Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
unsloth
trl
sft
text-generation-inference
Instructions to use Ba2han/outputs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/outputs with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/outputs")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/outputs") model = AutoModelForCausalLM.from_pretrained("Ba2han/outputs") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/outputs with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/outputs" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/outputs", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ba2han/outputs
- SGLang
How to use Ba2han/outputs 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/outputs" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/outputs", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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/outputs" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/outputs", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Studio
How to use Ba2han/outputs 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/outputs 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/outputs to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ba2han/outputs to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Ba2han/outputs", max_seq_length=2048, ) - Docker Model Runner
How to use Ba2han/outputs with Docker Model Runner:
docker model run hf.co/Ba2han/outputs
Training in progress, step 4576, 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 2518320880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fc3cf4ade68fc1be3b670cf7b2833546f6daa3f5702d270c9d455cba3ea3734
|
| 3 |
size 2518320880
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262925264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b04095dbe8fdd2c7b1060b4e9c236463420dd14b39c86fe79fd126a752b8dac
|
| 3 |
size 1262925264
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9401
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c86479cf0430135696e1b764fbfc0e3a1b7089b77125e35ec0f1d4c06eb1ed3c
|
| 3 |
size 9401
|
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": 2858,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -14030,6 +14030,2008 @@
|
|
| 14030 |
"learning_rate": 0.0012,
|
| 14031 |
"loss": 2.311366319656372,
|
| 14032 |
"step": 4004
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14033 |
}
|
| 14034 |
],
|
| 14035 |
"logging_steps": 2,
|
|
@@ -14049,7 +16051,7 @@
|
|
| 14049 |
"attributes": {}
|
| 14050 |
}
|
| 14051 |
},
|
| 14052 |
-
"total_flos": 1.
|
| 14053 |
"train_batch_size": 32,
|
| 14054 |
"trial_name": null,
|
| 14055 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.24020997375328085,
|
| 6 |
"eval_steps": 2858,
|
| 7 |
+
"global_step": 4576,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14030 |
"learning_rate": 0.0012,
|
| 14031 |
"loss": 2.311366319656372,
|
| 14032 |
"step": 4004
|
| 14033 |
+
},
|
| 14034 |
+
{
|
| 14035 |
+
"epoch": 0.21028871391076115,
|
| 14036 |
+
"grad_norm": 0.04495653137564659,
|
| 14037 |
+
"learning_rate": 0.0012,
|
| 14038 |
+
"loss": 2.2611324787139893,
|
| 14039 |
+
"step": 4006
|
| 14040 |
+
},
|
| 14041 |
+
{
|
| 14042 |
+
"epoch": 0.21039370078740158,
|
| 14043 |
+
"grad_norm": 0.04346334934234619,
|
| 14044 |
+
"learning_rate": 0.0012,
|
| 14045 |
+
"loss": 2.358962297439575,
|
| 14046 |
+
"step": 4008
|
| 14047 |
+
},
|
| 14048 |
+
{
|
| 14049 |
+
"epoch": 0.210498687664042,
|
| 14050 |
+
"grad_norm": 0.050905317068099976,
|
| 14051 |
+
"learning_rate": 0.0012,
|
| 14052 |
+
"loss": 2.271240472793579,
|
| 14053 |
+
"step": 4010
|
| 14054 |
+
},
|
| 14055 |
+
{
|
| 14056 |
+
"epoch": 0.2106036745406824,
|
| 14057 |
+
"grad_norm": 0.04278480261564255,
|
| 14058 |
+
"learning_rate": 0.0012,
|
| 14059 |
+
"loss": 2.3054041862487793,
|
| 14060 |
+
"step": 4012
|
| 14061 |
+
},
|
| 14062 |
+
{
|
| 14063 |
+
"epoch": 0.21070866141732283,
|
| 14064 |
+
"grad_norm": 0.051608193665742874,
|
| 14065 |
+
"learning_rate": 0.0012,
|
| 14066 |
+
"loss": 2.2933907508850098,
|
| 14067 |
+
"step": 4014
|
| 14068 |
+
},
|
| 14069 |
+
{
|
| 14070 |
+
"epoch": 0.21081364829396326,
|
| 14071 |
+
"grad_norm": 0.04247153922915459,
|
| 14072 |
+
"learning_rate": 0.0012,
|
| 14073 |
+
"loss": 2.3045263290405273,
|
| 14074 |
+
"step": 4016
|
| 14075 |
+
},
|
| 14076 |
+
{
|
| 14077 |
+
"epoch": 0.21091863517060366,
|
| 14078 |
+
"grad_norm": 0.05625001713633537,
|
| 14079 |
+
"learning_rate": 0.0012,
|
| 14080 |
+
"loss": 2.2936789989471436,
|
| 14081 |
+
"step": 4018
|
| 14082 |
+
},
|
| 14083 |
+
{
|
| 14084 |
+
"epoch": 0.2110236220472441,
|
| 14085 |
+
"grad_norm": 0.05116158351302147,
|
| 14086 |
+
"learning_rate": 0.0012,
|
| 14087 |
+
"loss": 2.317620038986206,
|
| 14088 |
+
"step": 4020
|
| 14089 |
+
},
|
| 14090 |
+
{
|
| 14091 |
+
"epoch": 0.21112860892388452,
|
| 14092 |
+
"grad_norm": 0.05501234531402588,
|
| 14093 |
+
"learning_rate": 0.0012,
|
| 14094 |
+
"loss": 2.2959837913513184,
|
| 14095 |
+
"step": 4022
|
| 14096 |
+
},
|
| 14097 |
+
{
|
| 14098 |
+
"epoch": 0.21123359580052495,
|
| 14099 |
+
"grad_norm": 0.0654350221157074,
|
| 14100 |
+
"learning_rate": 0.0012,
|
| 14101 |
+
"loss": 2.3056390285491943,
|
| 14102 |
+
"step": 4024
|
| 14103 |
+
},
|
| 14104 |
+
{
|
| 14105 |
+
"epoch": 0.21133858267716535,
|
| 14106 |
+
"grad_norm": 0.04688689485192299,
|
| 14107 |
+
"learning_rate": 0.0012,
|
| 14108 |
+
"loss": 2.338505983352661,
|
| 14109 |
+
"step": 4026
|
| 14110 |
+
},
|
| 14111 |
+
{
|
| 14112 |
+
"epoch": 0.21144356955380578,
|
| 14113 |
+
"grad_norm": 0.05448073521256447,
|
| 14114 |
+
"learning_rate": 0.0012,
|
| 14115 |
+
"loss": 2.329737901687622,
|
| 14116 |
+
"step": 4028
|
| 14117 |
+
},
|
| 14118 |
+
{
|
| 14119 |
+
"epoch": 0.2115485564304462,
|
| 14120 |
+
"grad_norm": 0.06295216083526611,
|
| 14121 |
+
"learning_rate": 0.0012,
|
| 14122 |
+
"loss": 2.3223397731781006,
|
| 14123 |
+
"step": 4030
|
| 14124 |
+
},
|
| 14125 |
+
{
|
| 14126 |
+
"epoch": 0.2116535433070866,
|
| 14127 |
+
"grad_norm": 0.057402774691581726,
|
| 14128 |
+
"learning_rate": 0.0012,
|
| 14129 |
+
"loss": 2.367483139038086,
|
| 14130 |
+
"step": 4032
|
| 14131 |
+
},
|
| 14132 |
+
{
|
| 14133 |
+
"epoch": 0.21175853018372703,
|
| 14134 |
+
"grad_norm": 0.0429740808904171,
|
| 14135 |
+
"learning_rate": 0.0012,
|
| 14136 |
+
"loss": 2.299720048904419,
|
| 14137 |
+
"step": 4034
|
| 14138 |
+
},
|
| 14139 |
+
{
|
| 14140 |
+
"epoch": 0.21186351706036746,
|
| 14141 |
+
"grad_norm": 0.05856316536664963,
|
| 14142 |
+
"learning_rate": 0.0012,
|
| 14143 |
+
"loss": 2.313579559326172,
|
| 14144 |
+
"step": 4036
|
| 14145 |
+
},
|
| 14146 |
+
{
|
| 14147 |
+
"epoch": 0.21196850393700786,
|
| 14148 |
+
"grad_norm": 0.052115898579359055,
|
| 14149 |
+
"learning_rate": 0.0012,
|
| 14150 |
+
"loss": 2.3258323669433594,
|
| 14151 |
+
"step": 4038
|
| 14152 |
+
},
|
| 14153 |
+
{
|
| 14154 |
+
"epoch": 0.2120734908136483,
|
| 14155 |
+
"grad_norm": 0.04795091599225998,
|
| 14156 |
+
"learning_rate": 0.0012,
|
| 14157 |
+
"loss": 2.2880218029022217,
|
| 14158 |
+
"step": 4040
|
| 14159 |
+
},
|
| 14160 |
+
{
|
| 14161 |
+
"epoch": 0.21217847769028872,
|
| 14162 |
+
"grad_norm": 0.04308042675256729,
|
| 14163 |
+
"learning_rate": 0.0012,
|
| 14164 |
+
"loss": 2.3229575157165527,
|
| 14165 |
+
"step": 4042
|
| 14166 |
+
},
|
| 14167 |
+
{
|
| 14168 |
+
"epoch": 0.21228346456692915,
|
| 14169 |
+
"grad_norm": 0.05045262351632118,
|
| 14170 |
+
"learning_rate": 0.0012,
|
| 14171 |
+
"loss": 2.318390369415283,
|
| 14172 |
+
"step": 4044
|
| 14173 |
+
},
|
| 14174 |
+
{
|
| 14175 |
+
"epoch": 0.21238845144356955,
|
| 14176 |
+
"grad_norm": 0.050159793347120285,
|
| 14177 |
+
"learning_rate": 0.0012,
|
| 14178 |
+
"loss": 2.2929673194885254,
|
| 14179 |
+
"step": 4046
|
| 14180 |
+
},
|
| 14181 |
+
{
|
| 14182 |
+
"epoch": 0.21249343832020998,
|
| 14183 |
+
"grad_norm": 0.044212501496076584,
|
| 14184 |
+
"learning_rate": 0.0012,
|
| 14185 |
+
"loss": 2.3120975494384766,
|
| 14186 |
+
"step": 4048
|
| 14187 |
+
},
|
| 14188 |
+
{
|
| 14189 |
+
"epoch": 0.2125984251968504,
|
| 14190 |
+
"grad_norm": 0.04438139498233795,
|
| 14191 |
+
"learning_rate": 0.0012,
|
| 14192 |
+
"loss": 2.313922643661499,
|
| 14193 |
+
"step": 4050
|
| 14194 |
+
},
|
| 14195 |
+
{
|
| 14196 |
+
"epoch": 0.2127034120734908,
|
| 14197 |
+
"grad_norm": 0.04693599417805672,
|
| 14198 |
+
"learning_rate": 0.0012,
|
| 14199 |
+
"loss": 2.3095078468322754,
|
| 14200 |
+
"step": 4052
|
| 14201 |
+
},
|
| 14202 |
+
{
|
| 14203 |
+
"epoch": 0.21280839895013123,
|
| 14204 |
+
"grad_norm": 0.05397019535303116,
|
| 14205 |
+
"learning_rate": 0.0012,
|
| 14206 |
+
"loss": 2.3006434440612793,
|
| 14207 |
+
"step": 4054
|
| 14208 |
+
},
|
| 14209 |
+
{
|
| 14210 |
+
"epoch": 0.21291338582677166,
|
| 14211 |
+
"grad_norm": 0.056138888001441956,
|
| 14212 |
+
"learning_rate": 0.0012,
|
| 14213 |
+
"loss": 2.3176822662353516,
|
| 14214 |
+
"step": 4056
|
| 14215 |
+
},
|
| 14216 |
+
{
|
| 14217 |
+
"epoch": 0.21301837270341206,
|
| 14218 |
+
"grad_norm": 0.06166312098503113,
|
| 14219 |
+
"learning_rate": 0.0012,
|
| 14220 |
+
"loss": 2.4013116359710693,
|
| 14221 |
+
"step": 4058
|
| 14222 |
+
},
|
| 14223 |
+
{
|
| 14224 |
+
"epoch": 0.2131233595800525,
|
| 14225 |
+
"grad_norm": 0.054339248687028885,
|
| 14226 |
+
"learning_rate": 0.0012,
|
| 14227 |
+
"loss": 2.3173820972442627,
|
| 14228 |
+
"step": 4060
|
| 14229 |
+
},
|
| 14230 |
+
{
|
| 14231 |
+
"epoch": 0.21322834645669292,
|
| 14232 |
+
"grad_norm": 0.05540439486503601,
|
| 14233 |
+
"learning_rate": 0.0012,
|
| 14234 |
+
"loss": 2.35890793800354,
|
| 14235 |
+
"step": 4062
|
| 14236 |
+
},
|
| 14237 |
+
{
|
| 14238 |
+
"epoch": 0.21333333333333335,
|
| 14239 |
+
"grad_norm": 0.04593516141176224,
|
| 14240 |
+
"learning_rate": 0.0012,
|
| 14241 |
+
"loss": 2.400446891784668,
|
| 14242 |
+
"step": 4064
|
| 14243 |
+
},
|
| 14244 |
+
{
|
| 14245 |
+
"epoch": 0.21343832020997375,
|
| 14246 |
+
"grad_norm": 0.05097497999668121,
|
| 14247 |
+
"learning_rate": 0.0012,
|
| 14248 |
+
"loss": 2.306729555130005,
|
| 14249 |
+
"step": 4066
|
| 14250 |
+
},
|
| 14251 |
+
{
|
| 14252 |
+
"epoch": 0.21354330708661418,
|
| 14253 |
+
"grad_norm": 0.04635836184024811,
|
| 14254 |
+
"learning_rate": 0.0012,
|
| 14255 |
+
"loss": 2.278862237930298,
|
| 14256 |
+
"step": 4068
|
| 14257 |
+
},
|
| 14258 |
+
{
|
| 14259 |
+
"epoch": 0.2136482939632546,
|
| 14260 |
+
"grad_norm": 0.04317694157361984,
|
| 14261 |
+
"learning_rate": 0.0012,
|
| 14262 |
+
"loss": 2.4010167121887207,
|
| 14263 |
+
"step": 4070
|
| 14264 |
+
},
|
| 14265 |
+
{
|
| 14266 |
+
"epoch": 0.213753280839895,
|
| 14267 |
+
"grad_norm": 0.04648065194487572,
|
| 14268 |
+
"learning_rate": 0.0012,
|
| 14269 |
+
"loss": 2.2032086849212646,
|
| 14270 |
+
"step": 4072
|
| 14271 |
+
},
|
| 14272 |
+
{
|
| 14273 |
+
"epoch": 0.21385826771653543,
|
| 14274 |
+
"grad_norm": 0.05719921737909317,
|
| 14275 |
+
"learning_rate": 0.0012,
|
| 14276 |
+
"loss": 2.3567428588867188,
|
| 14277 |
+
"step": 4074
|
| 14278 |
+
},
|
| 14279 |
+
{
|
| 14280 |
+
"epoch": 0.21396325459317586,
|
| 14281 |
+
"grad_norm": 0.051019005477428436,
|
| 14282 |
+
"learning_rate": 0.0012,
|
| 14283 |
+
"loss": 2.2901158332824707,
|
| 14284 |
+
"step": 4076
|
| 14285 |
+
},
|
| 14286 |
+
{
|
| 14287 |
+
"epoch": 0.21406824146981626,
|
| 14288 |
+
"grad_norm": 0.051970530301332474,
|
| 14289 |
+
"learning_rate": 0.0012,
|
| 14290 |
+
"loss": 2.284844160079956,
|
| 14291 |
+
"step": 4078
|
| 14292 |
+
},
|
| 14293 |
+
{
|
| 14294 |
+
"epoch": 0.2141732283464567,
|
| 14295 |
+
"grad_norm": 0.0531952828168869,
|
| 14296 |
+
"learning_rate": 0.0012,
|
| 14297 |
+
"loss": 2.2967491149902344,
|
| 14298 |
+
"step": 4080
|
| 14299 |
+
},
|
| 14300 |
+
{
|
| 14301 |
+
"epoch": 0.21427821522309712,
|
| 14302 |
+
"grad_norm": 0.04833419248461723,
|
| 14303 |
+
"learning_rate": 0.0012,
|
| 14304 |
+
"loss": 2.333690881729126,
|
| 14305 |
+
"step": 4082
|
| 14306 |
+
},
|
| 14307 |
+
{
|
| 14308 |
+
"epoch": 0.21438320209973755,
|
| 14309 |
+
"grad_norm": 0.046158622950315475,
|
| 14310 |
+
"learning_rate": 0.0012,
|
| 14311 |
+
"loss": 2.303281307220459,
|
| 14312 |
+
"step": 4084
|
| 14313 |
+
},
|
| 14314 |
+
{
|
| 14315 |
+
"epoch": 0.21448818897637795,
|
| 14316 |
+
"grad_norm": 0.04928277060389519,
|
| 14317 |
+
"learning_rate": 0.0012,
|
| 14318 |
+
"loss": 2.3516345024108887,
|
| 14319 |
+
"step": 4086
|
| 14320 |
+
},
|
| 14321 |
+
{
|
| 14322 |
+
"epoch": 0.21459317585301838,
|
| 14323 |
+
"grad_norm": 0.04409465938806534,
|
| 14324 |
+
"learning_rate": 0.0012,
|
| 14325 |
+
"loss": 2.280799627304077,
|
| 14326 |
+
"step": 4088
|
| 14327 |
+
},
|
| 14328 |
+
{
|
| 14329 |
+
"epoch": 0.2146981627296588,
|
| 14330 |
+
"grad_norm": 0.04494433477520943,
|
| 14331 |
+
"learning_rate": 0.0012,
|
| 14332 |
+
"loss": 2.230400562286377,
|
| 14333 |
+
"step": 4090
|
| 14334 |
+
},
|
| 14335 |
+
{
|
| 14336 |
+
"epoch": 0.2148031496062992,
|
| 14337 |
+
"grad_norm": 0.046967070549726486,
|
| 14338 |
+
"learning_rate": 0.0012,
|
| 14339 |
+
"loss": 2.3395323753356934,
|
| 14340 |
+
"step": 4092
|
| 14341 |
+
},
|
| 14342 |
+
{
|
| 14343 |
+
"epoch": 0.21490813648293963,
|
| 14344 |
+
"grad_norm": 0.05687651038169861,
|
| 14345 |
+
"learning_rate": 0.0012,
|
| 14346 |
+
"loss": 2.370884895324707,
|
| 14347 |
+
"step": 4094
|
| 14348 |
+
},
|
| 14349 |
+
{
|
| 14350 |
+
"epoch": 0.21501312335958006,
|
| 14351 |
+
"grad_norm": 0.04313536733388901,
|
| 14352 |
+
"learning_rate": 0.0012,
|
| 14353 |
+
"loss": 2.312525987625122,
|
| 14354 |
+
"step": 4096
|
| 14355 |
+
},
|
| 14356 |
+
{
|
| 14357 |
+
"epoch": 0.21511811023622046,
|
| 14358 |
+
"grad_norm": 0.06246824562549591,
|
| 14359 |
+
"learning_rate": 0.0012,
|
| 14360 |
+
"loss": 2.331078290939331,
|
| 14361 |
+
"step": 4098
|
| 14362 |
+
},
|
| 14363 |
+
{
|
| 14364 |
+
"epoch": 0.2152230971128609,
|
| 14365 |
+
"grad_norm": 0.05046330392360687,
|
| 14366 |
+
"learning_rate": 0.0012,
|
| 14367 |
+
"loss": 2.2873222827911377,
|
| 14368 |
+
"step": 4100
|
| 14369 |
+
},
|
| 14370 |
+
{
|
| 14371 |
+
"epoch": 0.21532808398950132,
|
| 14372 |
+
"grad_norm": 0.04251859337091446,
|
| 14373 |
+
"learning_rate": 0.0012,
|
| 14374 |
+
"loss": 2.363299608230591,
|
| 14375 |
+
"step": 4102
|
| 14376 |
+
},
|
| 14377 |
+
{
|
| 14378 |
+
"epoch": 0.21543307086614175,
|
| 14379 |
+
"grad_norm": 0.04940452054142952,
|
| 14380 |
+
"learning_rate": 0.0012,
|
| 14381 |
+
"loss": 2.410923719406128,
|
| 14382 |
+
"step": 4104
|
| 14383 |
+
},
|
| 14384 |
+
{
|
| 14385 |
+
"epoch": 0.21553805774278215,
|
| 14386 |
+
"grad_norm": 0.04762861877679825,
|
| 14387 |
+
"learning_rate": 0.0012,
|
| 14388 |
+
"loss": 2.31616473197937,
|
| 14389 |
+
"step": 4106
|
| 14390 |
+
},
|
| 14391 |
+
{
|
| 14392 |
+
"epoch": 0.21564304461942257,
|
| 14393 |
+
"grad_norm": 0.04446468502283096,
|
| 14394 |
+
"learning_rate": 0.0012,
|
| 14395 |
+
"loss": 2.317147970199585,
|
| 14396 |
+
"step": 4108
|
| 14397 |
+
},
|
| 14398 |
+
{
|
| 14399 |
+
"epoch": 0.215748031496063,
|
| 14400 |
+
"grad_norm": 0.04426930472254753,
|
| 14401 |
+
"learning_rate": 0.0012,
|
| 14402 |
+
"loss": 2.2439184188842773,
|
| 14403 |
+
"step": 4110
|
| 14404 |
+
},
|
| 14405 |
+
{
|
| 14406 |
+
"epoch": 0.2158530183727034,
|
| 14407 |
+
"grad_norm": 0.04193851351737976,
|
| 14408 |
+
"learning_rate": 0.0012,
|
| 14409 |
+
"loss": 2.349778175354004,
|
| 14410 |
+
"step": 4112
|
| 14411 |
+
},
|
| 14412 |
+
{
|
| 14413 |
+
"epoch": 0.21595800524934383,
|
| 14414 |
+
"grad_norm": 0.041560955345630646,
|
| 14415 |
+
"learning_rate": 0.0012,
|
| 14416 |
+
"loss": 2.366396427154541,
|
| 14417 |
+
"step": 4114
|
| 14418 |
+
},
|
| 14419 |
+
{
|
| 14420 |
+
"epoch": 0.21606299212598426,
|
| 14421 |
+
"grad_norm": 0.04422576352953911,
|
| 14422 |
+
"learning_rate": 0.0012,
|
| 14423 |
+
"loss": 2.312945604324341,
|
| 14424 |
+
"step": 4116
|
| 14425 |
+
},
|
| 14426 |
+
{
|
| 14427 |
+
"epoch": 0.21616797900262466,
|
| 14428 |
+
"grad_norm": 0.05393075570464134,
|
| 14429 |
+
"learning_rate": 0.0012,
|
| 14430 |
+
"loss": 2.3067989349365234,
|
| 14431 |
+
"step": 4118
|
| 14432 |
+
},
|
| 14433 |
+
{
|
| 14434 |
+
"epoch": 0.2162729658792651,
|
| 14435 |
+
"grad_norm": 0.04484538733959198,
|
| 14436 |
+
"learning_rate": 0.0012,
|
| 14437 |
+
"loss": 2.28342604637146,
|
| 14438 |
+
"step": 4120
|
| 14439 |
+
},
|
| 14440 |
+
{
|
| 14441 |
+
"epoch": 0.21637795275590552,
|
| 14442 |
+
"grad_norm": 0.061773937195539474,
|
| 14443 |
+
"learning_rate": 0.0012,
|
| 14444 |
+
"loss": 2.26025128364563,
|
| 14445 |
+
"step": 4122
|
| 14446 |
+
},
|
| 14447 |
+
{
|
| 14448 |
+
"epoch": 0.21648293963254595,
|
| 14449 |
+
"grad_norm": 0.04098367318511009,
|
| 14450 |
+
"learning_rate": 0.0012,
|
| 14451 |
+
"loss": 2.371824264526367,
|
| 14452 |
+
"step": 4124
|
| 14453 |
+
},
|
| 14454 |
+
{
|
| 14455 |
+
"epoch": 0.21658792650918635,
|
| 14456 |
+
"grad_norm": 0.05587400123476982,
|
| 14457 |
+
"learning_rate": 0.0012,
|
| 14458 |
+
"loss": 2.2899320125579834,
|
| 14459 |
+
"step": 4126
|
| 14460 |
+
},
|
| 14461 |
+
{
|
| 14462 |
+
"epoch": 0.21669291338582677,
|
| 14463 |
+
"grad_norm": 0.04715770483016968,
|
| 14464 |
+
"learning_rate": 0.0012,
|
| 14465 |
+
"loss": 2.3074800968170166,
|
| 14466 |
+
"step": 4128
|
| 14467 |
+
},
|
| 14468 |
+
{
|
| 14469 |
+
"epoch": 0.2167979002624672,
|
| 14470 |
+
"grad_norm": 0.043049752712249756,
|
| 14471 |
+
"learning_rate": 0.0012,
|
| 14472 |
+
"loss": 2.317303419113159,
|
| 14473 |
+
"step": 4130
|
| 14474 |
+
},
|
| 14475 |
+
{
|
| 14476 |
+
"epoch": 0.2169028871391076,
|
| 14477 |
+
"grad_norm": 0.04621218889951706,
|
| 14478 |
+
"learning_rate": 0.0012,
|
| 14479 |
+
"loss": 2.308896780014038,
|
| 14480 |
+
"step": 4132
|
| 14481 |
+
},
|
| 14482 |
+
{
|
| 14483 |
+
"epoch": 0.21700787401574803,
|
| 14484 |
+
"grad_norm": 0.04045797511935234,
|
| 14485 |
+
"learning_rate": 0.0012,
|
| 14486 |
+
"loss": 2.309241533279419,
|
| 14487 |
+
"step": 4134
|
| 14488 |
+
},
|
| 14489 |
+
{
|
| 14490 |
+
"epoch": 0.21711286089238846,
|
| 14491 |
+
"grad_norm": 0.04133361950516701,
|
| 14492 |
+
"learning_rate": 0.0012,
|
| 14493 |
+
"loss": 2.3342676162719727,
|
| 14494 |
+
"step": 4136
|
| 14495 |
+
},
|
| 14496 |
+
{
|
| 14497 |
+
"epoch": 0.21721784776902886,
|
| 14498 |
+
"grad_norm": 0.051185641437768936,
|
| 14499 |
+
"learning_rate": 0.0012,
|
| 14500 |
+
"loss": 2.323913097381592,
|
| 14501 |
+
"step": 4138
|
| 14502 |
+
},
|
| 14503 |
+
{
|
| 14504 |
+
"epoch": 0.2173228346456693,
|
| 14505 |
+
"grad_norm": 0.041654154658317566,
|
| 14506 |
+
"learning_rate": 0.0012,
|
| 14507 |
+
"loss": 2.2728166580200195,
|
| 14508 |
+
"step": 4140
|
| 14509 |
+
},
|
| 14510 |
+
{
|
| 14511 |
+
"epoch": 0.21742782152230972,
|
| 14512 |
+
"grad_norm": 0.04694750905036926,
|
| 14513 |
+
"learning_rate": 0.0012,
|
| 14514 |
+
"loss": 2.3197927474975586,
|
| 14515 |
+
"step": 4142
|
| 14516 |
+
},
|
| 14517 |
+
{
|
| 14518 |
+
"epoch": 0.21753280839895014,
|
| 14519 |
+
"grad_norm": 0.0430593304336071,
|
| 14520 |
+
"learning_rate": 0.0012,
|
| 14521 |
+
"loss": 2.326516628265381,
|
| 14522 |
+
"step": 4144
|
| 14523 |
+
},
|
| 14524 |
+
{
|
| 14525 |
+
"epoch": 0.21763779527559055,
|
| 14526 |
+
"grad_norm": 0.04853262007236481,
|
| 14527 |
+
"learning_rate": 0.0012,
|
| 14528 |
+
"loss": 2.324626922607422,
|
| 14529 |
+
"step": 4146
|
| 14530 |
+
},
|
| 14531 |
+
{
|
| 14532 |
+
"epoch": 0.21774278215223097,
|
| 14533 |
+
"grad_norm": 0.047873273491859436,
|
| 14534 |
+
"learning_rate": 0.0012,
|
| 14535 |
+
"loss": 2.3178484439849854,
|
| 14536 |
+
"step": 4148
|
| 14537 |
+
},
|
| 14538 |
+
{
|
| 14539 |
+
"epoch": 0.2178477690288714,
|
| 14540 |
+
"grad_norm": 0.04545560106635094,
|
| 14541 |
+
"learning_rate": 0.0012,
|
| 14542 |
+
"loss": 2.2776436805725098,
|
| 14543 |
+
"step": 4150
|
| 14544 |
+
},
|
| 14545 |
+
{
|
| 14546 |
+
"epoch": 0.2179527559055118,
|
| 14547 |
+
"grad_norm": 0.05220489576458931,
|
| 14548 |
+
"learning_rate": 0.0012,
|
| 14549 |
+
"loss": 2.29337739944458,
|
| 14550 |
+
"step": 4152
|
| 14551 |
+
},
|
| 14552 |
+
{
|
| 14553 |
+
"epoch": 0.21805774278215223,
|
| 14554 |
+
"grad_norm": 0.050712764263153076,
|
| 14555 |
+
"learning_rate": 0.0012,
|
| 14556 |
+
"loss": 2.3473429679870605,
|
| 14557 |
+
"step": 4154
|
| 14558 |
+
},
|
| 14559 |
+
{
|
| 14560 |
+
"epoch": 0.21816272965879266,
|
| 14561 |
+
"grad_norm": 0.05195896700024605,
|
| 14562 |
+
"learning_rate": 0.0012,
|
| 14563 |
+
"loss": 2.2903647422790527,
|
| 14564 |
+
"step": 4156
|
| 14565 |
+
},
|
| 14566 |
+
{
|
| 14567 |
+
"epoch": 0.21826771653543306,
|
| 14568 |
+
"grad_norm": 0.05322682857513428,
|
| 14569 |
+
"learning_rate": 0.0012,
|
| 14570 |
+
"loss": 2.312148332595825,
|
| 14571 |
+
"step": 4158
|
| 14572 |
+
},
|
| 14573 |
+
{
|
| 14574 |
+
"epoch": 0.2183727034120735,
|
| 14575 |
+
"grad_norm": 0.04223117604851723,
|
| 14576 |
+
"learning_rate": 0.0012,
|
| 14577 |
+
"loss": 2.290886640548706,
|
| 14578 |
+
"step": 4160
|
| 14579 |
+
},
|
| 14580 |
+
{
|
| 14581 |
+
"epoch": 0.21847769028871392,
|
| 14582 |
+
"grad_norm": 0.04521167278289795,
|
| 14583 |
+
"learning_rate": 0.0012,
|
| 14584 |
+
"loss": 2.3284990787506104,
|
| 14585 |
+
"step": 4162
|
| 14586 |
+
},
|
| 14587 |
+
{
|
| 14588 |
+
"epoch": 0.21858267716535434,
|
| 14589 |
+
"grad_norm": 0.05357779189944267,
|
| 14590 |
+
"learning_rate": 0.0012,
|
| 14591 |
+
"loss": 2.3308699131011963,
|
| 14592 |
+
"step": 4164
|
| 14593 |
+
},
|
| 14594 |
+
{
|
| 14595 |
+
"epoch": 0.21868766404199474,
|
| 14596 |
+
"grad_norm": 0.05185701698064804,
|
| 14597 |
+
"learning_rate": 0.0012,
|
| 14598 |
+
"loss": 2.3478989601135254,
|
| 14599 |
+
"step": 4166
|
| 14600 |
+
},
|
| 14601 |
+
{
|
| 14602 |
+
"epoch": 0.21879265091863517,
|
| 14603 |
+
"grad_norm": 0.04900883883237839,
|
| 14604 |
+
"learning_rate": 0.0012,
|
| 14605 |
+
"loss": 2.247326612472534,
|
| 14606 |
+
"step": 4168
|
| 14607 |
+
},
|
| 14608 |
+
{
|
| 14609 |
+
"epoch": 0.2188976377952756,
|
| 14610 |
+
"grad_norm": 0.04892588034272194,
|
| 14611 |
+
"learning_rate": 0.0012,
|
| 14612 |
+
"loss": 2.28316330909729,
|
| 14613 |
+
"step": 4170
|
| 14614 |
+
},
|
| 14615 |
+
{
|
| 14616 |
+
"epoch": 0.219002624671916,
|
| 14617 |
+
"grad_norm": 0.05695449188351631,
|
| 14618 |
+
"learning_rate": 0.0012,
|
| 14619 |
+
"loss": 2.3374922275543213,
|
| 14620 |
+
"step": 4172
|
| 14621 |
+
},
|
| 14622 |
+
{
|
| 14623 |
+
"epoch": 0.21910761154855643,
|
| 14624 |
+
"grad_norm": 0.047799114137887955,
|
| 14625 |
+
"learning_rate": 0.0012,
|
| 14626 |
+
"loss": 2.2822232246398926,
|
| 14627 |
+
"step": 4174
|
| 14628 |
+
},
|
| 14629 |
+
{
|
| 14630 |
+
"epoch": 0.21921259842519686,
|
| 14631 |
+
"grad_norm": 0.06139787286520004,
|
| 14632 |
+
"learning_rate": 0.0012,
|
| 14633 |
+
"loss": 2.387678861618042,
|
| 14634 |
+
"step": 4176
|
| 14635 |
+
},
|
| 14636 |
+
{
|
| 14637 |
+
"epoch": 0.21931758530183726,
|
| 14638 |
+
"grad_norm": 0.058951735496520996,
|
| 14639 |
+
"learning_rate": 0.0012,
|
| 14640 |
+
"loss": 2.3177285194396973,
|
| 14641 |
+
"step": 4178
|
| 14642 |
+
},
|
| 14643 |
+
{
|
| 14644 |
+
"epoch": 0.2194225721784777,
|
| 14645 |
+
"grad_norm": 0.04283323884010315,
|
| 14646 |
+
"learning_rate": 0.0012,
|
| 14647 |
+
"loss": 2.2705626487731934,
|
| 14648 |
+
"step": 4180
|
| 14649 |
+
},
|
| 14650 |
+
{
|
| 14651 |
+
"epoch": 0.21952755905511812,
|
| 14652 |
+
"grad_norm": 0.04229465126991272,
|
| 14653 |
+
"learning_rate": 0.0012,
|
| 14654 |
+
"loss": 2.2388198375701904,
|
| 14655 |
+
"step": 4182
|
| 14656 |
+
},
|
| 14657 |
+
{
|
| 14658 |
+
"epoch": 0.21963254593175854,
|
| 14659 |
+
"grad_norm": 0.05744798853993416,
|
| 14660 |
+
"learning_rate": 0.0012,
|
| 14661 |
+
"loss": 2.3290746212005615,
|
| 14662 |
+
"step": 4184
|
| 14663 |
+
},
|
| 14664 |
+
{
|
| 14665 |
+
"epoch": 0.21973753280839894,
|
| 14666 |
+
"grad_norm": 0.04573589935898781,
|
| 14667 |
+
"learning_rate": 0.0012,
|
| 14668 |
+
"loss": 2.320200204849243,
|
| 14669 |
+
"step": 4186
|
| 14670 |
+
},
|
| 14671 |
+
{
|
| 14672 |
+
"epoch": 0.21984251968503937,
|
| 14673 |
+
"grad_norm": 0.04751855507493019,
|
| 14674 |
+
"learning_rate": 0.0012,
|
| 14675 |
+
"loss": 2.3202855587005615,
|
| 14676 |
+
"step": 4188
|
| 14677 |
+
},
|
| 14678 |
+
{
|
| 14679 |
+
"epoch": 0.2199475065616798,
|
| 14680 |
+
"grad_norm": 0.048275742679834366,
|
| 14681 |
+
"learning_rate": 0.0012,
|
| 14682 |
+
"loss": 2.3013250827789307,
|
| 14683 |
+
"step": 4190
|
| 14684 |
+
},
|
| 14685 |
+
{
|
| 14686 |
+
"epoch": 0.2200524934383202,
|
| 14687 |
+
"grad_norm": 0.058497656136751175,
|
| 14688 |
+
"learning_rate": 0.0012,
|
| 14689 |
+
"loss": 2.27345609664917,
|
| 14690 |
+
"step": 4192
|
| 14691 |
+
},
|
| 14692 |
+
{
|
| 14693 |
+
"epoch": 0.22015748031496063,
|
| 14694 |
+
"grad_norm": 0.051108937710523605,
|
| 14695 |
+
"learning_rate": 0.0012,
|
| 14696 |
+
"loss": 2.2596054077148438,
|
| 14697 |
+
"step": 4194
|
| 14698 |
+
},
|
| 14699 |
+
{
|
| 14700 |
+
"epoch": 0.22026246719160106,
|
| 14701 |
+
"grad_norm": 0.04845741391181946,
|
| 14702 |
+
"learning_rate": 0.0012,
|
| 14703 |
+
"loss": 2.3169047832489014,
|
| 14704 |
+
"step": 4196
|
| 14705 |
+
},
|
| 14706 |
+
{
|
| 14707 |
+
"epoch": 0.22036745406824146,
|
| 14708 |
+
"grad_norm": 0.042769309133291245,
|
| 14709 |
+
"learning_rate": 0.0012,
|
| 14710 |
+
"loss": 2.295724391937256,
|
| 14711 |
+
"step": 4198
|
| 14712 |
+
},
|
| 14713 |
+
{
|
| 14714 |
+
"epoch": 0.2204724409448819,
|
| 14715 |
+
"grad_norm": 0.04947136342525482,
|
| 14716 |
+
"learning_rate": 0.0012,
|
| 14717 |
+
"loss": 2.3279497623443604,
|
| 14718 |
+
"step": 4200
|
| 14719 |
+
},
|
| 14720 |
+
{
|
| 14721 |
+
"epoch": 0.22057742782152231,
|
| 14722 |
+
"grad_norm": 0.044778622686862946,
|
| 14723 |
+
"learning_rate": 0.0012,
|
| 14724 |
+
"loss": 2.3165154457092285,
|
| 14725 |
+
"step": 4202
|
| 14726 |
+
},
|
| 14727 |
+
{
|
| 14728 |
+
"epoch": 0.22068241469816274,
|
| 14729 |
+
"grad_norm": 0.04317520186305046,
|
| 14730 |
+
"learning_rate": 0.0012,
|
| 14731 |
+
"loss": 2.3089873790740967,
|
| 14732 |
+
"step": 4204
|
| 14733 |
+
},
|
| 14734 |
+
{
|
| 14735 |
+
"epoch": 0.22078740157480314,
|
| 14736 |
+
"grad_norm": 0.04124528169631958,
|
| 14737 |
+
"learning_rate": 0.0012,
|
| 14738 |
+
"loss": 2.334254741668701,
|
| 14739 |
+
"step": 4206
|
| 14740 |
+
},
|
| 14741 |
+
{
|
| 14742 |
+
"epoch": 0.22089238845144357,
|
| 14743 |
+
"grad_norm": 0.0462951622903347,
|
| 14744 |
+
"learning_rate": 0.0012,
|
| 14745 |
+
"loss": 2.3085663318634033,
|
| 14746 |
+
"step": 4208
|
| 14747 |
+
},
|
| 14748 |
+
{
|
| 14749 |
+
"epoch": 0.220997375328084,
|
| 14750 |
+
"grad_norm": 0.0524025596678257,
|
| 14751 |
+
"learning_rate": 0.0012,
|
| 14752 |
+
"loss": 2.3321595191955566,
|
| 14753 |
+
"step": 4210
|
| 14754 |
+
},
|
| 14755 |
+
{
|
| 14756 |
+
"epoch": 0.2211023622047244,
|
| 14757 |
+
"grad_norm": 0.04186313971877098,
|
| 14758 |
+
"learning_rate": 0.0012,
|
| 14759 |
+
"loss": 2.2270355224609375,
|
| 14760 |
+
"step": 4212
|
| 14761 |
+
},
|
| 14762 |
+
{
|
| 14763 |
+
"epoch": 0.22120734908136483,
|
| 14764 |
+
"grad_norm": 0.048091527074575424,
|
| 14765 |
+
"learning_rate": 0.0012,
|
| 14766 |
+
"loss": 2.3487181663513184,
|
| 14767 |
+
"step": 4214
|
| 14768 |
+
},
|
| 14769 |
+
{
|
| 14770 |
+
"epoch": 0.22131233595800526,
|
| 14771 |
+
"grad_norm": 0.04905278608202934,
|
| 14772 |
+
"learning_rate": 0.0012,
|
| 14773 |
+
"loss": 2.336594820022583,
|
| 14774 |
+
"step": 4216
|
| 14775 |
+
},
|
| 14776 |
+
{
|
| 14777 |
+
"epoch": 0.22141732283464566,
|
| 14778 |
+
"grad_norm": 0.046344462782144547,
|
| 14779 |
+
"learning_rate": 0.0012,
|
| 14780 |
+
"loss": 2.250112295150757,
|
| 14781 |
+
"step": 4218
|
| 14782 |
+
},
|
| 14783 |
+
{
|
| 14784 |
+
"epoch": 0.2215223097112861,
|
| 14785 |
+
"grad_norm": 0.04182909429073334,
|
| 14786 |
+
"learning_rate": 0.0012,
|
| 14787 |
+
"loss": 2.2659411430358887,
|
| 14788 |
+
"step": 4220
|
| 14789 |
+
},
|
| 14790 |
+
{
|
| 14791 |
+
"epoch": 0.22162729658792651,
|
| 14792 |
+
"grad_norm": 0.043180521577596664,
|
| 14793 |
+
"learning_rate": 0.0012,
|
| 14794 |
+
"loss": 2.3385767936706543,
|
| 14795 |
+
"step": 4222
|
| 14796 |
+
},
|
| 14797 |
+
{
|
| 14798 |
+
"epoch": 0.22173228346456694,
|
| 14799 |
+
"grad_norm": 0.04595552384853363,
|
| 14800 |
+
"learning_rate": 0.0012,
|
| 14801 |
+
"loss": 2.345278263092041,
|
| 14802 |
+
"step": 4224
|
| 14803 |
+
},
|
| 14804 |
+
{
|
| 14805 |
+
"epoch": 0.22183727034120734,
|
| 14806 |
+
"grad_norm": 0.043637875467538834,
|
| 14807 |
+
"learning_rate": 0.0012,
|
| 14808 |
+
"loss": 2.289701461791992,
|
| 14809 |
+
"step": 4226
|
| 14810 |
+
},
|
| 14811 |
+
{
|
| 14812 |
+
"epoch": 0.22194225721784777,
|
| 14813 |
+
"grad_norm": 0.04451509565114975,
|
| 14814 |
+
"learning_rate": 0.0012,
|
| 14815 |
+
"loss": 2.3371353149414062,
|
| 14816 |
+
"step": 4228
|
| 14817 |
+
},
|
| 14818 |
+
{
|
| 14819 |
+
"epoch": 0.2220472440944882,
|
| 14820 |
+
"grad_norm": 0.05209393799304962,
|
| 14821 |
+
"learning_rate": 0.0012,
|
| 14822 |
+
"loss": 2.2456445693969727,
|
| 14823 |
+
"step": 4230
|
| 14824 |
+
},
|
| 14825 |
+
{
|
| 14826 |
+
"epoch": 0.2221522309711286,
|
| 14827 |
+
"grad_norm": 0.048868577927351,
|
| 14828 |
+
"learning_rate": 0.0012,
|
| 14829 |
+
"loss": 2.3224151134490967,
|
| 14830 |
+
"step": 4232
|
| 14831 |
+
},
|
| 14832 |
+
{
|
| 14833 |
+
"epoch": 0.22225721784776903,
|
| 14834 |
+
"grad_norm": 0.06716137379407883,
|
| 14835 |
+
"learning_rate": 0.0012,
|
| 14836 |
+
"loss": 2.3239402770996094,
|
| 14837 |
+
"step": 4234
|
| 14838 |
+
},
|
| 14839 |
+
{
|
| 14840 |
+
"epoch": 0.22236220472440946,
|
| 14841 |
+
"grad_norm": 0.05277295783162117,
|
| 14842 |
+
"learning_rate": 0.0012,
|
| 14843 |
+
"loss": 2.3631808757781982,
|
| 14844 |
+
"step": 4236
|
| 14845 |
+
},
|
| 14846 |
+
{
|
| 14847 |
+
"epoch": 0.22246719160104986,
|
| 14848 |
+
"grad_norm": 0.048199065029621124,
|
| 14849 |
+
"learning_rate": 0.0012,
|
| 14850 |
+
"loss": 2.3341164588928223,
|
| 14851 |
+
"step": 4238
|
| 14852 |
+
},
|
| 14853 |
+
{
|
| 14854 |
+
"epoch": 0.22257217847769029,
|
| 14855 |
+
"grad_norm": 0.06629456579685211,
|
| 14856 |
+
"learning_rate": 0.0012,
|
| 14857 |
+
"loss": 2.2959859371185303,
|
| 14858 |
+
"step": 4240
|
| 14859 |
+
},
|
| 14860 |
+
{
|
| 14861 |
+
"epoch": 0.22267716535433071,
|
| 14862 |
+
"grad_norm": 0.050782814621925354,
|
| 14863 |
+
"learning_rate": 0.0012,
|
| 14864 |
+
"loss": 2.2927043437957764,
|
| 14865 |
+
"step": 4242
|
| 14866 |
+
},
|
| 14867 |
+
{
|
| 14868 |
+
"epoch": 0.22278215223097114,
|
| 14869 |
+
"grad_norm": 0.047282785177230835,
|
| 14870 |
+
"learning_rate": 0.0012,
|
| 14871 |
+
"loss": 2.3118107318878174,
|
| 14872 |
+
"step": 4244
|
| 14873 |
+
},
|
| 14874 |
+
{
|
| 14875 |
+
"epoch": 0.22288713910761154,
|
| 14876 |
+
"grad_norm": 0.06405793875455856,
|
| 14877 |
+
"learning_rate": 0.0012,
|
| 14878 |
+
"loss": 2.283233404159546,
|
| 14879 |
+
"step": 4246
|
| 14880 |
+
},
|
| 14881 |
+
{
|
| 14882 |
+
"epoch": 0.22299212598425197,
|
| 14883 |
+
"grad_norm": 0.04794490337371826,
|
| 14884 |
+
"learning_rate": 0.0012,
|
| 14885 |
+
"loss": 2.294689178466797,
|
| 14886 |
+
"step": 4248
|
| 14887 |
+
},
|
| 14888 |
+
{
|
| 14889 |
+
"epoch": 0.2230971128608924,
|
| 14890 |
+
"grad_norm": 0.04764171689748764,
|
| 14891 |
+
"learning_rate": 0.0012,
|
| 14892 |
+
"loss": 2.302403450012207,
|
| 14893 |
+
"step": 4250
|
| 14894 |
+
},
|
| 14895 |
+
{
|
| 14896 |
+
"epoch": 0.2232020997375328,
|
| 14897 |
+
"grad_norm": 0.045342158526182175,
|
| 14898 |
+
"learning_rate": 0.0012,
|
| 14899 |
+
"loss": 2.2779250144958496,
|
| 14900 |
+
"step": 4252
|
| 14901 |
+
},
|
| 14902 |
+
{
|
| 14903 |
+
"epoch": 0.22330708661417323,
|
| 14904 |
+
"grad_norm": 0.04361673817038536,
|
| 14905 |
+
"learning_rate": 0.0012,
|
| 14906 |
+
"loss": 2.336688995361328,
|
| 14907 |
+
"step": 4254
|
| 14908 |
+
},
|
| 14909 |
+
{
|
| 14910 |
+
"epoch": 0.22341207349081366,
|
| 14911 |
+
"grad_norm": 0.043020568788051605,
|
| 14912 |
+
"learning_rate": 0.0012,
|
| 14913 |
+
"loss": 2.2903409004211426,
|
| 14914 |
+
"step": 4256
|
| 14915 |
+
},
|
| 14916 |
+
{
|
| 14917 |
+
"epoch": 0.22351706036745406,
|
| 14918 |
+
"grad_norm": 0.06655947118997574,
|
| 14919 |
+
"learning_rate": 0.0012,
|
| 14920 |
+
"loss": 2.345411539077759,
|
| 14921 |
+
"step": 4258
|
| 14922 |
+
},
|
| 14923 |
+
{
|
| 14924 |
+
"epoch": 0.22362204724409449,
|
| 14925 |
+
"grad_norm": 0.07394736260175705,
|
| 14926 |
+
"learning_rate": 0.0012,
|
| 14927 |
+
"loss": 2.3201165199279785,
|
| 14928 |
+
"step": 4260
|
| 14929 |
+
},
|
| 14930 |
+
{
|
| 14931 |
+
"epoch": 0.2237270341207349,
|
| 14932 |
+
"grad_norm": 0.04830233380198479,
|
| 14933 |
+
"learning_rate": 0.0012,
|
| 14934 |
+
"loss": 2.3345603942871094,
|
| 14935 |
+
"step": 4262
|
| 14936 |
+
},
|
| 14937 |
+
{
|
| 14938 |
+
"epoch": 0.22383202099737534,
|
| 14939 |
+
"grad_norm": 0.05969711020588875,
|
| 14940 |
+
"learning_rate": 0.0012,
|
| 14941 |
+
"loss": 2.329921245574951,
|
| 14942 |
+
"step": 4264
|
| 14943 |
+
},
|
| 14944 |
+
{
|
| 14945 |
+
"epoch": 0.22393700787401574,
|
| 14946 |
+
"grad_norm": 0.06056008115410805,
|
| 14947 |
+
"learning_rate": 0.0012,
|
| 14948 |
+
"loss": 2.321152687072754,
|
| 14949 |
+
"step": 4266
|
| 14950 |
+
},
|
| 14951 |
+
{
|
| 14952 |
+
"epoch": 0.22404199475065617,
|
| 14953 |
+
"grad_norm": 0.051685284823179245,
|
| 14954 |
+
"learning_rate": 0.0012,
|
| 14955 |
+
"loss": 2.318547010421753,
|
| 14956 |
+
"step": 4268
|
| 14957 |
+
},
|
| 14958 |
+
{
|
| 14959 |
+
"epoch": 0.2241469816272966,
|
| 14960 |
+
"grad_norm": 0.04345134273171425,
|
| 14961 |
+
"learning_rate": 0.0012,
|
| 14962 |
+
"loss": 2.2690176963806152,
|
| 14963 |
+
"step": 4270
|
| 14964 |
+
},
|
| 14965 |
+
{
|
| 14966 |
+
"epoch": 0.224251968503937,
|
| 14967 |
+
"grad_norm": 0.04598156362771988,
|
| 14968 |
+
"learning_rate": 0.0012,
|
| 14969 |
+
"loss": 2.3037829399108887,
|
| 14970 |
+
"step": 4272
|
| 14971 |
+
},
|
| 14972 |
+
{
|
| 14973 |
+
"epoch": 0.22435695538057743,
|
| 14974 |
+
"grad_norm": 0.05697587877511978,
|
| 14975 |
+
"learning_rate": 0.0012,
|
| 14976 |
+
"loss": 2.380026340484619,
|
| 14977 |
+
"step": 4274
|
| 14978 |
+
},
|
| 14979 |
+
{
|
| 14980 |
+
"epoch": 0.22446194225721786,
|
| 14981 |
+
"grad_norm": 0.05932621657848358,
|
| 14982 |
+
"learning_rate": 0.0012,
|
| 14983 |
+
"loss": 2.2725887298583984,
|
| 14984 |
+
"step": 4276
|
| 14985 |
+
},
|
| 14986 |
+
{
|
| 14987 |
+
"epoch": 0.22456692913385826,
|
| 14988 |
+
"grad_norm": 0.04200233146548271,
|
| 14989 |
+
"learning_rate": 0.0012,
|
| 14990 |
+
"loss": 2.387545108795166,
|
| 14991 |
+
"step": 4278
|
| 14992 |
+
},
|
| 14993 |
+
{
|
| 14994 |
+
"epoch": 0.22467191601049868,
|
| 14995 |
+
"grad_norm": 0.04376065731048584,
|
| 14996 |
+
"learning_rate": 0.0012,
|
| 14997 |
+
"loss": 2.2766029834747314,
|
| 14998 |
+
"step": 4280
|
| 14999 |
+
},
|
| 15000 |
+
{
|
| 15001 |
+
"epoch": 0.2247769028871391,
|
| 15002 |
+
"grad_norm": 0.04619079828262329,
|
| 15003 |
+
"learning_rate": 0.0012,
|
| 15004 |
+
"loss": 2.318946123123169,
|
| 15005 |
+
"step": 4282
|
| 15006 |
+
},
|
| 15007 |
+
{
|
| 15008 |
+
"epoch": 0.22488188976377954,
|
| 15009 |
+
"grad_norm": 0.04519796743988991,
|
| 15010 |
+
"learning_rate": 0.0012,
|
| 15011 |
+
"loss": 2.2926626205444336,
|
| 15012 |
+
"step": 4284
|
| 15013 |
+
},
|
| 15014 |
+
{
|
| 15015 |
+
"epoch": 0.22498687664041994,
|
| 15016 |
+
"grad_norm": 0.040054310113191605,
|
| 15017 |
+
"learning_rate": 0.0012,
|
| 15018 |
+
"loss": 2.2810792922973633,
|
| 15019 |
+
"step": 4286
|
| 15020 |
+
},
|
| 15021 |
+
{
|
| 15022 |
+
"epoch": 0.22509186351706037,
|
| 15023 |
+
"grad_norm": 0.04028797149658203,
|
| 15024 |
+
"learning_rate": 0.0012,
|
| 15025 |
+
"loss": 2.254239082336426,
|
| 15026 |
+
"step": 4288
|
| 15027 |
+
},
|
| 15028 |
+
{
|
| 15029 |
+
"epoch": 0.2251968503937008,
|
| 15030 |
+
"grad_norm": 0.044445790350437164,
|
| 15031 |
+
"learning_rate": 0.0012,
|
| 15032 |
+
"loss": 2.2583539485931396,
|
| 15033 |
+
"step": 4290
|
| 15034 |
+
},
|
| 15035 |
+
{
|
| 15036 |
+
"epoch": 0.2253018372703412,
|
| 15037 |
+
"grad_norm": 0.040539901703596115,
|
| 15038 |
+
"learning_rate": 0.0012,
|
| 15039 |
+
"loss": 2.333839178085327,
|
| 15040 |
+
"step": 4292
|
| 15041 |
+
},
|
| 15042 |
+
{
|
| 15043 |
+
"epoch": 0.22540682414698163,
|
| 15044 |
+
"grad_norm": 0.04011664167046547,
|
| 15045 |
+
"learning_rate": 0.0012,
|
| 15046 |
+
"loss": 2.2584564685821533,
|
| 15047 |
+
"step": 4294
|
| 15048 |
+
},
|
| 15049 |
+
{
|
| 15050 |
+
"epoch": 0.22551181102362206,
|
| 15051 |
+
"grad_norm": 0.04276219382882118,
|
| 15052 |
+
"learning_rate": 0.0012,
|
| 15053 |
+
"loss": 2.310431718826294,
|
| 15054 |
+
"step": 4296
|
| 15055 |
+
},
|
| 15056 |
+
{
|
| 15057 |
+
"epoch": 0.22561679790026246,
|
| 15058 |
+
"grad_norm": 0.05779052525758743,
|
| 15059 |
+
"learning_rate": 0.0012,
|
| 15060 |
+
"loss": 2.309715509414673,
|
| 15061 |
+
"step": 4298
|
| 15062 |
+
},
|
| 15063 |
+
{
|
| 15064 |
+
"epoch": 0.22572178477690288,
|
| 15065 |
+
"grad_norm": 0.05907858535647392,
|
| 15066 |
+
"learning_rate": 0.0012,
|
| 15067 |
+
"loss": 2.3372511863708496,
|
| 15068 |
+
"step": 4300
|
| 15069 |
+
},
|
| 15070 |
+
{
|
| 15071 |
+
"epoch": 0.2258267716535433,
|
| 15072 |
+
"grad_norm": 0.05285631865262985,
|
| 15073 |
+
"learning_rate": 0.0012,
|
| 15074 |
+
"loss": 2.346162796020508,
|
| 15075 |
+
"step": 4302
|
| 15076 |
+
},
|
| 15077 |
+
{
|
| 15078 |
+
"epoch": 0.22593175853018374,
|
| 15079 |
+
"grad_norm": 0.04860261455178261,
|
| 15080 |
+
"learning_rate": 0.0012,
|
| 15081 |
+
"loss": 2.376268148422241,
|
| 15082 |
+
"step": 4304
|
| 15083 |
+
},
|
| 15084 |
+
{
|
| 15085 |
+
"epoch": 0.22603674540682414,
|
| 15086 |
+
"grad_norm": 0.0445830337703228,
|
| 15087 |
+
"learning_rate": 0.0012,
|
| 15088 |
+
"loss": 2.3106093406677246,
|
| 15089 |
+
"step": 4306
|
| 15090 |
+
},
|
| 15091 |
+
{
|
| 15092 |
+
"epoch": 0.22614173228346457,
|
| 15093 |
+
"grad_norm": 0.05020787566900253,
|
| 15094 |
+
"learning_rate": 0.0012,
|
| 15095 |
+
"loss": 2.3394832611083984,
|
| 15096 |
+
"step": 4308
|
| 15097 |
+
},
|
| 15098 |
+
{
|
| 15099 |
+
"epoch": 0.226246719160105,
|
| 15100 |
+
"grad_norm": 0.04057034105062485,
|
| 15101 |
+
"learning_rate": 0.0012,
|
| 15102 |
+
"loss": 2.249891519546509,
|
| 15103 |
+
"step": 4310
|
| 15104 |
+
},
|
| 15105 |
+
{
|
| 15106 |
+
"epoch": 0.2263517060367454,
|
| 15107 |
+
"grad_norm": 0.04468918964266777,
|
| 15108 |
+
"learning_rate": 0.0012,
|
| 15109 |
+
"loss": 2.2871294021606445,
|
| 15110 |
+
"step": 4312
|
| 15111 |
+
},
|
| 15112 |
+
{
|
| 15113 |
+
"epoch": 0.22645669291338583,
|
| 15114 |
+
"grad_norm": 0.054384466260671616,
|
| 15115 |
+
"learning_rate": 0.0012,
|
| 15116 |
+
"loss": 2.3488190174102783,
|
| 15117 |
+
"step": 4314
|
| 15118 |
+
},
|
| 15119 |
+
{
|
| 15120 |
+
"epoch": 0.22656167979002625,
|
| 15121 |
+
"grad_norm": 0.04411957785487175,
|
| 15122 |
+
"learning_rate": 0.0012,
|
| 15123 |
+
"loss": 2.3114612102508545,
|
| 15124 |
+
"step": 4316
|
| 15125 |
+
},
|
| 15126 |
+
{
|
| 15127 |
+
"epoch": 0.22666666666666666,
|
| 15128 |
+
"grad_norm": 0.0659596398472786,
|
| 15129 |
+
"learning_rate": 0.0012,
|
| 15130 |
+
"loss": 2.324754238128662,
|
| 15131 |
+
"step": 4318
|
| 15132 |
+
},
|
| 15133 |
+
{
|
| 15134 |
+
"epoch": 0.22677165354330708,
|
| 15135 |
+
"grad_norm": 0.045985061675310135,
|
| 15136 |
+
"learning_rate": 0.0012,
|
| 15137 |
+
"loss": 2.296888589859009,
|
| 15138 |
+
"step": 4320
|
| 15139 |
+
},
|
| 15140 |
+
{
|
| 15141 |
+
"epoch": 0.2268766404199475,
|
| 15142 |
+
"grad_norm": 0.040438923984766006,
|
| 15143 |
+
"learning_rate": 0.0012,
|
| 15144 |
+
"loss": 2.3299787044525146,
|
| 15145 |
+
"step": 4322
|
| 15146 |
+
},
|
| 15147 |
+
{
|
| 15148 |
+
"epoch": 0.22698162729658794,
|
| 15149 |
+
"grad_norm": 0.04580257087945938,
|
| 15150 |
+
"learning_rate": 0.0012,
|
| 15151 |
+
"loss": 2.245194911956787,
|
| 15152 |
+
"step": 4324
|
| 15153 |
+
},
|
| 15154 |
+
{
|
| 15155 |
+
"epoch": 0.22708661417322834,
|
| 15156 |
+
"grad_norm": 0.06081218272447586,
|
| 15157 |
+
"learning_rate": 0.0012,
|
| 15158 |
+
"loss": 2.3110268115997314,
|
| 15159 |
+
"step": 4326
|
| 15160 |
+
},
|
| 15161 |
+
{
|
| 15162 |
+
"epoch": 0.22719160104986877,
|
| 15163 |
+
"grad_norm": 0.05053591728210449,
|
| 15164 |
+
"learning_rate": 0.0012,
|
| 15165 |
+
"loss": 2.295142650604248,
|
| 15166 |
+
"step": 4328
|
| 15167 |
+
},
|
| 15168 |
+
{
|
| 15169 |
+
"epoch": 0.2272965879265092,
|
| 15170 |
+
"grad_norm": 0.04593752324581146,
|
| 15171 |
+
"learning_rate": 0.0012,
|
| 15172 |
+
"loss": 2.32218074798584,
|
| 15173 |
+
"step": 4330
|
| 15174 |
+
},
|
| 15175 |
+
{
|
| 15176 |
+
"epoch": 0.2274015748031496,
|
| 15177 |
+
"grad_norm": 0.05189074948430061,
|
| 15178 |
+
"learning_rate": 0.0012,
|
| 15179 |
+
"loss": 2.221546173095703,
|
| 15180 |
+
"step": 4332
|
| 15181 |
+
},
|
| 15182 |
+
{
|
| 15183 |
+
"epoch": 0.22750656167979003,
|
| 15184 |
+
"grad_norm": 0.05759125202894211,
|
| 15185 |
+
"learning_rate": 0.0012,
|
| 15186 |
+
"loss": 2.3206329345703125,
|
| 15187 |
+
"step": 4334
|
| 15188 |
+
},
|
| 15189 |
+
{
|
| 15190 |
+
"epoch": 0.22761154855643045,
|
| 15191 |
+
"grad_norm": 0.05540764704346657,
|
| 15192 |
+
"learning_rate": 0.0012,
|
| 15193 |
+
"loss": 2.285482406616211,
|
| 15194 |
+
"step": 4336
|
| 15195 |
+
},
|
| 15196 |
+
{
|
| 15197 |
+
"epoch": 0.22771653543307085,
|
| 15198 |
+
"grad_norm": 0.04945513978600502,
|
| 15199 |
+
"learning_rate": 0.0012,
|
| 15200 |
+
"loss": 2.3308613300323486,
|
| 15201 |
+
"step": 4338
|
| 15202 |
+
},
|
| 15203 |
+
{
|
| 15204 |
+
"epoch": 0.22782152230971128,
|
| 15205 |
+
"grad_norm": 0.040794651955366135,
|
| 15206 |
+
"learning_rate": 0.0012,
|
| 15207 |
+
"loss": 2.26810622215271,
|
| 15208 |
+
"step": 4340
|
| 15209 |
+
},
|
| 15210 |
+
{
|
| 15211 |
+
"epoch": 0.2279265091863517,
|
| 15212 |
+
"grad_norm": 0.0515298955142498,
|
| 15213 |
+
"learning_rate": 0.0012,
|
| 15214 |
+
"loss": 2.2894325256347656,
|
| 15215 |
+
"step": 4342
|
| 15216 |
+
},
|
| 15217 |
+
{
|
| 15218 |
+
"epoch": 0.22803149606299214,
|
| 15219 |
+
"grad_norm": 0.06840723752975464,
|
| 15220 |
+
"learning_rate": 0.0012,
|
| 15221 |
+
"loss": 2.3459198474884033,
|
| 15222 |
+
"step": 4344
|
| 15223 |
+
},
|
| 15224 |
+
{
|
| 15225 |
+
"epoch": 0.22813648293963254,
|
| 15226 |
+
"grad_norm": 0.04800982028245926,
|
| 15227 |
+
"learning_rate": 0.0012,
|
| 15228 |
+
"loss": 2.302959680557251,
|
| 15229 |
+
"step": 4346
|
| 15230 |
+
},
|
| 15231 |
+
{
|
| 15232 |
+
"epoch": 0.22824146981627297,
|
| 15233 |
+
"grad_norm": 0.04245338588953018,
|
| 15234 |
+
"learning_rate": 0.0012,
|
| 15235 |
+
"loss": 2.2573957443237305,
|
| 15236 |
+
"step": 4348
|
| 15237 |
+
},
|
| 15238 |
+
{
|
| 15239 |
+
"epoch": 0.2283464566929134,
|
| 15240 |
+
"grad_norm": 0.06061679869890213,
|
| 15241 |
+
"learning_rate": 0.0012,
|
| 15242 |
+
"loss": 2.2338314056396484,
|
| 15243 |
+
"step": 4350
|
| 15244 |
+
},
|
| 15245 |
+
{
|
| 15246 |
+
"epoch": 0.2284514435695538,
|
| 15247 |
+
"grad_norm": 0.057015858590602875,
|
| 15248 |
+
"learning_rate": 0.0012,
|
| 15249 |
+
"loss": 2.319645404815674,
|
| 15250 |
+
"step": 4352
|
| 15251 |
+
},
|
| 15252 |
+
{
|
| 15253 |
+
"epoch": 0.22855643044619423,
|
| 15254 |
+
"grad_norm": 0.04812008515000343,
|
| 15255 |
+
"learning_rate": 0.0012,
|
| 15256 |
+
"loss": 2.3143668174743652,
|
| 15257 |
+
"step": 4354
|
| 15258 |
+
},
|
| 15259 |
+
{
|
| 15260 |
+
"epoch": 0.22866141732283465,
|
| 15261 |
+
"grad_norm": 0.04824516549706459,
|
| 15262 |
+
"learning_rate": 0.0012,
|
| 15263 |
+
"loss": 2.2588586807250977,
|
| 15264 |
+
"step": 4356
|
| 15265 |
+
},
|
| 15266 |
+
{
|
| 15267 |
+
"epoch": 0.22876640419947505,
|
| 15268 |
+
"grad_norm": 0.0625266283750534,
|
| 15269 |
+
"learning_rate": 0.0012,
|
| 15270 |
+
"loss": 2.299670934677124,
|
| 15271 |
+
"step": 4358
|
| 15272 |
+
},
|
| 15273 |
+
{
|
| 15274 |
+
"epoch": 0.22887139107611548,
|
| 15275 |
+
"grad_norm": 0.05461130663752556,
|
| 15276 |
+
"learning_rate": 0.0012,
|
| 15277 |
+
"loss": 2.284795045852661,
|
| 15278 |
+
"step": 4360
|
| 15279 |
+
},
|
| 15280 |
+
{
|
| 15281 |
+
"epoch": 0.2289763779527559,
|
| 15282 |
+
"grad_norm": 0.042621586471796036,
|
| 15283 |
+
"learning_rate": 0.0012,
|
| 15284 |
+
"loss": 2.288219690322876,
|
| 15285 |
+
"step": 4362
|
| 15286 |
+
},
|
| 15287 |
+
{
|
| 15288 |
+
"epoch": 0.22908136482939634,
|
| 15289 |
+
"grad_norm": 0.04423161596059799,
|
| 15290 |
+
"learning_rate": 0.0012,
|
| 15291 |
+
"loss": 2.2048380374908447,
|
| 15292 |
+
"step": 4364
|
| 15293 |
+
},
|
| 15294 |
+
{
|
| 15295 |
+
"epoch": 0.22918635170603674,
|
| 15296 |
+
"grad_norm": 0.045524850487709045,
|
| 15297 |
+
"learning_rate": 0.0012,
|
| 15298 |
+
"loss": 2.2570865154266357,
|
| 15299 |
+
"step": 4366
|
| 15300 |
+
},
|
| 15301 |
+
{
|
| 15302 |
+
"epoch": 0.22929133858267717,
|
| 15303 |
+
"grad_norm": 0.04483406990766525,
|
| 15304 |
+
"learning_rate": 0.0012,
|
| 15305 |
+
"loss": 2.386355400085449,
|
| 15306 |
+
"step": 4368
|
| 15307 |
+
},
|
| 15308 |
+
{
|
| 15309 |
+
"epoch": 0.2293963254593176,
|
| 15310 |
+
"grad_norm": 0.0458289198577404,
|
| 15311 |
+
"learning_rate": 0.0012,
|
| 15312 |
+
"loss": 2.2681515216827393,
|
| 15313 |
+
"step": 4370
|
| 15314 |
+
},
|
| 15315 |
+
{
|
| 15316 |
+
"epoch": 0.229501312335958,
|
| 15317 |
+
"grad_norm": 0.04469006881117821,
|
| 15318 |
+
"learning_rate": 0.0012,
|
| 15319 |
+
"loss": 2.317216157913208,
|
| 15320 |
+
"step": 4372
|
| 15321 |
+
},
|
| 15322 |
+
{
|
| 15323 |
+
"epoch": 0.22960629921259842,
|
| 15324 |
+
"grad_norm": 0.05440415441989899,
|
| 15325 |
+
"learning_rate": 0.0012,
|
| 15326 |
+
"loss": 2.3524014949798584,
|
| 15327 |
+
"step": 4374
|
| 15328 |
+
},
|
| 15329 |
+
{
|
| 15330 |
+
"epoch": 0.22971128608923885,
|
| 15331 |
+
"grad_norm": 0.04562048614025116,
|
| 15332 |
+
"learning_rate": 0.0012,
|
| 15333 |
+
"loss": 2.268861770629883,
|
| 15334 |
+
"step": 4376
|
| 15335 |
+
},
|
| 15336 |
+
{
|
| 15337 |
+
"epoch": 0.22981627296587925,
|
| 15338 |
+
"grad_norm": 0.043899890035390854,
|
| 15339 |
+
"learning_rate": 0.0012,
|
| 15340 |
+
"loss": 2.236745595932007,
|
| 15341 |
+
"step": 4378
|
| 15342 |
+
},
|
| 15343 |
+
{
|
| 15344 |
+
"epoch": 0.22992125984251968,
|
| 15345 |
+
"grad_norm": 0.05589818209409714,
|
| 15346 |
+
"learning_rate": 0.0012,
|
| 15347 |
+
"loss": 2.3216350078582764,
|
| 15348 |
+
"step": 4380
|
| 15349 |
+
},
|
| 15350 |
+
{
|
| 15351 |
+
"epoch": 0.2300262467191601,
|
| 15352 |
+
"grad_norm": 0.05757816508412361,
|
| 15353 |
+
"learning_rate": 0.0012,
|
| 15354 |
+
"loss": 2.3198108673095703,
|
| 15355 |
+
"step": 4382
|
| 15356 |
+
},
|
| 15357 |
+
{
|
| 15358 |
+
"epoch": 0.23013123359580054,
|
| 15359 |
+
"grad_norm": 0.04763399437069893,
|
| 15360 |
+
"learning_rate": 0.0012,
|
| 15361 |
+
"loss": 2.2359776496887207,
|
| 15362 |
+
"step": 4384
|
| 15363 |
+
},
|
| 15364 |
+
{
|
| 15365 |
+
"epoch": 0.23023622047244094,
|
| 15366 |
+
"grad_norm": 0.05214901641011238,
|
| 15367 |
+
"learning_rate": 0.0012,
|
| 15368 |
+
"loss": 2.269841194152832,
|
| 15369 |
+
"step": 4386
|
| 15370 |
+
},
|
| 15371 |
+
{
|
| 15372 |
+
"epoch": 0.23034120734908137,
|
| 15373 |
+
"grad_norm": 0.05183875933289528,
|
| 15374 |
+
"learning_rate": 0.0012,
|
| 15375 |
+
"loss": 2.2681427001953125,
|
| 15376 |
+
"step": 4388
|
| 15377 |
+
},
|
| 15378 |
+
{
|
| 15379 |
+
"epoch": 0.2304461942257218,
|
| 15380 |
+
"grad_norm": 0.043433286249637604,
|
| 15381 |
+
"learning_rate": 0.0012,
|
| 15382 |
+
"loss": 2.2771997451782227,
|
| 15383 |
+
"step": 4390
|
| 15384 |
+
},
|
| 15385 |
+
{
|
| 15386 |
+
"epoch": 0.2305511811023622,
|
| 15387 |
+
"grad_norm": 0.05537429824471474,
|
| 15388 |
+
"learning_rate": 0.0012,
|
| 15389 |
+
"loss": 2.2396957874298096,
|
| 15390 |
+
"step": 4392
|
| 15391 |
+
},
|
| 15392 |
+
{
|
| 15393 |
+
"epoch": 0.23065616797900262,
|
| 15394 |
+
"grad_norm": 0.06353399157524109,
|
| 15395 |
+
"learning_rate": 0.0012,
|
| 15396 |
+
"loss": 2.306800603866577,
|
| 15397 |
+
"step": 4394
|
| 15398 |
+
},
|
| 15399 |
+
{
|
| 15400 |
+
"epoch": 0.23076115485564305,
|
| 15401 |
+
"grad_norm": 0.053038179874420166,
|
| 15402 |
+
"learning_rate": 0.0012,
|
| 15403 |
+
"loss": 2.3055763244628906,
|
| 15404 |
+
"step": 4396
|
| 15405 |
+
},
|
| 15406 |
+
{
|
| 15407 |
+
"epoch": 0.23086614173228345,
|
| 15408 |
+
"grad_norm": 0.05523674935102463,
|
| 15409 |
+
"learning_rate": 0.0012,
|
| 15410 |
+
"loss": 2.3658432960510254,
|
| 15411 |
+
"step": 4398
|
| 15412 |
+
},
|
| 15413 |
+
{
|
| 15414 |
+
"epoch": 0.23097112860892388,
|
| 15415 |
+
"grad_norm": 0.07258778810501099,
|
| 15416 |
+
"learning_rate": 0.0012,
|
| 15417 |
+
"loss": 2.2956926822662354,
|
| 15418 |
+
"step": 4400
|
| 15419 |
+
},
|
| 15420 |
+
{
|
| 15421 |
+
"epoch": 0.2310761154855643,
|
| 15422 |
+
"grad_norm": 0.055484045296907425,
|
| 15423 |
+
"learning_rate": 0.0012,
|
| 15424 |
+
"loss": 2.3231942653656006,
|
| 15425 |
+
"step": 4402
|
| 15426 |
+
},
|
| 15427 |
+
{
|
| 15428 |
+
"epoch": 0.23118110236220474,
|
| 15429 |
+
"grad_norm": 0.04638616740703583,
|
| 15430 |
+
"learning_rate": 0.0012,
|
| 15431 |
+
"loss": 2.244957208633423,
|
| 15432 |
+
"step": 4404
|
| 15433 |
+
},
|
| 15434 |
+
{
|
| 15435 |
+
"epoch": 0.23128608923884514,
|
| 15436 |
+
"grad_norm": 0.04976091906428337,
|
| 15437 |
+
"learning_rate": 0.0012,
|
| 15438 |
+
"loss": 2.208756446838379,
|
| 15439 |
+
"step": 4406
|
| 15440 |
+
},
|
| 15441 |
+
{
|
| 15442 |
+
"epoch": 0.23139107611548557,
|
| 15443 |
+
"grad_norm": 0.04240934178233147,
|
| 15444 |
+
"learning_rate": 0.0012,
|
| 15445 |
+
"loss": 2.271836996078491,
|
| 15446 |
+
"step": 4408
|
| 15447 |
+
},
|
| 15448 |
+
{
|
| 15449 |
+
"epoch": 0.231496062992126,
|
| 15450 |
+
"grad_norm": 0.045365408062934875,
|
| 15451 |
+
"learning_rate": 0.0012,
|
| 15452 |
+
"loss": 2.2855451107025146,
|
| 15453 |
+
"step": 4410
|
| 15454 |
+
},
|
| 15455 |
+
{
|
| 15456 |
+
"epoch": 0.2316010498687664,
|
| 15457 |
+
"grad_norm": 0.04454977810382843,
|
| 15458 |
+
"learning_rate": 0.0012,
|
| 15459 |
+
"loss": 2.223578453063965,
|
| 15460 |
+
"step": 4412
|
| 15461 |
+
},
|
| 15462 |
+
{
|
| 15463 |
+
"epoch": 0.23170603674540682,
|
| 15464 |
+
"grad_norm": 0.050736457109451294,
|
| 15465 |
+
"learning_rate": 0.0012,
|
| 15466 |
+
"loss": 2.287034273147583,
|
| 15467 |
+
"step": 4414
|
| 15468 |
+
},
|
| 15469 |
+
{
|
| 15470 |
+
"epoch": 0.23181102362204725,
|
| 15471 |
+
"grad_norm": 0.04402821138501167,
|
| 15472 |
+
"learning_rate": 0.0012,
|
| 15473 |
+
"loss": 2.2653558254241943,
|
| 15474 |
+
"step": 4416
|
| 15475 |
+
},
|
| 15476 |
+
{
|
| 15477 |
+
"epoch": 0.23191601049868765,
|
| 15478 |
+
"grad_norm": 0.05391089618206024,
|
| 15479 |
+
"learning_rate": 0.0012,
|
| 15480 |
+
"loss": 2.31840443611145,
|
| 15481 |
+
"step": 4418
|
| 15482 |
+
},
|
| 15483 |
+
{
|
| 15484 |
+
"epoch": 0.23202099737532808,
|
| 15485 |
+
"grad_norm": 0.05326833575963974,
|
| 15486 |
+
"learning_rate": 0.0012,
|
| 15487 |
+
"loss": 2.2889912128448486,
|
| 15488 |
+
"step": 4420
|
| 15489 |
+
},
|
| 15490 |
+
{
|
| 15491 |
+
"epoch": 0.2321259842519685,
|
| 15492 |
+
"grad_norm": 0.07055206596851349,
|
| 15493 |
+
"learning_rate": 0.0012,
|
| 15494 |
+
"loss": 2.316769599914551,
|
| 15495 |
+
"step": 4422
|
| 15496 |
+
},
|
| 15497 |
+
{
|
| 15498 |
+
"epoch": 0.23223097112860894,
|
| 15499 |
+
"grad_norm": 0.04401353746652603,
|
| 15500 |
+
"learning_rate": 0.0012,
|
| 15501 |
+
"loss": 2.2936203479766846,
|
| 15502 |
+
"step": 4424
|
| 15503 |
+
},
|
| 15504 |
+
{
|
| 15505 |
+
"epoch": 0.23233595800524934,
|
| 15506 |
+
"grad_norm": 0.04690353572368622,
|
| 15507 |
+
"learning_rate": 0.0012,
|
| 15508 |
+
"loss": 2.3698108196258545,
|
| 15509 |
+
"step": 4426
|
| 15510 |
+
},
|
| 15511 |
+
{
|
| 15512 |
+
"epoch": 0.23244094488188977,
|
| 15513 |
+
"grad_norm": 0.04592208191752434,
|
| 15514 |
+
"learning_rate": 0.0012,
|
| 15515 |
+
"loss": 2.2719690799713135,
|
| 15516 |
+
"step": 4428
|
| 15517 |
+
},
|
| 15518 |
+
{
|
| 15519 |
+
"epoch": 0.2325459317585302,
|
| 15520 |
+
"grad_norm": 0.05718933790922165,
|
| 15521 |
+
"learning_rate": 0.0012,
|
| 15522 |
+
"loss": 2.291151523590088,
|
| 15523 |
+
"step": 4430
|
| 15524 |
+
},
|
| 15525 |
+
{
|
| 15526 |
+
"epoch": 0.2326509186351706,
|
| 15527 |
+
"grad_norm": 0.041708316653966904,
|
| 15528 |
+
"learning_rate": 0.0012,
|
| 15529 |
+
"loss": 2.250962495803833,
|
| 15530 |
+
"step": 4432
|
| 15531 |
+
},
|
| 15532 |
+
{
|
| 15533 |
+
"epoch": 0.23275590551181102,
|
| 15534 |
+
"grad_norm": 0.0560762882232666,
|
| 15535 |
+
"learning_rate": 0.0012,
|
| 15536 |
+
"loss": 2.304586172103882,
|
| 15537 |
+
"step": 4434
|
| 15538 |
+
},
|
| 15539 |
+
{
|
| 15540 |
+
"epoch": 0.23286089238845145,
|
| 15541 |
+
"grad_norm": 0.055388517677783966,
|
| 15542 |
+
"learning_rate": 0.0012,
|
| 15543 |
+
"loss": 2.3200602531433105,
|
| 15544 |
+
"step": 4436
|
| 15545 |
+
},
|
| 15546 |
+
{
|
| 15547 |
+
"epoch": 0.23296587926509185,
|
| 15548 |
+
"grad_norm": 0.04475594684481621,
|
| 15549 |
+
"learning_rate": 0.0012,
|
| 15550 |
+
"loss": 2.300713062286377,
|
| 15551 |
+
"step": 4438
|
| 15552 |
+
},
|
| 15553 |
+
{
|
| 15554 |
+
"epoch": 0.23307086614173228,
|
| 15555 |
+
"grad_norm": 0.04688408598303795,
|
| 15556 |
+
"learning_rate": 0.0012,
|
| 15557 |
+
"loss": 2.267047166824341,
|
| 15558 |
+
"step": 4440
|
| 15559 |
+
},
|
| 15560 |
+
{
|
| 15561 |
+
"epoch": 0.2331758530183727,
|
| 15562 |
+
"grad_norm": 0.05469619482755661,
|
| 15563 |
+
"learning_rate": 0.0012,
|
| 15564 |
+
"loss": 2.3083431720733643,
|
| 15565 |
+
"step": 4442
|
| 15566 |
+
},
|
| 15567 |
+
{
|
| 15568 |
+
"epoch": 0.23328083989501314,
|
| 15569 |
+
"grad_norm": 0.04785188287496567,
|
| 15570 |
+
"learning_rate": 0.0012,
|
| 15571 |
+
"loss": 2.252305746078491,
|
| 15572 |
+
"step": 4444
|
| 15573 |
+
},
|
| 15574 |
+
{
|
| 15575 |
+
"epoch": 0.23338582677165354,
|
| 15576 |
+
"grad_norm": 0.05497340112924576,
|
| 15577 |
+
"learning_rate": 0.0012,
|
| 15578 |
+
"loss": 2.2744996547698975,
|
| 15579 |
+
"step": 4446
|
| 15580 |
+
},
|
| 15581 |
+
{
|
| 15582 |
+
"epoch": 0.23349081364829397,
|
| 15583 |
+
"grad_norm": 0.05560217425227165,
|
| 15584 |
+
"learning_rate": 0.0012,
|
| 15585 |
+
"loss": 2.277060031890869,
|
| 15586 |
+
"step": 4448
|
| 15587 |
+
},
|
| 15588 |
+
{
|
| 15589 |
+
"epoch": 0.2335958005249344,
|
| 15590 |
+
"grad_norm": 0.05788816511631012,
|
| 15591 |
+
"learning_rate": 0.0012,
|
| 15592 |
+
"loss": 2.2618017196655273,
|
| 15593 |
+
"step": 4450
|
| 15594 |
+
},
|
| 15595 |
+
{
|
| 15596 |
+
"epoch": 0.2337007874015748,
|
| 15597 |
+
"grad_norm": 0.04659624025225639,
|
| 15598 |
+
"learning_rate": 0.0012,
|
| 15599 |
+
"loss": 2.3181817531585693,
|
| 15600 |
+
"step": 4452
|
| 15601 |
+
},
|
| 15602 |
+
{
|
| 15603 |
+
"epoch": 0.23380577427821522,
|
| 15604 |
+
"grad_norm": 0.04405904933810234,
|
| 15605 |
+
"learning_rate": 0.0012,
|
| 15606 |
+
"loss": 2.329939365386963,
|
| 15607 |
+
"step": 4454
|
| 15608 |
+
},
|
| 15609 |
+
{
|
| 15610 |
+
"epoch": 0.23391076115485565,
|
| 15611 |
+
"grad_norm": 0.04342251643538475,
|
| 15612 |
+
"learning_rate": 0.0012,
|
| 15613 |
+
"loss": 2.326190233230591,
|
| 15614 |
+
"step": 4456
|
| 15615 |
+
},
|
| 15616 |
+
{
|
| 15617 |
+
"epoch": 0.23401574803149605,
|
| 15618 |
+
"grad_norm": 0.03961675614118576,
|
| 15619 |
+
"learning_rate": 0.0012,
|
| 15620 |
+
"loss": 2.3183648586273193,
|
| 15621 |
+
"step": 4458
|
| 15622 |
+
},
|
| 15623 |
+
{
|
| 15624 |
+
"epoch": 0.23412073490813648,
|
| 15625 |
+
"grad_norm": 0.046559687703847885,
|
| 15626 |
+
"learning_rate": 0.0012,
|
| 15627 |
+
"loss": 2.2894206047058105,
|
| 15628 |
+
"step": 4460
|
| 15629 |
+
},
|
| 15630 |
+
{
|
| 15631 |
+
"epoch": 0.2342257217847769,
|
| 15632 |
+
"grad_norm": 0.04673216864466667,
|
| 15633 |
+
"learning_rate": 0.0012,
|
| 15634 |
+
"loss": 2.3515894412994385,
|
| 15635 |
+
"step": 4462
|
| 15636 |
+
},
|
| 15637 |
+
{
|
| 15638 |
+
"epoch": 0.23433070866141734,
|
| 15639 |
+
"grad_norm": 0.047728072851896286,
|
| 15640 |
+
"learning_rate": 0.0012,
|
| 15641 |
+
"loss": 2.369748115539551,
|
| 15642 |
+
"step": 4464
|
| 15643 |
+
},
|
| 15644 |
+
{
|
| 15645 |
+
"epoch": 0.23443569553805774,
|
| 15646 |
+
"grad_norm": 0.046276796609163284,
|
| 15647 |
+
"learning_rate": 0.0012,
|
| 15648 |
+
"loss": 2.30195689201355,
|
| 15649 |
+
"step": 4466
|
| 15650 |
+
},
|
| 15651 |
+
{
|
| 15652 |
+
"epoch": 0.23454068241469817,
|
| 15653 |
+
"grad_norm": 0.04797663539648056,
|
| 15654 |
+
"learning_rate": 0.0012,
|
| 15655 |
+
"loss": 2.2799692153930664,
|
| 15656 |
+
"step": 4468
|
| 15657 |
+
},
|
| 15658 |
+
{
|
| 15659 |
+
"epoch": 0.2346456692913386,
|
| 15660 |
+
"grad_norm": 0.0424526184797287,
|
| 15661 |
+
"learning_rate": 0.0012,
|
| 15662 |
+
"loss": 2.3059475421905518,
|
| 15663 |
+
"step": 4470
|
| 15664 |
+
},
|
| 15665 |
+
{
|
| 15666 |
+
"epoch": 0.234750656167979,
|
| 15667 |
+
"grad_norm": 0.046768952161073685,
|
| 15668 |
+
"learning_rate": 0.0012,
|
| 15669 |
+
"loss": 2.2672009468078613,
|
| 15670 |
+
"step": 4472
|
| 15671 |
+
},
|
| 15672 |
+
{
|
| 15673 |
+
"epoch": 0.23485564304461942,
|
| 15674 |
+
"grad_norm": 0.04720231145620346,
|
| 15675 |
+
"learning_rate": 0.0012,
|
| 15676 |
+
"loss": 2.3187689781188965,
|
| 15677 |
+
"step": 4474
|
| 15678 |
+
},
|
| 15679 |
+
{
|
| 15680 |
+
"epoch": 0.23496062992125985,
|
| 15681 |
+
"grad_norm": 0.05006071552634239,
|
| 15682 |
+
"learning_rate": 0.0012,
|
| 15683 |
+
"loss": 2.304008960723877,
|
| 15684 |
+
"step": 4476
|
| 15685 |
+
},
|
| 15686 |
+
{
|
| 15687 |
+
"epoch": 0.23506561679790025,
|
| 15688 |
+
"grad_norm": 0.04533524066209793,
|
| 15689 |
+
"learning_rate": 0.0012,
|
| 15690 |
+
"loss": 2.3390920162200928,
|
| 15691 |
+
"step": 4478
|
| 15692 |
+
},
|
| 15693 |
+
{
|
| 15694 |
+
"epoch": 0.23517060367454068,
|
| 15695 |
+
"grad_norm": 0.040898144245147705,
|
| 15696 |
+
"learning_rate": 0.0012,
|
| 15697 |
+
"loss": 2.265878438949585,
|
| 15698 |
+
"step": 4480
|
| 15699 |
+
},
|
| 15700 |
+
{
|
| 15701 |
+
"epoch": 0.2352755905511811,
|
| 15702 |
+
"grad_norm": 0.04486710950732231,
|
| 15703 |
+
"learning_rate": 0.0012,
|
| 15704 |
+
"loss": 2.2515499591827393,
|
| 15705 |
+
"step": 4482
|
| 15706 |
+
},
|
| 15707 |
+
{
|
| 15708 |
+
"epoch": 0.23538057742782154,
|
| 15709 |
+
"grad_norm": 0.041984762996435165,
|
| 15710 |
+
"learning_rate": 0.0012,
|
| 15711 |
+
"loss": 2.2575745582580566,
|
| 15712 |
+
"step": 4484
|
| 15713 |
+
},
|
| 15714 |
+
{
|
| 15715 |
+
"epoch": 0.23548556430446194,
|
| 15716 |
+
"grad_norm": 0.05554104968905449,
|
| 15717 |
+
"learning_rate": 0.0012,
|
| 15718 |
+
"loss": 2.322751522064209,
|
| 15719 |
+
"step": 4486
|
| 15720 |
+
},
|
| 15721 |
+
{
|
| 15722 |
+
"epoch": 0.23559055118110236,
|
| 15723 |
+
"grad_norm": 0.04145142063498497,
|
| 15724 |
+
"learning_rate": 0.0012,
|
| 15725 |
+
"loss": 2.2614521980285645,
|
| 15726 |
+
"step": 4488
|
| 15727 |
+
},
|
| 15728 |
+
{
|
| 15729 |
+
"epoch": 0.2356955380577428,
|
| 15730 |
+
"grad_norm": 0.055921074002981186,
|
| 15731 |
+
"learning_rate": 0.0012,
|
| 15732 |
+
"loss": 2.3078503608703613,
|
| 15733 |
+
"step": 4490
|
| 15734 |
+
},
|
| 15735 |
+
{
|
| 15736 |
+
"epoch": 0.2358005249343832,
|
| 15737 |
+
"grad_norm": 0.054193031042814255,
|
| 15738 |
+
"learning_rate": 0.0012,
|
| 15739 |
+
"loss": 2.2978594303131104,
|
| 15740 |
+
"step": 4492
|
| 15741 |
+
},
|
| 15742 |
+
{
|
| 15743 |
+
"epoch": 0.23590551181102362,
|
| 15744 |
+
"grad_norm": 0.04495964199304581,
|
| 15745 |
+
"learning_rate": 0.0012,
|
| 15746 |
+
"loss": 2.2903988361358643,
|
| 15747 |
+
"step": 4494
|
| 15748 |
+
},
|
| 15749 |
+
{
|
| 15750 |
+
"epoch": 0.23601049868766405,
|
| 15751 |
+
"grad_norm": 0.05226229876279831,
|
| 15752 |
+
"learning_rate": 0.0012,
|
| 15753 |
+
"loss": 2.2459139823913574,
|
| 15754 |
+
"step": 4496
|
| 15755 |
+
},
|
| 15756 |
+
{
|
| 15757 |
+
"epoch": 0.23611548556430445,
|
| 15758 |
+
"grad_norm": 0.04779040068387985,
|
| 15759 |
+
"learning_rate": 0.0012,
|
| 15760 |
+
"loss": 2.252250909805298,
|
| 15761 |
+
"step": 4498
|
| 15762 |
+
},
|
| 15763 |
+
{
|
| 15764 |
+
"epoch": 0.23622047244094488,
|
| 15765 |
+
"grad_norm": 0.04290228709578514,
|
| 15766 |
+
"learning_rate": 0.0012,
|
| 15767 |
+
"loss": 2.3300724029541016,
|
| 15768 |
+
"step": 4500
|
| 15769 |
+
},
|
| 15770 |
+
{
|
| 15771 |
+
"epoch": 0.2363254593175853,
|
| 15772 |
+
"grad_norm": 0.04971368610858917,
|
| 15773 |
+
"learning_rate": 0.0012,
|
| 15774 |
+
"loss": 2.2043352127075195,
|
| 15775 |
+
"step": 4502
|
| 15776 |
+
},
|
| 15777 |
+
{
|
| 15778 |
+
"epoch": 0.23643044619422574,
|
| 15779 |
+
"grad_norm": 0.05122550204396248,
|
| 15780 |
+
"learning_rate": 0.0012,
|
| 15781 |
+
"loss": 2.26519513130188,
|
| 15782 |
+
"step": 4504
|
| 15783 |
+
},
|
| 15784 |
+
{
|
| 15785 |
+
"epoch": 0.23653543307086614,
|
| 15786 |
+
"grad_norm": 0.050881944596767426,
|
| 15787 |
+
"learning_rate": 0.0012,
|
| 15788 |
+
"loss": 2.2418110370635986,
|
| 15789 |
+
"step": 4506
|
| 15790 |
+
},
|
| 15791 |
+
{
|
| 15792 |
+
"epoch": 0.23664041994750656,
|
| 15793 |
+
"grad_norm": 0.055314648896455765,
|
| 15794 |
+
"learning_rate": 0.0012,
|
| 15795 |
+
"loss": 2.3609554767608643,
|
| 15796 |
+
"step": 4508
|
| 15797 |
+
},
|
| 15798 |
+
{
|
| 15799 |
+
"epoch": 0.236745406824147,
|
| 15800 |
+
"grad_norm": 0.045042671263217926,
|
| 15801 |
+
"learning_rate": 0.0012,
|
| 15802 |
+
"loss": 2.2657241821289062,
|
| 15803 |
+
"step": 4510
|
| 15804 |
+
},
|
| 15805 |
+
{
|
| 15806 |
+
"epoch": 0.2368503937007874,
|
| 15807 |
+
"grad_norm": 0.04744456708431244,
|
| 15808 |
+
"learning_rate": 0.0012,
|
| 15809 |
+
"loss": 2.243210792541504,
|
| 15810 |
+
"step": 4512
|
| 15811 |
+
},
|
| 15812 |
+
{
|
| 15813 |
+
"epoch": 0.23695538057742782,
|
| 15814 |
+
"grad_norm": 0.0509062260389328,
|
| 15815 |
+
"learning_rate": 0.0012,
|
| 15816 |
+
"loss": 2.2628448009490967,
|
| 15817 |
+
"step": 4514
|
| 15818 |
+
},
|
| 15819 |
+
{
|
| 15820 |
+
"epoch": 0.23706036745406825,
|
| 15821 |
+
"grad_norm": 0.043165456503629684,
|
| 15822 |
+
"learning_rate": 0.0012,
|
| 15823 |
+
"loss": 2.3144235610961914,
|
| 15824 |
+
"step": 4516
|
| 15825 |
+
},
|
| 15826 |
+
{
|
| 15827 |
+
"epoch": 0.23716535433070865,
|
| 15828 |
+
"grad_norm": 0.04750717431306839,
|
| 15829 |
+
"learning_rate": 0.0012,
|
| 15830 |
+
"loss": 2.307105779647827,
|
| 15831 |
+
"step": 4518
|
| 15832 |
+
},
|
| 15833 |
+
{
|
| 15834 |
+
"epoch": 0.23727034120734908,
|
| 15835 |
+
"grad_norm": 0.04492338001728058,
|
| 15836 |
+
"learning_rate": 0.0012,
|
| 15837 |
+
"loss": 2.310054063796997,
|
| 15838 |
+
"step": 4520
|
| 15839 |
+
},
|
| 15840 |
+
{
|
| 15841 |
+
"epoch": 0.2373753280839895,
|
| 15842 |
+
"grad_norm": 0.05172404274344444,
|
| 15843 |
+
"learning_rate": 0.0012,
|
| 15844 |
+
"loss": 2.2880706787109375,
|
| 15845 |
+
"step": 4522
|
| 15846 |
+
},
|
| 15847 |
+
{
|
| 15848 |
+
"epoch": 0.23748031496062993,
|
| 15849 |
+
"grad_norm": 0.044152822345495224,
|
| 15850 |
+
"learning_rate": 0.0012,
|
| 15851 |
+
"loss": 2.2584123611450195,
|
| 15852 |
+
"step": 4524
|
| 15853 |
+
},
|
| 15854 |
+
{
|
| 15855 |
+
"epoch": 0.23758530183727034,
|
| 15856 |
+
"grad_norm": 0.04109400510787964,
|
| 15857 |
+
"learning_rate": 0.0012,
|
| 15858 |
+
"loss": 2.2770683765411377,
|
| 15859 |
+
"step": 4526
|
| 15860 |
+
},
|
| 15861 |
+
{
|
| 15862 |
+
"epoch": 0.23769028871391076,
|
| 15863 |
+
"grad_norm": 0.04776942729949951,
|
| 15864 |
+
"learning_rate": 0.0012,
|
| 15865 |
+
"loss": 2.2667975425720215,
|
| 15866 |
+
"step": 4528
|
| 15867 |
+
},
|
| 15868 |
+
{
|
| 15869 |
+
"epoch": 0.2377952755905512,
|
| 15870 |
+
"grad_norm": 0.04051545262336731,
|
| 15871 |
+
"learning_rate": 0.0012,
|
| 15872 |
+
"loss": 2.28139066696167,
|
| 15873 |
+
"step": 4530
|
| 15874 |
+
},
|
| 15875 |
+
{
|
| 15876 |
+
"epoch": 0.2379002624671916,
|
| 15877 |
+
"grad_norm": 0.05094573646783829,
|
| 15878 |
+
"learning_rate": 0.0012,
|
| 15879 |
+
"loss": 2.243377923965454,
|
| 15880 |
+
"step": 4532
|
| 15881 |
+
},
|
| 15882 |
+
{
|
| 15883 |
+
"epoch": 0.23800524934383202,
|
| 15884 |
+
"grad_norm": 0.0504525750875473,
|
| 15885 |
+
"learning_rate": 0.0012,
|
| 15886 |
+
"loss": 2.358797073364258,
|
| 15887 |
+
"step": 4534
|
| 15888 |
+
},
|
| 15889 |
+
{
|
| 15890 |
+
"epoch": 0.23811023622047245,
|
| 15891 |
+
"grad_norm": 0.0609479621052742,
|
| 15892 |
+
"learning_rate": 0.0012,
|
| 15893 |
+
"loss": 2.3099706172943115,
|
| 15894 |
+
"step": 4536
|
| 15895 |
+
},
|
| 15896 |
+
{
|
| 15897 |
+
"epoch": 0.23821522309711285,
|
| 15898 |
+
"grad_norm": 0.054735217243433,
|
| 15899 |
+
"learning_rate": 0.0012,
|
| 15900 |
+
"loss": 2.3026208877563477,
|
| 15901 |
+
"step": 4538
|
| 15902 |
+
},
|
| 15903 |
+
{
|
| 15904 |
+
"epoch": 0.23832020997375328,
|
| 15905 |
+
"grad_norm": 0.05896087735891342,
|
| 15906 |
+
"learning_rate": 0.0012,
|
| 15907 |
+
"loss": 2.3070952892303467,
|
| 15908 |
+
"step": 4540
|
| 15909 |
+
},
|
| 15910 |
+
{
|
| 15911 |
+
"epoch": 0.2384251968503937,
|
| 15912 |
+
"grad_norm": 0.042677462100982666,
|
| 15913 |
+
"learning_rate": 0.0012,
|
| 15914 |
+
"loss": 2.261115550994873,
|
| 15915 |
+
"step": 4542
|
| 15916 |
+
},
|
| 15917 |
+
{
|
| 15918 |
+
"epoch": 0.23853018372703413,
|
| 15919 |
+
"grad_norm": 0.04975593835115433,
|
| 15920 |
+
"learning_rate": 0.0012,
|
| 15921 |
+
"loss": 2.2962639331817627,
|
| 15922 |
+
"step": 4544
|
| 15923 |
+
},
|
| 15924 |
+
{
|
| 15925 |
+
"epoch": 0.23863517060367453,
|
| 15926 |
+
"grad_norm": 0.056896526366472244,
|
| 15927 |
+
"learning_rate": 0.0012,
|
| 15928 |
+
"loss": 2.2488622665405273,
|
| 15929 |
+
"step": 4546
|
| 15930 |
+
},
|
| 15931 |
+
{
|
| 15932 |
+
"epoch": 0.23874015748031496,
|
| 15933 |
+
"grad_norm": 0.05259842798113823,
|
| 15934 |
+
"learning_rate": 0.0012,
|
| 15935 |
+
"loss": 2.3095009326934814,
|
| 15936 |
+
"step": 4548
|
| 15937 |
+
},
|
| 15938 |
+
{
|
| 15939 |
+
"epoch": 0.2388451443569554,
|
| 15940 |
+
"grad_norm": 0.040080588310956955,
|
| 15941 |
+
"learning_rate": 0.0012,
|
| 15942 |
+
"loss": 2.3321497440338135,
|
| 15943 |
+
"step": 4550
|
| 15944 |
+
},
|
| 15945 |
+
{
|
| 15946 |
+
"epoch": 0.2389501312335958,
|
| 15947 |
+
"grad_norm": 0.056621503084897995,
|
| 15948 |
+
"learning_rate": 0.0012,
|
| 15949 |
+
"loss": 2.3155789375305176,
|
| 15950 |
+
"step": 4552
|
| 15951 |
+
},
|
| 15952 |
+
{
|
| 15953 |
+
"epoch": 0.23905511811023622,
|
| 15954 |
+
"grad_norm": 0.05764010176062584,
|
| 15955 |
+
"learning_rate": 0.0012,
|
| 15956 |
+
"loss": 2.223724842071533,
|
| 15957 |
+
"step": 4554
|
| 15958 |
+
},
|
| 15959 |
+
{
|
| 15960 |
+
"epoch": 0.23916010498687665,
|
| 15961 |
+
"grad_norm": 0.06446745246648788,
|
| 15962 |
+
"learning_rate": 0.0012,
|
| 15963 |
+
"loss": 2.2965478897094727,
|
| 15964 |
+
"step": 4556
|
| 15965 |
+
},
|
| 15966 |
+
{
|
| 15967 |
+
"epoch": 0.23926509186351705,
|
| 15968 |
+
"grad_norm": 0.06030760705471039,
|
| 15969 |
+
"learning_rate": 0.0012,
|
| 15970 |
+
"loss": 2.2818381786346436,
|
| 15971 |
+
"step": 4558
|
| 15972 |
+
},
|
| 15973 |
+
{
|
| 15974 |
+
"epoch": 0.23937007874015748,
|
| 15975 |
+
"grad_norm": 0.04732225835323334,
|
| 15976 |
+
"learning_rate": 0.0012,
|
| 15977 |
+
"loss": 2.2826409339904785,
|
| 15978 |
+
"step": 4560
|
| 15979 |
+
},
|
| 15980 |
+
{
|
| 15981 |
+
"epoch": 0.2394750656167979,
|
| 15982 |
+
"grad_norm": 0.04975082352757454,
|
| 15983 |
+
"learning_rate": 0.0012,
|
| 15984 |
+
"loss": 2.267821788787842,
|
| 15985 |
+
"step": 4562
|
| 15986 |
+
},
|
| 15987 |
+
{
|
| 15988 |
+
"epoch": 0.23958005249343833,
|
| 15989 |
+
"grad_norm": 0.05664706975221634,
|
| 15990 |
+
"learning_rate": 0.0012,
|
| 15991 |
+
"loss": 2.3279306888580322,
|
| 15992 |
+
"step": 4564
|
| 15993 |
+
},
|
| 15994 |
+
{
|
| 15995 |
+
"epoch": 0.23968503937007873,
|
| 15996 |
+
"grad_norm": 0.06428372859954834,
|
| 15997 |
+
"learning_rate": 0.0012,
|
| 15998 |
+
"loss": 2.304891347885132,
|
| 15999 |
+
"step": 4566
|
| 16000 |
+
},
|
| 16001 |
+
{
|
| 16002 |
+
"epoch": 0.23979002624671916,
|
| 16003 |
+
"grad_norm": 0.04758835211396217,
|
| 16004 |
+
"learning_rate": 0.0012,
|
| 16005 |
+
"loss": 2.285029172897339,
|
| 16006 |
+
"step": 4568
|
| 16007 |
+
},
|
| 16008 |
+
{
|
| 16009 |
+
"epoch": 0.2398950131233596,
|
| 16010 |
+
"grad_norm": 0.042825087904930115,
|
| 16011 |
+
"learning_rate": 0.0012,
|
| 16012 |
+
"loss": 2.2356975078582764,
|
| 16013 |
+
"step": 4570
|
| 16014 |
+
},
|
| 16015 |
+
{
|
| 16016 |
+
"epoch": 0.24,
|
| 16017 |
+
"grad_norm": 0.047939449548721313,
|
| 16018 |
+
"learning_rate": 0.0012,
|
| 16019 |
+
"loss": 2.30220627784729,
|
| 16020 |
+
"step": 4572
|
| 16021 |
+
},
|
| 16022 |
+
{
|
| 16023 |
+
"epoch": 0.24010498687664042,
|
| 16024 |
+
"grad_norm": 0.045379653573036194,
|
| 16025 |
+
"learning_rate": 0.0012,
|
| 16026 |
+
"loss": 2.2967724800109863,
|
| 16027 |
+
"step": 4574
|
| 16028 |
+
},
|
| 16029 |
+
{
|
| 16030 |
+
"epoch": 0.24020997375328085,
|
| 16031 |
+
"grad_norm": 0.04387134686112404,
|
| 16032 |
+
"learning_rate": 0.0012,
|
| 16033 |
+
"loss": 2.3183960914611816,
|
| 16034 |
+
"step": 4576
|
| 16035 |
}
|
| 16036 |
],
|
| 16037 |
"logging_steps": 2,
|
|
|
|
| 16051 |
"attributes": {}
|
| 16052 |
}
|
| 16053 |
},
|
| 16054 |
+
"total_flos": 1.2469891962421322e+19,
|
| 16055 |
"train_batch_size": 32,
|
| 16056 |
"trial_name": null,
|
| 16057 |
"trial_params": null
|