Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +6 -0
- .ipynb_checkpoints/README-checkpoint.md +129 -0
- .ipynb_checkpoints/test_model-checkpoint.py +32 -0
- README.md +126 -3
- adapter_config.json +42 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +24 -0
- chat_template.jinja +54 -0
- checkpoint-200/README.md +208 -0
- checkpoint-200/adapter_config.json +42 -0
- checkpoint-200/adapter_model.safetensors +3 -0
- checkpoint-200/added_tokens.json +24 -0
- checkpoint-200/chat_template.jinja +54 -0
- checkpoint-200/merges.txt +0 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +31 -0
- checkpoint-200/tokenizer.json +3 -0
- checkpoint-200/tokenizer_config.json +207 -0
- checkpoint-200/trainer_state.json +2234 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-200/vocab.json +0 -0
- checkpoint-300/README.md +208 -0
- checkpoint-300/adapter_config.json +42 -0
- checkpoint-300/adapter_model.safetensors +3 -0
- checkpoint-300/added_tokens.json +24 -0
- checkpoint-300/chat_template.jinja +54 -0
- checkpoint-300/merges.txt +0 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +31 -0
- checkpoint-300/tokenizer.json +3 -0
- checkpoint-300/tokenizer_config.json +207 -0
- checkpoint-300/trainer_state.json +0 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-300/vocab.json +0 -0
- checkpoint-400/README.md +208 -0
- checkpoint-400/adapter_config.json +42 -0
- checkpoint-400/adapter_model.safetensors +3 -0
- checkpoint-400/added_tokens.json +24 -0
- checkpoint-400/chat_template.jinja +54 -0
- checkpoint-400/merges.txt +0 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/special_tokens_map.json +31 -0
- checkpoint-400/tokenizer.json +3 -0
- checkpoint-400/tokenizer_config.json +207 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
checkpoint-432/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
img-assets/header.jpg filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 4 |
+
tags:
|
| 5 |
+
- n8n
|
| 6 |
+
- workflow
|
| 7 |
+
- automation
|
| 8 |
+
- fine-tuned
|
| 9 |
+
- code-generation
|
| 10 |
+
- qlora
|
| 11 |
+
datasets:
|
| 12 |
+
- mbakgun/n8nbuilder-n8n-workflows-dataset
|
| 13 |
+
pipeline_tag: text-generation
|
| 14 |
+
language:
|
| 15 |
+
- en
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
# Qwen2.5-Coder-14B-n8n-Workflow-Generator
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
Fine-tuned Qwen2.5-Coder-14B-Instruct model specialized for generating n8n workflow JSONs from natural language descriptions.
|
| 23 |
+
|
| 24 |
+
## Model Description
|
| 25 |
+
|
| 26 |
+
This model is a QLoRA fine-tuned version of [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct) on the [n8nbuilder-n8n-workflows-dataset](https://huggingface.co/datasets/mbakgun/n8nbuilder-n8n-workflows-dataset), containing +2.5K n8n workflow templates.
|
| 27 |
+
|
| 28 |
+
**Training Details:**
|
| 29 |
+
- **Base Model**: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 30 |
+
- **Method**: QLoRA (4-bit quantization)
|
| 31 |
+
- **LoRA Rank**: 32
|
| 32 |
+
- **LoRA Alpha**: 64
|
| 33 |
+
- **Training Steps**: 432 (3 epochs)
|
| 34 |
+
- **Sequence Length**: 8192 tokens
|
| 35 |
+
- **Learning Rate**: 2e-4
|
| 36 |
+
|
| 37 |
+
## Usage
|
| 38 |
+
|
| 39 |
+
### Transformers
|
| 40 |
+
|
| 41 |
+
```python
|
| 42 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 43 |
+
import torch
|
| 44 |
+
|
| 45 |
+
model_name = "mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator"
|
| 46 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 47 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 48 |
+
model_name,
|
| 49 |
+
torch_dtype=torch.bfloat16,
|
| 50 |
+
device_map="auto"
|
| 51 |
+
)
|
| 52 |
+
|
| 53 |
+
system_prompt = "You are an expert n8n workflow generation assistant. Your goal is to create valid, efficient, and error-free n8n workflow JSONs based on the user's requirements. Always output ONLY the valid JSON workflow."
|
| 54 |
+
|
| 55 |
+
user_input = "Create a workflow that monitors a RSS feed and sends new items to Discord."
|
| 56 |
+
|
| 57 |
+
prompt = f"{system_prompt}\n\n{user_input}"
|
| 58 |
+
|
| 59 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
| 60 |
+
outputs = model.generate(
|
| 61 |
+
**inputs,
|
| 62 |
+
max_new_tokens=4096,
|
| 63 |
+
temperature=0.7,
|
| 64 |
+
do_sample=True
|
| 65 |
+
)
|
| 66 |
+
|
| 67 |
+
workflow_json = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
| 68 |
+
print(workflow_json)
|
| 69 |
+
```
|
| 70 |
+
|
| 71 |
+
### MLX (Apple Silicon)
|
| 72 |
+
|
| 73 |
+
```bash
|
| 74 |
+
# Convert to MLX
|
| 75 |
+
mlx_lm.convert \
|
| 76 |
+
--hf-path mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator \
|
| 77 |
+
--mlx-path ./qwen25-n8n-mlx \
|
| 78 |
+
-q
|
| 79 |
+
|
| 80 |
+
# Generate
|
| 81 |
+
mlx_lm.generate \
|
| 82 |
+
--model ./qwen25-n8n-mlx \
|
| 83 |
+
--prompt "You are an expert n8n workflow generation assistant...\n\nCreate a workflow that sends Slack notifications when GitHub issues are created." \
|
| 84 |
+
--max-tokens 4096
|
| 85 |
+
```
|
| 86 |
+
|
| 87 |
+
## Training Data
|
| 88 |
+
|
| 89 |
+
This model was fine-tuned on the [n8nbuilder-n8n-workflows-dataset](https://huggingface.co/datasets/mbakgun/n8nbuilder-n8n-workflows-dataset), which contains:
|
| 90 |
+
- **2,304 workflow templates** (after filtering sequences >8192 tokens)
|
| 91 |
+
- Format: Alpaca (instruction/input/output)
|
| 92 |
+
- Source: n8n.io public template gallery
|
| 93 |
+
- [n8nbuilder.dev - Create n8n Workflows in Seconds with AI](https://n8nbuilder.dev)
|
| 94 |
+
|
| 95 |
+
## Performance
|
| 96 |
+
|
| 97 |
+
- **Training Speed**: ~33.85s/step on H100 PCIe
|
| 98 |
+
- **VRAM Usage**: ~30GB (4-bit QLoRA)
|
| 99 |
+
- **Inference**: ~25-40 tok/s on Mac Mini M4 64GB (MLX)
|
| 100 |
+
|
| 101 |
+
## Limitations
|
| 102 |
+
|
| 103 |
+
- Generated workflows may require manual validation
|
| 104 |
+
- Long workflows (>8192 tokens) may be truncated
|
| 105 |
+
- Model trained on public templates only
|
| 106 |
+
|
| 107 |
+
|
| 108 |
+
|
| 109 |
+
## Citation
|
| 110 |
+
|
| 111 |
+
```bibtex
|
| 112 |
+
@model{qwen25_coder_n8n_2025,
|
| 113 |
+
title={Qwen2.5-Coder-14B-n8n-Workflow-Generator},
|
| 114 |
+
author={mbakgun},
|
| 115 |
+
year={2025},
|
| 116 |
+
base_model={Qwen/Qwen2.5-Coder-14B-Instruct},
|
| 117 |
+
dataset={mbakgun/n8nbuilder-n8n-workflows-dataset},
|
| 118 |
+
url={https://huggingface.co/mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator}
|
| 119 |
+
}
|
| 120 |
+
```
|
| 121 |
+
|
| 122 |
+
## Acknowledgments
|
| 123 |
+
|
| 124 |
+
- [Qwen Team](https://huggingface.co/Qwen) for the base model
|
| 125 |
+
- [n8n](https://n8n.io) for the workflow automation platform
|
| 126 |
+
- [n8n-mcp](https://github.com/czlonkowski/n8n-mcp) for template indexing
|
| 127 |
+
|
| 128 |
+
## License
|
| 129 |
+
Apache 2.0
|
.ipynb_checkpoints/test_model-checkpoint.py
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import torch
|
| 2 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 3 |
+
from peft import PeftModel
|
| 4 |
+
|
| 5 |
+
base_model_name = "Qwen/Qwen2.5-Coder-14B-Instruct"
|
| 6 |
+
adapter_path = "./outputs/qwen25-coder-n8n"
|
| 7 |
+
|
| 8 |
+
print("Loading base model...")
|
| 9 |
+
base_model = AutoModelForCausalLM.from_pretrained(
|
| 10 |
+
base_model_name,
|
| 11 |
+
torch_dtype=torch.bfloat16,
|
| 12 |
+
device_map="auto",
|
| 13 |
+
trust_remote_code=True
|
| 14 |
+
)
|
| 15 |
+
|
| 16 |
+
print("Loading adapter...")
|
| 17 |
+
model = PeftModel.from_pretrained(base_model, adapter_path)
|
| 18 |
+
tokenizer = AutoTokenizer.from_pretrained(base_model_name)
|
| 19 |
+
|
| 20 |
+
system_prompt = "You are an expert n8n workflow generation assistant. Your goal is to create valid, efficient, and error-free n8n workflow JSONs based on the user's requirements. Always output ONLY the valid JSON workflow."
|
| 21 |
+
user_input = "Create a workflow that gets data from a webhook and sends it to Slack. Also have a sticky note as documentation."
|
| 22 |
+
|
| 23 |
+
messages = [
|
| 24 |
+
{"role": "system", "content": system_prompt},
|
| 25 |
+
{"role": "user", "content": user_input}
|
| 26 |
+
]
|
| 27 |
+
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 28 |
+
inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
| 29 |
+
|
| 30 |
+
print("Generating workflow...")
|
| 31 |
+
outputs = model.generate(**inputs, max_new_tokens=2048, do_sample=True, temperature=0.1)
|
| 32 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
README.md
CHANGED
|
@@ -1,3 +1,126 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
|
| 8 |
+
- lora
|
| 9 |
+
- transformers
|
| 10 |
+
datasets:
|
| 11 |
+
- mbakgun/n8nbuilder-n8n-workflows-dataset
|
| 12 |
+
pipeline_tag: text-generation
|
| 13 |
+
model-index:
|
| 14 |
+
- name: outputs/qwen25-coder-n8n
|
| 15 |
+
results: []
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 19 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 20 |
+
|
| 21 |
+
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
| 22 |
+
<details><summary>See axolotl config</summary>
|
| 23 |
+
|
| 24 |
+
axolotl version: `0.13.0.dev0`
|
| 25 |
+
```yaml
|
| 26 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 27 |
+
|
| 28 |
+
load_in_4bit: true
|
| 29 |
+
adapter: qlora
|
| 30 |
+
|
| 31 |
+
bnb_4bit_compute_dtype: bfloat16
|
| 32 |
+
bnb_4bit_use_double_quant: true
|
| 33 |
+
bnb_4bit_quant_type: nf4
|
| 34 |
+
|
| 35 |
+
lora_r: 32
|
| 36 |
+
lora_alpha: 64
|
| 37 |
+
lora_dropout: 0.05
|
| 38 |
+
lora_target_modules:
|
| 39 |
+
- q_proj
|
| 40 |
+
- k_proj
|
| 41 |
+
- v_proj
|
| 42 |
+
- o_proj
|
| 43 |
+
- gate_proj
|
| 44 |
+
- up_proj
|
| 45 |
+
- down_proj
|
| 46 |
+
|
| 47 |
+
datasets:
|
| 48 |
+
- path: mbakgun/n8nbuilder-n8n-workflows-dataset
|
| 49 |
+
type: alpaca
|
| 50 |
+
|
| 51 |
+
sequence_len: 8192
|
| 52 |
+
sample_packing: false
|
| 53 |
+
pad_to_sequence_len: false
|
| 54 |
+
|
| 55 |
+
micro_batch_size: 1
|
| 56 |
+
gradient_accumulation_steps: 16
|
| 57 |
+
num_epochs: 3
|
| 58 |
+
|
| 59 |
+
learning_rate: 2e-4
|
| 60 |
+
lr_scheduler: cosine
|
| 61 |
+
warmup_ratio: 0.1
|
| 62 |
+
weight_decay: 0.01
|
| 63 |
+
|
| 64 |
+
optimizer: adamw_bnb_8bit
|
| 65 |
+
bf16: true
|
| 66 |
+
tf32: true
|
| 67 |
+
|
| 68 |
+
gradient_checkpointing: true
|
| 69 |
+
gradient_checkpointing_kwargs:
|
| 70 |
+
use_reentrant: false
|
| 71 |
+
|
| 72 |
+
train_on_inputs: false
|
| 73 |
+
|
| 74 |
+
output_dir: ./outputs/qwen25-coder-n8n
|
| 75 |
+
save_strategy: steps
|
| 76 |
+
save_steps: 100
|
| 77 |
+
logging_steps: 1
|
| 78 |
+
|
| 79 |
+
flash_attention: true
|
| 80 |
+
```
|
| 81 |
+
|
| 82 |
+
</details><br>
|
| 83 |
+
|
| 84 |
+
# outputs/qwen25-coder-n8n
|
| 85 |
+
|
| 86 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct) on the mbakgun/n8nbuilder-n8n-workflows-dataset dataset.
|
| 87 |
+
|
| 88 |
+
## Model description
|
| 89 |
+
|
| 90 |
+
More information needed
|
| 91 |
+
|
| 92 |
+
## Intended uses & limitations
|
| 93 |
+
|
| 94 |
+
More information needed
|
| 95 |
+
|
| 96 |
+
## Training and evaluation data
|
| 97 |
+
|
| 98 |
+
More information needed
|
| 99 |
+
|
| 100 |
+
## Training procedure
|
| 101 |
+
|
| 102 |
+
### Training hyperparameters
|
| 103 |
+
|
| 104 |
+
The following hyperparameters were used during training:
|
| 105 |
+
- learning_rate: 0.0002
|
| 106 |
+
- train_batch_size: 1
|
| 107 |
+
- eval_batch_size: 1
|
| 108 |
+
- seed: 42
|
| 109 |
+
- gradient_accumulation_steps: 16
|
| 110 |
+
- total_train_batch_size: 16
|
| 111 |
+
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 112 |
+
- lr_scheduler_type: cosine
|
| 113 |
+
- lr_scheduler_warmup_steps: 43
|
| 114 |
+
- training_steps: 432
|
| 115 |
+
|
| 116 |
+
### Training results
|
| 117 |
+
|
| 118 |
+
|
| 119 |
+
|
| 120 |
+
### Framework versions
|
| 121 |
+
|
| 122 |
+
- PEFT 0.17.1
|
| 123 |
+
- Transformers 4.57.0
|
| 124 |
+
- Pytorch 2.7.1+cu126
|
| 125 |
+
- Datasets 4.0.0
|
| 126 |
+
- Tokenizers 0.22.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": null,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"up_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
+
"k_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": [],
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b1d9d4ffcee0be992300b65795d78890d05f2efab9415fbf6c3b0d766246125
|
| 3 |
+
size 550593184
|
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 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-200/README.md
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
|
| 8 |
+
- lora
|
| 9 |
+
- transformers
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Model ID
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
|
| 22 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
- **Developed by:** [More Information Needed]
|
| 27 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 28 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 29 |
+
- **Model type:** [More Information Needed]
|
| 30 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 31 |
+
- **License:** [More Information Needed]
|
| 32 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 33 |
+
|
| 34 |
+
### Model Sources [optional]
|
| 35 |
+
|
| 36 |
+
<!-- Provide the basic links for the model. -->
|
| 37 |
+
|
| 38 |
+
- **Repository:** [More Information Needed]
|
| 39 |
+
- **Paper [optional]:** [More Information Needed]
|
| 40 |
+
- **Demo [optional]:** [More Information Needed]
|
| 41 |
+
|
| 42 |
+
## Uses
|
| 43 |
+
|
| 44 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 45 |
+
|
| 46 |
+
### Direct Use
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Downstream Use [optional]
|
| 53 |
+
|
| 54 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
### Out-of-Scope Use
|
| 59 |
+
|
| 60 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
## Bias, Risks, and Limitations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 67 |
+
|
| 68 |
+
[More Information Needed]
|
| 69 |
+
|
| 70 |
+
### Recommendations
|
| 71 |
+
|
| 72 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 73 |
+
|
| 74 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 75 |
+
|
| 76 |
+
## How to Get Started with the Model
|
| 77 |
+
|
| 78 |
+
Use the code below to get started with the model.
|
| 79 |
+
|
| 80 |
+
[More Information Needed]
|
| 81 |
+
|
| 82 |
+
## Training Details
|
| 83 |
+
|
| 84 |
+
### Training Data
|
| 85 |
+
|
| 86 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 87 |
+
|
| 88 |
+
[More Information Needed]
|
| 89 |
+
|
| 90 |
+
### Training Procedure
|
| 91 |
+
|
| 92 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 93 |
+
|
| 94 |
+
#### Preprocessing [optional]
|
| 95 |
+
|
| 96 |
+
[More Information Needed]
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
#### Training Hyperparameters
|
| 100 |
+
|
| 101 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 102 |
+
|
| 103 |
+
#### Speeds, Sizes, Times [optional]
|
| 104 |
+
|
| 105 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 106 |
+
|
| 107 |
+
[More Information Needed]
|
| 108 |
+
|
| 109 |
+
## Evaluation
|
| 110 |
+
|
| 111 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 112 |
+
|
| 113 |
+
### Testing Data, Factors & Metrics
|
| 114 |
+
|
| 115 |
+
#### Testing Data
|
| 116 |
+
|
| 117 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Factors
|
| 122 |
+
|
| 123 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
#### Metrics
|
| 128 |
+
|
| 129 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 130 |
+
|
| 131 |
+
[More Information Needed]
|
| 132 |
+
|
| 133 |
+
### Results
|
| 134 |
+
|
| 135 |
+
[More Information Needed]
|
| 136 |
+
|
| 137 |
+
#### Summary
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Model Examination [optional]
|
| 142 |
+
|
| 143 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 144 |
+
|
| 145 |
+
[More Information Needed]
|
| 146 |
+
|
| 147 |
+
## Environmental Impact
|
| 148 |
+
|
| 149 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 150 |
+
|
| 151 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 152 |
+
|
| 153 |
+
- **Hardware Type:** [More Information Needed]
|
| 154 |
+
- **Hours used:** [More Information Needed]
|
| 155 |
+
- **Cloud Provider:** [More Information Needed]
|
| 156 |
+
- **Compute Region:** [More Information Needed]
|
| 157 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 158 |
+
|
| 159 |
+
## Technical Specifications [optional]
|
| 160 |
+
|
| 161 |
+
### Model Architecture and Objective
|
| 162 |
+
|
| 163 |
+
[More Information Needed]
|
| 164 |
+
|
| 165 |
+
### Compute Infrastructure
|
| 166 |
+
|
| 167 |
+
[More Information Needed]
|
| 168 |
+
|
| 169 |
+
#### Hardware
|
| 170 |
+
|
| 171 |
+
[More Information Needed]
|
| 172 |
+
|
| 173 |
+
#### Software
|
| 174 |
+
|
| 175 |
+
[More Information Needed]
|
| 176 |
+
|
| 177 |
+
## Citation [optional]
|
| 178 |
+
|
| 179 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 180 |
+
|
| 181 |
+
**BibTeX:**
|
| 182 |
+
|
| 183 |
+
[More Information Needed]
|
| 184 |
+
|
| 185 |
+
**APA:**
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## Glossary [optional]
|
| 190 |
+
|
| 191 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 192 |
+
|
| 193 |
+
[More Information Needed]
|
| 194 |
+
|
| 195 |
+
## More Information [optional]
|
| 196 |
+
|
| 197 |
+
[More Information Needed]
|
| 198 |
+
|
| 199 |
+
## Model Card Authors [optional]
|
| 200 |
+
|
| 201 |
+
[More Information Needed]
|
| 202 |
+
|
| 203 |
+
## Model Card Contact
|
| 204 |
+
|
| 205 |
+
[More Information Needed]
|
| 206 |
+
### Framework versions
|
| 207 |
+
|
| 208 |
+
- PEFT 0.17.1
|
checkpoint-200/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": null,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"up_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
+
"k_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": [],
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
checkpoint-200/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9721072167c0246f36fd6fb94902be365c05f3d748ece7ae1cd9bd285f36b00
|
| 3 |
+
size 550593184
|
checkpoint-200/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-200/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-200/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:699f57458d973a6dfd8c65ff135cc49dcbd877e444891872bd7ec217061e98da
|
| 3 |
+
size 280341861
|
checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16f82cf93e8654130004eec31b114ac5df86dc9281afce0ca2f6572fb5a44f6b
|
| 3 |
+
size 14645
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91f21784a8f0cb263be2beb02bbf445ff22229c9edf3c87d40868a63594e9f4e
|
| 3 |
+
size 1465
|
checkpoint-200/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-200/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
checkpoint-200/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 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 32768,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,2234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.3888888888888888,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.006944444444444444,
|
| 14 |
+
"grad_norm": 0.09848134219646454,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.0821,
|
| 17 |
+
"memory/device_reserved (GiB)": 30.8,
|
| 18 |
+
"memory/max_active (GiB)": 27.69,
|
| 19 |
+
"memory/max_allocated (GiB)": 27.69,
|
| 20 |
+
"step": 1,
|
| 21 |
+
"tokens_per_second_per_gpu": 1763.68
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.013888888888888888,
|
| 25 |
+
"grad_norm": 0.11234692484140396,
|
| 26 |
+
"learning_rate": 4.651162790697674e-06,
|
| 27 |
+
"loss": 1.2119,
|
| 28 |
+
"memory/device_reserved (GiB)": 31.05,
|
| 29 |
+
"memory/max_active (GiB)": 25.68,
|
| 30 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 31 |
+
"step": 2,
|
| 32 |
+
"tokens_per_second_per_gpu": 1834.64
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.020833333333333332,
|
| 36 |
+
"grad_norm": 0.11071926355361938,
|
| 37 |
+
"learning_rate": 9.302325581395349e-06,
|
| 38 |
+
"loss": 1.2053,
|
| 39 |
+
"memory/device_reserved (GiB)": 31.05,
|
| 40 |
+
"memory/max_active (GiB)": 27.01,
|
| 41 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 42 |
+
"step": 3,
|
| 43 |
+
"tokens_per_second_per_gpu": 1875.82
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.027777777777777776,
|
| 47 |
+
"grad_norm": 0.10147764533758163,
|
| 48 |
+
"learning_rate": 1.3953488372093024e-05,
|
| 49 |
+
"loss": 1.0514,
|
| 50 |
+
"memory/device_reserved (GiB)": 32.27,
|
| 51 |
+
"memory/max_active (GiB)": 28.9,
|
| 52 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 53 |
+
"step": 4,
|
| 54 |
+
"tokens_per_second_per_gpu": 1792.72
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.034722222222222224,
|
| 58 |
+
"grad_norm": 0.10568977892398834,
|
| 59 |
+
"learning_rate": 1.8604651162790697e-05,
|
| 60 |
+
"loss": 1.209,
|
| 61 |
+
"memory/device_reserved (GiB)": 32.27,
|
| 62 |
+
"memory/max_active (GiB)": 27.95,
|
| 63 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 64 |
+
"step": 5,
|
| 65 |
+
"tokens_per_second_per_gpu": 1840.61
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.041666666666666664,
|
| 69 |
+
"grad_norm": 0.10363873094320297,
|
| 70 |
+
"learning_rate": 2.3255813953488374e-05,
|
| 71 |
+
"loss": 1.0817,
|
| 72 |
+
"memory/device_reserved (GiB)": 32.27,
|
| 73 |
+
"memory/max_active (GiB)": 27.95,
|
| 74 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 75 |
+
"step": 6,
|
| 76 |
+
"tokens_per_second_per_gpu": 1784.92
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.04861111111111111,
|
| 80 |
+
"grad_norm": 0.113986074924469,
|
| 81 |
+
"learning_rate": 2.7906976744186048e-05,
|
| 82 |
+
"loss": 1.1571,
|
| 83 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 84 |
+
"memory/max_active (GiB)": 28.9,
|
| 85 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 86 |
+
"step": 7,
|
| 87 |
+
"tokens_per_second_per_gpu": 1892.63
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.05555555555555555,
|
| 91 |
+
"grad_norm": 0.1191892921924591,
|
| 92 |
+
"learning_rate": 3.2558139534883724e-05,
|
| 93 |
+
"loss": 1.1444,
|
| 94 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 95 |
+
"memory/max_active (GiB)": 28.9,
|
| 96 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 97 |
+
"step": 8,
|
| 98 |
+
"tokens_per_second_per_gpu": 1863.93
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.0625,
|
| 102 |
+
"grad_norm": 0.11628979444503784,
|
| 103 |
+
"learning_rate": 3.7209302325581394e-05,
|
| 104 |
+
"loss": 1.1786,
|
| 105 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 106 |
+
"memory/max_active (GiB)": 24.64,
|
| 107 |
+
"memory/max_allocated (GiB)": 24.64,
|
| 108 |
+
"step": 9,
|
| 109 |
+
"tokens_per_second_per_gpu": 1764.21
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.06944444444444445,
|
| 113 |
+
"grad_norm": 0.10155434161424637,
|
| 114 |
+
"learning_rate": 4.186046511627907e-05,
|
| 115 |
+
"loss": 1.0695,
|
| 116 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 117 |
+
"memory/max_active (GiB)": 27.2,
|
| 118 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 119 |
+
"step": 10,
|
| 120 |
+
"tokens_per_second_per_gpu": 1823.2
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.0763888888888889,
|
| 124 |
+
"grad_norm": 0.08485760539770126,
|
| 125 |
+
"learning_rate": 4.651162790697675e-05,
|
| 126 |
+
"loss": 1.0805,
|
| 127 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 128 |
+
"memory/max_active (GiB)": 27.01,
|
| 129 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 130 |
+
"step": 11,
|
| 131 |
+
"tokens_per_second_per_gpu": 1805.0
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.08333333333333333,
|
| 135 |
+
"grad_norm": 0.07211048156023026,
|
| 136 |
+
"learning_rate": 5.1162790697674425e-05,
|
| 137 |
+
"loss": 1.0824,
|
| 138 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 139 |
+
"memory/max_active (GiB)": 27.95,
|
| 140 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 141 |
+
"step": 12,
|
| 142 |
+
"tokens_per_second_per_gpu": 1799.74
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.09027777777777778,
|
| 146 |
+
"grad_norm": 0.06483420729637146,
|
| 147 |
+
"learning_rate": 5.5813953488372095e-05,
|
| 148 |
+
"loss": 1.0264,
|
| 149 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 150 |
+
"memory/max_active (GiB)": 27.95,
|
| 151 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 152 |
+
"step": 13,
|
| 153 |
+
"tokens_per_second_per_gpu": 1798.61
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.09722222222222222,
|
| 157 |
+
"grad_norm": 0.06657296419143677,
|
| 158 |
+
"learning_rate": 6.0465116279069765e-05,
|
| 159 |
+
"loss": 1.0967,
|
| 160 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 161 |
+
"memory/max_active (GiB)": 28.9,
|
| 162 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 163 |
+
"step": 14,
|
| 164 |
+
"tokens_per_second_per_gpu": 1788.44
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.10416666666666667,
|
| 168 |
+
"grad_norm": 0.195042684674263,
|
| 169 |
+
"learning_rate": 6.511627906976745e-05,
|
| 170 |
+
"loss": 1.1489,
|
| 171 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 172 |
+
"memory/max_active (GiB)": 24.8,
|
| 173 |
+
"memory/max_allocated (GiB)": 24.8,
|
| 174 |
+
"step": 15,
|
| 175 |
+
"tokens_per_second_per_gpu": 1785.21
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.1111111111111111,
|
| 179 |
+
"grad_norm": 0.07728952169418335,
|
| 180 |
+
"learning_rate": 6.976744186046513e-05,
|
| 181 |
+
"loss": 1.0985,
|
| 182 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 183 |
+
"memory/max_active (GiB)": 27.95,
|
| 184 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 185 |
+
"step": 16,
|
| 186 |
+
"tokens_per_second_per_gpu": 1752.91
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.11805555555555555,
|
| 190 |
+
"grad_norm": 0.08134876191616058,
|
| 191 |
+
"learning_rate": 7.441860465116279e-05,
|
| 192 |
+
"loss": 1.1112,
|
| 193 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 194 |
+
"memory/max_active (GiB)": 26.06,
|
| 195 |
+
"memory/max_allocated (GiB)": 26.06,
|
| 196 |
+
"step": 17,
|
| 197 |
+
"tokens_per_second_per_gpu": 1813.48
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.125,
|
| 201 |
+
"grad_norm": 0.08289807289838791,
|
| 202 |
+
"learning_rate": 7.906976744186047e-05,
|
| 203 |
+
"loss": 1.0222,
|
| 204 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 205 |
+
"memory/max_active (GiB)": 27.95,
|
| 206 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 207 |
+
"step": 18,
|
| 208 |
+
"tokens_per_second_per_gpu": 1852.47
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.13194444444444445,
|
| 212 |
+
"grad_norm": 0.09635733813047409,
|
| 213 |
+
"learning_rate": 8.372093023255814e-05,
|
| 214 |
+
"loss": 1.1493,
|
| 215 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 216 |
+
"memory/max_active (GiB)": 24.17,
|
| 217 |
+
"memory/max_allocated (GiB)": 24.17,
|
| 218 |
+
"step": 19,
|
| 219 |
+
"tokens_per_second_per_gpu": 1745.06
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1388888888888889,
|
| 223 |
+
"grad_norm": 0.08602173626422882,
|
| 224 |
+
"learning_rate": 8.837209302325582e-05,
|
| 225 |
+
"loss": 0.9912,
|
| 226 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 227 |
+
"memory/max_active (GiB)": 26.25,
|
| 228 |
+
"memory/max_allocated (GiB)": 26.25,
|
| 229 |
+
"step": 20,
|
| 230 |
+
"tokens_per_second_per_gpu": 1758.58
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.14583333333333334,
|
| 234 |
+
"grad_norm": 0.08320974558591843,
|
| 235 |
+
"learning_rate": 9.30232558139535e-05,
|
| 236 |
+
"loss": 1.1637,
|
| 237 |
+
"memory/device_reserved (GiB)": 32.33,
|
| 238 |
+
"memory/max_active (GiB)": 27.95,
|
| 239 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 240 |
+
"step": 21,
|
| 241 |
+
"tokens_per_second_per_gpu": 1772.58
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.1527777777777778,
|
| 245 |
+
"grad_norm": 0.0785663053393364,
|
| 246 |
+
"learning_rate": 9.767441860465116e-05,
|
| 247 |
+
"loss": 1.0209,
|
| 248 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 249 |
+
"memory/max_active (GiB)": 28.9,
|
| 250 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 251 |
+
"step": 22,
|
| 252 |
+
"tokens_per_second_per_gpu": 1822.66
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.1597222222222222,
|
| 256 |
+
"grad_norm": 0.07734047621488571,
|
| 257 |
+
"learning_rate": 0.00010232558139534885,
|
| 258 |
+
"loss": 0.9858,
|
| 259 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 260 |
+
"memory/max_active (GiB)": 27.95,
|
| 261 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 262 |
+
"step": 23,
|
| 263 |
+
"tokens_per_second_per_gpu": 1889.88
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.16666666666666666,
|
| 267 |
+
"grad_norm": 0.07255646586418152,
|
| 268 |
+
"learning_rate": 0.00010697674418604651,
|
| 269 |
+
"loss": 1.0003,
|
| 270 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 271 |
+
"memory/max_active (GiB)": 28.9,
|
| 272 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 273 |
+
"step": 24,
|
| 274 |
+
"tokens_per_second_per_gpu": 1833.16
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.1736111111111111,
|
| 278 |
+
"grad_norm": 0.07897679507732391,
|
| 279 |
+
"learning_rate": 0.00011162790697674419,
|
| 280 |
+
"loss": 1.0143,
|
| 281 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 282 |
+
"memory/max_active (GiB)": 28.15,
|
| 283 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 284 |
+
"step": 25,
|
| 285 |
+
"tokens_per_second_per_gpu": 1900.98
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.18055555555555555,
|
| 289 |
+
"grad_norm": 0.09510312229394913,
|
| 290 |
+
"learning_rate": 0.00011627906976744187,
|
| 291 |
+
"loss": 1.0341,
|
| 292 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 293 |
+
"memory/max_active (GiB)": 23.18,
|
| 294 |
+
"memory/max_allocated (GiB)": 23.18,
|
| 295 |
+
"step": 26,
|
| 296 |
+
"tokens_per_second_per_gpu": 1701.34
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.1875,
|
| 300 |
+
"grad_norm": 0.07016909122467041,
|
| 301 |
+
"learning_rate": 0.00012093023255813953,
|
| 302 |
+
"loss": 1.0004,
|
| 303 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 304 |
+
"memory/max_active (GiB)": 28.38,
|
| 305 |
+
"memory/max_allocated (GiB)": 28.38,
|
| 306 |
+
"step": 27,
|
| 307 |
+
"tokens_per_second_per_gpu": 1891.5
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.19444444444444445,
|
| 311 |
+
"grad_norm": 0.07151541113853455,
|
| 312 |
+
"learning_rate": 0.0001255813953488372,
|
| 313 |
+
"loss": 0.9588,
|
| 314 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 315 |
+
"memory/max_active (GiB)": 28.9,
|
| 316 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 317 |
+
"step": 28,
|
| 318 |
+
"tokens_per_second_per_gpu": 1890.08
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.2013888888888889,
|
| 322 |
+
"grad_norm": 0.07155290246009827,
|
| 323 |
+
"learning_rate": 0.0001302325581395349,
|
| 324 |
+
"loss": 1.0078,
|
| 325 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 326 |
+
"memory/max_active (GiB)": 27.01,
|
| 327 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 328 |
+
"step": 29,
|
| 329 |
+
"tokens_per_second_per_gpu": 1759.11
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.20833333333333334,
|
| 333 |
+
"grad_norm": 0.08267220109701157,
|
| 334 |
+
"learning_rate": 0.00013488372093023256,
|
| 335 |
+
"loss": 1.0343,
|
| 336 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 337 |
+
"memory/max_active (GiB)": 26.49,
|
| 338 |
+
"memory/max_allocated (GiB)": 26.49,
|
| 339 |
+
"step": 30,
|
| 340 |
+
"tokens_per_second_per_gpu": 1794.99
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.2152777777777778,
|
| 344 |
+
"grad_norm": 0.06379543989896774,
|
| 345 |
+
"learning_rate": 0.00013953488372093025,
|
| 346 |
+
"loss": 0.9155,
|
| 347 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 348 |
+
"memory/max_active (GiB)": 28.9,
|
| 349 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 350 |
+
"step": 31,
|
| 351 |
+
"tokens_per_second_per_gpu": 1829.94
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.2222222222222222,
|
| 355 |
+
"grad_norm": 0.07846751064062119,
|
| 356 |
+
"learning_rate": 0.00014418604651162791,
|
| 357 |
+
"loss": 1.0727,
|
| 358 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 359 |
+
"memory/max_active (GiB)": 23.79,
|
| 360 |
+
"memory/max_allocated (GiB)": 23.79,
|
| 361 |
+
"step": 32,
|
| 362 |
+
"tokens_per_second_per_gpu": 1854.31
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.22916666666666666,
|
| 366 |
+
"grad_norm": 0.07601239532232285,
|
| 367 |
+
"learning_rate": 0.00014883720930232558,
|
| 368 |
+
"loss": 1.0472,
|
| 369 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 370 |
+
"memory/max_active (GiB)": 28.9,
|
| 371 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 372 |
+
"step": 33,
|
| 373 |
+
"tokens_per_second_per_gpu": 1806.02
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.2361111111111111,
|
| 377 |
+
"grad_norm": 0.09074926376342773,
|
| 378 |
+
"learning_rate": 0.00015348837209302327,
|
| 379 |
+
"loss": 1.034,
|
| 380 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 381 |
+
"memory/max_active (GiB)": 23.79,
|
| 382 |
+
"memory/max_allocated (GiB)": 23.79,
|
| 383 |
+
"step": 34,
|
| 384 |
+
"tokens_per_second_per_gpu": 1814.81
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.24305555555555555,
|
| 388 |
+
"grad_norm": 0.07441543787717819,
|
| 389 |
+
"learning_rate": 0.00015813953488372093,
|
| 390 |
+
"loss": 0.9786,
|
| 391 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 392 |
+
"memory/max_active (GiB)": 27.01,
|
| 393 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 394 |
+
"step": 35,
|
| 395 |
+
"tokens_per_second_per_gpu": 1865.18
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.25,
|
| 399 |
+
"grad_norm": 0.08436308056116104,
|
| 400 |
+
"learning_rate": 0.00016279069767441862,
|
| 401 |
+
"loss": 0.9218,
|
| 402 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 403 |
+
"memory/max_active (GiB)": 27.01,
|
| 404 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 405 |
+
"step": 36,
|
| 406 |
+
"tokens_per_second_per_gpu": 1860.2
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.2569444444444444,
|
| 410 |
+
"grad_norm": 0.07554468512535095,
|
| 411 |
+
"learning_rate": 0.00016744186046511629,
|
| 412 |
+
"loss": 1.0504,
|
| 413 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 414 |
+
"memory/max_active (GiB)": 25.68,
|
| 415 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 416 |
+
"step": 37,
|
| 417 |
+
"tokens_per_second_per_gpu": 1816.31
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.2638888888888889,
|
| 421 |
+
"grad_norm": 0.09911656379699707,
|
| 422 |
+
"learning_rate": 0.00017209302325581395,
|
| 423 |
+
"loss": 0.9141,
|
| 424 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 425 |
+
"memory/max_active (GiB)": 26.26,
|
| 426 |
+
"memory/max_allocated (GiB)": 26.26,
|
| 427 |
+
"step": 38,
|
| 428 |
+
"tokens_per_second_per_gpu": 1863.8
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.2708333333333333,
|
| 432 |
+
"grad_norm": 0.07778877764940262,
|
| 433 |
+
"learning_rate": 0.00017674418604651164,
|
| 434 |
+
"loss": 1.0342,
|
| 435 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 436 |
+
"memory/max_active (GiB)": 24.17,
|
| 437 |
+
"memory/max_allocated (GiB)": 24.17,
|
| 438 |
+
"step": 39,
|
| 439 |
+
"tokens_per_second_per_gpu": 1619.33
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.2777777777777778,
|
| 443 |
+
"grad_norm": 0.09776122868061066,
|
| 444 |
+
"learning_rate": 0.0001813953488372093,
|
| 445 |
+
"loss": 0.9365,
|
| 446 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 447 |
+
"memory/max_active (GiB)": 26.06,
|
| 448 |
+
"memory/max_allocated (GiB)": 26.06,
|
| 449 |
+
"step": 40,
|
| 450 |
+
"tokens_per_second_per_gpu": 1708.88
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2847222222222222,
|
| 454 |
+
"grad_norm": 0.09212527424097061,
|
| 455 |
+
"learning_rate": 0.000186046511627907,
|
| 456 |
+
"loss": 0.9455,
|
| 457 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 458 |
+
"memory/max_active (GiB)": 28.9,
|
| 459 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 460 |
+
"step": 41,
|
| 461 |
+
"tokens_per_second_per_gpu": 1854.36
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.2916666666666667,
|
| 465 |
+
"grad_norm": 0.1160384938120842,
|
| 466 |
+
"learning_rate": 0.00019069767441860466,
|
| 467 |
+
"loss": 0.9964,
|
| 468 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 469 |
+
"memory/max_active (GiB)": 23.7,
|
| 470 |
+
"memory/max_allocated (GiB)": 23.7,
|
| 471 |
+
"step": 42,
|
| 472 |
+
"tokens_per_second_per_gpu": 1775.41
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.2986111111111111,
|
| 476 |
+
"grad_norm": 0.06805545091629028,
|
| 477 |
+
"learning_rate": 0.00019534883720930232,
|
| 478 |
+
"loss": 0.8627,
|
| 479 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 480 |
+
"memory/max_active (GiB)": 25.68,
|
| 481 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 482 |
+
"step": 43,
|
| 483 |
+
"tokens_per_second_per_gpu": 1830.25
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.3055555555555556,
|
| 487 |
+
"grad_norm": 0.06951376795768738,
|
| 488 |
+
"learning_rate": 0.0002,
|
| 489 |
+
"loss": 0.9417,
|
| 490 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 491 |
+
"memory/max_active (GiB)": 25.68,
|
| 492 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 493 |
+
"step": 44,
|
| 494 |
+
"tokens_per_second_per_gpu": 1843.05
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.3125,
|
| 498 |
+
"grad_norm": 0.06728649139404297,
|
| 499 |
+
"learning_rate": 0.00019999673886943734,
|
| 500 |
+
"loss": 0.9017,
|
| 501 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 502 |
+
"memory/max_active (GiB)": 27.95,
|
| 503 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 504 |
+
"step": 45,
|
| 505 |
+
"tokens_per_second_per_gpu": 1889.73
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.3194444444444444,
|
| 509 |
+
"grad_norm": 0.0888209342956543,
|
| 510 |
+
"learning_rate": 0.0001999869556904488,
|
| 511 |
+
"loss": 1.0087,
|
| 512 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 513 |
+
"memory/max_active (GiB)": 27.95,
|
| 514 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 515 |
+
"step": 46,
|
| 516 |
+
"tokens_per_second_per_gpu": 1805.58
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.3263888888888889,
|
| 520 |
+
"grad_norm": 0.07477093487977982,
|
| 521 |
+
"learning_rate": 0.00019997065110111885,
|
| 522 |
+
"loss": 0.9246,
|
| 523 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 524 |
+
"memory/max_active (GiB)": 27.2,
|
| 525 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 526 |
+
"step": 47,
|
| 527 |
+
"tokens_per_second_per_gpu": 1807.73
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3333333333333333,
|
| 531 |
+
"grad_norm": 0.08000776916742325,
|
| 532 |
+
"learning_rate": 0.00019994782616487538,
|
| 533 |
+
"loss": 0.936,
|
| 534 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 535 |
+
"memory/max_active (GiB)": 27.01,
|
| 536 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 537 |
+
"step": 48,
|
| 538 |
+
"tokens_per_second_per_gpu": 1732.16
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.3402777777777778,
|
| 542 |
+
"grad_norm": 0.2703610956668854,
|
| 543 |
+
"learning_rate": 0.00019991848237042035,
|
| 544 |
+
"loss": 0.9732,
|
| 545 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 546 |
+
"memory/max_active (GiB)": 24.64,
|
| 547 |
+
"memory/max_allocated (GiB)": 24.64,
|
| 548 |
+
"step": 49,
|
| 549 |
+
"tokens_per_second_per_gpu": 1814.28
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3472222222222222,
|
| 553 |
+
"grad_norm": 0.08173573762178421,
|
| 554 |
+
"learning_rate": 0.00019988262163163264,
|
| 555 |
+
"loss": 0.9867,
|
| 556 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 557 |
+
"memory/max_active (GiB)": 26.25,
|
| 558 |
+
"memory/max_allocated (GiB)": 26.25,
|
| 559 |
+
"step": 50,
|
| 560 |
+
"tokens_per_second_per_gpu": 1746.16
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.3541666666666667,
|
| 564 |
+
"grad_norm": 0.06703449040651321,
|
| 565 |
+
"learning_rate": 0.00019984024628744328,
|
| 566 |
+
"loss": 0.9353,
|
| 567 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 568 |
+
"memory/max_active (GiB)": 25.31,
|
| 569 |
+
"memory/max_allocated (GiB)": 25.31,
|
| 570 |
+
"step": 51,
|
| 571 |
+
"tokens_per_second_per_gpu": 1803.49
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.3611111111111111,
|
| 575 |
+
"grad_norm": 0.0770621970295906,
|
| 576 |
+
"learning_rate": 0.0001997913591016829,
|
| 577 |
+
"loss": 0.9705,
|
| 578 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 579 |
+
"memory/max_active (GiB)": 27.44,
|
| 580 |
+
"memory/max_allocated (GiB)": 27.44,
|
| 581 |
+
"step": 52,
|
| 582 |
+
"tokens_per_second_per_gpu": 1805.23
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.3680555555555556,
|
| 586 |
+
"grad_norm": 0.08800782263278961,
|
| 587 |
+
"learning_rate": 0.00019973596326290137,
|
| 588 |
+
"loss": 0.9082,
|
| 589 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 590 |
+
"memory/max_active (GiB)": 28.9,
|
| 591 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 592 |
+
"step": 53,
|
| 593 |
+
"tokens_per_second_per_gpu": 1787.79
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.375,
|
| 597 |
+
"grad_norm": 0.0656328946352005,
|
| 598 |
+
"learning_rate": 0.00019967406238415998,
|
| 599 |
+
"loss": 0.964,
|
| 600 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 601 |
+
"memory/max_active (GiB)": 28.9,
|
| 602 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 603 |
+
"step": 54,
|
| 604 |
+
"tokens_per_second_per_gpu": 1888.13
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.3819444444444444,
|
| 608 |
+
"grad_norm": 0.09178014099597931,
|
| 609 |
+
"learning_rate": 0.00019960566050279566,
|
| 610 |
+
"loss": 0.918,
|
| 611 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 612 |
+
"memory/max_active (GiB)": 27.2,
|
| 613 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 614 |
+
"step": 55,
|
| 615 |
+
"tokens_per_second_per_gpu": 1822.06
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.3888888888888889,
|
| 619 |
+
"grad_norm": 0.07544898241758347,
|
| 620 |
+
"learning_rate": 0.00019953076208015772,
|
| 621 |
+
"loss": 1.0078,
|
| 622 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 623 |
+
"memory/max_active (GiB)": 28.9,
|
| 624 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 625 |
+
"step": 56,
|
| 626 |
+
"tokens_per_second_per_gpu": 1779.76
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.3958333333333333,
|
| 630 |
+
"grad_norm": 0.07013165950775146,
|
| 631 |
+
"learning_rate": 0.0001994493720013169,
|
| 632 |
+
"loss": 0.952,
|
| 633 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 634 |
+
"memory/max_active (GiB)": 27.01,
|
| 635 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 636 |
+
"step": 57,
|
| 637 |
+
"tokens_per_second_per_gpu": 1875.9
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.4027777777777778,
|
| 641 |
+
"grad_norm": 0.2212851643562317,
|
| 642 |
+
"learning_rate": 0.00019936149557474666,
|
| 643 |
+
"loss": 0.9751,
|
| 644 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 645 |
+
"memory/max_active (GiB)": 27.01,
|
| 646 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 647 |
+
"step": 58,
|
| 648 |
+
"tokens_per_second_per_gpu": 1808.54
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.4097222222222222,
|
| 652 |
+
"grad_norm": 0.0661102756857872,
|
| 653 |
+
"learning_rate": 0.00019926713853197695,
|
| 654 |
+
"loss": 0.9055,
|
| 655 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 656 |
+
"memory/max_active (GiB)": 24.74,
|
| 657 |
+
"memory/max_allocated (GiB)": 24.74,
|
| 658 |
+
"step": 59,
|
| 659 |
+
"tokens_per_second_per_gpu": 1802.3
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.4166666666666667,
|
| 663 |
+
"grad_norm": 0.08663811534643173,
|
| 664 |
+
"learning_rate": 0.0001991663070272206,
|
| 665 |
+
"loss": 0.9826,
|
| 666 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 667 |
+
"memory/max_active (GiB)": 24.17,
|
| 668 |
+
"memory/max_allocated (GiB)": 24.17,
|
| 669 |
+
"step": 60,
|
| 670 |
+
"tokens_per_second_per_gpu": 1707.88
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.4236111111111111,
|
| 674 |
+
"grad_norm": 0.07683200389146805,
|
| 675 |
+
"learning_rate": 0.0001990590076369715,
|
| 676 |
+
"loss": 0.9759,
|
| 677 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 678 |
+
"memory/max_active (GiB)": 27.95,
|
| 679 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 680 |
+
"step": 61,
|
| 681 |
+
"tokens_per_second_per_gpu": 1895.98
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.4305555555555556,
|
| 685 |
+
"grad_norm": 0.07595925778150558,
|
| 686 |
+
"learning_rate": 0.00019894524735957622,
|
| 687 |
+
"loss": 0.9168,
|
| 688 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 689 |
+
"memory/max_active (GiB)": 28.9,
|
| 690 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 691 |
+
"step": 62,
|
| 692 |
+
"tokens_per_second_per_gpu": 1797.18
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.4375,
|
| 696 |
+
"grad_norm": 0.07661418616771698,
|
| 697 |
+
"learning_rate": 0.00019882503361477705,
|
| 698 |
+
"loss": 0.9679,
|
| 699 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 700 |
+
"memory/max_active (GiB)": 28.15,
|
| 701 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 702 |
+
"step": 63,
|
| 703 |
+
"tokens_per_second_per_gpu": 1830.69
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.4444444444444444,
|
| 707 |
+
"grad_norm": 0.08054457604885101,
|
| 708 |
+
"learning_rate": 0.00019869837424322829,
|
| 709 |
+
"loss": 0.9592,
|
| 710 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 711 |
+
"memory/max_active (GiB)": 27.95,
|
| 712 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 713 |
+
"step": 64,
|
| 714 |
+
"tokens_per_second_per_gpu": 1798.08
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.4513888888888889,
|
| 718 |
+
"grad_norm": 0.08320043236017227,
|
| 719 |
+
"learning_rate": 0.00019856527750598493,
|
| 720 |
+
"loss": 0.9257,
|
| 721 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 722 |
+
"memory/max_active (GiB)": 28.15,
|
| 723 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 724 |
+
"step": 65,
|
| 725 |
+
"tokens_per_second_per_gpu": 1795.23
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.4583333333333333,
|
| 729 |
+
"grad_norm": 0.0733579471707344,
|
| 730 |
+
"learning_rate": 0.00019842575208396372,
|
| 731 |
+
"loss": 0.8969,
|
| 732 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 733 |
+
"memory/max_active (GiB)": 28.15,
|
| 734 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 735 |
+
"step": 66,
|
| 736 |
+
"tokens_per_second_per_gpu": 1861.37
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.4652777777777778,
|
| 740 |
+
"grad_norm": 0.29595091938972473,
|
| 741 |
+
"learning_rate": 0.00019827980707737703,
|
| 742 |
+
"loss": 0.8604,
|
| 743 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 744 |
+
"memory/max_active (GiB)": 28.15,
|
| 745 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 746 |
+
"step": 67,
|
| 747 |
+
"tokens_per_second_per_gpu": 1844.94
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.4722222222222222,
|
| 751 |
+
"grad_norm": 0.10486430674791336,
|
| 752 |
+
"learning_rate": 0.00019812745200513927,
|
| 753 |
+
"loss": 0.9479,
|
| 754 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 755 |
+
"memory/max_active (GiB)": 27.2,
|
| 756 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 757 |
+
"step": 68,
|
| 758 |
+
"tokens_per_second_per_gpu": 1823.2
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.4791666666666667,
|
| 762 |
+
"grad_norm": 0.13543325662612915,
|
| 763 |
+
"learning_rate": 0.0001979686968042461,
|
| 764 |
+
"loss": 0.9287,
|
| 765 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 766 |
+
"memory/max_active (GiB)": 25.68,
|
| 767 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 768 |
+
"step": 69,
|
| 769 |
+
"tokens_per_second_per_gpu": 1821.33
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.4861111111111111,
|
| 773 |
+
"grad_norm": 0.07873474061489105,
|
| 774 |
+
"learning_rate": 0.00019780355182912626,
|
| 775 |
+
"loss": 0.9248,
|
| 776 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 777 |
+
"memory/max_active (GiB)": 27.95,
|
| 778 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 779 |
+
"step": 70,
|
| 780 |
+
"tokens_per_second_per_gpu": 1771.5
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4930555555555556,
|
| 784 |
+
"grad_norm": 0.06926668435335159,
|
| 785 |
+
"learning_rate": 0.0001976320278509663,
|
| 786 |
+
"loss": 0.9172,
|
| 787 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 788 |
+
"memory/max_active (GiB)": 26.06,
|
| 789 |
+
"memory/max_allocated (GiB)": 26.06,
|
| 790 |
+
"step": 71,
|
| 791 |
+
"tokens_per_second_per_gpu": 1875.05
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.5,
|
| 795 |
+
"grad_norm": 0.08082268387079239,
|
| 796 |
+
"learning_rate": 0.0001974541360570079,
|
| 797 |
+
"loss": 0.8823,
|
| 798 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 799 |
+
"memory/max_active (GiB)": 28.9,
|
| 800 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 801 |
+
"step": 72,
|
| 802 |
+
"tokens_per_second_per_gpu": 1865.89
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.5069444444444444,
|
| 806 |
+
"grad_norm": 0.07178379595279694,
|
| 807 |
+
"learning_rate": 0.00019726988804981844,
|
| 808 |
+
"loss": 0.9185,
|
| 809 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 810 |
+
"memory/max_active (GiB)": 27.2,
|
| 811 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 812 |
+
"step": 73,
|
| 813 |
+
"tokens_per_second_per_gpu": 1854.53
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.5138888888888888,
|
| 817 |
+
"grad_norm": 0.07196955382823944,
|
| 818 |
+
"learning_rate": 0.00019707929584653408,
|
| 819 |
+
"loss": 0.9461,
|
| 820 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 821 |
+
"memory/max_active (GiB)": 28.15,
|
| 822 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 823 |
+
"step": 74,
|
| 824 |
+
"tokens_per_second_per_gpu": 1820.12
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.5208333333333334,
|
| 828 |
+
"grad_norm": 0.07153692096471786,
|
| 829 |
+
"learning_rate": 0.00019688237187807594,
|
| 830 |
+
"loss": 1.0447,
|
| 831 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 832 |
+
"memory/max_active (GiB)": 25.68,
|
| 833 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 834 |
+
"step": 75,
|
| 835 |
+
"tokens_per_second_per_gpu": 1809.64
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.5277777777777778,
|
| 839 |
+
"grad_norm": 0.06721945106983185,
|
| 840 |
+
"learning_rate": 0.00019667912898833955,
|
| 841 |
+
"loss": 0.8106,
|
| 842 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 843 |
+
"memory/max_active (GiB)": 23.22,
|
| 844 |
+
"memory/max_allocated (GiB)": 23.22,
|
| 845 |
+
"step": 76,
|
| 846 |
+
"tokens_per_second_per_gpu": 1785.2
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.5347222222222222,
|
| 850 |
+
"grad_norm": 0.08322236686944962,
|
| 851 |
+
"learning_rate": 0.00019646958043335677,
|
| 852 |
+
"loss": 0.9299,
|
| 853 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 854 |
+
"memory/max_active (GiB)": 24.64,
|
| 855 |
+
"memory/max_allocated (GiB)": 24.64,
|
| 856 |
+
"step": 77,
|
| 857 |
+
"tokens_per_second_per_gpu": 1836.34
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.5416666666666666,
|
| 861 |
+
"grad_norm": 0.06773433834314346,
|
| 862 |
+
"learning_rate": 0.00019625373988043165,
|
| 863 |
+
"loss": 0.9262,
|
| 864 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 865 |
+
"memory/max_active (GiB)": 27.95,
|
| 866 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 867 |
+
"step": 78,
|
| 868 |
+
"tokens_per_second_per_gpu": 1850.19
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.5486111111111112,
|
| 872 |
+
"grad_norm": 0.06558340042829514,
|
| 873 |
+
"learning_rate": 0.00019603162140724862,
|
| 874 |
+
"loss": 0.9067,
|
| 875 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 876 |
+
"memory/max_active (GiB)": 27.2,
|
| 877 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 878 |
+
"step": 79,
|
| 879 |
+
"tokens_per_second_per_gpu": 1876.53
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.5555555555555556,
|
| 883 |
+
"grad_norm": 0.06962298601865768,
|
| 884 |
+
"learning_rate": 0.0001958032395009545,
|
| 885 |
+
"loss": 0.8971,
|
| 886 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 887 |
+
"memory/max_active (GiB)": 25.68,
|
| 888 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 889 |
+
"step": 80,
|
| 890 |
+
"tokens_per_second_per_gpu": 1767.39
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.5625,
|
| 894 |
+
"grad_norm": 0.08821487426757812,
|
| 895 |
+
"learning_rate": 0.00019556860905721362,
|
| 896 |
+
"loss": 0.9593,
|
| 897 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 898 |
+
"memory/max_active (GiB)": 25.11,
|
| 899 |
+
"memory/max_allocated (GiB)": 25.11,
|
| 900 |
+
"step": 81,
|
| 901 |
+
"tokens_per_second_per_gpu": 1789.22
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.5694444444444444,
|
| 905 |
+
"grad_norm": 0.07249249517917633,
|
| 906 |
+
"learning_rate": 0.00019532774537923617,
|
| 907 |
+
"loss": 0.9409,
|
| 908 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 909 |
+
"memory/max_active (GiB)": 27.44,
|
| 910 |
+
"memory/max_allocated (GiB)": 27.44,
|
| 911 |
+
"step": 82,
|
| 912 |
+
"tokens_per_second_per_gpu": 1764.78
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.5763888888888888,
|
| 916 |
+
"grad_norm": 0.08999690413475037,
|
| 917 |
+
"learning_rate": 0.00019508066417678018,
|
| 918 |
+
"loss": 0.8989,
|
| 919 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 920 |
+
"memory/max_active (GiB)": 28.9,
|
| 921 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 922 |
+
"step": 83,
|
| 923 |
+
"tokens_per_second_per_gpu": 1821.55
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.5833333333333334,
|
| 927 |
+
"grad_norm": 0.06516412645578384,
|
| 928 |
+
"learning_rate": 0.00019482738156512692,
|
| 929 |
+
"loss": 0.957,
|
| 930 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 931 |
+
"memory/max_active (GiB)": 28.38,
|
| 932 |
+
"memory/max_allocated (GiB)": 28.38,
|
| 933 |
+
"step": 84,
|
| 934 |
+
"tokens_per_second_per_gpu": 1902.34
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5902777777777778,
|
| 938 |
+
"grad_norm": 0.0862964540719986,
|
| 939 |
+
"learning_rate": 0.00019456791406402964,
|
| 940 |
+
"loss": 0.9576,
|
| 941 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 942 |
+
"memory/max_active (GiB)": 28.9,
|
| 943 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 944 |
+
"step": 85,
|
| 945 |
+
"tokens_per_second_per_gpu": 1848.41
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.5972222222222222,
|
| 949 |
+
"grad_norm": 0.11609019339084625,
|
| 950 |
+
"learning_rate": 0.00019430227859663633,
|
| 951 |
+
"loss": 0.9729,
|
| 952 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 953 |
+
"memory/max_active (GiB)": 28.15,
|
| 954 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 955 |
+
"step": 86,
|
| 956 |
+
"tokens_per_second_per_gpu": 1869.76
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.6041666666666666,
|
| 960 |
+
"grad_norm": 0.08986852318048477,
|
| 961 |
+
"learning_rate": 0.00019403049248838578,
|
| 962 |
+
"loss": 0.9315,
|
| 963 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 964 |
+
"memory/max_active (GiB)": 27.01,
|
| 965 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 966 |
+
"step": 87,
|
| 967 |
+
"tokens_per_second_per_gpu": 1824.83
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.6111111111111112,
|
| 971 |
+
"grad_norm": 0.08460818976163864,
|
| 972 |
+
"learning_rate": 0.00019375257346587773,
|
| 973 |
+
"loss": 0.9937,
|
| 974 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 975 |
+
"memory/max_active (GiB)": 28.9,
|
| 976 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 977 |
+
"step": 88,
|
| 978 |
+
"tokens_per_second_per_gpu": 1763.25
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.6180555555555556,
|
| 982 |
+
"grad_norm": 0.07170393317937851,
|
| 983 |
+
"learning_rate": 0.0001934685396557165,
|
| 984 |
+
"loss": 0.937,
|
| 985 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 986 |
+
"memory/max_active (GiB)": 27.95,
|
| 987 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 988 |
+
"step": 89,
|
| 989 |
+
"tokens_per_second_per_gpu": 1806.52
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.625,
|
| 993 |
+
"grad_norm": 0.1740889698266983,
|
| 994 |
+
"learning_rate": 0.00019317840958332888,
|
| 995 |
+
"loss": 0.8459,
|
| 996 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 997 |
+
"memory/max_active (GiB)": 28.9,
|
| 998 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 999 |
+
"step": 90,
|
| 1000 |
+
"tokens_per_second_per_gpu": 1882.4
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.6319444444444444,
|
| 1004 |
+
"grad_norm": 0.06397266685962677,
|
| 1005 |
+
"learning_rate": 0.00019288220217175583,
|
| 1006 |
+
"loss": 0.7879,
|
| 1007 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1008 |
+
"memory/max_active (GiB)": 28.9,
|
| 1009 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1010 |
+
"step": 91,
|
| 1011 |
+
"tokens_per_second_per_gpu": 1867.77
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.6388888888888888,
|
| 1015 |
+
"grad_norm": 0.06102391704916954,
|
| 1016 |
+
"learning_rate": 0.00019257993674041813,
|
| 1017 |
+
"loss": 0.8671,
|
| 1018 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1019 |
+
"memory/max_active (GiB)": 28.15,
|
| 1020 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 1021 |
+
"step": 92,
|
| 1022 |
+
"tokens_per_second_per_gpu": 1878.38
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.6458333333333334,
|
| 1026 |
+
"grad_norm": 0.06330034881830215,
|
| 1027 |
+
"learning_rate": 0.00019227163300385662,
|
| 1028 |
+
"loss": 0.9089,
|
| 1029 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1030 |
+
"memory/max_active (GiB)": 28.9,
|
| 1031 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1032 |
+
"step": 93,
|
| 1033 |
+
"tokens_per_second_per_gpu": 1859.18
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.6527777777777778,
|
| 1037 |
+
"grad_norm": 0.07149945199489594,
|
| 1038 |
+
"learning_rate": 0.00019195731107044594,
|
| 1039 |
+
"loss": 0.8842,
|
| 1040 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1041 |
+
"memory/max_active (GiB)": 28.9,
|
| 1042 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1043 |
+
"step": 94,
|
| 1044 |
+
"tokens_per_second_per_gpu": 1784.86
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.6597222222222222,
|
| 1048 |
+
"grad_norm": 0.07301725447177887,
|
| 1049 |
+
"learning_rate": 0.0001916369914410834,
|
| 1050 |
+
"loss": 0.875,
|
| 1051 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1052 |
+
"memory/max_active (GiB)": 28.15,
|
| 1053 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 1054 |
+
"step": 95,
|
| 1055 |
+
"tokens_per_second_per_gpu": 1697.59
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.6666666666666666,
|
| 1059 |
+
"grad_norm": 0.060419220477342606,
|
| 1060 |
+
"learning_rate": 0.00019131069500785174,
|
| 1061 |
+
"loss": 0.798,
|
| 1062 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1063 |
+
"memory/max_active (GiB)": 27.95,
|
| 1064 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 1065 |
+
"step": 96,
|
| 1066 |
+
"tokens_per_second_per_gpu": 1802.63
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.6736111111111112,
|
| 1070 |
+
"grad_norm": 0.06787065416574478,
|
| 1071 |
+
"learning_rate": 0.00019097844305265624,
|
| 1072 |
+
"loss": 0.8801,
|
| 1073 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1074 |
+
"memory/max_active (GiB)": 28.9,
|
| 1075 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1076 |
+
"step": 97,
|
| 1077 |
+
"tokens_per_second_per_gpu": 1756.93
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.6805555555555556,
|
| 1081 |
+
"grad_norm": 0.07948441058397293,
|
| 1082 |
+
"learning_rate": 0.0001906402572458371,
|
| 1083 |
+
"loss": 0.9047,
|
| 1084 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1085 |
+
"memory/max_active (GiB)": 27.01,
|
| 1086 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 1087 |
+
"step": 98,
|
| 1088 |
+
"tokens_per_second_per_gpu": 1838.22
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.6875,
|
| 1092 |
+
"grad_norm": 0.06950388848781586,
|
| 1093 |
+
"learning_rate": 0.0001902961596447557,
|
| 1094 |
+
"loss": 0.9473,
|
| 1095 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1096 |
+
"memory/max_active (GiB)": 26.06,
|
| 1097 |
+
"memory/max_allocated (GiB)": 26.06,
|
| 1098 |
+
"step": 99,
|
| 1099 |
+
"tokens_per_second_per_gpu": 1809.3
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.6944444444444444,
|
| 1103 |
+
"grad_norm": 0.059347931295633316,
|
| 1104 |
+
"learning_rate": 0.00018994617269235616,
|
| 1105 |
+
"loss": 0.837,
|
| 1106 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1107 |
+
"memory/max_active (GiB)": 28.9,
|
| 1108 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1109 |
+
"step": 100,
|
| 1110 |
+
"tokens_per_second_per_gpu": 1897.82
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 0.7013888888888888,
|
| 1114 |
+
"grad_norm": 0.0786047875881195,
|
| 1115 |
+
"learning_rate": 0.00018959031921570135,
|
| 1116 |
+
"loss": 0.8884,
|
| 1117 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1118 |
+
"memory/max_active (GiB)": 24.17,
|
| 1119 |
+
"memory/max_allocated (GiB)": 24.17,
|
| 1120 |
+
"step": 101,
|
| 1121 |
+
"tokens_per_second_per_gpu": 1783.4
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 0.7083333333333334,
|
| 1125 |
+
"grad_norm": 0.0657181590795517,
|
| 1126 |
+
"learning_rate": 0.0001892286224244843,
|
| 1127 |
+
"loss": 0.9047,
|
| 1128 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1129 |
+
"memory/max_active (GiB)": 28.15,
|
| 1130 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 1131 |
+
"step": 102,
|
| 1132 |
+
"tokens_per_second_per_gpu": 1810.31
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.7152777777777778,
|
| 1136 |
+
"grad_norm": 0.07979200780391693,
|
| 1137 |
+
"learning_rate": 0.00018886110590951417,
|
| 1138 |
+
"loss": 0.9022,
|
| 1139 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1140 |
+
"memory/max_active (GiB)": 25.11,
|
| 1141 |
+
"memory/max_allocated (GiB)": 25.11,
|
| 1142 |
+
"step": 103,
|
| 1143 |
+
"tokens_per_second_per_gpu": 1739.77
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.7222222222222222,
|
| 1147 |
+
"grad_norm": 0.07467928528785706,
|
| 1148 |
+
"learning_rate": 0.00018848779364117775,
|
| 1149 |
+
"loss": 0.8916,
|
| 1150 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1151 |
+
"memory/max_active (GiB)": 24.64,
|
| 1152 |
+
"memory/max_allocated (GiB)": 24.64,
|
| 1153 |
+
"step": 104,
|
| 1154 |
+
"tokens_per_second_per_gpu": 1796.23
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.7291666666666666,
|
| 1158 |
+
"grad_norm": 0.07130390405654907,
|
| 1159 |
+
"learning_rate": 0.000188108709967876,
|
| 1160 |
+
"loss": 0.9186,
|
| 1161 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1162 |
+
"memory/max_active (GiB)": 28.9,
|
| 1163 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1164 |
+
"step": 105,
|
| 1165 |
+
"tokens_per_second_per_gpu": 1834.56
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.7361111111111112,
|
| 1169 |
+
"grad_norm": 0.08154763281345367,
|
| 1170 |
+
"learning_rate": 0.000187723879614436,
|
| 1171 |
+
"loss": 0.9381,
|
| 1172 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1173 |
+
"memory/max_active (GiB)": 26.06,
|
| 1174 |
+
"memory/max_allocated (GiB)": 26.06,
|
| 1175 |
+
"step": 106,
|
| 1176 |
+
"tokens_per_second_per_gpu": 1711.53
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 0.7430555555555556,
|
| 1180 |
+
"grad_norm": 0.07683106511831284,
|
| 1181 |
+
"learning_rate": 0.00018733332768049827,
|
| 1182 |
+
"loss": 0.9567,
|
| 1183 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1184 |
+
"memory/max_active (GiB)": 27.95,
|
| 1185 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 1186 |
+
"step": 107,
|
| 1187 |
+
"tokens_per_second_per_gpu": 1720.36
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.75,
|
| 1191 |
+
"grad_norm": 0.07069261372089386,
|
| 1192 |
+
"learning_rate": 0.00018693707963887978,
|
| 1193 |
+
"loss": 0.9454,
|
| 1194 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1195 |
+
"memory/max_active (GiB)": 26.06,
|
| 1196 |
+
"memory/max_allocated (GiB)": 26.06,
|
| 1197 |
+
"step": 108,
|
| 1198 |
+
"tokens_per_second_per_gpu": 1795.58
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 0.7569444444444444,
|
| 1202 |
+
"grad_norm": 0.07336299121379852,
|
| 1203 |
+
"learning_rate": 0.0001865351613339125,
|
| 1204 |
+
"loss": 0.9739,
|
| 1205 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1206 |
+
"memory/max_active (GiB)": 25.68,
|
| 1207 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 1208 |
+
"step": 109,
|
| 1209 |
+
"tokens_per_second_per_gpu": 1695.16
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.7638888888888888,
|
| 1213 |
+
"grad_norm": 0.0726110115647316,
|
| 1214 |
+
"learning_rate": 0.0001861275989797578,
|
| 1215 |
+
"loss": 0.8957,
|
| 1216 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1217 |
+
"memory/max_active (GiB)": 28.9,
|
| 1218 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1219 |
+
"step": 110,
|
| 1220 |
+
"tokens_per_second_per_gpu": 1866.56
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.7708333333333334,
|
| 1224 |
+
"grad_norm": 0.08780913054943085,
|
| 1225 |
+
"learning_rate": 0.00018571441915869662,
|
| 1226 |
+
"loss": 0.9204,
|
| 1227 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1228 |
+
"memory/max_active (GiB)": 27.2,
|
| 1229 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 1230 |
+
"step": 111,
|
| 1231 |
+
"tokens_per_second_per_gpu": 1820.22
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.7777777777777778,
|
| 1235 |
+
"grad_norm": 0.10503561049699783,
|
| 1236 |
+
"learning_rate": 0.0001852956488193959,
|
| 1237 |
+
"loss": 0.9357,
|
| 1238 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1239 |
+
"memory/max_active (GiB)": 28.9,
|
| 1240 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1241 |
+
"step": 112,
|
| 1242 |
+
"tokens_per_second_per_gpu": 1793.45
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.7847222222222222,
|
| 1246 |
+
"grad_norm": 0.06898421794176102,
|
| 1247 |
+
"learning_rate": 0.0001848713152751506,
|
| 1248 |
+
"loss": 0.8725,
|
| 1249 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1250 |
+
"memory/max_active (GiB)": 27.01,
|
| 1251 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 1252 |
+
"step": 113,
|
| 1253 |
+
"tokens_per_second_per_gpu": 1794.32
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 0.7916666666666666,
|
| 1257 |
+
"grad_norm": 0.06764024496078491,
|
| 1258 |
+
"learning_rate": 0.00018444144620210256,
|
| 1259 |
+
"loss": 0.9115,
|
| 1260 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1261 |
+
"memory/max_active (GiB)": 27.01,
|
| 1262 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 1263 |
+
"step": 114,
|
| 1264 |
+
"tokens_per_second_per_gpu": 1811.27
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.7986111111111112,
|
| 1268 |
+
"grad_norm": 0.07626543939113617,
|
| 1269 |
+
"learning_rate": 0.00018400606963743518,
|
| 1270 |
+
"loss": 0.866,
|
| 1271 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1272 |
+
"memory/max_active (GiB)": 27.01,
|
| 1273 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 1274 |
+
"step": 115,
|
| 1275 |
+
"tokens_per_second_per_gpu": 1798.98
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.8055555555555556,
|
| 1279 |
+
"grad_norm": 0.06234179437160492,
|
| 1280 |
+
"learning_rate": 0.00018356521397754495,
|
| 1281 |
+
"loss": 0.911,
|
| 1282 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1283 |
+
"memory/max_active (GiB)": 27.95,
|
| 1284 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 1285 |
+
"step": 116,
|
| 1286 |
+
"tokens_per_second_per_gpu": 1837.38
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.8125,
|
| 1290 |
+
"grad_norm": 0.07429645955562592,
|
| 1291 |
+
"learning_rate": 0.00018311890797618915,
|
| 1292 |
+
"loss": 0.9853,
|
| 1293 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1294 |
+
"memory/max_active (GiB)": 28.9,
|
| 1295 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1296 |
+
"step": 117,
|
| 1297 |
+
"tokens_per_second_per_gpu": 1909.7
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.8194444444444444,
|
| 1301 |
+
"grad_norm": 0.0701533630490303,
|
| 1302 |
+
"learning_rate": 0.00018266718074261062,
|
| 1303 |
+
"loss": 0.8815,
|
| 1304 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1305 |
+
"memory/max_active (GiB)": 27.01,
|
| 1306 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 1307 |
+
"step": 118,
|
| 1308 |
+
"tokens_per_second_per_gpu": 1862.25
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.8263888888888888,
|
| 1312 |
+
"grad_norm": 0.08356419950723648,
|
| 1313 |
+
"learning_rate": 0.00018221006173963912,
|
| 1314 |
+
"loss": 0.9683,
|
| 1315 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1316 |
+
"memory/max_active (GiB)": 25.68,
|
| 1317 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 1318 |
+
"step": 119,
|
| 1319 |
+
"tokens_per_second_per_gpu": 1779.76
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.8333333333333334,
|
| 1323 |
+
"grad_norm": 0.06717222929000854,
|
| 1324 |
+
"learning_rate": 0.00018174758078176963,
|
| 1325 |
+
"loss": 0.8591,
|
| 1326 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1327 |
+
"memory/max_active (GiB)": 24.17,
|
| 1328 |
+
"memory/max_allocated (GiB)": 24.17,
|
| 1329 |
+
"step": 120,
|
| 1330 |
+
"tokens_per_second_per_gpu": 1819.98
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.8402777777777778,
|
| 1334 |
+
"grad_norm": 0.07267988473176956,
|
| 1335 |
+
"learning_rate": 0.00018127976803321793,
|
| 1336 |
+
"loss": 0.8717,
|
| 1337 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1338 |
+
"memory/max_active (GiB)": 27.01,
|
| 1339 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 1340 |
+
"step": 121,
|
| 1341 |
+
"tokens_per_second_per_gpu": 1790.21
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.8472222222222222,
|
| 1345 |
+
"grad_norm": 0.07312195748090744,
|
| 1346 |
+
"learning_rate": 0.00018080665400595303,
|
| 1347 |
+
"loss": 0.8591,
|
| 1348 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1349 |
+
"memory/max_active (GiB)": 25.68,
|
| 1350 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 1351 |
+
"step": 122,
|
| 1352 |
+
"tokens_per_second_per_gpu": 1784.17
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.8541666666666666,
|
| 1356 |
+
"grad_norm": 0.06259205937385559,
|
| 1357 |
+
"learning_rate": 0.00018032826955770724,
|
| 1358 |
+
"loss": 0.826,
|
| 1359 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1360 |
+
"memory/max_active (GiB)": 28.15,
|
| 1361 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 1362 |
+
"step": 123,
|
| 1363 |
+
"tokens_per_second_per_gpu": 1872.69
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.8611111111111112,
|
| 1367 |
+
"grad_norm": 0.062194038182497025,
|
| 1368 |
+
"learning_rate": 0.00017984464588996342,
|
| 1369 |
+
"loss": 0.8974,
|
| 1370 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1371 |
+
"memory/max_active (GiB)": 28.15,
|
| 1372 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 1373 |
+
"step": 124,
|
| 1374 |
+
"tokens_per_second_per_gpu": 1856.73
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.8680555555555556,
|
| 1378 |
+
"grad_norm": 0.06809177249670029,
|
| 1379 |
+
"learning_rate": 0.00017935581454592002,
|
| 1380 |
+
"loss": 0.8899,
|
| 1381 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1382 |
+
"memory/max_active (GiB)": 27.95,
|
| 1383 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 1384 |
+
"step": 125,
|
| 1385 |
+
"tokens_per_second_per_gpu": 1904.82
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.875,
|
| 1389 |
+
"grad_norm": 0.058420922607183456,
|
| 1390 |
+
"learning_rate": 0.00017886180740843383,
|
| 1391 |
+
"loss": 0.8287,
|
| 1392 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1393 |
+
"memory/max_active (GiB)": 27.2,
|
| 1394 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 1395 |
+
"step": 126,
|
| 1396 |
+
"tokens_per_second_per_gpu": 1699.16
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.8819444444444444,
|
| 1400 |
+
"grad_norm": 0.06883256137371063,
|
| 1401 |
+
"learning_rate": 0.00017836265669794033,
|
| 1402 |
+
"loss": 0.7913,
|
| 1403 |
+
"memory/device_reserved (GiB)": 32.39,
|
| 1404 |
+
"memory/max_active (GiB)": 27.95,
|
| 1405 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 1406 |
+
"step": 127,
|
| 1407 |
+
"tokens_per_second_per_gpu": 1877.6
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 0.8888888888888888,
|
| 1411 |
+
"grad_norm": 0.06439166516065598,
|
| 1412 |
+
"learning_rate": 0.00017785839497035222,
|
| 1413 |
+
"loss": 0.8462,
|
| 1414 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1415 |
+
"memory/max_active (GiB)": 28.9,
|
| 1416 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1417 |
+
"step": 128,
|
| 1418 |
+
"tokens_per_second_per_gpu": 1785.45
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.8958333333333334,
|
| 1422 |
+
"grad_norm": 0.07990575581789017,
|
| 1423 |
+
"learning_rate": 0.00017734905511493615,
|
| 1424 |
+
"loss": 0.9299,
|
| 1425 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1426 |
+
"memory/max_active (GiB)": 25.68,
|
| 1427 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 1428 |
+
"step": 129,
|
| 1429 |
+
"tokens_per_second_per_gpu": 1863.91
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 0.9027777777777778,
|
| 1433 |
+
"grad_norm": 0.13562186062335968,
|
| 1434 |
+
"learning_rate": 0.0001768346703521675,
|
| 1435 |
+
"loss": 0.8973,
|
| 1436 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1437 |
+
"memory/max_active (GiB)": 25.11,
|
| 1438 |
+
"memory/max_allocated (GiB)": 25.11,
|
| 1439 |
+
"step": 130,
|
| 1440 |
+
"tokens_per_second_per_gpu": 1841.01
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 0.9097222222222222,
|
| 1444 |
+
"grad_norm": 0.0757925733923912,
|
| 1445 |
+
"learning_rate": 0.0001763152742315637,
|
| 1446 |
+
"loss": 0.8393,
|
| 1447 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1448 |
+
"memory/max_active (GiB)": 26.06,
|
| 1449 |
+
"memory/max_allocated (GiB)": 26.06,
|
| 1450 |
+
"step": 131,
|
| 1451 |
+
"tokens_per_second_per_gpu": 1841.76
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.9166666666666666,
|
| 1455 |
+
"grad_norm": 0.1594410538673401,
|
| 1456 |
+
"learning_rate": 0.000175790900629496,
|
| 1457 |
+
"loss": 0.9476,
|
| 1458 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1459 |
+
"memory/max_active (GiB)": 28.15,
|
| 1460 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 1461 |
+
"step": 132,
|
| 1462 |
+
"tokens_per_second_per_gpu": 1900.8
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 0.9236111111111112,
|
| 1466 |
+
"grad_norm": 0.07541660219430923,
|
| 1467 |
+
"learning_rate": 0.00017526158374698,
|
| 1468 |
+
"loss": 0.8889,
|
| 1469 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1470 |
+
"memory/max_active (GiB)": 27.2,
|
| 1471 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 1472 |
+
"step": 133,
|
| 1473 |
+
"tokens_per_second_per_gpu": 1862.75
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.9305555555555556,
|
| 1477 |
+
"grad_norm": 0.06783576309680939,
|
| 1478 |
+
"learning_rate": 0.00017472735810744494,
|
| 1479 |
+
"loss": 0.8986,
|
| 1480 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1481 |
+
"memory/max_active (GiB)": 25.11,
|
| 1482 |
+
"memory/max_allocated (GiB)": 25.11,
|
| 1483 |
+
"step": 134,
|
| 1484 |
+
"tokens_per_second_per_gpu": 1834.08
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.9375,
|
| 1488 |
+
"grad_norm": 0.08990088850259781,
|
| 1489 |
+
"learning_rate": 0.00017418825855448206,
|
| 1490 |
+
"loss": 0.8216,
|
| 1491 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1492 |
+
"memory/max_active (GiB)": 24.17,
|
| 1493 |
+
"memory/max_allocated (GiB)": 24.17,
|
| 1494 |
+
"step": 135,
|
| 1495 |
+
"tokens_per_second_per_gpu": 1756.08
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 0.9444444444444444,
|
| 1499 |
+
"grad_norm": 0.06768841296434402,
|
| 1500 |
+
"learning_rate": 0.00017364432024957193,
|
| 1501 |
+
"loss": 0.9572,
|
| 1502 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1503 |
+
"memory/max_active (GiB)": 27.44,
|
| 1504 |
+
"memory/max_allocated (GiB)": 27.44,
|
| 1505 |
+
"step": 136,
|
| 1506 |
+
"tokens_per_second_per_gpu": 1894.76
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.9513888888888888,
|
| 1510 |
+
"grad_norm": 0.07805129885673523,
|
| 1511 |
+
"learning_rate": 0.00017309557866979113,
|
| 1512 |
+
"loss": 0.9175,
|
| 1513 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1514 |
+
"memory/max_active (GiB)": 24.74,
|
| 1515 |
+
"memory/max_allocated (GiB)": 24.74,
|
| 1516 |
+
"step": 137,
|
| 1517 |
+
"tokens_per_second_per_gpu": 1814.77
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.9583333333333334,
|
| 1521 |
+
"grad_norm": 0.07132866978645325,
|
| 1522 |
+
"learning_rate": 0.00017254206960549842,
|
| 1523 |
+
"loss": 0.9275,
|
| 1524 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1525 |
+
"memory/max_active (GiB)": 26.49,
|
| 1526 |
+
"memory/max_allocated (GiB)": 26.49,
|
| 1527 |
+
"step": 138,
|
| 1528 |
+
"tokens_per_second_per_gpu": 1802.23
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.9652777777777778,
|
| 1532 |
+
"grad_norm": 0.0779808983206749,
|
| 1533 |
+
"learning_rate": 0.00017198382915800033,
|
| 1534 |
+
"loss": 0.9107,
|
| 1535 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1536 |
+
"memory/max_active (GiB)": 26.25,
|
| 1537 |
+
"memory/max_allocated (GiB)": 26.25,
|
| 1538 |
+
"step": 139,
|
| 1539 |
+
"tokens_per_second_per_gpu": 1816.41
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.9722222222222222,
|
| 1543 |
+
"grad_norm": 0.07991725951433182,
|
| 1544 |
+
"learning_rate": 0.0001714208937371965,
|
| 1545 |
+
"loss": 0.8597,
|
| 1546 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1547 |
+
"memory/max_active (GiB)": 24.64,
|
| 1548 |
+
"memory/max_allocated (GiB)": 24.64,
|
| 1549 |
+
"step": 140,
|
| 1550 |
+
"tokens_per_second_per_gpu": 1831.07
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.9791666666666666,
|
| 1554 |
+
"grad_norm": 0.07846493273973465,
|
| 1555 |
+
"learning_rate": 0.00017085330005920516,
|
| 1556 |
+
"loss": 0.9037,
|
| 1557 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1558 |
+
"memory/max_active (GiB)": 27.2,
|
| 1559 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 1560 |
+
"step": 141,
|
| 1561 |
+
"tokens_per_second_per_gpu": 1772.26
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.9861111111111112,
|
| 1565 |
+
"grad_norm": 0.07660206407308578,
|
| 1566 |
+
"learning_rate": 0.00017028108514396799,
|
| 1567 |
+
"loss": 0.8545,
|
| 1568 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1569 |
+
"memory/max_active (GiB)": 27.2,
|
| 1570 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 1571 |
+
"step": 142,
|
| 1572 |
+
"tokens_per_second_per_gpu": 1841.68
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 0.9930555555555556,
|
| 1576 |
+
"grad_norm": 0.06597072631120682,
|
| 1577 |
+
"learning_rate": 0.000169704286312836,
|
| 1578 |
+
"loss": 0.8313,
|
| 1579 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1580 |
+
"memory/max_active (GiB)": 27.95,
|
| 1581 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 1582 |
+
"step": 143,
|
| 1583 |
+
"tokens_per_second_per_gpu": 1819.32
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 1.0,
|
| 1587 |
+
"grad_norm": 0.12106018513441086,
|
| 1588 |
+
"learning_rate": 0.00016912294118613517,
|
| 1589 |
+
"loss": 0.9172,
|
| 1590 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1591 |
+
"memory/max_active (GiB)": 28.15,
|
| 1592 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 1593 |
+
"step": 144,
|
| 1594 |
+
"tokens_per_second_per_gpu": 1816.15
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 1.0069444444444444,
|
| 1598 |
+
"grad_norm": 0.07370701432228088,
|
| 1599 |
+
"learning_rate": 0.00016853708768071264,
|
| 1600 |
+
"loss": 0.9025,
|
| 1601 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1602 |
+
"memory/max_active (GiB)": 27.2,
|
| 1603 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 1604 |
+
"step": 145,
|
| 1605 |
+
"tokens_per_second_per_gpu": 1740.51
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.0138888888888888,
|
| 1609 |
+
"grad_norm": 0.06994107365608215,
|
| 1610 |
+
"learning_rate": 0.0001679467640074639,
|
| 1611 |
+
"loss": 0.8453,
|
| 1612 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1613 |
+
"memory/max_active (GiB)": 27.95,
|
| 1614 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 1615 |
+
"step": 146,
|
| 1616 |
+
"tokens_per_second_per_gpu": 1858.12
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 1.0208333333333333,
|
| 1620 |
+
"grad_norm": 0.07402420789003372,
|
| 1621 |
+
"learning_rate": 0.00016735200866884036,
|
| 1622 |
+
"loss": 0.8769,
|
| 1623 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1624 |
+
"memory/max_active (GiB)": 27.95,
|
| 1625 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 1626 |
+
"step": 147,
|
| 1627 |
+
"tokens_per_second_per_gpu": 1768.73
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.0277777777777777,
|
| 1631 |
+
"grad_norm": 0.09437773376703262,
|
| 1632 |
+
"learning_rate": 0.00016675286045633828,
|
| 1633 |
+
"loss": 0.9602,
|
| 1634 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1635 |
+
"memory/max_active (GiB)": 25.11,
|
| 1636 |
+
"memory/max_allocated (GiB)": 25.11,
|
| 1637 |
+
"step": 148,
|
| 1638 |
+
"tokens_per_second_per_gpu": 1793.91
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 1.0347222222222223,
|
| 1642 |
+
"grad_norm": 0.09405123442411423,
|
| 1643 |
+
"learning_rate": 0.00016614935844796864,
|
| 1644 |
+
"loss": 0.9701,
|
| 1645 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1646 |
+
"memory/max_active (GiB)": 25.68,
|
| 1647 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 1648 |
+
"step": 149,
|
| 1649 |
+
"tokens_per_second_per_gpu": 1738.78
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.0416666666666667,
|
| 1653 |
+
"grad_norm": 0.0800110325217247,
|
| 1654 |
+
"learning_rate": 0.00016554154200570825,
|
| 1655 |
+
"loss": 0.9213,
|
| 1656 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1657 |
+
"memory/max_active (GiB)": 28.9,
|
| 1658 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1659 |
+
"step": 150,
|
| 1660 |
+
"tokens_per_second_per_gpu": 1838.3
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 1.0486111111111112,
|
| 1664 |
+
"grad_norm": 0.07217224687337875,
|
| 1665 |
+
"learning_rate": 0.0001649294507729327,
|
| 1666 |
+
"loss": 0.9151,
|
| 1667 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1668 |
+
"memory/max_active (GiB)": 24.74,
|
| 1669 |
+
"memory/max_allocated (GiB)": 24.74,
|
| 1670 |
+
"step": 151,
|
| 1671 |
+
"tokens_per_second_per_gpu": 1800.16
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 1.0555555555555556,
|
| 1675 |
+
"grad_norm": 0.11542835831642151,
|
| 1676 |
+
"learning_rate": 0.0001643131246718305,
|
| 1677 |
+
"loss": 0.8443,
|
| 1678 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1679 |
+
"memory/max_active (GiB)": 26.26,
|
| 1680 |
+
"memory/max_allocated (GiB)": 26.26,
|
| 1681 |
+
"step": 152,
|
| 1682 |
+
"tokens_per_second_per_gpu": 1808.4
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.0625,
|
| 1686 |
+
"grad_norm": 0.16738373041152954,
|
| 1687 |
+
"learning_rate": 0.00016369260390079933,
|
| 1688 |
+
"loss": 0.8658,
|
| 1689 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1690 |
+
"memory/max_active (GiB)": 24.74,
|
| 1691 |
+
"memory/max_allocated (GiB)": 24.74,
|
| 1692 |
+
"step": 153,
|
| 1693 |
+
"tokens_per_second_per_gpu": 1786.38
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 1.0694444444444444,
|
| 1697 |
+
"grad_norm": 0.08216153830289841,
|
| 1698 |
+
"learning_rate": 0.0001630679289318242,
|
| 1699 |
+
"loss": 0.8402,
|
| 1700 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1701 |
+
"memory/max_active (GiB)": 24.17,
|
| 1702 |
+
"memory/max_allocated (GiB)": 24.17,
|
| 1703 |
+
"step": 154,
|
| 1704 |
+
"tokens_per_second_per_gpu": 1721.01
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.0763888888888888,
|
| 1708 |
+
"grad_norm": 0.0893600732088089,
|
| 1709 |
+
"learning_rate": 0.00016243914050783785,
|
| 1710 |
+
"loss": 0.843,
|
| 1711 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1712 |
+
"memory/max_active (GiB)": 25.68,
|
| 1713 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 1714 |
+
"step": 155,
|
| 1715 |
+
"tokens_per_second_per_gpu": 1769.48
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 1.0833333333333333,
|
| 1719 |
+
"grad_norm": 0.08116093277931213,
|
| 1720 |
+
"learning_rate": 0.00016180627964006313,
|
| 1721 |
+
"loss": 0.8911,
|
| 1722 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1723 |
+
"memory/max_active (GiB)": 27.2,
|
| 1724 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 1725 |
+
"step": 156,
|
| 1726 |
+
"tokens_per_second_per_gpu": 1890.64
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 1.0902777777777777,
|
| 1730 |
+
"grad_norm": 0.08874551951885223,
|
| 1731 |
+
"learning_rate": 0.00016116938760533844,
|
| 1732 |
+
"loss": 0.9208,
|
| 1733 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1734 |
+
"memory/max_active (GiB)": 27.01,
|
| 1735 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 1736 |
+
"step": 157,
|
| 1737 |
+
"tokens_per_second_per_gpu": 1768.32
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.0972222222222223,
|
| 1741 |
+
"grad_norm": 0.10523993521928787,
|
| 1742 |
+
"learning_rate": 0.00016052850594342534,
|
| 1743 |
+
"loss": 0.9199,
|
| 1744 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1745 |
+
"memory/max_active (GiB)": 23.22,
|
| 1746 |
+
"memory/max_allocated (GiB)": 23.22,
|
| 1747 |
+
"step": 158,
|
| 1748 |
+
"tokens_per_second_per_gpu": 1866.22
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 1.1041666666666667,
|
| 1752 |
+
"grad_norm": 0.1344747096300125,
|
| 1753 |
+
"learning_rate": 0.00015988367645429938,
|
| 1754 |
+
"loss": 0.8523,
|
| 1755 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1756 |
+
"memory/max_active (GiB)": 25.11,
|
| 1757 |
+
"memory/max_allocated (GiB)": 25.11,
|
| 1758 |
+
"step": 159,
|
| 1759 |
+
"tokens_per_second_per_gpu": 1796.77
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.1111111111111112,
|
| 1763 |
+
"grad_norm": 0.10914891213178635,
|
| 1764 |
+
"learning_rate": 0.0001592349411954236,
|
| 1765 |
+
"loss": 0.9055,
|
| 1766 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1767 |
+
"memory/max_active (GiB)": 27.01,
|
| 1768 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 1769 |
+
"step": 160,
|
| 1770 |
+
"tokens_per_second_per_gpu": 1796.0
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 1.1180555555555556,
|
| 1774 |
+
"grad_norm": 0.09863642603158951,
|
| 1775 |
+
"learning_rate": 0.0001585823424790056,
|
| 1776 |
+
"loss": 0.834,
|
| 1777 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1778 |
+
"memory/max_active (GiB)": 26.26,
|
| 1779 |
+
"memory/max_allocated (GiB)": 26.26,
|
| 1780 |
+
"step": 161,
|
| 1781 |
+
"tokens_per_second_per_gpu": 1744.31
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.125,
|
| 1785 |
+
"grad_norm": 0.0731300413608551,
|
| 1786 |
+
"learning_rate": 0.0001579259228692378,
|
| 1787 |
+
"loss": 0.8731,
|
| 1788 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1789 |
+
"memory/max_active (GiB)": 27.01,
|
| 1790 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 1791 |
+
"step": 162,
|
| 1792 |
+
"tokens_per_second_per_gpu": 1840.36
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 1.1319444444444444,
|
| 1796 |
+
"grad_norm": 0.08072181046009064,
|
| 1797 |
+
"learning_rate": 0.00015726572517952122,
|
| 1798 |
+
"loss": 0.8169,
|
| 1799 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1800 |
+
"memory/max_active (GiB)": 28.9,
|
| 1801 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1802 |
+
"step": 163,
|
| 1803 |
+
"tokens_per_second_per_gpu": 1874.55
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 1.1388888888888888,
|
| 1807 |
+
"grad_norm": 0.07996222376823425,
|
| 1808 |
+
"learning_rate": 0.00015660179246967314,
|
| 1809 |
+
"loss": 0.8925,
|
| 1810 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1811 |
+
"memory/max_active (GiB)": 28.38,
|
| 1812 |
+
"memory/max_allocated (GiB)": 28.38,
|
| 1813 |
+
"step": 164,
|
| 1814 |
+
"tokens_per_second_per_gpu": 1858.78
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 1.1458333333333333,
|
| 1818 |
+
"grad_norm": 0.07483426481485367,
|
| 1819 |
+
"learning_rate": 0.00015593416804311852,
|
| 1820 |
+
"loss": 0.842,
|
| 1821 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1822 |
+
"memory/max_active (GiB)": 27.95,
|
| 1823 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 1824 |
+
"step": 165,
|
| 1825 |
+
"tokens_per_second_per_gpu": 1792.51
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 1.1527777777777777,
|
| 1829 |
+
"grad_norm": 0.07248706370592117,
|
| 1830 |
+
"learning_rate": 0.00015526289544406585,
|
| 1831 |
+
"loss": 0.8672,
|
| 1832 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1833 |
+
"memory/max_active (GiB)": 26.06,
|
| 1834 |
+
"memory/max_allocated (GiB)": 26.06,
|
| 1835 |
+
"step": 166,
|
| 1836 |
+
"tokens_per_second_per_gpu": 1778.82
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.1597222222222223,
|
| 1840 |
+
"grad_norm": 0.07618600875139236,
|
| 1841 |
+
"learning_rate": 0.0001545880184546669,
|
| 1842 |
+
"loss": 0.9355,
|
| 1843 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1844 |
+
"memory/max_active (GiB)": 25.11,
|
| 1845 |
+
"memory/max_allocated (GiB)": 25.11,
|
| 1846 |
+
"step": 167,
|
| 1847 |
+
"tokens_per_second_per_gpu": 1743.04
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 1.1666666666666667,
|
| 1851 |
+
"grad_norm": 0.06785187125205994,
|
| 1852 |
+
"learning_rate": 0.0001539095810921612,
|
| 1853 |
+
"loss": 0.8303,
|
| 1854 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1855 |
+
"memory/max_active (GiB)": 28.9,
|
| 1856 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1857 |
+
"step": 168,
|
| 1858 |
+
"tokens_per_second_per_gpu": 1858.47
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.1736111111111112,
|
| 1862 |
+
"grad_norm": 0.06521926075220108,
|
| 1863 |
+
"learning_rate": 0.0001532276276060051,
|
| 1864 |
+
"loss": 0.8736,
|
| 1865 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1866 |
+
"memory/max_active (GiB)": 28.9,
|
| 1867 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1868 |
+
"step": 169,
|
| 1869 |
+
"tokens_per_second_per_gpu": 1828.71
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 1.1805555555555556,
|
| 1873 |
+
"grad_norm": 0.07702817767858505,
|
| 1874 |
+
"learning_rate": 0.00015254220247498573,
|
| 1875 |
+
"loss": 0.8526,
|
| 1876 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1877 |
+
"memory/max_active (GiB)": 28.15,
|
| 1878 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 1879 |
+
"step": 170,
|
| 1880 |
+
"tokens_per_second_per_gpu": 1843.68
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 1.1875,
|
| 1884 |
+
"grad_norm": 0.1337224841117859,
|
| 1885 |
+
"learning_rate": 0.0001518533504043199,
|
| 1886 |
+
"loss": 0.8973,
|
| 1887 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1888 |
+
"memory/max_active (GiB)": 26.25,
|
| 1889 |
+
"memory/max_allocated (GiB)": 26.25,
|
| 1890 |
+
"step": 171,
|
| 1891 |
+
"tokens_per_second_per_gpu": 1884.45
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 1.1944444444444444,
|
| 1895 |
+
"grad_norm": 0.09579396992921829,
|
| 1896 |
+
"learning_rate": 0.0001511611163227385,
|
| 1897 |
+
"loss": 0.8214,
|
| 1898 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1899 |
+
"memory/max_active (GiB)": 28.9,
|
| 1900 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1901 |
+
"step": 172,
|
| 1902 |
+
"tokens_per_second_per_gpu": 1824.99
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 1.2013888888888888,
|
| 1906 |
+
"grad_norm": 0.08288433402776718,
|
| 1907 |
+
"learning_rate": 0.00015046554537955585,
|
| 1908 |
+
"loss": 0.8975,
|
| 1909 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1910 |
+
"memory/max_active (GiB)": 27.01,
|
| 1911 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 1912 |
+
"step": 173,
|
| 1913 |
+
"tokens_per_second_per_gpu": 1815.52
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.2083333333333333,
|
| 1917 |
+
"grad_norm": 0.07618972659111023,
|
| 1918 |
+
"learning_rate": 0.00014976668294172527,
|
| 1919 |
+
"loss": 0.8802,
|
| 1920 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1921 |
+
"memory/max_active (GiB)": 26.49,
|
| 1922 |
+
"memory/max_allocated (GiB)": 26.49,
|
| 1923 |
+
"step": 174,
|
| 1924 |
+
"tokens_per_second_per_gpu": 1844.86
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 1.2152777777777777,
|
| 1928 |
+
"grad_norm": 0.08120069652795792,
|
| 1929 |
+
"learning_rate": 0.00014906457459087978,
|
| 1930 |
+
"loss": 0.8764,
|
| 1931 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1932 |
+
"memory/max_active (GiB)": 28.15,
|
| 1933 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 1934 |
+
"step": 175,
|
| 1935 |
+
"tokens_per_second_per_gpu": 1855.53
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.2222222222222223,
|
| 1939 |
+
"grad_norm": 0.0804535299539566,
|
| 1940 |
+
"learning_rate": 0.00014835926612035945,
|
| 1941 |
+
"loss": 0.7791,
|
| 1942 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1943 |
+
"memory/max_active (GiB)": 27.01,
|
| 1944 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 1945 |
+
"step": 176,
|
| 1946 |
+
"tokens_per_second_per_gpu": 1806.63
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.2291666666666667,
|
| 1950 |
+
"grad_norm": 0.07893332093954086,
|
| 1951 |
+
"learning_rate": 0.00014765080353222447,
|
| 1952 |
+
"loss": 0.8774,
|
| 1953 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1954 |
+
"memory/max_active (GiB)": 23.75,
|
| 1955 |
+
"memory/max_allocated (GiB)": 23.75,
|
| 1956 |
+
"step": 177,
|
| 1957 |
+
"tokens_per_second_per_gpu": 1791.96
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 1.2361111111111112,
|
| 1961 |
+
"grad_norm": 0.08453946560621262,
|
| 1962 |
+
"learning_rate": 0.0001469392330342548,
|
| 1963 |
+
"loss": 0.8865,
|
| 1964 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1965 |
+
"memory/max_active (GiB)": 28.9,
|
| 1966 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 1967 |
+
"step": 178,
|
| 1968 |
+
"tokens_per_second_per_gpu": 1846.08
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 1.2430555555555556,
|
| 1972 |
+
"grad_norm": 0.09483584016561508,
|
| 1973 |
+
"learning_rate": 0.0001462246010369364,
|
| 1974 |
+
"loss": 0.8611,
|
| 1975 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1976 |
+
"memory/max_active (GiB)": 28.15,
|
| 1977 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 1978 |
+
"step": 179,
|
| 1979 |
+
"tokens_per_second_per_gpu": 1746.22
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 1.25,
|
| 1983 |
+
"grad_norm": 0.10927578061819077,
|
| 1984 |
+
"learning_rate": 0.0001455069541504342,
|
| 1985 |
+
"loss": 0.887,
|
| 1986 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1987 |
+
"memory/max_active (GiB)": 24.17,
|
| 1988 |
+
"memory/max_allocated (GiB)": 24.17,
|
| 1989 |
+
"step": 180,
|
| 1990 |
+
"tokens_per_second_per_gpu": 1829.41
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 1.2569444444444444,
|
| 1994 |
+
"grad_norm": 0.08271358907222748,
|
| 1995 |
+
"learning_rate": 0.00014478633918155217,
|
| 1996 |
+
"loss": 0.7864,
|
| 1997 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 1998 |
+
"memory/max_active (GiB)": 27.95,
|
| 1999 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 2000 |
+
"step": 181,
|
| 2001 |
+
"tokens_per_second_per_gpu": 1757.68
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 1.2638888888888888,
|
| 2005 |
+
"grad_norm": 0.09157366305589676,
|
| 2006 |
+
"learning_rate": 0.00014406280313068018,
|
| 2007 |
+
"loss": 0.8428,
|
| 2008 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2009 |
+
"memory/max_active (GiB)": 28.9,
|
| 2010 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 2011 |
+
"step": 182,
|
| 2012 |
+
"tokens_per_second_per_gpu": 1808.32
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.2708333333333333,
|
| 2016 |
+
"grad_norm": 0.09229514002799988,
|
| 2017 |
+
"learning_rate": 0.0001433363931887289,
|
| 2018 |
+
"loss": 0.8618,
|
| 2019 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2020 |
+
"memory/max_active (GiB)": 24.27,
|
| 2021 |
+
"memory/max_allocated (GiB)": 24.27,
|
| 2022 |
+
"step": 183,
|
| 2023 |
+
"tokens_per_second_per_gpu": 1808.02
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 1.2777777777777777,
|
| 2027 |
+
"grad_norm": 0.08157222718000412,
|
| 2028 |
+
"learning_rate": 0.00014260715673405157,
|
| 2029 |
+
"loss": 0.8205,
|
| 2030 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2031 |
+
"memory/max_active (GiB)": 27.44,
|
| 2032 |
+
"memory/max_allocated (GiB)": 27.44,
|
| 2033 |
+
"step": 184,
|
| 2034 |
+
"tokens_per_second_per_gpu": 1820.59
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.2847222222222223,
|
| 2038 |
+
"grad_norm": 0.07500192523002625,
|
| 2039 |
+
"learning_rate": 0.00014187514132935392,
|
| 2040 |
+
"loss": 0.8863,
|
| 2041 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2042 |
+
"memory/max_active (GiB)": 27.95,
|
| 2043 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 2044 |
+
"step": 185,
|
| 2045 |
+
"tokens_per_second_per_gpu": 1786.34
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 1.2916666666666667,
|
| 2049 |
+
"grad_norm": 0.08555968850851059,
|
| 2050 |
+
"learning_rate": 0.00014114039471859222,
|
| 2051 |
+
"loss": 0.8631,
|
| 2052 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2053 |
+
"memory/max_active (GiB)": 28.38,
|
| 2054 |
+
"memory/max_allocated (GiB)": 28.38,
|
| 2055 |
+
"step": 186,
|
| 2056 |
+
"tokens_per_second_per_gpu": 1752.67
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 1.2986111111111112,
|
| 2060 |
+
"grad_norm": 0.08531264960765839,
|
| 2061 |
+
"learning_rate": 0.00014040296482385894,
|
| 2062 |
+
"loss": 0.9533,
|
| 2063 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2064 |
+
"memory/max_active (GiB)": 28.9,
|
| 2065 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 2066 |
+
"step": 187,
|
| 2067 |
+
"tokens_per_second_per_gpu": 1935.53
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.3055555555555556,
|
| 2071 |
+
"grad_norm": 0.0975320041179657,
|
| 2072 |
+
"learning_rate": 0.0001396628997422575,
|
| 2073 |
+
"loss": 0.9088,
|
| 2074 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2075 |
+
"memory/max_active (GiB)": 25.68,
|
| 2076 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 2077 |
+
"step": 188,
|
| 2078 |
+
"tokens_per_second_per_gpu": 1858.47
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 1.3125,
|
| 2082 |
+
"grad_norm": 0.08182326704263687,
|
| 2083 |
+
"learning_rate": 0.00013892024774276495,
|
| 2084 |
+
"loss": 0.8836,
|
| 2085 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2086 |
+
"memory/max_active (GiB)": 28.15,
|
| 2087 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 2088 |
+
"step": 189,
|
| 2089 |
+
"tokens_per_second_per_gpu": 1805.73
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.3194444444444444,
|
| 2093 |
+
"grad_norm": 0.09812135249376297,
|
| 2094 |
+
"learning_rate": 0.00013817505726308402,
|
| 2095 |
+
"loss": 0.8415,
|
| 2096 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2097 |
+
"memory/max_active (GiB)": 28.15,
|
| 2098 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 2099 |
+
"step": 190,
|
| 2100 |
+
"tokens_per_second_per_gpu": 1786.37
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 1.3263888888888888,
|
| 2104 |
+
"grad_norm": 0.0917779952287674,
|
| 2105 |
+
"learning_rate": 0.00013742737690648361,
|
| 2106 |
+
"loss": 0.8869,
|
| 2107 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2108 |
+
"memory/max_active (GiB)": 27.2,
|
| 2109 |
+
"memory/max_allocated (GiB)": 27.2,
|
| 2110 |
+
"step": 191,
|
| 2111 |
+
"tokens_per_second_per_gpu": 1818.34
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 1.3333333333333333,
|
| 2115 |
+
"grad_norm": 0.0986262708902359,
|
| 2116 |
+
"learning_rate": 0.00013667725543862905,
|
| 2117 |
+
"loss": 0.8554,
|
| 2118 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2119 |
+
"memory/max_active (GiB)": 27.01,
|
| 2120 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 2121 |
+
"step": 192,
|
| 2122 |
+
"tokens_per_second_per_gpu": 1825.63
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 1.3402777777777777,
|
| 2126 |
+
"grad_norm": 0.08627785742282867,
|
| 2127 |
+
"learning_rate": 0.00013592474178440115,
|
| 2128 |
+
"loss": 0.8649,
|
| 2129 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2130 |
+
"memory/max_active (GiB)": 27.01,
|
| 2131 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 2132 |
+
"step": 193,
|
| 2133 |
+
"tokens_per_second_per_gpu": 1804.99
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 1.3472222222222223,
|
| 2137 |
+
"grad_norm": 0.07916709780693054,
|
| 2138 |
+
"learning_rate": 0.0001351698850247055,
|
| 2139 |
+
"loss": 0.8681,
|
| 2140 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2141 |
+
"memory/max_active (GiB)": 28.9,
|
| 2142 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 2143 |
+
"step": 194,
|
| 2144 |
+
"tokens_per_second_per_gpu": 1806.46
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.3541666666666667,
|
| 2148 |
+
"grad_norm": 0.08284994214773178,
|
| 2149 |
+
"learning_rate": 0.000134412734393271,
|
| 2150 |
+
"loss": 0.8953,
|
| 2151 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2152 |
+
"memory/max_active (GiB)": 27.01,
|
| 2153 |
+
"memory/max_allocated (GiB)": 27.01,
|
| 2154 |
+
"step": 195,
|
| 2155 |
+
"tokens_per_second_per_gpu": 1827.15
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 1.3611111111111112,
|
| 2159 |
+
"grad_norm": 0.08089049905538559,
|
| 2160 |
+
"learning_rate": 0.00013365333927343906,
|
| 2161 |
+
"loss": 0.9466,
|
| 2162 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2163 |
+
"memory/max_active (GiB)": 28.9,
|
| 2164 |
+
"memory/max_allocated (GiB)": 28.9,
|
| 2165 |
+
"step": 196,
|
| 2166 |
+
"tokens_per_second_per_gpu": 1850.2
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.3680555555555556,
|
| 2170 |
+
"grad_norm": 0.09982682019472122,
|
| 2171 |
+
"learning_rate": 0.00013289174919494228,
|
| 2172 |
+
"loss": 0.8445,
|
| 2173 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2174 |
+
"memory/max_active (GiB)": 28.15,
|
| 2175 |
+
"memory/max_allocated (GiB)": 28.15,
|
| 2176 |
+
"step": 197,
|
| 2177 |
+
"tokens_per_second_per_gpu": 1776.51
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 1.375,
|
| 2181 |
+
"grad_norm": 0.08014615625143051,
|
| 2182 |
+
"learning_rate": 0.0001321280138306743,
|
| 2183 |
+
"loss": 0.92,
|
| 2184 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2185 |
+
"memory/max_active (GiB)": 25.68,
|
| 2186 |
+
"memory/max_allocated (GiB)": 25.68,
|
| 2187 |
+
"step": 198,
|
| 2188 |
+
"tokens_per_second_per_gpu": 1849.96
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 1.3819444444444444,
|
| 2192 |
+
"grad_norm": 0.10110778361558914,
|
| 2193 |
+
"learning_rate": 0.00013136218299344992,
|
| 2194 |
+
"loss": 0.7737,
|
| 2195 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2196 |
+
"memory/max_active (GiB)": 27.95,
|
| 2197 |
+
"memory/max_allocated (GiB)": 27.95,
|
| 2198 |
+
"step": 199,
|
| 2199 |
+
"tokens_per_second_per_gpu": 1853.85
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 1.3888888888888888,
|
| 2203 |
+
"grad_norm": 0.15635082125663757,
|
| 2204 |
+
"learning_rate": 0.0001305943066327561,
|
| 2205 |
+
"loss": 0.9339,
|
| 2206 |
+
"memory/device_reserved (GiB)": 32.41,
|
| 2207 |
+
"memory/max_active (GiB)": 25.31,
|
| 2208 |
+
"memory/max_allocated (GiB)": 25.31,
|
| 2209 |
+
"step": 200,
|
| 2210 |
+
"tokens_per_second_per_gpu": 1818.61
|
| 2211 |
+
}
|
| 2212 |
+
],
|
| 2213 |
+
"logging_steps": 1,
|
| 2214 |
+
"max_steps": 432,
|
| 2215 |
+
"num_input_tokens_seen": 0,
|
| 2216 |
+
"num_train_epochs": 3,
|
| 2217 |
+
"save_steps": 100,
|
| 2218 |
+
"stateful_callbacks": {
|
| 2219 |
+
"TrainerControl": {
|
| 2220 |
+
"args": {
|
| 2221 |
+
"should_epoch_stop": false,
|
| 2222 |
+
"should_evaluate": false,
|
| 2223 |
+
"should_log": false,
|
| 2224 |
+
"should_save": true,
|
| 2225 |
+
"should_training_stop": false
|
| 2226 |
+
},
|
| 2227 |
+
"attributes": {}
|
| 2228 |
+
}
|
| 2229 |
+
},
|
| 2230 |
+
"total_flos": 1.1164899726190264e+18,
|
| 2231 |
+
"train_batch_size": 1,
|
| 2232 |
+
"trial_name": null,
|
| 2233 |
+
"trial_params": null
|
| 2234 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:929c176313b9455ecfcfecff8ea223e55e5864009e2253728ac173998dcc6858
|
| 3 |
+
size 7313
|
checkpoint-200/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/README.md
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
|
| 8 |
+
- lora
|
| 9 |
+
- transformers
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Model ID
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
|
| 22 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
- **Developed by:** [More Information Needed]
|
| 27 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 28 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 29 |
+
- **Model type:** [More Information Needed]
|
| 30 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 31 |
+
- **License:** [More Information Needed]
|
| 32 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 33 |
+
|
| 34 |
+
### Model Sources [optional]
|
| 35 |
+
|
| 36 |
+
<!-- Provide the basic links for the model. -->
|
| 37 |
+
|
| 38 |
+
- **Repository:** [More Information Needed]
|
| 39 |
+
- **Paper [optional]:** [More Information Needed]
|
| 40 |
+
- **Demo [optional]:** [More Information Needed]
|
| 41 |
+
|
| 42 |
+
## Uses
|
| 43 |
+
|
| 44 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 45 |
+
|
| 46 |
+
### Direct Use
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Downstream Use [optional]
|
| 53 |
+
|
| 54 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
### Out-of-Scope Use
|
| 59 |
+
|
| 60 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
## Bias, Risks, and Limitations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 67 |
+
|
| 68 |
+
[More Information Needed]
|
| 69 |
+
|
| 70 |
+
### Recommendations
|
| 71 |
+
|
| 72 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 73 |
+
|
| 74 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 75 |
+
|
| 76 |
+
## How to Get Started with the Model
|
| 77 |
+
|
| 78 |
+
Use the code below to get started with the model.
|
| 79 |
+
|
| 80 |
+
[More Information Needed]
|
| 81 |
+
|
| 82 |
+
## Training Details
|
| 83 |
+
|
| 84 |
+
### Training Data
|
| 85 |
+
|
| 86 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 87 |
+
|
| 88 |
+
[More Information Needed]
|
| 89 |
+
|
| 90 |
+
### Training Procedure
|
| 91 |
+
|
| 92 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 93 |
+
|
| 94 |
+
#### Preprocessing [optional]
|
| 95 |
+
|
| 96 |
+
[More Information Needed]
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
#### Training Hyperparameters
|
| 100 |
+
|
| 101 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 102 |
+
|
| 103 |
+
#### Speeds, Sizes, Times [optional]
|
| 104 |
+
|
| 105 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 106 |
+
|
| 107 |
+
[More Information Needed]
|
| 108 |
+
|
| 109 |
+
## Evaluation
|
| 110 |
+
|
| 111 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 112 |
+
|
| 113 |
+
### Testing Data, Factors & Metrics
|
| 114 |
+
|
| 115 |
+
#### Testing Data
|
| 116 |
+
|
| 117 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Factors
|
| 122 |
+
|
| 123 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
#### Metrics
|
| 128 |
+
|
| 129 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 130 |
+
|
| 131 |
+
[More Information Needed]
|
| 132 |
+
|
| 133 |
+
### Results
|
| 134 |
+
|
| 135 |
+
[More Information Needed]
|
| 136 |
+
|
| 137 |
+
#### Summary
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Model Examination [optional]
|
| 142 |
+
|
| 143 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 144 |
+
|
| 145 |
+
[More Information Needed]
|
| 146 |
+
|
| 147 |
+
## Environmental Impact
|
| 148 |
+
|
| 149 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 150 |
+
|
| 151 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 152 |
+
|
| 153 |
+
- **Hardware Type:** [More Information Needed]
|
| 154 |
+
- **Hours used:** [More Information Needed]
|
| 155 |
+
- **Cloud Provider:** [More Information Needed]
|
| 156 |
+
- **Compute Region:** [More Information Needed]
|
| 157 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 158 |
+
|
| 159 |
+
## Technical Specifications [optional]
|
| 160 |
+
|
| 161 |
+
### Model Architecture and Objective
|
| 162 |
+
|
| 163 |
+
[More Information Needed]
|
| 164 |
+
|
| 165 |
+
### Compute Infrastructure
|
| 166 |
+
|
| 167 |
+
[More Information Needed]
|
| 168 |
+
|
| 169 |
+
#### Hardware
|
| 170 |
+
|
| 171 |
+
[More Information Needed]
|
| 172 |
+
|
| 173 |
+
#### Software
|
| 174 |
+
|
| 175 |
+
[More Information Needed]
|
| 176 |
+
|
| 177 |
+
## Citation [optional]
|
| 178 |
+
|
| 179 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 180 |
+
|
| 181 |
+
**BibTeX:**
|
| 182 |
+
|
| 183 |
+
[More Information Needed]
|
| 184 |
+
|
| 185 |
+
**APA:**
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## Glossary [optional]
|
| 190 |
+
|
| 191 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 192 |
+
|
| 193 |
+
[More Information Needed]
|
| 194 |
+
|
| 195 |
+
## More Information [optional]
|
| 196 |
+
|
| 197 |
+
[More Information Needed]
|
| 198 |
+
|
| 199 |
+
## Model Card Authors [optional]
|
| 200 |
+
|
| 201 |
+
[More Information Needed]
|
| 202 |
+
|
| 203 |
+
## Model Card Contact
|
| 204 |
+
|
| 205 |
+
[More Information Needed]
|
| 206 |
+
### Framework versions
|
| 207 |
+
|
| 208 |
+
- PEFT 0.17.1
|
checkpoint-300/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": null,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"up_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
+
"k_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": [],
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
checkpoint-300/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5832547a563b9cfb181f6eeef8a35ebf95dff6f0050f7b37b5950109239cf197
|
| 3 |
+
size 550593184
|
checkpoint-300/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-300/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-300/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:135531222ff124b2cb39970b707fae2b724a6b2f15f1809690a5d9fd2f80fefd
|
| 3 |
+
size 280342501
|
checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d0bb6efab72a136bee4f23b2793e9cc2cab1acc28416a13c80533640d65e29f
|
| 3 |
+
size 14645
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba621f4a32bf8b97dde7ea36b2b0ca1d3db0a938e7e275774ff8f3bea77371bd
|
| 3 |
+
size 1465
|
checkpoint-300/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-300/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
checkpoint-300/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 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 32768,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
checkpoint-300/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:929c176313b9455ecfcfecff8ea223e55e5864009e2253728ac173998dcc6858
|
| 3 |
+
size 7313
|
checkpoint-300/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/README.md
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- base_model:adapter:Qwen/Qwen2.5-Coder-14B-Instruct
|
| 8 |
+
- lora
|
| 9 |
+
- transformers
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Model ID
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
|
| 22 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
- **Developed by:** [More Information Needed]
|
| 27 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 28 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 29 |
+
- **Model type:** [More Information Needed]
|
| 30 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 31 |
+
- **License:** [More Information Needed]
|
| 32 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 33 |
+
|
| 34 |
+
### Model Sources [optional]
|
| 35 |
+
|
| 36 |
+
<!-- Provide the basic links for the model. -->
|
| 37 |
+
|
| 38 |
+
- **Repository:** [More Information Needed]
|
| 39 |
+
- **Paper [optional]:** [More Information Needed]
|
| 40 |
+
- **Demo [optional]:** [More Information Needed]
|
| 41 |
+
|
| 42 |
+
## Uses
|
| 43 |
+
|
| 44 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 45 |
+
|
| 46 |
+
### Direct Use
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Downstream Use [optional]
|
| 53 |
+
|
| 54 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
### Out-of-Scope Use
|
| 59 |
+
|
| 60 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
## Bias, Risks, and Limitations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 67 |
+
|
| 68 |
+
[More Information Needed]
|
| 69 |
+
|
| 70 |
+
### Recommendations
|
| 71 |
+
|
| 72 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 73 |
+
|
| 74 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 75 |
+
|
| 76 |
+
## How to Get Started with the Model
|
| 77 |
+
|
| 78 |
+
Use the code below to get started with the model.
|
| 79 |
+
|
| 80 |
+
[More Information Needed]
|
| 81 |
+
|
| 82 |
+
## Training Details
|
| 83 |
+
|
| 84 |
+
### Training Data
|
| 85 |
+
|
| 86 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 87 |
+
|
| 88 |
+
[More Information Needed]
|
| 89 |
+
|
| 90 |
+
### Training Procedure
|
| 91 |
+
|
| 92 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 93 |
+
|
| 94 |
+
#### Preprocessing [optional]
|
| 95 |
+
|
| 96 |
+
[More Information Needed]
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
#### Training Hyperparameters
|
| 100 |
+
|
| 101 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 102 |
+
|
| 103 |
+
#### Speeds, Sizes, Times [optional]
|
| 104 |
+
|
| 105 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 106 |
+
|
| 107 |
+
[More Information Needed]
|
| 108 |
+
|
| 109 |
+
## Evaluation
|
| 110 |
+
|
| 111 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 112 |
+
|
| 113 |
+
### Testing Data, Factors & Metrics
|
| 114 |
+
|
| 115 |
+
#### Testing Data
|
| 116 |
+
|
| 117 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Factors
|
| 122 |
+
|
| 123 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
#### Metrics
|
| 128 |
+
|
| 129 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 130 |
+
|
| 131 |
+
[More Information Needed]
|
| 132 |
+
|
| 133 |
+
### Results
|
| 134 |
+
|
| 135 |
+
[More Information Needed]
|
| 136 |
+
|
| 137 |
+
#### Summary
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Model Examination [optional]
|
| 142 |
+
|
| 143 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 144 |
+
|
| 145 |
+
[More Information Needed]
|
| 146 |
+
|
| 147 |
+
## Environmental Impact
|
| 148 |
+
|
| 149 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 150 |
+
|
| 151 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 152 |
+
|
| 153 |
+
- **Hardware Type:** [More Information Needed]
|
| 154 |
+
- **Hours used:** [More Information Needed]
|
| 155 |
+
- **Cloud Provider:** [More Information Needed]
|
| 156 |
+
- **Compute Region:** [More Information Needed]
|
| 157 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 158 |
+
|
| 159 |
+
## Technical Specifications [optional]
|
| 160 |
+
|
| 161 |
+
### Model Architecture and Objective
|
| 162 |
+
|
| 163 |
+
[More Information Needed]
|
| 164 |
+
|
| 165 |
+
### Compute Infrastructure
|
| 166 |
+
|
| 167 |
+
[More Information Needed]
|
| 168 |
+
|
| 169 |
+
#### Hardware
|
| 170 |
+
|
| 171 |
+
[More Information Needed]
|
| 172 |
+
|
| 173 |
+
#### Software
|
| 174 |
+
|
| 175 |
+
[More Information Needed]
|
| 176 |
+
|
| 177 |
+
## Citation [optional]
|
| 178 |
+
|
| 179 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 180 |
+
|
| 181 |
+
**BibTeX:**
|
| 182 |
+
|
| 183 |
+
[More Information Needed]
|
| 184 |
+
|
| 185 |
+
**APA:**
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## Glossary [optional]
|
| 190 |
+
|
| 191 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 192 |
+
|
| 193 |
+
[More Information Needed]
|
| 194 |
+
|
| 195 |
+
## More Information [optional]
|
| 196 |
+
|
| 197 |
+
[More Information Needed]
|
| 198 |
+
|
| 199 |
+
## Model Card Authors [optional]
|
| 200 |
+
|
| 201 |
+
[More Information Needed]
|
| 202 |
+
|
| 203 |
+
## Model Card Contact
|
| 204 |
+
|
| 205 |
+
[More Information Needed]
|
| 206 |
+
### Framework versions
|
| 207 |
+
|
| 208 |
+
- PEFT 0.17.1
|
checkpoint-400/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": null,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"up_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
+
"k_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": [],
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
checkpoint-400/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10e4d52c8bd97535a59f37ca6afde5832448973f04f40508dc8cb930cf51ec83
|
| 3 |
+
size 550593184
|
checkpoint-400/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-400/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-400/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c4a8e9f5bfb8a404416b710ef6226a0d9f5571fd1188a1e54c2bffd998c781e
|
| 3 |
+
size 280342501
|
checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24275ac9622942d95b5824053b082dd58b38ff30318f5a8c1efd68328d3217dc
|
| 3 |
+
size 14645
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a54cce168c10d482d913193a6364c9721d98ba4602ce24cae6eda811715d0d10
|
| 3 |
+
size 1465
|
checkpoint-400/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-400/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
checkpoint-400/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 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 32768,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|