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 5240, 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:aa1a687f4e9722c5253df1fa03ba0789418e75825bd275c9abca0a9cc181f89a
|
| 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 sha256:711cbb739988679b97c0a2bebdefb1b75c7583d991dddeccfcea552635a27288
|
| 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 sha256:589a9274e4b657bba5aea1ba0fcdb2f281d8346b7bc9fca08b0a12d2beacb29b
|
| 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,
|
|
@@ -16052,6 +16052,2302 @@
|
|
| 16052 |
"learning_rate": 2.137859449657027e-05,
|
| 16053 |
"loss": 1.968224048614502,
|
| 16054 |
"step": 4584
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16055 |
}
|
| 16056 |
],
|
| 16057 |
"logging_steps": 2,
|
|
@@ -16071,7 +18367,7 @@
|
|
| 16071 |
"attributes": {}
|
| 16072 |
}
|
| 16073 |
},
|
| 16074 |
-
"total_flos": 2.
|
| 16075 |
"train_batch_size": 4,
|
| 16076 |
"trial_name": null,
|
| 16077 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8005958633333969,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16052 |
"learning_rate": 2.137859449657027e-05,
|
| 16053 |
"loss": 1.968224048614502,
|
| 16054 |
"step": 4584
|
| 16055 |
+
},
|
| 16056 |
+
{
|
| 16057 |
+
"epoch": 0.7006741658868242,
|
| 16058 |
+
"grad_norm": 0.15234375,
|
| 16059 |
+
"learning_rate": 2.1338452903021755e-05,
|
| 16060 |
+
"loss": 1.8755196332931519,
|
| 16061 |
+
"step": 4586
|
| 16062 |
+
},
|
| 16063 |
+
{
|
| 16064 |
+
"epoch": 0.7009797368270277,
|
| 16065 |
+
"grad_norm": 0.154296875,
|
| 16066 |
+
"learning_rate": 2.129833880525105e-05,
|
| 16067 |
+
"loss": 1.9695606231689453,
|
| 16068 |
+
"step": 4588
|
| 16069 |
+
},
|
| 16070 |
+
{
|
| 16071 |
+
"epoch": 0.7012853077672313,
|
| 16072 |
+
"grad_norm": 0.15625,
|
| 16073 |
+
"learning_rate": 2.1258252241740674e-05,
|
| 16074 |
+
"loss": 1.9371024370193481,
|
| 16075 |
+
"step": 4590
|
| 16076 |
+
},
|
| 16077 |
+
{
|
| 16078 |
+
"epoch": 0.701590878707435,
|
| 16079 |
+
"grad_norm": 0.1591796875,
|
| 16080 |
+
"learning_rate": 2.1218193250946694e-05,
|
| 16081 |
+
"loss": 1.8908581733703613,
|
| 16082 |
+
"step": 4592
|
| 16083 |
+
},
|
| 16084 |
+
{
|
| 16085 |
+
"epoch": 0.7018964496476385,
|
| 16086 |
+
"grad_norm": 0.1513671875,
|
| 16087 |
+
"learning_rate": 2.1178161871298794e-05,
|
| 16088 |
+
"loss": 1.9395697116851807,
|
| 16089 |
+
"step": 4594
|
| 16090 |
+
},
|
| 16091 |
+
{
|
| 16092 |
+
"epoch": 0.7022020205878421,
|
| 16093 |
+
"grad_norm": 0.154296875,
|
| 16094 |
+
"learning_rate": 2.1138158141200144e-05,
|
| 16095 |
+
"loss": 1.9223661422729492,
|
| 16096 |
+
"step": 4596
|
| 16097 |
+
},
|
| 16098 |
+
{
|
| 16099 |
+
"epoch": 0.7025075915280456,
|
| 16100 |
+
"grad_norm": 0.1591796875,
|
| 16101 |
+
"learning_rate": 2.109818209902733e-05,
|
| 16102 |
+
"loss": 1.8914926052093506,
|
| 16103 |
+
"step": 4598
|
| 16104 |
+
},
|
| 16105 |
+
{
|
| 16106 |
+
"epoch": 0.7028131624682493,
|
| 16107 |
+
"grad_norm": 0.150390625,
|
| 16108 |
+
"learning_rate": 2.1058233783130442e-05,
|
| 16109 |
+
"loss": 1.9594392776489258,
|
| 16110 |
+
"step": 4600
|
| 16111 |
+
},
|
| 16112 |
+
{
|
| 16113 |
+
"epoch": 0.7031187334084529,
|
| 16114 |
+
"grad_norm": 0.1552734375,
|
| 16115 |
+
"learning_rate": 2.101831323183296e-05,
|
| 16116 |
+
"loss": 1.946835994720459,
|
| 16117 |
+
"step": 4602
|
| 16118 |
+
},
|
| 16119 |
+
{
|
| 16120 |
+
"epoch": 0.7034243043486564,
|
| 16121 |
+
"grad_norm": 0.1494140625,
|
| 16122 |
+
"learning_rate": 2.097842048343171e-05,
|
| 16123 |
+
"loss": 1.9439353942871094,
|
| 16124 |
+
"step": 4604
|
| 16125 |
+
},
|
| 16126 |
+
{
|
| 16127 |
+
"epoch": 0.70372987528886,
|
| 16128 |
+
"grad_norm": 0.1533203125,
|
| 16129 |
+
"learning_rate": 2.0938555576196866e-05,
|
| 16130 |
+
"loss": 1.921536922454834,
|
| 16131 |
+
"step": 4606
|
| 16132 |
+
},
|
| 16133 |
+
{
|
| 16134 |
+
"epoch": 0.7040354462290637,
|
| 16135 |
+
"grad_norm": 0.169921875,
|
| 16136 |
+
"learning_rate": 2.089871854837188e-05,
|
| 16137 |
+
"loss": 1.9454617500305176,
|
| 16138 |
+
"step": 4608
|
| 16139 |
+
},
|
| 16140 |
+
{
|
| 16141 |
+
"epoch": 0.7043410171692672,
|
| 16142 |
+
"grad_norm": 0.1611328125,
|
| 16143 |
+
"learning_rate": 2.085890943817347e-05,
|
| 16144 |
+
"loss": 1.964470386505127,
|
| 16145 |
+
"step": 4610
|
| 16146 |
+
},
|
| 16147 |
+
{
|
| 16148 |
+
"epoch": 0.7046465881094708,
|
| 16149 |
+
"grad_norm": 0.16015625,
|
| 16150 |
+
"learning_rate": 2.0819128283791557e-05,
|
| 16151 |
+
"loss": 1.8847994804382324,
|
| 16152 |
+
"step": 4612
|
| 16153 |
+
},
|
| 16154 |
+
{
|
| 16155 |
+
"epoch": 0.7049521590496743,
|
| 16156 |
+
"grad_norm": 0.15234375,
|
| 16157 |
+
"learning_rate": 2.0779375123389256e-05,
|
| 16158 |
+
"loss": 1.9382939338684082,
|
| 16159 |
+
"step": 4614
|
| 16160 |
+
},
|
| 16161 |
+
{
|
| 16162 |
+
"epoch": 0.705257729989878,
|
| 16163 |
+
"grad_norm": 0.16015625,
|
| 16164 |
+
"learning_rate": 2.0739649995102822e-05,
|
| 16165 |
+
"loss": 1.9522302150726318,
|
| 16166 |
+
"step": 4616
|
| 16167 |
+
},
|
| 16168 |
+
{
|
| 16169 |
+
"epoch": 0.7055633009300816,
|
| 16170 |
+
"grad_norm": 0.1552734375,
|
| 16171 |
+
"learning_rate": 2.069995293704161e-05,
|
| 16172 |
+
"loss": 1.955070972442627,
|
| 16173 |
+
"step": 4618
|
| 16174 |
+
},
|
| 16175 |
+
{
|
| 16176 |
+
"epoch": 0.7058688718702851,
|
| 16177 |
+
"grad_norm": 0.169921875,
|
| 16178 |
+
"learning_rate": 2.0660283987288064e-05,
|
| 16179 |
+
"loss": 1.9438831806182861,
|
| 16180 |
+
"step": 4620
|
| 16181 |
+
},
|
| 16182 |
+
{
|
| 16183 |
+
"epoch": 0.7061744428104887,
|
| 16184 |
+
"grad_norm": 0.1552734375,
|
| 16185 |
+
"learning_rate": 2.062064318389767e-05,
|
| 16186 |
+
"loss": 1.920861005783081,
|
| 16187 |
+
"step": 4622
|
| 16188 |
+
},
|
| 16189 |
+
{
|
| 16190 |
+
"epoch": 0.7064800137506924,
|
| 16191 |
+
"grad_norm": 0.1708984375,
|
| 16192 |
+
"learning_rate": 2.0581030564898856e-05,
|
| 16193 |
+
"loss": 1.8968591690063477,
|
| 16194 |
+
"step": 4624
|
| 16195 |
+
},
|
| 16196 |
+
{
|
| 16197 |
+
"epoch": 0.7067855846908959,
|
| 16198 |
+
"grad_norm": 0.1572265625,
|
| 16199 |
+
"learning_rate": 2.0541446168293055e-05,
|
| 16200 |
+
"loss": 1.9185283184051514,
|
| 16201 |
+
"step": 4626
|
| 16202 |
+
},
|
| 16203 |
+
{
|
| 16204 |
+
"epoch": 0.7070911556310995,
|
| 16205 |
+
"grad_norm": 0.146484375,
|
| 16206 |
+
"learning_rate": 2.0501890032054654e-05,
|
| 16207 |
+
"loss": 1.9276275634765625,
|
| 16208 |
+
"step": 4628
|
| 16209 |
+
},
|
| 16210 |
+
{
|
| 16211 |
+
"epoch": 0.707396726571303,
|
| 16212 |
+
"grad_norm": 0.1513671875,
|
| 16213 |
+
"learning_rate": 2.046236219413089e-05,
|
| 16214 |
+
"loss": 1.9223703145980835,
|
| 16215 |
+
"step": 4630
|
| 16216 |
+
},
|
| 16217 |
+
{
|
| 16218 |
+
"epoch": 0.7077022975115067,
|
| 16219 |
+
"grad_norm": 0.1533203125,
|
| 16220 |
+
"learning_rate": 2.0422862692441845e-05,
|
| 16221 |
+
"loss": 1.95781409740448,
|
| 16222 |
+
"step": 4632
|
| 16223 |
+
},
|
| 16224 |
+
{
|
| 16225 |
+
"epoch": 0.7080078684517103,
|
| 16226 |
+
"grad_norm": 0.1533203125,
|
| 16227 |
+
"learning_rate": 2.038339156488046e-05,
|
| 16228 |
+
"loss": 1.8905434608459473,
|
| 16229 |
+
"step": 4634
|
| 16230 |
+
},
|
| 16231 |
+
{
|
| 16232 |
+
"epoch": 0.7083134393919138,
|
| 16233 |
+
"grad_norm": 0.1572265625,
|
| 16234 |
+
"learning_rate": 2.0343948849312396e-05,
|
| 16235 |
+
"loss": 1.9605793952941895,
|
| 16236 |
+
"step": 4636
|
| 16237 |
+
},
|
| 16238 |
+
{
|
| 16239 |
+
"epoch": 0.7086190103321174,
|
| 16240 |
+
"grad_norm": 0.1533203125,
|
| 16241 |
+
"learning_rate": 2.0304534583576097e-05,
|
| 16242 |
+
"loss": 1.9730207920074463,
|
| 16243 |
+
"step": 4638
|
| 16244 |
+
},
|
| 16245 |
+
{
|
| 16246 |
+
"epoch": 0.708924581272321,
|
| 16247 |
+
"grad_norm": 0.146484375,
|
| 16248 |
+
"learning_rate": 2.026514880548271e-05,
|
| 16249 |
+
"loss": 1.9389474391937256,
|
| 16250 |
+
"step": 4640
|
| 16251 |
+
},
|
| 16252 |
+
{
|
| 16253 |
+
"epoch": 0.7092301522125246,
|
| 16254 |
+
"grad_norm": 0.15625,
|
| 16255 |
+
"learning_rate": 2.0225791552816037e-05,
|
| 16256 |
+
"loss": 1.915098786354065,
|
| 16257 |
+
"step": 4642
|
| 16258 |
+
},
|
| 16259 |
+
{
|
| 16260 |
+
"epoch": 0.7095357231527282,
|
| 16261 |
+
"grad_norm": 0.1767578125,
|
| 16262 |
+
"learning_rate": 2.0186462863332568e-05,
|
| 16263 |
+
"loss": 1.9179885387420654,
|
| 16264 |
+
"step": 4644
|
| 16265 |
+
},
|
| 16266 |
+
{
|
| 16267 |
+
"epoch": 0.7098412940929317,
|
| 16268 |
+
"grad_norm": 0.1572265625,
|
| 16269 |
+
"learning_rate": 2.014716277476134e-05,
|
| 16270 |
+
"loss": 1.8936024904251099,
|
| 16271 |
+
"step": 4646
|
| 16272 |
+
},
|
| 16273 |
+
{
|
| 16274 |
+
"epoch": 0.7101468650331354,
|
| 16275 |
+
"grad_norm": 0.1572265625,
|
| 16276 |
+
"learning_rate": 2.0107891324803935e-05,
|
| 16277 |
+
"loss": 1.9248602390289307,
|
| 16278 |
+
"step": 4648
|
| 16279 |
+
},
|
| 16280 |
+
{
|
| 16281 |
+
"epoch": 0.710452435973339,
|
| 16282 |
+
"grad_norm": 0.1552734375,
|
| 16283 |
+
"learning_rate": 2.0068648551134507e-05,
|
| 16284 |
+
"loss": 1.9408196210861206,
|
| 16285 |
+
"step": 4650
|
| 16286 |
+
},
|
| 16287 |
+
{
|
| 16288 |
+
"epoch": 0.7107580069135425,
|
| 16289 |
+
"grad_norm": 0.16015625,
|
| 16290 |
+
"learning_rate": 2.0029434491399684e-05,
|
| 16291 |
+
"loss": 1.9001014232635498,
|
| 16292 |
+
"step": 4652
|
| 16293 |
+
},
|
| 16294 |
+
{
|
| 16295 |
+
"epoch": 0.7110635778537461,
|
| 16296 |
+
"grad_norm": 0.1513671875,
|
| 16297 |
+
"learning_rate": 1.999024918321855e-05,
|
| 16298 |
+
"loss": 1.9563229084014893,
|
| 16299 |
+
"step": 4654
|
| 16300 |
+
},
|
| 16301 |
+
{
|
| 16302 |
+
"epoch": 0.7113691487939497,
|
| 16303 |
+
"grad_norm": 0.1533203125,
|
| 16304 |
+
"learning_rate": 1.9951092664182597e-05,
|
| 16305 |
+
"loss": 1.9204964637756348,
|
| 16306 |
+
"step": 4656
|
| 16307 |
+
},
|
| 16308 |
+
{
|
| 16309 |
+
"epoch": 0.7116747197341533,
|
| 16310 |
+
"grad_norm": 0.1533203125,
|
| 16311 |
+
"learning_rate": 1.9911964971855717e-05,
|
| 16312 |
+
"loss": 1.9163750410079956,
|
| 16313 |
+
"step": 4658
|
| 16314 |
+
},
|
| 16315 |
+
{
|
| 16316 |
+
"epoch": 0.7119802906743569,
|
| 16317 |
+
"grad_norm": 0.15234375,
|
| 16318 |
+
"learning_rate": 1.9872866143774127e-05,
|
| 16319 |
+
"loss": 2.001438856124878,
|
| 16320 |
+
"step": 4660
|
| 16321 |
+
},
|
| 16322 |
+
{
|
| 16323 |
+
"epoch": 0.7122858616145604,
|
| 16324 |
+
"grad_norm": 0.146484375,
|
| 16325 |
+
"learning_rate": 1.9833796217446367e-05,
|
| 16326 |
+
"loss": 1.9700798988342285,
|
| 16327 |
+
"step": 4662
|
| 16328 |
+
},
|
| 16329 |
+
{
|
| 16330 |
+
"epoch": 0.7125914325547641,
|
| 16331 |
+
"grad_norm": 0.1591796875,
|
| 16332 |
+
"learning_rate": 1.9794755230353245e-05,
|
| 16333 |
+
"loss": 1.9430890083312988,
|
| 16334 |
+
"step": 4664
|
| 16335 |
+
},
|
| 16336 |
+
{
|
| 16337 |
+
"epoch": 0.7128970034949677,
|
| 16338 |
+
"grad_norm": 0.1591796875,
|
| 16339 |
+
"learning_rate": 1.9755743219947814e-05,
|
| 16340 |
+
"loss": 1.9217801094055176,
|
| 16341 |
+
"step": 4666
|
| 16342 |
+
},
|
| 16343 |
+
{
|
| 16344 |
+
"epoch": 0.7132025744351712,
|
| 16345 |
+
"grad_norm": 0.16796875,
|
| 16346 |
+
"learning_rate": 1.9716760223655324e-05,
|
| 16347 |
+
"loss": 1.95479154586792,
|
| 16348 |
+
"step": 4668
|
| 16349 |
+
},
|
| 16350 |
+
{
|
| 16351 |
+
"epoch": 0.7135081453753748,
|
| 16352 |
+
"grad_norm": 0.1474609375,
|
| 16353 |
+
"learning_rate": 1.967780627887319e-05,
|
| 16354 |
+
"loss": 1.9301427602767944,
|
| 16355 |
+
"step": 4670
|
| 16356 |
+
},
|
| 16357 |
+
{
|
| 16358 |
+
"epoch": 0.7138137163155784,
|
| 16359 |
+
"grad_norm": 0.1552734375,
|
| 16360 |
+
"learning_rate": 1.963888142297097e-05,
|
| 16361 |
+
"loss": 1.9208242893218994,
|
| 16362 |
+
"step": 4672
|
| 16363 |
+
},
|
| 16364 |
+
{
|
| 16365 |
+
"epoch": 0.714119287255782,
|
| 16366 |
+
"grad_norm": 0.150390625,
|
| 16367 |
+
"learning_rate": 1.9599985693290278e-05,
|
| 16368 |
+
"loss": 1.9459141492843628,
|
| 16369 |
+
"step": 4674
|
| 16370 |
+
},
|
| 16371 |
+
{
|
| 16372 |
+
"epoch": 0.7144248581959856,
|
| 16373 |
+
"grad_norm": 0.1474609375,
|
| 16374 |
+
"learning_rate": 1.9561119127144812e-05,
|
| 16375 |
+
"loss": 1.962223768234253,
|
| 16376 |
+
"step": 4676
|
| 16377 |
+
},
|
| 16378 |
+
{
|
| 16379 |
+
"epoch": 0.7147304291361891,
|
| 16380 |
+
"grad_norm": 0.1591796875,
|
| 16381 |
+
"learning_rate": 1.952228176182032e-05,
|
| 16382 |
+
"loss": 1.924882173538208,
|
| 16383 |
+
"step": 4678
|
| 16384 |
+
},
|
| 16385 |
+
{
|
| 16386 |
+
"epoch": 0.7150360000763928,
|
| 16387 |
+
"grad_norm": 0.15625,
|
| 16388 |
+
"learning_rate": 1.9483473634574506e-05,
|
| 16389 |
+
"loss": 1.9689513444900513,
|
| 16390 |
+
"step": 4680
|
| 16391 |
+
},
|
| 16392 |
+
{
|
| 16393 |
+
"epoch": 0.7153415710165963,
|
| 16394 |
+
"grad_norm": 0.16015625,
|
| 16395 |
+
"learning_rate": 1.9444694782637017e-05,
|
| 16396 |
+
"loss": 1.9687175750732422,
|
| 16397 |
+
"step": 4682
|
| 16398 |
+
},
|
| 16399 |
+
{
|
| 16400 |
+
"epoch": 0.7156471419567999,
|
| 16401 |
+
"grad_norm": 0.1474609375,
|
| 16402 |
+
"learning_rate": 1.9405945243209454e-05,
|
| 16403 |
+
"loss": 1.9318571090698242,
|
| 16404 |
+
"step": 4684
|
| 16405 |
+
},
|
| 16406 |
+
{
|
| 16407 |
+
"epoch": 0.7159527128970035,
|
| 16408 |
+
"grad_norm": 0.150390625,
|
| 16409 |
+
"learning_rate": 1.9367225053465236e-05,
|
| 16410 |
+
"loss": 1.9433820247650146,
|
| 16411 |
+
"step": 4686
|
| 16412 |
+
},
|
| 16413 |
+
{
|
| 16414 |
+
"epoch": 0.7162582838372071,
|
| 16415 |
+
"grad_norm": 0.1484375,
|
| 16416 |
+
"learning_rate": 1.9328534250549672e-05,
|
| 16417 |
+
"loss": 1.9375088214874268,
|
| 16418 |
+
"step": 4688
|
| 16419 |
+
},
|
| 16420 |
+
{
|
| 16421 |
+
"epoch": 0.7165638547774107,
|
| 16422 |
+
"grad_norm": 0.1591796875,
|
| 16423 |
+
"learning_rate": 1.9289872871579884e-05,
|
| 16424 |
+
"loss": 1.9241113662719727,
|
| 16425 |
+
"step": 4690
|
| 16426 |
+
},
|
| 16427 |
+
{
|
| 16428 |
+
"epoch": 0.7168694257176143,
|
| 16429 |
+
"grad_norm": 0.162109375,
|
| 16430 |
+
"learning_rate": 1.9251240953644718e-05,
|
| 16431 |
+
"loss": 1.8833391666412354,
|
| 16432 |
+
"step": 4692
|
| 16433 |
+
},
|
| 16434 |
+
{
|
| 16435 |
+
"epoch": 0.7171749966578178,
|
| 16436 |
+
"grad_norm": 0.158203125,
|
| 16437 |
+
"learning_rate": 1.921263853380484e-05,
|
| 16438 |
+
"loss": 1.9201912879943848,
|
| 16439 |
+
"step": 4694
|
| 16440 |
+
},
|
| 16441 |
+
{
|
| 16442 |
+
"epoch": 0.7174805675980215,
|
| 16443 |
+
"grad_norm": 0.1513671875,
|
| 16444 |
+
"learning_rate": 1.917406564909256e-05,
|
| 16445 |
+
"loss": 1.9495917558670044,
|
| 16446 |
+
"step": 4696
|
| 16447 |
+
},
|
| 16448 |
+
{
|
| 16449 |
+
"epoch": 0.717786138538225,
|
| 16450 |
+
"grad_norm": 0.16015625,
|
| 16451 |
+
"learning_rate": 1.913552233651183e-05,
|
| 16452 |
+
"loss": 1.9588115215301514,
|
| 16453 |
+
"step": 4698
|
| 16454 |
+
},
|
| 16455 |
+
{
|
| 16456 |
+
"epoch": 0.7180917094784286,
|
| 16457 |
+
"grad_norm": 0.158203125,
|
| 16458 |
+
"learning_rate": 1.9097008633038288e-05,
|
| 16459 |
+
"loss": 1.9311401844024658,
|
| 16460 |
+
"step": 4700
|
| 16461 |
+
},
|
| 16462 |
+
{
|
| 16463 |
+
"epoch": 0.7183972804186322,
|
| 16464 |
+
"grad_norm": 0.1494140625,
|
| 16465 |
+
"learning_rate": 1.9058524575619142e-05,
|
| 16466 |
+
"loss": 1.9666945934295654,
|
| 16467 |
+
"step": 4702
|
| 16468 |
+
},
|
| 16469 |
+
{
|
| 16470 |
+
"epoch": 0.7187028513588358,
|
| 16471 |
+
"grad_norm": 0.1669921875,
|
| 16472 |
+
"learning_rate": 1.9020070201173163e-05,
|
| 16473 |
+
"loss": 1.9513300657272339,
|
| 16474 |
+
"step": 4704
|
| 16475 |
+
},
|
| 16476 |
+
{
|
| 16477 |
+
"epoch": 0.7190084222990394,
|
| 16478 |
+
"grad_norm": 0.15234375,
|
| 16479 |
+
"learning_rate": 1.8981645546590643e-05,
|
| 16480 |
+
"loss": 1.9117223024368286,
|
| 16481 |
+
"step": 4706
|
| 16482 |
+
},
|
| 16483 |
+
{
|
| 16484 |
+
"epoch": 0.7193139932392429,
|
| 16485 |
+
"grad_norm": 0.1513671875,
|
| 16486 |
+
"learning_rate": 1.8943250648733375e-05,
|
| 16487 |
+
"loss": 1.949718713760376,
|
| 16488 |
+
"step": 4708
|
| 16489 |
+
},
|
| 16490 |
+
{
|
| 16491 |
+
"epoch": 0.7196195641794465,
|
| 16492 |
+
"grad_norm": 0.15234375,
|
| 16493 |
+
"learning_rate": 1.8904885544434586e-05,
|
| 16494 |
+
"loss": 1.9251072406768799,
|
| 16495 |
+
"step": 4710
|
| 16496 |
+
},
|
| 16497 |
+
{
|
| 16498 |
+
"epoch": 0.7199251351196502,
|
| 16499 |
+
"grad_norm": 0.158203125,
|
| 16500 |
+
"learning_rate": 1.8866550270498938e-05,
|
| 16501 |
+
"loss": 1.8929214477539062,
|
| 16502 |
+
"step": 4712
|
| 16503 |
+
},
|
| 16504 |
+
{
|
| 16505 |
+
"epoch": 0.7202307060598537,
|
| 16506 |
+
"grad_norm": 0.1533203125,
|
| 16507 |
+
"learning_rate": 1.8828244863702475e-05,
|
| 16508 |
+
"loss": 1.9119584560394287,
|
| 16509 |
+
"step": 4714
|
| 16510 |
+
},
|
| 16511 |
+
{
|
| 16512 |
+
"epoch": 0.7205362770000573,
|
| 16513 |
+
"grad_norm": 0.15625,
|
| 16514 |
+
"learning_rate": 1.8789969360792576e-05,
|
| 16515 |
+
"loss": 1.9273262023925781,
|
| 16516 |
+
"step": 4716
|
| 16517 |
+
},
|
| 16518 |
+
{
|
| 16519 |
+
"epoch": 0.7208418479402608,
|
| 16520 |
+
"grad_norm": 0.15234375,
|
| 16521 |
+
"learning_rate": 1.8751723798487942e-05,
|
| 16522 |
+
"loss": 1.971761703491211,
|
| 16523 |
+
"step": 4718
|
| 16524 |
+
},
|
| 16525 |
+
{
|
| 16526 |
+
"epoch": 0.7211474188804645,
|
| 16527 |
+
"grad_norm": 0.1494140625,
|
| 16528 |
+
"learning_rate": 1.871350821347855e-05,
|
| 16529 |
+
"loss": 1.9287257194519043,
|
| 16530 |
+
"step": 4720
|
| 16531 |
+
},
|
| 16532 |
+
{
|
| 16533 |
+
"epoch": 0.7214529898206681,
|
| 16534 |
+
"grad_norm": 0.162109375,
|
| 16535 |
+
"learning_rate": 1.8675322642425617e-05,
|
| 16536 |
+
"loss": 1.9287736415863037,
|
| 16537 |
+
"step": 4722
|
| 16538 |
+
},
|
| 16539 |
+
{
|
| 16540 |
+
"epoch": 0.7217585607608716,
|
| 16541 |
+
"grad_norm": 0.1669921875,
|
| 16542 |
+
"learning_rate": 1.8637167121961592e-05,
|
| 16543 |
+
"loss": 1.9077949523925781,
|
| 16544 |
+
"step": 4724
|
| 16545 |
+
},
|
| 16546 |
+
{
|
| 16547 |
+
"epoch": 0.7220641317010752,
|
| 16548 |
+
"grad_norm": 0.162109375,
|
| 16549 |
+
"learning_rate": 1.8599041688690005e-05,
|
| 16550 |
+
"loss": 1.934358835220337,
|
| 16551 |
+
"step": 4726
|
| 16552 |
+
},
|
| 16553 |
+
{
|
| 16554 |
+
"epoch": 0.7223697026412789,
|
| 16555 |
+
"grad_norm": 0.146484375,
|
| 16556 |
+
"learning_rate": 1.8560946379185655e-05,
|
| 16557 |
+
"loss": 1.9641317129135132,
|
| 16558 |
+
"step": 4728
|
| 16559 |
+
},
|
| 16560 |
+
{
|
| 16561 |
+
"epoch": 0.7226752735814824,
|
| 16562 |
+
"grad_norm": 0.1552734375,
|
| 16563 |
+
"learning_rate": 1.8522881229994355e-05,
|
| 16564 |
+
"loss": 1.9045966863632202,
|
| 16565 |
+
"step": 4730
|
| 16566 |
+
},
|
| 16567 |
+
{
|
| 16568 |
+
"epoch": 0.722980844521686,
|
| 16569 |
+
"grad_norm": 0.15625,
|
| 16570 |
+
"learning_rate": 1.8484846277633004e-05,
|
| 16571 |
+
"loss": 1.9610586166381836,
|
| 16572 |
+
"step": 4732
|
| 16573 |
+
},
|
| 16574 |
+
{
|
| 16575 |
+
"epoch": 0.7232864154618895,
|
| 16576 |
+
"grad_norm": 0.1552734375,
|
| 16577 |
+
"learning_rate": 1.8446841558589538e-05,
|
| 16578 |
+
"loss": 1.9932210445404053,
|
| 16579 |
+
"step": 4734
|
| 16580 |
+
},
|
| 16581 |
+
{
|
| 16582 |
+
"epoch": 0.7235919864020932,
|
| 16583 |
+
"grad_norm": 0.16015625,
|
| 16584 |
+
"learning_rate": 1.840886710932291e-05,
|
| 16585 |
+
"loss": 1.8670823574066162,
|
| 16586 |
+
"step": 4736
|
| 16587 |
+
},
|
| 16588 |
+
{
|
| 16589 |
+
"epoch": 0.7238975573422968,
|
| 16590 |
+
"grad_norm": 0.1650390625,
|
| 16591 |
+
"learning_rate": 1.837092296626296e-05,
|
| 16592 |
+
"loss": 1.935203194618225,
|
| 16593 |
+
"step": 4738
|
| 16594 |
+
},
|
| 16595 |
+
{
|
| 16596 |
+
"epoch": 0.7242031282825003,
|
| 16597 |
+
"grad_norm": 0.1591796875,
|
| 16598 |
+
"learning_rate": 1.8333009165810528e-05,
|
| 16599 |
+
"loss": 1.9194544553756714,
|
| 16600 |
+
"step": 4740
|
| 16601 |
+
},
|
| 16602 |
+
{
|
| 16603 |
+
"epoch": 0.7245086992227039,
|
| 16604 |
+
"grad_norm": 0.1533203125,
|
| 16605 |
+
"learning_rate": 1.829512574433731e-05,
|
| 16606 |
+
"loss": 1.9469494819641113,
|
| 16607 |
+
"step": 4742
|
| 16608 |
+
},
|
| 16609 |
+
{
|
| 16610 |
+
"epoch": 0.7248142701629076,
|
| 16611 |
+
"grad_norm": 0.166015625,
|
| 16612 |
+
"learning_rate": 1.8257272738185906e-05,
|
| 16613 |
+
"loss": 1.9067566394805908,
|
| 16614 |
+
"step": 4744
|
| 16615 |
+
},
|
| 16616 |
+
{
|
| 16617 |
+
"epoch": 0.7251198411031111,
|
| 16618 |
+
"grad_norm": 0.1552734375,
|
| 16619 |
+
"learning_rate": 1.8219450183669696e-05,
|
| 16620 |
+
"loss": 1.9273923635482788,
|
| 16621 |
+
"step": 4746
|
| 16622 |
+
},
|
| 16623 |
+
{
|
| 16624 |
+
"epoch": 0.7254254120433147,
|
| 16625 |
+
"grad_norm": 0.1650390625,
|
| 16626 |
+
"learning_rate": 1.8181658117072826e-05,
|
| 16627 |
+
"loss": 1.973062515258789,
|
| 16628 |
+
"step": 4748
|
| 16629 |
+
},
|
| 16630 |
+
{
|
| 16631 |
+
"epoch": 0.7257309829835182,
|
| 16632 |
+
"grad_norm": 0.154296875,
|
| 16633 |
+
"learning_rate": 1.814389657465023e-05,
|
| 16634 |
+
"loss": 1.9222396612167358,
|
| 16635 |
+
"step": 4750
|
| 16636 |
+
},
|
| 16637 |
+
{
|
| 16638 |
+
"epoch": 0.7260365539237219,
|
| 16639 |
+
"grad_norm": 0.15234375,
|
| 16640 |
+
"learning_rate": 1.810616559262756e-05,
|
| 16641 |
+
"loss": 1.9485801458358765,
|
| 16642 |
+
"step": 4752
|
| 16643 |
+
},
|
| 16644 |
+
{
|
| 16645 |
+
"epoch": 0.7263421248639255,
|
| 16646 |
+
"grad_norm": 0.1474609375,
|
| 16647 |
+
"learning_rate": 1.8068465207201148e-05,
|
| 16648 |
+
"loss": 1.8959683179855347,
|
| 16649 |
+
"step": 4754
|
| 16650 |
+
},
|
| 16651 |
+
{
|
| 16652 |
+
"epoch": 0.726647695804129,
|
| 16653 |
+
"grad_norm": 0.1552734375,
|
| 16654 |
+
"learning_rate": 1.8030795454537947e-05,
|
| 16655 |
+
"loss": 1.908111333847046,
|
| 16656 |
+
"step": 4756
|
| 16657 |
+
},
|
| 16658 |
+
{
|
| 16659 |
+
"epoch": 0.7269532667443326,
|
| 16660 |
+
"grad_norm": 0.15625,
|
| 16661 |
+
"learning_rate": 1.799315637077556e-05,
|
| 16662 |
+
"loss": 1.9586628675460815,
|
| 16663 |
+
"step": 4758
|
| 16664 |
+
},
|
| 16665 |
+
{
|
| 16666 |
+
"epoch": 0.7272588376845363,
|
| 16667 |
+
"grad_norm": 0.1533203125,
|
| 16668 |
+
"learning_rate": 1.7955547992022148e-05,
|
| 16669 |
+
"loss": 1.9309020042419434,
|
| 16670 |
+
"step": 4760
|
| 16671 |
+
},
|
| 16672 |
+
{
|
| 16673 |
+
"epoch": 0.7275644086247398,
|
| 16674 |
+
"grad_norm": 0.146484375,
|
| 16675 |
+
"learning_rate": 1.791797035435642e-05,
|
| 16676 |
+
"loss": 1.9013597965240479,
|
| 16677 |
+
"step": 4762
|
| 16678 |
+
},
|
| 16679 |
+
{
|
| 16680 |
+
"epoch": 0.7278699795649434,
|
| 16681 |
+
"grad_norm": 0.15234375,
|
| 16682 |
+
"learning_rate": 1.7880423493827596e-05,
|
| 16683 |
+
"loss": 1.9387192726135254,
|
| 16684 |
+
"step": 4764
|
| 16685 |
+
},
|
| 16686 |
+
{
|
| 16687 |
+
"epoch": 0.7281755505051469,
|
| 16688 |
+
"grad_norm": 0.1572265625,
|
| 16689 |
+
"learning_rate": 1.784290744645537e-05,
|
| 16690 |
+
"loss": 1.9207229614257812,
|
| 16691 |
+
"step": 4766
|
| 16692 |
+
},
|
| 16693 |
+
{
|
| 16694 |
+
"epoch": 0.7284811214453506,
|
| 16695 |
+
"grad_norm": 0.1513671875,
|
| 16696 |
+
"learning_rate": 1.7805422248229874e-05,
|
| 16697 |
+
"loss": 1.9390525817871094,
|
| 16698 |
+
"step": 4768
|
| 16699 |
+
},
|
| 16700 |
+
{
|
| 16701 |
+
"epoch": 0.7287866923855542,
|
| 16702 |
+
"grad_norm": 0.166015625,
|
| 16703 |
+
"learning_rate": 1.7767967935111644e-05,
|
| 16704 |
+
"loss": 1.9819443225860596,
|
| 16705 |
+
"step": 4770
|
| 16706 |
+
},
|
| 16707 |
+
{
|
| 16708 |
+
"epoch": 0.7290922633257577,
|
| 16709 |
+
"grad_norm": 0.1513671875,
|
| 16710 |
+
"learning_rate": 1.7730544543031592e-05,
|
| 16711 |
+
"loss": 1.9220540523529053,
|
| 16712 |
+
"step": 4772
|
| 16713 |
+
},
|
| 16714 |
+
{
|
| 16715 |
+
"epoch": 0.7293978342659613,
|
| 16716 |
+
"grad_norm": 0.1591796875,
|
| 16717 |
+
"learning_rate": 1.769315210789099e-05,
|
| 16718 |
+
"loss": 1.9109694957733154,
|
| 16719 |
+
"step": 4774
|
| 16720 |
+
},
|
| 16721 |
+
{
|
| 16722 |
+
"epoch": 0.729703405206165,
|
| 16723 |
+
"grad_norm": 0.1552734375,
|
| 16724 |
+
"learning_rate": 1.7655790665561316e-05,
|
| 16725 |
+
"loss": 1.979938268661499,
|
| 16726 |
+
"step": 4776
|
| 16727 |
+
},
|
| 16728 |
+
{
|
| 16729 |
+
"epoch": 0.7300089761463685,
|
| 16730 |
+
"grad_norm": 0.158203125,
|
| 16731 |
+
"learning_rate": 1.7618460251884462e-05,
|
| 16732 |
+
"loss": 1.921796441078186,
|
| 16733 |
+
"step": 4778
|
| 16734 |
+
},
|
| 16735 |
+
{
|
| 16736 |
+
"epoch": 0.7303145470865721,
|
| 16737 |
+
"grad_norm": 0.154296875,
|
| 16738 |
+
"learning_rate": 1.758116090267244e-05,
|
| 16739 |
+
"loss": 1.9355378150939941,
|
| 16740 |
+
"step": 4780
|
| 16741 |
+
},
|
| 16742 |
+
{
|
| 16743 |
+
"epoch": 0.7306201180267756,
|
| 16744 |
+
"grad_norm": 0.15234375,
|
| 16745 |
+
"learning_rate": 1.7543892653707518e-05,
|
| 16746 |
+
"loss": 1.9606791734695435,
|
| 16747 |
+
"step": 4782
|
| 16748 |
+
},
|
| 16749 |
+
{
|
| 16750 |
+
"epoch": 0.7309256889669793,
|
| 16751 |
+
"grad_norm": 0.15234375,
|
| 16752 |
+
"learning_rate": 1.750665554074209e-05,
|
| 16753 |
+
"loss": 1.8958525657653809,
|
| 16754 |
+
"step": 4784
|
| 16755 |
+
},
|
| 16756 |
+
{
|
| 16757 |
+
"epoch": 0.7312312599071829,
|
| 16758 |
+
"grad_norm": 0.1474609375,
|
| 16759 |
+
"learning_rate": 1.7469449599498732e-05,
|
| 16760 |
+
"loss": 1.9194191694259644,
|
| 16761 |
+
"step": 4786
|
| 16762 |
+
},
|
| 16763 |
+
{
|
| 16764 |
+
"epoch": 0.7315368308473864,
|
| 16765 |
+
"grad_norm": 0.15234375,
|
| 16766 |
+
"learning_rate": 1.7432274865670045e-05,
|
| 16767 |
+
"loss": 1.934452772140503,
|
| 16768 |
+
"step": 4788
|
| 16769 |
+
},
|
| 16770 |
+
{
|
| 16771 |
+
"epoch": 0.73184240178759,
|
| 16772 |
+
"grad_norm": 0.15234375,
|
| 16773 |
+
"learning_rate": 1.7395131374918748e-05,
|
| 16774 |
+
"loss": 1.8939144611358643,
|
| 16775 |
+
"step": 4790
|
| 16776 |
+
},
|
| 16777 |
+
{
|
| 16778 |
+
"epoch": 0.7321479727277936,
|
| 16779 |
+
"grad_norm": 0.1494140625,
|
| 16780 |
+
"learning_rate": 1.7358019162877576e-05,
|
| 16781 |
+
"loss": 1.9336751699447632,
|
| 16782 |
+
"step": 4792
|
| 16783 |
+
},
|
| 16784 |
+
{
|
| 16785 |
+
"epoch": 0.7324535436679972,
|
| 16786 |
+
"grad_norm": 0.1552734375,
|
| 16787 |
+
"learning_rate": 1.7320938265149233e-05,
|
| 16788 |
+
"loss": 1.9245452880859375,
|
| 16789 |
+
"step": 4794
|
| 16790 |
+
},
|
| 16791 |
+
{
|
| 16792 |
+
"epoch": 0.7327591146082008,
|
| 16793 |
+
"grad_norm": 0.16015625,
|
| 16794 |
+
"learning_rate": 1.728388871730643e-05,
|
| 16795 |
+
"loss": 1.9232783317565918,
|
| 16796 |
+
"step": 4796
|
| 16797 |
+
},
|
| 16798 |
+
{
|
| 16799 |
+
"epoch": 0.7330646855484043,
|
| 16800 |
+
"grad_norm": 0.1533203125,
|
| 16801 |
+
"learning_rate": 1.7246870554891782e-05,
|
| 16802 |
+
"loss": 1.9245027303695679,
|
| 16803 |
+
"step": 4798
|
| 16804 |
+
},
|
| 16805 |
+
{
|
| 16806 |
+
"epoch": 0.733370256488608,
|
| 16807 |
+
"grad_norm": 0.1513671875,
|
| 16808 |
+
"learning_rate": 1.720988381341775e-05,
|
| 16809 |
+
"loss": 1.9550033807754517,
|
| 16810 |
+
"step": 4800
|
| 16811 |
+
},
|
| 16812 |
+
{
|
| 16813 |
+
"epoch": 0.7336758274288115,
|
| 16814 |
+
"grad_norm": 0.162109375,
|
| 16815 |
+
"learning_rate": 1.7172928528366704e-05,
|
| 16816 |
+
"loss": 1.9011597633361816,
|
| 16817 |
+
"step": 4802
|
| 16818 |
+
},
|
| 16819 |
+
{
|
| 16820 |
+
"epoch": 0.7339813983690151,
|
| 16821 |
+
"grad_norm": 0.150390625,
|
| 16822 |
+
"learning_rate": 1.7136004735190836e-05,
|
| 16823 |
+
"loss": 1.9456148147583008,
|
| 16824 |
+
"step": 4804
|
| 16825 |
+
},
|
| 16826 |
+
{
|
| 16827 |
+
"epoch": 0.7342869693092187,
|
| 16828 |
+
"grad_norm": 0.1533203125,
|
| 16829 |
+
"learning_rate": 1.7099112469312106e-05,
|
| 16830 |
+
"loss": 1.9340481758117676,
|
| 16831 |
+
"step": 4806
|
| 16832 |
+
},
|
| 16833 |
+
{
|
| 16834 |
+
"epoch": 0.7345925402494223,
|
| 16835 |
+
"grad_norm": 0.1484375,
|
| 16836 |
+
"learning_rate": 1.706225176612224e-05,
|
| 16837 |
+
"loss": 1.9359420537948608,
|
| 16838 |
+
"step": 4808
|
| 16839 |
+
},
|
| 16840 |
+
{
|
| 16841 |
+
"epoch": 0.7348981111896259,
|
| 16842 |
+
"grad_norm": 0.1533203125,
|
| 16843 |
+
"learning_rate": 1.702542266098267e-05,
|
| 16844 |
+
"loss": 1.9376999139785767,
|
| 16845 |
+
"step": 4810
|
| 16846 |
+
},
|
| 16847 |
+
{
|
| 16848 |
+
"epoch": 0.7352036821298294,
|
| 16849 |
+
"grad_norm": 0.158203125,
|
| 16850 |
+
"learning_rate": 1.698862518922455e-05,
|
| 16851 |
+
"loss": 1.972898006439209,
|
| 16852 |
+
"step": 4812
|
| 16853 |
+
},
|
| 16854 |
+
{
|
| 16855 |
+
"epoch": 0.735509253070033,
|
| 16856 |
+
"grad_norm": 0.1533203125,
|
| 16857 |
+
"learning_rate": 1.6951859386148643e-05,
|
| 16858 |
+
"loss": 1.900374174118042,
|
| 16859 |
+
"step": 4814
|
| 16860 |
+
},
|
| 16861 |
+
{
|
| 16862 |
+
"epoch": 0.7358148240102367,
|
| 16863 |
+
"grad_norm": 0.162109375,
|
| 16864 |
+
"learning_rate": 1.691512528702537e-05,
|
| 16865 |
+
"loss": 1.9102061986923218,
|
| 16866 |
+
"step": 4816
|
| 16867 |
+
},
|
| 16868 |
+
{
|
| 16869 |
+
"epoch": 0.7361203949504402,
|
| 16870 |
+
"grad_norm": 0.15625,
|
| 16871 |
+
"learning_rate": 1.6878422927094713e-05,
|
| 16872 |
+
"loss": 1.8930972814559937,
|
| 16873 |
+
"step": 4818
|
| 16874 |
+
},
|
| 16875 |
+
{
|
| 16876 |
+
"epoch": 0.7364259658906438,
|
| 16877 |
+
"grad_norm": 0.158203125,
|
| 16878 |
+
"learning_rate": 1.6841752341566213e-05,
|
| 16879 |
+
"loss": 1.9254446029663086,
|
| 16880 |
+
"step": 4820
|
| 16881 |
+
},
|
| 16882 |
+
{
|
| 16883 |
+
"epoch": 0.7367315368308474,
|
| 16884 |
+
"grad_norm": 0.1552734375,
|
| 16885 |
+
"learning_rate": 1.680511356561893e-05,
|
| 16886 |
+
"loss": 1.8980698585510254,
|
| 16887 |
+
"step": 4822
|
| 16888 |
+
},
|
| 16889 |
+
{
|
| 16890 |
+
"epoch": 0.737037107771051,
|
| 16891 |
+
"grad_norm": 0.15625,
|
| 16892 |
+
"learning_rate": 1.6768506634401426e-05,
|
| 16893 |
+
"loss": 1.917577862739563,
|
| 16894 |
+
"step": 4824
|
| 16895 |
+
},
|
| 16896 |
+
{
|
| 16897 |
+
"epoch": 0.7373426787112546,
|
| 16898 |
+
"grad_norm": 0.1552734375,
|
| 16899 |
+
"learning_rate": 1.6731931583031646e-05,
|
| 16900 |
+
"loss": 1.9219036102294922,
|
| 16901 |
+
"step": 4826
|
| 16902 |
+
},
|
| 16903 |
+
{
|
| 16904 |
+
"epoch": 0.7376482496514581,
|
| 16905 |
+
"grad_norm": 0.1650390625,
|
| 16906 |
+
"learning_rate": 1.6695388446597047e-05,
|
| 16907 |
+
"loss": 1.9290618896484375,
|
| 16908 |
+
"step": 4828
|
| 16909 |
+
},
|
| 16910 |
+
{
|
| 16911 |
+
"epoch": 0.7379538205916617,
|
| 16912 |
+
"grad_norm": 0.17578125,
|
| 16913 |
+
"learning_rate": 1.6658877260154414e-05,
|
| 16914 |
+
"loss": 1.9295827150344849,
|
| 16915 |
+
"step": 4830
|
| 16916 |
+
},
|
| 16917 |
+
{
|
| 16918 |
+
"epoch": 0.7382593915318654,
|
| 16919 |
+
"grad_norm": 0.1484375,
|
| 16920 |
+
"learning_rate": 1.6622398058729883e-05,
|
| 16921 |
+
"loss": 1.9448530673980713,
|
| 16922 |
+
"step": 4832
|
| 16923 |
+
},
|
| 16924 |
+
{
|
| 16925 |
+
"epoch": 0.7385649624720689,
|
| 16926 |
+
"grad_norm": 0.154296875,
|
| 16927 |
+
"learning_rate": 1.658595087731892e-05,
|
| 16928 |
+
"loss": 1.9359034299850464,
|
| 16929 |
+
"step": 4834
|
| 16930 |
+
},
|
| 16931 |
+
{
|
| 16932 |
+
"epoch": 0.7388705334122725,
|
| 16933 |
+
"grad_norm": 0.1552734375,
|
| 16934 |
+
"learning_rate": 1.6549535750886275e-05,
|
| 16935 |
+
"loss": 1.885801076889038,
|
| 16936 |
+
"step": 4836
|
| 16937 |
+
},
|
| 16938 |
+
{
|
| 16939 |
+
"epoch": 0.739176104352476,
|
| 16940 |
+
"grad_norm": 0.150390625,
|
| 16941 |
+
"learning_rate": 1.6513152714365916e-05,
|
| 16942 |
+
"loss": 1.933889389038086,
|
| 16943 |
+
"step": 4838
|
| 16944 |
+
},
|
| 16945 |
+
{
|
| 16946 |
+
"epoch": 0.7394816752926797,
|
| 16947 |
+
"grad_norm": 0.1533203125,
|
| 16948 |
+
"learning_rate": 1.6476801802661063e-05,
|
| 16949 |
+
"loss": 1.926424503326416,
|
| 16950 |
+
"step": 4840
|
| 16951 |
+
},
|
| 16952 |
+
{
|
| 16953 |
+
"epoch": 0.7397872462328833,
|
| 16954 |
+
"grad_norm": 0.1669921875,
|
| 16955 |
+
"learning_rate": 1.6440483050644096e-05,
|
| 16956 |
+
"loss": 1.8922525644302368,
|
| 16957 |
+
"step": 4842
|
| 16958 |
+
},
|
| 16959 |
+
{
|
| 16960 |
+
"epoch": 0.7400928171730868,
|
| 16961 |
+
"grad_norm": 0.1513671875,
|
| 16962 |
+
"learning_rate": 1.640419649315654e-05,
|
| 16963 |
+
"loss": 1.91448974609375,
|
| 16964 |
+
"step": 4844
|
| 16965 |
+
},
|
| 16966 |
+
{
|
| 16967 |
+
"epoch": 0.7403983881132904,
|
| 16968 |
+
"grad_norm": 0.158203125,
|
| 16969 |
+
"learning_rate": 1.6367942165009087e-05,
|
| 16970 |
+
"loss": 1.9399285316467285,
|
| 16971 |
+
"step": 4846
|
| 16972 |
+
},
|
| 16973 |
+
{
|
| 16974 |
+
"epoch": 0.7407039590534941,
|
| 16975 |
+
"grad_norm": 0.1591796875,
|
| 16976 |
+
"learning_rate": 1.633172010098146e-05,
|
| 16977 |
+
"loss": 1.9476866722106934,
|
| 16978 |
+
"step": 4848
|
| 16979 |
+
},
|
| 16980 |
+
{
|
| 16981 |
+
"epoch": 0.7410095299936976,
|
| 16982 |
+
"grad_norm": 0.1767578125,
|
| 16983 |
+
"learning_rate": 1.6295530335822413e-05,
|
| 16984 |
+
"loss": 1.9306056499481201,
|
| 16985 |
+
"step": 4850
|
| 16986 |
+
},
|
| 16987 |
+
{
|
| 16988 |
+
"epoch": 0.7413151009339012,
|
| 16989 |
+
"grad_norm": 0.1552734375,
|
| 16990 |
+
"learning_rate": 1.6259372904249754e-05,
|
| 16991 |
+
"loss": 1.9353654384613037,
|
| 16992 |
+
"step": 4852
|
| 16993 |
+
},
|
| 16994 |
+
{
|
| 16995 |
+
"epoch": 0.7416206718741047,
|
| 16996 |
+
"grad_norm": 0.1572265625,
|
| 16997 |
+
"learning_rate": 1.622324784095026e-05,
|
| 16998 |
+
"loss": 1.9204692840576172,
|
| 16999 |
+
"step": 4854
|
| 17000 |
+
},
|
| 17001 |
+
{
|
| 17002 |
+
"epoch": 0.7419262428143084,
|
| 17003 |
+
"grad_norm": 0.146484375,
|
| 17004 |
+
"learning_rate": 1.6187155180579662e-05,
|
| 17005 |
+
"loss": 1.9401675462722778,
|
| 17006 |
+
"step": 4856
|
| 17007 |
+
},
|
| 17008 |
+
{
|
| 17009 |
+
"epoch": 0.742231813754512,
|
| 17010 |
+
"grad_norm": 0.158203125,
|
| 17011 |
+
"learning_rate": 1.6151094957762592e-05,
|
| 17012 |
+
"loss": 1.9176608324050903,
|
| 17013 |
+
"step": 4858
|
| 17014 |
+
},
|
| 17015 |
+
{
|
| 17016 |
+
"epoch": 0.7425373846947155,
|
| 17017 |
+
"grad_norm": 0.154296875,
|
| 17018 |
+
"learning_rate": 1.6115067207092583e-05,
|
| 17019 |
+
"loss": 1.9320135116577148,
|
| 17020 |
+
"step": 4860
|
| 17021 |
+
},
|
| 17022 |
+
{
|
| 17023 |
+
"epoch": 0.7428429556349191,
|
| 17024 |
+
"grad_norm": 0.1591796875,
|
| 17025 |
+
"learning_rate": 1.6079071963131997e-05,
|
| 17026 |
+
"loss": 1.9036394357681274,
|
| 17027 |
+
"step": 4862
|
| 17028 |
+
},
|
| 17029 |
+
{
|
| 17030 |
+
"epoch": 0.7431485265751228,
|
| 17031 |
+
"grad_norm": 0.15234375,
|
| 17032 |
+
"learning_rate": 1.604310926041203e-05,
|
| 17033 |
+
"loss": 1.9338078498840332,
|
| 17034 |
+
"step": 4864
|
| 17035 |
+
},
|
| 17036 |
+
{
|
| 17037 |
+
"epoch": 0.7434540975153263,
|
| 17038 |
+
"grad_norm": 0.154296875,
|
| 17039 |
+
"learning_rate": 1.6007179133432644e-05,
|
| 17040 |
+
"loss": 1.9759202003479004,
|
| 17041 |
+
"step": 4866
|
| 17042 |
+
},
|
| 17043 |
+
{
|
| 17044 |
+
"epoch": 0.7437596684555299,
|
| 17045 |
+
"grad_norm": 0.1533203125,
|
| 17046 |
+
"learning_rate": 1.5971281616662553e-05,
|
| 17047 |
+
"loss": 1.9322929382324219,
|
| 17048 |
+
"step": 4868
|
| 17049 |
+
},
|
| 17050 |
+
{
|
| 17051 |
+
"epoch": 0.7440652393957334,
|
| 17052 |
+
"grad_norm": 0.1552734375,
|
| 17053 |
+
"learning_rate": 1.5935416744539206e-05,
|
| 17054 |
+
"loss": 1.936887264251709,
|
| 17055 |
+
"step": 4870
|
| 17056 |
+
},
|
| 17057 |
+
{
|
| 17058 |
+
"epoch": 0.7443708103359371,
|
| 17059 |
+
"grad_norm": 0.16015625,
|
| 17060 |
+
"learning_rate": 1.5899584551468704e-05,
|
| 17061 |
+
"loss": 1.8834519386291504,
|
| 17062 |
+
"step": 4872
|
| 17063 |
+
},
|
| 17064 |
+
{
|
| 17065 |
+
"epoch": 0.7446763812761407,
|
| 17066 |
+
"grad_norm": 0.1591796875,
|
| 17067 |
+
"learning_rate": 1.5863785071825844e-05,
|
| 17068 |
+
"loss": 1.942356824874878,
|
| 17069 |
+
"step": 4874
|
| 17070 |
+
},
|
| 17071 |
+
{
|
| 17072 |
+
"epoch": 0.7449819522163442,
|
| 17073 |
+
"grad_norm": 0.15625,
|
| 17074 |
+
"learning_rate": 1.5828018339953964e-05,
|
| 17075 |
+
"loss": 1.9527716636657715,
|
| 17076 |
+
"step": 4876
|
| 17077 |
+
},
|
| 17078 |
+
{
|
| 17079 |
+
"epoch": 0.7452875231565478,
|
| 17080 |
+
"grad_norm": 0.1572265625,
|
| 17081 |
+
"learning_rate": 1.5792284390165054e-05,
|
| 17082 |
+
"loss": 1.9101110696792603,
|
| 17083 |
+
"step": 4878
|
| 17084 |
+
},
|
| 17085 |
+
{
|
| 17086 |
+
"epoch": 0.7455930940967515,
|
| 17087 |
+
"grad_norm": 0.1513671875,
|
| 17088 |
+
"learning_rate": 1.5756583256739645e-05,
|
| 17089 |
+
"loss": 1.936516523361206,
|
| 17090 |
+
"step": 4880
|
| 17091 |
+
},
|
| 17092 |
+
{
|
| 17093 |
+
"epoch": 0.745898665036955,
|
| 17094 |
+
"grad_norm": 0.1591796875,
|
| 17095 |
+
"learning_rate": 1.5720914973926766e-05,
|
| 17096 |
+
"loss": 1.9219439029693604,
|
| 17097 |
+
"step": 4882
|
| 17098 |
+
},
|
| 17099 |
+
{
|
| 17100 |
+
"epoch": 0.7462042359771586,
|
| 17101 |
+
"grad_norm": 0.154296875,
|
| 17102 |
+
"learning_rate": 1.5685279575943945e-05,
|
| 17103 |
+
"loss": 1.9240226745605469,
|
| 17104 |
+
"step": 4884
|
| 17105 |
+
},
|
| 17106 |
+
{
|
| 17107 |
+
"epoch": 0.7465098069173621,
|
| 17108 |
+
"grad_norm": 0.1494140625,
|
| 17109 |
+
"learning_rate": 1.564967709697718e-05,
|
| 17110 |
+
"loss": 1.9120197296142578,
|
| 17111 |
+
"step": 4886
|
| 17112 |
+
},
|
| 17113 |
+
{
|
| 17114 |
+
"epoch": 0.7468153778575658,
|
| 17115 |
+
"grad_norm": 0.1484375,
|
| 17116 |
+
"learning_rate": 1.561410757118082e-05,
|
| 17117 |
+
"loss": 1.9179697036743164,
|
| 17118 |
+
"step": 4888
|
| 17119 |
+
},
|
| 17120 |
+
{
|
| 17121 |
+
"epoch": 0.7471209487977694,
|
| 17122 |
+
"grad_norm": 0.14453125,
|
| 17123 |
+
"learning_rate": 1.557857103267768e-05,
|
| 17124 |
+
"loss": 1.9247615337371826,
|
| 17125 |
+
"step": 4890
|
| 17126 |
+
},
|
| 17127 |
+
{
|
| 17128 |
+
"epoch": 0.7474265197379729,
|
| 17129 |
+
"grad_norm": 0.154296875,
|
| 17130 |
+
"learning_rate": 1.554306751555889e-05,
|
| 17131 |
+
"loss": 1.941112995147705,
|
| 17132 |
+
"step": 4892
|
| 17133 |
+
},
|
| 17134 |
+
{
|
| 17135 |
+
"epoch": 0.7477320906781765,
|
| 17136 |
+
"grad_norm": 0.1630859375,
|
| 17137 |
+
"learning_rate": 1.5507597053883898e-05,
|
| 17138 |
+
"loss": 1.9041484594345093,
|
| 17139 |
+
"step": 4894
|
| 17140 |
+
},
|
| 17141 |
+
{
|
| 17142 |
+
"epoch": 0.7480376616183801,
|
| 17143 |
+
"grad_norm": 0.1572265625,
|
| 17144 |
+
"learning_rate": 1.5472159681680483e-05,
|
| 17145 |
+
"loss": 1.9315097332000732,
|
| 17146 |
+
"step": 4896
|
| 17147 |
+
},
|
| 17148 |
+
{
|
| 17149 |
+
"epoch": 0.7483432325585837,
|
| 17150 |
+
"grad_norm": 0.1494140625,
|
| 17151 |
+
"learning_rate": 1.543675543294465e-05,
|
| 17152 |
+
"loss": 1.9029995203018188,
|
| 17153 |
+
"step": 4898
|
| 17154 |
+
},
|
| 17155 |
+
{
|
| 17156 |
+
"epoch": 0.7486488034987873,
|
| 17157 |
+
"grad_norm": 0.1552734375,
|
| 17158 |
+
"learning_rate": 1.5401384341640596e-05,
|
| 17159 |
+
"loss": 1.943681001663208,
|
| 17160 |
+
"step": 4900
|
| 17161 |
+
},
|
| 17162 |
+
{
|
| 17163 |
+
"epoch": 0.7489543744389908,
|
| 17164 |
+
"grad_norm": 0.150390625,
|
| 17165 |
+
"learning_rate": 1.536604644170076e-05,
|
| 17166 |
+
"loss": 1.9345145225524902,
|
| 17167 |
+
"step": 4902
|
| 17168 |
+
},
|
| 17169 |
+
{
|
| 17170 |
+
"epoch": 0.7492599453791945,
|
| 17171 |
+
"grad_norm": 0.15234375,
|
| 17172 |
+
"learning_rate": 1.533074176702572e-05,
|
| 17173 |
+
"loss": 1.9256540536880493,
|
| 17174 |
+
"step": 4904
|
| 17175 |
+
},
|
| 17176 |
+
{
|
| 17177 |
+
"epoch": 0.749565516319398,
|
| 17178 |
+
"grad_norm": 0.1533203125,
|
| 17179 |
+
"learning_rate": 1.5295470351484183e-05,
|
| 17180 |
+
"loss": 1.9194281101226807,
|
| 17181 |
+
"step": 4906
|
| 17182 |
+
},
|
| 17183 |
+
{
|
| 17184 |
+
"epoch": 0.7498710872596016,
|
| 17185 |
+
"grad_norm": 0.1630859375,
|
| 17186 |
+
"learning_rate": 1.5260232228912942e-05,
|
| 17187 |
+
"loss": 1.9517762660980225,
|
| 17188 |
+
"step": 4908
|
| 17189 |
+
},
|
| 17190 |
+
{
|
| 17191 |
+
"epoch": 0.7501766581998052,
|
| 17192 |
+
"grad_norm": 0.1552734375,
|
| 17193 |
+
"learning_rate": 1.5225027433116856e-05,
|
| 17194 |
+
"loss": 1.9476008415222168,
|
| 17195 |
+
"step": 4910
|
| 17196 |
+
},
|
| 17197 |
+
{
|
| 17198 |
+
"epoch": 0.7504822291400088,
|
| 17199 |
+
"grad_norm": 0.162109375,
|
| 17200 |
+
"learning_rate": 1.518985599786883e-05,
|
| 17201 |
+
"loss": 1.8917043209075928,
|
| 17202 |
+
"step": 4912
|
| 17203 |
+
},
|
| 17204 |
+
{
|
| 17205 |
+
"epoch": 0.7507878000802124,
|
| 17206 |
+
"grad_norm": 0.158203125,
|
| 17207 |
+
"learning_rate": 1.5154717956909731e-05,
|
| 17208 |
+
"loss": 1.9212429523468018,
|
| 17209 |
+
"step": 4914
|
| 17210 |
+
},
|
| 17211 |
+
{
|
| 17212 |
+
"epoch": 0.751093371020416,
|
| 17213 |
+
"grad_norm": 0.16015625,
|
| 17214 |
+
"learning_rate": 1.5119613343948413e-05,
|
| 17215 |
+
"loss": 1.9514460563659668,
|
| 17216 |
+
"step": 4916
|
| 17217 |
+
},
|
| 17218 |
+
{
|
| 17219 |
+
"epoch": 0.7513989419606195,
|
| 17220 |
+
"grad_norm": 0.150390625,
|
| 17221 |
+
"learning_rate": 1.5084542192661666e-05,
|
| 17222 |
+
"loss": 1.9224693775177002,
|
| 17223 |
+
"step": 4918
|
| 17224 |
+
},
|
| 17225 |
+
{
|
| 17226 |
+
"epoch": 0.7517045129008232,
|
| 17227 |
+
"grad_norm": 0.16015625,
|
| 17228 |
+
"learning_rate": 1.504950453669416e-05,
|
| 17229 |
+
"loss": 1.9353735446929932,
|
| 17230 |
+
"step": 4920
|
| 17231 |
+
},
|
| 17232 |
+
{
|
| 17233 |
+
"epoch": 0.7520100838410267,
|
| 17234 |
+
"grad_norm": 0.15234375,
|
| 17235 |
+
"learning_rate": 1.5014500409658444e-05,
|
| 17236 |
+
"loss": 1.944659948348999,
|
| 17237 |
+
"step": 4922
|
| 17238 |
+
},
|
| 17239 |
+
{
|
| 17240 |
+
"epoch": 0.7523156547812303,
|
| 17241 |
+
"grad_norm": 0.15625,
|
| 17242 |
+
"learning_rate": 1.4979529845134915e-05,
|
| 17243 |
+
"loss": 1.9696897268295288,
|
| 17244 |
+
"step": 4924
|
| 17245 |
+
},
|
| 17246 |
+
{
|
| 17247 |
+
"epoch": 0.7526212257214339,
|
| 17248 |
+
"grad_norm": 0.1572265625,
|
| 17249 |
+
"learning_rate": 1.4944592876671732e-05,
|
| 17250 |
+
"loss": 1.9561878442764282,
|
| 17251 |
+
"step": 4926
|
| 17252 |
+
},
|
| 17253 |
+
{
|
| 17254 |
+
"epoch": 0.7529267966616375,
|
| 17255 |
+
"grad_norm": 0.1572265625,
|
| 17256 |
+
"learning_rate": 1.4909689537784844e-05,
|
| 17257 |
+
"loss": 1.9504321813583374,
|
| 17258 |
+
"step": 4928
|
| 17259 |
+
},
|
| 17260 |
+
{
|
| 17261 |
+
"epoch": 0.7532323676018411,
|
| 17262 |
+
"grad_norm": 0.1484375,
|
| 17263 |
+
"learning_rate": 1.4874819861957978e-05,
|
| 17264 |
+
"loss": 1.9749677181243896,
|
| 17265 |
+
"step": 4930
|
| 17266 |
+
},
|
| 17267 |
+
{
|
| 17268 |
+
"epoch": 0.7535379385420446,
|
| 17269 |
+
"grad_norm": 0.15234375,
|
| 17270 |
+
"learning_rate": 1.4839983882642516e-05,
|
| 17271 |
+
"loss": 1.9431102275848389,
|
| 17272 |
+
"step": 4932
|
| 17273 |
+
},
|
| 17274 |
+
{
|
| 17275 |
+
"epoch": 0.7538435094822482,
|
| 17276 |
+
"grad_norm": 0.158203125,
|
| 17277 |
+
"learning_rate": 1.4805181633257532e-05,
|
| 17278 |
+
"loss": 1.921071171760559,
|
| 17279 |
+
"step": 4934
|
| 17280 |
+
},
|
| 17281 |
+
{
|
| 17282 |
+
"epoch": 0.7541490804224519,
|
| 17283 |
+
"grad_norm": 0.1611328125,
|
| 17284 |
+
"learning_rate": 1.477041314718976e-05,
|
| 17285 |
+
"loss": 1.9767943620681763,
|
| 17286 |
+
"step": 4936
|
| 17287 |
+
},
|
| 17288 |
+
{
|
| 17289 |
+
"epoch": 0.7544546513626554,
|
| 17290 |
+
"grad_norm": 0.15234375,
|
| 17291 |
+
"learning_rate": 1.473567845779349e-05,
|
| 17292 |
+
"loss": 1.963395595550537,
|
| 17293 |
+
"step": 4938
|
| 17294 |
+
},
|
| 17295 |
+
{
|
| 17296 |
+
"epoch": 0.754760222302859,
|
| 17297 |
+
"grad_norm": 0.15234375,
|
| 17298 |
+
"learning_rate": 1.4700977598390641e-05,
|
| 17299 |
+
"loss": 1.950207233428955,
|
| 17300 |
+
"step": 4940
|
| 17301 |
+
},
|
| 17302 |
+
{
|
| 17303 |
+
"epoch": 0.7550657932430626,
|
| 17304 |
+
"grad_norm": 0.154296875,
|
| 17305 |
+
"learning_rate": 1.4666310602270666e-05,
|
| 17306 |
+
"loss": 1.9091548919677734,
|
| 17307 |
+
"step": 4942
|
| 17308 |
+
},
|
| 17309 |
+
{
|
| 17310 |
+
"epoch": 0.7553713641832662,
|
| 17311 |
+
"grad_norm": 0.1591796875,
|
| 17312 |
+
"learning_rate": 1.4631677502690511e-05,
|
| 17313 |
+
"loss": 1.9578845500946045,
|
| 17314 |
+
"step": 4944
|
| 17315 |
+
},
|
| 17316 |
+
{
|
| 17317 |
+
"epoch": 0.7556769351234698,
|
| 17318 |
+
"grad_norm": 0.1494140625,
|
| 17319 |
+
"learning_rate": 1.4597078332874652e-05,
|
| 17320 |
+
"loss": 1.937915563583374,
|
| 17321 |
+
"step": 4946
|
| 17322 |
+
},
|
| 17323 |
+
{
|
| 17324 |
+
"epoch": 0.7559825060636733,
|
| 17325 |
+
"grad_norm": 0.15234375,
|
| 17326 |
+
"learning_rate": 1.4562513126014988e-05,
|
| 17327 |
+
"loss": 1.92669677734375,
|
| 17328 |
+
"step": 4948
|
| 17329 |
+
},
|
| 17330 |
+
{
|
| 17331 |
+
"epoch": 0.7562880770038769,
|
| 17332 |
+
"grad_norm": 0.1669921875,
|
| 17333 |
+
"learning_rate": 1.4527981915270794e-05,
|
| 17334 |
+
"loss": 1.9479687213897705,
|
| 17335 |
+
"step": 4950
|
| 17336 |
+
},
|
| 17337 |
+
{
|
| 17338 |
+
"epoch": 0.7565936479440806,
|
| 17339 |
+
"grad_norm": 0.1484375,
|
| 17340 |
+
"learning_rate": 1.4493484733768797e-05,
|
| 17341 |
+
"loss": 1.9171351194381714,
|
| 17342 |
+
"step": 4952
|
| 17343 |
+
},
|
| 17344 |
+
{
|
| 17345 |
+
"epoch": 0.7568992188842841,
|
| 17346 |
+
"grad_norm": 0.1552734375,
|
| 17347 |
+
"learning_rate": 1.4459021614603047e-05,
|
| 17348 |
+
"loss": 1.9565486907958984,
|
| 17349 |
+
"step": 4954
|
| 17350 |
+
},
|
| 17351 |
+
{
|
| 17352 |
+
"epoch": 0.7572047898244877,
|
| 17353 |
+
"grad_norm": 0.16015625,
|
| 17354 |
+
"learning_rate": 1.4424592590834924e-05,
|
| 17355 |
+
"loss": 1.8952078819274902,
|
| 17356 |
+
"step": 4956
|
| 17357 |
+
},
|
| 17358 |
+
{
|
| 17359 |
+
"epoch": 0.7575103607646912,
|
| 17360 |
+
"grad_norm": 0.1533203125,
|
| 17361 |
+
"learning_rate": 1.4390197695493097e-05,
|
| 17362 |
+
"loss": 1.9264326095581055,
|
| 17363 |
+
"step": 4958
|
| 17364 |
+
},
|
| 17365 |
+
{
|
| 17366 |
+
"epoch": 0.7578159317048949,
|
| 17367 |
+
"grad_norm": 0.1591796875,
|
| 17368 |
+
"learning_rate": 1.4355836961573498e-05,
|
| 17369 |
+
"loss": 1.9107179641723633,
|
| 17370 |
+
"step": 4960
|
| 17371 |
+
},
|
| 17372 |
+
{
|
| 17373 |
+
"epoch": 0.7581215026450985,
|
| 17374 |
+
"grad_norm": 0.1611328125,
|
| 17375 |
+
"learning_rate": 1.4321510422039281e-05,
|
| 17376 |
+
"loss": 1.9692254066467285,
|
| 17377 |
+
"step": 4962
|
| 17378 |
+
},
|
| 17379 |
+
{
|
| 17380 |
+
"epoch": 0.758427073585302,
|
| 17381 |
+
"grad_norm": 0.1552734375,
|
| 17382 |
+
"learning_rate": 1.4287218109820805e-05,
|
| 17383 |
+
"loss": 1.9302308559417725,
|
| 17384 |
+
"step": 4964
|
| 17385 |
+
},
|
| 17386 |
+
{
|
| 17387 |
+
"epoch": 0.7587326445255056,
|
| 17388 |
+
"grad_norm": 0.154296875,
|
| 17389 |
+
"learning_rate": 1.425296005781559e-05,
|
| 17390 |
+
"loss": 1.9446437358856201,
|
| 17391 |
+
"step": 4966
|
| 17392 |
+
},
|
| 17393 |
+
{
|
| 17394 |
+
"epoch": 0.7590382154657093,
|
| 17395 |
+
"grad_norm": 0.1591796875,
|
| 17396 |
+
"learning_rate": 1.421873629888828e-05,
|
| 17397 |
+
"loss": 1.9372225999832153,
|
| 17398 |
+
"step": 4968
|
| 17399 |
+
},
|
| 17400 |
+
{
|
| 17401 |
+
"epoch": 0.7593437864059128,
|
| 17402 |
+
"grad_norm": 0.1513671875,
|
| 17403 |
+
"learning_rate": 1.418454686587064e-05,
|
| 17404 |
+
"loss": 1.936021089553833,
|
| 17405 |
+
"step": 4970
|
| 17406 |
+
},
|
| 17407 |
+
{
|
| 17408 |
+
"epoch": 0.7596493573461164,
|
| 17409 |
+
"grad_norm": 0.1611328125,
|
| 17410 |
+
"learning_rate": 1.4150391791561491e-05,
|
| 17411 |
+
"loss": 1.9343297481536865,
|
| 17412 |
+
"step": 4972
|
| 17413 |
+
},
|
| 17414 |
+
{
|
| 17415 |
+
"epoch": 0.7599549282863199,
|
| 17416 |
+
"grad_norm": 0.1650390625,
|
| 17417 |
+
"learning_rate": 1.4116271108726692e-05,
|
| 17418 |
+
"loss": 1.9290649890899658,
|
| 17419 |
+
"step": 4974
|
| 17420 |
+
},
|
| 17421 |
+
{
|
| 17422 |
+
"epoch": 0.7602604992265236,
|
| 17423 |
+
"grad_norm": 0.1533203125,
|
| 17424 |
+
"learning_rate": 1.4082184850099134e-05,
|
| 17425 |
+
"loss": 1.9679656028747559,
|
| 17426 |
+
"step": 4976
|
| 17427 |
+
},
|
| 17428 |
+
{
|
| 17429 |
+
"epoch": 0.7605660701667272,
|
| 17430 |
+
"grad_norm": 0.1552734375,
|
| 17431 |
+
"learning_rate": 1.4048133048378614e-05,
|
| 17432 |
+
"loss": 1.9006730318069458,
|
| 17433 |
+
"step": 4978
|
| 17434 |
+
},
|
| 17435 |
+
{
|
| 17436 |
+
"epoch": 0.7608716411069307,
|
| 17437 |
+
"grad_norm": 0.154296875,
|
| 17438 |
+
"learning_rate": 1.4014115736231969e-05,
|
| 17439 |
+
"loss": 1.9213688373565674,
|
| 17440 |
+
"step": 4980
|
| 17441 |
+
},
|
| 17442 |
+
{
|
| 17443 |
+
"epoch": 0.7611772120471343,
|
| 17444 |
+
"grad_norm": 0.1552734375,
|
| 17445 |
+
"learning_rate": 1.3980132946292896e-05,
|
| 17446 |
+
"loss": 1.8962403535842896,
|
| 17447 |
+
"step": 4982
|
| 17448 |
+
},
|
| 17449 |
+
{
|
| 17450 |
+
"epoch": 0.761482782987338,
|
| 17451 |
+
"grad_norm": 0.15234375,
|
| 17452 |
+
"learning_rate": 1.394618471116197e-05,
|
| 17453 |
+
"loss": 1.9177250862121582,
|
| 17454 |
+
"step": 4984
|
| 17455 |
+
},
|
| 17456 |
+
{
|
| 17457 |
+
"epoch": 0.7617883539275415,
|
| 17458 |
+
"grad_norm": 0.1552734375,
|
| 17459 |
+
"learning_rate": 1.3912271063406652e-05,
|
| 17460 |
+
"loss": 1.912928819656372,
|
| 17461 |
+
"step": 4986
|
| 17462 |
+
},
|
| 17463 |
+
{
|
| 17464 |
+
"epoch": 0.7620939248677451,
|
| 17465 |
+
"grad_norm": 0.1640625,
|
| 17466 |
+
"learning_rate": 1.3878392035561166e-05,
|
| 17467 |
+
"loss": 1.898256540298462,
|
| 17468 |
+
"step": 4988
|
| 17469 |
+
},
|
| 17470 |
+
{
|
| 17471 |
+
"epoch": 0.7623994958079486,
|
| 17472 |
+
"grad_norm": 0.1640625,
|
| 17473 |
+
"learning_rate": 1.3844547660126567e-05,
|
| 17474 |
+
"loss": 1.904240369796753,
|
| 17475 |
+
"step": 4990
|
| 17476 |
+
},
|
| 17477 |
+
{
|
| 17478 |
+
"epoch": 0.7627050667481523,
|
| 17479 |
+
"grad_norm": 0.15234375,
|
| 17480 |
+
"learning_rate": 1.3810737969570659e-05,
|
| 17481 |
+
"loss": 1.9135196208953857,
|
| 17482 |
+
"step": 4992
|
| 17483 |
+
},
|
| 17484 |
+
{
|
| 17485 |
+
"epoch": 0.7630106376883559,
|
| 17486 |
+
"grad_norm": 0.154296875,
|
| 17487 |
+
"learning_rate": 1.3776962996327957e-05,
|
| 17488 |
+
"loss": 1.9367570877075195,
|
| 17489 |
+
"step": 4994
|
| 17490 |
+
},
|
| 17491 |
+
{
|
| 17492 |
+
"epoch": 0.7633162086285594,
|
| 17493 |
+
"grad_norm": 0.1552734375,
|
| 17494 |
+
"learning_rate": 1.3743222772799713e-05,
|
| 17495 |
+
"loss": 1.942852258682251,
|
| 17496 |
+
"step": 4996
|
| 17497 |
+
},
|
| 17498 |
+
{
|
| 17499 |
+
"epoch": 0.763621779568763,
|
| 17500 |
+
"grad_norm": 0.1591796875,
|
| 17501 |
+
"learning_rate": 1.3709517331353817e-05,
|
| 17502 |
+
"loss": 1.9226059913635254,
|
| 17503 |
+
"step": 4998
|
| 17504 |
+
},
|
| 17505 |
+
{
|
| 17506 |
+
"epoch": 0.7639273505089667,
|
| 17507 |
+
"grad_norm": 0.1533203125,
|
| 17508 |
+
"learning_rate": 1.3675846704324746e-05,
|
| 17509 |
+
"loss": 1.9270179271697998,
|
| 17510 |
+
"step": 5000
|
| 17511 |
+
},
|
| 17512 |
+
{
|
| 17513 |
+
"epoch": 0.7642329214491702,
|
| 17514 |
+
"grad_norm": 0.171875,
|
| 17515 |
+
"learning_rate": 1.3642210924013643e-05,
|
| 17516 |
+
"loss": 1.9104570150375366,
|
| 17517 |
+
"step": 5002
|
| 17518 |
+
},
|
| 17519 |
+
{
|
| 17520 |
+
"epoch": 0.7645384923893738,
|
| 17521 |
+
"grad_norm": 0.1689453125,
|
| 17522 |
+
"learning_rate": 1.36086100226882e-05,
|
| 17523 |
+
"loss": 1.9581544399261475,
|
| 17524 |
+
"step": 5004
|
| 17525 |
+
},
|
| 17526 |
+
{
|
| 17527 |
+
"epoch": 0.7648440633295773,
|
| 17528 |
+
"grad_norm": 0.15234375,
|
| 17529 |
+
"learning_rate": 1.357504403258264e-05,
|
| 17530 |
+
"loss": 1.9120666980743408,
|
| 17531 |
+
"step": 5006
|
| 17532 |
+
},
|
| 17533 |
+
{
|
| 17534 |
+
"epoch": 0.765149634269781,
|
| 17535 |
+
"grad_norm": 0.150390625,
|
| 17536 |
+
"learning_rate": 1.3541512985897714e-05,
|
| 17537 |
+
"loss": 1.9201164245605469,
|
| 17538 |
+
"step": 5008
|
| 17539 |
+
},
|
| 17540 |
+
{
|
| 17541 |
+
"epoch": 0.7654552052099846,
|
| 17542 |
+
"grad_norm": 0.1591796875,
|
| 17543 |
+
"learning_rate": 1.350801691480063e-05,
|
| 17544 |
+
"loss": 1.9252748489379883,
|
| 17545 |
+
"step": 5010
|
| 17546 |
+
},
|
| 17547 |
+
{
|
| 17548 |
+
"epoch": 0.7657607761501881,
|
| 17549 |
+
"grad_norm": 0.15625,
|
| 17550 |
+
"learning_rate": 1.3474555851425059e-05,
|
| 17551 |
+
"loss": 1.9564262628555298,
|
| 17552 |
+
"step": 5012
|
| 17553 |
+
},
|
| 17554 |
+
{
|
| 17555 |
+
"epoch": 0.7660663470903917,
|
| 17556 |
+
"grad_norm": 0.1494140625,
|
| 17557 |
+
"learning_rate": 1.3441129827871073e-05,
|
| 17558 |
+
"loss": 1.9446051120758057,
|
| 17559 |
+
"step": 5014
|
| 17560 |
+
},
|
| 17561 |
+
{
|
| 17562 |
+
"epoch": 0.7663719180305953,
|
| 17563 |
+
"grad_norm": 0.162109375,
|
| 17564 |
+
"learning_rate": 1.3407738876205144e-05,
|
| 17565 |
+
"loss": 1.9372518062591553,
|
| 17566 |
+
"step": 5016
|
| 17567 |
+
},
|
| 17568 |
+
{
|
| 17569 |
+
"epoch": 0.7666774889707989,
|
| 17570 |
+
"grad_norm": 0.158203125,
|
| 17571 |
+
"learning_rate": 1.337438302846009e-05,
|
| 17572 |
+
"loss": 1.9010809659957886,
|
| 17573 |
+
"step": 5018
|
| 17574 |
+
},
|
| 17575 |
+
{
|
| 17576 |
+
"epoch": 0.7669830599110025,
|
| 17577 |
+
"grad_norm": 0.1669921875,
|
| 17578 |
+
"learning_rate": 1.3341062316635055e-05,
|
| 17579 |
+
"loss": 1.9671292304992676,
|
| 17580 |
+
"step": 5020
|
| 17581 |
+
},
|
| 17582 |
+
{
|
| 17583 |
+
"epoch": 0.767288630851206,
|
| 17584 |
+
"grad_norm": 0.1669921875,
|
| 17585 |
+
"learning_rate": 1.3307776772695473e-05,
|
| 17586 |
+
"loss": 1.9720847606658936,
|
| 17587 |
+
"step": 5022
|
| 17588 |
+
},
|
| 17589 |
+
{
|
| 17590 |
+
"epoch": 0.7675942017914097,
|
| 17591 |
+
"grad_norm": 0.15234375,
|
| 17592 |
+
"learning_rate": 1.3274526428573053e-05,
|
| 17593 |
+
"loss": 1.9131839275360107,
|
| 17594 |
+
"step": 5024
|
| 17595 |
+
},
|
| 17596 |
+
{
|
| 17597 |
+
"epoch": 0.7678997727316133,
|
| 17598 |
+
"grad_norm": 0.1533203125,
|
| 17599 |
+
"learning_rate": 1.3241311316165739e-05,
|
| 17600 |
+
"loss": 1.9470791816711426,
|
| 17601 |
+
"step": 5026
|
| 17602 |
+
},
|
| 17603 |
+
{
|
| 17604 |
+
"epoch": 0.7682053436718168,
|
| 17605 |
+
"grad_norm": 0.1630859375,
|
| 17606 |
+
"learning_rate": 1.3208131467337614e-05,
|
| 17607 |
+
"loss": 1.9490231275558472,
|
| 17608 |
+
"step": 5028
|
| 17609 |
+
},
|
| 17610 |
+
{
|
| 17611 |
+
"epoch": 0.7685109146120204,
|
| 17612 |
+
"grad_norm": 0.1455078125,
|
| 17613 |
+
"learning_rate": 1.317498691391903e-05,
|
| 17614 |
+
"loss": 1.8980166912078857,
|
| 17615 |
+
"step": 5030
|
| 17616 |
+
},
|
| 17617 |
+
{
|
| 17618 |
+
"epoch": 0.768816485552224,
|
| 17619 |
+
"grad_norm": 0.1513671875,
|
| 17620 |
+
"learning_rate": 1.3141877687706411e-05,
|
| 17621 |
+
"loss": 1.9476318359375,
|
| 17622 |
+
"step": 5032
|
| 17623 |
+
},
|
| 17624 |
+
{
|
| 17625 |
+
"epoch": 0.7691220564924276,
|
| 17626 |
+
"grad_norm": 0.15234375,
|
| 17627 |
+
"learning_rate": 1.3108803820462317e-05,
|
| 17628 |
+
"loss": 1.9962636232376099,
|
| 17629 |
+
"step": 5034
|
| 17630 |
+
},
|
| 17631 |
+
{
|
| 17632 |
+
"epoch": 0.7694276274326312,
|
| 17633 |
+
"grad_norm": 0.1611328125,
|
| 17634 |
+
"learning_rate": 1.307576534391538e-05,
|
| 17635 |
+
"loss": 1.916093111038208,
|
| 17636 |
+
"step": 5036
|
| 17637 |
+
},
|
| 17638 |
+
{
|
| 17639 |
+
"epoch": 0.7697331983728347,
|
| 17640 |
+
"grad_norm": 0.158203125,
|
| 17641 |
+
"learning_rate": 1.3042762289760296e-05,
|
| 17642 |
+
"loss": 1.9381229877471924,
|
| 17643 |
+
"step": 5038
|
| 17644 |
+
},
|
| 17645 |
+
{
|
| 17646 |
+
"epoch": 0.7700387693130384,
|
| 17647 |
+
"grad_norm": 0.1591796875,
|
| 17648 |
+
"learning_rate": 1.300979468965774e-05,
|
| 17649 |
+
"loss": 1.9245405197143555,
|
| 17650 |
+
"step": 5040
|
| 17651 |
+
},
|
| 17652 |
+
{
|
| 17653 |
+
"epoch": 0.7703443402532419,
|
| 17654 |
+
"grad_norm": 0.15625,
|
| 17655 |
+
"learning_rate": 1.29768625752344e-05,
|
| 17656 |
+
"loss": 1.93449068069458,
|
| 17657 |
+
"step": 5042
|
| 17658 |
+
},
|
| 17659 |
+
{
|
| 17660 |
+
"epoch": 0.7706499111934455,
|
| 17661 |
+
"grad_norm": 0.154296875,
|
| 17662 |
+
"learning_rate": 1.294396597808294e-05,
|
| 17663 |
+
"loss": 1.9083449840545654,
|
| 17664 |
+
"step": 5044
|
| 17665 |
+
},
|
| 17666 |
+
{
|
| 17667 |
+
"epoch": 0.7709554821336491,
|
| 17668 |
+
"grad_norm": 0.162109375,
|
| 17669 |
+
"learning_rate": 1.2911104929761903e-05,
|
| 17670 |
+
"loss": 1.9736361503601074,
|
| 17671 |
+
"step": 5046
|
| 17672 |
+
},
|
| 17673 |
+
{
|
| 17674 |
+
"epoch": 0.7712610530738527,
|
| 17675 |
+
"grad_norm": 0.158203125,
|
| 17676 |
+
"learning_rate": 1.2878279461795811e-05,
|
| 17677 |
+
"loss": 1.9151121377944946,
|
| 17678 |
+
"step": 5048
|
| 17679 |
+
},
|
| 17680 |
+
{
|
| 17681 |
+
"epoch": 0.7715666240140563,
|
| 17682 |
+
"grad_norm": 0.154296875,
|
| 17683 |
+
"learning_rate": 1.2845489605674954e-05,
|
| 17684 |
+
"loss": 1.9041707515716553,
|
| 17685 |
+
"step": 5050
|
| 17686 |
+
},
|
| 17687 |
+
{
|
| 17688 |
+
"epoch": 0.7718721949542598,
|
| 17689 |
+
"grad_norm": 0.154296875,
|
| 17690 |
+
"learning_rate": 1.2812735392855523e-05,
|
| 17691 |
+
"loss": 1.9041962623596191,
|
| 17692 |
+
"step": 5052
|
| 17693 |
+
},
|
| 17694 |
+
{
|
| 17695 |
+
"epoch": 0.7721777658944634,
|
| 17696 |
+
"grad_norm": 0.1552734375,
|
| 17697 |
+
"learning_rate": 1.2780016854759502e-05,
|
| 17698 |
+
"loss": 1.9047939777374268,
|
| 17699 |
+
"step": 5054
|
| 17700 |
+
},
|
| 17701 |
+
{
|
| 17702 |
+
"epoch": 0.7724833368346671,
|
| 17703 |
+
"grad_norm": 0.1513671875,
|
| 17704 |
+
"learning_rate": 1.2747334022774638e-05,
|
| 17705 |
+
"loss": 1.9125609397888184,
|
| 17706 |
+
"step": 5056
|
| 17707 |
+
},
|
| 17708 |
+
{
|
| 17709 |
+
"epoch": 0.7727889077748706,
|
| 17710 |
+
"grad_norm": 0.1572265625,
|
| 17711 |
+
"learning_rate": 1.2714686928254432e-05,
|
| 17712 |
+
"loss": 1.940215826034546,
|
| 17713 |
+
"step": 5058
|
| 17714 |
+
},
|
| 17715 |
+
{
|
| 17716 |
+
"epoch": 0.7730944787150742,
|
| 17717 |
+
"grad_norm": 0.1552734375,
|
| 17718 |
+
"learning_rate": 1.2682075602518112e-05,
|
| 17719 |
+
"loss": 1.937150001525879,
|
| 17720 |
+
"step": 5060
|
| 17721 |
+
},
|
| 17722 |
+
{
|
| 17723 |
+
"epoch": 0.7734000496552778,
|
| 17724 |
+
"grad_norm": 0.158203125,
|
| 17725 |
+
"learning_rate": 1.2649500076850579e-05,
|
| 17726 |
+
"loss": 1.9100359678268433,
|
| 17727 |
+
"step": 5062
|
| 17728 |
+
},
|
| 17729 |
+
{
|
| 17730 |
+
"epoch": 0.7737056205954814,
|
| 17731 |
+
"grad_norm": 0.150390625,
|
| 17732 |
+
"learning_rate": 1.2616960382502397e-05,
|
| 17733 |
+
"loss": 1.936317801475525,
|
| 17734 |
+
"step": 5064
|
| 17735 |
+
},
|
| 17736 |
+
{
|
| 17737 |
+
"epoch": 0.774011191535685,
|
| 17738 |
+
"grad_norm": 0.1708984375,
|
| 17739 |
+
"learning_rate": 1.2584456550689744e-05,
|
| 17740 |
+
"loss": 1.906294345855713,
|
| 17741 |
+
"step": 5066
|
| 17742 |
+
},
|
| 17743 |
+
{
|
| 17744 |
+
"epoch": 0.7743167624758885,
|
| 17745 |
+
"grad_norm": 0.1591796875,
|
| 17746 |
+
"learning_rate": 1.2551988612594407e-05,
|
| 17747 |
+
"loss": 1.9258465766906738,
|
| 17748 |
+
"step": 5068
|
| 17749 |
+
},
|
| 17750 |
+
{
|
| 17751 |
+
"epoch": 0.7746223334160921,
|
| 17752 |
+
"grad_norm": 0.1669921875,
|
| 17753 |
+
"learning_rate": 1.2519556599363735e-05,
|
| 17754 |
+
"loss": 1.9239153861999512,
|
| 17755 |
+
"step": 5070
|
| 17756 |
+
},
|
| 17757 |
+
{
|
| 17758 |
+
"epoch": 0.7749279043562958,
|
| 17759 |
+
"grad_norm": 0.162109375,
|
| 17760 |
+
"learning_rate": 1.248716054211062e-05,
|
| 17761 |
+
"loss": 1.9423909187316895,
|
| 17762 |
+
"step": 5072
|
| 17763 |
+
},
|
| 17764 |
+
{
|
| 17765 |
+
"epoch": 0.7752334752964993,
|
| 17766 |
+
"grad_norm": 0.1572265625,
|
| 17767 |
+
"learning_rate": 1.245480047191344e-05,
|
| 17768 |
+
"loss": 1.905983567237854,
|
| 17769 |
+
"step": 5074
|
| 17770 |
+
},
|
| 17771 |
+
{
|
| 17772 |
+
"epoch": 0.7755390462367029,
|
| 17773 |
+
"grad_norm": 0.162109375,
|
| 17774 |
+
"learning_rate": 1.2422476419816093e-05,
|
| 17775 |
+
"loss": 1.9369637966156006,
|
| 17776 |
+
"step": 5076
|
| 17777 |
+
},
|
| 17778 |
+
{
|
| 17779 |
+
"epoch": 0.7758446171769064,
|
| 17780 |
+
"grad_norm": 0.1533203125,
|
| 17781 |
+
"learning_rate": 1.2390188416827842e-05,
|
| 17782 |
+
"loss": 1.956169843673706,
|
| 17783 |
+
"step": 5078
|
| 17784 |
+
},
|
| 17785 |
+
{
|
| 17786 |
+
"epoch": 0.7761501881171101,
|
| 17787 |
+
"grad_norm": 0.1484375,
|
| 17788 |
+
"learning_rate": 1.235793649392346e-05,
|
| 17789 |
+
"loss": 1.925276279449463,
|
| 17790 |
+
"step": 5080
|
| 17791 |
+
},
|
| 17792 |
+
{
|
| 17793 |
+
"epoch": 0.7764557590573137,
|
| 17794 |
+
"grad_norm": 0.1650390625,
|
| 17795 |
+
"learning_rate": 1.2325720682043063e-05,
|
| 17796 |
+
"loss": 1.9239652156829834,
|
| 17797 |
+
"step": 5082
|
| 17798 |
+
},
|
| 17799 |
+
{
|
| 17800 |
+
"epoch": 0.7767613299975172,
|
| 17801 |
+
"grad_norm": 0.1494140625,
|
| 17802 |
+
"learning_rate": 1.229354101209212e-05,
|
| 17803 |
+
"loss": 1.885994791984558,
|
| 17804 |
+
"step": 5084
|
| 17805 |
+
},
|
| 17806 |
+
{
|
| 17807 |
+
"epoch": 0.7770669009377208,
|
| 17808 |
+
"grad_norm": 0.1533203125,
|
| 17809 |
+
"learning_rate": 1.2261397514941442e-05,
|
| 17810 |
+
"loss": 1.9166903495788574,
|
| 17811 |
+
"step": 5086
|
| 17812 |
+
},
|
| 17813 |
+
{
|
| 17814 |
+
"epoch": 0.7773724718779245,
|
| 17815 |
+
"grad_norm": 0.150390625,
|
| 17816 |
+
"learning_rate": 1.2229290221427148e-05,
|
| 17817 |
+
"loss": 1.9465073347091675,
|
| 17818 |
+
"step": 5088
|
| 17819 |
+
},
|
| 17820 |
+
{
|
| 17821 |
+
"epoch": 0.777678042818128,
|
| 17822 |
+
"grad_norm": 0.16015625,
|
| 17823 |
+
"learning_rate": 1.2197219162350576e-05,
|
| 17824 |
+
"loss": 1.9269946813583374,
|
| 17825 |
+
"step": 5090
|
| 17826 |
+
},
|
| 17827 |
+
{
|
| 17828 |
+
"epoch": 0.7779836137583316,
|
| 17829 |
+
"grad_norm": 0.158203125,
|
| 17830 |
+
"learning_rate": 1.2165184368478354e-05,
|
| 17831 |
+
"loss": 1.969733715057373,
|
| 17832 |
+
"step": 5092
|
| 17833 |
+
},
|
| 17834 |
+
{
|
| 17835 |
+
"epoch": 0.7782891846985351,
|
| 17836 |
+
"grad_norm": 0.1572265625,
|
| 17837 |
+
"learning_rate": 1.2133185870542313e-05,
|
| 17838 |
+
"loss": 1.914946436882019,
|
| 17839 |
+
"step": 5094
|
| 17840 |
+
},
|
| 17841 |
+
{
|
| 17842 |
+
"epoch": 0.7785947556387388,
|
| 17843 |
+
"grad_norm": 0.15625,
|
| 17844 |
+
"learning_rate": 1.2101223699239433e-05,
|
| 17845 |
+
"loss": 1.9840538501739502,
|
| 17846 |
+
"step": 5096
|
| 17847 |
+
},
|
| 17848 |
+
{
|
| 17849 |
+
"epoch": 0.7789003265789424,
|
| 17850 |
+
"grad_norm": 0.146484375,
|
| 17851 |
+
"learning_rate": 1.2069297885231905e-05,
|
| 17852 |
+
"loss": 1.960890531539917,
|
| 17853 |
+
"step": 5098
|
| 17854 |
+
},
|
| 17855 |
+
{
|
| 17856 |
+
"epoch": 0.7792058975191459,
|
| 17857 |
+
"grad_norm": 0.1513671875,
|
| 17858 |
+
"learning_rate": 1.2037408459146992e-05,
|
| 17859 |
+
"loss": 1.8939318656921387,
|
| 17860 |
+
"step": 5100
|
| 17861 |
+
},
|
| 17862 |
+
{
|
| 17863 |
+
"epoch": 0.7795114684593495,
|
| 17864 |
+
"grad_norm": 0.158203125,
|
| 17865 |
+
"learning_rate": 1.2005555451577038e-05,
|
| 17866 |
+
"loss": 1.89341139793396,
|
| 17867 |
+
"step": 5102
|
| 17868 |
+
},
|
| 17869 |
+
{
|
| 17870 |
+
"epoch": 0.7798170393995532,
|
| 17871 |
+
"grad_norm": 0.1650390625,
|
| 17872 |
+
"learning_rate": 1.1973738893079495e-05,
|
| 17873 |
+
"loss": 1.9576774835586548,
|
| 17874 |
+
"step": 5104
|
| 17875 |
+
},
|
| 17876 |
+
{
|
| 17877 |
+
"epoch": 0.7801226103397567,
|
| 17878 |
+
"grad_norm": 0.1533203125,
|
| 17879 |
+
"learning_rate": 1.1941958814176812e-05,
|
| 17880 |
+
"loss": 1.9645620584487915,
|
| 17881 |
+
"step": 5106
|
| 17882 |
+
},
|
| 17883 |
+
{
|
| 17884 |
+
"epoch": 0.7804281812799603,
|
| 17885 |
+
"grad_norm": 0.1484375,
|
| 17886 |
+
"learning_rate": 1.191021524535647e-05,
|
| 17887 |
+
"loss": 1.912255048751831,
|
| 17888 |
+
"step": 5108
|
| 17889 |
+
},
|
| 17890 |
+
{
|
| 17891 |
+
"epoch": 0.7807337522201638,
|
| 17892 |
+
"grad_norm": 0.15625,
|
| 17893 |
+
"learning_rate": 1.1878508217070899e-05,
|
| 17894 |
+
"loss": 1.886203408241272,
|
| 17895 |
+
"step": 5110
|
| 17896 |
+
},
|
| 17897 |
+
{
|
| 17898 |
+
"epoch": 0.7810393231603674,
|
| 17899 |
+
"grad_norm": 0.154296875,
|
| 17900 |
+
"learning_rate": 1.18468377597375e-05,
|
| 17901 |
+
"loss": 1.9148609638214111,
|
| 17902 |
+
"step": 5112
|
| 17903 |
+
},
|
| 17904 |
+
{
|
| 17905 |
+
"epoch": 0.7813448941005711,
|
| 17906 |
+
"grad_norm": 0.1572265625,
|
| 17907 |
+
"learning_rate": 1.1815203903738569e-05,
|
| 17908 |
+
"loss": 1.9005967378616333,
|
| 17909 |
+
"step": 5114
|
| 17910 |
+
},
|
| 17911 |
+
{
|
| 17912 |
+
"epoch": 0.7816504650407746,
|
| 17913 |
+
"grad_norm": 0.1650390625,
|
| 17914 |
+
"learning_rate": 1.1783606679421305e-05,
|
| 17915 |
+
"loss": 1.9226658344268799,
|
| 17916 |
+
"step": 5116
|
| 17917 |
+
},
|
| 17918 |
+
{
|
| 17919 |
+
"epoch": 0.7819560359809782,
|
| 17920 |
+
"grad_norm": 0.1533203125,
|
| 17921 |
+
"learning_rate": 1.1752046117097747e-05,
|
| 17922 |
+
"loss": 1.9273567199707031,
|
| 17923 |
+
"step": 5118
|
| 17924 |
+
},
|
| 17925 |
+
{
|
| 17926 |
+
"epoch": 0.7822616069211817,
|
| 17927 |
+
"grad_norm": 0.1640625,
|
| 17928 |
+
"learning_rate": 1.1720522247044785e-05,
|
| 17929 |
+
"loss": 1.933349370956421,
|
| 17930 |
+
"step": 5120
|
| 17931 |
+
},
|
| 17932 |
+
{
|
| 17933 |
+
"epoch": 0.7825671778613854,
|
| 17934 |
+
"grad_norm": 0.15234375,
|
| 17935 |
+
"learning_rate": 1.1689035099504098e-05,
|
| 17936 |
+
"loss": 1.9247326850891113,
|
| 17937 |
+
"step": 5122
|
| 17938 |
+
},
|
| 17939 |
+
{
|
| 17940 |
+
"epoch": 0.782872748801589,
|
| 17941 |
+
"grad_norm": 0.1572265625,
|
| 17942 |
+
"learning_rate": 1.1657584704682128e-05,
|
| 17943 |
+
"loss": 1.9638586044311523,
|
| 17944 |
+
"step": 5124
|
| 17945 |
+
},
|
| 17946 |
+
{
|
| 17947 |
+
"epoch": 0.7831783197417925,
|
| 17948 |
+
"grad_norm": 0.1533203125,
|
| 17949 |
+
"learning_rate": 1.1626171092750094e-05,
|
| 17950 |
+
"loss": 1.9862494468688965,
|
| 17951 |
+
"step": 5126
|
| 17952 |
+
},
|
| 17953 |
+
{
|
| 17954 |
+
"epoch": 0.7834838906819961,
|
| 17955 |
+
"grad_norm": 0.1533203125,
|
| 17956 |
+
"learning_rate": 1.1594794293843852e-05,
|
| 17957 |
+
"loss": 1.9227653741836548,
|
| 17958 |
+
"step": 5128
|
| 17959 |
+
},
|
| 17960 |
+
{
|
| 17961 |
+
"epoch": 0.7837894616221998,
|
| 17962 |
+
"grad_norm": 0.15625,
|
| 17963 |
+
"learning_rate": 1.1563454338064034e-05,
|
| 17964 |
+
"loss": 1.9155776500701904,
|
| 17965 |
+
"step": 5130
|
| 17966 |
+
},
|
| 17967 |
+
{
|
| 17968 |
+
"epoch": 0.7840950325624033,
|
| 17969 |
+
"grad_norm": 0.1650390625,
|
| 17970 |
+
"learning_rate": 1.1532151255475876e-05,
|
| 17971 |
+
"loss": 1.9749836921691895,
|
| 17972 |
+
"step": 5132
|
| 17973 |
+
},
|
| 17974 |
+
{
|
| 17975 |
+
"epoch": 0.7844006035026069,
|
| 17976 |
+
"grad_norm": 0.1513671875,
|
| 17977 |
+
"learning_rate": 1.1500885076109252e-05,
|
| 17978 |
+
"loss": 1.9278974533081055,
|
| 17979 |
+
"step": 5134
|
| 17980 |
+
},
|
| 17981 |
+
{
|
| 17982 |
+
"epoch": 0.7847061744428104,
|
| 17983 |
+
"grad_norm": 0.158203125,
|
| 17984 |
+
"learning_rate": 1.1469655829958625e-05,
|
| 17985 |
+
"loss": 1.901437759399414,
|
| 17986 |
+
"step": 5136
|
| 17987 |
+
},
|
| 17988 |
+
{
|
| 17989 |
+
"epoch": 0.7850117453830141,
|
| 17990 |
+
"grad_norm": 0.1611328125,
|
| 17991 |
+
"learning_rate": 1.1438463546983058e-05,
|
| 17992 |
+
"loss": 1.9371318817138672,
|
| 17993 |
+
"step": 5138
|
| 17994 |
+
},
|
| 17995 |
+
{
|
| 17996 |
+
"epoch": 0.7853173163232177,
|
| 17997 |
+
"grad_norm": 0.15234375,
|
| 17998 |
+
"learning_rate": 1.1407308257106092e-05,
|
| 17999 |
+
"loss": 1.9491982460021973,
|
| 18000 |
+
"step": 5140
|
| 18001 |
+
},
|
| 18002 |
+
{
|
| 18003 |
+
"epoch": 0.7856228872634212,
|
| 18004 |
+
"grad_norm": 0.1513671875,
|
| 18005 |
+
"learning_rate": 1.1376189990215842e-05,
|
| 18006 |
+
"loss": 1.9267663955688477,
|
| 18007 |
+
"step": 5142
|
| 18008 |
+
},
|
| 18009 |
+
{
|
| 18010 |
+
"epoch": 0.7859284582036248,
|
| 18011 |
+
"grad_norm": 0.158203125,
|
| 18012 |
+
"learning_rate": 1.134510877616487e-05,
|
| 18013 |
+
"loss": 1.9577958583831787,
|
| 18014 |
+
"step": 5144
|
| 18015 |
+
},
|
| 18016 |
+
{
|
| 18017 |
+
"epoch": 0.7862340291438285,
|
| 18018 |
+
"grad_norm": 0.1513671875,
|
| 18019 |
+
"learning_rate": 1.1314064644770201e-05,
|
| 18020 |
+
"loss": 1.936807632446289,
|
| 18021 |
+
"step": 5146
|
| 18022 |
+
},
|
| 18023 |
+
{
|
| 18024 |
+
"epoch": 0.786539600084032,
|
| 18025 |
+
"grad_norm": 0.1455078125,
|
| 18026 |
+
"learning_rate": 1.1283057625813315e-05,
|
| 18027 |
+
"loss": 1.906538486480713,
|
| 18028 |
+
"step": 5148
|
| 18029 |
+
},
|
| 18030 |
+
{
|
| 18031 |
+
"epoch": 0.7868451710242356,
|
| 18032 |
+
"grad_norm": 0.1513671875,
|
| 18033 |
+
"learning_rate": 1.1252087749040058e-05,
|
| 18034 |
+
"loss": 1.9113422632217407,
|
| 18035 |
+
"step": 5150
|
| 18036 |
+
},
|
| 18037 |
+
{
|
| 18038 |
+
"epoch": 0.7871507419644391,
|
| 18039 |
+
"grad_norm": 0.1689453125,
|
| 18040 |
+
"learning_rate": 1.1221155044160619e-05,
|
| 18041 |
+
"loss": 1.931211233139038,
|
| 18042 |
+
"step": 5152
|
| 18043 |
+
},
|
| 18044 |
+
{
|
| 18045 |
+
"epoch": 0.7874563129046428,
|
| 18046 |
+
"grad_norm": 0.1533203125,
|
| 18047 |
+
"learning_rate": 1.1190259540849585e-05,
|
| 18048 |
+
"loss": 1.89674973487854,
|
| 18049 |
+
"step": 5154
|
| 18050 |
+
},
|
| 18051 |
+
{
|
| 18052 |
+
"epoch": 0.7877618838448464,
|
| 18053 |
+
"grad_norm": 0.1533203125,
|
| 18054 |
+
"learning_rate": 1.1159401268745812e-05,
|
| 18055 |
+
"loss": 1.926396369934082,
|
| 18056 |
+
"step": 5156
|
| 18057 |
+
},
|
| 18058 |
+
{
|
| 18059 |
+
"epoch": 0.7880674547850499,
|
| 18060 |
+
"grad_norm": 0.1513671875,
|
| 18061 |
+
"learning_rate": 1.1128580257452465e-05,
|
| 18062 |
+
"loss": 1.9355146884918213,
|
| 18063 |
+
"step": 5158
|
| 18064 |
+
},
|
| 18065 |
+
{
|
| 18066 |
+
"epoch": 0.7883730257252535,
|
| 18067 |
+
"grad_norm": 0.1513671875,
|
| 18068 |
+
"learning_rate": 1.1097796536536942e-05,
|
| 18069 |
+
"loss": 1.9320380687713623,
|
| 18070 |
+
"step": 5160
|
| 18071 |
+
},
|
| 18072 |
+
{
|
| 18073 |
+
"epoch": 0.7886785966654571,
|
| 18074 |
+
"grad_norm": 0.1552734375,
|
| 18075 |
+
"learning_rate": 1.1067050135530887e-05,
|
| 18076 |
+
"loss": 1.8710808753967285,
|
| 18077 |
+
"step": 5162
|
| 18078 |
+
},
|
| 18079 |
+
{
|
| 18080 |
+
"epoch": 0.7889841676056607,
|
| 18081 |
+
"grad_norm": 0.1591796875,
|
| 18082 |
+
"learning_rate": 1.103634108393013e-05,
|
| 18083 |
+
"loss": 1.9382953643798828,
|
| 18084 |
+
"step": 5164
|
| 18085 |
+
},
|
| 18086 |
+
{
|
| 18087 |
+
"epoch": 0.7892897385458643,
|
| 18088 |
+
"grad_norm": 0.1591796875,
|
| 18089 |
+
"learning_rate": 1.1005669411194674e-05,
|
| 18090 |
+
"loss": 1.8970255851745605,
|
| 18091 |
+
"step": 5166
|
| 18092 |
+
},
|
| 18093 |
+
{
|
| 18094 |
+
"epoch": 0.7895953094860678,
|
| 18095 |
+
"grad_norm": 0.1494140625,
|
| 18096 |
+
"learning_rate": 1.0975035146748663e-05,
|
| 18097 |
+
"loss": 1.9567101001739502,
|
| 18098 |
+
"step": 5168
|
| 18099 |
+
},
|
| 18100 |
+
{
|
| 18101 |
+
"epoch": 0.7899008804262715,
|
| 18102 |
+
"grad_norm": 0.1513671875,
|
| 18103 |
+
"learning_rate": 1.0944438319980354e-05,
|
| 18104 |
+
"loss": 1.9063657522201538,
|
| 18105 |
+
"step": 5170
|
| 18106 |
+
},
|
| 18107 |
+
{
|
| 18108 |
+
"epoch": 0.790206451366475,
|
| 18109 |
+
"grad_norm": 0.16015625,
|
| 18110 |
+
"learning_rate": 1.0913878960242091e-05,
|
| 18111 |
+
"loss": 1.9300537109375,
|
| 18112 |
+
"step": 5172
|
| 18113 |
+
},
|
| 18114 |
+
{
|
| 18115 |
+
"epoch": 0.7905120223066786,
|
| 18116 |
+
"grad_norm": 0.1572265625,
|
| 18117 |
+
"learning_rate": 1.0883357096850278e-05,
|
| 18118 |
+
"loss": 1.9953930377960205,
|
| 18119 |
+
"step": 5174
|
| 18120 |
+
},
|
| 18121 |
+
{
|
| 18122 |
+
"epoch": 0.7908175932468822,
|
| 18123 |
+
"grad_norm": 0.1533203125,
|
| 18124 |
+
"learning_rate": 1.0852872759085348e-05,
|
| 18125 |
+
"loss": 1.9258501529693604,
|
| 18126 |
+
"step": 5176
|
| 18127 |
+
},
|
| 18128 |
+
{
|
| 18129 |
+
"epoch": 0.7911231641870858,
|
| 18130 |
+
"grad_norm": 0.1552734375,
|
| 18131 |
+
"learning_rate": 1.0822425976191702e-05,
|
| 18132 |
+
"loss": 1.9638206958770752,
|
| 18133 |
+
"step": 5178
|
| 18134 |
+
},
|
| 18135 |
+
{
|
| 18136 |
+
"epoch": 0.7914287351272894,
|
| 18137 |
+
"grad_norm": 0.1484375,
|
| 18138 |
+
"learning_rate": 1.0792016777377755e-05,
|
| 18139 |
+
"loss": 1.9529961347579956,
|
| 18140 |
+
"step": 5180
|
| 18141 |
+
},
|
| 18142 |
+
{
|
| 18143 |
+
"epoch": 0.791734306067493,
|
| 18144 |
+
"grad_norm": 0.15625,
|
| 18145 |
+
"learning_rate": 1.0761645191815866e-05,
|
| 18146 |
+
"loss": 1.9157311916351318,
|
| 18147 |
+
"step": 5182
|
| 18148 |
+
},
|
| 18149 |
+
{
|
| 18150 |
+
"epoch": 0.7920398770076965,
|
| 18151 |
+
"grad_norm": 0.1484375,
|
| 18152 |
+
"learning_rate": 1.073131124864229e-05,
|
| 18153 |
+
"loss": 1.914663553237915,
|
| 18154 |
+
"step": 5184
|
| 18155 |
+
},
|
| 18156 |
+
{
|
| 18157 |
+
"epoch": 0.7923454479479002,
|
| 18158 |
+
"grad_norm": 0.150390625,
|
| 18159 |
+
"learning_rate": 1.070101497695718e-05,
|
| 18160 |
+
"loss": 1.9575788974761963,
|
| 18161 |
+
"step": 5186
|
| 18162 |
+
},
|
| 18163 |
+
{
|
| 18164 |
+
"epoch": 0.7926510188881037,
|
| 18165 |
+
"grad_norm": 0.1494140625,
|
| 18166 |
+
"learning_rate": 1.0670756405824562e-05,
|
| 18167 |
+
"loss": 1.9224178791046143,
|
| 18168 |
+
"step": 5188
|
| 18169 |
+
},
|
| 18170 |
+
{
|
| 18171 |
+
"epoch": 0.7929565898283073,
|
| 18172 |
+
"grad_norm": 0.1513671875,
|
| 18173 |
+
"learning_rate": 1.0640535564272246e-05,
|
| 18174 |
+
"loss": 1.9463192224502563,
|
| 18175 |
+
"step": 5190
|
| 18176 |
+
},
|
| 18177 |
+
{
|
| 18178 |
+
"epoch": 0.7932621607685109,
|
| 18179 |
+
"grad_norm": 0.166015625,
|
| 18180 |
+
"learning_rate": 1.0610352481291908e-05,
|
| 18181 |
+
"loss": 1.9710593223571777,
|
| 18182 |
+
"step": 5192
|
| 18183 |
+
},
|
| 18184 |
+
{
|
| 18185 |
+
"epoch": 0.7935677317087145,
|
| 18186 |
+
"grad_norm": 0.15625,
|
| 18187 |
+
"learning_rate": 1.0580207185838964e-05,
|
| 18188 |
+
"loss": 1.9118977785110474,
|
| 18189 |
+
"step": 5194
|
| 18190 |
+
},
|
| 18191 |
+
{
|
| 18192 |
+
"epoch": 0.7938733026489181,
|
| 18193 |
+
"grad_norm": 0.154296875,
|
| 18194 |
+
"learning_rate": 1.0550099706832584e-05,
|
| 18195 |
+
"loss": 1.975113034248352,
|
| 18196 |
+
"step": 5196
|
| 18197 |
+
},
|
| 18198 |
+
{
|
| 18199 |
+
"epoch": 0.7941788735891216,
|
| 18200 |
+
"grad_norm": 0.154296875,
|
| 18201 |
+
"learning_rate": 1.052003007315569e-05,
|
| 18202 |
+
"loss": 1.9333195686340332,
|
| 18203 |
+
"step": 5198
|
| 18204 |
+
},
|
| 18205 |
+
{
|
| 18206 |
+
"epoch": 0.7944844445293252,
|
| 18207 |
+
"grad_norm": 0.1689453125,
|
| 18208 |
+
"learning_rate": 1.0489998313654881e-05,
|
| 18209 |
+
"loss": 1.9312257766723633,
|
| 18210 |
+
"step": 5200
|
| 18211 |
+
},
|
| 18212 |
+
{
|
| 18213 |
+
"epoch": 0.7947900154695289,
|
| 18214 |
+
"grad_norm": 0.1552734375,
|
| 18215 |
+
"learning_rate": 1.0460004457140382e-05,
|
| 18216 |
+
"loss": 1.9096062183380127,
|
| 18217 |
+
"step": 5202
|
| 18218 |
+
},
|
| 18219 |
+
{
|
| 18220 |
+
"epoch": 0.7950955864097324,
|
| 18221 |
+
"grad_norm": 0.1650390625,
|
| 18222 |
+
"learning_rate": 1.04300485323861e-05,
|
| 18223 |
+
"loss": 1.899652123451233,
|
| 18224 |
+
"step": 5204
|
| 18225 |
+
},
|
| 18226 |
+
{
|
| 18227 |
+
"epoch": 0.795401157349936,
|
| 18228 |
+
"grad_norm": 0.1494140625,
|
| 18229 |
+
"learning_rate": 1.0400130568129558e-05,
|
| 18230 |
+
"loss": 1.9238977432250977,
|
| 18231 |
+
"step": 5206
|
| 18232 |
+
},
|
| 18233 |
+
{
|
| 18234 |
+
"epoch": 0.7957067282901396,
|
| 18235 |
+
"grad_norm": 0.1533203125,
|
| 18236 |
+
"learning_rate": 1.0370250593071829e-05,
|
| 18237 |
+
"loss": 1.9320460557937622,
|
| 18238 |
+
"step": 5208
|
| 18239 |
+
},
|
| 18240 |
+
{
|
| 18241 |
+
"epoch": 0.7960122992303432,
|
| 18242 |
+
"grad_norm": 0.15234375,
|
| 18243 |
+
"learning_rate": 1.034040863587758e-05,
|
| 18244 |
+
"loss": 1.894615650177002,
|
| 18245 |
+
"step": 5210
|
| 18246 |
+
},
|
| 18247 |
+
{
|
| 18248 |
+
"epoch": 0.7963178701705468,
|
| 18249 |
+
"grad_norm": 0.150390625,
|
| 18250 |
+
"learning_rate": 1.0310604725174971e-05,
|
| 18251 |
+
"loss": 1.9332349300384521,
|
| 18252 |
+
"step": 5212
|
| 18253 |
+
},
|
| 18254 |
+
{
|
| 18255 |
+
"epoch": 0.7966234411107503,
|
| 18256 |
+
"grad_norm": 0.154296875,
|
| 18257 |
+
"learning_rate": 1.0280838889555689e-05,
|
| 18258 |
+
"loss": 1.9156787395477295,
|
| 18259 |
+
"step": 5214
|
| 18260 |
+
},
|
| 18261 |
+
{
|
| 18262 |
+
"epoch": 0.7969290120509539,
|
| 18263 |
+
"grad_norm": 0.1533203125,
|
| 18264 |
+
"learning_rate": 1.0251111157574884e-05,
|
| 18265 |
+
"loss": 1.924987554550171,
|
| 18266 |
+
"step": 5216
|
| 18267 |
+
},
|
| 18268 |
+
{
|
| 18269 |
+
"epoch": 0.7972345829911576,
|
| 18270 |
+
"grad_norm": 0.1591796875,
|
| 18271 |
+
"learning_rate": 1.0221421557751149e-05,
|
| 18272 |
+
"loss": 1.956756353378296,
|
| 18273 |
+
"step": 5218
|
| 18274 |
+
},
|
| 18275 |
+
{
|
| 18276 |
+
"epoch": 0.7975401539313611,
|
| 18277 |
+
"grad_norm": 0.154296875,
|
| 18278 |
+
"learning_rate": 1.0191770118566507e-05,
|
| 18279 |
+
"loss": 1.9304670095443726,
|
| 18280 |
+
"step": 5220
|
| 18281 |
+
},
|
| 18282 |
+
{
|
| 18283 |
+
"epoch": 0.7978457248715647,
|
| 18284 |
+
"grad_norm": 0.15234375,
|
| 18285 |
+
"learning_rate": 1.0162156868466354e-05,
|
| 18286 |
+
"loss": 1.935002326965332,
|
| 18287 |
+
"step": 5222
|
| 18288 |
+
},
|
| 18289 |
+
{
|
| 18290 |
+
"epoch": 0.7981512958117682,
|
| 18291 |
+
"grad_norm": 0.15625,
|
| 18292 |
+
"learning_rate": 1.0132581835859473e-05,
|
| 18293 |
+
"loss": 1.9504282474517822,
|
| 18294 |
+
"step": 5224
|
| 18295 |
+
},
|
| 18296 |
+
{
|
| 18297 |
+
"epoch": 0.7984568667519719,
|
| 18298 |
+
"grad_norm": 0.1513671875,
|
| 18299 |
+
"learning_rate": 1.0103045049117981e-05,
|
| 18300 |
+
"loss": 1.9410508871078491,
|
| 18301 |
+
"step": 5226
|
| 18302 |
+
},
|
| 18303 |
+
{
|
| 18304 |
+
"epoch": 0.7987624376921755,
|
| 18305 |
+
"grad_norm": 0.146484375,
|
| 18306 |
+
"learning_rate": 1.0073546536577266e-05,
|
| 18307 |
+
"loss": 1.9163868427276611,
|
| 18308 |
+
"step": 5228
|
| 18309 |
+
},
|
| 18310 |
+
{
|
| 18311 |
+
"epoch": 0.799068008632379,
|
| 18312 |
+
"grad_norm": 0.15625,
|
| 18313 |
+
"learning_rate": 1.0044086326536034e-05,
|
| 18314 |
+
"loss": 1.925628423690796,
|
| 18315 |
+
"step": 5230
|
| 18316 |
+
},
|
| 18317 |
+
{
|
| 18318 |
+
"epoch": 0.7993735795725826,
|
| 18319 |
+
"grad_norm": 0.1591796875,
|
| 18320 |
+
"learning_rate": 1.0014664447256272e-05,
|
| 18321 |
+
"loss": 1.9294524192810059,
|
| 18322 |
+
"step": 5232
|
| 18323 |
+
},
|
| 18324 |
+
{
|
| 18325 |
+
"epoch": 0.7996791505127863,
|
| 18326 |
+
"grad_norm": 0.1533203125,
|
| 18327 |
+
"learning_rate": 9.985280926963141e-06,
|
| 18328 |
+
"loss": 1.9411351680755615,
|
| 18329 |
+
"step": 5234
|
| 18330 |
+
},
|
| 18331 |
+
{
|
| 18332 |
+
"epoch": 0.7999847214529898,
|
| 18333 |
+
"grad_norm": 0.16015625,
|
| 18334 |
+
"learning_rate": 9.955935793845034e-06,
|
| 18335 |
+
"loss": 1.930655837059021,
|
| 18336 |
+
"step": 5236
|
| 18337 |
+
},
|
| 18338 |
+
{
|
| 18339 |
+
"epoch": 0.8002902923931934,
|
| 18340 |
+
"grad_norm": 0.1552734375,
|
| 18341 |
+
"learning_rate": 9.926629076053518e-06,
|
| 18342 |
+
"loss": 1.9452321529388428,
|
| 18343 |
+
"step": 5238
|
| 18344 |
+
},
|
| 18345 |
+
{
|
| 18346 |
+
"epoch": 0.8005958633333969,
|
| 18347 |
+
"grad_norm": 0.1474609375,
|
| 18348 |
+
"learning_rate": 9.897360801703276e-06,
|
| 18349 |
+
"loss": 1.9135477542877197,
|
| 18350 |
+
"step": 5240
|
| 18351 |
}
|
| 18352 |
],
|
| 18353 |
"logging_steps": 2,
|
|
|
|
| 18367 |
"attributes": {}
|
| 18368 |
}
|
| 18369 |
},
|
| 18370 |
+
"total_flos": 2.421872589124141e+18,
|
| 18371 |
"train_batch_size": 4,
|
| 18372 |
"trial_name": null,
|
| 18373 |
"trial_params": null
|