Text Generation
Transformers
Safetensors
llama
Generated from Trainer
trl
sft
unsloth
text-generation-inference
Instructions to use Ba2han/model-layered-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/model-layered-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/model-layered-1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/model-layered-1") model = AutoModelForCausalLM.from_pretrained("Ba2han/model-layered-1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/model-layered-1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/model-layered-1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/model-layered-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ba2han/model-layered-1
- SGLang
How to use Ba2han/model-layered-1 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/model-layered-1" \ --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/model-layered-1", "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/model-layered-1" \ --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/model-layered-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Desktop
- Docker Model Runner
How to use Ba2han/model-layered-1 with Docker Model Runner:
docker model run hf.co/Ba2han/model-layered-1
Training in progress, step 12000, 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 1000555808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ff0f96e24f1d88e7a13c54e6521a948d243ed2ce731a47512ec17b6c8bce2e0
|
| 3 |
size 1000555808
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1318473087
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbc40f347b4fe447db7aa41bb1127a32f8dc9ccb1ba31559e50f889599bb2622
|
| 3 |
size 1318473087
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71721b7935d6d6dd8d5dbb15fb4d353f26a47a8d1b70ce4ce8b22eab93e6a890
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -81908,6 +81908,2106 @@
|
|
| 81908 |
"learning_rate": 0.00022651069026093202,
|
| 81909 |
"loss": 1.8935,
|
| 81910 |
"step": 11700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81911 |
}
|
| 81912 |
],
|
| 81913 |
"logging_steps": 1,
|
|
@@ -81927,7 +84027,7 @@
|
|
| 81927 |
"attributes": {}
|
| 81928 |
}
|
| 81929 |
},
|
| 81930 |
-
"total_flos": 6.
|
| 81931 |
"train_batch_size": 8,
|
| 81932 |
"trial_name": null,
|
| 81933 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6666666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 12000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 81908 |
"learning_rate": 0.00022651069026093202,
|
| 81909 |
"loss": 1.8935,
|
| 81910 |
"step": 11700
|
| 81911 |
+
},
|
| 81912 |
+
{
|
| 81913 |
+
"epoch": 0.6500555555555556,
|
| 81914 |
+
"grad_norm": 0.0966796875,
|
| 81915 |
+
"learning_rate": 0.00022644650435297677,
|
| 81916 |
+
"loss": 1.9343,
|
| 81917 |
+
"step": 11701
|
| 81918 |
+
},
|
| 81919 |
+
{
|
| 81920 |
+
"epoch": 0.6501111111111111,
|
| 81921 |
+
"grad_norm": 0.09765625,
|
| 81922 |
+
"learning_rate": 0.00022638232394975064,
|
| 81923 |
+
"loss": 1.9338,
|
| 81924 |
+
"step": 11702
|
| 81925 |
+
},
|
| 81926 |
+
{
|
| 81927 |
+
"epoch": 0.6501666666666667,
|
| 81928 |
+
"grad_norm": 0.0986328125,
|
| 81929 |
+
"learning_rate": 0.00022631814905328904,
|
| 81930 |
+
"loss": 2.0128,
|
| 81931 |
+
"step": 11703
|
| 81932 |
+
},
|
| 81933 |
+
{
|
| 81934 |
+
"epoch": 0.6502222222222223,
|
| 81935 |
+
"grad_norm": 0.09765625,
|
| 81936 |
+
"learning_rate": 0.00022625397966562777,
|
| 81937 |
+
"loss": 1.8506,
|
| 81938 |
+
"step": 11704
|
| 81939 |
+
},
|
| 81940 |
+
{
|
| 81941 |
+
"epoch": 0.6502777777777777,
|
| 81942 |
+
"grad_norm": 0.0947265625,
|
| 81943 |
+
"learning_rate": 0.00022618981578880206,
|
| 81944 |
+
"loss": 1.7908,
|
| 81945 |
+
"step": 11705
|
| 81946 |
+
},
|
| 81947 |
+
{
|
| 81948 |
+
"epoch": 0.6503333333333333,
|
| 81949 |
+
"grad_norm": 0.095703125,
|
| 81950 |
+
"learning_rate": 0.0002261256574248468,
|
| 81951 |
+
"loss": 1.911,
|
| 81952 |
+
"step": 11706
|
| 81953 |
+
},
|
| 81954 |
+
{
|
| 81955 |
+
"epoch": 0.6503888888888889,
|
| 81956 |
+
"grad_norm": 0.09619140625,
|
| 81957 |
+
"learning_rate": 0.0002260615045757972,
|
| 81958 |
+
"loss": 1.9026,
|
| 81959 |
+
"step": 11707
|
| 81960 |
+
},
|
| 81961 |
+
{
|
| 81962 |
+
"epoch": 0.6504444444444445,
|
| 81963 |
+
"grad_norm": 0.09619140625,
|
| 81964 |
+
"learning_rate": 0.00022599735724368808,
|
| 81965 |
+
"loss": 1.8878,
|
| 81966 |
+
"step": 11708
|
| 81967 |
+
},
|
| 81968 |
+
{
|
| 81969 |
+
"epoch": 0.6505,
|
| 81970 |
+
"grad_norm": 0.0966796875,
|
| 81971 |
+
"learning_rate": 0.000225933215430554,
|
| 81972 |
+
"loss": 1.8746,
|
| 81973 |
+
"step": 11709
|
| 81974 |
+
},
|
| 81975 |
+
{
|
| 81976 |
+
"epoch": 0.6505555555555556,
|
| 81977 |
+
"grad_norm": 0.0966796875,
|
| 81978 |
+
"learning_rate": 0.0002258690791384292,
|
| 81979 |
+
"loss": 1.8939,
|
| 81980 |
+
"step": 11710
|
| 81981 |
+
},
|
| 81982 |
+
{
|
| 81983 |
+
"epoch": 0.6506111111111111,
|
| 81984 |
+
"grad_norm": 0.095703125,
|
| 81985 |
+
"learning_rate": 0.0002258049483693483,
|
| 81986 |
+
"loss": 1.8844,
|
| 81987 |
+
"step": 11711
|
| 81988 |
+
},
|
| 81989 |
+
{
|
| 81990 |
+
"epoch": 0.6506666666666666,
|
| 81991 |
+
"grad_norm": 0.09619140625,
|
| 81992 |
+
"learning_rate": 0.0002257408231253451,
|
| 81993 |
+
"loss": 1.9396,
|
| 81994 |
+
"step": 11712
|
| 81995 |
+
},
|
| 81996 |
+
{
|
| 81997 |
+
"epoch": 0.6507222222222222,
|
| 81998 |
+
"grad_norm": 0.095703125,
|
| 81999 |
+
"learning_rate": 0.00022567670340845354,
|
| 82000 |
+
"loss": 1.8953,
|
| 82001 |
+
"step": 11713
|
| 82002 |
+
},
|
| 82003 |
+
{
|
| 82004 |
+
"epoch": 0.6507777777777778,
|
| 82005 |
+
"grad_norm": 0.09716796875,
|
| 82006 |
+
"learning_rate": 0.00022561258922070744,
|
| 82007 |
+
"loss": 1.9702,
|
| 82008 |
+
"step": 11714
|
| 82009 |
+
},
|
| 82010 |
+
{
|
| 82011 |
+
"epoch": 0.6508333333333334,
|
| 82012 |
+
"grad_norm": 0.0986328125,
|
| 82013 |
+
"learning_rate": 0.00022554848056414027,
|
| 82014 |
+
"loss": 1.9134,
|
| 82015 |
+
"step": 11715
|
| 82016 |
+
},
|
| 82017 |
+
{
|
| 82018 |
+
"epoch": 0.6508888888888889,
|
| 82019 |
+
"grad_norm": 0.09765625,
|
| 82020 |
+
"learning_rate": 0.00022548437744078555,
|
| 82021 |
+
"loss": 1.9556,
|
| 82022 |
+
"step": 11716
|
| 82023 |
+
},
|
| 82024 |
+
{
|
| 82025 |
+
"epoch": 0.6509444444444444,
|
| 82026 |
+
"grad_norm": 0.09765625,
|
| 82027 |
+
"learning_rate": 0.00022542027985267632,
|
| 82028 |
+
"loss": 1.9487,
|
| 82029 |
+
"step": 11717
|
| 82030 |
+
},
|
| 82031 |
+
{
|
| 82032 |
+
"epoch": 0.651,
|
| 82033 |
+
"grad_norm": 0.095703125,
|
| 82034 |
+
"learning_rate": 0.00022535618780184584,
|
| 82035 |
+
"loss": 1.8488,
|
| 82036 |
+
"step": 11718
|
| 82037 |
+
},
|
| 82038 |
+
{
|
| 82039 |
+
"epoch": 0.6510555555555556,
|
| 82040 |
+
"grad_norm": 0.09521484375,
|
| 82041 |
+
"learning_rate": 0.00022529210129032675,
|
| 82042 |
+
"loss": 1.8569,
|
| 82043 |
+
"step": 11719
|
| 82044 |
+
},
|
| 82045 |
+
{
|
| 82046 |
+
"epoch": 0.6511111111111111,
|
| 82047 |
+
"grad_norm": 0.095703125,
|
| 82048 |
+
"learning_rate": 0.00022522802032015174,
|
| 82049 |
+
"loss": 1.9214,
|
| 82050 |
+
"step": 11720
|
| 82051 |
+
},
|
| 82052 |
+
{
|
| 82053 |
+
"epoch": 0.6511666666666667,
|
| 82054 |
+
"grad_norm": 0.0966796875,
|
| 82055 |
+
"learning_rate": 0.0002251639448933535,
|
| 82056 |
+
"loss": 1.8996,
|
| 82057 |
+
"step": 11721
|
| 82058 |
+
},
|
| 82059 |
+
{
|
| 82060 |
+
"epoch": 0.6512222222222223,
|
| 82061 |
+
"grad_norm": 0.09619140625,
|
| 82062 |
+
"learning_rate": 0.00022509987501196407,
|
| 82063 |
+
"loss": 1.9185,
|
| 82064 |
+
"step": 11722
|
| 82065 |
+
},
|
| 82066 |
+
{
|
| 82067 |
+
"epoch": 0.6512777777777777,
|
| 82068 |
+
"grad_norm": 0.095703125,
|
| 82069 |
+
"learning_rate": 0.00022503581067801593,
|
| 82070 |
+
"loss": 1.9303,
|
| 82071 |
+
"step": 11723
|
| 82072 |
+
},
|
| 82073 |
+
{
|
| 82074 |
+
"epoch": 0.6513333333333333,
|
| 82075 |
+
"grad_norm": 0.09521484375,
|
| 82076 |
+
"learning_rate": 0.00022497175189354097,
|
| 82077 |
+
"loss": 1.9265,
|
| 82078 |
+
"step": 11724
|
| 82079 |
+
},
|
| 82080 |
+
{
|
| 82081 |
+
"epoch": 0.6513888888888889,
|
| 82082 |
+
"grad_norm": 0.0966796875,
|
| 82083 |
+
"learning_rate": 0.00022490769866057072,
|
| 82084 |
+
"loss": 1.902,
|
| 82085 |
+
"step": 11725
|
| 82086 |
+
},
|
| 82087 |
+
{
|
| 82088 |
+
"epoch": 0.6514444444444445,
|
| 82089 |
+
"grad_norm": 0.09716796875,
|
| 82090 |
+
"learning_rate": 0.00022484365098113718,
|
| 82091 |
+
"loss": 1.9012,
|
| 82092 |
+
"step": 11726
|
| 82093 |
+
},
|
| 82094 |
+
{
|
| 82095 |
+
"epoch": 0.6515,
|
| 82096 |
+
"grad_norm": 0.0966796875,
|
| 82097 |
+
"learning_rate": 0.0002247796088572714,
|
| 82098 |
+
"loss": 1.925,
|
| 82099 |
+
"step": 11727
|
| 82100 |
+
},
|
| 82101 |
+
{
|
| 82102 |
+
"epoch": 0.6515555555555556,
|
| 82103 |
+
"grad_norm": 0.09619140625,
|
| 82104 |
+
"learning_rate": 0.00022471557229100512,
|
| 82105 |
+
"loss": 1.819,
|
| 82106 |
+
"step": 11728
|
| 82107 |
+
},
|
| 82108 |
+
{
|
| 82109 |
+
"epoch": 0.6516111111111111,
|
| 82110 |
+
"grad_norm": 0.09814453125,
|
| 82111 |
+
"learning_rate": 0.000224651541284369,
|
| 82112 |
+
"loss": 1.9469,
|
| 82113 |
+
"step": 11729
|
| 82114 |
+
},
|
| 82115 |
+
{
|
| 82116 |
+
"epoch": 0.6516666666666666,
|
| 82117 |
+
"grad_norm": 0.0966796875,
|
| 82118 |
+
"learning_rate": 0.00022458751583939433,
|
| 82119 |
+
"loss": 1.948,
|
| 82120 |
+
"step": 11730
|
| 82121 |
+
},
|
| 82122 |
+
{
|
| 82123 |
+
"epoch": 0.6517222222222222,
|
| 82124 |
+
"grad_norm": 0.09619140625,
|
| 82125 |
+
"learning_rate": 0.00022452349595811167,
|
| 82126 |
+
"loss": 1.9558,
|
| 82127 |
+
"step": 11731
|
| 82128 |
+
},
|
| 82129 |
+
{
|
| 82130 |
+
"epoch": 0.6517777777777778,
|
| 82131 |
+
"grad_norm": 0.095703125,
|
| 82132 |
+
"learning_rate": 0.00022445948164255146,
|
| 82133 |
+
"loss": 1.903,
|
| 82134 |
+
"step": 11732
|
| 82135 |
+
},
|
| 82136 |
+
{
|
| 82137 |
+
"epoch": 0.6518333333333334,
|
| 82138 |
+
"grad_norm": 0.095703125,
|
| 82139 |
+
"learning_rate": 0.0002243954728947444,
|
| 82140 |
+
"loss": 1.8658,
|
| 82141 |
+
"step": 11733
|
| 82142 |
+
},
|
| 82143 |
+
{
|
| 82144 |
+
"epoch": 0.6518888888888889,
|
| 82145 |
+
"grad_norm": 0.0966796875,
|
| 82146 |
+
"learning_rate": 0.00022433146971672047,
|
| 82147 |
+
"loss": 1.954,
|
| 82148 |
+
"step": 11734
|
| 82149 |
+
},
|
| 82150 |
+
{
|
| 82151 |
+
"epoch": 0.6519444444444444,
|
| 82152 |
+
"grad_norm": 0.09521484375,
|
| 82153 |
+
"learning_rate": 0.00022426747211050968,
|
| 82154 |
+
"loss": 1.8759,
|
| 82155 |
+
"step": 11735
|
| 82156 |
+
},
|
| 82157 |
+
{
|
| 82158 |
+
"epoch": 0.652,
|
| 82159 |
+
"grad_norm": 0.095703125,
|
| 82160 |
+
"learning_rate": 0.00022420348007814198,
|
| 82161 |
+
"loss": 1.8832,
|
| 82162 |
+
"step": 11736
|
| 82163 |
+
},
|
| 82164 |
+
{
|
| 82165 |
+
"epoch": 0.6520555555555556,
|
| 82166 |
+
"grad_norm": 0.0947265625,
|
| 82167 |
+
"learning_rate": 0.0002241394936216472,
|
| 82168 |
+
"loss": 1.8422,
|
| 82169 |
+
"step": 11737
|
| 82170 |
+
},
|
| 82171 |
+
{
|
| 82172 |
+
"epoch": 0.6521111111111111,
|
| 82173 |
+
"grad_norm": 0.09521484375,
|
| 82174 |
+
"learning_rate": 0.0002240755127430547,
|
| 82175 |
+
"loss": 1.8288,
|
| 82176 |
+
"step": 11738
|
| 82177 |
+
},
|
| 82178 |
+
{
|
| 82179 |
+
"epoch": 0.6521666666666667,
|
| 82180 |
+
"grad_norm": 0.09765625,
|
| 82181 |
+
"learning_rate": 0.00022401153744439368,
|
| 82182 |
+
"loss": 1.9451,
|
| 82183 |
+
"step": 11739
|
| 82184 |
+
},
|
| 82185 |
+
{
|
| 82186 |
+
"epoch": 0.6522222222222223,
|
| 82187 |
+
"grad_norm": 0.0947265625,
|
| 82188 |
+
"learning_rate": 0.00022394756772769355,
|
| 82189 |
+
"loss": 1.8807,
|
| 82190 |
+
"step": 11740
|
| 82191 |
+
},
|
| 82192 |
+
{
|
| 82193 |
+
"epoch": 0.6522777777777777,
|
| 82194 |
+
"grad_norm": 0.095703125,
|
| 82195 |
+
"learning_rate": 0.0002238836035949832,
|
| 82196 |
+
"loss": 1.9394,
|
| 82197 |
+
"step": 11741
|
| 82198 |
+
},
|
| 82199 |
+
{
|
| 82200 |
+
"epoch": 0.6523333333333333,
|
| 82201 |
+
"grad_norm": 0.09765625,
|
| 82202 |
+
"learning_rate": 0.00022381964504829128,
|
| 82203 |
+
"loss": 1.9862,
|
| 82204 |
+
"step": 11742
|
| 82205 |
+
},
|
| 82206 |
+
{
|
| 82207 |
+
"epoch": 0.6523888888888889,
|
| 82208 |
+
"grad_norm": 0.0966796875,
|
| 82209 |
+
"learning_rate": 0.00022375569208964646,
|
| 82210 |
+
"loss": 1.8661,
|
| 82211 |
+
"step": 11743
|
| 82212 |
+
},
|
| 82213 |
+
{
|
| 82214 |
+
"epoch": 0.6524444444444445,
|
| 82215 |
+
"grad_norm": 0.0966796875,
|
| 82216 |
+
"learning_rate": 0.00022369174472107757,
|
| 82217 |
+
"loss": 1.8705,
|
| 82218 |
+
"step": 11744
|
| 82219 |
+
},
|
| 82220 |
+
{
|
| 82221 |
+
"epoch": 0.6525,
|
| 82222 |
+
"grad_norm": 0.09814453125,
|
| 82223 |
+
"learning_rate": 0.00022362780294461225,
|
| 82224 |
+
"loss": 1.9078,
|
| 82225 |
+
"step": 11745
|
| 82226 |
+
},
|
| 82227 |
+
{
|
| 82228 |
+
"epoch": 0.6525555555555556,
|
| 82229 |
+
"grad_norm": 0.095703125,
|
| 82230 |
+
"learning_rate": 0.0002235638667622789,
|
| 82231 |
+
"loss": 1.8429,
|
| 82232 |
+
"step": 11746
|
| 82233 |
+
},
|
| 82234 |
+
{
|
| 82235 |
+
"epoch": 0.6526111111111111,
|
| 82236 |
+
"grad_norm": 0.09521484375,
|
| 82237 |
+
"learning_rate": 0.0002234999361761056,
|
| 82238 |
+
"loss": 1.791,
|
| 82239 |
+
"step": 11747
|
| 82240 |
+
},
|
| 82241 |
+
{
|
| 82242 |
+
"epoch": 0.6526666666666666,
|
| 82243 |
+
"grad_norm": 0.095703125,
|
| 82244 |
+
"learning_rate": 0.0002234360111881199,
|
| 82245 |
+
"loss": 1.9588,
|
| 82246 |
+
"step": 11748
|
| 82247 |
+
},
|
| 82248 |
+
{
|
| 82249 |
+
"epoch": 0.6527222222222222,
|
| 82250 |
+
"grad_norm": 0.095703125,
|
| 82251 |
+
"learning_rate": 0.00022337209180034928,
|
| 82252 |
+
"loss": 1.9438,
|
| 82253 |
+
"step": 11749
|
| 82254 |
+
},
|
| 82255 |
+
{
|
| 82256 |
+
"epoch": 0.6527777777777778,
|
| 82257 |
+
"grad_norm": 0.0966796875,
|
| 82258 |
+
"learning_rate": 0.0002233081780148213,
|
| 82259 |
+
"loss": 1.8306,
|
| 82260 |
+
"step": 11750
|
| 82261 |
+
},
|
| 82262 |
+
{
|
| 82263 |
+
"epoch": 0.6528333333333334,
|
| 82264 |
+
"grad_norm": 0.09716796875,
|
| 82265 |
+
"learning_rate": 0.00022324426983356315,
|
| 82266 |
+
"loss": 1.8644,
|
| 82267 |
+
"step": 11751
|
| 82268 |
+
},
|
| 82269 |
+
{
|
| 82270 |
+
"epoch": 0.6528888888888889,
|
| 82271 |
+
"grad_norm": 0.0966796875,
|
| 82272 |
+
"learning_rate": 0.00022318036725860156,
|
| 82273 |
+
"loss": 1.8791,
|
| 82274 |
+
"step": 11752
|
| 82275 |
+
},
|
| 82276 |
+
{
|
| 82277 |
+
"epoch": 0.6529444444444444,
|
| 82278 |
+
"grad_norm": 0.0966796875,
|
| 82279 |
+
"learning_rate": 0.00022311647029196364,
|
| 82280 |
+
"loss": 1.9116,
|
| 82281 |
+
"step": 11753
|
| 82282 |
+
},
|
| 82283 |
+
{
|
| 82284 |
+
"epoch": 0.653,
|
| 82285 |
+
"grad_norm": 0.09814453125,
|
| 82286 |
+
"learning_rate": 0.0002230525789356762,
|
| 82287 |
+
"loss": 1.9724,
|
| 82288 |
+
"step": 11754
|
| 82289 |
+
},
|
| 82290 |
+
{
|
| 82291 |
+
"epoch": 0.6530555555555555,
|
| 82292 |
+
"grad_norm": 0.09716796875,
|
| 82293 |
+
"learning_rate": 0.00022298869319176546,
|
| 82294 |
+
"loss": 1.9206,
|
| 82295 |
+
"step": 11755
|
| 82296 |
+
},
|
| 82297 |
+
{
|
| 82298 |
+
"epoch": 0.6531111111111111,
|
| 82299 |
+
"grad_norm": 0.0986328125,
|
| 82300 |
+
"learning_rate": 0.0002229248130622578,
|
| 82301 |
+
"loss": 1.9489,
|
| 82302 |
+
"step": 11756
|
| 82303 |
+
},
|
| 82304 |
+
{
|
| 82305 |
+
"epoch": 0.6531666666666667,
|
| 82306 |
+
"grad_norm": 0.09716796875,
|
| 82307 |
+
"learning_rate": 0.00022286093854917947,
|
| 82308 |
+
"loss": 1.9062,
|
| 82309 |
+
"step": 11757
|
| 82310 |
+
},
|
| 82311 |
+
{
|
| 82312 |
+
"epoch": 0.6532222222222223,
|
| 82313 |
+
"grad_norm": 0.095703125,
|
| 82314 |
+
"learning_rate": 0.00022279706965455627,
|
| 82315 |
+
"loss": 1.9219,
|
| 82316 |
+
"step": 11758
|
| 82317 |
+
},
|
| 82318 |
+
{
|
| 82319 |
+
"epoch": 0.6532777777777777,
|
| 82320 |
+
"grad_norm": 0.095703125,
|
| 82321 |
+
"learning_rate": 0.00022273320638041395,
|
| 82322 |
+
"loss": 1.9109,
|
| 82323 |
+
"step": 11759
|
| 82324 |
+
},
|
| 82325 |
+
{
|
| 82326 |
+
"epoch": 0.6533333333333333,
|
| 82327 |
+
"grad_norm": 0.0947265625,
|
| 82328 |
+
"learning_rate": 0.00022266934872877835,
|
| 82329 |
+
"loss": 1.8615,
|
| 82330 |
+
"step": 11760
|
| 82331 |
+
},
|
| 82332 |
+
{
|
| 82333 |
+
"epoch": 0.6533888888888889,
|
| 82334 |
+
"grad_norm": 0.09423828125,
|
| 82335 |
+
"learning_rate": 0.00022260549670167462,
|
| 82336 |
+
"loss": 1.8871,
|
| 82337 |
+
"step": 11761
|
| 82338 |
+
},
|
| 82339 |
+
{
|
| 82340 |
+
"epoch": 0.6534444444444445,
|
| 82341 |
+
"grad_norm": 0.095703125,
|
| 82342 |
+
"learning_rate": 0.00022254165030112825,
|
| 82343 |
+
"loss": 1.8635,
|
| 82344 |
+
"step": 11762
|
| 82345 |
+
},
|
| 82346 |
+
{
|
| 82347 |
+
"epoch": 0.6535,
|
| 82348 |
+
"grad_norm": 0.0966796875,
|
| 82349 |
+
"learning_rate": 0.00022247780952916406,
|
| 82350 |
+
"loss": 1.8755,
|
| 82351 |
+
"step": 11763
|
| 82352 |
+
},
|
| 82353 |
+
{
|
| 82354 |
+
"epoch": 0.6535555555555556,
|
| 82355 |
+
"grad_norm": 0.09521484375,
|
| 82356 |
+
"learning_rate": 0.00022241397438780723,
|
| 82357 |
+
"loss": 1.8892,
|
| 82358 |
+
"step": 11764
|
| 82359 |
+
},
|
| 82360 |
+
{
|
| 82361 |
+
"epoch": 0.6536111111111111,
|
| 82362 |
+
"grad_norm": 0.09521484375,
|
| 82363 |
+
"learning_rate": 0.0002223501448790822,
|
| 82364 |
+
"loss": 1.9292,
|
| 82365 |
+
"step": 11765
|
| 82366 |
+
},
|
| 82367 |
+
{
|
| 82368 |
+
"epoch": 0.6536666666666666,
|
| 82369 |
+
"grad_norm": 0.0966796875,
|
| 82370 |
+
"learning_rate": 0.0002222863210050136,
|
| 82371 |
+
"loss": 1.9604,
|
| 82372 |
+
"step": 11766
|
| 82373 |
+
},
|
| 82374 |
+
{
|
| 82375 |
+
"epoch": 0.6537222222222222,
|
| 82376 |
+
"grad_norm": 0.09619140625,
|
| 82377 |
+
"learning_rate": 0.00022222250276762582,
|
| 82378 |
+
"loss": 1.9572,
|
| 82379 |
+
"step": 11767
|
| 82380 |
+
},
|
| 82381 |
+
{
|
| 82382 |
+
"epoch": 0.6537777777777778,
|
| 82383 |
+
"grad_norm": 0.09619140625,
|
| 82384 |
+
"learning_rate": 0.00022215869016894285,
|
| 82385 |
+
"loss": 1.905,
|
| 82386 |
+
"step": 11768
|
| 82387 |
+
},
|
| 82388 |
+
{
|
| 82389 |
+
"epoch": 0.6538333333333334,
|
| 82390 |
+
"grad_norm": 0.0966796875,
|
| 82391 |
+
"learning_rate": 0.00022209488321098904,
|
| 82392 |
+
"loss": 1.9535,
|
| 82393 |
+
"step": 11769
|
| 82394 |
+
},
|
| 82395 |
+
{
|
| 82396 |
+
"epoch": 0.6538888888888889,
|
| 82397 |
+
"grad_norm": 0.095703125,
|
| 82398 |
+
"learning_rate": 0.0002220310818957879,
|
| 82399 |
+
"loss": 1.9067,
|
| 82400 |
+
"step": 11770
|
| 82401 |
+
},
|
| 82402 |
+
{
|
| 82403 |
+
"epoch": 0.6539444444444444,
|
| 82404 |
+
"grad_norm": 0.0966796875,
|
| 82405 |
+
"learning_rate": 0.00022196728622536304,
|
| 82406 |
+
"loss": 1.9234,
|
| 82407 |
+
"step": 11771
|
| 82408 |
+
},
|
| 82409 |
+
{
|
| 82410 |
+
"epoch": 0.654,
|
| 82411 |
+
"grad_norm": 0.09716796875,
|
| 82412 |
+
"learning_rate": 0.0002219034962017382,
|
| 82413 |
+
"loss": 1.9789,
|
| 82414 |
+
"step": 11772
|
| 82415 |
+
},
|
| 82416 |
+
{
|
| 82417 |
+
"epoch": 0.6540555555555555,
|
| 82418 |
+
"grad_norm": 0.095703125,
|
| 82419 |
+
"learning_rate": 0.00022183971182693633,
|
| 82420 |
+
"loss": 1.917,
|
| 82421 |
+
"step": 11773
|
| 82422 |
+
},
|
| 82423 |
+
{
|
| 82424 |
+
"epoch": 0.6541111111111111,
|
| 82425 |
+
"grad_norm": 0.09619140625,
|
| 82426 |
+
"learning_rate": 0.00022177593310298082,
|
| 82427 |
+
"loss": 1.8596,
|
| 82428 |
+
"step": 11774
|
| 82429 |
+
},
|
| 82430 |
+
{
|
| 82431 |
+
"epoch": 0.6541666666666667,
|
| 82432 |
+
"grad_norm": 0.09619140625,
|
| 82433 |
+
"learning_rate": 0.00022171216003189433,
|
| 82434 |
+
"loss": 1.8817,
|
| 82435 |
+
"step": 11775
|
| 82436 |
+
},
|
| 82437 |
+
{
|
| 82438 |
+
"epoch": 0.6542222222222223,
|
| 82439 |
+
"grad_norm": 0.095703125,
|
| 82440 |
+
"learning_rate": 0.00022164839261569984,
|
| 82441 |
+
"loss": 1.9074,
|
| 82442 |
+
"step": 11776
|
| 82443 |
+
},
|
| 82444 |
+
{
|
| 82445 |
+
"epoch": 0.6542777777777777,
|
| 82446 |
+
"grad_norm": 0.09619140625,
|
| 82447 |
+
"learning_rate": 0.00022158463085641982,
|
| 82448 |
+
"loss": 1.935,
|
| 82449 |
+
"step": 11777
|
| 82450 |
+
},
|
| 82451 |
+
{
|
| 82452 |
+
"epoch": 0.6543333333333333,
|
| 82453 |
+
"grad_norm": 0.095703125,
|
| 82454 |
+
"learning_rate": 0.0002215208747560765,
|
| 82455 |
+
"loss": 1.9349,
|
| 82456 |
+
"step": 11778
|
| 82457 |
+
},
|
| 82458 |
+
{
|
| 82459 |
+
"epoch": 0.6543888888888889,
|
| 82460 |
+
"grad_norm": 0.0966796875,
|
| 82461 |
+
"learning_rate": 0.0002214571243166923,
|
| 82462 |
+
"loss": 1.9228,
|
| 82463 |
+
"step": 11779
|
| 82464 |
+
},
|
| 82465 |
+
{
|
| 82466 |
+
"epoch": 0.6544444444444445,
|
| 82467 |
+
"grad_norm": 0.09521484375,
|
| 82468 |
+
"learning_rate": 0.0002213933795402892,
|
| 82469 |
+
"loss": 1.8686,
|
| 82470 |
+
"step": 11780
|
| 82471 |
+
},
|
| 82472 |
+
{
|
| 82473 |
+
"epoch": 0.6545,
|
| 82474 |
+
"grad_norm": 0.0947265625,
|
| 82475 |
+
"learning_rate": 0.00022132964042888875,
|
| 82476 |
+
"loss": 1.8611,
|
| 82477 |
+
"step": 11781
|
| 82478 |
+
},
|
| 82479 |
+
{
|
| 82480 |
+
"epoch": 0.6545555555555556,
|
| 82481 |
+
"grad_norm": 0.09716796875,
|
| 82482 |
+
"learning_rate": 0.00022126590698451292,
|
| 82483 |
+
"loss": 1.9215,
|
| 82484 |
+
"step": 11782
|
| 82485 |
+
},
|
| 82486 |
+
{
|
| 82487 |
+
"epoch": 0.6546111111111111,
|
| 82488 |
+
"grad_norm": 0.0966796875,
|
| 82489 |
+
"learning_rate": 0.00022120217920918326,
|
| 82490 |
+
"loss": 1.9233,
|
| 82491 |
+
"step": 11783
|
| 82492 |
+
},
|
| 82493 |
+
{
|
| 82494 |
+
"epoch": 0.6546666666666666,
|
| 82495 |
+
"grad_norm": 0.09716796875,
|
| 82496 |
+
"learning_rate": 0.00022113845710492095,
|
| 82497 |
+
"loss": 1.952,
|
| 82498 |
+
"step": 11784
|
| 82499 |
+
},
|
| 82500 |
+
{
|
| 82501 |
+
"epoch": 0.6547222222222222,
|
| 82502 |
+
"grad_norm": 0.09619140625,
|
| 82503 |
+
"learning_rate": 0.00022107474067374692,
|
| 82504 |
+
"loss": 1.8896,
|
| 82505 |
+
"step": 11785
|
| 82506 |
+
},
|
| 82507 |
+
{
|
| 82508 |
+
"epoch": 0.6547777777777778,
|
| 82509 |
+
"grad_norm": 0.09619140625,
|
| 82510 |
+
"learning_rate": 0.0002210110299176825,
|
| 82511 |
+
"loss": 1.8752,
|
| 82512 |
+
"step": 11786
|
| 82513 |
+
},
|
| 82514 |
+
{
|
| 82515 |
+
"epoch": 0.6548333333333334,
|
| 82516 |
+
"grad_norm": 0.0947265625,
|
| 82517 |
+
"learning_rate": 0.00022094732483874817,
|
| 82518 |
+
"loss": 1.8265,
|
| 82519 |
+
"step": 11787
|
| 82520 |
+
},
|
| 82521 |
+
{
|
| 82522 |
+
"epoch": 0.6548888888888889,
|
| 82523 |
+
"grad_norm": 0.09619140625,
|
| 82524 |
+
"learning_rate": 0.00022088362543896443,
|
| 82525 |
+
"loss": 1.9029,
|
| 82526 |
+
"step": 11788
|
| 82527 |
+
},
|
| 82528 |
+
{
|
| 82529 |
+
"epoch": 0.6549444444444444,
|
| 82530 |
+
"grad_norm": 0.09619140625,
|
| 82531 |
+
"learning_rate": 0.00022081993172035191,
|
| 82532 |
+
"loss": 1.8936,
|
| 82533 |
+
"step": 11789
|
| 82534 |
+
},
|
| 82535 |
+
{
|
| 82536 |
+
"epoch": 0.655,
|
| 82537 |
+
"grad_norm": 0.09619140625,
|
| 82538 |
+
"learning_rate": 0.000220756243684931,
|
| 82539 |
+
"loss": 1.8583,
|
| 82540 |
+
"step": 11790
|
| 82541 |
+
},
|
| 82542 |
+
{
|
| 82543 |
+
"epoch": 0.6550555555555555,
|
| 82544 |
+
"grad_norm": 0.095703125,
|
| 82545 |
+
"learning_rate": 0.00022069256133472123,
|
| 82546 |
+
"loss": 1.8689,
|
| 82547 |
+
"step": 11791
|
| 82548 |
+
},
|
| 82549 |
+
{
|
| 82550 |
+
"epoch": 0.6551111111111111,
|
| 82551 |
+
"grad_norm": 0.09521484375,
|
| 82552 |
+
"learning_rate": 0.00022062888467174277,
|
| 82553 |
+
"loss": 1.8665,
|
| 82554 |
+
"step": 11792
|
| 82555 |
+
},
|
| 82556 |
+
{
|
| 82557 |
+
"epoch": 0.6551666666666667,
|
| 82558 |
+
"grad_norm": 0.0947265625,
|
| 82559 |
+
"learning_rate": 0.00022056521369801538,
|
| 82560 |
+
"loss": 1.8606,
|
| 82561 |
+
"step": 11793
|
| 82562 |
+
},
|
| 82563 |
+
{
|
| 82564 |
+
"epoch": 0.6552222222222223,
|
| 82565 |
+
"grad_norm": 0.0947265625,
|
| 82566 |
+
"learning_rate": 0.00022050154841555844,
|
| 82567 |
+
"loss": 1.8085,
|
| 82568 |
+
"step": 11794
|
| 82569 |
+
},
|
| 82570 |
+
{
|
| 82571 |
+
"epoch": 0.6552777777777777,
|
| 82572 |
+
"grad_norm": 0.09423828125,
|
| 82573 |
+
"learning_rate": 0.00022043788882639115,
|
| 82574 |
+
"loss": 1.8387,
|
| 82575 |
+
"step": 11795
|
| 82576 |
+
},
|
| 82577 |
+
{
|
| 82578 |
+
"epoch": 0.6553333333333333,
|
| 82579 |
+
"grad_norm": 0.0966796875,
|
| 82580 |
+
"learning_rate": 0.0002203742349325327,
|
| 82581 |
+
"loss": 1.8823,
|
| 82582 |
+
"step": 11796
|
| 82583 |
+
},
|
| 82584 |
+
{
|
| 82585 |
+
"epoch": 0.6553888888888889,
|
| 82586 |
+
"grad_norm": 0.09521484375,
|
| 82587 |
+
"learning_rate": 0.00022031058673600257,
|
| 82588 |
+
"loss": 1.879,
|
| 82589 |
+
"step": 11797
|
| 82590 |
+
},
|
| 82591 |
+
{
|
| 82592 |
+
"epoch": 0.6554444444444445,
|
| 82593 |
+
"grad_norm": 0.09765625,
|
| 82594 |
+
"learning_rate": 0.00022024694423881868,
|
| 82595 |
+
"loss": 1.9107,
|
| 82596 |
+
"step": 11798
|
| 82597 |
+
},
|
| 82598 |
+
{
|
| 82599 |
+
"epoch": 0.6555,
|
| 82600 |
+
"grad_norm": 0.0947265625,
|
| 82601 |
+
"learning_rate": 0.00022018330744300006,
|
| 82602 |
+
"loss": 1.7561,
|
| 82603 |
+
"step": 11799
|
| 82604 |
+
},
|
| 82605 |
+
{
|
| 82606 |
+
"epoch": 0.6555555555555556,
|
| 82607 |
+
"grad_norm": 0.09814453125,
|
| 82608 |
+
"learning_rate": 0.00022011967635056546,
|
| 82609 |
+
"loss": 1.9328,
|
| 82610 |
+
"step": 11800
|
| 82611 |
+
},
|
| 82612 |
+
{
|
| 82613 |
+
"epoch": 0.6556111111111111,
|
| 82614 |
+
"grad_norm": 0.095703125,
|
| 82615 |
+
"learning_rate": 0.00022005605096353246,
|
| 82616 |
+
"loss": 1.8808,
|
| 82617 |
+
"step": 11801
|
| 82618 |
+
},
|
| 82619 |
+
{
|
| 82620 |
+
"epoch": 0.6556666666666666,
|
| 82621 |
+
"grad_norm": 0.09521484375,
|
| 82622 |
+
"learning_rate": 0.0002199924312839194,
|
| 82623 |
+
"loss": 1.8179,
|
| 82624 |
+
"step": 11802
|
| 82625 |
+
},
|
| 82626 |
+
{
|
| 82627 |
+
"epoch": 0.6557222222222222,
|
| 82628 |
+
"grad_norm": 0.09716796875,
|
| 82629 |
+
"learning_rate": 0.00021992881731374434,
|
| 82630 |
+
"loss": 1.8881,
|
| 82631 |
+
"step": 11803
|
| 82632 |
+
},
|
| 82633 |
+
{
|
| 82634 |
+
"epoch": 0.6557777777777778,
|
| 82635 |
+
"grad_norm": 0.09521484375,
|
| 82636 |
+
"learning_rate": 0.00021986520905502478,
|
| 82637 |
+
"loss": 1.898,
|
| 82638 |
+
"step": 11804
|
| 82639 |
+
},
|
| 82640 |
+
{
|
| 82641 |
+
"epoch": 0.6558333333333334,
|
| 82642 |
+
"grad_norm": 0.0966796875,
|
| 82643 |
+
"learning_rate": 0.00021980160650977816,
|
| 82644 |
+
"loss": 1.8461,
|
| 82645 |
+
"step": 11805
|
| 82646 |
+
},
|
| 82647 |
+
{
|
| 82648 |
+
"epoch": 0.6558888888888889,
|
| 82649 |
+
"grad_norm": 0.095703125,
|
| 82650 |
+
"learning_rate": 0.00021973800968002184,
|
| 82651 |
+
"loss": 1.8427,
|
| 82652 |
+
"step": 11806
|
| 82653 |
+
},
|
| 82654 |
+
{
|
| 82655 |
+
"epoch": 0.6559444444444444,
|
| 82656 |
+
"grad_norm": 0.09716796875,
|
| 82657 |
+
"learning_rate": 0.0002196744185677734,
|
| 82658 |
+
"loss": 1.9245,
|
| 82659 |
+
"step": 11807
|
| 82660 |
+
},
|
| 82661 |
+
{
|
| 82662 |
+
"epoch": 0.656,
|
| 82663 |
+
"grad_norm": 0.09765625,
|
| 82664 |
+
"learning_rate": 0.00021961083317504913,
|
| 82665 |
+
"loss": 1.8872,
|
| 82666 |
+
"step": 11808
|
| 82667 |
+
},
|
| 82668 |
+
{
|
| 82669 |
+
"epoch": 0.6560555555555555,
|
| 82670 |
+
"grad_norm": 0.0966796875,
|
| 82671 |
+
"learning_rate": 0.00021954725350386612,
|
| 82672 |
+
"loss": 1.8855,
|
| 82673 |
+
"step": 11809
|
| 82674 |
+
},
|
| 82675 |
+
{
|
| 82676 |
+
"epoch": 0.6561111111111111,
|
| 82677 |
+
"grad_norm": 0.09619140625,
|
| 82678 |
+
"learning_rate": 0.0002194836795562412,
|
| 82679 |
+
"loss": 1.926,
|
| 82680 |
+
"step": 11810
|
| 82681 |
+
},
|
| 82682 |
+
{
|
| 82683 |
+
"epoch": 0.6561666666666667,
|
| 82684 |
+
"grad_norm": 0.09814453125,
|
| 82685 |
+
"learning_rate": 0.00021942011133419055,
|
| 82686 |
+
"loss": 1.9547,
|
| 82687 |
+
"step": 11811
|
| 82688 |
+
},
|
| 82689 |
+
{
|
| 82690 |
+
"epoch": 0.6562222222222223,
|
| 82691 |
+
"grad_norm": 0.095703125,
|
| 82692 |
+
"learning_rate": 0.00021935654883973026,
|
| 82693 |
+
"loss": 1.8799,
|
| 82694 |
+
"step": 11812
|
| 82695 |
+
},
|
| 82696 |
+
{
|
| 82697 |
+
"epoch": 0.6562777777777777,
|
| 82698 |
+
"grad_norm": 0.09619140625,
|
| 82699 |
+
"learning_rate": 0.00021929299207487676,
|
| 82700 |
+
"loss": 1.7265,
|
| 82701 |
+
"step": 11813
|
| 82702 |
+
},
|
| 82703 |
+
{
|
| 82704 |
+
"epoch": 0.6563333333333333,
|
| 82705 |
+
"grad_norm": 0.09814453125,
|
| 82706 |
+
"learning_rate": 0.0002192294410416458,
|
| 82707 |
+
"loss": 1.8748,
|
| 82708 |
+
"step": 11814
|
| 82709 |
+
},
|
| 82710 |
+
{
|
| 82711 |
+
"epoch": 0.6563888888888889,
|
| 82712 |
+
"grad_norm": 0.09326171875,
|
| 82713 |
+
"learning_rate": 0.00021916589574205272,
|
| 82714 |
+
"loss": 1.8052,
|
| 82715 |
+
"step": 11815
|
| 82716 |
+
},
|
| 82717 |
+
{
|
| 82718 |
+
"epoch": 0.6564444444444445,
|
| 82719 |
+
"grad_norm": 0.09814453125,
|
| 82720 |
+
"learning_rate": 0.00021910235617811344,
|
| 82721 |
+
"loss": 1.8886,
|
| 82722 |
+
"step": 11816
|
| 82723 |
+
},
|
| 82724 |
+
{
|
| 82725 |
+
"epoch": 0.6565,
|
| 82726 |
+
"grad_norm": 0.09619140625,
|
| 82727 |
+
"learning_rate": 0.00021903882235184337,
|
| 82728 |
+
"loss": 1.8705,
|
| 82729 |
+
"step": 11817
|
| 82730 |
+
},
|
| 82731 |
+
{
|
| 82732 |
+
"epoch": 0.6565555555555556,
|
| 82733 |
+
"grad_norm": 0.095703125,
|
| 82734 |
+
"learning_rate": 0.00021897529426525742,
|
| 82735 |
+
"loss": 1.8535,
|
| 82736 |
+
"step": 11818
|
| 82737 |
+
},
|
| 82738 |
+
{
|
| 82739 |
+
"epoch": 0.6566111111111111,
|
| 82740 |
+
"grad_norm": 0.09716796875,
|
| 82741 |
+
"learning_rate": 0.00021891177192037052,
|
| 82742 |
+
"loss": 1.9446,
|
| 82743 |
+
"step": 11819
|
| 82744 |
+
},
|
| 82745 |
+
{
|
| 82746 |
+
"epoch": 0.6566666666666666,
|
| 82747 |
+
"grad_norm": 0.09521484375,
|
| 82748 |
+
"learning_rate": 0.00021884825531919764,
|
| 82749 |
+
"loss": 1.8746,
|
| 82750 |
+
"step": 11820
|
| 82751 |
+
},
|
| 82752 |
+
{
|
| 82753 |
+
"epoch": 0.6567222222222222,
|
| 82754 |
+
"grad_norm": 0.0966796875,
|
| 82755 |
+
"learning_rate": 0.0002187847444637532,
|
| 82756 |
+
"loss": 1.851,
|
| 82757 |
+
"step": 11821
|
| 82758 |
+
},
|
| 82759 |
+
{
|
| 82760 |
+
"epoch": 0.6567777777777778,
|
| 82761 |
+
"grad_norm": 0.09619140625,
|
| 82762 |
+
"learning_rate": 0.00021872123935605183,
|
| 82763 |
+
"loss": 1.8594,
|
| 82764 |
+
"step": 11822
|
| 82765 |
+
},
|
| 82766 |
+
{
|
| 82767 |
+
"epoch": 0.6568333333333334,
|
| 82768 |
+
"grad_norm": 0.09716796875,
|
| 82769 |
+
"learning_rate": 0.00021865773999810774,
|
| 82770 |
+
"loss": 1.8477,
|
| 82771 |
+
"step": 11823
|
| 82772 |
+
},
|
| 82773 |
+
{
|
| 82774 |
+
"epoch": 0.6568888888888889,
|
| 82775 |
+
"grad_norm": 0.0927734375,
|
| 82776 |
+
"learning_rate": 0.00021859424639193467,
|
| 82777 |
+
"loss": 1.7497,
|
| 82778 |
+
"step": 11824
|
| 82779 |
+
},
|
| 82780 |
+
{
|
| 82781 |
+
"epoch": 0.6569444444444444,
|
| 82782 |
+
"grad_norm": 0.095703125,
|
| 82783 |
+
"learning_rate": 0.00021853075853954694,
|
| 82784 |
+
"loss": 1.9208,
|
| 82785 |
+
"step": 11825
|
| 82786 |
+
},
|
| 82787 |
+
{
|
| 82788 |
+
"epoch": 0.657,
|
| 82789 |
+
"grad_norm": 0.0947265625,
|
| 82790 |
+
"learning_rate": 0.00021846727644295787,
|
| 82791 |
+
"loss": 1.8444,
|
| 82792 |
+
"step": 11826
|
| 82793 |
+
},
|
| 82794 |
+
{
|
| 82795 |
+
"epoch": 0.6570555555555555,
|
| 82796 |
+
"grad_norm": 0.095703125,
|
| 82797 |
+
"learning_rate": 0.0002184038001041813,
|
| 82798 |
+
"loss": 1.842,
|
| 82799 |
+
"step": 11827
|
| 82800 |
+
},
|
| 82801 |
+
{
|
| 82802 |
+
"epoch": 0.6571111111111111,
|
| 82803 |
+
"grad_norm": 0.0966796875,
|
| 82804 |
+
"learning_rate": 0.0002183403295252303,
|
| 82805 |
+
"loss": 1.9012,
|
| 82806 |
+
"step": 11828
|
| 82807 |
+
},
|
| 82808 |
+
{
|
| 82809 |
+
"epoch": 0.6571666666666667,
|
| 82810 |
+
"grad_norm": 0.09619140625,
|
| 82811 |
+
"learning_rate": 0.0002182768647081182,
|
| 82812 |
+
"loss": 1.8665,
|
| 82813 |
+
"step": 11829
|
| 82814 |
+
},
|
| 82815 |
+
{
|
| 82816 |
+
"epoch": 0.6572222222222223,
|
| 82817 |
+
"grad_norm": 0.095703125,
|
| 82818 |
+
"learning_rate": 0.00021821340565485788,
|
| 82819 |
+
"loss": 1.8776,
|
| 82820 |
+
"step": 11830
|
| 82821 |
+
},
|
| 82822 |
+
{
|
| 82823 |
+
"epoch": 0.6572777777777777,
|
| 82824 |
+
"grad_norm": 0.0947265625,
|
| 82825 |
+
"learning_rate": 0.00021814995236746194,
|
| 82826 |
+
"loss": 1.7991,
|
| 82827 |
+
"step": 11831
|
| 82828 |
+
},
|
| 82829 |
+
{
|
| 82830 |
+
"epoch": 0.6573333333333333,
|
| 82831 |
+
"grad_norm": 0.09521484375,
|
| 82832 |
+
"learning_rate": 0.00021808650484794338,
|
| 82833 |
+
"loss": 1.8702,
|
| 82834 |
+
"step": 11832
|
| 82835 |
+
},
|
| 82836 |
+
{
|
| 82837 |
+
"epoch": 0.6573888888888889,
|
| 82838 |
+
"grad_norm": 0.09716796875,
|
| 82839 |
+
"learning_rate": 0.0002180230630983143,
|
| 82840 |
+
"loss": 1.935,
|
| 82841 |
+
"step": 11833
|
| 82842 |
+
},
|
| 82843 |
+
{
|
| 82844 |
+
"epoch": 0.6574444444444445,
|
| 82845 |
+
"grad_norm": 0.09521484375,
|
| 82846 |
+
"learning_rate": 0.00021795962712058687,
|
| 82847 |
+
"loss": 1.8781,
|
| 82848 |
+
"step": 11834
|
| 82849 |
+
},
|
| 82850 |
+
{
|
| 82851 |
+
"epoch": 0.6575,
|
| 82852 |
+
"grad_norm": 0.09765625,
|
| 82853 |
+
"learning_rate": 0.0002178961969167733,
|
| 82854 |
+
"loss": 1.908,
|
| 82855 |
+
"step": 11835
|
| 82856 |
+
},
|
| 82857 |
+
{
|
| 82858 |
+
"epoch": 0.6575555555555556,
|
| 82859 |
+
"grad_norm": 0.09521484375,
|
| 82860 |
+
"learning_rate": 0.0002178327724888856,
|
| 82861 |
+
"loss": 1.8379,
|
| 82862 |
+
"step": 11836
|
| 82863 |
+
},
|
| 82864 |
+
{
|
| 82865 |
+
"epoch": 0.6576111111111111,
|
| 82866 |
+
"grad_norm": 0.0966796875,
|
| 82867 |
+
"learning_rate": 0.00021776935383893532,
|
| 82868 |
+
"loss": 1.8289,
|
| 82869 |
+
"step": 11837
|
| 82870 |
+
},
|
| 82871 |
+
{
|
| 82872 |
+
"epoch": 0.6576666666666666,
|
| 82873 |
+
"grad_norm": 0.09619140625,
|
| 82874 |
+
"learning_rate": 0.00021770594096893374,
|
| 82875 |
+
"loss": 1.9044,
|
| 82876 |
+
"step": 11838
|
| 82877 |
+
},
|
| 82878 |
+
{
|
| 82879 |
+
"epoch": 0.6577222222222222,
|
| 82880 |
+
"grad_norm": 0.09521484375,
|
| 82881 |
+
"learning_rate": 0.0002176425338808925,
|
| 82882 |
+
"loss": 1.8306,
|
| 82883 |
+
"step": 11839
|
| 82884 |
+
},
|
| 82885 |
+
{
|
| 82886 |
+
"epoch": 0.6577777777777778,
|
| 82887 |
+
"grad_norm": 0.09521484375,
|
| 82888 |
+
"learning_rate": 0.00021757913257682262,
|
| 82889 |
+
"loss": 1.8285,
|
| 82890 |
+
"step": 11840
|
| 82891 |
+
},
|
| 82892 |
+
{
|
| 82893 |
+
"epoch": 0.6578333333333334,
|
| 82894 |
+
"grad_norm": 0.09619140625,
|
| 82895 |
+
"learning_rate": 0.0002175157370587348,
|
| 82896 |
+
"loss": 1.9256,
|
| 82897 |
+
"step": 11841
|
| 82898 |
+
},
|
| 82899 |
+
{
|
| 82900 |
+
"epoch": 0.6578888888888889,
|
| 82901 |
+
"grad_norm": 0.09765625,
|
| 82902 |
+
"learning_rate": 0.0002174523473286401,
|
| 82903 |
+
"loss": 1.9239,
|
| 82904 |
+
"step": 11842
|
| 82905 |
+
},
|
| 82906 |
+
{
|
| 82907 |
+
"epoch": 0.6579444444444444,
|
| 82908 |
+
"grad_norm": 0.0947265625,
|
| 82909 |
+
"learning_rate": 0.00021738896338854927,
|
| 82910 |
+
"loss": 1.8097,
|
| 82911 |
+
"step": 11843
|
| 82912 |
+
},
|
| 82913 |
+
{
|
| 82914 |
+
"epoch": 0.658,
|
| 82915 |
+
"grad_norm": 0.095703125,
|
| 82916 |
+
"learning_rate": 0.00021732558524047222,
|
| 82917 |
+
"loss": 1.8709,
|
| 82918 |
+
"step": 11844
|
| 82919 |
+
},
|
| 82920 |
+
{
|
| 82921 |
+
"epoch": 0.6580555555555555,
|
| 82922 |
+
"grad_norm": 0.0966796875,
|
| 82923 |
+
"learning_rate": 0.00021726221288641932,
|
| 82924 |
+
"loss": 1.9015,
|
| 82925 |
+
"step": 11845
|
| 82926 |
+
},
|
| 82927 |
+
{
|
| 82928 |
+
"epoch": 0.6581111111111111,
|
| 82929 |
+
"grad_norm": 0.0966796875,
|
| 82930 |
+
"learning_rate": 0.00021719884632840093,
|
| 82931 |
+
"loss": 1.8927,
|
| 82932 |
+
"step": 11846
|
| 82933 |
+
},
|
| 82934 |
+
{
|
| 82935 |
+
"epoch": 0.6581666666666667,
|
| 82936 |
+
"grad_norm": 0.09765625,
|
| 82937 |
+
"learning_rate": 0.00021713548556842659,
|
| 82938 |
+
"loss": 1.8413,
|
| 82939 |
+
"step": 11847
|
| 82940 |
+
},
|
| 82941 |
+
{
|
| 82942 |
+
"epoch": 0.6582222222222223,
|
| 82943 |
+
"grad_norm": 0.09765625,
|
| 82944 |
+
"learning_rate": 0.00021707213060850587,
|
| 82945 |
+
"loss": 1.8434,
|
| 82946 |
+
"step": 11848
|
| 82947 |
+
},
|
| 82948 |
+
{
|
| 82949 |
+
"epoch": 0.6582777777777777,
|
| 82950 |
+
"grad_norm": 0.09765625,
|
| 82951 |
+
"learning_rate": 0.0002170087814506485,
|
| 82952 |
+
"loss": 1.9622,
|
| 82953 |
+
"step": 11849
|
| 82954 |
+
},
|
| 82955 |
+
{
|
| 82956 |
+
"epoch": 0.6583333333333333,
|
| 82957 |
+
"grad_norm": 0.09521484375,
|
| 82958 |
+
"learning_rate": 0.00021694543809686376,
|
| 82959 |
+
"loss": 1.8628,
|
| 82960 |
+
"step": 11850
|
| 82961 |
+
},
|
| 82962 |
+
{
|
| 82963 |
+
"epoch": 0.6583888888888889,
|
| 82964 |
+
"grad_norm": 0.0966796875,
|
| 82965 |
+
"learning_rate": 0.0002168821005491605,
|
| 82966 |
+
"loss": 1.8456,
|
| 82967 |
+
"step": 11851
|
| 82968 |
+
},
|
| 82969 |
+
{
|
| 82970 |
+
"epoch": 0.6584444444444445,
|
| 82971 |
+
"grad_norm": 0.0966796875,
|
| 82972 |
+
"learning_rate": 0.0002168187688095478,
|
| 82973 |
+
"loss": 1.9119,
|
| 82974 |
+
"step": 11852
|
| 82975 |
+
},
|
| 82976 |
+
{
|
| 82977 |
+
"epoch": 0.6585,
|
| 82978 |
+
"grad_norm": 0.09521484375,
|
| 82979 |
+
"learning_rate": 0.00021675544288003474,
|
| 82980 |
+
"loss": 1.8947,
|
| 82981 |
+
"step": 11853
|
| 82982 |
+
},
|
| 82983 |
+
{
|
| 82984 |
+
"epoch": 0.6585555555555556,
|
| 82985 |
+
"grad_norm": 0.09765625,
|
| 82986 |
+
"learning_rate": 0.00021669212276262924,
|
| 82987 |
+
"loss": 1.8638,
|
| 82988 |
+
"step": 11854
|
| 82989 |
+
},
|
| 82990 |
+
{
|
| 82991 |
+
"epoch": 0.6586111111111111,
|
| 82992 |
+
"grad_norm": 0.0966796875,
|
| 82993 |
+
"learning_rate": 0.00021662880845933996,
|
| 82994 |
+
"loss": 1.8176,
|
| 82995 |
+
"step": 11855
|
| 82996 |
+
},
|
| 82997 |
+
{
|
| 82998 |
+
"epoch": 0.6586666666666666,
|
| 82999 |
+
"grad_norm": 0.0986328125,
|
| 83000 |
+
"learning_rate": 0.0002165654999721753,
|
| 83001 |
+
"loss": 1.887,
|
| 83002 |
+
"step": 11856
|
| 83003 |
+
},
|
| 83004 |
+
{
|
| 83005 |
+
"epoch": 0.6587222222222222,
|
| 83006 |
+
"grad_norm": 0.0966796875,
|
| 83007 |
+
"learning_rate": 0.0002165021973031431,
|
| 83008 |
+
"loss": 1.8026,
|
| 83009 |
+
"step": 11857
|
| 83010 |
+
},
|
| 83011 |
+
{
|
| 83012 |
+
"epoch": 0.6587777777777778,
|
| 83013 |
+
"grad_norm": 0.0966796875,
|
| 83014 |
+
"learning_rate": 0.00021643890045425096,
|
| 83015 |
+
"loss": 1.8717,
|
| 83016 |
+
"step": 11858
|
| 83017 |
+
},
|
| 83018 |
+
{
|
| 83019 |
+
"epoch": 0.6588333333333334,
|
| 83020 |
+
"grad_norm": 0.0966796875,
|
| 83021 |
+
"learning_rate": 0.0002163756094275069,
|
| 83022 |
+
"loss": 1.9108,
|
| 83023 |
+
"step": 11859
|
| 83024 |
+
},
|
| 83025 |
+
{
|
| 83026 |
+
"epoch": 0.6588888888888889,
|
| 83027 |
+
"grad_norm": 0.09716796875,
|
| 83028 |
+
"learning_rate": 0.00021631232422491815,
|
| 83029 |
+
"loss": 1.7865,
|
| 83030 |
+
"step": 11860
|
| 83031 |
+
},
|
| 83032 |
+
{
|
| 83033 |
+
"epoch": 0.6589444444444444,
|
| 83034 |
+
"grad_norm": 0.09716796875,
|
| 83035 |
+
"learning_rate": 0.00021624904484849187,
|
| 83036 |
+
"loss": 1.9106,
|
| 83037 |
+
"step": 11861
|
| 83038 |
+
},
|
| 83039 |
+
{
|
| 83040 |
+
"epoch": 0.659,
|
| 83041 |
+
"grad_norm": 0.09619140625,
|
| 83042 |
+
"learning_rate": 0.00021618577130023527,
|
| 83043 |
+
"loss": 1.9264,
|
| 83044 |
+
"step": 11862
|
| 83045 |
+
},
|
| 83046 |
+
{
|
| 83047 |
+
"epoch": 0.6590555555555555,
|
| 83048 |
+
"grad_norm": 0.09375,
|
| 83049 |
+
"learning_rate": 0.00021612250358215546,
|
| 83050 |
+
"loss": 1.8302,
|
| 83051 |
+
"step": 11863
|
| 83052 |
+
},
|
| 83053 |
+
{
|
| 83054 |
+
"epoch": 0.6591111111111111,
|
| 83055 |
+
"grad_norm": 0.09912109375,
|
| 83056 |
+
"learning_rate": 0.00021605924169625887,
|
| 83057 |
+
"loss": 1.9019,
|
| 83058 |
+
"step": 11864
|
| 83059 |
+
},
|
| 83060 |
+
{
|
| 83061 |
+
"epoch": 0.6591666666666667,
|
| 83062 |
+
"grad_norm": 0.09765625,
|
| 83063 |
+
"learning_rate": 0.000215995985644552,
|
| 83064 |
+
"loss": 1.9262,
|
| 83065 |
+
"step": 11865
|
| 83066 |
+
},
|
| 83067 |
+
{
|
| 83068 |
+
"epoch": 0.6592222222222223,
|
| 83069 |
+
"grad_norm": 0.09716796875,
|
| 83070 |
+
"learning_rate": 0.00021593273542904143,
|
| 83071 |
+
"loss": 1.9736,
|
| 83072 |
+
"step": 11866
|
| 83073 |
+
},
|
| 83074 |
+
{
|
| 83075 |
+
"epoch": 0.6592777777777777,
|
| 83076 |
+
"grad_norm": 0.099609375,
|
| 83077 |
+
"learning_rate": 0.0002158694910517332,
|
| 83078 |
+
"loss": 1.9645,
|
| 83079 |
+
"step": 11867
|
| 83080 |
+
},
|
| 83081 |
+
{
|
| 83082 |
+
"epoch": 0.6593333333333333,
|
| 83083 |
+
"grad_norm": 0.0986328125,
|
| 83084 |
+
"learning_rate": 0.00021580625251463306,
|
| 83085 |
+
"loss": 1.9508,
|
| 83086 |
+
"step": 11868
|
| 83087 |
+
},
|
| 83088 |
+
{
|
| 83089 |
+
"epoch": 0.6593888888888889,
|
| 83090 |
+
"grad_norm": 0.09912109375,
|
| 83091 |
+
"learning_rate": 0.00021574301981974717,
|
| 83092 |
+
"loss": 1.9825,
|
| 83093 |
+
"step": 11869
|
| 83094 |
+
},
|
| 83095 |
+
{
|
| 83096 |
+
"epoch": 0.6594444444444445,
|
| 83097 |
+
"grad_norm": 0.09716796875,
|
| 83098 |
+
"learning_rate": 0.0002156797929690808,
|
| 83099 |
+
"loss": 1.9086,
|
| 83100 |
+
"step": 11870
|
| 83101 |
+
},
|
| 83102 |
+
{
|
| 83103 |
+
"epoch": 0.6595,
|
| 83104 |
+
"grad_norm": 0.099609375,
|
| 83105 |
+
"learning_rate": 0.00021561657196463965,
|
| 83106 |
+
"loss": 1.9092,
|
| 83107 |
+
"step": 11871
|
| 83108 |
+
},
|
| 83109 |
+
{
|
| 83110 |
+
"epoch": 0.6595555555555556,
|
| 83111 |
+
"grad_norm": 0.0966796875,
|
| 83112 |
+
"learning_rate": 0.0002155533568084287,
|
| 83113 |
+
"loss": 1.9246,
|
| 83114 |
+
"step": 11872
|
| 83115 |
+
},
|
| 83116 |
+
{
|
| 83117 |
+
"epoch": 0.6596111111111111,
|
| 83118 |
+
"grad_norm": 0.09912109375,
|
| 83119 |
+
"learning_rate": 0.00021549014750245324,
|
| 83120 |
+
"loss": 1.9419,
|
| 83121 |
+
"step": 11873
|
| 83122 |
+
},
|
| 83123 |
+
{
|
| 83124 |
+
"epoch": 0.6596666666666666,
|
| 83125 |
+
"grad_norm": 0.10009765625,
|
| 83126 |
+
"learning_rate": 0.000215426944048718,
|
| 83127 |
+
"loss": 2.0453,
|
| 83128 |
+
"step": 11874
|
| 83129 |
+
},
|
| 83130 |
+
{
|
| 83131 |
+
"epoch": 0.6597222222222222,
|
| 83132 |
+
"grad_norm": 0.099609375,
|
| 83133 |
+
"learning_rate": 0.00021536374644922748,
|
| 83134 |
+
"loss": 2.055,
|
| 83135 |
+
"step": 11875
|
| 83136 |
+
},
|
| 83137 |
+
{
|
| 83138 |
+
"epoch": 0.6597777777777778,
|
| 83139 |
+
"grad_norm": 0.0986328125,
|
| 83140 |
+
"learning_rate": 0.00021530055470598652,
|
| 83141 |
+
"loss": 2.0176,
|
| 83142 |
+
"step": 11876
|
| 83143 |
+
},
|
| 83144 |
+
{
|
| 83145 |
+
"epoch": 0.6598333333333334,
|
| 83146 |
+
"grad_norm": 0.099609375,
|
| 83147 |
+
"learning_rate": 0.00021523736882099904,
|
| 83148 |
+
"loss": 2.0047,
|
| 83149 |
+
"step": 11877
|
| 83150 |
+
},
|
| 83151 |
+
{
|
| 83152 |
+
"epoch": 0.6598888888888889,
|
| 83153 |
+
"grad_norm": 0.1005859375,
|
| 83154 |
+
"learning_rate": 0.00021517418879626955,
|
| 83155 |
+
"loss": 2.0048,
|
| 83156 |
+
"step": 11878
|
| 83157 |
+
},
|
| 83158 |
+
{
|
| 83159 |
+
"epoch": 0.6599444444444444,
|
| 83160 |
+
"grad_norm": 0.103515625,
|
| 83161 |
+
"learning_rate": 0.00021511101463380175,
|
| 83162 |
+
"loss": 2.0428,
|
| 83163 |
+
"step": 11879
|
| 83164 |
+
},
|
| 83165 |
+
{
|
| 83166 |
+
"epoch": 0.66,
|
| 83167 |
+
"grad_norm": 0.1015625,
|
| 83168 |
+
"learning_rate": 0.00021504784633559923,
|
| 83169 |
+
"loss": 2.0506,
|
| 83170 |
+
"step": 11880
|
| 83171 |
+
},
|
| 83172 |
+
{
|
| 83173 |
+
"epoch": 0.6600555555555555,
|
| 83174 |
+
"grad_norm": 0.09814453125,
|
| 83175 |
+
"learning_rate": 0.000214984683903666,
|
| 83176 |
+
"loss": 2.1199,
|
| 83177 |
+
"step": 11881
|
| 83178 |
+
},
|
| 83179 |
+
{
|
| 83180 |
+
"epoch": 0.6601111111111111,
|
| 83181 |
+
"grad_norm": 0.10107421875,
|
| 83182 |
+
"learning_rate": 0.0002149215273400049,
|
| 83183 |
+
"loss": 2.1349,
|
| 83184 |
+
"step": 11882
|
| 83185 |
+
},
|
| 83186 |
+
{
|
| 83187 |
+
"epoch": 0.6601666666666667,
|
| 83188 |
+
"grad_norm": 0.09716796875,
|
| 83189 |
+
"learning_rate": 0.00021485837664661958,
|
| 83190 |
+
"loss": 2.1243,
|
| 83191 |
+
"step": 11883
|
| 83192 |
+
},
|
| 83193 |
+
{
|
| 83194 |
+
"epoch": 0.6602222222222223,
|
| 83195 |
+
"grad_norm": 0.099609375,
|
| 83196 |
+
"learning_rate": 0.00021479523182551264,
|
| 83197 |
+
"loss": 2.0951,
|
| 83198 |
+
"step": 11884
|
| 83199 |
+
},
|
| 83200 |
+
{
|
| 83201 |
+
"epoch": 0.6602777777777777,
|
| 83202 |
+
"grad_norm": 0.10107421875,
|
| 83203 |
+
"learning_rate": 0.0002147320928786873,
|
| 83204 |
+
"loss": 2.0811,
|
| 83205 |
+
"step": 11885
|
| 83206 |
+
},
|
| 83207 |
+
{
|
| 83208 |
+
"epoch": 0.6603333333333333,
|
| 83209 |
+
"grad_norm": 0.09912109375,
|
| 83210 |
+
"learning_rate": 0.00021466895980814594,
|
| 83211 |
+
"loss": 2.1234,
|
| 83212 |
+
"step": 11886
|
| 83213 |
+
},
|
| 83214 |
+
{
|
| 83215 |
+
"epoch": 0.6603888888888889,
|
| 83216 |
+
"grad_norm": 0.10400390625,
|
| 83217 |
+
"learning_rate": 0.0002146058326158909,
|
| 83218 |
+
"loss": 2.0661,
|
| 83219 |
+
"step": 11887
|
| 83220 |
+
},
|
| 83221 |
+
{
|
| 83222 |
+
"epoch": 0.6604444444444444,
|
| 83223 |
+
"grad_norm": 0.09814453125,
|
| 83224 |
+
"learning_rate": 0.00021454271130392472,
|
| 83225 |
+
"loss": 2.0293,
|
| 83226 |
+
"step": 11888
|
| 83227 |
+
},
|
| 83228 |
+
{
|
| 83229 |
+
"epoch": 0.6605,
|
| 83230 |
+
"grad_norm": 0.10009765625,
|
| 83231 |
+
"learning_rate": 0.00021447959587424933,
|
| 83232 |
+
"loss": 2.1599,
|
| 83233 |
+
"step": 11889
|
| 83234 |
+
},
|
| 83235 |
+
{
|
| 83236 |
+
"epoch": 0.6605555555555556,
|
| 83237 |
+
"grad_norm": 0.1005859375,
|
| 83238 |
+
"learning_rate": 0.0002144164863288664,
|
| 83239 |
+
"loss": 2.1427,
|
| 83240 |
+
"step": 11890
|
| 83241 |
+
},
|
| 83242 |
+
{
|
| 83243 |
+
"epoch": 0.6606111111111111,
|
| 83244 |
+
"grad_norm": 0.099609375,
|
| 83245 |
+
"learning_rate": 0.00021435338266977784,
|
| 83246 |
+
"loss": 2.0962,
|
| 83247 |
+
"step": 11891
|
| 83248 |
+
},
|
| 83249 |
+
{
|
| 83250 |
+
"epoch": 0.6606666666666666,
|
| 83251 |
+
"grad_norm": 0.1005859375,
|
| 83252 |
+
"learning_rate": 0.0002142902848989853,
|
| 83253 |
+
"loss": 2.1719,
|
| 83254 |
+
"step": 11892
|
| 83255 |
+
},
|
| 83256 |
+
{
|
| 83257 |
+
"epoch": 0.6607222222222222,
|
| 83258 |
+
"grad_norm": 0.0986328125,
|
| 83259 |
+
"learning_rate": 0.00021422719301848994,
|
| 83260 |
+
"loss": 2.1496,
|
| 83261 |
+
"step": 11893
|
| 83262 |
+
},
|
| 83263 |
+
{
|
| 83264 |
+
"epoch": 0.6607777777777778,
|
| 83265 |
+
"grad_norm": 0.099609375,
|
| 83266 |
+
"learning_rate": 0.00021416410703029276,
|
| 83267 |
+
"loss": 2.1721,
|
| 83268 |
+
"step": 11894
|
| 83269 |
+
},
|
| 83270 |
+
{
|
| 83271 |
+
"epoch": 0.6608333333333334,
|
| 83272 |
+
"grad_norm": 0.0986328125,
|
| 83273 |
+
"learning_rate": 0.00021410102693639494,
|
| 83274 |
+
"loss": 2.1964,
|
| 83275 |
+
"step": 11895
|
| 83276 |
+
},
|
| 83277 |
+
{
|
| 83278 |
+
"epoch": 0.6608888888888889,
|
| 83279 |
+
"grad_norm": 0.10009765625,
|
| 83280 |
+
"learning_rate": 0.00021403795273879718,
|
| 83281 |
+
"loss": 2.2047,
|
| 83282 |
+
"step": 11896
|
| 83283 |
+
},
|
| 83284 |
+
{
|
| 83285 |
+
"epoch": 0.6609444444444444,
|
| 83286 |
+
"grad_norm": 0.099609375,
|
| 83287 |
+
"learning_rate": 0.00021397488443949985,
|
| 83288 |
+
"loss": 2.2235,
|
| 83289 |
+
"step": 11897
|
| 83290 |
+
},
|
| 83291 |
+
{
|
| 83292 |
+
"epoch": 0.661,
|
| 83293 |
+
"grad_norm": 0.1005859375,
|
| 83294 |
+
"learning_rate": 0.00021391182204050346,
|
| 83295 |
+
"loss": 2.2518,
|
| 83296 |
+
"step": 11898
|
| 83297 |
+
},
|
| 83298 |
+
{
|
| 83299 |
+
"epoch": 0.6610555555555555,
|
| 83300 |
+
"grad_norm": 0.10009765625,
|
| 83301 |
+
"learning_rate": 0.00021384876554380856,
|
| 83302 |
+
"loss": 2.1942,
|
| 83303 |
+
"step": 11899
|
| 83304 |
+
},
|
| 83305 |
+
{
|
| 83306 |
+
"epoch": 0.6611111111111111,
|
| 83307 |
+
"grad_norm": 0.099609375,
|
| 83308 |
+
"learning_rate": 0.00021378571495141456,
|
| 83309 |
+
"loss": 2.1396,
|
| 83310 |
+
"step": 11900
|
| 83311 |
+
},
|
| 83312 |
+
{
|
| 83313 |
+
"epoch": 0.6611666666666667,
|
| 83314 |
+
"grad_norm": 0.0986328125,
|
| 83315 |
+
"learning_rate": 0.00021372267026532158,
|
| 83316 |
+
"loss": 2.1451,
|
| 83317 |
+
"step": 11901
|
| 83318 |
+
},
|
| 83319 |
+
{
|
| 83320 |
+
"epoch": 0.6612222222222223,
|
| 83321 |
+
"grad_norm": 0.1005859375,
|
| 83322 |
+
"learning_rate": 0.0002136596314875294,
|
| 83323 |
+
"loss": 2.2174,
|
| 83324 |
+
"step": 11902
|
| 83325 |
+
},
|
| 83326 |
+
{
|
| 83327 |
+
"epoch": 0.6612777777777777,
|
| 83328 |
+
"grad_norm": 0.10009765625,
|
| 83329 |
+
"learning_rate": 0.00021359659862003728,
|
| 83330 |
+
"loss": 2.2125,
|
| 83331 |
+
"step": 11903
|
| 83332 |
+
},
|
| 83333 |
+
{
|
| 83334 |
+
"epoch": 0.6613333333333333,
|
| 83335 |
+
"grad_norm": 0.10009765625,
|
| 83336 |
+
"learning_rate": 0.00021353357166484433,
|
| 83337 |
+
"loss": 2.2279,
|
| 83338 |
+
"step": 11904
|
| 83339 |
+
},
|
| 83340 |
+
{
|
| 83341 |
+
"epoch": 0.6613888888888889,
|
| 83342 |
+
"grad_norm": 0.10205078125,
|
| 83343 |
+
"learning_rate": 0.00021347055062395005,
|
| 83344 |
+
"loss": 2.268,
|
| 83345 |
+
"step": 11905
|
| 83346 |
+
},
|
| 83347 |
+
{
|
| 83348 |
+
"epoch": 0.6614444444444444,
|
| 83349 |
+
"grad_norm": 0.099609375,
|
| 83350 |
+
"learning_rate": 0.000213407535499353,
|
| 83351 |
+
"loss": 2.2769,
|
| 83352 |
+
"step": 11906
|
| 83353 |
+
},
|
| 83354 |
+
{
|
| 83355 |
+
"epoch": 0.6615,
|
| 83356 |
+
"grad_norm": 0.099609375,
|
| 83357 |
+
"learning_rate": 0.00021334452629305189,
|
| 83358 |
+
"loss": 2.2674,
|
| 83359 |
+
"step": 11907
|
| 83360 |
+
},
|
| 83361 |
+
{
|
| 83362 |
+
"epoch": 0.6615555555555556,
|
| 83363 |
+
"grad_norm": 0.1005859375,
|
| 83364 |
+
"learning_rate": 0.00021328152300704526,
|
| 83365 |
+
"loss": 2.2558,
|
| 83366 |
+
"step": 11908
|
| 83367 |
+
},
|
| 83368 |
+
{
|
| 83369 |
+
"epoch": 0.6616111111111111,
|
| 83370 |
+
"grad_norm": 0.103515625,
|
| 83371 |
+
"learning_rate": 0.00021321852564333167,
|
| 83372 |
+
"loss": 2.2988,
|
| 83373 |
+
"step": 11909
|
| 83374 |
+
},
|
| 83375 |
+
{
|
| 83376 |
+
"epoch": 0.6616666666666666,
|
| 83377 |
+
"grad_norm": 0.1015625,
|
| 83378 |
+
"learning_rate": 0.000213155534203909,
|
| 83379 |
+
"loss": 2.2943,
|
| 83380 |
+
"step": 11910
|
| 83381 |
+
},
|
| 83382 |
+
{
|
| 83383 |
+
"epoch": 0.6617222222222222,
|
| 83384 |
+
"grad_norm": 0.099609375,
|
| 83385 |
+
"learning_rate": 0.0002130925486907752,
|
| 83386 |
+
"loss": 2.1772,
|
| 83387 |
+
"step": 11911
|
| 83388 |
+
},
|
| 83389 |
+
{
|
| 83390 |
+
"epoch": 0.6617777777777778,
|
| 83391 |
+
"grad_norm": 0.10009765625,
|
| 83392 |
+
"learning_rate": 0.0002130295691059282,
|
| 83393 |
+
"loss": 2.1303,
|
| 83394 |
+
"step": 11912
|
| 83395 |
+
},
|
| 83396 |
+
{
|
| 83397 |
+
"epoch": 0.6618333333333334,
|
| 83398 |
+
"grad_norm": 0.1015625,
|
| 83399 |
+
"learning_rate": 0.00021296659545136547,
|
| 83400 |
+
"loss": 2.385,
|
| 83401 |
+
"step": 11913
|
| 83402 |
+
},
|
| 83403 |
+
{
|
| 83404 |
+
"epoch": 0.6618888888888889,
|
| 83405 |
+
"grad_norm": 0.10302734375,
|
| 83406 |
+
"learning_rate": 0.0002129036277290842,
|
| 83407 |
+
"loss": 2.4061,
|
| 83408 |
+
"step": 11914
|
| 83409 |
+
},
|
| 83410 |
+
{
|
| 83411 |
+
"epoch": 0.6619444444444444,
|
| 83412 |
+
"grad_norm": 0.1025390625,
|
| 83413 |
+
"learning_rate": 0.00021284066594108204,
|
| 83414 |
+
"loss": 2.3371,
|
| 83415 |
+
"step": 11915
|
| 83416 |
+
},
|
| 83417 |
+
{
|
| 83418 |
+
"epoch": 0.662,
|
| 83419 |
+
"grad_norm": 0.1025390625,
|
| 83420 |
+
"learning_rate": 0.00021277771008935547,
|
| 83421 |
+
"loss": 2.3113,
|
| 83422 |
+
"step": 11916
|
| 83423 |
+
},
|
| 83424 |
+
{
|
| 83425 |
+
"epoch": 0.6620555555555555,
|
| 83426 |
+
"grad_norm": 0.1015625,
|
| 83427 |
+
"learning_rate": 0.00021271476017590177,
|
| 83428 |
+
"loss": 2.3118,
|
| 83429 |
+
"step": 11917
|
| 83430 |
+
},
|
| 83431 |
+
{
|
| 83432 |
+
"epoch": 0.6621111111111111,
|
| 83433 |
+
"grad_norm": 0.1005859375,
|
| 83434 |
+
"learning_rate": 0.00021265181620271716,
|
| 83435 |
+
"loss": 2.274,
|
| 83436 |
+
"step": 11918
|
| 83437 |
+
},
|
| 83438 |
+
{
|
| 83439 |
+
"epoch": 0.6621666666666667,
|
| 83440 |
+
"grad_norm": 0.103515625,
|
| 83441 |
+
"learning_rate": 0.00021258887817179854,
|
| 83442 |
+
"loss": 2.3175,
|
| 83443 |
+
"step": 11919
|
| 83444 |
+
},
|
| 83445 |
+
{
|
| 83446 |
+
"epoch": 0.6622222222222223,
|
| 83447 |
+
"grad_norm": 0.09814453125,
|
| 83448 |
+
"learning_rate": 0.00021252594608514182,
|
| 83449 |
+
"loss": 2.3721,
|
| 83450 |
+
"step": 11920
|
| 83451 |
+
},
|
| 83452 |
+
{
|
| 83453 |
+
"epoch": 0.6622777777777777,
|
| 83454 |
+
"grad_norm": 0.10400390625,
|
| 83455 |
+
"learning_rate": 0.0002124630199447431,
|
| 83456 |
+
"loss": 2.3221,
|
| 83457 |
+
"step": 11921
|
| 83458 |
+
},
|
| 83459 |
+
{
|
| 83460 |
+
"epoch": 0.6623333333333333,
|
| 83461 |
+
"grad_norm": 0.1015625,
|
| 83462 |
+
"learning_rate": 0.00021240009975259842,
|
| 83463 |
+
"loss": 2.347,
|
| 83464 |
+
"step": 11922
|
| 83465 |
+
},
|
| 83466 |
+
{
|
| 83467 |
+
"epoch": 0.6623888888888889,
|
| 83468 |
+
"grad_norm": 0.1005859375,
|
| 83469 |
+
"learning_rate": 0.0002123371855107032,
|
| 83470 |
+
"loss": 2.2989,
|
| 83471 |
+
"step": 11923
|
| 83472 |
+
},
|
| 83473 |
+
{
|
| 83474 |
+
"epoch": 0.6624444444444444,
|
| 83475 |
+
"grad_norm": 0.1025390625,
|
| 83476 |
+
"learning_rate": 0.00021227427722105328,
|
| 83477 |
+
"loss": 2.4197,
|
| 83478 |
+
"step": 11924
|
| 83479 |
+
},
|
| 83480 |
+
{
|
| 83481 |
+
"epoch": 0.6625,
|
| 83482 |
+
"grad_norm": 0.10205078125,
|
| 83483 |
+
"learning_rate": 0.0002122113748856438,
|
| 83484 |
+
"loss": 2.3402,
|
| 83485 |
+
"step": 11925
|
| 83486 |
+
},
|
| 83487 |
+
{
|
| 83488 |
+
"epoch": 0.6625555555555556,
|
| 83489 |
+
"grad_norm": 0.10302734375,
|
| 83490 |
+
"learning_rate": 0.00021214847850646975,
|
| 83491 |
+
"loss": 2.4125,
|
| 83492 |
+
"step": 11926
|
| 83493 |
+
},
|
| 83494 |
+
{
|
| 83495 |
+
"epoch": 0.6626111111111112,
|
| 83496 |
+
"grad_norm": 0.10498046875,
|
| 83497 |
+
"learning_rate": 0.00021208558808552628,
|
| 83498 |
+
"loss": 2.3862,
|
| 83499 |
+
"step": 11927
|
| 83500 |
+
},
|
| 83501 |
+
{
|
| 83502 |
+
"epoch": 0.6626666666666666,
|
| 83503 |
+
"grad_norm": 0.099609375,
|
| 83504 |
+
"learning_rate": 0.0002120227036248079,
|
| 83505 |
+
"loss": 2.2925,
|
| 83506 |
+
"step": 11928
|
| 83507 |
+
},
|
| 83508 |
+
{
|
| 83509 |
+
"epoch": 0.6627222222222222,
|
| 83510 |
+
"grad_norm": 0.1025390625,
|
| 83511 |
+
"learning_rate": 0.00021195982512630952,
|
| 83512 |
+
"loss": 2.3899,
|
| 83513 |
+
"step": 11929
|
| 83514 |
+
},
|
| 83515 |
+
{
|
| 83516 |
+
"epoch": 0.6627777777777778,
|
| 83517 |
+
"grad_norm": 0.1005859375,
|
| 83518 |
+
"learning_rate": 0.00021189695259202514,
|
| 83519 |
+
"loss": 2.408,
|
| 83520 |
+
"step": 11930
|
| 83521 |
+
},
|
| 83522 |
+
{
|
| 83523 |
+
"epoch": 0.6628333333333334,
|
| 83524 |
+
"grad_norm": 0.10400390625,
|
| 83525 |
+
"learning_rate": 0.0002118340860239492,
|
| 83526 |
+
"loss": 2.4005,
|
| 83527 |
+
"step": 11931
|
| 83528 |
+
},
|
| 83529 |
+
{
|
| 83530 |
+
"epoch": 0.6628888888888889,
|
| 83531 |
+
"grad_norm": 0.10205078125,
|
| 83532 |
+
"learning_rate": 0.00021177122542407557,
|
| 83533 |
+
"loss": 2.3821,
|
| 83534 |
+
"step": 11932
|
| 83535 |
+
},
|
| 83536 |
+
{
|
| 83537 |
+
"epoch": 0.6629444444444444,
|
| 83538 |
+
"grad_norm": 0.1005859375,
|
| 83539 |
+
"learning_rate": 0.0002117083707943979,
|
| 83540 |
+
"loss": 2.3045,
|
| 83541 |
+
"step": 11933
|
| 83542 |
+
},
|
| 83543 |
+
{
|
| 83544 |
+
"epoch": 0.663,
|
| 83545 |
+
"grad_norm": 0.1015625,
|
| 83546 |
+
"learning_rate": 0.00021164552213691012,
|
| 83547 |
+
"loss": 2.4533,
|
| 83548 |
+
"step": 11934
|
| 83549 |
+
},
|
| 83550 |
+
{
|
| 83551 |
+
"epoch": 0.6630555555555555,
|
| 83552 |
+
"grad_norm": 0.109375,
|
| 83553 |
+
"learning_rate": 0.0002115826794536055,
|
| 83554 |
+
"loss": 2.449,
|
| 83555 |
+
"step": 11935
|
| 83556 |
+
},
|
| 83557 |
+
{
|
| 83558 |
+
"epoch": 0.6631111111111111,
|
| 83559 |
+
"grad_norm": 0.1025390625,
|
| 83560 |
+
"learning_rate": 0.00021151984274647706,
|
| 83561 |
+
"loss": 2.289,
|
| 83562 |
+
"step": 11936
|
| 83563 |
+
},
|
| 83564 |
+
{
|
| 83565 |
+
"epoch": 0.6631666666666667,
|
| 83566 |
+
"grad_norm": 0.1015625,
|
| 83567 |
+
"learning_rate": 0.0002114570120175181,
|
| 83568 |
+
"loss": 2.2961,
|
| 83569 |
+
"step": 11937
|
| 83570 |
+
},
|
| 83571 |
+
{
|
| 83572 |
+
"epoch": 0.6632222222222223,
|
| 83573 |
+
"grad_norm": 0.10595703125,
|
| 83574 |
+
"learning_rate": 0.0002113941872687215,
|
| 83575 |
+
"loss": 2.5493,
|
| 83576 |
+
"step": 11938
|
| 83577 |
+
},
|
| 83578 |
+
{
|
| 83579 |
+
"epoch": 0.6632777777777777,
|
| 83580 |
+
"grad_norm": 0.10107421875,
|
| 83581 |
+
"learning_rate": 0.00021133136850207986,
|
| 83582 |
+
"loss": 2.3175,
|
| 83583 |
+
"step": 11939
|
| 83584 |
+
},
|
| 83585 |
+
{
|
| 83586 |
+
"epoch": 0.6633333333333333,
|
| 83587 |
+
"grad_norm": 0.1025390625,
|
| 83588 |
+
"learning_rate": 0.00021126855571958544,
|
| 83589 |
+
"loss": 2.3429,
|
| 83590 |
+
"step": 11940
|
| 83591 |
+
},
|
| 83592 |
+
{
|
| 83593 |
+
"epoch": 0.6633888888888889,
|
| 83594 |
+
"grad_norm": 0.1015625,
|
| 83595 |
+
"learning_rate": 0.0002112057489232308,
|
| 83596 |
+
"loss": 2.4027,
|
| 83597 |
+
"step": 11941
|
| 83598 |
+
},
|
| 83599 |
+
{
|
| 83600 |
+
"epoch": 0.6634444444444444,
|
| 83601 |
+
"grad_norm": 0.103515625,
|
| 83602 |
+
"learning_rate": 0.00021114294811500802,
|
| 83603 |
+
"loss": 2.5544,
|
| 83604 |
+
"step": 11942
|
| 83605 |
+
},
|
| 83606 |
+
{
|
| 83607 |
+
"epoch": 0.6635,
|
| 83608 |
+
"grad_norm": 0.1015625,
|
| 83609 |
+
"learning_rate": 0.00021108015329690871,
|
| 83610 |
+
"loss": 2.3922,
|
| 83611 |
+
"step": 11943
|
| 83612 |
+
},
|
| 83613 |
+
{
|
| 83614 |
+
"epoch": 0.6635555555555556,
|
| 83615 |
+
"grad_norm": 0.10302734375,
|
| 83616 |
+
"learning_rate": 0.00021101736447092474,
|
| 83617 |
+
"loss": 2.4072,
|
| 83618 |
+
"step": 11944
|
| 83619 |
+
},
|
| 83620 |
+
{
|
| 83621 |
+
"epoch": 0.6636111111111112,
|
| 83622 |
+
"grad_norm": 0.1064453125,
|
| 83623 |
+
"learning_rate": 0.00021095458163904806,
|
| 83624 |
+
"loss": 2.5211,
|
| 83625 |
+
"step": 11945
|
| 83626 |
+
},
|
| 83627 |
+
{
|
| 83628 |
+
"epoch": 0.6636666666666666,
|
| 83629 |
+
"grad_norm": 0.103515625,
|
| 83630 |
+
"learning_rate": 0.00021089180480326927,
|
| 83631 |
+
"loss": 2.3495,
|
| 83632 |
+
"step": 11946
|
| 83633 |
+
},
|
| 83634 |
+
{
|
| 83635 |
+
"epoch": 0.6637222222222222,
|
| 83636 |
+
"grad_norm": 0.1015625,
|
| 83637 |
+
"learning_rate": 0.0002108290339655798,
|
| 83638 |
+
"loss": 2.4413,
|
| 83639 |
+
"step": 11947
|
| 83640 |
+
},
|
| 83641 |
+
{
|
| 83642 |
+
"epoch": 0.6637777777777778,
|
| 83643 |
+
"grad_norm": 0.10791015625,
|
| 83644 |
+
"learning_rate": 0.00021076626912797087,
|
| 83645 |
+
"loss": 2.542,
|
| 83646 |
+
"step": 11948
|
| 83647 |
+
},
|
| 83648 |
+
{
|
| 83649 |
+
"epoch": 0.6638333333333334,
|
| 83650 |
+
"grad_norm": 0.10302734375,
|
| 83651 |
+
"learning_rate": 0.00021070351029243298,
|
| 83652 |
+
"loss": 2.3854,
|
| 83653 |
+
"step": 11949
|
| 83654 |
+
},
|
| 83655 |
+
{
|
| 83656 |
+
"epoch": 0.6638888888888889,
|
| 83657 |
+
"grad_norm": 0.103515625,
|
| 83658 |
+
"learning_rate": 0.00021064075746095662,
|
| 83659 |
+
"loss": 2.4745,
|
| 83660 |
+
"step": 11950
|
| 83661 |
+
},
|
| 83662 |
+
{
|
| 83663 |
+
"epoch": 0.6639444444444444,
|
| 83664 |
+
"grad_norm": 0.10400390625,
|
| 83665 |
+
"learning_rate": 0.00021057801063553244,
|
| 83666 |
+
"loss": 2.4613,
|
| 83667 |
+
"step": 11951
|
| 83668 |
+
},
|
| 83669 |
+
{
|
| 83670 |
+
"epoch": 0.664,
|
| 83671 |
+
"grad_norm": 0.1025390625,
|
| 83672 |
+
"learning_rate": 0.00021051526981815047,
|
| 83673 |
+
"loss": 2.4101,
|
| 83674 |
+
"step": 11952
|
| 83675 |
+
},
|
| 83676 |
+
{
|
| 83677 |
+
"epoch": 0.6640555555555555,
|
| 83678 |
+
"grad_norm": 0.10302734375,
|
| 83679 |
+
"learning_rate": 0.00021045253501080055,
|
| 83680 |
+
"loss": 2.5501,
|
| 83681 |
+
"step": 11953
|
| 83682 |
+
},
|
| 83683 |
+
{
|
| 83684 |
+
"epoch": 0.6641111111111111,
|
| 83685 |
+
"grad_norm": 0.10546875,
|
| 83686 |
+
"learning_rate": 0.00021038980621547267,
|
| 83687 |
+
"loss": 2.46,
|
| 83688 |
+
"step": 11954
|
| 83689 |
+
},
|
| 83690 |
+
{
|
| 83691 |
+
"epoch": 0.6641666666666667,
|
| 83692 |
+
"grad_norm": 0.1005859375,
|
| 83693 |
+
"learning_rate": 0.00021032708343415678,
|
| 83694 |
+
"loss": 2.3548,
|
| 83695 |
+
"step": 11955
|
| 83696 |
+
},
|
| 83697 |
+
{
|
| 83698 |
+
"epoch": 0.6642222222222223,
|
| 83699 |
+
"grad_norm": 0.10302734375,
|
| 83700 |
+
"learning_rate": 0.00021026436666884163,
|
| 83701 |
+
"loss": 2.5548,
|
| 83702 |
+
"step": 11956
|
| 83703 |
+
},
|
| 83704 |
+
{
|
| 83705 |
+
"epoch": 0.6642777777777777,
|
| 83706 |
+
"grad_norm": 0.1025390625,
|
| 83707 |
+
"learning_rate": 0.00021020165592151678,
|
| 83708 |
+
"loss": 2.4083,
|
| 83709 |
+
"step": 11957
|
| 83710 |
+
},
|
| 83711 |
+
{
|
| 83712 |
+
"epoch": 0.6643333333333333,
|
| 83713 |
+
"grad_norm": 0.103515625,
|
| 83714 |
+
"learning_rate": 0.00021013895119417146,
|
| 83715 |
+
"loss": 2.4294,
|
| 83716 |
+
"step": 11958
|
| 83717 |
+
},
|
| 83718 |
+
{
|
| 83719 |
+
"epoch": 0.6643888888888889,
|
| 83720 |
+
"grad_norm": 0.10595703125,
|
| 83721 |
+
"learning_rate": 0.00021007625248879434,
|
| 83722 |
+
"loss": 2.6201,
|
| 83723 |
+
"step": 11959
|
| 83724 |
+
},
|
| 83725 |
+
{
|
| 83726 |
+
"epoch": 0.6644444444444444,
|
| 83727 |
+
"grad_norm": 0.10205078125,
|
| 83728 |
+
"learning_rate": 0.0002100135598073739,
|
| 83729 |
+
"loss": 2.322,
|
| 83730 |
+
"step": 11960
|
| 83731 |
+
},
|
| 83732 |
+
{
|
| 83733 |
+
"epoch": 0.6645,
|
| 83734 |
+
"grad_norm": 0.10107421875,
|
| 83735 |
+
"learning_rate": 0.00020995087315189896,
|
| 83736 |
+
"loss": 2.3813,
|
| 83737 |
+
"step": 11961
|
| 83738 |
+
},
|
| 83739 |
+
{
|
| 83740 |
+
"epoch": 0.6645555555555556,
|
| 83741 |
+
"grad_norm": 0.10302734375,
|
| 83742 |
+
"learning_rate": 0.00020988819252435768,
|
| 83743 |
+
"loss": 2.5274,
|
| 83744 |
+
"step": 11962
|
| 83745 |
+
},
|
| 83746 |
+
{
|
| 83747 |
+
"epoch": 0.6646111111111112,
|
| 83748 |
+
"grad_norm": 0.1044921875,
|
| 83749 |
+
"learning_rate": 0.00020982551792673797,
|
| 83750 |
+
"loss": 2.3906,
|
| 83751 |
+
"step": 11963
|
| 83752 |
+
},
|
| 83753 |
+
{
|
| 83754 |
+
"epoch": 0.6646666666666666,
|
| 83755 |
+
"grad_norm": 0.10302734375,
|
| 83756 |
+
"learning_rate": 0.00020976284936102783,
|
| 83757 |
+
"loss": 2.5733,
|
| 83758 |
+
"step": 11964
|
| 83759 |
+
},
|
| 83760 |
+
{
|
| 83761 |
+
"epoch": 0.6647222222222222,
|
| 83762 |
+
"grad_norm": 0.1025390625,
|
| 83763 |
+
"learning_rate": 0.00020970018682921519,
|
| 83764 |
+
"loss": 2.3422,
|
| 83765 |
+
"step": 11965
|
| 83766 |
+
},
|
| 83767 |
+
{
|
| 83768 |
+
"epoch": 0.6647777777777778,
|
| 83769 |
+
"grad_norm": 0.103515625,
|
| 83770 |
+
"learning_rate": 0.00020963753033328733,
|
| 83771 |
+
"loss": 2.4482,
|
| 83772 |
+
"step": 11966
|
| 83773 |
+
},
|
| 83774 |
+
{
|
| 83775 |
+
"epoch": 0.6648333333333334,
|
| 83776 |
+
"grad_norm": 0.1044921875,
|
| 83777 |
+
"learning_rate": 0.00020957487987523145,
|
| 83778 |
+
"loss": 2.5919,
|
| 83779 |
+
"step": 11967
|
| 83780 |
+
},
|
| 83781 |
+
{
|
| 83782 |
+
"epoch": 0.6648888888888889,
|
| 83783 |
+
"grad_norm": 0.10205078125,
|
| 83784 |
+
"learning_rate": 0.00020951223545703508,
|
| 83785 |
+
"loss": 2.4576,
|
| 83786 |
+
"step": 11968
|
| 83787 |
+
},
|
| 83788 |
+
{
|
| 83789 |
+
"epoch": 0.6649444444444444,
|
| 83790 |
+
"grad_norm": 0.10302734375,
|
| 83791 |
+
"learning_rate": 0.00020944959708068495,
|
| 83792 |
+
"loss": 2.4694,
|
| 83793 |
+
"step": 11969
|
| 83794 |
+
},
|
| 83795 |
+
{
|
| 83796 |
+
"epoch": 0.665,
|
| 83797 |
+
"grad_norm": 0.10302734375,
|
| 83798 |
+
"learning_rate": 0.0002093869647481676,
|
| 83799 |
+
"loss": 2.4252,
|
| 83800 |
+
"step": 11970
|
| 83801 |
+
},
|
| 83802 |
+
{
|
| 83803 |
+
"epoch": 0.6650555555555555,
|
| 83804 |
+
"grad_norm": 0.1005859375,
|
| 83805 |
+
"learning_rate": 0.00020932433846146994,
|
| 83806 |
+
"loss": 2.3745,
|
| 83807 |
+
"step": 11971
|
| 83808 |
+
},
|
| 83809 |
+
{
|
| 83810 |
+
"epoch": 0.6651111111111111,
|
| 83811 |
+
"grad_norm": 0.1044921875,
|
| 83812 |
+
"learning_rate": 0.00020926171822257806,
|
| 83813 |
+
"loss": 2.5274,
|
| 83814 |
+
"step": 11972
|
| 83815 |
+
},
|
| 83816 |
+
{
|
| 83817 |
+
"epoch": 0.6651666666666667,
|
| 83818 |
+
"grad_norm": 0.1025390625,
|
| 83819 |
+
"learning_rate": 0.00020919910403347837,
|
| 83820 |
+
"loss": 2.3953,
|
| 83821 |
+
"step": 11973
|
| 83822 |
+
},
|
| 83823 |
+
{
|
| 83824 |
+
"epoch": 0.6652222222222223,
|
| 83825 |
+
"grad_norm": 0.10546875,
|
| 83826 |
+
"learning_rate": 0.00020913649589615662,
|
| 83827 |
+
"loss": 2.4743,
|
| 83828 |
+
"step": 11974
|
| 83829 |
+
},
|
| 83830 |
+
{
|
| 83831 |
+
"epoch": 0.6652777777777777,
|
| 83832 |
+
"grad_norm": 0.10107421875,
|
| 83833 |
+
"learning_rate": 0.00020907389381259885,
|
| 83834 |
+
"loss": 2.3036,
|
| 83835 |
+
"step": 11975
|
| 83836 |
+
},
|
| 83837 |
+
{
|
| 83838 |
+
"epoch": 0.6653333333333333,
|
| 83839 |
+
"grad_norm": 0.10107421875,
|
| 83840 |
+
"learning_rate": 0.00020901129778479053,
|
| 83841 |
+
"loss": 2.5315,
|
| 83842 |
+
"step": 11976
|
| 83843 |
+
},
|
| 83844 |
+
{
|
| 83845 |
+
"epoch": 0.6653888888888889,
|
| 83846 |
+
"grad_norm": 0.1025390625,
|
| 83847 |
+
"learning_rate": 0.0002089487078147169,
|
| 83848 |
+
"loss": 2.4344,
|
| 83849 |
+
"step": 11977
|
| 83850 |
+
},
|
| 83851 |
+
{
|
| 83852 |
+
"epoch": 0.6654444444444444,
|
| 83853 |
+
"grad_norm": 0.103515625,
|
| 83854 |
+
"learning_rate": 0.00020888612390436353,
|
| 83855 |
+
"loss": 2.5641,
|
| 83856 |
+
"step": 11978
|
| 83857 |
+
},
|
| 83858 |
+
{
|
| 83859 |
+
"epoch": 0.6655,
|
| 83860 |
+
"grad_norm": 0.10205078125,
|
| 83861 |
+
"learning_rate": 0.0002088235460557151,
|
| 83862 |
+
"loss": 2.3017,
|
| 83863 |
+
"step": 11979
|
| 83864 |
+
},
|
| 83865 |
+
{
|
| 83866 |
+
"epoch": 0.6655555555555556,
|
| 83867 |
+
"grad_norm": 0.1025390625,
|
| 83868 |
+
"learning_rate": 0.00020876097427075668,
|
| 83869 |
+
"loss": 2.5044,
|
| 83870 |
+
"step": 11980
|
| 83871 |
+
},
|
| 83872 |
+
{
|
| 83873 |
+
"epoch": 0.6656111111111112,
|
| 83874 |
+
"grad_norm": 0.10009765625,
|
| 83875 |
+
"learning_rate": 0.00020869840855147284,
|
| 83876 |
+
"loss": 2.3169,
|
| 83877 |
+
"step": 11981
|
| 83878 |
+
},
|
| 83879 |
+
{
|
| 83880 |
+
"epoch": 0.6656666666666666,
|
| 83881 |
+
"grad_norm": 0.10107421875,
|
| 83882 |
+
"learning_rate": 0.00020863584889984783,
|
| 83883 |
+
"loss": 2.5301,
|
| 83884 |
+
"step": 11982
|
| 83885 |
+
},
|
| 83886 |
+
{
|
| 83887 |
+
"epoch": 0.6657222222222222,
|
| 83888 |
+
"grad_norm": 0.10205078125,
|
| 83889 |
+
"learning_rate": 0.00020857329531786612,
|
| 83890 |
+
"loss": 2.345,
|
| 83891 |
+
"step": 11983
|
| 83892 |
+
},
|
| 83893 |
+
{
|
| 83894 |
+
"epoch": 0.6657777777777778,
|
| 83895 |
+
"grad_norm": 0.099609375,
|
| 83896 |
+
"learning_rate": 0.00020851074780751182,
|
| 83897 |
+
"loss": 2.4314,
|
| 83898 |
+
"step": 11984
|
| 83899 |
+
},
|
| 83900 |
+
{
|
| 83901 |
+
"epoch": 0.6658333333333334,
|
| 83902 |
+
"grad_norm": 0.10107421875,
|
| 83903 |
+
"learning_rate": 0.00020844820637076877,
|
| 83904 |
+
"loss": 2.3469,
|
| 83905 |
+
"step": 11985
|
| 83906 |
+
},
|
| 83907 |
+
{
|
| 83908 |
+
"epoch": 0.6658888888888889,
|
| 83909 |
+
"grad_norm": 0.10009765625,
|
| 83910 |
+
"learning_rate": 0.00020838567100962032,
|
| 83911 |
+
"loss": 2.5514,
|
| 83912 |
+
"step": 11986
|
| 83913 |
+
},
|
| 83914 |
+
{
|
| 83915 |
+
"epoch": 0.6659444444444444,
|
| 83916 |
+
"grad_norm": 0.1015625,
|
| 83917 |
+
"learning_rate": 0.00020832314172605044,
|
| 83918 |
+
"loss": 2.3667,
|
| 83919 |
+
"step": 11987
|
| 83920 |
+
},
|
| 83921 |
+
{
|
| 83922 |
+
"epoch": 0.666,
|
| 83923 |
+
"grad_norm": 0.1005859375,
|
| 83924 |
+
"learning_rate": 0.00020826061852204214,
|
| 83925 |
+
"loss": 2.5127,
|
| 83926 |
+
"step": 11988
|
| 83927 |
+
},
|
| 83928 |
+
{
|
| 83929 |
+
"epoch": 0.6660555555555555,
|
| 83930 |
+
"grad_norm": 0.10107421875,
|
| 83931 |
+
"learning_rate": 0.0002081981013995785,
|
| 83932 |
+
"loss": 2.3362,
|
| 83933 |
+
"step": 11989
|
| 83934 |
+
},
|
| 83935 |
+
{
|
| 83936 |
+
"epoch": 0.6661111111111111,
|
| 83937 |
+
"grad_norm": 0.10107421875,
|
| 83938 |
+
"learning_rate": 0.0002081355903606424,
|
| 83939 |
+
"loss": 2.479,
|
| 83940 |
+
"step": 11990
|
| 83941 |
+
},
|
| 83942 |
+
{
|
| 83943 |
+
"epoch": 0.6661666666666667,
|
| 83944 |
+
"grad_norm": 0.09765625,
|
| 83945 |
+
"learning_rate": 0.00020807308540721694,
|
| 83946 |
+
"loss": 2.2521,
|
| 83947 |
+
"step": 11991
|
| 83948 |
+
},
|
| 83949 |
+
{
|
| 83950 |
+
"epoch": 0.6662222222222223,
|
| 83951 |
+
"grad_norm": 0.10107421875,
|
| 83952 |
+
"learning_rate": 0.00020801058654128403,
|
| 83953 |
+
"loss": 2.5025,
|
| 83954 |
+
"step": 11992
|
| 83955 |
+
},
|
| 83956 |
+
{
|
| 83957 |
+
"epoch": 0.6662777777777777,
|
| 83958 |
+
"grad_norm": 0.09912109375,
|
| 83959 |
+
"learning_rate": 0.00020794809376482634,
|
| 83960 |
+
"loss": 2.2969,
|
| 83961 |
+
"step": 11993
|
| 83962 |
+
},
|
| 83963 |
+
{
|
| 83964 |
+
"epoch": 0.6663333333333333,
|
| 83965 |
+
"grad_norm": 0.099609375,
|
| 83966 |
+
"learning_rate": 0.00020788560707982607,
|
| 83967 |
+
"loss": 2.4959,
|
| 83968 |
+
"step": 11994
|
| 83969 |
+
},
|
| 83970 |
+
{
|
| 83971 |
+
"epoch": 0.6663888888888889,
|
| 83972 |
+
"grad_norm": 0.0986328125,
|
| 83973 |
+
"learning_rate": 0.00020782312648826509,
|
| 83974 |
+
"loss": 2.3884,
|
| 83975 |
+
"step": 11995
|
| 83976 |
+
},
|
| 83977 |
+
{
|
| 83978 |
+
"epoch": 0.6664444444444444,
|
| 83979 |
+
"grad_norm": 0.10205078125,
|
| 83980 |
+
"learning_rate": 0.00020776065199212487,
|
| 83981 |
+
"loss": 2.4567,
|
| 83982 |
+
"step": 11996
|
| 83983 |
+
},
|
| 83984 |
+
{
|
| 83985 |
+
"epoch": 0.6665,
|
| 83986 |
+
"grad_norm": 0.09912109375,
|
| 83987 |
+
"learning_rate": 0.00020769818359338724,
|
| 83988 |
+
"loss": 2.2739,
|
| 83989 |
+
"step": 11997
|
| 83990 |
+
},
|
| 83991 |
+
{
|
| 83992 |
+
"epoch": 0.6665555555555556,
|
| 83993 |
+
"grad_norm": 0.1005859375,
|
| 83994 |
+
"learning_rate": 0.00020763572129403382,
|
| 83995 |
+
"loss": 2.4389,
|
| 83996 |
+
"step": 11998
|
| 83997 |
+
},
|
| 83998 |
+
{
|
| 83999 |
+
"epoch": 0.6666111111111112,
|
| 84000 |
+
"grad_norm": 0.1005859375,
|
| 84001 |
+
"learning_rate": 0.00020757326509604515,
|
| 84002 |
+
"loss": 2.3524,
|
| 84003 |
+
"step": 11999
|
| 84004 |
+
},
|
| 84005 |
+
{
|
| 84006 |
+
"epoch": 0.6666666666666666,
|
| 84007 |
+
"grad_norm": 0.099609375,
|
| 84008 |
+
"learning_rate": 0.0002075108150014025,
|
| 84009 |
+
"loss": 2.4399,
|
| 84010 |
+
"step": 12000
|
| 84011 |
}
|
| 84012 |
],
|
| 84013 |
"logging_steps": 1,
|
|
|
|
| 84027 |
"attributes": {}
|
| 84028 |
}
|
| 84029 |
},
|
| 84030 |
+
"total_flos": 6.329101012082495e+18,
|
| 84031 |
"train_batch_size": 8,
|
| 84032 |
"trial_name": null,
|
| 84033 |
"trial_params": null
|