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 15840, 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 2519929824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20ea5f7585b58037ef6766befaa0e3dd3972a5984d33bc8f660c150d4f7004e8
|
| 3 |
size 2519929824
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1263881876
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dde9090de2d5b851bbc1b8ac29ce36b96de7801304fef72c174b7beef82b289d
|
| 3 |
size 1263881876
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10233
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:467ab64b0f273bc5cf44f044fe5b2ba3231edd9607ffb9d3cf59c5e73c849ccd
|
| 3 |
size 10233
|
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": 3300,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -53170,6 +53170,2316 @@
|
|
| 53170 |
"learning_rate": 0.0002668686868686869,
|
| 53171 |
"loss": 3.026644229888916,
|
| 53172 |
"step": 15180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53173 |
}
|
| 53174 |
],
|
| 53175 |
"logging_steps": 2,
|
|
@@ -53189,7 +55499,7 @@
|
|
| 53189 |
"attributes": {}
|
| 53190 |
}
|
| 53191 |
},
|
| 53192 |
-
"total_flos": 3.
|
| 53193 |
"train_batch_size": 20,
|
| 53194 |
"trial_name": null,
|
| 53195 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.96,
|
| 6 |
"eval_steps": 3300,
|
| 7 |
+
"global_step": 15840,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 53170 |
"learning_rate": 0.0002668686868686869,
|
| 53171 |
"loss": 3.026644229888916,
|
| 53172 |
"step": 15180
|
| 53173 |
+
},
|
| 53174 |
+
{
|
| 53175 |
+
"epoch": 0.9201212121212121,
|
| 53176 |
+
"grad_norm": 0.047228019684553146,
|
| 53177 |
+
"learning_rate": 0.00026646464646464646,
|
| 53178 |
+
"loss": 2.9886648654937744,
|
| 53179 |
+
"step": 15182
|
| 53180 |
+
},
|
| 53181 |
+
{
|
| 53182 |
+
"epoch": 0.9202424242424242,
|
| 53183 |
+
"grad_norm": 0.04819478467106819,
|
| 53184 |
+
"learning_rate": 0.0002660606060606061,
|
| 53185 |
+
"loss": 2.9803049564361572,
|
| 53186 |
+
"step": 15184
|
| 53187 |
+
},
|
| 53188 |
+
{
|
| 53189 |
+
"epoch": 0.9203636363636364,
|
| 53190 |
+
"grad_norm": 0.05041540786623955,
|
| 53191 |
+
"learning_rate": 0.00026565656565656566,
|
| 53192 |
+
"loss": 2.9912827014923096,
|
| 53193 |
+
"step": 15186
|
| 53194 |
+
},
|
| 53195 |
+
{
|
| 53196 |
+
"epoch": 0.9204848484848485,
|
| 53197 |
+
"grad_norm": 0.05379606783390045,
|
| 53198 |
+
"learning_rate": 0.0002652525252525253,
|
| 53199 |
+
"loss": 3.0327024459838867,
|
| 53200 |
+
"step": 15188
|
| 53201 |
+
},
|
| 53202 |
+
{
|
| 53203 |
+
"epoch": 0.9206060606060606,
|
| 53204 |
+
"grad_norm": 0.04872296005487442,
|
| 53205 |
+
"learning_rate": 0.00026484848484848486,
|
| 53206 |
+
"loss": 3.034039258956909,
|
| 53207 |
+
"step": 15190
|
| 53208 |
+
},
|
| 53209 |
+
{
|
| 53210 |
+
"epoch": 0.9207272727272727,
|
| 53211 |
+
"grad_norm": 0.05528697744011879,
|
| 53212 |
+
"learning_rate": 0.00026444444444444443,
|
| 53213 |
+
"loss": 2.954509735107422,
|
| 53214 |
+
"step": 15192
|
| 53215 |
+
},
|
| 53216 |
+
{
|
| 53217 |
+
"epoch": 0.9208484848484848,
|
| 53218 |
+
"grad_norm": 0.049840137362480164,
|
| 53219 |
+
"learning_rate": 0.00026404040404040405,
|
| 53220 |
+
"loss": 3.013262987136841,
|
| 53221 |
+
"step": 15194
|
| 53222 |
+
},
|
| 53223 |
+
{
|
| 53224 |
+
"epoch": 0.920969696969697,
|
| 53225 |
+
"grad_norm": 0.04598007723689079,
|
| 53226 |
+
"learning_rate": 0.0002636363636363636,
|
| 53227 |
+
"loss": 3.0502090454101562,
|
| 53228 |
+
"step": 15196
|
| 53229 |
+
},
|
| 53230 |
+
{
|
| 53231 |
+
"epoch": 0.9210909090909091,
|
| 53232 |
+
"grad_norm": 0.04628410190343857,
|
| 53233 |
+
"learning_rate": 0.00026323232323232325,
|
| 53234 |
+
"loss": 3.0407967567443848,
|
| 53235 |
+
"step": 15198
|
| 53236 |
+
},
|
| 53237 |
+
{
|
| 53238 |
+
"epoch": 0.9212121212121213,
|
| 53239 |
+
"grad_norm": 0.05356813594698906,
|
| 53240 |
+
"learning_rate": 0.0002628282828282828,
|
| 53241 |
+
"loss": 3.0016002655029297,
|
| 53242 |
+
"step": 15200
|
| 53243 |
+
},
|
| 53244 |
+
{
|
| 53245 |
+
"epoch": 0.9213333333333333,
|
| 53246 |
+
"grad_norm": 0.05797095224261284,
|
| 53247 |
+
"learning_rate": 0.00026242424242424244,
|
| 53248 |
+
"loss": 2.997265100479126,
|
| 53249 |
+
"step": 15202
|
| 53250 |
+
},
|
| 53251 |
+
{
|
| 53252 |
+
"epoch": 0.9214545454545454,
|
| 53253 |
+
"grad_norm": 0.048060767352581024,
|
| 53254 |
+
"learning_rate": 0.00026202020202020207,
|
| 53255 |
+
"loss": 3.0207021236419678,
|
| 53256 |
+
"step": 15204
|
| 53257 |
+
},
|
| 53258 |
+
{
|
| 53259 |
+
"epoch": 0.9215757575757576,
|
| 53260 |
+
"grad_norm": 0.05373968556523323,
|
| 53261 |
+
"learning_rate": 0.00026161616161616164,
|
| 53262 |
+
"loss": 3.00209903717041,
|
| 53263 |
+
"step": 15206
|
| 53264 |
+
},
|
| 53265 |
+
{
|
| 53266 |
+
"epoch": 0.9216969696969697,
|
| 53267 |
+
"grad_norm": 0.052732985466718674,
|
| 53268 |
+
"learning_rate": 0.00026121212121212126,
|
| 53269 |
+
"loss": 3.001075506210327,
|
| 53270 |
+
"step": 15208
|
| 53271 |
+
},
|
| 53272 |
+
{
|
| 53273 |
+
"epoch": 0.9218181818181819,
|
| 53274 |
+
"grad_norm": 0.052968792617321014,
|
| 53275 |
+
"learning_rate": 0.00026080808080808084,
|
| 53276 |
+
"loss": 3.001727342605591,
|
| 53277 |
+
"step": 15210
|
| 53278 |
+
},
|
| 53279 |
+
{
|
| 53280 |
+
"epoch": 0.921939393939394,
|
| 53281 |
+
"grad_norm": 0.04739104583859444,
|
| 53282 |
+
"learning_rate": 0.0002604040404040404,
|
| 53283 |
+
"loss": 2.997205972671509,
|
| 53284 |
+
"step": 15212
|
| 53285 |
+
},
|
| 53286 |
+
{
|
| 53287 |
+
"epoch": 0.922060606060606,
|
| 53288 |
+
"grad_norm": 0.05933232232928276,
|
| 53289 |
+
"learning_rate": 0.00026000000000000003,
|
| 53290 |
+
"loss": 3.032184362411499,
|
| 53291 |
+
"step": 15214
|
| 53292 |
+
},
|
| 53293 |
+
{
|
| 53294 |
+
"epoch": 0.9221818181818182,
|
| 53295 |
+
"grad_norm": 0.04867679998278618,
|
| 53296 |
+
"learning_rate": 0.0002595959595959596,
|
| 53297 |
+
"loss": 3.0752642154693604,
|
| 53298 |
+
"step": 15216
|
| 53299 |
+
},
|
| 53300 |
+
{
|
| 53301 |
+
"epoch": 0.9223030303030303,
|
| 53302 |
+
"grad_norm": 0.04845423996448517,
|
| 53303 |
+
"learning_rate": 0.00025919191919191923,
|
| 53304 |
+
"loss": 3.0263795852661133,
|
| 53305 |
+
"step": 15218
|
| 53306 |
+
},
|
| 53307 |
+
{
|
| 53308 |
+
"epoch": 0.9224242424242424,
|
| 53309 |
+
"grad_norm": 0.05050051584839821,
|
| 53310 |
+
"learning_rate": 0.0002587878787878788,
|
| 53311 |
+
"loss": 3.0147366523742676,
|
| 53312 |
+
"step": 15220
|
| 53313 |
+
},
|
| 53314 |
+
{
|
| 53315 |
+
"epoch": 0.9225454545454546,
|
| 53316 |
+
"grad_norm": 0.04731815680861473,
|
| 53317 |
+
"learning_rate": 0.00025838383838383837,
|
| 53318 |
+
"loss": 3.06956148147583,
|
| 53319 |
+
"step": 15222
|
| 53320 |
+
},
|
| 53321 |
+
{
|
| 53322 |
+
"epoch": 0.9226666666666666,
|
| 53323 |
+
"grad_norm": 0.04742210730910301,
|
| 53324 |
+
"learning_rate": 0.000257979797979798,
|
| 53325 |
+
"loss": 2.99751353263855,
|
| 53326 |
+
"step": 15224
|
| 53327 |
+
},
|
| 53328 |
+
{
|
| 53329 |
+
"epoch": 0.9227878787878788,
|
| 53330 |
+
"grad_norm": 0.048089079558849335,
|
| 53331 |
+
"learning_rate": 0.00025757575757575756,
|
| 53332 |
+
"loss": 2.970702648162842,
|
| 53333 |
+
"step": 15226
|
| 53334 |
+
},
|
| 53335 |
+
{
|
| 53336 |
+
"epoch": 0.9229090909090909,
|
| 53337 |
+
"grad_norm": 0.049308281391859055,
|
| 53338 |
+
"learning_rate": 0.0002571717171717172,
|
| 53339 |
+
"loss": 3.0644397735595703,
|
| 53340 |
+
"step": 15228
|
| 53341 |
+
},
|
| 53342 |
+
{
|
| 53343 |
+
"epoch": 0.923030303030303,
|
| 53344 |
+
"grad_norm": 0.04764939472079277,
|
| 53345 |
+
"learning_rate": 0.00025676767676767676,
|
| 53346 |
+
"loss": 3.059779644012451,
|
| 53347 |
+
"step": 15230
|
| 53348 |
+
},
|
| 53349 |
+
{
|
| 53350 |
+
"epoch": 0.9231515151515152,
|
| 53351 |
+
"grad_norm": 0.04847784340381622,
|
| 53352 |
+
"learning_rate": 0.0002563636363636364,
|
| 53353 |
+
"loss": 3.0484306812286377,
|
| 53354 |
+
"step": 15232
|
| 53355 |
+
},
|
| 53356 |
+
{
|
| 53357 |
+
"epoch": 0.9232727272727272,
|
| 53358 |
+
"grad_norm": 0.0526236928999424,
|
| 53359 |
+
"learning_rate": 0.00025595959595959596,
|
| 53360 |
+
"loss": 3.0095198154449463,
|
| 53361 |
+
"step": 15234
|
| 53362 |
+
},
|
| 53363 |
+
{
|
| 53364 |
+
"epoch": 0.9233939393939394,
|
| 53365 |
+
"grad_norm": 0.05197611078619957,
|
| 53366 |
+
"learning_rate": 0.00025555555555555553,
|
| 53367 |
+
"loss": 3.085571050643921,
|
| 53368 |
+
"step": 15236
|
| 53369 |
+
},
|
| 53370 |
+
{
|
| 53371 |
+
"epoch": 0.9235151515151515,
|
| 53372 |
+
"grad_norm": 0.050345152616500854,
|
| 53373 |
+
"learning_rate": 0.0002551515151515152,
|
| 53374 |
+
"loss": 3.0545616149902344,
|
| 53375 |
+
"step": 15238
|
| 53376 |
+
},
|
| 53377 |
+
{
|
| 53378 |
+
"epoch": 0.9236363636363636,
|
| 53379 |
+
"grad_norm": 0.05184698477387428,
|
| 53380 |
+
"learning_rate": 0.0002547474747474748,
|
| 53381 |
+
"loss": 3.0053529739379883,
|
| 53382 |
+
"step": 15240
|
| 53383 |
+
},
|
| 53384 |
+
{
|
| 53385 |
+
"epoch": 0.9237575757575758,
|
| 53386 |
+
"grad_norm": 0.04677793011069298,
|
| 53387 |
+
"learning_rate": 0.00025434343434343435,
|
| 53388 |
+
"loss": 3.06418776512146,
|
| 53389 |
+
"step": 15242
|
| 53390 |
+
},
|
| 53391 |
+
{
|
| 53392 |
+
"epoch": 0.9238787878787879,
|
| 53393 |
+
"grad_norm": 0.048886727541685104,
|
| 53394 |
+
"learning_rate": 0.000253939393939394,
|
| 53395 |
+
"loss": 3.037677526473999,
|
| 53396 |
+
"step": 15244
|
| 53397 |
+
},
|
| 53398 |
+
{
|
| 53399 |
+
"epoch": 0.924,
|
| 53400 |
+
"grad_norm": 0.05041050538420677,
|
| 53401 |
+
"learning_rate": 0.00025353535353535354,
|
| 53402 |
+
"loss": 3.036999225616455,
|
| 53403 |
+
"step": 15246
|
| 53404 |
+
},
|
| 53405 |
+
{
|
| 53406 |
+
"epoch": 0.9241212121212121,
|
| 53407 |
+
"grad_norm": 0.048749301582574844,
|
| 53408 |
+
"learning_rate": 0.00025313131313131317,
|
| 53409 |
+
"loss": 3.015958786010742,
|
| 53410 |
+
"step": 15248
|
| 53411 |
+
},
|
| 53412 |
+
{
|
| 53413 |
+
"epoch": 0.9242424242424242,
|
| 53414 |
+
"grad_norm": 0.05030302703380585,
|
| 53415 |
+
"learning_rate": 0.00025272727272727274,
|
| 53416 |
+
"loss": 3.0140326023101807,
|
| 53417 |
+
"step": 15250
|
| 53418 |
+
},
|
| 53419 |
+
{
|
| 53420 |
+
"epoch": 0.9243636363636364,
|
| 53421 |
+
"grad_norm": 0.053868625313043594,
|
| 53422 |
+
"learning_rate": 0.00025232323232323236,
|
| 53423 |
+
"loss": 3.0658063888549805,
|
| 53424 |
+
"step": 15252
|
| 53425 |
+
},
|
| 53426 |
+
{
|
| 53427 |
+
"epoch": 0.9244848484848485,
|
| 53428 |
+
"grad_norm": 0.05038420110940933,
|
| 53429 |
+
"learning_rate": 0.00025191919191919194,
|
| 53430 |
+
"loss": 3.070720911026001,
|
| 53431 |
+
"step": 15254
|
| 53432 |
+
},
|
| 53433 |
+
{
|
| 53434 |
+
"epoch": 0.9246060606060607,
|
| 53435 |
+
"grad_norm": 0.047590795904397964,
|
| 53436 |
+
"learning_rate": 0.0002515151515151515,
|
| 53437 |
+
"loss": 3.056928873062134,
|
| 53438 |
+
"step": 15256
|
| 53439 |
+
},
|
| 53440 |
+
{
|
| 53441 |
+
"epoch": 0.9247272727272727,
|
| 53442 |
+
"grad_norm": 0.05170606076717377,
|
| 53443 |
+
"learning_rate": 0.00025111111111111113,
|
| 53444 |
+
"loss": 3.060220956802368,
|
| 53445 |
+
"step": 15258
|
| 53446 |
+
},
|
| 53447 |
+
{
|
| 53448 |
+
"epoch": 0.9248484848484848,
|
| 53449 |
+
"grad_norm": 0.05282248929142952,
|
| 53450 |
+
"learning_rate": 0.0002507070707070707,
|
| 53451 |
+
"loss": 3.0586512088775635,
|
| 53452 |
+
"step": 15260
|
| 53453 |
+
},
|
| 53454 |
+
{
|
| 53455 |
+
"epoch": 0.924969696969697,
|
| 53456 |
+
"grad_norm": 0.05099230259656906,
|
| 53457 |
+
"learning_rate": 0.0002503030303030303,
|
| 53458 |
+
"loss": 2.974452018737793,
|
| 53459 |
+
"step": 15262
|
| 53460 |
+
},
|
| 53461 |
+
{
|
| 53462 |
+
"epoch": 0.9250909090909091,
|
| 53463 |
+
"grad_norm": 0.04809005931019783,
|
| 53464 |
+
"learning_rate": 0.0002498989898989899,
|
| 53465 |
+
"loss": 3.0251190662384033,
|
| 53466 |
+
"step": 15264
|
| 53467 |
+
},
|
| 53468 |
+
{
|
| 53469 |
+
"epoch": 0.9252121212121213,
|
| 53470 |
+
"grad_norm": 0.04923873767256737,
|
| 53471 |
+
"learning_rate": 0.00024949494949494947,
|
| 53472 |
+
"loss": 3.0753602981567383,
|
| 53473 |
+
"step": 15266
|
| 53474 |
+
},
|
| 53475 |
+
{
|
| 53476 |
+
"epoch": 0.9253333333333333,
|
| 53477 |
+
"grad_norm": 0.047278109937906265,
|
| 53478 |
+
"learning_rate": 0.0002490909090909091,
|
| 53479 |
+
"loss": 3.0312376022338867,
|
| 53480 |
+
"step": 15268
|
| 53481 |
+
},
|
| 53482 |
+
{
|
| 53483 |
+
"epoch": 0.9254545454545454,
|
| 53484 |
+
"grad_norm": 0.053930480033159256,
|
| 53485 |
+
"learning_rate": 0.00024868686868686866,
|
| 53486 |
+
"loss": 3.020648956298828,
|
| 53487 |
+
"step": 15270
|
| 53488 |
+
},
|
| 53489 |
+
{
|
| 53490 |
+
"epoch": 0.9255757575757576,
|
| 53491 |
+
"grad_norm": 0.049685489386320114,
|
| 53492 |
+
"learning_rate": 0.0002482828282828283,
|
| 53493 |
+
"loss": 2.998873233795166,
|
| 53494 |
+
"step": 15272
|
| 53495 |
+
},
|
| 53496 |
+
{
|
| 53497 |
+
"epoch": 0.9256969696969697,
|
| 53498 |
+
"grad_norm": 0.05520882084965706,
|
| 53499 |
+
"learning_rate": 0.0002478787878787879,
|
| 53500 |
+
"loss": 3.058461904525757,
|
| 53501 |
+
"step": 15274
|
| 53502 |
+
},
|
| 53503 |
+
{
|
| 53504 |
+
"epoch": 0.9258181818181819,
|
| 53505 |
+
"grad_norm": 0.04783989489078522,
|
| 53506 |
+
"learning_rate": 0.0002474747474747475,
|
| 53507 |
+
"loss": 2.9944565296173096,
|
| 53508 |
+
"step": 15276
|
| 53509 |
+
},
|
| 53510 |
+
{
|
| 53511 |
+
"epoch": 0.925939393939394,
|
| 53512 |
+
"grad_norm": 0.05035402253270149,
|
| 53513 |
+
"learning_rate": 0.0002470707070707071,
|
| 53514 |
+
"loss": 2.998457670211792,
|
| 53515 |
+
"step": 15278
|
| 53516 |
+
},
|
| 53517 |
+
{
|
| 53518 |
+
"epoch": 0.926060606060606,
|
| 53519 |
+
"grad_norm": 0.04756399616599083,
|
| 53520 |
+
"learning_rate": 0.0002466666666666667,
|
| 53521 |
+
"loss": 3.059016704559326,
|
| 53522 |
+
"step": 15280
|
| 53523 |
+
},
|
| 53524 |
+
{
|
| 53525 |
+
"epoch": 0.9261818181818182,
|
| 53526 |
+
"grad_norm": 0.046713534742593765,
|
| 53527 |
+
"learning_rate": 0.0002462626262626263,
|
| 53528 |
+
"loss": 3.0394210815429688,
|
| 53529 |
+
"step": 15282
|
| 53530 |
+
},
|
| 53531 |
+
{
|
| 53532 |
+
"epoch": 0.9263030303030303,
|
| 53533 |
+
"grad_norm": 0.04686173424124718,
|
| 53534 |
+
"learning_rate": 0.0002458585858585859,
|
| 53535 |
+
"loss": 3.045168399810791,
|
| 53536 |
+
"step": 15284
|
| 53537 |
+
},
|
| 53538 |
+
{
|
| 53539 |
+
"epoch": 0.9264242424242424,
|
| 53540 |
+
"grad_norm": 0.047304607927799225,
|
| 53541 |
+
"learning_rate": 0.00024545454545454545,
|
| 53542 |
+
"loss": 3.0148980617523193,
|
| 53543 |
+
"step": 15286
|
| 53544 |
+
},
|
| 53545 |
+
{
|
| 53546 |
+
"epoch": 0.9265454545454546,
|
| 53547 |
+
"grad_norm": 0.04716654494404793,
|
| 53548 |
+
"learning_rate": 0.00024505050505050507,
|
| 53549 |
+
"loss": 3.025423765182495,
|
| 53550 |
+
"step": 15288
|
| 53551 |
+
},
|
| 53552 |
+
{
|
| 53553 |
+
"epoch": 0.9266666666666666,
|
| 53554 |
+
"grad_norm": 0.04873797297477722,
|
| 53555 |
+
"learning_rate": 0.00024464646464646464,
|
| 53556 |
+
"loss": 3.0100975036621094,
|
| 53557 |
+
"step": 15290
|
| 53558 |
+
},
|
| 53559 |
+
{
|
| 53560 |
+
"epoch": 0.9267878787878788,
|
| 53561 |
+
"grad_norm": 0.0538412444293499,
|
| 53562 |
+
"learning_rate": 0.00024424242424242427,
|
| 53563 |
+
"loss": 2.9873123168945312,
|
| 53564 |
+
"step": 15292
|
| 53565 |
+
},
|
| 53566 |
+
{
|
| 53567 |
+
"epoch": 0.9269090909090909,
|
| 53568 |
+
"grad_norm": 0.0496443472802639,
|
| 53569 |
+
"learning_rate": 0.00024383838383838384,
|
| 53570 |
+
"loss": 3.0609822273254395,
|
| 53571 |
+
"step": 15294
|
| 53572 |
+
},
|
| 53573 |
+
{
|
| 53574 |
+
"epoch": 0.927030303030303,
|
| 53575 |
+
"grad_norm": 0.063149094581604,
|
| 53576 |
+
"learning_rate": 0.00024343434343434344,
|
| 53577 |
+
"loss": 3.008270502090454,
|
| 53578 |
+
"step": 15296
|
| 53579 |
+
},
|
| 53580 |
+
{
|
| 53581 |
+
"epoch": 0.9271515151515152,
|
| 53582 |
+
"grad_norm": 0.05574154853820801,
|
| 53583 |
+
"learning_rate": 0.00024303030303030304,
|
| 53584 |
+
"loss": 3.0382161140441895,
|
| 53585 |
+
"step": 15298
|
| 53586 |
+
},
|
| 53587 |
+
{
|
| 53588 |
+
"epoch": 0.9272727272727272,
|
| 53589 |
+
"grad_norm": 0.05069867521524429,
|
| 53590 |
+
"learning_rate": 0.00024262626262626263,
|
| 53591 |
+
"loss": 3.023195266723633,
|
| 53592 |
+
"step": 15300
|
| 53593 |
+
},
|
| 53594 |
+
{
|
| 53595 |
+
"epoch": 0.9273939393939394,
|
| 53596 |
+
"grad_norm": 0.048660460859537125,
|
| 53597 |
+
"learning_rate": 0.0002422222222222222,
|
| 53598 |
+
"loss": 3.0100245475769043,
|
| 53599 |
+
"step": 15302
|
| 53600 |
+
},
|
| 53601 |
+
{
|
| 53602 |
+
"epoch": 0.9275151515151515,
|
| 53603 |
+
"grad_norm": 0.04848002642393112,
|
| 53604 |
+
"learning_rate": 0.0002418181818181818,
|
| 53605 |
+
"loss": 3.0627706050872803,
|
| 53606 |
+
"step": 15304
|
| 53607 |
+
},
|
| 53608 |
+
{
|
| 53609 |
+
"epoch": 0.9276363636363636,
|
| 53610 |
+
"grad_norm": 0.04914858564734459,
|
| 53611 |
+
"learning_rate": 0.0002414141414141414,
|
| 53612 |
+
"loss": 3.026715040206909,
|
| 53613 |
+
"step": 15306
|
| 53614 |
+
},
|
| 53615 |
+
{
|
| 53616 |
+
"epoch": 0.9277575757575758,
|
| 53617 |
+
"grad_norm": 0.049361877143383026,
|
| 53618 |
+
"learning_rate": 0.00024101010101010105,
|
| 53619 |
+
"loss": 3.0934410095214844,
|
| 53620 |
+
"step": 15308
|
| 53621 |
+
},
|
| 53622 |
+
{
|
| 53623 |
+
"epoch": 0.9278787878787879,
|
| 53624 |
+
"grad_norm": 0.048982419073581696,
|
| 53625 |
+
"learning_rate": 0.00024060606060606062,
|
| 53626 |
+
"loss": 3.031724214553833,
|
| 53627 |
+
"step": 15310
|
| 53628 |
+
},
|
| 53629 |
+
{
|
| 53630 |
+
"epoch": 0.928,
|
| 53631 |
+
"grad_norm": 0.04893830418586731,
|
| 53632 |
+
"learning_rate": 0.00024020202020202022,
|
| 53633 |
+
"loss": 3.046769380569458,
|
| 53634 |
+
"step": 15312
|
| 53635 |
+
},
|
| 53636 |
+
{
|
| 53637 |
+
"epoch": 0.9281212121212121,
|
| 53638 |
+
"grad_norm": 0.048483893275260925,
|
| 53639 |
+
"learning_rate": 0.00023979797979797982,
|
| 53640 |
+
"loss": 3.0229108333587646,
|
| 53641 |
+
"step": 15314
|
| 53642 |
+
},
|
| 53643 |
+
{
|
| 53644 |
+
"epoch": 0.9282424242424242,
|
| 53645 |
+
"grad_norm": 0.04734852537512779,
|
| 53646 |
+
"learning_rate": 0.00023939393939393942,
|
| 53647 |
+
"loss": 3.0378520488739014,
|
| 53648 |
+
"step": 15316
|
| 53649 |
+
},
|
| 53650 |
+
{
|
| 53651 |
+
"epoch": 0.9283636363636364,
|
| 53652 |
+
"grad_norm": 0.05064778029918671,
|
| 53653 |
+
"learning_rate": 0.00023898989898989901,
|
| 53654 |
+
"loss": 3.0349087715148926,
|
| 53655 |
+
"step": 15318
|
| 53656 |
+
},
|
| 53657 |
+
{
|
| 53658 |
+
"epoch": 0.9284848484848485,
|
| 53659 |
+
"grad_norm": 0.048299457877874374,
|
| 53660 |
+
"learning_rate": 0.0002385858585858586,
|
| 53661 |
+
"loss": 3.02449107170105,
|
| 53662 |
+
"step": 15320
|
| 53663 |
+
},
|
| 53664 |
+
{
|
| 53665 |
+
"epoch": 0.9286060606060607,
|
| 53666 |
+
"grad_norm": 0.054908037185668945,
|
| 53667 |
+
"learning_rate": 0.00023818181818181818,
|
| 53668 |
+
"loss": 3.0441524982452393,
|
| 53669 |
+
"step": 15322
|
| 53670 |
+
},
|
| 53671 |
+
{
|
| 53672 |
+
"epoch": 0.9287272727272727,
|
| 53673 |
+
"grad_norm": 0.057252589613199234,
|
| 53674 |
+
"learning_rate": 0.00023777777777777778,
|
| 53675 |
+
"loss": 3.018800973892212,
|
| 53676 |
+
"step": 15324
|
| 53677 |
+
},
|
| 53678 |
+
{
|
| 53679 |
+
"epoch": 0.9288484848484848,
|
| 53680 |
+
"grad_norm": 0.04773838818073273,
|
| 53681 |
+
"learning_rate": 0.00023737373737373738,
|
| 53682 |
+
"loss": 3.0674197673797607,
|
| 53683 |
+
"step": 15326
|
| 53684 |
+
},
|
| 53685 |
+
{
|
| 53686 |
+
"epoch": 0.928969696969697,
|
| 53687 |
+
"grad_norm": 0.05324708670377731,
|
| 53688 |
+
"learning_rate": 0.00023696969696969698,
|
| 53689 |
+
"loss": 3.025228500366211,
|
| 53690 |
+
"step": 15328
|
| 53691 |
+
},
|
| 53692 |
+
{
|
| 53693 |
+
"epoch": 0.9290909090909091,
|
| 53694 |
+
"grad_norm": 0.052584752440452576,
|
| 53695 |
+
"learning_rate": 0.00023656565656565657,
|
| 53696 |
+
"loss": 3.0662190914154053,
|
| 53697 |
+
"step": 15330
|
| 53698 |
+
},
|
| 53699 |
+
{
|
| 53700 |
+
"epoch": 0.9292121212121213,
|
| 53701 |
+
"grad_norm": 0.04914461448788643,
|
| 53702 |
+
"learning_rate": 0.00023616161616161617,
|
| 53703 |
+
"loss": 3.0336921215057373,
|
| 53704 |
+
"step": 15332
|
| 53705 |
+
},
|
| 53706 |
+
{
|
| 53707 |
+
"epoch": 0.9293333333333333,
|
| 53708 |
+
"grad_norm": 0.04678596928715706,
|
| 53709 |
+
"learning_rate": 0.00023575757575757574,
|
| 53710 |
+
"loss": 3.0516581535339355,
|
| 53711 |
+
"step": 15334
|
| 53712 |
+
},
|
| 53713 |
+
{
|
| 53714 |
+
"epoch": 0.9294545454545454,
|
| 53715 |
+
"grad_norm": 0.05105559900403023,
|
| 53716 |
+
"learning_rate": 0.00023535353535353534,
|
| 53717 |
+
"loss": 3.0353193283081055,
|
| 53718 |
+
"step": 15336
|
| 53719 |
+
},
|
| 53720 |
+
{
|
| 53721 |
+
"epoch": 0.9295757575757576,
|
| 53722 |
+
"grad_norm": 0.05281532555818558,
|
| 53723 |
+
"learning_rate": 0.00023494949494949494,
|
| 53724 |
+
"loss": 3.0382118225097656,
|
| 53725 |
+
"step": 15338
|
| 53726 |
+
},
|
| 53727 |
+
{
|
| 53728 |
+
"epoch": 0.9296969696969697,
|
| 53729 |
+
"grad_norm": 0.0475974939763546,
|
| 53730 |
+
"learning_rate": 0.00023454545454545454,
|
| 53731 |
+
"loss": 3.005657434463501,
|
| 53732 |
+
"step": 15340
|
| 53733 |
+
},
|
| 53734 |
+
{
|
| 53735 |
+
"epoch": 0.9298181818181818,
|
| 53736 |
+
"grad_norm": 0.04936264082789421,
|
| 53737 |
+
"learning_rate": 0.00023414141414141416,
|
| 53738 |
+
"loss": 3.044907808303833,
|
| 53739 |
+
"step": 15342
|
| 53740 |
+
},
|
| 53741 |
+
{
|
| 53742 |
+
"epoch": 0.929939393939394,
|
| 53743 |
+
"grad_norm": 0.048163238912820816,
|
| 53744 |
+
"learning_rate": 0.00023373737373737376,
|
| 53745 |
+
"loss": 3.0071632862091064,
|
| 53746 |
+
"step": 15344
|
| 53747 |
+
},
|
| 53748 |
+
{
|
| 53749 |
+
"epoch": 0.930060606060606,
|
| 53750 |
+
"grad_norm": 0.05633603408932686,
|
| 53751 |
+
"learning_rate": 0.00023333333333333336,
|
| 53752 |
+
"loss": 3.020859956741333,
|
| 53753 |
+
"step": 15346
|
| 53754 |
+
},
|
| 53755 |
+
{
|
| 53756 |
+
"epoch": 0.9301818181818182,
|
| 53757 |
+
"grad_norm": 0.05004741996526718,
|
| 53758 |
+
"learning_rate": 0.00023292929292929296,
|
| 53759 |
+
"loss": 3.0235211849212646,
|
| 53760 |
+
"step": 15348
|
| 53761 |
+
},
|
| 53762 |
+
{
|
| 53763 |
+
"epoch": 0.9303030303030303,
|
| 53764 |
+
"grad_norm": 0.049934227019548416,
|
| 53765 |
+
"learning_rate": 0.00023252525252525255,
|
| 53766 |
+
"loss": 3.036956548690796,
|
| 53767 |
+
"step": 15350
|
| 53768 |
+
},
|
| 53769 |
+
{
|
| 53770 |
+
"epoch": 0.9304242424242424,
|
| 53771 |
+
"grad_norm": 0.049190279096364975,
|
| 53772 |
+
"learning_rate": 0.00023212121212121215,
|
| 53773 |
+
"loss": 3.025552749633789,
|
| 53774 |
+
"step": 15352
|
| 53775 |
+
},
|
| 53776 |
+
{
|
| 53777 |
+
"epoch": 0.9305454545454546,
|
| 53778 |
+
"grad_norm": 0.05435819551348686,
|
| 53779 |
+
"learning_rate": 0.00023171717171717172,
|
| 53780 |
+
"loss": 2.99115252494812,
|
| 53781 |
+
"step": 15354
|
| 53782 |
+
},
|
| 53783 |
+
{
|
| 53784 |
+
"epoch": 0.9306666666666666,
|
| 53785 |
+
"grad_norm": 0.04900391399860382,
|
| 53786 |
+
"learning_rate": 0.00023131313131313132,
|
| 53787 |
+
"loss": 3.0508484840393066,
|
| 53788 |
+
"step": 15356
|
| 53789 |
+
},
|
| 53790 |
+
{
|
| 53791 |
+
"epoch": 0.9307878787878788,
|
| 53792 |
+
"grad_norm": 0.051562950015068054,
|
| 53793 |
+
"learning_rate": 0.00023090909090909092,
|
| 53794 |
+
"loss": 3.045416831970215,
|
| 53795 |
+
"step": 15358
|
| 53796 |
+
},
|
| 53797 |
+
{
|
| 53798 |
+
"epoch": 0.9309090909090909,
|
| 53799 |
+
"grad_norm": 0.04933543503284454,
|
| 53800 |
+
"learning_rate": 0.00023050505050505052,
|
| 53801 |
+
"loss": 3.006898880004883,
|
| 53802 |
+
"step": 15360
|
| 53803 |
+
},
|
| 53804 |
+
{
|
| 53805 |
+
"epoch": 0.931030303030303,
|
| 53806 |
+
"grad_norm": 0.05090056359767914,
|
| 53807 |
+
"learning_rate": 0.00023010101010101011,
|
| 53808 |
+
"loss": 2.9832661151885986,
|
| 53809 |
+
"step": 15362
|
| 53810 |
+
},
|
| 53811 |
+
{
|
| 53812 |
+
"epoch": 0.9311515151515152,
|
| 53813 |
+
"grad_norm": 0.04939740151166916,
|
| 53814 |
+
"learning_rate": 0.0002296969696969697,
|
| 53815 |
+
"loss": 3.0564041137695312,
|
| 53816 |
+
"step": 15364
|
| 53817 |
+
},
|
| 53818 |
+
{
|
| 53819 |
+
"epoch": 0.9312727272727273,
|
| 53820 |
+
"grad_norm": 0.05001511052250862,
|
| 53821 |
+
"learning_rate": 0.00022929292929292928,
|
| 53822 |
+
"loss": 3.053158760070801,
|
| 53823 |
+
"step": 15366
|
| 53824 |
+
},
|
| 53825 |
+
{
|
| 53826 |
+
"epoch": 0.9313939393939394,
|
| 53827 |
+
"grad_norm": 0.05077577754855156,
|
| 53828 |
+
"learning_rate": 0.00022888888888888888,
|
| 53829 |
+
"loss": 2.972395896911621,
|
| 53830 |
+
"step": 15368
|
| 53831 |
+
},
|
| 53832 |
+
{
|
| 53833 |
+
"epoch": 0.9315151515151515,
|
| 53834 |
+
"grad_norm": 0.04800216108560562,
|
| 53835 |
+
"learning_rate": 0.00022848484848484848,
|
| 53836 |
+
"loss": 3.0438199043273926,
|
| 53837 |
+
"step": 15370
|
| 53838 |
+
},
|
| 53839 |
+
{
|
| 53840 |
+
"epoch": 0.9316363636363636,
|
| 53841 |
+
"grad_norm": 0.05949001759290695,
|
| 53842 |
+
"learning_rate": 0.00022808080808080808,
|
| 53843 |
+
"loss": 3.070096731185913,
|
| 53844 |
+
"step": 15372
|
| 53845 |
+
},
|
| 53846 |
+
{
|
| 53847 |
+
"epoch": 0.9317575757575758,
|
| 53848 |
+
"grad_norm": 0.048368051648139954,
|
| 53849 |
+
"learning_rate": 0.00022767676767676767,
|
| 53850 |
+
"loss": 3.044050455093384,
|
| 53851 |
+
"step": 15374
|
| 53852 |
+
},
|
| 53853 |
+
{
|
| 53854 |
+
"epoch": 0.9318787878787879,
|
| 53855 |
+
"grad_norm": 0.055126748979091644,
|
| 53856 |
+
"learning_rate": 0.0002272727272727273,
|
| 53857 |
+
"loss": 2.989521026611328,
|
| 53858 |
+
"step": 15376
|
| 53859 |
+
},
|
| 53860 |
+
{
|
| 53861 |
+
"epoch": 0.932,
|
| 53862 |
+
"grad_norm": 0.049378860741853714,
|
| 53863 |
+
"learning_rate": 0.0002268686868686869,
|
| 53864 |
+
"loss": 3.0819180011749268,
|
| 53865 |
+
"step": 15378
|
| 53866 |
+
},
|
| 53867 |
+
{
|
| 53868 |
+
"epoch": 0.9321212121212121,
|
| 53869 |
+
"grad_norm": 0.052349235862493515,
|
| 53870 |
+
"learning_rate": 0.0002264646464646465,
|
| 53871 |
+
"loss": 3.013503074645996,
|
| 53872 |
+
"step": 15380
|
| 53873 |
+
},
|
| 53874 |
+
{
|
| 53875 |
+
"epoch": 0.9322424242424242,
|
| 53876 |
+
"grad_norm": 0.04820221662521362,
|
| 53877 |
+
"learning_rate": 0.0002260606060606061,
|
| 53878 |
+
"loss": 3.0219874382019043,
|
| 53879 |
+
"step": 15382
|
| 53880 |
+
},
|
| 53881 |
+
{
|
| 53882 |
+
"epoch": 0.9323636363636364,
|
| 53883 |
+
"grad_norm": 0.05067289620637894,
|
| 53884 |
+
"learning_rate": 0.00022565656565656566,
|
| 53885 |
+
"loss": 3.045125961303711,
|
| 53886 |
+
"step": 15384
|
| 53887 |
+
},
|
| 53888 |
+
{
|
| 53889 |
+
"epoch": 0.9324848484848485,
|
| 53890 |
+
"grad_norm": 0.048089075833559036,
|
| 53891 |
+
"learning_rate": 0.00022525252525252526,
|
| 53892 |
+
"loss": 3.0080020427703857,
|
| 53893 |
+
"step": 15386
|
| 53894 |
+
},
|
| 53895 |
+
{
|
| 53896 |
+
"epoch": 0.9326060606060607,
|
| 53897 |
+
"grad_norm": 0.052010297775268555,
|
| 53898 |
+
"learning_rate": 0.00022484848484848486,
|
| 53899 |
+
"loss": 3.0249948501586914,
|
| 53900 |
+
"step": 15388
|
| 53901 |
+
},
|
| 53902 |
+
{
|
| 53903 |
+
"epoch": 0.9327272727272727,
|
| 53904 |
+
"grad_norm": 0.049142975360155106,
|
| 53905 |
+
"learning_rate": 0.00022444444444444446,
|
| 53906 |
+
"loss": 3.065917730331421,
|
| 53907 |
+
"step": 15390
|
| 53908 |
+
},
|
| 53909 |
+
{
|
| 53910 |
+
"epoch": 0.9328484848484848,
|
| 53911 |
+
"grad_norm": 0.046916522085666656,
|
| 53912 |
+
"learning_rate": 0.00022404040404040406,
|
| 53913 |
+
"loss": 3.052931785583496,
|
| 53914 |
+
"step": 15392
|
| 53915 |
+
},
|
| 53916 |
+
{
|
| 53917 |
+
"epoch": 0.932969696969697,
|
| 53918 |
+
"grad_norm": 0.04994691535830498,
|
| 53919 |
+
"learning_rate": 0.00022363636363636365,
|
| 53920 |
+
"loss": 3.014647960662842,
|
| 53921 |
+
"step": 15394
|
| 53922 |
+
},
|
| 53923 |
+
{
|
| 53924 |
+
"epoch": 0.9330909090909091,
|
| 53925 |
+
"grad_norm": 0.04775870218873024,
|
| 53926 |
+
"learning_rate": 0.00022323232323232322,
|
| 53927 |
+
"loss": 3.017942190170288,
|
| 53928 |
+
"step": 15396
|
| 53929 |
+
},
|
| 53930 |
+
{
|
| 53931 |
+
"epoch": 0.9332121212121212,
|
| 53932 |
+
"grad_norm": 0.04726095125079155,
|
| 53933 |
+
"learning_rate": 0.00022282828282828282,
|
| 53934 |
+
"loss": 3.0403971672058105,
|
| 53935 |
+
"step": 15398
|
| 53936 |
+
},
|
| 53937 |
+
{
|
| 53938 |
+
"epoch": 0.9333333333333333,
|
| 53939 |
+
"grad_norm": 0.04900322109460831,
|
| 53940 |
+
"learning_rate": 0.00022242424242424242,
|
| 53941 |
+
"loss": 2.9968631267547607,
|
| 53942 |
+
"step": 15400
|
| 53943 |
+
},
|
| 53944 |
+
{
|
| 53945 |
+
"epoch": 0.9334545454545454,
|
| 53946 |
+
"grad_norm": 0.049017518758773804,
|
| 53947 |
+
"learning_rate": 0.00022202020202020202,
|
| 53948 |
+
"loss": 3.014045476913452,
|
| 53949 |
+
"step": 15402
|
| 53950 |
+
},
|
| 53951 |
+
{
|
| 53952 |
+
"epoch": 0.9335757575757576,
|
| 53953 |
+
"grad_norm": 0.051660433411598206,
|
| 53954 |
+
"learning_rate": 0.00022161616161616162,
|
| 53955 |
+
"loss": 3.028594732284546,
|
| 53956 |
+
"step": 15404
|
| 53957 |
+
},
|
| 53958 |
+
{
|
| 53959 |
+
"epoch": 0.9336969696969697,
|
| 53960 |
+
"grad_norm": 0.050443023443222046,
|
| 53961 |
+
"learning_rate": 0.00022121212121212121,
|
| 53962 |
+
"loss": 3.022115707397461,
|
| 53963 |
+
"step": 15406
|
| 53964 |
+
},
|
| 53965 |
+
{
|
| 53966 |
+
"epoch": 0.9338181818181818,
|
| 53967 |
+
"grad_norm": 0.058351535350084305,
|
| 53968 |
+
"learning_rate": 0.00022080808080808078,
|
| 53969 |
+
"loss": 3.019472599029541,
|
| 53970 |
+
"step": 15408
|
| 53971 |
+
},
|
| 53972 |
+
{
|
| 53973 |
+
"epoch": 0.933939393939394,
|
| 53974 |
+
"grad_norm": 0.05187256634235382,
|
| 53975 |
+
"learning_rate": 0.00022040404040404044,
|
| 53976 |
+
"loss": 3.0418455600738525,
|
| 53977 |
+
"step": 15410
|
| 53978 |
+
},
|
| 53979 |
+
{
|
| 53980 |
+
"epoch": 0.934060606060606,
|
| 53981 |
+
"grad_norm": 0.06027960032224655,
|
| 53982 |
+
"learning_rate": 0.00022000000000000003,
|
| 53983 |
+
"loss": 3.056389331817627,
|
| 53984 |
+
"step": 15412
|
| 53985 |
+
},
|
| 53986 |
+
{
|
| 53987 |
+
"epoch": 0.9341818181818182,
|
| 53988 |
+
"grad_norm": 0.05715470016002655,
|
| 53989 |
+
"learning_rate": 0.00021959595959595963,
|
| 53990 |
+
"loss": 3.0256123542785645,
|
| 53991 |
+
"step": 15414
|
| 53992 |
+
},
|
| 53993 |
+
{
|
| 53994 |
+
"epoch": 0.9343030303030303,
|
| 53995 |
+
"grad_norm": 0.057363491505384445,
|
| 53996 |
+
"learning_rate": 0.0002191919191919192,
|
| 53997 |
+
"loss": 3.0516445636749268,
|
| 53998 |
+
"step": 15416
|
| 53999 |
+
},
|
| 54000 |
+
{
|
| 54001 |
+
"epoch": 0.9344242424242424,
|
| 54002 |
+
"grad_norm": 0.07863470911979675,
|
| 54003 |
+
"learning_rate": 0.0002187878787878788,
|
| 54004 |
+
"loss": 3.014742374420166,
|
| 54005 |
+
"step": 15418
|
| 54006 |
+
},
|
| 54007 |
+
{
|
| 54008 |
+
"epoch": 0.9345454545454546,
|
| 54009 |
+
"grad_norm": 0.05683382973074913,
|
| 54010 |
+
"learning_rate": 0.0002183838383838384,
|
| 54011 |
+
"loss": 3.038984537124634,
|
| 54012 |
+
"step": 15420
|
| 54013 |
+
},
|
| 54014 |
+
{
|
| 54015 |
+
"epoch": 0.9346666666666666,
|
| 54016 |
+
"grad_norm": 0.05901367589831352,
|
| 54017 |
+
"learning_rate": 0.000217979797979798,
|
| 54018 |
+
"loss": 2.999816656112671,
|
| 54019 |
+
"step": 15422
|
| 54020 |
+
},
|
| 54021 |
+
{
|
| 54022 |
+
"epoch": 0.9347878787878788,
|
| 54023 |
+
"grad_norm": 0.051490239799022675,
|
| 54024 |
+
"learning_rate": 0.0002175757575757576,
|
| 54025 |
+
"loss": 3.0703554153442383,
|
| 54026 |
+
"step": 15424
|
| 54027 |
+
},
|
| 54028 |
+
{
|
| 54029 |
+
"epoch": 0.9349090909090909,
|
| 54030 |
+
"grad_norm": 0.048576731234788895,
|
| 54031 |
+
"learning_rate": 0.0002171717171717172,
|
| 54032 |
+
"loss": 2.999354600906372,
|
| 54033 |
+
"step": 15426
|
| 54034 |
+
},
|
| 54035 |
+
{
|
| 54036 |
+
"epoch": 0.935030303030303,
|
| 54037 |
+
"grad_norm": 0.057345952838659286,
|
| 54038 |
+
"learning_rate": 0.00021676767676767676,
|
| 54039 |
+
"loss": 3.001673460006714,
|
| 54040 |
+
"step": 15428
|
| 54041 |
+
},
|
| 54042 |
+
{
|
| 54043 |
+
"epoch": 0.9351515151515152,
|
| 54044 |
+
"grad_norm": 0.0488053634762764,
|
| 54045 |
+
"learning_rate": 0.00021636363636363636,
|
| 54046 |
+
"loss": 3.0274736881256104,
|
| 54047 |
+
"step": 15430
|
| 54048 |
+
},
|
| 54049 |
+
{
|
| 54050 |
+
"epoch": 0.9352727272727273,
|
| 54051 |
+
"grad_norm": 0.061473146080970764,
|
| 54052 |
+
"learning_rate": 0.00021595959595959596,
|
| 54053 |
+
"loss": 3.0239806175231934,
|
| 54054 |
+
"step": 15432
|
| 54055 |
+
},
|
| 54056 |
+
{
|
| 54057 |
+
"epoch": 0.9353939393939394,
|
| 54058 |
+
"grad_norm": 0.04858576878905296,
|
| 54059 |
+
"learning_rate": 0.00021555555555555556,
|
| 54060 |
+
"loss": 3.029201030731201,
|
| 54061 |
+
"step": 15434
|
| 54062 |
+
},
|
| 54063 |
+
{
|
| 54064 |
+
"epoch": 0.9355151515151515,
|
| 54065 |
+
"grad_norm": 0.056817322969436646,
|
| 54066 |
+
"learning_rate": 0.00021515151515151516,
|
| 54067 |
+
"loss": 3.02553653717041,
|
| 54068 |
+
"step": 15436
|
| 54069 |
+
},
|
| 54070 |
+
{
|
| 54071 |
+
"epoch": 0.9356363636363636,
|
| 54072 |
+
"grad_norm": 0.0488731786608696,
|
| 54073 |
+
"learning_rate": 0.00021474747474747475,
|
| 54074 |
+
"loss": 3.06377911567688,
|
| 54075 |
+
"step": 15438
|
| 54076 |
+
},
|
| 54077 |
+
{
|
| 54078 |
+
"epoch": 0.9357575757575758,
|
| 54079 |
+
"grad_norm": 0.059253159910440445,
|
| 54080 |
+
"learning_rate": 0.00021434343434343432,
|
| 54081 |
+
"loss": 3.0484466552734375,
|
| 54082 |
+
"step": 15440
|
| 54083 |
+
},
|
| 54084 |
+
{
|
| 54085 |
+
"epoch": 0.9358787878787879,
|
| 54086 |
+
"grad_norm": 0.04934869706630707,
|
| 54087 |
+
"learning_rate": 0.00021393939393939392,
|
| 54088 |
+
"loss": 3.0966053009033203,
|
| 54089 |
+
"step": 15442
|
| 54090 |
+
},
|
| 54091 |
+
{
|
| 54092 |
+
"epoch": 0.936,
|
| 54093 |
+
"grad_norm": 0.05286795273423195,
|
| 54094 |
+
"learning_rate": 0.00021353535353535357,
|
| 54095 |
+
"loss": 3.067439317703247,
|
| 54096 |
+
"step": 15444
|
| 54097 |
+
},
|
| 54098 |
+
{
|
| 54099 |
+
"epoch": 0.9361212121212121,
|
| 54100 |
+
"grad_norm": 0.04865637049078941,
|
| 54101 |
+
"learning_rate": 0.00021313131313131317,
|
| 54102 |
+
"loss": 3.0359151363372803,
|
| 54103 |
+
"step": 15446
|
| 54104 |
+
},
|
| 54105 |
+
{
|
| 54106 |
+
"epoch": 0.9362424242424242,
|
| 54107 |
+
"grad_norm": 0.04912964999675751,
|
| 54108 |
+
"learning_rate": 0.00021272727272727274,
|
| 54109 |
+
"loss": 3.038516044616699,
|
| 54110 |
+
"step": 15448
|
| 54111 |
+
},
|
| 54112 |
+
{
|
| 54113 |
+
"epoch": 0.9363636363636364,
|
| 54114 |
+
"grad_norm": 0.05106290802359581,
|
| 54115 |
+
"learning_rate": 0.00021232323232323234,
|
| 54116 |
+
"loss": 3.0596604347229004,
|
| 54117 |
+
"step": 15450
|
| 54118 |
+
},
|
| 54119 |
+
{
|
| 54120 |
+
"epoch": 0.9364848484848485,
|
| 54121 |
+
"grad_norm": 0.048987556248903275,
|
| 54122 |
+
"learning_rate": 0.00021191919191919194,
|
| 54123 |
+
"loss": 3.029167413711548,
|
| 54124 |
+
"step": 15452
|
| 54125 |
+
},
|
| 54126 |
+
{
|
| 54127 |
+
"epoch": 0.9366060606060606,
|
| 54128 |
+
"grad_norm": 0.05086161941289902,
|
| 54129 |
+
"learning_rate": 0.00021151515151515154,
|
| 54130 |
+
"loss": 3.0369575023651123,
|
| 54131 |
+
"step": 15454
|
| 54132 |
+
},
|
| 54133 |
+
{
|
| 54134 |
+
"epoch": 0.9367272727272727,
|
| 54135 |
+
"grad_norm": 0.05616499483585358,
|
| 54136 |
+
"learning_rate": 0.00021111111111111113,
|
| 54137 |
+
"loss": 3.037477493286133,
|
| 54138 |
+
"step": 15456
|
| 54139 |
+
},
|
| 54140 |
+
{
|
| 54141 |
+
"epoch": 0.9368484848484848,
|
| 54142 |
+
"grad_norm": 0.04882238432765007,
|
| 54143 |
+
"learning_rate": 0.00021070707070707073,
|
| 54144 |
+
"loss": 3.042635202407837,
|
| 54145 |
+
"step": 15458
|
| 54146 |
+
},
|
| 54147 |
+
{
|
| 54148 |
+
"epoch": 0.936969696969697,
|
| 54149 |
+
"grad_norm": 0.04921192303299904,
|
| 54150 |
+
"learning_rate": 0.0002103030303030303,
|
| 54151 |
+
"loss": 3.0063631534576416,
|
| 54152 |
+
"step": 15460
|
| 54153 |
+
},
|
| 54154 |
+
{
|
| 54155 |
+
"epoch": 0.9370909090909091,
|
| 54156 |
+
"grad_norm": 0.054276689887046814,
|
| 54157 |
+
"learning_rate": 0.0002098989898989899,
|
| 54158 |
+
"loss": 2.989459991455078,
|
| 54159 |
+
"step": 15462
|
| 54160 |
+
},
|
| 54161 |
+
{
|
| 54162 |
+
"epoch": 0.9372121212121212,
|
| 54163 |
+
"grad_norm": 0.050851497799158096,
|
| 54164 |
+
"learning_rate": 0.0002094949494949495,
|
| 54165 |
+
"loss": 3.0287585258483887,
|
| 54166 |
+
"step": 15464
|
| 54167 |
+
},
|
| 54168 |
+
{
|
| 54169 |
+
"epoch": 0.9373333333333334,
|
| 54170 |
+
"grad_norm": 0.05902981758117676,
|
| 54171 |
+
"learning_rate": 0.0002090909090909091,
|
| 54172 |
+
"loss": 3.0534214973449707,
|
| 54173 |
+
"step": 15466
|
| 54174 |
+
},
|
| 54175 |
+
{
|
| 54176 |
+
"epoch": 0.9374545454545454,
|
| 54177 |
+
"grad_norm": 0.05460544675588608,
|
| 54178 |
+
"learning_rate": 0.0002086868686868687,
|
| 54179 |
+
"loss": 3.0622527599334717,
|
| 54180 |
+
"step": 15468
|
| 54181 |
+
},
|
| 54182 |
+
{
|
| 54183 |
+
"epoch": 0.9375757575757576,
|
| 54184 |
+
"grad_norm": 0.05116083845496178,
|
| 54185 |
+
"learning_rate": 0.0002082828282828283,
|
| 54186 |
+
"loss": 3.0016589164733887,
|
| 54187 |
+
"step": 15470
|
| 54188 |
+
},
|
| 54189 |
+
{
|
| 54190 |
+
"epoch": 0.9376969696969697,
|
| 54191 |
+
"grad_norm": 0.05332960933446884,
|
| 54192 |
+
"learning_rate": 0.00020787878787878786,
|
| 54193 |
+
"loss": 3.038156270980835,
|
| 54194 |
+
"step": 15472
|
| 54195 |
+
},
|
| 54196 |
+
{
|
| 54197 |
+
"epoch": 0.9378181818181818,
|
| 54198 |
+
"grad_norm": 0.051887400448322296,
|
| 54199 |
+
"learning_rate": 0.00020747474747474746,
|
| 54200 |
+
"loss": 3.0635199546813965,
|
| 54201 |
+
"step": 15474
|
| 54202 |
+
},
|
| 54203 |
+
{
|
| 54204 |
+
"epoch": 0.937939393939394,
|
| 54205 |
+
"grad_norm": 0.05284327641129494,
|
| 54206 |
+
"learning_rate": 0.00020707070707070706,
|
| 54207 |
+
"loss": 2.9723293781280518,
|
| 54208 |
+
"step": 15476
|
| 54209 |
+
},
|
| 54210 |
+
{
|
| 54211 |
+
"epoch": 0.938060606060606,
|
| 54212 |
+
"grad_norm": 0.05430933088064194,
|
| 54213 |
+
"learning_rate": 0.00020666666666666668,
|
| 54214 |
+
"loss": 3.017566680908203,
|
| 54215 |
+
"step": 15478
|
| 54216 |
+
},
|
| 54217 |
+
{
|
| 54218 |
+
"epoch": 0.9381818181818182,
|
| 54219 |
+
"grad_norm": 0.049333009868860245,
|
| 54220 |
+
"learning_rate": 0.00020626262626262628,
|
| 54221 |
+
"loss": 3.047358512878418,
|
| 54222 |
+
"step": 15480
|
| 54223 |
+
},
|
| 54224 |
+
{
|
| 54225 |
+
"epoch": 0.9383030303030303,
|
| 54226 |
+
"grad_norm": 0.04948105663061142,
|
| 54227 |
+
"learning_rate": 0.00020585858585858588,
|
| 54228 |
+
"loss": 2.9835963249206543,
|
| 54229 |
+
"step": 15482
|
| 54230 |
+
},
|
| 54231 |
+
{
|
| 54232 |
+
"epoch": 0.9384242424242424,
|
| 54233 |
+
"grad_norm": 0.04893963411450386,
|
| 54234 |
+
"learning_rate": 0.00020545454545454548,
|
| 54235 |
+
"loss": 3.0200445652008057,
|
| 54236 |
+
"step": 15484
|
| 54237 |
+
},
|
| 54238 |
+
{
|
| 54239 |
+
"epoch": 0.9385454545454546,
|
| 54240 |
+
"grad_norm": 0.04996220022439957,
|
| 54241 |
+
"learning_rate": 0.00020505050505050508,
|
| 54242 |
+
"loss": 3.012974262237549,
|
| 54243 |
+
"step": 15486
|
| 54244 |
+
},
|
| 54245 |
+
{
|
| 54246 |
+
"epoch": 0.9386666666666666,
|
| 54247 |
+
"grad_norm": 0.04869063198566437,
|
| 54248 |
+
"learning_rate": 0.00020464646464646467,
|
| 54249 |
+
"loss": 2.975890874862671,
|
| 54250 |
+
"step": 15488
|
| 54251 |
+
},
|
| 54252 |
+
{
|
| 54253 |
+
"epoch": 0.9387878787878788,
|
| 54254 |
+
"grad_norm": 0.0509868785738945,
|
| 54255 |
+
"learning_rate": 0.00020424242424242425,
|
| 54256 |
+
"loss": 3.030564546585083,
|
| 54257 |
+
"step": 15490
|
| 54258 |
+
},
|
| 54259 |
+
{
|
| 54260 |
+
"epoch": 0.9389090909090909,
|
| 54261 |
+
"grad_norm": 0.04893852770328522,
|
| 54262 |
+
"learning_rate": 0.00020383838383838384,
|
| 54263 |
+
"loss": 3.0349881649017334,
|
| 54264 |
+
"step": 15492
|
| 54265 |
+
},
|
| 54266 |
+
{
|
| 54267 |
+
"epoch": 0.939030303030303,
|
| 54268 |
+
"grad_norm": 0.0536225251853466,
|
| 54269 |
+
"learning_rate": 0.00020343434343434344,
|
| 54270 |
+
"loss": 3.03829026222229,
|
| 54271 |
+
"step": 15494
|
| 54272 |
+
},
|
| 54273 |
+
{
|
| 54274 |
+
"epoch": 0.9391515151515152,
|
| 54275 |
+
"grad_norm": 0.06121872365474701,
|
| 54276 |
+
"learning_rate": 0.00020303030303030304,
|
| 54277 |
+
"loss": 3.0408029556274414,
|
| 54278 |
+
"step": 15496
|
| 54279 |
+
},
|
| 54280 |
+
{
|
| 54281 |
+
"epoch": 0.9392727272727273,
|
| 54282 |
+
"grad_norm": 0.05058020353317261,
|
| 54283 |
+
"learning_rate": 0.00020262626262626264,
|
| 54284 |
+
"loss": 3.004079818725586,
|
| 54285 |
+
"step": 15498
|
| 54286 |
+
},
|
| 54287 |
+
{
|
| 54288 |
+
"epoch": 0.9393939393939394,
|
| 54289 |
+
"grad_norm": 0.052557215094566345,
|
| 54290 |
+
"learning_rate": 0.00020222222222222223,
|
| 54291 |
+
"loss": 3.034640073776245,
|
| 54292 |
+
"step": 15500
|
| 54293 |
+
},
|
| 54294 |
+
{
|
| 54295 |
+
"epoch": 0.9395151515151515,
|
| 54296 |
+
"grad_norm": 0.04807470738887787,
|
| 54297 |
+
"learning_rate": 0.0002018181818181818,
|
| 54298 |
+
"loss": 3.004066228866577,
|
| 54299 |
+
"step": 15502
|
| 54300 |
+
},
|
| 54301 |
+
{
|
| 54302 |
+
"epoch": 0.9396363636363636,
|
| 54303 |
+
"grad_norm": 0.050174351781606674,
|
| 54304 |
+
"learning_rate": 0.0002014141414141414,
|
| 54305 |
+
"loss": 2.9793128967285156,
|
| 54306 |
+
"step": 15504
|
| 54307 |
+
},
|
| 54308 |
+
{
|
| 54309 |
+
"epoch": 0.9397575757575758,
|
| 54310 |
+
"grad_norm": 0.049994777888059616,
|
| 54311 |
+
"learning_rate": 0.000201010101010101,
|
| 54312 |
+
"loss": 2.9896397590637207,
|
| 54313 |
+
"step": 15506
|
| 54314 |
+
},
|
| 54315 |
+
{
|
| 54316 |
+
"epoch": 0.9398787878787879,
|
| 54317 |
+
"grad_norm": 0.04861712455749512,
|
| 54318 |
+
"learning_rate": 0.0002006060606060606,
|
| 54319 |
+
"loss": 3.0374317169189453,
|
| 54320 |
+
"step": 15508
|
| 54321 |
+
},
|
| 54322 |
+
{
|
| 54323 |
+
"epoch": 0.94,
|
| 54324 |
+
"grad_norm": 0.04972008988261223,
|
| 54325 |
+
"learning_rate": 0.0002002020202020202,
|
| 54326 |
+
"loss": 3.0536744594573975,
|
| 54327 |
+
"step": 15510
|
| 54328 |
+
},
|
| 54329 |
+
{
|
| 54330 |
+
"epoch": 0.9401212121212121,
|
| 54331 |
+
"grad_norm": 0.04871795326471329,
|
| 54332 |
+
"learning_rate": 0.0001997979797979798,
|
| 54333 |
+
"loss": 3.011591672897339,
|
| 54334 |
+
"step": 15512
|
| 54335 |
+
},
|
| 54336 |
+
{
|
| 54337 |
+
"epoch": 0.9402424242424242,
|
| 54338 |
+
"grad_norm": 0.05662468448281288,
|
| 54339 |
+
"learning_rate": 0.0001993939393939394,
|
| 54340 |
+
"loss": 3.0120842456817627,
|
| 54341 |
+
"step": 15514
|
| 54342 |
+
},
|
| 54343 |
+
{
|
| 54344 |
+
"epoch": 0.9403636363636364,
|
| 54345 |
+
"grad_norm": 0.05033624917268753,
|
| 54346 |
+
"learning_rate": 0.000198989898989899,
|
| 54347 |
+
"loss": 3.0425589084625244,
|
| 54348 |
+
"step": 15516
|
| 54349 |
+
},
|
| 54350 |
+
{
|
| 54351 |
+
"epoch": 0.9404848484848485,
|
| 54352 |
+
"grad_norm": 0.04844122752547264,
|
| 54353 |
+
"learning_rate": 0.0001985858585858586,
|
| 54354 |
+
"loss": 3.0392324924468994,
|
| 54355 |
+
"step": 15518
|
| 54356 |
+
},
|
| 54357 |
+
{
|
| 54358 |
+
"epoch": 0.9406060606060606,
|
| 54359 |
+
"grad_norm": 0.04987867549061775,
|
| 54360 |
+
"learning_rate": 0.00019818181818181821,
|
| 54361 |
+
"loss": 3.04712176322937,
|
| 54362 |
+
"step": 15520
|
| 54363 |
+
},
|
| 54364 |
+
{
|
| 54365 |
+
"epoch": 0.9407272727272727,
|
| 54366 |
+
"grad_norm": 0.04952312633395195,
|
| 54367 |
+
"learning_rate": 0.00019777777777777778,
|
| 54368 |
+
"loss": 3.0573787689208984,
|
| 54369 |
+
"step": 15522
|
| 54370 |
+
},
|
| 54371 |
+
{
|
| 54372 |
+
"epoch": 0.9408484848484848,
|
| 54373 |
+
"grad_norm": 0.048636384308338165,
|
| 54374 |
+
"learning_rate": 0.00019737373737373738,
|
| 54375 |
+
"loss": 3.0145039558410645,
|
| 54376 |
+
"step": 15524
|
| 54377 |
+
},
|
| 54378 |
+
{
|
| 54379 |
+
"epoch": 0.940969696969697,
|
| 54380 |
+
"grad_norm": 0.05189495533704758,
|
| 54381 |
+
"learning_rate": 0.00019696969696969698,
|
| 54382 |
+
"loss": 3.03045916557312,
|
| 54383 |
+
"step": 15526
|
| 54384 |
+
},
|
| 54385 |
+
{
|
| 54386 |
+
"epoch": 0.9410909090909091,
|
| 54387 |
+
"grad_norm": 0.048595838248729706,
|
| 54388 |
+
"learning_rate": 0.00019656565656565658,
|
| 54389 |
+
"loss": 3.004059314727783,
|
| 54390 |
+
"step": 15528
|
| 54391 |
+
},
|
| 54392 |
+
{
|
| 54393 |
+
"epoch": 0.9412121212121212,
|
| 54394 |
+
"grad_norm": 0.0512409508228302,
|
| 54395 |
+
"learning_rate": 0.00019616161616161618,
|
| 54396 |
+
"loss": 3.001244068145752,
|
| 54397 |
+
"step": 15530
|
| 54398 |
+
},
|
| 54399 |
+
{
|
| 54400 |
+
"epoch": 0.9413333333333334,
|
| 54401 |
+
"grad_norm": 0.05690300837159157,
|
| 54402 |
+
"learning_rate": 0.00019575757575757577,
|
| 54403 |
+
"loss": 3.03310227394104,
|
| 54404 |
+
"step": 15532
|
| 54405 |
+
},
|
| 54406 |
+
{
|
| 54407 |
+
"epoch": 0.9414545454545454,
|
| 54408 |
+
"grad_norm": 0.05050172656774521,
|
| 54409 |
+
"learning_rate": 0.00019535353535353534,
|
| 54410 |
+
"loss": 3.04647159576416,
|
| 54411 |
+
"step": 15534
|
| 54412 |
+
},
|
| 54413 |
+
{
|
| 54414 |
+
"epoch": 0.9415757575757576,
|
| 54415 |
+
"grad_norm": 0.05274985358119011,
|
| 54416 |
+
"learning_rate": 0.00019494949494949494,
|
| 54417 |
+
"loss": 3.04443359375,
|
| 54418 |
+
"step": 15536
|
| 54419 |
+
},
|
| 54420 |
+
{
|
| 54421 |
+
"epoch": 0.9416969696969697,
|
| 54422 |
+
"grad_norm": 0.05387469381093979,
|
| 54423 |
+
"learning_rate": 0.00019454545454545457,
|
| 54424 |
+
"loss": 3.0400564670562744,
|
| 54425 |
+
"step": 15538
|
| 54426 |
+
},
|
| 54427 |
+
{
|
| 54428 |
+
"epoch": 0.9418181818181818,
|
| 54429 |
+
"grad_norm": 0.04906125366687775,
|
| 54430 |
+
"learning_rate": 0.00019414141414141417,
|
| 54431 |
+
"loss": 3.0327491760253906,
|
| 54432 |
+
"step": 15540
|
| 54433 |
+
},
|
| 54434 |
+
{
|
| 54435 |
+
"epoch": 0.941939393939394,
|
| 54436 |
+
"grad_norm": 0.04946596175432205,
|
| 54437 |
+
"learning_rate": 0.00019373737373737376,
|
| 54438 |
+
"loss": 3.0425045490264893,
|
| 54439 |
+
"step": 15542
|
| 54440 |
+
},
|
| 54441 |
+
{
|
| 54442 |
+
"epoch": 0.942060606060606,
|
| 54443 |
+
"grad_norm": 0.04992404952645302,
|
| 54444 |
+
"learning_rate": 0.00019333333333333333,
|
| 54445 |
+
"loss": 3.027269124984741,
|
| 54446 |
+
"step": 15544
|
| 54447 |
+
},
|
| 54448 |
+
{
|
| 54449 |
+
"epoch": 0.9421818181818182,
|
| 54450 |
+
"grad_norm": 0.0529591403901577,
|
| 54451 |
+
"learning_rate": 0.00019292929292929293,
|
| 54452 |
+
"loss": 3.0505707263946533,
|
| 54453 |
+
"step": 15546
|
| 54454 |
+
},
|
| 54455 |
+
{
|
| 54456 |
+
"epoch": 0.9423030303030303,
|
| 54457 |
+
"grad_norm": 0.051120344549417496,
|
| 54458 |
+
"learning_rate": 0.00019252525252525253,
|
| 54459 |
+
"loss": 3.057781219482422,
|
| 54460 |
+
"step": 15548
|
| 54461 |
+
},
|
| 54462 |
+
{
|
| 54463 |
+
"epoch": 0.9424242424242424,
|
| 54464 |
+
"grad_norm": 0.0478610061109066,
|
| 54465 |
+
"learning_rate": 0.00019212121212121213,
|
| 54466 |
+
"loss": 2.998856782913208,
|
| 54467 |
+
"step": 15550
|
| 54468 |
+
},
|
| 54469 |
+
{
|
| 54470 |
+
"epoch": 0.9425454545454546,
|
| 54471 |
+
"grad_norm": 0.05590425431728363,
|
| 54472 |
+
"learning_rate": 0.00019171717171717173,
|
| 54473 |
+
"loss": 3.0110368728637695,
|
| 54474 |
+
"step": 15552
|
| 54475 |
+
},
|
| 54476 |
+
{
|
| 54477 |
+
"epoch": 0.9426666666666667,
|
| 54478 |
+
"grad_norm": 0.04849468171596527,
|
| 54479 |
+
"learning_rate": 0.00019131313131313132,
|
| 54480 |
+
"loss": 2.9929254055023193,
|
| 54481 |
+
"step": 15554
|
| 54482 |
+
},
|
| 54483 |
+
{
|
| 54484 |
+
"epoch": 0.9427878787878788,
|
| 54485 |
+
"grad_norm": 0.05134075507521629,
|
| 54486 |
+
"learning_rate": 0.00019090909090909092,
|
| 54487 |
+
"loss": 3.020890235900879,
|
| 54488 |
+
"step": 15556
|
| 54489 |
+
},
|
| 54490 |
+
{
|
| 54491 |
+
"epoch": 0.9429090909090909,
|
| 54492 |
+
"grad_norm": 0.04853273555636406,
|
| 54493 |
+
"learning_rate": 0.00019050505050505052,
|
| 54494 |
+
"loss": 3.007770538330078,
|
| 54495 |
+
"step": 15558
|
| 54496 |
+
},
|
| 54497 |
+
{
|
| 54498 |
+
"epoch": 0.943030303030303,
|
| 54499 |
+
"grad_norm": 0.05042204260826111,
|
| 54500 |
+
"learning_rate": 0.00019010101010101012,
|
| 54501 |
+
"loss": 3.064668893814087,
|
| 54502 |
+
"step": 15560
|
| 54503 |
+
},
|
| 54504 |
+
{
|
| 54505 |
+
"epoch": 0.9431515151515152,
|
| 54506 |
+
"grad_norm": 0.04948095977306366,
|
| 54507 |
+
"learning_rate": 0.00018969696969696972,
|
| 54508 |
+
"loss": 3.0182790756225586,
|
| 54509 |
+
"step": 15562
|
| 54510 |
+
},
|
| 54511 |
+
{
|
| 54512 |
+
"epoch": 0.9432727272727273,
|
| 54513 |
+
"grad_norm": 0.04921668767929077,
|
| 54514 |
+
"learning_rate": 0.0001892929292929293,
|
| 54515 |
+
"loss": 3.009406566619873,
|
| 54516 |
+
"step": 15564
|
| 54517 |
+
},
|
| 54518 |
+
{
|
| 54519 |
+
"epoch": 0.9433939393939393,
|
| 54520 |
+
"grad_norm": 0.0481036901473999,
|
| 54521 |
+
"learning_rate": 0.00018888888888888888,
|
| 54522 |
+
"loss": 2.981588363647461,
|
| 54523 |
+
"step": 15566
|
| 54524 |
+
},
|
| 54525 |
+
{
|
| 54526 |
+
"epoch": 0.9435151515151515,
|
| 54527 |
+
"grad_norm": 0.048717956990003586,
|
| 54528 |
+
"learning_rate": 0.00018848484848484848,
|
| 54529 |
+
"loss": 3.024655818939209,
|
| 54530 |
+
"step": 15568
|
| 54531 |
+
},
|
| 54532 |
+
{
|
| 54533 |
+
"epoch": 0.9436363636363636,
|
| 54534 |
+
"grad_norm": 0.049209363758563995,
|
| 54535 |
+
"learning_rate": 0.00018808080808080808,
|
| 54536 |
+
"loss": 3.032827377319336,
|
| 54537 |
+
"step": 15570
|
| 54538 |
+
},
|
| 54539 |
+
{
|
| 54540 |
+
"epoch": 0.9437575757575758,
|
| 54541 |
+
"grad_norm": 0.049004729837179184,
|
| 54542 |
+
"learning_rate": 0.0001876767676767677,
|
| 54543 |
+
"loss": 3.0418193340301514,
|
| 54544 |
+
"step": 15572
|
| 54545 |
+
},
|
| 54546 |
+
{
|
| 54547 |
+
"epoch": 0.9438787878787879,
|
| 54548 |
+
"grad_norm": 0.04952102154493332,
|
| 54549 |
+
"learning_rate": 0.00018727272727272728,
|
| 54550 |
+
"loss": 3.0262014865875244,
|
| 54551 |
+
"step": 15574
|
| 54552 |
+
},
|
| 54553 |
+
{
|
| 54554 |
+
"epoch": 0.944,
|
| 54555 |
+
"grad_norm": 0.04889124259352684,
|
| 54556 |
+
"learning_rate": 0.00018686868686868687,
|
| 54557 |
+
"loss": 3.0542666912078857,
|
| 54558 |
+
"step": 15576
|
| 54559 |
+
},
|
| 54560 |
+
{
|
| 54561 |
+
"epoch": 0.9441212121212121,
|
| 54562 |
+
"grad_norm": 0.048753343522548676,
|
| 54563 |
+
"learning_rate": 0.00018646464646464647,
|
| 54564 |
+
"loss": 2.9826924800872803,
|
| 54565 |
+
"step": 15578
|
| 54566 |
+
},
|
| 54567 |
+
{
|
| 54568 |
+
"epoch": 0.9442424242424242,
|
| 54569 |
+
"grad_norm": 0.05071985721588135,
|
| 54570 |
+
"learning_rate": 0.00018606060606060607,
|
| 54571 |
+
"loss": 3.0763566493988037,
|
| 54572 |
+
"step": 15580
|
| 54573 |
+
},
|
| 54574 |
+
{
|
| 54575 |
+
"epoch": 0.9443636363636364,
|
| 54576 |
+
"grad_norm": 0.049242135137319565,
|
| 54577 |
+
"learning_rate": 0.00018565656565656567,
|
| 54578 |
+
"loss": 3.0639493465423584,
|
| 54579 |
+
"step": 15582
|
| 54580 |
+
},
|
| 54581 |
+
{
|
| 54582 |
+
"epoch": 0.9444848484848485,
|
| 54583 |
+
"grad_norm": 0.05701543018221855,
|
| 54584 |
+
"learning_rate": 0.00018525252525252527,
|
| 54585 |
+
"loss": 3.0447423458099365,
|
| 54586 |
+
"step": 15584
|
| 54587 |
+
},
|
| 54588 |
+
{
|
| 54589 |
+
"epoch": 0.9446060606060606,
|
| 54590 |
+
"grad_norm": 0.05647512525320053,
|
| 54591 |
+
"learning_rate": 0.00018484848484848484,
|
| 54592 |
+
"loss": 3.072296380996704,
|
| 54593 |
+
"step": 15586
|
| 54594 |
+
},
|
| 54595 |
+
{
|
| 54596 |
+
"epoch": 0.9447272727272727,
|
| 54597 |
+
"grad_norm": 0.05138588324189186,
|
| 54598 |
+
"learning_rate": 0.00018444444444444446,
|
| 54599 |
+
"loss": 3.007584810256958,
|
| 54600 |
+
"step": 15588
|
| 54601 |
+
},
|
| 54602 |
+
{
|
| 54603 |
+
"epoch": 0.9448484848484848,
|
| 54604 |
+
"grad_norm": 0.049444276839494705,
|
| 54605 |
+
"learning_rate": 0.00018404040404040406,
|
| 54606 |
+
"loss": 3.0514116287231445,
|
| 54607 |
+
"step": 15590
|
| 54608 |
+
},
|
| 54609 |
+
{
|
| 54610 |
+
"epoch": 0.944969696969697,
|
| 54611 |
+
"grad_norm": 0.04912831634283066,
|
| 54612 |
+
"learning_rate": 0.00018363636363636366,
|
| 54613 |
+
"loss": 3.0397298336029053,
|
| 54614 |
+
"step": 15592
|
| 54615 |
+
},
|
| 54616 |
+
{
|
| 54617 |
+
"epoch": 0.9450909090909091,
|
| 54618 |
+
"grad_norm": 0.053070224821567535,
|
| 54619 |
+
"learning_rate": 0.00018323232323232326,
|
| 54620 |
+
"loss": 3.0223476886749268,
|
| 54621 |
+
"step": 15594
|
| 54622 |
+
},
|
| 54623 |
+
{
|
| 54624 |
+
"epoch": 0.9452121212121212,
|
| 54625 |
+
"grad_norm": 0.05408964306116104,
|
| 54626 |
+
"learning_rate": 0.00018282828282828283,
|
| 54627 |
+
"loss": 3.0384228229522705,
|
| 54628 |
+
"step": 15596
|
| 54629 |
+
},
|
| 54630 |
+
{
|
| 54631 |
+
"epoch": 0.9453333333333334,
|
| 54632 |
+
"grad_norm": 0.05109323188662529,
|
| 54633 |
+
"learning_rate": 0.00018242424242424242,
|
| 54634 |
+
"loss": 3.0653445720672607,
|
| 54635 |
+
"step": 15598
|
| 54636 |
+
},
|
| 54637 |
+
{
|
| 54638 |
+
"epoch": 0.9454545454545454,
|
| 54639 |
+
"grad_norm": 0.05126390978693962,
|
| 54640 |
+
"learning_rate": 0.00018202020202020202,
|
| 54641 |
+
"loss": 3.090996503829956,
|
| 54642 |
+
"step": 15600
|
| 54643 |
+
},
|
| 54644 |
+
{
|
| 54645 |
+
"epoch": 0.9455757575757576,
|
| 54646 |
+
"grad_norm": 0.0491819754242897,
|
| 54647 |
+
"learning_rate": 0.00018161616161616162,
|
| 54648 |
+
"loss": 3.0530757904052734,
|
| 54649 |
+
"step": 15602
|
| 54650 |
+
},
|
| 54651 |
+
{
|
| 54652 |
+
"epoch": 0.9456969696969697,
|
| 54653 |
+
"grad_norm": 0.050144605338573456,
|
| 54654 |
+
"learning_rate": 0.00018121212121212122,
|
| 54655 |
+
"loss": 3.0149037837982178,
|
| 54656 |
+
"step": 15604
|
| 54657 |
+
},
|
| 54658 |
+
{
|
| 54659 |
+
"epoch": 0.9458181818181818,
|
| 54660 |
+
"grad_norm": 0.04924320802092552,
|
| 54661 |
+
"learning_rate": 0.00018080808080808082,
|
| 54662 |
+
"loss": 3.067002296447754,
|
| 54663 |
+
"step": 15606
|
| 54664 |
+
},
|
| 54665 |
+
{
|
| 54666 |
+
"epoch": 0.945939393939394,
|
| 54667 |
+
"grad_norm": 0.04983403533697128,
|
| 54668 |
+
"learning_rate": 0.0001804040404040404,
|
| 54669 |
+
"loss": 3.019683361053467,
|
| 54670 |
+
"step": 15608
|
| 54671 |
+
},
|
| 54672 |
+
{
|
| 54673 |
+
"epoch": 0.946060606060606,
|
| 54674 |
+
"grad_norm": 0.05141449719667435,
|
| 54675 |
+
"learning_rate": 0.00018,
|
| 54676 |
+
"loss": 3.0369372367858887,
|
| 54677 |
+
"step": 15610
|
| 54678 |
+
},
|
| 54679 |
+
{
|
| 54680 |
+
"epoch": 0.9461818181818182,
|
| 54681 |
+
"grad_norm": 0.04863531515002251,
|
| 54682 |
+
"learning_rate": 0.0001795959595959596,
|
| 54683 |
+
"loss": 3.0308358669281006,
|
| 54684 |
+
"step": 15612
|
| 54685 |
+
},
|
| 54686 |
+
{
|
| 54687 |
+
"epoch": 0.9463030303030303,
|
| 54688 |
+
"grad_norm": 0.049230001866817474,
|
| 54689 |
+
"learning_rate": 0.0001791919191919192,
|
| 54690 |
+
"loss": 3.0470571517944336,
|
| 54691 |
+
"step": 15614
|
| 54692 |
+
},
|
| 54693 |
+
{
|
| 54694 |
+
"epoch": 0.9464242424242424,
|
| 54695 |
+
"grad_norm": 0.048427753150463104,
|
| 54696 |
+
"learning_rate": 0.0001787878787878788,
|
| 54697 |
+
"loss": 3.0499167442321777,
|
| 54698 |
+
"step": 15616
|
| 54699 |
+
},
|
| 54700 |
+
{
|
| 54701 |
+
"epoch": 0.9465454545454546,
|
| 54702 |
+
"grad_norm": 0.048432476818561554,
|
| 54703 |
+
"learning_rate": 0.00017838383838383838,
|
| 54704 |
+
"loss": 3.043076992034912,
|
| 54705 |
+
"step": 15618
|
| 54706 |
+
},
|
| 54707 |
+
{
|
| 54708 |
+
"epoch": 0.9466666666666667,
|
| 54709 |
+
"grad_norm": 0.04924627020955086,
|
| 54710 |
+
"learning_rate": 0.00017797979797979797,
|
| 54711 |
+
"loss": 3.0535717010498047,
|
| 54712 |
+
"step": 15620
|
| 54713 |
+
},
|
| 54714 |
+
{
|
| 54715 |
+
"epoch": 0.9467878787878787,
|
| 54716 |
+
"grad_norm": 0.051176052540540695,
|
| 54717 |
+
"learning_rate": 0.0001775757575757576,
|
| 54718 |
+
"loss": 3.048149585723877,
|
| 54719 |
+
"step": 15622
|
| 54720 |
+
},
|
| 54721 |
+
{
|
| 54722 |
+
"epoch": 0.9469090909090909,
|
| 54723 |
+
"grad_norm": 0.04843096435070038,
|
| 54724 |
+
"learning_rate": 0.0001771717171717172,
|
| 54725 |
+
"loss": 3.042633295059204,
|
| 54726 |
+
"step": 15624
|
| 54727 |
+
},
|
| 54728 |
+
{
|
| 54729 |
+
"epoch": 0.947030303030303,
|
| 54730 |
+
"grad_norm": 0.04827112704515457,
|
| 54731 |
+
"learning_rate": 0.0001767676767676768,
|
| 54732 |
+
"loss": 3.014803409576416,
|
| 54733 |
+
"step": 15626
|
| 54734 |
+
},
|
| 54735 |
+
{
|
| 54736 |
+
"epoch": 0.9471515151515152,
|
| 54737 |
+
"grad_norm": 0.05004272237420082,
|
| 54738 |
+
"learning_rate": 0.00017636363636363637,
|
| 54739 |
+
"loss": 3.0407724380493164,
|
| 54740 |
+
"step": 15628
|
| 54741 |
+
},
|
| 54742 |
+
{
|
| 54743 |
+
"epoch": 0.9472727272727273,
|
| 54744 |
+
"grad_norm": 0.04909525811672211,
|
| 54745 |
+
"learning_rate": 0.00017595959595959596,
|
| 54746 |
+
"loss": 3.035121202468872,
|
| 54747 |
+
"step": 15630
|
| 54748 |
+
},
|
| 54749 |
+
{
|
| 54750 |
+
"epoch": 0.9473939393939393,
|
| 54751 |
+
"grad_norm": 0.05698690935969353,
|
| 54752 |
+
"learning_rate": 0.00017555555555555556,
|
| 54753 |
+
"loss": 3.038562059402466,
|
| 54754 |
+
"step": 15632
|
| 54755 |
+
},
|
| 54756 |
+
{
|
| 54757 |
+
"epoch": 0.9475151515151515,
|
| 54758 |
+
"grad_norm": 0.04843836650252342,
|
| 54759 |
+
"learning_rate": 0.00017515151515151516,
|
| 54760 |
+
"loss": 3.0429539680480957,
|
| 54761 |
+
"step": 15634
|
| 54762 |
+
},
|
| 54763 |
+
{
|
| 54764 |
+
"epoch": 0.9476363636363636,
|
| 54765 |
+
"grad_norm": 0.049286969006061554,
|
| 54766 |
+
"learning_rate": 0.00017474747474747476,
|
| 54767 |
+
"loss": 3.086639881134033,
|
| 54768 |
+
"step": 15636
|
| 54769 |
+
},
|
| 54770 |
+
{
|
| 54771 |
+
"epoch": 0.9477575757575758,
|
| 54772 |
+
"grad_norm": 0.04797523096203804,
|
| 54773 |
+
"learning_rate": 0.00017434343434343435,
|
| 54774 |
+
"loss": 3.0544376373291016,
|
| 54775 |
+
"step": 15638
|
| 54776 |
+
},
|
| 54777 |
+
{
|
| 54778 |
+
"epoch": 0.9478787878787879,
|
| 54779 |
+
"grad_norm": 0.05267041176557541,
|
| 54780 |
+
"learning_rate": 0.00017393939393939395,
|
| 54781 |
+
"loss": 3.0665767192840576,
|
| 54782 |
+
"step": 15640
|
| 54783 |
+
},
|
| 54784 |
+
{
|
| 54785 |
+
"epoch": 0.948,
|
| 54786 |
+
"grad_norm": 0.04922143369913101,
|
| 54787 |
+
"learning_rate": 0.00017353535353535355,
|
| 54788 |
+
"loss": 3.023818254470825,
|
| 54789 |
+
"step": 15642
|
| 54790 |
+
},
|
| 54791 |
+
{
|
| 54792 |
+
"epoch": 0.9481212121212121,
|
| 54793 |
+
"grad_norm": 0.048744723200798035,
|
| 54794 |
+
"learning_rate": 0.00017313131313131315,
|
| 54795 |
+
"loss": 3.0475008487701416,
|
| 54796 |
+
"step": 15644
|
| 54797 |
+
},
|
| 54798 |
+
{
|
| 54799 |
+
"epoch": 0.9482424242424242,
|
| 54800 |
+
"grad_norm": 0.048895835876464844,
|
| 54801 |
+
"learning_rate": 0.00017272727272727275,
|
| 54802 |
+
"loss": 3.0317225456237793,
|
| 54803 |
+
"step": 15646
|
| 54804 |
+
},
|
| 54805 |
+
{
|
| 54806 |
+
"epoch": 0.9483636363636364,
|
| 54807 |
+
"grad_norm": 0.04969105124473572,
|
| 54808 |
+
"learning_rate": 0.00017232323232323232,
|
| 54809 |
+
"loss": 3.0166869163513184,
|
| 54810 |
+
"step": 15648
|
| 54811 |
+
},
|
| 54812 |
+
{
|
| 54813 |
+
"epoch": 0.9484848484848485,
|
| 54814 |
+
"grad_norm": 0.04833272099494934,
|
| 54815 |
+
"learning_rate": 0.00017191919191919192,
|
| 54816 |
+
"loss": 3.034177303314209,
|
| 54817 |
+
"step": 15650
|
| 54818 |
+
},
|
| 54819 |
+
{
|
| 54820 |
+
"epoch": 0.9486060606060606,
|
| 54821 |
+
"grad_norm": 0.05050016567111015,
|
| 54822 |
+
"learning_rate": 0.0001715151515151515,
|
| 54823 |
+
"loss": 3.0504894256591797,
|
| 54824 |
+
"step": 15652
|
| 54825 |
+
},
|
| 54826 |
+
{
|
| 54827 |
+
"epoch": 0.9487272727272728,
|
| 54828 |
+
"grad_norm": 0.05115874484181404,
|
| 54829 |
+
"learning_rate": 0.0001711111111111111,
|
| 54830 |
+
"loss": 3.0455822944641113,
|
| 54831 |
+
"step": 15654
|
| 54832 |
+
},
|
| 54833 |
+
{
|
| 54834 |
+
"epoch": 0.9488484848484848,
|
| 54835 |
+
"grad_norm": 0.049892958253622055,
|
| 54836 |
+
"learning_rate": 0.0001707070707070707,
|
| 54837 |
+
"loss": 3.1053671836853027,
|
| 54838 |
+
"step": 15656
|
| 54839 |
+
},
|
| 54840 |
+
{
|
| 54841 |
+
"epoch": 0.948969696969697,
|
| 54842 |
+
"grad_norm": 0.051689811050891876,
|
| 54843 |
+
"learning_rate": 0.0001703030303030303,
|
| 54844 |
+
"loss": 3.044862747192383,
|
| 54845 |
+
"step": 15658
|
| 54846 |
+
},
|
| 54847 |
+
{
|
| 54848 |
+
"epoch": 0.9490909090909091,
|
| 54849 |
+
"grad_norm": 0.050586894154548645,
|
| 54850 |
+
"learning_rate": 0.0001698989898989899,
|
| 54851 |
+
"loss": 3.032987117767334,
|
| 54852 |
+
"step": 15660
|
| 54853 |
+
},
|
| 54854 |
+
{
|
| 54855 |
+
"epoch": 0.9492121212121212,
|
| 54856 |
+
"grad_norm": 0.04895954579114914,
|
| 54857 |
+
"learning_rate": 0.0001694949494949495,
|
| 54858 |
+
"loss": 3.06919264793396,
|
| 54859 |
+
"step": 15662
|
| 54860 |
+
},
|
| 54861 |
+
{
|
| 54862 |
+
"epoch": 0.9493333333333334,
|
| 54863 |
+
"grad_norm": 0.05009319260716438,
|
| 54864 |
+
"learning_rate": 0.0001690909090909091,
|
| 54865 |
+
"loss": 3.071161985397339,
|
| 54866 |
+
"step": 15664
|
| 54867 |
+
},
|
| 54868 |
+
{
|
| 54869 |
+
"epoch": 0.9494545454545454,
|
| 54870 |
+
"grad_norm": 0.051976896822452545,
|
| 54871 |
+
"learning_rate": 0.0001686868686868687,
|
| 54872 |
+
"loss": 3.0612051486968994,
|
| 54873 |
+
"step": 15666
|
| 54874 |
+
},
|
| 54875 |
+
{
|
| 54876 |
+
"epoch": 0.9495757575757576,
|
| 54877 |
+
"grad_norm": 0.05031817778944969,
|
| 54878 |
+
"learning_rate": 0.0001682828282828283,
|
| 54879 |
+
"loss": 3.0508081912994385,
|
| 54880 |
+
"step": 15668
|
| 54881 |
+
},
|
| 54882 |
+
{
|
| 54883 |
+
"epoch": 0.9496969696969697,
|
| 54884 |
+
"grad_norm": 0.048356011509895325,
|
| 54885 |
+
"learning_rate": 0.00016787878787878787,
|
| 54886 |
+
"loss": 3.0699217319488525,
|
| 54887 |
+
"step": 15670
|
| 54888 |
+
},
|
| 54889 |
+
{
|
| 54890 |
+
"epoch": 0.9498181818181818,
|
| 54891 |
+
"grad_norm": 0.05238514021039009,
|
| 54892 |
+
"learning_rate": 0.00016747474747474747,
|
| 54893 |
+
"loss": 3.0066373348236084,
|
| 54894 |
+
"step": 15672
|
| 54895 |
+
},
|
| 54896 |
+
{
|
| 54897 |
+
"epoch": 0.949939393939394,
|
| 54898 |
+
"grad_norm": 0.04901914298534393,
|
| 54899 |
+
"learning_rate": 0.0001670707070707071,
|
| 54900 |
+
"loss": 3.0517160892486572,
|
| 54901 |
+
"step": 15674
|
| 54902 |
+
},
|
| 54903 |
+
{
|
| 54904 |
+
"epoch": 0.950060606060606,
|
| 54905 |
+
"grad_norm": 0.05048520490527153,
|
| 54906 |
+
"learning_rate": 0.0001666666666666667,
|
| 54907 |
+
"loss": 3.0555028915405273,
|
| 54908 |
+
"step": 15676
|
| 54909 |
+
},
|
| 54910 |
+
{
|
| 54911 |
+
"epoch": 0.9501818181818181,
|
| 54912 |
+
"grad_norm": 0.05010529235005379,
|
| 54913 |
+
"learning_rate": 0.00016626262626262629,
|
| 54914 |
+
"loss": 3.0781137943267822,
|
| 54915 |
+
"step": 15678
|
| 54916 |
+
},
|
| 54917 |
+
{
|
| 54918 |
+
"epoch": 0.9503030303030303,
|
| 54919 |
+
"grad_norm": 0.05323826149106026,
|
| 54920 |
+
"learning_rate": 0.00016585858585858586,
|
| 54921 |
+
"loss": 3.1238059997558594,
|
| 54922 |
+
"step": 15680
|
| 54923 |
+
},
|
| 54924 |
+
{
|
| 54925 |
+
"epoch": 0.9504242424242424,
|
| 54926 |
+
"grad_norm": 0.053634583950042725,
|
| 54927 |
+
"learning_rate": 0.00016545454545454545,
|
| 54928 |
+
"loss": 3.034567356109619,
|
| 54929 |
+
"step": 15682
|
| 54930 |
+
},
|
| 54931 |
+
{
|
| 54932 |
+
"epoch": 0.9505454545454546,
|
| 54933 |
+
"grad_norm": 0.04938892275094986,
|
| 54934 |
+
"learning_rate": 0.00016505050505050505,
|
| 54935 |
+
"loss": 3.068929433822632,
|
| 54936 |
+
"step": 15684
|
| 54937 |
+
},
|
| 54938 |
+
{
|
| 54939 |
+
"epoch": 0.9506666666666667,
|
| 54940 |
+
"grad_norm": 0.04895763844251633,
|
| 54941 |
+
"learning_rate": 0.00016464646464646465,
|
| 54942 |
+
"loss": 3.060349464416504,
|
| 54943 |
+
"step": 15686
|
| 54944 |
+
},
|
| 54945 |
+
{
|
| 54946 |
+
"epoch": 0.9507878787878787,
|
| 54947 |
+
"grad_norm": 0.0484452024102211,
|
| 54948 |
+
"learning_rate": 0.00016424242424242425,
|
| 54949 |
+
"loss": 3.071992874145508,
|
| 54950 |
+
"step": 15688
|
| 54951 |
+
},
|
| 54952 |
+
{
|
| 54953 |
+
"epoch": 0.9509090909090909,
|
| 54954 |
+
"grad_norm": 0.05171800032258034,
|
| 54955 |
+
"learning_rate": 0.00016383838383838385,
|
| 54956 |
+
"loss": 3.048373222351074,
|
| 54957 |
+
"step": 15690
|
| 54958 |
+
},
|
| 54959 |
+
{
|
| 54960 |
+
"epoch": 0.951030303030303,
|
| 54961 |
+
"grad_norm": 0.049861203879117966,
|
| 54962 |
+
"learning_rate": 0.00016343434343434344,
|
| 54963 |
+
"loss": 3.1033411026000977,
|
| 54964 |
+
"step": 15692
|
| 54965 |
+
},
|
| 54966 |
+
{
|
| 54967 |
+
"epoch": 0.9511515151515152,
|
| 54968 |
+
"grad_norm": 0.050121549516916275,
|
| 54969 |
+
"learning_rate": 0.00016303030303030304,
|
| 54970 |
+
"loss": 3.063870906829834,
|
| 54971 |
+
"step": 15694
|
| 54972 |
+
},
|
| 54973 |
+
{
|
| 54974 |
+
"epoch": 0.9512727272727273,
|
| 54975 |
+
"grad_norm": 0.0517585463821888,
|
| 54976 |
+
"learning_rate": 0.00016262626262626264,
|
| 54977 |
+
"loss": 3.1038029193878174,
|
| 54978 |
+
"step": 15696
|
| 54979 |
+
},
|
| 54980 |
+
{
|
| 54981 |
+
"epoch": 0.9513939393939393,
|
| 54982 |
+
"grad_norm": 0.05002948269248009,
|
| 54983 |
+
"learning_rate": 0.00016222222222222224,
|
| 54984 |
+
"loss": 3.060966730117798,
|
| 54985 |
+
"step": 15698
|
| 54986 |
+
},
|
| 54987 |
+
{
|
| 54988 |
+
"epoch": 0.9515151515151515,
|
| 54989 |
+
"grad_norm": 0.04929853975772858,
|
| 54990 |
+
"learning_rate": 0.00016181818181818184,
|
| 54991 |
+
"loss": 3.042423725128174,
|
| 54992 |
+
"step": 15700
|
| 54993 |
+
},
|
| 54994 |
+
{
|
| 54995 |
+
"epoch": 0.9516363636363636,
|
| 54996 |
+
"grad_norm": 0.04830727353692055,
|
| 54997 |
+
"learning_rate": 0.0001614141414141414,
|
| 54998 |
+
"loss": 3.0788261890411377,
|
| 54999 |
+
"step": 15702
|
| 55000 |
+
},
|
| 55001 |
+
{
|
| 55002 |
+
"epoch": 0.9517575757575758,
|
| 55003 |
+
"grad_norm": 0.04835592210292816,
|
| 55004 |
+
"learning_rate": 0.000161010101010101,
|
| 55005 |
+
"loss": 3.041840076446533,
|
| 55006 |
+
"step": 15704
|
| 55007 |
+
},
|
| 55008 |
+
{
|
| 55009 |
+
"epoch": 0.9518787878787879,
|
| 55010 |
+
"grad_norm": 0.04859842732548714,
|
| 55011 |
+
"learning_rate": 0.0001606060606060606,
|
| 55012 |
+
"loss": 3.039973735809326,
|
| 55013 |
+
"step": 15706
|
| 55014 |
+
},
|
| 55015 |
+
{
|
| 55016 |
+
"epoch": 0.952,
|
| 55017 |
+
"grad_norm": 0.049100473523139954,
|
| 55018 |
+
"learning_rate": 0.00016020202020202023,
|
| 55019 |
+
"loss": 3.0315284729003906,
|
| 55020 |
+
"step": 15708
|
| 55021 |
+
},
|
| 55022 |
+
{
|
| 55023 |
+
"epoch": 0.9521212121212121,
|
| 55024 |
+
"grad_norm": 0.050308942794799805,
|
| 55025 |
+
"learning_rate": 0.00015979797979797983,
|
| 55026 |
+
"loss": 3.0698208808898926,
|
| 55027 |
+
"step": 15710
|
| 55028 |
+
},
|
| 55029 |
+
{
|
| 55030 |
+
"epoch": 0.9522424242424242,
|
| 55031 |
+
"grad_norm": 0.05116778984665871,
|
| 55032 |
+
"learning_rate": 0.0001593939393939394,
|
| 55033 |
+
"loss": 3.0448875427246094,
|
| 55034 |
+
"step": 15712
|
| 55035 |
+
},
|
| 55036 |
+
{
|
| 55037 |
+
"epoch": 0.9523636363636364,
|
| 55038 |
+
"grad_norm": 0.0494735985994339,
|
| 55039 |
+
"learning_rate": 0.000158989898989899,
|
| 55040 |
+
"loss": 3.0764763355255127,
|
| 55041 |
+
"step": 15714
|
| 55042 |
+
},
|
| 55043 |
+
{
|
| 55044 |
+
"epoch": 0.9524848484848485,
|
| 55045 |
+
"grad_norm": 0.060145922005176544,
|
| 55046 |
+
"learning_rate": 0.0001585858585858586,
|
| 55047 |
+
"loss": 3.077226400375366,
|
| 55048 |
+
"step": 15716
|
| 55049 |
+
},
|
| 55050 |
+
{
|
| 55051 |
+
"epoch": 0.9526060606060606,
|
| 55052 |
+
"grad_norm": 0.04869908466935158,
|
| 55053 |
+
"learning_rate": 0.0001581818181818182,
|
| 55054 |
+
"loss": 3.072455406188965,
|
| 55055 |
+
"step": 15718
|
| 55056 |
+
},
|
| 55057 |
+
{
|
| 55058 |
+
"epoch": 0.9527272727272728,
|
| 55059 |
+
"grad_norm": 0.05627526342868805,
|
| 55060 |
+
"learning_rate": 0.0001577777777777778,
|
| 55061 |
+
"loss": 3.0303144454956055,
|
| 55062 |
+
"step": 15720
|
| 55063 |
+
},
|
| 55064 |
+
{
|
| 55065 |
+
"epoch": 0.9528484848484848,
|
| 55066 |
+
"grad_norm": 0.04811324551701546,
|
| 55067 |
+
"learning_rate": 0.00015737373737373739,
|
| 55068 |
+
"loss": 3.0413079261779785,
|
| 55069 |
+
"step": 15722
|
| 55070 |
+
},
|
| 55071 |
+
{
|
| 55072 |
+
"epoch": 0.952969696969697,
|
| 55073 |
+
"grad_norm": 0.051033999770879745,
|
| 55074 |
+
"learning_rate": 0.00015696969696969696,
|
| 55075 |
+
"loss": 3.095437526702881,
|
| 55076 |
+
"step": 15724
|
| 55077 |
+
},
|
| 55078 |
+
{
|
| 55079 |
+
"epoch": 0.9530909090909091,
|
| 55080 |
+
"grad_norm": 0.04885207861661911,
|
| 55081 |
+
"learning_rate": 0.00015656565656565658,
|
| 55082 |
+
"loss": 3.08821439743042,
|
| 55083 |
+
"step": 15726
|
| 55084 |
+
},
|
| 55085 |
+
{
|
| 55086 |
+
"epoch": 0.9532121212121212,
|
| 55087 |
+
"grad_norm": 0.05047230049967766,
|
| 55088 |
+
"learning_rate": 0.00015616161616161618,
|
| 55089 |
+
"loss": 3.063981533050537,
|
| 55090 |
+
"step": 15728
|
| 55091 |
+
},
|
| 55092 |
+
{
|
| 55093 |
+
"epoch": 0.9533333333333334,
|
| 55094 |
+
"grad_norm": 0.04993906244635582,
|
| 55095 |
+
"learning_rate": 0.00015575757575757578,
|
| 55096 |
+
"loss": 3.0649547576904297,
|
| 55097 |
+
"step": 15730
|
| 55098 |
+
},
|
| 55099 |
+
{
|
| 55100 |
+
"epoch": 0.9534545454545454,
|
| 55101 |
+
"grad_norm": 0.04901989549398422,
|
| 55102 |
+
"learning_rate": 0.00015535353535353538,
|
| 55103 |
+
"loss": 3.0588221549987793,
|
| 55104 |
+
"step": 15732
|
| 55105 |
+
},
|
| 55106 |
+
{
|
| 55107 |
+
"epoch": 0.9535757575757575,
|
| 55108 |
+
"grad_norm": 0.05232423171401024,
|
| 55109 |
+
"learning_rate": 0.00015494949494949495,
|
| 55110 |
+
"loss": 3.0712108612060547,
|
| 55111 |
+
"step": 15734
|
| 55112 |
+
},
|
| 55113 |
+
{
|
| 55114 |
+
"epoch": 0.9536969696969697,
|
| 55115 |
+
"grad_norm": 0.051649320870637894,
|
| 55116 |
+
"learning_rate": 0.00015454545454545454,
|
| 55117 |
+
"loss": 3.0475387573242188,
|
| 55118 |
+
"step": 15736
|
| 55119 |
+
},
|
| 55120 |
+
{
|
| 55121 |
+
"epoch": 0.9538181818181818,
|
| 55122 |
+
"grad_norm": 0.05005862936377525,
|
| 55123 |
+
"learning_rate": 0.00015414141414141414,
|
| 55124 |
+
"loss": 3.088308095932007,
|
| 55125 |
+
"step": 15738
|
| 55126 |
+
},
|
| 55127 |
+
{
|
| 55128 |
+
"epoch": 0.953939393939394,
|
| 55129 |
+
"grad_norm": 0.049746960401535034,
|
| 55130 |
+
"learning_rate": 0.00015373737373737374,
|
| 55131 |
+
"loss": 3.082504987716675,
|
| 55132 |
+
"step": 15740
|
| 55133 |
+
},
|
| 55134 |
+
{
|
| 55135 |
+
"epoch": 0.954060606060606,
|
| 55136 |
+
"grad_norm": 0.04855158552527428,
|
| 55137 |
+
"learning_rate": 0.00015333333333333334,
|
| 55138 |
+
"loss": 3.0292022228240967,
|
| 55139 |
+
"step": 15742
|
| 55140 |
+
},
|
| 55141 |
+
{
|
| 55142 |
+
"epoch": 0.9541818181818181,
|
| 55143 |
+
"grad_norm": 0.04768714681267738,
|
| 55144 |
+
"learning_rate": 0.00015292929292929294,
|
| 55145 |
+
"loss": 3.0590527057647705,
|
| 55146 |
+
"step": 15744
|
| 55147 |
+
},
|
| 55148 |
+
{
|
| 55149 |
+
"epoch": 0.9543030303030303,
|
| 55150 |
+
"grad_norm": 0.04855417087674141,
|
| 55151 |
+
"learning_rate": 0.00015252525252525253,
|
| 55152 |
+
"loss": 3.1062064170837402,
|
| 55153 |
+
"step": 15746
|
| 55154 |
+
},
|
| 55155 |
+
{
|
| 55156 |
+
"epoch": 0.9544242424242424,
|
| 55157 |
+
"grad_norm": 0.05530768632888794,
|
| 55158 |
+
"learning_rate": 0.00015212121212121213,
|
| 55159 |
+
"loss": 3.082184314727783,
|
| 55160 |
+
"step": 15748
|
| 55161 |
+
},
|
| 55162 |
+
{
|
| 55163 |
+
"epoch": 0.9545454545454546,
|
| 55164 |
+
"grad_norm": 0.04959571734070778,
|
| 55165 |
+
"learning_rate": 0.00015171717171717173,
|
| 55166 |
+
"loss": 3.034513473510742,
|
| 55167 |
+
"step": 15750
|
| 55168 |
+
},
|
| 55169 |
+
{
|
| 55170 |
+
"epoch": 0.9546666666666667,
|
| 55171 |
+
"grad_norm": 0.05376448482275009,
|
| 55172 |
+
"learning_rate": 0.00015131313131313133,
|
| 55173 |
+
"loss": 3.058668851852417,
|
| 55174 |
+
"step": 15752
|
| 55175 |
+
},
|
| 55176 |
+
{
|
| 55177 |
+
"epoch": 0.9547878787878787,
|
| 55178 |
+
"grad_norm": 0.04869585484266281,
|
| 55179 |
+
"learning_rate": 0.0001509090909090909,
|
| 55180 |
+
"loss": 3.086904764175415,
|
| 55181 |
+
"step": 15754
|
| 55182 |
+
},
|
| 55183 |
+
{
|
| 55184 |
+
"epoch": 0.9549090909090909,
|
| 55185 |
+
"grad_norm": 0.051713403314352036,
|
| 55186 |
+
"learning_rate": 0.0001505050505050505,
|
| 55187 |
+
"loss": 3.0616326332092285,
|
| 55188 |
+
"step": 15756
|
| 55189 |
+
},
|
| 55190 |
+
{
|
| 55191 |
+
"epoch": 0.955030303030303,
|
| 55192 |
+
"grad_norm": 0.05046727880835533,
|
| 55193 |
+
"learning_rate": 0.0001501010101010101,
|
| 55194 |
+
"loss": 3.0670979022979736,
|
| 55195 |
+
"step": 15758
|
| 55196 |
+
},
|
| 55197 |
+
{
|
| 55198 |
+
"epoch": 0.9551515151515152,
|
| 55199 |
+
"grad_norm": 0.04920874163508415,
|
| 55200 |
+
"learning_rate": 0.00014969696969696972,
|
| 55201 |
+
"loss": 3.0991592407226562,
|
| 55202 |
+
"step": 15760
|
| 55203 |
+
},
|
| 55204 |
+
{
|
| 55205 |
+
"epoch": 0.9552727272727273,
|
| 55206 |
+
"grad_norm": 0.05251651257276535,
|
| 55207 |
+
"learning_rate": 0.00014929292929292932,
|
| 55208 |
+
"loss": 3.0664758682250977,
|
| 55209 |
+
"step": 15762
|
| 55210 |
+
},
|
| 55211 |
+
{
|
| 55212 |
+
"epoch": 0.9553939393939394,
|
| 55213 |
+
"grad_norm": 0.049125295132398605,
|
| 55214 |
+
"learning_rate": 0.0001488888888888889,
|
| 55215 |
+
"loss": 3.0915982723236084,
|
| 55216 |
+
"step": 15764
|
| 55217 |
+
},
|
| 55218 |
+
{
|
| 55219 |
+
"epoch": 0.9555151515151515,
|
| 55220 |
+
"grad_norm": 0.048347122967243195,
|
| 55221 |
+
"learning_rate": 0.00014848484848484849,
|
| 55222 |
+
"loss": 3.070382595062256,
|
| 55223 |
+
"step": 15766
|
| 55224 |
+
},
|
| 55225 |
+
{
|
| 55226 |
+
"epoch": 0.9556363636363636,
|
| 55227 |
+
"grad_norm": 0.04870107024908066,
|
| 55228 |
+
"learning_rate": 0.00014808080808080808,
|
| 55229 |
+
"loss": 3.075108051300049,
|
| 55230 |
+
"step": 15768
|
| 55231 |
+
},
|
| 55232 |
+
{
|
| 55233 |
+
"epoch": 0.9557575757575758,
|
| 55234 |
+
"grad_norm": 0.0488167405128479,
|
| 55235 |
+
"learning_rate": 0.00014767676767676768,
|
| 55236 |
+
"loss": 3.0865166187286377,
|
| 55237 |
+
"step": 15770
|
| 55238 |
+
},
|
| 55239 |
+
{
|
| 55240 |
+
"epoch": 0.9558787878787879,
|
| 55241 |
+
"grad_norm": 0.05521353706717491,
|
| 55242 |
+
"learning_rate": 0.00014727272727272728,
|
| 55243 |
+
"loss": 3.079735040664673,
|
| 55244 |
+
"step": 15772
|
| 55245 |
+
},
|
| 55246 |
+
{
|
| 55247 |
+
"epoch": 0.956,
|
| 55248 |
+
"grad_norm": 0.04917971417307854,
|
| 55249 |
+
"learning_rate": 0.00014686868686868688,
|
| 55250 |
+
"loss": 3.0745558738708496,
|
| 55251 |
+
"step": 15774
|
| 55252 |
+
},
|
| 55253 |
+
{
|
| 55254 |
+
"epoch": 0.9561212121212121,
|
| 55255 |
+
"grad_norm": 0.05129864066839218,
|
| 55256 |
+
"learning_rate": 0.00014646464646464648,
|
| 55257 |
+
"loss": 3.0585780143737793,
|
| 55258 |
+
"step": 15776
|
| 55259 |
+
},
|
| 55260 |
+
{
|
| 55261 |
+
"epoch": 0.9562424242424242,
|
| 55262 |
+
"grad_norm": 0.05071466416120529,
|
| 55263 |
+
"learning_rate": 0.00014606060606060607,
|
| 55264 |
+
"loss": 3.1265082359313965,
|
| 55265 |
+
"step": 15778
|
| 55266 |
+
},
|
| 55267 |
+
{
|
| 55268 |
+
"epoch": 0.9563636363636364,
|
| 55269 |
+
"grad_norm": 0.05265762656927109,
|
| 55270 |
+
"learning_rate": 0.00014565656565656567,
|
| 55271 |
+
"loss": 3.0922024250030518,
|
| 55272 |
+
"step": 15780
|
| 55273 |
+
},
|
| 55274 |
+
{
|
| 55275 |
+
"epoch": 0.9564848484848485,
|
| 55276 |
+
"grad_norm": 0.05322057753801346,
|
| 55277 |
+
"learning_rate": 0.00014525252525252527,
|
| 55278 |
+
"loss": 3.0842103958129883,
|
| 55279 |
+
"step": 15782
|
| 55280 |
+
},
|
| 55281 |
+
{
|
| 55282 |
+
"epoch": 0.9566060606060606,
|
| 55283 |
+
"grad_norm": 0.04821353778243065,
|
| 55284 |
+
"learning_rate": 0.00014484848484848487,
|
| 55285 |
+
"loss": 3.0852701663970947,
|
| 55286 |
+
"step": 15784
|
| 55287 |
+
},
|
| 55288 |
+
{
|
| 55289 |
+
"epoch": 0.9567272727272728,
|
| 55290 |
+
"grad_norm": 0.04867221415042877,
|
| 55291 |
+
"learning_rate": 0.00014444444444444444,
|
| 55292 |
+
"loss": 3.073138475418091,
|
| 55293 |
+
"step": 15786
|
| 55294 |
+
},
|
| 55295 |
+
{
|
| 55296 |
+
"epoch": 0.9568484848484848,
|
| 55297 |
+
"grad_norm": 0.05084449425339699,
|
| 55298 |
+
"learning_rate": 0.00014404040404040404,
|
| 55299 |
+
"loss": 3.09576416015625,
|
| 55300 |
+
"step": 15788
|
| 55301 |
+
},
|
| 55302 |
+
{
|
| 55303 |
+
"epoch": 0.9569696969696969,
|
| 55304 |
+
"grad_norm": 0.04853491112589836,
|
| 55305 |
+
"learning_rate": 0.00014363636363636363,
|
| 55306 |
+
"loss": 3.089974880218506,
|
| 55307 |
+
"step": 15790
|
| 55308 |
+
},
|
| 55309 |
+
{
|
| 55310 |
+
"epoch": 0.9570909090909091,
|
| 55311 |
+
"grad_norm": 0.048672761768102646,
|
| 55312 |
+
"learning_rate": 0.00014323232323232323,
|
| 55313 |
+
"loss": 3.050147771835327,
|
| 55314 |
+
"step": 15792
|
| 55315 |
+
},
|
| 55316 |
+
{
|
| 55317 |
+
"epoch": 0.9572121212121212,
|
| 55318 |
+
"grad_norm": 0.0500684417784214,
|
| 55319 |
+
"learning_rate": 0.00014282828282828286,
|
| 55320 |
+
"loss": 3.0851659774780273,
|
| 55321 |
+
"step": 15794
|
| 55322 |
+
},
|
| 55323 |
+
{
|
| 55324 |
+
"epoch": 0.9573333333333334,
|
| 55325 |
+
"grad_norm": 0.051558975130319595,
|
| 55326 |
+
"learning_rate": 0.00014242424242424243,
|
| 55327 |
+
"loss": 3.1109042167663574,
|
| 55328 |
+
"step": 15796
|
| 55329 |
+
},
|
| 55330 |
+
{
|
| 55331 |
+
"epoch": 0.9574545454545454,
|
| 55332 |
+
"grad_norm": 0.05559660121798515,
|
| 55333 |
+
"learning_rate": 0.00014202020202020203,
|
| 55334 |
+
"loss": 3.1125175952911377,
|
| 55335 |
+
"step": 15798
|
| 55336 |
+
},
|
| 55337 |
+
{
|
| 55338 |
+
"epoch": 0.9575757575757575,
|
| 55339 |
+
"grad_norm": 0.05025303363800049,
|
| 55340 |
+
"learning_rate": 0.00014161616161616162,
|
| 55341 |
+
"loss": 3.0782811641693115,
|
| 55342 |
+
"step": 15800
|
| 55343 |
+
},
|
| 55344 |
+
{
|
| 55345 |
+
"epoch": 0.9576969696969697,
|
| 55346 |
+
"grad_norm": 0.05206725373864174,
|
| 55347 |
+
"learning_rate": 0.00014121212121212122,
|
| 55348 |
+
"loss": 3.1086833477020264,
|
| 55349 |
+
"step": 15802
|
| 55350 |
+
},
|
| 55351 |
+
{
|
| 55352 |
+
"epoch": 0.9578181818181818,
|
| 55353 |
+
"grad_norm": 0.05180590599775314,
|
| 55354 |
+
"learning_rate": 0.00014080808080808082,
|
| 55355 |
+
"loss": 3.0979292392730713,
|
| 55356 |
+
"step": 15804
|
| 55357 |
+
},
|
| 55358 |
+
{
|
| 55359 |
+
"epoch": 0.957939393939394,
|
| 55360 |
+
"grad_norm": 0.057155441492795944,
|
| 55361 |
+
"learning_rate": 0.00014040404040404042,
|
| 55362 |
+
"loss": 3.0437703132629395,
|
| 55363 |
+
"step": 15806
|
| 55364 |
+
},
|
| 55365 |
+
{
|
| 55366 |
+
"epoch": 0.9580606060606061,
|
| 55367 |
+
"grad_norm": 0.04766825586557388,
|
| 55368 |
+
"learning_rate": 0.00014,
|
| 55369 |
+
"loss": 3.0877349376678467,
|
| 55370 |
+
"step": 15808
|
| 55371 |
+
},
|
| 55372 |
+
{
|
| 55373 |
+
"epoch": 0.9581818181818181,
|
| 55374 |
+
"grad_norm": 0.04803939536213875,
|
| 55375 |
+
"learning_rate": 0.0001395959595959596,
|
| 55376 |
+
"loss": 3.0672221183776855,
|
| 55377 |
+
"step": 15810
|
| 55378 |
+
},
|
| 55379 |
+
{
|
| 55380 |
+
"epoch": 0.9583030303030303,
|
| 55381 |
+
"grad_norm": 0.0549965463578701,
|
| 55382 |
+
"learning_rate": 0.0001391919191919192,
|
| 55383 |
+
"loss": 3.0717720985412598,
|
| 55384 |
+
"step": 15812
|
| 55385 |
+
},
|
| 55386 |
+
{
|
| 55387 |
+
"epoch": 0.9584242424242424,
|
| 55388 |
+
"grad_norm": 0.0514734722673893,
|
| 55389 |
+
"learning_rate": 0.0001387878787878788,
|
| 55390 |
+
"loss": 3.0707602500915527,
|
| 55391 |
+
"step": 15814
|
| 55392 |
+
},
|
| 55393 |
+
{
|
| 55394 |
+
"epoch": 0.9585454545454546,
|
| 55395 |
+
"grad_norm": 0.04876880720257759,
|
| 55396 |
+
"learning_rate": 0.0001383838383838384,
|
| 55397 |
+
"loss": 3.0840048789978027,
|
| 55398 |
+
"step": 15816
|
| 55399 |
+
},
|
| 55400 |
+
{
|
| 55401 |
+
"epoch": 0.9586666666666667,
|
| 55402 |
+
"grad_norm": 0.055530328303575516,
|
| 55403 |
+
"learning_rate": 0.00013797979797979798,
|
| 55404 |
+
"loss": 3.1017704010009766,
|
| 55405 |
+
"step": 15818
|
| 55406 |
+
},
|
| 55407 |
+
{
|
| 55408 |
+
"epoch": 0.9587878787878787,
|
| 55409 |
+
"grad_norm": 0.0503402054309845,
|
| 55410 |
+
"learning_rate": 0.00013757575757575758,
|
| 55411 |
+
"loss": 3.0865015983581543,
|
| 55412 |
+
"step": 15820
|
| 55413 |
+
},
|
| 55414 |
+
{
|
| 55415 |
+
"epoch": 0.9589090909090909,
|
| 55416 |
+
"grad_norm": 0.051434144377708435,
|
| 55417 |
+
"learning_rate": 0.00013717171717171717,
|
| 55418 |
+
"loss": 3.088186740875244,
|
| 55419 |
+
"step": 15822
|
| 55420 |
+
},
|
| 55421 |
+
{
|
| 55422 |
+
"epoch": 0.959030303030303,
|
| 55423 |
+
"grad_norm": 0.053344182670116425,
|
| 55424 |
+
"learning_rate": 0.00013676767676767677,
|
| 55425 |
+
"loss": 3.0878305435180664,
|
| 55426 |
+
"step": 15824
|
| 55427 |
+
},
|
| 55428 |
+
{
|
| 55429 |
+
"epoch": 0.9591515151515152,
|
| 55430 |
+
"grad_norm": 0.04888543114066124,
|
| 55431 |
+
"learning_rate": 0.00013636363636363637,
|
| 55432 |
+
"loss": 3.078613758087158,
|
| 55433 |
+
"step": 15826
|
| 55434 |
+
},
|
| 55435 |
+
{
|
| 55436 |
+
"epoch": 0.9592727272727273,
|
| 55437 |
+
"grad_norm": 0.05574370175600052,
|
| 55438 |
+
"learning_rate": 0.00013595959595959597,
|
| 55439 |
+
"loss": 3.1451833248138428,
|
| 55440 |
+
"step": 15828
|
| 55441 |
+
},
|
| 55442 |
+
{
|
| 55443 |
+
"epoch": 0.9593939393939394,
|
| 55444 |
+
"grad_norm": 0.055157892405986786,
|
| 55445 |
+
"learning_rate": 0.00013555555555555556,
|
| 55446 |
+
"loss": 3.088019609451294,
|
| 55447 |
+
"step": 15830
|
| 55448 |
+
},
|
| 55449 |
+
{
|
| 55450 |
+
"epoch": 0.9595151515151515,
|
| 55451 |
+
"grad_norm": 0.04848414286971092,
|
| 55452 |
+
"learning_rate": 0.00013515151515151516,
|
| 55453 |
+
"loss": 3.117337465286255,
|
| 55454 |
+
"step": 15832
|
| 55455 |
+
},
|
| 55456 |
+
{
|
| 55457 |
+
"epoch": 0.9596363636363636,
|
| 55458 |
+
"grad_norm": 0.059998758137226105,
|
| 55459 |
+
"learning_rate": 0.00013474747474747476,
|
| 55460 |
+
"loss": 3.1215593814849854,
|
| 55461 |
+
"step": 15834
|
| 55462 |
+
},
|
| 55463 |
+
{
|
| 55464 |
+
"epoch": 0.9597575757575758,
|
| 55465 |
+
"grad_norm": 0.049959585070610046,
|
| 55466 |
+
"learning_rate": 0.00013434343434343436,
|
| 55467 |
+
"loss": 3.1201400756835938,
|
| 55468 |
+
"step": 15836
|
| 55469 |
+
},
|
| 55470 |
+
{
|
| 55471 |
+
"epoch": 0.9598787878787879,
|
| 55472 |
+
"grad_norm": 0.04953428730368614,
|
| 55473 |
+
"learning_rate": 0.00013393939393939393,
|
| 55474 |
+
"loss": 3.060267448425293,
|
| 55475 |
+
"step": 15838
|
| 55476 |
+
},
|
| 55477 |
+
{
|
| 55478 |
+
"epoch": 0.96,
|
| 55479 |
+
"grad_norm": 0.04891553148627281,
|
| 55480 |
+
"learning_rate": 0.00013353535353535353,
|
| 55481 |
+
"loss": 3.091520071029663,
|
| 55482 |
+
"step": 15840
|
| 55483 |
}
|
| 55484 |
],
|
| 55485 |
"logging_steps": 2,
|
|
|
|
| 55499 |
"attributes": {}
|
| 55500 |
}
|
| 55501 |
},
|
| 55502 |
+
"total_flos": 3.7619745465690006e+19,
|
| 55503 |
"train_batch_size": 20,
|
| 55504 |
"trial_name": null,
|
| 55505 |
"trial_params": null
|