Text Generation
Transformers
Safetensors
English
qwen3
text-generation-inference
unsloth
conversational
Instructions to use CompassioninMachineLearning/qwen-pretrained-part1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CompassioninMachineLearning/qwen-pretrained-part1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CompassioninMachineLearning/qwen-pretrained-part1") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CompassioninMachineLearning/qwen-pretrained-part1") model = AutoModelForCausalLM.from_pretrained("CompassioninMachineLearning/qwen-pretrained-part1", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use CompassioninMachineLearning/qwen-pretrained-part1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CompassioninMachineLearning/qwen-pretrained-part1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CompassioninMachineLearning/qwen-pretrained-part1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/CompassioninMachineLearning/qwen-pretrained-part1
- SGLang
How to use CompassioninMachineLearning/qwen-pretrained-part1 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 "CompassioninMachineLearning/qwen-pretrained-part1" \ --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": "CompassioninMachineLearning/qwen-pretrained-part1", "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 "CompassioninMachineLearning/qwen-pretrained-part1" \ --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": "CompassioninMachineLearning/qwen-pretrained-part1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use CompassioninMachineLearning/qwen-pretrained-part1 with Docker Model Runner:
docker model run hf.co/CompassioninMachineLearning/qwen-pretrained-part1
add trainer_state.json
Browse files- trainer_state.json +872 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,872 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 500,
|
| 3 |
+
"best_metric": 0.09908278286457062,
|
| 4 |
+
"best_model_checkpoint": "/workspace/anchor/qwen-pretrained/train/checkpoint-500",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 538,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.009306654257794323,
|
| 14 |
+
"grad_norm": 8.3795747756958,
|
| 15 |
+
"learning_rate": 2.962962962962963e-05,
|
| 16 |
+
"loss": 1.0965,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.018613308515588647,
|
| 21 |
+
"grad_norm": 3.7024037837982178,
|
| 22 |
+
"learning_rate": 6.666666666666667e-05,
|
| 23 |
+
"loss": 0.8571,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02791996277338297,
|
| 28 |
+
"grad_norm": 2.2940096855163574,
|
| 29 |
+
"learning_rate": 0.0001037037037037037,
|
| 30 |
+
"loss": 0.629,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03722661703117729,
|
| 35 |
+
"grad_norm": 2.2930526733398438,
|
| 36 |
+
"learning_rate": 0.00014074074074074076,
|
| 37 |
+
"loss": 0.527,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04653327128897161,
|
| 42 |
+
"grad_norm": 4.794444561004639,
|
| 43 |
+
"learning_rate": 0.00017777777777777779,
|
| 44 |
+
"loss": 0.5039,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05583992554676594,
|
| 49 |
+
"grad_norm": 3.5820388793945312,
|
| 50 |
+
"learning_rate": 0.0001999924406845452,
|
| 51 |
+
"loss": 0.4196,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06514657980456026,
|
| 56 |
+
"grad_norm": 3.9649713039398193,
|
| 57 |
+
"learning_rate": 0.00019990741151022301,
|
| 58 |
+
"loss": 0.3942,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07445323406235459,
|
| 63 |
+
"grad_norm": 2.7851450443267822,
|
| 64 |
+
"learning_rate": 0.00019972798462510112,
|
| 65 |
+
"loss": 0.3424,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08375988832014891,
|
| 70 |
+
"grad_norm": 2.488961935043335,
|
| 71 |
+
"learning_rate": 0.0001994543295610186,
|
| 72 |
+
"loss": 0.2828,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09306654257794322,
|
| 77 |
+
"grad_norm": 6.255297660827637,
|
| 78 |
+
"learning_rate": 0.00019908670488149148,
|
| 79 |
+
"loss": 0.2322,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.09306654257794322,
|
| 84 |
+
"eval_loss": 0.22483031451702118,
|
| 85 |
+
"eval_runtime": 157.1846,
|
| 86 |
+
"eval_samples_per_second": 1.406,
|
| 87 |
+
"eval_steps_per_second": 0.706,
|
| 88 |
+
"step": 50
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.10237319683573755,
|
| 92 |
+
"grad_norm": 1.058211326599121,
|
| 93 |
+
"learning_rate": 0.00019862545793740852,
|
| 94 |
+
"loss": 0.2246,
|
| 95 |
+
"step": 55
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.11167985109353187,
|
| 99 |
+
"grad_norm": 1.2681463956832886,
|
| 100 |
+
"learning_rate": 0.00019807102453883602,
|
| 101 |
+
"loss": 0.2238,
|
| 102 |
+
"step": 60
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.1209865053513262,
|
| 106 |
+
"grad_norm": 1.2710065841674805,
|
| 107 |
+
"learning_rate": 0.00019742392854324185,
|
| 108 |
+
"loss": 0.2353,
|
| 109 |
+
"step": 65
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.13029315960912052,
|
| 113 |
+
"grad_norm": 1.0538429021835327,
|
| 114 |
+
"learning_rate": 0.00019668478136052774,
|
| 115 |
+
"loss": 0.21,
|
| 116 |
+
"step": 70
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.13959981386691483,
|
| 120 |
+
"grad_norm": 1.3220242261886597,
|
| 121 |
+
"learning_rate": 0.00019585428137533744,
|
| 122 |
+
"loss": 0.2222,
|
| 123 |
+
"step": 75
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.14890646812470917,
|
| 127 |
+
"grad_norm": 1.1070969104766846,
|
| 128 |
+
"learning_rate": 0.00019493321328718652,
|
| 129 |
+
"loss": 0.1745,
|
| 130 |
+
"step": 80
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.15821312238250348,
|
| 134 |
+
"grad_norm": 1.2554668188095093,
|
| 135 |
+
"learning_rate": 0.00019392244736903772,
|
| 136 |
+
"loss": 0.1952,
|
| 137 |
+
"step": 85
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.16751977664029782,
|
| 141 |
+
"grad_norm": 1.53813898563385,
|
| 142 |
+
"learning_rate": 0.00019282293864502178,
|
| 143 |
+
"loss": 0.1863,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.17682643089809214,
|
| 148 |
+
"grad_norm": 1.1727522611618042,
|
| 149 |
+
"learning_rate": 0.0001916357259880809,
|
| 150 |
+
"loss": 0.1683,
|
| 151 |
+
"step": 95
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.18613308515588645,
|
| 155 |
+
"grad_norm": 0.9360535144805908,
|
| 156 |
+
"learning_rate": 0.0001903619311383879,
|
| 157 |
+
"loss": 0.1681,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.18613308515588645,
|
| 162 |
+
"eval_loss": 0.14435869455337524,
|
| 163 |
+
"eval_runtime": 72.7707,
|
| 164 |
+
"eval_samples_per_second": 3.037,
|
| 165 |
+
"eval_steps_per_second": 1.525,
|
| 166 |
+
"step": 100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.19543973941368079,
|
| 170 |
+
"grad_norm": 1.1460329294204712,
|
| 171 |
+
"learning_rate": 0.00018900275764346768,
|
| 172 |
+
"loss": 0.1456,
|
| 173 |
+
"step": 105
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.2047463936714751,
|
| 177 |
+
"grad_norm": 1.0264545679092407,
|
| 178 |
+
"learning_rate": 0.00018755948972102294,
|
| 179 |
+
"loss": 0.1788,
|
| 180 |
+
"step": 110
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.21405304792926944,
|
| 184 |
+
"grad_norm": 0.9038275480270386,
|
| 185 |
+
"learning_rate": 0.00018603349104553884,
|
| 186 |
+
"loss": 0.1864,
|
| 187 |
+
"step": 115
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.22335970218706375,
|
| 191 |
+
"grad_norm": 0.8495742082595825,
|
| 192 |
+
"learning_rate": 0.00018442620345981232,
|
| 193 |
+
"loss": 0.1442,
|
| 194 |
+
"step": 120
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.23266635644485809,
|
| 198 |
+
"grad_norm": 0.7527527213096619,
|
| 199 |
+
"learning_rate": 0.00018273914561262424,
|
| 200 |
+
"loss": 0.1555,
|
| 201 |
+
"step": 125
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.2419730107026524,
|
| 205 |
+
"grad_norm": 0.6647666692733765,
|
| 206 |
+
"learning_rate": 0.00018097391152384115,
|
| 207 |
+
"loss": 0.1383,
|
| 208 |
+
"step": 130
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.25127966496044674,
|
| 212 |
+
"grad_norm": 0.8701847195625305,
|
| 213 |
+
"learning_rate": 0.0001791321690783025,
|
| 214 |
+
"loss": 0.1671,
|
| 215 |
+
"step": 135
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.26058631921824105,
|
| 219 |
+
"grad_norm": 0.6835318803787231,
|
| 220 |
+
"learning_rate": 0.00017721565844991643,
|
| 221 |
+
"loss": 0.1458,
|
| 222 |
+
"step": 140
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.26989297347603536,
|
| 226 |
+
"grad_norm": 0.8638496994972229,
|
| 227 |
+
"learning_rate": 0.00017522619045745315,
|
| 228 |
+
"loss": 0.163,
|
| 229 |
+
"step": 145
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.27919962773382967,
|
| 233 |
+
"grad_norm": 1.0149871110916138,
|
| 234 |
+
"learning_rate": 0.00017316564485358923,
|
| 235 |
+
"loss": 0.1518,
|
| 236 |
+
"step": 150
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.27919962773382967,
|
| 240 |
+
"eval_loss": 0.12961792945861816,
|
| 241 |
+
"eval_runtime": 72.8727,
|
| 242 |
+
"eval_samples_per_second": 3.033,
|
| 243 |
+
"eval_steps_per_second": 1.523,
|
| 244 |
+
"step": 150
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.28850628199162404,
|
| 248 |
+
"grad_norm": 0.8869348168373108,
|
| 249 |
+
"learning_rate": 0.00017103596854881972,
|
| 250 |
+
"loss": 0.161,
|
| 251 |
+
"step": 155
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.29781293624941835,
|
| 255 |
+
"grad_norm": 0.6964899897575378,
|
| 256 |
+
"learning_rate": 0.00016883917377191602,
|
| 257 |
+
"loss": 0.1496,
|
| 258 |
+
"step": 160
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.30711959050721266,
|
| 262 |
+
"grad_norm": 0.7895644307136536,
|
| 263 |
+
"learning_rate": 0.00016657733616866756,
|
| 264 |
+
"loss": 0.178,
|
| 265 |
+
"step": 165
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.31642624476500697,
|
| 269 |
+
"grad_norm": 0.8652212023735046,
|
| 270 |
+
"learning_rate": 0.00016425259284070398,
|
| 271 |
+
"loss": 0.1572,
|
| 272 |
+
"step": 170
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.3257328990228013,
|
| 276 |
+
"grad_norm": 0.8598363995552063,
|
| 277 |
+
"learning_rate": 0.00016186714032625035,
|
| 278 |
+
"loss": 0.1329,
|
| 279 |
+
"step": 175
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.33503955328059565,
|
| 283 |
+
"grad_norm": 0.9525418877601624,
|
| 284 |
+
"learning_rate": 0.000159423232524724,
|
| 285 |
+
"loss": 0.1509,
|
| 286 |
+
"step": 180
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.34434620753838996,
|
| 290 |
+
"grad_norm": 0.8453659415245056,
|
| 291 |
+
"learning_rate": 0.0001569231785671332,
|
| 292 |
+
"loss": 0.1619,
|
| 293 |
+
"step": 185
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.35365286179618427,
|
| 297 |
+
"grad_norm": 0.9399647116661072,
|
| 298 |
+
"learning_rate": 0.00015436934063429013,
|
| 299 |
+
"loss": 0.1637,
|
| 300 |
+
"step": 190
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.3629595160539786,
|
| 304 |
+
"grad_norm": 0.8372876048088074,
|
| 305 |
+
"learning_rate": 0.00015176413172490004,
|
| 306 |
+
"loss": 0.1622,
|
| 307 |
+
"step": 195
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.3722661703117729,
|
| 311 |
+
"grad_norm": 0.711920976638794,
|
| 312 |
+
"learning_rate": 0.00014911001337563452,
|
| 313 |
+
"loss": 0.1504,
|
| 314 |
+
"step": 200
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3722661703117729,
|
| 318 |
+
"eval_loss": 0.12358199059963226,
|
| 319 |
+
"eval_runtime": 73.0008,
|
| 320 |
+
"eval_samples_per_second": 3.027,
|
| 321 |
+
"eval_steps_per_second": 1.521,
|
| 322 |
+
"step": 200
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.38157282456956726,
|
| 326 |
+
"grad_norm": 0.8126468658447266,
|
| 327 |
+
"learning_rate": 0.00014640949333534403,
|
| 328 |
+
"loss": 0.1526,
|
| 329 |
+
"step": 205
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.39087947882736157,
|
| 333 |
+
"grad_norm": 0.635465681552887,
|
| 334 |
+
"learning_rate": 0.0001436651231956064,
|
| 335 |
+
"loss": 0.1358,
|
| 336 |
+
"step": 210
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.4001861330851559,
|
| 340 |
+
"grad_norm": 0.5986313819885254,
|
| 341 |
+
"learning_rate": 0.00014087949597985065,
|
| 342 |
+
"loss": 0.15,
|
| 343 |
+
"step": 215
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.4094927873429502,
|
| 347 |
+
"grad_norm": 0.7797956466674805,
|
| 348 |
+
"learning_rate": 0.00013805524369333373,
|
| 349 |
+
"loss": 0.1442,
|
| 350 |
+
"step": 220
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.41879944160074456,
|
| 354 |
+
"grad_norm": 0.6968953609466553,
|
| 355 |
+
"learning_rate": 0.00013519503483628542,
|
| 356 |
+
"loss": 0.1437,
|
| 357 |
+
"step": 225
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.42810609585853887,
|
| 361 |
+
"grad_norm": 0.6117879152297974,
|
| 362 |
+
"learning_rate": 0.00013230157188257063,
|
| 363 |
+
"loss": 0.1214,
|
| 364 |
+
"step": 230
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.4374127501163332,
|
| 368 |
+
"grad_norm": 0.6684589982032776,
|
| 369 |
+
"learning_rate": 0.0001293775887262517,
|
| 370 |
+
"loss": 0.1383,
|
| 371 |
+
"step": 235
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.4467194043741275,
|
| 375 |
+
"grad_norm": 0.7364048957824707,
|
| 376 |
+
"learning_rate": 0.00012642584809846333,
|
| 377 |
+
"loss": 0.1222,
|
| 378 |
+
"step": 240
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.4560260586319218,
|
| 382 |
+
"grad_norm": 0.7387944459915161,
|
| 383 |
+
"learning_rate": 0.00012344913895704097,
|
| 384 |
+
"loss": 0.1202,
|
| 385 |
+
"step": 245
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.46533271288971617,
|
| 389 |
+
"grad_norm": 0.6471113562583923,
|
| 390 |
+
"learning_rate": 0.00012045027385136825,
|
| 391 |
+
"loss": 0.1446,
|
| 392 |
+
"step": 250
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.46533271288971617,
|
| 396 |
+
"eval_loss": 0.11554089933633804,
|
| 397 |
+
"eval_runtime": 73.039,
|
| 398 |
+
"eval_samples_per_second": 3.026,
|
| 399 |
+
"eval_steps_per_second": 1.52,
|
| 400 |
+
"step": 250
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.4746393671475105,
|
| 404 |
+
"grad_norm": 0.7449938058853149,
|
| 405 |
+
"learning_rate": 0.0001174320862649344,
|
| 406 |
+
"loss": 0.1425,
|
| 407 |
+
"step": 255
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.4839460214053048,
|
| 411 |
+
"grad_norm": 0.8666985630989075,
|
| 412 |
+
"learning_rate": 0.00011439742793811205,
|
| 413 |
+
"loss": 0.131,
|
| 414 |
+
"step": 260
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.4932526756630991,
|
| 418 |
+
"grad_norm": 0.9995303750038147,
|
| 419 |
+
"learning_rate": 0.00011134916617368464,
|
| 420 |
+
"loss": 0.1322,
|
| 421 |
+
"step": 265
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.5025593299208935,
|
| 425 |
+
"grad_norm": 0.6491286754608154,
|
| 426 |
+
"learning_rate": 0.00010829018112766996,
|
| 427 |
+
"loss": 0.1293,
|
| 428 |
+
"step": 270
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.5118659841786878,
|
| 432 |
+
"grad_norm": 0.8522428274154663,
|
| 433 |
+
"learning_rate": 0.00010522336308799904,
|
| 434 |
+
"loss": 0.1372,
|
| 435 |
+
"step": 275
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.5211726384364821,
|
| 439 |
+
"grad_norm": 0.7563990354537964,
|
| 440 |
+
"learning_rate": 0.00010215160974362223,
|
| 441 |
+
"loss": 0.1277,
|
| 442 |
+
"step": 280
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.5304792926942764,
|
| 446 |
+
"grad_norm": 0.6848676800727844,
|
| 447 |
+
"learning_rate": 9.907782344662195e-05,
|
| 448 |
+
"loss": 0.1294,
|
| 449 |
+
"step": 285
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.5397859469520707,
|
| 453 |
+
"grad_norm": 0.6876094341278076,
|
| 454 |
+
"learning_rate": 9.600490846991994e-05,
|
| 455 |
+
"loss": 0.1383,
|
| 456 |
+
"step": 290
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.549092601209865,
|
| 460 |
+
"grad_norm": 0.6399123668670654,
|
| 461 |
+
"learning_rate": 9.29357682631691e-05,
|
| 462 |
+
"loss": 0.1241,
|
| 463 |
+
"step": 295
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.5583992554676593,
|
| 467 |
+
"grad_norm": 0.6791756749153137,
|
| 468 |
+
"learning_rate": 8.987330270942389e-05,
|
| 469 |
+
"loss": 0.14,
|
| 470 |
+
"step": 300
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.5583992554676593,
|
| 474 |
+
"eval_loss": 0.1100185289978981,
|
| 475 |
+
"eval_runtime": 72.8167,
|
| 476 |
+
"eval_samples_per_second": 3.035,
|
| 477 |
+
"eval_steps_per_second": 1.524,
|
| 478 |
+
"step": 300
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.5677059097254537,
|
| 482 |
+
"grad_norm": 0.8283066749572754,
|
| 483 |
+
"learning_rate": 8.682040538517974e-05,
|
| 484 |
+
"loss": 0.1346,
|
| 485 |
+
"step": 305
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.5770125639832481,
|
| 489 |
+
"grad_norm": 0.7044147253036499,
|
| 490 |
+
"learning_rate": 8.377996082637216e-05,
|
| 491 |
+
"loss": 0.1386,
|
| 492 |
+
"step": 310
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.5863192182410424,
|
| 496 |
+
"grad_norm": 0.696846067905426,
|
| 497 |
+
"learning_rate": 8.075484180291701e-05,
|
| 498 |
+
"loss": 0.1173,
|
| 499 |
+
"step": 315
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.5956258724988367,
|
| 503 |
+
"grad_norm": 0.7000551819801331,
|
| 504 |
+
"learning_rate": 7.774790660436858e-05,
|
| 505 |
+
"loss": 0.1319,
|
| 506 |
+
"step": 320
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.604932526756631,
|
| 510 |
+
"grad_norm": 0.8282796144485474,
|
| 511 |
+
"learning_rate": 7.476199633925895e-05,
|
| 512 |
+
"loss": 0.1373,
|
| 513 |
+
"step": 325
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6142391810144253,
|
| 517 |
+
"grad_norm": 0.6185778379440308,
|
| 518 |
+
"learning_rate": 7.179993225067136e-05,
|
| 519 |
+
"loss": 0.1376,
|
| 520 |
+
"step": 330
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.6235458352722196,
|
| 524 |
+
"grad_norm": 0.6192060112953186,
|
| 525 |
+
"learning_rate": 6.886451305058293e-05,
|
| 526 |
+
"loss": 0.1296,
|
| 527 |
+
"step": 335
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.6328524895300139,
|
| 531 |
+
"grad_norm": 0.5297410488128662,
|
| 532 |
+
"learning_rate": 6.595851227549657e-05,
|
| 533 |
+
"loss": 0.1114,
|
| 534 |
+
"step": 340
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.6421591437878083,
|
| 538 |
+
"grad_norm": 0.6853290796279907,
|
| 539 |
+
"learning_rate": 6.308467566585929e-05,
|
| 540 |
+
"loss": 0.1258,
|
| 541 |
+
"step": 345
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.6514657980456026,
|
| 545 |
+
"grad_norm": 0.5415284633636475,
|
| 546 |
+
"learning_rate": 6.024571857174443e-05,
|
| 547 |
+
"loss": 0.1151,
|
| 548 |
+
"step": 350
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.6514657980456026,
|
| 552 |
+
"eval_loss": 0.10505883395671844,
|
| 553 |
+
"eval_runtime": 72.7668,
|
| 554 |
+
"eval_samples_per_second": 3.037,
|
| 555 |
+
"eval_steps_per_second": 1.525,
|
| 556 |
+
"step": 350
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6607724523033969,
|
| 560 |
+
"grad_norm": 0.6376184225082397,
|
| 561 |
+
"learning_rate": 5.7444323387247544e-05,
|
| 562 |
+
"loss": 0.1196,
|
| 563 |
+
"step": 355
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6700791065611913,
|
| 567 |
+
"grad_norm": 0.9076871871948242,
|
| 568 |
+
"learning_rate": 5.468313701602141e-05,
|
| 569 |
+
"loss": 0.1199,
|
| 570 |
+
"step": 360
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.6793857608189856,
|
| 574 |
+
"grad_norm": 0.8146594166755676,
|
| 575 |
+
"learning_rate": 5.196476837034381e-05,
|
| 576 |
+
"loss": 0.1278,
|
| 577 |
+
"step": 365
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6886924150767799,
|
| 581 |
+
"grad_norm": 0.7426274418830872,
|
| 582 |
+
"learning_rate": 4.9291785906081925e-05,
|
| 583 |
+
"loss": 0.1356,
|
| 584 |
+
"step": 370
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.6979990693345742,
|
| 588 |
+
"grad_norm": 0.8531163334846497,
|
| 589 |
+
"learning_rate": 4.6666715195881586e-05,
|
| 590 |
+
"loss": 0.1322,
|
| 591 |
+
"step": 375
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.7073057235923685,
|
| 595 |
+
"grad_norm": 0.6669689416885376,
|
| 596 |
+
"learning_rate": 4.409203654287538e-05,
|
| 597 |
+
"loss": 0.1228,
|
| 598 |
+
"step": 380
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.7166123778501629,
|
| 602 |
+
"grad_norm": 0.7575223445892334,
|
| 603 |
+
"learning_rate": 4.1570182637163155e-05,
|
| 604 |
+
"loss": 0.1384,
|
| 605 |
+
"step": 385
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.7259190321079572,
|
| 609 |
+
"grad_norm": 0.677855908870697,
|
| 610 |
+
"learning_rate": 3.910353625728035e-05,
|
| 611 |
+
"loss": 0.1195,
|
| 612 |
+
"step": 390
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.7352256863657515,
|
| 616 |
+
"grad_norm": 0.6284500360488892,
|
| 617 |
+
"learning_rate": 3.66944280188248e-05,
|
| 618 |
+
"loss": 0.119,
|
| 619 |
+
"step": 395
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.7445323406235458,
|
| 623 |
+
"grad_norm": 0.5671315789222717,
|
| 624 |
+
"learning_rate": 3.434513417237041e-05,
|
| 625 |
+
"loss": 0.1159,
|
| 626 |
+
"step": 400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.7445323406235458,
|
| 630 |
+
"eval_loss": 0.10208839178085327,
|
| 631 |
+
"eval_runtime": 72.8321,
|
| 632 |
+
"eval_samples_per_second": 3.034,
|
| 633 |
+
"eval_steps_per_second": 1.524,
|
| 634 |
+
"step": 400
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.7538389948813402,
|
| 638 |
+
"grad_norm": 0.6890803575515747,
|
| 639 |
+
"learning_rate": 3.205787445274707e-05,
|
| 640 |
+
"loss": 0.1254,
|
| 641 |
+
"step": 405
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.7631456491391345,
|
| 645 |
+
"grad_norm": 0.6065118312835693,
|
| 646 |
+
"learning_rate": 2.9834809981720224e-05,
|
| 647 |
+
"loss": 0.1076,
|
| 648 |
+
"step": 410
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.7724523033969288,
|
| 652 |
+
"grad_norm": 0.734563946723938,
|
| 653 |
+
"learning_rate": 2.7678041226050533e-05,
|
| 654 |
+
"loss": 0.1283,
|
| 655 |
+
"step": 415
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.7817589576547231,
|
| 659 |
+
"grad_norm": 0.6849725842475891,
|
| 660 |
+
"learning_rate": 2.5589606012863963e-05,
|
| 661 |
+
"loss": 0.1235,
|
| 662 |
+
"step": 420
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.7910656119125175,
|
| 666 |
+
"grad_norm": 0.7363895773887634,
|
| 667 |
+
"learning_rate": 2.3571477604206792e-05,
|
| 668 |
+
"loss": 0.1329,
|
| 669 |
+
"step": 425
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.8003722661703118,
|
| 673 |
+
"grad_norm": 0.6717341542243958,
|
| 674 |
+
"learning_rate": 2.1625562832605284e-05,
|
| 675 |
+
"loss": 0.1339,
|
| 676 |
+
"step": 430
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.8096789204281061,
|
| 680 |
+
"grad_norm": 0.6806132197380066,
|
| 681 |
+
"learning_rate": 1.975370029939111e-05,
|
| 682 |
+
"loss": 0.1198,
|
| 683 |
+
"step": 435
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.8189855746859004,
|
| 687 |
+
"grad_norm": 0.7354431748390198,
|
| 688 |
+
"learning_rate": 1.795765863749549e-05,
|
| 689 |
+
"loss": 0.1436,
|
| 690 |
+
"step": 440
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.8282922289436947,
|
| 694 |
+
"grad_norm": 0.5758335590362549,
|
| 695 |
+
"learning_rate": 1.623913484035282e-05,
|
| 696 |
+
"loss": 0.108,
|
| 697 |
+
"step": 445
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.8375988832014891,
|
| 701 |
+
"grad_norm": 0.5895151495933533,
|
| 702 |
+
"learning_rate": 1.4599752658493304e-05,
|
| 703 |
+
"loss": 0.1384,
|
| 704 |
+
"step": 450
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.8375988832014891,
|
| 708 |
+
"eval_loss": 0.10044225305318832,
|
| 709 |
+
"eval_runtime": 72.8277,
|
| 710 |
+
"eval_samples_per_second": 3.035,
|
| 711 |
+
"eval_steps_per_second": 1.524,
|
| 712 |
+
"step": 450
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.8469055374592834,
|
| 716 |
+
"grad_norm": 0.5299936532974243,
|
| 717 |
+
"learning_rate": 1.30410610653389e-05,
|
| 718 |
+
"loss": 0.1082,
|
| 719 |
+
"step": 455
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.8562121917170777,
|
| 723 |
+
"grad_norm": 0.6784066557884216,
|
| 724 |
+
"learning_rate": 1.1564532793653072e-05,
|
| 725 |
+
"loss": 0.1279,
|
| 726 |
+
"step": 460
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.865518845974872,
|
| 730 |
+
"grad_norm": 0.7089002728462219,
|
| 731 |
+
"learning_rate": 1.0171562944026103e-05,
|
| 732 |
+
"loss": 0.121,
|
| 733 |
+
"step": 465
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.8748255002326664,
|
| 737 |
+
"grad_norm": 0.7150669097900391,
|
| 738 |
+
"learning_rate": 8.863467666711866e-06,
|
| 739 |
+
"loss": 0.1,
|
| 740 |
+
"step": 470
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.8841321544904607,
|
| 744 |
+
"grad_norm": 0.7433251142501831,
|
| 745 |
+
"learning_rate": 7.641482918060506e-06,
|
| 746 |
+
"loss": 0.1111,
|
| 747 |
+
"step": 475
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.893438808748255,
|
| 751 |
+
"grad_norm": 0.6310339570045471,
|
| 752 |
+
"learning_rate": 6.506763292722851e-06,
|
| 753 |
+
"loss": 0.0885,
|
| 754 |
+
"step": 480
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.9027454630060493,
|
| 758 |
+
"grad_norm": 0.5972334742546082,
|
| 759 |
+
"learning_rate": 5.460380932729303e-06,
|
| 760 |
+
"loss": 0.1061,
|
| 761 |
+
"step": 485
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.9120521172638436,
|
| 765 |
+
"grad_norm": 0.6366889476776123,
|
| 766 |
+
"learning_rate": 4.503324514474483e-06,
|
| 767 |
+
"loss": 0.1347,
|
| 768 |
+
"step": 490
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.9213587715216379,
|
| 772 |
+
"grad_norm": 0.7572676539421082,
|
| 773 |
+
"learning_rate": 3.636498314564307e-06,
|
| 774 |
+
"loss": 0.1174,
|
| 775 |
+
"step": 495
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.9306654257794323,
|
| 779 |
+
"grad_norm": 0.6025388836860657,
|
| 780 |
+
"learning_rate": 2.860721355408602e-06,
|
| 781 |
+
"loss": 0.1112,
|
| 782 |
+
"step": 500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.9306654257794323,
|
| 786 |
+
"eval_loss": 0.09908278286457062,
|
| 787 |
+
"eval_runtime": 72.8525,
|
| 788 |
+
"eval_samples_per_second": 3.034,
|
| 789 |
+
"eval_steps_per_second": 1.524,
|
| 790 |
+
"step": 500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.9399720800372267,
|
| 794 |
+
"grad_norm": 0.6565231680870056,
|
| 795 |
+
"learning_rate": 2.1767266313661105e-06,
|
| 796 |
+
"loss": 0.1077,
|
| 797 |
+
"step": 505
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.949278734295021,
|
| 801 |
+
"grad_norm": 0.5436176657676697,
|
| 802 |
+
"learning_rate": 1.5851604161734256e-06,
|
| 803 |
+
"loss": 0.1193,
|
| 804 |
+
"step": 510
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.9585853885528153,
|
| 808 |
+
"grad_norm": 0.8013174533843994,
|
| 809 |
+
"learning_rate": 1.0865816523119466e-06,
|
| 810 |
+
"loss": 0.1193,
|
| 811 |
+
"step": 515
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.9678920428106096,
|
| 815 |
+
"grad_norm": 0.6958430409431458,
|
| 816 |
+
"learning_rate": 6.814614228900507e-07,
|
| 817 |
+
"loss": 0.1152,
|
| 818 |
+
"step": 520
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.9771986970684039,
|
| 822 |
+
"grad_norm": 0.5581568479537964,
|
| 823 |
+
"learning_rate": 3.701825065392184e-07,
|
| 824 |
+
"loss": 0.1249,
|
| 825 |
+
"step": 525
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.9865053513261982,
|
| 829 |
+
"grad_norm": 0.7202214002609253,
|
| 830 |
+
"learning_rate": 1.5303901574502678e-07,
|
| 831 |
+
"loss": 0.1164,
|
| 832 |
+
"step": 530
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.9958120055839925,
|
| 836 |
+
"grad_norm": 0.5646489262580872,
|
| 837 |
+
"learning_rate": 3.023611895428546e-08,
|
| 838 |
+
"loss": 0.1061,
|
| 839 |
+
"step": 535
|
| 840 |
+
}
|
| 841 |
+
],
|
| 842 |
+
"logging_steps": 5,
|
| 843 |
+
"max_steps": 538,
|
| 844 |
+
"num_input_tokens_seen": 0,
|
| 845 |
+
"num_train_epochs": 1,
|
| 846 |
+
"save_steps": 100,
|
| 847 |
+
"stateful_callbacks": {
|
| 848 |
+
"EarlyStoppingCallback": {
|
| 849 |
+
"args": {
|
| 850 |
+
"early_stopping_patience": 2,
|
| 851 |
+
"early_stopping_threshold": 0.001
|
| 852 |
+
},
|
| 853 |
+
"attributes": {
|
| 854 |
+
"early_stopping_patience_counter": 0
|
| 855 |
+
}
|
| 856 |
+
},
|
| 857 |
+
"TrainerControl": {
|
| 858 |
+
"args": {
|
| 859 |
+
"should_epoch_stop": false,
|
| 860 |
+
"should_evaluate": false,
|
| 861 |
+
"should_log": false,
|
| 862 |
+
"should_save": true,
|
| 863 |
+
"should_training_stop": true
|
| 864 |
+
},
|
| 865 |
+
"attributes": {}
|
| 866 |
+
}
|
| 867 |
+
},
|
| 868 |
+
"total_flos": 2.3722943184871096e+18,
|
| 869 |
+
"train_batch_size": 2,
|
| 870 |
+
"trial_name": null,
|
| 871 |
+
"trial_params": null
|
| 872 |
+
}
|