Commit
·
095847d
1
Parent(s):
6492807
Push model đã tối ưu (fp16 + 4bit) sau fine-tuning
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +0 -38
- adapter_config.json +3 -3
- checkpoint-1000/README.md +0 -202
- checkpoint-1000/adapter_config.json +0 -37
- checkpoint-1000/adapter_model.safetensors +0 -3
- checkpoint-1000/added_tokens.json +0 -25
- checkpoint-1000/merges.txt +0 -0
- checkpoint-1000/optimizer.pt +0 -3
- checkpoint-1000/rng_state.pth +0 -3
- checkpoint-1000/scheduler.pt +0 -3
- checkpoint-1000/special_tokens_map.json +0 -31
- checkpoint-1000/tokenizer.json +0 -3
- checkpoint-1000/tokenizer_config.json +0 -217
- checkpoint-1000/trainer_state.json +0 -264
- checkpoint-1000/training_args.bin +0 -3
- checkpoint-1000/vocab.json +0 -0
- checkpoint-1500/README.md +0 -202
- checkpoint-1500/adapter_config.json +0 -37
- checkpoint-1500/adapter_model.safetensors +0 -3
- checkpoint-1500/added_tokens.json +0 -25
- checkpoint-1500/merges.txt +0 -0
- checkpoint-1500/optimizer.pt +0 -3
- checkpoint-1500/rng_state.pth +0 -3
- checkpoint-1500/scheduler.pt +0 -3
- checkpoint-1500/special_tokens_map.json +0 -31
- checkpoint-1500/tokenizer.json +0 -3
- checkpoint-1500/tokenizer_config.json +0 -217
- checkpoint-1500/trainer_state.json +0 -383
- checkpoint-1500/training_args.bin +0 -3
- checkpoint-1500/vocab.json +0 -0
- checkpoint-2000/README.md +0 -202
- checkpoint-2000/adapter_config.json +0 -37
- checkpoint-2000/adapter_model.safetensors +0 -3
- checkpoint-2000/added_tokens.json +0 -25
- checkpoint-2000/merges.txt +0 -0
- checkpoint-2000/optimizer.pt +0 -3
- checkpoint-2000/rng_state.pth +0 -3
- checkpoint-2000/scheduler.pt +0 -3
- checkpoint-2000/special_tokens_map.json +0 -31
- checkpoint-2000/tokenizer.json +0 -3
- checkpoint-2000/tokenizer_config.json +0 -217
- checkpoint-2000/trainer_state.json +0 -495
- checkpoint-2000/training_args.bin +0 -3
- checkpoint-2000/vocab.json +0 -0
- checkpoint-500/README.md +0 -202
- checkpoint-500/adapter_config.json +0 -37
- checkpoint-500/adapter_model.safetensors +0 -3
- checkpoint-500/added_tokens.json +0 -25
- checkpoint-500/merges.txt +0 -0
- checkpoint-500/optimizer.pt +0 -3
.gitattributes
DELETED
|
@@ -1,38 +0,0 @@
|
|
| 1 |
-
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
-
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
-
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
-
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
-
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
-
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
-
checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
-
checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
-
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
| 26 |
"k_proj",
|
| 27 |
"o_proj",
|
|
|
|
| 28 |
"q_proj",
|
| 29 |
-
"up_proj",
|
| 30 |
"v_proj",
|
| 31 |
-
"
|
| 32 |
-
"gate_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
+
"down_proj",
|
| 27 |
"k_proj",
|
| 28 |
"o_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
"q_proj",
|
|
|
|
| 31 |
"v_proj",
|
| 32 |
+
"up_proj"
|
|
|
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
checkpoint-1000/README.md
DELETED
|
@@ -1,202 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit
|
| 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 0.14.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/adapter_config.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "unsloth/qwen2.5-7b-instruct-bnb-4bit",
|
| 5 |
-
"bias": "none",
|
| 6 |
-
"eva_config": null,
|
| 7 |
-
"exclude_modules": null,
|
| 8 |
-
"fan_in_fan_out": false,
|
| 9 |
-
"inference_mode": true,
|
| 10 |
-
"init_lora_weights": true,
|
| 11 |
-
"layer_replication": null,
|
| 12 |
-
"layers_pattern": null,
|
| 13 |
-
"layers_to_transform": null,
|
| 14 |
-
"loftq_config": {},
|
| 15 |
-
"lora_alpha": 16,
|
| 16 |
-
"lora_bias": false,
|
| 17 |
-
"lora_dropout": 0,
|
| 18 |
-
"megatron_config": null,
|
| 19 |
-
"megatron_core": "megatron.core",
|
| 20 |
-
"modules_to_save": null,
|
| 21 |
-
"peft_type": "LORA",
|
| 22 |
-
"r": 16,
|
| 23 |
-
"rank_pattern": {},
|
| 24 |
-
"revision": null,
|
| 25 |
-
"target_modules": [
|
| 26 |
-
"gate_proj",
|
| 27 |
-
"up_proj",
|
| 28 |
-
"v_proj",
|
| 29 |
-
"down_proj",
|
| 30 |
-
"q_proj",
|
| 31 |
-
"o_proj",
|
| 32 |
-
"k_proj"
|
| 33 |
-
],
|
| 34 |
-
"task_type": "CAUSAL_LM",
|
| 35 |
-
"use_dora": false,
|
| 36 |
-
"use_rslora": false
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/adapter_model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:682cbd8609e1ad41b61fcafcb77f8a8431665f2144e737f09bec3a2d52a167f4
|
| 3 |
-
size 161533192
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/added_tokens.json
DELETED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"</tool_call>": 151658,
|
| 3 |
-
"<tool_call>": 151657,
|
| 4 |
-
"<|PAD_TOKEN|>": 151665,
|
| 5 |
-
"<|box_end|>": 151649,
|
| 6 |
-
"<|box_start|>": 151648,
|
| 7 |
-
"<|endoftext|>": 151643,
|
| 8 |
-
"<|file_sep|>": 151664,
|
| 9 |
-
"<|fim_middle|>": 151660,
|
| 10 |
-
"<|fim_pad|>": 151662,
|
| 11 |
-
"<|fim_prefix|>": 151659,
|
| 12 |
-
"<|fim_suffix|>": 151661,
|
| 13 |
-
"<|im_end|>": 151645,
|
| 14 |
-
"<|im_start|>": 151644,
|
| 15 |
-
"<|image_pad|>": 151655,
|
| 16 |
-
"<|object_ref_end|>": 151647,
|
| 17 |
-
"<|object_ref_start|>": 151646,
|
| 18 |
-
"<|quad_end|>": 151651,
|
| 19 |
-
"<|quad_start|>": 151650,
|
| 20 |
-
"<|repo_name|>": 151663,
|
| 21 |
-
"<|video_pad|>": 151656,
|
| 22 |
-
"<|vision_end|>": 151653,
|
| 23 |
-
"<|vision_pad|>": 151654,
|
| 24 |
-
"<|vision_start|>": 151652
|
| 25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:524dc8e3faab7f26e2249e9ecf0628b7b6138a11c2de5b678a7351ff31bfcad8
|
| 3 |
-
size 82461044
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:203e9bfabd925cb4ec7129d24877156fcee87215187c35a867e358e56a9425a4
|
| 3 |
-
size 14244
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c9fd164f9da57597a5394db32de3f909d3edec1ee801dc3317ccb7facfe79af3
|
| 3 |
-
size 1064
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<|im_start|>",
|
| 4 |
-
"<|im_end|>",
|
| 5 |
-
"<|object_ref_start|>",
|
| 6 |
-
"<|object_ref_end|>",
|
| 7 |
-
"<|box_start|>",
|
| 8 |
-
"<|box_end|>",
|
| 9 |
-
"<|quad_start|>",
|
| 10 |
-
"<|quad_end|>",
|
| 11 |
-
"<|vision_start|>",
|
| 12 |
-
"<|vision_end|>",
|
| 13 |
-
"<|vision_pad|>",
|
| 14 |
-
"<|image_pad|>",
|
| 15 |
-
"<|video_pad|>"
|
| 16 |
-
],
|
| 17 |
-
"eos_token": {
|
| 18 |
-
"content": "<|im_end|>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
},
|
| 24 |
-
"pad_token": {
|
| 25 |
-
"content": "<|PAD_TOKEN|>",
|
| 26 |
-
"lstrip": false,
|
| 27 |
-
"normalized": false,
|
| 28 |
-
"rstrip": false,
|
| 29 |
-
"single_word": false
|
| 30 |
-
}
|
| 31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
|
| 3 |
-
size 11422086
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/tokenizer_config.json
DELETED
|
@@ -1,217 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
-
"add_prefix_space": false,
|
| 4 |
-
"added_tokens_decoder": {
|
| 5 |
-
"151643": {
|
| 6 |
-
"content": "<|endoftext|>",
|
| 7 |
-
"lstrip": false,
|
| 8 |
-
"normalized": false,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false,
|
| 11 |
-
"special": true
|
| 12 |
-
},
|
| 13 |
-
"151644": {
|
| 14 |
-
"content": "<|im_start|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"151645": {
|
| 22 |
-
"content": "<|im_end|>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
},
|
| 29 |
-
"151646": {
|
| 30 |
-
"content": "<|object_ref_start|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"151647": {
|
| 38 |
-
"content": "<|object_ref_end|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"151648": {
|
| 46 |
-
"content": "<|box_start|>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"151649": {
|
| 54 |
-
"content": "<|box_end|>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
},
|
| 61 |
-
"151650": {
|
| 62 |
-
"content": "<|quad_start|>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
"151651": {
|
| 70 |
-
"content": "<|quad_end|>",
|
| 71 |
-
"lstrip": false,
|
| 72 |
-
"normalized": false,
|
| 73 |
-
"rstrip": false,
|
| 74 |
-
"single_word": false,
|
| 75 |
-
"special": true
|
| 76 |
-
},
|
| 77 |
-
"151652": {
|
| 78 |
-
"content": "<|vision_start|>",
|
| 79 |
-
"lstrip": false,
|
| 80 |
-
"normalized": false,
|
| 81 |
-
"rstrip": false,
|
| 82 |
-
"single_word": false,
|
| 83 |
-
"special": true
|
| 84 |
-
},
|
| 85 |
-
"151653": {
|
| 86 |
-
"content": "<|vision_end|>",
|
| 87 |
-
"lstrip": false,
|
| 88 |
-
"normalized": false,
|
| 89 |
-
"rstrip": false,
|
| 90 |
-
"single_word": false,
|
| 91 |
-
"special": true
|
| 92 |
-
},
|
| 93 |
-
"151654": {
|
| 94 |
-
"content": "<|vision_pad|>",
|
| 95 |
-
"lstrip": false,
|
| 96 |
-
"normalized": false,
|
| 97 |
-
"rstrip": false,
|
| 98 |
-
"single_word": false,
|
| 99 |
-
"special": true
|
| 100 |
-
},
|
| 101 |
-
"151655": {
|
| 102 |
-
"content": "<|image_pad|>",
|
| 103 |
-
"lstrip": false,
|
| 104 |
-
"normalized": false,
|
| 105 |
-
"rstrip": false,
|
| 106 |
-
"single_word": false,
|
| 107 |
-
"special": true
|
| 108 |
-
},
|
| 109 |
-
"151656": {
|
| 110 |
-
"content": "<|video_pad|>",
|
| 111 |
-
"lstrip": false,
|
| 112 |
-
"normalized": false,
|
| 113 |
-
"rstrip": false,
|
| 114 |
-
"single_word": false,
|
| 115 |
-
"special": true
|
| 116 |
-
},
|
| 117 |
-
"151657": {
|
| 118 |
-
"content": "<tool_call>",
|
| 119 |
-
"lstrip": false,
|
| 120 |
-
"normalized": false,
|
| 121 |
-
"rstrip": false,
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"special": false
|
| 124 |
-
},
|
| 125 |
-
"151658": {
|
| 126 |
-
"content": "</tool_call>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
-
"rstrip": false,
|
| 130 |
-
"single_word": false,
|
| 131 |
-
"special": false
|
| 132 |
-
},
|
| 133 |
-
"151659": {
|
| 134 |
-
"content": "<|fim_prefix|>",
|
| 135 |
-
"lstrip": false,
|
| 136 |
-
"normalized": false,
|
| 137 |
-
"rstrip": false,
|
| 138 |
-
"single_word": false,
|
| 139 |
-
"special": false
|
| 140 |
-
},
|
| 141 |
-
"151660": {
|
| 142 |
-
"content": "<|fim_middle|>",
|
| 143 |
-
"lstrip": false,
|
| 144 |
-
"normalized": false,
|
| 145 |
-
"rstrip": false,
|
| 146 |
-
"single_word": false,
|
| 147 |
-
"special": false
|
| 148 |
-
},
|
| 149 |
-
"151661": {
|
| 150 |
-
"content": "<|fim_suffix|>",
|
| 151 |
-
"lstrip": false,
|
| 152 |
-
"normalized": false,
|
| 153 |
-
"rstrip": false,
|
| 154 |
-
"single_word": false,
|
| 155 |
-
"special": false
|
| 156 |
-
},
|
| 157 |
-
"151662": {
|
| 158 |
-
"content": "<|fim_pad|>",
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"normalized": false,
|
| 161 |
-
"rstrip": false,
|
| 162 |
-
"single_word": false,
|
| 163 |
-
"special": false
|
| 164 |
-
},
|
| 165 |
-
"151663": {
|
| 166 |
-
"content": "<|repo_name|>",
|
| 167 |
-
"lstrip": false,
|
| 168 |
-
"normalized": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"single_word": false,
|
| 171 |
-
"special": false
|
| 172 |
-
},
|
| 173 |
-
"151664": {
|
| 174 |
-
"content": "<|file_sep|>",
|
| 175 |
-
"lstrip": false,
|
| 176 |
-
"normalized": false,
|
| 177 |
-
"rstrip": false,
|
| 178 |
-
"single_word": false,
|
| 179 |
-
"special": false
|
| 180 |
-
},
|
| 181 |
-
"151665": {
|
| 182 |
-
"content": "<|PAD_TOKEN|>",
|
| 183 |
-
"lstrip": false,
|
| 184 |
-
"normalized": false,
|
| 185 |
-
"rstrip": false,
|
| 186 |
-
"single_word": false,
|
| 187 |
-
"special": true
|
| 188 |
-
}
|
| 189 |
-
},
|
| 190 |
-
"additional_special_tokens": [
|
| 191 |
-
"<|im_start|>",
|
| 192 |
-
"<|im_end|>",
|
| 193 |
-
"<|object_ref_start|>",
|
| 194 |
-
"<|object_ref_end|>",
|
| 195 |
-
"<|box_start|>",
|
| 196 |
-
"<|box_end|>",
|
| 197 |
-
"<|quad_start|>",
|
| 198 |
-
"<|quad_end|>",
|
| 199 |
-
"<|vision_start|>",
|
| 200 |
-
"<|vision_end|>",
|
| 201 |
-
"<|vision_pad|>",
|
| 202 |
-
"<|image_pad|>",
|
| 203 |
-
"<|video_pad|>"
|
| 204 |
-
],
|
| 205 |
-
"bos_token": null,
|
| 206 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 207 |
-
"clean_up_tokenization_spaces": false,
|
| 208 |
-
"eos_token": "<|im_end|>",
|
| 209 |
-
"errors": "replace",
|
| 210 |
-
"extra_special_tokens": {},
|
| 211 |
-
"model_max_length": 32768,
|
| 212 |
-
"pad_token": "<|PAD_TOKEN|>",
|
| 213 |
-
"padding_side": "right",
|
| 214 |
-
"split_special_tokens": false,
|
| 215 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 216 |
-
"unk_token": null
|
| 217 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/trainer_state.json
DELETED
|
@@ -1,264 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.1560693641618498,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 1000,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.03468208092485549,
|
| 13 |
-
"grad_norm": 25.502880096435547,
|
| 14 |
-
"learning_rate": 6e-05,
|
| 15 |
-
"loss": 4.6656,
|
| 16 |
-
"step": 30
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.06936416184971098,
|
| 20 |
-
"grad_norm": 25.456541061401367,
|
| 21 |
-
"learning_rate": 9.948717948717949e-05,
|
| 22 |
-
"loss": 4.8124,
|
| 23 |
-
"step": 60
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.10404624277456648,
|
| 27 |
-
"grad_norm": 26.5838680267334,
|
| 28 |
-
"learning_rate": 9.794871794871795e-05,
|
| 29 |
-
"loss": 4.6459,
|
| 30 |
-
"step": 90
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.13872832369942195,
|
| 34 |
-
"grad_norm": 15.426424026489258,
|
| 35 |
-
"learning_rate": 9.641025641025641e-05,
|
| 36 |
-
"loss": 4.7755,
|
| 37 |
-
"step": 120
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.17341040462427745,
|
| 41 |
-
"grad_norm": 23.283618927001953,
|
| 42 |
-
"learning_rate": 9.487179487179487e-05,
|
| 43 |
-
"loss": 4.6794,
|
| 44 |
-
"step": 150
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.20809248554913296,
|
| 48 |
-
"grad_norm": 56.052162170410156,
|
| 49 |
-
"learning_rate": 9.333333333333334e-05,
|
| 50 |
-
"loss": 4.6939,
|
| 51 |
-
"step": 180
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.24277456647398843,
|
| 55 |
-
"grad_norm": 31.77360725402832,
|
| 56 |
-
"learning_rate": 9.179487179487179e-05,
|
| 57 |
-
"loss": 4.9231,
|
| 58 |
-
"step": 210
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.2774566473988439,
|
| 62 |
-
"grad_norm": 25.487804412841797,
|
| 63 |
-
"learning_rate": 9.025641025641026e-05,
|
| 64 |
-
"loss": 4.5026,
|
| 65 |
-
"step": 240
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.31213872832369943,
|
| 69 |
-
"grad_norm": 8.0370454788208,
|
| 70 |
-
"learning_rate": 8.871794871794872e-05,
|
| 71 |
-
"loss": 4.614,
|
| 72 |
-
"step": 270
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.3468208092485549,
|
| 76 |
-
"grad_norm": 25.447399139404297,
|
| 77 |
-
"learning_rate": 8.717948717948718e-05,
|
| 78 |
-
"loss": 4.5324,
|
| 79 |
-
"step": 300
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.3815028901734104,
|
| 83 |
-
"grad_norm": 14.47839069366455,
|
| 84 |
-
"learning_rate": 8.564102564102564e-05,
|
| 85 |
-
"loss": 4.3082,
|
| 86 |
-
"step": 330
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.4161849710982659,
|
| 90 |
-
"grad_norm": 17.378986358642578,
|
| 91 |
-
"learning_rate": 8.410256410256411e-05,
|
| 92 |
-
"loss": 4.5481,
|
| 93 |
-
"step": 360
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.4508670520231214,
|
| 97 |
-
"grad_norm": 15.464962005615234,
|
| 98 |
-
"learning_rate": 8.256410256410256e-05,
|
| 99 |
-
"loss": 4.6948,
|
| 100 |
-
"step": 390
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.48554913294797686,
|
| 104 |
-
"grad_norm": 14.592923164367676,
|
| 105 |
-
"learning_rate": 8.102564102564103e-05,
|
| 106 |
-
"loss": 4.4292,
|
| 107 |
-
"step": 420
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.5202312138728323,
|
| 111 |
-
"grad_norm": 40.595680236816406,
|
| 112 |
-
"learning_rate": 7.948717948717948e-05,
|
| 113 |
-
"loss": 4.287,
|
| 114 |
-
"step": 450
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.5549132947976878,
|
| 118 |
-
"grad_norm": 6.701582908630371,
|
| 119 |
-
"learning_rate": 7.794871794871795e-05,
|
| 120 |
-
"loss": 4.2174,
|
| 121 |
-
"step": 480
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.5895953757225434,
|
| 125 |
-
"grad_norm": 26.53321647644043,
|
| 126 |
-
"learning_rate": 7.641025641025641e-05,
|
| 127 |
-
"loss": 4.4222,
|
| 128 |
-
"step": 510
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.6242774566473989,
|
| 132 |
-
"grad_norm": 63.24378204345703,
|
| 133 |
-
"learning_rate": 7.487179487179487e-05,
|
| 134 |
-
"loss": 4.2019,
|
| 135 |
-
"step": 540
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.6589595375722543,
|
| 139 |
-
"grad_norm": 7.677667140960693,
|
| 140 |
-
"learning_rate": 7.333333333333333e-05,
|
| 141 |
-
"loss": 4.1925,
|
| 142 |
-
"step": 570
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.6936416184971098,
|
| 146 |
-
"grad_norm": 8.878572463989258,
|
| 147 |
-
"learning_rate": 7.17948717948718e-05,
|
| 148 |
-
"loss": 4.1576,
|
| 149 |
-
"step": 600
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.7283236994219653,
|
| 153 |
-
"grad_norm": 28.011911392211914,
|
| 154 |
-
"learning_rate": 7.025641025641025e-05,
|
| 155 |
-
"loss": 4.0491,
|
| 156 |
-
"step": 630
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.7630057803468208,
|
| 160 |
-
"grad_norm": 10.01468563079834,
|
| 161 |
-
"learning_rate": 6.871794871794872e-05,
|
| 162 |
-
"loss": 3.9603,
|
| 163 |
-
"step": 660
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 0.7976878612716763,
|
| 167 |
-
"grad_norm": 26.743711471557617,
|
| 168 |
-
"learning_rate": 6.717948717948718e-05,
|
| 169 |
-
"loss": 3.985,
|
| 170 |
-
"step": 690
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.8323699421965318,
|
| 174 |
-
"grad_norm": 16.028484344482422,
|
| 175 |
-
"learning_rate": 6.564102564102564e-05,
|
| 176 |
-
"loss": 3.9719,
|
| 177 |
-
"step": 720
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.8670520231213873,
|
| 181 |
-
"grad_norm": 10.875771522521973,
|
| 182 |
-
"learning_rate": 6.410256410256412e-05,
|
| 183 |
-
"loss": 3.9563,
|
| 184 |
-
"step": 750
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 0.9017341040462428,
|
| 188 |
-
"grad_norm": 20.58451271057129,
|
| 189 |
-
"learning_rate": 6.256410256410256e-05,
|
| 190 |
-
"loss": 3.9632,
|
| 191 |
-
"step": 780
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 0.9364161849710982,
|
| 195 |
-
"grad_norm": 9.106192588806152,
|
| 196 |
-
"learning_rate": 6.1025641025641035e-05,
|
| 197 |
-
"loss": 4.1386,
|
| 198 |
-
"step": 810
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"epoch": 0.9710982658959537,
|
| 202 |
-
"grad_norm": 19.22503662109375,
|
| 203 |
-
"learning_rate": 5.948717948717949e-05,
|
| 204 |
-
"loss": 3.9935,
|
| 205 |
-
"step": 840
|
| 206 |
-
},
|
| 207 |
-
{
|
| 208 |
-
"epoch": 1.0057803468208093,
|
| 209 |
-
"grad_norm": 15.524847030639648,
|
| 210 |
-
"learning_rate": 5.7948717948717954e-05,
|
| 211 |
-
"loss": 3.9245,
|
| 212 |
-
"step": 870
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 1.0404624277456647,
|
| 216 |
-
"grad_norm": 18.22639274597168,
|
| 217 |
-
"learning_rate": 5.6410256410256414e-05,
|
| 218 |
-
"loss": 3.7308,
|
| 219 |
-
"step": 900
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 1.0751445086705202,
|
| 223 |
-
"grad_norm": 7.170041561126709,
|
| 224 |
-
"learning_rate": 5.487179487179488e-05,
|
| 225 |
-
"loss": 3.9673,
|
| 226 |
-
"step": 930
|
| 227 |
-
},
|
| 228 |
-
{
|
| 229 |
-
"epoch": 1.1098265895953756,
|
| 230 |
-
"grad_norm": 40.25141525268555,
|
| 231 |
-
"learning_rate": 5.333333333333333e-05,
|
| 232 |
-
"loss": 3.7899,
|
| 233 |
-
"step": 960
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 1.1445086705202312,
|
| 237 |
-
"grad_norm": 50.212242126464844,
|
| 238 |
-
"learning_rate": 5.17948717948718e-05,
|
| 239 |
-
"loss": 3.8516,
|
| 240 |
-
"step": 990
|
| 241 |
-
}
|
| 242 |
-
],
|
| 243 |
-
"logging_steps": 30,
|
| 244 |
-
"max_steps": 2000,
|
| 245 |
-
"num_input_tokens_seen": 0,
|
| 246 |
-
"num_train_epochs": 3,
|
| 247 |
-
"save_steps": 500,
|
| 248 |
-
"stateful_callbacks": {
|
| 249 |
-
"TrainerControl": {
|
| 250 |
-
"args": {
|
| 251 |
-
"should_epoch_stop": false,
|
| 252 |
-
"should_evaluate": false,
|
| 253 |
-
"should_log": false,
|
| 254 |
-
"should_save": true,
|
| 255 |
-
"should_training_stop": false
|
| 256 |
-
},
|
| 257 |
-
"attributes": {}
|
| 258 |
-
}
|
| 259 |
-
},
|
| 260 |
-
"total_flos": 1.175161524821975e+17,
|
| 261 |
-
"train_batch_size": 2,
|
| 262 |
-
"trial_name": null,
|
| 263 |
-
"trial_params": null
|
| 264 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0f1794c5b75fe3c4ed55af4c8d5f8e5eeeb619c7c0af49191e895e7872712caf
|
| 3 |
-
size 5560
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/README.md
DELETED
|
@@ -1,202 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit
|
| 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 0.14.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/adapter_config.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "unsloth/qwen2.5-7b-instruct-bnb-4bit",
|
| 5 |
-
"bias": "none",
|
| 6 |
-
"eva_config": null,
|
| 7 |
-
"exclude_modules": null,
|
| 8 |
-
"fan_in_fan_out": false,
|
| 9 |
-
"inference_mode": true,
|
| 10 |
-
"init_lora_weights": true,
|
| 11 |
-
"layer_replication": null,
|
| 12 |
-
"layers_pattern": null,
|
| 13 |
-
"layers_to_transform": null,
|
| 14 |
-
"loftq_config": {},
|
| 15 |
-
"lora_alpha": 16,
|
| 16 |
-
"lora_bias": false,
|
| 17 |
-
"lora_dropout": 0,
|
| 18 |
-
"megatron_config": null,
|
| 19 |
-
"megatron_core": "megatron.core",
|
| 20 |
-
"modules_to_save": null,
|
| 21 |
-
"peft_type": "LORA",
|
| 22 |
-
"r": 16,
|
| 23 |
-
"rank_pattern": {},
|
| 24 |
-
"revision": null,
|
| 25 |
-
"target_modules": [
|
| 26 |
-
"gate_proj",
|
| 27 |
-
"up_proj",
|
| 28 |
-
"v_proj",
|
| 29 |
-
"down_proj",
|
| 30 |
-
"q_proj",
|
| 31 |
-
"o_proj",
|
| 32 |
-
"k_proj"
|
| 33 |
-
],
|
| 34 |
-
"task_type": "CAUSAL_LM",
|
| 35 |
-
"use_dora": false,
|
| 36 |
-
"use_rslora": false
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/adapter_model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a432f9a32cb640c4fb831ce0058a0f1cd75da0a4c763b0a8352d5d3f791635a3
|
| 3 |
-
size 161533192
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/added_tokens.json
DELETED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"</tool_call>": 151658,
|
| 3 |
-
"<tool_call>": 151657,
|
| 4 |
-
"<|PAD_TOKEN|>": 151665,
|
| 5 |
-
"<|box_end|>": 151649,
|
| 6 |
-
"<|box_start|>": 151648,
|
| 7 |
-
"<|endoftext|>": 151643,
|
| 8 |
-
"<|file_sep|>": 151664,
|
| 9 |
-
"<|fim_middle|>": 151660,
|
| 10 |
-
"<|fim_pad|>": 151662,
|
| 11 |
-
"<|fim_prefix|>": 151659,
|
| 12 |
-
"<|fim_suffix|>": 151661,
|
| 13 |
-
"<|im_end|>": 151645,
|
| 14 |
-
"<|im_start|>": 151644,
|
| 15 |
-
"<|image_pad|>": 151655,
|
| 16 |
-
"<|object_ref_end|>": 151647,
|
| 17 |
-
"<|object_ref_start|>": 151646,
|
| 18 |
-
"<|quad_end|>": 151651,
|
| 19 |
-
"<|quad_start|>": 151650,
|
| 20 |
-
"<|repo_name|>": 151663,
|
| 21 |
-
"<|video_pad|>": 151656,
|
| 22 |
-
"<|vision_end|>": 151653,
|
| 23 |
-
"<|vision_pad|>": 151654,
|
| 24 |
-
"<|vision_start|>": 151652
|
| 25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e60d0bd6c1fb2d4bb3a503bfbde234e802ab7e060afbab14221e05135c24a2d3
|
| 3 |
-
size 82461044
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:203e9bfabd925cb4ec7129d24877156fcee87215187c35a867e358e56a9425a4
|
| 3 |
-
size 14244
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:22841c7733ff4f355528a6539501f2e9b82c0721f01f5181e1e850e67cbc3305
|
| 3 |
-
size 1064
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<|im_start|>",
|
| 4 |
-
"<|im_end|>",
|
| 5 |
-
"<|object_ref_start|>",
|
| 6 |
-
"<|object_ref_end|>",
|
| 7 |
-
"<|box_start|>",
|
| 8 |
-
"<|box_end|>",
|
| 9 |
-
"<|quad_start|>",
|
| 10 |
-
"<|quad_end|>",
|
| 11 |
-
"<|vision_start|>",
|
| 12 |
-
"<|vision_end|>",
|
| 13 |
-
"<|vision_pad|>",
|
| 14 |
-
"<|image_pad|>",
|
| 15 |
-
"<|video_pad|>"
|
| 16 |
-
],
|
| 17 |
-
"eos_token": {
|
| 18 |
-
"content": "<|im_end|>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
},
|
| 24 |
-
"pad_token": {
|
| 25 |
-
"content": "<|PAD_TOKEN|>",
|
| 26 |
-
"lstrip": false,
|
| 27 |
-
"normalized": false,
|
| 28 |
-
"rstrip": false,
|
| 29 |
-
"single_word": false
|
| 30 |
-
}
|
| 31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
|
| 3 |
-
size 11422086
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/tokenizer_config.json
DELETED
|
@@ -1,217 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
-
"add_prefix_space": false,
|
| 4 |
-
"added_tokens_decoder": {
|
| 5 |
-
"151643": {
|
| 6 |
-
"content": "<|endoftext|>",
|
| 7 |
-
"lstrip": false,
|
| 8 |
-
"normalized": false,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false,
|
| 11 |
-
"special": true
|
| 12 |
-
},
|
| 13 |
-
"151644": {
|
| 14 |
-
"content": "<|im_start|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"151645": {
|
| 22 |
-
"content": "<|im_end|>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
},
|
| 29 |
-
"151646": {
|
| 30 |
-
"content": "<|object_ref_start|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"151647": {
|
| 38 |
-
"content": "<|object_ref_end|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"151648": {
|
| 46 |
-
"content": "<|box_start|>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"151649": {
|
| 54 |
-
"content": "<|box_end|>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
},
|
| 61 |
-
"151650": {
|
| 62 |
-
"content": "<|quad_start|>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
"151651": {
|
| 70 |
-
"content": "<|quad_end|>",
|
| 71 |
-
"lstrip": false,
|
| 72 |
-
"normalized": false,
|
| 73 |
-
"rstrip": false,
|
| 74 |
-
"single_word": false,
|
| 75 |
-
"special": true
|
| 76 |
-
},
|
| 77 |
-
"151652": {
|
| 78 |
-
"content": "<|vision_start|>",
|
| 79 |
-
"lstrip": false,
|
| 80 |
-
"normalized": false,
|
| 81 |
-
"rstrip": false,
|
| 82 |
-
"single_word": false,
|
| 83 |
-
"special": true
|
| 84 |
-
},
|
| 85 |
-
"151653": {
|
| 86 |
-
"content": "<|vision_end|>",
|
| 87 |
-
"lstrip": false,
|
| 88 |
-
"normalized": false,
|
| 89 |
-
"rstrip": false,
|
| 90 |
-
"single_word": false,
|
| 91 |
-
"special": true
|
| 92 |
-
},
|
| 93 |
-
"151654": {
|
| 94 |
-
"content": "<|vision_pad|>",
|
| 95 |
-
"lstrip": false,
|
| 96 |
-
"normalized": false,
|
| 97 |
-
"rstrip": false,
|
| 98 |
-
"single_word": false,
|
| 99 |
-
"special": true
|
| 100 |
-
},
|
| 101 |
-
"151655": {
|
| 102 |
-
"content": "<|image_pad|>",
|
| 103 |
-
"lstrip": false,
|
| 104 |
-
"normalized": false,
|
| 105 |
-
"rstrip": false,
|
| 106 |
-
"single_word": false,
|
| 107 |
-
"special": true
|
| 108 |
-
},
|
| 109 |
-
"151656": {
|
| 110 |
-
"content": "<|video_pad|>",
|
| 111 |
-
"lstrip": false,
|
| 112 |
-
"normalized": false,
|
| 113 |
-
"rstrip": false,
|
| 114 |
-
"single_word": false,
|
| 115 |
-
"special": true
|
| 116 |
-
},
|
| 117 |
-
"151657": {
|
| 118 |
-
"content": "<tool_call>",
|
| 119 |
-
"lstrip": false,
|
| 120 |
-
"normalized": false,
|
| 121 |
-
"rstrip": false,
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"special": false
|
| 124 |
-
},
|
| 125 |
-
"151658": {
|
| 126 |
-
"content": "</tool_call>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
-
"rstrip": false,
|
| 130 |
-
"single_word": false,
|
| 131 |
-
"special": false
|
| 132 |
-
},
|
| 133 |
-
"151659": {
|
| 134 |
-
"content": "<|fim_prefix|>",
|
| 135 |
-
"lstrip": false,
|
| 136 |
-
"normalized": false,
|
| 137 |
-
"rstrip": false,
|
| 138 |
-
"single_word": false,
|
| 139 |
-
"special": false
|
| 140 |
-
},
|
| 141 |
-
"151660": {
|
| 142 |
-
"content": "<|fim_middle|>",
|
| 143 |
-
"lstrip": false,
|
| 144 |
-
"normalized": false,
|
| 145 |
-
"rstrip": false,
|
| 146 |
-
"single_word": false,
|
| 147 |
-
"special": false
|
| 148 |
-
},
|
| 149 |
-
"151661": {
|
| 150 |
-
"content": "<|fim_suffix|>",
|
| 151 |
-
"lstrip": false,
|
| 152 |
-
"normalized": false,
|
| 153 |
-
"rstrip": false,
|
| 154 |
-
"single_word": false,
|
| 155 |
-
"special": false
|
| 156 |
-
},
|
| 157 |
-
"151662": {
|
| 158 |
-
"content": "<|fim_pad|>",
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"normalized": false,
|
| 161 |
-
"rstrip": false,
|
| 162 |
-
"single_word": false,
|
| 163 |
-
"special": false
|
| 164 |
-
},
|
| 165 |
-
"151663": {
|
| 166 |
-
"content": "<|repo_name|>",
|
| 167 |
-
"lstrip": false,
|
| 168 |
-
"normalized": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"single_word": false,
|
| 171 |
-
"special": false
|
| 172 |
-
},
|
| 173 |
-
"151664": {
|
| 174 |
-
"content": "<|file_sep|>",
|
| 175 |
-
"lstrip": false,
|
| 176 |
-
"normalized": false,
|
| 177 |
-
"rstrip": false,
|
| 178 |
-
"single_word": false,
|
| 179 |
-
"special": false
|
| 180 |
-
},
|
| 181 |
-
"151665": {
|
| 182 |
-
"content": "<|PAD_TOKEN|>",
|
| 183 |
-
"lstrip": false,
|
| 184 |
-
"normalized": false,
|
| 185 |
-
"rstrip": false,
|
| 186 |
-
"single_word": false,
|
| 187 |
-
"special": true
|
| 188 |
-
}
|
| 189 |
-
},
|
| 190 |
-
"additional_special_tokens": [
|
| 191 |
-
"<|im_start|>",
|
| 192 |
-
"<|im_end|>",
|
| 193 |
-
"<|object_ref_start|>",
|
| 194 |
-
"<|object_ref_end|>",
|
| 195 |
-
"<|box_start|>",
|
| 196 |
-
"<|box_end|>",
|
| 197 |
-
"<|quad_start|>",
|
| 198 |
-
"<|quad_end|>",
|
| 199 |
-
"<|vision_start|>",
|
| 200 |
-
"<|vision_end|>",
|
| 201 |
-
"<|vision_pad|>",
|
| 202 |
-
"<|image_pad|>",
|
| 203 |
-
"<|video_pad|>"
|
| 204 |
-
],
|
| 205 |
-
"bos_token": null,
|
| 206 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 207 |
-
"clean_up_tokenization_spaces": false,
|
| 208 |
-
"eos_token": "<|im_end|>",
|
| 209 |
-
"errors": "replace",
|
| 210 |
-
"extra_special_tokens": {},
|
| 211 |
-
"model_max_length": 32768,
|
| 212 |
-
"pad_token": "<|PAD_TOKEN|>",
|
| 213 |
-
"padding_side": "right",
|
| 214 |
-
"split_special_tokens": false,
|
| 215 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 216 |
-
"unk_token": null
|
| 217 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/trainer_state.json
DELETED
|
@@ -1,383 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.7341040462427746,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 1500,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.03468208092485549,
|
| 13 |
-
"grad_norm": 25.502880096435547,
|
| 14 |
-
"learning_rate": 6e-05,
|
| 15 |
-
"loss": 4.6656,
|
| 16 |
-
"step": 30
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.06936416184971098,
|
| 20 |
-
"grad_norm": 25.456541061401367,
|
| 21 |
-
"learning_rate": 9.948717948717949e-05,
|
| 22 |
-
"loss": 4.8124,
|
| 23 |
-
"step": 60
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.10404624277456648,
|
| 27 |
-
"grad_norm": 26.5838680267334,
|
| 28 |
-
"learning_rate": 9.794871794871795e-05,
|
| 29 |
-
"loss": 4.6459,
|
| 30 |
-
"step": 90
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.13872832369942195,
|
| 34 |
-
"grad_norm": 15.426424026489258,
|
| 35 |
-
"learning_rate": 9.641025641025641e-05,
|
| 36 |
-
"loss": 4.7755,
|
| 37 |
-
"step": 120
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.17341040462427745,
|
| 41 |
-
"grad_norm": 23.283618927001953,
|
| 42 |
-
"learning_rate": 9.487179487179487e-05,
|
| 43 |
-
"loss": 4.6794,
|
| 44 |
-
"step": 150
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.20809248554913296,
|
| 48 |
-
"grad_norm": 56.052162170410156,
|
| 49 |
-
"learning_rate": 9.333333333333334e-05,
|
| 50 |
-
"loss": 4.6939,
|
| 51 |
-
"step": 180
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.24277456647398843,
|
| 55 |
-
"grad_norm": 31.77360725402832,
|
| 56 |
-
"learning_rate": 9.179487179487179e-05,
|
| 57 |
-
"loss": 4.9231,
|
| 58 |
-
"step": 210
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.2774566473988439,
|
| 62 |
-
"grad_norm": 25.487804412841797,
|
| 63 |
-
"learning_rate": 9.025641025641026e-05,
|
| 64 |
-
"loss": 4.5026,
|
| 65 |
-
"step": 240
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.31213872832369943,
|
| 69 |
-
"grad_norm": 8.0370454788208,
|
| 70 |
-
"learning_rate": 8.871794871794872e-05,
|
| 71 |
-
"loss": 4.614,
|
| 72 |
-
"step": 270
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.3468208092485549,
|
| 76 |
-
"grad_norm": 25.447399139404297,
|
| 77 |
-
"learning_rate": 8.717948717948718e-05,
|
| 78 |
-
"loss": 4.5324,
|
| 79 |
-
"step": 300
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.3815028901734104,
|
| 83 |
-
"grad_norm": 14.47839069366455,
|
| 84 |
-
"learning_rate": 8.564102564102564e-05,
|
| 85 |
-
"loss": 4.3082,
|
| 86 |
-
"step": 330
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.4161849710982659,
|
| 90 |
-
"grad_norm": 17.378986358642578,
|
| 91 |
-
"learning_rate": 8.410256410256411e-05,
|
| 92 |
-
"loss": 4.5481,
|
| 93 |
-
"step": 360
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.4508670520231214,
|
| 97 |
-
"grad_norm": 15.464962005615234,
|
| 98 |
-
"learning_rate": 8.256410256410256e-05,
|
| 99 |
-
"loss": 4.6948,
|
| 100 |
-
"step": 390
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.48554913294797686,
|
| 104 |
-
"grad_norm": 14.592923164367676,
|
| 105 |
-
"learning_rate": 8.102564102564103e-05,
|
| 106 |
-
"loss": 4.4292,
|
| 107 |
-
"step": 420
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.5202312138728323,
|
| 111 |
-
"grad_norm": 40.595680236816406,
|
| 112 |
-
"learning_rate": 7.948717948717948e-05,
|
| 113 |
-
"loss": 4.287,
|
| 114 |
-
"step": 450
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.5549132947976878,
|
| 118 |
-
"grad_norm": 6.701582908630371,
|
| 119 |
-
"learning_rate": 7.794871794871795e-05,
|
| 120 |
-
"loss": 4.2174,
|
| 121 |
-
"step": 480
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.5895953757225434,
|
| 125 |
-
"grad_norm": 26.53321647644043,
|
| 126 |
-
"learning_rate": 7.641025641025641e-05,
|
| 127 |
-
"loss": 4.4222,
|
| 128 |
-
"step": 510
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.6242774566473989,
|
| 132 |
-
"grad_norm": 63.24378204345703,
|
| 133 |
-
"learning_rate": 7.487179487179487e-05,
|
| 134 |
-
"loss": 4.2019,
|
| 135 |
-
"step": 540
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.6589595375722543,
|
| 139 |
-
"grad_norm": 7.677667140960693,
|
| 140 |
-
"learning_rate": 7.333333333333333e-05,
|
| 141 |
-
"loss": 4.1925,
|
| 142 |
-
"step": 570
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.6936416184971098,
|
| 146 |
-
"grad_norm": 8.878572463989258,
|
| 147 |
-
"learning_rate": 7.17948717948718e-05,
|
| 148 |
-
"loss": 4.1576,
|
| 149 |
-
"step": 600
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.7283236994219653,
|
| 153 |
-
"grad_norm": 28.011911392211914,
|
| 154 |
-
"learning_rate": 7.025641025641025e-05,
|
| 155 |
-
"loss": 4.0491,
|
| 156 |
-
"step": 630
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.7630057803468208,
|
| 160 |
-
"grad_norm": 10.01468563079834,
|
| 161 |
-
"learning_rate": 6.871794871794872e-05,
|
| 162 |
-
"loss": 3.9603,
|
| 163 |
-
"step": 660
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 0.7976878612716763,
|
| 167 |
-
"grad_norm": 26.743711471557617,
|
| 168 |
-
"learning_rate": 6.717948717948718e-05,
|
| 169 |
-
"loss": 3.985,
|
| 170 |
-
"step": 690
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.8323699421965318,
|
| 174 |
-
"grad_norm": 16.028484344482422,
|
| 175 |
-
"learning_rate": 6.564102564102564e-05,
|
| 176 |
-
"loss": 3.9719,
|
| 177 |
-
"step": 720
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.8670520231213873,
|
| 181 |
-
"grad_norm": 10.875771522521973,
|
| 182 |
-
"learning_rate": 6.410256410256412e-05,
|
| 183 |
-
"loss": 3.9563,
|
| 184 |
-
"step": 750
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 0.9017341040462428,
|
| 188 |
-
"grad_norm": 20.58451271057129,
|
| 189 |
-
"learning_rate": 6.256410256410256e-05,
|
| 190 |
-
"loss": 3.9632,
|
| 191 |
-
"step": 780
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 0.9364161849710982,
|
| 195 |
-
"grad_norm": 9.106192588806152,
|
| 196 |
-
"learning_rate": 6.1025641025641035e-05,
|
| 197 |
-
"loss": 4.1386,
|
| 198 |
-
"step": 810
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"epoch": 0.9710982658959537,
|
| 202 |
-
"grad_norm": 19.22503662109375,
|
| 203 |
-
"learning_rate": 5.948717948717949e-05,
|
| 204 |
-
"loss": 3.9935,
|
| 205 |
-
"step": 840
|
| 206 |
-
},
|
| 207 |
-
{
|
| 208 |
-
"epoch": 1.0057803468208093,
|
| 209 |
-
"grad_norm": 15.524847030639648,
|
| 210 |
-
"learning_rate": 5.7948717948717954e-05,
|
| 211 |
-
"loss": 3.9245,
|
| 212 |
-
"step": 870
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 1.0404624277456647,
|
| 216 |
-
"grad_norm": 18.22639274597168,
|
| 217 |
-
"learning_rate": 5.6410256410256414e-05,
|
| 218 |
-
"loss": 3.7308,
|
| 219 |
-
"step": 900
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 1.0751445086705202,
|
| 223 |
-
"grad_norm": 7.170041561126709,
|
| 224 |
-
"learning_rate": 5.487179487179488e-05,
|
| 225 |
-
"loss": 3.9673,
|
| 226 |
-
"step": 930
|
| 227 |
-
},
|
| 228 |
-
{
|
| 229 |
-
"epoch": 1.1098265895953756,
|
| 230 |
-
"grad_norm": 40.25141525268555,
|
| 231 |
-
"learning_rate": 5.333333333333333e-05,
|
| 232 |
-
"loss": 3.7899,
|
| 233 |
-
"step": 960
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 1.1445086705202312,
|
| 237 |
-
"grad_norm": 50.212242126464844,
|
| 238 |
-
"learning_rate": 5.17948717948718e-05,
|
| 239 |
-
"loss": 3.8516,
|
| 240 |
-
"step": 990
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"epoch": 1.1791907514450868,
|
| 244 |
-
"grad_norm": 24.091739654541016,
|
| 245 |
-
"learning_rate": 5.025641025641026e-05,
|
| 246 |
-
"loss": 3.7711,
|
| 247 |
-
"step": 1020
|
| 248 |
-
},
|
| 249 |
-
{
|
| 250 |
-
"epoch": 1.2138728323699421,
|
| 251 |
-
"grad_norm": 23.369264602661133,
|
| 252 |
-
"learning_rate": 4.871794871794872e-05,
|
| 253 |
-
"loss": 3.8054,
|
| 254 |
-
"step": 1050
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 1.2485549132947977,
|
| 258 |
-
"grad_norm": 10.953289031982422,
|
| 259 |
-
"learning_rate": 4.717948717948718e-05,
|
| 260 |
-
"loss": 3.8031,
|
| 261 |
-
"step": 1080
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 1.2832369942196533,
|
| 265 |
-
"grad_norm": 9.630565643310547,
|
| 266 |
-
"learning_rate": 4.5641025641025645e-05,
|
| 267 |
-
"loss": 3.7168,
|
| 268 |
-
"step": 1110
|
| 269 |
-
},
|
| 270 |
-
{
|
| 271 |
-
"epoch": 1.3179190751445087,
|
| 272 |
-
"grad_norm": 10.57132339477539,
|
| 273 |
-
"learning_rate": 4.4102564102564104e-05,
|
| 274 |
-
"loss": 3.8477,
|
| 275 |
-
"step": 1140
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 1.352601156069364,
|
| 279 |
-
"grad_norm": 75.70760345458984,
|
| 280 |
-
"learning_rate": 4.2564102564102564e-05,
|
| 281 |
-
"loss": 3.787,
|
| 282 |
-
"step": 1170
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 1.3872832369942196,
|
| 286 |
-
"grad_norm": 13.153851509094238,
|
| 287 |
-
"learning_rate": 4.1025641025641023e-05,
|
| 288 |
-
"loss": 3.8109,
|
| 289 |
-
"step": 1200
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 1.4219653179190752,
|
| 293 |
-
"grad_norm": 20.857892990112305,
|
| 294 |
-
"learning_rate": 3.948717948717949e-05,
|
| 295 |
-
"loss": 3.5523,
|
| 296 |
-
"step": 1230
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 1.4566473988439306,
|
| 300 |
-
"grad_norm": 11.085583686828613,
|
| 301 |
-
"learning_rate": 3.794871794871795e-05,
|
| 302 |
-
"loss": 3.8683,
|
| 303 |
-
"step": 1260
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 1.4913294797687862,
|
| 307 |
-
"grad_norm": 34.30192184448242,
|
| 308 |
-
"learning_rate": 3.641025641025641e-05,
|
| 309 |
-
"loss": 3.5747,
|
| 310 |
-
"step": 1290
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"epoch": 1.5260115606936417,
|
| 314 |
-
"grad_norm": 51.97711944580078,
|
| 315 |
-
"learning_rate": 3.487179487179487e-05,
|
| 316 |
-
"loss": 3.6888,
|
| 317 |
-
"step": 1320
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 1.560693641618497,
|
| 321 |
-
"grad_norm": 10.605939865112305,
|
| 322 |
-
"learning_rate": 3.3333333333333335e-05,
|
| 323 |
-
"loss": 3.5827,
|
| 324 |
-
"step": 1350
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 1.5953757225433525,
|
| 328 |
-
"grad_norm": 10.216195106506348,
|
| 329 |
-
"learning_rate": 3.1794871794871795e-05,
|
| 330 |
-
"loss": 3.7847,
|
| 331 |
-
"step": 1380
|
| 332 |
-
},
|
| 333 |
-
{
|
| 334 |
-
"epoch": 1.630057803468208,
|
| 335 |
-
"grad_norm": 17.42462730407715,
|
| 336 |
-
"learning_rate": 3.0256410256410257e-05,
|
| 337 |
-
"loss": 3.6322,
|
| 338 |
-
"step": 1410
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 1.6647398843930636,
|
| 342 |
-
"grad_norm": 14.82337760925293,
|
| 343 |
-
"learning_rate": 2.8717948717948717e-05,
|
| 344 |
-
"loss": 3.6198,
|
| 345 |
-
"step": 1440
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 1.699421965317919,
|
| 349 |
-
"grad_norm": 17.812990188598633,
|
| 350 |
-
"learning_rate": 2.717948717948718e-05,
|
| 351 |
-
"loss": 3.4807,
|
| 352 |
-
"step": 1470
|
| 353 |
-
},
|
| 354 |
-
{
|
| 355 |
-
"epoch": 1.7341040462427746,
|
| 356 |
-
"grad_norm": 10.059772491455078,
|
| 357 |
-
"learning_rate": 2.564102564102564e-05,
|
| 358 |
-
"loss": 3.529,
|
| 359 |
-
"step": 1500
|
| 360 |
-
}
|
| 361 |
-
],
|
| 362 |
-
"logging_steps": 30,
|
| 363 |
-
"max_steps": 2000,
|
| 364 |
-
"num_input_tokens_seen": 0,
|
| 365 |
-
"num_train_epochs": 3,
|
| 366 |
-
"save_steps": 500,
|
| 367 |
-
"stateful_callbacks": {
|
| 368 |
-
"TrainerControl": {
|
| 369 |
-
"args": {
|
| 370 |
-
"should_epoch_stop": false,
|
| 371 |
-
"should_evaluate": false,
|
| 372 |
-
"should_log": false,
|
| 373 |
-
"should_save": true,
|
| 374 |
-
"should_training_stop": false
|
| 375 |
-
},
|
| 376 |
-
"attributes": {}
|
| 377 |
-
}
|
| 378 |
-
},
|
| 379 |
-
"total_flos": 1.775748571124183e+17,
|
| 380 |
-
"train_batch_size": 2,
|
| 381 |
-
"trial_name": null,
|
| 382 |
-
"trial_params": null
|
| 383 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0f1794c5b75fe3c4ed55af4c8d5f8e5eeeb619c7c0af49191e895e7872712caf
|
| 3 |
-
size 5560
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1500/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/README.md
DELETED
|
@@ -1,202 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit
|
| 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 0.14.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/adapter_config.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "unsloth/qwen2.5-7b-instruct-bnb-4bit",
|
| 5 |
-
"bias": "none",
|
| 6 |
-
"eva_config": null,
|
| 7 |
-
"exclude_modules": null,
|
| 8 |
-
"fan_in_fan_out": false,
|
| 9 |
-
"inference_mode": true,
|
| 10 |
-
"init_lora_weights": true,
|
| 11 |
-
"layer_replication": null,
|
| 12 |
-
"layers_pattern": null,
|
| 13 |
-
"layers_to_transform": null,
|
| 14 |
-
"loftq_config": {},
|
| 15 |
-
"lora_alpha": 16,
|
| 16 |
-
"lora_bias": false,
|
| 17 |
-
"lora_dropout": 0,
|
| 18 |
-
"megatron_config": null,
|
| 19 |
-
"megatron_core": "megatron.core",
|
| 20 |
-
"modules_to_save": null,
|
| 21 |
-
"peft_type": "LORA",
|
| 22 |
-
"r": 16,
|
| 23 |
-
"rank_pattern": {},
|
| 24 |
-
"revision": null,
|
| 25 |
-
"target_modules": [
|
| 26 |
-
"gate_proj",
|
| 27 |
-
"up_proj",
|
| 28 |
-
"v_proj",
|
| 29 |
-
"down_proj",
|
| 30 |
-
"q_proj",
|
| 31 |
-
"o_proj",
|
| 32 |
-
"k_proj"
|
| 33 |
-
],
|
| 34 |
-
"task_type": "CAUSAL_LM",
|
| 35 |
-
"use_dora": false,
|
| 36 |
-
"use_rslora": false
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/adapter_model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6fb4dd085e1bc77276085ce36469a6fe0c5ffa263be36f0e35a73e78399db259
|
| 3 |
-
size 161533192
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/added_tokens.json
DELETED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"</tool_call>": 151658,
|
| 3 |
-
"<tool_call>": 151657,
|
| 4 |
-
"<|PAD_TOKEN|>": 151665,
|
| 5 |
-
"<|box_end|>": 151649,
|
| 6 |
-
"<|box_start|>": 151648,
|
| 7 |
-
"<|endoftext|>": 151643,
|
| 8 |
-
"<|file_sep|>": 151664,
|
| 9 |
-
"<|fim_middle|>": 151660,
|
| 10 |
-
"<|fim_pad|>": 151662,
|
| 11 |
-
"<|fim_prefix|>": 151659,
|
| 12 |
-
"<|fim_suffix|>": 151661,
|
| 13 |
-
"<|im_end|>": 151645,
|
| 14 |
-
"<|im_start|>": 151644,
|
| 15 |
-
"<|image_pad|>": 151655,
|
| 16 |
-
"<|object_ref_end|>": 151647,
|
| 17 |
-
"<|object_ref_start|>": 151646,
|
| 18 |
-
"<|quad_end|>": 151651,
|
| 19 |
-
"<|quad_start|>": 151650,
|
| 20 |
-
"<|repo_name|>": 151663,
|
| 21 |
-
"<|video_pad|>": 151656,
|
| 22 |
-
"<|vision_end|>": 151653,
|
| 23 |
-
"<|vision_pad|>": 151654,
|
| 24 |
-
"<|vision_start|>": 151652
|
| 25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:10aa676e43344d2aadd33bfa664f9ddf4efddecc10152f2ac8ac0937e11db885
|
| 3 |
-
size 82461044
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4981123ff3cf7bd5b7f76839e90e4776f747ca4c38dcb41876fa010c0dea8b23
|
| 3 |
-
size 14244
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f6a1e3232c9dd0558d3b582345b4a537ca2d63d9ae2df7d7189cbdc92c4e384f
|
| 3 |
-
size 1064
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<|im_start|>",
|
| 4 |
-
"<|im_end|>",
|
| 5 |
-
"<|object_ref_start|>",
|
| 6 |
-
"<|object_ref_end|>",
|
| 7 |
-
"<|box_start|>",
|
| 8 |
-
"<|box_end|>",
|
| 9 |
-
"<|quad_start|>",
|
| 10 |
-
"<|quad_end|>",
|
| 11 |
-
"<|vision_start|>",
|
| 12 |
-
"<|vision_end|>",
|
| 13 |
-
"<|vision_pad|>",
|
| 14 |
-
"<|image_pad|>",
|
| 15 |
-
"<|video_pad|>"
|
| 16 |
-
],
|
| 17 |
-
"eos_token": {
|
| 18 |
-
"content": "<|im_end|>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
},
|
| 24 |
-
"pad_token": {
|
| 25 |
-
"content": "<|PAD_TOKEN|>",
|
| 26 |
-
"lstrip": false,
|
| 27 |
-
"normalized": false,
|
| 28 |
-
"rstrip": false,
|
| 29 |
-
"single_word": false
|
| 30 |
-
}
|
| 31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
|
| 3 |
-
size 11422086
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/tokenizer_config.json
DELETED
|
@@ -1,217 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
-
"add_prefix_space": false,
|
| 4 |
-
"added_tokens_decoder": {
|
| 5 |
-
"151643": {
|
| 6 |
-
"content": "<|endoftext|>",
|
| 7 |
-
"lstrip": false,
|
| 8 |
-
"normalized": false,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false,
|
| 11 |
-
"special": true
|
| 12 |
-
},
|
| 13 |
-
"151644": {
|
| 14 |
-
"content": "<|im_start|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"151645": {
|
| 22 |
-
"content": "<|im_end|>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
},
|
| 29 |
-
"151646": {
|
| 30 |
-
"content": "<|object_ref_start|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"151647": {
|
| 38 |
-
"content": "<|object_ref_end|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"151648": {
|
| 46 |
-
"content": "<|box_start|>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"151649": {
|
| 54 |
-
"content": "<|box_end|>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
},
|
| 61 |
-
"151650": {
|
| 62 |
-
"content": "<|quad_start|>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
"151651": {
|
| 70 |
-
"content": "<|quad_end|>",
|
| 71 |
-
"lstrip": false,
|
| 72 |
-
"normalized": false,
|
| 73 |
-
"rstrip": false,
|
| 74 |
-
"single_word": false,
|
| 75 |
-
"special": true
|
| 76 |
-
},
|
| 77 |
-
"151652": {
|
| 78 |
-
"content": "<|vision_start|>",
|
| 79 |
-
"lstrip": false,
|
| 80 |
-
"normalized": false,
|
| 81 |
-
"rstrip": false,
|
| 82 |
-
"single_word": false,
|
| 83 |
-
"special": true
|
| 84 |
-
},
|
| 85 |
-
"151653": {
|
| 86 |
-
"content": "<|vision_end|>",
|
| 87 |
-
"lstrip": false,
|
| 88 |
-
"normalized": false,
|
| 89 |
-
"rstrip": false,
|
| 90 |
-
"single_word": false,
|
| 91 |
-
"special": true
|
| 92 |
-
},
|
| 93 |
-
"151654": {
|
| 94 |
-
"content": "<|vision_pad|>",
|
| 95 |
-
"lstrip": false,
|
| 96 |
-
"normalized": false,
|
| 97 |
-
"rstrip": false,
|
| 98 |
-
"single_word": false,
|
| 99 |
-
"special": true
|
| 100 |
-
},
|
| 101 |
-
"151655": {
|
| 102 |
-
"content": "<|image_pad|>",
|
| 103 |
-
"lstrip": false,
|
| 104 |
-
"normalized": false,
|
| 105 |
-
"rstrip": false,
|
| 106 |
-
"single_word": false,
|
| 107 |
-
"special": true
|
| 108 |
-
},
|
| 109 |
-
"151656": {
|
| 110 |
-
"content": "<|video_pad|>",
|
| 111 |
-
"lstrip": false,
|
| 112 |
-
"normalized": false,
|
| 113 |
-
"rstrip": false,
|
| 114 |
-
"single_word": false,
|
| 115 |
-
"special": true
|
| 116 |
-
},
|
| 117 |
-
"151657": {
|
| 118 |
-
"content": "<tool_call>",
|
| 119 |
-
"lstrip": false,
|
| 120 |
-
"normalized": false,
|
| 121 |
-
"rstrip": false,
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"special": false
|
| 124 |
-
},
|
| 125 |
-
"151658": {
|
| 126 |
-
"content": "</tool_call>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
-
"rstrip": false,
|
| 130 |
-
"single_word": false,
|
| 131 |
-
"special": false
|
| 132 |
-
},
|
| 133 |
-
"151659": {
|
| 134 |
-
"content": "<|fim_prefix|>",
|
| 135 |
-
"lstrip": false,
|
| 136 |
-
"normalized": false,
|
| 137 |
-
"rstrip": false,
|
| 138 |
-
"single_word": false,
|
| 139 |
-
"special": false
|
| 140 |
-
},
|
| 141 |
-
"151660": {
|
| 142 |
-
"content": "<|fim_middle|>",
|
| 143 |
-
"lstrip": false,
|
| 144 |
-
"normalized": false,
|
| 145 |
-
"rstrip": false,
|
| 146 |
-
"single_word": false,
|
| 147 |
-
"special": false
|
| 148 |
-
},
|
| 149 |
-
"151661": {
|
| 150 |
-
"content": "<|fim_suffix|>",
|
| 151 |
-
"lstrip": false,
|
| 152 |
-
"normalized": false,
|
| 153 |
-
"rstrip": false,
|
| 154 |
-
"single_word": false,
|
| 155 |
-
"special": false
|
| 156 |
-
},
|
| 157 |
-
"151662": {
|
| 158 |
-
"content": "<|fim_pad|>",
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"normalized": false,
|
| 161 |
-
"rstrip": false,
|
| 162 |
-
"single_word": false,
|
| 163 |
-
"special": false
|
| 164 |
-
},
|
| 165 |
-
"151663": {
|
| 166 |
-
"content": "<|repo_name|>",
|
| 167 |
-
"lstrip": false,
|
| 168 |
-
"normalized": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"single_word": false,
|
| 171 |
-
"special": false
|
| 172 |
-
},
|
| 173 |
-
"151664": {
|
| 174 |
-
"content": "<|file_sep|>",
|
| 175 |
-
"lstrip": false,
|
| 176 |
-
"normalized": false,
|
| 177 |
-
"rstrip": false,
|
| 178 |
-
"single_word": false,
|
| 179 |
-
"special": false
|
| 180 |
-
},
|
| 181 |
-
"151665": {
|
| 182 |
-
"content": "<|PAD_TOKEN|>",
|
| 183 |
-
"lstrip": false,
|
| 184 |
-
"normalized": false,
|
| 185 |
-
"rstrip": false,
|
| 186 |
-
"single_word": false,
|
| 187 |
-
"special": true
|
| 188 |
-
}
|
| 189 |
-
},
|
| 190 |
-
"additional_special_tokens": [
|
| 191 |
-
"<|im_start|>",
|
| 192 |
-
"<|im_end|>",
|
| 193 |
-
"<|object_ref_start|>",
|
| 194 |
-
"<|object_ref_end|>",
|
| 195 |
-
"<|box_start|>",
|
| 196 |
-
"<|box_end|>",
|
| 197 |
-
"<|quad_start|>",
|
| 198 |
-
"<|quad_end|>",
|
| 199 |
-
"<|vision_start|>",
|
| 200 |
-
"<|vision_end|>",
|
| 201 |
-
"<|vision_pad|>",
|
| 202 |
-
"<|image_pad|>",
|
| 203 |
-
"<|video_pad|>"
|
| 204 |
-
],
|
| 205 |
-
"bos_token": null,
|
| 206 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 207 |
-
"clean_up_tokenization_spaces": false,
|
| 208 |
-
"eos_token": "<|im_end|>",
|
| 209 |
-
"errors": "replace",
|
| 210 |
-
"extra_special_tokens": {},
|
| 211 |
-
"model_max_length": 32768,
|
| 212 |
-
"pad_token": "<|PAD_TOKEN|>",
|
| 213 |
-
"padding_side": "right",
|
| 214 |
-
"split_special_tokens": false,
|
| 215 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 216 |
-
"unk_token": null
|
| 217 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/trainer_state.json
DELETED
|
@@ -1,495 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.3121387283236996,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 2000,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.03468208092485549,
|
| 13 |
-
"grad_norm": 25.502880096435547,
|
| 14 |
-
"learning_rate": 6e-05,
|
| 15 |
-
"loss": 4.6656,
|
| 16 |
-
"step": 30
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.06936416184971098,
|
| 20 |
-
"grad_norm": 25.456541061401367,
|
| 21 |
-
"learning_rate": 9.948717948717949e-05,
|
| 22 |
-
"loss": 4.8124,
|
| 23 |
-
"step": 60
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.10404624277456648,
|
| 27 |
-
"grad_norm": 26.5838680267334,
|
| 28 |
-
"learning_rate": 9.794871794871795e-05,
|
| 29 |
-
"loss": 4.6459,
|
| 30 |
-
"step": 90
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.13872832369942195,
|
| 34 |
-
"grad_norm": 15.426424026489258,
|
| 35 |
-
"learning_rate": 9.641025641025641e-05,
|
| 36 |
-
"loss": 4.7755,
|
| 37 |
-
"step": 120
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.17341040462427745,
|
| 41 |
-
"grad_norm": 23.283618927001953,
|
| 42 |
-
"learning_rate": 9.487179487179487e-05,
|
| 43 |
-
"loss": 4.6794,
|
| 44 |
-
"step": 150
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.20809248554913296,
|
| 48 |
-
"grad_norm": 56.052162170410156,
|
| 49 |
-
"learning_rate": 9.333333333333334e-05,
|
| 50 |
-
"loss": 4.6939,
|
| 51 |
-
"step": 180
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.24277456647398843,
|
| 55 |
-
"grad_norm": 31.77360725402832,
|
| 56 |
-
"learning_rate": 9.179487179487179e-05,
|
| 57 |
-
"loss": 4.9231,
|
| 58 |
-
"step": 210
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.2774566473988439,
|
| 62 |
-
"grad_norm": 25.487804412841797,
|
| 63 |
-
"learning_rate": 9.025641025641026e-05,
|
| 64 |
-
"loss": 4.5026,
|
| 65 |
-
"step": 240
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.31213872832369943,
|
| 69 |
-
"grad_norm": 8.0370454788208,
|
| 70 |
-
"learning_rate": 8.871794871794872e-05,
|
| 71 |
-
"loss": 4.614,
|
| 72 |
-
"step": 270
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.3468208092485549,
|
| 76 |
-
"grad_norm": 25.447399139404297,
|
| 77 |
-
"learning_rate": 8.717948717948718e-05,
|
| 78 |
-
"loss": 4.5324,
|
| 79 |
-
"step": 300
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.3815028901734104,
|
| 83 |
-
"grad_norm": 14.47839069366455,
|
| 84 |
-
"learning_rate": 8.564102564102564e-05,
|
| 85 |
-
"loss": 4.3082,
|
| 86 |
-
"step": 330
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.4161849710982659,
|
| 90 |
-
"grad_norm": 17.378986358642578,
|
| 91 |
-
"learning_rate": 8.410256410256411e-05,
|
| 92 |
-
"loss": 4.5481,
|
| 93 |
-
"step": 360
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.4508670520231214,
|
| 97 |
-
"grad_norm": 15.464962005615234,
|
| 98 |
-
"learning_rate": 8.256410256410256e-05,
|
| 99 |
-
"loss": 4.6948,
|
| 100 |
-
"step": 390
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.48554913294797686,
|
| 104 |
-
"grad_norm": 14.592923164367676,
|
| 105 |
-
"learning_rate": 8.102564102564103e-05,
|
| 106 |
-
"loss": 4.4292,
|
| 107 |
-
"step": 420
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.5202312138728323,
|
| 111 |
-
"grad_norm": 40.595680236816406,
|
| 112 |
-
"learning_rate": 7.948717948717948e-05,
|
| 113 |
-
"loss": 4.287,
|
| 114 |
-
"step": 450
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.5549132947976878,
|
| 118 |
-
"grad_norm": 6.701582908630371,
|
| 119 |
-
"learning_rate": 7.794871794871795e-05,
|
| 120 |
-
"loss": 4.2174,
|
| 121 |
-
"step": 480
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.5895953757225434,
|
| 125 |
-
"grad_norm": 26.53321647644043,
|
| 126 |
-
"learning_rate": 7.641025641025641e-05,
|
| 127 |
-
"loss": 4.4222,
|
| 128 |
-
"step": 510
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.6242774566473989,
|
| 132 |
-
"grad_norm": 63.24378204345703,
|
| 133 |
-
"learning_rate": 7.487179487179487e-05,
|
| 134 |
-
"loss": 4.2019,
|
| 135 |
-
"step": 540
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.6589595375722543,
|
| 139 |
-
"grad_norm": 7.677667140960693,
|
| 140 |
-
"learning_rate": 7.333333333333333e-05,
|
| 141 |
-
"loss": 4.1925,
|
| 142 |
-
"step": 570
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.6936416184971098,
|
| 146 |
-
"grad_norm": 8.878572463989258,
|
| 147 |
-
"learning_rate": 7.17948717948718e-05,
|
| 148 |
-
"loss": 4.1576,
|
| 149 |
-
"step": 600
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.7283236994219653,
|
| 153 |
-
"grad_norm": 28.011911392211914,
|
| 154 |
-
"learning_rate": 7.025641025641025e-05,
|
| 155 |
-
"loss": 4.0491,
|
| 156 |
-
"step": 630
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.7630057803468208,
|
| 160 |
-
"grad_norm": 10.01468563079834,
|
| 161 |
-
"learning_rate": 6.871794871794872e-05,
|
| 162 |
-
"loss": 3.9603,
|
| 163 |
-
"step": 660
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 0.7976878612716763,
|
| 167 |
-
"grad_norm": 26.743711471557617,
|
| 168 |
-
"learning_rate": 6.717948717948718e-05,
|
| 169 |
-
"loss": 3.985,
|
| 170 |
-
"step": 690
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.8323699421965318,
|
| 174 |
-
"grad_norm": 16.028484344482422,
|
| 175 |
-
"learning_rate": 6.564102564102564e-05,
|
| 176 |
-
"loss": 3.9719,
|
| 177 |
-
"step": 720
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.8670520231213873,
|
| 181 |
-
"grad_norm": 10.875771522521973,
|
| 182 |
-
"learning_rate": 6.410256410256412e-05,
|
| 183 |
-
"loss": 3.9563,
|
| 184 |
-
"step": 750
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 0.9017341040462428,
|
| 188 |
-
"grad_norm": 20.58451271057129,
|
| 189 |
-
"learning_rate": 6.256410256410256e-05,
|
| 190 |
-
"loss": 3.9632,
|
| 191 |
-
"step": 780
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 0.9364161849710982,
|
| 195 |
-
"grad_norm": 9.106192588806152,
|
| 196 |
-
"learning_rate": 6.1025641025641035e-05,
|
| 197 |
-
"loss": 4.1386,
|
| 198 |
-
"step": 810
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"epoch": 0.9710982658959537,
|
| 202 |
-
"grad_norm": 19.22503662109375,
|
| 203 |
-
"learning_rate": 5.948717948717949e-05,
|
| 204 |
-
"loss": 3.9935,
|
| 205 |
-
"step": 840
|
| 206 |
-
},
|
| 207 |
-
{
|
| 208 |
-
"epoch": 1.0057803468208093,
|
| 209 |
-
"grad_norm": 15.524847030639648,
|
| 210 |
-
"learning_rate": 5.7948717948717954e-05,
|
| 211 |
-
"loss": 3.9245,
|
| 212 |
-
"step": 870
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 1.0404624277456647,
|
| 216 |
-
"grad_norm": 18.22639274597168,
|
| 217 |
-
"learning_rate": 5.6410256410256414e-05,
|
| 218 |
-
"loss": 3.7308,
|
| 219 |
-
"step": 900
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 1.0751445086705202,
|
| 223 |
-
"grad_norm": 7.170041561126709,
|
| 224 |
-
"learning_rate": 5.487179487179488e-05,
|
| 225 |
-
"loss": 3.9673,
|
| 226 |
-
"step": 930
|
| 227 |
-
},
|
| 228 |
-
{
|
| 229 |
-
"epoch": 1.1098265895953756,
|
| 230 |
-
"grad_norm": 40.25141525268555,
|
| 231 |
-
"learning_rate": 5.333333333333333e-05,
|
| 232 |
-
"loss": 3.7899,
|
| 233 |
-
"step": 960
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 1.1445086705202312,
|
| 237 |
-
"grad_norm": 50.212242126464844,
|
| 238 |
-
"learning_rate": 5.17948717948718e-05,
|
| 239 |
-
"loss": 3.8516,
|
| 240 |
-
"step": 990
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"epoch": 1.1791907514450868,
|
| 244 |
-
"grad_norm": 24.091739654541016,
|
| 245 |
-
"learning_rate": 5.025641025641026e-05,
|
| 246 |
-
"loss": 3.7711,
|
| 247 |
-
"step": 1020
|
| 248 |
-
},
|
| 249 |
-
{
|
| 250 |
-
"epoch": 1.2138728323699421,
|
| 251 |
-
"grad_norm": 23.369264602661133,
|
| 252 |
-
"learning_rate": 4.871794871794872e-05,
|
| 253 |
-
"loss": 3.8054,
|
| 254 |
-
"step": 1050
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 1.2485549132947977,
|
| 258 |
-
"grad_norm": 10.953289031982422,
|
| 259 |
-
"learning_rate": 4.717948717948718e-05,
|
| 260 |
-
"loss": 3.8031,
|
| 261 |
-
"step": 1080
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 1.2832369942196533,
|
| 265 |
-
"grad_norm": 9.630565643310547,
|
| 266 |
-
"learning_rate": 4.5641025641025645e-05,
|
| 267 |
-
"loss": 3.7168,
|
| 268 |
-
"step": 1110
|
| 269 |
-
},
|
| 270 |
-
{
|
| 271 |
-
"epoch": 1.3179190751445087,
|
| 272 |
-
"grad_norm": 10.57132339477539,
|
| 273 |
-
"learning_rate": 4.4102564102564104e-05,
|
| 274 |
-
"loss": 3.8477,
|
| 275 |
-
"step": 1140
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 1.352601156069364,
|
| 279 |
-
"grad_norm": 75.70760345458984,
|
| 280 |
-
"learning_rate": 4.2564102564102564e-05,
|
| 281 |
-
"loss": 3.787,
|
| 282 |
-
"step": 1170
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 1.3872832369942196,
|
| 286 |
-
"grad_norm": 13.153851509094238,
|
| 287 |
-
"learning_rate": 4.1025641025641023e-05,
|
| 288 |
-
"loss": 3.8109,
|
| 289 |
-
"step": 1200
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 1.4219653179190752,
|
| 293 |
-
"grad_norm": 20.857892990112305,
|
| 294 |
-
"learning_rate": 3.948717948717949e-05,
|
| 295 |
-
"loss": 3.5523,
|
| 296 |
-
"step": 1230
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 1.4566473988439306,
|
| 300 |
-
"grad_norm": 11.085583686828613,
|
| 301 |
-
"learning_rate": 3.794871794871795e-05,
|
| 302 |
-
"loss": 3.8683,
|
| 303 |
-
"step": 1260
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 1.4913294797687862,
|
| 307 |
-
"grad_norm": 34.30192184448242,
|
| 308 |
-
"learning_rate": 3.641025641025641e-05,
|
| 309 |
-
"loss": 3.5747,
|
| 310 |
-
"step": 1290
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"epoch": 1.5260115606936417,
|
| 314 |
-
"grad_norm": 51.97711944580078,
|
| 315 |
-
"learning_rate": 3.487179487179487e-05,
|
| 316 |
-
"loss": 3.6888,
|
| 317 |
-
"step": 1320
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 1.560693641618497,
|
| 321 |
-
"grad_norm": 10.605939865112305,
|
| 322 |
-
"learning_rate": 3.3333333333333335e-05,
|
| 323 |
-
"loss": 3.5827,
|
| 324 |
-
"step": 1350
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 1.5953757225433525,
|
| 328 |
-
"grad_norm": 10.216195106506348,
|
| 329 |
-
"learning_rate": 3.1794871794871795e-05,
|
| 330 |
-
"loss": 3.7847,
|
| 331 |
-
"step": 1380
|
| 332 |
-
},
|
| 333 |
-
{
|
| 334 |
-
"epoch": 1.630057803468208,
|
| 335 |
-
"grad_norm": 17.42462730407715,
|
| 336 |
-
"learning_rate": 3.0256410256410257e-05,
|
| 337 |
-
"loss": 3.6322,
|
| 338 |
-
"step": 1410
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 1.6647398843930636,
|
| 342 |
-
"grad_norm": 14.82337760925293,
|
| 343 |
-
"learning_rate": 2.8717948717948717e-05,
|
| 344 |
-
"loss": 3.6198,
|
| 345 |
-
"step": 1440
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 1.699421965317919,
|
| 349 |
-
"grad_norm": 17.812990188598633,
|
| 350 |
-
"learning_rate": 2.717948717948718e-05,
|
| 351 |
-
"loss": 3.4807,
|
| 352 |
-
"step": 1470
|
| 353 |
-
},
|
| 354 |
-
{
|
| 355 |
-
"epoch": 1.7341040462427746,
|
| 356 |
-
"grad_norm": 10.059772491455078,
|
| 357 |
-
"learning_rate": 2.564102564102564e-05,
|
| 358 |
-
"loss": 3.529,
|
| 359 |
-
"step": 1500
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 1.7687861271676302,
|
| 363 |
-
"grad_norm": 14.55814266204834,
|
| 364 |
-
"learning_rate": 2.4102564102564103e-05,
|
| 365 |
-
"loss": 3.5979,
|
| 366 |
-
"step": 1530
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 1.8034682080924855,
|
| 370 |
-
"grad_norm": 9.438383102416992,
|
| 371 |
-
"learning_rate": 2.2564102564102566e-05,
|
| 372 |
-
"loss": 3.6289,
|
| 373 |
-
"step": 1560
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 1.838150289017341,
|
| 377 |
-
"grad_norm": 8.599316596984863,
|
| 378 |
-
"learning_rate": 2.102564102564103e-05,
|
| 379 |
-
"loss": 3.5702,
|
| 380 |
-
"step": 1590
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 1.8728323699421965,
|
| 384 |
-
"grad_norm": 17.82367515563965,
|
| 385 |
-
"learning_rate": 1.9487179487179488e-05,
|
| 386 |
-
"loss": 3.5129,
|
| 387 |
-
"step": 1620
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 1.907514450867052,
|
| 391 |
-
"grad_norm": 20.726346969604492,
|
| 392 |
-
"learning_rate": 1.794871794871795e-05,
|
| 393 |
-
"loss": 3.4773,
|
| 394 |
-
"step": 1650
|
| 395 |
-
},
|
| 396 |
-
{
|
| 397 |
-
"epoch": 1.9421965317919074,
|
| 398 |
-
"grad_norm": 8.656140327453613,
|
| 399 |
-
"learning_rate": 1.641025641025641e-05,
|
| 400 |
-
"loss": 3.4055,
|
| 401 |
-
"step": 1680
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 1.976878612716763,
|
| 405 |
-
"grad_norm": 16.18499755859375,
|
| 406 |
-
"learning_rate": 1.4871794871794872e-05,
|
| 407 |
-
"loss": 3.3752,
|
| 408 |
-
"step": 1710
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"epoch": 2.0115606936416186,
|
| 412 |
-
"grad_norm": 7.710521697998047,
|
| 413 |
-
"learning_rate": 1.3333333333333333e-05,
|
| 414 |
-
"loss": 3.4809,
|
| 415 |
-
"step": 1740
|
| 416 |
-
},
|
| 417 |
-
{
|
| 418 |
-
"epoch": 2.046242774566474,
|
| 419 |
-
"grad_norm": 14.836627960205078,
|
| 420 |
-
"learning_rate": 1.1794871794871795e-05,
|
| 421 |
-
"loss": 3.4611,
|
| 422 |
-
"step": 1770
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 2.0809248554913293,
|
| 426 |
-
"grad_norm": 12.528371810913086,
|
| 427 |
-
"learning_rate": 1.0256410256410256e-05,
|
| 428 |
-
"loss": 3.3767,
|
| 429 |
-
"step": 1800
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 2.115606936416185,
|
| 433 |
-
"grad_norm": 17.02320098876953,
|
| 434 |
-
"learning_rate": 8.717948717948717e-06,
|
| 435 |
-
"loss": 3.3892,
|
| 436 |
-
"step": 1830
|
| 437 |
-
},
|
| 438 |
-
{
|
| 439 |
-
"epoch": 2.1502890173410405,
|
| 440 |
-
"grad_norm": 7.57002592086792,
|
| 441 |
-
"learning_rate": 7.179487179487179e-06,
|
| 442 |
-
"loss": 3.5143,
|
| 443 |
-
"step": 1860
|
| 444 |
-
},
|
| 445 |
-
{
|
| 446 |
-
"epoch": 2.184971098265896,
|
| 447 |
-
"grad_norm": 11.202415466308594,
|
| 448 |
-
"learning_rate": 5.641025641025641e-06,
|
| 449 |
-
"loss": 3.3684,
|
| 450 |
-
"step": 1890
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"epoch": 2.2196531791907512,
|
| 454 |
-
"grad_norm": 9.897978782653809,
|
| 455 |
-
"learning_rate": 4.102564102564103e-06,
|
| 456 |
-
"loss": 3.4132,
|
| 457 |
-
"step": 1920
|
| 458 |
-
},
|
| 459 |
-
{
|
| 460 |
-
"epoch": 2.254335260115607,
|
| 461 |
-
"grad_norm": 7.221506595611572,
|
| 462 |
-
"learning_rate": 2.564102564102564e-06,
|
| 463 |
-
"loss": 3.3146,
|
| 464 |
-
"step": 1950
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 2.2890173410404624,
|
| 468 |
-
"grad_norm": 13.679113388061523,
|
| 469 |
-
"learning_rate": 1.0256410256410257e-06,
|
| 470 |
-
"loss": 3.2997,
|
| 471 |
-
"step": 1980
|
| 472 |
-
}
|
| 473 |
-
],
|
| 474 |
-
"logging_steps": 30,
|
| 475 |
-
"max_steps": 2000,
|
| 476 |
-
"num_input_tokens_seen": 0,
|
| 477 |
-
"num_train_epochs": 3,
|
| 478 |
-
"save_steps": 500,
|
| 479 |
-
"stateful_callbacks": {
|
| 480 |
-
"TrainerControl": {
|
| 481 |
-
"args": {
|
| 482 |
-
"should_epoch_stop": false,
|
| 483 |
-
"should_evaluate": false,
|
| 484 |
-
"should_log": false,
|
| 485 |
-
"should_save": true,
|
| 486 |
-
"should_training_stop": true
|
| 487 |
-
},
|
| 488 |
-
"attributes": {}
|
| 489 |
-
}
|
| 490 |
-
},
|
| 491 |
-
"total_flos": 2.357170932351406e+17,
|
| 492 |
-
"train_batch_size": 2,
|
| 493 |
-
"trial_name": null,
|
| 494 |
-
"trial_params": null
|
| 495 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0f1794c5b75fe3c4ed55af4c8d5f8e5eeeb619c7c0af49191e895e7872712caf
|
| 3 |
-
size 5560
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-500/README.md
DELETED
|
@@ -1,202 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit
|
| 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 0.14.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-500/adapter_config.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "unsloth/qwen2.5-7b-instruct-bnb-4bit",
|
| 5 |
-
"bias": "none",
|
| 6 |
-
"eva_config": null,
|
| 7 |
-
"exclude_modules": null,
|
| 8 |
-
"fan_in_fan_out": false,
|
| 9 |
-
"inference_mode": true,
|
| 10 |
-
"init_lora_weights": true,
|
| 11 |
-
"layer_replication": null,
|
| 12 |
-
"layers_pattern": null,
|
| 13 |
-
"layers_to_transform": null,
|
| 14 |
-
"loftq_config": {},
|
| 15 |
-
"lora_alpha": 16,
|
| 16 |
-
"lora_bias": false,
|
| 17 |
-
"lora_dropout": 0,
|
| 18 |
-
"megatron_config": null,
|
| 19 |
-
"megatron_core": "megatron.core",
|
| 20 |
-
"modules_to_save": null,
|
| 21 |
-
"peft_type": "LORA",
|
| 22 |
-
"r": 16,
|
| 23 |
-
"rank_pattern": {},
|
| 24 |
-
"revision": null,
|
| 25 |
-
"target_modules": [
|
| 26 |
-
"gate_proj",
|
| 27 |
-
"up_proj",
|
| 28 |
-
"v_proj",
|
| 29 |
-
"down_proj",
|
| 30 |
-
"q_proj",
|
| 31 |
-
"o_proj",
|
| 32 |
-
"k_proj"
|
| 33 |
-
],
|
| 34 |
-
"task_type": "CAUSAL_LM",
|
| 35 |
-
"use_dora": false,
|
| 36 |
-
"use_rslora": false
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-500/adapter_model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7b75ec8226cc85c56d6066121db706e256d1b468f6fb15600a56502dcdde1a8e
|
| 3 |
-
size 161533192
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-500/added_tokens.json
DELETED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"</tool_call>": 151658,
|
| 3 |
-
"<tool_call>": 151657,
|
| 4 |
-
"<|PAD_TOKEN|>": 151665,
|
| 5 |
-
"<|box_end|>": 151649,
|
| 6 |
-
"<|box_start|>": 151648,
|
| 7 |
-
"<|endoftext|>": 151643,
|
| 8 |
-
"<|file_sep|>": 151664,
|
| 9 |
-
"<|fim_middle|>": 151660,
|
| 10 |
-
"<|fim_pad|>": 151662,
|
| 11 |
-
"<|fim_prefix|>": 151659,
|
| 12 |
-
"<|fim_suffix|>": 151661,
|
| 13 |
-
"<|im_end|>": 151645,
|
| 14 |
-
"<|im_start|>": 151644,
|
| 15 |
-
"<|image_pad|>": 151655,
|
| 16 |
-
"<|object_ref_end|>": 151647,
|
| 17 |
-
"<|object_ref_start|>": 151646,
|
| 18 |
-
"<|quad_end|>": 151651,
|
| 19 |
-
"<|quad_start|>": 151650,
|
| 20 |
-
"<|repo_name|>": 151663,
|
| 21 |
-
"<|video_pad|>": 151656,
|
| 22 |
-
"<|vision_end|>": 151653,
|
| 23 |
-
"<|vision_pad|>": 151654,
|
| 24 |
-
"<|vision_start|>": 151652
|
| 25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-500/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-500/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:142ee6ad54fc8987bbe260c060a799175fe13737af353c5fbe279c8ed94b3506
|
| 3 |
-
size 82461044
|
|
|
|
|
|
|
|
|
|
|
|