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 5148, 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 sha256:47721f33850a537ad69daae204f5de76b7f24f7ff291d0b13463b34fb245b108
|
| 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 sha256:9c40f63851638d73040789ebb2860cb706cbcf7c2cb08b5c17a0ead013921023
|
| 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 sha256:66e5b4bdc02103a7c9eab9b472b3f7f8f7db060dcbe48e71120cd03e5cb6b2a2
|
| 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,
|
|
@@ -16032,6 +16032,2008 @@
|
|
| 16032 |
"learning_rate": 0.0012,
|
| 16033 |
"loss": 2.3183960914611816,
|
| 16034 |
"step": 4576
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16035 |
}
|
| 16036 |
],
|
| 16037 |
"logging_steps": 2,
|
|
@@ -16051,7 +18053,7 @@
|
|
| 16051 |
"attributes": {}
|
| 16052 |
}
|
| 16053 |
},
|
| 16054 |
-
"total_flos": 1.
|
| 16055 |
"train_batch_size": 32,
|
| 16056 |
"trial_name": null,
|
| 16057 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.27023622047244095,
|
| 6 |
"eval_steps": 2858,
|
| 7 |
+
"global_step": 5148,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16032 |
"learning_rate": 0.0012,
|
| 16033 |
"loss": 2.3183960914611816,
|
| 16034 |
"step": 4576
|
| 16035 |
+
},
|
| 16036 |
+
{
|
| 16037 |
+
"epoch": 0.24031496062992125,
|
| 16038 |
+
"grad_norm": 0.04025544598698616,
|
| 16039 |
+
"learning_rate": 0.0012,
|
| 16040 |
+
"loss": 2.3546688556671143,
|
| 16041 |
+
"step": 4578
|
| 16042 |
+
},
|
| 16043 |
+
{
|
| 16044 |
+
"epoch": 0.24041994750656168,
|
| 16045 |
+
"grad_norm": 0.04522841051220894,
|
| 16046 |
+
"learning_rate": 0.0012,
|
| 16047 |
+
"loss": 2.3766186237335205,
|
| 16048 |
+
"step": 4580
|
| 16049 |
+
},
|
| 16050 |
+
{
|
| 16051 |
+
"epoch": 0.2405249343832021,
|
| 16052 |
+
"grad_norm": 0.04767121747136116,
|
| 16053 |
+
"learning_rate": 0.0012,
|
| 16054 |
+
"loss": 2.324263572692871,
|
| 16055 |
+
"step": 4582
|
| 16056 |
+
},
|
| 16057 |
+
{
|
| 16058 |
+
"epoch": 0.24062992125984253,
|
| 16059 |
+
"grad_norm": 0.04112609848380089,
|
| 16060 |
+
"learning_rate": 0.0012,
|
| 16061 |
+
"loss": 2.235241174697876,
|
| 16062 |
+
"step": 4584
|
| 16063 |
+
},
|
| 16064 |
+
{
|
| 16065 |
+
"epoch": 0.24073490813648293,
|
| 16066 |
+
"grad_norm": 0.06176736205816269,
|
| 16067 |
+
"learning_rate": 0.0012,
|
| 16068 |
+
"loss": 2.2415523529052734,
|
| 16069 |
+
"step": 4586
|
| 16070 |
+
},
|
| 16071 |
+
{
|
| 16072 |
+
"epoch": 0.24083989501312336,
|
| 16073 |
+
"grad_norm": 0.0672881230711937,
|
| 16074 |
+
"learning_rate": 0.0012,
|
| 16075 |
+
"loss": 2.2226812839508057,
|
| 16076 |
+
"step": 4588
|
| 16077 |
+
},
|
| 16078 |
+
{
|
| 16079 |
+
"epoch": 0.2409448818897638,
|
| 16080 |
+
"grad_norm": 0.045163340866565704,
|
| 16081 |
+
"learning_rate": 0.0012,
|
| 16082 |
+
"loss": 2.3225061893463135,
|
| 16083 |
+
"step": 4590
|
| 16084 |
+
},
|
| 16085 |
+
{
|
| 16086 |
+
"epoch": 0.2410498687664042,
|
| 16087 |
+
"grad_norm": 0.046377502381801605,
|
| 16088 |
+
"learning_rate": 0.0012,
|
| 16089 |
+
"loss": 2.216074228286743,
|
| 16090 |
+
"step": 4592
|
| 16091 |
+
},
|
| 16092 |
+
{
|
| 16093 |
+
"epoch": 0.24115485564304462,
|
| 16094 |
+
"grad_norm": 0.05541412904858589,
|
| 16095 |
+
"learning_rate": 0.0012,
|
| 16096 |
+
"loss": 2.3550772666931152,
|
| 16097 |
+
"step": 4594
|
| 16098 |
+
},
|
| 16099 |
+
{
|
| 16100 |
+
"epoch": 0.24125984251968505,
|
| 16101 |
+
"grad_norm": 0.06450573354959488,
|
| 16102 |
+
"learning_rate": 0.0012,
|
| 16103 |
+
"loss": 2.2907474040985107,
|
| 16104 |
+
"step": 4596
|
| 16105 |
+
},
|
| 16106 |
+
{
|
| 16107 |
+
"epoch": 0.24136482939632545,
|
| 16108 |
+
"grad_norm": 0.06265146285295486,
|
| 16109 |
+
"learning_rate": 0.0012,
|
| 16110 |
+
"loss": 2.3114988803863525,
|
| 16111 |
+
"step": 4598
|
| 16112 |
+
},
|
| 16113 |
+
{
|
| 16114 |
+
"epoch": 0.24146981627296588,
|
| 16115 |
+
"grad_norm": 0.0519854910671711,
|
| 16116 |
+
"learning_rate": 0.0012,
|
| 16117 |
+
"loss": 2.293036460876465,
|
| 16118 |
+
"step": 4600
|
| 16119 |
+
},
|
| 16120 |
+
{
|
| 16121 |
+
"epoch": 0.2415748031496063,
|
| 16122 |
+
"grad_norm": 0.04675883427262306,
|
| 16123 |
+
"learning_rate": 0.0012,
|
| 16124 |
+
"loss": 2.221972942352295,
|
| 16125 |
+
"step": 4602
|
| 16126 |
+
},
|
| 16127 |
+
{
|
| 16128 |
+
"epoch": 0.24167979002624673,
|
| 16129 |
+
"grad_norm": 0.044240642338991165,
|
| 16130 |
+
"learning_rate": 0.0012,
|
| 16131 |
+
"loss": 2.310084104537964,
|
| 16132 |
+
"step": 4604
|
| 16133 |
+
},
|
| 16134 |
+
{
|
| 16135 |
+
"epoch": 0.24178477690288713,
|
| 16136 |
+
"grad_norm": 0.04151823744177818,
|
| 16137 |
+
"learning_rate": 0.0012,
|
| 16138 |
+
"loss": 2.330192804336548,
|
| 16139 |
+
"step": 4606
|
| 16140 |
+
},
|
| 16141 |
+
{
|
| 16142 |
+
"epoch": 0.24188976377952756,
|
| 16143 |
+
"grad_norm": 0.04698100686073303,
|
| 16144 |
+
"learning_rate": 0.0012,
|
| 16145 |
+
"loss": 2.2125535011291504,
|
| 16146 |
+
"step": 4608
|
| 16147 |
+
},
|
| 16148 |
+
{
|
| 16149 |
+
"epoch": 0.241994750656168,
|
| 16150 |
+
"grad_norm": 0.04495207220315933,
|
| 16151 |
+
"learning_rate": 0.0012,
|
| 16152 |
+
"loss": 2.3275091648101807,
|
| 16153 |
+
"step": 4610
|
| 16154 |
+
},
|
| 16155 |
+
{
|
| 16156 |
+
"epoch": 0.2420997375328084,
|
| 16157 |
+
"grad_norm": 0.04824955388903618,
|
| 16158 |
+
"learning_rate": 0.0012,
|
| 16159 |
+
"loss": 2.2159383296966553,
|
| 16160 |
+
"step": 4612
|
| 16161 |
+
},
|
| 16162 |
+
{
|
| 16163 |
+
"epoch": 0.24220472440944882,
|
| 16164 |
+
"grad_norm": 0.05769748613238335,
|
| 16165 |
+
"learning_rate": 0.0012,
|
| 16166 |
+
"loss": 2.2644124031066895,
|
| 16167 |
+
"step": 4614
|
| 16168 |
+
},
|
| 16169 |
+
{
|
| 16170 |
+
"epoch": 0.24230971128608925,
|
| 16171 |
+
"grad_norm": 0.041623301804065704,
|
| 16172 |
+
"learning_rate": 0.0012,
|
| 16173 |
+
"loss": 2.2963812351226807,
|
| 16174 |
+
"step": 4616
|
| 16175 |
+
},
|
| 16176 |
+
{
|
| 16177 |
+
"epoch": 0.24241469816272965,
|
| 16178 |
+
"grad_norm": 0.05436648055911064,
|
| 16179 |
+
"learning_rate": 0.0012,
|
| 16180 |
+
"loss": 2.2610256671905518,
|
| 16181 |
+
"step": 4618
|
| 16182 |
+
},
|
| 16183 |
+
{
|
| 16184 |
+
"epoch": 0.24251968503937008,
|
| 16185 |
+
"grad_norm": 0.0574633851647377,
|
| 16186 |
+
"learning_rate": 0.0012,
|
| 16187 |
+
"loss": 2.203213691711426,
|
| 16188 |
+
"step": 4620
|
| 16189 |
+
},
|
| 16190 |
+
{
|
| 16191 |
+
"epoch": 0.2426246719160105,
|
| 16192 |
+
"grad_norm": 0.042980313301086426,
|
| 16193 |
+
"learning_rate": 0.0012,
|
| 16194 |
+
"loss": 2.3276772499084473,
|
| 16195 |
+
"step": 4622
|
| 16196 |
+
},
|
| 16197 |
+
{
|
| 16198 |
+
"epoch": 0.24272965879265093,
|
| 16199 |
+
"grad_norm": 0.04954439401626587,
|
| 16200 |
+
"learning_rate": 0.0012,
|
| 16201 |
+
"loss": 2.2846028804779053,
|
| 16202 |
+
"step": 4624
|
| 16203 |
+
},
|
| 16204 |
+
{
|
| 16205 |
+
"epoch": 0.24283464566929133,
|
| 16206 |
+
"grad_norm": 0.05313866585493088,
|
| 16207 |
+
"learning_rate": 0.0012,
|
| 16208 |
+
"loss": 2.2593700885772705,
|
| 16209 |
+
"step": 4626
|
| 16210 |
+
},
|
| 16211 |
+
{
|
| 16212 |
+
"epoch": 0.24293963254593176,
|
| 16213 |
+
"grad_norm": 0.05134128779172897,
|
| 16214 |
+
"learning_rate": 0.0012,
|
| 16215 |
+
"loss": 2.2920877933502197,
|
| 16216 |
+
"step": 4628
|
| 16217 |
+
},
|
| 16218 |
+
{
|
| 16219 |
+
"epoch": 0.2430446194225722,
|
| 16220 |
+
"grad_norm": 0.048293065279722214,
|
| 16221 |
+
"learning_rate": 0.0012,
|
| 16222 |
+
"loss": 2.246211290359497,
|
| 16223 |
+
"step": 4630
|
| 16224 |
+
},
|
| 16225 |
+
{
|
| 16226 |
+
"epoch": 0.2431496062992126,
|
| 16227 |
+
"grad_norm": 0.0430818572640419,
|
| 16228 |
+
"learning_rate": 0.0012,
|
| 16229 |
+
"loss": 2.3531477451324463,
|
| 16230 |
+
"step": 4632
|
| 16231 |
+
},
|
| 16232 |
+
{
|
| 16233 |
+
"epoch": 0.24325459317585302,
|
| 16234 |
+
"grad_norm": 0.0447818823158741,
|
| 16235 |
+
"learning_rate": 0.0012,
|
| 16236 |
+
"loss": 2.244706630706787,
|
| 16237 |
+
"step": 4634
|
| 16238 |
+
},
|
| 16239 |
+
{
|
| 16240 |
+
"epoch": 0.24335958005249345,
|
| 16241 |
+
"grad_norm": 0.04243616759777069,
|
| 16242 |
+
"learning_rate": 0.0012,
|
| 16243 |
+
"loss": 2.351853609085083,
|
| 16244 |
+
"step": 4636
|
| 16245 |
+
},
|
| 16246 |
+
{
|
| 16247 |
+
"epoch": 0.24346456692913385,
|
| 16248 |
+
"grad_norm": 0.03830438107252121,
|
| 16249 |
+
"learning_rate": 0.0012,
|
| 16250 |
+
"loss": 2.2965593338012695,
|
| 16251 |
+
"step": 4638
|
| 16252 |
+
},
|
| 16253 |
+
{
|
| 16254 |
+
"epoch": 0.24356955380577427,
|
| 16255 |
+
"grad_norm": 0.03952629864215851,
|
| 16256 |
+
"learning_rate": 0.0012,
|
| 16257 |
+
"loss": 2.2501986026763916,
|
| 16258 |
+
"step": 4640
|
| 16259 |
+
},
|
| 16260 |
+
{
|
| 16261 |
+
"epoch": 0.2436745406824147,
|
| 16262 |
+
"grad_norm": 0.04199547693133354,
|
| 16263 |
+
"learning_rate": 0.0012,
|
| 16264 |
+
"loss": 2.3093745708465576,
|
| 16265 |
+
"step": 4642
|
| 16266 |
+
},
|
| 16267 |
+
{
|
| 16268 |
+
"epoch": 0.24377952755905513,
|
| 16269 |
+
"grad_norm": 0.049509692937135696,
|
| 16270 |
+
"learning_rate": 0.0012,
|
| 16271 |
+
"loss": 2.2589216232299805,
|
| 16272 |
+
"step": 4644
|
| 16273 |
+
},
|
| 16274 |
+
{
|
| 16275 |
+
"epoch": 0.24388451443569553,
|
| 16276 |
+
"grad_norm": 0.04493927210569382,
|
| 16277 |
+
"learning_rate": 0.0012,
|
| 16278 |
+
"loss": 2.21498441696167,
|
| 16279 |
+
"step": 4646
|
| 16280 |
+
},
|
| 16281 |
+
{
|
| 16282 |
+
"epoch": 0.24398950131233596,
|
| 16283 |
+
"grad_norm": 0.0456310473382473,
|
| 16284 |
+
"learning_rate": 0.0012,
|
| 16285 |
+
"loss": 2.3317220211029053,
|
| 16286 |
+
"step": 4648
|
| 16287 |
+
},
|
| 16288 |
+
{
|
| 16289 |
+
"epoch": 0.2440944881889764,
|
| 16290 |
+
"grad_norm": 0.056037481874227524,
|
| 16291 |
+
"learning_rate": 0.0012,
|
| 16292 |
+
"loss": 2.254631996154785,
|
| 16293 |
+
"step": 4650
|
| 16294 |
+
},
|
| 16295 |
+
{
|
| 16296 |
+
"epoch": 0.2441994750656168,
|
| 16297 |
+
"grad_norm": 0.05382557958364487,
|
| 16298 |
+
"learning_rate": 0.0012,
|
| 16299 |
+
"loss": 2.2894015312194824,
|
| 16300 |
+
"step": 4652
|
| 16301 |
+
},
|
| 16302 |
+
{
|
| 16303 |
+
"epoch": 0.24430446194225722,
|
| 16304 |
+
"grad_norm": 0.05333792418241501,
|
| 16305 |
+
"learning_rate": 0.0012,
|
| 16306 |
+
"loss": 2.318774461746216,
|
| 16307 |
+
"step": 4654
|
| 16308 |
+
},
|
| 16309 |
+
{
|
| 16310 |
+
"epoch": 0.24440944881889765,
|
| 16311 |
+
"grad_norm": 0.045724257826805115,
|
| 16312 |
+
"learning_rate": 0.0012,
|
| 16313 |
+
"loss": 2.260037899017334,
|
| 16314 |
+
"step": 4656
|
| 16315 |
+
},
|
| 16316 |
+
{
|
| 16317 |
+
"epoch": 0.24451443569553805,
|
| 16318 |
+
"grad_norm": 0.05595235154032707,
|
| 16319 |
+
"learning_rate": 0.0012,
|
| 16320 |
+
"loss": 2.286158800125122,
|
| 16321 |
+
"step": 4658
|
| 16322 |
+
},
|
| 16323 |
+
{
|
| 16324 |
+
"epoch": 0.24461942257217847,
|
| 16325 |
+
"grad_norm": 0.05507221072912216,
|
| 16326 |
+
"learning_rate": 0.0012,
|
| 16327 |
+
"loss": 2.2971017360687256,
|
| 16328 |
+
"step": 4660
|
| 16329 |
+
},
|
| 16330 |
+
{
|
| 16331 |
+
"epoch": 0.2447244094488189,
|
| 16332 |
+
"grad_norm": 0.05406492203474045,
|
| 16333 |
+
"learning_rate": 0.0012,
|
| 16334 |
+
"loss": 2.2564895153045654,
|
| 16335 |
+
"step": 4662
|
| 16336 |
+
},
|
| 16337 |
+
{
|
| 16338 |
+
"epoch": 0.24482939632545933,
|
| 16339 |
+
"grad_norm": 0.047884657979011536,
|
| 16340 |
+
"learning_rate": 0.0012,
|
| 16341 |
+
"loss": 2.2479703426361084,
|
| 16342 |
+
"step": 4664
|
| 16343 |
+
},
|
| 16344 |
+
{
|
| 16345 |
+
"epoch": 0.24493438320209973,
|
| 16346 |
+
"grad_norm": 0.05354277417063713,
|
| 16347 |
+
"learning_rate": 0.0012,
|
| 16348 |
+
"loss": 2.2433807849884033,
|
| 16349 |
+
"step": 4666
|
| 16350 |
+
},
|
| 16351 |
+
{
|
| 16352 |
+
"epoch": 0.24503937007874016,
|
| 16353 |
+
"grad_norm": 0.04241223260760307,
|
| 16354 |
+
"learning_rate": 0.0012,
|
| 16355 |
+
"loss": 2.277157783508301,
|
| 16356 |
+
"step": 4668
|
| 16357 |
+
},
|
| 16358 |
+
{
|
| 16359 |
+
"epoch": 0.2451443569553806,
|
| 16360 |
+
"grad_norm": 0.057455018162727356,
|
| 16361 |
+
"learning_rate": 0.0012,
|
| 16362 |
+
"loss": 2.2421364784240723,
|
| 16363 |
+
"step": 4670
|
| 16364 |
+
},
|
| 16365 |
+
{
|
| 16366 |
+
"epoch": 0.245249343832021,
|
| 16367 |
+
"grad_norm": 0.07717055082321167,
|
| 16368 |
+
"learning_rate": 0.0012,
|
| 16369 |
+
"loss": 2.242356538772583,
|
| 16370 |
+
"step": 4672
|
| 16371 |
+
},
|
| 16372 |
+
{
|
| 16373 |
+
"epoch": 0.24535433070866142,
|
| 16374 |
+
"grad_norm": 0.06713193655014038,
|
| 16375 |
+
"learning_rate": 0.0012,
|
| 16376 |
+
"loss": 2.2551069259643555,
|
| 16377 |
+
"step": 4674
|
| 16378 |
+
},
|
| 16379 |
+
{
|
| 16380 |
+
"epoch": 0.24545931758530184,
|
| 16381 |
+
"grad_norm": 0.04472770541906357,
|
| 16382 |
+
"learning_rate": 0.0012,
|
| 16383 |
+
"loss": 2.3062899112701416,
|
| 16384 |
+
"step": 4676
|
| 16385 |
+
},
|
| 16386 |
+
{
|
| 16387 |
+
"epoch": 0.24556430446194225,
|
| 16388 |
+
"grad_norm": 0.05163189023733139,
|
| 16389 |
+
"learning_rate": 0.0012,
|
| 16390 |
+
"loss": 2.309715747833252,
|
| 16391 |
+
"step": 4678
|
| 16392 |
+
},
|
| 16393 |
+
{
|
| 16394 |
+
"epoch": 0.24566929133858267,
|
| 16395 |
+
"grad_norm": 0.06982250511646271,
|
| 16396 |
+
"learning_rate": 0.0012,
|
| 16397 |
+
"loss": 2.3067264556884766,
|
| 16398 |
+
"step": 4680
|
| 16399 |
+
},
|
| 16400 |
+
{
|
| 16401 |
+
"epoch": 0.2457742782152231,
|
| 16402 |
+
"grad_norm": 0.06054172292351723,
|
| 16403 |
+
"learning_rate": 0.0012,
|
| 16404 |
+
"loss": 2.295724868774414,
|
| 16405 |
+
"step": 4682
|
| 16406 |
+
},
|
| 16407 |
+
{
|
| 16408 |
+
"epoch": 0.24587926509186353,
|
| 16409 |
+
"grad_norm": 0.05155261233448982,
|
| 16410 |
+
"learning_rate": 0.0012,
|
| 16411 |
+
"loss": 2.2650253772735596,
|
| 16412 |
+
"step": 4684
|
| 16413 |
+
},
|
| 16414 |
+
{
|
| 16415 |
+
"epoch": 0.24598425196850393,
|
| 16416 |
+
"grad_norm": 0.059923749417066574,
|
| 16417 |
+
"learning_rate": 0.0012,
|
| 16418 |
+
"loss": 2.186849594116211,
|
| 16419 |
+
"step": 4686
|
| 16420 |
+
},
|
| 16421 |
+
{
|
| 16422 |
+
"epoch": 0.24608923884514436,
|
| 16423 |
+
"grad_norm": 0.041195280849933624,
|
| 16424 |
+
"learning_rate": 0.0012,
|
| 16425 |
+
"loss": 2.2770073413848877,
|
| 16426 |
+
"step": 4688
|
| 16427 |
+
},
|
| 16428 |
+
{
|
| 16429 |
+
"epoch": 0.2461942257217848,
|
| 16430 |
+
"grad_norm": 0.040079958736896515,
|
| 16431 |
+
"learning_rate": 0.0012,
|
| 16432 |
+
"loss": 2.2854340076446533,
|
| 16433 |
+
"step": 4690
|
| 16434 |
+
},
|
| 16435 |
+
{
|
| 16436 |
+
"epoch": 0.2462992125984252,
|
| 16437 |
+
"grad_norm": 0.041357409209012985,
|
| 16438 |
+
"learning_rate": 0.0012,
|
| 16439 |
+
"loss": 2.235025405883789,
|
| 16440 |
+
"step": 4692
|
| 16441 |
+
},
|
| 16442 |
+
{
|
| 16443 |
+
"epoch": 0.24640419947506562,
|
| 16444 |
+
"grad_norm": 0.05765795335173607,
|
| 16445 |
+
"learning_rate": 0.0012,
|
| 16446 |
+
"loss": 2.2647898197174072,
|
| 16447 |
+
"step": 4694
|
| 16448 |
+
},
|
| 16449 |
+
{
|
| 16450 |
+
"epoch": 0.24650918635170604,
|
| 16451 |
+
"grad_norm": 0.06258568912744522,
|
| 16452 |
+
"learning_rate": 0.0012,
|
| 16453 |
+
"loss": 2.2381017208099365,
|
| 16454 |
+
"step": 4696
|
| 16455 |
+
},
|
| 16456 |
+
{
|
| 16457 |
+
"epoch": 0.24661417322834644,
|
| 16458 |
+
"grad_norm": 0.07105593383312225,
|
| 16459 |
+
"learning_rate": 0.0012,
|
| 16460 |
+
"loss": 2.2809910774230957,
|
| 16461 |
+
"step": 4698
|
| 16462 |
+
},
|
| 16463 |
+
{
|
| 16464 |
+
"epoch": 0.24671916010498687,
|
| 16465 |
+
"grad_norm": 0.05172877386212349,
|
| 16466 |
+
"learning_rate": 0.0012,
|
| 16467 |
+
"loss": 2.299325704574585,
|
| 16468 |
+
"step": 4700
|
| 16469 |
+
},
|
| 16470 |
+
{
|
| 16471 |
+
"epoch": 0.2468241469816273,
|
| 16472 |
+
"grad_norm": 0.040314167737960815,
|
| 16473 |
+
"learning_rate": 0.0012,
|
| 16474 |
+
"loss": 2.2650139331817627,
|
| 16475 |
+
"step": 4702
|
| 16476 |
+
},
|
| 16477 |
+
{
|
| 16478 |
+
"epoch": 0.24692913385826773,
|
| 16479 |
+
"grad_norm": 0.04459555074572563,
|
| 16480 |
+
"learning_rate": 0.0012,
|
| 16481 |
+
"loss": 2.2387709617614746,
|
| 16482 |
+
"step": 4704
|
| 16483 |
+
},
|
| 16484 |
+
{
|
| 16485 |
+
"epoch": 0.24703412073490813,
|
| 16486 |
+
"grad_norm": 0.05051412433385849,
|
| 16487 |
+
"learning_rate": 0.0012,
|
| 16488 |
+
"loss": 2.2018113136291504,
|
| 16489 |
+
"step": 4706
|
| 16490 |
+
},
|
| 16491 |
+
{
|
| 16492 |
+
"epoch": 0.24713910761154856,
|
| 16493 |
+
"grad_norm": 0.05147827789187431,
|
| 16494 |
+
"learning_rate": 0.0012,
|
| 16495 |
+
"loss": 2.248319625854492,
|
| 16496 |
+
"step": 4708
|
| 16497 |
+
},
|
| 16498 |
+
{
|
| 16499 |
+
"epoch": 0.247244094488189,
|
| 16500 |
+
"grad_norm": 0.05281038582324982,
|
| 16501 |
+
"learning_rate": 0.0012,
|
| 16502 |
+
"loss": 2.239764451980591,
|
| 16503 |
+
"step": 4710
|
| 16504 |
+
},
|
| 16505 |
+
{
|
| 16506 |
+
"epoch": 0.2473490813648294,
|
| 16507 |
+
"grad_norm": 0.04525014013051987,
|
| 16508 |
+
"learning_rate": 0.0012,
|
| 16509 |
+
"loss": 2.2782928943634033,
|
| 16510 |
+
"step": 4712
|
| 16511 |
+
},
|
| 16512 |
+
{
|
| 16513 |
+
"epoch": 0.24745406824146982,
|
| 16514 |
+
"grad_norm": 0.050340764224529266,
|
| 16515 |
+
"learning_rate": 0.0012,
|
| 16516 |
+
"loss": 2.2510249614715576,
|
| 16517 |
+
"step": 4714
|
| 16518 |
+
},
|
| 16519 |
+
{
|
| 16520 |
+
"epoch": 0.24755905511811024,
|
| 16521 |
+
"grad_norm": 0.045012541115283966,
|
| 16522 |
+
"learning_rate": 0.0012,
|
| 16523 |
+
"loss": 2.283738851547241,
|
| 16524 |
+
"step": 4716
|
| 16525 |
+
},
|
| 16526 |
+
{
|
| 16527 |
+
"epoch": 0.24766404199475064,
|
| 16528 |
+
"grad_norm": 0.04262952134013176,
|
| 16529 |
+
"learning_rate": 0.0012,
|
| 16530 |
+
"loss": 2.2767388820648193,
|
| 16531 |
+
"step": 4718
|
| 16532 |
+
},
|
| 16533 |
+
{
|
| 16534 |
+
"epoch": 0.24776902887139107,
|
| 16535 |
+
"grad_norm": 0.04275166988372803,
|
| 16536 |
+
"learning_rate": 0.0012,
|
| 16537 |
+
"loss": 2.277662754058838,
|
| 16538 |
+
"step": 4720
|
| 16539 |
+
},
|
| 16540 |
+
{
|
| 16541 |
+
"epoch": 0.2478740157480315,
|
| 16542 |
+
"grad_norm": 0.04262080416083336,
|
| 16543 |
+
"learning_rate": 0.0012,
|
| 16544 |
+
"loss": 2.372594118118286,
|
| 16545 |
+
"step": 4722
|
| 16546 |
+
},
|
| 16547 |
+
{
|
| 16548 |
+
"epoch": 0.24797900262467193,
|
| 16549 |
+
"grad_norm": 0.04736216366291046,
|
| 16550 |
+
"learning_rate": 0.0012,
|
| 16551 |
+
"loss": 2.2902767658233643,
|
| 16552 |
+
"step": 4724
|
| 16553 |
+
},
|
| 16554 |
+
{
|
| 16555 |
+
"epoch": 0.24808398950131233,
|
| 16556 |
+
"grad_norm": 0.046013232320547104,
|
| 16557 |
+
"learning_rate": 0.0012,
|
| 16558 |
+
"loss": 2.2432475090026855,
|
| 16559 |
+
"step": 4726
|
| 16560 |
+
},
|
| 16561 |
+
{
|
| 16562 |
+
"epoch": 0.24818897637795276,
|
| 16563 |
+
"grad_norm": 0.05455389618873596,
|
| 16564 |
+
"learning_rate": 0.0012,
|
| 16565 |
+
"loss": 2.244962453842163,
|
| 16566 |
+
"step": 4728
|
| 16567 |
+
},
|
| 16568 |
+
{
|
| 16569 |
+
"epoch": 0.2482939632545932,
|
| 16570 |
+
"grad_norm": 0.0553353913128376,
|
| 16571 |
+
"learning_rate": 0.0012,
|
| 16572 |
+
"loss": 2.2790112495422363,
|
| 16573 |
+
"step": 4730
|
| 16574 |
+
},
|
| 16575 |
+
{
|
| 16576 |
+
"epoch": 0.2483989501312336,
|
| 16577 |
+
"grad_norm": 0.04525799676775932,
|
| 16578 |
+
"learning_rate": 0.0012,
|
| 16579 |
+
"loss": 2.3458375930786133,
|
| 16580 |
+
"step": 4732
|
| 16581 |
+
},
|
| 16582 |
+
{
|
| 16583 |
+
"epoch": 0.24850393700787402,
|
| 16584 |
+
"grad_norm": 0.049275174736976624,
|
| 16585 |
+
"learning_rate": 0.0012,
|
| 16586 |
+
"loss": 2.3431742191314697,
|
| 16587 |
+
"step": 4734
|
| 16588 |
+
},
|
| 16589 |
+
{
|
| 16590 |
+
"epoch": 0.24860892388451444,
|
| 16591 |
+
"grad_norm": 0.042889874428510666,
|
| 16592 |
+
"learning_rate": 0.0012,
|
| 16593 |
+
"loss": 2.22617244720459,
|
| 16594 |
+
"step": 4736
|
| 16595 |
+
},
|
| 16596 |
+
{
|
| 16597 |
+
"epoch": 0.24871391076115484,
|
| 16598 |
+
"grad_norm": 0.047272972762584686,
|
| 16599 |
+
"learning_rate": 0.0012,
|
| 16600 |
+
"loss": 2.2757434844970703,
|
| 16601 |
+
"step": 4738
|
| 16602 |
+
},
|
| 16603 |
+
{
|
| 16604 |
+
"epoch": 0.24881889763779527,
|
| 16605 |
+
"grad_norm": 0.056186869740486145,
|
| 16606 |
+
"learning_rate": 0.0012,
|
| 16607 |
+
"loss": 2.2856342792510986,
|
| 16608 |
+
"step": 4740
|
| 16609 |
+
},
|
| 16610 |
+
{
|
| 16611 |
+
"epoch": 0.2489238845144357,
|
| 16612 |
+
"grad_norm": 0.05777687206864357,
|
| 16613 |
+
"learning_rate": 0.0012,
|
| 16614 |
+
"loss": 2.2205350399017334,
|
| 16615 |
+
"step": 4742
|
| 16616 |
+
},
|
| 16617 |
+
{
|
| 16618 |
+
"epoch": 0.24902887139107613,
|
| 16619 |
+
"grad_norm": 0.048081833869218826,
|
| 16620 |
+
"learning_rate": 0.0012,
|
| 16621 |
+
"loss": 2.297046184539795,
|
| 16622 |
+
"step": 4744
|
| 16623 |
+
},
|
| 16624 |
+
{
|
| 16625 |
+
"epoch": 0.24913385826771653,
|
| 16626 |
+
"grad_norm": 0.05949201062321663,
|
| 16627 |
+
"learning_rate": 0.0012,
|
| 16628 |
+
"loss": 2.2300994396209717,
|
| 16629 |
+
"step": 4746
|
| 16630 |
+
},
|
| 16631 |
+
{
|
| 16632 |
+
"epoch": 0.24923884514435696,
|
| 16633 |
+
"grad_norm": 0.04665645956993103,
|
| 16634 |
+
"learning_rate": 0.0012,
|
| 16635 |
+
"loss": 2.3574230670928955,
|
| 16636 |
+
"step": 4748
|
| 16637 |
+
},
|
| 16638 |
+
{
|
| 16639 |
+
"epoch": 0.24934383202099739,
|
| 16640 |
+
"grad_norm": 0.04890789836645126,
|
| 16641 |
+
"learning_rate": 0.0012,
|
| 16642 |
+
"loss": 2.308995485305786,
|
| 16643 |
+
"step": 4750
|
| 16644 |
+
},
|
| 16645 |
+
{
|
| 16646 |
+
"epoch": 0.2494488188976378,
|
| 16647 |
+
"grad_norm": 0.04818953946232796,
|
| 16648 |
+
"learning_rate": 0.0012,
|
| 16649 |
+
"loss": 2.2597556114196777,
|
| 16650 |
+
"step": 4752
|
| 16651 |
+
},
|
| 16652 |
+
{
|
| 16653 |
+
"epoch": 0.24955380577427821,
|
| 16654 |
+
"grad_norm": 0.045685797929763794,
|
| 16655 |
+
"learning_rate": 0.0012,
|
| 16656 |
+
"loss": 2.2269060611724854,
|
| 16657 |
+
"step": 4754
|
| 16658 |
+
},
|
| 16659 |
+
{
|
| 16660 |
+
"epoch": 0.24965879265091864,
|
| 16661 |
+
"grad_norm": 0.05053800344467163,
|
| 16662 |
+
"learning_rate": 0.0012,
|
| 16663 |
+
"loss": 2.275675058364868,
|
| 16664 |
+
"step": 4756
|
| 16665 |
+
},
|
| 16666 |
+
{
|
| 16667 |
+
"epoch": 0.24976377952755904,
|
| 16668 |
+
"grad_norm": 0.05772832781076431,
|
| 16669 |
+
"learning_rate": 0.0012,
|
| 16670 |
+
"loss": 2.3128585815429688,
|
| 16671 |
+
"step": 4758
|
| 16672 |
+
},
|
| 16673 |
+
{
|
| 16674 |
+
"epoch": 0.24986876640419947,
|
| 16675 |
+
"grad_norm": 0.05254777893424034,
|
| 16676 |
+
"learning_rate": 0.0012,
|
| 16677 |
+
"loss": 2.247760534286499,
|
| 16678 |
+
"step": 4760
|
| 16679 |
+
},
|
| 16680 |
+
{
|
| 16681 |
+
"epoch": 0.2499737532808399,
|
| 16682 |
+
"grad_norm": 0.04644748941063881,
|
| 16683 |
+
"learning_rate": 0.0012,
|
| 16684 |
+
"loss": 2.345424175262451,
|
| 16685 |
+
"step": 4762
|
| 16686 |
+
},
|
| 16687 |
+
{
|
| 16688 |
+
"epoch": 0.25007874015748033,
|
| 16689 |
+
"grad_norm": 0.04920418560504913,
|
| 16690 |
+
"learning_rate": 0.0012,
|
| 16691 |
+
"loss": 2.2785484790802,
|
| 16692 |
+
"step": 4764
|
| 16693 |
+
},
|
| 16694 |
+
{
|
| 16695 |
+
"epoch": 0.25018372703412073,
|
| 16696 |
+
"grad_norm": 0.04373258352279663,
|
| 16697 |
+
"learning_rate": 0.0012,
|
| 16698 |
+
"loss": 2.1854000091552734,
|
| 16699 |
+
"step": 4766
|
| 16700 |
+
},
|
| 16701 |
+
{
|
| 16702 |
+
"epoch": 0.25028871391076113,
|
| 16703 |
+
"grad_norm": 0.04795217514038086,
|
| 16704 |
+
"learning_rate": 0.0012,
|
| 16705 |
+
"loss": 2.241166591644287,
|
| 16706 |
+
"step": 4768
|
| 16707 |
+
},
|
| 16708 |
+
{
|
| 16709 |
+
"epoch": 0.2503937007874016,
|
| 16710 |
+
"grad_norm": 0.053111664950847626,
|
| 16711 |
+
"learning_rate": 0.0012,
|
| 16712 |
+
"loss": 2.315652370452881,
|
| 16713 |
+
"step": 4770
|
| 16714 |
+
},
|
| 16715 |
+
{
|
| 16716 |
+
"epoch": 0.250498687664042,
|
| 16717 |
+
"grad_norm": 0.04199931025505066,
|
| 16718 |
+
"learning_rate": 0.0012,
|
| 16719 |
+
"loss": 2.2592966556549072,
|
| 16720 |
+
"step": 4772
|
| 16721 |
+
},
|
| 16722 |
+
{
|
| 16723 |
+
"epoch": 0.25060367454068244,
|
| 16724 |
+
"grad_norm": 0.04415667802095413,
|
| 16725 |
+
"learning_rate": 0.0012,
|
| 16726 |
+
"loss": 2.3195626735687256,
|
| 16727 |
+
"step": 4774
|
| 16728 |
+
},
|
| 16729 |
+
{
|
| 16730 |
+
"epoch": 0.25070866141732284,
|
| 16731 |
+
"grad_norm": 0.04014856740832329,
|
| 16732 |
+
"learning_rate": 0.0012,
|
| 16733 |
+
"loss": 2.31204891204834,
|
| 16734 |
+
"step": 4776
|
| 16735 |
+
},
|
| 16736 |
+
{
|
| 16737 |
+
"epoch": 0.25081364829396324,
|
| 16738 |
+
"grad_norm": 0.04149448126554489,
|
| 16739 |
+
"learning_rate": 0.0012,
|
| 16740 |
+
"loss": 2.216075897216797,
|
| 16741 |
+
"step": 4778
|
| 16742 |
+
},
|
| 16743 |
+
{
|
| 16744 |
+
"epoch": 0.2509186351706037,
|
| 16745 |
+
"grad_norm": 0.043129146099090576,
|
| 16746 |
+
"learning_rate": 0.0012,
|
| 16747 |
+
"loss": 2.2728641033172607,
|
| 16748 |
+
"step": 4780
|
| 16749 |
+
},
|
| 16750 |
+
{
|
| 16751 |
+
"epoch": 0.2510236220472441,
|
| 16752 |
+
"grad_norm": 0.046268414705991745,
|
| 16753 |
+
"learning_rate": 0.0012,
|
| 16754 |
+
"loss": 2.2619526386260986,
|
| 16755 |
+
"step": 4782
|
| 16756 |
+
},
|
| 16757 |
+
{
|
| 16758 |
+
"epoch": 0.2511286089238845,
|
| 16759 |
+
"grad_norm": 0.04422568157315254,
|
| 16760 |
+
"learning_rate": 0.0012,
|
| 16761 |
+
"loss": 2.2984426021575928,
|
| 16762 |
+
"step": 4784
|
| 16763 |
+
},
|
| 16764 |
+
{
|
| 16765 |
+
"epoch": 0.25123359580052496,
|
| 16766 |
+
"grad_norm": 0.04222942143678665,
|
| 16767 |
+
"learning_rate": 0.0012,
|
| 16768 |
+
"loss": 2.2392961978912354,
|
| 16769 |
+
"step": 4786
|
| 16770 |
+
},
|
| 16771 |
+
{
|
| 16772 |
+
"epoch": 0.25133858267716536,
|
| 16773 |
+
"grad_norm": 0.04161546751856804,
|
| 16774 |
+
"learning_rate": 0.0012,
|
| 16775 |
+
"loss": 2.256932020187378,
|
| 16776 |
+
"step": 4788
|
| 16777 |
+
},
|
| 16778 |
+
{
|
| 16779 |
+
"epoch": 0.25144356955380576,
|
| 16780 |
+
"grad_norm": 0.043737322092056274,
|
| 16781 |
+
"learning_rate": 0.0012,
|
| 16782 |
+
"loss": 2.273273229598999,
|
| 16783 |
+
"step": 4790
|
| 16784 |
+
},
|
| 16785 |
+
{
|
| 16786 |
+
"epoch": 0.2515485564304462,
|
| 16787 |
+
"grad_norm": 0.04259445518255234,
|
| 16788 |
+
"learning_rate": 0.0012,
|
| 16789 |
+
"loss": 2.2522459030151367,
|
| 16790 |
+
"step": 4792
|
| 16791 |
+
},
|
| 16792 |
+
{
|
| 16793 |
+
"epoch": 0.2516535433070866,
|
| 16794 |
+
"grad_norm": 0.05439925938844681,
|
| 16795 |
+
"learning_rate": 0.0012,
|
| 16796 |
+
"loss": 2.3083269596099854,
|
| 16797 |
+
"step": 4794
|
| 16798 |
+
},
|
| 16799 |
+
{
|
| 16800 |
+
"epoch": 0.251758530183727,
|
| 16801 |
+
"grad_norm": 0.05589040741324425,
|
| 16802 |
+
"learning_rate": 0.0012,
|
| 16803 |
+
"loss": 2.2996280193328857,
|
| 16804 |
+
"step": 4796
|
| 16805 |
+
},
|
| 16806 |
+
{
|
| 16807 |
+
"epoch": 0.25186351706036747,
|
| 16808 |
+
"grad_norm": 0.04450809955596924,
|
| 16809 |
+
"learning_rate": 0.0012,
|
| 16810 |
+
"loss": 2.3380682468414307,
|
| 16811 |
+
"step": 4798
|
| 16812 |
+
},
|
| 16813 |
+
{
|
| 16814 |
+
"epoch": 0.25196850393700787,
|
| 16815 |
+
"grad_norm": 0.052577726542949677,
|
| 16816 |
+
"learning_rate": 0.0012,
|
| 16817 |
+
"loss": 2.187272310256958,
|
| 16818 |
+
"step": 4800
|
| 16819 |
+
},
|
| 16820 |
+
{
|
| 16821 |
+
"epoch": 0.25207349081364827,
|
| 16822 |
+
"grad_norm": 0.050958022475242615,
|
| 16823 |
+
"learning_rate": 0.0012,
|
| 16824 |
+
"loss": 2.2546634674072266,
|
| 16825 |
+
"step": 4802
|
| 16826 |
+
},
|
| 16827 |
+
{
|
| 16828 |
+
"epoch": 0.2521784776902887,
|
| 16829 |
+
"grad_norm": 0.05081610754132271,
|
| 16830 |
+
"learning_rate": 0.0012,
|
| 16831 |
+
"loss": 2.2970945835113525,
|
| 16832 |
+
"step": 4804
|
| 16833 |
+
},
|
| 16834 |
+
{
|
| 16835 |
+
"epoch": 0.2522834645669291,
|
| 16836 |
+
"grad_norm": 0.044849053025245667,
|
| 16837 |
+
"learning_rate": 0.0012,
|
| 16838 |
+
"loss": 2.3133704662323,
|
| 16839 |
+
"step": 4806
|
| 16840 |
+
},
|
| 16841 |
+
{
|
| 16842 |
+
"epoch": 0.25238845144356953,
|
| 16843 |
+
"grad_norm": 0.039470888674259186,
|
| 16844 |
+
"learning_rate": 0.0012,
|
| 16845 |
+
"loss": 2.232126474380493,
|
| 16846 |
+
"step": 4808
|
| 16847 |
+
},
|
| 16848 |
+
{
|
| 16849 |
+
"epoch": 0.25249343832021,
|
| 16850 |
+
"grad_norm": 0.04755723848938942,
|
| 16851 |
+
"learning_rate": 0.0012,
|
| 16852 |
+
"loss": 2.2686383724212646,
|
| 16853 |
+
"step": 4810
|
| 16854 |
+
},
|
| 16855 |
+
{
|
| 16856 |
+
"epoch": 0.2525984251968504,
|
| 16857 |
+
"grad_norm": 0.05096384510397911,
|
| 16858 |
+
"learning_rate": 0.0012,
|
| 16859 |
+
"loss": 2.273664712905884,
|
| 16860 |
+
"step": 4812
|
| 16861 |
+
},
|
| 16862 |
+
{
|
| 16863 |
+
"epoch": 0.25270341207349084,
|
| 16864 |
+
"grad_norm": 0.061847712844610214,
|
| 16865 |
+
"learning_rate": 0.0012,
|
| 16866 |
+
"loss": 2.290898323059082,
|
| 16867 |
+
"step": 4814
|
| 16868 |
+
},
|
| 16869 |
+
{
|
| 16870 |
+
"epoch": 0.25280839895013124,
|
| 16871 |
+
"grad_norm": 0.04640721529722214,
|
| 16872 |
+
"learning_rate": 0.0012,
|
| 16873 |
+
"loss": 2.3145945072174072,
|
| 16874 |
+
"step": 4816
|
| 16875 |
+
},
|
| 16876 |
+
{
|
| 16877 |
+
"epoch": 0.25291338582677164,
|
| 16878 |
+
"grad_norm": 0.06200100854039192,
|
| 16879 |
+
"learning_rate": 0.0012,
|
| 16880 |
+
"loss": 2.31445050239563,
|
| 16881 |
+
"step": 4818
|
| 16882 |
+
},
|
| 16883 |
+
{
|
| 16884 |
+
"epoch": 0.2530183727034121,
|
| 16885 |
+
"grad_norm": 0.06149599328637123,
|
| 16886 |
+
"learning_rate": 0.0012,
|
| 16887 |
+
"loss": 2.241593837738037,
|
| 16888 |
+
"step": 4820
|
| 16889 |
+
},
|
| 16890 |
+
{
|
| 16891 |
+
"epoch": 0.2531233595800525,
|
| 16892 |
+
"grad_norm": 0.04669628664851189,
|
| 16893 |
+
"learning_rate": 0.0012,
|
| 16894 |
+
"loss": 2.2366836071014404,
|
| 16895 |
+
"step": 4822
|
| 16896 |
+
},
|
| 16897 |
+
{
|
| 16898 |
+
"epoch": 0.2532283464566929,
|
| 16899 |
+
"grad_norm": 0.055651139467954636,
|
| 16900 |
+
"learning_rate": 0.0012,
|
| 16901 |
+
"loss": 2.140180826187134,
|
| 16902 |
+
"step": 4824
|
| 16903 |
+
},
|
| 16904 |
+
{
|
| 16905 |
+
"epoch": 0.25333333333333335,
|
| 16906 |
+
"grad_norm": 0.059728194028139114,
|
| 16907 |
+
"learning_rate": 0.0012,
|
| 16908 |
+
"loss": 2.29640531539917,
|
| 16909 |
+
"step": 4826
|
| 16910 |
+
},
|
| 16911 |
+
{
|
| 16912 |
+
"epoch": 0.25343832020997376,
|
| 16913 |
+
"grad_norm": 0.051788728684186935,
|
| 16914 |
+
"learning_rate": 0.0012,
|
| 16915 |
+
"loss": 2.220189094543457,
|
| 16916 |
+
"step": 4828
|
| 16917 |
+
},
|
| 16918 |
+
{
|
| 16919 |
+
"epoch": 0.25354330708661416,
|
| 16920 |
+
"grad_norm": 0.04497329145669937,
|
| 16921 |
+
"learning_rate": 0.0012,
|
| 16922 |
+
"loss": 2.240278720855713,
|
| 16923 |
+
"step": 4830
|
| 16924 |
+
},
|
| 16925 |
+
{
|
| 16926 |
+
"epoch": 0.2536482939632546,
|
| 16927 |
+
"grad_norm": 0.04020310193300247,
|
| 16928 |
+
"learning_rate": 0.0012,
|
| 16929 |
+
"loss": 2.285639524459839,
|
| 16930 |
+
"step": 4832
|
| 16931 |
+
},
|
| 16932 |
+
{
|
| 16933 |
+
"epoch": 0.253753280839895,
|
| 16934 |
+
"grad_norm": 0.043702319264411926,
|
| 16935 |
+
"learning_rate": 0.0012,
|
| 16936 |
+
"loss": 2.2924351692199707,
|
| 16937 |
+
"step": 4834
|
| 16938 |
+
},
|
| 16939 |
+
{
|
| 16940 |
+
"epoch": 0.2538582677165354,
|
| 16941 |
+
"grad_norm": 0.046045009046792984,
|
| 16942 |
+
"learning_rate": 0.0012,
|
| 16943 |
+
"loss": 2.2616324424743652,
|
| 16944 |
+
"step": 4836
|
| 16945 |
+
},
|
| 16946 |
+
{
|
| 16947 |
+
"epoch": 0.25396325459317587,
|
| 16948 |
+
"grad_norm": 0.04277903214097023,
|
| 16949 |
+
"learning_rate": 0.0012,
|
| 16950 |
+
"loss": 2.3265380859375,
|
| 16951 |
+
"step": 4838
|
| 16952 |
+
},
|
| 16953 |
+
{
|
| 16954 |
+
"epoch": 0.25406824146981627,
|
| 16955 |
+
"grad_norm": 0.04956955835223198,
|
| 16956 |
+
"learning_rate": 0.0012,
|
| 16957 |
+
"loss": 2.2428877353668213,
|
| 16958 |
+
"step": 4840
|
| 16959 |
+
},
|
| 16960 |
+
{
|
| 16961 |
+
"epoch": 0.25417322834645667,
|
| 16962 |
+
"grad_norm": 0.04579349607229233,
|
| 16963 |
+
"learning_rate": 0.0012,
|
| 16964 |
+
"loss": 2.2690658569335938,
|
| 16965 |
+
"step": 4842
|
| 16966 |
+
},
|
| 16967 |
+
{
|
| 16968 |
+
"epoch": 0.2542782152230971,
|
| 16969 |
+
"grad_norm": 0.045570049434900284,
|
| 16970 |
+
"learning_rate": 0.0012,
|
| 16971 |
+
"loss": 2.2955610752105713,
|
| 16972 |
+
"step": 4844
|
| 16973 |
+
},
|
| 16974 |
+
{
|
| 16975 |
+
"epoch": 0.2543832020997375,
|
| 16976 |
+
"grad_norm": 0.04226912930607796,
|
| 16977 |
+
"learning_rate": 0.0012,
|
| 16978 |
+
"loss": 2.296703338623047,
|
| 16979 |
+
"step": 4846
|
| 16980 |
+
},
|
| 16981 |
+
{
|
| 16982 |
+
"epoch": 0.2544881889763779,
|
| 16983 |
+
"grad_norm": 0.04170621931552887,
|
| 16984 |
+
"learning_rate": 0.0012,
|
| 16985 |
+
"loss": 2.285489320755005,
|
| 16986 |
+
"step": 4848
|
| 16987 |
+
},
|
| 16988 |
+
{
|
| 16989 |
+
"epoch": 0.2545931758530184,
|
| 16990 |
+
"grad_norm": 0.05194440856575966,
|
| 16991 |
+
"learning_rate": 0.0012,
|
| 16992 |
+
"loss": 2.2659668922424316,
|
| 16993 |
+
"step": 4850
|
| 16994 |
+
},
|
| 16995 |
+
{
|
| 16996 |
+
"epoch": 0.2546981627296588,
|
| 16997 |
+
"grad_norm": 0.05482574552297592,
|
| 16998 |
+
"learning_rate": 0.0012,
|
| 16999 |
+
"loss": 2.3385798931121826,
|
| 17000 |
+
"step": 4852
|
| 17001 |
+
},
|
| 17002 |
+
{
|
| 17003 |
+
"epoch": 0.25480314960629924,
|
| 17004 |
+
"grad_norm": 0.060105182230472565,
|
| 17005 |
+
"learning_rate": 0.0012,
|
| 17006 |
+
"loss": 2.2890753746032715,
|
| 17007 |
+
"step": 4854
|
| 17008 |
+
},
|
| 17009 |
+
{
|
| 17010 |
+
"epoch": 0.25490813648293964,
|
| 17011 |
+
"grad_norm": 0.049228016287088394,
|
| 17012 |
+
"learning_rate": 0.0012,
|
| 17013 |
+
"loss": 2.2852401733398438,
|
| 17014 |
+
"step": 4856
|
| 17015 |
+
},
|
| 17016 |
+
{
|
| 17017 |
+
"epoch": 0.25501312335958004,
|
| 17018 |
+
"grad_norm": 0.053668174892663956,
|
| 17019 |
+
"learning_rate": 0.0012,
|
| 17020 |
+
"loss": 2.310084819793701,
|
| 17021 |
+
"step": 4858
|
| 17022 |
+
},
|
| 17023 |
+
{
|
| 17024 |
+
"epoch": 0.2551181102362205,
|
| 17025 |
+
"grad_norm": 0.04837637394666672,
|
| 17026 |
+
"learning_rate": 0.0012,
|
| 17027 |
+
"loss": 2.2294797897338867,
|
| 17028 |
+
"step": 4860
|
| 17029 |
+
},
|
| 17030 |
+
{
|
| 17031 |
+
"epoch": 0.2552230971128609,
|
| 17032 |
+
"grad_norm": 0.04660574346780777,
|
| 17033 |
+
"learning_rate": 0.0012,
|
| 17034 |
+
"loss": 2.2638001441955566,
|
| 17035 |
+
"step": 4862
|
| 17036 |
+
},
|
| 17037 |
+
{
|
| 17038 |
+
"epoch": 0.2553280839895013,
|
| 17039 |
+
"grad_norm": 0.04887060075998306,
|
| 17040 |
+
"learning_rate": 0.0012,
|
| 17041 |
+
"loss": 2.2719671726226807,
|
| 17042 |
+
"step": 4864
|
| 17043 |
+
},
|
| 17044 |
+
{
|
| 17045 |
+
"epoch": 0.25543307086614175,
|
| 17046 |
+
"grad_norm": 0.04905172809958458,
|
| 17047 |
+
"learning_rate": 0.0012,
|
| 17048 |
+
"loss": 2.266357660293579,
|
| 17049 |
+
"step": 4866
|
| 17050 |
+
},
|
| 17051 |
+
{
|
| 17052 |
+
"epoch": 0.25553805774278215,
|
| 17053 |
+
"grad_norm": 0.05803888663649559,
|
| 17054 |
+
"learning_rate": 0.0012,
|
| 17055 |
+
"loss": 2.222536087036133,
|
| 17056 |
+
"step": 4868
|
| 17057 |
+
},
|
| 17058 |
+
{
|
| 17059 |
+
"epoch": 0.25564304461942255,
|
| 17060 |
+
"grad_norm": 0.04990249499678612,
|
| 17061 |
+
"learning_rate": 0.0012,
|
| 17062 |
+
"loss": 2.341496706008911,
|
| 17063 |
+
"step": 4870
|
| 17064 |
+
},
|
| 17065 |
+
{
|
| 17066 |
+
"epoch": 0.255748031496063,
|
| 17067 |
+
"grad_norm": 0.052773367613554,
|
| 17068 |
+
"learning_rate": 0.0012,
|
| 17069 |
+
"loss": 2.31154465675354,
|
| 17070 |
+
"step": 4872
|
| 17071 |
+
},
|
| 17072 |
+
{
|
| 17073 |
+
"epoch": 0.2558530183727034,
|
| 17074 |
+
"grad_norm": 0.04494437202811241,
|
| 17075 |
+
"learning_rate": 0.0012,
|
| 17076 |
+
"loss": 2.285032272338867,
|
| 17077 |
+
"step": 4874
|
| 17078 |
+
},
|
| 17079 |
+
{
|
| 17080 |
+
"epoch": 0.2559580052493438,
|
| 17081 |
+
"grad_norm": 0.052033431828022,
|
| 17082 |
+
"learning_rate": 0.0012,
|
| 17083 |
+
"loss": 2.222803831100464,
|
| 17084 |
+
"step": 4876
|
| 17085 |
+
},
|
| 17086 |
+
{
|
| 17087 |
+
"epoch": 0.25606299212598427,
|
| 17088 |
+
"grad_norm": 0.05891354754567146,
|
| 17089 |
+
"learning_rate": 0.0012,
|
| 17090 |
+
"loss": 2.2949697971343994,
|
| 17091 |
+
"step": 4878
|
| 17092 |
+
},
|
| 17093 |
+
{
|
| 17094 |
+
"epoch": 0.25616797900262467,
|
| 17095 |
+
"grad_norm": 0.046633996069431305,
|
| 17096 |
+
"learning_rate": 0.0012,
|
| 17097 |
+
"loss": 2.2789199352264404,
|
| 17098 |
+
"step": 4880
|
| 17099 |
+
},
|
| 17100 |
+
{
|
| 17101 |
+
"epoch": 0.25627296587926507,
|
| 17102 |
+
"grad_norm": 0.050691280514001846,
|
| 17103 |
+
"learning_rate": 0.0012,
|
| 17104 |
+
"loss": 2.3577420711517334,
|
| 17105 |
+
"step": 4882
|
| 17106 |
+
},
|
| 17107 |
+
{
|
| 17108 |
+
"epoch": 0.2563779527559055,
|
| 17109 |
+
"grad_norm": 0.05182667821645737,
|
| 17110 |
+
"learning_rate": 0.0012,
|
| 17111 |
+
"loss": 2.31245493888855,
|
| 17112 |
+
"step": 4884
|
| 17113 |
+
},
|
| 17114 |
+
{
|
| 17115 |
+
"epoch": 0.2564829396325459,
|
| 17116 |
+
"grad_norm": 0.04288569092750549,
|
| 17117 |
+
"learning_rate": 0.0012,
|
| 17118 |
+
"loss": 2.3281142711639404,
|
| 17119 |
+
"step": 4886
|
| 17120 |
+
},
|
| 17121 |
+
{
|
| 17122 |
+
"epoch": 0.2565879265091863,
|
| 17123 |
+
"grad_norm": 0.052317190915346146,
|
| 17124 |
+
"learning_rate": 0.0012,
|
| 17125 |
+
"loss": 2.252451181411743,
|
| 17126 |
+
"step": 4888
|
| 17127 |
+
},
|
| 17128 |
+
{
|
| 17129 |
+
"epoch": 0.2566929133858268,
|
| 17130 |
+
"grad_norm": 0.051650520414114,
|
| 17131 |
+
"learning_rate": 0.0012,
|
| 17132 |
+
"loss": 2.2552082538604736,
|
| 17133 |
+
"step": 4890
|
| 17134 |
+
},
|
| 17135 |
+
{
|
| 17136 |
+
"epoch": 0.2567979002624672,
|
| 17137 |
+
"grad_norm": 0.05839875712990761,
|
| 17138 |
+
"learning_rate": 0.0012,
|
| 17139 |
+
"loss": 2.2577197551727295,
|
| 17140 |
+
"step": 4892
|
| 17141 |
+
},
|
| 17142 |
+
{
|
| 17143 |
+
"epoch": 0.25690288713910764,
|
| 17144 |
+
"grad_norm": 0.04445129260420799,
|
| 17145 |
+
"learning_rate": 0.0012,
|
| 17146 |
+
"loss": 2.219287395477295,
|
| 17147 |
+
"step": 4894
|
| 17148 |
+
},
|
| 17149 |
+
{
|
| 17150 |
+
"epoch": 0.25700787401574804,
|
| 17151 |
+
"grad_norm": 0.05907997116446495,
|
| 17152 |
+
"learning_rate": 0.0012,
|
| 17153 |
+
"loss": 2.2342333793640137,
|
| 17154 |
+
"step": 4896
|
| 17155 |
+
},
|
| 17156 |
+
{
|
| 17157 |
+
"epoch": 0.25711286089238844,
|
| 17158 |
+
"grad_norm": 0.06300616264343262,
|
| 17159 |
+
"learning_rate": 0.0012,
|
| 17160 |
+
"loss": 2.2845840454101562,
|
| 17161 |
+
"step": 4898
|
| 17162 |
+
},
|
| 17163 |
+
{
|
| 17164 |
+
"epoch": 0.2572178477690289,
|
| 17165 |
+
"grad_norm": 0.05668189749121666,
|
| 17166 |
+
"learning_rate": 0.0012,
|
| 17167 |
+
"loss": 2.2237861156463623,
|
| 17168 |
+
"step": 4900
|
| 17169 |
+
},
|
| 17170 |
+
{
|
| 17171 |
+
"epoch": 0.2573228346456693,
|
| 17172 |
+
"grad_norm": 0.05590416491031647,
|
| 17173 |
+
"learning_rate": 0.0012,
|
| 17174 |
+
"loss": 2.2546637058258057,
|
| 17175 |
+
"step": 4902
|
| 17176 |
+
},
|
| 17177 |
+
{
|
| 17178 |
+
"epoch": 0.2574278215223097,
|
| 17179 |
+
"grad_norm": 0.04464484006166458,
|
| 17180 |
+
"learning_rate": 0.0012,
|
| 17181 |
+
"loss": 2.22969651222229,
|
| 17182 |
+
"step": 4904
|
| 17183 |
+
},
|
| 17184 |
+
{
|
| 17185 |
+
"epoch": 0.25753280839895015,
|
| 17186 |
+
"grad_norm": 0.03867115452885628,
|
| 17187 |
+
"learning_rate": 0.0012,
|
| 17188 |
+
"loss": 2.254499673843384,
|
| 17189 |
+
"step": 4906
|
| 17190 |
+
},
|
| 17191 |
+
{
|
| 17192 |
+
"epoch": 0.25763779527559055,
|
| 17193 |
+
"grad_norm": 0.04090867564082146,
|
| 17194 |
+
"learning_rate": 0.0012,
|
| 17195 |
+
"loss": 2.261538505554199,
|
| 17196 |
+
"step": 4908
|
| 17197 |
+
},
|
| 17198 |
+
{
|
| 17199 |
+
"epoch": 0.25774278215223095,
|
| 17200 |
+
"grad_norm": 0.044658783823251724,
|
| 17201 |
+
"learning_rate": 0.0012,
|
| 17202 |
+
"loss": 2.2111923694610596,
|
| 17203 |
+
"step": 4910
|
| 17204 |
+
},
|
| 17205 |
+
{
|
| 17206 |
+
"epoch": 0.2578477690288714,
|
| 17207 |
+
"grad_norm": 0.04548951983451843,
|
| 17208 |
+
"learning_rate": 0.0012,
|
| 17209 |
+
"loss": 2.255542278289795,
|
| 17210 |
+
"step": 4912
|
| 17211 |
+
},
|
| 17212 |
+
{
|
| 17213 |
+
"epoch": 0.2579527559055118,
|
| 17214 |
+
"grad_norm": 0.04709501937031746,
|
| 17215 |
+
"learning_rate": 0.0012,
|
| 17216 |
+
"loss": 2.3346002101898193,
|
| 17217 |
+
"step": 4914
|
| 17218 |
+
},
|
| 17219 |
+
{
|
| 17220 |
+
"epoch": 0.2580577427821522,
|
| 17221 |
+
"grad_norm": 0.04845765233039856,
|
| 17222 |
+
"learning_rate": 0.0012,
|
| 17223 |
+
"loss": 2.2692573070526123,
|
| 17224 |
+
"step": 4916
|
| 17225 |
+
},
|
| 17226 |
+
{
|
| 17227 |
+
"epoch": 0.25816272965879267,
|
| 17228 |
+
"grad_norm": 0.04249967634677887,
|
| 17229 |
+
"learning_rate": 0.0012,
|
| 17230 |
+
"loss": 2.3280584812164307,
|
| 17231 |
+
"step": 4918
|
| 17232 |
+
},
|
| 17233 |
+
{
|
| 17234 |
+
"epoch": 0.25826771653543307,
|
| 17235 |
+
"grad_norm": 0.044410064816474915,
|
| 17236 |
+
"learning_rate": 0.0012,
|
| 17237 |
+
"loss": 2.1823465824127197,
|
| 17238 |
+
"step": 4920
|
| 17239 |
+
},
|
| 17240 |
+
{
|
| 17241 |
+
"epoch": 0.25837270341207347,
|
| 17242 |
+
"grad_norm": 0.05168010666966438,
|
| 17243 |
+
"learning_rate": 0.0012,
|
| 17244 |
+
"loss": 2.2380783557891846,
|
| 17245 |
+
"step": 4922
|
| 17246 |
+
},
|
| 17247 |
+
{
|
| 17248 |
+
"epoch": 0.2584776902887139,
|
| 17249 |
+
"grad_norm": 0.05476720258593559,
|
| 17250 |
+
"learning_rate": 0.0012,
|
| 17251 |
+
"loss": 2.312969923019409,
|
| 17252 |
+
"step": 4924
|
| 17253 |
+
},
|
| 17254 |
+
{
|
| 17255 |
+
"epoch": 0.2585826771653543,
|
| 17256 |
+
"grad_norm": 0.05512009933590889,
|
| 17257 |
+
"learning_rate": 0.0012,
|
| 17258 |
+
"loss": 2.2615082263946533,
|
| 17259 |
+
"step": 4926
|
| 17260 |
+
},
|
| 17261 |
+
{
|
| 17262 |
+
"epoch": 0.2586876640419947,
|
| 17263 |
+
"grad_norm": 0.04240155592560768,
|
| 17264 |
+
"learning_rate": 0.0012,
|
| 17265 |
+
"loss": 2.2540860176086426,
|
| 17266 |
+
"step": 4928
|
| 17267 |
+
},
|
| 17268 |
+
{
|
| 17269 |
+
"epoch": 0.2587926509186352,
|
| 17270 |
+
"grad_norm": 0.04350067675113678,
|
| 17271 |
+
"learning_rate": 0.0012,
|
| 17272 |
+
"loss": 2.2854015827178955,
|
| 17273 |
+
"step": 4930
|
| 17274 |
+
},
|
| 17275 |
+
{
|
| 17276 |
+
"epoch": 0.2588976377952756,
|
| 17277 |
+
"grad_norm": 0.04384393244981766,
|
| 17278 |
+
"learning_rate": 0.0012,
|
| 17279 |
+
"loss": 2.282374143600464,
|
| 17280 |
+
"step": 4932
|
| 17281 |
+
},
|
| 17282 |
+
{
|
| 17283 |
+
"epoch": 0.25900262467191604,
|
| 17284 |
+
"grad_norm": 0.04330199211835861,
|
| 17285 |
+
"learning_rate": 0.0012,
|
| 17286 |
+
"loss": 2.32200026512146,
|
| 17287 |
+
"step": 4934
|
| 17288 |
+
},
|
| 17289 |
+
{
|
| 17290 |
+
"epoch": 0.25910761154855644,
|
| 17291 |
+
"grad_norm": 0.053958721458911896,
|
| 17292 |
+
"learning_rate": 0.0012,
|
| 17293 |
+
"loss": 2.2698402404785156,
|
| 17294 |
+
"step": 4936
|
| 17295 |
+
},
|
| 17296 |
+
{
|
| 17297 |
+
"epoch": 0.25921259842519684,
|
| 17298 |
+
"grad_norm": 0.04503243416547775,
|
| 17299 |
+
"learning_rate": 0.0012,
|
| 17300 |
+
"loss": 2.3026628494262695,
|
| 17301 |
+
"step": 4938
|
| 17302 |
+
},
|
| 17303 |
+
{
|
| 17304 |
+
"epoch": 0.2593175853018373,
|
| 17305 |
+
"grad_norm": 0.059724561870098114,
|
| 17306 |
+
"learning_rate": 0.0012,
|
| 17307 |
+
"loss": 2.2365381717681885,
|
| 17308 |
+
"step": 4940
|
| 17309 |
+
},
|
| 17310 |
+
{
|
| 17311 |
+
"epoch": 0.2594225721784777,
|
| 17312 |
+
"grad_norm": 0.04209195822477341,
|
| 17313 |
+
"learning_rate": 0.0012,
|
| 17314 |
+
"loss": 2.2940402030944824,
|
| 17315 |
+
"step": 4942
|
| 17316 |
+
},
|
| 17317 |
+
{
|
| 17318 |
+
"epoch": 0.2595275590551181,
|
| 17319 |
+
"grad_norm": 0.043781690299510956,
|
| 17320 |
+
"learning_rate": 0.0012,
|
| 17321 |
+
"loss": 2.2483420372009277,
|
| 17322 |
+
"step": 4944
|
| 17323 |
+
},
|
| 17324 |
+
{
|
| 17325 |
+
"epoch": 0.25963254593175855,
|
| 17326 |
+
"grad_norm": 0.04905322194099426,
|
| 17327 |
+
"learning_rate": 0.0012,
|
| 17328 |
+
"loss": 2.285515308380127,
|
| 17329 |
+
"step": 4946
|
| 17330 |
+
},
|
| 17331 |
+
{
|
| 17332 |
+
"epoch": 0.25973753280839895,
|
| 17333 |
+
"grad_norm": 0.03907564654946327,
|
| 17334 |
+
"learning_rate": 0.0012,
|
| 17335 |
+
"loss": 2.2359941005706787,
|
| 17336 |
+
"step": 4948
|
| 17337 |
+
},
|
| 17338 |
+
{
|
| 17339 |
+
"epoch": 0.25984251968503935,
|
| 17340 |
+
"grad_norm": 0.044622454792261124,
|
| 17341 |
+
"learning_rate": 0.0012,
|
| 17342 |
+
"loss": 2.2473971843719482,
|
| 17343 |
+
"step": 4950
|
| 17344 |
+
},
|
| 17345 |
+
{
|
| 17346 |
+
"epoch": 0.2599475065616798,
|
| 17347 |
+
"grad_norm": 0.049914173781871796,
|
| 17348 |
+
"learning_rate": 0.0012,
|
| 17349 |
+
"loss": 2.2973828315734863,
|
| 17350 |
+
"step": 4952
|
| 17351 |
+
},
|
| 17352 |
+
{
|
| 17353 |
+
"epoch": 0.2600524934383202,
|
| 17354 |
+
"grad_norm": 0.04418397322297096,
|
| 17355 |
+
"learning_rate": 0.0012,
|
| 17356 |
+
"loss": 2.300748109817505,
|
| 17357 |
+
"step": 4954
|
| 17358 |
+
},
|
| 17359 |
+
{
|
| 17360 |
+
"epoch": 0.2601574803149606,
|
| 17361 |
+
"grad_norm": 0.04188762232661247,
|
| 17362 |
+
"learning_rate": 0.0012,
|
| 17363 |
+
"loss": 2.257521152496338,
|
| 17364 |
+
"step": 4956
|
| 17365 |
+
},
|
| 17366 |
+
{
|
| 17367 |
+
"epoch": 0.26026246719160107,
|
| 17368 |
+
"grad_norm": 0.04161308705806732,
|
| 17369 |
+
"learning_rate": 0.0012,
|
| 17370 |
+
"loss": 2.2507195472717285,
|
| 17371 |
+
"step": 4958
|
| 17372 |
+
},
|
| 17373 |
+
{
|
| 17374 |
+
"epoch": 0.26036745406824147,
|
| 17375 |
+
"grad_norm": 0.04159074276685715,
|
| 17376 |
+
"learning_rate": 0.0012,
|
| 17377 |
+
"loss": 2.165569543838501,
|
| 17378 |
+
"step": 4960
|
| 17379 |
+
},
|
| 17380 |
+
{
|
| 17381 |
+
"epoch": 0.26047244094488187,
|
| 17382 |
+
"grad_norm": 0.04413628950715065,
|
| 17383 |
+
"learning_rate": 0.0012,
|
| 17384 |
+
"loss": 2.2998969554901123,
|
| 17385 |
+
"step": 4962
|
| 17386 |
+
},
|
| 17387 |
+
{
|
| 17388 |
+
"epoch": 0.2605774278215223,
|
| 17389 |
+
"grad_norm": 0.049211323261260986,
|
| 17390 |
+
"learning_rate": 0.0012,
|
| 17391 |
+
"loss": 2.245408296585083,
|
| 17392 |
+
"step": 4964
|
| 17393 |
+
},
|
| 17394 |
+
{
|
| 17395 |
+
"epoch": 0.2606824146981627,
|
| 17396 |
+
"grad_norm": 0.04275268688797951,
|
| 17397 |
+
"learning_rate": 0.0012,
|
| 17398 |
+
"loss": 2.373617649078369,
|
| 17399 |
+
"step": 4966
|
| 17400 |
+
},
|
| 17401 |
+
{
|
| 17402 |
+
"epoch": 0.2607874015748031,
|
| 17403 |
+
"grad_norm": 0.06681369245052338,
|
| 17404 |
+
"learning_rate": 0.0012,
|
| 17405 |
+
"loss": 2.279995918273926,
|
| 17406 |
+
"step": 4968
|
| 17407 |
+
},
|
| 17408 |
+
{
|
| 17409 |
+
"epoch": 0.2608923884514436,
|
| 17410 |
+
"grad_norm": 0.05982321500778198,
|
| 17411 |
+
"learning_rate": 0.0012,
|
| 17412 |
+
"loss": 2.267404079437256,
|
| 17413 |
+
"step": 4970
|
| 17414 |
+
},
|
| 17415 |
+
{
|
| 17416 |
+
"epoch": 0.260997375328084,
|
| 17417 |
+
"grad_norm": 0.043729327619075775,
|
| 17418 |
+
"learning_rate": 0.0012,
|
| 17419 |
+
"loss": 2.2819578647613525,
|
| 17420 |
+
"step": 4972
|
| 17421 |
+
},
|
| 17422 |
+
{
|
| 17423 |
+
"epoch": 0.26110236220472444,
|
| 17424 |
+
"grad_norm": 0.04800916090607643,
|
| 17425 |
+
"learning_rate": 0.0012,
|
| 17426 |
+
"loss": 2.2755162715911865,
|
| 17427 |
+
"step": 4974
|
| 17428 |
+
},
|
| 17429 |
+
{
|
| 17430 |
+
"epoch": 0.26120734908136484,
|
| 17431 |
+
"grad_norm": 0.04966862499713898,
|
| 17432 |
+
"learning_rate": 0.0012,
|
| 17433 |
+
"loss": 2.2427830696105957,
|
| 17434 |
+
"step": 4976
|
| 17435 |
+
},
|
| 17436 |
+
{
|
| 17437 |
+
"epoch": 0.26131233595800524,
|
| 17438 |
+
"grad_norm": 0.044070765376091,
|
| 17439 |
+
"learning_rate": 0.0012,
|
| 17440 |
+
"loss": 2.299154043197632,
|
| 17441 |
+
"step": 4978
|
| 17442 |
+
},
|
| 17443 |
+
{
|
| 17444 |
+
"epoch": 0.2614173228346457,
|
| 17445 |
+
"grad_norm": 0.04456094652414322,
|
| 17446 |
+
"learning_rate": 0.0012,
|
| 17447 |
+
"loss": 2.2563531398773193,
|
| 17448 |
+
"step": 4980
|
| 17449 |
+
},
|
| 17450 |
+
{
|
| 17451 |
+
"epoch": 0.2615223097112861,
|
| 17452 |
+
"grad_norm": 0.04037667065858841,
|
| 17453 |
+
"learning_rate": 0.0012,
|
| 17454 |
+
"loss": 2.2629873752593994,
|
| 17455 |
+
"step": 4982
|
| 17456 |
+
},
|
| 17457 |
+
{
|
| 17458 |
+
"epoch": 0.2616272965879265,
|
| 17459 |
+
"grad_norm": 0.04044541344046593,
|
| 17460 |
+
"learning_rate": 0.0012,
|
| 17461 |
+
"loss": 2.241744041442871,
|
| 17462 |
+
"step": 4984
|
| 17463 |
+
},
|
| 17464 |
+
{
|
| 17465 |
+
"epoch": 0.26173228346456695,
|
| 17466 |
+
"grad_norm": 0.05393529683351517,
|
| 17467 |
+
"learning_rate": 0.0012,
|
| 17468 |
+
"loss": 2.275893449783325,
|
| 17469 |
+
"step": 4986
|
| 17470 |
+
},
|
| 17471 |
+
{
|
| 17472 |
+
"epoch": 0.26183727034120735,
|
| 17473 |
+
"grad_norm": 0.042625512927770615,
|
| 17474 |
+
"learning_rate": 0.0012,
|
| 17475 |
+
"loss": 2.3064448833465576,
|
| 17476 |
+
"step": 4988
|
| 17477 |
+
},
|
| 17478 |
+
{
|
| 17479 |
+
"epoch": 0.26194225721784775,
|
| 17480 |
+
"grad_norm": 0.04461318254470825,
|
| 17481 |
+
"learning_rate": 0.0012,
|
| 17482 |
+
"loss": 2.2677364349365234,
|
| 17483 |
+
"step": 4990
|
| 17484 |
+
},
|
| 17485 |
+
{
|
| 17486 |
+
"epoch": 0.2620472440944882,
|
| 17487 |
+
"grad_norm": 0.040530912578105927,
|
| 17488 |
+
"learning_rate": 0.0012,
|
| 17489 |
+
"loss": 2.3266191482543945,
|
| 17490 |
+
"step": 4992
|
| 17491 |
+
},
|
| 17492 |
+
{
|
| 17493 |
+
"epoch": 0.2621522309711286,
|
| 17494 |
+
"grad_norm": 0.05136874318122864,
|
| 17495 |
+
"learning_rate": 0.0012,
|
| 17496 |
+
"loss": 2.2600855827331543,
|
| 17497 |
+
"step": 4994
|
| 17498 |
+
},
|
| 17499 |
+
{
|
| 17500 |
+
"epoch": 0.262257217847769,
|
| 17501 |
+
"grad_norm": 0.046839743852615356,
|
| 17502 |
+
"learning_rate": 0.0012,
|
| 17503 |
+
"loss": 2.257643222808838,
|
| 17504 |
+
"step": 4996
|
| 17505 |
+
},
|
| 17506 |
+
{
|
| 17507 |
+
"epoch": 0.26236220472440946,
|
| 17508 |
+
"grad_norm": 0.045070912688970566,
|
| 17509 |
+
"learning_rate": 0.0012,
|
| 17510 |
+
"loss": 2.339334726333618,
|
| 17511 |
+
"step": 4998
|
| 17512 |
+
},
|
| 17513 |
+
{
|
| 17514 |
+
"epoch": 0.26246719160104987,
|
| 17515 |
+
"grad_norm": 0.046434178948402405,
|
| 17516 |
+
"learning_rate": 0.0012,
|
| 17517 |
+
"loss": 2.2501938343048096,
|
| 17518 |
+
"step": 5000
|
| 17519 |
+
},
|
| 17520 |
+
{
|
| 17521 |
+
"epoch": 0.26257217847769027,
|
| 17522 |
+
"grad_norm": 0.04022817313671112,
|
| 17523 |
+
"learning_rate": 0.0012,
|
| 17524 |
+
"loss": 2.3015031814575195,
|
| 17525 |
+
"step": 5002
|
| 17526 |
+
},
|
| 17527 |
+
{
|
| 17528 |
+
"epoch": 0.2626771653543307,
|
| 17529 |
+
"grad_norm": 0.040529366582632065,
|
| 17530 |
+
"learning_rate": 0.0012,
|
| 17531 |
+
"loss": 2.309487819671631,
|
| 17532 |
+
"step": 5004
|
| 17533 |
+
},
|
| 17534 |
+
{
|
| 17535 |
+
"epoch": 0.2627821522309711,
|
| 17536 |
+
"grad_norm": 0.04512261971831322,
|
| 17537 |
+
"learning_rate": 0.0012,
|
| 17538 |
+
"loss": 2.2534313201904297,
|
| 17539 |
+
"step": 5006
|
| 17540 |
+
},
|
| 17541 |
+
{
|
| 17542 |
+
"epoch": 0.2628871391076115,
|
| 17543 |
+
"grad_norm": 0.04092295467853546,
|
| 17544 |
+
"learning_rate": 0.0012,
|
| 17545 |
+
"loss": 2.206160068511963,
|
| 17546 |
+
"step": 5008
|
| 17547 |
+
},
|
| 17548 |
+
{
|
| 17549 |
+
"epoch": 0.262992125984252,
|
| 17550 |
+
"grad_norm": 0.04524299129843712,
|
| 17551 |
+
"learning_rate": 0.0012,
|
| 17552 |
+
"loss": 2.309462308883667,
|
| 17553 |
+
"step": 5010
|
| 17554 |
+
},
|
| 17555 |
+
{
|
| 17556 |
+
"epoch": 0.2630971128608924,
|
| 17557 |
+
"grad_norm": 0.04607023298740387,
|
| 17558 |
+
"learning_rate": 0.0012,
|
| 17559 |
+
"loss": 2.2744665145874023,
|
| 17560 |
+
"step": 5012
|
| 17561 |
+
},
|
| 17562 |
+
{
|
| 17563 |
+
"epoch": 0.26320209973753284,
|
| 17564 |
+
"grad_norm": 0.04772073030471802,
|
| 17565 |
+
"learning_rate": 0.0012,
|
| 17566 |
+
"loss": 2.288214921951294,
|
| 17567 |
+
"step": 5014
|
| 17568 |
+
},
|
| 17569 |
+
{
|
| 17570 |
+
"epoch": 0.26330708661417324,
|
| 17571 |
+
"grad_norm": 0.04103020578622818,
|
| 17572 |
+
"learning_rate": 0.0012,
|
| 17573 |
+
"loss": 2.245680332183838,
|
| 17574 |
+
"step": 5016
|
| 17575 |
+
},
|
| 17576 |
+
{
|
| 17577 |
+
"epoch": 0.26341207349081364,
|
| 17578 |
+
"grad_norm": 0.04386391118168831,
|
| 17579 |
+
"learning_rate": 0.0012,
|
| 17580 |
+
"loss": 2.2828447818756104,
|
| 17581 |
+
"step": 5018
|
| 17582 |
+
},
|
| 17583 |
+
{
|
| 17584 |
+
"epoch": 0.2635170603674541,
|
| 17585 |
+
"grad_norm": 0.041193775832653046,
|
| 17586 |
+
"learning_rate": 0.0012,
|
| 17587 |
+
"loss": 2.2676820755004883,
|
| 17588 |
+
"step": 5020
|
| 17589 |
+
},
|
| 17590 |
+
{
|
| 17591 |
+
"epoch": 0.2636220472440945,
|
| 17592 |
+
"grad_norm": 0.039965029805898666,
|
| 17593 |
+
"learning_rate": 0.0012,
|
| 17594 |
+
"loss": 2.193035364151001,
|
| 17595 |
+
"step": 5022
|
| 17596 |
+
},
|
| 17597 |
+
{
|
| 17598 |
+
"epoch": 0.2637270341207349,
|
| 17599 |
+
"grad_norm": 0.04703955724835396,
|
| 17600 |
+
"learning_rate": 0.0012,
|
| 17601 |
+
"loss": 2.2178616523742676,
|
| 17602 |
+
"step": 5024
|
| 17603 |
+
},
|
| 17604 |
+
{
|
| 17605 |
+
"epoch": 0.26383202099737535,
|
| 17606 |
+
"grad_norm": 0.05145041644573212,
|
| 17607 |
+
"learning_rate": 0.0012,
|
| 17608 |
+
"loss": 2.204716444015503,
|
| 17609 |
+
"step": 5026
|
| 17610 |
+
},
|
| 17611 |
+
{
|
| 17612 |
+
"epoch": 0.26393700787401575,
|
| 17613 |
+
"grad_norm": 0.054030194878578186,
|
| 17614 |
+
"learning_rate": 0.0012,
|
| 17615 |
+
"loss": 2.213313341140747,
|
| 17616 |
+
"step": 5028
|
| 17617 |
+
},
|
| 17618 |
+
{
|
| 17619 |
+
"epoch": 0.26404199475065615,
|
| 17620 |
+
"grad_norm": 0.0379985012114048,
|
| 17621 |
+
"learning_rate": 0.0012,
|
| 17622 |
+
"loss": 2.2000699043273926,
|
| 17623 |
+
"step": 5030
|
| 17624 |
+
},
|
| 17625 |
+
{
|
| 17626 |
+
"epoch": 0.2641469816272966,
|
| 17627 |
+
"grad_norm": 0.05144575983285904,
|
| 17628 |
+
"learning_rate": 0.0012,
|
| 17629 |
+
"loss": 2.2344679832458496,
|
| 17630 |
+
"step": 5032
|
| 17631 |
+
},
|
| 17632 |
+
{
|
| 17633 |
+
"epoch": 0.264251968503937,
|
| 17634 |
+
"grad_norm": 0.059187695384025574,
|
| 17635 |
+
"learning_rate": 0.0012,
|
| 17636 |
+
"loss": 2.229187488555908,
|
| 17637 |
+
"step": 5034
|
| 17638 |
+
},
|
| 17639 |
+
{
|
| 17640 |
+
"epoch": 0.2643569553805774,
|
| 17641 |
+
"grad_norm": 0.04317374527454376,
|
| 17642 |
+
"learning_rate": 0.0012,
|
| 17643 |
+
"loss": 2.257744073867798,
|
| 17644 |
+
"step": 5036
|
| 17645 |
+
},
|
| 17646 |
+
{
|
| 17647 |
+
"epoch": 0.26446194225721786,
|
| 17648 |
+
"grad_norm": 0.041171588003635406,
|
| 17649 |
+
"learning_rate": 0.0012,
|
| 17650 |
+
"loss": 2.2590715885162354,
|
| 17651 |
+
"step": 5038
|
| 17652 |
+
},
|
| 17653 |
+
{
|
| 17654 |
+
"epoch": 0.26456692913385826,
|
| 17655 |
+
"grad_norm": 0.05093836784362793,
|
| 17656 |
+
"learning_rate": 0.0012,
|
| 17657 |
+
"loss": 2.2974300384521484,
|
| 17658 |
+
"step": 5040
|
| 17659 |
+
},
|
| 17660 |
+
{
|
| 17661 |
+
"epoch": 0.26467191601049866,
|
| 17662 |
+
"grad_norm": 0.057788003236055374,
|
| 17663 |
+
"learning_rate": 0.0012,
|
| 17664 |
+
"loss": 2.2829160690307617,
|
| 17665 |
+
"step": 5042
|
| 17666 |
+
},
|
| 17667 |
+
{
|
| 17668 |
+
"epoch": 0.2647769028871391,
|
| 17669 |
+
"grad_norm": 0.04173847287893295,
|
| 17670 |
+
"learning_rate": 0.0012,
|
| 17671 |
+
"loss": 2.3117971420288086,
|
| 17672 |
+
"step": 5044
|
| 17673 |
+
},
|
| 17674 |
+
{
|
| 17675 |
+
"epoch": 0.2648818897637795,
|
| 17676 |
+
"grad_norm": 0.03895029425621033,
|
| 17677 |
+
"learning_rate": 0.0012,
|
| 17678 |
+
"loss": 2.27656626701355,
|
| 17679 |
+
"step": 5046
|
| 17680 |
+
},
|
| 17681 |
+
{
|
| 17682 |
+
"epoch": 0.2649868766404199,
|
| 17683 |
+
"grad_norm": 0.0589369460940361,
|
| 17684 |
+
"learning_rate": 0.0012,
|
| 17685 |
+
"loss": 2.3261489868164062,
|
| 17686 |
+
"step": 5048
|
| 17687 |
+
},
|
| 17688 |
+
{
|
| 17689 |
+
"epoch": 0.2650918635170604,
|
| 17690 |
+
"grad_norm": 0.05507330223917961,
|
| 17691 |
+
"learning_rate": 0.0012,
|
| 17692 |
+
"loss": 2.2376649379730225,
|
| 17693 |
+
"step": 5050
|
| 17694 |
+
},
|
| 17695 |
+
{
|
| 17696 |
+
"epoch": 0.2651968503937008,
|
| 17697 |
+
"grad_norm": 0.055575449019670486,
|
| 17698 |
+
"learning_rate": 0.0012,
|
| 17699 |
+
"loss": 2.282378911972046,
|
| 17700 |
+
"step": 5052
|
| 17701 |
+
},
|
| 17702 |
+
{
|
| 17703 |
+
"epoch": 0.26530183727034123,
|
| 17704 |
+
"grad_norm": 0.050034016370773315,
|
| 17705 |
+
"learning_rate": 0.0012,
|
| 17706 |
+
"loss": 2.294539213180542,
|
| 17707 |
+
"step": 5054
|
| 17708 |
+
},
|
| 17709 |
+
{
|
| 17710 |
+
"epoch": 0.26540682414698163,
|
| 17711 |
+
"grad_norm": 0.04704972729086876,
|
| 17712 |
+
"learning_rate": 0.0012,
|
| 17713 |
+
"loss": 2.3100059032440186,
|
| 17714 |
+
"step": 5056
|
| 17715 |
+
},
|
| 17716 |
+
{
|
| 17717 |
+
"epoch": 0.26551181102362204,
|
| 17718 |
+
"grad_norm": 0.05343134328722954,
|
| 17719 |
+
"learning_rate": 0.0012,
|
| 17720 |
+
"loss": 2.243628740310669,
|
| 17721 |
+
"step": 5058
|
| 17722 |
+
},
|
| 17723 |
+
{
|
| 17724 |
+
"epoch": 0.2656167979002625,
|
| 17725 |
+
"grad_norm": 0.0467628575861454,
|
| 17726 |
+
"learning_rate": 0.0012,
|
| 17727 |
+
"loss": 2.2851243019104004,
|
| 17728 |
+
"step": 5060
|
| 17729 |
+
},
|
| 17730 |
+
{
|
| 17731 |
+
"epoch": 0.2657217847769029,
|
| 17732 |
+
"grad_norm": 0.05380236357450485,
|
| 17733 |
+
"learning_rate": 0.0012,
|
| 17734 |
+
"loss": 2.2758820056915283,
|
| 17735 |
+
"step": 5062
|
| 17736 |
+
},
|
| 17737 |
+
{
|
| 17738 |
+
"epoch": 0.2658267716535433,
|
| 17739 |
+
"grad_norm": 0.05407636612653732,
|
| 17740 |
+
"learning_rate": 0.0012,
|
| 17741 |
+
"loss": 2.3003361225128174,
|
| 17742 |
+
"step": 5064
|
| 17743 |
+
},
|
| 17744 |
+
{
|
| 17745 |
+
"epoch": 0.26593175853018375,
|
| 17746 |
+
"grad_norm": 0.052542705088853836,
|
| 17747 |
+
"learning_rate": 0.0012,
|
| 17748 |
+
"loss": 2.2502987384796143,
|
| 17749 |
+
"step": 5066
|
| 17750 |
+
},
|
| 17751 |
+
{
|
| 17752 |
+
"epoch": 0.26603674540682415,
|
| 17753 |
+
"grad_norm": 0.04755691438913345,
|
| 17754 |
+
"learning_rate": 0.0012,
|
| 17755 |
+
"loss": 2.2613093852996826,
|
| 17756 |
+
"step": 5068
|
| 17757 |
+
},
|
| 17758 |
+
{
|
| 17759 |
+
"epoch": 0.26614173228346455,
|
| 17760 |
+
"grad_norm": 0.05705041438341141,
|
| 17761 |
+
"learning_rate": 0.0012,
|
| 17762 |
+
"loss": 2.246142864227295,
|
| 17763 |
+
"step": 5070
|
| 17764 |
+
},
|
| 17765 |
+
{
|
| 17766 |
+
"epoch": 0.266246719160105,
|
| 17767 |
+
"grad_norm": 0.04383765906095505,
|
| 17768 |
+
"learning_rate": 0.0012,
|
| 17769 |
+
"loss": 2.280973196029663,
|
| 17770 |
+
"step": 5072
|
| 17771 |
+
},
|
| 17772 |
+
{
|
| 17773 |
+
"epoch": 0.2663517060367454,
|
| 17774 |
+
"grad_norm": 0.040501322597265244,
|
| 17775 |
+
"learning_rate": 0.0012,
|
| 17776 |
+
"loss": 2.262176752090454,
|
| 17777 |
+
"step": 5074
|
| 17778 |
+
},
|
| 17779 |
+
{
|
| 17780 |
+
"epoch": 0.2664566929133858,
|
| 17781 |
+
"grad_norm": 0.0593101903796196,
|
| 17782 |
+
"learning_rate": 0.0012,
|
| 17783 |
+
"loss": 2.198565721511841,
|
| 17784 |
+
"step": 5076
|
| 17785 |
+
},
|
| 17786 |
+
{
|
| 17787 |
+
"epoch": 0.26656167979002626,
|
| 17788 |
+
"grad_norm": 0.043886758387088776,
|
| 17789 |
+
"learning_rate": 0.0012,
|
| 17790 |
+
"loss": 2.249985694885254,
|
| 17791 |
+
"step": 5078
|
| 17792 |
+
},
|
| 17793 |
+
{
|
| 17794 |
+
"epoch": 0.26666666666666666,
|
| 17795 |
+
"grad_norm": 0.04127727448940277,
|
| 17796 |
+
"learning_rate": 0.0012,
|
| 17797 |
+
"loss": 2.220440626144409,
|
| 17798 |
+
"step": 5080
|
| 17799 |
+
},
|
| 17800 |
+
{
|
| 17801 |
+
"epoch": 0.26677165354330706,
|
| 17802 |
+
"grad_norm": 0.053086988627910614,
|
| 17803 |
+
"learning_rate": 0.0012,
|
| 17804 |
+
"loss": 2.2163002490997314,
|
| 17805 |
+
"step": 5082
|
| 17806 |
+
},
|
| 17807 |
+
{
|
| 17808 |
+
"epoch": 0.2668766404199475,
|
| 17809 |
+
"grad_norm": 0.04117255657911301,
|
| 17810 |
+
"learning_rate": 0.0012,
|
| 17811 |
+
"loss": 2.2664849758148193,
|
| 17812 |
+
"step": 5084
|
| 17813 |
+
},
|
| 17814 |
+
{
|
| 17815 |
+
"epoch": 0.2669816272965879,
|
| 17816 |
+
"grad_norm": 0.05153685808181763,
|
| 17817 |
+
"learning_rate": 0.0012,
|
| 17818 |
+
"loss": 2.2096123695373535,
|
| 17819 |
+
"step": 5086
|
| 17820 |
+
},
|
| 17821 |
+
{
|
| 17822 |
+
"epoch": 0.2670866141732283,
|
| 17823 |
+
"grad_norm": 0.04466959089040756,
|
| 17824 |
+
"learning_rate": 0.0012,
|
| 17825 |
+
"loss": 2.2284493446350098,
|
| 17826 |
+
"step": 5088
|
| 17827 |
+
},
|
| 17828 |
+
{
|
| 17829 |
+
"epoch": 0.2671916010498688,
|
| 17830 |
+
"grad_norm": 0.0444822683930397,
|
| 17831 |
+
"learning_rate": 0.0012,
|
| 17832 |
+
"loss": 2.26193904876709,
|
| 17833 |
+
"step": 5090
|
| 17834 |
+
},
|
| 17835 |
+
{
|
| 17836 |
+
"epoch": 0.2672965879265092,
|
| 17837 |
+
"grad_norm": 0.055846165865659714,
|
| 17838 |
+
"learning_rate": 0.0012,
|
| 17839 |
+
"loss": 2.274122714996338,
|
| 17840 |
+
"step": 5092
|
| 17841 |
+
},
|
| 17842 |
+
{
|
| 17843 |
+
"epoch": 0.26740157480314963,
|
| 17844 |
+
"grad_norm": 0.046085525304079056,
|
| 17845 |
+
"learning_rate": 0.0012,
|
| 17846 |
+
"loss": 2.2516560554504395,
|
| 17847 |
+
"step": 5094
|
| 17848 |
+
},
|
| 17849 |
+
{
|
| 17850 |
+
"epoch": 0.26750656167979003,
|
| 17851 |
+
"grad_norm": 0.04166245460510254,
|
| 17852 |
+
"learning_rate": 0.0012,
|
| 17853 |
+
"loss": 2.2271530628204346,
|
| 17854 |
+
"step": 5096
|
| 17855 |
+
},
|
| 17856 |
+
{
|
| 17857 |
+
"epoch": 0.26761154855643043,
|
| 17858 |
+
"grad_norm": 0.06221449002623558,
|
| 17859 |
+
"learning_rate": 0.0012,
|
| 17860 |
+
"loss": 2.2581262588500977,
|
| 17861 |
+
"step": 5098
|
| 17862 |
+
},
|
| 17863 |
+
{
|
| 17864 |
+
"epoch": 0.2677165354330709,
|
| 17865 |
+
"grad_norm": 0.05801258981227875,
|
| 17866 |
+
"learning_rate": 0.0012,
|
| 17867 |
+
"loss": 2.1995127201080322,
|
| 17868 |
+
"step": 5100
|
| 17869 |
+
},
|
| 17870 |
+
{
|
| 17871 |
+
"epoch": 0.2678215223097113,
|
| 17872 |
+
"grad_norm": 0.04624233394861221,
|
| 17873 |
+
"learning_rate": 0.0012,
|
| 17874 |
+
"loss": 2.268223762512207,
|
| 17875 |
+
"step": 5102
|
| 17876 |
+
},
|
| 17877 |
+
{
|
| 17878 |
+
"epoch": 0.2679265091863517,
|
| 17879 |
+
"grad_norm": 0.0422876700758934,
|
| 17880 |
+
"learning_rate": 0.0012,
|
| 17881 |
+
"loss": 2.2413103580474854,
|
| 17882 |
+
"step": 5104
|
| 17883 |
+
},
|
| 17884 |
+
{
|
| 17885 |
+
"epoch": 0.26803149606299215,
|
| 17886 |
+
"grad_norm": 0.060698773711919785,
|
| 17887 |
+
"learning_rate": 0.0012,
|
| 17888 |
+
"loss": 2.2058167457580566,
|
| 17889 |
+
"step": 5106
|
| 17890 |
+
},
|
| 17891 |
+
{
|
| 17892 |
+
"epoch": 0.26813648293963255,
|
| 17893 |
+
"grad_norm": 0.07605348527431488,
|
| 17894 |
+
"learning_rate": 0.0012,
|
| 17895 |
+
"loss": 2.2573413848876953,
|
| 17896 |
+
"step": 5108
|
| 17897 |
+
},
|
| 17898 |
+
{
|
| 17899 |
+
"epoch": 0.26824146981627295,
|
| 17900 |
+
"grad_norm": 0.06772256642580032,
|
| 17901 |
+
"learning_rate": 0.0012,
|
| 17902 |
+
"loss": 2.3053171634674072,
|
| 17903 |
+
"step": 5110
|
| 17904 |
+
},
|
| 17905 |
+
{
|
| 17906 |
+
"epoch": 0.2683464566929134,
|
| 17907 |
+
"grad_norm": 0.055610351264476776,
|
| 17908 |
+
"learning_rate": 0.0012,
|
| 17909 |
+
"loss": 2.219200611114502,
|
| 17910 |
+
"step": 5112
|
| 17911 |
+
},
|
| 17912 |
+
{
|
| 17913 |
+
"epoch": 0.2684514435695538,
|
| 17914 |
+
"grad_norm": 0.04572371020913124,
|
| 17915 |
+
"learning_rate": 0.0012,
|
| 17916 |
+
"loss": 2.2559776306152344,
|
| 17917 |
+
"step": 5114
|
| 17918 |
+
},
|
| 17919 |
+
{
|
| 17920 |
+
"epoch": 0.2685564304461942,
|
| 17921 |
+
"grad_norm": 0.04032288119196892,
|
| 17922 |
+
"learning_rate": 0.0012,
|
| 17923 |
+
"loss": 2.2613399028778076,
|
| 17924 |
+
"step": 5116
|
| 17925 |
+
},
|
| 17926 |
+
{
|
| 17927 |
+
"epoch": 0.26866141732283466,
|
| 17928 |
+
"grad_norm": 0.044630300253629684,
|
| 17929 |
+
"learning_rate": 0.0012,
|
| 17930 |
+
"loss": 2.1907413005828857,
|
| 17931 |
+
"step": 5118
|
| 17932 |
+
},
|
| 17933 |
+
{
|
| 17934 |
+
"epoch": 0.26876640419947506,
|
| 17935 |
+
"grad_norm": 0.05549032241106033,
|
| 17936 |
+
"learning_rate": 0.0012,
|
| 17937 |
+
"loss": 2.3090739250183105,
|
| 17938 |
+
"step": 5120
|
| 17939 |
+
},
|
| 17940 |
+
{
|
| 17941 |
+
"epoch": 0.26887139107611546,
|
| 17942 |
+
"grad_norm": 0.056200530380010605,
|
| 17943 |
+
"learning_rate": 0.0012,
|
| 17944 |
+
"loss": 2.2689030170440674,
|
| 17945 |
+
"step": 5122
|
| 17946 |
+
},
|
| 17947 |
+
{
|
| 17948 |
+
"epoch": 0.2689763779527559,
|
| 17949 |
+
"grad_norm": 0.051823101937770844,
|
| 17950 |
+
"learning_rate": 0.0012,
|
| 17951 |
+
"loss": 2.253622055053711,
|
| 17952 |
+
"step": 5124
|
| 17953 |
+
},
|
| 17954 |
+
{
|
| 17955 |
+
"epoch": 0.2690813648293963,
|
| 17956 |
+
"grad_norm": 0.05246010795235634,
|
| 17957 |
+
"learning_rate": 0.0012,
|
| 17958 |
+
"loss": 2.2694437503814697,
|
| 17959 |
+
"step": 5126
|
| 17960 |
+
},
|
| 17961 |
+
{
|
| 17962 |
+
"epoch": 0.2691863517060367,
|
| 17963 |
+
"grad_norm": 0.04751601442694664,
|
| 17964 |
+
"learning_rate": 0.0012,
|
| 17965 |
+
"loss": 2.2180328369140625,
|
| 17966 |
+
"step": 5128
|
| 17967 |
+
},
|
| 17968 |
+
{
|
| 17969 |
+
"epoch": 0.2692913385826772,
|
| 17970 |
+
"grad_norm": 0.0462307445704937,
|
| 17971 |
+
"learning_rate": 0.0012,
|
| 17972 |
+
"loss": 2.260592222213745,
|
| 17973 |
+
"step": 5130
|
| 17974 |
+
},
|
| 17975 |
+
{
|
| 17976 |
+
"epoch": 0.2693963254593176,
|
| 17977 |
+
"grad_norm": 0.0397898405790329,
|
| 17978 |
+
"learning_rate": 0.0012,
|
| 17979 |
+
"loss": 2.2467007637023926,
|
| 17980 |
+
"step": 5132
|
| 17981 |
+
},
|
| 17982 |
+
{
|
| 17983 |
+
"epoch": 0.26950131233595803,
|
| 17984 |
+
"grad_norm": 0.04381628334522247,
|
| 17985 |
+
"learning_rate": 0.0012,
|
| 17986 |
+
"loss": 2.2451229095458984,
|
| 17987 |
+
"step": 5134
|
| 17988 |
+
},
|
| 17989 |
+
{
|
| 17990 |
+
"epoch": 0.26960629921259843,
|
| 17991 |
+
"grad_norm": 0.04376918449997902,
|
| 17992 |
+
"learning_rate": 0.0012,
|
| 17993 |
+
"loss": 2.2664287090301514,
|
| 17994 |
+
"step": 5136
|
| 17995 |
+
},
|
| 17996 |
+
{
|
| 17997 |
+
"epoch": 0.26971128608923883,
|
| 17998 |
+
"grad_norm": 0.04185127466917038,
|
| 17999 |
+
"learning_rate": 0.0012,
|
| 18000 |
+
"loss": 2.2027206420898438,
|
| 18001 |
+
"step": 5138
|
| 18002 |
+
},
|
| 18003 |
+
{
|
| 18004 |
+
"epoch": 0.2698162729658793,
|
| 18005 |
+
"grad_norm": 0.048498038202524185,
|
| 18006 |
+
"learning_rate": 0.0012,
|
| 18007 |
+
"loss": 2.222946882247925,
|
| 18008 |
+
"step": 5140
|
| 18009 |
+
},
|
| 18010 |
+
{
|
| 18011 |
+
"epoch": 0.2699212598425197,
|
| 18012 |
+
"grad_norm": 0.04271905496716499,
|
| 18013 |
+
"learning_rate": 0.0012,
|
| 18014 |
+
"loss": 2.252061128616333,
|
| 18015 |
+
"step": 5142
|
| 18016 |
+
},
|
| 18017 |
+
{
|
| 18018 |
+
"epoch": 0.2700262467191601,
|
| 18019 |
+
"grad_norm": 0.04319673404097557,
|
| 18020 |
+
"learning_rate": 0.0012,
|
| 18021 |
+
"loss": 2.295635461807251,
|
| 18022 |
+
"step": 5144
|
| 18023 |
+
},
|
| 18024 |
+
{
|
| 18025 |
+
"epoch": 0.27013123359580055,
|
| 18026 |
+
"grad_norm": 0.03982343524694443,
|
| 18027 |
+
"learning_rate": 0.0012,
|
| 18028 |
+
"loss": 2.214515209197998,
|
| 18029 |
+
"step": 5146
|
| 18030 |
+
},
|
| 18031 |
+
{
|
| 18032 |
+
"epoch": 0.27023622047244095,
|
| 18033 |
+
"grad_norm": 0.04607882350683212,
|
| 18034 |
+
"learning_rate": 0.0012,
|
| 18035 |
+
"loss": 2.3006198406219482,
|
| 18036 |
+
"step": 5148
|
| 18037 |
}
|
| 18038 |
],
|
| 18039 |
"logging_steps": 2,
|
|
|
|
| 18053 |
"attributes": {}
|
| 18054 |
}
|
| 18055 |
},
|
| 18056 |
+
"total_flos": 1.4029520818102014e+19,
|
| 18057 |
"train_batch_size": 32,
|
| 18058 |
"trial_name": null,
|
| 18059 |
"trial_params": null
|