Instructions to use Lie24/Role_LLM_Cube_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lie24/Role_LLM_Cube_v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Lie24/Role_LLM_Cube_v1") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Lie24/Role_LLM_Cube_v1") model = AutoModelForCausalLM.from_pretrained("Lie24/Role_LLM_Cube_v1") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Lie24/Role_LLM_Cube_v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Lie24/Role_LLM_Cube_v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lie24/Role_LLM_Cube_v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Lie24/Role_LLM_Cube_v1
- SGLang
How to use Lie24/Role_LLM_Cube_v1 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Lie24/Role_LLM_Cube_v1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lie24/Role_LLM_Cube_v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Lie24/Role_LLM_Cube_v1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lie24/Role_LLM_Cube_v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Lie24/Role_LLM_Cube_v1 with Docker Model Runner:
docker model run hf.co/Lie24/Role_LLM_Cube_v1
zxl commited on
Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +3339 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,3339 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 470,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02127659574468085,
|
| 13 |
+
"grad_norm": 19.769559521884688,
|
| 14 |
+
"learning_rate": 2.5000000000000004e-07,
|
| 15 |
+
"loss": 1.5136,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0425531914893617,
|
| 20 |
+
"grad_norm": 22.366909847966127,
|
| 21 |
+
"learning_rate": 5.000000000000001e-07,
|
| 22 |
+
"loss": 1.4656,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06382978723404255,
|
| 27 |
+
"grad_norm": 27.397989604017898,
|
| 28 |
+
"learning_rate": 7.5e-07,
|
| 29 |
+
"loss": 1.5124,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0851063829787234,
|
| 34 |
+
"grad_norm": 18.58567583552412,
|
| 35 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 36 |
+
"loss": 1.5225,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10638297872340426,
|
| 41 |
+
"grad_norm": 18.165996038203307,
|
| 42 |
+
"learning_rate": 1.25e-06,
|
| 43 |
+
"loss": 1.5576,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1276595744680851,
|
| 48 |
+
"grad_norm": 13.681392535187342,
|
| 49 |
+
"learning_rate": 1.5e-06,
|
| 50 |
+
"loss": 1.4687,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14893617021276595,
|
| 55 |
+
"grad_norm": 14.999691223127021,
|
| 56 |
+
"learning_rate": 1.75e-06,
|
| 57 |
+
"loss": 1.3933,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1702127659574468,
|
| 62 |
+
"grad_norm": 9.360244090412072,
|
| 63 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 64 |
+
"loss": 1.4721,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.19148936170212766,
|
| 69 |
+
"grad_norm": 11.174023539278728,
|
| 70 |
+
"learning_rate": 2.25e-06,
|
| 71 |
+
"loss": 1.44,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2127659574468085,
|
| 76 |
+
"grad_norm": 9.866648780480253,
|
| 77 |
+
"learning_rate": 2.5e-06,
|
| 78 |
+
"loss": 1.2595,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.23404255319148937,
|
| 83 |
+
"grad_norm": 9.512446051741868,
|
| 84 |
+
"learning_rate": 2.7500000000000004e-06,
|
| 85 |
+
"loss": 1.4442,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2553191489361702,
|
| 90 |
+
"grad_norm": 8.670274331402473,
|
| 91 |
+
"learning_rate": 3e-06,
|
| 92 |
+
"loss": 1.2739,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2765957446808511,
|
| 97 |
+
"grad_norm": 6.920817280642445,
|
| 98 |
+
"learning_rate": 3.2500000000000002e-06,
|
| 99 |
+
"loss": 1.276,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2978723404255319,
|
| 104 |
+
"grad_norm": 7.10414215318037,
|
| 105 |
+
"learning_rate": 3.5e-06,
|
| 106 |
+
"loss": 1.2421,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3191489361702128,
|
| 111 |
+
"grad_norm": 6.159725671936445,
|
| 112 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 113 |
+
"loss": 1.239,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3404255319148936,
|
| 118 |
+
"grad_norm": 7.6873175205954825,
|
| 119 |
+
"learning_rate": 4.000000000000001e-06,
|
| 120 |
+
"loss": 1.2396,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3617021276595745,
|
| 125 |
+
"grad_norm": 6.528518611068642,
|
| 126 |
+
"learning_rate": 4.25e-06,
|
| 127 |
+
"loss": 1.1543,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3829787234042553,
|
| 132 |
+
"grad_norm": 6.77428307591927,
|
| 133 |
+
"learning_rate": 4.5e-06,
|
| 134 |
+
"loss": 1.1545,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.40425531914893614,
|
| 139 |
+
"grad_norm": 6.417164213417,
|
| 140 |
+
"learning_rate": 4.75e-06,
|
| 141 |
+
"loss": 1.0959,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.425531914893617,
|
| 146 |
+
"grad_norm": 6.180266176299509,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 1.1381,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.44680851063829785,
|
| 153 |
+
"grad_norm": 6.238735118043302,
|
| 154 |
+
"learning_rate": 4.999939076763487e-06,
|
| 155 |
+
"loss": 0.9938,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.46808510638297873,
|
| 160 |
+
"grad_norm": 5.503542713382496,
|
| 161 |
+
"learning_rate": 4.999756310023261e-06,
|
| 162 |
+
"loss": 1.0336,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.48936170212765956,
|
| 167 |
+
"grad_norm": 5.7109281559241305,
|
| 168 |
+
"learning_rate": 4.999451708687114e-06,
|
| 169 |
+
"loss": 1.0293,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5106382978723404,
|
| 174 |
+
"grad_norm": 5.933533265865748,
|
| 175 |
+
"learning_rate": 4.999025287600886e-06,
|
| 176 |
+
"loss": 1.0838,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5319148936170213,
|
| 181 |
+
"grad_norm": 6.058382477727568,
|
| 182 |
+
"learning_rate": 4.99847706754774e-06,
|
| 183 |
+
"loss": 1.147,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5531914893617021,
|
| 188 |
+
"grad_norm": 5.039016064603872,
|
| 189 |
+
"learning_rate": 4.997807075247147e-06,
|
| 190 |
+
"loss": 1.0661,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.574468085106383,
|
| 195 |
+
"grad_norm": 5.673653311719194,
|
| 196 |
+
"learning_rate": 4.9970153433535855e-06,
|
| 197 |
+
"loss": 1.1088,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5957446808510638,
|
| 202 |
+
"grad_norm": 6.772514217020031,
|
| 203 |
+
"learning_rate": 4.996101910454953e-06,
|
| 204 |
+
"loss": 1.0398,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6170212765957447,
|
| 209 |
+
"grad_norm": 7.261784604470834,
|
| 210 |
+
"learning_rate": 4.9950668210706795e-06,
|
| 211 |
+
"loss": 1.1197,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6382978723404256,
|
| 216 |
+
"grad_norm": 5.125305508590899,
|
| 217 |
+
"learning_rate": 4.993910125649561e-06,
|
| 218 |
+
"loss": 1.0096,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6595744680851063,
|
| 223 |
+
"grad_norm": 5.79320276945061,
|
| 224 |
+
"learning_rate": 4.992631880567301e-06,
|
| 225 |
+
"loss": 1.0418,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6808510638297872,
|
| 230 |
+
"grad_norm": 6.583723424976928,
|
| 231 |
+
"learning_rate": 4.9912321481237616e-06,
|
| 232 |
+
"loss": 1.1084,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7021276595744681,
|
| 237 |
+
"grad_norm": 5.166238541818618,
|
| 238 |
+
"learning_rate": 4.989710996539926e-06,
|
| 239 |
+
"loss": 1.0269,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.723404255319149,
|
| 244 |
+
"grad_norm": 4.702597984819574,
|
| 245 |
+
"learning_rate": 4.988068499954578e-06,
|
| 246 |
+
"loss": 0.9362,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7446808510638298,
|
| 251 |
+
"grad_norm": 5.035553587199529,
|
| 252 |
+
"learning_rate": 4.986304738420684e-06,
|
| 253 |
+
"loss": 1.0027,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.7659574468085106,
|
| 258 |
+
"grad_norm": 5.979469659293992,
|
| 259 |
+
"learning_rate": 4.984419797901491e-06,
|
| 260 |
+
"loss": 1.0197,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7872340425531915,
|
| 265 |
+
"grad_norm": 7.251693613828905,
|
| 266 |
+
"learning_rate": 4.9824137702663424e-06,
|
| 267 |
+
"loss": 1.0665,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.8085106382978723,
|
| 272 |
+
"grad_norm": 5.336704026070371,
|
| 273 |
+
"learning_rate": 4.980286753286196e-06,
|
| 274 |
+
"loss": 1.0612,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8297872340425532,
|
| 279 |
+
"grad_norm": 4.572621845298497,
|
| 280 |
+
"learning_rate": 4.978038850628855e-06,
|
| 281 |
+
"loss": 0.891,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.851063829787234,
|
| 286 |
+
"grad_norm": 5.901358668805014,
|
| 287 |
+
"learning_rate": 4.975670171853926e-06,
|
| 288 |
+
"loss": 1.003,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8723404255319149,
|
| 293 |
+
"grad_norm": 5.967637194891353,
|
| 294 |
+
"learning_rate": 4.973180832407471e-06,
|
| 295 |
+
"loss": 1.0412,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8936170212765957,
|
| 300 |
+
"grad_norm": 4.651650771697547,
|
| 301 |
+
"learning_rate": 4.970570953616383e-06,
|
| 302 |
+
"loss": 0.905,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.9148936170212766,
|
| 307 |
+
"grad_norm": 4.40595275321189,
|
| 308 |
+
"learning_rate": 4.96784066268247e-06,
|
| 309 |
+
"loss": 0.9606,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.9361702127659575,
|
| 314 |
+
"grad_norm": 4.297391018229843,
|
| 315 |
+
"learning_rate": 4.964990092676263e-06,
|
| 316 |
+
"loss": 0.912,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.9574468085106383,
|
| 321 |
+
"grad_norm": 5.8520797403685565,
|
| 322 |
+
"learning_rate": 4.962019382530521e-06,
|
| 323 |
+
"loss": 0.99,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.9787234042553191,
|
| 328 |
+
"grad_norm": 4.460582020214977,
|
| 329 |
+
"learning_rate": 4.958928677033465e-06,
|
| 330 |
+
"loss": 0.9338,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.0,
|
| 335 |
+
"grad_norm": 5.108150405797771,
|
| 336 |
+
"learning_rate": 4.9557181268217225e-06,
|
| 337 |
+
"loss": 0.8841,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.0212765957446808,
|
| 342 |
+
"grad_norm": 4.42640489710439,
|
| 343 |
+
"learning_rate": 4.9523878883729794e-06,
|
| 344 |
+
"loss": 0.6441,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.0425531914893618,
|
| 349 |
+
"grad_norm": 4.783433777129786,
|
| 350 |
+
"learning_rate": 4.94893812399836e-06,
|
| 351 |
+
"loss": 0.7076,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.0638297872340425,
|
| 356 |
+
"grad_norm": 4.461478664530093,
|
| 357 |
+
"learning_rate": 4.9453690018345144e-06,
|
| 358 |
+
"loss": 0.6507,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.0851063829787233,
|
| 363 |
+
"grad_norm": 4.659068920568944,
|
| 364 |
+
"learning_rate": 4.9416806958354206e-06,
|
| 365 |
+
"loss": 0.6388,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.1063829787234043,
|
| 370 |
+
"grad_norm": 5.326272476452319,
|
| 371 |
+
"learning_rate": 4.937873385763909e-06,
|
| 372 |
+
"loss": 0.6629,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.127659574468085,
|
| 377 |
+
"grad_norm": 4.42497697146127,
|
| 378 |
+
"learning_rate": 4.933947257182901e-06,
|
| 379 |
+
"loss": 0.6969,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.148936170212766,
|
| 384 |
+
"grad_norm": 4.342156315066868,
|
| 385 |
+
"learning_rate": 4.9299025014463665e-06,
|
| 386 |
+
"loss": 0.6389,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.1702127659574468,
|
| 391 |
+
"grad_norm": 5.535251688604961,
|
| 392 |
+
"learning_rate": 4.925739315689991e-06,
|
| 393 |
+
"loss": 0.6549,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.1914893617021276,
|
| 398 |
+
"grad_norm": 4.098290419568537,
|
| 399 |
+
"learning_rate": 4.921457902821578e-06,
|
| 400 |
+
"loss": 0.6581,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.2127659574468086,
|
| 405 |
+
"grad_norm": 4.804191552305714,
|
| 406 |
+
"learning_rate": 4.917058471511149e-06,
|
| 407 |
+
"loss": 0.6574,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.2340425531914894,
|
| 412 |
+
"grad_norm": 4.661998643228261,
|
| 413 |
+
"learning_rate": 4.912541236180779e-06,
|
| 414 |
+
"loss": 0.6206,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.2553191489361701,
|
| 419 |
+
"grad_norm": 5.457436437790183,
|
| 420 |
+
"learning_rate": 4.907906416994146e-06,
|
| 421 |
+
"loss": 0.6949,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.2765957446808511,
|
| 426 |
+
"grad_norm": 5.287463616155875,
|
| 427 |
+
"learning_rate": 4.903154239845798e-06,
|
| 428 |
+
"loss": 0.6171,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.297872340425532,
|
| 433 |
+
"grad_norm": 6.534162370166582,
|
| 434 |
+
"learning_rate": 4.898284936350144e-06,
|
| 435 |
+
"loss": 0.6738,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.3191489361702127,
|
| 440 |
+
"grad_norm": 5.14242301334199,
|
| 441 |
+
"learning_rate": 4.893298743830168e-06,
|
| 442 |
+
"loss": 0.71,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.3404255319148937,
|
| 447 |
+
"grad_norm": 4.864653117677477,
|
| 448 |
+
"learning_rate": 4.888195905305859e-06,
|
| 449 |
+
"loss": 0.6353,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.3617021276595744,
|
| 454 |
+
"grad_norm": 4.469502230256778,
|
| 455 |
+
"learning_rate": 4.882976669482368e-06,
|
| 456 |
+
"loss": 0.6301,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.3829787234042552,
|
| 461 |
+
"grad_norm": 4.650400360608429,
|
| 462 |
+
"learning_rate": 4.8776412907378845e-06,
|
| 463 |
+
"loss": 0.6298,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.4042553191489362,
|
| 468 |
+
"grad_norm": 4.75068049245489,
|
| 469 |
+
"learning_rate": 4.8721900291112415e-06,
|
| 470 |
+
"loss": 0.6132,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.425531914893617,
|
| 475 |
+
"grad_norm": 5.406681668582622,
|
| 476 |
+
"learning_rate": 4.866623150289241e-06,
|
| 477 |
+
"loss": 0.6177,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.4468085106382977,
|
| 482 |
+
"grad_norm": 4.689427420330228,
|
| 483 |
+
"learning_rate": 4.860940925593703e-06,
|
| 484 |
+
"loss": 0.601,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.4680851063829787,
|
| 489 |
+
"grad_norm": 5.66362626435671,
|
| 490 |
+
"learning_rate": 4.855143631968242e-06,
|
| 491 |
+
"loss": 0.6987,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.4893617021276595,
|
| 496 |
+
"grad_norm": 6.639330863120106,
|
| 497 |
+
"learning_rate": 4.849231551964771e-06,
|
| 498 |
+
"loss": 0.705,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.5106382978723403,
|
| 503 |
+
"grad_norm": 5.15079243645691,
|
| 504 |
+
"learning_rate": 4.84320497372973e-06,
|
| 505 |
+
"loss": 0.6812,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.5319148936170213,
|
| 510 |
+
"grad_norm": 5.318900788335571,
|
| 511 |
+
"learning_rate": 4.837064190990036e-06,
|
| 512 |
+
"loss": 0.6717,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.5531914893617023,
|
| 517 |
+
"grad_norm": 4.39050844628742,
|
| 518 |
+
"learning_rate": 4.830809503038781e-06,
|
| 519 |
+
"loss": 0.5978,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.574468085106383,
|
| 524 |
+
"grad_norm": 4.11981361882099,
|
| 525 |
+
"learning_rate": 4.824441214720629e-06,
|
| 526 |
+
"loss": 0.5789,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.5957446808510638,
|
| 531 |
+
"grad_norm": 4.898106888331966,
|
| 532 |
+
"learning_rate": 4.817959636416969e-06,
|
| 533 |
+
"loss": 0.638,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.6170212765957448,
|
| 538 |
+
"grad_norm": 4.144574853637901,
|
| 539 |
+
"learning_rate": 4.811365084030784e-06,
|
| 540 |
+
"loss": 0.6631,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.6382978723404256,
|
| 545 |
+
"grad_norm": 4.236596267103849,
|
| 546 |
+
"learning_rate": 4.804657878971252e-06,
|
| 547 |
+
"loss": 0.5618,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.6595744680851063,
|
| 552 |
+
"grad_norm": 4.772661867276851,
|
| 553 |
+
"learning_rate": 4.7978383481380865e-06,
|
| 554 |
+
"loss": 0.6064,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.6808510638297873,
|
| 559 |
+
"grad_norm": 5.5176007762843335,
|
| 560 |
+
"learning_rate": 4.790906823905599e-06,
|
| 561 |
+
"loss": 0.6346,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.702127659574468,
|
| 566 |
+
"grad_norm": 4.1371187239001825,
|
| 567 |
+
"learning_rate": 4.783863644106502e-06,
|
| 568 |
+
"loss": 0.598,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.7234042553191489,
|
| 573 |
+
"grad_norm": 4.617726148114806,
|
| 574 |
+
"learning_rate": 4.776709152015443e-06,
|
| 575 |
+
"loss": 0.572,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.7446808510638299,
|
| 580 |
+
"grad_norm": 4.389883430040871,
|
| 581 |
+
"learning_rate": 4.769443696332272e-06,
|
| 582 |
+
"loss": 0.6145,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.7659574468085106,
|
| 587 |
+
"grad_norm": 5.027199601611735,
|
| 588 |
+
"learning_rate": 4.762067631165049e-06,
|
| 589 |
+
"loss": 0.6858,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.7872340425531914,
|
| 594 |
+
"grad_norm": 4.990601804039334,
|
| 595 |
+
"learning_rate": 4.754581316012785e-06,
|
| 596 |
+
"loss": 0.561,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.8085106382978724,
|
| 601 |
+
"grad_norm": 5.705018779334882,
|
| 602 |
+
"learning_rate": 4.746985115747918e-06,
|
| 603 |
+
"loss": 0.6323,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.8297872340425532,
|
| 608 |
+
"grad_norm": 5.1505009350987265,
|
| 609 |
+
"learning_rate": 4.7392794005985324e-06,
|
| 610 |
+
"loss": 0.5952,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.851063829787234,
|
| 615 |
+
"grad_norm": 5.16517962200903,
|
| 616 |
+
"learning_rate": 4.731464546130315e-06,
|
| 617 |
+
"loss": 0.6462,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.872340425531915,
|
| 622 |
+
"grad_norm": 5.203202926098486,
|
| 623 |
+
"learning_rate": 4.723540933228245e-06,
|
| 624 |
+
"loss": 0.5949,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.8936170212765957,
|
| 629 |
+
"grad_norm": 4.6706368589871134,
|
| 630 |
+
"learning_rate": 4.715508948078037e-06,
|
| 631 |
+
"loss": 0.5878,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.9148936170212765,
|
| 636 |
+
"grad_norm": 4.351714864184194,
|
| 637 |
+
"learning_rate": 4.707368982147318e-06,
|
| 638 |
+
"loss": 0.6227,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.9361702127659575,
|
| 643 |
+
"grad_norm": 5.11397965814302,
|
| 644 |
+
"learning_rate": 4.699121432166542e-06,
|
| 645 |
+
"loss": 0.6347,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.9574468085106385,
|
| 650 |
+
"grad_norm": 5.875205347984843,
|
| 651 |
+
"learning_rate": 4.690766700109659e-06,
|
| 652 |
+
"loss": 0.5905,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.978723404255319,
|
| 657 |
+
"grad_norm": 6.03539957826197,
|
| 658 |
+
"learning_rate": 4.682305193174524e-06,
|
| 659 |
+
"loss": 0.6894,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.0,
|
| 664 |
+
"grad_norm": 3.8707434069223026,
|
| 665 |
+
"learning_rate": 4.673737323763048e-06,
|
| 666 |
+
"loss": 0.4095,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.021276595744681,
|
| 671 |
+
"grad_norm": 4.967672001558827,
|
| 672 |
+
"learning_rate": 4.665063509461098e-06,
|
| 673 |
+
"loss": 0.3403,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.0425531914893615,
|
| 678 |
+
"grad_norm": 3.5072435391900436,
|
| 679 |
+
"learning_rate": 4.656284173018144e-06,
|
| 680 |
+
"loss": 0.3736,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.0638297872340425,
|
| 685 |
+
"grad_norm": 4.360376932941338,
|
| 686 |
+
"learning_rate": 4.6473997423266615e-06,
|
| 687 |
+
"loss": 0.4061,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.0851063829787235,
|
| 692 |
+
"grad_norm": 4.224245961638772,
|
| 693 |
+
"learning_rate": 4.638410650401267e-06,
|
| 694 |
+
"loss": 0.3515,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.106382978723404,
|
| 699 |
+
"grad_norm": 4.792845268520252,
|
| 700 |
+
"learning_rate": 4.62931733535762e-06,
|
| 701 |
+
"loss": 0.3432,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.127659574468085,
|
| 706 |
+
"grad_norm": 4.9719261969262085,
|
| 707 |
+
"learning_rate": 4.620120240391065e-06,
|
| 708 |
+
"loss": 0.3495,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.148936170212766,
|
| 713 |
+
"grad_norm": 3.9393952177630864,
|
| 714 |
+
"learning_rate": 4.610819813755038e-06,
|
| 715 |
+
"loss": 0.3505,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.1702127659574466,
|
| 720 |
+
"grad_norm": 5.0676129989734084,
|
| 721 |
+
"learning_rate": 4.601416508739211e-06,
|
| 722 |
+
"loss": 0.345,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.1914893617021276,
|
| 727 |
+
"grad_norm": 4.268873683189594,
|
| 728 |
+
"learning_rate": 4.591910783647405e-06,
|
| 729 |
+
"loss": 0.3411,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.2127659574468086,
|
| 734 |
+
"grad_norm": 5.648372477585861,
|
| 735 |
+
"learning_rate": 4.582303101775249e-06,
|
| 736 |
+
"loss": 0.3414,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.2340425531914896,
|
| 741 |
+
"grad_norm": 4.569109738179888,
|
| 742 |
+
"learning_rate": 4.572593931387604e-06,
|
| 743 |
+
"loss": 0.3107,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.25531914893617,
|
| 748 |
+
"grad_norm": 5.986604177134095,
|
| 749 |
+
"learning_rate": 4.562783745695738e-06,
|
| 750 |
+
"loss": 0.358,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.276595744680851,
|
| 755 |
+
"grad_norm": 4.593476704693552,
|
| 756 |
+
"learning_rate": 4.55287302283426e-06,
|
| 757 |
+
"loss": 0.3938,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.297872340425532,
|
| 762 |
+
"grad_norm": 4.729132719197455,
|
| 763 |
+
"learning_rate": 4.542862245837821e-06,
|
| 764 |
+
"loss": 0.3445,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.3191489361702127,
|
| 769 |
+
"grad_norm": 5.319389221723198,
|
| 770 |
+
"learning_rate": 4.5327519026175694e-06,
|
| 771 |
+
"loss": 0.3638,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.3404255319148937,
|
| 776 |
+
"grad_norm": 4.9962223266535295,
|
| 777 |
+
"learning_rate": 4.522542485937369e-06,
|
| 778 |
+
"loss": 0.3151,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.3617021276595747,
|
| 783 |
+
"grad_norm": 5.43349545021367,
|
| 784 |
+
"learning_rate": 4.512234493389785e-06,
|
| 785 |
+
"loss": 0.3386,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.382978723404255,
|
| 790 |
+
"grad_norm": 4.228899687733491,
|
| 791 |
+
"learning_rate": 4.501828427371834e-06,
|
| 792 |
+
"loss": 0.3381,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.404255319148936,
|
| 797 |
+
"grad_norm": 3.9364311500151214,
|
| 798 |
+
"learning_rate": 4.491324795060491e-06,
|
| 799 |
+
"loss": 0.3419,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.425531914893617,
|
| 804 |
+
"grad_norm": 6.072764335330948,
|
| 805 |
+
"learning_rate": 4.4807241083879774e-06,
|
| 806 |
+
"loss": 0.3447,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.4468085106382977,
|
| 811 |
+
"grad_norm": 4.690579387500509,
|
| 812 |
+
"learning_rate": 4.470026884016805e-06,
|
| 813 |
+
"loss": 0.3296,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.4680851063829787,
|
| 818 |
+
"grad_norm": 4.772781283406453,
|
| 819 |
+
"learning_rate": 4.4592336433146e-06,
|
| 820 |
+
"loss": 0.3112,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.4893617021276597,
|
| 825 |
+
"grad_norm": 4.222608771767499,
|
| 826 |
+
"learning_rate": 4.448344912328686e-06,
|
| 827 |
+
"loss": 0.3602,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.5106382978723403,
|
| 832 |
+
"grad_norm": 4.806194387046772,
|
| 833 |
+
"learning_rate": 4.437361221760449e-06,
|
| 834 |
+
"loss": 0.3433,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.5319148936170213,
|
| 839 |
+
"grad_norm": 4.610773667593825,
|
| 840 |
+
"learning_rate": 4.426283106939474e-06,
|
| 841 |
+
"loss": 0.3423,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.5531914893617023,
|
| 846 |
+
"grad_norm": 3.9378113503820114,
|
| 847 |
+
"learning_rate": 4.415111107797445e-06,
|
| 848 |
+
"loss": 0.335,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.574468085106383,
|
| 853 |
+
"grad_norm": 4.262317442324841,
|
| 854 |
+
"learning_rate": 4.403845768841842e-06,
|
| 855 |
+
"loss": 0.2964,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.595744680851064,
|
| 860 |
+
"grad_norm": 4.586717288805483,
|
| 861 |
+
"learning_rate": 4.3924876391293915e-06,
|
| 862 |
+
"loss": 0.3503,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.617021276595745,
|
| 867 |
+
"grad_norm": 4.420522314781192,
|
| 868 |
+
"learning_rate": 4.381037272239311e-06,
|
| 869 |
+
"loss": 0.348,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.6382978723404253,
|
| 874 |
+
"grad_norm": 3.6908626258947694,
|
| 875 |
+
"learning_rate": 4.36949522624633e-06,
|
| 876 |
+
"loss": 0.3473,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.6595744680851063,
|
| 881 |
+
"grad_norm": 4.276095484034931,
|
| 882 |
+
"learning_rate": 4.357862063693486e-06,
|
| 883 |
+
"loss": 0.3734,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.6808510638297873,
|
| 888 |
+
"grad_norm": 4.16461417799402,
|
| 889 |
+
"learning_rate": 4.346138351564711e-06,
|
| 890 |
+
"loss": 0.3563,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.702127659574468,
|
| 895 |
+
"grad_norm": 4.106373804902514,
|
| 896 |
+
"learning_rate": 4.334324661257191e-06,
|
| 897 |
+
"loss": 0.2954,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.723404255319149,
|
| 902 |
+
"grad_norm": 4.113950324587281,
|
| 903 |
+
"learning_rate": 4.322421568553529e-06,
|
| 904 |
+
"loss": 0.3443,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.74468085106383,
|
| 909 |
+
"grad_norm": 4.190826822795899,
|
| 910 |
+
"learning_rate": 4.3104296535936695e-06,
|
| 911 |
+
"loss": 0.3395,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.7659574468085104,
|
| 916 |
+
"grad_norm": 4.9676092124733575,
|
| 917 |
+
"learning_rate": 4.2983495008466285e-06,
|
| 918 |
+
"loss": 0.3789,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.7872340425531914,
|
| 923 |
+
"grad_norm": 4.175058791875455,
|
| 924 |
+
"learning_rate": 4.286181699082008e-06,
|
| 925 |
+
"loss": 0.3388,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.8085106382978724,
|
| 930 |
+
"grad_norm": 5.475615243400478,
|
| 931 |
+
"learning_rate": 4.273926841341303e-06,
|
| 932 |
+
"loss": 0.3614,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.829787234042553,
|
| 937 |
+
"grad_norm": 4.132179706281526,
|
| 938 |
+
"learning_rate": 4.261585524908987e-06,
|
| 939 |
+
"loss": 0.3031,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.851063829787234,
|
| 944 |
+
"grad_norm": 4.52680856181224,
|
| 945 |
+
"learning_rate": 4.249158351283414e-06,
|
| 946 |
+
"loss": 0.3202,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.872340425531915,
|
| 951 |
+
"grad_norm": 4.4158856257333206,
|
| 952 |
+
"learning_rate": 4.236645926147493e-06,
|
| 953 |
+
"loss": 0.3817,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.8936170212765955,
|
| 958 |
+
"grad_norm": 4.131675629353336,
|
| 959 |
+
"learning_rate": 4.224048859339175e-06,
|
| 960 |
+
"loss": 0.325,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.9148936170212765,
|
| 965 |
+
"grad_norm": 4.632609969168001,
|
| 966 |
+
"learning_rate": 4.211367764821722e-06,
|
| 967 |
+
"loss": 0.339,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.9361702127659575,
|
| 972 |
+
"grad_norm": 4.238399617644217,
|
| 973 |
+
"learning_rate": 4.198603260653792e-06,
|
| 974 |
+
"loss": 0.3803,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.9574468085106385,
|
| 979 |
+
"grad_norm": 4.990761801935908,
|
| 980 |
+
"learning_rate": 4.185755968959308e-06,
|
| 981 |
+
"loss": 0.3447,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.978723404255319,
|
| 986 |
+
"grad_norm": 4.548241919258143,
|
| 987 |
+
"learning_rate": 4.172826515897146e-06,
|
| 988 |
+
"loss": 0.3518,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.0,
|
| 993 |
+
"grad_norm": 3.430910087137401,
|
| 994 |
+
"learning_rate": 4.159815531630604e-06,
|
| 995 |
+
"loss": 0.2304,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 3.021276595744681,
|
| 1000 |
+
"grad_norm": 3.668126527915725,
|
| 1001 |
+
"learning_rate": 4.146723650296701e-06,
|
| 1002 |
+
"loss": 0.2235,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 3.0425531914893615,
|
| 1007 |
+
"grad_norm": 2.8667931520747327,
|
| 1008 |
+
"learning_rate": 4.133551509975264e-06,
|
| 1009 |
+
"loss": 0.1883,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.0638297872340425,
|
| 1014 |
+
"grad_norm": 3.5239577403765106,
|
| 1015 |
+
"learning_rate": 4.120299752657828e-06,
|
| 1016 |
+
"loss": 0.2217,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.0851063829787235,
|
| 1021 |
+
"grad_norm": 3.6921907938710308,
|
| 1022 |
+
"learning_rate": 4.106969024216348e-06,
|
| 1023 |
+
"loss": 0.2049,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.106382978723404,
|
| 1028 |
+
"grad_norm": 3.6392973250804577,
|
| 1029 |
+
"learning_rate": 4.093559974371725e-06,
|
| 1030 |
+
"loss": 0.1831,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.127659574468085,
|
| 1035 |
+
"grad_norm": 3.7365922708313133,
|
| 1036 |
+
"learning_rate": 4.080073256662128e-06,
|
| 1037 |
+
"loss": 0.198,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.148936170212766,
|
| 1042 |
+
"grad_norm": 4.42100805526352,
|
| 1043 |
+
"learning_rate": 4.066509528411151e-06,
|
| 1044 |
+
"loss": 0.1593,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 3.1702127659574466,
|
| 1049 |
+
"grad_norm": 3.701129708479829,
|
| 1050 |
+
"learning_rate": 4.052869450695776e-06,
|
| 1051 |
+
"loss": 0.1542,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.1914893617021276,
|
| 1056 |
+
"grad_norm": 3.9620190917388793,
|
| 1057 |
+
"learning_rate": 4.039153688314146e-06,
|
| 1058 |
+
"loss": 0.1673,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.2127659574468086,
|
| 1063 |
+
"grad_norm": 4.596659093022736,
|
| 1064 |
+
"learning_rate": 4.02536290975317e-06,
|
| 1065 |
+
"loss": 0.1781,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.2340425531914896,
|
| 1070 |
+
"grad_norm": 4.041018040517897,
|
| 1071 |
+
"learning_rate": 4.011497787155938e-06,
|
| 1072 |
+
"loss": 0.204,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.25531914893617,
|
| 1077 |
+
"grad_norm": 4.4750076668231324,
|
| 1078 |
+
"learning_rate": 3.997558996288965e-06,
|
| 1079 |
+
"loss": 0.2042,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 3.276595744680851,
|
| 1084 |
+
"grad_norm": 4.328565873011614,
|
| 1085 |
+
"learning_rate": 3.983547216509254e-06,
|
| 1086 |
+
"loss": 0.206,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 3.297872340425532,
|
| 1091 |
+
"grad_norm": 4.950916510385211,
|
| 1092 |
+
"learning_rate": 3.969463130731183e-06,
|
| 1093 |
+
"loss": 0.1735,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.3191489361702127,
|
| 1098 |
+
"grad_norm": 3.6634515919781356,
|
| 1099 |
+
"learning_rate": 3.955307425393224e-06,
|
| 1100 |
+
"loss": 0.2152,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.3404255319148937,
|
| 1105 |
+
"grad_norm": 3.5183557309327127,
|
| 1106 |
+
"learning_rate": 3.941080790424483e-06,
|
| 1107 |
+
"loss": 0.1788,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 3.3617021276595747,
|
| 1112 |
+
"grad_norm": 4.2312437308996245,
|
| 1113 |
+
"learning_rate": 3.92678391921108e-06,
|
| 1114 |
+
"loss": 0.1817,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 3.382978723404255,
|
| 1119 |
+
"grad_norm": 3.4224234758888654,
|
| 1120 |
+
"learning_rate": 3.912417508562345e-06,
|
| 1121 |
+
"loss": 0.1577,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 3.404255319148936,
|
| 1126 |
+
"grad_norm": 3.7251058715223597,
|
| 1127 |
+
"learning_rate": 3.897982258676867e-06,
|
| 1128 |
+
"loss": 0.2067,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 3.425531914893617,
|
| 1133 |
+
"grad_norm": 3.123331948611014,
|
| 1134 |
+
"learning_rate": 3.88347887310836e-06,
|
| 1135 |
+
"loss": 0.1867,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.4468085106382977,
|
| 1140 |
+
"grad_norm": 3.040022180599425,
|
| 1141 |
+
"learning_rate": 3.868908058731376e-06,
|
| 1142 |
+
"loss": 0.1488,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.4680851063829787,
|
| 1147 |
+
"grad_norm": 3.936251625166522,
|
| 1148 |
+
"learning_rate": 3.85427052570685e-06,
|
| 1149 |
+
"loss": 0.175,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 3.4893617021276597,
|
| 1154 |
+
"grad_norm": 3.35819244249543,
|
| 1155 |
+
"learning_rate": 3.839566987447492e-06,
|
| 1156 |
+
"loss": 0.1992,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 3.5106382978723403,
|
| 1161 |
+
"grad_norm": 3.8098483118828335,
|
| 1162 |
+
"learning_rate": 3.824798160583012e-06,
|
| 1163 |
+
"loss": 0.1677,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.5319148936170213,
|
| 1168 |
+
"grad_norm": 4.08720146453336,
|
| 1169 |
+
"learning_rate": 3.8099647649251984e-06,
|
| 1170 |
+
"loss": 0.1975,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 3.5531914893617023,
|
| 1175 |
+
"grad_norm": 3.546201338791242,
|
| 1176 |
+
"learning_rate": 3.795067523432826e-06,
|
| 1177 |
+
"loss": 0.1643,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.574468085106383,
|
| 1182 |
+
"grad_norm": 4.022986409946214,
|
| 1183 |
+
"learning_rate": 3.780107162176429e-06,
|
| 1184 |
+
"loss": 0.2025,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.595744680851064,
|
| 1189 |
+
"grad_norm": 4.116301951633153,
|
| 1190 |
+
"learning_rate": 3.7650844103029093e-06,
|
| 1191 |
+
"loss": 0.2063,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 3.617021276595745,
|
| 1196 |
+
"grad_norm": 5.498041562915274,
|
| 1197 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 1198 |
+
"loss": 0.1969,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 3.6382978723404253,
|
| 1203 |
+
"grad_norm": 3.571990562222316,
|
| 1204 |
+
"learning_rate": 3.7348546664605777e-06,
|
| 1205 |
+
"loss": 0.1946,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 3.6595744680851063,
|
| 1210 |
+
"grad_norm": 4.110746067790737,
|
| 1211 |
+
"learning_rate": 3.7196491478468322e-06,
|
| 1212 |
+
"loss": 0.192,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 3.6808510638297873,
|
| 1217 |
+
"grad_norm": 3.9747616004152984,
|
| 1218 |
+
"learning_rate": 3.7043841852542884e-06,
|
| 1219 |
+
"loss": 0.2076,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.702127659574468,
|
| 1224 |
+
"grad_norm": 4.049886537167864,
|
| 1225 |
+
"learning_rate": 3.689060522675689e-06,
|
| 1226 |
+
"loss": 0.1885,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 3.723404255319149,
|
| 1231 |
+
"grad_norm": 3.7605106851151593,
|
| 1232 |
+
"learning_rate": 3.6736789069647273e-06,
|
| 1233 |
+
"loss": 0.1819,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 3.74468085106383,
|
| 1238 |
+
"grad_norm": 4.293344674761706,
|
| 1239 |
+
"learning_rate": 3.658240087799655e-06,
|
| 1240 |
+
"loss": 0.1782,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 3.7659574468085104,
|
| 1245 |
+
"grad_norm": 3.094426165785156,
|
| 1246 |
+
"learning_rate": 3.642744817646736e-06,
|
| 1247 |
+
"loss": 0.1562,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 3.7872340425531914,
|
| 1252 |
+
"grad_norm": 4.471233004565249,
|
| 1253 |
+
"learning_rate": 3.627193851723577e-06,
|
| 1254 |
+
"loss": 0.1538,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 3.8085106382978724,
|
| 1259 |
+
"grad_norm": 3.8346276158744823,
|
| 1260 |
+
"learning_rate": 3.611587947962319e-06,
|
| 1261 |
+
"loss": 0.2037,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 3.829787234042553,
|
| 1266 |
+
"grad_norm": 4.6309266206267745,
|
| 1267 |
+
"learning_rate": 3.595927866972694e-06,
|
| 1268 |
+
"loss": 0.1706,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.851063829787234,
|
| 1273 |
+
"grad_norm": 3.574650150496055,
|
| 1274 |
+
"learning_rate": 3.5802143720049565e-06,
|
| 1275 |
+
"loss": 0.1793,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 3.872340425531915,
|
| 1280 |
+
"grad_norm": 4.104316685959246,
|
| 1281 |
+
"learning_rate": 3.564448228912682e-06,
|
| 1282 |
+
"loss": 0.1997,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 3.8936170212765955,
|
| 1287 |
+
"grad_norm": 3.7077174376752815,
|
| 1288 |
+
"learning_rate": 3.5486302061154433e-06,
|
| 1289 |
+
"loss": 0.2397,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 3.9148936170212765,
|
| 1294 |
+
"grad_norm": 3.8535618259715863,
|
| 1295 |
+
"learning_rate": 3.532761074561355e-06,
|
| 1296 |
+
"loss": 0.1724,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 3.9361702127659575,
|
| 1301 |
+
"grad_norm": 4.153454591162772,
|
| 1302 |
+
"learning_rate": 3.516841607689501e-06,
|
| 1303 |
+
"loss": 0.1879,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 3.9574468085106385,
|
| 1308 |
+
"grad_norm": 3.2186742898572254,
|
| 1309 |
+
"learning_rate": 3.5008725813922383e-06,
|
| 1310 |
+
"loss": 0.1793,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 3.978723404255319,
|
| 1315 |
+
"grad_norm": 3.8852555348009066,
|
| 1316 |
+
"learning_rate": 3.4848547739773782e-06,
|
| 1317 |
+
"loss": 0.2205,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 4.0,
|
| 1322 |
+
"grad_norm": 3.1773700849249984,
|
| 1323 |
+
"learning_rate": 3.4687889661302577e-06,
|
| 1324 |
+
"loss": 0.1375,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 4.0212765957446805,
|
| 1329 |
+
"grad_norm": 2.909112047920458,
|
| 1330 |
+
"learning_rate": 3.452675940875686e-06,
|
| 1331 |
+
"loss": 0.1081,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 4.042553191489362,
|
| 1336 |
+
"grad_norm": 2.5683738553439794,
|
| 1337 |
+
"learning_rate": 3.436516483539781e-06,
|
| 1338 |
+
"loss": 0.0953,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 4.0638297872340425,
|
| 1343 |
+
"grad_norm": 2.9198721500124845,
|
| 1344 |
+
"learning_rate": 3.4203113817116955e-06,
|
| 1345 |
+
"loss": 0.1053,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 4.085106382978723,
|
| 1350 |
+
"grad_norm": 2.24010493827577,
|
| 1351 |
+
"learning_rate": 3.4040614252052305e-06,
|
| 1352 |
+
"loss": 0.0927,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 4.1063829787234045,
|
| 1357 |
+
"grad_norm": 2.878670182658427,
|
| 1358 |
+
"learning_rate": 3.387767406020343e-06,
|
| 1359 |
+
"loss": 0.103,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 4.127659574468085,
|
| 1364 |
+
"grad_norm": 3.1788187649976978,
|
| 1365 |
+
"learning_rate": 3.3714301183045382e-06,
|
| 1366 |
+
"loss": 0.1118,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 4.148936170212766,
|
| 1371 |
+
"grad_norm": 3.3067413198545634,
|
| 1372 |
+
"learning_rate": 3.3550503583141726e-06,
|
| 1373 |
+
"loss": 0.1099,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 4.170212765957447,
|
| 1378 |
+
"grad_norm": 2.319050087976373,
|
| 1379 |
+
"learning_rate": 3.338628924375638e-06,
|
| 1380 |
+
"loss": 0.0898,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 4.191489361702128,
|
| 1385 |
+
"grad_norm": 2.6474547453865895,
|
| 1386 |
+
"learning_rate": 3.3221666168464584e-06,
|
| 1387 |
+
"loss": 0.0915,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 4.212765957446808,
|
| 1392 |
+
"grad_norm": 3.2898592433873217,
|
| 1393 |
+
"learning_rate": 3.3056642380762783e-06,
|
| 1394 |
+
"loss": 0.076,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 4.23404255319149,
|
| 1399 |
+
"grad_norm": 3.7084220696956685,
|
| 1400 |
+
"learning_rate": 3.2891225923677565e-06,
|
| 1401 |
+
"loss": 0.0832,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 4.25531914893617,
|
| 1406 |
+
"grad_norm": 3.853474111497437,
|
| 1407 |
+
"learning_rate": 3.272542485937369e-06,
|
| 1408 |
+
"loss": 0.1113,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 4.25531914893617,
|
| 1413 |
+
"eval_loss": 1.3551427125930786,
|
| 1414 |
+
"eval_runtime": 1.3449,
|
| 1415 |
+
"eval_samples_per_second": 17.102,
|
| 1416 |
+
"eval_steps_per_second": 0.744,
|
| 1417 |
+
"step": 200
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 4.276595744680851,
|
| 1421 |
+
"grad_norm": 3.1480732576505686,
|
| 1422 |
+
"learning_rate": 3.2559247268761117e-06,
|
| 1423 |
+
"loss": 0.0894,
|
| 1424 |
+
"step": 201
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 4.297872340425532,
|
| 1428 |
+
"grad_norm": 4.224708808728799,
|
| 1429 |
+
"learning_rate": 3.2392701251101172e-06,
|
| 1430 |
+
"loss": 0.1037,
|
| 1431 |
+
"step": 202
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 4.319148936170213,
|
| 1435 |
+
"grad_norm": 3.127550241031144,
|
| 1436 |
+
"learning_rate": 3.222579492361179e-06,
|
| 1437 |
+
"loss": 0.1193,
|
| 1438 |
+
"step": 203
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 4.340425531914893,
|
| 1442 |
+
"grad_norm": 3.358278204814404,
|
| 1443 |
+
"learning_rate": 3.205853642107192e-06,
|
| 1444 |
+
"loss": 0.1088,
|
| 1445 |
+
"step": 204
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 4.361702127659575,
|
| 1449 |
+
"grad_norm": 3.5723872992052668,
|
| 1450 |
+
"learning_rate": 3.189093389542498e-06,
|
| 1451 |
+
"loss": 0.1156,
|
| 1452 |
+
"step": 205
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 4.382978723404255,
|
| 1456 |
+
"grad_norm": 3.3910498011991863,
|
| 1457 |
+
"learning_rate": 3.1722995515381644e-06,
|
| 1458 |
+
"loss": 0.0813,
|
| 1459 |
+
"step": 206
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 4.404255319148936,
|
| 1463 |
+
"grad_norm": 3.987898875106463,
|
| 1464 |
+
"learning_rate": 3.155472946602162e-06,
|
| 1465 |
+
"loss": 0.1063,
|
| 1466 |
+
"step": 207
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 4.425531914893617,
|
| 1470 |
+
"grad_norm": 3.0288381078835416,
|
| 1471 |
+
"learning_rate": 3.1386143948394764e-06,
|
| 1472 |
+
"loss": 0.1089,
|
| 1473 |
+
"step": 208
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 4.446808510638298,
|
| 1477 |
+
"grad_norm": 3.3307094726424635,
|
| 1478 |
+
"learning_rate": 3.121724717912138e-06,
|
| 1479 |
+
"loss": 0.1142,
|
| 1480 |
+
"step": 209
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 4.468085106382979,
|
| 1484 |
+
"grad_norm": 2.9848172012011664,
|
| 1485 |
+
"learning_rate": 3.1048047389991693e-06,
|
| 1486 |
+
"loss": 0.1157,
|
| 1487 |
+
"step": 210
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 4.48936170212766,
|
| 1491 |
+
"grad_norm": 2.978438802813703,
|
| 1492 |
+
"learning_rate": 3.087855282756475e-06,
|
| 1493 |
+
"loss": 0.0942,
|
| 1494 |
+
"step": 211
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 4.51063829787234,
|
| 1498 |
+
"grad_norm": 2.8670301514814565,
|
| 1499 |
+
"learning_rate": 3.0708771752766397e-06,
|
| 1500 |
+
"loss": 0.0876,
|
| 1501 |
+
"step": 212
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 4.531914893617021,
|
| 1505 |
+
"grad_norm": 3.0160259648937626,
|
| 1506 |
+
"learning_rate": 3.053871244048669e-06,
|
| 1507 |
+
"loss": 0.1057,
|
| 1508 |
+
"step": 213
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 4.553191489361702,
|
| 1512 |
+
"grad_norm": 3.552730667163276,
|
| 1513 |
+
"learning_rate": 3.0368383179176584e-06,
|
| 1514 |
+
"loss": 0.0681,
|
| 1515 |
+
"step": 214
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 4.574468085106383,
|
| 1519 |
+
"grad_norm": 3.0671796344169744,
|
| 1520 |
+
"learning_rate": 3.019779227044398e-06,
|
| 1521 |
+
"loss": 0.1052,
|
| 1522 |
+
"step": 215
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 4.595744680851064,
|
| 1526 |
+
"grad_norm": 3.4917736614570343,
|
| 1527 |
+
"learning_rate": 3.002694802864912e-06,
|
| 1528 |
+
"loss": 0.1131,
|
| 1529 |
+
"step": 216
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 4.617021276595745,
|
| 1533 |
+
"grad_norm": 2.997068423954694,
|
| 1534 |
+
"learning_rate": 2.98558587804993e-06,
|
| 1535 |
+
"loss": 0.1249,
|
| 1536 |
+
"step": 217
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 4.638297872340425,
|
| 1540 |
+
"grad_norm": 2.945598337302224,
|
| 1541 |
+
"learning_rate": 2.9684532864643123e-06,
|
| 1542 |
+
"loss": 0.0916,
|
| 1543 |
+
"step": 218
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 4.659574468085106,
|
| 1547 |
+
"grad_norm": 2.5534208875346494,
|
| 1548 |
+
"learning_rate": 2.9512978631264006e-06,
|
| 1549 |
+
"loss": 0.0834,
|
| 1550 |
+
"step": 219
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 4.680851063829787,
|
| 1554 |
+
"grad_norm": 2.3947639549989144,
|
| 1555 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 1556 |
+
"loss": 0.0974,
|
| 1557 |
+
"step": 220
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 4.702127659574468,
|
| 1561 |
+
"grad_norm": 3.3251173109542074,
|
| 1562 |
+
"learning_rate": 2.9169218667902562e-06,
|
| 1563 |
+
"loss": 0.1011,
|
| 1564 |
+
"step": 221
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 4.723404255319149,
|
| 1568 |
+
"grad_norm": 3.059268693430171,
|
| 1569 |
+
"learning_rate": 2.8997029692295875e-06,
|
| 1570 |
+
"loss": 0.0821,
|
| 1571 |
+
"step": 222
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 4.74468085106383,
|
| 1575 |
+
"grad_norm": 3.5597698182253965,
|
| 1576 |
+
"learning_rate": 2.8824645907100957e-06,
|
| 1577 |
+
"loss": 0.0856,
|
| 1578 |
+
"step": 223
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 4.76595744680851,
|
| 1582 |
+
"grad_norm": 3.3566578614960423,
|
| 1583 |
+
"learning_rate": 2.8652075714060296e-06,
|
| 1584 |
+
"loss": 0.132,
|
| 1585 |
+
"step": 224
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 4.787234042553192,
|
| 1589 |
+
"grad_norm": 3.470592088594595,
|
| 1590 |
+
"learning_rate": 2.847932752400164e-06,
|
| 1591 |
+
"loss": 0.0958,
|
| 1592 |
+
"step": 225
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 4.808510638297872,
|
| 1596 |
+
"grad_norm": 2.911346797843613,
|
| 1597 |
+
"learning_rate": 2.8306409756428067e-06,
|
| 1598 |
+
"loss": 0.0894,
|
| 1599 |
+
"step": 226
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 4.829787234042553,
|
| 1603 |
+
"grad_norm": 4.613111358505509,
|
| 1604 |
+
"learning_rate": 2.813333083910761e-06,
|
| 1605 |
+
"loss": 0.1166,
|
| 1606 |
+
"step": 227
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 4.851063829787234,
|
| 1610 |
+
"grad_norm": 3.015962228404618,
|
| 1611 |
+
"learning_rate": 2.7960099207662535e-06,
|
| 1612 |
+
"loss": 0.1155,
|
| 1613 |
+
"step": 228
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 4.872340425531915,
|
| 1617 |
+
"grad_norm": 2.987399829854267,
|
| 1618 |
+
"learning_rate": 2.778672330515814e-06,
|
| 1619 |
+
"loss": 0.1104,
|
| 1620 |
+
"step": 229
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 4.8936170212765955,
|
| 1624 |
+
"grad_norm": 2.829987084084442,
|
| 1625 |
+
"learning_rate": 2.761321158169134e-06,
|
| 1626 |
+
"loss": 0.1066,
|
| 1627 |
+
"step": 230
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 4.914893617021277,
|
| 1631 |
+
"grad_norm": 3.708679514606222,
|
| 1632 |
+
"learning_rate": 2.743957249397874e-06,
|
| 1633 |
+
"loss": 0.1048,
|
| 1634 |
+
"step": 231
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 4.9361702127659575,
|
| 1638 |
+
"grad_norm": 2.749591872522463,
|
| 1639 |
+
"learning_rate": 2.726581450494451e-06,
|
| 1640 |
+
"loss": 0.1159,
|
| 1641 |
+
"step": 232
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 4.957446808510638,
|
| 1645 |
+
"grad_norm": 3.776661504783798,
|
| 1646 |
+
"learning_rate": 2.70919460833079e-06,
|
| 1647 |
+
"loss": 0.1167,
|
| 1648 |
+
"step": 233
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 4.9787234042553195,
|
| 1652 |
+
"grad_norm": 3.091697194785843,
|
| 1653 |
+
"learning_rate": 2.6917975703170466e-06,
|
| 1654 |
+
"loss": 0.1174,
|
| 1655 |
+
"step": 234
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 5.0,
|
| 1659 |
+
"grad_norm": 2.8077659070563192,
|
| 1660 |
+
"learning_rate": 2.6743911843603134e-06,
|
| 1661 |
+
"loss": 0.0737,
|
| 1662 |
+
"step": 235
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 5.0212765957446805,
|
| 1666 |
+
"grad_norm": 1.9864860542138973,
|
| 1667 |
+
"learning_rate": 2.6569762988232838e-06,
|
| 1668 |
+
"loss": 0.0498,
|
| 1669 |
+
"step": 236
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 5.042553191489362,
|
| 1673 |
+
"grad_norm": 2.080148938371656,
|
| 1674 |
+
"learning_rate": 2.63955376248291e-06,
|
| 1675 |
+
"loss": 0.0588,
|
| 1676 |
+
"step": 237
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 5.0638297872340425,
|
| 1680 |
+
"grad_norm": 2.4271830087344215,
|
| 1681 |
+
"learning_rate": 2.6221244244890336e-06,
|
| 1682 |
+
"loss": 0.04,
|
| 1683 |
+
"step": 238
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 5.085106382978723,
|
| 1687 |
+
"grad_norm": 2.182065583755821,
|
| 1688 |
+
"learning_rate": 2.604689134322999e-06,
|
| 1689 |
+
"loss": 0.0635,
|
| 1690 |
+
"step": 239
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 5.1063829787234045,
|
| 1694 |
+
"grad_norm": 2.3865912853026727,
|
| 1695 |
+
"learning_rate": 2.587248741756253e-06,
|
| 1696 |
+
"loss": 0.0602,
|
| 1697 |
+
"step": 240
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 5.127659574468085,
|
| 1701 |
+
"grad_norm": 2.3131711827099832,
|
| 1702 |
+
"learning_rate": 2.569804096808923e-06,
|
| 1703 |
+
"loss": 0.0709,
|
| 1704 |
+
"step": 241
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 5.148936170212766,
|
| 1708 |
+
"grad_norm": 2.3050528514219004,
|
| 1709 |
+
"learning_rate": 2.5523560497083927e-06,
|
| 1710 |
+
"loss": 0.0547,
|
| 1711 |
+
"step": 242
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 5.170212765957447,
|
| 1715 |
+
"grad_norm": 2.124162166492525,
|
| 1716 |
+
"learning_rate": 2.5349054508478636e-06,
|
| 1717 |
+
"loss": 0.046,
|
| 1718 |
+
"step": 243
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 5.191489361702128,
|
| 1722 |
+
"grad_norm": 1.9773286780066965,
|
| 1723 |
+
"learning_rate": 2.517453150744904e-06,
|
| 1724 |
+
"loss": 0.0432,
|
| 1725 |
+
"step": 244
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 5.212765957446808,
|
| 1729 |
+
"grad_norm": 3.116678592316818,
|
| 1730 |
+
"learning_rate": 2.5e-06,
|
| 1731 |
+
"loss": 0.0634,
|
| 1732 |
+
"step": 245
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 5.23404255319149,
|
| 1736 |
+
"grad_norm": 2.504016738413573,
|
| 1737 |
+
"learning_rate": 2.482546849255096e-06,
|
| 1738 |
+
"loss": 0.0589,
|
| 1739 |
+
"step": 246
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 5.25531914893617,
|
| 1743 |
+
"grad_norm": 3.505324999262586,
|
| 1744 |
+
"learning_rate": 2.4650945491521372e-06,
|
| 1745 |
+
"loss": 0.0547,
|
| 1746 |
+
"step": 247
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 5.276595744680851,
|
| 1750 |
+
"grad_norm": 2.2697348908750974,
|
| 1751 |
+
"learning_rate": 2.447643950291608e-06,
|
| 1752 |
+
"loss": 0.0608,
|
| 1753 |
+
"step": 248
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 5.297872340425532,
|
| 1757 |
+
"grad_norm": 2.8775304018384986,
|
| 1758 |
+
"learning_rate": 2.4301959031910785e-06,
|
| 1759 |
+
"loss": 0.0765,
|
| 1760 |
+
"step": 249
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 5.319148936170213,
|
| 1764 |
+
"grad_norm": 2.4093465444498614,
|
| 1765 |
+
"learning_rate": 2.4127512582437486e-06,
|
| 1766 |
+
"loss": 0.0583,
|
| 1767 |
+
"step": 250
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 5.340425531914893,
|
| 1771 |
+
"grad_norm": 2.365667376680801,
|
| 1772 |
+
"learning_rate": 2.3953108656770018e-06,
|
| 1773 |
+
"loss": 0.0629,
|
| 1774 |
+
"step": 251
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 5.361702127659575,
|
| 1778 |
+
"grad_norm": 2.713559880628167,
|
| 1779 |
+
"learning_rate": 2.377875575510967e-06,
|
| 1780 |
+
"loss": 0.0669,
|
| 1781 |
+
"step": 252
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 5.382978723404255,
|
| 1785 |
+
"grad_norm": 2.999000225951145,
|
| 1786 |
+
"learning_rate": 2.3604462375170905e-06,
|
| 1787 |
+
"loss": 0.0617,
|
| 1788 |
+
"step": 253
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 5.404255319148936,
|
| 1792 |
+
"grad_norm": 2.6164170571843512,
|
| 1793 |
+
"learning_rate": 2.3430237011767166e-06,
|
| 1794 |
+
"loss": 0.0582,
|
| 1795 |
+
"step": 254
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 5.425531914893617,
|
| 1799 |
+
"grad_norm": 2.4039871330574796,
|
| 1800 |
+
"learning_rate": 2.325608815639687e-06,
|
| 1801 |
+
"loss": 0.0578,
|
| 1802 |
+
"step": 255
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 5.446808510638298,
|
| 1806 |
+
"grad_norm": 2.97747740854911,
|
| 1807 |
+
"learning_rate": 2.3082024296829538e-06,
|
| 1808 |
+
"loss": 0.0659,
|
| 1809 |
+
"step": 256
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 5.468085106382979,
|
| 1813 |
+
"grad_norm": 2.336759542261552,
|
| 1814 |
+
"learning_rate": 2.290805391669212e-06,
|
| 1815 |
+
"loss": 0.0548,
|
| 1816 |
+
"step": 257
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 5.48936170212766,
|
| 1820 |
+
"grad_norm": 3.1670650790685846,
|
| 1821 |
+
"learning_rate": 2.2734185495055503e-06,
|
| 1822 |
+
"loss": 0.0585,
|
| 1823 |
+
"step": 258
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 5.51063829787234,
|
| 1827 |
+
"grad_norm": 3.2034707124777952,
|
| 1828 |
+
"learning_rate": 2.256042750602127e-06,
|
| 1829 |
+
"loss": 0.0593,
|
| 1830 |
+
"step": 259
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 5.531914893617021,
|
| 1834 |
+
"grad_norm": 2.3348070175379503,
|
| 1835 |
+
"learning_rate": 2.238678841830867e-06,
|
| 1836 |
+
"loss": 0.0547,
|
| 1837 |
+
"step": 260
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 5.553191489361702,
|
| 1841 |
+
"grad_norm": 2.608427512535968,
|
| 1842 |
+
"learning_rate": 2.2213276694841866e-06,
|
| 1843 |
+
"loss": 0.0643,
|
| 1844 |
+
"step": 261
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 5.574468085106383,
|
| 1848 |
+
"grad_norm": 2.4848496472118495,
|
| 1849 |
+
"learning_rate": 2.2039900792337477e-06,
|
| 1850 |
+
"loss": 0.0608,
|
| 1851 |
+
"step": 262
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 5.595744680851064,
|
| 1855 |
+
"grad_norm": 1.886510569911626,
|
| 1856 |
+
"learning_rate": 2.186666916089239e-06,
|
| 1857 |
+
"loss": 0.0599,
|
| 1858 |
+
"step": 263
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 5.617021276595745,
|
| 1862 |
+
"grad_norm": 2.8635289633291547,
|
| 1863 |
+
"learning_rate": 2.1693590243571937e-06,
|
| 1864 |
+
"loss": 0.0515,
|
| 1865 |
+
"step": 264
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 5.638297872340425,
|
| 1869 |
+
"grad_norm": 2.854324373551202,
|
| 1870 |
+
"learning_rate": 2.1520672475998374e-06,
|
| 1871 |
+
"loss": 0.0554,
|
| 1872 |
+
"step": 265
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 5.659574468085106,
|
| 1876 |
+
"grad_norm": 1.8544197687406436,
|
| 1877 |
+
"learning_rate": 2.134792428593971e-06,
|
| 1878 |
+
"loss": 0.0421,
|
| 1879 |
+
"step": 266
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 5.680851063829787,
|
| 1883 |
+
"grad_norm": 2.6205983731152322,
|
| 1884 |
+
"learning_rate": 2.117535409289905e-06,
|
| 1885 |
+
"loss": 0.0457,
|
| 1886 |
+
"step": 267
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 5.702127659574468,
|
| 1890 |
+
"grad_norm": 1.7630228804740633,
|
| 1891 |
+
"learning_rate": 2.1002970307704134e-06,
|
| 1892 |
+
"loss": 0.0369,
|
| 1893 |
+
"step": 268
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 5.723404255319149,
|
| 1897 |
+
"grad_norm": 2.638068560108755,
|
| 1898 |
+
"learning_rate": 2.0830781332097446e-06,
|
| 1899 |
+
"loss": 0.0583,
|
| 1900 |
+
"step": 269
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 5.74468085106383,
|
| 1904 |
+
"grad_norm": 3.1753027345645646,
|
| 1905 |
+
"learning_rate": 2.0658795558326745e-06,
|
| 1906 |
+
"loss": 0.0674,
|
| 1907 |
+
"step": 270
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 5.76595744680851,
|
| 1911 |
+
"grad_norm": 2.2642667997058257,
|
| 1912 |
+
"learning_rate": 2.0487021368736002e-06,
|
| 1913 |
+
"loss": 0.064,
|
| 1914 |
+
"step": 271
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 5.787234042553192,
|
| 1918 |
+
"grad_norm": 2.559426313332899,
|
| 1919 |
+
"learning_rate": 2.031546713535688e-06,
|
| 1920 |
+
"loss": 0.0549,
|
| 1921 |
+
"step": 272
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 5.808510638297872,
|
| 1925 |
+
"grad_norm": 2.878855059930482,
|
| 1926 |
+
"learning_rate": 2.0144141219500707e-06,
|
| 1927 |
+
"loss": 0.0559,
|
| 1928 |
+
"step": 273
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 5.829787234042553,
|
| 1932 |
+
"grad_norm": 2.283778113411308,
|
| 1933 |
+
"learning_rate": 1.997305197135089e-06,
|
| 1934 |
+
"loss": 0.0548,
|
| 1935 |
+
"step": 274
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 5.851063829787234,
|
| 1939 |
+
"grad_norm": 2.4192051614394003,
|
| 1940 |
+
"learning_rate": 1.9802207729556023e-06,
|
| 1941 |
+
"loss": 0.0502,
|
| 1942 |
+
"step": 275
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 5.872340425531915,
|
| 1946 |
+
"grad_norm": 2.322479824517103,
|
| 1947 |
+
"learning_rate": 1.963161682082342e-06,
|
| 1948 |
+
"loss": 0.064,
|
| 1949 |
+
"step": 276
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 5.8936170212765955,
|
| 1953 |
+
"grad_norm": 2.4593833670456005,
|
| 1954 |
+
"learning_rate": 1.946128755951332e-06,
|
| 1955 |
+
"loss": 0.058,
|
| 1956 |
+
"step": 277
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 5.914893617021277,
|
| 1960 |
+
"grad_norm": 2.5251545274407907,
|
| 1961 |
+
"learning_rate": 1.9291228247233607e-06,
|
| 1962 |
+
"loss": 0.0522,
|
| 1963 |
+
"step": 278
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 5.9361702127659575,
|
| 1967 |
+
"grad_norm": 1.8104094730869373,
|
| 1968 |
+
"learning_rate": 1.912144717243525e-06,
|
| 1969 |
+
"loss": 0.0296,
|
| 1970 |
+
"step": 279
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 5.957446808510638,
|
| 1974 |
+
"grad_norm": 2.689146388919388,
|
| 1975 |
+
"learning_rate": 1.895195261000831e-06,
|
| 1976 |
+
"loss": 0.0407,
|
| 1977 |
+
"step": 280
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 5.9787234042553195,
|
| 1981 |
+
"grad_norm": 1.8669924342723785,
|
| 1982 |
+
"learning_rate": 1.8782752820878636e-06,
|
| 1983 |
+
"loss": 0.0495,
|
| 1984 |
+
"step": 281
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 6.0,
|
| 1988 |
+
"grad_norm": 2.271539062015242,
|
| 1989 |
+
"learning_rate": 1.8613856051605242e-06,
|
| 1990 |
+
"loss": 0.0455,
|
| 1991 |
+
"step": 282
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 6.0212765957446805,
|
| 1995 |
+
"grad_norm": 1.525504212144237,
|
| 1996 |
+
"learning_rate": 1.8445270533978387e-06,
|
| 1997 |
+
"loss": 0.0377,
|
| 1998 |
+
"step": 283
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 6.042553191489362,
|
| 2002 |
+
"grad_norm": 1.0859867252268387,
|
| 2003 |
+
"learning_rate": 1.827700448461836e-06,
|
| 2004 |
+
"loss": 0.0221,
|
| 2005 |
+
"step": 284
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 6.0638297872340425,
|
| 2009 |
+
"grad_norm": 1.6689218206446002,
|
| 2010 |
+
"learning_rate": 1.8109066104575023e-06,
|
| 2011 |
+
"loss": 0.0237,
|
| 2012 |
+
"step": 285
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 6.085106382978723,
|
| 2016 |
+
"grad_norm": 1.7091034732477,
|
| 2017 |
+
"learning_rate": 1.7941463578928088e-06,
|
| 2018 |
+
"loss": 0.0316,
|
| 2019 |
+
"step": 286
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 6.1063829787234045,
|
| 2023 |
+
"grad_norm": 1.473946493341099,
|
| 2024 |
+
"learning_rate": 1.7774205076388207e-06,
|
| 2025 |
+
"loss": 0.0301,
|
| 2026 |
+
"step": 287
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 6.127659574468085,
|
| 2030 |
+
"grad_norm": 1.9210720976922275,
|
| 2031 |
+
"learning_rate": 1.7607298748898844e-06,
|
| 2032 |
+
"loss": 0.0241,
|
| 2033 |
+
"step": 288
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 6.148936170212766,
|
| 2037 |
+
"grad_norm": 2.2803503758262504,
|
| 2038 |
+
"learning_rate": 1.744075273123889e-06,
|
| 2039 |
+
"loss": 0.0454,
|
| 2040 |
+
"step": 289
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 6.170212765957447,
|
| 2044 |
+
"grad_norm": 2.024197465049683,
|
| 2045 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 2046 |
+
"loss": 0.0362,
|
| 2047 |
+
"step": 290
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 6.191489361702128,
|
| 2051 |
+
"grad_norm": 1.84667704080016,
|
| 2052 |
+
"learning_rate": 1.7108774076322443e-06,
|
| 2053 |
+
"loss": 0.0403,
|
| 2054 |
+
"step": 291
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 6.212765957446808,
|
| 2058 |
+
"grad_norm": 1.695502301672247,
|
| 2059 |
+
"learning_rate": 1.6943357619237227e-06,
|
| 2060 |
+
"loss": 0.0306,
|
| 2061 |
+
"step": 292
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 6.23404255319149,
|
| 2065 |
+
"grad_norm": 1.6806451272904126,
|
| 2066 |
+
"learning_rate": 1.677833383153542e-06,
|
| 2067 |
+
"loss": 0.0284,
|
| 2068 |
+
"step": 293
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 6.25531914893617,
|
| 2072 |
+
"grad_norm": 2.9118161159346854,
|
| 2073 |
+
"learning_rate": 1.661371075624363e-06,
|
| 2074 |
+
"loss": 0.0256,
|
| 2075 |
+
"step": 294
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 6.276595744680851,
|
| 2079 |
+
"grad_norm": 1.8173030910949344,
|
| 2080 |
+
"learning_rate": 1.6449496416858285e-06,
|
| 2081 |
+
"loss": 0.0284,
|
| 2082 |
+
"step": 295
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 6.297872340425532,
|
| 2086 |
+
"grad_norm": 2.223540017311328,
|
| 2087 |
+
"learning_rate": 1.6285698816954626e-06,
|
| 2088 |
+
"loss": 0.0443,
|
| 2089 |
+
"step": 296
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 6.319148936170213,
|
| 2093 |
+
"grad_norm": 1.4963288286875704,
|
| 2094 |
+
"learning_rate": 1.612232593979658e-06,
|
| 2095 |
+
"loss": 0.0367,
|
| 2096 |
+
"step": 297
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 6.340425531914893,
|
| 2100 |
+
"grad_norm": 1.3236418660083258,
|
| 2101 |
+
"learning_rate": 1.5959385747947697e-06,
|
| 2102 |
+
"loss": 0.0168,
|
| 2103 |
+
"step": 298
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 6.361702127659575,
|
| 2107 |
+
"grad_norm": 2.1082580928006704,
|
| 2108 |
+
"learning_rate": 1.5796886182883053e-06,
|
| 2109 |
+
"loss": 0.0384,
|
| 2110 |
+
"step": 299
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 6.382978723404255,
|
| 2114 |
+
"grad_norm": 2.0461518407784665,
|
| 2115 |
+
"learning_rate": 1.56348351646022e-06,
|
| 2116 |
+
"loss": 0.0348,
|
| 2117 |
+
"step": 300
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 6.404255319148936,
|
| 2121 |
+
"grad_norm": 1.9027154330548208,
|
| 2122 |
+
"learning_rate": 1.547324059124315e-06,
|
| 2123 |
+
"loss": 0.0409,
|
| 2124 |
+
"step": 301
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 6.425531914893617,
|
| 2128 |
+
"grad_norm": 1.8430627981587546,
|
| 2129 |
+
"learning_rate": 1.5312110338697427e-06,
|
| 2130 |
+
"loss": 0.0336,
|
| 2131 |
+
"step": 302
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 6.446808510638298,
|
| 2135 |
+
"grad_norm": 2.013051690553332,
|
| 2136 |
+
"learning_rate": 1.5151452260226224e-06,
|
| 2137 |
+
"loss": 0.0361,
|
| 2138 |
+
"step": 303
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 6.468085106382979,
|
| 2142 |
+
"grad_norm": 2.1207015485047753,
|
| 2143 |
+
"learning_rate": 1.4991274186077632e-06,
|
| 2144 |
+
"loss": 0.0405,
|
| 2145 |
+
"step": 304
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 6.48936170212766,
|
| 2149 |
+
"grad_norm": 1.3483418905294124,
|
| 2150 |
+
"learning_rate": 1.4831583923105e-06,
|
| 2151 |
+
"loss": 0.0264,
|
| 2152 |
+
"step": 305
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 6.51063829787234,
|
| 2156 |
+
"grad_norm": 1.2898003351353924,
|
| 2157 |
+
"learning_rate": 1.467238925438646e-06,
|
| 2158 |
+
"loss": 0.0326,
|
| 2159 |
+
"step": 306
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 6.531914893617021,
|
| 2163 |
+
"grad_norm": 1.83413124159608,
|
| 2164 |
+
"learning_rate": 1.4513697938845571e-06,
|
| 2165 |
+
"loss": 0.0329,
|
| 2166 |
+
"step": 307
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 6.553191489361702,
|
| 2170 |
+
"grad_norm": 1.9300831447222762,
|
| 2171 |
+
"learning_rate": 1.4355517710873184e-06,
|
| 2172 |
+
"loss": 0.0342,
|
| 2173 |
+
"step": 308
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 6.574468085106383,
|
| 2177 |
+
"grad_norm": 2.46498295305994,
|
| 2178 |
+
"learning_rate": 1.419785627995044e-06,
|
| 2179 |
+
"loss": 0.0293,
|
| 2180 |
+
"step": 309
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 6.595744680851064,
|
| 2184 |
+
"grad_norm": 1.8810365903428496,
|
| 2185 |
+
"learning_rate": 1.4040721330273063e-06,
|
| 2186 |
+
"loss": 0.0385,
|
| 2187 |
+
"step": 310
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 6.617021276595745,
|
| 2191 |
+
"grad_norm": 1.7341556708700896,
|
| 2192 |
+
"learning_rate": 1.388412052037682e-06,
|
| 2193 |
+
"loss": 0.0373,
|
| 2194 |
+
"step": 311
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 6.638297872340425,
|
| 2198 |
+
"grad_norm": 1.4886715538593713,
|
| 2199 |
+
"learning_rate": 1.3728061482764238e-06,
|
| 2200 |
+
"loss": 0.0374,
|
| 2201 |
+
"step": 312
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 6.659574468085106,
|
| 2205 |
+
"grad_norm": 1.8999495842705894,
|
| 2206 |
+
"learning_rate": 1.3572551823532654e-06,
|
| 2207 |
+
"loss": 0.0316,
|
| 2208 |
+
"step": 313
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 6.680851063829787,
|
| 2212 |
+
"grad_norm": 1.464463066404411,
|
| 2213 |
+
"learning_rate": 1.3417599122003464e-06,
|
| 2214 |
+
"loss": 0.033,
|
| 2215 |
+
"step": 314
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 6.702127659574468,
|
| 2219 |
+
"grad_norm": 1.8396892711483188,
|
| 2220 |
+
"learning_rate": 1.3263210930352737e-06,
|
| 2221 |
+
"loss": 0.0351,
|
| 2222 |
+
"step": 315
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 6.723404255319149,
|
| 2226 |
+
"grad_norm": 1.555502571877375,
|
| 2227 |
+
"learning_rate": 1.3109394773243117e-06,
|
| 2228 |
+
"loss": 0.0333,
|
| 2229 |
+
"step": 316
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 6.74468085106383,
|
| 2233 |
+
"grad_norm": 2.124808645505887,
|
| 2234 |
+
"learning_rate": 1.2956158147457116e-06,
|
| 2235 |
+
"loss": 0.0294,
|
| 2236 |
+
"step": 317
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 6.76595744680851,
|
| 2240 |
+
"grad_norm": 1.7688895712588661,
|
| 2241 |
+
"learning_rate": 1.280350852153168e-06,
|
| 2242 |
+
"loss": 0.0242,
|
| 2243 |
+
"step": 318
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 6.787234042553192,
|
| 2247 |
+
"grad_norm": 2.0383431308499325,
|
| 2248 |
+
"learning_rate": 1.2651453335394232e-06,
|
| 2249 |
+
"loss": 0.0353,
|
| 2250 |
+
"step": 319
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 6.808510638297872,
|
| 2254 |
+
"grad_norm": 1.7645071618559023,
|
| 2255 |
+
"learning_rate": 1.2500000000000007e-06,
|
| 2256 |
+
"loss": 0.0299,
|
| 2257 |
+
"step": 320
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 6.829787234042553,
|
| 2261 |
+
"grad_norm": 2.0474065053014217,
|
| 2262 |
+
"learning_rate": 1.234915589697091e-06,
|
| 2263 |
+
"loss": 0.0297,
|
| 2264 |
+
"step": 321
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 6.851063829787234,
|
| 2268 |
+
"grad_norm": 1.7823278045268314,
|
| 2269 |
+
"learning_rate": 1.2198928378235717e-06,
|
| 2270 |
+
"loss": 0.038,
|
| 2271 |
+
"step": 322
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 6.872340425531915,
|
| 2275 |
+
"grad_norm": 1.2380075941515003,
|
| 2276 |
+
"learning_rate": 1.204932476567175e-06,
|
| 2277 |
+
"loss": 0.031,
|
| 2278 |
+
"step": 323
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 6.8936170212765955,
|
| 2282 |
+
"grad_norm": 1.9796302395422996,
|
| 2283 |
+
"learning_rate": 1.1900352350748026e-06,
|
| 2284 |
+
"loss": 0.0381,
|
| 2285 |
+
"step": 324
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 6.914893617021277,
|
| 2289 |
+
"grad_norm": 1.3804831755312008,
|
| 2290 |
+
"learning_rate": 1.1752018394169882e-06,
|
| 2291 |
+
"loss": 0.0316,
|
| 2292 |
+
"step": 325
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 6.9361702127659575,
|
| 2296 |
+
"grad_norm": 1.6152383977065423,
|
| 2297 |
+
"learning_rate": 1.160433012552508e-06,
|
| 2298 |
+
"loss": 0.0343,
|
| 2299 |
+
"step": 326
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 6.957446808510638,
|
| 2303 |
+
"grad_norm": 1.69638635732096,
|
| 2304 |
+
"learning_rate": 1.1457294742931508e-06,
|
| 2305 |
+
"loss": 0.0296,
|
| 2306 |
+
"step": 327
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 6.9787234042553195,
|
| 2310 |
+
"grad_norm": 2.0806576931686456,
|
| 2311 |
+
"learning_rate": 1.1310919412686248e-06,
|
| 2312 |
+
"loss": 0.0341,
|
| 2313 |
+
"step": 328
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 7.0,
|
| 2317 |
+
"grad_norm": 1.8303598912826444,
|
| 2318 |
+
"learning_rate": 1.11652112689164e-06,
|
| 2319 |
+
"loss": 0.0405,
|
| 2320 |
+
"step": 329
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 7.0212765957446805,
|
| 2324 |
+
"grad_norm": 1.5859756930815514,
|
| 2325 |
+
"learning_rate": 1.1020177413231334e-06,
|
| 2326 |
+
"loss": 0.0252,
|
| 2327 |
+
"step": 330
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 7.042553191489362,
|
| 2331 |
+
"grad_norm": 0.7609936522020677,
|
| 2332 |
+
"learning_rate": 1.0875824914376555e-06,
|
| 2333 |
+
"loss": 0.0158,
|
| 2334 |
+
"step": 331
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 7.0638297872340425,
|
| 2338 |
+
"grad_norm": 2.0790528777967188,
|
| 2339 |
+
"learning_rate": 1.073216080788921e-06,
|
| 2340 |
+
"loss": 0.0175,
|
| 2341 |
+
"step": 332
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 7.085106382978723,
|
| 2345 |
+
"grad_norm": 1.0895054515077724,
|
| 2346 |
+
"learning_rate": 1.0589192095755172e-06,
|
| 2347 |
+
"loss": 0.0217,
|
| 2348 |
+
"step": 333
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 7.1063829787234045,
|
| 2352 |
+
"grad_norm": 1.0138202696131422,
|
| 2353 |
+
"learning_rate": 1.0446925746067768e-06,
|
| 2354 |
+
"loss": 0.0189,
|
| 2355 |
+
"step": 334
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 7.127659574468085,
|
| 2359 |
+
"grad_norm": 0.931336055385696,
|
| 2360 |
+
"learning_rate": 1.0305368692688175e-06,
|
| 2361 |
+
"loss": 0.0209,
|
| 2362 |
+
"step": 335
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 7.148936170212766,
|
| 2366 |
+
"grad_norm": 1.214374992403074,
|
| 2367 |
+
"learning_rate": 1.0164527834907468e-06,
|
| 2368 |
+
"loss": 0.0218,
|
| 2369 |
+
"step": 336
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 7.170212765957447,
|
| 2373 |
+
"grad_norm": 1.5245924187989146,
|
| 2374 |
+
"learning_rate": 1.0024410037110358e-06,
|
| 2375 |
+
"loss": 0.022,
|
| 2376 |
+
"step": 337
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 7.191489361702128,
|
| 2380 |
+
"grad_norm": 1.0820503643925237,
|
| 2381 |
+
"learning_rate": 9.88502212844063e-07,
|
| 2382 |
+
"loss": 0.0171,
|
| 2383 |
+
"step": 338
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 7.212765957446808,
|
| 2387 |
+
"grad_norm": 0.8009422999145568,
|
| 2388 |
+
"learning_rate": 9.746370902468311e-07,
|
| 2389 |
+
"loss": 0.0179,
|
| 2390 |
+
"step": 339
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 7.23404255319149,
|
| 2394 |
+
"grad_norm": 1.245836157318975,
|
| 2395 |
+
"learning_rate": 9.608463116858544e-07,
|
| 2396 |
+
"loss": 0.0196,
|
| 2397 |
+
"step": 340
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 7.25531914893617,
|
| 2401 |
+
"grad_norm": 0.9189114786673717,
|
| 2402 |
+
"learning_rate": 9.471305493042243e-07,
|
| 2403 |
+
"loss": 0.0206,
|
| 2404 |
+
"step": 341
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 7.276595744680851,
|
| 2408 |
+
"grad_norm": 1.2781854766390135,
|
| 2409 |
+
"learning_rate": 9.334904715888496e-07,
|
| 2410 |
+
"loss": 0.0164,
|
| 2411 |
+
"step": 342
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 7.297872340425532,
|
| 2415 |
+
"grad_norm": 1.5271374445001962,
|
| 2416 |
+
"learning_rate": 9.199267433378728e-07,
|
| 2417 |
+
"loss": 0.02,
|
| 2418 |
+
"step": 343
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 7.319148936170213,
|
| 2422 |
+
"grad_norm": 0.946456072976271,
|
| 2423 |
+
"learning_rate": 9.064400256282757e-07,
|
| 2424 |
+
"loss": 0.0214,
|
| 2425 |
+
"step": 344
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 7.340425531914893,
|
| 2429 |
+
"grad_norm": 1.270831674714735,
|
| 2430 |
+
"learning_rate": 8.930309757836517e-07,
|
| 2431 |
+
"loss": 0.0216,
|
| 2432 |
+
"step": 345
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 7.361702127659575,
|
| 2436 |
+
"grad_norm": 0.9172465899189646,
|
| 2437 |
+
"learning_rate": 8.797002473421729e-07,
|
| 2438 |
+
"loss": 0.0172,
|
| 2439 |
+
"step": 346
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 7.382978723404255,
|
| 2443 |
+
"grad_norm": 0.9762896610645739,
|
| 2444 |
+
"learning_rate": 8.664484900247363e-07,
|
| 2445 |
+
"loss": 0.0196,
|
| 2446 |
+
"step": 347
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 7.404255319148936,
|
| 2450 |
+
"grad_norm": 1.2366903890873284,
|
| 2451 |
+
"learning_rate": 8.532763497032987e-07,
|
| 2452 |
+
"loss": 0.0192,
|
| 2453 |
+
"step": 348
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 7.425531914893617,
|
| 2457 |
+
"grad_norm": 0.8921247183956026,
|
| 2458 |
+
"learning_rate": 8.40184468369396e-07,
|
| 2459 |
+
"loss": 0.0138,
|
| 2460 |
+
"step": 349
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 7.446808510638298,
|
| 2464 |
+
"grad_norm": 1.371683786414812,
|
| 2465 |
+
"learning_rate": 8.271734841028553e-07,
|
| 2466 |
+
"loss": 0.0257,
|
| 2467 |
+
"step": 350
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 7.468085106382979,
|
| 2471 |
+
"grad_norm": 1.6706279670454172,
|
| 2472 |
+
"learning_rate": 8.142440310406923e-07,
|
| 2473 |
+
"loss": 0.0221,
|
| 2474 |
+
"step": 351
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 7.48936170212766,
|
| 2478 |
+
"grad_norm": 1.0048836984452958,
|
| 2479 |
+
"learning_rate": 8.013967393462094e-07,
|
| 2480 |
+
"loss": 0.0179,
|
| 2481 |
+
"step": 352
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 7.51063829787234,
|
| 2485 |
+
"grad_norm": 1.028897861820127,
|
| 2486 |
+
"learning_rate": 7.886322351782782e-07,
|
| 2487 |
+
"loss": 0.0173,
|
| 2488 |
+
"step": 353
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 7.531914893617021,
|
| 2492 |
+
"grad_norm": 0.9414634888570663,
|
| 2493 |
+
"learning_rate": 7.759511406608255e-07,
|
| 2494 |
+
"loss": 0.0194,
|
| 2495 |
+
"step": 354
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 7.553191489361702,
|
| 2499 |
+
"grad_norm": 1.3421193366601667,
|
| 2500 |
+
"learning_rate": 7.633540738525066e-07,
|
| 2501 |
+
"loss": 0.0155,
|
| 2502 |
+
"step": 355
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 7.574468085106383,
|
| 2506 |
+
"grad_norm": 1.3991724028833572,
|
| 2507 |
+
"learning_rate": 7.508416487165862e-07,
|
| 2508 |
+
"loss": 0.0242,
|
| 2509 |
+
"step": 356
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 7.595744680851064,
|
| 2513 |
+
"grad_norm": 3.4908651855373067,
|
| 2514 |
+
"learning_rate": 7.384144750910133e-07,
|
| 2515 |
+
"loss": 0.0201,
|
| 2516 |
+
"step": 357
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 7.617021276595745,
|
| 2520 |
+
"grad_norm": 1.1125708607058544,
|
| 2521 |
+
"learning_rate": 7.260731586586983e-07,
|
| 2522 |
+
"loss": 0.0181,
|
| 2523 |
+
"step": 358
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 7.638297872340425,
|
| 2527 |
+
"grad_norm": 2.003422428134198,
|
| 2528 |
+
"learning_rate": 7.138183009179922e-07,
|
| 2529 |
+
"loss": 0.0244,
|
| 2530 |
+
"step": 359
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 7.659574468085106,
|
| 2534 |
+
"grad_norm": 0.8666069576765489,
|
| 2535 |
+
"learning_rate": 7.016504991533727e-07,
|
| 2536 |
+
"loss": 0.0231,
|
| 2537 |
+
"step": 360
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 7.680851063829787,
|
| 2541 |
+
"grad_norm": 0.8225857804515108,
|
| 2542 |
+
"learning_rate": 6.895703464063319e-07,
|
| 2543 |
+
"loss": 0.0127,
|
| 2544 |
+
"step": 361
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 7.702127659574468,
|
| 2548 |
+
"grad_norm": 1.2220101527746525,
|
| 2549 |
+
"learning_rate": 6.775784314464717e-07,
|
| 2550 |
+
"loss": 0.0261,
|
| 2551 |
+
"step": 362
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 7.723404255319149,
|
| 2555 |
+
"grad_norm": 1.291947063153676,
|
| 2556 |
+
"learning_rate": 6.656753387428089e-07,
|
| 2557 |
+
"loss": 0.024,
|
| 2558 |
+
"step": 363
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 7.74468085106383,
|
| 2562 |
+
"grad_norm": 1.288638995380391,
|
| 2563 |
+
"learning_rate": 6.538616484352902e-07,
|
| 2564 |
+
"loss": 0.016,
|
| 2565 |
+
"step": 364
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 7.76595744680851,
|
| 2569 |
+
"grad_norm": 1.3674238710009354,
|
| 2570 |
+
"learning_rate": 6.421379363065142e-07,
|
| 2571 |
+
"loss": 0.0253,
|
| 2572 |
+
"step": 365
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 7.787234042553192,
|
| 2576 |
+
"grad_norm": 0.877515831783811,
|
| 2577 |
+
"learning_rate": 6.305047737536707e-07,
|
| 2578 |
+
"loss": 0.0162,
|
| 2579 |
+
"step": 366
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 7.808510638297872,
|
| 2583 |
+
"grad_norm": 1.1630712659406794,
|
| 2584 |
+
"learning_rate": 6.189627277606894e-07,
|
| 2585 |
+
"loss": 0.0227,
|
| 2586 |
+
"step": 367
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 7.829787234042553,
|
| 2590 |
+
"grad_norm": 1.2379019290179472,
|
| 2591 |
+
"learning_rate": 6.075123608706093e-07,
|
| 2592 |
+
"loss": 0.0179,
|
| 2593 |
+
"step": 368
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 7.851063829787234,
|
| 2597 |
+
"grad_norm": 0.9761836229980341,
|
| 2598 |
+
"learning_rate": 5.961542311581586e-07,
|
| 2599 |
+
"loss": 0.017,
|
| 2600 |
+
"step": 369
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 7.872340425531915,
|
| 2604 |
+
"grad_norm": 1.2905446310752584,
|
| 2605 |
+
"learning_rate": 5.848888922025553e-07,
|
| 2606 |
+
"loss": 0.0237,
|
| 2607 |
+
"step": 370
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 7.8936170212765955,
|
| 2611 |
+
"grad_norm": 1.0599111161417107,
|
| 2612 |
+
"learning_rate": 5.737168930605272e-07,
|
| 2613 |
+
"loss": 0.0193,
|
| 2614 |
+
"step": 371
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 7.914893617021277,
|
| 2618 |
+
"grad_norm": 0.9002316779352258,
|
| 2619 |
+
"learning_rate": 5.626387782395512e-07,
|
| 2620 |
+
"loss": 0.0219,
|
| 2621 |
+
"step": 372
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 7.9361702127659575,
|
| 2625 |
+
"grad_norm": 1.0871181403304409,
|
| 2626 |
+
"learning_rate": 5.516550876713142e-07,
|
| 2627 |
+
"loss": 0.0202,
|
| 2628 |
+
"step": 373
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 7.957446808510638,
|
| 2632 |
+
"grad_norm": 0.7739867037107642,
|
| 2633 |
+
"learning_rate": 5.407663566854008e-07,
|
| 2634 |
+
"loss": 0.0141,
|
| 2635 |
+
"step": 374
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 7.9787234042553195,
|
| 2639 |
+
"grad_norm": 1.1646231525599027,
|
| 2640 |
+
"learning_rate": 5.299731159831953e-07,
|
| 2641 |
+
"loss": 0.0199,
|
| 2642 |
+
"step": 375
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 8.0,
|
| 2646 |
+
"grad_norm": 0.8486174354933951,
|
| 2647 |
+
"learning_rate": 5.192758916120236e-07,
|
| 2648 |
+
"loss": 0.0183,
|
| 2649 |
+
"step": 376
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 8.02127659574468,
|
| 2653 |
+
"grad_norm": 0.5857908765113855,
|
| 2654 |
+
"learning_rate": 5.086752049395094e-07,
|
| 2655 |
+
"loss": 0.0154,
|
| 2656 |
+
"step": 377
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 8.042553191489361,
|
| 2660 |
+
"grad_norm": 0.820073038781464,
|
| 2661 |
+
"learning_rate": 4.981715726281666e-07,
|
| 2662 |
+
"loss": 0.0162,
|
| 2663 |
+
"step": 378
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 8.063829787234043,
|
| 2667 |
+
"grad_norm": 0.5353750025209411,
|
| 2668 |
+
"learning_rate": 4.87765506610215e-07,
|
| 2669 |
+
"loss": 0.0117,
|
| 2670 |
+
"step": 379
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 8.085106382978724,
|
| 2674 |
+
"grad_norm": 0.6641723492880932,
|
| 2675 |
+
"learning_rate": 4.774575140626317e-07,
|
| 2676 |
+
"loss": 0.0155,
|
| 2677 |
+
"step": 380
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 8.106382978723405,
|
| 2681 |
+
"grad_norm": 1.5478055693073858,
|
| 2682 |
+
"learning_rate": 4.672480973824312e-07,
|
| 2683 |
+
"loss": 0.0138,
|
| 2684 |
+
"step": 381
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 8.127659574468085,
|
| 2688 |
+
"grad_norm": 0.5935452327954517,
|
| 2689 |
+
"learning_rate": 4.5713775416217884e-07,
|
| 2690 |
+
"loss": 0.0128,
|
| 2691 |
+
"step": 382
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 8.148936170212766,
|
| 2695 |
+
"grad_norm": 0.45835158236977624,
|
| 2696 |
+
"learning_rate": 4.4712697716573994e-07,
|
| 2697 |
+
"loss": 0.014,
|
| 2698 |
+
"step": 383
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 8.170212765957446,
|
| 2702 |
+
"grad_norm": 0.495302571001091,
|
| 2703 |
+
"learning_rate": 4.372162543042624e-07,
|
| 2704 |
+
"loss": 0.0135,
|
| 2705 |
+
"step": 384
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 8.191489361702128,
|
| 2709 |
+
"grad_norm": 0.4653447676593763,
|
| 2710 |
+
"learning_rate": 4.27406068612396e-07,
|
| 2711 |
+
"loss": 0.0113,
|
| 2712 |
+
"step": 385
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 8.212765957446809,
|
| 2716 |
+
"grad_norm": 0.5764443378886089,
|
| 2717 |
+
"learning_rate": 4.1769689822475147e-07,
|
| 2718 |
+
"loss": 0.0149,
|
| 2719 |
+
"step": 386
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 8.23404255319149,
|
| 2723 |
+
"grad_norm": 0.34507606047404416,
|
| 2724 |
+
"learning_rate": 4.0808921635259595e-07,
|
| 2725 |
+
"loss": 0.0096,
|
| 2726 |
+
"step": 387
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 8.25531914893617,
|
| 2730 |
+
"grad_norm": 0.6316918421422608,
|
| 2731 |
+
"learning_rate": 3.9858349126078945e-07,
|
| 2732 |
+
"loss": 0.0149,
|
| 2733 |
+
"step": 388
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 8.27659574468085,
|
| 2737 |
+
"grad_norm": 1.13945433310328,
|
| 2738 |
+
"learning_rate": 3.891801862449629e-07,
|
| 2739 |
+
"loss": 0.0171,
|
| 2740 |
+
"step": 389
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 8.297872340425531,
|
| 2744 |
+
"grad_norm": 1.6671178791582812,
|
| 2745 |
+
"learning_rate": 3.798797596089351e-07,
|
| 2746 |
+
"loss": 0.0162,
|
| 2747 |
+
"step": 390
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 8.319148936170214,
|
| 2751 |
+
"grad_norm": 0.6242884167930942,
|
| 2752 |
+
"learning_rate": 3.7068266464238085e-07,
|
| 2753 |
+
"loss": 0.0171,
|
| 2754 |
+
"step": 391
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 8.340425531914894,
|
| 2758 |
+
"grad_norm": 0.6157189166745389,
|
| 2759 |
+
"learning_rate": 3.615893495987335e-07,
|
| 2760 |
+
"loss": 0.0083,
|
| 2761 |
+
"step": 392
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 8.361702127659575,
|
| 2765 |
+
"grad_norm": 1.187375482456905,
|
| 2766 |
+
"learning_rate": 3.5260025767333894e-07,
|
| 2767 |
+
"loss": 0.0133,
|
| 2768 |
+
"step": 393
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 8.382978723404255,
|
| 2772 |
+
"grad_norm": 0.9198827823698973,
|
| 2773 |
+
"learning_rate": 3.4371582698185636e-07,
|
| 2774 |
+
"loss": 0.0168,
|
| 2775 |
+
"step": 394
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 8.404255319148936,
|
| 2779 |
+
"grad_norm": 0.9127337383828107,
|
| 2780 |
+
"learning_rate": 3.3493649053890325e-07,
|
| 2781 |
+
"loss": 0.0167,
|
| 2782 |
+
"step": 395
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 8.425531914893616,
|
| 2786 |
+
"grad_norm": 0.4716697636311403,
|
| 2787 |
+
"learning_rate": 3.262626762369525e-07,
|
| 2788 |
+
"loss": 0.0134,
|
| 2789 |
+
"step": 396
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 8.446808510638299,
|
| 2793 |
+
"grad_norm": 0.5430698963916597,
|
| 2794 |
+
"learning_rate": 3.176948068254762e-07,
|
| 2795 |
+
"loss": 0.0115,
|
| 2796 |
+
"step": 397
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 8.46808510638298,
|
| 2800 |
+
"grad_norm": 0.5589379122310724,
|
| 2801 |
+
"learning_rate": 3.092332998903416e-07,
|
| 2802 |
+
"loss": 0.0134,
|
| 2803 |
+
"step": 398
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 8.48936170212766,
|
| 2807 |
+
"grad_norm": 1.0297905449956246,
|
| 2808 |
+
"learning_rate": 3.0087856783345916e-07,
|
| 2809 |
+
"loss": 0.0165,
|
| 2810 |
+
"step": 399
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 8.51063829787234,
|
| 2814 |
+
"grad_norm": 0.5586126342363132,
|
| 2815 |
+
"learning_rate": 2.9263101785268253e-07,
|
| 2816 |
+
"loss": 0.0129,
|
| 2817 |
+
"step": 400
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 8.51063829787234,
|
| 2821 |
+
"eval_loss": 1.6673990488052368,
|
| 2822 |
+
"eval_runtime": 1.6235,
|
| 2823 |
+
"eval_samples_per_second": 14.167,
|
| 2824 |
+
"eval_steps_per_second": 0.616,
|
| 2825 |
+
"step": 400
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 8.53191489361702,
|
| 2829 |
+
"grad_norm": 0.5428039786664497,
|
| 2830 |
+
"learning_rate": 2.844910519219632e-07,
|
| 2831 |
+
"loss": 0.0128,
|
| 2832 |
+
"step": 401
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 8.553191489361701,
|
| 2836 |
+
"grad_norm": 0.633307262716061,
|
| 2837 |
+
"learning_rate": 2.764590667717562e-07,
|
| 2838 |
+
"loss": 0.0161,
|
| 2839 |
+
"step": 402
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 8.574468085106384,
|
| 2843 |
+
"grad_norm": 0.5251963830034382,
|
| 2844 |
+
"learning_rate": 2.6853545386968607e-07,
|
| 2845 |
+
"loss": 0.0115,
|
| 2846 |
+
"step": 403
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 8.595744680851064,
|
| 2850 |
+
"grad_norm": 0.48124935494240734,
|
| 2851 |
+
"learning_rate": 2.6072059940146775e-07,
|
| 2852 |
+
"loss": 0.0097,
|
| 2853 |
+
"step": 404
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 8.617021276595745,
|
| 2857 |
+
"grad_norm": 0.5546850016440125,
|
| 2858 |
+
"learning_rate": 2.53014884252083e-07,
|
| 2859 |
+
"loss": 0.0095,
|
| 2860 |
+
"step": 405
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 8.638297872340425,
|
| 2864 |
+
"grad_norm": 0.6870597575288601,
|
| 2865 |
+
"learning_rate": 2.454186839872158e-07,
|
| 2866 |
+
"loss": 0.0161,
|
| 2867 |
+
"step": 406
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 8.659574468085106,
|
| 2871 |
+
"grad_norm": 0.5075138452670342,
|
| 2872 |
+
"learning_rate": 2.3793236883495164e-07,
|
| 2873 |
+
"loss": 0.0137,
|
| 2874 |
+
"step": 407
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 8.680851063829786,
|
| 2878 |
+
"grad_norm": 0.7184250889463067,
|
| 2879 |
+
"learning_rate": 2.3055630366772857e-07,
|
| 2880 |
+
"loss": 0.0124,
|
| 2881 |
+
"step": 408
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 8.702127659574469,
|
| 2885 |
+
"grad_norm": 0.6095068862526991,
|
| 2886 |
+
"learning_rate": 2.2329084798455747e-07,
|
| 2887 |
+
"loss": 0.0145,
|
| 2888 |
+
"step": 409
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 8.72340425531915,
|
| 2892 |
+
"grad_norm": 0.5513423746444825,
|
| 2893 |
+
"learning_rate": 2.1613635589349756e-07,
|
| 2894 |
+
"loss": 0.0155,
|
| 2895 |
+
"step": 410
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 8.74468085106383,
|
| 2899 |
+
"grad_norm": 0.5875898983901224,
|
| 2900 |
+
"learning_rate": 2.0909317609440093e-07,
|
| 2901 |
+
"loss": 0.0146,
|
| 2902 |
+
"step": 411
|
| 2903 |
+
},
|
| 2904 |
+
{
|
| 2905 |
+
"epoch": 8.76595744680851,
|
| 2906 |
+
"grad_norm": 0.5750560265603247,
|
| 2907 |
+
"learning_rate": 2.0216165186191406e-07,
|
| 2908 |
+
"loss": 0.0131,
|
| 2909 |
+
"step": 412
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 8.787234042553191,
|
| 2913 |
+
"grad_norm": 0.6746724848758707,
|
| 2914 |
+
"learning_rate": 1.95342121028749e-07,
|
| 2915 |
+
"loss": 0.0118,
|
| 2916 |
+
"step": 413
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"epoch": 8.808510638297872,
|
| 2920 |
+
"grad_norm": 0.6972301523231518,
|
| 2921 |
+
"learning_rate": 1.8863491596921745e-07,
|
| 2922 |
+
"loss": 0.0143,
|
| 2923 |
+
"step": 414
|
| 2924 |
+
},
|
| 2925 |
+
{
|
| 2926 |
+
"epoch": 8.829787234042554,
|
| 2927 |
+
"grad_norm": 0.7525328974002997,
|
| 2928 |
+
"learning_rate": 1.8204036358303173e-07,
|
| 2929 |
+
"loss": 0.0144,
|
| 2930 |
+
"step": 415
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 8.851063829787234,
|
| 2934 |
+
"grad_norm": 0.5087036176440635,
|
| 2935 |
+
"learning_rate": 1.7555878527937164e-07,
|
| 2936 |
+
"loss": 0.0117,
|
| 2937 |
+
"step": 416
|
| 2938 |
+
},
|
| 2939 |
+
{
|
| 2940 |
+
"epoch": 8.872340425531915,
|
| 2941 |
+
"grad_norm": 0.6061494141417032,
|
| 2942 |
+
"learning_rate": 1.6919049696121957e-07,
|
| 2943 |
+
"loss": 0.0168,
|
| 2944 |
+
"step": 417
|
| 2945 |
+
},
|
| 2946 |
+
{
|
| 2947 |
+
"epoch": 8.893617021276595,
|
| 2948 |
+
"grad_norm": 0.6674633587572225,
|
| 2949 |
+
"learning_rate": 1.629358090099639e-07,
|
| 2950 |
+
"loss": 0.0154,
|
| 2951 |
+
"step": 418
|
| 2952 |
+
},
|
| 2953 |
+
{
|
| 2954 |
+
"epoch": 8.914893617021276,
|
| 2955 |
+
"grad_norm": 0.6381527241007888,
|
| 2956 |
+
"learning_rate": 1.567950262702714e-07,
|
| 2957 |
+
"loss": 0.0118,
|
| 2958 |
+
"step": 419
|
| 2959 |
+
},
|
| 2960 |
+
{
|
| 2961 |
+
"epoch": 8.936170212765958,
|
| 2962 |
+
"grad_norm": 0.5652826587480684,
|
| 2963 |
+
"learning_rate": 1.507684480352292e-07,
|
| 2964 |
+
"loss": 0.0142,
|
| 2965 |
+
"step": 420
|
| 2966 |
+
},
|
| 2967 |
+
{
|
| 2968 |
+
"epoch": 8.957446808510639,
|
| 2969 |
+
"grad_norm": 0.5390136780396995,
|
| 2970 |
+
"learning_rate": 1.4485636803175828e-07,
|
| 2971 |
+
"loss": 0.0153,
|
| 2972 |
+
"step": 421
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 8.97872340425532,
|
| 2976 |
+
"grad_norm": 0.4433110433252025,
|
| 2977 |
+
"learning_rate": 1.3905907440629752e-07,
|
| 2978 |
+
"loss": 0.0128,
|
| 2979 |
+
"step": 422
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 9.0,
|
| 2983 |
+
"grad_norm": 0.3937254962258607,
|
| 2984 |
+
"learning_rate": 1.3337684971075932e-07,
|
| 2985 |
+
"loss": 0.0141,
|
| 2986 |
+
"step": 423
|
| 2987 |
+
},
|
| 2988 |
+
{
|
| 2989 |
+
"epoch": 9.02127659574468,
|
| 2990 |
+
"grad_norm": 0.42872899914768886,
|
| 2991 |
+
"learning_rate": 1.278099708887587e-07,
|
| 2992 |
+
"loss": 0.0139,
|
| 2993 |
+
"step": 424
|
| 2994 |
+
},
|
| 2995 |
+
{
|
| 2996 |
+
"epoch": 9.042553191489361,
|
| 2997 |
+
"grad_norm": 0.43176685764328526,
|
| 2998 |
+
"learning_rate": 1.223587092621162e-07,
|
| 2999 |
+
"loss": 0.01,
|
| 3000 |
+
"step": 425
|
| 3001 |
+
},
|
| 3002 |
+
{
|
| 3003 |
+
"epoch": 9.063829787234043,
|
| 3004 |
+
"grad_norm": 0.3743485104670554,
|
| 3005 |
+
"learning_rate": 1.1702333051763271e-07,
|
| 3006 |
+
"loss": 0.0082,
|
| 3007 |
+
"step": 426
|
| 3008 |
+
},
|
| 3009 |
+
{
|
| 3010 |
+
"epoch": 9.085106382978724,
|
| 3011 |
+
"grad_norm": 0.39987032601374245,
|
| 3012 |
+
"learning_rate": 1.1180409469414094e-07,
|
| 3013 |
+
"loss": 0.0125,
|
| 3014 |
+
"step": 427
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 9.106382978723405,
|
| 3018 |
+
"grad_norm": 0.39568260783662074,
|
| 3019 |
+
"learning_rate": 1.067012561698319e-07,
|
| 3020 |
+
"loss": 0.0099,
|
| 3021 |
+
"step": 428
|
| 3022 |
+
},
|
| 3023 |
+
{
|
| 3024 |
+
"epoch": 9.127659574468085,
|
| 3025 |
+
"grad_norm": 0.4002164747878374,
|
| 3026 |
+
"learning_rate": 1.0171506364985622e-07,
|
| 3027 |
+
"loss": 0.0141,
|
| 3028 |
+
"step": 429
|
| 3029 |
+
},
|
| 3030 |
+
{
|
| 3031 |
+
"epoch": 9.148936170212766,
|
| 3032 |
+
"grad_norm": 0.3140844748261339,
|
| 3033 |
+
"learning_rate": 9.684576015420277e-08,
|
| 3034 |
+
"loss": 0.0083,
|
| 3035 |
+
"step": 430
|
| 3036 |
+
},
|
| 3037 |
+
{
|
| 3038 |
+
"epoch": 9.170212765957446,
|
| 3039 |
+
"grad_norm": 3.0839571989766026,
|
| 3040 |
+
"learning_rate": 9.209358300585474e-08,
|
| 3041 |
+
"loss": 0.0107,
|
| 3042 |
+
"step": 431
|
| 3043 |
+
},
|
| 3044 |
+
{
|
| 3045 |
+
"epoch": 9.191489361702128,
|
| 3046 |
+
"grad_norm": 0.43386426711502496,
|
| 3047 |
+
"learning_rate": 8.745876381922147e-08,
|
| 3048 |
+
"loss": 0.0114,
|
| 3049 |
+
"step": 432
|
| 3050 |
+
},
|
| 3051 |
+
{
|
| 3052 |
+
"epoch": 9.212765957446809,
|
| 3053 |
+
"grad_norm": 0.49575077577441945,
|
| 3054 |
+
"learning_rate": 8.294152848885156e-08,
|
| 3055 |
+
"loss": 0.0122,
|
| 3056 |
+
"step": 433
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 9.23404255319149,
|
| 3060 |
+
"grad_norm": 0.42605421543375827,
|
| 3061 |
+
"learning_rate": 7.854209717842231e-08,
|
| 3062 |
+
"loss": 0.0123,
|
| 3063 |
+
"step": 434
|
| 3064 |
+
},
|
| 3065 |
+
{
|
| 3066 |
+
"epoch": 9.25531914893617,
|
| 3067 |
+
"grad_norm": 0.4159085198061852,
|
| 3068 |
+
"learning_rate": 7.426068431000883e-08,
|
| 3069 |
+
"loss": 0.011,
|
| 3070 |
+
"step": 435
|
| 3071 |
+
},
|
| 3072 |
+
{
|
| 3073 |
+
"epoch": 9.27659574468085,
|
| 3074 |
+
"grad_norm": 0.4297510739797917,
|
| 3075 |
+
"learning_rate": 7.009749855363457e-08,
|
| 3076 |
+
"loss": 0.0096,
|
| 3077 |
+
"step": 436
|
| 3078 |
+
},
|
| 3079 |
+
{
|
| 3080 |
+
"epoch": 9.297872340425531,
|
| 3081 |
+
"grad_norm": 0.39770284394181865,
|
| 3082 |
+
"learning_rate": 6.605274281709929e-08,
|
| 3083 |
+
"loss": 0.0108,
|
| 3084 |
+
"step": 437
|
| 3085 |
+
},
|
| 3086 |
+
{
|
| 3087 |
+
"epoch": 9.319148936170214,
|
| 3088 |
+
"grad_norm": 0.3799358013058963,
|
| 3089 |
+
"learning_rate": 6.212661423609184e-08,
|
| 3090 |
+
"loss": 0.0135,
|
| 3091 |
+
"step": 438
|
| 3092 |
+
},
|
| 3093 |
+
{
|
| 3094 |
+
"epoch": 9.340425531914894,
|
| 3095 |
+
"grad_norm": 0.40685286788703806,
|
| 3096 |
+
"learning_rate": 5.83193041645802e-08,
|
| 3097 |
+
"loss": 0.0105,
|
| 3098 |
+
"step": 439
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 9.361702127659575,
|
| 3102 |
+
"grad_norm": 0.5276489442708509,
|
| 3103 |
+
"learning_rate": 5.463099816548578e-08,
|
| 3104 |
+
"loss": 0.0159,
|
| 3105 |
+
"step": 440
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"epoch": 9.382978723404255,
|
| 3109 |
+
"grad_norm": 0.3398816914667588,
|
| 3110 |
+
"learning_rate": 5.106187600163987e-08,
|
| 3111 |
+
"loss": 0.01,
|
| 3112 |
+
"step": 441
|
| 3113 |
+
},
|
| 3114 |
+
{
|
| 3115 |
+
"epoch": 9.404255319148936,
|
| 3116 |
+
"grad_norm": 0.43060715328426347,
|
| 3117 |
+
"learning_rate": 4.761211162702117e-08,
|
| 3118 |
+
"loss": 0.0109,
|
| 3119 |
+
"step": 442
|
| 3120 |
+
},
|
| 3121 |
+
{
|
| 3122 |
+
"epoch": 9.425531914893616,
|
| 3123 |
+
"grad_norm": 0.6155281563788073,
|
| 3124 |
+
"learning_rate": 4.428187317827848e-08,
|
| 3125 |
+
"loss": 0.0107,
|
| 3126 |
+
"step": 443
|
| 3127 |
+
},
|
| 3128 |
+
{
|
| 3129 |
+
"epoch": 9.446808510638299,
|
| 3130 |
+
"grad_norm": 0.4920360355401412,
|
| 3131 |
+
"learning_rate": 4.1071322966535487e-08,
|
| 3132 |
+
"loss": 0.0139,
|
| 3133 |
+
"step": 444
|
| 3134 |
+
},
|
| 3135 |
+
{
|
| 3136 |
+
"epoch": 9.46808510638298,
|
| 3137 |
+
"grad_norm": 0.44825099453614115,
|
| 3138 |
+
"learning_rate": 3.798061746947995e-08,
|
| 3139 |
+
"loss": 0.0113,
|
| 3140 |
+
"step": 445
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 9.48936170212766,
|
| 3144 |
+
"grad_norm": 0.48315881463136157,
|
| 3145 |
+
"learning_rate": 3.5009907323737826e-08,
|
| 3146 |
+
"loss": 0.0131,
|
| 3147 |
+
"step": 446
|
| 3148 |
+
},
|
| 3149 |
+
{
|
| 3150 |
+
"epoch": 9.51063829787234,
|
| 3151 |
+
"grad_norm": 0.3897061025707457,
|
| 3152 |
+
"learning_rate": 3.2159337317530234e-08,
|
| 3153 |
+
"loss": 0.0131,
|
| 3154 |
+
"step": 447
|
| 3155 |
+
},
|
| 3156 |
+
{
|
| 3157 |
+
"epoch": 9.53191489361702,
|
| 3158 |
+
"grad_norm": 0.3845441440160021,
|
| 3159 |
+
"learning_rate": 2.9429046383618042e-08,
|
| 3160 |
+
"loss": 0.0094,
|
| 3161 |
+
"step": 448
|
| 3162 |
+
},
|
| 3163 |
+
{
|
| 3164 |
+
"epoch": 9.553191489361701,
|
| 3165 |
+
"grad_norm": 0.4018776472448016,
|
| 3166 |
+
"learning_rate": 2.681916759252917e-08,
|
| 3167 |
+
"loss": 0.0117,
|
| 3168 |
+
"step": 449
|
| 3169 |
+
},
|
| 3170 |
+
{
|
| 3171 |
+
"epoch": 9.574468085106384,
|
| 3172 |
+
"grad_norm": 0.3789922116838833,
|
| 3173 |
+
"learning_rate": 2.4329828146074096e-08,
|
| 3174 |
+
"loss": 0.0099,
|
| 3175 |
+
"step": 450
|
| 3176 |
+
},
|
| 3177 |
+
{
|
| 3178 |
+
"epoch": 9.595744680851064,
|
| 3179 |
+
"grad_norm": 0.47356186931300714,
|
| 3180 |
+
"learning_rate": 2.1961149371145795e-08,
|
| 3181 |
+
"loss": 0.012,
|
| 3182 |
+
"step": 451
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 9.617021276595745,
|
| 3186 |
+
"grad_norm": 0.5175691416116797,
|
| 3187 |
+
"learning_rate": 1.9713246713805588e-08,
|
| 3188 |
+
"loss": 0.0137,
|
| 3189 |
+
"step": 452
|
| 3190 |
+
},
|
| 3191 |
+
{
|
| 3192 |
+
"epoch": 9.638297872340425,
|
| 3193 |
+
"grad_norm": 0.35550871415754165,
|
| 3194 |
+
"learning_rate": 1.7586229733657646e-08,
|
| 3195 |
+
"loss": 0.0126,
|
| 3196 |
+
"step": 453
|
| 3197 |
+
},
|
| 3198 |
+
{
|
| 3199 |
+
"epoch": 9.659574468085106,
|
| 3200 |
+
"grad_norm": 0.4521940543192018,
|
| 3201 |
+
"learning_rate": 1.5580202098509078e-08,
|
| 3202 |
+
"loss": 0.0123,
|
| 3203 |
+
"step": 454
|
| 3204 |
+
},
|
| 3205 |
+
{
|
| 3206 |
+
"epoch": 9.680851063829786,
|
| 3207 |
+
"grad_norm": 0.3645510186204655,
|
| 3208 |
+
"learning_rate": 1.3695261579316776e-08,
|
| 3209 |
+
"loss": 0.0099,
|
| 3210 |
+
"step": 455
|
| 3211 |
+
},
|
| 3212 |
+
{
|
| 3213 |
+
"epoch": 9.702127659574469,
|
| 3214 |
+
"grad_norm": 0.5052016943572653,
|
| 3215 |
+
"learning_rate": 1.193150004542204e-08,
|
| 3216 |
+
"loss": 0.0108,
|
| 3217 |
+
"step": 456
|
| 3218 |
+
},
|
| 3219 |
+
{
|
| 3220 |
+
"epoch": 9.72340425531915,
|
| 3221 |
+
"grad_norm": 0.4591420783076054,
|
| 3222 |
+
"learning_rate": 1.0289003460074165e-08,
|
| 3223 |
+
"loss": 0.0136,
|
| 3224 |
+
"step": 457
|
| 3225 |
+
},
|
| 3226 |
+
{
|
| 3227 |
+
"epoch": 9.74468085106383,
|
| 3228 |
+
"grad_norm": 0.3979451604394145,
|
| 3229 |
+
"learning_rate": 8.767851876239075e-09,
|
| 3230 |
+
"loss": 0.0124,
|
| 3231 |
+
"step": 458
|
| 3232 |
+
},
|
| 3233 |
+
{
|
| 3234 |
+
"epoch": 9.76595744680851,
|
| 3235 |
+
"grad_norm": 0.4508311448933257,
|
| 3236 |
+
"learning_rate": 7.368119432699383e-09,
|
| 3237 |
+
"loss": 0.0117,
|
| 3238 |
+
"step": 459
|
| 3239 |
+
},
|
| 3240 |
+
{
|
| 3241 |
+
"epoch": 9.787234042553191,
|
| 3242 |
+
"grad_norm": 0.48162461236003445,
|
| 3243 |
+
"learning_rate": 6.089874350439507e-09,
|
| 3244 |
+
"loss": 0.0131,
|
| 3245 |
+
"step": 460
|
| 3246 |
+
},
|
| 3247 |
+
{
|
| 3248 |
+
"epoch": 9.808510638297872,
|
| 3249 |
+
"grad_norm": 0.3727617520322409,
|
| 3250 |
+
"learning_rate": 4.933178929321103e-09,
|
| 3251 |
+
"loss": 0.0092,
|
| 3252 |
+
"step": 461
|
| 3253 |
+
},
|
| 3254 |
+
{
|
| 3255 |
+
"epoch": 9.829787234042554,
|
| 3256 |
+
"grad_norm": 0.37748204227545856,
|
| 3257 |
+
"learning_rate": 3.8980895450474455e-09,
|
| 3258 |
+
"loss": 0.0108,
|
| 3259 |
+
"step": 462
|
| 3260 |
+
},
|
| 3261 |
+
{
|
| 3262 |
+
"epoch": 9.851063829787234,
|
| 3263 |
+
"grad_norm": 0.30954369790579545,
|
| 3264 |
+
"learning_rate": 2.984656646415063e-09,
|
| 3265 |
+
"loss": 0.0082,
|
| 3266 |
+
"step": 463
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 9.872340425531915,
|
| 3270 |
+
"grad_norm": 0.441565820890093,
|
| 3271 |
+
"learning_rate": 2.192924752854042e-09,
|
| 3272 |
+
"loss": 0.014,
|
| 3273 |
+
"step": 464
|
| 3274 |
+
},
|
| 3275 |
+
{
|
| 3276 |
+
"epoch": 9.893617021276595,
|
| 3277 |
+
"grad_norm": 0.42642106144925446,
|
| 3278 |
+
"learning_rate": 1.5229324522605949e-09,
|
| 3279 |
+
"loss": 0.0086,
|
| 3280 |
+
"step": 465
|
| 3281 |
+
},
|
| 3282 |
+
{
|
| 3283 |
+
"epoch": 9.914893617021276,
|
| 3284 |
+
"grad_norm": 0.3393626098420996,
|
| 3285 |
+
"learning_rate": 9.747123991141193e-10,
|
| 3286 |
+
"loss": 0.008,
|
| 3287 |
+
"step": 466
|
| 3288 |
+
},
|
| 3289 |
+
{
|
| 3290 |
+
"epoch": 9.936170212765958,
|
| 3291 |
+
"grad_norm": 0.4441469010998739,
|
| 3292 |
+
"learning_rate": 5.48291312886251e-10,
|
| 3293 |
+
"loss": 0.0135,
|
| 3294 |
+
"step": 467
|
| 3295 |
+
},
|
| 3296 |
+
{
|
| 3297 |
+
"epoch": 9.957446808510639,
|
| 3298 |
+
"grad_norm": 0.44011051414564956,
|
| 3299 |
+
"learning_rate": 2.43689976739403e-10,
|
| 3300 |
+
"loss": 0.0117,
|
| 3301 |
+
"step": 468
|
| 3302 |
+
},
|
| 3303 |
+
{
|
| 3304 |
+
"epoch": 9.97872340425532,
|
| 3305 |
+
"grad_norm": 0.47111655728750834,
|
| 3306 |
+
"learning_rate": 6.092323651313293e-11,
|
| 3307 |
+
"loss": 0.0104,
|
| 3308 |
+
"step": 469
|
| 3309 |
+
},
|
| 3310 |
+
{
|
| 3311 |
+
"epoch": 10.0,
|
| 3312 |
+
"grad_norm": 0.5133248194623898,
|
| 3313 |
+
"learning_rate": 0.0,
|
| 3314 |
+
"loss": 0.0161,
|
| 3315 |
+
"step": 470
|
| 3316 |
+
}
|
| 3317 |
+
],
|
| 3318 |
+
"logging_steps": 1.0,
|
| 3319 |
+
"max_steps": 470,
|
| 3320 |
+
"num_input_tokens_seen": 0,
|
| 3321 |
+
"num_train_epochs": 10,
|
| 3322 |
+
"save_steps": 1000,
|
| 3323 |
+
"stateful_callbacks": {
|
| 3324 |
+
"TrainerControl": {
|
| 3325 |
+
"args": {
|
| 3326 |
+
"should_epoch_stop": false,
|
| 3327 |
+
"should_evaluate": false,
|
| 3328 |
+
"should_log": false,
|
| 3329 |
+
"should_save": true,
|
| 3330 |
+
"should_training_stop": true
|
| 3331 |
+
},
|
| 3332 |
+
"attributes": {}
|
| 3333 |
+
}
|
| 3334 |
+
},
|
| 3335 |
+
"total_flos": 32811979898880.0,
|
| 3336 |
+
"train_batch_size": 6,
|
| 3337 |
+
"trial_name": null,
|
| 3338 |
+
"trial_params": null
|
| 3339 |
+
}
|