Batch upload: checkpoint-1000 checkpoint-10000 checkpoint-100000 checkpoint-101000 checkpoint-102000 checkpoint-103000 checkpoint-104000 checkpoint-105000 checkpoint-106000 checkpoint-107000 checkpoint-108000 checkpoint-108168 checkpoint-11000 checkpoint-12000 checkpoint-13000 checkpoint-14000 checkpoint-15000 checkpoint-16000 checkpoint-17000 checkpoint-18000 checkpoint-19000 checkpoint-2000 checkpoint-20000 checkpoint-21000 checkpoint-22000 checkpoint-23000 checkpoint-24000 checkpoint-25000 checkpoint-26000 checkpoint-27000 checkpoint-28000 checkpoint-29000 checkpoint-3000 checkpoint-30000 checkpoint-31000 checkpoint-32000 checkpoint-33000 checkpoint-34000 checkpoint-35000 checkpoint-36000 checkpoint-37000 checkpoint-38000 checkpoint-39000 checkpoint-4000 checkpoint-40000 checkpoint-41000 checkpoint-42000 checkpoint-43000 checkpoint-44000 checkpoint-45000
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- checkpoint-1000/README.md +202 -0
- checkpoint-1000/adapter_config.json +34 -0
- checkpoint-1000/adapter_model.safetensors +3 -0
- checkpoint-1000/added_tokens.json +24 -0
- checkpoint-1000/merges.txt +0 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +31 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +207 -0
- checkpoint-1000/trainer_state.json +181 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1000/vocab.json +0 -0
- checkpoint-10000/README.md +202 -0
- checkpoint-10000/adapter_config.json +34 -0
- checkpoint-10000/adapter_model.safetensors +3 -0
- checkpoint-10000/added_tokens.json +24 -0
- checkpoint-10000/merges.txt +0 -0
- checkpoint-10000/optimizer.pt +3 -0
- checkpoint-10000/rng_state.pth +3 -0
- checkpoint-10000/scheduler.pt +3 -0
- checkpoint-10000/special_tokens_map.json +31 -0
- checkpoint-10000/tokenizer.json +0 -0
- checkpoint-10000/tokenizer_config.json +207 -0
- checkpoint-10000/trainer_state.json +1513 -0
- checkpoint-10000/training_args.bin +3 -0
- checkpoint-10000/vocab.json +0 -0
- checkpoint-100000/README.md +202 -0
- checkpoint-100000/adapter_config.json +34 -0
- checkpoint-100000/adapter_model.safetensors +3 -0
- checkpoint-100000/added_tokens.json +24 -0
- checkpoint-100000/merges.txt +0 -0
- checkpoint-100000/optimizer.pt +3 -0
- checkpoint-100000/rng_state.pth +3 -0
- checkpoint-100000/scheduler.pt +3 -0
- checkpoint-100000/special_tokens_map.json +31 -0
- checkpoint-100000/tokenizer.json +0 -0
- checkpoint-100000/tokenizer_config.json +207 -0
- checkpoint-100000/trainer_state.json +0 -0
- checkpoint-100000/training_args.bin +3 -0
- checkpoint-100000/vocab.json +0 -0
- checkpoint-101000/README.md +202 -0
- checkpoint-101000/adapter_config.json +34 -0
- checkpoint-101000/adapter_model.safetensors +3 -0
- checkpoint-101000/added_tokens.json +24 -0
- checkpoint-101000/merges.txt +0 -0
- checkpoint-101000/optimizer.pt +3 -0
- checkpoint-101000/rng_state.pth +3 -0
- checkpoint-101000/scheduler.pt +3 -0
checkpoint-1000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-0.5B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-1000/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-1000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d0f65c41d08fa4d4863948bc82f64633161640733c4b1b468893122b579f1f2
|
| 3 |
+
size 35237104
|
checkpoint-1000/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-1000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ff6ad3cd0439c1d789571f2cd1c6bf55e7f1cc9a82ca2945e3922244b7c30b6
|
| 3 |
+
size 70667778
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67c15fc23e0ef69d5e4826db880ea884dae1fba42ab4cc76a66b49ba792d4953
|
| 3 |
+
size 14244
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:430c7b0d8be62cd36ca0d3ffcd4b3e719e4c633121d2f3915be116aeffd29e7c
|
| 3 |
+
size 1064
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.02773453886128917,
|
| 5 |
+
"eval_steps": 1000,
|
| 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": 0.0013867269430644586,
|
| 13 |
+
"grad_norm": 1.8933687210083008,
|
| 14 |
+
"learning_rate": 2.957486136783734e-06,
|
| 15 |
+
"loss": 1.2241,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002773453886128917,
|
| 20 |
+
"grad_norm": 0.7502820491790771,
|
| 21 |
+
"learning_rate": 6.038200862600124e-06,
|
| 22 |
+
"loss": 1.0267,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.004160180829193376,
|
| 27 |
+
"grad_norm": 0.5821689963340759,
|
| 28 |
+
"learning_rate": 9.118915588416513e-06,
|
| 29 |
+
"loss": 0.8167,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.005546907772257834,
|
| 34 |
+
"grad_norm": 0.5138927698135376,
|
| 35 |
+
"learning_rate": 1.2199630314232902e-05,
|
| 36 |
+
"loss": 0.6408,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.006933634715322293,
|
| 41 |
+
"grad_norm": 0.619263768196106,
|
| 42 |
+
"learning_rate": 1.5280345040049293e-05,
|
| 43 |
+
"loss": 0.5468,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.008320361658386751,
|
| 48 |
+
"grad_norm": 0.5078439712524414,
|
| 49 |
+
"learning_rate": 1.836105976586568e-05,
|
| 50 |
+
"loss": 0.4952,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.00970708860145121,
|
| 55 |
+
"grad_norm": 0.5653749108314514,
|
| 56 |
+
"learning_rate": 2.144177449168207e-05,
|
| 57 |
+
"loss": 0.4388,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.011093815544515669,
|
| 62 |
+
"grad_norm": 0.6189213991165161,
|
| 63 |
+
"learning_rate": 2.452248921749846e-05,
|
| 64 |
+
"loss": 0.4232,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.012480542487580126,
|
| 69 |
+
"grad_norm": 0.6082913875579834,
|
| 70 |
+
"learning_rate": 2.760320394331485e-05,
|
| 71 |
+
"loss": 0.401,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.013867269430644586,
|
| 76 |
+
"grad_norm": 0.6956301331520081,
|
| 77 |
+
"learning_rate": 3.068391866913124e-05,
|
| 78 |
+
"loss": 0.3895,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.015253996373709043,
|
| 83 |
+
"grad_norm": 0.7030412554740906,
|
| 84 |
+
"learning_rate": 3.3764633394947633e-05,
|
| 85 |
+
"loss": 0.3676,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.016640723316773503,
|
| 90 |
+
"grad_norm": 0.6779190897941589,
|
| 91 |
+
"learning_rate": 3.684534812076402e-05,
|
| 92 |
+
"loss": 0.3653,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.01802745025983796,
|
| 97 |
+
"grad_norm": 0.8930213451385498,
|
| 98 |
+
"learning_rate": 3.992606284658041e-05,
|
| 99 |
+
"loss": 0.3645,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.01941417720290242,
|
| 104 |
+
"grad_norm": 0.6423994302749634,
|
| 105 |
+
"learning_rate": 4.30067775723968e-05,
|
| 106 |
+
"loss": 0.3514,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.02080090414596688,
|
| 111 |
+
"grad_norm": 0.7728660106658936,
|
| 112 |
+
"learning_rate": 4.608749229821319e-05,
|
| 113 |
+
"loss": 0.3468,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.022187631089031337,
|
| 118 |
+
"grad_norm": 0.7561061978340149,
|
| 119 |
+
"learning_rate": 4.916820702402958e-05,
|
| 120 |
+
"loss": 0.3499,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.023574358032095795,
|
| 125 |
+
"grad_norm": 0.6163890957832336,
|
| 126 |
+
"learning_rate": 5.224892174984597e-05,
|
| 127 |
+
"loss": 0.3417,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.024961084975160253,
|
| 132 |
+
"grad_norm": 0.7334563732147217,
|
| 133 |
+
"learning_rate": 5.532963647566236e-05,
|
| 134 |
+
"loss": 0.3299,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.026347811918224714,
|
| 139 |
+
"grad_norm": 0.655237078666687,
|
| 140 |
+
"learning_rate": 5.841035120147874e-05,
|
| 141 |
+
"loss": 0.3306,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.02773453886128917,
|
| 146 |
+
"grad_norm": 0.8147113919258118,
|
| 147 |
+
"learning_rate": 6.149106592729513e-05,
|
| 148 |
+
"loss": 0.3281,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.02773453886128917,
|
| 153 |
+
"eval_loss": 0.32194069027900696,
|
| 154 |
+
"eval_runtime": 501.2457,
|
| 155 |
+
"eval_samples_per_second": 5.7,
|
| 156 |
+
"eval_steps_per_second": 5.7,
|
| 157 |
+
"step": 1000
|
| 158 |
+
}
|
| 159 |
+
],
|
| 160 |
+
"logging_steps": 50,
|
| 161 |
+
"max_steps": 108168,
|
| 162 |
+
"num_input_tokens_seen": 0,
|
| 163 |
+
"num_train_epochs": 3,
|
| 164 |
+
"save_steps": 1000,
|
| 165 |
+
"stateful_callbacks": {
|
| 166 |
+
"TrainerControl": {
|
| 167 |
+
"args": {
|
| 168 |
+
"should_epoch_stop": false,
|
| 169 |
+
"should_evaluate": false,
|
| 170 |
+
"should_log": false,
|
| 171 |
+
"should_save": true,
|
| 172 |
+
"should_training_stop": false
|
| 173 |
+
},
|
| 174 |
+
"attributes": {}
|
| 175 |
+
}
|
| 176 |
+
},
|
| 177 |
+
"total_flos": 1.802385752064e+16,
|
| 178 |
+
"train_batch_size": 1,
|
| 179 |
+
"trial_name": null,
|
| 180 |
+
"trial_params": null
|
| 181 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e593d4080c231741ba3acb7aa362bf85842c0c2beaca29489d434eca5cc7fa0
|
| 3 |
+
size 5432
|
checkpoint-1000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-0.5B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-10000/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-10000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8388c74c627a1d4b1598c16d860bc46e2549ecae8baa506fdeb87d3453ed311d
|
| 3 |
+
size 35237104
|
checkpoint-10000/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-10000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7e049b89765e9a37930bebf3a5be684170c214ca657ed3dae2c97ceee36ee0e
|
| 3 |
+
size 70667778
|
checkpoint-10000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edc8f9131d4d1c2a3fb07a9d3ef9b3ece7220bb4f3a2a5762f9ad2f9635dbc3c
|
| 3 |
+
size 14244
|
checkpoint-10000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97fefaec88ab34fa963e63591c6f53ba9a4a528c387c8d03a9a416316b7d69fe
|
| 3 |
+
size 1064
|
checkpoint-10000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-10000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
checkpoint-10000/trainer_state.json
ADDED
|
@@ -0,0 +1,1513 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2773453886128917,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 10000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0013867269430644586,
|
| 13 |
+
"grad_norm": 1.8933687210083008,
|
| 14 |
+
"learning_rate": 2.957486136783734e-06,
|
| 15 |
+
"loss": 1.2241,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002773453886128917,
|
| 20 |
+
"grad_norm": 0.7502820491790771,
|
| 21 |
+
"learning_rate": 6.038200862600124e-06,
|
| 22 |
+
"loss": 1.0267,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.004160180829193376,
|
| 27 |
+
"grad_norm": 0.5821689963340759,
|
| 28 |
+
"learning_rate": 9.118915588416513e-06,
|
| 29 |
+
"loss": 0.8167,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.005546907772257834,
|
| 34 |
+
"grad_norm": 0.5138927698135376,
|
| 35 |
+
"learning_rate": 1.2199630314232902e-05,
|
| 36 |
+
"loss": 0.6408,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.006933634715322293,
|
| 41 |
+
"grad_norm": 0.619263768196106,
|
| 42 |
+
"learning_rate": 1.5280345040049293e-05,
|
| 43 |
+
"loss": 0.5468,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.008320361658386751,
|
| 48 |
+
"grad_norm": 0.5078439712524414,
|
| 49 |
+
"learning_rate": 1.836105976586568e-05,
|
| 50 |
+
"loss": 0.4952,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.00970708860145121,
|
| 55 |
+
"grad_norm": 0.5653749108314514,
|
| 56 |
+
"learning_rate": 2.144177449168207e-05,
|
| 57 |
+
"loss": 0.4388,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.011093815544515669,
|
| 62 |
+
"grad_norm": 0.6189213991165161,
|
| 63 |
+
"learning_rate": 2.452248921749846e-05,
|
| 64 |
+
"loss": 0.4232,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.012480542487580126,
|
| 69 |
+
"grad_norm": 0.6082913875579834,
|
| 70 |
+
"learning_rate": 2.760320394331485e-05,
|
| 71 |
+
"loss": 0.401,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.013867269430644586,
|
| 76 |
+
"grad_norm": 0.6956301331520081,
|
| 77 |
+
"learning_rate": 3.068391866913124e-05,
|
| 78 |
+
"loss": 0.3895,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.015253996373709043,
|
| 83 |
+
"grad_norm": 0.7030412554740906,
|
| 84 |
+
"learning_rate": 3.3764633394947633e-05,
|
| 85 |
+
"loss": 0.3676,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.016640723316773503,
|
| 90 |
+
"grad_norm": 0.6779190897941589,
|
| 91 |
+
"learning_rate": 3.684534812076402e-05,
|
| 92 |
+
"loss": 0.3653,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.01802745025983796,
|
| 97 |
+
"grad_norm": 0.8930213451385498,
|
| 98 |
+
"learning_rate": 3.992606284658041e-05,
|
| 99 |
+
"loss": 0.3645,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.01941417720290242,
|
| 104 |
+
"grad_norm": 0.6423994302749634,
|
| 105 |
+
"learning_rate": 4.30067775723968e-05,
|
| 106 |
+
"loss": 0.3514,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.02080090414596688,
|
| 111 |
+
"grad_norm": 0.7728660106658936,
|
| 112 |
+
"learning_rate": 4.608749229821319e-05,
|
| 113 |
+
"loss": 0.3468,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.022187631089031337,
|
| 118 |
+
"grad_norm": 0.7561061978340149,
|
| 119 |
+
"learning_rate": 4.916820702402958e-05,
|
| 120 |
+
"loss": 0.3499,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.023574358032095795,
|
| 125 |
+
"grad_norm": 0.6163890957832336,
|
| 126 |
+
"learning_rate": 5.224892174984597e-05,
|
| 127 |
+
"loss": 0.3417,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.024961084975160253,
|
| 132 |
+
"grad_norm": 0.7334563732147217,
|
| 133 |
+
"learning_rate": 5.532963647566236e-05,
|
| 134 |
+
"loss": 0.3299,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.026347811918224714,
|
| 139 |
+
"grad_norm": 0.655237078666687,
|
| 140 |
+
"learning_rate": 5.841035120147874e-05,
|
| 141 |
+
"loss": 0.3306,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.02773453886128917,
|
| 146 |
+
"grad_norm": 0.8147113919258118,
|
| 147 |
+
"learning_rate": 6.149106592729513e-05,
|
| 148 |
+
"loss": 0.3281,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.02773453886128917,
|
| 153 |
+
"eval_loss": 0.32194069027900696,
|
| 154 |
+
"eval_runtime": 501.2457,
|
| 155 |
+
"eval_samples_per_second": 5.7,
|
| 156 |
+
"eval_steps_per_second": 5.7,
|
| 157 |
+
"step": 1000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.02912126580435363,
|
| 161 |
+
"grad_norm": 0.6397083401679993,
|
| 162 |
+
"learning_rate": 6.457178065311152e-05,
|
| 163 |
+
"loss": 0.3204,
|
| 164 |
+
"step": 1050
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.030507992747418087,
|
| 168 |
+
"grad_norm": 0.5808627009391785,
|
| 169 |
+
"learning_rate": 6.765249537892791e-05,
|
| 170 |
+
"loss": 0.3229,
|
| 171 |
+
"step": 1100
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.03189471969048255,
|
| 175 |
+
"grad_norm": 0.6929567456245422,
|
| 176 |
+
"learning_rate": 7.073321010474431e-05,
|
| 177 |
+
"loss": 0.3148,
|
| 178 |
+
"step": 1150
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.033281446633547006,
|
| 182 |
+
"grad_norm": 0.620298445224762,
|
| 183 |
+
"learning_rate": 7.38139248305607e-05,
|
| 184 |
+
"loss": 0.32,
|
| 185 |
+
"step": 1200
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.034668173576611463,
|
| 189 |
+
"grad_norm": 0.5947968363761902,
|
| 190 |
+
"learning_rate": 7.689463955637708e-05,
|
| 191 |
+
"loss": 0.306,
|
| 192 |
+
"step": 1250
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.03605490051967592,
|
| 196 |
+
"grad_norm": 0.6097683906555176,
|
| 197 |
+
"learning_rate": 7.997535428219347e-05,
|
| 198 |
+
"loss": 0.3179,
|
| 199 |
+
"step": 1300
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.03744162746274038,
|
| 203 |
+
"grad_norm": 0.6339348554611206,
|
| 204 |
+
"learning_rate": 8.305606900800986e-05,
|
| 205 |
+
"loss": 0.3161,
|
| 206 |
+
"step": 1350
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.03882835440580484,
|
| 210 |
+
"grad_norm": 0.5278933644294739,
|
| 211 |
+
"learning_rate": 8.613678373382625e-05,
|
| 212 |
+
"loss": 0.3153,
|
| 213 |
+
"step": 1400
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.040215081348869294,
|
| 217 |
+
"grad_norm": 0.4927423894405365,
|
| 218 |
+
"learning_rate": 8.921749845964264e-05,
|
| 219 |
+
"loss": 0.3111,
|
| 220 |
+
"step": 1450
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.04160180829193376,
|
| 224 |
+
"grad_norm": 0.4745596945285797,
|
| 225 |
+
"learning_rate": 9.229821318545902e-05,
|
| 226 |
+
"loss": 0.304,
|
| 227 |
+
"step": 1500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.04298853523499822,
|
| 231 |
+
"grad_norm": 0.6532231569290161,
|
| 232 |
+
"learning_rate": 9.537892791127541e-05,
|
| 233 |
+
"loss": 0.3084,
|
| 234 |
+
"step": 1550
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.044375262178062674,
|
| 238 |
+
"grad_norm": 0.5528659820556641,
|
| 239 |
+
"learning_rate": 9.84596426370918e-05,
|
| 240 |
+
"loss": 0.3084,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.04576198912112713,
|
| 245 |
+
"grad_norm": 0.45793089270591736,
|
| 246 |
+
"learning_rate": 0.0001015403573629082,
|
| 247 |
+
"loss": 0.2964,
|
| 248 |
+
"step": 1650
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.04714871606419159,
|
| 252 |
+
"grad_norm": 0.5063529014587402,
|
| 253 |
+
"learning_rate": 0.00010462107208872458,
|
| 254 |
+
"loss": 0.2924,
|
| 255 |
+
"step": 1700
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.04853544300725605,
|
| 259 |
+
"grad_norm": 0.48600247502326965,
|
| 260 |
+
"learning_rate": 0.00010770178681454097,
|
| 261 |
+
"loss": 0.2947,
|
| 262 |
+
"step": 1750
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.049922169950320505,
|
| 266 |
+
"grad_norm": 0.4872143268585205,
|
| 267 |
+
"learning_rate": 0.00011078250154035737,
|
| 268 |
+
"loss": 0.297,
|
| 269 |
+
"step": 1800
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.05130889689338496,
|
| 273 |
+
"grad_norm": 0.5091805458068848,
|
| 274 |
+
"learning_rate": 0.00011386321626617376,
|
| 275 |
+
"loss": 0.2888,
|
| 276 |
+
"step": 1850
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.05269562383644943,
|
| 280 |
+
"grad_norm": 0.41649994254112244,
|
| 281 |
+
"learning_rate": 0.00011694393099199015,
|
| 282 |
+
"loss": 0.2871,
|
| 283 |
+
"step": 1900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.054082350779513885,
|
| 287 |
+
"grad_norm": 0.5174862146377563,
|
| 288 |
+
"learning_rate": 0.00012002464571780654,
|
| 289 |
+
"loss": 0.2922,
|
| 290 |
+
"step": 1950
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.05546907772257834,
|
| 294 |
+
"grad_norm": 0.45786553621292114,
|
| 295 |
+
"learning_rate": 0.00012310536044362293,
|
| 296 |
+
"loss": 0.2883,
|
| 297 |
+
"step": 2000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.05546907772257834,
|
| 301 |
+
"eval_loss": 0.28488224744796753,
|
| 302 |
+
"eval_runtime": 500.9558,
|
| 303 |
+
"eval_samples_per_second": 5.703,
|
| 304 |
+
"eval_steps_per_second": 5.703,
|
| 305 |
+
"step": 2000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.0568558046656428,
|
| 309 |
+
"grad_norm": 0.4992533326148987,
|
| 310 |
+
"learning_rate": 0.00012606284658040666,
|
| 311 |
+
"loss": 0.3033,
|
| 312 |
+
"step": 2050
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.05824253160870726,
|
| 316 |
+
"grad_norm": 0.4205988049507141,
|
| 317 |
+
"learning_rate": 0.00012914356130622304,
|
| 318 |
+
"loss": 0.2867,
|
| 319 |
+
"step": 2100
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.059629258551771716,
|
| 323 |
+
"grad_norm": 0.4288152754306793,
|
| 324 |
+
"learning_rate": 0.00013222427603203944,
|
| 325 |
+
"loss": 0.2795,
|
| 326 |
+
"step": 2150
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.061015985494836174,
|
| 330 |
+
"grad_norm": 0.4856145977973938,
|
| 331 |
+
"learning_rate": 0.00013530499075785582,
|
| 332 |
+
"loss": 0.2833,
|
| 333 |
+
"step": 2200
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.06240271243790063,
|
| 337 |
+
"grad_norm": 0.4891654849052429,
|
| 338 |
+
"learning_rate": 0.00013838570548367222,
|
| 339 |
+
"loss": 0.2797,
|
| 340 |
+
"step": 2250
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.0637894393809651,
|
| 344 |
+
"grad_norm": 0.39899352192878723,
|
| 345 |
+
"learning_rate": 0.00014146642020948863,
|
| 346 |
+
"loss": 0.2785,
|
| 347 |
+
"step": 2300
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.06517616632402955,
|
| 351 |
+
"grad_norm": 0.3616255819797516,
|
| 352 |
+
"learning_rate": 0.000144547134935305,
|
| 353 |
+
"loss": 0.2798,
|
| 354 |
+
"step": 2350
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.06656289326709401,
|
| 358 |
+
"grad_norm": 0.3556617498397827,
|
| 359 |
+
"learning_rate": 0.0001476278496611214,
|
| 360 |
+
"loss": 0.2811,
|
| 361 |
+
"step": 2400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.06794962021015846,
|
| 365 |
+
"grad_norm": 0.39639297127723694,
|
| 366 |
+
"learning_rate": 0.00015070856438693776,
|
| 367 |
+
"loss": 0.2813,
|
| 368 |
+
"step": 2450
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.06933634715322293,
|
| 372 |
+
"grad_norm": 0.35177573561668396,
|
| 373 |
+
"learning_rate": 0.00015378927911275416,
|
| 374 |
+
"loss": 0.2797,
|
| 375 |
+
"step": 2500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.07072307409628739,
|
| 379 |
+
"grad_norm": 0.38610222935676575,
|
| 380 |
+
"learning_rate": 0.00015686999383857054,
|
| 381 |
+
"loss": 0.2747,
|
| 382 |
+
"step": 2550
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.07210980103935184,
|
| 386 |
+
"grad_norm": 0.36727309226989746,
|
| 387 |
+
"learning_rate": 0.00015995070856438694,
|
| 388 |
+
"loss": 0.2776,
|
| 389 |
+
"step": 2600
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.07349652798241631,
|
| 393 |
+
"grad_norm": 0.3905107378959656,
|
| 394 |
+
"learning_rate": 0.00016303142329020332,
|
| 395 |
+
"loss": 0.2772,
|
| 396 |
+
"step": 2650
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.07488325492548076,
|
| 400 |
+
"grad_norm": 0.3958912193775177,
|
| 401 |
+
"learning_rate": 0.00016611213801601973,
|
| 402 |
+
"loss": 0.2707,
|
| 403 |
+
"step": 2700
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.07626998186854522,
|
| 407 |
+
"grad_norm": 0.4029497504234314,
|
| 408 |
+
"learning_rate": 0.0001691928527418361,
|
| 409 |
+
"loss": 0.2692,
|
| 410 |
+
"step": 2750
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.07765670881160967,
|
| 414 |
+
"grad_norm": 0.3514055907726288,
|
| 415 |
+
"learning_rate": 0.0001722735674676525,
|
| 416 |
+
"loss": 0.2759,
|
| 417 |
+
"step": 2800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.07904343575467414,
|
| 421 |
+
"grad_norm": 0.34912553429603577,
|
| 422 |
+
"learning_rate": 0.00017529266789895255,
|
| 423 |
+
"loss": 0.2793,
|
| 424 |
+
"step": 2850
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.08043016269773859,
|
| 428 |
+
"grad_norm": 0.3493233621120453,
|
| 429 |
+
"learning_rate": 0.00017831176833025262,
|
| 430 |
+
"loss": 0.2845,
|
| 431 |
+
"step": 2900
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.08181688964080305,
|
| 435 |
+
"grad_norm": 0.30080145597457886,
|
| 436 |
+
"learning_rate": 0.00018139248305606902,
|
| 437 |
+
"loss": 0.2686,
|
| 438 |
+
"step": 2950
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.08320361658386752,
|
| 442 |
+
"grad_norm": 0.3265998959541321,
|
| 443 |
+
"learning_rate": 0.0001844731977818854,
|
| 444 |
+
"loss": 0.2695,
|
| 445 |
+
"step": 3000
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.08320361658386752,
|
| 449 |
+
"eval_loss": 0.26523345708847046,
|
| 450 |
+
"eval_runtime": 500.4565,
|
| 451 |
+
"eval_samples_per_second": 5.709,
|
| 452 |
+
"eval_steps_per_second": 5.709,
|
| 453 |
+
"step": 3000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.08459034352693197,
|
| 457 |
+
"grad_norm": 0.29866209626197815,
|
| 458 |
+
"learning_rate": 0.0001875539125077018,
|
| 459 |
+
"loss": 0.2679,
|
| 460 |
+
"step": 3050
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.08597707046999643,
|
| 464 |
+
"grad_norm": 0.3191625475883484,
|
| 465 |
+
"learning_rate": 0.00019063462723351818,
|
| 466 |
+
"loss": 0.267,
|
| 467 |
+
"step": 3100
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.08736379741306088,
|
| 471 |
+
"grad_norm": 0.3110339939594269,
|
| 472 |
+
"learning_rate": 0.00019371534195933459,
|
| 473 |
+
"loss": 0.2658,
|
| 474 |
+
"step": 3150
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.08875052435612535,
|
| 478 |
+
"grad_norm": 0.32120850682258606,
|
| 479 |
+
"learning_rate": 0.00019679605668515096,
|
| 480 |
+
"loss": 0.2724,
|
| 481 |
+
"step": 3200
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.0901372512991898,
|
| 485 |
+
"grad_norm": 0.28446418046951294,
|
| 486 |
+
"learning_rate": 0.00019987677141096734,
|
| 487 |
+
"loss": 0.268,
|
| 488 |
+
"step": 3250
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.09152397824225426,
|
| 492 |
+
"grad_norm": 0.2722443640232086,
|
| 493 |
+
"learning_rate": 0.00019999989671933422,
|
| 494 |
+
"loss": 0.2716,
|
| 495 |
+
"step": 3300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.09291070518531871,
|
| 499 |
+
"grad_norm": 0.31304416060447693,
|
| 500 |
+
"learning_rate": 0.00019999956948482068,
|
| 501 |
+
"loss": 0.2631,
|
| 502 |
+
"step": 3350
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.09429743212838318,
|
| 506 |
+
"grad_norm": 0.2516928017139435,
|
| 507 |
+
"learning_rate": 0.00019999901811788604,
|
| 508 |
+
"loss": 0.2647,
|
| 509 |
+
"step": 3400
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.09568415907144764,
|
| 513 |
+
"grad_norm": 0.288006067276001,
|
| 514 |
+
"learning_rate": 0.00019999824261976613,
|
| 515 |
+
"loss": 0.263,
|
| 516 |
+
"step": 3450
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.0970708860145121,
|
| 520 |
+
"grad_norm": 0.2745107114315033,
|
| 521 |
+
"learning_rate": 0.00019999724299219913,
|
| 522 |
+
"loss": 0.2642,
|
| 523 |
+
"step": 3500
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.09845761295757656,
|
| 527 |
+
"grad_norm": 2.800987720489502,
|
| 528 |
+
"learning_rate": 0.00019999601923742548,
|
| 529 |
+
"loss": 0.7176,
|
| 530 |
+
"step": 3550
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.09984433990064101,
|
| 534 |
+
"grad_norm": 0.3590925931930542,
|
| 535 |
+
"learning_rate": 0.00019999457135818805,
|
| 536 |
+
"loss": 0.3146,
|
| 537 |
+
"step": 3600
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.10123106684370548,
|
| 541 |
+
"grad_norm": 0.32617494463920593,
|
| 542 |
+
"learning_rate": 0.00019999289935773202,
|
| 543 |
+
"loss": 0.2786,
|
| 544 |
+
"step": 3650
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.10261779378676993,
|
| 548 |
+
"grad_norm": 0.3239264488220215,
|
| 549 |
+
"learning_rate": 0.0001999910032398049,
|
| 550 |
+
"loss": 0.2807,
|
| 551 |
+
"step": 3700
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.10400452072983439,
|
| 555 |
+
"grad_norm": 0.3022274076938629,
|
| 556 |
+
"learning_rate": 0.00019998888300865652,
|
| 557 |
+
"loss": 0.2758,
|
| 558 |
+
"step": 3750
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.10539124767289886,
|
| 562 |
+
"grad_norm": 0.33024862408638,
|
| 563 |
+
"learning_rate": 0.000199986538669039,
|
| 564 |
+
"loss": 0.2687,
|
| 565 |
+
"step": 3800
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.1067779746159633,
|
| 569 |
+
"grad_norm": 0.6899451017379761,
|
| 570 |
+
"learning_rate": 0.00019998397022620687,
|
| 571 |
+
"loss": 0.2699,
|
| 572 |
+
"step": 3850
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.10816470155902777,
|
| 576 |
+
"grad_norm": 0.2794604003429413,
|
| 577 |
+
"learning_rate": 0.0001999811776859168,
|
| 578 |
+
"loss": 0.2667,
|
| 579 |
+
"step": 3900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.10955142850209222,
|
| 583 |
+
"grad_norm": 0.2764255106449127,
|
| 584 |
+
"learning_rate": 0.00019997816105442778,
|
| 585 |
+
"loss": 0.2658,
|
| 586 |
+
"step": 3950
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.11093815544515669,
|
| 590 |
+
"grad_norm": 0.43574222922325134,
|
| 591 |
+
"learning_rate": 0.0001999749203385012,
|
| 592 |
+
"loss": 0.2664,
|
| 593 |
+
"step": 4000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.11093815544515669,
|
| 597 |
+
"eval_loss": 0.26065966486930847,
|
| 598 |
+
"eval_runtime": 500.842,
|
| 599 |
+
"eval_samples_per_second": 5.704,
|
| 600 |
+
"eval_steps_per_second": 5.704,
|
| 601 |
+
"step": 4000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.11232488238822114,
|
| 605 |
+
"grad_norm": 0.5340762734413147,
|
| 606 |
+
"learning_rate": 0.00019997145554540046,
|
| 607 |
+
"loss": 0.272,
|
| 608 |
+
"step": 4050
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.1137116093312856,
|
| 612 |
+
"grad_norm": 0.32403895258903503,
|
| 613 |
+
"learning_rate": 0.00019996776668289136,
|
| 614 |
+
"loss": 0.2679,
|
| 615 |
+
"step": 4100
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.11509833627435005,
|
| 619 |
+
"grad_norm": 0.2928290367126465,
|
| 620 |
+
"learning_rate": 0.0001999638537592419,
|
| 621 |
+
"loss": 0.2624,
|
| 622 |
+
"step": 4150
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.11648506321741452,
|
| 626 |
+
"grad_norm": 0.23226021230220795,
|
| 627 |
+
"learning_rate": 0.00019995971678322228,
|
| 628 |
+
"loss": 0.2557,
|
| 629 |
+
"step": 4200
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.11787179016047898,
|
| 633 |
+
"grad_norm": 0.2748055160045624,
|
| 634 |
+
"learning_rate": 0.00019995535576410476,
|
| 635 |
+
"loss": 0.2625,
|
| 636 |
+
"step": 4250
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.11925851710354343,
|
| 640 |
+
"grad_norm": 0.2713299095630646,
|
| 641 |
+
"learning_rate": 0.00019995077071166385,
|
| 642 |
+
"loss": 0.2611,
|
| 643 |
+
"step": 4300
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.1206452440466079,
|
| 647 |
+
"grad_norm": 0.24674977362155914,
|
| 648 |
+
"learning_rate": 0.00019994596163617624,
|
| 649 |
+
"loss": 0.2647,
|
| 650 |
+
"step": 4350
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.12203197098967235,
|
| 654 |
+
"grad_norm": 0.359017014503479,
|
| 655 |
+
"learning_rate": 0.00019994092854842065,
|
| 656 |
+
"loss": 0.2601,
|
| 657 |
+
"step": 4400
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.12341869793273681,
|
| 661 |
+
"grad_norm": 0.38051414489746094,
|
| 662 |
+
"learning_rate": 0.00019993567145967791,
|
| 663 |
+
"loss": 0.253,
|
| 664 |
+
"step": 4450
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.12480542487580126,
|
| 668 |
+
"grad_norm": 0.26227161288261414,
|
| 669 |
+
"learning_rate": 0.0001999301903817309,
|
| 670 |
+
"loss": 0.2584,
|
| 671 |
+
"step": 4500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.12619215181886573,
|
| 675 |
+
"grad_norm": 0.21259668469429016,
|
| 676 |
+
"learning_rate": 0.00019992448532686453,
|
| 677 |
+
"loss": 0.2618,
|
| 678 |
+
"step": 4550
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.1275788787619302,
|
| 682 |
+
"grad_norm": 0.23226451873779297,
|
| 683 |
+
"learning_rate": 0.0001999185563078658,
|
| 684 |
+
"loss": 0.2526,
|
| 685 |
+
"step": 4600
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.12896560570499466,
|
| 689 |
+
"grad_norm": 0.24459871649742126,
|
| 690 |
+
"learning_rate": 0.00019991240333802352,
|
| 691 |
+
"loss": 0.2523,
|
| 692 |
+
"step": 4650
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.1303523326480591,
|
| 696 |
+
"grad_norm": 0.29185208678245544,
|
| 697 |
+
"learning_rate": 0.00019990602643112863,
|
| 698 |
+
"loss": 0.2546,
|
| 699 |
+
"step": 4700
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.13173905959112356,
|
| 703 |
+
"grad_norm": 0.23443324863910675,
|
| 704 |
+
"learning_rate": 0.00019989942560147387,
|
| 705 |
+
"loss": 0.2557,
|
| 706 |
+
"step": 4750
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.13312578653418802,
|
| 710 |
+
"grad_norm": 0.22915039956569672,
|
| 711 |
+
"learning_rate": 0.00019989260086385394,
|
| 712 |
+
"loss": 0.2546,
|
| 713 |
+
"step": 4800
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.1345125134772525,
|
| 717 |
+
"grad_norm": 0.2710748016834259,
|
| 718 |
+
"learning_rate": 0.00019988555223356531,
|
| 719 |
+
"loss": 0.2619,
|
| 720 |
+
"step": 4850
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.13589924042031692,
|
| 724 |
+
"grad_norm": 0.24671098589897156,
|
| 725 |
+
"learning_rate": 0.00019987827972640633,
|
| 726 |
+
"loss": 0.2594,
|
| 727 |
+
"step": 4900
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.1372859673633814,
|
| 731 |
+
"grad_norm": 0.2359282672405243,
|
| 732 |
+
"learning_rate": 0.00019987078335867713,
|
| 733 |
+
"loss": 0.2616,
|
| 734 |
+
"step": 4950
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.13867269430644585,
|
| 738 |
+
"grad_norm": 0.2197064608335495,
|
| 739 |
+
"learning_rate": 0.00019986306314717956,
|
| 740 |
+
"loss": 0.2507,
|
| 741 |
+
"step": 5000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.13867269430644585,
|
| 745 |
+
"eval_loss": 0.25083017349243164,
|
| 746 |
+
"eval_runtime": 500.7995,
|
| 747 |
+
"eval_samples_per_second": 5.705,
|
| 748 |
+
"eval_steps_per_second": 5.705,
|
| 749 |
+
"step": 5000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.14005942124951032,
|
| 753 |
+
"grad_norm": 0.2249370515346527,
|
| 754 |
+
"learning_rate": 0.0001998551191092172,
|
| 755 |
+
"loss": 0.2574,
|
| 756 |
+
"step": 5050
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.14144614819257478,
|
| 760 |
+
"grad_norm": 0.36345556378364563,
|
| 761 |
+
"learning_rate": 0.0001998469512625953,
|
| 762 |
+
"loss": 0.2493,
|
| 763 |
+
"step": 5100
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.14283287513563922,
|
| 767 |
+
"grad_norm": 0.24807791411876678,
|
| 768 |
+
"learning_rate": 0.00019983855962562067,
|
| 769 |
+
"loss": 0.2542,
|
| 770 |
+
"step": 5150
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.14421960207870368,
|
| 774 |
+
"grad_norm": 3.6125738620758057,
|
| 775 |
+
"learning_rate": 0.00019982994421710186,
|
| 776 |
+
"loss": 0.2595,
|
| 777 |
+
"step": 5200
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.14560632902176815,
|
| 781 |
+
"grad_norm": 0.4985048472881317,
|
| 782 |
+
"learning_rate": 0.0001998211050563488,
|
| 783 |
+
"loss": 0.2558,
|
| 784 |
+
"step": 5250
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.14699305596483261,
|
| 788 |
+
"grad_norm": 0.3320443332195282,
|
| 789 |
+
"learning_rate": 0.00019981204216317308,
|
| 790 |
+
"loss": 0.2545,
|
| 791 |
+
"step": 5300
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.14837978290789705,
|
| 795 |
+
"grad_norm": 0.2081877887248993,
|
| 796 |
+
"learning_rate": 0.00019980275555788759,
|
| 797 |
+
"loss": 0.2536,
|
| 798 |
+
"step": 5350
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.14976650985096152,
|
| 802 |
+
"grad_norm": 0.27258801460266113,
|
| 803 |
+
"learning_rate": 0.00019979324526130676,
|
| 804 |
+
"loss": 0.2505,
|
| 805 |
+
"step": 5400
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.15115323679402598,
|
| 809 |
+
"grad_norm": 0.23199999332427979,
|
| 810 |
+
"learning_rate": 0.00019978351129474632,
|
| 811 |
+
"loss": 0.2556,
|
| 812 |
+
"step": 5450
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.15253996373709044,
|
| 816 |
+
"grad_norm": 0.20929445326328278,
|
| 817 |
+
"learning_rate": 0.00019977355368002334,
|
| 818 |
+
"loss": 0.2486,
|
| 819 |
+
"step": 5500
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.1539266906801549,
|
| 823 |
+
"grad_norm": 0.23551955819129944,
|
| 824 |
+
"learning_rate": 0.00019976337243945617,
|
| 825 |
+
"loss": 0.2517,
|
| 826 |
+
"step": 5550
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.15531341762321935,
|
| 830 |
+
"grad_norm": 0.30231812596321106,
|
| 831 |
+
"learning_rate": 0.0001997529675958644,
|
| 832 |
+
"loss": 0.2498,
|
| 833 |
+
"step": 5600
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.1567001445662838,
|
| 837 |
+
"grad_norm": 0.24430635571479797,
|
| 838 |
+
"learning_rate": 0.00019974233917256865,
|
| 839 |
+
"loss": 0.2523,
|
| 840 |
+
"step": 5650
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.15808687150934828,
|
| 844 |
+
"grad_norm": 6.362756252288818,
|
| 845 |
+
"learning_rate": 0.0001997314871933909,
|
| 846 |
+
"loss": 0.2529,
|
| 847 |
+
"step": 5700
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.15947359845241274,
|
| 851 |
+
"grad_norm": 0.2339017242193222,
|
| 852 |
+
"learning_rate": 0.00019972041168265397,
|
| 853 |
+
"loss": 0.2524,
|
| 854 |
+
"step": 5750
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.16086032539547718,
|
| 858 |
+
"grad_norm": 0.22503100335597992,
|
| 859 |
+
"learning_rate": 0.0001997091126651818,
|
| 860 |
+
"loss": 0.251,
|
| 861 |
+
"step": 5800
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.16224705233854164,
|
| 865 |
+
"grad_norm": 0.26495125889778137,
|
| 866 |
+
"learning_rate": 0.00019969759016629928,
|
| 867 |
+
"loss": 0.2517,
|
| 868 |
+
"step": 5850
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.1636337792816061,
|
| 872 |
+
"grad_norm": 0.25339657068252563,
|
| 873 |
+
"learning_rate": 0.00019968584421183212,
|
| 874 |
+
"loss": 0.2505,
|
| 875 |
+
"step": 5900
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.16502050622467057,
|
| 879 |
+
"grad_norm": 0.20266841351985931,
|
| 880 |
+
"learning_rate": 0.000199673874828107,
|
| 881 |
+
"loss": 0.2501,
|
| 882 |
+
"step": 5950
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.16640723316773504,
|
| 886 |
+
"grad_norm": 0.19285647571086884,
|
| 887 |
+
"learning_rate": 0.00019966168204195125,
|
| 888 |
+
"loss": 0.2445,
|
| 889 |
+
"step": 6000
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.16640723316773504,
|
| 893 |
+
"eval_loss": 0.24731825292110443,
|
| 894 |
+
"eval_runtime": 500.9495,
|
| 895 |
+
"eval_samples_per_second": 5.703,
|
| 896 |
+
"eval_steps_per_second": 5.703,
|
| 897 |
+
"step": 6000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.16779396011079947,
|
| 901 |
+
"grad_norm": 0.2121065855026245,
|
| 902 |
+
"learning_rate": 0.000199649265880693,
|
| 903 |
+
"loss": 0.2466,
|
| 904 |
+
"step": 6050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.16918068705386394,
|
| 908 |
+
"grad_norm": 0.2560518980026245,
|
| 909 |
+
"learning_rate": 0.000199636626372161,
|
| 910 |
+
"loss": 0.2572,
|
| 911 |
+
"step": 6100
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.1705674139969284,
|
| 915 |
+
"grad_norm": 0.22927352786064148,
|
| 916 |
+
"learning_rate": 0.00019962376354468466,
|
| 917 |
+
"loss": 0.2509,
|
| 918 |
+
"step": 6150
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.17195414093999287,
|
| 922 |
+
"grad_norm": 0.2201690673828125,
|
| 923 |
+
"learning_rate": 0.00019961067742709377,
|
| 924 |
+
"loss": 0.2501,
|
| 925 |
+
"step": 6200
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.1733408678830573,
|
| 929 |
+
"grad_norm": 0.23233374953269958,
|
| 930 |
+
"learning_rate": 0.0001995973680487188,
|
| 931 |
+
"loss": 0.2525,
|
| 932 |
+
"step": 6250
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.17472759482612177,
|
| 936 |
+
"grad_norm": 0.254256933927536,
|
| 937 |
+
"learning_rate": 0.00019958383543939041,
|
| 938 |
+
"loss": 0.2499,
|
| 939 |
+
"step": 6300
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.17611432176918623,
|
| 943 |
+
"grad_norm": 0.1754632294178009,
|
| 944 |
+
"learning_rate": 0.00019957007962943975,
|
| 945 |
+
"loss": 0.251,
|
| 946 |
+
"step": 6350
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.1775010487122507,
|
| 950 |
+
"grad_norm": 0.23628771305084229,
|
| 951 |
+
"learning_rate": 0.00019955610064969817,
|
| 952 |
+
"loss": 0.256,
|
| 953 |
+
"step": 6400
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.17888777565531516,
|
| 957 |
+
"grad_norm": 0.23698653280735016,
|
| 958 |
+
"learning_rate": 0.00019954189853149725,
|
| 959 |
+
"loss": 0.2474,
|
| 960 |
+
"step": 6450
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.1802745025983796,
|
| 964 |
+
"grad_norm": 0.27713823318481445,
|
| 965 |
+
"learning_rate": 0.00019952747330666867,
|
| 966 |
+
"loss": 0.2481,
|
| 967 |
+
"step": 6500
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.18166122954144406,
|
| 971 |
+
"grad_norm": 0.1710810512304306,
|
| 972 |
+
"learning_rate": 0.00019951282500754413,
|
| 973 |
+
"loss": 0.2564,
|
| 974 |
+
"step": 6550
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.18304795648450853,
|
| 978 |
+
"grad_norm": 0.21406157314777374,
|
| 979 |
+
"learning_rate": 0.00019949795366695544,
|
| 980 |
+
"loss": 0.2517,
|
| 981 |
+
"step": 6600
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.184434683427573,
|
| 985 |
+
"grad_norm": 0.20108449459075928,
|
| 986 |
+
"learning_rate": 0.00019948285931823415,
|
| 987 |
+
"loss": 0.2518,
|
| 988 |
+
"step": 6650
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.18582141037063743,
|
| 992 |
+
"grad_norm": 5.1352715492248535,
|
| 993 |
+
"learning_rate": 0.0001994675419952118,
|
| 994 |
+
"loss": 0.2546,
|
| 995 |
+
"step": 6700
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.1872081373137019,
|
| 999 |
+
"grad_norm": 0.22743810713291168,
|
| 1000 |
+
"learning_rate": 0.00019945200173221962,
|
| 1001 |
+
"loss": 0.2457,
|
| 1002 |
+
"step": 6750
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.18859486425676636,
|
| 1006 |
+
"grad_norm": 0.20475907623767853,
|
| 1007 |
+
"learning_rate": 0.0001994362385640885,
|
| 1008 |
+
"loss": 0.2529,
|
| 1009 |
+
"step": 6800
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.18998159119983082,
|
| 1013 |
+
"grad_norm": 0.22172316908836365,
|
| 1014 |
+
"learning_rate": 0.000199420252526149,
|
| 1015 |
+
"loss": 0.2554,
|
| 1016 |
+
"step": 6850
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.1913683181428953,
|
| 1020 |
+
"grad_norm": 2.967470407485962,
|
| 1021 |
+
"learning_rate": 0.0001994040436542311,
|
| 1022 |
+
"loss": 0.2555,
|
| 1023 |
+
"step": 6900
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.19275504508595973,
|
| 1027 |
+
"grad_norm": 0.23698735237121582,
|
| 1028 |
+
"learning_rate": 0.00019938761198466437,
|
| 1029 |
+
"loss": 0.2619,
|
| 1030 |
+
"step": 6950
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.1941417720290242,
|
| 1034 |
+
"grad_norm": 0.17891797423362732,
|
| 1035 |
+
"learning_rate": 0.0001993709575542776,
|
| 1036 |
+
"loss": 0.2464,
|
| 1037 |
+
"step": 7000
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.1941417720290242,
|
| 1041 |
+
"eval_loss": 0.24410127103328705,
|
| 1042 |
+
"eval_runtime": 500.8833,
|
| 1043 |
+
"eval_samples_per_second": 5.704,
|
| 1044 |
+
"eval_steps_per_second": 5.704,
|
| 1045 |
+
"step": 7000
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.19552849897208865,
|
| 1049 |
+
"grad_norm": 0.21030811965465546,
|
| 1050 |
+
"learning_rate": 0.00019935408040039901,
|
| 1051 |
+
"loss": 0.2517,
|
| 1052 |
+
"step": 7050
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.19691522591515312,
|
| 1056 |
+
"grad_norm": 0.1913098245859146,
|
| 1057 |
+
"learning_rate": 0.00019933698056085586,
|
| 1058 |
+
"loss": 0.249,
|
| 1059 |
+
"step": 7100
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.19830195285821758,
|
| 1063 |
+
"grad_norm": 0.2044433057308197,
|
| 1064 |
+
"learning_rate": 0.00019931965807397465,
|
| 1065 |
+
"loss": 0.2496,
|
| 1066 |
+
"step": 7150
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.19968867980128202,
|
| 1070 |
+
"grad_norm": 0.18698015809059143,
|
| 1071 |
+
"learning_rate": 0.00019930211297858078,
|
| 1072 |
+
"loss": 0.2537,
|
| 1073 |
+
"step": 7200
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.20107540674434649,
|
| 1077 |
+
"grad_norm": 0.22580522298812866,
|
| 1078 |
+
"learning_rate": 0.00019928434531399876,
|
| 1079 |
+
"loss": 0.2456,
|
| 1080 |
+
"step": 7250
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.20246213368741095,
|
| 1084 |
+
"grad_norm": 0.1749202162027359,
|
| 1085 |
+
"learning_rate": 0.00019926635512005183,
|
| 1086 |
+
"loss": 0.2504,
|
| 1087 |
+
"step": 7300
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.20384886063047541,
|
| 1091 |
+
"grad_norm": 0.2123364359140396,
|
| 1092 |
+
"learning_rate": 0.00019924814243706197,
|
| 1093 |
+
"loss": 0.2477,
|
| 1094 |
+
"step": 7350
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.20523558757353985,
|
| 1098 |
+
"grad_norm": 0.2234705090522766,
|
| 1099 |
+
"learning_rate": 0.00019922970730584997,
|
| 1100 |
+
"loss": 0.2457,
|
| 1101 |
+
"step": 7400
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.20662231451660432,
|
| 1105 |
+
"grad_norm": 0.20742256939411163,
|
| 1106 |
+
"learning_rate": 0.00019921104976773505,
|
| 1107 |
+
"loss": 0.249,
|
| 1108 |
+
"step": 7450
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.20800904145966878,
|
| 1112 |
+
"grad_norm": 0.18315458297729492,
|
| 1113 |
+
"learning_rate": 0.000199192169864535,
|
| 1114 |
+
"loss": 0.2459,
|
| 1115 |
+
"step": 7500
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.20939576840273325,
|
| 1119 |
+
"grad_norm": 0.19357183575630188,
|
| 1120 |
+
"learning_rate": 0.000199173067638566,
|
| 1121 |
+
"loss": 0.2439,
|
| 1122 |
+
"step": 7550
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.2107824953457977,
|
| 1126 |
+
"grad_norm": 0.2398926168680191,
|
| 1127 |
+
"learning_rate": 0.00019915374313264248,
|
| 1128 |
+
"loss": 0.2497,
|
| 1129 |
+
"step": 7600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.21216922228886215,
|
| 1133 |
+
"grad_norm": 0.20313721895217896,
|
| 1134 |
+
"learning_rate": 0.00019913419639007714,
|
| 1135 |
+
"loss": 0.2447,
|
| 1136 |
+
"step": 7650
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.2135559492319266,
|
| 1140 |
+
"grad_norm": 0.17255066335201263,
|
| 1141 |
+
"learning_rate": 0.00019911442745468075,
|
| 1142 |
+
"loss": 0.2447,
|
| 1143 |
+
"step": 7700
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.21494267617499108,
|
| 1147 |
+
"grad_norm": 0.19140756130218506,
|
| 1148 |
+
"learning_rate": 0.0001990944363707621,
|
| 1149 |
+
"loss": 0.2383,
|
| 1150 |
+
"step": 7750
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.21632940311805554,
|
| 1154 |
+
"grad_norm": 0.15212053060531616,
|
| 1155 |
+
"learning_rate": 0.00019907422318312783,
|
| 1156 |
+
"loss": 0.2485,
|
| 1157 |
+
"step": 7800
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.21771613006111998,
|
| 1161 |
+
"grad_norm": 0.1841588169336319,
|
| 1162 |
+
"learning_rate": 0.0001990537879370825,
|
| 1163 |
+
"loss": 0.2432,
|
| 1164 |
+
"step": 7850
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.21910285700418444,
|
| 1168 |
+
"grad_norm": 0.2013355791568756,
|
| 1169 |
+
"learning_rate": 0.00019903313067842833,
|
| 1170 |
+
"loss": 0.2431,
|
| 1171 |
+
"step": 7900
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.2204895839472489,
|
| 1175 |
+
"grad_norm": 0.17149454355239868,
|
| 1176 |
+
"learning_rate": 0.0001990122514534651,
|
| 1177 |
+
"loss": 0.247,
|
| 1178 |
+
"step": 7950
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.22187631089031337,
|
| 1182 |
+
"grad_norm": 0.24272453784942627,
|
| 1183 |
+
"learning_rate": 0.00019899115030899014,
|
| 1184 |
+
"loss": 0.2468,
|
| 1185 |
+
"step": 8000
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.22187631089031337,
|
| 1189 |
+
"eval_loss": 0.24099861085414886,
|
| 1190 |
+
"eval_runtime": 501.2129,
|
| 1191 |
+
"eval_samples_per_second": 5.7,
|
| 1192 |
+
"eval_steps_per_second": 5.7,
|
| 1193 |
+
"step": 8000
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.22326303783337784,
|
| 1197 |
+
"grad_norm": 0.2419915497303009,
|
| 1198 |
+
"learning_rate": 0.00019896982729229813,
|
| 1199 |
+
"loss": 0.2454,
|
| 1200 |
+
"step": 8050
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.22464976477644227,
|
| 1204 |
+
"grad_norm": 0.16482336819171906,
|
| 1205 |
+
"learning_rate": 0.0001989482824511811,
|
| 1206 |
+
"loss": 0.2423,
|
| 1207 |
+
"step": 8100
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.22603649171950674,
|
| 1211 |
+
"grad_norm": 0.22351431846618652,
|
| 1212 |
+
"learning_rate": 0.00019892651583392824,
|
| 1213 |
+
"loss": 0.2501,
|
| 1214 |
+
"step": 8150
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.2274232186625712,
|
| 1218 |
+
"grad_norm": 0.19319549202919006,
|
| 1219 |
+
"learning_rate": 0.0001989045274893258,
|
| 1220 |
+
"loss": 0.2452,
|
| 1221 |
+
"step": 8200
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.22880994560563567,
|
| 1225 |
+
"grad_norm": 0.15613292157649994,
|
| 1226 |
+
"learning_rate": 0.00019888231746665696,
|
| 1227 |
+
"loss": 0.2428,
|
| 1228 |
+
"step": 8250
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.2301966725487001,
|
| 1232 |
+
"grad_norm": 0.18092665076255798,
|
| 1233 |
+
"learning_rate": 0.00019885988581570184,
|
| 1234 |
+
"loss": 0.2448,
|
| 1235 |
+
"step": 8300
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.23158339949176457,
|
| 1239 |
+
"grad_norm": 0.18928927183151245,
|
| 1240 |
+
"learning_rate": 0.00019883723258673724,
|
| 1241 |
+
"loss": 0.2493,
|
| 1242 |
+
"step": 8350
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.23297012643482903,
|
| 1246 |
+
"grad_norm": 0.19816988706588745,
|
| 1247 |
+
"learning_rate": 0.0001988143578305366,
|
| 1248 |
+
"loss": 0.2465,
|
| 1249 |
+
"step": 8400
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.2343568533778935,
|
| 1253 |
+
"grad_norm": 0.19853706657886505,
|
| 1254 |
+
"learning_rate": 0.00019879126159836992,
|
| 1255 |
+
"loss": 0.2443,
|
| 1256 |
+
"step": 8450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.23574358032095796,
|
| 1260 |
+
"grad_norm": 0.17544203996658325,
|
| 1261 |
+
"learning_rate": 0.00019876794394200353,
|
| 1262 |
+
"loss": 0.2429,
|
| 1263 |
+
"step": 8500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.2371303072640224,
|
| 1267 |
+
"grad_norm": 0.16583149135112762,
|
| 1268 |
+
"learning_rate": 0.0001987444049137001,
|
| 1269 |
+
"loss": 0.244,
|
| 1270 |
+
"step": 8550
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.23851703420708686,
|
| 1274 |
+
"grad_norm": 0.18239592015743256,
|
| 1275 |
+
"learning_rate": 0.00019872064456621848,
|
| 1276 |
+
"loss": 0.2447,
|
| 1277 |
+
"step": 8600
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.23990376115015133,
|
| 1281 |
+
"grad_norm": 0.15820704400539398,
|
| 1282 |
+
"learning_rate": 0.0001986966629528135,
|
| 1283 |
+
"loss": 0.2469,
|
| 1284 |
+
"step": 8650
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.2412904880932158,
|
| 1288 |
+
"grad_norm": 0.18477188050746918,
|
| 1289 |
+
"learning_rate": 0.00019867246012723598,
|
| 1290 |
+
"loss": 0.2407,
|
| 1291 |
+
"step": 8700
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.24267721503628023,
|
| 1295 |
+
"grad_norm": 0.1676979809999466,
|
| 1296 |
+
"learning_rate": 0.0001986480361437325,
|
| 1297 |
+
"loss": 0.2448,
|
| 1298 |
+
"step": 8750
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.2440639419793447,
|
| 1302 |
+
"grad_norm": 0.2173600196838379,
|
| 1303 |
+
"learning_rate": 0.00019862339105704543,
|
| 1304 |
+
"loss": 0.2409,
|
| 1305 |
+
"step": 8800
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.24545066892240916,
|
| 1309 |
+
"grad_norm": 0.17326687276363373,
|
| 1310 |
+
"learning_rate": 0.00019859852492241256,
|
| 1311 |
+
"loss": 0.2387,
|
| 1312 |
+
"step": 8850
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.24683739586547362,
|
| 1316 |
+
"grad_norm": 0.16229301691055298,
|
| 1317 |
+
"learning_rate": 0.00019857343779556725,
|
| 1318 |
+
"loss": 0.2467,
|
| 1319 |
+
"step": 8900
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.2482241228085381,
|
| 1323 |
+
"grad_norm": 0.21166543662548065,
|
| 1324 |
+
"learning_rate": 0.0001985481297327381,
|
| 1325 |
+
"loss": 0.2507,
|
| 1326 |
+
"step": 8950
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.24961084975160253,
|
| 1330 |
+
"grad_norm": 0.17892777919769287,
|
| 1331 |
+
"learning_rate": 0.00019852260079064894,
|
| 1332 |
+
"loss": 0.2416,
|
| 1333 |
+
"step": 9000
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.24961084975160253,
|
| 1337 |
+
"eval_loss": 0.23973840475082397,
|
| 1338 |
+
"eval_runtime": 500.5349,
|
| 1339 |
+
"eval_samples_per_second": 5.708,
|
| 1340 |
+
"eval_steps_per_second": 5.708,
|
| 1341 |
+
"step": 9000
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.250997576694667,
|
| 1345 |
+
"grad_norm": 0.20435132086277008,
|
| 1346 |
+
"learning_rate": 0.00019849685102651867,
|
| 1347 |
+
"loss": 0.2385,
|
| 1348 |
+
"step": 9050
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 0.25238430363773146,
|
| 1352 |
+
"grad_norm": 0.1890842318534851,
|
| 1353 |
+
"learning_rate": 0.0001984708804980611,
|
| 1354 |
+
"loss": 0.2416,
|
| 1355 |
+
"step": 9100
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 0.2537710305807959,
|
| 1359 |
+
"grad_norm": 0.18390174210071564,
|
| 1360 |
+
"learning_rate": 0.00019844468926348482,
|
| 1361 |
+
"loss": 0.2469,
|
| 1362 |
+
"step": 9150
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.2551577575238604,
|
| 1366 |
+
"grad_norm": 0.23599492013454437,
|
| 1367 |
+
"learning_rate": 0.00019841827738149314,
|
| 1368 |
+
"loss": 0.2417,
|
| 1369 |
+
"step": 9200
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.25654448446692485,
|
| 1373 |
+
"grad_norm": 0.1522965133190155,
|
| 1374 |
+
"learning_rate": 0.00019839164491128398,
|
| 1375 |
+
"loss": 0.2427,
|
| 1376 |
+
"step": 9250
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 0.2579312114099893,
|
| 1380 |
+
"grad_norm": 0.206534281373024,
|
| 1381 |
+
"learning_rate": 0.00019836479191254948,
|
| 1382 |
+
"loss": 0.2452,
|
| 1383 |
+
"step": 9300
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 0.2593179383530537,
|
| 1387 |
+
"grad_norm": 0.18928374350070953,
|
| 1388 |
+
"learning_rate": 0.00019833771844547627,
|
| 1389 |
+
"loss": 0.244,
|
| 1390 |
+
"step": 9350
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 0.2607046652961182,
|
| 1394 |
+
"grad_norm": 0.17130087316036224,
|
| 1395 |
+
"learning_rate": 0.00019831042457074498,
|
| 1396 |
+
"loss": 0.2488,
|
| 1397 |
+
"step": 9400
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 0.26209139223918265,
|
| 1401 |
+
"grad_norm": 0.17631781101226807,
|
| 1402 |
+
"learning_rate": 0.00019828291034953033,
|
| 1403 |
+
"loss": 0.2441,
|
| 1404 |
+
"step": 9450
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 0.2634781191822471,
|
| 1408 |
+
"grad_norm": 0.1852494180202484,
|
| 1409 |
+
"learning_rate": 0.00019825517584350083,
|
| 1410 |
+
"loss": 0.2414,
|
| 1411 |
+
"step": 9500
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 0.2648648461253116,
|
| 1415 |
+
"grad_norm": 0.21513506770133972,
|
| 1416 |
+
"learning_rate": 0.0001982272211148188,
|
| 1417 |
+
"loss": 0.2412,
|
| 1418 |
+
"step": 9550
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.26625157306837605,
|
| 1422 |
+
"grad_norm": 0.18172813951969147,
|
| 1423 |
+
"learning_rate": 0.0001981990462261401,
|
| 1424 |
+
"loss": 0.2435,
|
| 1425 |
+
"step": 9600
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 0.2676383000114405,
|
| 1429 |
+
"grad_norm": 0.1561124324798584,
|
| 1430 |
+
"learning_rate": 0.00019817065124061407,
|
| 1431 |
+
"loss": 0.238,
|
| 1432 |
+
"step": 9650
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 0.269025026954505,
|
| 1436 |
+
"grad_norm": 0.16663338243961334,
|
| 1437 |
+
"learning_rate": 0.00019814203622188338,
|
| 1438 |
+
"loss": 0.2383,
|
| 1439 |
+
"step": 9700
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 0.27041175389756944,
|
| 1443 |
+
"grad_norm": 0.17735238373279572,
|
| 1444 |
+
"learning_rate": 0.0001981132012340838,
|
| 1445 |
+
"loss": 0.2459,
|
| 1446 |
+
"step": 9750
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 0.27179848084063385,
|
| 1450 |
+
"grad_norm": 0.21334126591682434,
|
| 1451 |
+
"learning_rate": 0.00019808414634184417,
|
| 1452 |
+
"loss": 0.2425,
|
| 1453 |
+
"step": 9800
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 0.2731852077836983,
|
| 1457 |
+
"grad_norm": 0.16817434132099152,
|
| 1458 |
+
"learning_rate": 0.00019805487161028625,
|
| 1459 |
+
"loss": 0.2361,
|
| 1460 |
+
"step": 9850
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 0.2745719347267628,
|
| 1464 |
+
"grad_norm": 0.17149919271469116,
|
| 1465 |
+
"learning_rate": 0.00019802537710502443,
|
| 1466 |
+
"loss": 0.2431,
|
| 1467 |
+
"step": 9900
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.27595866166982724,
|
| 1471 |
+
"grad_norm": 0.1521356999874115,
|
| 1472 |
+
"learning_rate": 0.00019799566289216576,
|
| 1473 |
+
"loss": 0.2411,
|
| 1474 |
+
"step": 9950
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 0.2773453886128917,
|
| 1478 |
+
"grad_norm": 0.15583455562591553,
|
| 1479 |
+
"learning_rate": 0.00019796572903830974,
|
| 1480 |
+
"loss": 0.2388,
|
| 1481 |
+
"step": 10000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 0.2773453886128917,
|
| 1485 |
+
"eval_loss": 0.23783154785633087,
|
| 1486 |
+
"eval_runtime": 501.3932,
|
| 1487 |
+
"eval_samples_per_second": 5.698,
|
| 1488 |
+
"eval_steps_per_second": 5.698,
|
| 1489 |
+
"step": 10000
|
| 1490 |
+
}
|
| 1491 |
+
],
|
| 1492 |
+
"logging_steps": 50,
|
| 1493 |
+
"max_steps": 108168,
|
| 1494 |
+
"num_input_tokens_seen": 0,
|
| 1495 |
+
"num_train_epochs": 3,
|
| 1496 |
+
"save_steps": 1000,
|
| 1497 |
+
"stateful_callbacks": {
|
| 1498 |
+
"TrainerControl": {
|
| 1499 |
+
"args": {
|
| 1500 |
+
"should_epoch_stop": false,
|
| 1501 |
+
"should_evaluate": false,
|
| 1502 |
+
"should_log": false,
|
| 1503 |
+
"should_save": true,
|
| 1504 |
+
"should_training_stop": false
|
| 1505 |
+
},
|
| 1506 |
+
"attributes": {}
|
| 1507 |
+
}
|
| 1508 |
+
},
|
| 1509 |
+
"total_flos": 1.802385752064e+17,
|
| 1510 |
+
"train_batch_size": 1,
|
| 1511 |
+
"trial_name": null,
|
| 1512 |
+
"trial_params": null
|
| 1513 |
+
}
|
checkpoint-10000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e593d4080c231741ba3acb7aa362bf85842c0c2beaca29489d434eca5cc7fa0
|
| 3 |
+
size 5432
|
checkpoint-10000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-0.5B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-100000/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-100000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3c26895ebe509beb048b4a5df2b3584dbd61ab7a7d0df3e4e21af59776ac2fd
|
| 3 |
+
size 35237104
|
checkpoint-100000/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-100000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90bd07cc32cdde47422b75334992b9028b7d157d071423d5d3a3561121396d95
|
| 3 |
+
size 70667778
|
checkpoint-100000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81d6044f360391f451823995f67c8a25a8f965bd2bf1917d5adbc2e6af6a05e6
|
| 3 |
+
size 14244
|
checkpoint-100000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3492fc7749e1f19a47db06ff67f7a756ea45f058edac424b40411da4350e0678
|
| 3 |
+
size 1064
|
checkpoint-100000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-100000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
checkpoint-100000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e593d4080c231741ba3acb7aa362bf85842c0c2beaca29489d434eca5cc7fa0
|
| 3 |
+
size 5432
|
checkpoint-100000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-101000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-0.5B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-101000/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-101000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dfd0236cc0e15e7055065e987e6fe540dc814097e82681e163632e03e80fcab
|
| 3 |
+
size 35237104
|
checkpoint-101000/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-101000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-101000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b70a06edad3ab9a340b005ff18c8b6780f3d3085c8cdaa34d3172f1f075ffd7
|
| 3 |
+
size 70667778
|
checkpoint-101000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50f020ffad9fe17df1c07fa175e61340c75596ed3d0c2722273bea78476d9068
|
| 3 |
+
size 14244
|
checkpoint-101000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da286f94045493eb2418832babaf8f5961021808b00eecaf9c6e2022aad67b87
|
| 3 |
+
size 1064
|