Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
sft
unsloth
conversational
custom_code
text-generation-inference
Instructions to use Ba2han/sft-test3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/sft-test3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/sft-test3", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/sft-test3", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Ba2han/sft-test3", trust_remote_code=True) 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 Settings
- vLLM
How to use Ba2han/sft-test3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/sft-test3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/sft-test3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ba2han/sft-test3
- SGLang
How to use Ba2han/sft-test3 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 "Ba2han/sft-test3" \ --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": "Ba2han/sft-test3", "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 "Ba2han/sft-test3" \ --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": "Ba2han/sft-test3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use Ba2han/sft-test3 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/sft-test3 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/sft-test3 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ba2han/sft-test3 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Ba2han/sft-test3", max_seq_length=2048, ) - Docker Model Runner
How to use Ba2han/sft-test3 with Docker Model Runner:
docker model run hf.co/Ba2han/sft-test3
Training in progress, step 5895, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1049614696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b5aec2d039ada1e3b5e0307f55498c0f7a92d19e6490a8ec63cf1058243a33d
|
| 3 |
size 1049614696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 962892367
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f003a8b69e0f6a87e7521471301038b5c036cb028b9d798553f3b6fea5e4039e
|
| 3 |
size 962892367
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a92cb2f40ffa8ca35e7530438abb7f80de1c47603e0dcb24cc215af067453174
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -18348,6 +18348,2295 @@
|
|
| 18348 |
"learning_rate": 9.897360801703276e-06,
|
| 18349 |
"loss": 1.9135477542877197,
|
| 18350 |
"step": 5240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18351 |
}
|
| 18352 |
],
|
| 18353 |
"logging_steps": 2,
|
|
@@ -18367,7 +20656,7 @@
|
|
| 18367 |
"attributes": {}
|
| 18368 |
}
|
| 18369 |
},
|
| 18370 |
-
"total_flos": 2.
|
| 18371 |
"train_batch_size": 4,
|
| 18372 |
"trial_name": null,
|
| 18373 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9006703462500716,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5895,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 18348 |
"learning_rate": 9.897360801703276e-06,
|
| 18349 |
"loss": 1.9135477542877197,
|
| 18350 |
"step": 5240
|
| 18351 |
+
},
|
| 18352 |
+
{
|
| 18353 |
+
"epoch": 0.8009014342736006,
|
| 18354 |
+
"grad_norm": 0.1494140625,
|
| 18355 |
+
"learning_rate": 9.868130998872155e-06,
|
| 18356 |
+
"loss": 1.9447505474090576,
|
| 18357 |
+
"step": 5242
|
| 18358 |
+
},
|
| 18359 |
+
{
|
| 18360 |
+
"epoch": 0.8012070052138042,
|
| 18361 |
+
"grad_norm": 0.1611328125,
|
| 18362 |
+
"learning_rate": 9.838939695601068e-06,
|
| 18363 |
+
"loss": 1.9290874004364014,
|
| 18364 |
+
"step": 5244
|
| 18365 |
+
},
|
| 18366 |
+
{
|
| 18367 |
+
"epoch": 0.8015125761540077,
|
| 18368 |
+
"grad_norm": 0.1533203125,
|
| 18369 |
+
"learning_rate": 9.809786919893987e-06,
|
| 18370 |
+
"loss": 1.9263818264007568,
|
| 18371 |
+
"step": 5246
|
| 18372 |
+
},
|
| 18373 |
+
{
|
| 18374 |
+
"epoch": 0.8018181470942113,
|
| 18375 |
+
"grad_norm": 0.162109375,
|
| 18376 |
+
"learning_rate": 9.780672699717974e-06,
|
| 18377 |
+
"loss": 1.8890498876571655,
|
| 18378 |
+
"step": 5248
|
| 18379 |
+
},
|
| 18380 |
+
{
|
| 18381 |
+
"epoch": 0.802123718034415,
|
| 18382 |
+
"grad_norm": 0.15234375,
|
| 18383 |
+
"learning_rate": 9.75159706300306e-06,
|
| 18384 |
+
"loss": 1.9466395378112793,
|
| 18385 |
+
"step": 5250
|
| 18386 |
+
},
|
| 18387 |
+
{
|
| 18388 |
+
"epoch": 0.8024292889746185,
|
| 18389 |
+
"grad_norm": 0.1591796875,
|
| 18390 |
+
"learning_rate": 9.722560037642247e-06,
|
| 18391 |
+
"loss": 1.9744682312011719,
|
| 18392 |
+
"step": 5252
|
| 18393 |
+
},
|
| 18394 |
+
{
|
| 18395 |
+
"epoch": 0.8027348599148221,
|
| 18396 |
+
"grad_norm": 0.16015625,
|
| 18397 |
+
"learning_rate": 9.693561651491534e-06,
|
| 18398 |
+
"loss": 1.9145617485046387,
|
| 18399 |
+
"step": 5254
|
| 18400 |
+
},
|
| 18401 |
+
{
|
| 18402 |
+
"epoch": 0.8030404308550256,
|
| 18403 |
+
"grad_norm": 0.1552734375,
|
| 18404 |
+
"learning_rate": 9.664601932369833e-06,
|
| 18405 |
+
"loss": 1.9378736019134521,
|
| 18406 |
+
"step": 5256
|
| 18407 |
+
},
|
| 18408 |
+
{
|
| 18409 |
+
"epoch": 0.8033460017952293,
|
| 18410 |
+
"grad_norm": 0.1484375,
|
| 18411 |
+
"learning_rate": 9.63568090805897e-06,
|
| 18412 |
+
"loss": 1.9207696914672852,
|
| 18413 |
+
"step": 5258
|
| 18414 |
+
},
|
| 18415 |
+
{
|
| 18416 |
+
"epoch": 0.8036515727354329,
|
| 18417 |
+
"grad_norm": 0.1611328125,
|
| 18418 |
+
"learning_rate": 9.606798606303641e-06,
|
| 18419 |
+
"loss": 1.9298185110092163,
|
| 18420 |
+
"step": 5260
|
| 18421 |
+
},
|
| 18422 |
+
{
|
| 18423 |
+
"epoch": 0.8039571436756364,
|
| 18424 |
+
"grad_norm": 0.166015625,
|
| 18425 |
+
"learning_rate": 9.5779550548114e-06,
|
| 18426 |
+
"loss": 1.9330649375915527,
|
| 18427 |
+
"step": 5262
|
| 18428 |
+
},
|
| 18429 |
+
{
|
| 18430 |
+
"epoch": 0.80426271461584,
|
| 18431 |
+
"grad_norm": 0.1689453125,
|
| 18432 |
+
"learning_rate": 9.549150281252633e-06,
|
| 18433 |
+
"loss": 1.9487688541412354,
|
| 18434 |
+
"step": 5264
|
| 18435 |
+
},
|
| 18436 |
+
{
|
| 18437 |
+
"epoch": 0.8045682855560436,
|
| 18438 |
+
"grad_norm": 0.15625,
|
| 18439 |
+
"learning_rate": 9.520384313260511e-06,
|
| 18440 |
+
"loss": 1.8908498287200928,
|
| 18441 |
+
"step": 5266
|
| 18442 |
+
},
|
| 18443 |
+
{
|
| 18444 |
+
"epoch": 0.8048738564962472,
|
| 18445 |
+
"grad_norm": 0.15625,
|
| 18446 |
+
"learning_rate": 9.491657178430995e-06,
|
| 18447 |
+
"loss": 1.9486370086669922,
|
| 18448 |
+
"step": 5268
|
| 18449 |
+
},
|
| 18450 |
+
{
|
| 18451 |
+
"epoch": 0.8051794274364508,
|
| 18452 |
+
"grad_norm": 0.1513671875,
|
| 18453 |
+
"learning_rate": 9.462968904322773e-06,
|
| 18454 |
+
"loss": 1.9872796535491943,
|
| 18455 |
+
"step": 5270
|
| 18456 |
+
},
|
| 18457 |
+
{
|
| 18458 |
+
"epoch": 0.8054849983766543,
|
| 18459 |
+
"grad_norm": 0.16015625,
|
| 18460 |
+
"learning_rate": 9.434319518457269e-06,
|
| 18461 |
+
"loss": 1.9366258382797241,
|
| 18462 |
+
"step": 5272
|
| 18463 |
+
},
|
| 18464 |
+
{
|
| 18465 |
+
"epoch": 0.805790569316858,
|
| 18466 |
+
"grad_norm": 0.150390625,
|
| 18467 |
+
"learning_rate": 9.40570904831859e-06,
|
| 18468 |
+
"loss": 1.946537971496582,
|
| 18469 |
+
"step": 5274
|
| 18470 |
+
},
|
| 18471 |
+
{
|
| 18472 |
+
"epoch": 0.8060961402570616,
|
| 18473 |
+
"grad_norm": 0.1474609375,
|
| 18474 |
+
"learning_rate": 9.377137521353519e-06,
|
| 18475 |
+
"loss": 1.957240104675293,
|
| 18476 |
+
"step": 5276
|
| 18477 |
+
},
|
| 18478 |
+
{
|
| 18479 |
+
"epoch": 0.8064017111972651,
|
| 18480 |
+
"grad_norm": 0.150390625,
|
| 18481 |
+
"learning_rate": 9.348604964971485e-06,
|
| 18482 |
+
"loss": 1.9818679094314575,
|
| 18483 |
+
"step": 5278
|
| 18484 |
+
},
|
| 18485 |
+
{
|
| 18486 |
+
"epoch": 0.8067072821374687,
|
| 18487 |
+
"grad_norm": 0.162109375,
|
| 18488 |
+
"learning_rate": 9.320111406544479e-06,
|
| 18489 |
+
"loss": 1.9543893337249756,
|
| 18490 |
+
"step": 5280
|
| 18491 |
+
},
|
| 18492 |
+
{
|
| 18493 |
+
"epoch": 0.8070128530776723,
|
| 18494 |
+
"grad_norm": 0.166015625,
|
| 18495 |
+
"learning_rate": 9.291656873407172e-06,
|
| 18496 |
+
"loss": 1.9423015117645264,
|
| 18497 |
+
"step": 5282
|
| 18498 |
+
},
|
| 18499 |
+
{
|
| 18500 |
+
"epoch": 0.8073184240178759,
|
| 18501 |
+
"grad_norm": 0.14453125,
|
| 18502 |
+
"learning_rate": 9.263241392856725e-06,
|
| 18503 |
+
"loss": 1.9486720561981201,
|
| 18504 |
+
"step": 5284
|
| 18505 |
+
},
|
| 18506 |
+
{
|
| 18507 |
+
"epoch": 0.8076239949580795,
|
| 18508 |
+
"grad_norm": 0.1630859375,
|
| 18509 |
+
"learning_rate": 9.234864992152864e-06,
|
| 18510 |
+
"loss": 1.9313347339630127,
|
| 18511 |
+
"step": 5286
|
| 18512 |
+
},
|
| 18513 |
+
{
|
| 18514 |
+
"epoch": 0.807929565898283,
|
| 18515 |
+
"grad_norm": 0.154296875,
|
| 18516 |
+
"learning_rate": 9.206527698517813e-06,
|
| 18517 |
+
"loss": 1.9515111446380615,
|
| 18518 |
+
"step": 5288
|
| 18519 |
+
},
|
| 18520 |
+
{
|
| 18521 |
+
"epoch": 0.8082351368384867,
|
| 18522 |
+
"grad_norm": 0.150390625,
|
| 18523 |
+
"learning_rate": 9.178229539136302e-06,
|
| 18524 |
+
"loss": 1.9429893493652344,
|
| 18525 |
+
"step": 5290
|
| 18526 |
+
},
|
| 18527 |
+
{
|
| 18528 |
+
"epoch": 0.8085407077786902,
|
| 18529 |
+
"grad_norm": 0.15234375,
|
| 18530 |
+
"learning_rate": 9.149970541155477e-06,
|
| 18531 |
+
"loss": 1.9920744895935059,
|
| 18532 |
+
"step": 5292
|
| 18533 |
+
},
|
| 18534 |
+
{
|
| 18535 |
+
"epoch": 0.8088462787188938,
|
| 18536 |
+
"grad_norm": 0.16015625,
|
| 18537 |
+
"learning_rate": 9.121750731684947e-06,
|
| 18538 |
+
"loss": 1.9074058532714844,
|
| 18539 |
+
"step": 5294
|
| 18540 |
+
},
|
| 18541 |
+
{
|
| 18542 |
+
"epoch": 0.8091518496590974,
|
| 18543 |
+
"grad_norm": 0.1494140625,
|
| 18544 |
+
"learning_rate": 9.093570137796714e-06,
|
| 18545 |
+
"loss": 1.8882205486297607,
|
| 18546 |
+
"step": 5296
|
| 18547 |
+
},
|
| 18548 |
+
{
|
| 18549 |
+
"epoch": 0.809457420599301,
|
| 18550 |
+
"grad_norm": 0.1689453125,
|
| 18551 |
+
"learning_rate": 9.065428786525182e-06,
|
| 18552 |
+
"loss": 1.9532999992370605,
|
| 18553 |
+
"step": 5298
|
| 18554 |
+
},
|
| 18555 |
+
{
|
| 18556 |
+
"epoch": 0.8097629915395046,
|
| 18557 |
+
"grad_norm": 0.150390625,
|
| 18558 |
+
"learning_rate": 9.037326704867093e-06,
|
| 18559 |
+
"loss": 1.9208903312683105,
|
| 18560 |
+
"step": 5300
|
| 18561 |
+
},
|
| 18562 |
+
{
|
| 18563 |
+
"epoch": 0.8100685624797082,
|
| 18564 |
+
"grad_norm": 0.154296875,
|
| 18565 |
+
"learning_rate": 9.009263919781496e-06,
|
| 18566 |
+
"loss": 1.9288264513015747,
|
| 18567 |
+
"step": 5302
|
| 18568 |
+
},
|
| 18569 |
+
{
|
| 18570 |
+
"epoch": 0.8103741334199117,
|
| 18571 |
+
"grad_norm": 0.1533203125,
|
| 18572 |
+
"learning_rate": 8.981240458189766e-06,
|
| 18573 |
+
"loss": 1.9888395071029663,
|
| 18574 |
+
"step": 5304
|
| 18575 |
+
},
|
| 18576 |
+
{
|
| 18577 |
+
"epoch": 0.8106797043601154,
|
| 18578 |
+
"grad_norm": 0.1669921875,
|
| 18579 |
+
"learning_rate": 8.953256346975553e-06,
|
| 18580 |
+
"loss": 1.958566427230835,
|
| 18581 |
+
"step": 5306
|
| 18582 |
+
},
|
| 18583 |
+
{
|
| 18584 |
+
"epoch": 0.8109852753003189,
|
| 18585 |
+
"grad_norm": 0.1591796875,
|
| 18586 |
+
"learning_rate": 8.92531161298475e-06,
|
| 18587 |
+
"loss": 1.9258359670639038,
|
| 18588 |
+
"step": 5308
|
| 18589 |
+
},
|
| 18590 |
+
{
|
| 18591 |
+
"epoch": 0.8112908462405225,
|
| 18592 |
+
"grad_norm": 0.146484375,
|
| 18593 |
+
"learning_rate": 8.897406283025478e-06,
|
| 18594 |
+
"loss": 1.9313774108886719,
|
| 18595 |
+
"step": 5310
|
| 18596 |
+
},
|
| 18597 |
+
{
|
| 18598 |
+
"epoch": 0.8115964171807261,
|
| 18599 |
+
"grad_norm": 0.15234375,
|
| 18600 |
+
"learning_rate": 8.869540383868057e-06,
|
| 18601 |
+
"loss": 1.9082694053649902,
|
| 18602 |
+
"step": 5312
|
| 18603 |
+
},
|
| 18604 |
+
{
|
| 18605 |
+
"epoch": 0.8119019881209297,
|
| 18606 |
+
"grad_norm": 0.15234375,
|
| 18607 |
+
"learning_rate": 8.841713942244972e-06,
|
| 18608 |
+
"loss": 1.9145747423171997,
|
| 18609 |
+
"step": 5314
|
| 18610 |
+
},
|
| 18611 |
+
{
|
| 18612 |
+
"epoch": 0.8122075590611333,
|
| 18613 |
+
"grad_norm": 0.1591796875,
|
| 18614 |
+
"learning_rate": 8.813926984850873e-06,
|
| 18615 |
+
"loss": 1.9453145265579224,
|
| 18616 |
+
"step": 5316
|
| 18617 |
+
},
|
| 18618 |
+
{
|
| 18619 |
+
"epoch": 0.8125131300013368,
|
| 18620 |
+
"grad_norm": 0.1494140625,
|
| 18621 |
+
"learning_rate": 8.78617953834252e-06,
|
| 18622 |
+
"loss": 1.9169728755950928,
|
| 18623 |
+
"step": 5318
|
| 18624 |
+
},
|
| 18625 |
+
{
|
| 18626 |
+
"epoch": 0.8128187009415404,
|
| 18627 |
+
"grad_norm": 0.1552734375,
|
| 18628 |
+
"learning_rate": 8.758471629338761e-06,
|
| 18629 |
+
"loss": 1.9105486869812012,
|
| 18630 |
+
"step": 5320
|
| 18631 |
+
},
|
| 18632 |
+
{
|
| 18633 |
+
"epoch": 0.8131242718817441,
|
| 18634 |
+
"grad_norm": 0.1552734375,
|
| 18635 |
+
"learning_rate": 8.730803284420524e-06,
|
| 18636 |
+
"loss": 1.8978204727172852,
|
| 18637 |
+
"step": 5322
|
| 18638 |
+
},
|
| 18639 |
+
{
|
| 18640 |
+
"epoch": 0.8134298428219476,
|
| 18641 |
+
"grad_norm": 0.146484375,
|
| 18642 |
+
"learning_rate": 8.703174530130792e-06,
|
| 18643 |
+
"loss": 1.9674570560455322,
|
| 18644 |
+
"step": 5324
|
| 18645 |
+
},
|
| 18646 |
+
{
|
| 18647 |
+
"epoch": 0.8137354137621512,
|
| 18648 |
+
"grad_norm": 0.16796875,
|
| 18649 |
+
"learning_rate": 8.67558539297455e-06,
|
| 18650 |
+
"loss": 1.906785011291504,
|
| 18651 |
+
"step": 5326
|
| 18652 |
+
},
|
| 18653 |
+
{
|
| 18654 |
+
"epoch": 0.8140409847023548,
|
| 18655 |
+
"grad_norm": 0.1611328125,
|
| 18656 |
+
"learning_rate": 8.6480358994188e-06,
|
| 18657 |
+
"loss": 1.9341810941696167,
|
| 18658 |
+
"step": 5328
|
| 18659 |
+
},
|
| 18660 |
+
{
|
| 18661 |
+
"epoch": 0.8143465556425584,
|
| 18662 |
+
"grad_norm": 0.16015625,
|
| 18663 |
+
"learning_rate": 8.62052607589246e-06,
|
| 18664 |
+
"loss": 1.9651890993118286,
|
| 18665 |
+
"step": 5330
|
| 18666 |
+
},
|
| 18667 |
+
{
|
| 18668 |
+
"epoch": 0.814652126582762,
|
| 18669 |
+
"grad_norm": 0.1494140625,
|
| 18670 |
+
"learning_rate": 8.59305594878646e-06,
|
| 18671 |
+
"loss": 1.945563554763794,
|
| 18672 |
+
"step": 5332
|
| 18673 |
+
},
|
| 18674 |
+
{
|
| 18675 |
+
"epoch": 0.8149576975229655,
|
| 18676 |
+
"grad_norm": 0.1669921875,
|
| 18677 |
+
"learning_rate": 8.565625544453615e-06,
|
| 18678 |
+
"loss": 1.8801608085632324,
|
| 18679 |
+
"step": 5334
|
| 18680 |
+
},
|
| 18681 |
+
{
|
| 18682 |
+
"epoch": 0.8152632684631691,
|
| 18683 |
+
"grad_norm": 0.1533203125,
|
| 18684 |
+
"learning_rate": 8.538234889208624e-06,
|
| 18685 |
+
"loss": 1.960620403289795,
|
| 18686 |
+
"step": 5336
|
| 18687 |
+
},
|
| 18688 |
+
{
|
| 18689 |
+
"epoch": 0.8155688394033728,
|
| 18690 |
+
"grad_norm": 0.169921875,
|
| 18691 |
+
"learning_rate": 8.510884009328074e-06,
|
| 18692 |
+
"loss": 1.9375795125961304,
|
| 18693 |
+
"step": 5338
|
| 18694 |
+
},
|
| 18695 |
+
{
|
| 18696 |
+
"epoch": 0.8158744103435763,
|
| 18697 |
+
"grad_norm": 0.146484375,
|
| 18698 |
+
"learning_rate": 8.483572931050399e-06,
|
| 18699 |
+
"loss": 1.936337947845459,
|
| 18700 |
+
"step": 5340
|
| 18701 |
+
},
|
| 18702 |
+
{
|
| 18703 |
+
"epoch": 0.8161799812837799,
|
| 18704 |
+
"grad_norm": 0.1494140625,
|
| 18705 |
+
"learning_rate": 8.456301680575801e-06,
|
| 18706 |
+
"loss": 1.9581674337387085,
|
| 18707 |
+
"step": 5342
|
| 18708 |
+
},
|
| 18709 |
+
{
|
| 18710 |
+
"epoch": 0.8164855522239834,
|
| 18711 |
+
"grad_norm": 0.15625,
|
| 18712 |
+
"learning_rate": 8.42907028406633e-06,
|
| 18713 |
+
"loss": 1.9231221675872803,
|
| 18714 |
+
"step": 5344
|
| 18715 |
+
},
|
| 18716 |
+
{
|
| 18717 |
+
"epoch": 0.8167911231641871,
|
| 18718 |
+
"grad_norm": 0.158203125,
|
| 18719 |
+
"learning_rate": 8.401878767645782e-06,
|
| 18720 |
+
"loss": 1.9569289684295654,
|
| 18721 |
+
"step": 5346
|
| 18722 |
+
},
|
| 18723 |
+
{
|
| 18724 |
+
"epoch": 0.8170966941043907,
|
| 18725 |
+
"grad_norm": 0.154296875,
|
| 18726 |
+
"learning_rate": 8.37472715739968e-06,
|
| 18727 |
+
"loss": 1.9175503253936768,
|
| 18728 |
+
"step": 5348
|
| 18729 |
+
},
|
| 18730 |
+
{
|
| 18731 |
+
"epoch": 0.8174022650445942,
|
| 18732 |
+
"grad_norm": 0.1484375,
|
| 18733 |
+
"learning_rate": 8.347615479375309e-06,
|
| 18734 |
+
"loss": 1.9485225677490234,
|
| 18735 |
+
"step": 5350
|
| 18736 |
+
},
|
| 18737 |
+
{
|
| 18738 |
+
"epoch": 0.8177078359847978,
|
| 18739 |
+
"grad_norm": 0.15234375,
|
| 18740 |
+
"learning_rate": 8.320543759581612e-06,
|
| 18741 |
+
"loss": 1.947117567062378,
|
| 18742 |
+
"step": 5352
|
| 18743 |
+
},
|
| 18744 |
+
{
|
| 18745 |
+
"epoch": 0.8180134069250015,
|
| 18746 |
+
"grad_norm": 0.1513671875,
|
| 18747 |
+
"learning_rate": 8.29351202398918e-06,
|
| 18748 |
+
"loss": 1.9112671613693237,
|
| 18749 |
+
"step": 5354
|
| 18750 |
+
},
|
| 18751 |
+
{
|
| 18752 |
+
"epoch": 0.818318977865205,
|
| 18753 |
+
"grad_norm": 0.1650390625,
|
| 18754 |
+
"learning_rate": 8.266520298530283e-06,
|
| 18755 |
+
"loss": 1.968353509902954,
|
| 18756 |
+
"step": 5356
|
| 18757 |
+
},
|
| 18758 |
+
{
|
| 18759 |
+
"epoch": 0.8186245488054086,
|
| 18760 |
+
"grad_norm": 0.154296875,
|
| 18761 |
+
"learning_rate": 8.239568609098796e-06,
|
| 18762 |
+
"loss": 1.907436728477478,
|
| 18763 |
+
"step": 5358
|
| 18764 |
+
},
|
| 18765 |
+
{
|
| 18766 |
+
"epoch": 0.8189301197456121,
|
| 18767 |
+
"grad_norm": 0.1572265625,
|
| 18768 |
+
"learning_rate": 8.212656981550182e-06,
|
| 18769 |
+
"loss": 1.899935007095337,
|
| 18770 |
+
"step": 5360
|
| 18771 |
+
},
|
| 18772 |
+
{
|
| 18773 |
+
"epoch": 0.8192356906858158,
|
| 18774 |
+
"grad_norm": 0.158203125,
|
| 18775 |
+
"learning_rate": 8.185785441701478e-06,
|
| 18776 |
+
"loss": 1.9148812294006348,
|
| 18777 |
+
"step": 5362
|
| 18778 |
+
},
|
| 18779 |
+
{
|
| 18780 |
+
"epoch": 0.8195412616260194,
|
| 18781 |
+
"grad_norm": 0.1533203125,
|
| 18782 |
+
"learning_rate": 8.158954015331261e-06,
|
| 18783 |
+
"loss": 1.8635931015014648,
|
| 18784 |
+
"step": 5364
|
| 18785 |
+
},
|
| 18786 |
+
{
|
| 18787 |
+
"epoch": 0.8198468325662229,
|
| 18788 |
+
"grad_norm": 0.1484375,
|
| 18789 |
+
"learning_rate": 8.132162728179621e-06,
|
| 18790 |
+
"loss": 1.9083846807479858,
|
| 18791 |
+
"step": 5366
|
| 18792 |
+
},
|
| 18793 |
+
{
|
| 18794 |
+
"epoch": 0.8201524035064265,
|
| 18795 |
+
"grad_norm": 0.1494140625,
|
| 18796 |
+
"learning_rate": 8.105411605948148e-06,
|
| 18797 |
+
"loss": 1.9347401857376099,
|
| 18798 |
+
"step": 5368
|
| 18799 |
+
},
|
| 18800 |
+
{
|
| 18801 |
+
"epoch": 0.8204579744466302,
|
| 18802 |
+
"grad_norm": 0.158203125,
|
| 18803 |
+
"learning_rate": 8.078700674299905e-06,
|
| 18804 |
+
"loss": 1.907139778137207,
|
| 18805 |
+
"step": 5370
|
| 18806 |
+
},
|
| 18807 |
+
{
|
| 18808 |
+
"epoch": 0.8207635453868337,
|
| 18809 |
+
"grad_norm": 0.16015625,
|
| 18810 |
+
"learning_rate": 8.05202995885938e-06,
|
| 18811 |
+
"loss": 1.9341109991073608,
|
| 18812 |
+
"step": 5372
|
| 18813 |
+
},
|
| 18814 |
+
{
|
| 18815 |
+
"epoch": 0.8210691163270373,
|
| 18816 |
+
"grad_norm": 0.1513671875,
|
| 18817 |
+
"learning_rate": 8.025399485212509e-06,
|
| 18818 |
+
"loss": 1.9497134685516357,
|
| 18819 |
+
"step": 5374
|
| 18820 |
+
},
|
| 18821 |
+
{
|
| 18822 |
+
"epoch": 0.8213746872672408,
|
| 18823 |
+
"grad_norm": 0.15625,
|
| 18824 |
+
"learning_rate": 7.9988092789066e-06,
|
| 18825 |
+
"loss": 1.9095563888549805,
|
| 18826 |
+
"step": 5376
|
| 18827 |
+
},
|
| 18828 |
+
{
|
| 18829 |
+
"epoch": 0.8216802582074445,
|
| 18830 |
+
"grad_norm": 0.16015625,
|
| 18831 |
+
"learning_rate": 7.972259365450347e-06,
|
| 18832 |
+
"loss": 1.9408921003341675,
|
| 18833 |
+
"step": 5378
|
| 18834 |
+
},
|
| 18835 |
+
{
|
| 18836 |
+
"epoch": 0.8219858291476481,
|
| 18837 |
+
"grad_norm": 0.1640625,
|
| 18838 |
+
"learning_rate": 7.945749770313754e-06,
|
| 18839 |
+
"loss": 1.9433181285858154,
|
| 18840 |
+
"step": 5380
|
| 18841 |
+
},
|
| 18842 |
+
{
|
| 18843 |
+
"epoch": 0.8222914000878516,
|
| 18844 |
+
"grad_norm": 0.1513671875,
|
| 18845 |
+
"learning_rate": 7.919280518928207e-06,
|
| 18846 |
+
"loss": 1.958287239074707,
|
| 18847 |
+
"step": 5382
|
| 18848 |
+
},
|
| 18849 |
+
{
|
| 18850 |
+
"epoch": 0.8225969710280552,
|
| 18851 |
+
"grad_norm": 0.1591796875,
|
| 18852 |
+
"learning_rate": 7.892851636686338e-06,
|
| 18853 |
+
"loss": 1.9320762157440186,
|
| 18854 |
+
"step": 5384
|
| 18855 |
+
},
|
| 18856 |
+
{
|
| 18857 |
+
"epoch": 0.8229025419682588,
|
| 18858 |
+
"grad_norm": 0.15234375,
|
| 18859 |
+
"learning_rate": 7.866463148942082e-06,
|
| 18860 |
+
"loss": 1.9127472639083862,
|
| 18861 |
+
"step": 5386
|
| 18862 |
+
},
|
| 18863 |
+
{
|
| 18864 |
+
"epoch": 0.8232081129084624,
|
| 18865 |
+
"grad_norm": 0.15625,
|
| 18866 |
+
"learning_rate": 7.840115081010608e-06,
|
| 18867 |
+
"loss": 1.9117984771728516,
|
| 18868 |
+
"step": 5388
|
| 18869 |
+
},
|
| 18870 |
+
{
|
| 18871 |
+
"epoch": 0.823513683848666,
|
| 18872 |
+
"grad_norm": 0.1884765625,
|
| 18873 |
+
"learning_rate": 7.813807458168321e-06,
|
| 18874 |
+
"loss": 1.9184699058532715,
|
| 18875 |
+
"step": 5390
|
| 18876 |
+
},
|
| 18877 |
+
{
|
| 18878 |
+
"epoch": 0.8238192547888695,
|
| 18879 |
+
"grad_norm": 0.1533203125,
|
| 18880 |
+
"learning_rate": 7.78754030565279e-06,
|
| 18881 |
+
"loss": 1.955857753753662,
|
| 18882 |
+
"step": 5392
|
| 18883 |
+
},
|
| 18884 |
+
{
|
| 18885 |
+
"epoch": 0.8241248257290732,
|
| 18886 |
+
"grad_norm": 0.150390625,
|
| 18887 |
+
"learning_rate": 7.761313648662805e-06,
|
| 18888 |
+
"loss": 1.8981866836547852,
|
| 18889 |
+
"step": 5394
|
| 18890 |
+
},
|
| 18891 |
+
{
|
| 18892 |
+
"epoch": 0.8244303966692768,
|
| 18893 |
+
"grad_norm": 0.150390625,
|
| 18894 |
+
"learning_rate": 7.735127512358292e-06,
|
| 18895 |
+
"loss": 1.8971281051635742,
|
| 18896 |
+
"step": 5396
|
| 18897 |
+
},
|
| 18898 |
+
{
|
| 18899 |
+
"epoch": 0.8247359676094803,
|
| 18900 |
+
"grad_norm": 0.1513671875,
|
| 18901 |
+
"learning_rate": 7.708981921860282e-06,
|
| 18902 |
+
"loss": 1.90993070602417,
|
| 18903 |
+
"step": 5398
|
| 18904 |
+
},
|
| 18905 |
+
{
|
| 18906 |
+
"epoch": 0.8250415385496839,
|
| 18907 |
+
"grad_norm": 0.1572265625,
|
| 18908 |
+
"learning_rate": 7.682876902250957e-06,
|
| 18909 |
+
"loss": 1.8913421630859375,
|
| 18910 |
+
"step": 5400
|
| 18911 |
+
},
|
| 18912 |
+
{
|
| 18913 |
+
"epoch": 0.8253471094898875,
|
| 18914 |
+
"grad_norm": 0.1513671875,
|
| 18915 |
+
"learning_rate": 7.656812478573555e-06,
|
| 18916 |
+
"loss": 1.9415556192398071,
|
| 18917 |
+
"step": 5402
|
| 18918 |
+
},
|
| 18919 |
+
{
|
| 18920 |
+
"epoch": 0.8256526804300911,
|
| 18921 |
+
"grad_norm": 0.15625,
|
| 18922 |
+
"learning_rate": 7.630788675832334e-06,
|
| 18923 |
+
"loss": 1.9170390367507935,
|
| 18924 |
+
"step": 5404
|
| 18925 |
+
},
|
| 18926 |
+
{
|
| 18927 |
+
"epoch": 0.8259582513702947,
|
| 18928 |
+
"grad_norm": 0.1494140625,
|
| 18929 |
+
"learning_rate": 7.604805518992625e-06,
|
| 18930 |
+
"loss": 1.9260592460632324,
|
| 18931 |
+
"step": 5406
|
| 18932 |
+
},
|
| 18933 |
+
{
|
| 18934 |
+
"epoch": 0.8262638223104982,
|
| 18935 |
+
"grad_norm": 0.150390625,
|
| 18936 |
+
"learning_rate": 7.578863032980765e-06,
|
| 18937 |
+
"loss": 1.9869914054870605,
|
| 18938 |
+
"step": 5408
|
| 18939 |
+
},
|
| 18940 |
+
{
|
| 18941 |
+
"epoch": 0.8265693932507019,
|
| 18942 |
+
"grad_norm": 0.15234375,
|
| 18943 |
+
"learning_rate": 7.552961242684054e-06,
|
| 18944 |
+
"loss": 1.9211745262145996,
|
| 18945 |
+
"step": 5410
|
| 18946 |
+
},
|
| 18947 |
+
{
|
| 18948 |
+
"epoch": 0.8268749641909054,
|
| 18949 |
+
"grad_norm": 0.15625,
|
| 18950 |
+
"learning_rate": 7.527100172950774e-06,
|
| 18951 |
+
"loss": 1.9367847442626953,
|
| 18952 |
+
"step": 5412
|
| 18953 |
+
},
|
| 18954 |
+
{
|
| 18955 |
+
"epoch": 0.827180535131109,
|
| 18956 |
+
"grad_norm": 0.150390625,
|
| 18957 |
+
"learning_rate": 7.5012798485901145e-06,
|
| 18958 |
+
"loss": 1.902390718460083,
|
| 18959 |
+
"step": 5414
|
| 18960 |
+
},
|
| 18961 |
+
{
|
| 18962 |
+
"epoch": 0.8274861060713126,
|
| 18963 |
+
"grad_norm": 0.1513671875,
|
| 18964 |
+
"learning_rate": 7.475500294372212e-06,
|
| 18965 |
+
"loss": 1.9021257162094116,
|
| 18966 |
+
"step": 5416
|
| 18967 |
+
},
|
| 18968 |
+
{
|
| 18969 |
+
"epoch": 0.8277916770115162,
|
| 18970 |
+
"grad_norm": 0.15625,
|
| 18971 |
+
"learning_rate": 7.449761535028061e-06,
|
| 18972 |
+
"loss": 1.9334955215454102,
|
| 18973 |
+
"step": 5418
|
| 18974 |
+
},
|
| 18975 |
+
{
|
| 18976 |
+
"epoch": 0.8280972479517198,
|
| 18977 |
+
"grad_norm": 0.1513671875,
|
| 18978 |
+
"learning_rate": 7.424063595249537e-06,
|
| 18979 |
+
"loss": 1.9655771255493164,
|
| 18980 |
+
"step": 5420
|
| 18981 |
+
},
|
| 18982 |
+
{
|
| 18983 |
+
"epoch": 0.8284028188919234,
|
| 18984 |
+
"grad_norm": 0.158203125,
|
| 18985 |
+
"learning_rate": 7.398406499689342e-06,
|
| 18986 |
+
"loss": 1.9226950407028198,
|
| 18987 |
+
"step": 5422
|
| 18988 |
+
},
|
| 18989 |
+
{
|
| 18990 |
+
"epoch": 0.8287083898321269,
|
| 18991 |
+
"grad_norm": 0.1552734375,
|
| 18992 |
+
"learning_rate": 7.372790272961017e-06,
|
| 18993 |
+
"loss": 1.9292882680892944,
|
| 18994 |
+
"step": 5424
|
| 18995 |
+
},
|
| 18996 |
+
{
|
| 18997 |
+
"epoch": 0.8290139607723306,
|
| 18998 |
+
"grad_norm": 0.1630859375,
|
| 18999 |
+
"learning_rate": 7.34721493963888e-06,
|
| 19000 |
+
"loss": 1.9559669494628906,
|
| 19001 |
+
"step": 5426
|
| 19002 |
+
},
|
| 19003 |
+
{
|
| 19004 |
+
"epoch": 0.8293195317125341,
|
| 19005 |
+
"grad_norm": 0.1513671875,
|
| 19006 |
+
"learning_rate": 7.321680524258029e-06,
|
| 19007 |
+
"loss": 1.985828161239624,
|
| 19008 |
+
"step": 5428
|
| 19009 |
+
},
|
| 19010 |
+
{
|
| 19011 |
+
"epoch": 0.8296251026527377,
|
| 19012 |
+
"grad_norm": 0.1494140625,
|
| 19013 |
+
"learning_rate": 7.296187051314279e-06,
|
| 19014 |
+
"loss": 1.9555485248565674,
|
| 19015 |
+
"step": 5430
|
| 19016 |
+
},
|
| 19017 |
+
{
|
| 19018 |
+
"epoch": 0.8299306735929413,
|
| 19019 |
+
"grad_norm": 0.15234375,
|
| 19020 |
+
"learning_rate": 7.270734545264196e-06,
|
| 19021 |
+
"loss": 1.9439975023269653,
|
| 19022 |
+
"step": 5432
|
| 19023 |
+
},
|
| 19024 |
+
{
|
| 19025 |
+
"epoch": 0.8302362445331449,
|
| 19026 |
+
"grad_norm": 0.1474609375,
|
| 19027 |
+
"learning_rate": 7.245323030525059e-06,
|
| 19028 |
+
"loss": 1.934565782546997,
|
| 19029 |
+
"step": 5434
|
| 19030 |
+
},
|
| 19031 |
+
{
|
| 19032 |
+
"epoch": 0.8305418154733485,
|
| 19033 |
+
"grad_norm": 0.15625,
|
| 19034 |
+
"learning_rate": 7.2199525314747994e-06,
|
| 19035 |
+
"loss": 1.9251108169555664,
|
| 19036 |
+
"step": 5436
|
| 19037 |
+
},
|
| 19038 |
+
{
|
| 19039 |
+
"epoch": 0.830847386413552,
|
| 19040 |
+
"grad_norm": 0.15234375,
|
| 19041 |
+
"learning_rate": 7.194623072451995e-06,
|
| 19042 |
+
"loss": 1.887392520904541,
|
| 19043 |
+
"step": 5438
|
| 19044 |
+
},
|
| 19045 |
+
{
|
| 19046 |
+
"epoch": 0.8311529573537556,
|
| 19047 |
+
"grad_norm": 0.15625,
|
| 19048 |
+
"learning_rate": 7.169334677755884e-06,
|
| 19049 |
+
"loss": 1.9096488952636719,
|
| 19050 |
+
"step": 5440
|
| 19051 |
+
},
|
| 19052 |
+
{
|
| 19053 |
+
"epoch": 0.8314585282939593,
|
| 19054 |
+
"grad_norm": 0.1630859375,
|
| 19055 |
+
"learning_rate": 7.144087371646263e-06,
|
| 19056 |
+
"loss": 1.9032042026519775,
|
| 19057 |
+
"step": 5442
|
| 19058 |
+
},
|
| 19059 |
+
{
|
| 19060 |
+
"epoch": 0.8317640992341628,
|
| 19061 |
+
"grad_norm": 0.15625,
|
| 19062 |
+
"learning_rate": 7.118881178343556e-06,
|
| 19063 |
+
"loss": 1.9050054550170898,
|
| 19064 |
+
"step": 5444
|
| 19065 |
+
},
|
| 19066 |
+
{
|
| 19067 |
+
"epoch": 0.8320696701743664,
|
| 19068 |
+
"grad_norm": 0.1494140625,
|
| 19069 |
+
"learning_rate": 7.0937161220287155e-06,
|
| 19070 |
+
"loss": 1.894331455230713,
|
| 19071 |
+
"step": 5446
|
| 19072 |
+
},
|
| 19073 |
+
{
|
| 19074 |
+
"epoch": 0.83237524111457,
|
| 19075 |
+
"grad_norm": 0.1533203125,
|
| 19076 |
+
"learning_rate": 7.068592226843246e-06,
|
| 19077 |
+
"loss": 1.9416897296905518,
|
| 19078 |
+
"step": 5448
|
| 19079 |
+
},
|
| 19080 |
+
{
|
| 19081 |
+
"epoch": 0.8326808120547736,
|
| 19082 |
+
"grad_norm": 0.1591796875,
|
| 19083 |
+
"learning_rate": 7.043509516889179e-06,
|
| 19084 |
+
"loss": 1.8912389278411865,
|
| 19085 |
+
"step": 5450
|
| 19086 |
+
},
|
| 19087 |
+
{
|
| 19088 |
+
"epoch": 0.8329863829949772,
|
| 19089 |
+
"grad_norm": 0.154296875,
|
| 19090 |
+
"learning_rate": 7.018468016229018e-06,
|
| 19091 |
+
"loss": 1.935148000717163,
|
| 19092 |
+
"step": 5452
|
| 19093 |
+
},
|
| 19094 |
+
{
|
| 19095 |
+
"epoch": 0.8332919539351807,
|
| 19096 |
+
"grad_norm": 0.1513671875,
|
| 19097 |
+
"learning_rate": 6.993467748885718e-06,
|
| 19098 |
+
"loss": 1.955526351928711,
|
| 19099 |
+
"step": 5454
|
| 19100 |
+
},
|
| 19101 |
+
{
|
| 19102 |
+
"epoch": 0.8335975248753843,
|
| 19103 |
+
"grad_norm": 0.146484375,
|
| 19104 |
+
"learning_rate": 6.968508738842699e-06,
|
| 19105 |
+
"loss": 1.8973287343978882,
|
| 19106 |
+
"step": 5456
|
| 19107 |
+
},
|
| 19108 |
+
{
|
| 19109 |
+
"epoch": 0.833903095815588,
|
| 19110 |
+
"grad_norm": 0.1513671875,
|
| 19111 |
+
"learning_rate": 6.9435910100438036e-06,
|
| 19112 |
+
"loss": 1.9233163595199585,
|
| 19113 |
+
"step": 5458
|
| 19114 |
+
},
|
| 19115 |
+
{
|
| 19116 |
+
"epoch": 0.8342086667557915,
|
| 19117 |
+
"grad_norm": 0.158203125,
|
| 19118 |
+
"learning_rate": 6.91871458639326e-06,
|
| 19119 |
+
"loss": 1.9654291868209839,
|
| 19120 |
+
"step": 5460
|
| 19121 |
+
},
|
| 19122 |
+
{
|
| 19123 |
+
"epoch": 0.8345142376959951,
|
| 19124 |
+
"grad_norm": 0.162109375,
|
| 19125 |
+
"learning_rate": 6.893879491755683e-06,
|
| 19126 |
+
"loss": 1.9275715351104736,
|
| 19127 |
+
"step": 5462
|
| 19128 |
+
},
|
| 19129 |
+
{
|
| 19130 |
+
"epoch": 0.8348198086361986,
|
| 19131 |
+
"grad_norm": 0.158203125,
|
| 19132 |
+
"learning_rate": 6.869085749956033e-06,
|
| 19133 |
+
"loss": 1.9508109092712402,
|
| 19134 |
+
"step": 5464
|
| 19135 |
+
},
|
| 19136 |
+
{
|
| 19137 |
+
"epoch": 0.8351253795764023,
|
| 19138 |
+
"grad_norm": 0.1572265625,
|
| 19139 |
+
"learning_rate": 6.8443333847795945e-06,
|
| 19140 |
+
"loss": 1.93628990650177,
|
| 19141 |
+
"step": 5466
|
| 19142 |
+
},
|
| 19143 |
+
{
|
| 19144 |
+
"epoch": 0.8354309505166059,
|
| 19145 |
+
"grad_norm": 0.154296875,
|
| 19146 |
+
"learning_rate": 6.819622419971966e-06,
|
| 19147 |
+
"loss": 1.8890342712402344,
|
| 19148 |
+
"step": 5468
|
| 19149 |
+
},
|
| 19150 |
+
{
|
| 19151 |
+
"epoch": 0.8357365214568094,
|
| 19152 |
+
"grad_norm": 0.1484375,
|
| 19153 |
+
"learning_rate": 6.794952879239036e-06,
|
| 19154 |
+
"loss": 1.9766144752502441,
|
| 19155 |
+
"step": 5470
|
| 19156 |
+
},
|
| 19157 |
+
{
|
| 19158 |
+
"epoch": 0.836042092397013,
|
| 19159 |
+
"grad_norm": 0.158203125,
|
| 19160 |
+
"learning_rate": 6.770324786246934e-06,
|
| 19161 |
+
"loss": 1.894834280014038,
|
| 19162 |
+
"step": 5472
|
| 19163 |
+
},
|
| 19164 |
+
{
|
| 19165 |
+
"epoch": 0.8363476633372167,
|
| 19166 |
+
"grad_norm": 0.15234375,
|
| 19167 |
+
"learning_rate": 6.745738164622045e-06,
|
| 19168 |
+
"loss": 1.930824637413025,
|
| 19169 |
+
"step": 5474
|
| 19170 |
+
},
|
| 19171 |
+
{
|
| 19172 |
+
"epoch": 0.8366532342774202,
|
| 19173 |
+
"grad_norm": 0.1611328125,
|
| 19174 |
+
"learning_rate": 6.721193037950962e-06,
|
| 19175 |
+
"loss": 1.9144682884216309,
|
| 19176 |
+
"step": 5476
|
| 19177 |
+
},
|
| 19178 |
+
{
|
| 19179 |
+
"epoch": 0.8369588052176238,
|
| 19180 |
+
"grad_norm": 0.1591796875,
|
| 19181 |
+
"learning_rate": 6.6966894297804835e-06,
|
| 19182 |
+
"loss": 1.9045817852020264,
|
| 19183 |
+
"step": 5478
|
| 19184 |
+
},
|
| 19185 |
+
{
|
| 19186 |
+
"epoch": 0.8372643761578273,
|
| 19187 |
+
"grad_norm": 0.16015625,
|
| 19188 |
+
"learning_rate": 6.672227363617545e-06,
|
| 19189 |
+
"loss": 1.939806342124939,
|
| 19190 |
+
"step": 5480
|
| 19191 |
+
},
|
| 19192 |
+
{
|
| 19193 |
+
"epoch": 0.837569947098031,
|
| 19194 |
+
"grad_norm": 0.1591796875,
|
| 19195 |
+
"learning_rate": 6.647806862929251e-06,
|
| 19196 |
+
"loss": 1.9073753356933594,
|
| 19197 |
+
"step": 5482
|
| 19198 |
+
},
|
| 19199 |
+
{
|
| 19200 |
+
"epoch": 0.8378755180382346,
|
| 19201 |
+
"grad_norm": 0.1669921875,
|
| 19202 |
+
"learning_rate": 6.623427951142852e-06,
|
| 19203 |
+
"loss": 1.944246530532837,
|
| 19204 |
+
"step": 5484
|
| 19205 |
+
},
|
| 19206 |
+
{
|
| 19207 |
+
"epoch": 0.8381810889784381,
|
| 19208 |
+
"grad_norm": 0.1552734375,
|
| 19209 |
+
"learning_rate": 6.599090651645673e-06,
|
| 19210 |
+
"loss": 1.9559378623962402,
|
| 19211 |
+
"step": 5486
|
| 19212 |
+
},
|
| 19213 |
+
{
|
| 19214 |
+
"epoch": 0.8384866599186417,
|
| 19215 |
+
"grad_norm": 0.15234375,
|
| 19216 |
+
"learning_rate": 6.5747949877851265e-06,
|
| 19217 |
+
"loss": 1.9094111919403076,
|
| 19218 |
+
"step": 5488
|
| 19219 |
+
},
|
| 19220 |
+
{
|
| 19221 |
+
"epoch": 0.8387922308588454,
|
| 19222 |
+
"grad_norm": 0.15625,
|
| 19223 |
+
"learning_rate": 6.550540982868692e-06,
|
| 19224 |
+
"loss": 1.948682188987732,
|
| 19225 |
+
"step": 5490
|
| 19226 |
+
},
|
| 19227 |
+
{
|
| 19228 |
+
"epoch": 0.8390978017990489,
|
| 19229 |
+
"grad_norm": 0.1650390625,
|
| 19230 |
+
"learning_rate": 6.526328660163855e-06,
|
| 19231 |
+
"loss": 1.9712698459625244,
|
| 19232 |
+
"step": 5492
|
| 19233 |
+
},
|
| 19234 |
+
{
|
| 19235 |
+
"epoch": 0.8394033727392525,
|
| 19236 |
+
"grad_norm": 0.154296875,
|
| 19237 |
+
"learning_rate": 6.502158042898149e-06,
|
| 19238 |
+
"loss": 1.9585237503051758,
|
| 19239 |
+
"step": 5494
|
| 19240 |
+
},
|
| 19241 |
+
{
|
| 19242 |
+
"epoch": 0.839708943679456,
|
| 19243 |
+
"grad_norm": 0.1728515625,
|
| 19244 |
+
"learning_rate": 6.47802915425908e-06,
|
| 19245 |
+
"loss": 1.9119877815246582,
|
| 19246 |
+
"step": 5496
|
| 19247 |
+
},
|
| 19248 |
+
{
|
| 19249 |
+
"epoch": 0.8400145146196597,
|
| 19250 |
+
"grad_norm": 0.1572265625,
|
| 19251 |
+
"learning_rate": 6.4539420173941215e-06,
|
| 19252 |
+
"loss": 1.9380617141723633,
|
| 19253 |
+
"step": 5498
|
| 19254 |
+
},
|
| 19255 |
+
{
|
| 19256 |
+
"epoch": 0.8403200855598633,
|
| 19257 |
+
"grad_norm": 0.1513671875,
|
| 19258 |
+
"learning_rate": 6.429896655410711e-06,
|
| 19259 |
+
"loss": 1.9383186101913452,
|
| 19260 |
+
"step": 5500
|
| 19261 |
+
},
|
| 19262 |
+
{
|
| 19263 |
+
"epoch": 0.8406256565000668,
|
| 19264 |
+
"grad_norm": 0.1591796875,
|
| 19265 |
+
"learning_rate": 6.405893091376208e-06,
|
| 19266 |
+
"loss": 1.9516736268997192,
|
| 19267 |
+
"step": 5502
|
| 19268 |
+
},
|
| 19269 |
+
{
|
| 19270 |
+
"epoch": 0.8409312274402704,
|
| 19271 |
+
"grad_norm": 0.162109375,
|
| 19272 |
+
"learning_rate": 6.381931348317844e-06,
|
| 19273 |
+
"loss": 1.9315450191497803,
|
| 19274 |
+
"step": 5504
|
| 19275 |
+
},
|
| 19276 |
+
{
|
| 19277 |
+
"epoch": 0.841236798380474,
|
| 19278 |
+
"grad_norm": 0.1494140625,
|
| 19279 |
+
"learning_rate": 6.3580114492227505e-06,
|
| 19280 |
+
"loss": 1.94757080078125,
|
| 19281 |
+
"step": 5506
|
| 19282 |
+
},
|
| 19283 |
+
{
|
| 19284 |
+
"epoch": 0.8415423693206776,
|
| 19285 |
+
"grad_norm": 0.1630859375,
|
| 19286 |
+
"learning_rate": 6.334133417037924e-06,
|
| 19287 |
+
"loss": 1.9369808435440063,
|
| 19288 |
+
"step": 5508
|
| 19289 |
+
},
|
| 19290 |
+
{
|
| 19291 |
+
"epoch": 0.8418479402608812,
|
| 19292 |
+
"grad_norm": 0.1611328125,
|
| 19293 |
+
"learning_rate": 6.310297274670196e-06,
|
| 19294 |
+
"loss": 1.9169738292694092,
|
| 19295 |
+
"step": 5510
|
| 19296 |
+
},
|
| 19297 |
+
{
|
| 19298 |
+
"epoch": 0.8421535112010847,
|
| 19299 |
+
"grad_norm": 0.166015625,
|
| 19300 |
+
"learning_rate": 6.286503044986197e-06,
|
| 19301 |
+
"loss": 1.987464427947998,
|
| 19302 |
+
"step": 5512
|
| 19303 |
+
},
|
| 19304 |
+
{
|
| 19305 |
+
"epoch": 0.8424590821412884,
|
| 19306 |
+
"grad_norm": 0.15234375,
|
| 19307 |
+
"learning_rate": 6.262750750812357e-06,
|
| 19308 |
+
"loss": 1.900130033493042,
|
| 19309 |
+
"step": 5514
|
| 19310 |
+
},
|
| 19311 |
+
{
|
| 19312 |
+
"epoch": 0.842764653081492,
|
| 19313 |
+
"grad_norm": 0.1552734375,
|
| 19314 |
+
"learning_rate": 6.239040414934893e-06,
|
| 19315 |
+
"loss": 1.9333908557891846,
|
| 19316 |
+
"step": 5516
|
| 19317 |
+
},
|
| 19318 |
+
{
|
| 19319 |
+
"epoch": 0.8430702240216955,
|
| 19320 |
+
"grad_norm": 0.1513671875,
|
| 19321 |
+
"learning_rate": 6.215372060099739e-06,
|
| 19322 |
+
"loss": 1.9390544891357422,
|
| 19323 |
+
"step": 5518
|
| 19324 |
+
},
|
| 19325 |
+
{
|
| 19326 |
+
"epoch": 0.8433757949618991,
|
| 19327 |
+
"grad_norm": 0.1572265625,
|
| 19328 |
+
"learning_rate": 6.191745709012581e-06,
|
| 19329 |
+
"loss": 1.952589750289917,
|
| 19330 |
+
"step": 5520
|
| 19331 |
+
},
|
| 19332 |
+
{
|
| 19333 |
+
"epoch": 0.8436813659021027,
|
| 19334 |
+
"grad_norm": 0.1552734375,
|
| 19335 |
+
"learning_rate": 6.1681613843388e-06,
|
| 19336 |
+
"loss": 1.9360315799713135,
|
| 19337 |
+
"step": 5522
|
| 19338 |
+
},
|
| 19339 |
+
{
|
| 19340 |
+
"epoch": 0.8439869368423063,
|
| 19341 |
+
"grad_norm": 0.1591796875,
|
| 19342 |
+
"learning_rate": 6.144619108703453e-06,
|
| 19343 |
+
"loss": 1.8973066806793213,
|
| 19344 |
+
"step": 5524
|
| 19345 |
+
},
|
| 19346 |
+
{
|
| 19347 |
+
"epoch": 0.8442925077825099,
|
| 19348 |
+
"grad_norm": 0.15625,
|
| 19349 |
+
"learning_rate": 6.121118904691275e-06,
|
| 19350 |
+
"loss": 1.9070980548858643,
|
| 19351 |
+
"step": 5526
|
| 19352 |
+
},
|
| 19353 |
+
{
|
| 19354 |
+
"epoch": 0.8445980787227134,
|
| 19355 |
+
"grad_norm": 0.1513671875,
|
| 19356 |
+
"learning_rate": 6.097660794846632e-06,
|
| 19357 |
+
"loss": 1.9509303569793701,
|
| 19358 |
+
"step": 5528
|
| 19359 |
+
},
|
| 19360 |
+
{
|
| 19361 |
+
"epoch": 0.8449036496629171,
|
| 19362 |
+
"grad_norm": 0.158203125,
|
| 19363 |
+
"learning_rate": 6.074244801673507e-06,
|
| 19364 |
+
"loss": 1.913062334060669,
|
| 19365 |
+
"step": 5530
|
| 19366 |
+
},
|
| 19367 |
+
{
|
| 19368 |
+
"epoch": 0.8452092206031206,
|
| 19369 |
+
"grad_norm": 0.15625,
|
| 19370 |
+
"learning_rate": 6.0508709476354565e-06,
|
| 19371 |
+
"loss": 1.9307677745819092,
|
| 19372 |
+
"step": 5532
|
| 19373 |
+
},
|
| 19374 |
+
{
|
| 19375 |
+
"epoch": 0.8455147915433242,
|
| 19376 |
+
"grad_norm": 0.15625,
|
| 19377 |
+
"learning_rate": 6.027539255155668e-06,
|
| 19378 |
+
"loss": 1.9243550300598145,
|
| 19379 |
+
"step": 5534
|
| 19380 |
+
},
|
| 19381 |
+
{
|
| 19382 |
+
"epoch": 0.8458203624835278,
|
| 19383 |
+
"grad_norm": 0.1708984375,
|
| 19384 |
+
"learning_rate": 6.0042497466168304e-06,
|
| 19385 |
+
"loss": 1.946771502494812,
|
| 19386 |
+
"step": 5536
|
| 19387 |
+
},
|
| 19388 |
+
{
|
| 19389 |
+
"epoch": 0.8461259334237314,
|
| 19390 |
+
"grad_norm": 0.1474609375,
|
| 19391 |
+
"learning_rate": 5.981002444361189e-06,
|
| 19392 |
+
"loss": 1.922659158706665,
|
| 19393 |
+
"step": 5538
|
| 19394 |
+
},
|
| 19395 |
+
{
|
| 19396 |
+
"epoch": 0.846431504363935,
|
| 19397 |
+
"grad_norm": 0.150390625,
|
| 19398 |
+
"learning_rate": 5.957797370690504e-06,
|
| 19399 |
+
"loss": 1.9169490337371826,
|
| 19400 |
+
"step": 5540
|
| 19401 |
+
},
|
| 19402 |
+
{
|
| 19403 |
+
"epoch": 0.8467370753041386,
|
| 19404 |
+
"grad_norm": 0.1630859375,
|
| 19405 |
+
"learning_rate": 5.934634547865991e-06,
|
| 19406 |
+
"loss": 1.9436589479446411,
|
| 19407 |
+
"step": 5542
|
| 19408 |
+
},
|
| 19409 |
+
{
|
| 19410 |
+
"epoch": 0.8470426462443421,
|
| 19411 |
+
"grad_norm": 0.1669921875,
|
| 19412 |
+
"learning_rate": 5.91151399810837e-06,
|
| 19413 |
+
"loss": 1.9220954179763794,
|
| 19414 |
+
"step": 5544
|
| 19415 |
+
},
|
| 19416 |
+
{
|
| 19417 |
+
"epoch": 0.8473482171845458,
|
| 19418 |
+
"grad_norm": 0.15234375,
|
| 19419 |
+
"learning_rate": 5.888435743597792e-06,
|
| 19420 |
+
"loss": 1.957187533378601,
|
| 19421 |
+
"step": 5546
|
| 19422 |
+
},
|
| 19423 |
+
{
|
| 19424 |
+
"epoch": 0.8476537881247493,
|
| 19425 |
+
"grad_norm": 0.1484375,
|
| 19426 |
+
"learning_rate": 5.865399806473831e-06,
|
| 19427 |
+
"loss": 1.8968881368637085,
|
| 19428 |
+
"step": 5548
|
| 19429 |
+
},
|
| 19430 |
+
{
|
| 19431 |
+
"epoch": 0.8479593590649529,
|
| 19432 |
+
"grad_norm": 0.15625,
|
| 19433 |
+
"learning_rate": 5.842406208835477e-06,
|
| 19434 |
+
"loss": 1.9096622467041016,
|
| 19435 |
+
"step": 5550
|
| 19436 |
+
},
|
| 19437 |
+
{
|
| 19438 |
+
"epoch": 0.8482649300051565,
|
| 19439 |
+
"grad_norm": 0.162109375,
|
| 19440 |
+
"learning_rate": 5.819454972741106e-06,
|
| 19441 |
+
"loss": 1.9144492149353027,
|
| 19442 |
+
"step": 5552
|
| 19443 |
+
},
|
| 19444 |
+
{
|
| 19445 |
+
"epoch": 0.8485705009453601,
|
| 19446 |
+
"grad_norm": 0.1611328125,
|
| 19447 |
+
"learning_rate": 5.796546120208418e-06,
|
| 19448 |
+
"loss": 1.9035193920135498,
|
| 19449 |
+
"step": 5554
|
| 19450 |
+
},
|
| 19451 |
+
{
|
| 19452 |
+
"epoch": 0.8488760718855637,
|
| 19453 |
+
"grad_norm": 0.1591796875,
|
| 19454 |
+
"learning_rate": 5.773679673214488e-06,
|
| 19455 |
+
"loss": 1.944746971130371,
|
| 19456 |
+
"step": 5556
|
| 19457 |
+
},
|
| 19458 |
+
{
|
| 19459 |
+
"epoch": 0.8491816428257672,
|
| 19460 |
+
"grad_norm": 0.1572265625,
|
| 19461 |
+
"learning_rate": 5.750855653695708e-06,
|
| 19462 |
+
"loss": 1.9467291831970215,
|
| 19463 |
+
"step": 5558
|
| 19464 |
+
},
|
| 19465 |
+
{
|
| 19466 |
+
"epoch": 0.8494872137659708,
|
| 19467 |
+
"grad_norm": 0.1591796875,
|
| 19468 |
+
"learning_rate": 5.728074083547752e-06,
|
| 19469 |
+
"loss": 1.9416916370391846,
|
| 19470 |
+
"step": 5560
|
| 19471 |
+
},
|
| 19472 |
+
{
|
| 19473 |
+
"epoch": 0.8497927847061745,
|
| 19474 |
+
"grad_norm": 0.1591796875,
|
| 19475 |
+
"learning_rate": 5.705334984625593e-06,
|
| 19476 |
+
"loss": 1.9316309690475464,
|
| 19477 |
+
"step": 5562
|
| 19478 |
+
},
|
| 19479 |
+
{
|
| 19480 |
+
"epoch": 0.850098355646378,
|
| 19481 |
+
"grad_norm": 0.1572265625,
|
| 19482 |
+
"learning_rate": 5.682638378743438e-06,
|
| 19483 |
+
"loss": 1.928184986114502,
|
| 19484 |
+
"step": 5564
|
| 19485 |
+
},
|
| 19486 |
+
{
|
| 19487 |
+
"epoch": 0.8504039265865816,
|
| 19488 |
+
"grad_norm": 0.15234375,
|
| 19489 |
+
"learning_rate": 5.659984287674741e-06,
|
| 19490 |
+
"loss": 1.9354751110076904,
|
| 19491 |
+
"step": 5566
|
| 19492 |
+
},
|
| 19493 |
+
{
|
| 19494 |
+
"epoch": 0.8507094975267852,
|
| 19495 |
+
"grad_norm": 0.1611328125,
|
| 19496 |
+
"learning_rate": 5.637372733152174e-06,
|
| 19497 |
+
"loss": 1.946413278579712,
|
| 19498 |
+
"step": 5568
|
| 19499 |
+
},
|
| 19500 |
+
{
|
| 19501 |
+
"epoch": 0.8510150684669888,
|
| 19502 |
+
"grad_norm": 0.1474609375,
|
| 19503 |
+
"learning_rate": 5.614803736867591e-06,
|
| 19504 |
+
"loss": 1.9728457927703857,
|
| 19505 |
+
"step": 5570
|
| 19506 |
+
},
|
| 19507 |
+
{
|
| 19508 |
+
"epoch": 0.8513206394071924,
|
| 19509 |
+
"grad_norm": 0.150390625,
|
| 19510 |
+
"learning_rate": 5.592277320472033e-06,
|
| 19511 |
+
"loss": 1.9165178537368774,
|
| 19512 |
+
"step": 5572
|
| 19513 |
+
},
|
| 19514 |
+
{
|
| 19515 |
+
"epoch": 0.8516262103473959,
|
| 19516 |
+
"grad_norm": 0.158203125,
|
| 19517 |
+
"learning_rate": 5.569793505575677e-06,
|
| 19518 |
+
"loss": 1.9829596281051636,
|
| 19519 |
+
"step": 5574
|
| 19520 |
+
},
|
| 19521 |
+
{
|
| 19522 |
+
"epoch": 0.8519317812875995,
|
| 19523 |
+
"grad_norm": 0.1455078125,
|
| 19524 |
+
"learning_rate": 5.547352313747844e-06,
|
| 19525 |
+
"loss": 1.9373838901519775,
|
| 19526 |
+
"step": 5576
|
| 19527 |
+
},
|
| 19528 |
+
{
|
| 19529 |
+
"epoch": 0.8522373522278032,
|
| 19530 |
+
"grad_norm": 0.15234375,
|
| 19531 |
+
"learning_rate": 5.52495376651696e-06,
|
| 19532 |
+
"loss": 1.9149088859558105,
|
| 19533 |
+
"step": 5578
|
| 19534 |
+
},
|
| 19535 |
+
{
|
| 19536 |
+
"epoch": 0.8525429231680067,
|
| 19537 |
+
"grad_norm": 0.158203125,
|
| 19538 |
+
"learning_rate": 5.502597885370553e-06,
|
| 19539 |
+
"loss": 1.9238390922546387,
|
| 19540 |
+
"step": 5580
|
| 19541 |
+
},
|
| 19542 |
+
{
|
| 19543 |
+
"epoch": 0.8528484941082103,
|
| 19544 |
+
"grad_norm": 0.15234375,
|
| 19545 |
+
"learning_rate": 5.480284691755178e-06,
|
| 19546 |
+
"loss": 1.9501891136169434,
|
| 19547 |
+
"step": 5582
|
| 19548 |
+
},
|
| 19549 |
+
{
|
| 19550 |
+
"epoch": 0.8531540650484138,
|
| 19551 |
+
"grad_norm": 0.15234375,
|
| 19552 |
+
"learning_rate": 5.4580142070765e-06,
|
| 19553 |
+
"loss": 1.9557846784591675,
|
| 19554 |
+
"step": 5584
|
| 19555 |
+
},
|
| 19556 |
+
{
|
| 19557 |
+
"epoch": 0.8534596359886175,
|
| 19558 |
+
"grad_norm": 0.1513671875,
|
| 19559 |
+
"learning_rate": 5.435786452699177e-06,
|
| 19560 |
+
"loss": 1.9540131092071533,
|
| 19561 |
+
"step": 5586
|
| 19562 |
+
},
|
| 19563 |
+
{
|
| 19564 |
+
"epoch": 0.8537652069288211,
|
| 19565 |
+
"grad_norm": 0.1611328125,
|
| 19566 |
+
"learning_rate": 5.41360144994687e-06,
|
| 19567 |
+
"loss": 1.9373104572296143,
|
| 19568 |
+
"step": 5588
|
| 19569 |
+
},
|
| 19570 |
+
{
|
| 19571 |
+
"epoch": 0.8540707778690246,
|
| 19572 |
+
"grad_norm": 0.1552734375,
|
| 19573 |
+
"learning_rate": 5.391459220102241e-06,
|
| 19574 |
+
"loss": 1.897569179534912,
|
| 19575 |
+
"step": 5590
|
| 19576 |
+
},
|
| 19577 |
+
{
|
| 19578 |
+
"epoch": 0.8543763488092282,
|
| 19579 |
+
"grad_norm": 0.1591796875,
|
| 19580 |
+
"learning_rate": 5.369359784406924e-06,
|
| 19581 |
+
"loss": 1.919455647468567,
|
| 19582 |
+
"step": 5592
|
| 19583 |
+
},
|
| 19584 |
+
{
|
| 19585 |
+
"epoch": 0.8546819197494319,
|
| 19586 |
+
"grad_norm": 0.16015625,
|
| 19587 |
+
"learning_rate": 5.347303164061479e-06,
|
| 19588 |
+
"loss": 1.9234287738800049,
|
| 19589 |
+
"step": 5594
|
| 19590 |
+
},
|
| 19591 |
+
{
|
| 19592 |
+
"epoch": 0.8549874906896354,
|
| 19593 |
+
"grad_norm": 0.1650390625,
|
| 19594 |
+
"learning_rate": 5.325289380225401e-06,
|
| 19595 |
+
"loss": 1.9281277656555176,
|
| 19596 |
+
"step": 5596
|
| 19597 |
+
},
|
| 19598 |
+
{
|
| 19599 |
+
"epoch": 0.855293061629839,
|
| 19600 |
+
"grad_norm": 0.158203125,
|
| 19601 |
+
"learning_rate": 5.303318454017103e-06,
|
| 19602 |
+
"loss": 1.9242134094238281,
|
| 19603 |
+
"step": 5598
|
| 19604 |
+
},
|
| 19605 |
+
{
|
| 19606 |
+
"epoch": 0.8555986325700425,
|
| 19607 |
+
"grad_norm": 0.16015625,
|
| 19608 |
+
"learning_rate": 5.2813904065138586e-06,
|
| 19609 |
+
"loss": 1.8991142511367798,
|
| 19610 |
+
"step": 5600
|
| 19611 |
+
},
|
| 19612 |
+
{
|
| 19613 |
+
"epoch": 0.8559042035102462,
|
| 19614 |
+
"grad_norm": 0.154296875,
|
| 19615 |
+
"learning_rate": 5.2595052587518514e-06,
|
| 19616 |
+
"loss": 1.950068473815918,
|
| 19617 |
+
"step": 5602
|
| 19618 |
+
},
|
| 19619 |
+
{
|
| 19620 |
+
"epoch": 0.8562097744504498,
|
| 19621 |
+
"grad_norm": 0.1552734375,
|
| 19622 |
+
"learning_rate": 5.237663031726053e-06,
|
| 19623 |
+
"loss": 1.912391185760498,
|
| 19624 |
+
"step": 5604
|
| 19625 |
+
},
|
| 19626 |
+
{
|
| 19627 |
+
"epoch": 0.8565153453906533,
|
| 19628 |
+
"grad_norm": 0.1591796875,
|
| 19629 |
+
"learning_rate": 5.215863746390298e-06,
|
| 19630 |
+
"loss": 1.9238295555114746,
|
| 19631 |
+
"step": 5606
|
| 19632 |
+
},
|
| 19633 |
+
{
|
| 19634 |
+
"epoch": 0.8568209163308569,
|
| 19635 |
+
"grad_norm": 0.1572265625,
|
| 19636 |
+
"learning_rate": 5.194107423657218e-06,
|
| 19637 |
+
"loss": 1.9392348527908325,
|
| 19638 |
+
"step": 5608
|
| 19639 |
+
},
|
| 19640 |
+
{
|
| 19641 |
+
"epoch": 0.8571264872710606,
|
| 19642 |
+
"grad_norm": 0.1572265625,
|
| 19643 |
+
"learning_rate": 5.172394084398219e-06,
|
| 19644 |
+
"loss": 1.8942393064498901,
|
| 19645 |
+
"step": 5610
|
| 19646 |
+
},
|
| 19647 |
+
{
|
| 19648 |
+
"epoch": 0.8574320582112641,
|
| 19649 |
+
"grad_norm": 0.158203125,
|
| 19650 |
+
"learning_rate": 5.150723749443487e-06,
|
| 19651 |
+
"loss": 1.9231719970703125,
|
| 19652 |
+
"step": 5612
|
| 19653 |
+
},
|
| 19654 |
+
{
|
| 19655 |
+
"epoch": 0.8577376291514677,
|
| 19656 |
+
"grad_norm": 0.1552734375,
|
| 19657 |
+
"learning_rate": 5.129096439581943e-06,
|
| 19658 |
+
"loss": 1.9403983354568481,
|
| 19659 |
+
"step": 5614
|
| 19660 |
+
},
|
| 19661 |
+
{
|
| 19662 |
+
"epoch": 0.8580432000916712,
|
| 19663 |
+
"grad_norm": 0.1650390625,
|
| 19664 |
+
"learning_rate": 5.10751217556123e-06,
|
| 19665 |
+
"loss": 1.9067273139953613,
|
| 19666 |
+
"step": 5616
|
| 19667 |
+
},
|
| 19668 |
+
{
|
| 19669 |
+
"epoch": 0.8583487710318749,
|
| 19670 |
+
"grad_norm": 0.1572265625,
|
| 19671 |
+
"learning_rate": 5.085970978087712e-06,
|
| 19672 |
+
"loss": 1.9070320129394531,
|
| 19673 |
+
"step": 5618
|
| 19674 |
+
},
|
| 19675 |
+
{
|
| 19676 |
+
"epoch": 0.8586543419720785,
|
| 19677 |
+
"grad_norm": 0.154296875,
|
| 19678 |
+
"learning_rate": 5.064472867826425e-06,
|
| 19679 |
+
"loss": 1.928659200668335,
|
| 19680 |
+
"step": 5620
|
| 19681 |
+
},
|
| 19682 |
+
{
|
| 19683 |
+
"epoch": 0.858959912912282,
|
| 19684 |
+
"grad_norm": 0.1513671875,
|
| 19685 |
+
"learning_rate": 5.043017865401067e-06,
|
| 19686 |
+
"loss": 1.9260876178741455,
|
| 19687 |
+
"step": 5622
|
| 19688 |
+
},
|
| 19689 |
+
{
|
| 19690 |
+
"epoch": 0.8592654838524856,
|
| 19691 |
+
"grad_norm": 0.1630859375,
|
| 19692 |
+
"learning_rate": 5.021605991393996e-06,
|
| 19693 |
+
"loss": 1.9572083950042725,
|
| 19694 |
+
"step": 5624
|
| 19695 |
+
},
|
| 19696 |
+
{
|
| 19697 |
+
"epoch": 0.8595710547926892,
|
| 19698 |
+
"grad_norm": 0.150390625,
|
| 19699 |
+
"learning_rate": 5.00023726634618e-06,
|
| 19700 |
+
"loss": 1.9245845079421997,
|
| 19701 |
+
"step": 5626
|
| 19702 |
+
},
|
| 19703 |
+
{
|
| 19704 |
+
"epoch": 0.8598766257328928,
|
| 19705 |
+
"grad_norm": 0.1640625,
|
| 19706 |
+
"learning_rate": 4.978911710757206e-06,
|
| 19707 |
+
"loss": 1.9399700164794922,
|
| 19708 |
+
"step": 5628
|
| 19709 |
+
},
|
| 19710 |
+
{
|
| 19711 |
+
"epoch": 0.8601821966730964,
|
| 19712 |
+
"grad_norm": 0.1630859375,
|
| 19713 |
+
"learning_rate": 4.957629345085241e-06,
|
| 19714 |
+
"loss": 1.94962739944458,
|
| 19715 |
+
"step": 5630
|
| 19716 |
+
},
|
| 19717 |
+
{
|
| 19718 |
+
"epoch": 0.8604877676132999,
|
| 19719 |
+
"grad_norm": 0.1611328125,
|
| 19720 |
+
"learning_rate": 4.936390189747003e-06,
|
| 19721 |
+
"loss": 1.883622169494629,
|
| 19722 |
+
"step": 5632
|
| 19723 |
+
},
|
| 19724 |
+
{
|
| 19725 |
+
"epoch": 0.8607933385535036,
|
| 19726 |
+
"grad_norm": 0.154296875,
|
| 19727 |
+
"learning_rate": 4.915194265117801e-06,
|
| 19728 |
+
"loss": 1.9216220378875732,
|
| 19729 |
+
"step": 5634
|
| 19730 |
+
},
|
| 19731 |
+
{
|
| 19732 |
+
"epoch": 0.8610989094937072,
|
| 19733 |
+
"grad_norm": 0.1572265625,
|
| 19734 |
+
"learning_rate": 4.894041591531428e-06,
|
| 19735 |
+
"loss": 1.9240925312042236,
|
| 19736 |
+
"step": 5636
|
| 19737 |
+
},
|
| 19738 |
+
{
|
| 19739 |
+
"epoch": 0.8614044804339107,
|
| 19740 |
+
"grad_norm": 0.1552734375,
|
| 19741 |
+
"learning_rate": 4.872932189280205e-06,
|
| 19742 |
+
"loss": 1.9457688331604004,
|
| 19743 |
+
"step": 5638
|
| 19744 |
+
},
|
| 19745 |
+
{
|
| 19746 |
+
"epoch": 0.8617100513741143,
|
| 19747 |
+
"grad_norm": 0.17578125,
|
| 19748 |
+
"learning_rate": 4.851866078614936e-06,
|
| 19749 |
+
"loss": 1.9430060386657715,
|
| 19750 |
+
"step": 5640
|
| 19751 |
+
},
|
| 19752 |
+
{
|
| 19753 |
+
"epoch": 0.8620156223143179,
|
| 19754 |
+
"grad_norm": 0.158203125,
|
| 19755 |
+
"learning_rate": 4.8308432797449066e-06,
|
| 19756 |
+
"loss": 1.909024953842163,
|
| 19757 |
+
"step": 5642
|
| 19758 |
+
},
|
| 19759 |
+
{
|
| 19760 |
+
"epoch": 0.8623211932545215,
|
| 19761 |
+
"grad_norm": 0.16015625,
|
| 19762 |
+
"learning_rate": 4.809863812837828e-06,
|
| 19763 |
+
"loss": 1.9639408588409424,
|
| 19764 |
+
"step": 5644
|
| 19765 |
+
},
|
| 19766 |
+
{
|
| 19767 |
+
"epoch": 0.8626267641947251,
|
| 19768 |
+
"grad_norm": 0.15234375,
|
| 19769 |
+
"learning_rate": 4.788927698019862e-06,
|
| 19770 |
+
"loss": 1.9260194301605225,
|
| 19771 |
+
"step": 5646
|
| 19772 |
+
},
|
| 19773 |
+
{
|
| 19774 |
+
"epoch": 0.8629323351349286,
|
| 19775 |
+
"grad_norm": 0.1552734375,
|
| 19776 |
+
"learning_rate": 4.7680349553755776e-06,
|
| 19777 |
+
"loss": 1.919152021408081,
|
| 19778 |
+
"step": 5648
|
| 19779 |
+
},
|
| 19780 |
+
{
|
| 19781 |
+
"epoch": 0.8632379060751323,
|
| 19782 |
+
"grad_norm": 0.1572265625,
|
| 19783 |
+
"learning_rate": 4.747185604947918e-06,
|
| 19784 |
+
"loss": 1.9370826482772827,
|
| 19785 |
+
"step": 5650
|
| 19786 |
+
},
|
| 19787 |
+
{
|
| 19788 |
+
"epoch": 0.8635434770153358,
|
| 19789 |
+
"grad_norm": 0.1513671875,
|
| 19790 |
+
"learning_rate": 4.726379666738234e-06,
|
| 19791 |
+
"loss": 1.9106435775756836,
|
| 19792 |
+
"step": 5652
|
| 19793 |
+
},
|
| 19794 |
+
{
|
| 19795 |
+
"epoch": 0.8638490479555394,
|
| 19796 |
+
"grad_norm": 0.1572265625,
|
| 19797 |
+
"learning_rate": 4.705617160706221e-06,
|
| 19798 |
+
"loss": 1.9070804119110107,
|
| 19799 |
+
"step": 5654
|
| 19800 |
+
},
|
| 19801 |
+
{
|
| 19802 |
+
"epoch": 0.864154618895743,
|
| 19803 |
+
"grad_norm": 0.1494140625,
|
| 19804 |
+
"learning_rate": 4.6848981067698695e-06,
|
| 19805 |
+
"loss": 1.8994380235671997,
|
| 19806 |
+
"step": 5656
|
| 19807 |
+
},
|
| 19808 |
+
{
|
| 19809 |
+
"epoch": 0.8644601898359466,
|
| 19810 |
+
"grad_norm": 0.1640625,
|
| 19811 |
+
"learning_rate": 4.6642225248055285e-06,
|
| 19812 |
+
"loss": 1.932055950164795,
|
| 19813 |
+
"step": 5658
|
| 19814 |
+
},
|
| 19815 |
+
{
|
| 19816 |
+
"epoch": 0.8647657607761502,
|
| 19817 |
+
"grad_norm": 0.1552734375,
|
| 19818 |
+
"learning_rate": 4.643590434647827e-06,
|
| 19819 |
+
"loss": 1.9364428520202637,
|
| 19820 |
+
"step": 5660
|
| 19821 |
+
},
|
| 19822 |
+
{
|
| 19823 |
+
"epoch": 0.8650713317163538,
|
| 19824 |
+
"grad_norm": 0.1552734375,
|
| 19825 |
+
"learning_rate": 4.623001856089676e-06,
|
| 19826 |
+
"loss": 1.8843646049499512,
|
| 19827 |
+
"step": 5662
|
| 19828 |
+
},
|
| 19829 |
+
{
|
| 19830 |
+
"epoch": 0.8653769026565573,
|
| 19831 |
+
"grad_norm": 0.1572265625,
|
| 19832 |
+
"learning_rate": 4.602456808882233e-06,
|
| 19833 |
+
"loss": 1.9217307567596436,
|
| 19834 |
+
"step": 5664
|
| 19835 |
+
},
|
| 19836 |
+
{
|
| 19837 |
+
"epoch": 0.865682473596761,
|
| 19838 |
+
"grad_norm": 0.1689453125,
|
| 19839 |
+
"learning_rate": 4.581955312734915e-06,
|
| 19840 |
+
"loss": 1.925365924835205,
|
| 19841 |
+
"step": 5666
|
| 19842 |
+
},
|
| 19843 |
+
{
|
| 19844 |
+
"epoch": 0.8659880445369645,
|
| 19845 |
+
"grad_norm": 0.1591796875,
|
| 19846 |
+
"learning_rate": 4.561497387315339e-06,
|
| 19847 |
+
"loss": 1.9003105163574219,
|
| 19848 |
+
"step": 5668
|
| 19849 |
+
},
|
| 19850 |
+
{
|
| 19851 |
+
"epoch": 0.8662936154771681,
|
| 19852 |
+
"grad_norm": 0.1513671875,
|
| 19853 |
+
"learning_rate": 4.54108305224934e-06,
|
| 19854 |
+
"loss": 1.9311163425445557,
|
| 19855 |
+
"step": 5670
|
| 19856 |
+
},
|
| 19857 |
+
{
|
| 19858 |
+
"epoch": 0.8665991864173717,
|
| 19859 |
+
"grad_norm": 0.1669921875,
|
| 19860 |
+
"learning_rate": 4.520712327120918e-06,
|
| 19861 |
+
"loss": 1.9086508750915527,
|
| 19862 |
+
"step": 5672
|
| 19863 |
+
},
|
| 19864 |
+
{
|
| 19865 |
+
"epoch": 0.8669047573575753,
|
| 19866 |
+
"grad_norm": 0.1484375,
|
| 19867 |
+
"learning_rate": 4.5003852314722535e-06,
|
| 19868 |
+
"loss": 1.918457269668579,
|
| 19869 |
+
"step": 5674
|
| 19870 |
+
},
|
| 19871 |
+
{
|
| 19872 |
+
"epoch": 0.8672103282977789,
|
| 19873 |
+
"grad_norm": 0.1630859375,
|
| 19874 |
+
"learning_rate": 4.480101784803669e-06,
|
| 19875 |
+
"loss": 1.9615026712417603,
|
| 19876 |
+
"step": 5676
|
| 19877 |
+
},
|
| 19878 |
+
{
|
| 19879 |
+
"epoch": 0.8675158992379824,
|
| 19880 |
+
"grad_norm": 0.1494140625,
|
| 19881 |
+
"learning_rate": 4.4598620065736004e-06,
|
| 19882 |
+
"loss": 1.9189040660858154,
|
| 19883 |
+
"step": 5678
|
| 19884 |
+
},
|
| 19885 |
+
{
|
| 19886 |
+
"epoch": 0.867821470178186,
|
| 19887 |
+
"grad_norm": 0.15625,
|
| 19888 |
+
"learning_rate": 4.439665916198615e-06,
|
| 19889 |
+
"loss": 1.9428104162216187,
|
| 19890 |
+
"step": 5680
|
| 19891 |
+
},
|
| 19892 |
+
{
|
| 19893 |
+
"epoch": 0.8681270411183897,
|
| 19894 |
+
"grad_norm": 0.1513671875,
|
| 19895 |
+
"learning_rate": 4.419513533053337e-06,
|
| 19896 |
+
"loss": 1.8929343223571777,
|
| 19897 |
+
"step": 5682
|
| 19898 |
+
},
|
| 19899 |
+
{
|
| 19900 |
+
"epoch": 0.8684326120585932,
|
| 19901 |
+
"grad_norm": 0.158203125,
|
| 19902 |
+
"learning_rate": 4.399404876470475e-06,
|
| 19903 |
+
"loss": 1.9404113292694092,
|
| 19904 |
+
"step": 5684
|
| 19905 |
+
},
|
| 19906 |
+
{
|
| 19907 |
+
"epoch": 0.8687381829987968,
|
| 19908 |
+
"grad_norm": 0.15625,
|
| 19909 |
+
"learning_rate": 4.379339965740814e-06,
|
| 19910 |
+
"loss": 1.9303513765335083,
|
| 19911 |
+
"step": 5686
|
| 19912 |
+
},
|
| 19913 |
+
{
|
| 19914 |
+
"epoch": 0.8690437539390004,
|
| 19915 |
+
"grad_norm": 0.1533203125,
|
| 19916 |
+
"learning_rate": 4.359318820113145e-06,
|
| 19917 |
+
"loss": 1.9417698383331299,
|
| 19918 |
+
"step": 5688
|
| 19919 |
+
},
|
| 19920 |
+
{
|
| 19921 |
+
"epoch": 0.869349324879204,
|
| 19922 |
+
"grad_norm": 0.1484375,
|
| 19923 |
+
"learning_rate": 4.339341458794283e-06,
|
| 19924 |
+
"loss": 1.934277057647705,
|
| 19925 |
+
"step": 5690
|
| 19926 |
+
},
|
| 19927 |
+
{
|
| 19928 |
+
"epoch": 0.8696548958194076,
|
| 19929 |
+
"grad_norm": 0.15625,
|
| 19930 |
+
"learning_rate": 4.319407900949035e-06,
|
| 19931 |
+
"loss": 1.9582271575927734,
|
| 19932 |
+
"step": 5692
|
| 19933 |
+
},
|
| 19934 |
+
{
|
| 19935 |
+
"epoch": 0.8699604667596111,
|
| 19936 |
+
"grad_norm": 0.154296875,
|
| 19937 |
+
"learning_rate": 4.299518165700178e-06,
|
| 19938 |
+
"loss": 1.8967641592025757,
|
| 19939 |
+
"step": 5694
|
| 19940 |
+
},
|
| 19941 |
+
{
|
| 19942 |
+
"epoch": 0.8702660376998147,
|
| 19943 |
+
"grad_norm": 0.15234375,
|
| 19944 |
+
"learning_rate": 4.279672272128471e-06,
|
| 19945 |
+
"loss": 1.9236761331558228,
|
| 19946 |
+
"step": 5696
|
| 19947 |
+
},
|
| 19948 |
+
{
|
| 19949 |
+
"epoch": 0.8705716086400184,
|
| 19950 |
+
"grad_norm": 0.15234375,
|
| 19951 |
+
"learning_rate": 4.259870239272601e-06,
|
| 19952 |
+
"loss": 1.9345602989196777,
|
| 19953 |
+
"step": 5698
|
| 19954 |
+
},
|
| 19955 |
+
{
|
| 19956 |
+
"epoch": 0.8708771795802219,
|
| 19957 |
+
"grad_norm": 0.1591796875,
|
| 19958 |
+
"learning_rate": 4.240112086129167e-06,
|
| 19959 |
+
"loss": 1.987321376800537,
|
| 19960 |
+
"step": 5700
|
| 19961 |
+
},
|
| 19962 |
+
{
|
| 19963 |
+
"epoch": 0.8711827505204255,
|
| 19964 |
+
"grad_norm": 0.162109375,
|
| 19965 |
+
"learning_rate": 4.2203978316527115e-06,
|
| 19966 |
+
"loss": 1.9306111335754395,
|
| 19967 |
+
"step": 5702
|
| 19968 |
+
},
|
| 19969 |
+
{
|
| 19970 |
+
"epoch": 0.871488321460629,
|
| 19971 |
+
"grad_norm": 0.1552734375,
|
| 19972 |
+
"learning_rate": 4.200727494755635e-06,
|
| 19973 |
+
"loss": 1.9340063333511353,
|
| 19974 |
+
"step": 5704
|
| 19975 |
+
},
|
| 19976 |
+
{
|
| 19977 |
+
"epoch": 0.8717938924008327,
|
| 19978 |
+
"grad_norm": 0.1572265625,
|
| 19979 |
+
"learning_rate": 4.1811010943081875e-06,
|
| 19980 |
+
"loss": 1.9426398277282715,
|
| 19981 |
+
"step": 5706
|
| 19982 |
+
},
|
| 19983 |
+
{
|
| 19984 |
+
"epoch": 0.8720994633410363,
|
| 19985 |
+
"grad_norm": 0.154296875,
|
| 19986 |
+
"learning_rate": 4.161518649138507e-06,
|
| 19987 |
+
"loss": 1.8874531984329224,
|
| 19988 |
+
"step": 5708
|
| 19989 |
+
},
|
| 19990 |
+
{
|
| 19991 |
+
"epoch": 0.8724050342812398,
|
| 19992 |
+
"grad_norm": 0.1611328125,
|
| 19993 |
+
"learning_rate": 4.141980178032551e-06,
|
| 19994 |
+
"loss": 1.900639533996582,
|
| 19995 |
+
"step": 5710
|
| 19996 |
+
},
|
| 19997 |
+
{
|
| 19998 |
+
"epoch": 0.8727106052214434,
|
| 19999 |
+
"grad_norm": 0.158203125,
|
| 20000 |
+
"learning_rate": 4.122485699734085e-06,
|
| 20001 |
+
"loss": 1.9584507942199707,
|
| 20002 |
+
"step": 5712
|
| 20003 |
+
},
|
| 20004 |
+
{
|
| 20005 |
+
"epoch": 0.8730161761616471,
|
| 20006 |
+
"grad_norm": 0.1513671875,
|
| 20007 |
+
"learning_rate": 4.103035232944685e-06,
|
| 20008 |
+
"loss": 1.9127771854400635,
|
| 20009 |
+
"step": 5714
|
| 20010 |
+
},
|
| 20011 |
+
{
|
| 20012 |
+
"epoch": 0.8733217471018506,
|
| 20013 |
+
"grad_norm": 0.1630859375,
|
| 20014 |
+
"learning_rate": 4.083628796323685e-06,
|
| 20015 |
+
"loss": 1.9308061599731445,
|
| 20016 |
+
"step": 5716
|
| 20017 |
+
},
|
| 20018 |
+
{
|
| 20019 |
+
"epoch": 0.8736273180420542,
|
| 20020 |
+
"grad_norm": 0.1572265625,
|
| 20021 |
+
"learning_rate": 4.064266408488193e-06,
|
| 20022 |
+
"loss": 1.9214849472045898,
|
| 20023 |
+
"step": 5718
|
| 20024 |
+
},
|
| 20025 |
+
{
|
| 20026 |
+
"epoch": 0.8739328889822577,
|
| 20027 |
+
"grad_norm": 0.158203125,
|
| 20028 |
+
"learning_rate": 4.044948088013067e-06,
|
| 20029 |
+
"loss": 1.9081079959869385,
|
| 20030 |
+
"step": 5720
|
| 20031 |
+
},
|
| 20032 |
+
{
|
| 20033 |
+
"epoch": 0.8742384599224614,
|
| 20034 |
+
"grad_norm": 0.15234375,
|
| 20035 |
+
"learning_rate": 4.025673853430872e-06,
|
| 20036 |
+
"loss": 1.911156415939331,
|
| 20037 |
+
"step": 5722
|
| 20038 |
+
},
|
| 20039 |
+
{
|
| 20040 |
+
"epoch": 0.874544030862665,
|
| 20041 |
+
"grad_norm": 0.1669921875,
|
| 20042 |
+
"learning_rate": 4.006443723231895e-06,
|
| 20043 |
+
"loss": 1.9548486471176147,
|
| 20044 |
+
"step": 5724
|
| 20045 |
+
},
|
| 20046 |
+
{
|
| 20047 |
+
"epoch": 0.8748496018028685,
|
| 20048 |
+
"grad_norm": 0.1572265625,
|
| 20049 |
+
"learning_rate": 3.9872577158641065e-06,
|
| 20050 |
+
"loss": 1.9364920854568481,
|
| 20051 |
+
"step": 5726
|
| 20052 |
+
},
|
| 20053 |
+
{
|
| 20054 |
+
"epoch": 0.8751551727430721,
|
| 20055 |
+
"grad_norm": 0.1533203125,
|
| 20056 |
+
"learning_rate": 3.968115849733145e-06,
|
| 20057 |
+
"loss": 1.9458601474761963,
|
| 20058 |
+
"step": 5728
|
| 20059 |
+
},
|
| 20060 |
+
{
|
| 20061 |
+
"epoch": 0.8754607436832758,
|
| 20062 |
+
"grad_norm": 0.1494140625,
|
| 20063 |
+
"learning_rate": 3.949018143202321e-06,
|
| 20064 |
+
"loss": 1.9117388725280762,
|
| 20065 |
+
"step": 5730
|
| 20066 |
+
},
|
| 20067 |
+
{
|
| 20068 |
+
"epoch": 0.8757663146234793,
|
| 20069 |
+
"grad_norm": 0.150390625,
|
| 20070 |
+
"learning_rate": 3.929964614592546e-06,
|
| 20071 |
+
"loss": 1.921003818511963,
|
| 20072 |
+
"step": 5732
|
| 20073 |
+
},
|
| 20074 |
+
{
|
| 20075 |
+
"epoch": 0.8760718855636829,
|
| 20076 |
+
"grad_norm": 0.1455078125,
|
| 20077 |
+
"learning_rate": 3.910955282182377e-06,
|
| 20078 |
+
"loss": 1.9134628772735596,
|
| 20079 |
+
"step": 5734
|
| 20080 |
+
},
|
| 20081 |
+
{
|
| 20082 |
+
"epoch": 0.8763774565038864,
|
| 20083 |
+
"grad_norm": 0.15234375,
|
| 20084 |
+
"learning_rate": 3.891990164207982e-06,
|
| 20085 |
+
"loss": 1.919639229774475,
|
| 20086 |
+
"step": 5736
|
| 20087 |
+
},
|
| 20088 |
+
{
|
| 20089 |
+
"epoch": 0.8766830274440901,
|
| 20090 |
+
"grad_norm": 0.154296875,
|
| 20091 |
+
"learning_rate": 3.873069278863089e-06,
|
| 20092 |
+
"loss": 1.8986468315124512,
|
| 20093 |
+
"step": 5738
|
| 20094 |
+
},
|
| 20095 |
+
{
|
| 20096 |
+
"epoch": 0.8769885983842937,
|
| 20097 |
+
"grad_norm": 0.150390625,
|
| 20098 |
+
"learning_rate": 3.854192644299004e-06,
|
| 20099 |
+
"loss": 1.9229134321212769,
|
| 20100 |
+
"step": 5740
|
| 20101 |
+
},
|
| 20102 |
+
{
|
| 20103 |
+
"epoch": 0.8772941693244972,
|
| 20104 |
+
"grad_norm": 0.1533203125,
|
| 20105 |
+
"learning_rate": 3.835360278624594e-06,
|
| 20106 |
+
"loss": 1.880665898323059,
|
| 20107 |
+
"step": 5742
|
| 20108 |
+
},
|
| 20109 |
+
{
|
| 20110 |
+
"epoch": 0.8775997402647008,
|
| 20111 |
+
"grad_norm": 0.15234375,
|
| 20112 |
+
"learning_rate": 3.816572199906216e-06,
|
| 20113 |
+
"loss": 1.9181175231933594,
|
| 20114 |
+
"step": 5744
|
| 20115 |
+
},
|
| 20116 |
+
{
|
| 20117 |
+
"epoch": 0.8779053112049044,
|
| 20118 |
+
"grad_norm": 0.1533203125,
|
| 20119 |
+
"learning_rate": 3.7978284261677878e-06,
|
| 20120 |
+
"loss": 1.933004379272461,
|
| 20121 |
+
"step": 5746
|
| 20122 |
+
},
|
| 20123 |
+
{
|
| 20124 |
+
"epoch": 0.878210882145108,
|
| 20125 |
+
"grad_norm": 0.1572265625,
|
| 20126 |
+
"learning_rate": 3.7791289753906945e-06,
|
| 20127 |
+
"loss": 1.90108323097229,
|
| 20128 |
+
"step": 5748
|
| 20129 |
+
},
|
| 20130 |
+
{
|
| 20131 |
+
"epoch": 0.8785164530853116,
|
| 20132 |
+
"grad_norm": 0.154296875,
|
| 20133 |
+
"learning_rate": 3.7604738655138193e-06,
|
| 20134 |
+
"loss": 1.9382555484771729,
|
| 20135 |
+
"step": 5750
|
| 20136 |
+
},
|
| 20137 |
+
{
|
| 20138 |
+
"epoch": 0.8788220240255151,
|
| 20139 |
+
"grad_norm": 0.1611328125,
|
| 20140 |
+
"learning_rate": 3.7418631144335025e-06,
|
| 20141 |
+
"loss": 1.9013570547103882,
|
| 20142 |
+
"step": 5752
|
| 20143 |
+
},
|
| 20144 |
+
{
|
| 20145 |
+
"epoch": 0.8791275949657188,
|
| 20146 |
+
"grad_norm": 0.1494140625,
|
| 20147 |
+
"learning_rate": 3.72329674000354e-06,
|
| 20148 |
+
"loss": 1.9080922603607178,
|
| 20149 |
+
"step": 5754
|
| 20150 |
+
},
|
| 20151 |
+
{
|
| 20152 |
+
"epoch": 0.8794331659059224,
|
| 20153 |
+
"grad_norm": 0.150390625,
|
| 20154 |
+
"learning_rate": 3.704774760035118e-06,
|
| 20155 |
+
"loss": 1.9279974699020386,
|
| 20156 |
+
"step": 5756
|
| 20157 |
+
},
|
| 20158 |
+
{
|
| 20159 |
+
"epoch": 0.8797387368461259,
|
| 20160 |
+
"grad_norm": 0.154296875,
|
| 20161 |
+
"learning_rate": 3.6862971922968725e-06,
|
| 20162 |
+
"loss": 1.929750680923462,
|
| 20163 |
+
"step": 5758
|
| 20164 |
+
},
|
| 20165 |
+
{
|
| 20166 |
+
"epoch": 0.8800443077863295,
|
| 20167 |
+
"grad_norm": 0.1552734375,
|
| 20168 |
+
"learning_rate": 3.6678640545148244e-06,
|
| 20169 |
+
"loss": 1.9579010009765625,
|
| 20170 |
+
"step": 5760
|
| 20171 |
+
},
|
| 20172 |
+
{
|
| 20173 |
+
"epoch": 0.8803498787265331,
|
| 20174 |
+
"grad_norm": 0.158203125,
|
| 20175 |
+
"learning_rate": 3.649475364372368e-06,
|
| 20176 |
+
"loss": 1.986173391342163,
|
| 20177 |
+
"step": 5762
|
| 20178 |
+
},
|
| 20179 |
+
{
|
| 20180 |
+
"epoch": 0.8806554496667367,
|
| 20181 |
+
"grad_norm": 0.158203125,
|
| 20182 |
+
"learning_rate": 3.6311311395102576e-06,
|
| 20183 |
+
"loss": 1.9096217155456543,
|
| 20184 |
+
"step": 5764
|
| 20185 |
+
},
|
| 20186 |
+
{
|
| 20187 |
+
"epoch": 0.8809610206069403,
|
| 20188 |
+
"grad_norm": 0.150390625,
|
| 20189 |
+
"learning_rate": 3.612831397526589e-06,
|
| 20190 |
+
"loss": 1.9361560344696045,
|
| 20191 |
+
"step": 5766
|
| 20192 |
+
},
|
| 20193 |
+
{
|
| 20194 |
+
"epoch": 0.8812665915471438,
|
| 20195 |
+
"grad_norm": 0.15234375,
|
| 20196 |
+
"learning_rate": 3.594576155976792e-06,
|
| 20197 |
+
"loss": 1.9362998008728027,
|
| 20198 |
+
"step": 5768
|
| 20199 |
+
},
|
| 20200 |
+
{
|
| 20201 |
+
"epoch": 0.8815721624873475,
|
| 20202 |
+
"grad_norm": 0.1611328125,
|
| 20203 |
+
"learning_rate": 3.5763654323735963e-06,
|
| 20204 |
+
"loss": 1.9269673824310303,
|
| 20205 |
+
"step": 5770
|
| 20206 |
+
},
|
| 20207 |
+
{
|
| 20208 |
+
"epoch": 0.881877733427551,
|
| 20209 |
+
"grad_norm": 0.16015625,
|
| 20210 |
+
"learning_rate": 3.5581992441870273e-06,
|
| 20211 |
+
"loss": 1.9340938329696655,
|
| 20212 |
+
"step": 5772
|
| 20213 |
+
},
|
| 20214 |
+
{
|
| 20215 |
+
"epoch": 0.8821833043677546,
|
| 20216 |
+
"grad_norm": 0.1630859375,
|
| 20217 |
+
"learning_rate": 3.5400776088444e-06,
|
| 20218 |
+
"loss": 1.9949707984924316,
|
| 20219 |
+
"step": 5774
|
| 20220 |
+
},
|
| 20221 |
+
{
|
| 20222 |
+
"epoch": 0.8824888753079582,
|
| 20223 |
+
"grad_norm": 0.1494140625,
|
| 20224 |
+
"learning_rate": 3.522000543730264e-06,
|
| 20225 |
+
"loss": 1.8833447694778442,
|
| 20226 |
+
"step": 5776
|
| 20227 |
+
},
|
| 20228 |
+
{
|
| 20229 |
+
"epoch": 0.8827944462481618,
|
| 20230 |
+
"grad_norm": 0.1513671875,
|
| 20231 |
+
"learning_rate": 3.5039680661864305e-06,
|
| 20232 |
+
"loss": 1.9736084938049316,
|
| 20233 |
+
"step": 5778
|
| 20234 |
+
},
|
| 20235 |
+
{
|
| 20236 |
+
"epoch": 0.8831000171883654,
|
| 20237 |
+
"grad_norm": 0.15234375,
|
| 20238 |
+
"learning_rate": 3.4859801935119397e-06,
|
| 20239 |
+
"loss": 1.8819376230239868,
|
| 20240 |
+
"step": 5780
|
| 20241 |
+
},
|
| 20242 |
+
{
|
| 20243 |
+
"epoch": 0.883405588128569,
|
| 20244 |
+
"grad_norm": 0.1572265625,
|
| 20245 |
+
"learning_rate": 3.46803694296301e-06,
|
| 20246 |
+
"loss": 1.9628992080688477,
|
| 20247 |
+
"step": 5782
|
| 20248 |
+
},
|
| 20249 |
+
{
|
| 20250 |
+
"epoch": 0.8837111590687725,
|
| 20251 |
+
"grad_norm": 0.1474609375,
|
| 20252 |
+
"learning_rate": 3.4501383317530835e-06,
|
| 20253 |
+
"loss": 1.9647903442382812,
|
| 20254 |
+
"step": 5784
|
| 20255 |
+
},
|
| 20256 |
+
{
|
| 20257 |
+
"epoch": 0.8840167300089762,
|
| 20258 |
+
"grad_norm": 0.15625,
|
| 20259 |
+
"learning_rate": 3.43228437705278e-06,
|
| 20260 |
+
"loss": 1.930952548980713,
|
| 20261 |
+
"step": 5786
|
| 20262 |
+
},
|
| 20263 |
+
{
|
| 20264 |
+
"epoch": 0.8843223009491797,
|
| 20265 |
+
"grad_norm": 0.1533203125,
|
| 20266 |
+
"learning_rate": 3.414475095989861e-06,
|
| 20267 |
+
"loss": 1.9725368022918701,
|
| 20268 |
+
"step": 5788
|
| 20269 |
+
},
|
| 20270 |
+
{
|
| 20271 |
+
"epoch": 0.8846278718893833,
|
| 20272 |
+
"grad_norm": 0.1552734375,
|
| 20273 |
+
"learning_rate": 3.3967105056492477e-06,
|
| 20274 |
+
"loss": 1.929149866104126,
|
| 20275 |
+
"step": 5790
|
| 20276 |
+
},
|
| 20277 |
+
{
|
| 20278 |
+
"epoch": 0.8849334428295869,
|
| 20279 |
+
"grad_norm": 0.15234375,
|
| 20280 |
+
"learning_rate": 3.378990623072975e-06,
|
| 20281 |
+
"loss": 1.9438199996948242,
|
| 20282 |
+
"step": 5792
|
| 20283 |
+
},
|
| 20284 |
+
{
|
| 20285 |
+
"epoch": 0.8852390137697905,
|
| 20286 |
+
"grad_norm": 0.1640625,
|
| 20287 |
+
"learning_rate": 3.361315465260184e-06,
|
| 20288 |
+
"loss": 1.9255844354629517,
|
| 20289 |
+
"step": 5794
|
| 20290 |
+
},
|
| 20291 |
+
{
|
| 20292 |
+
"epoch": 0.8855445847099941,
|
| 20293 |
+
"grad_norm": 0.15625,
|
| 20294 |
+
"learning_rate": 3.343685049167128e-06,
|
| 20295 |
+
"loss": 1.911487102508545,
|
| 20296 |
+
"step": 5796
|
| 20297 |
+
},
|
| 20298 |
+
{
|
| 20299 |
+
"epoch": 0.8858501556501976,
|
| 20300 |
+
"grad_norm": 0.154296875,
|
| 20301 |
+
"learning_rate": 3.326099391707127e-06,
|
| 20302 |
+
"loss": 1.9725837707519531,
|
| 20303 |
+
"step": 5798
|
| 20304 |
+
},
|
| 20305 |
+
{
|
| 20306 |
+
"epoch": 0.8861557265904012,
|
| 20307 |
+
"grad_norm": 0.15625,
|
| 20308 |
+
"learning_rate": 3.308558509750559e-06,
|
| 20309 |
+
"loss": 1.9418776035308838,
|
| 20310 |
+
"step": 5800
|
| 20311 |
+
},
|
| 20312 |
+
{
|
| 20313 |
+
"epoch": 0.8864612975306049,
|
| 20314 |
+
"grad_norm": 0.15625,
|
| 20315 |
+
"learning_rate": 3.291062420124874e-06,
|
| 20316 |
+
"loss": 1.918705940246582,
|
| 20317 |
+
"step": 5802
|
| 20318 |
+
},
|
| 20319 |
+
{
|
| 20320 |
+
"epoch": 0.8867668684708084,
|
| 20321 |
+
"grad_norm": 0.162109375,
|
| 20322 |
+
"learning_rate": 3.2736111396145353e-06,
|
| 20323 |
+
"loss": 1.936877727508545,
|
| 20324 |
+
"step": 5804
|
| 20325 |
+
},
|
| 20326 |
+
{
|
| 20327 |
+
"epoch": 0.887072439411012,
|
| 20328 |
+
"grad_norm": 0.1611328125,
|
| 20329 |
+
"learning_rate": 3.2562046849609838e-06,
|
| 20330 |
+
"loss": 1.90072500705719,
|
| 20331 |
+
"step": 5806
|
| 20332 |
+
},
|
| 20333 |
+
{
|
| 20334 |
+
"epoch": 0.8873780103512156,
|
| 20335 |
+
"grad_norm": 0.1513671875,
|
| 20336 |
+
"learning_rate": 3.2388430728627185e-06,
|
| 20337 |
+
"loss": 1.9550862312316895,
|
| 20338 |
+
"step": 5808
|
| 20339 |
+
},
|
| 20340 |
+
{
|
| 20341 |
+
"epoch": 0.8876835812914192,
|
| 20342 |
+
"grad_norm": 0.1455078125,
|
| 20343 |
+
"learning_rate": 3.2215263199751766e-06,
|
| 20344 |
+
"loss": 1.9030277729034424,
|
| 20345 |
+
"step": 5810
|
| 20346 |
+
},
|
| 20347 |
+
{
|
| 20348 |
+
"epoch": 0.8879891522316228,
|
| 20349 |
+
"grad_norm": 0.1826171875,
|
| 20350 |
+
"learning_rate": 3.2042544429107867e-06,
|
| 20351 |
+
"loss": 1.975062608718872,
|
| 20352 |
+
"step": 5812
|
| 20353 |
+
},
|
| 20354 |
+
{
|
| 20355 |
+
"epoch": 0.8882947231718263,
|
| 20356 |
+
"grad_norm": 0.1533203125,
|
| 20357 |
+
"learning_rate": 3.187027458238906e-06,
|
| 20358 |
+
"loss": 1.9785717725753784,
|
| 20359 |
+
"step": 5814
|
| 20360 |
+
},
|
| 20361 |
+
{
|
| 20362 |
+
"epoch": 0.8886002941120299,
|
| 20363 |
+
"grad_norm": 0.1513671875,
|
| 20364 |
+
"learning_rate": 3.1698453824858422e-06,
|
| 20365 |
+
"loss": 1.9287816286087036,
|
| 20366 |
+
"step": 5816
|
| 20367 |
+
},
|
| 20368 |
+
{
|
| 20369 |
+
"epoch": 0.8889058650522336,
|
| 20370 |
+
"grad_norm": 0.158203125,
|
| 20371 |
+
"learning_rate": 3.15270823213481e-06,
|
| 20372 |
+
"loss": 1.9210256338119507,
|
| 20373 |
+
"step": 5818
|
| 20374 |
+
},
|
| 20375 |
+
{
|
| 20376 |
+
"epoch": 0.8892114359924371,
|
| 20377 |
+
"grad_norm": 0.1494140625,
|
| 20378 |
+
"learning_rate": 3.1356160236259314e-06,
|
| 20379 |
+
"loss": 1.9072009325027466,
|
| 20380 |
+
"step": 5820
|
| 20381 |
+
},
|
| 20382 |
+
{
|
| 20383 |
+
"epoch": 0.8895170069326407,
|
| 20384 |
+
"grad_norm": 0.1513671875,
|
| 20385 |
+
"learning_rate": 3.118568773356212e-06,
|
| 20386 |
+
"loss": 1.9628467559814453,
|
| 20387 |
+
"step": 5822
|
| 20388 |
+
},
|
| 20389 |
+
{
|
| 20390 |
+
"epoch": 0.8898225778728442,
|
| 20391 |
+
"grad_norm": 0.150390625,
|
| 20392 |
+
"learning_rate": 3.1015664976795254e-06,
|
| 20393 |
+
"loss": 1.947974681854248,
|
| 20394 |
+
"step": 5824
|
| 20395 |
+
},
|
| 20396 |
+
{
|
| 20397 |
+
"epoch": 0.8901281488130479,
|
| 20398 |
+
"grad_norm": 0.150390625,
|
| 20399 |
+
"learning_rate": 3.0846092129066086e-06,
|
| 20400 |
+
"loss": 1.9378952980041504,
|
| 20401 |
+
"step": 5826
|
| 20402 |
+
},
|
| 20403 |
+
{
|
| 20404 |
+
"epoch": 0.8904337197532515,
|
| 20405 |
+
"grad_norm": 0.1640625,
|
| 20406 |
+
"learning_rate": 3.0676969353050313e-06,
|
| 20407 |
+
"loss": 1.9494190216064453,
|
| 20408 |
+
"step": 5828
|
| 20409 |
+
},
|
| 20410 |
+
{
|
| 20411 |
+
"epoch": 0.890739290693455,
|
| 20412 |
+
"grad_norm": 0.1552734375,
|
| 20413 |
+
"learning_rate": 3.050829681099182e-06,
|
| 20414 |
+
"loss": 1.914715051651001,
|
| 20415 |
+
"step": 5830
|
| 20416 |
+
},
|
| 20417 |
+
{
|
| 20418 |
+
"epoch": 0.8910448616336586,
|
| 20419 |
+
"grad_norm": 0.1533203125,
|
| 20420 |
+
"learning_rate": 3.0340074664702734e-06,
|
| 20421 |
+
"loss": 1.9198564291000366,
|
| 20422 |
+
"step": 5832
|
| 20423 |
+
},
|
| 20424 |
+
{
|
| 20425 |
+
"epoch": 0.8913504325738623,
|
| 20426 |
+
"grad_norm": 0.1630859375,
|
| 20427 |
+
"learning_rate": 3.017230307556279e-06,
|
| 20428 |
+
"loss": 1.8492562770843506,
|
| 20429 |
+
"step": 5834
|
| 20430 |
+
},
|
| 20431 |
+
{
|
| 20432 |
+
"epoch": 0.8916560035140658,
|
| 20433 |
+
"grad_norm": 0.1591796875,
|
| 20434 |
+
"learning_rate": 3.0004982204519914e-06,
|
| 20435 |
+
"loss": 1.9057127237319946,
|
| 20436 |
+
"step": 5836
|
| 20437 |
+
},
|
| 20438 |
+
{
|
| 20439 |
+
"epoch": 0.8919615744542694,
|
| 20440 |
+
"grad_norm": 0.1552734375,
|
| 20441 |
+
"learning_rate": 2.983811221208932e-06,
|
| 20442 |
+
"loss": 1.9147027730941772,
|
| 20443 |
+
"step": 5838
|
| 20444 |
+
},
|
| 20445 |
+
{
|
| 20446 |
+
"epoch": 0.8922671453944729,
|
| 20447 |
+
"grad_norm": 0.1455078125,
|
| 20448 |
+
"learning_rate": 2.9671693258353784e-06,
|
| 20449 |
+
"loss": 1.910662293434143,
|
| 20450 |
+
"step": 5840
|
| 20451 |
+
},
|
| 20452 |
+
{
|
| 20453 |
+
"epoch": 0.8925727163346766,
|
| 20454 |
+
"grad_norm": 0.1630859375,
|
| 20455 |
+
"learning_rate": 2.9505725502963543e-06,
|
| 20456 |
+
"loss": 1.9301095008850098,
|
| 20457 |
+
"step": 5842
|
| 20458 |
+
},
|
| 20459 |
+
{
|
| 20460 |
+
"epoch": 0.8928782872748802,
|
| 20461 |
+
"grad_norm": 0.150390625,
|
| 20462 |
+
"learning_rate": 2.934020910513563e-06,
|
| 20463 |
+
"loss": 1.9186041355133057,
|
| 20464 |
+
"step": 5844
|
| 20465 |
+
},
|
| 20466 |
+
{
|
| 20467 |
+
"epoch": 0.8931838582150837,
|
| 20468 |
+
"grad_norm": 0.150390625,
|
| 20469 |
+
"learning_rate": 2.917514422365436e-06,
|
| 20470 |
+
"loss": 1.927135705947876,
|
| 20471 |
+
"step": 5846
|
| 20472 |
+
},
|
| 20473 |
+
{
|
| 20474 |
+
"epoch": 0.8934894291552873,
|
| 20475 |
+
"grad_norm": 0.1591796875,
|
| 20476 |
+
"learning_rate": 2.90105310168709e-06,
|
| 20477 |
+
"loss": 1.9148643016815186,
|
| 20478 |
+
"step": 5848
|
| 20479 |
+
},
|
| 20480 |
+
{
|
| 20481 |
+
"epoch": 0.893795000095491,
|
| 20482 |
+
"grad_norm": 0.1484375,
|
| 20483 |
+
"learning_rate": 2.884636964270293e-06,
|
| 20484 |
+
"loss": 1.9043611288070679,
|
| 20485 |
+
"step": 5850
|
| 20486 |
+
},
|
| 20487 |
+
{
|
| 20488 |
+
"epoch": 0.8941005710356945,
|
| 20489 |
+
"grad_norm": 0.1572265625,
|
| 20490 |
+
"learning_rate": 2.8682660258634807e-06,
|
| 20491 |
+
"loss": 1.898861050605774,
|
| 20492 |
+
"step": 5852
|
| 20493 |
+
},
|
| 20494 |
+
{
|
| 20495 |
+
"epoch": 0.8944061419758981,
|
| 20496 |
+
"grad_norm": 0.16015625,
|
| 20497 |
+
"learning_rate": 2.8519403021717406e-06,
|
| 20498 |
+
"loss": 1.9677066802978516,
|
| 20499 |
+
"step": 5854
|
| 20500 |
+
},
|
| 20501 |
+
{
|
| 20502 |
+
"epoch": 0.8947117129161016,
|
| 20503 |
+
"grad_norm": 0.154296875,
|
| 20504 |
+
"learning_rate": 2.8356598088567553e-06,
|
| 20505 |
+
"loss": 1.9331365823745728,
|
| 20506 |
+
"step": 5856
|
| 20507 |
+
},
|
| 20508 |
+
{
|
| 20509 |
+
"epoch": 0.8950172838563053,
|
| 20510 |
+
"grad_norm": 0.154296875,
|
| 20511 |
+
"learning_rate": 2.819424561536832e-06,
|
| 20512 |
+
"loss": 1.9013080596923828,
|
| 20513 |
+
"step": 5858
|
| 20514 |
+
},
|
| 20515 |
+
{
|
| 20516 |
+
"epoch": 0.8953228547965089,
|
| 20517 |
+
"grad_norm": 0.1533203125,
|
| 20518 |
+
"learning_rate": 2.8032345757868727e-06,
|
| 20519 |
+
"loss": 1.914252519607544,
|
| 20520 |
+
"step": 5860
|
| 20521 |
+
},
|
| 20522 |
+
{
|
| 20523 |
+
"epoch": 0.8956284257367124,
|
| 20524 |
+
"grad_norm": 0.166015625,
|
| 20525 |
+
"learning_rate": 2.787089867138365e-06,
|
| 20526 |
+
"loss": 1.8945543766021729,
|
| 20527 |
+
"step": 5862
|
| 20528 |
+
},
|
| 20529 |
+
{
|
| 20530 |
+
"epoch": 0.895933996676916,
|
| 20531 |
+
"grad_norm": 0.1591796875,
|
| 20532 |
+
"learning_rate": 2.7709904510793416e-06,
|
| 20533 |
+
"loss": 1.9115732908248901,
|
| 20534 |
+
"step": 5864
|
| 20535 |
+
},
|
| 20536 |
+
{
|
| 20537 |
+
"epoch": 0.8962395676171196,
|
| 20538 |
+
"grad_norm": 0.1474609375,
|
| 20539 |
+
"learning_rate": 2.754936343054404e-06,
|
| 20540 |
+
"loss": 1.9698188304901123,
|
| 20541 |
+
"step": 5866
|
| 20542 |
+
},
|
| 20543 |
+
{
|
| 20544 |
+
"epoch": 0.8965451385573232,
|
| 20545 |
+
"grad_norm": 0.16015625,
|
| 20546 |
+
"learning_rate": 2.7389275584646822e-06,
|
| 20547 |
+
"loss": 1.9305498600006104,
|
| 20548 |
+
"step": 5868
|
| 20549 |
+
},
|
| 20550 |
+
{
|
| 20551 |
+
"epoch": 0.8968507094975268,
|
| 20552 |
+
"grad_norm": 0.15625,
|
| 20553 |
+
"learning_rate": 2.7229641126678197e-06,
|
| 20554 |
+
"loss": 1.9752240180969238,
|
| 20555 |
+
"step": 5870
|
| 20556 |
+
},
|
| 20557 |
+
{
|
| 20558 |
+
"epoch": 0.8971562804377303,
|
| 20559 |
+
"grad_norm": 0.1552734375,
|
| 20560 |
+
"learning_rate": 2.7070460209779768e-06,
|
| 20561 |
+
"loss": 1.9207557439804077,
|
| 20562 |
+
"step": 5872
|
| 20563 |
+
},
|
| 20564 |
+
{
|
| 20565 |
+
"epoch": 0.897461851377934,
|
| 20566 |
+
"grad_norm": 0.150390625,
|
| 20567 |
+
"learning_rate": 2.6911732986657947e-06,
|
| 20568 |
+
"loss": 1.9918582439422607,
|
| 20569 |
+
"step": 5874
|
| 20570 |
+
},
|
| 20571 |
+
{
|
| 20572 |
+
"epoch": 0.8977674223181376,
|
| 20573 |
+
"grad_norm": 0.1591796875,
|
| 20574 |
+
"learning_rate": 2.6753459609583973e-06,
|
| 20575 |
+
"loss": 1.8950719833374023,
|
| 20576 |
+
"step": 5876
|
| 20577 |
+
},
|
| 20578 |
+
{
|
| 20579 |
+
"epoch": 0.8980729932583411,
|
| 20580 |
+
"grad_norm": 0.15625,
|
| 20581 |
+
"learning_rate": 2.659564023039368e-06,
|
| 20582 |
+
"loss": 1.9712969064712524,
|
| 20583 |
+
"step": 5878
|
| 20584 |
+
},
|
| 20585 |
+
{
|
| 20586 |
+
"epoch": 0.8983785641985447,
|
| 20587 |
+
"grad_norm": 0.154296875,
|
| 20588 |
+
"learning_rate": 2.6438275000487288e-06,
|
| 20589 |
+
"loss": 1.9380093812942505,
|
| 20590 |
+
"step": 5880
|
| 20591 |
+
},
|
| 20592 |
+
{
|
| 20593 |
+
"epoch": 0.8986841351387483,
|
| 20594 |
+
"grad_norm": 0.1533203125,
|
| 20595 |
+
"learning_rate": 2.628136407082954e-06,
|
| 20596 |
+
"loss": 1.9350781440734863,
|
| 20597 |
+
"step": 5882
|
| 20598 |
+
},
|
| 20599 |
+
{
|
| 20600 |
+
"epoch": 0.8989897060789519,
|
| 20601 |
+
"grad_norm": 0.1630859375,
|
| 20602 |
+
"learning_rate": 2.6124907591949023e-06,
|
| 20603 |
+
"loss": 1.9404035806655884,
|
| 20604 |
+
"step": 5884
|
| 20605 |
+
},
|
| 20606 |
+
{
|
| 20607 |
+
"epoch": 0.8992952770191555,
|
| 20608 |
+
"grad_norm": 0.1494140625,
|
| 20609 |
+
"learning_rate": 2.5968905713938727e-06,
|
| 20610 |
+
"loss": 1.9350078105926514,
|
| 20611 |
+
"step": 5886
|
| 20612 |
+
},
|
| 20613 |
+
{
|
| 20614 |
+
"epoch": 0.899600847959359,
|
| 20615 |
+
"grad_norm": 0.1474609375,
|
| 20616 |
+
"learning_rate": 2.581335858645534e-06,
|
| 20617 |
+
"loss": 1.95409095287323,
|
| 20618 |
+
"step": 5888
|
| 20619 |
+
},
|
| 20620 |
+
{
|
| 20621 |
+
"epoch": 0.8999064188995627,
|
| 20622 |
+
"grad_norm": 0.150390625,
|
| 20623 |
+
"learning_rate": 2.5658266358719317e-06,
|
| 20624 |
+
"loss": 1.9507861137390137,
|
| 20625 |
+
"step": 5890
|
| 20626 |
+
},
|
| 20627 |
+
{
|
| 20628 |
+
"epoch": 0.9002119898397662,
|
| 20629 |
+
"grad_norm": 0.15625,
|
| 20630 |
+
"learning_rate": 2.550362917951471e-06,
|
| 20631 |
+
"loss": 1.9552593231201172,
|
| 20632 |
+
"step": 5892
|
| 20633 |
+
},
|
| 20634 |
+
{
|
| 20635 |
+
"epoch": 0.9005175607799698,
|
| 20636 |
+
"grad_norm": 0.1513671875,
|
| 20637 |
+
"learning_rate": 2.5349447197189126e-06,
|
| 20638 |
+
"loss": 1.889303207397461,
|
| 20639 |
+
"step": 5894
|
| 20640 |
}
|
| 20641 |
],
|
| 20642 |
"logging_steps": 2,
|
|
|
|
| 20656 |
"attributes": {}
|
| 20657 |
}
|
| 20658 |
},
|
| 20659 |
+
"total_flos": 2.7245697169736335e+18,
|
| 20660 |
"train_batch_size": 4,
|
| 20661 |
"trial_name": null,
|
| 20662 |
"trial_params": null
|