Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
unsloth
sft
conversational
text-generation-inference
Instructions to use Ba2han/test_CPTlsft2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/test_CPTlsft2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/test_CPTlsft2") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/test_CPTlsft2") model = AutoModelForCausalLM.from_pretrained("Ba2han/test_CPTlsft2", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/test_CPTlsft2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/test_CPTlsft2" # 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/test_CPTlsft2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ba2han/test_CPTlsft2
- SGLang
How to use Ba2han/test_CPTlsft2 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/test_CPTlsft2" \ --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/test_CPTlsft2", "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/test_CPTlsft2" \ --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/test_CPTlsft2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use Ba2han/test_CPTlsft2 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/test_CPTlsft2 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/test_CPTlsft2 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ba2han/test_CPTlsft2 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Ba2han/test_CPTlsft2", max_seq_length=2048, ) - Docker Model Runner
How to use Ba2han/test_CPTlsft2 with Docker Model Runner:
docker model run hf.co/Ba2han/test_CPTlsft2
Training in progress, step 4592, 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 2934397032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7654ec051fb7b61b282482bbcc40c52cd29dee31e13f5d5d5e233d28e824e854
|
| 3 |
size 2934397032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3631584265
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3d8e19b70742dd6fa4a9e9b5bbc2219d2b86571433c9801a12f2f4d07dc571f
|
| 3 |
size 3631584265
|
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:ddc86c2dc78a767461cef68fe209b3b3d8837a5700ddfda58bab5fd398c26597
|
| 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": 1.
|
| 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,
|
|
@@ -14071,6 +14071,2015 @@
|
|
| 14071 |
"learning_rate": 3.5678704856787045e-05,
|
| 14072 |
"loss": 2.170813798904419,
|
| 14073 |
"step": 4018
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14074 |
}
|
| 14075 |
],
|
| 14076 |
"logging_steps": 2,
|
|
@@ -14090,7 +16099,7 @@
|
|
| 14090 |
"attributes": {}
|
| 14091 |
}
|
| 14092 |
},
|
| 14093 |
-
"total_flos":
|
| 14094 |
"train_batch_size": 1,
|
| 14095 |
"trial_name": null,
|
| 14096 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.6011472008647594,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4592,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14071 |
"learning_rate": 3.5678704856787045e-05,
|
| 14072 |
"loss": 2.170813798904419,
|
| 14073 |
"step": 4018
|
| 14074 |
+
},
|
| 14075 |
+
{
|
| 14076 |
+
"epoch": 1.4016946493017417,
|
| 14077 |
+
"grad_norm": 0.16216611862182617,
|
| 14078 |
+
"learning_rate": 3.5637193856371945e-05,
|
| 14079 |
+
"loss": 1.963215708732605,
|
| 14080 |
+
"step": 4020
|
| 14081 |
+
},
|
| 14082 |
+
{
|
| 14083 |
+
"epoch": 1.4023920358456683,
|
| 14084 |
+
"grad_norm": 0.1840636134147644,
|
| 14085 |
+
"learning_rate": 3.559568285595683e-05,
|
| 14086 |
+
"loss": 1.8479241132736206,
|
| 14087 |
+
"step": 4022
|
| 14088 |
+
},
|
| 14089 |
+
{
|
| 14090 |
+
"epoch": 1.4030894223895949,
|
| 14091 |
+
"grad_norm": 0.20008444786071777,
|
| 14092 |
+
"learning_rate": 3.555417185554172e-05,
|
| 14093 |
+
"loss": 1.6921862363815308,
|
| 14094 |
+
"step": 4024
|
| 14095 |
+
},
|
| 14096 |
+
{
|
| 14097 |
+
"epoch": 1.4037868089335217,
|
| 14098 |
+
"grad_norm": 0.19347982108592987,
|
| 14099 |
+
"learning_rate": 3.551266085512661e-05,
|
| 14100 |
+
"loss": 1.75076425075531,
|
| 14101 |
+
"step": 4026
|
| 14102 |
+
},
|
| 14103 |
+
{
|
| 14104 |
+
"epoch": 1.4044841954774483,
|
| 14105 |
+
"grad_norm": 0.22057102620601654,
|
| 14106 |
+
"learning_rate": 3.54711498547115e-05,
|
| 14107 |
+
"loss": 1.9814503192901611,
|
| 14108 |
+
"step": 4028
|
| 14109 |
+
},
|
| 14110 |
+
{
|
| 14111 |
+
"epoch": 1.4051815820213749,
|
| 14112 |
+
"grad_norm": 0.20400013029575348,
|
| 14113 |
+
"learning_rate": 3.5429638854296385e-05,
|
| 14114 |
+
"loss": 1.83992600440979,
|
| 14115 |
+
"step": 4030
|
| 14116 |
+
},
|
| 14117 |
+
{
|
| 14118 |
+
"epoch": 1.4058789685653015,
|
| 14119 |
+
"grad_norm": 0.21387846767902374,
|
| 14120 |
+
"learning_rate": 3.538812785388128e-05,
|
| 14121 |
+
"loss": 1.9891995191574097,
|
| 14122 |
+
"step": 4032
|
| 14123 |
+
},
|
| 14124 |
+
{
|
| 14125 |
+
"epoch": 1.406576355109228,
|
| 14126 |
+
"grad_norm": 0.2546032965183258,
|
| 14127 |
+
"learning_rate": 3.534661685346617e-05,
|
| 14128 |
+
"loss": 1.8944637775421143,
|
| 14129 |
+
"step": 4034
|
| 14130 |
+
},
|
| 14131 |
+
{
|
| 14132 |
+
"epoch": 1.4072737416531549,
|
| 14133 |
+
"grad_norm": 0.214521586894989,
|
| 14134 |
+
"learning_rate": 3.5305105853051064e-05,
|
| 14135 |
+
"loss": 1.8203704357147217,
|
| 14136 |
+
"step": 4036
|
| 14137 |
+
},
|
| 14138 |
+
{
|
| 14139 |
+
"epoch": 1.4079711281970815,
|
| 14140 |
+
"grad_norm": 0.21132892370224,
|
| 14141 |
+
"learning_rate": 3.526359485263595e-05,
|
| 14142 |
+
"loss": 1.85984468460083,
|
| 14143 |
+
"step": 4038
|
| 14144 |
+
},
|
| 14145 |
+
{
|
| 14146 |
+
"epoch": 1.408668514741008,
|
| 14147 |
+
"grad_norm": 0.20359593629837036,
|
| 14148 |
+
"learning_rate": 3.522208385222084e-05,
|
| 14149 |
+
"loss": 1.8268412351608276,
|
| 14150 |
+
"step": 4040
|
| 14151 |
+
},
|
| 14152 |
+
{
|
| 14153 |
+
"epoch": 1.4093659012849347,
|
| 14154 |
+
"grad_norm": 0.21819265186786652,
|
| 14155 |
+
"learning_rate": 3.518057285180573e-05,
|
| 14156 |
+
"loss": 1.7824187278747559,
|
| 14157 |
+
"step": 4042
|
| 14158 |
+
},
|
| 14159 |
+
{
|
| 14160 |
+
"epoch": 1.4100632878288613,
|
| 14161 |
+
"grad_norm": 0.17693446576595306,
|
| 14162 |
+
"learning_rate": 3.513906185139062e-05,
|
| 14163 |
+
"loss": 1.7772114276885986,
|
| 14164 |
+
"step": 4044
|
| 14165 |
+
},
|
| 14166 |
+
{
|
| 14167 |
+
"epoch": 1.410760674372788,
|
| 14168 |
+
"grad_norm": 0.26175910234451294,
|
| 14169 |
+
"learning_rate": 3.509755085097551e-05,
|
| 14170 |
+
"loss": 2.01741361618042,
|
| 14171 |
+
"step": 4046
|
| 14172 |
+
},
|
| 14173 |
+
{
|
| 14174 |
+
"epoch": 1.4114580609167147,
|
| 14175 |
+
"grad_norm": 0.4403669834136963,
|
| 14176 |
+
"learning_rate": 3.5056039850560404e-05,
|
| 14177 |
+
"loss": 1.5121135711669922,
|
| 14178 |
+
"step": 4048
|
| 14179 |
+
},
|
| 14180 |
+
{
|
| 14181 |
+
"epoch": 1.4121554474606413,
|
| 14182 |
+
"grad_norm": 0.1782636046409607,
|
| 14183 |
+
"learning_rate": 3.501452885014529e-05,
|
| 14184 |
+
"loss": 2.056703567504883,
|
| 14185 |
+
"step": 4050
|
| 14186 |
+
},
|
| 14187 |
+
{
|
| 14188 |
+
"epoch": 1.4128528340045678,
|
| 14189 |
+
"grad_norm": 0.22794538736343384,
|
| 14190 |
+
"learning_rate": 3.4973017849730177e-05,
|
| 14191 |
+
"loss": 1.6770656108856201,
|
| 14192 |
+
"step": 4052
|
| 14193 |
+
},
|
| 14194 |
+
{
|
| 14195 |
+
"epoch": 1.4135502205484944,
|
| 14196 |
+
"grad_norm": 0.2163773626089096,
|
| 14197 |
+
"learning_rate": 3.493150684931507e-05,
|
| 14198 |
+
"loss": 1.9402332305908203,
|
| 14199 |
+
"step": 4054
|
| 14200 |
+
},
|
| 14201 |
+
{
|
| 14202 |
+
"epoch": 1.4142476070924213,
|
| 14203 |
+
"grad_norm": 0.23980838060379028,
|
| 14204 |
+
"learning_rate": 3.4889995848899956e-05,
|
| 14205 |
+
"loss": 2.0581789016723633,
|
| 14206 |
+
"step": 4056
|
| 14207 |
+
},
|
| 14208 |
+
{
|
| 14209 |
+
"epoch": 1.4149449936363478,
|
| 14210 |
+
"grad_norm": 0.16321487724781036,
|
| 14211 |
+
"learning_rate": 3.484848484848485e-05,
|
| 14212 |
+
"loss": 2.007432222366333,
|
| 14213 |
+
"step": 4058
|
| 14214 |
+
},
|
| 14215 |
+
{
|
| 14216 |
+
"epoch": 1.4156423801802744,
|
| 14217 |
+
"grad_norm": 0.22912773489952087,
|
| 14218 |
+
"learning_rate": 3.480697384806974e-05,
|
| 14219 |
+
"loss": 1.9420256614685059,
|
| 14220 |
+
"step": 4060
|
| 14221 |
+
},
|
| 14222 |
+
{
|
| 14223 |
+
"epoch": 1.416339766724201,
|
| 14224 |
+
"grad_norm": 0.18415477871894836,
|
| 14225 |
+
"learning_rate": 3.476546284765463e-05,
|
| 14226 |
+
"loss": 1.902016282081604,
|
| 14227 |
+
"step": 4062
|
| 14228 |
+
},
|
| 14229 |
+
{
|
| 14230 |
+
"epoch": 1.4170371532681276,
|
| 14231 |
+
"grad_norm": 0.2103758454322815,
|
| 14232 |
+
"learning_rate": 3.472395184723952e-05,
|
| 14233 |
+
"loss": 2.004079818725586,
|
| 14234 |
+
"step": 4064
|
| 14235 |
+
},
|
| 14236 |
+
{
|
| 14237 |
+
"epoch": 1.4177345398120544,
|
| 14238 |
+
"grad_norm": 0.19446878135204315,
|
| 14239 |
+
"learning_rate": 3.468244084682441e-05,
|
| 14240 |
+
"loss": 1.9384950399398804,
|
| 14241 |
+
"step": 4066
|
| 14242 |
+
},
|
| 14243 |
+
{
|
| 14244 |
+
"epoch": 1.418431926355981,
|
| 14245 |
+
"grad_norm": 0.22194212675094604,
|
| 14246 |
+
"learning_rate": 3.4640929846409296e-05,
|
| 14247 |
+
"loss": 1.9696013927459717,
|
| 14248 |
+
"step": 4068
|
| 14249 |
+
},
|
| 14250 |
+
{
|
| 14251 |
+
"epoch": 1.4191293128999076,
|
| 14252 |
+
"grad_norm": 0.1842203140258789,
|
| 14253 |
+
"learning_rate": 3.459941884599419e-05,
|
| 14254 |
+
"loss": 1.9772635698318481,
|
| 14255 |
+
"step": 4070
|
| 14256 |
+
},
|
| 14257 |
+
{
|
| 14258 |
+
"epoch": 1.4198266994438342,
|
| 14259 |
+
"grad_norm": 0.23830775916576385,
|
| 14260 |
+
"learning_rate": 3.455790784557908e-05,
|
| 14261 |
+
"loss": 1.716020107269287,
|
| 14262 |
+
"step": 4072
|
| 14263 |
+
},
|
| 14264 |
+
{
|
| 14265 |
+
"epoch": 1.4205240859877608,
|
| 14266 |
+
"grad_norm": 0.3197784125804901,
|
| 14267 |
+
"learning_rate": 3.451639684516397e-05,
|
| 14268 |
+
"loss": 2.0234553813934326,
|
| 14269 |
+
"step": 4074
|
| 14270 |
+
},
|
| 14271 |
+
{
|
| 14272 |
+
"epoch": 1.4212214725316876,
|
| 14273 |
+
"grad_norm": 0.24736444652080536,
|
| 14274 |
+
"learning_rate": 3.447488584474886e-05,
|
| 14275 |
+
"loss": 2.014583110809326,
|
| 14276 |
+
"step": 4076
|
| 14277 |
+
},
|
| 14278 |
+
{
|
| 14279 |
+
"epoch": 1.4219188590756142,
|
| 14280 |
+
"grad_norm": 0.18203675746917725,
|
| 14281 |
+
"learning_rate": 3.443337484433375e-05,
|
| 14282 |
+
"loss": 2.062819480895996,
|
| 14283 |
+
"step": 4078
|
| 14284 |
+
},
|
| 14285 |
+
{
|
| 14286 |
+
"epoch": 1.4226162456195408,
|
| 14287 |
+
"grad_norm": 0.34547385573387146,
|
| 14288 |
+
"learning_rate": 3.439186384391864e-05,
|
| 14289 |
+
"loss": 1.8202629089355469,
|
| 14290 |
+
"step": 4080
|
| 14291 |
+
},
|
| 14292 |
+
{
|
| 14293 |
+
"epoch": 1.4233136321634674,
|
| 14294 |
+
"grad_norm": 0.2565050721168518,
|
| 14295 |
+
"learning_rate": 3.435035284350353e-05,
|
| 14296 |
+
"loss": 1.916255235671997,
|
| 14297 |
+
"step": 4082
|
| 14298 |
+
},
|
| 14299 |
+
{
|
| 14300 |
+
"epoch": 1.424011018707394,
|
| 14301 |
+
"grad_norm": 0.2017725557088852,
|
| 14302 |
+
"learning_rate": 3.430884184308842e-05,
|
| 14303 |
+
"loss": 1.856203556060791,
|
| 14304 |
+
"step": 4084
|
| 14305 |
+
},
|
| 14306 |
+
{
|
| 14307 |
+
"epoch": 1.4247084052513208,
|
| 14308 |
+
"grad_norm": 0.17718103528022766,
|
| 14309 |
+
"learning_rate": 3.4267330842673315e-05,
|
| 14310 |
+
"loss": 1.9452753067016602,
|
| 14311 |
+
"step": 4086
|
| 14312 |
+
},
|
| 14313 |
+
{
|
| 14314 |
+
"epoch": 1.4254057917952472,
|
| 14315 |
+
"grad_norm": 0.22691674530506134,
|
| 14316 |
+
"learning_rate": 3.42258198422582e-05,
|
| 14317 |
+
"loss": 1.9916186332702637,
|
| 14318 |
+
"step": 4088
|
| 14319 |
+
},
|
| 14320 |
+
{
|
| 14321 |
+
"epoch": 1.426103178339174,
|
| 14322 |
+
"grad_norm": 0.2360876351594925,
|
| 14323 |
+
"learning_rate": 3.418430884184309e-05,
|
| 14324 |
+
"loss": 1.9206513166427612,
|
| 14325 |
+
"step": 4090
|
| 14326 |
+
},
|
| 14327 |
+
{
|
| 14328 |
+
"epoch": 1.4268005648831006,
|
| 14329 |
+
"grad_norm": 0.21341641247272491,
|
| 14330 |
+
"learning_rate": 3.414279784142798e-05,
|
| 14331 |
+
"loss": 1.9444701671600342,
|
| 14332 |
+
"step": 4092
|
| 14333 |
+
},
|
| 14334 |
+
{
|
| 14335 |
+
"epoch": 1.4274979514270272,
|
| 14336 |
+
"grad_norm": 0.20100471377372742,
|
| 14337 |
+
"learning_rate": 3.410128684101287e-05,
|
| 14338 |
+
"loss": 1.8804447650909424,
|
| 14339 |
+
"step": 4094
|
| 14340 |
+
},
|
| 14341 |
+
{
|
| 14342 |
+
"epoch": 1.4281953379709538,
|
| 14343 |
+
"grad_norm": 0.2367202192544937,
|
| 14344 |
+
"learning_rate": 3.405977584059776e-05,
|
| 14345 |
+
"loss": 1.7431578636169434,
|
| 14346 |
+
"step": 4096
|
| 14347 |
+
},
|
| 14348 |
+
{
|
| 14349 |
+
"epoch": 1.4288927245148804,
|
| 14350 |
+
"grad_norm": 0.17000959813594818,
|
| 14351 |
+
"learning_rate": 3.4018264840182654e-05,
|
| 14352 |
+
"loss": 1.6879067420959473,
|
| 14353 |
+
"step": 4098
|
| 14354 |
+
},
|
| 14355 |
+
{
|
| 14356 |
+
"epoch": 1.4295901110588072,
|
| 14357 |
+
"grad_norm": 0.23608246445655823,
|
| 14358 |
+
"learning_rate": 3.397675383976754e-05,
|
| 14359 |
+
"loss": 1.7276872396469116,
|
| 14360 |
+
"step": 4100
|
| 14361 |
+
},
|
| 14362 |
+
{
|
| 14363 |
+
"epoch": 1.4302874976027338,
|
| 14364 |
+
"grad_norm": 0.1636294573545456,
|
| 14365 |
+
"learning_rate": 3.3935242839352433e-05,
|
| 14366 |
+
"loss": 1.8374544382095337,
|
| 14367 |
+
"step": 4102
|
| 14368 |
+
},
|
| 14369 |
+
{
|
| 14370 |
+
"epoch": 1.4309848841466604,
|
| 14371 |
+
"grad_norm": 0.27517223358154297,
|
| 14372 |
+
"learning_rate": 3.389373183893732e-05,
|
| 14373 |
+
"loss": 1.8124754428863525,
|
| 14374 |
+
"step": 4104
|
| 14375 |
+
},
|
| 14376 |
+
{
|
| 14377 |
+
"epoch": 1.431682270690587,
|
| 14378 |
+
"grad_norm": 0.17434199154376984,
|
| 14379 |
+
"learning_rate": 3.3852220838522206e-05,
|
| 14380 |
+
"loss": 1.9215025901794434,
|
| 14381 |
+
"step": 4106
|
| 14382 |
+
},
|
| 14383 |
+
{
|
| 14384 |
+
"epoch": 1.4323796572345135,
|
| 14385 |
+
"grad_norm": 0.2249208241701126,
|
| 14386 |
+
"learning_rate": 3.38107098381071e-05,
|
| 14387 |
+
"loss": 1.9626878499984741,
|
| 14388 |
+
"step": 4108
|
| 14389 |
+
},
|
| 14390 |
+
{
|
| 14391 |
+
"epoch": 1.4330770437784404,
|
| 14392 |
+
"grad_norm": 0.22073271870613098,
|
| 14393 |
+
"learning_rate": 3.376919883769199e-05,
|
| 14394 |
+
"loss": 1.8417041301727295,
|
| 14395 |
+
"step": 4110
|
| 14396 |
+
},
|
| 14397 |
+
{
|
| 14398 |
+
"epoch": 1.433774430322367,
|
| 14399 |
+
"grad_norm": 0.231496199965477,
|
| 14400 |
+
"learning_rate": 3.372768783727688e-05,
|
| 14401 |
+
"loss": 1.8525700569152832,
|
| 14402 |
+
"step": 4112
|
| 14403 |
+
},
|
| 14404 |
+
{
|
| 14405 |
+
"epoch": 1.4344718168662935,
|
| 14406 |
+
"grad_norm": 0.20072703063488007,
|
| 14407 |
+
"learning_rate": 3.368617683686177e-05,
|
| 14408 |
+
"loss": 1.935911774635315,
|
| 14409 |
+
"step": 4114
|
| 14410 |
+
},
|
| 14411 |
+
{
|
| 14412 |
+
"epoch": 1.4351692034102201,
|
| 14413 |
+
"grad_norm": 0.19549134373664856,
|
| 14414 |
+
"learning_rate": 3.364466583644666e-05,
|
| 14415 |
+
"loss": 1.8967294692993164,
|
| 14416 |
+
"step": 4116
|
| 14417 |
+
},
|
| 14418 |
+
{
|
| 14419 |
+
"epoch": 1.4358665899541467,
|
| 14420 |
+
"grad_norm": 0.2024395614862442,
|
| 14421 |
+
"learning_rate": 3.3603154836031546e-05,
|
| 14422 |
+
"loss": 1.7203136682510376,
|
| 14423 |
+
"step": 4118
|
| 14424 |
+
},
|
| 14425 |
+
{
|
| 14426 |
+
"epoch": 1.4365639764980735,
|
| 14427 |
+
"grad_norm": 0.16281065344810486,
|
| 14428 |
+
"learning_rate": 3.356164383561644e-05,
|
| 14429 |
+
"loss": 1.841869831085205,
|
| 14430 |
+
"step": 4120
|
| 14431 |
+
},
|
| 14432 |
+
{
|
| 14433 |
+
"epoch": 1.4372613630420001,
|
| 14434 |
+
"grad_norm": 0.20409001410007477,
|
| 14435 |
+
"learning_rate": 3.352013283520133e-05,
|
| 14436 |
+
"loss": 2.0007100105285645,
|
| 14437 |
+
"step": 4122
|
| 14438 |
+
},
|
| 14439 |
+
{
|
| 14440 |
+
"epoch": 1.4379587495859267,
|
| 14441 |
+
"grad_norm": 0.18246321380138397,
|
| 14442 |
+
"learning_rate": 3.3478621834786225e-05,
|
| 14443 |
+
"loss": 1.8394222259521484,
|
| 14444 |
+
"step": 4124
|
| 14445 |
+
},
|
| 14446 |
+
{
|
| 14447 |
+
"epoch": 1.4386561361298533,
|
| 14448 |
+
"grad_norm": 0.17156104743480682,
|
| 14449 |
+
"learning_rate": 3.343711083437111e-05,
|
| 14450 |
+
"loss": 1.9702026844024658,
|
| 14451 |
+
"step": 4126
|
| 14452 |
+
},
|
| 14453 |
+
{
|
| 14454 |
+
"epoch": 1.43935352267378,
|
| 14455 |
+
"grad_norm": 0.2202550321817398,
|
| 14456 |
+
"learning_rate": 3.3395599833956e-05,
|
| 14457 |
+
"loss": 1.8255903720855713,
|
| 14458 |
+
"step": 4128
|
| 14459 |
+
},
|
| 14460 |
+
{
|
| 14461 |
+
"epoch": 1.4400509092177067,
|
| 14462 |
+
"grad_norm": 0.22926436364650726,
|
| 14463 |
+
"learning_rate": 3.335408883354089e-05,
|
| 14464 |
+
"loss": 1.9207851886749268,
|
| 14465 |
+
"step": 4130
|
| 14466 |
+
},
|
| 14467 |
+
{
|
| 14468 |
+
"epoch": 1.4407482957616333,
|
| 14469 |
+
"grad_norm": 0.22136305272579193,
|
| 14470 |
+
"learning_rate": 3.331257783312578e-05,
|
| 14471 |
+
"loss": 1.8368303775787354,
|
| 14472 |
+
"step": 4132
|
| 14473 |
+
},
|
| 14474 |
+
{
|
| 14475 |
+
"epoch": 1.44144568230556,
|
| 14476 |
+
"grad_norm": 0.21406474709510803,
|
| 14477 |
+
"learning_rate": 3.3271066832710665e-05,
|
| 14478 |
+
"loss": 1.7291842699050903,
|
| 14479 |
+
"step": 4134
|
| 14480 |
+
},
|
| 14481 |
+
{
|
| 14482 |
+
"epoch": 1.4421430688494865,
|
| 14483 |
+
"grad_norm": 0.2021942436695099,
|
| 14484 |
+
"learning_rate": 3.3229555832295565e-05,
|
| 14485 |
+
"loss": 2.00429105758667,
|
| 14486 |
+
"step": 4136
|
| 14487 |
+
},
|
| 14488 |
+
{
|
| 14489 |
+
"epoch": 1.442840455393413,
|
| 14490 |
+
"grad_norm": 0.17133504152297974,
|
| 14491 |
+
"learning_rate": 3.318804483188045e-05,
|
| 14492 |
+
"loss": 1.8942899703979492,
|
| 14493 |
+
"step": 4138
|
| 14494 |
+
},
|
| 14495 |
+
{
|
| 14496 |
+
"epoch": 1.44353784193734,
|
| 14497 |
+
"grad_norm": 0.23039887845516205,
|
| 14498 |
+
"learning_rate": 3.314653383146534e-05,
|
| 14499 |
+
"loss": 1.8624145984649658,
|
| 14500 |
+
"step": 4140
|
| 14501 |
+
},
|
| 14502 |
+
{
|
| 14503 |
+
"epoch": 1.4442352284812665,
|
| 14504 |
+
"grad_norm": 0.19916106760501862,
|
| 14505 |
+
"learning_rate": 3.310502283105023e-05,
|
| 14506 |
+
"loss": 1.8991811275482178,
|
| 14507 |
+
"step": 4142
|
| 14508 |
+
},
|
| 14509 |
+
{
|
| 14510 |
+
"epoch": 1.444932615025193,
|
| 14511 |
+
"grad_norm": 0.2166530042886734,
|
| 14512 |
+
"learning_rate": 3.306351183063512e-05,
|
| 14513 |
+
"loss": 1.8596470355987549,
|
| 14514 |
+
"step": 4144
|
| 14515 |
+
},
|
| 14516 |
+
{
|
| 14517 |
+
"epoch": 1.4456300015691197,
|
| 14518 |
+
"grad_norm": 0.18740181624889374,
|
| 14519 |
+
"learning_rate": 3.302200083022001e-05,
|
| 14520 |
+
"loss": 1.948809266090393,
|
| 14521 |
+
"step": 4146
|
| 14522 |
+
},
|
| 14523 |
+
{
|
| 14524 |
+
"epoch": 1.4463273881130463,
|
| 14525 |
+
"grad_norm": 0.17723046243190765,
|
| 14526 |
+
"learning_rate": 3.29804898298049e-05,
|
| 14527 |
+
"loss": 1.8506078720092773,
|
| 14528 |
+
"step": 4148
|
| 14529 |
+
},
|
| 14530 |
+
{
|
| 14531 |
+
"epoch": 1.447024774656973,
|
| 14532 |
+
"grad_norm": 0.21443305909633636,
|
| 14533 |
+
"learning_rate": 3.293897882938979e-05,
|
| 14534 |
+
"loss": 1.7285115718841553,
|
| 14535 |
+
"step": 4150
|
| 14536 |
+
},
|
| 14537 |
+
{
|
| 14538 |
+
"epoch": 1.4477221612008997,
|
| 14539 |
+
"grad_norm": 0.19111402332782745,
|
| 14540 |
+
"learning_rate": 3.2897467828974684e-05,
|
| 14541 |
+
"loss": 1.6482958793640137,
|
| 14542 |
+
"step": 4152
|
| 14543 |
+
},
|
| 14544 |
+
{
|
| 14545 |
+
"epoch": 1.4484195477448263,
|
| 14546 |
+
"grad_norm": 0.3252273201942444,
|
| 14547 |
+
"learning_rate": 3.285595682855957e-05,
|
| 14548 |
+
"loss": 1.6977410316467285,
|
| 14549 |
+
"step": 4154
|
| 14550 |
+
},
|
| 14551 |
+
{
|
| 14552 |
+
"epoch": 1.4491169342887529,
|
| 14553 |
+
"grad_norm": 0.2883060574531555,
|
| 14554 |
+
"learning_rate": 3.281444582814446e-05,
|
| 14555 |
+
"loss": 1.6457706689834595,
|
| 14556 |
+
"step": 4156
|
| 14557 |
+
},
|
| 14558 |
+
{
|
| 14559 |
+
"epoch": 1.4498143208326795,
|
| 14560 |
+
"grad_norm": 0.235630065202713,
|
| 14561 |
+
"learning_rate": 3.277293482772935e-05,
|
| 14562 |
+
"loss": 1.8759286403656006,
|
| 14563 |
+
"step": 4158
|
| 14564 |
+
},
|
| 14565 |
+
{
|
| 14566 |
+
"epoch": 1.4505117073766063,
|
| 14567 |
+
"grad_norm": 0.18711936473846436,
|
| 14568 |
+
"learning_rate": 3.2731423827314236e-05,
|
| 14569 |
+
"loss": 1.8516727685928345,
|
| 14570 |
+
"step": 4160
|
| 14571 |
+
},
|
| 14572 |
+
{
|
| 14573 |
+
"epoch": 1.4512090939205329,
|
| 14574 |
+
"grad_norm": 0.22569718956947327,
|
| 14575 |
+
"learning_rate": 3.268991282689913e-05,
|
| 14576 |
+
"loss": 2.0689921379089355,
|
| 14577 |
+
"step": 4162
|
| 14578 |
+
},
|
| 14579 |
+
{
|
| 14580 |
+
"epoch": 1.4519064804644595,
|
| 14581 |
+
"grad_norm": 0.18883809447288513,
|
| 14582 |
+
"learning_rate": 3.264840182648402e-05,
|
| 14583 |
+
"loss": 1.899646520614624,
|
| 14584 |
+
"step": 4164
|
| 14585 |
+
},
|
| 14586 |
+
{
|
| 14587 |
+
"epoch": 1.452603867008386,
|
| 14588 |
+
"grad_norm": 0.21534138917922974,
|
| 14589 |
+
"learning_rate": 3.260689082606891e-05,
|
| 14590 |
+
"loss": 2.1046838760375977,
|
| 14591 |
+
"step": 4166
|
| 14592 |
+
},
|
| 14593 |
+
{
|
| 14594 |
+
"epoch": 1.4533012535523127,
|
| 14595 |
+
"grad_norm": 0.27049872279167175,
|
| 14596 |
+
"learning_rate": 3.25653798256538e-05,
|
| 14597 |
+
"loss": 2.0120396614074707,
|
| 14598 |
+
"step": 4168
|
| 14599 |
+
},
|
| 14600 |
+
{
|
| 14601 |
+
"epoch": 1.4539986400962395,
|
| 14602 |
+
"grad_norm": 0.23462948203086853,
|
| 14603 |
+
"learning_rate": 3.252386882523869e-05,
|
| 14604 |
+
"loss": 1.9374223947525024,
|
| 14605 |
+
"step": 4170
|
| 14606 |
+
},
|
| 14607 |
+
{
|
| 14608 |
+
"epoch": 1.4546960266401658,
|
| 14609 |
+
"grad_norm": 0.24656078219413757,
|
| 14610 |
+
"learning_rate": 3.2482357824823576e-05,
|
| 14611 |
+
"loss": 1.8995258808135986,
|
| 14612 |
+
"step": 4172
|
| 14613 |
+
},
|
| 14614 |
+
{
|
| 14615 |
+
"epoch": 1.4553934131840927,
|
| 14616 |
+
"grad_norm": 0.1956031173467636,
|
| 14617 |
+
"learning_rate": 3.244084682440847e-05,
|
| 14618 |
+
"loss": 1.9521234035491943,
|
| 14619 |
+
"step": 4174
|
| 14620 |
+
},
|
| 14621 |
+
{
|
| 14622 |
+
"epoch": 1.4560907997280192,
|
| 14623 |
+
"grad_norm": 0.29042989015579224,
|
| 14624 |
+
"learning_rate": 3.239933582399336e-05,
|
| 14625 |
+
"loss": 1.9295008182525635,
|
| 14626 |
+
"step": 4176
|
| 14627 |
+
},
|
| 14628 |
+
{
|
| 14629 |
+
"epoch": 1.4567881862719458,
|
| 14630 |
+
"grad_norm": 0.18132352828979492,
|
| 14631 |
+
"learning_rate": 3.235782482357825e-05,
|
| 14632 |
+
"loss": 1.949939250946045,
|
| 14633 |
+
"step": 4178
|
| 14634 |
+
},
|
| 14635 |
+
{
|
| 14636 |
+
"epoch": 1.4574855728158727,
|
| 14637 |
+
"grad_norm": 0.2633827328681946,
|
| 14638 |
+
"learning_rate": 3.231631382316314e-05,
|
| 14639 |
+
"loss": 1.9462300539016724,
|
| 14640 |
+
"step": 4180
|
| 14641 |
+
},
|
| 14642 |
+
{
|
| 14643 |
+
"epoch": 1.458182959359799,
|
| 14644 |
+
"grad_norm": 0.29535162448883057,
|
| 14645 |
+
"learning_rate": 3.227480282274803e-05,
|
| 14646 |
+
"loss": 1.8570556640625,
|
| 14647 |
+
"step": 4182
|
| 14648 |
+
},
|
| 14649 |
+
{
|
| 14650 |
+
"epoch": 1.4588803459037258,
|
| 14651 |
+
"grad_norm": 0.19173215329647064,
|
| 14652 |
+
"learning_rate": 3.2233291822332915e-05,
|
| 14653 |
+
"loss": 2.079622745513916,
|
| 14654 |
+
"step": 4184
|
| 14655 |
+
},
|
| 14656 |
+
{
|
| 14657 |
+
"epoch": 1.4595777324476524,
|
| 14658 |
+
"grad_norm": 0.22502847015857697,
|
| 14659 |
+
"learning_rate": 3.219178082191781e-05,
|
| 14660 |
+
"loss": 1.883758306503296,
|
| 14661 |
+
"step": 4186
|
| 14662 |
+
},
|
| 14663 |
+
{
|
| 14664 |
+
"epoch": 1.460275118991579,
|
| 14665 |
+
"grad_norm": 0.22633635997772217,
|
| 14666 |
+
"learning_rate": 3.21502698215027e-05,
|
| 14667 |
+
"loss": 1.8361179828643799,
|
| 14668 |
+
"step": 4188
|
| 14669 |
+
},
|
| 14670 |
+
{
|
| 14671 |
+
"epoch": 1.4609725055355056,
|
| 14672 |
+
"grad_norm": 0.20793241262435913,
|
| 14673 |
+
"learning_rate": 3.2108758821087595e-05,
|
| 14674 |
+
"loss": 2.172873020172119,
|
| 14675 |
+
"step": 4190
|
| 14676 |
+
},
|
| 14677 |
+
{
|
| 14678 |
+
"epoch": 1.4616698920794322,
|
| 14679 |
+
"grad_norm": 0.22675487399101257,
|
| 14680 |
+
"learning_rate": 3.206724782067248e-05,
|
| 14681 |
+
"loss": 1.9477754831314087,
|
| 14682 |
+
"step": 4192
|
| 14683 |
+
},
|
| 14684 |
+
{
|
| 14685 |
+
"epoch": 1.462367278623359,
|
| 14686 |
+
"grad_norm": 0.26028743386268616,
|
| 14687 |
+
"learning_rate": 3.202573682025737e-05,
|
| 14688 |
+
"loss": 1.8193738460540771,
|
| 14689 |
+
"step": 4194
|
| 14690 |
+
},
|
| 14691 |
+
{
|
| 14692 |
+
"epoch": 1.4630646651672856,
|
| 14693 |
+
"grad_norm": 0.2475419044494629,
|
| 14694 |
+
"learning_rate": 3.198422581984226e-05,
|
| 14695 |
+
"loss": 1.974073886871338,
|
| 14696 |
+
"step": 4196
|
| 14697 |
+
},
|
| 14698 |
+
{
|
| 14699 |
+
"epoch": 1.4637620517112122,
|
| 14700 |
+
"grad_norm": 0.2499392181634903,
|
| 14701 |
+
"learning_rate": 3.194271481942715e-05,
|
| 14702 |
+
"loss": 1.8304438591003418,
|
| 14703 |
+
"step": 4198
|
| 14704 |
+
},
|
| 14705 |
+
{
|
| 14706 |
+
"epoch": 1.4644594382551388,
|
| 14707 |
+
"grad_norm": 0.237641379237175,
|
| 14708 |
+
"learning_rate": 3.190120381901204e-05,
|
| 14709 |
+
"loss": 1.8094310760498047,
|
| 14710 |
+
"step": 4200
|
| 14711 |
+
},
|
| 14712 |
+
{
|
| 14713 |
+
"epoch": 1.4651568247990654,
|
| 14714 |
+
"grad_norm": 0.3710329234600067,
|
| 14715 |
+
"learning_rate": 3.1859692818596934e-05,
|
| 14716 |
+
"loss": 1.8436793088912964,
|
| 14717 |
+
"step": 4202
|
| 14718 |
+
},
|
| 14719 |
+
{
|
| 14720 |
+
"epoch": 1.4658542113429922,
|
| 14721 |
+
"grad_norm": 0.17323395609855652,
|
| 14722 |
+
"learning_rate": 3.181818181818182e-05,
|
| 14723 |
+
"loss": 1.7896754741668701,
|
| 14724 |
+
"step": 4204
|
| 14725 |
+
},
|
| 14726 |
+
{
|
| 14727 |
+
"epoch": 1.4665515978869188,
|
| 14728 |
+
"grad_norm": 0.19435246288776398,
|
| 14729 |
+
"learning_rate": 3.177667081776671e-05,
|
| 14730 |
+
"loss": 2.132152795791626,
|
| 14731 |
+
"step": 4206
|
| 14732 |
+
},
|
| 14733 |
+
{
|
| 14734 |
+
"epoch": 1.4672489844308454,
|
| 14735 |
+
"grad_norm": 0.2881922125816345,
|
| 14736 |
+
"learning_rate": 3.17351598173516e-05,
|
| 14737 |
+
"loss": 1.7988765239715576,
|
| 14738 |
+
"step": 4208
|
| 14739 |
+
},
|
| 14740 |
+
{
|
| 14741 |
+
"epoch": 1.467946370974772,
|
| 14742 |
+
"grad_norm": 0.19056060910224915,
|
| 14743 |
+
"learning_rate": 3.1693648816936487e-05,
|
| 14744 |
+
"loss": 1.7471990585327148,
|
| 14745 |
+
"step": 4210
|
| 14746 |
+
},
|
| 14747 |
+
{
|
| 14748 |
+
"epoch": 1.4686437575186986,
|
| 14749 |
+
"grad_norm": 0.20850984752178192,
|
| 14750 |
+
"learning_rate": 3.165213781652138e-05,
|
| 14751 |
+
"loss": 1.7588502168655396,
|
| 14752 |
+
"step": 4212
|
| 14753 |
+
},
|
| 14754 |
+
{
|
| 14755 |
+
"epoch": 1.4693411440626254,
|
| 14756 |
+
"grad_norm": 0.2419462502002716,
|
| 14757 |
+
"learning_rate": 3.161062681610627e-05,
|
| 14758 |
+
"loss": 1.7379381656646729,
|
| 14759 |
+
"step": 4214
|
| 14760 |
+
},
|
| 14761 |
+
{
|
| 14762 |
+
"epoch": 1.470038530606552,
|
| 14763 |
+
"grad_norm": 0.27557116746902466,
|
| 14764 |
+
"learning_rate": 3.156911581569116e-05,
|
| 14765 |
+
"loss": 1.7018725872039795,
|
| 14766 |
+
"step": 4216
|
| 14767 |
+
},
|
| 14768 |
+
{
|
| 14769 |
+
"epoch": 1.4707359171504786,
|
| 14770 |
+
"grad_norm": 0.21285809576511383,
|
| 14771 |
+
"learning_rate": 3.152760481527605e-05,
|
| 14772 |
+
"loss": 1.9607921838760376,
|
| 14773 |
+
"step": 4218
|
| 14774 |
+
},
|
| 14775 |
+
{
|
| 14776 |
+
"epoch": 1.4714333036944052,
|
| 14777 |
+
"grad_norm": 0.233015775680542,
|
| 14778 |
+
"learning_rate": 3.148609381486094e-05,
|
| 14779 |
+
"loss": 1.8311192989349365,
|
| 14780 |
+
"step": 4220
|
| 14781 |
+
},
|
| 14782 |
+
{
|
| 14783 |
+
"epoch": 1.4721306902383318,
|
| 14784 |
+
"grad_norm": 0.19445312023162842,
|
| 14785 |
+
"learning_rate": 3.1444582814445826e-05,
|
| 14786 |
+
"loss": 2.0046186447143555,
|
| 14787 |
+
"step": 4222
|
| 14788 |
+
},
|
| 14789 |
+
{
|
| 14790 |
+
"epoch": 1.4728280767822586,
|
| 14791 |
+
"grad_norm": 0.25397178530693054,
|
| 14792 |
+
"learning_rate": 3.140307181403072e-05,
|
| 14793 |
+
"loss": 1.7237898111343384,
|
| 14794 |
+
"step": 4224
|
| 14795 |
+
},
|
| 14796 |
+
{
|
| 14797 |
+
"epoch": 1.4735254633261852,
|
| 14798 |
+
"grad_norm": 0.17368128895759583,
|
| 14799 |
+
"learning_rate": 3.136156081361561e-05,
|
| 14800 |
+
"loss": 1.955993890762329,
|
| 14801 |
+
"step": 4226
|
| 14802 |
+
},
|
| 14803 |
+
{
|
| 14804 |
+
"epoch": 1.4742228498701118,
|
| 14805 |
+
"grad_norm": 0.2297562062740326,
|
| 14806 |
+
"learning_rate": 3.13200498132005e-05,
|
| 14807 |
+
"loss": 1.8776400089263916,
|
| 14808 |
+
"step": 4228
|
| 14809 |
+
},
|
| 14810 |
+
{
|
| 14811 |
+
"epoch": 1.4749202364140384,
|
| 14812 |
+
"grad_norm": 0.2735278308391571,
|
| 14813 |
+
"learning_rate": 3.127853881278539e-05,
|
| 14814 |
+
"loss": 1.8230985403060913,
|
| 14815 |
+
"step": 4230
|
| 14816 |
+
},
|
| 14817 |
+
{
|
| 14818 |
+
"epoch": 1.475617622957965,
|
| 14819 |
+
"grad_norm": 0.2162596881389618,
|
| 14820 |
+
"learning_rate": 3.123702781237028e-05,
|
| 14821 |
+
"loss": 1.7406185865402222,
|
| 14822 |
+
"step": 4232
|
| 14823 |
+
},
|
| 14824 |
+
{
|
| 14825 |
+
"epoch": 1.4763150095018918,
|
| 14826 |
+
"grad_norm": 0.26232606172561646,
|
| 14827 |
+
"learning_rate": 3.119551681195517e-05,
|
| 14828 |
+
"loss": 2.011214256286621,
|
| 14829 |
+
"step": 4234
|
| 14830 |
+
},
|
| 14831 |
+
{
|
| 14832 |
+
"epoch": 1.4770123960458184,
|
| 14833 |
+
"grad_norm": 0.25555673241615295,
|
| 14834 |
+
"learning_rate": 3.115400581154006e-05,
|
| 14835 |
+
"loss": 1.908860683441162,
|
| 14836 |
+
"step": 4236
|
| 14837 |
+
},
|
| 14838 |
+
{
|
| 14839 |
+
"epoch": 1.477709782589745,
|
| 14840 |
+
"grad_norm": 0.27135029435157776,
|
| 14841 |
+
"learning_rate": 3.1112494811124945e-05,
|
| 14842 |
+
"loss": 1.7173230648040771,
|
| 14843 |
+
"step": 4238
|
| 14844 |
+
},
|
| 14845 |
+
{
|
| 14846 |
+
"epoch": 1.4784071691336715,
|
| 14847 |
+
"grad_norm": 0.18783152103424072,
|
| 14848 |
+
"learning_rate": 3.1070983810709845e-05,
|
| 14849 |
+
"loss": 1.9788048267364502,
|
| 14850 |
+
"step": 4240
|
| 14851 |
+
},
|
| 14852 |
+
{
|
| 14853 |
+
"epoch": 1.4791045556775981,
|
| 14854 |
+
"grad_norm": 0.22805720567703247,
|
| 14855 |
+
"learning_rate": 3.102947281029473e-05,
|
| 14856 |
+
"loss": 2.030653476715088,
|
| 14857 |
+
"step": 4242
|
| 14858 |
+
},
|
| 14859 |
+
{
|
| 14860 |
+
"epoch": 1.479801942221525,
|
| 14861 |
+
"grad_norm": 0.1582372486591339,
|
| 14862 |
+
"learning_rate": 3.098796180987962e-05,
|
| 14863 |
+
"loss": 1.6906356811523438,
|
| 14864 |
+
"step": 4244
|
| 14865 |
+
},
|
| 14866 |
+
{
|
| 14867 |
+
"epoch": 1.4804993287654515,
|
| 14868 |
+
"grad_norm": 0.19490480422973633,
|
| 14869 |
+
"learning_rate": 3.094645080946451e-05,
|
| 14870 |
+
"loss": 1.8677330017089844,
|
| 14871 |
+
"step": 4246
|
| 14872 |
+
},
|
| 14873 |
+
{
|
| 14874 |
+
"epoch": 1.4811967153093781,
|
| 14875 |
+
"grad_norm": 0.22457078099250793,
|
| 14876 |
+
"learning_rate": 3.09049398090494e-05,
|
| 14877 |
+
"loss": 2.066915512084961,
|
| 14878 |
+
"step": 4248
|
| 14879 |
+
},
|
| 14880 |
+
{
|
| 14881 |
+
"epoch": 1.4818941018533047,
|
| 14882 |
+
"grad_norm": 0.19483765959739685,
|
| 14883 |
+
"learning_rate": 3.0863428808634284e-05,
|
| 14884 |
+
"loss": 1.9681627750396729,
|
| 14885 |
+
"step": 4250
|
| 14886 |
+
},
|
| 14887 |
+
{
|
| 14888 |
+
"epoch": 1.4825914883972313,
|
| 14889 |
+
"grad_norm": 0.18761757016181946,
|
| 14890 |
+
"learning_rate": 3.082191780821918e-05,
|
| 14891 |
+
"loss": 1.7936248779296875,
|
| 14892 |
+
"step": 4252
|
| 14893 |
+
},
|
| 14894 |
+
{
|
| 14895 |
+
"epoch": 1.4832888749411581,
|
| 14896 |
+
"grad_norm": 0.24503754079341888,
|
| 14897 |
+
"learning_rate": 3.078040680780407e-05,
|
| 14898 |
+
"loss": 2.069383144378662,
|
| 14899 |
+
"step": 4254
|
| 14900 |
+
},
|
| 14901 |
+
{
|
| 14902 |
+
"epoch": 1.4839862614850847,
|
| 14903 |
+
"grad_norm": 0.35354992747306824,
|
| 14904 |
+
"learning_rate": 3.0738895807388964e-05,
|
| 14905 |
+
"loss": 1.8734214305877686,
|
| 14906 |
+
"step": 4256
|
| 14907 |
+
},
|
| 14908 |
+
{
|
| 14909 |
+
"epoch": 1.4846836480290113,
|
| 14910 |
+
"grad_norm": 0.2514292001724243,
|
| 14911 |
+
"learning_rate": 3.069738480697385e-05,
|
| 14912 |
+
"loss": 1.918771743774414,
|
| 14913 |
+
"step": 4258
|
| 14914 |
+
},
|
| 14915 |
+
{
|
| 14916 |
+
"epoch": 1.485381034572938,
|
| 14917 |
+
"grad_norm": 0.1698964387178421,
|
| 14918 |
+
"learning_rate": 3.065587380655874e-05,
|
| 14919 |
+
"loss": 1.973615288734436,
|
| 14920 |
+
"step": 4260
|
| 14921 |
+
},
|
| 14922 |
+
{
|
| 14923 |
+
"epoch": 1.4860784211168645,
|
| 14924 |
+
"grad_norm": 0.20615416765213013,
|
| 14925 |
+
"learning_rate": 3.061436280614363e-05,
|
| 14926 |
+
"loss": 1.7398695945739746,
|
| 14927 |
+
"step": 4262
|
| 14928 |
+
},
|
| 14929 |
+
{
|
| 14930 |
+
"epoch": 1.4867758076607913,
|
| 14931 |
+
"grad_norm": 0.27245327830314636,
|
| 14932 |
+
"learning_rate": 3.0572851805728516e-05,
|
| 14933 |
+
"loss": 1.8311172723770142,
|
| 14934 |
+
"step": 4264
|
| 14935 |
+
},
|
| 14936 |
+
{
|
| 14937 |
+
"epoch": 1.4874731942047177,
|
| 14938 |
+
"grad_norm": 0.28381961584091187,
|
| 14939 |
+
"learning_rate": 3.053134080531341e-05,
|
| 14940 |
+
"loss": 2.0440845489501953,
|
| 14941 |
+
"step": 4266
|
| 14942 |
+
},
|
| 14943 |
+
{
|
| 14944 |
+
"epoch": 1.4881705807486445,
|
| 14945 |
+
"grad_norm": 0.22662436962127686,
|
| 14946 |
+
"learning_rate": 3.04898298048983e-05,
|
| 14947 |
+
"loss": 1.9301950931549072,
|
| 14948 |
+
"step": 4268
|
| 14949 |
+
},
|
| 14950 |
+
{
|
| 14951 |
+
"epoch": 1.488867967292571,
|
| 14952 |
+
"grad_norm": 0.18592658638954163,
|
| 14953 |
+
"learning_rate": 3.044831880448319e-05,
|
| 14954 |
+
"loss": 1.7836358547210693,
|
| 14955 |
+
"step": 4270
|
| 14956 |
+
},
|
| 14957 |
+
{
|
| 14958 |
+
"epoch": 1.4895653538364977,
|
| 14959 |
+
"grad_norm": 0.21467696130275726,
|
| 14960 |
+
"learning_rate": 3.0406807804068076e-05,
|
| 14961 |
+
"loss": 1.9252032041549683,
|
| 14962 |
+
"step": 4272
|
| 14963 |
+
},
|
| 14964 |
+
{
|
| 14965 |
+
"epoch": 1.4902627403804243,
|
| 14966 |
+
"grad_norm": 0.22956031560897827,
|
| 14967 |
+
"learning_rate": 3.036529680365297e-05,
|
| 14968 |
+
"loss": 1.911210298538208,
|
| 14969 |
+
"step": 4274
|
| 14970 |
+
},
|
| 14971 |
+
{
|
| 14972 |
+
"epoch": 1.4909601269243509,
|
| 14973 |
+
"grad_norm": 0.19773449003696442,
|
| 14974 |
+
"learning_rate": 3.032378580323786e-05,
|
| 14975 |
+
"loss": 1.9682331085205078,
|
| 14976 |
+
"step": 4276
|
| 14977 |
+
},
|
| 14978 |
+
{
|
| 14979 |
+
"epoch": 1.4916575134682777,
|
| 14980 |
+
"grad_norm": 0.19668564200401306,
|
| 14981 |
+
"learning_rate": 3.0282274802822752e-05,
|
| 14982 |
+
"loss": 2.0410146713256836,
|
| 14983 |
+
"step": 4278
|
| 14984 |
+
},
|
| 14985 |
+
{
|
| 14986 |
+
"epoch": 1.4923549000122043,
|
| 14987 |
+
"grad_norm": 0.2678745687007904,
|
| 14988 |
+
"learning_rate": 3.024076380240764e-05,
|
| 14989 |
+
"loss": 1.948699712753296,
|
| 14990 |
+
"step": 4280
|
| 14991 |
+
},
|
| 14992 |
+
{
|
| 14993 |
+
"epoch": 1.4930522865561309,
|
| 14994 |
+
"grad_norm": 0.15882091224193573,
|
| 14995 |
+
"learning_rate": 3.019925280199253e-05,
|
| 14996 |
+
"loss": 2.104851245880127,
|
| 14997 |
+
"step": 4282
|
| 14998 |
+
},
|
| 14999 |
+
{
|
| 15000 |
+
"epoch": 1.4937496731000575,
|
| 15001 |
+
"grad_norm": 0.25176993012428284,
|
| 15002 |
+
"learning_rate": 3.0157741801577422e-05,
|
| 15003 |
+
"loss": 1.7860289812088013,
|
| 15004 |
+
"step": 4284
|
| 15005 |
+
},
|
| 15006 |
+
{
|
| 15007 |
+
"epoch": 1.494447059643984,
|
| 15008 |
+
"grad_norm": 0.21591933071613312,
|
| 15009 |
+
"learning_rate": 3.011623080116231e-05,
|
| 15010 |
+
"loss": 1.8135545253753662,
|
| 15011 |
+
"step": 4286
|
| 15012 |
+
},
|
| 15013 |
+
{
|
| 15014 |
+
"epoch": 1.4951444461879109,
|
| 15015 |
+
"grad_norm": 0.23614440858364105,
|
| 15016 |
+
"learning_rate": 3.00747198007472e-05,
|
| 15017 |
+
"loss": 1.829087734222412,
|
| 15018 |
+
"step": 4288
|
| 15019 |
+
},
|
| 15020 |
+
{
|
| 15021 |
+
"epoch": 1.4958418327318375,
|
| 15022 |
+
"grad_norm": 0.21727608144283295,
|
| 15023 |
+
"learning_rate": 3.003320880033209e-05,
|
| 15024 |
+
"loss": 1.7977166175842285,
|
| 15025 |
+
"step": 4290
|
| 15026 |
+
},
|
| 15027 |
+
{
|
| 15028 |
+
"epoch": 1.496539219275764,
|
| 15029 |
+
"grad_norm": 0.19061827659606934,
|
| 15030 |
+
"learning_rate": 2.9991697799916978e-05,
|
| 15031 |
+
"loss": 1.9947948455810547,
|
| 15032 |
+
"step": 4292
|
| 15033 |
+
},
|
| 15034 |
+
{
|
| 15035 |
+
"epoch": 1.4972366058196906,
|
| 15036 |
+
"grad_norm": 0.24229376018047333,
|
| 15037 |
+
"learning_rate": 2.9950186799501868e-05,
|
| 15038 |
+
"loss": 1.9775480031967163,
|
| 15039 |
+
"step": 4294
|
| 15040 |
+
},
|
| 15041 |
+
{
|
| 15042 |
+
"epoch": 1.4979339923636172,
|
| 15043 |
+
"grad_norm": 0.17827463150024414,
|
| 15044 |
+
"learning_rate": 2.990867579908676e-05,
|
| 15045 |
+
"loss": 1.904175043106079,
|
| 15046 |
+
"step": 4296
|
| 15047 |
+
},
|
| 15048 |
+
{
|
| 15049 |
+
"epoch": 1.498631378907544,
|
| 15050 |
+
"grad_norm": 0.24656245112419128,
|
| 15051 |
+
"learning_rate": 2.9867164798671648e-05,
|
| 15052 |
+
"loss": 1.9311580657958984,
|
| 15053 |
+
"step": 4298
|
| 15054 |
+
},
|
| 15055 |
+
{
|
| 15056 |
+
"epoch": 1.4993287654514706,
|
| 15057 |
+
"grad_norm": 0.2341352105140686,
|
| 15058 |
+
"learning_rate": 2.982565379825654e-05,
|
| 15059 |
+
"loss": 1.8169183731079102,
|
| 15060 |
+
"step": 4300
|
| 15061 |
+
},
|
| 15062 |
+
{
|
| 15063 |
+
"epoch": 1.5000261519953972,
|
| 15064 |
+
"grad_norm": 0.21976277232170105,
|
| 15065 |
+
"learning_rate": 2.978414279784143e-05,
|
| 15066 |
+
"loss": 1.9069582223892212,
|
| 15067 |
+
"step": 4302
|
| 15068 |
+
},
|
| 15069 |
+
{
|
| 15070 |
+
"epoch": 1.5007235385393238,
|
| 15071 |
+
"grad_norm": 0.18122829496860504,
|
| 15072 |
+
"learning_rate": 2.9742631797426317e-05,
|
| 15073 |
+
"loss": 1.9984383583068848,
|
| 15074 |
+
"step": 4304
|
| 15075 |
+
},
|
| 15076 |
+
{
|
| 15077 |
+
"epoch": 1.5014209250832504,
|
| 15078 |
+
"grad_norm": 0.527238130569458,
|
| 15079 |
+
"learning_rate": 2.970112079701121e-05,
|
| 15080 |
+
"loss": 1.7675752639770508,
|
| 15081 |
+
"step": 4306
|
| 15082 |
+
},
|
| 15083 |
+
{
|
| 15084 |
+
"epoch": 1.5021183116271772,
|
| 15085 |
+
"grad_norm": 0.23009146749973297,
|
| 15086 |
+
"learning_rate": 2.96596097965961e-05,
|
| 15087 |
+
"loss": 1.8511323928833008,
|
| 15088 |
+
"step": 4308
|
| 15089 |
+
},
|
| 15090 |
+
{
|
| 15091 |
+
"epoch": 1.5028156981711038,
|
| 15092 |
+
"grad_norm": 0.2193315178155899,
|
| 15093 |
+
"learning_rate": 2.9618098796180987e-05,
|
| 15094 |
+
"loss": 1.7352030277252197,
|
| 15095 |
+
"step": 4310
|
| 15096 |
+
},
|
| 15097 |
+
{
|
| 15098 |
+
"epoch": 1.5035130847150304,
|
| 15099 |
+
"grad_norm": 0.2285013347864151,
|
| 15100 |
+
"learning_rate": 2.957658779576588e-05,
|
| 15101 |
+
"loss": 2.0133321285247803,
|
| 15102 |
+
"step": 4312
|
| 15103 |
+
},
|
| 15104 |
+
{
|
| 15105 |
+
"epoch": 1.504210471258957,
|
| 15106 |
+
"grad_norm": 0.1797766536474228,
|
| 15107 |
+
"learning_rate": 2.953507679535077e-05,
|
| 15108 |
+
"loss": 1.6843817234039307,
|
| 15109 |
+
"step": 4314
|
| 15110 |
+
},
|
| 15111 |
+
{
|
| 15112 |
+
"epoch": 1.5049078578028836,
|
| 15113 |
+
"grad_norm": 0.20497511327266693,
|
| 15114 |
+
"learning_rate": 2.9493565794935657e-05,
|
| 15115 |
+
"loss": 1.9545986652374268,
|
| 15116 |
+
"step": 4316
|
| 15117 |
+
},
|
| 15118 |
+
{
|
| 15119 |
+
"epoch": 1.5056052443468104,
|
| 15120 |
+
"grad_norm": 0.3286879360675812,
|
| 15121 |
+
"learning_rate": 2.945205479452055e-05,
|
| 15122 |
+
"loss": 1.9560670852661133,
|
| 15123 |
+
"step": 4318
|
| 15124 |
+
},
|
| 15125 |
+
{
|
| 15126 |
+
"epoch": 1.506302630890737,
|
| 15127 |
+
"grad_norm": 0.2364288568496704,
|
| 15128 |
+
"learning_rate": 2.941054379410544e-05,
|
| 15129 |
+
"loss": 1.679736852645874,
|
| 15130 |
+
"step": 4320
|
| 15131 |
+
},
|
| 15132 |
+
{
|
| 15133 |
+
"epoch": 1.5070000174346636,
|
| 15134 |
+
"grad_norm": 0.20072239637374878,
|
| 15135 |
+
"learning_rate": 2.9369032793690333e-05,
|
| 15136 |
+
"loss": 1.8908525705337524,
|
| 15137 |
+
"step": 4322
|
| 15138 |
+
},
|
| 15139 |
+
{
|
| 15140 |
+
"epoch": 1.5076974039785902,
|
| 15141 |
+
"grad_norm": 0.32942745089530945,
|
| 15142 |
+
"learning_rate": 2.932752179327522e-05,
|
| 15143 |
+
"loss": 1.7327306270599365,
|
| 15144 |
+
"step": 4324
|
| 15145 |
+
},
|
| 15146 |
+
{
|
| 15147 |
+
"epoch": 1.5083947905225168,
|
| 15148 |
+
"grad_norm": 0.2948322594165802,
|
| 15149 |
+
"learning_rate": 2.928601079286011e-05,
|
| 15150 |
+
"loss": 1.835234522819519,
|
| 15151 |
+
"step": 4326
|
| 15152 |
+
},
|
| 15153 |
+
{
|
| 15154 |
+
"epoch": 1.5090921770664436,
|
| 15155 |
+
"grad_norm": 0.205282524228096,
|
| 15156 |
+
"learning_rate": 2.9244499792445003e-05,
|
| 15157 |
+
"loss": 1.8638992309570312,
|
| 15158 |
+
"step": 4328
|
| 15159 |
+
},
|
| 15160 |
+
{
|
| 15161 |
+
"epoch": 1.50978956361037,
|
| 15162 |
+
"grad_norm": 0.2971500754356384,
|
| 15163 |
+
"learning_rate": 2.920298879202989e-05,
|
| 15164 |
+
"loss": 1.9175176620483398,
|
| 15165 |
+
"step": 4330
|
| 15166 |
+
},
|
| 15167 |
+
{
|
| 15168 |
+
"epoch": 1.5104869501542968,
|
| 15169 |
+
"grad_norm": 0.18545030057430267,
|
| 15170 |
+
"learning_rate": 2.916147779161478e-05,
|
| 15171 |
+
"loss": 1.9995113611221313,
|
| 15172 |
+
"step": 4332
|
| 15173 |
+
},
|
| 15174 |
+
{
|
| 15175 |
+
"epoch": 1.5111843366982234,
|
| 15176 |
+
"grad_norm": 0.1809265911579132,
|
| 15177 |
+
"learning_rate": 2.9119966791199672e-05,
|
| 15178 |
+
"loss": 1.9885342121124268,
|
| 15179 |
+
"step": 4334
|
| 15180 |
+
},
|
| 15181 |
+
{
|
| 15182 |
+
"epoch": 1.51188172324215,
|
| 15183 |
+
"grad_norm": 0.24308079481124878,
|
| 15184 |
+
"learning_rate": 2.907845579078456e-05,
|
| 15185 |
+
"loss": 1.9155973196029663,
|
| 15186 |
+
"step": 4336
|
| 15187 |
+
},
|
| 15188 |
+
{
|
| 15189 |
+
"epoch": 1.5125791097860768,
|
| 15190 |
+
"grad_norm": 0.21333220601081848,
|
| 15191 |
+
"learning_rate": 2.903694479036945e-05,
|
| 15192 |
+
"loss": 1.998091697692871,
|
| 15193 |
+
"step": 4338
|
| 15194 |
+
},
|
| 15195 |
+
{
|
| 15196 |
+
"epoch": 1.5132764963300032,
|
| 15197 |
+
"grad_norm": 0.23621611297130585,
|
| 15198 |
+
"learning_rate": 2.8995433789954342e-05,
|
| 15199 |
+
"loss": 1.6689598560333252,
|
| 15200 |
+
"step": 4340
|
| 15201 |
+
},
|
| 15202 |
+
{
|
| 15203 |
+
"epoch": 1.51397388287393,
|
| 15204 |
+
"grad_norm": 0.19262677431106567,
|
| 15205 |
+
"learning_rate": 2.8953922789539228e-05,
|
| 15206 |
+
"loss": 2.021580696105957,
|
| 15207 |
+
"step": 4342
|
| 15208 |
+
},
|
| 15209 |
+
{
|
| 15210 |
+
"epoch": 1.5146712694178566,
|
| 15211 |
+
"grad_norm": 0.21616120636463165,
|
| 15212 |
+
"learning_rate": 2.891241178912412e-05,
|
| 15213 |
+
"loss": 1.8001134395599365,
|
| 15214 |
+
"step": 4344
|
| 15215 |
+
},
|
| 15216 |
+
{
|
| 15217 |
+
"epoch": 1.5153686559617832,
|
| 15218 |
+
"grad_norm": 0.24169668555259705,
|
| 15219 |
+
"learning_rate": 2.887090078870901e-05,
|
| 15220 |
+
"loss": 1.6586966514587402,
|
| 15221 |
+
"step": 4346
|
| 15222 |
+
},
|
| 15223 |
+
{
|
| 15224 |
+
"epoch": 1.51606604250571,
|
| 15225 |
+
"grad_norm": 0.24617350101470947,
|
| 15226 |
+
"learning_rate": 2.8829389788293898e-05,
|
| 15227 |
+
"loss": 1.7206151485443115,
|
| 15228 |
+
"step": 4348
|
| 15229 |
+
},
|
| 15230 |
+
{
|
| 15231 |
+
"epoch": 1.5167634290496363,
|
| 15232 |
+
"grad_norm": 0.16805648803710938,
|
| 15233 |
+
"learning_rate": 2.878787878787879e-05,
|
| 15234 |
+
"loss": 1.9847954511642456,
|
| 15235 |
+
"step": 4350
|
| 15236 |
+
},
|
| 15237 |
+
{
|
| 15238 |
+
"epoch": 1.5174608155935632,
|
| 15239 |
+
"grad_norm": 0.17351919412612915,
|
| 15240 |
+
"learning_rate": 2.874636778746368e-05,
|
| 15241 |
+
"loss": 1.878028154373169,
|
| 15242 |
+
"step": 4352
|
| 15243 |
+
},
|
| 15244 |
+
{
|
| 15245 |
+
"epoch": 1.5181582021374898,
|
| 15246 |
+
"grad_norm": 0.19319580495357513,
|
| 15247 |
+
"learning_rate": 2.8704856787048567e-05,
|
| 15248 |
+
"loss": 1.91669499874115,
|
| 15249 |
+
"step": 4354
|
| 15250 |
+
},
|
| 15251 |
+
{
|
| 15252 |
+
"epoch": 1.5188555886814163,
|
| 15253 |
+
"grad_norm": 0.18220485746860504,
|
| 15254 |
+
"learning_rate": 2.866334578663346e-05,
|
| 15255 |
+
"loss": 1.76810884475708,
|
| 15256 |
+
"step": 4356
|
| 15257 |
+
},
|
| 15258 |
+
{
|
| 15259 |
+
"epoch": 1.5195529752253432,
|
| 15260 |
+
"grad_norm": 0.26242494583129883,
|
| 15261 |
+
"learning_rate": 2.862183478621835e-05,
|
| 15262 |
+
"loss": 1.7875232696533203,
|
| 15263 |
+
"step": 4358
|
| 15264 |
+
},
|
| 15265 |
+
{
|
| 15266 |
+
"epoch": 1.5202503617692695,
|
| 15267 |
+
"grad_norm": 0.22367031872272491,
|
| 15268 |
+
"learning_rate": 2.8580323785803237e-05,
|
| 15269 |
+
"loss": 1.9266059398651123,
|
| 15270 |
+
"step": 4360
|
| 15271 |
+
},
|
| 15272 |
+
{
|
| 15273 |
+
"epoch": 1.5209477483131963,
|
| 15274 |
+
"grad_norm": 0.3521316349506378,
|
| 15275 |
+
"learning_rate": 2.853881278538813e-05,
|
| 15276 |
+
"loss": 1.8663140535354614,
|
| 15277 |
+
"step": 4362
|
| 15278 |
+
},
|
| 15279 |
+
{
|
| 15280 |
+
"epoch": 1.521645134857123,
|
| 15281 |
+
"grad_norm": 0.21653883159160614,
|
| 15282 |
+
"learning_rate": 2.8497301784973017e-05,
|
| 15283 |
+
"loss": 1.9207054376602173,
|
| 15284 |
+
"step": 4364
|
| 15285 |
+
},
|
| 15286 |
+
{
|
| 15287 |
+
"epoch": 1.5223425214010495,
|
| 15288 |
+
"grad_norm": 0.19742324948310852,
|
| 15289 |
+
"learning_rate": 2.8455790784557913e-05,
|
| 15290 |
+
"loss": 1.9935832023620605,
|
| 15291 |
+
"step": 4366
|
| 15292 |
+
},
|
| 15293 |
+
{
|
| 15294 |
+
"epoch": 1.5230399079449763,
|
| 15295 |
+
"grad_norm": 0.23529601097106934,
|
| 15296 |
+
"learning_rate": 2.84142797841428e-05,
|
| 15297 |
+
"loss": 1.8649508953094482,
|
| 15298 |
+
"step": 4368
|
| 15299 |
+
},
|
| 15300 |
+
{
|
| 15301 |
+
"epoch": 1.5237372944889027,
|
| 15302 |
+
"grad_norm": 0.17153075337409973,
|
| 15303 |
+
"learning_rate": 2.8372768783727686e-05,
|
| 15304 |
+
"loss": 1.8191823959350586,
|
| 15305 |
+
"step": 4370
|
| 15306 |
+
},
|
| 15307 |
+
{
|
| 15308 |
+
"epoch": 1.5244346810328295,
|
| 15309 |
+
"grad_norm": 0.24875670671463013,
|
| 15310 |
+
"learning_rate": 2.8331257783312583e-05,
|
| 15311 |
+
"loss": 1.959450364112854,
|
| 15312 |
+
"step": 4372
|
| 15313 |
+
},
|
| 15314 |
+
{
|
| 15315 |
+
"epoch": 1.5251320675767561,
|
| 15316 |
+
"grad_norm": 0.23544973134994507,
|
| 15317 |
+
"learning_rate": 2.828974678289747e-05,
|
| 15318 |
+
"loss": 2.0190210342407227,
|
| 15319 |
+
"step": 4374
|
| 15320 |
+
},
|
| 15321 |
+
{
|
| 15322 |
+
"epoch": 1.5258294541206827,
|
| 15323 |
+
"grad_norm": 0.18131598830223083,
|
| 15324 |
+
"learning_rate": 2.8248235782482356e-05,
|
| 15325 |
+
"loss": 1.9842783212661743,
|
| 15326 |
+
"step": 4376
|
| 15327 |
+
},
|
| 15328 |
+
{
|
| 15329 |
+
"epoch": 1.5265268406646095,
|
| 15330 |
+
"grad_norm": 0.1840776801109314,
|
| 15331 |
+
"learning_rate": 2.820672478206725e-05,
|
| 15332 |
+
"loss": 2.0165488719940186,
|
| 15333 |
+
"step": 4378
|
| 15334 |
+
},
|
| 15335 |
+
{
|
| 15336 |
+
"epoch": 1.527224227208536,
|
| 15337 |
+
"grad_norm": 0.2549632489681244,
|
| 15338 |
+
"learning_rate": 2.816521378165214e-05,
|
| 15339 |
+
"loss": 1.9990711212158203,
|
| 15340 |
+
"step": 4380
|
| 15341 |
+
},
|
| 15342 |
+
{
|
| 15343 |
+
"epoch": 1.5279216137524627,
|
| 15344 |
+
"grad_norm": 0.20285262167453766,
|
| 15345 |
+
"learning_rate": 2.8123702781237026e-05,
|
| 15346 |
+
"loss": 1.9805941581726074,
|
| 15347 |
+
"step": 4382
|
| 15348 |
+
},
|
| 15349 |
+
{
|
| 15350 |
+
"epoch": 1.5286190002963893,
|
| 15351 |
+
"grad_norm": 0.2610595226287842,
|
| 15352 |
+
"learning_rate": 2.808219178082192e-05,
|
| 15353 |
+
"loss": 1.9052305221557617,
|
| 15354 |
+
"step": 4384
|
| 15355 |
+
},
|
| 15356 |
+
{
|
| 15357 |
+
"epoch": 1.529316386840316,
|
| 15358 |
+
"grad_norm": 0.19016319513320923,
|
| 15359 |
+
"learning_rate": 2.804068078040681e-05,
|
| 15360 |
+
"loss": 1.8738257884979248,
|
| 15361 |
+
"step": 4386
|
| 15362 |
+
},
|
| 15363 |
+
{
|
| 15364 |
+
"epoch": 1.5300137733842427,
|
| 15365 |
+
"grad_norm": 0.24855868518352509,
|
| 15366 |
+
"learning_rate": 2.7999169779991702e-05,
|
| 15367 |
+
"loss": 1.9404520988464355,
|
| 15368 |
+
"step": 4388
|
| 15369 |
+
},
|
| 15370 |
+
{
|
| 15371 |
+
"epoch": 1.530711159928169,
|
| 15372 |
+
"grad_norm": 0.24818985164165497,
|
| 15373 |
+
"learning_rate": 2.795765877957659e-05,
|
| 15374 |
+
"loss": 1.8301239013671875,
|
| 15375 |
+
"step": 4390
|
| 15376 |
+
},
|
| 15377 |
+
{
|
| 15378 |
+
"epoch": 1.531408546472096,
|
| 15379 |
+
"grad_norm": 0.2025291919708252,
|
| 15380 |
+
"learning_rate": 2.791614777916148e-05,
|
| 15381 |
+
"loss": 1.9974764585494995,
|
| 15382 |
+
"step": 4392
|
| 15383 |
+
},
|
| 15384 |
+
{
|
| 15385 |
+
"epoch": 1.5321059330160225,
|
| 15386 |
+
"grad_norm": 0.23878057301044464,
|
| 15387 |
+
"learning_rate": 2.787463677874637e-05,
|
| 15388 |
+
"loss": 1.8272838592529297,
|
| 15389 |
+
"step": 4394
|
| 15390 |
+
},
|
| 15391 |
+
{
|
| 15392 |
+
"epoch": 1.532803319559949,
|
| 15393 |
+
"grad_norm": 0.16763503849506378,
|
| 15394 |
+
"learning_rate": 2.7833125778331258e-05,
|
| 15395 |
+
"loss": 1.6806379556655884,
|
| 15396 |
+
"step": 4396
|
| 15397 |
+
},
|
| 15398 |
+
{
|
| 15399 |
+
"epoch": 1.5335007061038757,
|
| 15400 |
+
"grad_norm": 0.1883159577846527,
|
| 15401 |
+
"learning_rate": 2.7791614777916148e-05,
|
| 15402 |
+
"loss": 1.9163085222244263,
|
| 15403 |
+
"step": 4398
|
| 15404 |
+
},
|
| 15405 |
+
{
|
| 15406 |
+
"epoch": 1.5341980926478023,
|
| 15407 |
+
"grad_norm": 0.22081787884235382,
|
| 15408 |
+
"learning_rate": 2.775010377750104e-05,
|
| 15409 |
+
"loss": 1.7372932434082031,
|
| 15410 |
+
"step": 4400
|
| 15411 |
+
},
|
| 15412 |
+
{
|
| 15413 |
+
"epoch": 1.534895479191729,
|
| 15414 |
+
"grad_norm": 0.1913776695728302,
|
| 15415 |
+
"learning_rate": 2.7708592777085928e-05,
|
| 15416 |
+
"loss": 1.8430018424987793,
|
| 15417 |
+
"step": 4402
|
| 15418 |
+
},
|
| 15419 |
+
{
|
| 15420 |
+
"epoch": 1.5355928657356557,
|
| 15421 |
+
"grad_norm": 0.17796553671360016,
|
| 15422 |
+
"learning_rate": 2.7667081776670818e-05,
|
| 15423 |
+
"loss": 1.8803733587265015,
|
| 15424 |
+
"step": 4404
|
| 15425 |
+
},
|
| 15426 |
+
{
|
| 15427 |
+
"epoch": 1.5362902522795823,
|
| 15428 |
+
"grad_norm": 0.2805418074131012,
|
| 15429 |
+
"learning_rate": 2.762557077625571e-05,
|
| 15430 |
+
"loss": 2.04244327545166,
|
| 15431 |
+
"step": 4406
|
| 15432 |
+
},
|
| 15433 |
+
{
|
| 15434 |
+
"epoch": 1.5369876388235089,
|
| 15435 |
+
"grad_norm": 0.18227362632751465,
|
| 15436 |
+
"learning_rate": 2.7584059775840597e-05,
|
| 15437 |
+
"loss": 1.9621096849441528,
|
| 15438 |
+
"step": 4408
|
| 15439 |
+
},
|
| 15440 |
+
{
|
| 15441 |
+
"epoch": 1.5376850253674355,
|
| 15442 |
+
"grad_norm": 0.24022343754768372,
|
| 15443 |
+
"learning_rate": 2.754254877542549e-05,
|
| 15444 |
+
"loss": 1.6480050086975098,
|
| 15445 |
+
"step": 4410
|
| 15446 |
+
},
|
| 15447 |
+
{
|
| 15448 |
+
"epoch": 1.5383824119113623,
|
| 15449 |
+
"grad_norm": 0.1897001564502716,
|
| 15450 |
+
"learning_rate": 2.750103777501038e-05,
|
| 15451 |
+
"loss": 1.7422631978988647,
|
| 15452 |
+
"step": 4412
|
| 15453 |
+
},
|
| 15454 |
+
{
|
| 15455 |
+
"epoch": 1.5390797984552886,
|
| 15456 |
+
"grad_norm": 0.17075501382350922,
|
| 15457 |
+
"learning_rate": 2.7459526774595267e-05,
|
| 15458 |
+
"loss": 1.953518033027649,
|
| 15459 |
+
"step": 4414
|
| 15460 |
+
},
|
| 15461 |
+
{
|
| 15462 |
+
"epoch": 1.5397771849992155,
|
| 15463 |
+
"grad_norm": 0.285891056060791,
|
| 15464 |
+
"learning_rate": 2.741801577418016e-05,
|
| 15465 |
+
"loss": 1.8298866748809814,
|
| 15466 |
+
"step": 4416
|
| 15467 |
+
},
|
| 15468 |
+
{
|
| 15469 |
+
"epoch": 1.540474571543142,
|
| 15470 |
+
"grad_norm": 0.2010376900434494,
|
| 15471 |
+
"learning_rate": 2.737650477376505e-05,
|
| 15472 |
+
"loss": 1.6861653327941895,
|
| 15473 |
+
"step": 4418
|
| 15474 |
+
},
|
| 15475 |
+
{
|
| 15476 |
+
"epoch": 1.5411719580870686,
|
| 15477 |
+
"grad_norm": 0.28427520394325256,
|
| 15478 |
+
"learning_rate": 2.7334993773349937e-05,
|
| 15479 |
+
"loss": 1.6987539529800415,
|
| 15480 |
+
"step": 4420
|
| 15481 |
+
},
|
| 15482 |
+
{
|
| 15483 |
+
"epoch": 1.5418693446309955,
|
| 15484 |
+
"grad_norm": 0.26670607924461365,
|
| 15485 |
+
"learning_rate": 2.729348277293483e-05,
|
| 15486 |
+
"loss": 1.6583788394927979,
|
| 15487 |
+
"step": 4422
|
| 15488 |
+
},
|
| 15489 |
+
{
|
| 15490 |
+
"epoch": 1.5425667311749218,
|
| 15491 |
+
"grad_norm": 0.21028931438922882,
|
| 15492 |
+
"learning_rate": 2.725197177251972e-05,
|
| 15493 |
+
"loss": 2.1383423805236816,
|
| 15494 |
+
"step": 4424
|
| 15495 |
+
},
|
| 15496 |
+
{
|
| 15497 |
+
"epoch": 1.5432641177188486,
|
| 15498 |
+
"grad_norm": 0.19236426055431366,
|
| 15499 |
+
"learning_rate": 2.7210460772104606e-05,
|
| 15500 |
+
"loss": 1.8114062547683716,
|
| 15501 |
+
"step": 4426
|
| 15502 |
+
},
|
| 15503 |
+
{
|
| 15504 |
+
"epoch": 1.5439615042627752,
|
| 15505 |
+
"grad_norm": 0.1726246178150177,
|
| 15506 |
+
"learning_rate": 2.71689497716895e-05,
|
| 15507 |
+
"loss": 1.966844081878662,
|
| 15508 |
+
"step": 4428
|
| 15509 |
+
},
|
| 15510 |
+
{
|
| 15511 |
+
"epoch": 1.5446588908067018,
|
| 15512 |
+
"grad_norm": 0.18041053414344788,
|
| 15513 |
+
"learning_rate": 2.712743877127439e-05,
|
| 15514 |
+
"loss": 2.085667133331299,
|
| 15515 |
+
"step": 4430
|
| 15516 |
+
},
|
| 15517 |
+
{
|
| 15518 |
+
"epoch": 1.5453562773506286,
|
| 15519 |
+
"grad_norm": 0.22201724350452423,
|
| 15520 |
+
"learning_rate": 2.7085927770859276e-05,
|
| 15521 |
+
"loss": 1.876138687133789,
|
| 15522 |
+
"step": 4432
|
| 15523 |
+
},
|
| 15524 |
+
{
|
| 15525 |
+
"epoch": 1.546053663894555,
|
| 15526 |
+
"grad_norm": 0.2123415172100067,
|
| 15527 |
+
"learning_rate": 2.704441677044417e-05,
|
| 15528 |
+
"loss": 1.756211757659912,
|
| 15529 |
+
"step": 4434
|
| 15530 |
+
},
|
| 15531 |
+
{
|
| 15532 |
+
"epoch": 1.5467510504384818,
|
| 15533 |
+
"grad_norm": 0.2050902545452118,
|
| 15534 |
+
"learning_rate": 2.700290577002906e-05,
|
| 15535 |
+
"loss": 1.9153730869293213,
|
| 15536 |
+
"step": 4436
|
| 15537 |
+
},
|
| 15538 |
+
{
|
| 15539 |
+
"epoch": 1.5474484369824084,
|
| 15540 |
+
"grad_norm": 0.2251085489988327,
|
| 15541 |
+
"learning_rate": 2.6961394769613952e-05,
|
| 15542 |
+
"loss": 1.8800716400146484,
|
| 15543 |
+
"step": 4438
|
| 15544 |
+
},
|
| 15545 |
+
{
|
| 15546 |
+
"epoch": 1.548145823526335,
|
| 15547 |
+
"grad_norm": 0.21331456303596497,
|
| 15548 |
+
"learning_rate": 2.691988376919884e-05,
|
| 15549 |
+
"loss": 1.902909278869629,
|
| 15550 |
+
"step": 4440
|
| 15551 |
+
},
|
| 15552 |
+
{
|
| 15553 |
+
"epoch": 1.5488432100702618,
|
| 15554 |
+
"grad_norm": 0.17269904911518097,
|
| 15555 |
+
"learning_rate": 2.687837276878373e-05,
|
| 15556 |
+
"loss": 1.8585556745529175,
|
| 15557 |
+
"step": 4442
|
| 15558 |
+
},
|
| 15559 |
+
{
|
| 15560 |
+
"epoch": 1.5495405966141882,
|
| 15561 |
+
"grad_norm": 0.2580990791320801,
|
| 15562 |
+
"learning_rate": 2.6836861768368622e-05,
|
| 15563 |
+
"loss": 1.897294044494629,
|
| 15564 |
+
"step": 4444
|
| 15565 |
+
},
|
| 15566 |
+
{
|
| 15567 |
+
"epoch": 1.550237983158115,
|
| 15568 |
+
"grad_norm": 0.20308732986450195,
|
| 15569 |
+
"learning_rate": 2.679535076795351e-05,
|
| 15570 |
+
"loss": 1.9232985973358154,
|
| 15571 |
+
"step": 4446
|
| 15572 |
+
},
|
| 15573 |
+
{
|
| 15574 |
+
"epoch": 1.5509353697020416,
|
| 15575 |
+
"grad_norm": 0.24419395625591278,
|
| 15576 |
+
"learning_rate": 2.6753839767538398e-05,
|
| 15577 |
+
"loss": 1.9122428894042969,
|
| 15578 |
+
"step": 4448
|
| 15579 |
+
},
|
| 15580 |
+
{
|
| 15581 |
+
"epoch": 1.5516327562459682,
|
| 15582 |
+
"grad_norm": 0.17414434254169464,
|
| 15583 |
+
"learning_rate": 2.671232876712329e-05,
|
| 15584 |
+
"loss": 1.7522237300872803,
|
| 15585 |
+
"step": 4450
|
| 15586 |
+
},
|
| 15587 |
+
{
|
| 15588 |
+
"epoch": 1.552330142789895,
|
| 15589 |
+
"grad_norm": 0.24114203453063965,
|
| 15590 |
+
"learning_rate": 2.6670817766708178e-05,
|
| 15591 |
+
"loss": 1.7971198558807373,
|
| 15592 |
+
"step": 4452
|
| 15593 |
+
},
|
| 15594 |
+
{
|
| 15595 |
+
"epoch": 1.5530275293338214,
|
| 15596 |
+
"grad_norm": 0.17447638511657715,
|
| 15597 |
+
"learning_rate": 2.6629306766293068e-05,
|
| 15598 |
+
"loss": 1.81462824344635,
|
| 15599 |
+
"step": 4454
|
| 15600 |
+
},
|
| 15601 |
+
{
|
| 15602 |
+
"epoch": 1.5537249158777482,
|
| 15603 |
+
"grad_norm": 0.21867063641548157,
|
| 15604 |
+
"learning_rate": 2.658779576587796e-05,
|
| 15605 |
+
"loss": 1.854804277420044,
|
| 15606 |
+
"step": 4456
|
| 15607 |
+
},
|
| 15608 |
+
{
|
| 15609 |
+
"epoch": 1.5544223024216748,
|
| 15610 |
+
"grad_norm": 0.16868700087070465,
|
| 15611 |
+
"learning_rate": 2.6546284765462848e-05,
|
| 15612 |
+
"loss": 2.0059430599212646,
|
| 15613 |
+
"step": 4458
|
| 15614 |
+
},
|
| 15615 |
+
{
|
| 15616 |
+
"epoch": 1.5551196889656014,
|
| 15617 |
+
"grad_norm": 0.2346510887145996,
|
| 15618 |
+
"learning_rate": 2.650477376504774e-05,
|
| 15619 |
+
"loss": 1.4958382844924927,
|
| 15620 |
+
"step": 4460
|
| 15621 |
+
},
|
| 15622 |
+
{
|
| 15623 |
+
"epoch": 1.5558170755095282,
|
| 15624 |
+
"grad_norm": 0.26675206422805786,
|
| 15625 |
+
"learning_rate": 2.646326276463263e-05,
|
| 15626 |
+
"loss": 1.9033410549163818,
|
| 15627 |
+
"step": 4462
|
| 15628 |
+
},
|
| 15629 |
+
{
|
| 15630 |
+
"epoch": 1.5565144620534546,
|
| 15631 |
+
"grad_norm": 0.18497225642204285,
|
| 15632 |
+
"learning_rate": 2.6421751764217517e-05,
|
| 15633 |
+
"loss": 1.9528168439865112,
|
| 15634 |
+
"step": 4464
|
| 15635 |
+
},
|
| 15636 |
+
{
|
| 15637 |
+
"epoch": 1.5572118485973814,
|
| 15638 |
+
"grad_norm": 0.20328418910503387,
|
| 15639 |
+
"learning_rate": 2.638024076380241e-05,
|
| 15640 |
+
"loss": 1.83001708984375,
|
| 15641 |
+
"step": 4466
|
| 15642 |
+
},
|
| 15643 |
+
{
|
| 15644 |
+
"epoch": 1.557909235141308,
|
| 15645 |
+
"grad_norm": 0.21240051090717316,
|
| 15646 |
+
"learning_rate": 2.63387297633873e-05,
|
| 15647 |
+
"loss": 1.8499531745910645,
|
| 15648 |
+
"step": 4468
|
| 15649 |
+
},
|
| 15650 |
+
{
|
| 15651 |
+
"epoch": 1.5586066216852346,
|
| 15652 |
+
"grad_norm": 0.24162444472312927,
|
| 15653 |
+
"learning_rate": 2.6297218762972187e-05,
|
| 15654 |
+
"loss": 1.6314120292663574,
|
| 15655 |
+
"step": 4470
|
| 15656 |
+
},
|
| 15657 |
+
{
|
| 15658 |
+
"epoch": 1.5593040082291614,
|
| 15659 |
+
"grad_norm": 0.27374324202537537,
|
| 15660 |
+
"learning_rate": 2.625570776255708e-05,
|
| 15661 |
+
"loss": 1.7221617698669434,
|
| 15662 |
+
"step": 4472
|
| 15663 |
+
},
|
| 15664 |
+
{
|
| 15665 |
+
"epoch": 1.5600013947730877,
|
| 15666 |
+
"grad_norm": 0.25410524010658264,
|
| 15667 |
+
"learning_rate": 2.6214196762141967e-05,
|
| 15668 |
+
"loss": 1.7684450149536133,
|
| 15669 |
+
"step": 4474
|
| 15670 |
+
},
|
| 15671 |
+
{
|
| 15672 |
+
"epoch": 1.5606987813170146,
|
| 15673 |
+
"grad_norm": 0.2422337681055069,
|
| 15674 |
+
"learning_rate": 2.6172685761726856e-05,
|
| 15675 |
+
"loss": 1.8309746980667114,
|
| 15676 |
+
"step": 4476
|
| 15677 |
+
},
|
| 15678 |
+
{
|
| 15679 |
+
"epoch": 1.5613961678609412,
|
| 15680 |
+
"grad_norm": 0.23445764183998108,
|
| 15681 |
+
"learning_rate": 2.613117476131175e-05,
|
| 15682 |
+
"loss": 2.1427254676818848,
|
| 15683 |
+
"step": 4478
|
| 15684 |
+
},
|
| 15685 |
+
{
|
| 15686 |
+
"epoch": 1.5620935544048677,
|
| 15687 |
+
"grad_norm": 0.1943419724702835,
|
| 15688 |
+
"learning_rate": 2.6089663760896636e-05,
|
| 15689 |
+
"loss": 1.7775300741195679,
|
| 15690 |
+
"step": 4480
|
| 15691 |
+
},
|
| 15692 |
+
{
|
| 15693 |
+
"epoch": 1.5627909409487943,
|
| 15694 |
+
"grad_norm": 0.20946148037910461,
|
| 15695 |
+
"learning_rate": 2.6048152760481533e-05,
|
| 15696 |
+
"loss": 1.8440033197402954,
|
| 15697 |
+
"step": 4482
|
| 15698 |
+
},
|
| 15699 |
+
{
|
| 15700 |
+
"epoch": 1.563488327492721,
|
| 15701 |
+
"grad_norm": 0.19684435427188873,
|
| 15702 |
+
"learning_rate": 2.600664176006642e-05,
|
| 15703 |
+
"loss": 1.8125154972076416,
|
| 15704 |
+
"step": 4484
|
| 15705 |
+
},
|
| 15706 |
+
{
|
| 15707 |
+
"epoch": 1.5641857140366477,
|
| 15708 |
+
"grad_norm": 0.26996201276779175,
|
| 15709 |
+
"learning_rate": 2.5965130759651306e-05,
|
| 15710 |
+
"loss": 1.7742915153503418,
|
| 15711 |
+
"step": 4486
|
| 15712 |
+
},
|
| 15713 |
+
{
|
| 15714 |
+
"epoch": 1.5648831005805743,
|
| 15715 |
+
"grad_norm": 0.174392968416214,
|
| 15716 |
+
"learning_rate": 2.59236197592362e-05,
|
| 15717 |
+
"loss": 1.9183518886566162,
|
| 15718 |
+
"step": 4488
|
| 15719 |
+
},
|
| 15720 |
+
{
|
| 15721 |
+
"epoch": 1.565580487124501,
|
| 15722 |
+
"grad_norm": 0.17263713479042053,
|
| 15723 |
+
"learning_rate": 2.588210875882109e-05,
|
| 15724 |
+
"loss": 1.842463731765747,
|
| 15725 |
+
"step": 4490
|
| 15726 |
+
},
|
| 15727 |
+
{
|
| 15728 |
+
"epoch": 1.5662778736684275,
|
| 15729 |
+
"grad_norm": 0.2301662117242813,
|
| 15730 |
+
"learning_rate": 2.5840597758405975e-05,
|
| 15731 |
+
"loss": 1.9093573093414307,
|
| 15732 |
+
"step": 4492
|
| 15733 |
+
},
|
| 15734 |
+
{
|
| 15735 |
+
"epoch": 1.5669752602123541,
|
| 15736 |
+
"grad_norm": 0.1826668381690979,
|
| 15737 |
+
"learning_rate": 2.579908675799087e-05,
|
| 15738 |
+
"loss": 1.9088093042373657,
|
| 15739 |
+
"step": 4494
|
| 15740 |
+
},
|
| 15741 |
+
{
|
| 15742 |
+
"epoch": 1.567672646756281,
|
| 15743 |
+
"grad_norm": 0.18410944938659668,
|
| 15744 |
+
"learning_rate": 2.575757575757576e-05,
|
| 15745 |
+
"loss": 1.831756830215454,
|
| 15746 |
+
"step": 4496
|
| 15747 |
+
},
|
| 15748 |
+
{
|
| 15749 |
+
"epoch": 1.5683700333002075,
|
| 15750 |
+
"grad_norm": 0.22626711428165436,
|
| 15751 |
+
"learning_rate": 2.5716064757160645e-05,
|
| 15752 |
+
"loss": 2.102736711502075,
|
| 15753 |
+
"step": 4498
|
| 15754 |
+
},
|
| 15755 |
+
{
|
| 15756 |
+
"epoch": 1.5690674198441341,
|
| 15757 |
+
"grad_norm": 0.24183250963687897,
|
| 15758 |
+
"learning_rate": 2.5674553756745538e-05,
|
| 15759 |
+
"loss": 1.976166009902954,
|
| 15760 |
+
"step": 4500
|
| 15761 |
+
},
|
| 15762 |
+
{
|
| 15763 |
+
"epoch": 1.5697648063880607,
|
| 15764 |
+
"grad_norm": 0.24379684031009674,
|
| 15765 |
+
"learning_rate": 2.5633042756330428e-05,
|
| 15766 |
+
"loss": 1.8924784660339355,
|
| 15767 |
+
"step": 4502
|
| 15768 |
+
},
|
| 15769 |
+
{
|
| 15770 |
+
"epoch": 1.5704621929319873,
|
| 15771 |
+
"grad_norm": 0.17403602600097656,
|
| 15772 |
+
"learning_rate": 2.559153175591532e-05,
|
| 15773 |
+
"loss": 2.0470175743103027,
|
| 15774 |
+
"step": 4504
|
| 15775 |
+
},
|
| 15776 |
+
{
|
| 15777 |
+
"epoch": 1.5711595794759141,
|
| 15778 |
+
"grad_norm": 0.1863819658756256,
|
| 15779 |
+
"learning_rate": 2.5550020755500208e-05,
|
| 15780 |
+
"loss": 2.1825854778289795,
|
| 15781 |
+
"step": 4506
|
| 15782 |
+
},
|
| 15783 |
+
{
|
| 15784 |
+
"epoch": 1.5718569660198405,
|
| 15785 |
+
"grad_norm": 0.16507472097873688,
|
| 15786 |
+
"learning_rate": 2.5508509755085098e-05,
|
| 15787 |
+
"loss": 1.951021671295166,
|
| 15788 |
+
"step": 4508
|
| 15789 |
+
},
|
| 15790 |
+
{
|
| 15791 |
+
"epoch": 1.5725543525637673,
|
| 15792 |
+
"grad_norm": 0.22446586191654205,
|
| 15793 |
+
"learning_rate": 2.546699875466999e-05,
|
| 15794 |
+
"loss": 1.9840681552886963,
|
| 15795 |
+
"step": 4510
|
| 15796 |
+
},
|
| 15797 |
+
{
|
| 15798 |
+
"epoch": 1.573251739107694,
|
| 15799 |
+
"grad_norm": 0.23697252571582794,
|
| 15800 |
+
"learning_rate": 2.5425487754254877e-05,
|
| 15801 |
+
"loss": 2.0239810943603516,
|
| 15802 |
+
"step": 4512
|
| 15803 |
+
},
|
| 15804 |
+
{
|
| 15805 |
+
"epoch": 1.5739491256516205,
|
| 15806 |
+
"grad_norm": 0.22238145768642426,
|
| 15807 |
+
"learning_rate": 2.5383976753839767e-05,
|
| 15808 |
+
"loss": 1.808410406112671,
|
| 15809 |
+
"step": 4514
|
| 15810 |
+
},
|
| 15811 |
+
{
|
| 15812 |
+
"epoch": 1.5746465121955473,
|
| 15813 |
+
"grad_norm": 0.31593209505081177,
|
| 15814 |
+
"learning_rate": 2.534246575342466e-05,
|
| 15815 |
+
"loss": 1.7202047109603882,
|
| 15816 |
+
"step": 4516
|
| 15817 |
+
},
|
| 15818 |
+
{
|
| 15819 |
+
"epoch": 1.5753438987394737,
|
| 15820 |
+
"grad_norm": 0.2227022647857666,
|
| 15821 |
+
"learning_rate": 2.5300954753009547e-05,
|
| 15822 |
+
"loss": 2.1358001232147217,
|
| 15823 |
+
"step": 4518
|
| 15824 |
+
},
|
| 15825 |
+
{
|
| 15826 |
+
"epoch": 1.5760412852834005,
|
| 15827 |
+
"grad_norm": 0.18909968435764313,
|
| 15828 |
+
"learning_rate": 2.5259443752594437e-05,
|
| 15829 |
+
"loss": 1.8523045778274536,
|
| 15830 |
+
"step": 4520
|
| 15831 |
+
},
|
| 15832 |
+
{
|
| 15833 |
+
"epoch": 1.576738671827327,
|
| 15834 |
+
"grad_norm": 0.2606893479824066,
|
| 15835 |
+
"learning_rate": 2.521793275217933e-05,
|
| 15836 |
+
"loss": 1.898789644241333,
|
| 15837 |
+
"step": 4522
|
| 15838 |
+
},
|
| 15839 |
+
{
|
| 15840 |
+
"epoch": 1.5774360583712537,
|
| 15841 |
+
"grad_norm": 0.21320763230323792,
|
| 15842 |
+
"learning_rate": 2.5176421751764217e-05,
|
| 15843 |
+
"loss": 1.7763218879699707,
|
| 15844 |
+
"step": 4524
|
| 15845 |
+
},
|
| 15846 |
+
{
|
| 15847 |
+
"epoch": 1.5781334449151805,
|
| 15848 |
+
"grad_norm": 0.20257368683815002,
|
| 15849 |
+
"learning_rate": 2.513491075134911e-05,
|
| 15850 |
+
"loss": 1.7035415172576904,
|
| 15851 |
+
"step": 4526
|
| 15852 |
+
},
|
| 15853 |
+
{
|
| 15854 |
+
"epoch": 1.5788308314591069,
|
| 15855 |
+
"grad_norm": 0.24113517999649048,
|
| 15856 |
+
"learning_rate": 2.5093399750934e-05,
|
| 15857 |
+
"loss": 1.7718031406402588,
|
| 15858 |
+
"step": 4528
|
| 15859 |
+
},
|
| 15860 |
+
{
|
| 15861 |
+
"epoch": 1.5795282180030337,
|
| 15862 |
+
"grad_norm": 0.23414462804794312,
|
| 15863 |
+
"learning_rate": 2.5051888750518886e-05,
|
| 15864 |
+
"loss": 1.9617892503738403,
|
| 15865 |
+
"step": 4530
|
| 15866 |
+
},
|
| 15867 |
+
{
|
| 15868 |
+
"epoch": 1.5802256045469603,
|
| 15869 |
+
"grad_norm": 0.20183584094047546,
|
| 15870 |
+
"learning_rate": 2.501037775010378e-05,
|
| 15871 |
+
"loss": 1.7238619327545166,
|
| 15872 |
+
"step": 4532
|
| 15873 |
+
},
|
| 15874 |
+
{
|
| 15875 |
+
"epoch": 1.5809229910908869,
|
| 15876 |
+
"grad_norm": 0.21193481981754303,
|
| 15877 |
+
"learning_rate": 2.496886674968867e-05,
|
| 15878 |
+
"loss": 1.9761714935302734,
|
| 15879 |
+
"step": 4534
|
| 15880 |
+
},
|
| 15881 |
+
{
|
| 15882 |
+
"epoch": 1.5816203776348137,
|
| 15883 |
+
"grad_norm": 0.23748309910297394,
|
| 15884 |
+
"learning_rate": 2.492735574927356e-05,
|
| 15885 |
+
"loss": 1.8902467489242554,
|
| 15886 |
+
"step": 4536
|
| 15887 |
+
},
|
| 15888 |
+
{
|
| 15889 |
+
"epoch": 1.58231776417874,
|
| 15890 |
+
"grad_norm": 0.20187820494174957,
|
| 15891 |
+
"learning_rate": 2.4885844748858446e-05,
|
| 15892 |
+
"loss": 1.877758264541626,
|
| 15893 |
+
"step": 4538
|
| 15894 |
+
},
|
| 15895 |
+
{
|
| 15896 |
+
"epoch": 1.5830151507226669,
|
| 15897 |
+
"grad_norm": 0.23040840029716492,
|
| 15898 |
+
"learning_rate": 2.484433374844334e-05,
|
| 15899 |
+
"loss": 1.8351686000823975,
|
| 15900 |
+
"step": 4540
|
| 15901 |
+
},
|
| 15902 |
+
{
|
| 15903 |
+
"epoch": 1.5837125372665934,
|
| 15904 |
+
"grad_norm": 0.21899482607841492,
|
| 15905 |
+
"learning_rate": 2.480282274802823e-05,
|
| 15906 |
+
"loss": 1.979339599609375,
|
| 15907 |
+
"step": 4542
|
| 15908 |
+
},
|
| 15909 |
+
{
|
| 15910 |
+
"epoch": 1.58440992381052,
|
| 15911 |
+
"grad_norm": 0.2788389325141907,
|
| 15912 |
+
"learning_rate": 2.476131174761312e-05,
|
| 15913 |
+
"loss": 1.9334053993225098,
|
| 15914 |
+
"step": 4544
|
| 15915 |
+
},
|
| 15916 |
+
{
|
| 15917 |
+
"epoch": 1.5851073103544469,
|
| 15918 |
+
"grad_norm": 0.15392333269119263,
|
| 15919 |
+
"learning_rate": 2.471980074719801e-05,
|
| 15920 |
+
"loss": 1.9474034309387207,
|
| 15921 |
+
"step": 4546
|
| 15922 |
+
},
|
| 15923 |
+
{
|
| 15924 |
+
"epoch": 1.5858046968983732,
|
| 15925 |
+
"grad_norm": 0.24061237275600433,
|
| 15926 |
+
"learning_rate": 2.46782897467829e-05,
|
| 15927 |
+
"loss": 1.825833797454834,
|
| 15928 |
+
"step": 4548
|
| 15929 |
+
},
|
| 15930 |
+
{
|
| 15931 |
+
"epoch": 1.5865020834423,
|
| 15932 |
+
"grad_norm": 0.22537417709827423,
|
| 15933 |
+
"learning_rate": 2.463677874636779e-05,
|
| 15934 |
+
"loss": 1.8872768878936768,
|
| 15935 |
+
"step": 4550
|
| 15936 |
+
},
|
| 15937 |
+
{
|
| 15938 |
+
"epoch": 1.5871994699862266,
|
| 15939 |
+
"grad_norm": 0.1721351444721222,
|
| 15940 |
+
"learning_rate": 2.4595267745952678e-05,
|
| 15941 |
+
"loss": 1.86381995677948,
|
| 15942 |
+
"step": 4552
|
| 15943 |
+
},
|
| 15944 |
+
{
|
| 15945 |
+
"epoch": 1.5878968565301532,
|
| 15946 |
+
"grad_norm": 0.2710893750190735,
|
| 15947 |
+
"learning_rate": 2.4553756745537568e-05,
|
| 15948 |
+
"loss": 1.5904405117034912,
|
| 15949 |
+
"step": 4554
|
| 15950 |
+
},
|
| 15951 |
+
{
|
| 15952 |
+
"epoch": 1.58859424307408,
|
| 15953 |
+
"grad_norm": 0.24607409536838531,
|
| 15954 |
+
"learning_rate": 2.4512245745122458e-05,
|
| 15955 |
+
"loss": 1.835451364517212,
|
| 15956 |
+
"step": 4556
|
| 15957 |
+
},
|
| 15958 |
+
{
|
| 15959 |
+
"epoch": 1.5892916296180064,
|
| 15960 |
+
"grad_norm": 0.1593160331249237,
|
| 15961 |
+
"learning_rate": 2.4470734744707348e-05,
|
| 15962 |
+
"loss": 1.8716810941696167,
|
| 15963 |
+
"step": 4558
|
| 15964 |
+
},
|
| 15965 |
+
{
|
| 15966 |
+
"epoch": 1.5899890161619332,
|
| 15967 |
+
"grad_norm": 0.1712384670972824,
|
| 15968 |
+
"learning_rate": 2.4429223744292238e-05,
|
| 15969 |
+
"loss": 1.8859171867370605,
|
| 15970 |
+
"step": 4560
|
| 15971 |
+
},
|
| 15972 |
+
{
|
| 15973 |
+
"epoch": 1.5906864027058598,
|
| 15974 |
+
"grad_norm": 0.1740417182445526,
|
| 15975 |
+
"learning_rate": 2.4387712743877128e-05,
|
| 15976 |
+
"loss": 1.9691619873046875,
|
| 15977 |
+
"step": 4562
|
| 15978 |
+
},
|
| 15979 |
+
{
|
| 15980 |
+
"epoch": 1.5913837892497864,
|
| 15981 |
+
"grad_norm": 0.2035098373889923,
|
| 15982 |
+
"learning_rate": 2.4346201743462018e-05,
|
| 15983 |
+
"loss": 1.9540915489196777,
|
| 15984 |
+
"step": 4564
|
| 15985 |
+
},
|
| 15986 |
+
{
|
| 15987 |
+
"epoch": 1.5920811757937132,
|
| 15988 |
+
"grad_norm": 0.17674970626831055,
|
| 15989 |
+
"learning_rate": 2.430469074304691e-05,
|
| 15990 |
+
"loss": 2.0212907791137695,
|
| 15991 |
+
"step": 4566
|
| 15992 |
+
},
|
| 15993 |
+
{
|
| 15994 |
+
"epoch": 1.5927785623376396,
|
| 15995 |
+
"grad_norm": 0.24654126167297363,
|
| 15996 |
+
"learning_rate": 2.4263179742631797e-05,
|
| 15997 |
+
"loss": 1.8362865447998047,
|
| 15998 |
+
"step": 4568
|
| 15999 |
+
},
|
| 16000 |
+
{
|
| 16001 |
+
"epoch": 1.5934759488815664,
|
| 16002 |
+
"grad_norm": 0.2556804418563843,
|
| 16003 |
+
"learning_rate": 2.4221668742216687e-05,
|
| 16004 |
+
"loss": 1.67009437084198,
|
| 16005 |
+
"step": 4570
|
| 16006 |
+
},
|
| 16007 |
+
{
|
| 16008 |
+
"epoch": 1.594173335425493,
|
| 16009 |
+
"grad_norm": 0.17135943472385406,
|
| 16010 |
+
"learning_rate": 2.418015774180158e-05,
|
| 16011 |
+
"loss": 1.947709560394287,
|
| 16012 |
+
"step": 4572
|
| 16013 |
+
},
|
| 16014 |
+
{
|
| 16015 |
+
"epoch": 1.5948707219694196,
|
| 16016 |
+
"grad_norm": 0.24243444204330444,
|
| 16017 |
+
"learning_rate": 2.413864674138647e-05,
|
| 16018 |
+
"loss": 1.7617876529693604,
|
| 16019 |
+
"step": 4574
|
| 16020 |
+
},
|
| 16021 |
+
{
|
| 16022 |
+
"epoch": 1.5955681085133462,
|
| 16023 |
+
"grad_norm": 0.33450421690940857,
|
| 16024 |
+
"learning_rate": 2.4097135740971357e-05,
|
| 16025 |
+
"loss": 1.7707524299621582,
|
| 16026 |
+
"step": 4576
|
| 16027 |
+
},
|
| 16028 |
+
{
|
| 16029 |
+
"epoch": 1.5962654950572728,
|
| 16030 |
+
"grad_norm": 0.27597707509994507,
|
| 16031 |
+
"learning_rate": 2.405562474055625e-05,
|
| 16032 |
+
"loss": 1.9219856262207031,
|
| 16033 |
+
"step": 4578
|
| 16034 |
+
},
|
| 16035 |
+
{
|
| 16036 |
+
"epoch": 1.5969628816011996,
|
| 16037 |
+
"grad_norm": 0.21139302849769592,
|
| 16038 |
+
"learning_rate": 2.401411374014114e-05,
|
| 16039 |
+
"loss": 2.03281831741333,
|
| 16040 |
+
"step": 4580
|
| 16041 |
+
},
|
| 16042 |
+
{
|
| 16043 |
+
"epoch": 1.5976602681451262,
|
| 16044 |
+
"grad_norm": 0.22571788728237152,
|
| 16045 |
+
"learning_rate": 2.3972602739726026e-05,
|
| 16046 |
+
"loss": 2.055140733718872,
|
| 16047 |
+
"step": 4582
|
| 16048 |
+
},
|
| 16049 |
+
{
|
| 16050 |
+
"epoch": 1.5983576546890528,
|
| 16051 |
+
"grad_norm": 0.24944792687892914,
|
| 16052 |
+
"learning_rate": 2.393109173931092e-05,
|
| 16053 |
+
"loss": 1.7604517936706543,
|
| 16054 |
+
"step": 4584
|
| 16055 |
+
},
|
| 16056 |
+
{
|
| 16057 |
+
"epoch": 1.5990550412329794,
|
| 16058 |
+
"grad_norm": 0.22140969336032867,
|
| 16059 |
+
"learning_rate": 2.388958073889581e-05,
|
| 16060 |
+
"loss": 1.9736140966415405,
|
| 16061 |
+
"step": 4586
|
| 16062 |
+
},
|
| 16063 |
+
{
|
| 16064 |
+
"epoch": 1.599752427776906,
|
| 16065 |
+
"grad_norm": 0.24355095624923706,
|
| 16066 |
+
"learning_rate": 2.38480697384807e-05,
|
| 16067 |
+
"loss": 1.6559598445892334,
|
| 16068 |
+
"step": 4588
|
| 16069 |
+
},
|
| 16070 |
+
{
|
| 16071 |
+
"epoch": 1.6004498143208328,
|
| 16072 |
+
"grad_norm": 0.19067931175231934,
|
| 16073 |
+
"learning_rate": 2.3806558738065586e-05,
|
| 16074 |
+
"loss": 2.0552828311920166,
|
| 16075 |
+
"step": 4590
|
| 16076 |
+
},
|
| 16077 |
+
{
|
| 16078 |
+
"epoch": 1.6011472008647594,
|
| 16079 |
+
"grad_norm": 0.23808273673057556,
|
| 16080 |
+
"learning_rate": 2.376504773765048e-05,
|
| 16081 |
+
"loss": 1.7038203477859497,
|
| 16082 |
+
"step": 4592
|
| 16083 |
}
|
| 16084 |
],
|
| 16085 |
"logging_steps": 2,
|
|
|
|
| 16099 |
"attributes": {}
|
| 16100 |
}
|
| 16101 |
},
|
| 16102 |
+
"total_flos": 8.234493030023823e+17,
|
| 16103 |
"train_batch_size": 1,
|
| 16104 |
"trial_name": null,
|
| 16105 |
"trial_params": null
|