Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
sft
unsloth
trl
text-generation-inference
Instructions to use Ba2han/TR_SFT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/TR_SFT2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/TR_SFT2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/TR_SFT2") model = AutoModelForCausalLM.from_pretrained("Ba2han/TR_SFT2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/TR_SFT2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/TR_SFT2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/TR_SFT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ba2han/TR_SFT2
- SGLang
How to use Ba2han/TR_SFT2 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/TR_SFT2" \ --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/TR_SFT2", "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/TR_SFT2" \ --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/TR_SFT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Desktop
- Docker Model Runner
How to use Ba2han/TR_SFT2 with Docker Model Runner:
docker model run hf.co/Ba2han/TR_SFT2
Training in progress, step 4320, 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 2519936480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9b6b8d34a323eb35eb2360398e496b2d620ea03e2f384b075e62783186309ca
|
| 3 |
size 2519936480
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1265545196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ad91be58f11ed0886f242cb4a74b158766a85bf4a99752e3ae108be1ffa6374
|
| 3 |
size 1265545196
|
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:d020f78ef494abfed985d6385447ef6e055a41c6c646e914cf5e4c499bd01410
|
| 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": 959,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -13480,6 +13480,1686 @@
|
|
| 13480 |
"learning_rate": 0.0002376829648084709,
|
| 13481 |
"loss": 1.4189400672912598,
|
| 13482 |
"step": 3840
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13483 |
}
|
| 13484 |
],
|
| 13485 |
"logging_steps": 2,
|
|
@@ -13499,7 +15179,7 @@
|
|
| 13499 |
"attributes": {}
|
| 13500 |
}
|
| 13501 |
},
|
| 13502 |
-
"total_flos":
|
| 13503 |
"train_batch_size": 8,
|
| 13504 |
"trial_name": null,
|
| 13505 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9014084507042254,
|
| 6 |
"eval_steps": 959,
|
| 7 |
+
"global_step": 4320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13480 |
"learning_rate": 0.0002376829648084709,
|
| 13481 |
"loss": 1.4189400672912598,
|
| 13482 |
"step": 3840
|
| 13483 |
+
},
|
| 13484 |
+
{
|
| 13485 |
+
"epoch": 0.8016692749087115,
|
| 13486 |
+
"grad_norm": 0.21303535997867584,
|
| 13487 |
+
"learning_rate": 0.00023718467767050764,
|
| 13488 |
+
"loss": 1.576297640800476,
|
| 13489 |
+
"step": 3842
|
| 13490 |
+
},
|
| 13491 |
+
{
|
| 13492 |
+
"epoch": 0.8020865936358894,
|
| 13493 |
+
"grad_norm": 0.20752784609794617,
|
| 13494 |
+
"learning_rate": 0.0002366863905325444,
|
| 13495 |
+
"loss": 1.6360690593719482,
|
| 13496 |
+
"step": 3844
|
| 13497 |
+
},
|
| 13498 |
+
{
|
| 13499 |
+
"epoch": 0.8025039123630673,
|
| 13500 |
+
"grad_norm": 0.16906622052192688,
|
| 13501 |
+
"learning_rate": 0.00023618810339458114,
|
| 13502 |
+
"loss": 1.7308926582336426,
|
| 13503 |
+
"step": 3846
|
| 13504 |
+
},
|
| 13505 |
+
{
|
| 13506 |
+
"epoch": 0.8029212310902452,
|
| 13507 |
+
"grad_norm": 0.16772274672985077,
|
| 13508 |
+
"learning_rate": 0.0002356898162566179,
|
| 13509 |
+
"loss": 1.6283552646636963,
|
| 13510 |
+
"step": 3848
|
| 13511 |
+
},
|
| 13512 |
+
{
|
| 13513 |
+
"epoch": 0.803338549817423,
|
| 13514 |
+
"grad_norm": 0.20605945587158203,
|
| 13515 |
+
"learning_rate": 0.00023519152911865464,
|
| 13516 |
+
"loss": 1.7920221090316772,
|
| 13517 |
+
"step": 3850
|
| 13518 |
+
},
|
| 13519 |
+
{
|
| 13520 |
+
"epoch": 0.8037558685446009,
|
| 13521 |
+
"grad_norm": 0.19974687695503235,
|
| 13522 |
+
"learning_rate": 0.0002346932419806914,
|
| 13523 |
+
"loss": 1.6810439825057983,
|
| 13524 |
+
"step": 3852
|
| 13525 |
+
},
|
| 13526 |
+
{
|
| 13527 |
+
"epoch": 0.8041731872717788,
|
| 13528 |
+
"grad_norm": 0.1850401908159256,
|
| 13529 |
+
"learning_rate": 0.00023419495484272815,
|
| 13530 |
+
"loss": 1.764756679534912,
|
| 13531 |
+
"step": 3854
|
| 13532 |
+
},
|
| 13533 |
+
{
|
| 13534 |
+
"epoch": 0.8045905059989567,
|
| 13535 |
+
"grad_norm": 0.20353806018829346,
|
| 13536 |
+
"learning_rate": 0.00023369666770476486,
|
| 13537 |
+
"loss": 1.595638394355774,
|
| 13538 |
+
"step": 3856
|
| 13539 |
+
},
|
| 13540 |
+
{
|
| 13541 |
+
"epoch": 0.8050078247261346,
|
| 13542 |
+
"grad_norm": 0.1756061315536499,
|
| 13543 |
+
"learning_rate": 0.00023319838056680162,
|
| 13544 |
+
"loss": 1.5819897651672363,
|
| 13545 |
+
"step": 3858
|
| 13546 |
+
},
|
| 13547 |
+
{
|
| 13548 |
+
"epoch": 0.8054251434533125,
|
| 13549 |
+
"grad_norm": 0.1912943422794342,
|
| 13550 |
+
"learning_rate": 0.00023270009342883836,
|
| 13551 |
+
"loss": 1.6187857389450073,
|
| 13552 |
+
"step": 3860
|
| 13553 |
+
},
|
| 13554 |
+
{
|
| 13555 |
+
"epoch": 0.8058424621804904,
|
| 13556 |
+
"grad_norm": 0.19449324905872345,
|
| 13557 |
+
"learning_rate": 0.00023220180629087513,
|
| 13558 |
+
"loss": 1.7449872493743896,
|
| 13559 |
+
"step": 3862
|
| 13560 |
+
},
|
| 13561 |
+
{
|
| 13562 |
+
"epoch": 0.8062597809076683,
|
| 13563 |
+
"grad_norm": 0.1860467940568924,
|
| 13564 |
+
"learning_rate": 0.00023170351915291186,
|
| 13565 |
+
"loss": 1.6441023349761963,
|
| 13566 |
+
"step": 3864
|
| 13567 |
+
},
|
| 13568 |
+
{
|
| 13569 |
+
"epoch": 0.8066770996348461,
|
| 13570 |
+
"grad_norm": 0.19042663276195526,
|
| 13571 |
+
"learning_rate": 0.0002312052320149486,
|
| 13572 |
+
"loss": 1.6760553121566772,
|
| 13573 |
+
"step": 3866
|
| 13574 |
+
},
|
| 13575 |
+
{
|
| 13576 |
+
"epoch": 0.807094418362024,
|
| 13577 |
+
"grad_norm": 0.18120992183685303,
|
| 13578 |
+
"learning_rate": 0.00023070694487698537,
|
| 13579 |
+
"loss": 1.6071486473083496,
|
| 13580 |
+
"step": 3868
|
| 13581 |
+
},
|
| 13582 |
+
{
|
| 13583 |
+
"epoch": 0.8075117370892019,
|
| 13584 |
+
"grad_norm": 0.17611190676689148,
|
| 13585 |
+
"learning_rate": 0.0002302086577390221,
|
| 13586 |
+
"loss": 1.721142292022705,
|
| 13587 |
+
"step": 3870
|
| 13588 |
+
},
|
| 13589 |
+
{
|
| 13590 |
+
"epoch": 0.8079290558163797,
|
| 13591 |
+
"grad_norm": 0.17643216252326965,
|
| 13592 |
+
"learning_rate": 0.00022971037060105887,
|
| 13593 |
+
"loss": 1.6106164455413818,
|
| 13594 |
+
"step": 3872
|
| 13595 |
+
},
|
| 13596 |
+
{
|
| 13597 |
+
"epoch": 0.8083463745435576,
|
| 13598 |
+
"grad_norm": 0.18115536868572235,
|
| 13599 |
+
"learning_rate": 0.0002292120834630956,
|
| 13600 |
+
"loss": 1.6975512504577637,
|
| 13601 |
+
"step": 3874
|
| 13602 |
+
},
|
| 13603 |
+
{
|
| 13604 |
+
"epoch": 0.8087636932707355,
|
| 13605 |
+
"grad_norm": 0.1759224385023117,
|
| 13606 |
+
"learning_rate": 0.00022871379632513237,
|
| 13607 |
+
"loss": 1.686223030090332,
|
| 13608 |
+
"step": 3876
|
| 13609 |
+
},
|
| 13610 |
+
{
|
| 13611 |
+
"epoch": 0.8091810119979134,
|
| 13612 |
+
"grad_norm": 0.18049465119838715,
|
| 13613 |
+
"learning_rate": 0.0002282155091871691,
|
| 13614 |
+
"loss": 1.5944403409957886,
|
| 13615 |
+
"step": 3878
|
| 13616 |
+
},
|
| 13617 |
+
{
|
| 13618 |
+
"epoch": 0.8095983307250912,
|
| 13619 |
+
"grad_norm": 0.17533127963542938,
|
| 13620 |
+
"learning_rate": 0.00022771722204920587,
|
| 13621 |
+
"loss": 1.5372076034545898,
|
| 13622 |
+
"step": 3880
|
| 13623 |
+
},
|
| 13624 |
+
{
|
| 13625 |
+
"epoch": 0.8100156494522691,
|
| 13626 |
+
"grad_norm": 0.2384546995162964,
|
| 13627 |
+
"learning_rate": 0.0002272189349112426,
|
| 13628 |
+
"loss": 1.6710647344589233,
|
| 13629 |
+
"step": 3882
|
| 13630 |
+
},
|
| 13631 |
+
{
|
| 13632 |
+
"epoch": 0.8104329681794471,
|
| 13633 |
+
"grad_norm": 0.15719540417194366,
|
| 13634 |
+
"learning_rate": 0.00022672064777327938,
|
| 13635 |
+
"loss": 1.618177056312561,
|
| 13636 |
+
"step": 3884
|
| 13637 |
+
},
|
| 13638 |
+
{
|
| 13639 |
+
"epoch": 0.810850286906625,
|
| 13640 |
+
"grad_norm": 0.1845632940530777,
|
| 13641 |
+
"learning_rate": 0.00022622236063531611,
|
| 13642 |
+
"loss": 1.7172913551330566,
|
| 13643 |
+
"step": 3886
|
| 13644 |
+
},
|
| 13645 |
+
{
|
| 13646 |
+
"epoch": 0.8112676056338028,
|
| 13647 |
+
"grad_norm": 0.23309579491615295,
|
| 13648 |
+
"learning_rate": 0.00022572407349735288,
|
| 13649 |
+
"loss": 1.574898362159729,
|
| 13650 |
+
"step": 3888
|
| 13651 |
+
},
|
| 13652 |
+
{
|
| 13653 |
+
"epoch": 0.8116849243609807,
|
| 13654 |
+
"grad_norm": 0.17386038601398468,
|
| 13655 |
+
"learning_rate": 0.00022522578635938962,
|
| 13656 |
+
"loss": 1.7423713207244873,
|
| 13657 |
+
"step": 3890
|
| 13658 |
+
},
|
| 13659 |
+
{
|
| 13660 |
+
"epoch": 0.8121022430881586,
|
| 13661 |
+
"grad_norm": 0.19860124588012695,
|
| 13662 |
+
"learning_rate": 0.00022472749922142638,
|
| 13663 |
+
"loss": 1.6700553894042969,
|
| 13664 |
+
"step": 3892
|
| 13665 |
+
},
|
| 13666 |
+
{
|
| 13667 |
+
"epoch": 0.8125195618153365,
|
| 13668 |
+
"grad_norm": 0.15150749683380127,
|
| 13669 |
+
"learning_rate": 0.00022422921208346312,
|
| 13670 |
+
"loss": 1.6848392486572266,
|
| 13671 |
+
"step": 3894
|
| 13672 |
+
},
|
| 13673 |
+
{
|
| 13674 |
+
"epoch": 0.8129368805425143,
|
| 13675 |
+
"grad_norm": 0.1860383003950119,
|
| 13676 |
+
"learning_rate": 0.00022373092494549989,
|
| 13677 |
+
"loss": 1.468409538269043,
|
| 13678 |
+
"step": 3896
|
| 13679 |
+
},
|
| 13680 |
+
{
|
| 13681 |
+
"epoch": 0.8133541992696922,
|
| 13682 |
+
"grad_norm": 0.16297782957553864,
|
| 13683 |
+
"learning_rate": 0.00022323263780753657,
|
| 13684 |
+
"loss": 1.722561240196228,
|
| 13685 |
+
"step": 3898
|
| 13686 |
+
},
|
| 13687 |
+
{
|
| 13688 |
+
"epoch": 0.8137715179968701,
|
| 13689 |
+
"grad_norm": 0.15188246965408325,
|
| 13690 |
+
"learning_rate": 0.00022273435066957333,
|
| 13691 |
+
"loss": 1.6671578884124756,
|
| 13692 |
+
"step": 3900
|
| 13693 |
+
},
|
| 13694 |
+
{
|
| 13695 |
+
"epoch": 0.814188836724048,
|
| 13696 |
+
"grad_norm": 0.1724192351102829,
|
| 13697 |
+
"learning_rate": 0.00022223606353161007,
|
| 13698 |
+
"loss": 1.5962269306182861,
|
| 13699 |
+
"step": 3902
|
| 13700 |
+
},
|
| 13701 |
+
{
|
| 13702 |
+
"epoch": 0.8146061554512258,
|
| 13703 |
+
"grad_norm": 0.18045011162757874,
|
| 13704 |
+
"learning_rate": 0.00022173777639364684,
|
| 13705 |
+
"loss": 1.5897287130355835,
|
| 13706 |
+
"step": 3904
|
| 13707 |
+
},
|
| 13708 |
+
{
|
| 13709 |
+
"epoch": 0.8150234741784037,
|
| 13710 |
+
"grad_norm": 0.1753378063440323,
|
| 13711 |
+
"learning_rate": 0.00022123948925568357,
|
| 13712 |
+
"loss": 1.6983929872512817,
|
| 13713 |
+
"step": 3906
|
| 13714 |
+
},
|
| 13715 |
+
{
|
| 13716 |
+
"epoch": 0.8154407929055817,
|
| 13717 |
+
"grad_norm": 0.1929623782634735,
|
| 13718 |
+
"learning_rate": 0.00022074120211772034,
|
| 13719 |
+
"loss": 1.6955832242965698,
|
| 13720 |
+
"step": 3908
|
| 13721 |
+
},
|
| 13722 |
+
{
|
| 13723 |
+
"epoch": 0.8158581116327596,
|
| 13724 |
+
"grad_norm": 0.1988271176815033,
|
| 13725 |
+
"learning_rate": 0.00022024291497975708,
|
| 13726 |
+
"loss": 1.6405982971191406,
|
| 13727 |
+
"step": 3910
|
| 13728 |
+
},
|
| 13729 |
+
{
|
| 13730 |
+
"epoch": 0.8162754303599374,
|
| 13731 |
+
"grad_norm": 0.1987425833940506,
|
| 13732 |
+
"learning_rate": 0.00021974462784179384,
|
| 13733 |
+
"loss": 1.6183756589889526,
|
| 13734 |
+
"step": 3912
|
| 13735 |
+
},
|
| 13736 |
+
{
|
| 13737 |
+
"epoch": 0.8166927490871153,
|
| 13738 |
+
"grad_norm": 0.2016177624464035,
|
| 13739 |
+
"learning_rate": 0.00021924634070383058,
|
| 13740 |
+
"loss": 1.5909420251846313,
|
| 13741 |
+
"step": 3914
|
| 13742 |
+
},
|
| 13743 |
+
{
|
| 13744 |
+
"epoch": 0.8171100678142932,
|
| 13745 |
+
"grad_norm": 0.1823321431875229,
|
| 13746 |
+
"learning_rate": 0.00021874805356586735,
|
| 13747 |
+
"loss": 1.6325428485870361,
|
| 13748 |
+
"step": 3916
|
| 13749 |
+
},
|
| 13750 |
+
{
|
| 13751 |
+
"epoch": 0.8175273865414711,
|
| 13752 |
+
"grad_norm": 0.1803046017885208,
|
| 13753 |
+
"learning_rate": 0.00021824976642790408,
|
| 13754 |
+
"loss": 1.6903064250946045,
|
| 13755 |
+
"step": 3918
|
| 13756 |
+
},
|
| 13757 |
+
{
|
| 13758 |
+
"epoch": 0.8179447052686489,
|
| 13759 |
+
"grad_norm": 0.15474292635917664,
|
| 13760 |
+
"learning_rate": 0.00021775147928994085,
|
| 13761 |
+
"loss": 1.6624375581741333,
|
| 13762 |
+
"step": 3920
|
| 13763 |
+
},
|
| 13764 |
+
{
|
| 13765 |
+
"epoch": 0.8183620239958268,
|
| 13766 |
+
"grad_norm": 0.18099120259284973,
|
| 13767 |
+
"learning_rate": 0.00021725319215197759,
|
| 13768 |
+
"loss": 1.6347200870513916,
|
| 13769 |
+
"step": 3922
|
| 13770 |
+
},
|
| 13771 |
+
{
|
| 13772 |
+
"epoch": 0.8187793427230047,
|
| 13773 |
+
"grad_norm": 0.15678411722183228,
|
| 13774 |
+
"learning_rate": 0.00021675490501401435,
|
| 13775 |
+
"loss": 1.616406798362732,
|
| 13776 |
+
"step": 3924
|
| 13777 |
+
},
|
| 13778 |
+
{
|
| 13779 |
+
"epoch": 0.8191966614501826,
|
| 13780 |
+
"grad_norm": 0.21508070826530457,
|
| 13781 |
+
"learning_rate": 0.0002162566178760511,
|
| 13782 |
+
"loss": 1.5474953651428223,
|
| 13783 |
+
"step": 3926
|
| 13784 |
+
},
|
| 13785 |
+
{
|
| 13786 |
+
"epoch": 0.8196139801773604,
|
| 13787 |
+
"grad_norm": 0.19049592316150665,
|
| 13788 |
+
"learning_rate": 0.00021575833073808785,
|
| 13789 |
+
"loss": 1.576249599456787,
|
| 13790 |
+
"step": 3928
|
| 13791 |
+
},
|
| 13792 |
+
{
|
| 13793 |
+
"epoch": 0.8200312989045383,
|
| 13794 |
+
"grad_norm": 0.1880476325750351,
|
| 13795 |
+
"learning_rate": 0.0002152600436001246,
|
| 13796 |
+
"loss": 1.64571213722229,
|
| 13797 |
+
"step": 3930
|
| 13798 |
+
},
|
| 13799 |
+
{
|
| 13800 |
+
"epoch": 0.8204486176317162,
|
| 13801 |
+
"grad_norm": 0.2017848640680313,
|
| 13802 |
+
"learning_rate": 0.00021476175646216136,
|
| 13803 |
+
"loss": 1.5606279373168945,
|
| 13804 |
+
"step": 3932
|
| 13805 |
+
},
|
| 13806 |
+
{
|
| 13807 |
+
"epoch": 0.8208659363588942,
|
| 13808 |
+
"grad_norm": 0.1754579246044159,
|
| 13809 |
+
"learning_rate": 0.0002142634693241981,
|
| 13810 |
+
"loss": 1.6150054931640625,
|
| 13811 |
+
"step": 3934
|
| 13812 |
+
},
|
| 13813 |
+
{
|
| 13814 |
+
"epoch": 0.821283255086072,
|
| 13815 |
+
"grad_norm": 0.17297819256782532,
|
| 13816 |
+
"learning_rate": 0.00021376518218623486,
|
| 13817 |
+
"loss": 1.6455872058868408,
|
| 13818 |
+
"step": 3936
|
| 13819 |
+
},
|
| 13820 |
+
{
|
| 13821 |
+
"epoch": 0.8217005738132499,
|
| 13822 |
+
"grad_norm": 0.17700959742069244,
|
| 13823 |
+
"learning_rate": 0.0002132668950482716,
|
| 13824 |
+
"loss": 1.6134843826293945,
|
| 13825 |
+
"step": 3938
|
| 13826 |
+
},
|
| 13827 |
+
{
|
| 13828 |
+
"epoch": 0.8221178925404278,
|
| 13829 |
+
"grad_norm": 0.19243700802326202,
|
| 13830 |
+
"learning_rate": 0.0002127686079103083,
|
| 13831 |
+
"loss": 1.6845083236694336,
|
| 13832 |
+
"step": 3940
|
| 13833 |
+
},
|
| 13834 |
+
{
|
| 13835 |
+
"epoch": 0.8225352112676056,
|
| 13836 |
+
"grad_norm": 0.1604607105255127,
|
| 13837 |
+
"learning_rate": 0.00021227032077234505,
|
| 13838 |
+
"loss": 1.5880975723266602,
|
| 13839 |
+
"step": 3942
|
| 13840 |
+
},
|
| 13841 |
+
{
|
| 13842 |
+
"epoch": 0.8229525299947835,
|
| 13843 |
+
"grad_norm": 0.1929977387189865,
|
| 13844 |
+
"learning_rate": 0.0002117720336343818,
|
| 13845 |
+
"loss": 1.4770071506500244,
|
| 13846 |
+
"step": 3944
|
| 13847 |
+
},
|
| 13848 |
+
{
|
| 13849 |
+
"epoch": 0.8233698487219614,
|
| 13850 |
+
"grad_norm": 0.1966904252767563,
|
| 13851 |
+
"learning_rate": 0.00021127374649641855,
|
| 13852 |
+
"loss": 1.651863932609558,
|
| 13853 |
+
"step": 3946
|
| 13854 |
+
},
|
| 13855 |
+
{
|
| 13856 |
+
"epoch": 0.8237871674491393,
|
| 13857 |
+
"grad_norm": 0.17531289160251617,
|
| 13858 |
+
"learning_rate": 0.0002107754593584553,
|
| 13859 |
+
"loss": 1.5507947206497192,
|
| 13860 |
+
"step": 3948
|
| 13861 |
+
},
|
| 13862 |
+
{
|
| 13863 |
+
"epoch": 0.8242044861763171,
|
| 13864 |
+
"grad_norm": 0.18605005741119385,
|
| 13865 |
+
"learning_rate": 0.00021027717222049205,
|
| 13866 |
+
"loss": 1.7106924057006836,
|
| 13867 |
+
"step": 3950
|
| 13868 |
+
},
|
| 13869 |
+
{
|
| 13870 |
+
"epoch": 0.824621804903495,
|
| 13871 |
+
"grad_norm": 0.21515291929244995,
|
| 13872 |
+
"learning_rate": 0.00020977888508252882,
|
| 13873 |
+
"loss": 1.7130653858184814,
|
| 13874 |
+
"step": 3952
|
| 13875 |
+
},
|
| 13876 |
+
{
|
| 13877 |
+
"epoch": 0.8250391236306729,
|
| 13878 |
+
"grad_norm": 0.20646436512470245,
|
| 13879 |
+
"learning_rate": 0.00020928059794456555,
|
| 13880 |
+
"loss": 1.656790018081665,
|
| 13881 |
+
"step": 3954
|
| 13882 |
+
},
|
| 13883 |
+
{
|
| 13884 |
+
"epoch": 0.8254564423578508,
|
| 13885 |
+
"grad_norm": 0.15887944400310516,
|
| 13886 |
+
"learning_rate": 0.00020878231080660232,
|
| 13887 |
+
"loss": 1.6606398820877075,
|
| 13888 |
+
"step": 3956
|
| 13889 |
+
},
|
| 13890 |
+
{
|
| 13891 |
+
"epoch": 0.8258737610850287,
|
| 13892 |
+
"grad_norm": 0.17161159217357635,
|
| 13893 |
+
"learning_rate": 0.00020828402366863906,
|
| 13894 |
+
"loss": 1.6557297706604004,
|
| 13895 |
+
"step": 3958
|
| 13896 |
+
},
|
| 13897 |
+
{
|
| 13898 |
+
"epoch": 0.8262910798122066,
|
| 13899 |
+
"grad_norm": 0.19186924397945404,
|
| 13900 |
+
"learning_rate": 0.00020778573653067582,
|
| 13901 |
+
"loss": 1.6486374139785767,
|
| 13902 |
+
"step": 3960
|
| 13903 |
+
},
|
| 13904 |
+
{
|
| 13905 |
+
"epoch": 0.8267083985393845,
|
| 13906 |
+
"grad_norm": 0.16262342035770416,
|
| 13907 |
+
"learning_rate": 0.00020728744939271256,
|
| 13908 |
+
"loss": 1.688956379890442,
|
| 13909 |
+
"step": 3962
|
| 13910 |
+
},
|
| 13911 |
+
{
|
| 13912 |
+
"epoch": 0.8271257172665624,
|
| 13913 |
+
"grad_norm": 0.15369129180908203,
|
| 13914 |
+
"learning_rate": 0.00020678916225474932,
|
| 13915 |
+
"loss": 1.68675696849823,
|
| 13916 |
+
"step": 3964
|
| 13917 |
+
},
|
| 13918 |
+
{
|
| 13919 |
+
"epoch": 0.8275430359937402,
|
| 13920 |
+
"grad_norm": 0.18608498573303223,
|
| 13921 |
+
"learning_rate": 0.00020629087511678606,
|
| 13922 |
+
"loss": 1.6111623048782349,
|
| 13923 |
+
"step": 3966
|
| 13924 |
+
},
|
| 13925 |
+
{
|
| 13926 |
+
"epoch": 0.8279603547209181,
|
| 13927 |
+
"grad_norm": 0.19858677685260773,
|
| 13928 |
+
"learning_rate": 0.00020579258797882283,
|
| 13929 |
+
"loss": 1.5222647190093994,
|
| 13930 |
+
"step": 3968
|
| 13931 |
+
},
|
| 13932 |
+
{
|
| 13933 |
+
"epoch": 0.828377673448096,
|
| 13934 |
+
"grad_norm": 0.18191881477832794,
|
| 13935 |
+
"learning_rate": 0.00020529430084085957,
|
| 13936 |
+
"loss": 1.5683807134628296,
|
| 13937 |
+
"step": 3970
|
| 13938 |
+
},
|
| 13939 |
+
{
|
| 13940 |
+
"epoch": 0.8287949921752739,
|
| 13941 |
+
"grad_norm": 0.16898715496063232,
|
| 13942 |
+
"learning_rate": 0.00020479601370289633,
|
| 13943 |
+
"loss": 1.5900148153305054,
|
| 13944 |
+
"step": 3972
|
| 13945 |
+
},
|
| 13946 |
+
{
|
| 13947 |
+
"epoch": 0.8292123109024517,
|
| 13948 |
+
"grad_norm": 0.2008662223815918,
|
| 13949 |
+
"learning_rate": 0.00020429772656493307,
|
| 13950 |
+
"loss": 1.6750458478927612,
|
| 13951 |
+
"step": 3974
|
| 13952 |
+
},
|
| 13953 |
+
{
|
| 13954 |
+
"epoch": 0.8296296296296296,
|
| 13955 |
+
"grad_norm": 0.1838344931602478,
|
| 13956 |
+
"learning_rate": 0.0002037994394269698,
|
| 13957 |
+
"loss": 1.597100019454956,
|
| 13958 |
+
"step": 3976
|
| 13959 |
+
},
|
| 13960 |
+
{
|
| 13961 |
+
"epoch": 0.8300469483568075,
|
| 13962 |
+
"grad_norm": 0.19462299346923828,
|
| 13963 |
+
"learning_rate": 0.00020330115228900657,
|
| 13964 |
+
"loss": 1.6593374013900757,
|
| 13965 |
+
"step": 3978
|
| 13966 |
+
},
|
| 13967 |
+
{
|
| 13968 |
+
"epoch": 0.8304642670839854,
|
| 13969 |
+
"grad_norm": 0.17652329802513123,
|
| 13970 |
+
"learning_rate": 0.0002028028651510433,
|
| 13971 |
+
"loss": 1.6299662590026855,
|
| 13972 |
+
"step": 3980
|
| 13973 |
+
},
|
| 13974 |
+
{
|
| 13975 |
+
"epoch": 0.8308815858111632,
|
| 13976 |
+
"grad_norm": 0.18837544322013855,
|
| 13977 |
+
"learning_rate": 0.00020230457801308002,
|
| 13978 |
+
"loss": 1.6133947372436523,
|
| 13979 |
+
"step": 3982
|
| 13980 |
+
},
|
| 13981 |
+
{
|
| 13982 |
+
"epoch": 0.8312989045383412,
|
| 13983 |
+
"grad_norm": 0.21258091926574707,
|
| 13984 |
+
"learning_rate": 0.00020180629087511678,
|
| 13985 |
+
"loss": 1.5445491075515747,
|
| 13986 |
+
"step": 3984
|
| 13987 |
+
},
|
| 13988 |
+
{
|
| 13989 |
+
"epoch": 0.8317162232655191,
|
| 13990 |
+
"grad_norm": 0.17253796756267548,
|
| 13991 |
+
"learning_rate": 0.00020130800373715352,
|
| 13992 |
+
"loss": 1.5718294382095337,
|
| 13993 |
+
"step": 3986
|
| 13994 |
+
},
|
| 13995 |
+
{
|
| 13996 |
+
"epoch": 0.832133541992697,
|
| 13997 |
+
"grad_norm": 0.1892494112253189,
|
| 13998 |
+
"learning_rate": 0.0002008097165991903,
|
| 13999 |
+
"loss": 1.5831724405288696,
|
| 14000 |
+
"step": 3988
|
| 14001 |
+
},
|
| 14002 |
+
{
|
| 14003 |
+
"epoch": 0.8325508607198748,
|
| 14004 |
+
"grad_norm": 0.18101245164871216,
|
| 14005 |
+
"learning_rate": 0.00020031142946122702,
|
| 14006 |
+
"loss": 1.6219923496246338,
|
| 14007 |
+
"step": 3990
|
| 14008 |
+
},
|
| 14009 |
+
{
|
| 14010 |
+
"epoch": 0.8329681794470527,
|
| 14011 |
+
"grad_norm": 0.2411927729845047,
|
| 14012 |
+
"learning_rate": 0.0001998131423232638,
|
| 14013 |
+
"loss": 1.6351206302642822,
|
| 14014 |
+
"step": 3992
|
| 14015 |
+
},
|
| 14016 |
+
{
|
| 14017 |
+
"epoch": 0.8333854981742306,
|
| 14018 |
+
"grad_norm": 0.16940459609031677,
|
| 14019 |
+
"learning_rate": 0.00019931485518530053,
|
| 14020 |
+
"loss": 1.620373010635376,
|
| 14021 |
+
"step": 3994
|
| 14022 |
+
},
|
| 14023 |
+
{
|
| 14024 |
+
"epoch": 0.8338028169014085,
|
| 14025 |
+
"grad_norm": 0.1804088056087494,
|
| 14026 |
+
"learning_rate": 0.0001988165680473373,
|
| 14027 |
+
"loss": 1.6183083057403564,
|
| 14028 |
+
"step": 3996
|
| 14029 |
+
},
|
| 14030 |
+
{
|
| 14031 |
+
"epoch": 0.8342201356285863,
|
| 14032 |
+
"grad_norm": 0.17482876777648926,
|
| 14033 |
+
"learning_rate": 0.00019831828090937403,
|
| 14034 |
+
"loss": 1.73622727394104,
|
| 14035 |
+
"step": 3998
|
| 14036 |
+
},
|
| 14037 |
+
{
|
| 14038 |
+
"epoch": 0.8346374543557642,
|
| 14039 |
+
"grad_norm": 0.17766039073467255,
|
| 14040 |
+
"learning_rate": 0.0001978199937714108,
|
| 14041 |
+
"loss": 1.7408409118652344,
|
| 14042 |
+
"step": 4000
|
| 14043 |
+
},
|
| 14044 |
+
{
|
| 14045 |
+
"epoch": 0.8350547730829421,
|
| 14046 |
+
"grad_norm": 0.17571066319942474,
|
| 14047 |
+
"learning_rate": 0.00019732170663344753,
|
| 14048 |
+
"loss": 1.6120573282241821,
|
| 14049 |
+
"step": 4002
|
| 14050 |
+
},
|
| 14051 |
+
{
|
| 14052 |
+
"epoch": 0.8354720918101199,
|
| 14053 |
+
"grad_norm": 0.18707862496376038,
|
| 14054 |
+
"learning_rate": 0.0001968234194954843,
|
| 14055 |
+
"loss": 1.7047288417816162,
|
| 14056 |
+
"step": 4004
|
| 14057 |
+
},
|
| 14058 |
+
{
|
| 14059 |
+
"epoch": 0.8358894105372978,
|
| 14060 |
+
"grad_norm": 0.1814654916524887,
|
| 14061 |
+
"learning_rate": 0.00019632513235752104,
|
| 14062 |
+
"loss": 1.6476895809173584,
|
| 14063 |
+
"step": 4006
|
| 14064 |
+
},
|
| 14065 |
+
{
|
| 14066 |
+
"epoch": 0.8363067292644757,
|
| 14067 |
+
"grad_norm": 0.2454279214143753,
|
| 14068 |
+
"learning_rate": 0.00019582684521955777,
|
| 14069 |
+
"loss": 1.6494747400283813,
|
| 14070 |
+
"step": 4008
|
| 14071 |
+
},
|
| 14072 |
+
{
|
| 14073 |
+
"epoch": 0.8367240479916537,
|
| 14074 |
+
"grad_norm": 0.18015429377555847,
|
| 14075 |
+
"learning_rate": 0.00019532855808159454,
|
| 14076 |
+
"loss": 1.6449940204620361,
|
| 14077 |
+
"step": 4010
|
| 14078 |
+
},
|
| 14079 |
+
{
|
| 14080 |
+
"epoch": 0.8371413667188315,
|
| 14081 |
+
"grad_norm": 0.19813057780265808,
|
| 14082 |
+
"learning_rate": 0.00019483027094363128,
|
| 14083 |
+
"loss": 1.461126685142517,
|
| 14084 |
+
"step": 4012
|
| 14085 |
+
},
|
| 14086 |
+
{
|
| 14087 |
+
"epoch": 0.8375586854460094,
|
| 14088 |
+
"grad_norm": 0.1895369291305542,
|
| 14089 |
+
"learning_rate": 0.00019433198380566801,
|
| 14090 |
+
"loss": 1.6304774284362793,
|
| 14091 |
+
"step": 4014
|
| 14092 |
+
},
|
| 14093 |
+
{
|
| 14094 |
+
"epoch": 0.8379760041731873,
|
| 14095 |
+
"grad_norm": 0.22598986327648163,
|
| 14096 |
+
"learning_rate": 0.00019383369666770478,
|
| 14097 |
+
"loss": 1.5876799821853638,
|
| 14098 |
+
"step": 4016
|
| 14099 |
+
},
|
| 14100 |
+
{
|
| 14101 |
+
"epoch": 0.8383933229003652,
|
| 14102 |
+
"grad_norm": 0.16353179514408112,
|
| 14103 |
+
"learning_rate": 0.00019333540952974152,
|
| 14104 |
+
"loss": 1.670882225036621,
|
| 14105 |
+
"step": 4018
|
| 14106 |
+
},
|
| 14107 |
+
{
|
| 14108 |
+
"epoch": 0.838810641627543,
|
| 14109 |
+
"grad_norm": 0.16480985283851624,
|
| 14110 |
+
"learning_rate": 0.00019283712239177828,
|
| 14111 |
+
"loss": 1.6846975088119507,
|
| 14112 |
+
"step": 4020
|
| 14113 |
+
},
|
| 14114 |
+
{
|
| 14115 |
+
"epoch": 0.8392279603547209,
|
| 14116 |
+
"grad_norm": 0.1873014122247696,
|
| 14117 |
+
"learning_rate": 0.00019233883525381502,
|
| 14118 |
+
"loss": 1.690040946006775,
|
| 14119 |
+
"step": 4022
|
| 14120 |
+
},
|
| 14121 |
+
{
|
| 14122 |
+
"epoch": 0.8396452790818988,
|
| 14123 |
+
"grad_norm": 0.17535239458084106,
|
| 14124 |
+
"learning_rate": 0.00019184054811585176,
|
| 14125 |
+
"loss": 1.6181294918060303,
|
| 14126 |
+
"step": 4024
|
| 14127 |
+
},
|
| 14128 |
+
{
|
| 14129 |
+
"epoch": 0.8400625978090767,
|
| 14130 |
+
"grad_norm": 0.23253878951072693,
|
| 14131 |
+
"learning_rate": 0.00019134226097788852,
|
| 14132 |
+
"loss": 1.5434880256652832,
|
| 14133 |
+
"step": 4026
|
| 14134 |
+
},
|
| 14135 |
+
{
|
| 14136 |
+
"epoch": 0.8404799165362545,
|
| 14137 |
+
"grad_norm": 0.16973750293254852,
|
| 14138 |
+
"learning_rate": 0.00019084397383992526,
|
| 14139 |
+
"loss": 1.6462557315826416,
|
| 14140 |
+
"step": 4028
|
| 14141 |
+
},
|
| 14142 |
+
{
|
| 14143 |
+
"epoch": 0.8408972352634324,
|
| 14144 |
+
"grad_norm": 0.19195866584777832,
|
| 14145 |
+
"learning_rate": 0.00019034568670196203,
|
| 14146 |
+
"loss": 1.6567882299423218,
|
| 14147 |
+
"step": 4030
|
| 14148 |
+
},
|
| 14149 |
+
{
|
| 14150 |
+
"epoch": 0.8413145539906103,
|
| 14151 |
+
"grad_norm": 0.19295237958431244,
|
| 14152 |
+
"learning_rate": 0.00018984739956399876,
|
| 14153 |
+
"loss": 1.635372281074524,
|
| 14154 |
+
"step": 4032
|
| 14155 |
+
},
|
| 14156 |
+
{
|
| 14157 |
+
"epoch": 0.8417318727177883,
|
| 14158 |
+
"grad_norm": 0.195025235414505,
|
| 14159 |
+
"learning_rate": 0.0001893491124260355,
|
| 14160 |
+
"loss": 1.7076184749603271,
|
| 14161 |
+
"step": 4034
|
| 14162 |
+
},
|
| 14163 |
+
{
|
| 14164 |
+
"epoch": 0.8421491914449661,
|
| 14165 |
+
"grad_norm": 0.22713610529899597,
|
| 14166 |
+
"learning_rate": 0.00018885082528807227,
|
| 14167 |
+
"loss": 1.5234016180038452,
|
| 14168 |
+
"step": 4036
|
| 14169 |
+
},
|
| 14170 |
+
{
|
| 14171 |
+
"epoch": 0.842566510172144,
|
| 14172 |
+
"grad_norm": 0.1975746899843216,
|
| 14173 |
+
"learning_rate": 0.000188352538150109,
|
| 14174 |
+
"loss": 1.711593747138977,
|
| 14175 |
+
"step": 4038
|
| 14176 |
+
},
|
| 14177 |
+
{
|
| 14178 |
+
"epoch": 0.8429838288993219,
|
| 14179 |
+
"grad_norm": 0.19030791521072388,
|
| 14180 |
+
"learning_rate": 0.00018785425101214574,
|
| 14181 |
+
"loss": 1.6802881956100464,
|
| 14182 |
+
"step": 4040
|
| 14183 |
+
},
|
| 14184 |
+
{
|
| 14185 |
+
"epoch": 0.8434011476264998,
|
| 14186 |
+
"grad_norm": 0.2094624787569046,
|
| 14187 |
+
"learning_rate": 0.0001873559638741825,
|
| 14188 |
+
"loss": 1.6112802028656006,
|
| 14189 |
+
"step": 4042
|
| 14190 |
+
},
|
| 14191 |
+
{
|
| 14192 |
+
"epoch": 0.8438184663536776,
|
| 14193 |
+
"grad_norm": 0.18288825452327728,
|
| 14194 |
+
"learning_rate": 0.00018685767673621924,
|
| 14195 |
+
"loss": 1.5856302976608276,
|
| 14196 |
+
"step": 4044
|
| 14197 |
+
},
|
| 14198 |
+
{
|
| 14199 |
+
"epoch": 0.8442357850808555,
|
| 14200 |
+
"grad_norm": 0.21274502575397491,
|
| 14201 |
+
"learning_rate": 0.000186359389598256,
|
| 14202 |
+
"loss": 1.674270749092102,
|
| 14203 |
+
"step": 4046
|
| 14204 |
+
},
|
| 14205 |
+
{
|
| 14206 |
+
"epoch": 0.8446531038080334,
|
| 14207 |
+
"grad_norm": 0.19420906901359558,
|
| 14208 |
+
"learning_rate": 0.00018586110246029275,
|
| 14209 |
+
"loss": 1.6582943201065063,
|
| 14210 |
+
"step": 4048
|
| 14211 |
+
},
|
| 14212 |
+
{
|
| 14213 |
+
"epoch": 0.8450704225352113,
|
| 14214 |
+
"grad_norm": 0.18451790511608124,
|
| 14215 |
+
"learning_rate": 0.0001853628153223295,
|
| 14216 |
+
"loss": 1.6256777048110962,
|
| 14217 |
+
"step": 4050
|
| 14218 |
+
},
|
| 14219 |
+
{
|
| 14220 |
+
"epoch": 0.8454877412623891,
|
| 14221 |
+
"grad_norm": 0.16896241903305054,
|
| 14222 |
+
"learning_rate": 0.00018486452818436625,
|
| 14223 |
+
"loss": 1.7003672122955322,
|
| 14224 |
+
"step": 4052
|
| 14225 |
+
},
|
| 14226 |
+
{
|
| 14227 |
+
"epoch": 0.845905059989567,
|
| 14228 |
+
"grad_norm": 0.18207846581935883,
|
| 14229 |
+
"learning_rate": 0.000184366241046403,
|
| 14230 |
+
"loss": 1.6286587715148926,
|
| 14231 |
+
"step": 4054
|
| 14232 |
+
},
|
| 14233 |
+
{
|
| 14234 |
+
"epoch": 0.8463223787167449,
|
| 14235 |
+
"grad_norm": 0.22023826837539673,
|
| 14236 |
+
"learning_rate": 0.00018386795390843973,
|
| 14237 |
+
"loss": 1.5539515018463135,
|
| 14238 |
+
"step": 4056
|
| 14239 |
+
},
|
| 14240 |
+
{
|
| 14241 |
+
"epoch": 0.8467396974439227,
|
| 14242 |
+
"grad_norm": 0.16868507862091064,
|
| 14243 |
+
"learning_rate": 0.0001833696667704765,
|
| 14244 |
+
"loss": 1.6270174980163574,
|
| 14245 |
+
"step": 4058
|
| 14246 |
+
},
|
| 14247 |
+
{
|
| 14248 |
+
"epoch": 0.8471570161711007,
|
| 14249 |
+
"grad_norm": 0.18117032945156097,
|
| 14250 |
+
"learning_rate": 0.00018287137963251323,
|
| 14251 |
+
"loss": 1.5214279890060425,
|
| 14252 |
+
"step": 4060
|
| 14253 |
+
},
|
| 14254 |
+
{
|
| 14255 |
+
"epoch": 0.8475743348982786,
|
| 14256 |
+
"grad_norm": 0.15181727707386017,
|
| 14257 |
+
"learning_rate": 0.00018237309249455,
|
| 14258 |
+
"loss": 1.6494383811950684,
|
| 14259 |
+
"step": 4062
|
| 14260 |
+
},
|
| 14261 |
+
{
|
| 14262 |
+
"epoch": 0.8479916536254565,
|
| 14263 |
+
"grad_norm": 0.23103384673595428,
|
| 14264 |
+
"learning_rate": 0.00018187480535658673,
|
| 14265 |
+
"loss": 1.5475603342056274,
|
| 14266 |
+
"step": 4064
|
| 14267 |
+
},
|
| 14268 |
+
{
|
| 14269 |
+
"epoch": 0.8484089723526343,
|
| 14270 |
+
"grad_norm": 0.1830928772687912,
|
| 14271 |
+
"learning_rate": 0.0001813765182186235,
|
| 14272 |
+
"loss": 1.7238051891326904,
|
| 14273 |
+
"step": 4066
|
| 14274 |
+
},
|
| 14275 |
+
{
|
| 14276 |
+
"epoch": 0.8488262910798122,
|
| 14277 |
+
"grad_norm": 0.1808210015296936,
|
| 14278 |
+
"learning_rate": 0.00018087823108066023,
|
| 14279 |
+
"loss": 1.6027417182922363,
|
| 14280 |
+
"step": 4068
|
| 14281 |
+
},
|
| 14282 |
+
{
|
| 14283 |
+
"epoch": 0.8492436098069901,
|
| 14284 |
+
"grad_norm": 0.17436878383159637,
|
| 14285 |
+
"learning_rate": 0.000180379943942697,
|
| 14286 |
+
"loss": 1.5270894765853882,
|
| 14287 |
+
"step": 4070
|
| 14288 |
+
},
|
| 14289 |
+
{
|
| 14290 |
+
"epoch": 0.849660928534168,
|
| 14291 |
+
"grad_norm": 0.2353087067604065,
|
| 14292 |
+
"learning_rate": 0.00017988165680473374,
|
| 14293 |
+
"loss": 1.660226821899414,
|
| 14294 |
+
"step": 4072
|
| 14295 |
+
},
|
| 14296 |
+
{
|
| 14297 |
+
"epoch": 0.8500782472613458,
|
| 14298 |
+
"grad_norm": 0.18193411827087402,
|
| 14299 |
+
"learning_rate": 0.0001793833696667705,
|
| 14300 |
+
"loss": 1.6704041957855225,
|
| 14301 |
+
"step": 4074
|
| 14302 |
+
},
|
| 14303 |
+
{
|
| 14304 |
+
"epoch": 0.8504955659885237,
|
| 14305 |
+
"grad_norm": 0.157639741897583,
|
| 14306 |
+
"learning_rate": 0.0001788850825288072,
|
| 14307 |
+
"loss": 1.721926212310791,
|
| 14308 |
+
"step": 4076
|
| 14309 |
+
},
|
| 14310 |
+
{
|
| 14311 |
+
"epoch": 0.8509128847157016,
|
| 14312 |
+
"grad_norm": 0.1731785237789154,
|
| 14313 |
+
"learning_rate": 0.00017838679539084398,
|
| 14314 |
+
"loss": 1.6603143215179443,
|
| 14315 |
+
"step": 4078
|
| 14316 |
+
},
|
| 14317 |
+
{
|
| 14318 |
+
"epoch": 0.8513302034428795,
|
| 14319 |
+
"grad_norm": 0.16457518935203552,
|
| 14320 |
+
"learning_rate": 0.00017788850825288072,
|
| 14321 |
+
"loss": 1.5349699258804321,
|
| 14322 |
+
"step": 4080
|
| 14323 |
+
},
|
| 14324 |
+
{
|
| 14325 |
+
"epoch": 0.8517475221700573,
|
| 14326 |
+
"grad_norm": 0.18919974565505981,
|
| 14327 |
+
"learning_rate": 0.00017739022111491748,
|
| 14328 |
+
"loss": 1.5536229610443115,
|
| 14329 |
+
"step": 4082
|
| 14330 |
+
},
|
| 14331 |
+
{
|
| 14332 |
+
"epoch": 0.8521648408972352,
|
| 14333 |
+
"grad_norm": 0.18905764818191528,
|
| 14334 |
+
"learning_rate": 0.00017689193397695422,
|
| 14335 |
+
"loss": 1.5567257404327393,
|
| 14336 |
+
"step": 4084
|
| 14337 |
+
},
|
| 14338 |
+
{
|
| 14339 |
+
"epoch": 0.8525821596244132,
|
| 14340 |
+
"grad_norm": 0.18444348871707916,
|
| 14341 |
+
"learning_rate": 0.00017639364683899098,
|
| 14342 |
+
"loss": 1.528328776359558,
|
| 14343 |
+
"step": 4086
|
| 14344 |
+
},
|
| 14345 |
+
{
|
| 14346 |
+
"epoch": 0.8529994783515911,
|
| 14347 |
+
"grad_norm": 0.18102359771728516,
|
| 14348 |
+
"learning_rate": 0.00017589535970102772,
|
| 14349 |
+
"loss": 1.6205244064331055,
|
| 14350 |
+
"step": 4088
|
| 14351 |
+
},
|
| 14352 |
+
{
|
| 14353 |
+
"epoch": 0.8534167970787689,
|
| 14354 |
+
"grad_norm": 0.19649460911750793,
|
| 14355 |
+
"learning_rate": 0.00017539707256306449,
|
| 14356 |
+
"loss": 1.5504631996154785,
|
| 14357 |
+
"step": 4090
|
| 14358 |
+
},
|
| 14359 |
+
{
|
| 14360 |
+
"epoch": 0.8538341158059468,
|
| 14361 |
+
"grad_norm": 0.17354848980903625,
|
| 14362 |
+
"learning_rate": 0.00017489878542510122,
|
| 14363 |
+
"loss": 1.652526617050171,
|
| 14364 |
+
"step": 4092
|
| 14365 |
+
},
|
| 14366 |
+
{
|
| 14367 |
+
"epoch": 0.8542514345331247,
|
| 14368 |
+
"grad_norm": 0.19733025133609772,
|
| 14369 |
+
"learning_rate": 0.000174400498287138,
|
| 14370 |
+
"loss": 1.679112434387207,
|
| 14371 |
+
"step": 4094
|
| 14372 |
+
},
|
| 14373 |
+
{
|
| 14374 |
+
"epoch": 0.8546687532603026,
|
| 14375 |
+
"grad_norm": 0.20596131682395935,
|
| 14376 |
+
"learning_rate": 0.0001739022111491747,
|
| 14377 |
+
"loss": 1.4270410537719727,
|
| 14378 |
+
"step": 4096
|
| 14379 |
+
},
|
| 14380 |
+
{
|
| 14381 |
+
"epoch": 0.8550860719874804,
|
| 14382 |
+
"grad_norm": 0.18710580468177795,
|
| 14383 |
+
"learning_rate": 0.00017340392401121146,
|
| 14384 |
+
"loss": 1.5961430072784424,
|
| 14385 |
+
"step": 4098
|
| 14386 |
+
},
|
| 14387 |
+
{
|
| 14388 |
+
"epoch": 0.8555033907146583,
|
| 14389 |
+
"grad_norm": 0.18958649039268494,
|
| 14390 |
+
"learning_rate": 0.0001729056368732482,
|
| 14391 |
+
"loss": 1.593994379043579,
|
| 14392 |
+
"step": 4100
|
| 14393 |
+
},
|
| 14394 |
+
{
|
| 14395 |
+
"epoch": 0.8559207094418362,
|
| 14396 |
+
"grad_norm": 0.1896360069513321,
|
| 14397 |
+
"learning_rate": 0.00017240734973528497,
|
| 14398 |
+
"loss": 1.6488350629806519,
|
| 14399 |
+
"step": 4102
|
| 14400 |
+
},
|
| 14401 |
+
{
|
| 14402 |
+
"epoch": 0.856338028169014,
|
| 14403 |
+
"grad_norm": 0.19518868625164032,
|
| 14404 |
+
"learning_rate": 0.0001719090625973217,
|
| 14405 |
+
"loss": 1.6326905488967896,
|
| 14406 |
+
"step": 4104
|
| 14407 |
+
},
|
| 14408 |
+
{
|
| 14409 |
+
"epoch": 0.8567553468961919,
|
| 14410 |
+
"grad_norm": 0.18605078756809235,
|
| 14411 |
+
"learning_rate": 0.00017141077545935847,
|
| 14412 |
+
"loss": 1.6978832483291626,
|
| 14413 |
+
"step": 4106
|
| 14414 |
+
},
|
| 14415 |
+
{
|
| 14416 |
+
"epoch": 0.8571726656233698,
|
| 14417 |
+
"grad_norm": 0.19510576128959656,
|
| 14418 |
+
"learning_rate": 0.0001709124883213952,
|
| 14419 |
+
"loss": 1.722651720046997,
|
| 14420 |
+
"step": 4108
|
| 14421 |
+
},
|
| 14422 |
+
{
|
| 14423 |
+
"epoch": 0.8575899843505478,
|
| 14424 |
+
"grad_norm": 0.16520658135414124,
|
| 14425 |
+
"learning_rate": 0.00017041420118343197,
|
| 14426 |
+
"loss": 1.6256784200668335,
|
| 14427 |
+
"step": 4110
|
| 14428 |
+
},
|
| 14429 |
+
{
|
| 14430 |
+
"epoch": 0.8580073030777257,
|
| 14431 |
+
"grad_norm": 0.1725723147392273,
|
| 14432 |
+
"learning_rate": 0.0001699159140454687,
|
| 14433 |
+
"loss": 1.6118927001953125,
|
| 14434 |
+
"step": 4112
|
| 14435 |
+
},
|
| 14436 |
+
{
|
| 14437 |
+
"epoch": 0.8584246218049035,
|
| 14438 |
+
"grad_norm": 0.17283189296722412,
|
| 14439 |
+
"learning_rate": 0.00016941762690750548,
|
| 14440 |
+
"loss": 1.6664702892303467,
|
| 14441 |
+
"step": 4114
|
| 14442 |
+
},
|
| 14443 |
+
{
|
| 14444 |
+
"epoch": 0.8588419405320814,
|
| 14445 |
+
"grad_norm": 0.1931280642747879,
|
| 14446 |
+
"learning_rate": 0.0001689193397695422,
|
| 14447 |
+
"loss": 1.6569066047668457,
|
| 14448 |
+
"step": 4116
|
| 14449 |
+
},
|
| 14450 |
+
{
|
| 14451 |
+
"epoch": 0.8592592592592593,
|
| 14452 |
+
"grad_norm": 0.1914769858121872,
|
| 14453 |
+
"learning_rate": 0.00016842105263157895,
|
| 14454 |
+
"loss": 1.6330338716506958,
|
| 14455 |
+
"step": 4118
|
| 14456 |
+
},
|
| 14457 |
+
{
|
| 14458 |
+
"epoch": 0.8596765779864372,
|
| 14459 |
+
"grad_norm": 0.19188779592514038,
|
| 14460 |
+
"learning_rate": 0.0001679227654936157,
|
| 14461 |
+
"loss": 1.6686639785766602,
|
| 14462 |
+
"step": 4120
|
| 14463 |
+
},
|
| 14464 |
+
{
|
| 14465 |
+
"epoch": 0.860093896713615,
|
| 14466 |
+
"grad_norm": 0.20317953824996948,
|
| 14467 |
+
"learning_rate": 0.00016742447835565245,
|
| 14468 |
+
"loss": 1.661203384399414,
|
| 14469 |
+
"step": 4122
|
| 14470 |
+
},
|
| 14471 |
+
{
|
| 14472 |
+
"epoch": 0.8605112154407929,
|
| 14473 |
+
"grad_norm": 0.1870126873254776,
|
| 14474 |
+
"learning_rate": 0.0001669261912176892,
|
| 14475 |
+
"loss": 1.6325947046279907,
|
| 14476 |
+
"step": 4124
|
| 14477 |
+
},
|
| 14478 |
+
{
|
| 14479 |
+
"epoch": 0.8609285341679708,
|
| 14480 |
+
"grad_norm": 0.1979297399520874,
|
| 14481 |
+
"learning_rate": 0.00016642790407972596,
|
| 14482 |
+
"loss": 1.6142420768737793,
|
| 14483 |
+
"step": 4126
|
| 14484 |
+
},
|
| 14485 |
+
{
|
| 14486 |
+
"epoch": 0.8613458528951486,
|
| 14487 |
+
"grad_norm": 0.17889894545078278,
|
| 14488 |
+
"learning_rate": 0.0001659296169417627,
|
| 14489 |
+
"loss": 1.7480411529541016,
|
| 14490 |
+
"step": 4128
|
| 14491 |
+
},
|
| 14492 |
+
{
|
| 14493 |
+
"epoch": 0.8617631716223265,
|
| 14494 |
+
"grad_norm": 0.1875065267086029,
|
| 14495 |
+
"learning_rate": 0.00016543132980379946,
|
| 14496 |
+
"loss": 1.6685492992401123,
|
| 14497 |
+
"step": 4130
|
| 14498 |
+
},
|
| 14499 |
+
{
|
| 14500 |
+
"epoch": 0.8621804903495044,
|
| 14501 |
+
"grad_norm": 0.1852869987487793,
|
| 14502 |
+
"learning_rate": 0.0001649330426658362,
|
| 14503 |
+
"loss": 1.5089213848114014,
|
| 14504 |
+
"step": 4132
|
| 14505 |
+
},
|
| 14506 |
+
{
|
| 14507 |
+
"epoch": 0.8625978090766823,
|
| 14508 |
+
"grad_norm": 0.21147358417510986,
|
| 14509 |
+
"learning_rate": 0.00016443475552787296,
|
| 14510 |
+
"loss": 1.6361830234527588,
|
| 14511 |
+
"step": 4134
|
| 14512 |
+
},
|
| 14513 |
+
{
|
| 14514 |
+
"epoch": 0.8630151278038602,
|
| 14515 |
+
"grad_norm": 0.19058911502361298,
|
| 14516 |
+
"learning_rate": 0.0001639364683899097,
|
| 14517 |
+
"loss": 1.6463992595672607,
|
| 14518 |
+
"step": 4136
|
| 14519 |
+
},
|
| 14520 |
+
{
|
| 14521 |
+
"epoch": 0.8634324465310381,
|
| 14522 |
+
"grad_norm": 0.2115446925163269,
|
| 14523 |
+
"learning_rate": 0.00016343818125194644,
|
| 14524 |
+
"loss": 1.5269619226455688,
|
| 14525 |
+
"step": 4138
|
| 14526 |
+
},
|
| 14527 |
+
{
|
| 14528 |
+
"epoch": 0.863849765258216,
|
| 14529 |
+
"grad_norm": 0.15730158984661102,
|
| 14530 |
+
"learning_rate": 0.00016293989411398318,
|
| 14531 |
+
"loss": 1.6363976001739502,
|
| 14532 |
+
"step": 4140
|
| 14533 |
+
},
|
| 14534 |
+
{
|
| 14535 |
+
"epoch": 0.8642670839853939,
|
| 14536 |
+
"grad_norm": 0.16966697573661804,
|
| 14537 |
+
"learning_rate": 0.00016244160697601994,
|
| 14538 |
+
"loss": 1.6779712438583374,
|
| 14539 |
+
"step": 4142
|
| 14540 |
+
},
|
| 14541 |
+
{
|
| 14542 |
+
"epoch": 0.8646844027125717,
|
| 14543 |
+
"grad_norm": 0.20783443748950958,
|
| 14544 |
+
"learning_rate": 0.00016194331983805668,
|
| 14545 |
+
"loss": 1.5522081851959229,
|
| 14546 |
+
"step": 4144
|
| 14547 |
+
},
|
| 14548 |
+
{
|
| 14549 |
+
"epoch": 0.8651017214397496,
|
| 14550 |
+
"grad_norm": 0.19765686988830566,
|
| 14551 |
+
"learning_rate": 0.00016144503270009344,
|
| 14552 |
+
"loss": 1.671380639076233,
|
| 14553 |
+
"step": 4146
|
| 14554 |
+
},
|
| 14555 |
+
{
|
| 14556 |
+
"epoch": 0.8655190401669275,
|
| 14557 |
+
"grad_norm": 0.20410001277923584,
|
| 14558 |
+
"learning_rate": 0.00016094674556213018,
|
| 14559 |
+
"loss": 1.6107127666473389,
|
| 14560 |
+
"step": 4148
|
| 14561 |
+
},
|
| 14562 |
+
{
|
| 14563 |
+
"epoch": 0.8659363588941054,
|
| 14564 |
+
"grad_norm": 0.190677672624588,
|
| 14565 |
+
"learning_rate": 0.00016044845842416695,
|
| 14566 |
+
"loss": 1.5826854705810547,
|
| 14567 |
+
"step": 4150
|
| 14568 |
+
},
|
| 14569 |
+
{
|
| 14570 |
+
"epoch": 0.8663536776212832,
|
| 14571 |
+
"grad_norm": 0.2105415016412735,
|
| 14572 |
+
"learning_rate": 0.00015995017128620368,
|
| 14573 |
+
"loss": 1.5512585639953613,
|
| 14574 |
+
"step": 4152
|
| 14575 |
+
},
|
| 14576 |
+
{
|
| 14577 |
+
"epoch": 0.8667709963484611,
|
| 14578 |
+
"grad_norm": 0.19135600328445435,
|
| 14579 |
+
"learning_rate": 0.00015945188414824045,
|
| 14580 |
+
"loss": 1.6250895261764526,
|
| 14581 |
+
"step": 4154
|
| 14582 |
+
},
|
| 14583 |
+
{
|
| 14584 |
+
"epoch": 0.867188315075639,
|
| 14585 |
+
"grad_norm": 0.18524521589279175,
|
| 14586 |
+
"learning_rate": 0.0001589535970102772,
|
| 14587 |
+
"loss": 1.5601701736450195,
|
| 14588 |
+
"step": 4156
|
| 14589 |
+
},
|
| 14590 |
+
{
|
| 14591 |
+
"epoch": 0.8676056338028169,
|
| 14592 |
+
"grad_norm": 0.18301470577716827,
|
| 14593 |
+
"learning_rate": 0.00015845530987231395,
|
| 14594 |
+
"loss": 1.6799218654632568,
|
| 14595 |
+
"step": 4158
|
| 14596 |
+
},
|
| 14597 |
+
{
|
| 14598 |
+
"epoch": 0.8680229525299947,
|
| 14599 |
+
"grad_norm": 0.17439837753772736,
|
| 14600 |
+
"learning_rate": 0.00015795702273435066,
|
| 14601 |
+
"loss": 1.6412632465362549,
|
| 14602 |
+
"step": 4160
|
| 14603 |
+
},
|
| 14604 |
+
{
|
| 14605 |
+
"epoch": 0.8684402712571727,
|
| 14606 |
+
"grad_norm": 0.1827184110879898,
|
| 14607 |
+
"learning_rate": 0.00015745873559638743,
|
| 14608 |
+
"loss": 1.7115901708602905,
|
| 14609 |
+
"step": 4162
|
| 14610 |
+
},
|
| 14611 |
+
{
|
| 14612 |
+
"epoch": 0.8688575899843506,
|
| 14613 |
+
"grad_norm": 0.17392058670520782,
|
| 14614 |
+
"learning_rate": 0.00015696044845842417,
|
| 14615 |
+
"loss": 1.626024603843689,
|
| 14616 |
+
"step": 4164
|
| 14617 |
+
},
|
| 14618 |
+
{
|
| 14619 |
+
"epoch": 0.8692749087115285,
|
| 14620 |
+
"grad_norm": 0.17182692885398865,
|
| 14621 |
+
"learning_rate": 0.00015646216132046093,
|
| 14622 |
+
"loss": 1.748465657234192,
|
| 14623 |
+
"step": 4166
|
| 14624 |
+
},
|
| 14625 |
+
{
|
| 14626 |
+
"epoch": 0.8696922274387063,
|
| 14627 |
+
"grad_norm": 0.22162099182605743,
|
| 14628 |
+
"learning_rate": 0.00015596387418249767,
|
| 14629 |
+
"loss": 1.7301583290100098,
|
| 14630 |
+
"step": 4168
|
| 14631 |
+
},
|
| 14632 |
+
{
|
| 14633 |
+
"epoch": 0.8701095461658842,
|
| 14634 |
+
"grad_norm": 0.16363243758678436,
|
| 14635 |
+
"learning_rate": 0.00015546558704453443,
|
| 14636 |
+
"loss": 1.6637986898422241,
|
| 14637 |
+
"step": 4170
|
| 14638 |
+
},
|
| 14639 |
+
{
|
| 14640 |
+
"epoch": 0.8705268648930621,
|
| 14641 |
+
"grad_norm": 0.1959371715784073,
|
| 14642 |
+
"learning_rate": 0.00015496729990657117,
|
| 14643 |
+
"loss": 1.6402276754379272,
|
| 14644 |
+
"step": 4172
|
| 14645 |
+
},
|
| 14646 |
+
{
|
| 14647 |
+
"epoch": 0.87094418362024,
|
| 14648 |
+
"grad_norm": 0.16994540393352509,
|
| 14649 |
+
"learning_rate": 0.00015446901276860794,
|
| 14650 |
+
"loss": 1.6850452423095703,
|
| 14651 |
+
"step": 4174
|
| 14652 |
+
},
|
| 14653 |
+
{
|
| 14654 |
+
"epoch": 0.8713615023474178,
|
| 14655 |
+
"grad_norm": 0.18915590643882751,
|
| 14656 |
+
"learning_rate": 0.00015397072563064467,
|
| 14657 |
+
"loss": 1.7614344358444214,
|
| 14658 |
+
"step": 4176
|
| 14659 |
+
},
|
| 14660 |
+
{
|
| 14661 |
+
"epoch": 0.8717788210745957,
|
| 14662 |
+
"grad_norm": 0.21564990282058716,
|
| 14663 |
+
"learning_rate": 0.00015347243849268144,
|
| 14664 |
+
"loss": 1.740942358970642,
|
| 14665 |
+
"step": 4178
|
| 14666 |
+
},
|
| 14667 |
+
{
|
| 14668 |
+
"epoch": 0.8721961398017736,
|
| 14669 |
+
"grad_norm": 0.17307381331920624,
|
| 14670 |
+
"learning_rate": 0.00015297415135471815,
|
| 14671 |
+
"loss": 1.6896008253097534,
|
| 14672 |
+
"step": 4180
|
| 14673 |
+
},
|
| 14674 |
+
{
|
| 14675 |
+
"epoch": 0.8726134585289514,
|
| 14676 |
+
"grad_norm": 0.17976069450378418,
|
| 14677 |
+
"learning_rate": 0.00015247586421675491,
|
| 14678 |
+
"loss": 1.5140951871871948,
|
| 14679 |
+
"step": 4182
|
| 14680 |
+
},
|
| 14681 |
+
{
|
| 14682 |
+
"epoch": 0.8730307772561293,
|
| 14683 |
+
"grad_norm": 0.18065252900123596,
|
| 14684 |
+
"learning_rate": 0.00015197757707879165,
|
| 14685 |
+
"loss": 1.6537516117095947,
|
| 14686 |
+
"step": 4184
|
| 14687 |
+
},
|
| 14688 |
+
{
|
| 14689 |
+
"epoch": 0.8734480959833073,
|
| 14690 |
+
"grad_norm": 0.17097200453281403,
|
| 14691 |
+
"learning_rate": 0.00015147928994082842,
|
| 14692 |
+
"loss": 1.5193525552749634,
|
| 14693 |
+
"step": 4186
|
| 14694 |
+
},
|
| 14695 |
+
{
|
| 14696 |
+
"epoch": 0.8738654147104852,
|
| 14697 |
+
"grad_norm": 0.20268303155899048,
|
| 14698 |
+
"learning_rate": 0.00015098100280286516,
|
| 14699 |
+
"loss": 1.6746410131454468,
|
| 14700 |
+
"step": 4188
|
| 14701 |
+
},
|
| 14702 |
+
{
|
| 14703 |
+
"epoch": 0.874282733437663,
|
| 14704 |
+
"grad_norm": 0.1816016286611557,
|
| 14705 |
+
"learning_rate": 0.00015048271566490192,
|
| 14706 |
+
"loss": 1.5819029808044434,
|
| 14707 |
+
"step": 4190
|
| 14708 |
+
},
|
| 14709 |
+
{
|
| 14710 |
+
"epoch": 0.8747000521648409,
|
| 14711 |
+
"grad_norm": 0.175307035446167,
|
| 14712 |
+
"learning_rate": 0.00014998442852693866,
|
| 14713 |
+
"loss": 1.6841760873794556,
|
| 14714 |
+
"step": 4192
|
| 14715 |
+
},
|
| 14716 |
+
{
|
| 14717 |
+
"epoch": 0.8751173708920188,
|
| 14718 |
+
"grad_norm": 0.20195969939231873,
|
| 14719 |
+
"learning_rate": 0.00014948614138897542,
|
| 14720 |
+
"loss": 1.6861398220062256,
|
| 14721 |
+
"step": 4194
|
| 14722 |
+
},
|
| 14723 |
+
{
|
| 14724 |
+
"epoch": 0.8755346896191967,
|
| 14725 |
+
"grad_norm": 0.18869267404079437,
|
| 14726 |
+
"learning_rate": 0.00014898785425101216,
|
| 14727 |
+
"loss": 1.6720318794250488,
|
| 14728 |
+
"step": 4196
|
| 14729 |
+
},
|
| 14730 |
+
{
|
| 14731 |
+
"epoch": 0.8759520083463745,
|
| 14732 |
+
"grad_norm": 0.16363096237182617,
|
| 14733 |
+
"learning_rate": 0.0001484895671130489,
|
| 14734 |
+
"loss": 1.781600832939148,
|
| 14735 |
+
"step": 4198
|
| 14736 |
+
},
|
| 14737 |
+
{
|
| 14738 |
+
"epoch": 0.8763693270735524,
|
| 14739 |
+
"grad_norm": 0.17589423060417175,
|
| 14740 |
+
"learning_rate": 0.00014799127997508564,
|
| 14741 |
+
"loss": 1.5781477689743042,
|
| 14742 |
+
"step": 4200
|
| 14743 |
+
},
|
| 14744 |
+
{
|
| 14745 |
+
"epoch": 0.8767866458007303,
|
| 14746 |
+
"grad_norm": 0.19791170954704285,
|
| 14747 |
+
"learning_rate": 0.0001474929928371224,
|
| 14748 |
+
"loss": 1.5444563627243042,
|
| 14749 |
+
"step": 4202
|
| 14750 |
+
},
|
| 14751 |
+
{
|
| 14752 |
+
"epoch": 0.8772039645279082,
|
| 14753 |
+
"grad_norm": 0.24233515560626984,
|
| 14754 |
+
"learning_rate": 0.00014699470569915914,
|
| 14755 |
+
"loss": 1.7058964967727661,
|
| 14756 |
+
"step": 4204
|
| 14757 |
+
},
|
| 14758 |
+
{
|
| 14759 |
+
"epoch": 0.877621283255086,
|
| 14760 |
+
"grad_norm": 0.1882489025592804,
|
| 14761 |
+
"learning_rate": 0.0001464964185611959,
|
| 14762 |
+
"loss": 1.5815865993499756,
|
| 14763 |
+
"step": 4206
|
| 14764 |
+
},
|
| 14765 |
+
{
|
| 14766 |
+
"epoch": 0.8780386019822639,
|
| 14767 |
+
"grad_norm": 0.17342013120651245,
|
| 14768 |
+
"learning_rate": 0.00014599813142323264,
|
| 14769 |
+
"loss": 1.646026372909546,
|
| 14770 |
+
"step": 4208
|
| 14771 |
+
},
|
| 14772 |
+
{
|
| 14773 |
+
"epoch": 0.8784559207094418,
|
| 14774 |
+
"grad_norm": 0.21900935471057892,
|
| 14775 |
+
"learning_rate": 0.0001454998442852694,
|
| 14776 |
+
"loss": 1.6741538047790527,
|
| 14777 |
+
"step": 4210
|
| 14778 |
+
},
|
| 14779 |
+
{
|
| 14780 |
+
"epoch": 0.8788732394366198,
|
| 14781 |
+
"grad_norm": 0.18033616244792938,
|
| 14782 |
+
"learning_rate": 0.00014500155714730614,
|
| 14783 |
+
"loss": 1.6662341356277466,
|
| 14784 |
+
"step": 4212
|
| 14785 |
+
},
|
| 14786 |
+
{
|
| 14787 |
+
"epoch": 0.8792905581637976,
|
| 14788 |
+
"grad_norm": 0.17369306087493896,
|
| 14789 |
+
"learning_rate": 0.00014450327000934288,
|
| 14790 |
+
"loss": 1.6094465255737305,
|
| 14791 |
+
"step": 4214
|
| 14792 |
+
},
|
| 14793 |
+
{
|
| 14794 |
+
"epoch": 0.8797078768909755,
|
| 14795 |
+
"grad_norm": 0.19994284212589264,
|
| 14796 |
+
"learning_rate": 0.00014400498287137965,
|
| 14797 |
+
"loss": 1.698074460029602,
|
| 14798 |
+
"step": 4216
|
| 14799 |
+
},
|
| 14800 |
+
{
|
| 14801 |
+
"epoch": 0.8801251956181534,
|
| 14802 |
+
"grad_norm": 0.18714231252670288,
|
| 14803 |
+
"learning_rate": 0.00014350669573341639,
|
| 14804 |
+
"loss": 1.6944200992584229,
|
| 14805 |
+
"step": 4218
|
| 14806 |
+
},
|
| 14807 |
+
{
|
| 14808 |
+
"epoch": 0.8805425143453313,
|
| 14809 |
+
"grad_norm": 0.18917585909366608,
|
| 14810 |
+
"learning_rate": 0.00014300840859545315,
|
| 14811 |
+
"loss": 1.6781073808670044,
|
| 14812 |
+
"step": 4220
|
| 14813 |
+
},
|
| 14814 |
+
{
|
| 14815 |
+
"epoch": 0.8809598330725091,
|
| 14816 |
+
"grad_norm": 0.1856914758682251,
|
| 14817 |
+
"learning_rate": 0.0001425101214574899,
|
| 14818 |
+
"loss": 1.825918197631836,
|
| 14819 |
+
"step": 4222
|
| 14820 |
+
},
|
| 14821 |
+
{
|
| 14822 |
+
"epoch": 0.881377151799687,
|
| 14823 |
+
"grad_norm": 0.18396899104118347,
|
| 14824 |
+
"learning_rate": 0.00014201183431952663,
|
| 14825 |
+
"loss": 1.5716090202331543,
|
| 14826 |
+
"step": 4224
|
| 14827 |
+
},
|
| 14828 |
+
{
|
| 14829 |
+
"epoch": 0.8817944705268649,
|
| 14830 |
+
"grad_norm": 0.1865542232990265,
|
| 14831 |
+
"learning_rate": 0.0001415135471815634,
|
| 14832 |
+
"loss": 1.6458405256271362,
|
| 14833 |
+
"step": 4226
|
| 14834 |
+
},
|
| 14835 |
+
{
|
| 14836 |
+
"epoch": 0.8822117892540428,
|
| 14837 |
+
"grad_norm": 0.23121407628059387,
|
| 14838 |
+
"learning_rate": 0.00014101526004360013,
|
| 14839 |
+
"loss": 1.6912405490875244,
|
| 14840 |
+
"step": 4228
|
| 14841 |
+
},
|
| 14842 |
+
{
|
| 14843 |
+
"epoch": 0.8826291079812206,
|
| 14844 |
+
"grad_norm": 0.24559205770492554,
|
| 14845 |
+
"learning_rate": 0.00014051697290563687,
|
| 14846 |
+
"loss": 1.7803088426589966,
|
| 14847 |
+
"step": 4230
|
| 14848 |
+
},
|
| 14849 |
+
{
|
| 14850 |
+
"epoch": 0.8830464267083985,
|
| 14851 |
+
"grad_norm": 0.19092410802841187,
|
| 14852 |
+
"learning_rate": 0.00014001868576767363,
|
| 14853 |
+
"loss": 1.6274560689926147,
|
| 14854 |
+
"step": 4232
|
| 14855 |
+
},
|
| 14856 |
+
{
|
| 14857 |
+
"epoch": 0.8834637454355764,
|
| 14858 |
+
"grad_norm": 0.19192136824131012,
|
| 14859 |
+
"learning_rate": 0.00013952039862971037,
|
| 14860 |
+
"loss": 1.5976357460021973,
|
| 14861 |
+
"step": 4234
|
| 14862 |
+
},
|
| 14863 |
+
{
|
| 14864 |
+
"epoch": 0.8838810641627542,
|
| 14865 |
+
"grad_norm": 0.19966883957386017,
|
| 14866 |
+
"learning_rate": 0.00013902211149174713,
|
| 14867 |
+
"loss": 1.6499944925308228,
|
| 14868 |
+
"step": 4236
|
| 14869 |
+
},
|
| 14870 |
+
{
|
| 14871 |
+
"epoch": 0.8842983828899322,
|
| 14872 |
+
"grad_norm": 0.18240401148796082,
|
| 14873 |
+
"learning_rate": 0.00013852382435378387,
|
| 14874 |
+
"loss": 1.6760348081588745,
|
| 14875 |
+
"step": 4238
|
| 14876 |
+
},
|
| 14877 |
+
{
|
| 14878 |
+
"epoch": 0.8847157016171101,
|
| 14879 |
+
"grad_norm": 0.22000983357429504,
|
| 14880 |
+
"learning_rate": 0.00013802553721582064,
|
| 14881 |
+
"loss": 1.765512466430664,
|
| 14882 |
+
"step": 4240
|
| 14883 |
+
},
|
| 14884 |
+
{
|
| 14885 |
+
"epoch": 0.885133020344288,
|
| 14886 |
+
"grad_norm": 0.17965154349803925,
|
| 14887 |
+
"learning_rate": 0.00013752725007785737,
|
| 14888 |
+
"loss": 1.5602142810821533,
|
| 14889 |
+
"step": 4242
|
| 14890 |
+
},
|
| 14891 |
+
{
|
| 14892 |
+
"epoch": 0.8855503390714659,
|
| 14893 |
+
"grad_norm": 0.20459780097007751,
|
| 14894 |
+
"learning_rate": 0.0001370289629398941,
|
| 14895 |
+
"loss": 1.513783574104309,
|
| 14896 |
+
"step": 4244
|
| 14897 |
+
},
|
| 14898 |
+
{
|
| 14899 |
+
"epoch": 0.8859676577986437,
|
| 14900 |
+
"grad_norm": 0.166926771402359,
|
| 14901 |
+
"learning_rate": 0.00013653067580193085,
|
| 14902 |
+
"loss": 1.7161343097686768,
|
| 14903 |
+
"step": 4246
|
| 14904 |
+
},
|
| 14905 |
+
{
|
| 14906 |
+
"epoch": 0.8863849765258216,
|
| 14907 |
+
"grad_norm": 0.17636346817016602,
|
| 14908 |
+
"learning_rate": 0.00013603238866396762,
|
| 14909 |
+
"loss": 1.6716426610946655,
|
| 14910 |
+
"step": 4248
|
| 14911 |
+
},
|
| 14912 |
+
{
|
| 14913 |
+
"epoch": 0.8868022952529995,
|
| 14914 |
+
"grad_norm": 0.1830795854330063,
|
| 14915 |
+
"learning_rate": 0.00013553410152600435,
|
| 14916 |
+
"loss": 1.5723251104354858,
|
| 14917 |
+
"step": 4250
|
| 14918 |
+
},
|
| 14919 |
+
{
|
| 14920 |
+
"epoch": 0.8872196139801773,
|
| 14921 |
+
"grad_norm": 0.185004323720932,
|
| 14922 |
+
"learning_rate": 0.00013503581438804112,
|
| 14923 |
+
"loss": 1.6882978677749634,
|
| 14924 |
+
"step": 4252
|
| 14925 |
+
},
|
| 14926 |
+
{
|
| 14927 |
+
"epoch": 0.8876369327073552,
|
| 14928 |
+
"grad_norm": 0.17411819100379944,
|
| 14929 |
+
"learning_rate": 0.00013453752725007786,
|
| 14930 |
+
"loss": 1.7141852378845215,
|
| 14931 |
+
"step": 4254
|
| 14932 |
+
},
|
| 14933 |
+
{
|
| 14934 |
+
"epoch": 0.8880542514345331,
|
| 14935 |
+
"grad_norm": 0.1981218308210373,
|
| 14936 |
+
"learning_rate": 0.00013403924011211462,
|
| 14937 |
+
"loss": 1.641402006149292,
|
| 14938 |
+
"step": 4256
|
| 14939 |
+
},
|
| 14940 |
+
{
|
| 14941 |
+
"epoch": 0.888471570161711,
|
| 14942 |
+
"grad_norm": 0.17821228504180908,
|
| 14943 |
+
"learning_rate": 0.00013354095297415136,
|
| 14944 |
+
"loss": 1.6480239629745483,
|
| 14945 |
+
"step": 4258
|
| 14946 |
+
},
|
| 14947 |
+
{
|
| 14948 |
+
"epoch": 0.8888888888888888,
|
| 14949 |
+
"grad_norm": 0.1579664647579193,
|
| 14950 |
+
"learning_rate": 0.00013304266583618812,
|
| 14951 |
+
"loss": 1.712760329246521,
|
| 14952 |
+
"step": 4260
|
| 14953 |
+
},
|
| 14954 |
+
{
|
| 14955 |
+
"epoch": 0.8893062076160668,
|
| 14956 |
+
"grad_norm": 0.19413398206233978,
|
| 14957 |
+
"learning_rate": 0.00013254437869822486,
|
| 14958 |
+
"loss": 1.7463946342468262,
|
| 14959 |
+
"step": 4262
|
| 14960 |
+
},
|
| 14961 |
+
{
|
| 14962 |
+
"epoch": 0.8897235263432447,
|
| 14963 |
+
"grad_norm": 0.2169637531042099,
|
| 14964 |
+
"learning_rate": 0.0001320460915602616,
|
| 14965 |
+
"loss": 1.4564887285232544,
|
| 14966 |
+
"step": 4264
|
| 14967 |
+
},
|
| 14968 |
+
{
|
| 14969 |
+
"epoch": 0.8901408450704226,
|
| 14970 |
+
"grad_norm": 0.1617715209722519,
|
| 14971 |
+
"learning_rate": 0.00013154780442229834,
|
| 14972 |
+
"loss": 1.6625990867614746,
|
| 14973 |
+
"step": 4266
|
| 14974 |
+
},
|
| 14975 |
+
{
|
| 14976 |
+
"epoch": 0.8905581637976004,
|
| 14977 |
+
"grad_norm": 0.17531977593898773,
|
| 14978 |
+
"learning_rate": 0.0001310495172843351,
|
| 14979 |
+
"loss": 1.5706746578216553,
|
| 14980 |
+
"step": 4268
|
| 14981 |
+
},
|
| 14982 |
+
{
|
| 14983 |
+
"epoch": 0.8909754825247783,
|
| 14984 |
+
"grad_norm": 0.18917573988437653,
|
| 14985 |
+
"learning_rate": 0.00013055123014637184,
|
| 14986 |
+
"loss": 1.6090871095657349,
|
| 14987 |
+
"step": 4270
|
| 14988 |
+
},
|
| 14989 |
+
{
|
| 14990 |
+
"epoch": 0.8913928012519562,
|
| 14991 |
+
"grad_norm": 0.16727563738822937,
|
| 14992 |
+
"learning_rate": 0.0001300529430084086,
|
| 14993 |
+
"loss": 1.4635460376739502,
|
| 14994 |
+
"step": 4272
|
| 14995 |
+
},
|
| 14996 |
+
{
|
| 14997 |
+
"epoch": 0.8918101199791341,
|
| 14998 |
+
"grad_norm": 0.19415424764156342,
|
| 14999 |
+
"learning_rate": 0.00012955465587044534,
|
| 15000 |
+
"loss": 1.6564855575561523,
|
| 15001 |
+
"step": 4274
|
| 15002 |
+
},
|
| 15003 |
+
{
|
| 15004 |
+
"epoch": 0.8922274387063119,
|
| 15005 |
+
"grad_norm": 0.17781133949756622,
|
| 15006 |
+
"learning_rate": 0.0001290563687324821,
|
| 15007 |
+
"loss": 1.6546841859817505,
|
| 15008 |
+
"step": 4276
|
| 15009 |
+
},
|
| 15010 |
+
{
|
| 15011 |
+
"epoch": 0.8926447574334898,
|
| 15012 |
+
"grad_norm": 0.17661771178245544,
|
| 15013 |
+
"learning_rate": 0.00012855808159451885,
|
| 15014 |
+
"loss": 1.615142583847046,
|
| 15015 |
+
"step": 4278
|
| 15016 |
+
},
|
| 15017 |
+
{
|
| 15018 |
+
"epoch": 0.8930620761606677,
|
| 15019 |
+
"grad_norm": 0.189763605594635,
|
| 15020 |
+
"learning_rate": 0.0001280597944565556,
|
| 15021 |
+
"loss": 1.648653268814087,
|
| 15022 |
+
"step": 4280
|
| 15023 |
+
},
|
| 15024 |
+
{
|
| 15025 |
+
"epoch": 0.8934793948878456,
|
| 15026 |
+
"grad_norm": 0.1889771819114685,
|
| 15027 |
+
"learning_rate": 0.00012756150731859235,
|
| 15028 |
+
"loss": 1.60526704788208,
|
| 15029 |
+
"step": 4282
|
| 15030 |
+
},
|
| 15031 |
+
{
|
| 15032 |
+
"epoch": 0.8938967136150234,
|
| 15033 |
+
"grad_norm": 0.20051011443138123,
|
| 15034 |
+
"learning_rate": 0.00012706322018062909,
|
| 15035 |
+
"loss": 1.6328041553497314,
|
| 15036 |
+
"step": 4284
|
| 15037 |
+
},
|
| 15038 |
+
{
|
| 15039 |
+
"epoch": 0.8943140323422013,
|
| 15040 |
+
"grad_norm": 0.24941663444042206,
|
| 15041 |
+
"learning_rate": 0.00012656493304266582,
|
| 15042 |
+
"loss": 1.7087427377700806,
|
| 15043 |
+
"step": 4286
|
| 15044 |
+
},
|
| 15045 |
+
{
|
| 15046 |
+
"epoch": 0.8947313510693793,
|
| 15047 |
+
"grad_norm": 0.17458072304725647,
|
| 15048 |
+
"learning_rate": 0.0001260666459047026,
|
| 15049 |
+
"loss": 1.7527358531951904,
|
| 15050 |
+
"step": 4288
|
| 15051 |
+
},
|
| 15052 |
+
{
|
| 15053 |
+
"epoch": 0.8951486697965572,
|
| 15054 |
+
"grad_norm": 0.16338342428207397,
|
| 15055 |
+
"learning_rate": 0.00012556835876673933,
|
| 15056 |
+
"loss": 1.6104542016983032,
|
| 15057 |
+
"step": 4290
|
| 15058 |
+
},
|
| 15059 |
+
{
|
| 15060 |
+
"epoch": 0.895565988523735,
|
| 15061 |
+
"grad_norm": 0.1791841834783554,
|
| 15062 |
+
"learning_rate": 0.0001250700716287761,
|
| 15063 |
+
"loss": 1.5636260509490967,
|
| 15064 |
+
"step": 4292
|
| 15065 |
+
},
|
| 15066 |
+
{
|
| 15067 |
+
"epoch": 0.8959833072509129,
|
| 15068 |
+
"grad_norm": 0.1994152069091797,
|
| 15069 |
+
"learning_rate": 0.00012457178449081283,
|
| 15070 |
+
"loss": 1.5894802808761597,
|
| 15071 |
+
"step": 4294
|
| 15072 |
+
},
|
| 15073 |
+
{
|
| 15074 |
+
"epoch": 0.8964006259780908,
|
| 15075 |
+
"grad_norm": 0.1872299164533615,
|
| 15076 |
+
"learning_rate": 0.0001240734973528496,
|
| 15077 |
+
"loss": 1.6312882900238037,
|
| 15078 |
+
"step": 4296
|
| 15079 |
+
},
|
| 15080 |
+
{
|
| 15081 |
+
"epoch": 0.8968179447052687,
|
| 15082 |
+
"grad_norm": 0.18088090419769287,
|
| 15083 |
+
"learning_rate": 0.00012357521021488633,
|
| 15084 |
+
"loss": 1.5215966701507568,
|
| 15085 |
+
"step": 4298
|
| 15086 |
+
},
|
| 15087 |
+
{
|
| 15088 |
+
"epoch": 0.8972352634324465,
|
| 15089 |
+
"grad_norm": 0.17654314637184143,
|
| 15090 |
+
"learning_rate": 0.0001230769230769231,
|
| 15091 |
+
"loss": 1.5884132385253906,
|
| 15092 |
+
"step": 4300
|
| 15093 |
+
},
|
| 15094 |
+
{
|
| 15095 |
+
"epoch": 0.8976525821596244,
|
| 15096 |
+
"grad_norm": 0.17969003319740295,
|
| 15097 |
+
"learning_rate": 0.00012257863593895984,
|
| 15098 |
+
"loss": 1.5834084749221802,
|
| 15099 |
+
"step": 4302
|
| 15100 |
+
},
|
| 15101 |
+
{
|
| 15102 |
+
"epoch": 0.8980699008868023,
|
| 15103 |
+
"grad_norm": 0.1986774057149887,
|
| 15104 |
+
"learning_rate": 0.0001220803488009966,
|
| 15105 |
+
"loss": 1.6546990871429443,
|
| 15106 |
+
"step": 4304
|
| 15107 |
+
},
|
| 15108 |
+
{
|
| 15109 |
+
"epoch": 0.8984872196139801,
|
| 15110 |
+
"grad_norm": 0.2006673812866211,
|
| 15111 |
+
"learning_rate": 0.00012158206166303332,
|
| 15112 |
+
"loss": 1.5141408443450928,
|
| 15113 |
+
"step": 4306
|
| 15114 |
+
},
|
| 15115 |
+
{
|
| 15116 |
+
"epoch": 0.898904538341158,
|
| 15117 |
+
"grad_norm": 0.18943582475185394,
|
| 15118 |
+
"learning_rate": 0.00012108377452507008,
|
| 15119 |
+
"loss": 1.582223892211914,
|
| 15120 |
+
"step": 4308
|
| 15121 |
+
},
|
| 15122 |
+
{
|
| 15123 |
+
"epoch": 0.8993218570683359,
|
| 15124 |
+
"grad_norm": 0.18200165033340454,
|
| 15125 |
+
"learning_rate": 0.00012058548738710683,
|
| 15126 |
+
"loss": 1.5982892513275146,
|
| 15127 |
+
"step": 4310
|
| 15128 |
+
},
|
| 15129 |
+
{
|
| 15130 |
+
"epoch": 0.8997391757955139,
|
| 15131 |
+
"grad_norm": 0.2065363973379135,
|
| 15132 |
+
"learning_rate": 0.00012008720024914358,
|
| 15133 |
+
"loss": 1.598642349243164,
|
| 15134 |
+
"step": 4312
|
| 15135 |
+
},
|
| 15136 |
+
{
|
| 15137 |
+
"epoch": 0.9001564945226918,
|
| 15138 |
+
"grad_norm": 0.16489578783512115,
|
| 15139 |
+
"learning_rate": 0.00011958891311118032,
|
| 15140 |
+
"loss": 1.6891593933105469,
|
| 15141 |
+
"step": 4314
|
| 15142 |
+
},
|
| 15143 |
+
{
|
| 15144 |
+
"epoch": 0.9005738132498696,
|
| 15145 |
+
"grad_norm": 0.20588769018650055,
|
| 15146 |
+
"learning_rate": 0.00011909062597321707,
|
| 15147 |
+
"loss": 1.6844552755355835,
|
| 15148 |
+
"step": 4316
|
| 15149 |
+
},
|
| 15150 |
+
{
|
| 15151 |
+
"epoch": 0.9009911319770475,
|
| 15152 |
+
"grad_norm": 0.22354429960250854,
|
| 15153 |
+
"learning_rate": 0.00011859233883525382,
|
| 15154 |
+
"loss": 1.479601263999939,
|
| 15155 |
+
"step": 4318
|
| 15156 |
+
},
|
| 15157 |
+
{
|
| 15158 |
+
"epoch": 0.9014084507042254,
|
| 15159 |
+
"grad_norm": 0.21314990520477295,
|
| 15160 |
+
"learning_rate": 0.00011809405169729057,
|
| 15161 |
+
"loss": 1.5884896516799927,
|
| 15162 |
+
"step": 4320
|
| 15163 |
}
|
| 15164 |
],
|
| 15165 |
"logging_steps": 2,
|
|
|
|
| 15179 |
"attributes": {}
|
| 15180 |
}
|
| 15181 |
},
|
| 15182 |
+
"total_flos": 9.859017257647795e+17,
|
| 15183 |
"train_batch_size": 8,
|
| 15184 |
"trial_name": null,
|
| 15185 |
"trial_params": null
|