1/2, steps: 300/3536, func: 0.054706, 8%: 2h 50m 13s
|
| 19 |
+
05/15/2026 19:30:13 - INFO - root - epochs: 1/2, steps: 350/3536, func: 0.054154, 9%: 2h 47m 39s
|
| 20 |
+
05/15/2026 19:32:50 - INFO - root - epochs: 1/2, steps: 400/3536, func: 0.053828, 11%: 2h 44m 54s
|
| 21 |
+
05/15/2026 19:35:28 - INFO - root - epochs: 1/2, steps: 450/3536, func: 0.053888, 12%: 2h 42m 15s
|
| 22 |
+
05/15/2026 19:38:05 - INFO - root - epochs: 1/2, steps: 500/3536, func: 0.052901, 14%: 2h 39m 34s
|
| 23 |
+
05/15/2026 19:40:41 - INFO - root - epochs: 1/2, steps: 550/3536, func: 0.054249, 15%: 2h 36m 50s
|
| 24 |
+
05/15/2026 19:43:18 - INFO - root - epochs: 1/2, steps: 600/3536, func: 0.052775, 16%: 2h 34m 11s
|
| 25 |
+
05/15/2026 19:45:56 - INFO - root - epochs: 1/2, steps: 650/3536, func: 0.053225, 18%: 2h 31m 33s
|
| 26 |
+
05/15/2026 19:48:33 - INFO - root - epochs: 1/2, steps: 700/3536, func: 0.052929, 19%: 2h 28m 53s
|
| 27 |
+
05/15/2026 19:51:11 - INFO - root - epochs: 1/2, steps: 750/3536, func: 0.052824, 21%: 2h 26m 19s
|
| 28 |
+
05/15/2026 19:53:47 - INFO - root - epochs: 1/2, steps: 800/3536, func: 0.052791, 22%: 2h 23m 36s
|
| 29 |
+
05/15/2026 19:56:22 - INFO - root - epochs: 1/2, steps: 850/3536, func: 0.053422, 24%: 2h 20m 50s
|
| 30 |
+
05/15/2026 19:58:57 - INFO - root - epochs: 1/2, steps: 900/3536, func: 0.052836, 25%: 2h 18m 8s
|
| 31 |
+
05/15/2026 20:01:32 - INFO - root - epochs: 1/2, steps: 950/3536, func: 0.052866, 26%: 2h 15m 24s
|
| 32 |
+
05/15/2026 20:04:07 - INFO - root - epochs: 1/2, steps: 1000/3536, func: 0.05261, 28%: 2h 12m 43s
|
| 33 |
+
05/15/2026 20:06:43 - INFO - root - epochs: 1/2, steps: 1050/3536, func: 0.053154, 29%: 2h 10m 3s
|
| 34 |
+
05/15/2026 20:09:18 - INFO - root - epochs: 1/2, steps: 1100/3536, func: 0.051337, 31%: 2h 7m 21s
|
| 35 |
+
05/15/2026 20:11:53 - INFO - root - epochs: 1/2, steps: 1150/3536, func: 0.052288, 32%: 2h 4m 42s
|
| 36 |
+
05/15/2026 20:14:28 - INFO - root - epochs: 1/2, steps: 1200/3536, func: 0.052022, 33%: 2h 2m 1s
|
| 37 |
+
05/15/2026 20:17:02 - INFO - root - epochs: 1/2, steps: 1250/3536, func: 0.053464, 35%: 1h 59m 21s
|
| 38 |
+
05/15/2026 20:19:39 - INFO - root - epochs: 1/2, steps: 1300/3536, func: 0.053476, 36%: 1h 56m 43s
|
| 39 |
+
05/15/2026 20:22:14 - INFO - root - epochs: 1/2, steps: 1350/3536, func: 0.052717, 38%: 1h 54m 5s
|
| 40 |
+
05/15/2026 20:24:49 - INFO - root - epochs: 1/2, steps: 1400/3536, func: 0.051697, 39%: 1h 51m 26s
|
| 41 |
+
05/15/2026 20:27:24 - INFO - root - epochs: 1/2, steps: 1450/3536, func: 0.052497, 40%: 1h 48m 47s
|
| 42 |
+
05/15/2026 20:29:57 - INFO - root - epochs: 1/2, steps: 1500/3536, func: 0.052098, 42%: 1h 46m 6s
|
| 43 |
+
05/15/2026 20:32:31 - INFO - root - epochs: 1/2, steps: 1550/3536, func: 0.052167, 43%: 1h 43m 28s
|
| 44 |
+
05/15/2026 20:35:05 - INFO - root - epochs: 1/2, steps: 1600/3536, func: 0.052335, 45%: 1h 40m 48s
|
| 45 |
+
05/15/2026 20:37:38 - INFO - root - epochs: 1/2, steps: 1650/3536, func: 0.051467, 46%: 1h 38m 9s
|
| 46 |
+
05/15/2026 20:40:11 - INFO - root - epochs: 1/2, steps: 1700/3536, func: 0.0527, 48%: 1h 35m 30s
|
| 47 |
+
05/15/2026 20:42:44 - INFO - root - epochs: 1/2, steps: 1750/3536, func: 0.05251, 49%: 1h 32m 50s
|
| 48 |
+
05/15/2026 20:45:20 - INFO - root - epochs: 2/2, steps: 1800/3536, func: 0.051787, 50%: 1h 30m 15s
|
| 49 |
+
05/15/2026 20:47:54 - INFO - root - epochs: 2/2, steps: 1850/3536, func: 0.051496, 52%: 1h 27m 37s
|
| 50 |
+
05/15/2026 20:50:27 - INFO - root - epochs: 2/2, steps: 1900/3536, func: 0.052407, 53%: 1h 24m 59s
|
| 51 |
+
05/15/2026 20:52:58 - INFO - root - epochs: 2/2, steps: 1950/3536, func: 0.052257, 55%: 1h 22m 20s
|
| 52 |
+
05/15/2026 20:55:27 - INFO - root - epochs: 2/2, steps: 2000/3536, func: 0.051656, 56%: 1h 19m 39s
|
| 53 |
+
05/15/2026 20:57:57 - INFO - root - epochs: 2/2, steps: 2050/3536, func: 0.051045, 57%: 1h 16m 59s
|
| 54 |
+
05/15/2026 21:00:33 - INFO - root - epochs: 2/2, steps: 2100/3536, func: 0.052583, 59%: 1h 14m 24s
|
| 55 |
+
05/15/2026 21:03:14 - INFO - root - epochs: 2/2, steps: 2150/3536, func: 0.052224, 60%: 1h 11m 52s
|
| 56 |
+
05/15/2026 21:05:56 - INFO - root - epochs: 2/2, steps: 2200/3536, func: 0.052227, 62%: 1h 9m 21s
|
| 57 |
+
05/15/2026 21:08:30 - INFO - root - epochs: 2/2, steps: 2250/3536, func: 0.052179, 63%: 1h 6m 44s
|
| 58 |
+
05/15/2026 21:11:11 - INFO - root - epochs: 2/2, steps: 2300/3536, func: 0.052093, 65%: 1h 4m 12s
|
| 59 |
+
05/15/2026 21:13:53 - INFO - root - epochs: 2/2, steps: 2350/3536, func: 0.052141, 66%: 1h 1m 39s
|
| 60 |
+
05/15/2026 21:16:22 - INFO - root - epochs: 2/2, steps: 2400/3536, func: 0.051118, 67%: 0h 59m 0s
|
| 61 |
+
05/15/2026 21:18:51 - INFO - root - epochs: 2/2, steps: 2450/3536, func: 0.051572, 69%: 0h 56m 22s
|
| 62 |
+
05/15/2026 21:21:21 - INFO - root - epochs: 2/2, steps: 2500/3536, func: 0.052727, 70%: 0h 53m 44s
|
| 63 |
+
05/15/2026 21:23:50 - INFO - root - epochs: 2/2, steps: 2550/3536, func: 0.050554, 72%: 0h 51m 6s
|
| 64 |
+
05/15/2026 21:26:19 - INFO - root - epochs: 2/2, steps: 2600/3536, func: 0.052245, 73%: 0h 48m 28s
|
| 65 |
+
05/15/2026 21:28:48 - INFO - root - epochs: 2/2, steps: 2650/3536, func: 0.051347, 74%: 0h 45m 51s
|
| 66 |
+
05/15/2026 21:31:17 - INFO - root - epochs: 2/2, steps: 2700/3536, func: 0.051098, 76%: 0h 43m 14s
|
| 67 |
+
05/15/2026 21:33:46 - INFO - root - epochs: 2/2, steps: 2750/3536, func: 0.052437, 77%: 0h 40m 37s
|
| 68 |
+
05/15/2026 21:36:16 - INFO - root - epochs: 2/2, steps: 2800/3536, func: 0.051171, 79%: 0h 38m 1s
|
| 69 |
+
05/15/2026 21:38:45 - INFO - root - epochs: 2/2, steps: 2850/3536, func: 0.051258, 80%: 0h 35m 25s
|
| 70 |
+
05/15/2026 21:41:15 - INFO - root - epochs: 2/2, steps: 2900/3536, func: 0.052864, 81%: 0h 32m 49s
|
| 71 |
+
05/15/2026 21:43:44 - INFO - root - epochs: 2/2, steps: 2950/3536, func: 0.052408, 83%: 0h 30m 13s
|
| 72 |
+
05/15/2026 21:46:13 - INFO - root - epochs: 2/2, steps: 3000/3536, func: 0.053137, 84%: 0h 27m 38s
|
| 73 |
+
05/15/2026 21:48:42 - INFO - root - epochs: 2/2, steps: 3050/3536, func: 0.051519, 86%: 0h 25m 3s
|
| 74 |
+
05/15/2026 21:51:13 - INFO - root - epochs: 2/2, steps: 3100/3536, func: 0.051677, 87%: 0h 22m 28s
|
| 75 |
+
05/15/2026 21:53:40 - INFO - root - epochs: 2/2, steps: 3150/3536, func: 0.051745, 89%: 0h 19m 53s
|
| 76 |
+
05/15/2026 21:56:07 - INFO - root - epochs: 2/2, steps: 3200/3536, func: 0.051179, 90%: 0h 17m 18s
|
| 77 |
+
05/15/2026 21:58:39 - INFO - root - epochs: 2/2, steps: 3250/3536, func: 0.050823, 91%: 0h 14m 44s
|
| 78 |
+
05/15/2026 22:01:15 - INFO - root - epochs: 2/2, steps: 3300/3536, func: 0.051552, 93%: 0h 12m 10s
|
| 79 |
+
05/15/2026 22:03:42 - INFO - root - epochs: 2/2, steps: 3350/3536, func: 0.051939, 94%: 0h 9m 35s
|
| 80 |
+
05/15/2026 22:06:09 - INFO - root - epochs: 2/2, steps: 3400/3536, func: 0.051432, 96%: 0h 7m 1s
|
| 81 |
+
05/15/2026 22:08:35 - INFO - root - epochs: 2/2, steps: 3450/3536, func: 0.050889, 97%: 0h 4m 27s
|
| 82 |
+
05/15/2026 22:11:03 - INFO - root - epochs: 2/2, steps: 3500/3536, func: 0.051312, 98%: 0h 1m 53s
|
| 83 |
+
05/15/2026 22:16:22 - INFO - root - final eval loss: func: 0.052181
|
| 84 |
+
05/15/2026 22:16:22 - INFO - root - Saving model checkpoint to /mnt/scratch/QRM/experiments/SCoDE/trained/llama2-7b-chat-lora-llama2-7b-chat_std/checkpoint-last
|
mistral-7b-lora-mistral-7b_std/checkpoint-last/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.8.2
|
mistral-7b-lora-mistral-7b_std/checkpoint-last/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 32,
|
| 13 |
+
"lora_dropout": 0.1,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"up_proj",
|
| 23 |
+
"down_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"lm_head"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
mistral-7b-lora-mistral-7b_std/checkpoint-last/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce78ec072ee48f391ee436bdb383381b14aea2f4cf5a074b29d56305619f225b
|
| 3 |
+
size 347246608
|
mistral-7b-lora-mistral-7b_std/checkpoint-last/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
mistral-7b-lora-mistral-7b_std/checkpoint-last/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mistral-7b-lora-mistral-7b_std/checkpoint-last/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
mistral-7b-lora-mistral-7b_std/checkpoint-last/tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"additional_special_tokens": [],
|
| 32 |
+
"bos_token": "<s>",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"extra_special_tokens": {},
|
| 36 |
+
"legacy": false,
|
| 37 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
+
"pad_token": null,
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false
|
| 44 |
+
}
|
mistral-7b-lora-mistral-7b_std/train.log
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
05/15/2026 17:56:50 - INFO - accelerate.utils.modeling - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk).
|
| 2 |
+
05/15/2026 17:57:22 - INFO - root - Training args Namespace(output_name='mistral-7b-lora-mistral-7b_std', datasets=['evol'], pretrain_name='mistral-7b', loss_weight=1.0, sven=False, num_train_epochs=2, learning_rate=2e-05, max_num_tokens=1024, batch_size=1, grad_acc_steps=16, weight_decay=0.01, adam_epsilon=1e-08, warmup_steps=0, max_grad_norm=1.0, dropout=0.1, kl_loss_weight=0, exclude_neg=False, no_weights=False, lora=True, r=16, lora_alpha=32, lora_dropout=0.1, sampling_size=20, sampling_method='minority', cwes=['all'], langs=['all'], logging_steps=50, save_epochs=10, seed=2, data_dir='/mnt/scratch/QRM/experiments/SCoDE/data_train_val', model_dir='/mnt/scratch/QRM/experiments/SCoDE/trained', output_dir='/mnt/scratch/QRM/experiments/SCoDE/trained/mistral-7b-lora-mistral-7b_std', logger=<RootLogger root (INFO)>)
|
| 3 |
+
05/15/2026 17:57:22 - INFO - root - ***** Running training *****
|
| 4 |
+
05/15/2026 17:57:22 - INFO - root - Num samples = 28588
|
| 5 |
+
05/15/2026 17:57:22 - INFO - root - Num epoch = 2
|
| 6 |
+
05/15/2026 17:57:22 - INFO - root - Batch size= 1
|
| 7 |
+
05/15/2026 17:57:22 - INFO - root - Total batch size (w. accumulation) = 16
|
| 8 |
+
05/15/2026 17:57:22 - INFO - root - Gradient Accumulation steps = 16
|
| 9 |
+
05/15/2026 17:57:22 - INFO - root - Total optimization steps = 3572
|
| 10 |
+
05/15/2026 17:57:22 - INFO - root - Num val samples = 3168
|
| 11 |
+
05/15/2026 17:57:22 - INFO - root - Num parameters = 7284252672
|
| 12 |
+
05/15/2026 17:57:22 - INFO - root - Num trainable parameters = 42520576
|
| 13 |
+
05/15/2026 18:00:01 - INFO - root - epochs: 1/2, steps: 50/3572, func: 0.04782, 1%: 3h 6m 23s
|
| 14 |
+
05/15/2026 18:02:38 - INFO - root - epochs: 1/2, steps: 100/3572, func: 0.046393, 2%: 3h 2m 39s
|
| 15 |
+
05/15/2026 18:05:14 - INFO - root - epochs: 1/2, steps: 150/3572, func: 0.046977, 4%: 2h 59m 25s
|
| 16 |
+
05/15/2026 18:07:51 - INFO - root - epochs: 1/2, steps: 200/3572, func: 0.045372, 5%: 2h 56m 40s
|
| 17 |
+
05/15/2026 18:10:27 - INFO - root - epochs: 1/2, steps: 250/3572, func: 0.046335, 6%: 2h 53m 59s
|
| 18 |
+
05/15/2026 18:13:04 - INFO - root - epochs: 1/2, steps: 300/3572, func: 0.044524, 8%: 2h 51m 18s
|
| 19 |
+
05/15/2026 18:15:41 - INFO - root - epochs: 1/2, steps: 350/3572, func: 0.044794, 9%: 2h 48m 43s
|
| 20 |
+
05/15/2026 18:18:17 - INFO - root - epochs: 1/2, steps: 400/3572, func: 0.045457, 11%: 2h 45m 58s
|
| 21 |
+
05/15/2026 18:20:54 - INFO - root - epochs: 1/2, steps: 450/3572, func: 0.044733, 12%: 2h 43m 17s
|
| 22 |
+
05/15/2026 18:23:30 - INFO - root - epochs: 1/2, steps: 500/3572, func: 0.044352, 13%: 2h 40m 34s
|
| 23 |
+
05/15/2026 18:26:06 - INFO - root - epochs: 1/2, steps: 550/3572, func: 0.044613, 15%: 2h 37m 55s
|
| 24 |
+
05/15/2026 18:28:43 - INFO - root - epochs: 1/2, steps: 600/3572, func: 0.045808, 16%: 2h 35m 18s
|
| 25 |
+
05/15/2026 18:31:20 - INFO - root - epochs: 1/2, steps: 650/3572, func: 0.045035, 18%: 2h 32m 42s
|
| 26 |
+
05/15/2026 18:33:56 - INFO - root - epochs: 1/2, steps: 700/3572, func: 0.044651, 19%: 2h 30m 4s
|
| 27 |
+
05/15/2026 18:36:33 - INFO - root - epochs: 1/2, steps: 750/3572, func: 0.044832, 20%: 2h 27m 26s
|
| 28 |
+
05/15/2026 18:39:08 - INFO - root - epochs: 1/2, steps: 800/3572, func: 0.044394, 22%: 2h 24m 47s
|
| 29 |
+
05/15/2026 18:41:45 - INFO - root - epochs: 1/2, steps: 850/3572, func: 0.045463, 23%: 2h 22m 10s
|
| 30 |
+
05/15/2026 18:44:22 - INFO - root - epochs: 1/2, steps: 900/3572, func: 0.043869, 25%: 2h 19m 34s
|
| 31 |
+
05/15/2026 18:46:58 - INFO - root - epochs: 1/2, steps: 950/3572, func: 0.043914, 26%: 2h 16m 57s
|
| 32 |
+
05/15/2026 18:49:35 - INFO - root - epochs: 1/2, steps: 1000/3572, func: 0.044635, 27%: 2h 14m 21s
|
| 33 |
+
05/15/2026 18:52:12 - INFO - root - epochs: 1/2, steps: 1050/3572, func: 0.044793, 29%: 2h 11m 44s
|
| 34 |
+
05/15/2026 18:54:48 - INFO - root - epochs: 1/2, steps: 1100/3572, func: 0.043871, 30%: 2h 9m 6s
|
| 35 |
+
05/15/2026 18:57:25 - INFO - root - epochs: 1/2, steps: 1150/3572, func: 0.044424, 32%: 2h 6m 30s
|
| 36 |
+
05/15/2026 19:00:01 - INFO - root - epochs: 1/2, steps: 1200/3572, func: 0.04448, 33%: 2h 3m 53s
|
| 37 |
+
05/15/2026 19:02:38 - INFO - root - epochs: 1/2, steps: 1250/3572, func: 0.043929, 34%: 2h 1m 16s
|
| 38 |
+
05/15/2026 19:05:14 - INFO - root - epochs: 1/2, steps: 1300/3572, func: 0.043855, 36%: 1h 58m 39s
|
| 39 |
+
05/15/2026 19:07:50 - INFO - root - epochs: 1/2, steps: 1350/3572, func: 0.044406, 37%: 1h 56m 1s
|
| 40 |
+
05/15/2026 19:10:26 - INFO - root - epochs: 1/2, steps: 1400/3572, func: 0.04391, 39%: 1h 53m 24s
|
| 41 |
+
05/15/2026 19:13:01 - INFO - root - epochs: 1/2, steps: 1450/3572, func: 0.043172, 40%: 1h 50m 45s
|
| 42 |
+
05/15/2026 19:15:36 - INFO - root - epochs: 1/2, steps: 1500/3572, func: 0.044031, 41%: 1h 48m 7s
|
| 43 |
+
05/15/2026 19:18:12 - INFO - root - epochs: 1/2, steps: 1550/3572, func: 0.044514, 43%: 1h 45m 29s
|
| 44 |
+
05/15/2026 19:20:47 - INFO - root - epochs: 1/2, steps: 1600/3572, func: 0.044062, 44%: 1h 42m 52s
|
| 45 |
+
05/15/2026 19:23:22 - INFO - root - epochs: 1/2, steps: 1650/3572, func: 0.044884, 46%: 1h 40m 13s
|
| 46 |
+
05/15/2026 19:25:58 - INFO - root - epochs: 1/2, steps: 1700/3572, func: 0.044205, 47%: 1h 37m 37s
|
| 47 |
+
05/15/2026 19:28:34 - INFO - root - epochs: 1/2, steps: 1750/3572, func: 0.04371, 48%: 1h 34m 59s
|
| 48 |
+
05/15/2026 19:31:12 - INFO - root - epochs: 2/2, steps: 1800/3572, func: 0.043733, 50%: 1h 32m 25s
|
| 49 |
+
05/15/2026 19:33:47 - INFO - root - epochs: 2/2, steps: 1850/3572, func: 0.041813, 51%: 1h 29m 47s
|
| 50 |
+
05/15/2026 19:36:21 - INFO - root - epochs: 2/2, steps: 1900/3572, func: 0.043437, 53%: 1h 27m 9s
|
| 51 |
+
05/15/2026 19:38:58 - INFO - root - epochs: 2/2, steps: 1950/3572, func: 0.042365, 54%: 1h 24m 33s
|
| 52 |
+
05/15/2026 19:41:32 - INFO - root - epochs: 2/2, steps: 2000/3572, func: 0.043135, 55%: 1h 21m 55s
|
| 53 |
+
05/15/2026 19:44:08 - INFO - root - epochs: 2/2, steps: 2050/3572, func: 0.042367, 57%: 1h 19m 19s
|
| 54 |
+
05/15/2026 19:46:44 - INFO - root - epochs: 2/2, steps: 2100/3572, func: 0.043078, 58%: 1h 16m 42s
|
| 55 |
+
05/15/2026 19:49:20 - INFO - root - epochs: 2/2, steps: 2150/3572, func: 0.042129, 60%: 1h 14m 6s
|
| 56 |
+
05/15/2026 19:51:56 - INFO - root - epochs: 2/2, steps: 2200/3572, func: 0.043458, 61%: 1h 11m 30s
|
| 57 |
+
05/15/2026 19:54:32 - INFO - root - epochs: 2/2, steps: 2250/3572, func: 0.042376, 62%: 1h 8m 53s
|
| 58 |
+
05/15/2026 19:57:07 - INFO - root - epochs: 2/2, steps: 2300/3572, func: 0.04351, 64%: 1h 6m 16s
|
| 59 |
+
05/15/2026 19:59:43 - INFO - root - epochs: 2/2, steps: 2350/3572, func: 0.042474, 65%: 1h 3m 40s
|
| 60 |
+
05/15/2026 20:02:19 - INFO - root - epochs: 2/2, steps: 2400/3572, func: 0.042419, 67%: 1h 1m 4s
|
| 61 |
+
05/15/2026 20:04:54 - INFO - root - epochs: 2/2, steps: 2450/3572, func: 0.042589, 68%: 0h 58m 27s
|
| 62 |
+
05/15/2026 20:07:30 - INFO - root - epochs: 2/2, steps: 2500/3572, func: 0.041758, 69%: 0h 55m 51s
|
| 63 |
+
05/15/2026 20:10:05 - INFO - root - epochs: 2/2, steps: 2550/3572, func: 0.043338, 71%: 0h 53m 14s
|
| 64 |
+
05/15/2026 20:12:41 - INFO - root - epochs: 2/2, steps: 2600/3572, func: 0.043566, 72%: 0h 50m 38s
|
| 65 |
+
05/15/2026 20:15:17 - INFO - root - epochs: 2/2, steps: 2650/3572, func: 0.043083, 74%: 0h 48m 2s
|
| 66 |
+
05/15/2026 20:17:53 - INFO - root - epochs: 2/2, steps: 2700/3572, func: 0.043279, 75%: 0h 45m 25s
|
| 67 |
+
05/15/2026 20:20:28 - INFO - root - epochs: 2/2, steps: 2750/3572, func: 0.042689, 76%: 0h 42m 49s
|
| 68 |
+
05/15/2026 20:23:04 - INFO - root - epochs: 2/2, steps: 2800/3572, func: 0.04225, 78%: 0h 40m 13s
|
| 69 |
+
05/15/2026 20:25:39 - INFO - root - epochs: 2/2, steps: 2850/3572, func: 0.042382, 79%: 0h 37m 36s
|
| 70 |
+
05/15/2026 20:28:14 - INFO - root - epochs: 2/2, steps: 2900/3572, func: 0.042185, 81%: 0h 35m 0s
|
| 71 |
+
05/15/2026 20:30:49 - INFO - root - epochs: 2/2, steps: 2950/3572, func: 0.043326, 82%: 0h 32m 24s
|
| 72 |
+
05/15/2026 20:33:26 - INFO - root - epochs: 2/2, steps: 3000/3572, func: 0.043274, 83%: 0h 29m 48s
|
| 73 |
+
05/15/2026 20:36:03 - INFO - root - epochs: 2/2, steps: 3050/3572, func: 0.042122, 85%: 0h 27m 12s
|
| 74 |
+
05/15/2026 20:38:38 - INFO - root - epochs: 2/2, steps: 3100/3572, func: 0.04308, 86%: 0h 24m 36s
|
| 75 |
+
05/15/2026 20:41:13 - INFO - root - epochs: 2/2, steps: 3150/3572, func: 0.042705, 88%: 0h 22m 0s
|
| 76 |
+
05/15/2026 20:43:49 - INFO - root - epochs: 2/2, steps: 3200/3572, func: 0.042302, 89%: 0h 19m 24s
|
| 77 |
+
05/15/2026 20:46:24 - INFO - root - epochs: 2/2, steps: 3250/3572, func: 0.042656, 90%: 0h 16m 47s
|
| 78 |
+
05/15/2026 20:49:01 - INFO - root - epochs: 2/2, steps: 3300/3572, func: 0.043938, 92%: 0h 14m 11s
|
| 79 |
+
05/15/2026 20:51:35 - INFO - root - epochs: 2/2, steps: 3350/3572, func: 0.043131, 93%: 0h 11m 35s
|
| 80 |
+
05/15/2026 20:54:10 - INFO - root - epochs: 2/2, steps: 3400/3572, func: 0.043427, 95%: 0h 8m 59s
|
| 81 |
+
05/15/2026 20:56:41 - INFO - root - epochs: 2/2, steps: 3450/3572, func: 0.042494, 96%: 0h 6m 23s
|
| 82 |
+
05/15/2026 20:59:12 - INFO - root - epochs: 2/2, steps: 3500/3572, func: 0.043126, 97%: 0h 3m 47s
|
| 83 |
+
05/15/2026 21:01:40 - INFO - root - epochs: 2/2, steps: 3550/3572, func: 0.042533, 99%: 0h 1m 11s
|
| 84 |
+
05/15/2026 21:06:22 - INFO - root - final eval loss: func: 0.044002
|
| 85 |
+
05/15/2026 21:06:22 - INFO - root - Saving model checkpoint to /mnt/scratch/QRM/experiments/SCoDE/trained/mistral-7b-lora-mistral-7b_std/checkpoint-last
|
phi-2_std/checkpoint-last/added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
phi-2_std/checkpoint-last/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"PhiForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 50256,
|
| 7 |
+
"embd_pdrop": 0.0,
|
| 8 |
+
"eos_token_id": 50256,
|
| 9 |
+
"hidden_act": "gelu_new",
|
| 10 |
+
"hidden_size": 2560,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 10240,
|
| 13 |
+
"layer_norm_eps": 1e-05,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "phi",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"num_key_value_heads": 32,
|
| 19 |
+
"partial_rotary_factor": 0.4,
|
| 20 |
+
"qk_layernorm": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.51.3",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 50295
|
| 29 |
+
}
|
phi-2_std/checkpoint-last/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.51.3"
|
| 6 |
+
}
|
phi-2_std/checkpoint-last/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
phi-2_std/checkpoint-last/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:badeac06704479196231d1d03fdf5ab39bb3485dce1e91f3924a36f00dfe6d4f
|
| 3 |
+
size 4990951248
|
phi-2_std/checkpoint-last/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99b8bb07d337617d217804728e0a9505e5272e9372a242eb5e975872244cf3c9
|
| 3 |
+
size 559197598
|
phi-2_std/checkpoint-last/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 5550098670
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.bias": "model-00002-of-00002.safetensors",
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.final_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 10 |
+
"model.final_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 352 |
+
"model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
| 355 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 357 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 360 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 361 |
+
"model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 362 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 364 |
+
"model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
| 368 |
+
"model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 370 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 372 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 373 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 374 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
|
| 459 |
+
}
|
| 460 |
+
}
|
phi-2_std/checkpoint-last/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"unk_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
phi-2_std/checkpoint-last/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
phi-2_std/checkpoint-last/tokenizer_config.json
ADDED
|
@@ -0,0 +1,325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": " ",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": false
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": " ",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": " ",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": " ",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": " ",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": " ",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": " ",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "\t\t\t\t\t\t\t",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "\t\t\t\t\t\t",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "\t\t\t\t\t",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "\t\t\t\t",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "\t\t\t",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "\t\t",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"bos_token": "<|endoftext|>",
|
| 318 |
+
"clean_up_tokenization_spaces": true,
|
| 319 |
+
"eos_token": "<|endoftext|>",
|
| 320 |
+
"extra_special_tokens": {},
|
| 321 |
+
"model_max_length": 2048,
|
| 322 |
+
"return_token_type_ids": false,
|
| 323 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 324 |
+
"unk_token": "<|endoftext|>"
|
| 325 |
+
}
|
phi-2_std/checkpoint-last/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|