Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
unsloth
sft
conversational
text-generation-inference
Instructions to use Ba2han/test_CPTlsft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/test_CPTlsft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/test_CPTlsft") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/test_CPTlsft") model = AutoModelForCausalLM.from_pretrained("Ba2han/test_CPTlsft", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/test_CPTlsft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/test_CPTlsft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/test_CPTlsft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ba2han/test_CPTlsft
- SGLang
How to use Ba2han/test_CPTlsft 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/test_CPTlsft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/test_CPTlsft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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/test_CPTlsft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/test_CPTlsft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use Ba2han/test_CPTlsft with Docker Model Runner:
docker model run hf.co/Ba2han/test_CPTlsft
Training in progress, step 3591, 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 2934397032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84500930c4550d0131db5e72ac033e9737d75547d0cc5bf9f54cd7337e27083b
|
| 3 |
size 2934397032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1470445304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acc1299a27c33dc388041448e1520c6a9f8b6b78c31084f13e98ee5ea9d5c51c
|
| 3 |
size 1470445304
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9785
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6db862809aaf5b1344c8387b680e8ff2c326806defd7ac7524a64d2cbf3d86c2
|
| 3 |
size 9785
|
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,
|
|
@@ -10781,6 +10781,1798 @@
|
|
| 10781 |
"learning_rate": 0.00034688346883468834,
|
| 10782 |
"loss": 2.546942710876465,
|
| 10783 |
"step": 3078
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10784 |
}
|
| 10785 |
],
|
| 10786 |
"logging_steps": 2,
|
|
@@ -10800,7 +12592,7 @@
|
|
| 10800 |
"attributes": {}
|
| 10801 |
}
|
| 10802 |
},
|
| 10803 |
-
"total_flos":
|
| 10804 |
"train_batch_size": 6,
|
| 10805 |
"trial_name": null,
|
| 10806 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7007854808020686,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3591,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10781 |
"learning_rate": 0.00034688346883468834,
|
| 10782 |
"loss": 2.546942710876465,
|
| 10783 |
"step": 3078
|
| 10784 |
+
},
|
| 10785 |
+
{
|
| 10786 |
+
"epoch": 0.6010635702785774,
|
| 10787 |
+
"grad_norm": 0.19421985745429993,
|
| 10788 |
+
"learning_rate": 0.0003465447154471545,
|
| 10789 |
+
"loss": 2.693014144897461,
|
| 10790 |
+
"step": 3080
|
| 10791 |
+
},
|
| 10792 |
+
{
|
| 10793 |
+
"epoch": 0.6014538712982388,
|
| 10794 |
+
"grad_norm": 0.18438977003097534,
|
| 10795 |
+
"learning_rate": 0.00034620596205962064,
|
| 10796 |
+
"loss": 2.4707751274108887,
|
| 10797 |
+
"step": 3082
|
| 10798 |
+
},
|
| 10799 |
+
{
|
| 10800 |
+
"epoch": 0.6018441723179002,
|
| 10801 |
+
"grad_norm": 0.18380297720432281,
|
| 10802 |
+
"learning_rate": 0.0003458672086720867,
|
| 10803 |
+
"loss": 2.5743346214294434,
|
| 10804 |
+
"step": 3084
|
| 10805 |
+
},
|
| 10806 |
+
{
|
| 10807 |
+
"epoch": 0.6022344733375616,
|
| 10808 |
+
"grad_norm": 0.16028916835784912,
|
| 10809 |
+
"learning_rate": 0.00034552845528455285,
|
| 10810 |
+
"loss": 2.6065125465393066,
|
| 10811 |
+
"step": 3086
|
| 10812 |
+
},
|
| 10813 |
+
{
|
| 10814 |
+
"epoch": 0.6026247743572231,
|
| 10815 |
+
"grad_norm": 0.19010736048221588,
|
| 10816 |
+
"learning_rate": 0.000345189701897019,
|
| 10817 |
+
"loss": 2.6068201065063477,
|
| 10818 |
+
"step": 3088
|
| 10819 |
+
},
|
| 10820 |
+
{
|
| 10821 |
+
"epoch": 0.6030150753768844,
|
| 10822 |
+
"grad_norm": 0.16771331429481506,
|
| 10823 |
+
"learning_rate": 0.0003448509485094851,
|
| 10824 |
+
"loss": 2.550327777862549,
|
| 10825 |
+
"step": 3090
|
| 10826 |
+
},
|
| 10827 |
+
{
|
| 10828 |
+
"epoch": 0.6034053763965458,
|
| 10829 |
+
"grad_norm": 0.14991259574890137,
|
| 10830 |
+
"learning_rate": 0.0003445121951219512,
|
| 10831 |
+
"loss": 2.5543417930603027,
|
| 10832 |
+
"step": 3092
|
| 10833 |
+
},
|
| 10834 |
+
{
|
| 10835 |
+
"epoch": 0.6037956774162072,
|
| 10836 |
+
"grad_norm": 0.14199498295783997,
|
| 10837 |
+
"learning_rate": 0.00034417344173441735,
|
| 10838 |
+
"loss": 2.667349338531494,
|
| 10839 |
+
"step": 3094
|
| 10840 |
+
},
|
| 10841 |
+
{
|
| 10842 |
+
"epoch": 0.6041859784358686,
|
| 10843 |
+
"grad_norm": 0.19624000787734985,
|
| 10844 |
+
"learning_rate": 0.00034383468834688345,
|
| 10845 |
+
"loss": 2.5678868293762207,
|
| 10846 |
+
"step": 3096
|
| 10847 |
+
},
|
| 10848 |
+
{
|
| 10849 |
+
"epoch": 0.60457627945553,
|
| 10850 |
+
"grad_norm": 0.16426290571689606,
|
| 10851 |
+
"learning_rate": 0.0003434959349593496,
|
| 10852 |
+
"loss": 2.5980710983276367,
|
| 10853 |
+
"step": 3098
|
| 10854 |
+
},
|
| 10855 |
+
{
|
| 10856 |
+
"epoch": 0.6049665804751915,
|
| 10857 |
+
"grad_norm": 0.14220376312732697,
|
| 10858 |
+
"learning_rate": 0.00034315718157181576,
|
| 10859 |
+
"loss": 2.5892529487609863,
|
| 10860 |
+
"step": 3100
|
| 10861 |
+
},
|
| 10862 |
+
{
|
| 10863 |
+
"epoch": 0.6053568814948529,
|
| 10864 |
+
"grad_norm": 0.13335052132606506,
|
| 10865 |
+
"learning_rate": 0.0003428184281842818,
|
| 10866 |
+
"loss": 2.575284957885742,
|
| 10867 |
+
"step": 3102
|
| 10868 |
+
},
|
| 10869 |
+
{
|
| 10870 |
+
"epoch": 0.6057471825145143,
|
| 10871 |
+
"grad_norm": 0.20660685002803802,
|
| 10872 |
+
"learning_rate": 0.00034247967479674796,
|
| 10873 |
+
"loss": 2.60807728767395,
|
| 10874 |
+
"step": 3104
|
| 10875 |
+
},
|
| 10876 |
+
{
|
| 10877 |
+
"epoch": 0.6061374835341757,
|
| 10878 |
+
"grad_norm": 0.1604757457971573,
|
| 10879 |
+
"learning_rate": 0.0003421409214092141,
|
| 10880 |
+
"loss": 2.636096477508545,
|
| 10881 |
+
"step": 3106
|
| 10882 |
+
},
|
| 10883 |
+
{
|
| 10884 |
+
"epoch": 0.6065277845538372,
|
| 10885 |
+
"grad_norm": 0.19139207899570465,
|
| 10886 |
+
"learning_rate": 0.0003418021680216802,
|
| 10887 |
+
"loss": 2.602609157562256,
|
| 10888 |
+
"step": 3108
|
| 10889 |
+
},
|
| 10890 |
+
{
|
| 10891 |
+
"epoch": 0.6069180855734986,
|
| 10892 |
+
"grad_norm": 0.1668536216020584,
|
| 10893 |
+
"learning_rate": 0.0003414634146341464,
|
| 10894 |
+
"loss": 2.6131253242492676,
|
| 10895 |
+
"step": 3110
|
| 10896 |
+
},
|
| 10897 |
+
{
|
| 10898 |
+
"epoch": 0.60730838659316,
|
| 10899 |
+
"grad_norm": 0.13915471732616425,
|
| 10900 |
+
"learning_rate": 0.0003411246612466125,
|
| 10901 |
+
"loss": 2.5836589336395264,
|
| 10902 |
+
"step": 3112
|
| 10903 |
+
},
|
| 10904 |
+
{
|
| 10905 |
+
"epoch": 0.6076986876128214,
|
| 10906 |
+
"grad_norm": 0.1655646413564682,
|
| 10907 |
+
"learning_rate": 0.0003407859078590786,
|
| 10908 |
+
"loss": 2.5873301029205322,
|
| 10909 |
+
"step": 3114
|
| 10910 |
+
},
|
| 10911 |
+
{
|
| 10912 |
+
"epoch": 0.6080889886324828,
|
| 10913 |
+
"grad_norm": 0.16964063048362732,
|
| 10914 |
+
"learning_rate": 0.00034044715447154473,
|
| 10915 |
+
"loss": 2.5679638385772705,
|
| 10916 |
+
"step": 3116
|
| 10917 |
+
},
|
| 10918 |
+
{
|
| 10919 |
+
"epoch": 0.6084792896521443,
|
| 10920 |
+
"grad_norm": 0.18029730021953583,
|
| 10921 |
+
"learning_rate": 0.0003401084010840109,
|
| 10922 |
+
"loss": 2.566615104675293,
|
| 10923 |
+
"step": 3118
|
| 10924 |
+
},
|
| 10925 |
+
{
|
| 10926 |
+
"epoch": 0.6088695906718057,
|
| 10927 |
+
"grad_norm": 0.1863914132118225,
|
| 10928 |
+
"learning_rate": 0.00033976964769647693,
|
| 10929 |
+
"loss": 2.5504086017608643,
|
| 10930 |
+
"step": 3120
|
| 10931 |
+
},
|
| 10932 |
+
{
|
| 10933 |
+
"epoch": 0.609259891691467,
|
| 10934 |
+
"grad_norm": 0.2689801752567291,
|
| 10935 |
+
"learning_rate": 0.0003394308943089431,
|
| 10936 |
+
"loss": 2.6075191497802734,
|
| 10937 |
+
"step": 3122
|
| 10938 |
+
},
|
| 10939 |
+
{
|
| 10940 |
+
"epoch": 0.6096501927111284,
|
| 10941 |
+
"grad_norm": 0.1415724903345108,
|
| 10942 |
+
"learning_rate": 0.00033909214092140924,
|
| 10943 |
+
"loss": 2.569967269897461,
|
| 10944 |
+
"step": 3124
|
| 10945 |
+
},
|
| 10946 |
+
{
|
| 10947 |
+
"epoch": 0.6100404937307898,
|
| 10948 |
+
"grad_norm": 0.1661580502986908,
|
| 10949 |
+
"learning_rate": 0.00033875338753387534,
|
| 10950 |
+
"loss": 2.557568311691284,
|
| 10951 |
+
"step": 3126
|
| 10952 |
+
},
|
| 10953 |
+
{
|
| 10954 |
+
"epoch": 0.6104307947504513,
|
| 10955 |
+
"grad_norm": 0.15292979776859283,
|
| 10956 |
+
"learning_rate": 0.0003384146341463415,
|
| 10957 |
+
"loss": 2.538832426071167,
|
| 10958 |
+
"step": 3128
|
| 10959 |
+
},
|
| 10960 |
+
{
|
| 10961 |
+
"epoch": 0.6108210957701127,
|
| 10962 |
+
"grad_norm": 0.16570191085338593,
|
| 10963 |
+
"learning_rate": 0.0003380758807588076,
|
| 10964 |
+
"loss": 2.6236729621887207,
|
| 10965 |
+
"step": 3130
|
| 10966 |
+
},
|
| 10967 |
+
{
|
| 10968 |
+
"epoch": 0.6112113967897741,
|
| 10969 |
+
"grad_norm": 0.16778142750263214,
|
| 10970 |
+
"learning_rate": 0.0003377371273712737,
|
| 10971 |
+
"loss": 2.6251637935638428,
|
| 10972 |
+
"step": 3132
|
| 10973 |
+
},
|
| 10974 |
+
{
|
| 10975 |
+
"epoch": 0.6116016978094355,
|
| 10976 |
+
"grad_norm": 0.18864795565605164,
|
| 10977 |
+
"learning_rate": 0.00033739837398373985,
|
| 10978 |
+
"loss": 2.6126151084899902,
|
| 10979 |
+
"step": 3134
|
| 10980 |
+
},
|
| 10981 |
+
{
|
| 10982 |
+
"epoch": 0.6119919988290969,
|
| 10983 |
+
"grad_norm": 0.15705017745494843,
|
| 10984 |
+
"learning_rate": 0.000337059620596206,
|
| 10985 |
+
"loss": 2.581561326980591,
|
| 10986 |
+
"step": 3136
|
| 10987 |
+
},
|
| 10988 |
+
{
|
| 10989 |
+
"epoch": 0.6123822998487584,
|
| 10990 |
+
"grad_norm": 0.15023377537727356,
|
| 10991 |
+
"learning_rate": 0.0003367208672086721,
|
| 10992 |
+
"loss": 2.5618574619293213,
|
| 10993 |
+
"step": 3138
|
| 10994 |
+
},
|
| 10995 |
+
{
|
| 10996 |
+
"epoch": 0.6127726008684198,
|
| 10997 |
+
"grad_norm": 0.17437201738357544,
|
| 10998 |
+
"learning_rate": 0.0003363821138211382,
|
| 10999 |
+
"loss": 2.6137313842773438,
|
| 11000 |
+
"step": 3140
|
| 11001 |
+
},
|
| 11002 |
+
{
|
| 11003 |
+
"epoch": 0.6131629018880812,
|
| 11004 |
+
"grad_norm": 0.19440729916095734,
|
| 11005 |
+
"learning_rate": 0.00033604336043360436,
|
| 11006 |
+
"loss": 2.596619129180908,
|
| 11007 |
+
"step": 3142
|
| 11008 |
+
},
|
| 11009 |
+
{
|
| 11010 |
+
"epoch": 0.6135532029077426,
|
| 11011 |
+
"grad_norm": 0.15925410389900208,
|
| 11012 |
+
"learning_rate": 0.00033570460704607046,
|
| 11013 |
+
"loss": 2.585352897644043,
|
| 11014 |
+
"step": 3144
|
| 11015 |
+
},
|
| 11016 |
+
{
|
| 11017 |
+
"epoch": 0.613943503927404,
|
| 11018 |
+
"grad_norm": 0.17228537797927856,
|
| 11019 |
+
"learning_rate": 0.0003353658536585366,
|
| 11020 |
+
"loss": 2.5965464115142822,
|
| 11021 |
+
"step": 3146
|
| 11022 |
+
},
|
| 11023 |
+
{
|
| 11024 |
+
"epoch": 0.6143338049470655,
|
| 11025 |
+
"grad_norm": 0.15582743287086487,
|
| 11026 |
+
"learning_rate": 0.0003350271002710027,
|
| 11027 |
+
"loss": 2.5441370010375977,
|
| 11028 |
+
"step": 3148
|
| 11029 |
+
},
|
| 11030 |
+
{
|
| 11031 |
+
"epoch": 0.6147241059667269,
|
| 11032 |
+
"grad_norm": 0.16282843053340912,
|
| 11033 |
+
"learning_rate": 0.0003346883468834688,
|
| 11034 |
+
"loss": 2.5016231536865234,
|
| 11035 |
+
"step": 3150
|
| 11036 |
+
},
|
| 11037 |
+
{
|
| 11038 |
+
"epoch": 0.6151144069863883,
|
| 11039 |
+
"grad_norm": 0.1913488507270813,
|
| 11040 |
+
"learning_rate": 0.00033434959349593497,
|
| 11041 |
+
"loss": 2.585716724395752,
|
| 11042 |
+
"step": 3152
|
| 11043 |
+
},
|
| 11044 |
+
{
|
| 11045 |
+
"epoch": 0.6155047080060496,
|
| 11046 |
+
"grad_norm": 0.1596071869134903,
|
| 11047 |
+
"learning_rate": 0.0003340108401084011,
|
| 11048 |
+
"loss": 2.629220485687256,
|
| 11049 |
+
"step": 3154
|
| 11050 |
+
},
|
| 11051 |
+
{
|
| 11052 |
+
"epoch": 0.615895009025711,
|
| 11053 |
+
"grad_norm": 0.15013210475444794,
|
| 11054 |
+
"learning_rate": 0.0003336720867208672,
|
| 11055 |
+
"loss": 2.563169240951538,
|
| 11056 |
+
"step": 3156
|
| 11057 |
+
},
|
| 11058 |
+
{
|
| 11059 |
+
"epoch": 0.6162853100453725,
|
| 11060 |
+
"grad_norm": 0.22157113254070282,
|
| 11061 |
+
"learning_rate": 0.0003333333333333333,
|
| 11062 |
+
"loss": 2.6260719299316406,
|
| 11063 |
+
"step": 3158
|
| 11064 |
+
},
|
| 11065 |
+
{
|
| 11066 |
+
"epoch": 0.6166756110650339,
|
| 11067 |
+
"grad_norm": 0.19343100488185883,
|
| 11068 |
+
"learning_rate": 0.0003329945799457995,
|
| 11069 |
+
"loss": 2.512995958328247,
|
| 11070 |
+
"step": 3160
|
| 11071 |
+
},
|
| 11072 |
+
{
|
| 11073 |
+
"epoch": 0.6170659120846953,
|
| 11074 |
+
"grad_norm": 0.22471114993095398,
|
| 11075 |
+
"learning_rate": 0.0003326558265582656,
|
| 11076 |
+
"loss": 2.580716848373413,
|
| 11077 |
+
"step": 3162
|
| 11078 |
+
},
|
| 11079 |
+
{
|
| 11080 |
+
"epoch": 0.6174562131043567,
|
| 11081 |
+
"grad_norm": 0.17613141238689423,
|
| 11082 |
+
"learning_rate": 0.00033231707317073173,
|
| 11083 |
+
"loss": 2.550299644470215,
|
| 11084 |
+
"step": 3164
|
| 11085 |
+
},
|
| 11086 |
+
{
|
| 11087 |
+
"epoch": 0.6178465141240181,
|
| 11088 |
+
"grad_norm": 0.21560071408748627,
|
| 11089 |
+
"learning_rate": 0.00033197831978319783,
|
| 11090 |
+
"loss": 2.618187427520752,
|
| 11091 |
+
"step": 3166
|
| 11092 |
+
},
|
| 11093 |
+
{
|
| 11094 |
+
"epoch": 0.6182368151436796,
|
| 11095 |
+
"grad_norm": 0.19656604528427124,
|
| 11096 |
+
"learning_rate": 0.00033163956639566393,
|
| 11097 |
+
"loss": 2.5828745365142822,
|
| 11098 |
+
"step": 3168
|
| 11099 |
+
},
|
| 11100 |
+
{
|
| 11101 |
+
"epoch": 0.618627116163341,
|
| 11102 |
+
"grad_norm": 0.19478477537631989,
|
| 11103 |
+
"learning_rate": 0.0003313008130081301,
|
| 11104 |
+
"loss": 2.5761055946350098,
|
| 11105 |
+
"step": 3170
|
| 11106 |
+
},
|
| 11107 |
+
{
|
| 11108 |
+
"epoch": 0.6190174171830024,
|
| 11109 |
+
"grad_norm": 0.13769787549972534,
|
| 11110 |
+
"learning_rate": 0.00033096205962059624,
|
| 11111 |
+
"loss": 2.5826897621154785,
|
| 11112 |
+
"step": 3172
|
| 11113 |
+
},
|
| 11114 |
+
{
|
| 11115 |
+
"epoch": 0.6194077182026638,
|
| 11116 |
+
"grad_norm": 0.18416687846183777,
|
| 11117 |
+
"learning_rate": 0.00033062330623306234,
|
| 11118 |
+
"loss": 2.580380916595459,
|
| 11119 |
+
"step": 3174
|
| 11120 |
+
},
|
| 11121 |
+
{
|
| 11122 |
+
"epoch": 0.6197980192223252,
|
| 11123 |
+
"grad_norm": 0.17751635611057281,
|
| 11124 |
+
"learning_rate": 0.00033028455284552844,
|
| 11125 |
+
"loss": 2.5757479667663574,
|
| 11126 |
+
"step": 3176
|
| 11127 |
+
},
|
| 11128 |
+
{
|
| 11129 |
+
"epoch": 0.6201883202419867,
|
| 11130 |
+
"grad_norm": 0.17219354212284088,
|
| 11131 |
+
"learning_rate": 0.0003299457994579946,
|
| 11132 |
+
"loss": 2.6023800373077393,
|
| 11133 |
+
"step": 3178
|
| 11134 |
+
},
|
| 11135 |
+
{
|
| 11136 |
+
"epoch": 0.6205786212616481,
|
| 11137 |
+
"grad_norm": 0.16872039437294006,
|
| 11138 |
+
"learning_rate": 0.0003296070460704607,
|
| 11139 |
+
"loss": 2.572619915008545,
|
| 11140 |
+
"step": 3180
|
| 11141 |
+
},
|
| 11142 |
+
{
|
| 11143 |
+
"epoch": 0.6209689222813095,
|
| 11144 |
+
"grad_norm": 0.25031930208206177,
|
| 11145 |
+
"learning_rate": 0.00032926829268292685,
|
| 11146 |
+
"loss": 2.6050851345062256,
|
| 11147 |
+
"step": 3182
|
| 11148 |
+
},
|
| 11149 |
+
{
|
| 11150 |
+
"epoch": 0.6213592233009708,
|
| 11151 |
+
"grad_norm": 0.22023609280586243,
|
| 11152 |
+
"learning_rate": 0.000328929539295393,
|
| 11153 |
+
"loss": 2.588379144668579,
|
| 11154 |
+
"step": 3184
|
| 11155 |
+
},
|
| 11156 |
+
{
|
| 11157 |
+
"epoch": 0.6217495243206322,
|
| 11158 |
+
"grad_norm": 0.16208498179912567,
|
| 11159 |
+
"learning_rate": 0.00032859078590785905,
|
| 11160 |
+
"loss": 2.5313475131988525,
|
| 11161 |
+
"step": 3186
|
| 11162 |
+
},
|
| 11163 |
+
{
|
| 11164 |
+
"epoch": 0.6221398253402937,
|
| 11165 |
+
"grad_norm": 0.14155396819114685,
|
| 11166 |
+
"learning_rate": 0.0003282520325203252,
|
| 11167 |
+
"loss": 2.5960001945495605,
|
| 11168 |
+
"step": 3188
|
| 11169 |
+
},
|
| 11170 |
+
{
|
| 11171 |
+
"epoch": 0.6225301263599551,
|
| 11172 |
+
"grad_norm": 0.2234107404947281,
|
| 11173 |
+
"learning_rate": 0.00032791327913279136,
|
| 11174 |
+
"loss": 2.588466167449951,
|
| 11175 |
+
"step": 3190
|
| 11176 |
+
},
|
| 11177 |
+
{
|
| 11178 |
+
"epoch": 0.6229204273796165,
|
| 11179 |
+
"grad_norm": 0.18295086920261383,
|
| 11180 |
+
"learning_rate": 0.00032757452574525746,
|
| 11181 |
+
"loss": 2.5738139152526855,
|
| 11182 |
+
"step": 3192
|
| 11183 |
+
},
|
| 11184 |
+
{
|
| 11185 |
+
"epoch": 0.6233107283992779,
|
| 11186 |
+
"grad_norm": 0.16664358973503113,
|
| 11187 |
+
"learning_rate": 0.00032723577235772356,
|
| 11188 |
+
"loss": 2.529301881790161,
|
| 11189 |
+
"step": 3194
|
| 11190 |
+
},
|
| 11191 |
+
{
|
| 11192 |
+
"epoch": 0.6237010294189393,
|
| 11193 |
+
"grad_norm": 0.20305675268173218,
|
| 11194 |
+
"learning_rate": 0.0003268970189701897,
|
| 11195 |
+
"loss": 2.598602294921875,
|
| 11196 |
+
"step": 3196
|
| 11197 |
+
},
|
| 11198 |
+
{
|
| 11199 |
+
"epoch": 0.6240913304386008,
|
| 11200 |
+
"grad_norm": 0.1321771740913391,
|
| 11201 |
+
"learning_rate": 0.0003265582655826558,
|
| 11202 |
+
"loss": 2.5528440475463867,
|
| 11203 |
+
"step": 3198
|
| 11204 |
+
},
|
| 11205 |
+
{
|
| 11206 |
+
"epoch": 0.6244816314582622,
|
| 11207 |
+
"grad_norm": 0.1623746156692505,
|
| 11208 |
+
"learning_rate": 0.00032621951219512197,
|
| 11209 |
+
"loss": 2.514591693878174,
|
| 11210 |
+
"step": 3200
|
| 11211 |
+
},
|
| 11212 |
+
{
|
| 11213 |
+
"epoch": 0.6248719324779236,
|
| 11214 |
+
"grad_norm": 0.17168059945106506,
|
| 11215 |
+
"learning_rate": 0.0003258807588075881,
|
| 11216 |
+
"loss": 2.593696355819702,
|
| 11217 |
+
"step": 3202
|
| 11218 |
+
},
|
| 11219 |
+
{
|
| 11220 |
+
"epoch": 0.625262233497585,
|
| 11221 |
+
"grad_norm": 0.20644061267375946,
|
| 11222 |
+
"learning_rate": 0.00032554200542005417,
|
| 11223 |
+
"loss": 2.578599691390991,
|
| 11224 |
+
"step": 3204
|
| 11225 |
+
},
|
| 11226 |
+
{
|
| 11227 |
+
"epoch": 0.6256525345172465,
|
| 11228 |
+
"grad_norm": 0.15321967005729675,
|
| 11229 |
+
"learning_rate": 0.0003252032520325203,
|
| 11230 |
+
"loss": 2.550872802734375,
|
| 11231 |
+
"step": 3206
|
| 11232 |
+
},
|
| 11233 |
+
{
|
| 11234 |
+
"epoch": 0.6260428355369079,
|
| 11235 |
+
"grad_norm": 0.1741722971200943,
|
| 11236 |
+
"learning_rate": 0.0003248644986449865,
|
| 11237 |
+
"loss": 2.557905673980713,
|
| 11238 |
+
"step": 3208
|
| 11239 |
+
},
|
| 11240 |
+
{
|
| 11241 |
+
"epoch": 0.6264331365565693,
|
| 11242 |
+
"grad_norm": 0.16127611696720123,
|
| 11243 |
+
"learning_rate": 0.0003245257452574526,
|
| 11244 |
+
"loss": 2.543262481689453,
|
| 11245 |
+
"step": 3210
|
| 11246 |
+
},
|
| 11247 |
+
{
|
| 11248 |
+
"epoch": 0.6268234375762307,
|
| 11249 |
+
"grad_norm": 0.17874029278755188,
|
| 11250 |
+
"learning_rate": 0.0003241869918699187,
|
| 11251 |
+
"loss": 2.5955605506896973,
|
| 11252 |
+
"step": 3212
|
| 11253 |
+
},
|
| 11254 |
+
{
|
| 11255 |
+
"epoch": 0.6272137385958921,
|
| 11256 |
+
"grad_norm": 0.17842744290828705,
|
| 11257 |
+
"learning_rate": 0.00032384823848238483,
|
| 11258 |
+
"loss": 2.5460407733917236,
|
| 11259 |
+
"step": 3214
|
| 11260 |
+
},
|
| 11261 |
+
{
|
| 11262 |
+
"epoch": 0.6276040396155534,
|
| 11263 |
+
"grad_norm": 0.1493091583251953,
|
| 11264 |
+
"learning_rate": 0.00032350948509485093,
|
| 11265 |
+
"loss": 2.5567626953125,
|
| 11266 |
+
"step": 3216
|
| 11267 |
+
},
|
| 11268 |
+
{
|
| 11269 |
+
"epoch": 0.6279943406352149,
|
| 11270 |
+
"grad_norm": 0.1526266485452652,
|
| 11271 |
+
"learning_rate": 0.0003231707317073171,
|
| 11272 |
+
"loss": 2.5675597190856934,
|
| 11273 |
+
"step": 3218
|
| 11274 |
+
},
|
| 11275 |
+
{
|
| 11276 |
+
"epoch": 0.6283846416548763,
|
| 11277 |
+
"grad_norm": 0.20548127591609955,
|
| 11278 |
+
"learning_rate": 0.00032283197831978324,
|
| 11279 |
+
"loss": 2.615328788757324,
|
| 11280 |
+
"step": 3220
|
| 11281 |
+
},
|
| 11282 |
+
{
|
| 11283 |
+
"epoch": 0.6287749426745377,
|
| 11284 |
+
"grad_norm": 0.1378091722726822,
|
| 11285 |
+
"learning_rate": 0.0003224932249322493,
|
| 11286 |
+
"loss": 2.5659730434417725,
|
| 11287 |
+
"step": 3222
|
| 11288 |
+
},
|
| 11289 |
+
{
|
| 11290 |
+
"epoch": 0.6291652436941991,
|
| 11291 |
+
"grad_norm": 0.2421988695859909,
|
| 11292 |
+
"learning_rate": 0.00032215447154471544,
|
| 11293 |
+
"loss": 2.5777974128723145,
|
| 11294 |
+
"step": 3224
|
| 11295 |
+
},
|
| 11296 |
+
{
|
| 11297 |
+
"epoch": 0.6295555447138605,
|
| 11298 |
+
"grad_norm": 0.17923657596111298,
|
| 11299 |
+
"learning_rate": 0.0003218157181571816,
|
| 11300 |
+
"loss": 2.5326948165893555,
|
| 11301 |
+
"step": 3226
|
| 11302 |
+
},
|
| 11303 |
+
{
|
| 11304 |
+
"epoch": 0.629945845733522,
|
| 11305 |
+
"grad_norm": 0.1884506493806839,
|
| 11306 |
+
"learning_rate": 0.0003214769647696477,
|
| 11307 |
+
"loss": 2.539327383041382,
|
| 11308 |
+
"step": 3228
|
| 11309 |
+
},
|
| 11310 |
+
{
|
| 11311 |
+
"epoch": 0.6303361467531834,
|
| 11312 |
+
"grad_norm": 0.18489061295986176,
|
| 11313 |
+
"learning_rate": 0.00032113821138211385,
|
| 11314 |
+
"loss": 2.5282340049743652,
|
| 11315 |
+
"step": 3230
|
| 11316 |
+
},
|
| 11317 |
+
{
|
| 11318 |
+
"epoch": 0.6307264477728448,
|
| 11319 |
+
"grad_norm": 0.23725561797618866,
|
| 11320 |
+
"learning_rate": 0.00032079945799457995,
|
| 11321 |
+
"loss": 2.5809316635131836,
|
| 11322 |
+
"step": 3232
|
| 11323 |
+
},
|
| 11324 |
+
{
|
| 11325 |
+
"epoch": 0.6311167487925062,
|
| 11326 |
+
"grad_norm": 0.21135766804218292,
|
| 11327 |
+
"learning_rate": 0.00032046070460704605,
|
| 11328 |
+
"loss": 2.50193452835083,
|
| 11329 |
+
"step": 3234
|
| 11330 |
+
},
|
| 11331 |
+
{
|
| 11332 |
+
"epoch": 0.6315070498121677,
|
| 11333 |
+
"grad_norm": 0.1736292690038681,
|
| 11334 |
+
"learning_rate": 0.0003201219512195122,
|
| 11335 |
+
"loss": 2.55315899848938,
|
| 11336 |
+
"step": 3236
|
| 11337 |
+
},
|
| 11338 |
+
{
|
| 11339 |
+
"epoch": 0.6318973508318291,
|
| 11340 |
+
"grad_norm": 0.18709367513656616,
|
| 11341 |
+
"learning_rate": 0.00031978319783197836,
|
| 11342 |
+
"loss": 2.5531299114227295,
|
| 11343 |
+
"step": 3238
|
| 11344 |
+
},
|
| 11345 |
+
{
|
| 11346 |
+
"epoch": 0.6322876518514905,
|
| 11347 |
+
"grad_norm": 0.17563560605049133,
|
| 11348 |
+
"learning_rate": 0.0003194444444444444,
|
| 11349 |
+
"loss": 2.532874584197998,
|
| 11350 |
+
"step": 3240
|
| 11351 |
+
},
|
| 11352 |
+
{
|
| 11353 |
+
"epoch": 0.6326779528711519,
|
| 11354 |
+
"grad_norm": 0.17579172551631927,
|
| 11355 |
+
"learning_rate": 0.00031910569105691056,
|
| 11356 |
+
"loss": 2.556750774383545,
|
| 11357 |
+
"step": 3242
|
| 11358 |
+
},
|
| 11359 |
+
{
|
| 11360 |
+
"epoch": 0.6330682538908133,
|
| 11361 |
+
"grad_norm": 0.15847933292388916,
|
| 11362 |
+
"learning_rate": 0.0003187669376693767,
|
| 11363 |
+
"loss": 2.65089750289917,
|
| 11364 |
+
"step": 3244
|
| 11365 |
+
},
|
| 11366 |
+
{
|
| 11367 |
+
"epoch": 0.6334585549104748,
|
| 11368 |
+
"grad_norm": 0.1559586077928543,
|
| 11369 |
+
"learning_rate": 0.0003184281842818428,
|
| 11370 |
+
"loss": 2.5496010780334473,
|
| 11371 |
+
"step": 3246
|
| 11372 |
+
},
|
| 11373 |
+
{
|
| 11374 |
+
"epoch": 0.6338488559301361,
|
| 11375 |
+
"grad_norm": 0.1703522801399231,
|
| 11376 |
+
"learning_rate": 0.00031808943089430897,
|
| 11377 |
+
"loss": 2.596816062927246,
|
| 11378 |
+
"step": 3248
|
| 11379 |
+
},
|
| 11380 |
+
{
|
| 11381 |
+
"epoch": 0.6342391569497975,
|
| 11382 |
+
"grad_norm": 0.1784750372171402,
|
| 11383 |
+
"learning_rate": 0.0003177506775067751,
|
| 11384 |
+
"loss": 2.561603546142578,
|
| 11385 |
+
"step": 3250
|
| 11386 |
+
},
|
| 11387 |
+
{
|
| 11388 |
+
"epoch": 0.6346294579694589,
|
| 11389 |
+
"grad_norm": 0.18561677634716034,
|
| 11390 |
+
"learning_rate": 0.0003174119241192412,
|
| 11391 |
+
"loss": 2.5508017539978027,
|
| 11392 |
+
"step": 3252
|
| 11393 |
+
},
|
| 11394 |
+
{
|
| 11395 |
+
"epoch": 0.6350197589891203,
|
| 11396 |
+
"grad_norm": 0.1744123101234436,
|
| 11397 |
+
"learning_rate": 0.00031707317073170733,
|
| 11398 |
+
"loss": 2.5839414596557617,
|
| 11399 |
+
"step": 3254
|
| 11400 |
+
},
|
| 11401 |
+
{
|
| 11402 |
+
"epoch": 0.6354100600087818,
|
| 11403 |
+
"grad_norm": 0.22406071424484253,
|
| 11404 |
+
"learning_rate": 0.0003167344173441735,
|
| 11405 |
+
"loss": 2.5495362281799316,
|
| 11406 |
+
"step": 3256
|
| 11407 |
+
},
|
| 11408 |
+
{
|
| 11409 |
+
"epoch": 0.6358003610284432,
|
| 11410 |
+
"grad_norm": 0.20249062776565552,
|
| 11411 |
+
"learning_rate": 0.00031639566395663953,
|
| 11412 |
+
"loss": 2.564523696899414,
|
| 11413 |
+
"step": 3258
|
| 11414 |
+
},
|
| 11415 |
+
{
|
| 11416 |
+
"epoch": 0.6361906620481046,
|
| 11417 |
+
"grad_norm": 0.19617381691932678,
|
| 11418 |
+
"learning_rate": 0.0003160569105691057,
|
| 11419 |
+
"loss": 2.6154041290283203,
|
| 11420 |
+
"step": 3260
|
| 11421 |
+
},
|
| 11422 |
+
{
|
| 11423 |
+
"epoch": 0.636580963067766,
|
| 11424 |
+
"grad_norm": 0.21104449033737183,
|
| 11425 |
+
"learning_rate": 0.00031571815718157184,
|
| 11426 |
+
"loss": 2.562690258026123,
|
| 11427 |
+
"step": 3262
|
| 11428 |
+
},
|
| 11429 |
+
{
|
| 11430 |
+
"epoch": 0.6369712640874274,
|
| 11431 |
+
"grad_norm": 0.1960573047399521,
|
| 11432 |
+
"learning_rate": 0.00031537940379403794,
|
| 11433 |
+
"loss": 2.5735602378845215,
|
| 11434 |
+
"step": 3264
|
| 11435 |
+
},
|
| 11436 |
+
{
|
| 11437 |
+
"epoch": 0.6373615651070889,
|
| 11438 |
+
"grad_norm": 0.18240493535995483,
|
| 11439 |
+
"learning_rate": 0.0003150406504065041,
|
| 11440 |
+
"loss": 2.5724992752075195,
|
| 11441 |
+
"step": 3266
|
| 11442 |
+
},
|
| 11443 |
+
{
|
| 11444 |
+
"epoch": 0.6377518661267503,
|
| 11445 |
+
"grad_norm": 0.171915665268898,
|
| 11446 |
+
"learning_rate": 0.0003147018970189702,
|
| 11447 |
+
"loss": 2.645590305328369,
|
| 11448 |
+
"step": 3268
|
| 11449 |
+
},
|
| 11450 |
+
{
|
| 11451 |
+
"epoch": 0.6381421671464117,
|
| 11452 |
+
"grad_norm": 0.2008330374956131,
|
| 11453 |
+
"learning_rate": 0.0003143631436314363,
|
| 11454 |
+
"loss": 2.5113089084625244,
|
| 11455 |
+
"step": 3270
|
| 11456 |
+
},
|
| 11457 |
+
{
|
| 11458 |
+
"epoch": 0.6385324681660731,
|
| 11459 |
+
"grad_norm": 0.1494937539100647,
|
| 11460 |
+
"learning_rate": 0.00031402439024390245,
|
| 11461 |
+
"loss": 2.5380754470825195,
|
| 11462 |
+
"step": 3272
|
| 11463 |
+
},
|
| 11464 |
+
{
|
| 11465 |
+
"epoch": 0.6389227691857345,
|
| 11466 |
+
"grad_norm": 0.20456747710704803,
|
| 11467 |
+
"learning_rate": 0.0003136856368563686,
|
| 11468 |
+
"loss": 2.5229926109313965,
|
| 11469 |
+
"step": 3274
|
| 11470 |
+
},
|
| 11471 |
+
{
|
| 11472 |
+
"epoch": 0.639313070205396,
|
| 11473 |
+
"grad_norm": 0.23638974130153656,
|
| 11474 |
+
"learning_rate": 0.0003133468834688347,
|
| 11475 |
+
"loss": 2.60117244720459,
|
| 11476 |
+
"step": 3276
|
| 11477 |
+
},
|
| 11478 |
+
{
|
| 11479 |
+
"epoch": 0.6397033712250573,
|
| 11480 |
+
"grad_norm": 0.16723428666591644,
|
| 11481 |
+
"learning_rate": 0.0003130081300813008,
|
| 11482 |
+
"loss": 2.5629093647003174,
|
| 11483 |
+
"step": 3278
|
| 11484 |
+
},
|
| 11485 |
+
{
|
| 11486 |
+
"epoch": 0.6400936722447187,
|
| 11487 |
+
"grad_norm": 0.19515161216259003,
|
| 11488 |
+
"learning_rate": 0.00031266937669376696,
|
| 11489 |
+
"loss": 2.6098110675811768,
|
| 11490 |
+
"step": 3280
|
| 11491 |
+
},
|
| 11492 |
+
{
|
| 11493 |
+
"epoch": 0.6404839732643801,
|
| 11494 |
+
"grad_norm": 0.2598382234573364,
|
| 11495 |
+
"learning_rate": 0.00031233062330623306,
|
| 11496 |
+
"loss": 2.5652332305908203,
|
| 11497 |
+
"step": 3282
|
| 11498 |
+
},
|
| 11499 |
+
{
|
| 11500 |
+
"epoch": 0.6408742742840415,
|
| 11501 |
+
"grad_norm": 0.18787533044815063,
|
| 11502 |
+
"learning_rate": 0.0003119918699186992,
|
| 11503 |
+
"loss": 2.578974723815918,
|
| 11504 |
+
"step": 3284
|
| 11505 |
+
},
|
| 11506 |
+
{
|
| 11507 |
+
"epoch": 0.641264575303703,
|
| 11508 |
+
"grad_norm": 0.15718777477741241,
|
| 11509 |
+
"learning_rate": 0.0003116531165311653,
|
| 11510 |
+
"loss": 2.5503551959991455,
|
| 11511 |
+
"step": 3286
|
| 11512 |
+
},
|
| 11513 |
+
{
|
| 11514 |
+
"epoch": 0.6416548763233644,
|
| 11515 |
+
"grad_norm": 0.15008695423603058,
|
| 11516 |
+
"learning_rate": 0.0003113143631436314,
|
| 11517 |
+
"loss": 2.579472064971924,
|
| 11518 |
+
"step": 3288
|
| 11519 |
+
},
|
| 11520 |
+
{
|
| 11521 |
+
"epoch": 0.6420451773430258,
|
| 11522 |
+
"grad_norm": 0.20172616839408875,
|
| 11523 |
+
"learning_rate": 0.00031097560975609757,
|
| 11524 |
+
"loss": 2.624621868133545,
|
| 11525 |
+
"step": 3290
|
| 11526 |
+
},
|
| 11527 |
+
{
|
| 11528 |
+
"epoch": 0.6424354783626872,
|
| 11529 |
+
"grad_norm": 0.19558916985988617,
|
| 11530 |
+
"learning_rate": 0.0003106368563685637,
|
| 11531 |
+
"loss": 2.5701732635498047,
|
| 11532 |
+
"step": 3292
|
| 11533 |
+
},
|
| 11534 |
+
{
|
| 11535 |
+
"epoch": 0.6428257793823486,
|
| 11536 |
+
"grad_norm": 0.14155083894729614,
|
| 11537 |
+
"learning_rate": 0.0003102981029810298,
|
| 11538 |
+
"loss": 2.51293683052063,
|
| 11539 |
+
"step": 3294
|
| 11540 |
+
},
|
| 11541 |
+
{
|
| 11542 |
+
"epoch": 0.6432160804020101,
|
| 11543 |
+
"grad_norm": 0.18246978521347046,
|
| 11544 |
+
"learning_rate": 0.0003099593495934959,
|
| 11545 |
+
"loss": 2.545320510864258,
|
| 11546 |
+
"step": 3296
|
| 11547 |
+
},
|
| 11548 |
+
{
|
| 11549 |
+
"epoch": 0.6436063814216715,
|
| 11550 |
+
"grad_norm": 0.2666906416416168,
|
| 11551 |
+
"learning_rate": 0.0003096205962059621,
|
| 11552 |
+
"loss": 2.5903568267822266,
|
| 11553 |
+
"step": 3298
|
| 11554 |
+
},
|
| 11555 |
+
{
|
| 11556 |
+
"epoch": 0.6439966824413329,
|
| 11557 |
+
"grad_norm": 0.20151375234127045,
|
| 11558 |
+
"learning_rate": 0.0003092818428184282,
|
| 11559 |
+
"loss": 2.6119165420532227,
|
| 11560 |
+
"step": 3300
|
| 11561 |
+
},
|
| 11562 |
+
{
|
| 11563 |
+
"epoch": 0.6443869834609943,
|
| 11564 |
+
"grad_norm": 0.19565391540527344,
|
| 11565 |
+
"learning_rate": 0.00030894308943089433,
|
| 11566 |
+
"loss": 2.552276372909546,
|
| 11567 |
+
"step": 3302
|
| 11568 |
+
},
|
| 11569 |
+
{
|
| 11570 |
+
"epoch": 0.6447772844806557,
|
| 11571 |
+
"grad_norm": 0.19761236011981964,
|
| 11572 |
+
"learning_rate": 0.0003086043360433605,
|
| 11573 |
+
"loss": 2.62076997756958,
|
| 11574 |
+
"step": 3304
|
| 11575 |
+
},
|
| 11576 |
+
{
|
| 11577 |
+
"epoch": 0.6451675855003172,
|
| 11578 |
+
"grad_norm": 0.18781393766403198,
|
| 11579 |
+
"learning_rate": 0.00030826558265582653,
|
| 11580 |
+
"loss": 2.5616402626037598,
|
| 11581 |
+
"step": 3306
|
| 11582 |
+
},
|
| 11583 |
+
{
|
| 11584 |
+
"epoch": 0.6455578865199786,
|
| 11585 |
+
"grad_norm": 0.16508027911186218,
|
| 11586 |
+
"learning_rate": 0.0003079268292682927,
|
| 11587 |
+
"loss": 2.5571203231811523,
|
| 11588 |
+
"step": 3308
|
| 11589 |
+
},
|
| 11590 |
+
{
|
| 11591 |
+
"epoch": 0.6459481875396399,
|
| 11592 |
+
"grad_norm": 0.1606653332710266,
|
| 11593 |
+
"learning_rate": 0.00030758807588075884,
|
| 11594 |
+
"loss": 2.597504138946533,
|
| 11595 |
+
"step": 3310
|
| 11596 |
+
},
|
| 11597 |
+
{
|
| 11598 |
+
"epoch": 0.6463384885593013,
|
| 11599 |
+
"grad_norm": 0.16009922325611115,
|
| 11600 |
+
"learning_rate": 0.00030724932249322494,
|
| 11601 |
+
"loss": 2.539309501647949,
|
| 11602 |
+
"step": 3312
|
| 11603 |
+
},
|
| 11604 |
+
{
|
| 11605 |
+
"epoch": 0.6467287895789627,
|
| 11606 |
+
"grad_norm": 0.18152594566345215,
|
| 11607 |
+
"learning_rate": 0.00030691056910569104,
|
| 11608 |
+
"loss": 2.6190736293792725,
|
| 11609 |
+
"step": 3314
|
| 11610 |
+
},
|
| 11611 |
+
{
|
| 11612 |
+
"epoch": 0.6471190905986242,
|
| 11613 |
+
"grad_norm": 0.20449279248714447,
|
| 11614 |
+
"learning_rate": 0.0003065718157181572,
|
| 11615 |
+
"loss": 2.577378988265991,
|
| 11616 |
+
"step": 3316
|
| 11617 |
+
},
|
| 11618 |
+
{
|
| 11619 |
+
"epoch": 0.6475093916182856,
|
| 11620 |
+
"grad_norm": 0.16201697289943695,
|
| 11621 |
+
"learning_rate": 0.0003062330623306233,
|
| 11622 |
+
"loss": 2.578219413757324,
|
| 11623 |
+
"step": 3318
|
| 11624 |
+
},
|
| 11625 |
+
{
|
| 11626 |
+
"epoch": 0.647899692637947,
|
| 11627 |
+
"grad_norm": 0.18602602183818817,
|
| 11628 |
+
"learning_rate": 0.00030589430894308945,
|
| 11629 |
+
"loss": 2.5291714668273926,
|
| 11630 |
+
"step": 3320
|
| 11631 |
+
},
|
| 11632 |
+
{
|
| 11633 |
+
"epoch": 0.6482899936576084,
|
| 11634 |
+
"grad_norm": 0.12662144005298615,
|
| 11635 |
+
"learning_rate": 0.0003055555555555556,
|
| 11636 |
+
"loss": 2.5561885833740234,
|
| 11637 |
+
"step": 3322
|
| 11638 |
+
},
|
| 11639 |
+
{
|
| 11640 |
+
"epoch": 0.6486802946772698,
|
| 11641 |
+
"grad_norm": 0.3594665825366974,
|
| 11642 |
+
"learning_rate": 0.00030521680216802165,
|
| 11643 |
+
"loss": 2.4665207862854004,
|
| 11644 |
+
"step": 3324
|
| 11645 |
+
},
|
| 11646 |
+
{
|
| 11647 |
+
"epoch": 0.6490705956969313,
|
| 11648 |
+
"grad_norm": 0.1411990225315094,
|
| 11649 |
+
"learning_rate": 0.0003048780487804878,
|
| 11650 |
+
"loss": 2.6028122901916504,
|
| 11651 |
+
"step": 3326
|
| 11652 |
+
},
|
| 11653 |
+
{
|
| 11654 |
+
"epoch": 0.6494608967165927,
|
| 11655 |
+
"grad_norm": 0.18448013067245483,
|
| 11656 |
+
"learning_rate": 0.00030453929539295396,
|
| 11657 |
+
"loss": 2.635477304458618,
|
| 11658 |
+
"step": 3328
|
| 11659 |
+
},
|
| 11660 |
+
{
|
| 11661 |
+
"epoch": 0.6498511977362541,
|
| 11662 |
+
"grad_norm": 0.1785985678434372,
|
| 11663 |
+
"learning_rate": 0.00030420054200542006,
|
| 11664 |
+
"loss": 2.538879871368408,
|
| 11665 |
+
"step": 3330
|
| 11666 |
+
},
|
| 11667 |
+
{
|
| 11668 |
+
"epoch": 0.6502414987559155,
|
| 11669 |
+
"grad_norm": 0.22115904092788696,
|
| 11670 |
+
"learning_rate": 0.00030386178861788616,
|
| 11671 |
+
"loss": 2.554517984390259,
|
| 11672 |
+
"step": 3332
|
| 11673 |
+
},
|
| 11674 |
+
{
|
| 11675 |
+
"epoch": 0.650631799775577,
|
| 11676 |
+
"grad_norm": 0.17713497579097748,
|
| 11677 |
+
"learning_rate": 0.0003035230352303523,
|
| 11678 |
+
"loss": 2.597719192504883,
|
| 11679 |
+
"step": 3334
|
| 11680 |
+
},
|
| 11681 |
+
{
|
| 11682 |
+
"epoch": 0.6510221007952384,
|
| 11683 |
+
"grad_norm": 0.16334472596645355,
|
| 11684 |
+
"learning_rate": 0.0003031842818428184,
|
| 11685 |
+
"loss": 2.6452531814575195,
|
| 11686 |
+
"step": 3336
|
| 11687 |
+
},
|
| 11688 |
+
{
|
| 11689 |
+
"epoch": 0.6514124018148998,
|
| 11690 |
+
"grad_norm": 0.20037977397441864,
|
| 11691 |
+
"learning_rate": 0.00030284552845528457,
|
| 11692 |
+
"loss": 2.6009209156036377,
|
| 11693 |
+
"step": 3338
|
| 11694 |
+
},
|
| 11695 |
+
{
|
| 11696 |
+
"epoch": 0.6518027028345612,
|
| 11697 |
+
"grad_norm": 0.206337571144104,
|
| 11698 |
+
"learning_rate": 0.0003025067750677507,
|
| 11699 |
+
"loss": 2.573038101196289,
|
| 11700 |
+
"step": 3340
|
| 11701 |
+
},
|
| 11702 |
+
{
|
| 11703 |
+
"epoch": 0.6521930038542225,
|
| 11704 |
+
"grad_norm": 0.14330193400382996,
|
| 11705 |
+
"learning_rate": 0.00030216802168021677,
|
| 11706 |
+
"loss": 2.5463953018188477,
|
| 11707 |
+
"step": 3342
|
| 11708 |
+
},
|
| 11709 |
+
{
|
| 11710 |
+
"epoch": 0.6525833048738839,
|
| 11711 |
+
"grad_norm": 0.19862887263298035,
|
| 11712 |
+
"learning_rate": 0.0003018292682926829,
|
| 11713 |
+
"loss": 2.617435932159424,
|
| 11714 |
+
"step": 3344
|
| 11715 |
+
},
|
| 11716 |
+
{
|
| 11717 |
+
"epoch": 0.6529736058935454,
|
| 11718 |
+
"grad_norm": 0.19782988727092743,
|
| 11719 |
+
"learning_rate": 0.0003014905149051491,
|
| 11720 |
+
"loss": 2.600987434387207,
|
| 11721 |
+
"step": 3346
|
| 11722 |
+
},
|
| 11723 |
+
{
|
| 11724 |
+
"epoch": 0.6533639069132068,
|
| 11725 |
+
"grad_norm": 0.15272484719753265,
|
| 11726 |
+
"learning_rate": 0.0003011517615176152,
|
| 11727 |
+
"loss": 2.6114158630371094,
|
| 11728 |
+
"step": 3348
|
| 11729 |
+
},
|
| 11730 |
+
{
|
| 11731 |
+
"epoch": 0.6537542079328682,
|
| 11732 |
+
"grad_norm": 0.1507917046546936,
|
| 11733 |
+
"learning_rate": 0.00030081300813008133,
|
| 11734 |
+
"loss": 2.6323466300964355,
|
| 11735 |
+
"step": 3350
|
| 11736 |
+
},
|
| 11737 |
+
{
|
| 11738 |
+
"epoch": 0.6541445089525296,
|
| 11739 |
+
"grad_norm": 0.1666819304227829,
|
| 11740 |
+
"learning_rate": 0.00030047425474254743,
|
| 11741 |
+
"loss": 2.5683703422546387,
|
| 11742 |
+
"step": 3352
|
| 11743 |
+
},
|
| 11744 |
+
{
|
| 11745 |
+
"epoch": 0.654534809972191,
|
| 11746 |
+
"grad_norm": 0.17175288498401642,
|
| 11747 |
+
"learning_rate": 0.00030013550135501353,
|
| 11748 |
+
"loss": 2.585705518722534,
|
| 11749 |
+
"step": 3354
|
| 11750 |
+
},
|
| 11751 |
+
{
|
| 11752 |
+
"epoch": 0.6549251109918525,
|
| 11753 |
+
"grad_norm": 0.20282787084579468,
|
| 11754 |
+
"learning_rate": 0.0002997967479674797,
|
| 11755 |
+
"loss": 2.6095528602600098,
|
| 11756 |
+
"step": 3356
|
| 11757 |
+
},
|
| 11758 |
+
{
|
| 11759 |
+
"epoch": 0.6553154120115139,
|
| 11760 |
+
"grad_norm": 0.15500469505786896,
|
| 11761 |
+
"learning_rate": 0.00029945799457994584,
|
| 11762 |
+
"loss": 2.5921764373779297,
|
| 11763 |
+
"step": 3358
|
| 11764 |
+
},
|
| 11765 |
+
{
|
| 11766 |
+
"epoch": 0.6557057130311753,
|
| 11767 |
+
"grad_norm": 0.18893395364284515,
|
| 11768 |
+
"learning_rate": 0.0002991192411924119,
|
| 11769 |
+
"loss": 2.585824966430664,
|
| 11770 |
+
"step": 3360
|
| 11771 |
+
},
|
| 11772 |
+
{
|
| 11773 |
+
"epoch": 0.6560960140508367,
|
| 11774 |
+
"grad_norm": 0.2073819935321808,
|
| 11775 |
+
"learning_rate": 0.00029878048780487804,
|
| 11776 |
+
"loss": 2.5739941596984863,
|
| 11777 |
+
"step": 3362
|
| 11778 |
+
},
|
| 11779 |
+
{
|
| 11780 |
+
"epoch": 0.6564863150704981,
|
| 11781 |
+
"grad_norm": 0.22668085992336273,
|
| 11782 |
+
"learning_rate": 0.0002984417344173442,
|
| 11783 |
+
"loss": 2.592435121536255,
|
| 11784 |
+
"step": 3364
|
| 11785 |
+
},
|
| 11786 |
+
{
|
| 11787 |
+
"epoch": 0.6568766160901596,
|
| 11788 |
+
"grad_norm": 0.20970658957958221,
|
| 11789 |
+
"learning_rate": 0.0002981029810298103,
|
| 11790 |
+
"loss": 2.5305070877075195,
|
| 11791 |
+
"step": 3366
|
| 11792 |
+
},
|
| 11793 |
+
{
|
| 11794 |
+
"epoch": 0.657266917109821,
|
| 11795 |
+
"grad_norm": 0.1877676099538803,
|
| 11796 |
+
"learning_rate": 0.00029776422764227645,
|
| 11797 |
+
"loss": 2.6138973236083984,
|
| 11798 |
+
"step": 3368
|
| 11799 |
+
},
|
| 11800 |
+
{
|
| 11801 |
+
"epoch": 0.6576572181294824,
|
| 11802 |
+
"grad_norm": 0.15409447252750397,
|
| 11803 |
+
"learning_rate": 0.00029742547425474255,
|
| 11804 |
+
"loss": 2.6427993774414062,
|
| 11805 |
+
"step": 3370
|
| 11806 |
+
},
|
| 11807 |
+
{
|
| 11808 |
+
"epoch": 0.6580475191491437,
|
| 11809 |
+
"grad_norm": 0.23056402802467346,
|
| 11810 |
+
"learning_rate": 0.00029708672086720865,
|
| 11811 |
+
"loss": 2.627070426940918,
|
| 11812 |
+
"step": 3372
|
| 11813 |
+
},
|
| 11814 |
+
{
|
| 11815 |
+
"epoch": 0.6584378201688051,
|
| 11816 |
+
"grad_norm": 0.17552685737609863,
|
| 11817 |
+
"learning_rate": 0.0002967479674796748,
|
| 11818 |
+
"loss": 2.5833306312561035,
|
| 11819 |
+
"step": 3374
|
| 11820 |
+
},
|
| 11821 |
+
{
|
| 11822 |
+
"epoch": 0.6588281211884666,
|
| 11823 |
+
"grad_norm": 0.17850284278392792,
|
| 11824 |
+
"learning_rate": 0.00029640921409214096,
|
| 11825 |
+
"loss": 2.580470561981201,
|
| 11826 |
+
"step": 3376
|
| 11827 |
+
},
|
| 11828 |
+
{
|
| 11829 |
+
"epoch": 0.659218422208128,
|
| 11830 |
+
"grad_norm": 0.17071230709552765,
|
| 11831 |
+
"learning_rate": 0.000296070460704607,
|
| 11832 |
+
"loss": 2.57330322265625,
|
| 11833 |
+
"step": 3378
|
| 11834 |
+
},
|
| 11835 |
+
{
|
| 11836 |
+
"epoch": 0.6596087232277894,
|
| 11837 |
+
"grad_norm": 0.18479770421981812,
|
| 11838 |
+
"learning_rate": 0.00029573170731707316,
|
| 11839 |
+
"loss": 2.5659661293029785,
|
| 11840 |
+
"step": 3380
|
| 11841 |
+
},
|
| 11842 |
+
{
|
| 11843 |
+
"epoch": 0.6599990242474508,
|
| 11844 |
+
"grad_norm": 0.2094133496284485,
|
| 11845 |
+
"learning_rate": 0.0002953929539295393,
|
| 11846 |
+
"loss": 2.560349464416504,
|
| 11847 |
+
"step": 3382
|
| 11848 |
+
},
|
| 11849 |
+
{
|
| 11850 |
+
"epoch": 0.6603893252671122,
|
| 11851 |
+
"grad_norm": 0.14916445314884186,
|
| 11852 |
+
"learning_rate": 0.0002950542005420054,
|
| 11853 |
+
"loss": 2.5665946006774902,
|
| 11854 |
+
"step": 3384
|
| 11855 |
+
},
|
| 11856 |
+
{
|
| 11857 |
+
"epoch": 0.6607796262867737,
|
| 11858 |
+
"grad_norm": 0.1509585976600647,
|
| 11859 |
+
"learning_rate": 0.00029471544715447157,
|
| 11860 |
+
"loss": 2.567208766937256,
|
| 11861 |
+
"step": 3386
|
| 11862 |
+
},
|
| 11863 |
+
{
|
| 11864 |
+
"epoch": 0.6611699273064351,
|
| 11865 |
+
"grad_norm": 0.18770365417003632,
|
| 11866 |
+
"learning_rate": 0.00029437669376693767,
|
| 11867 |
+
"loss": 2.626645565032959,
|
| 11868 |
+
"step": 3388
|
| 11869 |
+
},
|
| 11870 |
+
{
|
| 11871 |
+
"epoch": 0.6615602283260965,
|
| 11872 |
+
"grad_norm": 0.15767094492912292,
|
| 11873 |
+
"learning_rate": 0.00029403794037940377,
|
| 11874 |
+
"loss": 2.542384147644043,
|
| 11875 |
+
"step": 3390
|
| 11876 |
+
},
|
| 11877 |
+
{
|
| 11878 |
+
"epoch": 0.6619505293457579,
|
| 11879 |
+
"grad_norm": 0.20165543258190155,
|
| 11880 |
+
"learning_rate": 0.0002936991869918699,
|
| 11881 |
+
"loss": 2.6340911388397217,
|
| 11882 |
+
"step": 3392
|
| 11883 |
+
},
|
| 11884 |
+
{
|
| 11885 |
+
"epoch": 0.6623408303654194,
|
| 11886 |
+
"grad_norm": 0.15134866535663605,
|
| 11887 |
+
"learning_rate": 0.0002933604336043361,
|
| 11888 |
+
"loss": 2.539961814880371,
|
| 11889 |
+
"step": 3394
|
| 11890 |
+
},
|
| 11891 |
+
{
|
| 11892 |
+
"epoch": 0.6627311313850808,
|
| 11893 |
+
"grad_norm": 0.15308798849582672,
|
| 11894 |
+
"learning_rate": 0.0002930216802168022,
|
| 11895 |
+
"loss": 2.59468412399292,
|
| 11896 |
+
"step": 3396
|
| 11897 |
+
},
|
| 11898 |
+
{
|
| 11899 |
+
"epoch": 0.6631214324047422,
|
| 11900 |
+
"grad_norm": 0.18780267238616943,
|
| 11901 |
+
"learning_rate": 0.0002926829268292683,
|
| 11902 |
+
"loss": 2.5416975021362305,
|
| 11903 |
+
"step": 3398
|
| 11904 |
+
},
|
| 11905 |
+
{
|
| 11906 |
+
"epoch": 0.6635117334244036,
|
| 11907 |
+
"grad_norm": 0.1891191005706787,
|
| 11908 |
+
"learning_rate": 0.00029234417344173444,
|
| 11909 |
+
"loss": 2.5375816822052,
|
| 11910 |
+
"step": 3400
|
| 11911 |
+
},
|
| 11912 |
+
{
|
| 11913 |
+
"epoch": 0.663902034444065,
|
| 11914 |
+
"grad_norm": 0.16256257891654968,
|
| 11915 |
+
"learning_rate": 0.00029200542005420054,
|
| 11916 |
+
"loss": 2.5003700256347656,
|
| 11917 |
+
"step": 3402
|
| 11918 |
+
},
|
| 11919 |
+
{
|
| 11920 |
+
"epoch": 0.6642923354637263,
|
| 11921 |
+
"grad_norm": 0.18646782636642456,
|
| 11922 |
+
"learning_rate": 0.0002916666666666667,
|
| 11923 |
+
"loss": 2.629791498184204,
|
| 11924 |
+
"step": 3404
|
| 11925 |
+
},
|
| 11926 |
+
{
|
| 11927 |
+
"epoch": 0.6646826364833878,
|
| 11928 |
+
"grad_norm": 0.1507149040699005,
|
| 11929 |
+
"learning_rate": 0.0002913279132791328,
|
| 11930 |
+
"loss": 2.5971426963806152,
|
| 11931 |
+
"step": 3406
|
| 11932 |
+
},
|
| 11933 |
+
{
|
| 11934 |
+
"epoch": 0.6650729375030492,
|
| 11935 |
+
"grad_norm": 0.15289519727230072,
|
| 11936 |
+
"learning_rate": 0.0002909891598915989,
|
| 11937 |
+
"loss": 2.5353894233703613,
|
| 11938 |
+
"step": 3408
|
| 11939 |
+
},
|
| 11940 |
+
{
|
| 11941 |
+
"epoch": 0.6654632385227106,
|
| 11942 |
+
"grad_norm": 0.24489106237888336,
|
| 11943 |
+
"learning_rate": 0.00029065040650406505,
|
| 11944 |
+
"loss": 2.610733985900879,
|
| 11945 |
+
"step": 3410
|
| 11946 |
+
},
|
| 11947 |
+
{
|
| 11948 |
+
"epoch": 0.665853539542372,
|
| 11949 |
+
"grad_norm": 0.2502498924732208,
|
| 11950 |
+
"learning_rate": 0.0002903116531165312,
|
| 11951 |
+
"loss": 2.530853748321533,
|
| 11952 |
+
"step": 3412
|
| 11953 |
+
},
|
| 11954 |
+
{
|
| 11955 |
+
"epoch": 0.6662438405620335,
|
| 11956 |
+
"grad_norm": 0.19030004739761353,
|
| 11957 |
+
"learning_rate": 0.0002899728997289973,
|
| 11958 |
+
"loss": 2.5893993377685547,
|
| 11959 |
+
"step": 3414
|
| 11960 |
+
},
|
| 11961 |
+
{
|
| 11962 |
+
"epoch": 0.6666341415816949,
|
| 11963 |
+
"grad_norm": 0.17623953521251678,
|
| 11964 |
+
"learning_rate": 0.0002896341463414634,
|
| 11965 |
+
"loss": 2.610579490661621,
|
| 11966 |
+
"step": 3416
|
| 11967 |
+
},
|
| 11968 |
+
{
|
| 11969 |
+
"epoch": 0.6670244426013563,
|
| 11970 |
+
"grad_norm": 0.1587841808795929,
|
| 11971 |
+
"learning_rate": 0.00028929539295392956,
|
| 11972 |
+
"loss": 2.5943727493286133,
|
| 11973 |
+
"step": 3418
|
| 11974 |
+
},
|
| 11975 |
+
{
|
| 11976 |
+
"epoch": 0.6674147436210177,
|
| 11977 |
+
"grad_norm": 0.22349140048027039,
|
| 11978 |
+
"learning_rate": 0.00028895663956639566,
|
| 11979 |
+
"loss": 2.5818707942962646,
|
| 11980 |
+
"step": 3420
|
| 11981 |
+
},
|
| 11982 |
+
{
|
| 11983 |
+
"epoch": 0.6678050446406791,
|
| 11984 |
+
"grad_norm": 0.15634632110595703,
|
| 11985 |
+
"learning_rate": 0.0002886178861788618,
|
| 11986 |
+
"loss": 2.6007308959960938,
|
| 11987 |
+
"step": 3422
|
| 11988 |
+
},
|
| 11989 |
+
{
|
| 11990 |
+
"epoch": 0.6681953456603406,
|
| 11991 |
+
"grad_norm": 0.1775817573070526,
|
| 11992 |
+
"learning_rate": 0.0002882791327913279,
|
| 11993 |
+
"loss": 2.57694149017334,
|
| 11994 |
+
"step": 3424
|
| 11995 |
+
},
|
| 11996 |
+
{
|
| 11997 |
+
"epoch": 0.668585646680002,
|
| 11998 |
+
"grad_norm": 0.2009635865688324,
|
| 11999 |
+
"learning_rate": 0.000287940379403794,
|
| 12000 |
+
"loss": 2.5320677757263184,
|
| 12001 |
+
"step": 3426
|
| 12002 |
+
},
|
| 12003 |
+
{
|
| 12004 |
+
"epoch": 0.6689759476996634,
|
| 12005 |
+
"grad_norm": 0.1973264366388321,
|
| 12006 |
+
"learning_rate": 0.00028760162601626017,
|
| 12007 |
+
"loss": 2.5947256088256836,
|
| 12008 |
+
"step": 3428
|
| 12009 |
+
},
|
| 12010 |
+
{
|
| 12011 |
+
"epoch": 0.6693662487193248,
|
| 12012 |
+
"grad_norm": 0.1733711212873459,
|
| 12013 |
+
"learning_rate": 0.0002872628726287263,
|
| 12014 |
+
"loss": 2.612518310546875,
|
| 12015 |
+
"step": 3430
|
| 12016 |
+
},
|
| 12017 |
+
{
|
| 12018 |
+
"epoch": 0.6697565497389862,
|
| 12019 |
+
"grad_norm": 0.19108594954013824,
|
| 12020 |
+
"learning_rate": 0.0002869241192411924,
|
| 12021 |
+
"loss": 2.578172206878662,
|
| 12022 |
+
"step": 3432
|
| 12023 |
+
},
|
| 12024 |
+
{
|
| 12025 |
+
"epoch": 0.6701468507586477,
|
| 12026 |
+
"grad_norm": 0.19159026443958282,
|
| 12027 |
+
"learning_rate": 0.0002865853658536585,
|
| 12028 |
+
"loss": 2.529397487640381,
|
| 12029 |
+
"step": 3434
|
| 12030 |
+
},
|
| 12031 |
+
{
|
| 12032 |
+
"epoch": 0.670537151778309,
|
| 12033 |
+
"grad_norm": 0.15564581751823425,
|
| 12034 |
+
"learning_rate": 0.0002862466124661247,
|
| 12035 |
+
"loss": 2.6153948307037354,
|
| 12036 |
+
"step": 3436
|
| 12037 |
+
},
|
| 12038 |
+
{
|
| 12039 |
+
"epoch": 0.6709274527979704,
|
| 12040 |
+
"grad_norm": 0.16137953102588654,
|
| 12041 |
+
"learning_rate": 0.0002859078590785908,
|
| 12042 |
+
"loss": 2.5480706691741943,
|
| 12043 |
+
"step": 3438
|
| 12044 |
+
},
|
| 12045 |
+
{
|
| 12046 |
+
"epoch": 0.6713177538176318,
|
| 12047 |
+
"grad_norm": 0.19075652956962585,
|
| 12048 |
+
"learning_rate": 0.00028556910569105693,
|
| 12049 |
+
"loss": 2.611780881881714,
|
| 12050 |
+
"step": 3440
|
| 12051 |
+
},
|
| 12052 |
+
{
|
| 12053 |
+
"epoch": 0.6717080548372932,
|
| 12054 |
+
"grad_norm": 0.16507147252559662,
|
| 12055 |
+
"learning_rate": 0.0002852303523035231,
|
| 12056 |
+
"loss": 2.596035957336426,
|
| 12057 |
+
"step": 3442
|
| 12058 |
+
},
|
| 12059 |
+
{
|
| 12060 |
+
"epoch": 0.6720983558569547,
|
| 12061 |
+
"grad_norm": 0.17876233160495758,
|
| 12062 |
+
"learning_rate": 0.00028489159891598913,
|
| 12063 |
+
"loss": 2.5516724586486816,
|
| 12064 |
+
"step": 3444
|
| 12065 |
+
},
|
| 12066 |
+
{
|
| 12067 |
+
"epoch": 0.6724886568766161,
|
| 12068 |
+
"grad_norm": 0.15160194039344788,
|
| 12069 |
+
"learning_rate": 0.0002845528455284553,
|
| 12070 |
+
"loss": 2.5486698150634766,
|
| 12071 |
+
"step": 3446
|
| 12072 |
+
},
|
| 12073 |
+
{
|
| 12074 |
+
"epoch": 0.6728789578962775,
|
| 12075 |
+
"grad_norm": 0.18754079937934875,
|
| 12076 |
+
"learning_rate": 0.00028421409214092144,
|
| 12077 |
+
"loss": 2.580216407775879,
|
| 12078 |
+
"step": 3448
|
| 12079 |
+
},
|
| 12080 |
+
{
|
| 12081 |
+
"epoch": 0.6732692589159389,
|
| 12082 |
+
"grad_norm": 0.16114398837089539,
|
| 12083 |
+
"learning_rate": 0.00028387533875338754,
|
| 12084 |
+
"loss": 2.599320650100708,
|
| 12085 |
+
"step": 3450
|
| 12086 |
+
},
|
| 12087 |
+
{
|
| 12088 |
+
"epoch": 0.6736595599356003,
|
| 12089 |
+
"grad_norm": 0.19510778784751892,
|
| 12090 |
+
"learning_rate": 0.00028353658536585364,
|
| 12091 |
+
"loss": 2.601520538330078,
|
| 12092 |
+
"step": 3452
|
| 12093 |
+
},
|
| 12094 |
+
{
|
| 12095 |
+
"epoch": 0.6740498609552618,
|
| 12096 |
+
"grad_norm": 0.17651501297950745,
|
| 12097 |
+
"learning_rate": 0.0002831978319783198,
|
| 12098 |
+
"loss": 2.540130138397217,
|
| 12099 |
+
"step": 3454
|
| 12100 |
+
},
|
| 12101 |
+
{
|
| 12102 |
+
"epoch": 0.6744401619749232,
|
| 12103 |
+
"grad_norm": 0.23948103189468384,
|
| 12104 |
+
"learning_rate": 0.0002828590785907859,
|
| 12105 |
+
"loss": 2.5560247898101807,
|
| 12106 |
+
"step": 3456
|
| 12107 |
+
},
|
| 12108 |
+
{
|
| 12109 |
+
"epoch": 0.6748304629945846,
|
| 12110 |
+
"grad_norm": 0.16064074635505676,
|
| 12111 |
+
"learning_rate": 0.00028252032520325205,
|
| 12112 |
+
"loss": 2.624868631362915,
|
| 12113 |
+
"step": 3458
|
| 12114 |
+
},
|
| 12115 |
+
{
|
| 12116 |
+
"epoch": 0.675220764014246,
|
| 12117 |
+
"grad_norm": 0.1511070728302002,
|
| 12118 |
+
"learning_rate": 0.0002821815718157182,
|
| 12119 |
+
"loss": 2.6374998092651367,
|
| 12120 |
+
"step": 3460
|
| 12121 |
+
},
|
| 12122 |
+
{
|
| 12123 |
+
"epoch": 0.6756110650339074,
|
| 12124 |
+
"grad_norm": 0.18122602999210358,
|
| 12125 |
+
"learning_rate": 0.00028184281842818425,
|
| 12126 |
+
"loss": 2.503753900527954,
|
| 12127 |
+
"step": 3462
|
| 12128 |
+
},
|
| 12129 |
+
{
|
| 12130 |
+
"epoch": 0.6760013660535689,
|
| 12131 |
+
"grad_norm": 0.16176214814186096,
|
| 12132 |
+
"learning_rate": 0.0002815040650406504,
|
| 12133 |
+
"loss": 2.552935838699341,
|
| 12134 |
+
"step": 3464
|
| 12135 |
+
},
|
| 12136 |
+
{
|
| 12137 |
+
"epoch": 0.6763916670732302,
|
| 12138 |
+
"grad_norm": 0.14678943157196045,
|
| 12139 |
+
"learning_rate": 0.00028116531165311656,
|
| 12140 |
+
"loss": 2.5783491134643555,
|
| 12141 |
+
"step": 3466
|
| 12142 |
+
},
|
| 12143 |
+
{
|
| 12144 |
+
"epoch": 0.6767819680928916,
|
| 12145 |
+
"grad_norm": 0.14530348777770996,
|
| 12146 |
+
"learning_rate": 0.00028082655826558266,
|
| 12147 |
+
"loss": 2.5750467777252197,
|
| 12148 |
+
"step": 3468
|
| 12149 |
+
},
|
| 12150 |
+
{
|
| 12151 |
+
"epoch": 0.677172269112553,
|
| 12152 |
+
"grad_norm": 0.14161206781864166,
|
| 12153 |
+
"learning_rate": 0.0002804878048780488,
|
| 12154 |
+
"loss": 2.5305347442626953,
|
| 12155 |
+
"step": 3470
|
| 12156 |
+
},
|
| 12157 |
+
{
|
| 12158 |
+
"epoch": 0.6775625701322144,
|
| 12159 |
+
"grad_norm": 0.19915933907032013,
|
| 12160 |
+
"learning_rate": 0.0002801490514905149,
|
| 12161 |
+
"loss": 2.523327350616455,
|
| 12162 |
+
"step": 3472
|
| 12163 |
+
},
|
| 12164 |
+
{
|
| 12165 |
+
"epoch": 0.6779528711518759,
|
| 12166 |
+
"grad_norm": 0.16033072769641876,
|
| 12167 |
+
"learning_rate": 0.000279810298102981,
|
| 12168 |
+
"loss": 2.6067698001861572,
|
| 12169 |
+
"step": 3474
|
| 12170 |
+
},
|
| 12171 |
+
{
|
| 12172 |
+
"epoch": 0.6783431721715373,
|
| 12173 |
+
"grad_norm": 0.23114728927612305,
|
| 12174 |
+
"learning_rate": 0.00027947154471544717,
|
| 12175 |
+
"loss": 2.5749032497406006,
|
| 12176 |
+
"step": 3476
|
| 12177 |
+
},
|
| 12178 |
+
{
|
| 12179 |
+
"epoch": 0.6787334731911987,
|
| 12180 |
+
"grad_norm": 0.16545262932777405,
|
| 12181 |
+
"learning_rate": 0.0002791327913279133,
|
| 12182 |
+
"loss": 2.593946933746338,
|
| 12183 |
+
"step": 3478
|
| 12184 |
+
},
|
| 12185 |
+
{
|
| 12186 |
+
"epoch": 0.6791237742108601,
|
| 12187 |
+
"grad_norm": 0.1738792508840561,
|
| 12188 |
+
"learning_rate": 0.00027879403794037937,
|
| 12189 |
+
"loss": 2.554525375366211,
|
| 12190 |
+
"step": 3480
|
| 12191 |
+
},
|
| 12192 |
+
{
|
| 12193 |
+
"epoch": 0.6795140752305215,
|
| 12194 |
+
"grad_norm": 0.16824489831924438,
|
| 12195 |
+
"learning_rate": 0.0002784552845528455,
|
| 12196 |
+
"loss": 2.5360703468322754,
|
| 12197 |
+
"step": 3482
|
| 12198 |
+
},
|
| 12199 |
+
{
|
| 12200 |
+
"epoch": 0.679904376250183,
|
| 12201 |
+
"grad_norm": 0.14818450808525085,
|
| 12202 |
+
"learning_rate": 0.0002781165311653117,
|
| 12203 |
+
"loss": 2.57413387298584,
|
| 12204 |
+
"step": 3484
|
| 12205 |
+
},
|
| 12206 |
+
{
|
| 12207 |
+
"epoch": 0.6802946772698444,
|
| 12208 |
+
"grad_norm": 0.17091038823127747,
|
| 12209 |
+
"learning_rate": 0.0002777777777777778,
|
| 12210 |
+
"loss": 2.618990421295166,
|
| 12211 |
+
"step": 3486
|
| 12212 |
+
},
|
| 12213 |
+
{
|
| 12214 |
+
"epoch": 0.6806849782895058,
|
| 12215 |
+
"grad_norm": 0.1705619990825653,
|
| 12216 |
+
"learning_rate": 0.00027743902439024393,
|
| 12217 |
+
"loss": 2.5497422218322754,
|
| 12218 |
+
"step": 3488
|
| 12219 |
+
},
|
| 12220 |
+
{
|
| 12221 |
+
"epoch": 0.6810752793091672,
|
| 12222 |
+
"grad_norm": 0.16722330451011658,
|
| 12223 |
+
"learning_rate": 0.00027710027100271003,
|
| 12224 |
+
"loss": 2.6413745880126953,
|
| 12225 |
+
"step": 3490
|
| 12226 |
+
},
|
| 12227 |
+
{
|
| 12228 |
+
"epoch": 0.6814655803288286,
|
| 12229 |
+
"grad_norm": 0.15776386857032776,
|
| 12230 |
+
"learning_rate": 0.00027676151761517613,
|
| 12231 |
+
"loss": 2.6188578605651855,
|
| 12232 |
+
"step": 3492
|
| 12233 |
+
},
|
| 12234 |
+
{
|
| 12235 |
+
"epoch": 0.6818558813484901,
|
| 12236 |
+
"grad_norm": 0.15766285359859467,
|
| 12237 |
+
"learning_rate": 0.0002764227642276423,
|
| 12238 |
+
"loss": 2.583242177963257,
|
| 12239 |
+
"step": 3494
|
| 12240 |
+
},
|
| 12241 |
+
{
|
| 12242 |
+
"epoch": 0.6822461823681515,
|
| 12243 |
+
"grad_norm": 0.18853628635406494,
|
| 12244 |
+
"learning_rate": 0.00027608401084010844,
|
| 12245 |
+
"loss": 2.541515827178955,
|
| 12246 |
+
"step": 3496
|
| 12247 |
+
},
|
| 12248 |
+
{
|
| 12249 |
+
"epoch": 0.6826364833878128,
|
| 12250 |
+
"grad_norm": 0.13964493572711945,
|
| 12251 |
+
"learning_rate": 0.0002757452574525745,
|
| 12252 |
+
"loss": 2.570120334625244,
|
| 12253 |
+
"step": 3498
|
| 12254 |
+
},
|
| 12255 |
+
{
|
| 12256 |
+
"epoch": 0.6830267844074742,
|
| 12257 |
+
"grad_norm": 0.1581820845603943,
|
| 12258 |
+
"learning_rate": 0.00027540650406504064,
|
| 12259 |
+
"loss": 2.5609936714172363,
|
| 12260 |
+
"step": 3500
|
| 12261 |
+
},
|
| 12262 |
+
{
|
| 12263 |
+
"epoch": 0.6834170854271356,
|
| 12264 |
+
"grad_norm": 0.14818023145198822,
|
| 12265 |
+
"learning_rate": 0.0002750677506775068,
|
| 12266 |
+
"loss": 2.571629285812378,
|
| 12267 |
+
"step": 3502
|
| 12268 |
+
},
|
| 12269 |
+
{
|
| 12270 |
+
"epoch": 0.6838073864467971,
|
| 12271 |
+
"grad_norm": 0.20079585909843445,
|
| 12272 |
+
"learning_rate": 0.0002747289972899729,
|
| 12273 |
+
"loss": 2.5347564220428467,
|
| 12274 |
+
"step": 3504
|
| 12275 |
+
},
|
| 12276 |
+
{
|
| 12277 |
+
"epoch": 0.6841976874664585,
|
| 12278 |
+
"grad_norm": 0.193669393658638,
|
| 12279 |
+
"learning_rate": 0.00027439024390243905,
|
| 12280 |
+
"loss": 2.5349318981170654,
|
| 12281 |
+
"step": 3506
|
| 12282 |
+
},
|
| 12283 |
+
{
|
| 12284 |
+
"epoch": 0.6845879884861199,
|
| 12285 |
+
"grad_norm": 0.1569756418466568,
|
| 12286 |
+
"learning_rate": 0.00027405149051490515,
|
| 12287 |
+
"loss": 2.5877890586853027,
|
| 12288 |
+
"step": 3508
|
| 12289 |
+
},
|
| 12290 |
+
{
|
| 12291 |
+
"epoch": 0.6849782895057813,
|
| 12292 |
+
"grad_norm": 0.17633679509162903,
|
| 12293 |
+
"learning_rate": 0.00027371273712737125,
|
| 12294 |
+
"loss": 2.478084087371826,
|
| 12295 |
+
"step": 3510
|
| 12296 |
+
},
|
| 12297 |
+
{
|
| 12298 |
+
"epoch": 0.6853685905254427,
|
| 12299 |
+
"grad_norm": 0.19475726783275604,
|
| 12300 |
+
"learning_rate": 0.0002733739837398374,
|
| 12301 |
+
"loss": 2.5324668884277344,
|
| 12302 |
+
"step": 3512
|
| 12303 |
+
},
|
| 12304 |
+
{
|
| 12305 |
+
"epoch": 0.6857588915451042,
|
| 12306 |
+
"grad_norm": 0.17610110342502594,
|
| 12307 |
+
"learning_rate": 0.00027303523035230356,
|
| 12308 |
+
"loss": 2.591855525970459,
|
| 12309 |
+
"step": 3514
|
| 12310 |
+
},
|
| 12311 |
+
{
|
| 12312 |
+
"epoch": 0.6861491925647656,
|
| 12313 |
+
"grad_norm": 0.1726960390806198,
|
| 12314 |
+
"learning_rate": 0.00027269647696476966,
|
| 12315 |
+
"loss": 2.552464485168457,
|
| 12316 |
+
"step": 3516
|
| 12317 |
+
},
|
| 12318 |
+
{
|
| 12319 |
+
"epoch": 0.686539493584427,
|
| 12320 |
+
"grad_norm": 0.20242227613925934,
|
| 12321 |
+
"learning_rate": 0.00027235772357723576,
|
| 12322 |
+
"loss": 2.5683720111846924,
|
| 12323 |
+
"step": 3518
|
| 12324 |
+
},
|
| 12325 |
+
{
|
| 12326 |
+
"epoch": 0.6869297946040884,
|
| 12327 |
+
"grad_norm": 0.16837498545646667,
|
| 12328 |
+
"learning_rate": 0.0002720189701897019,
|
| 12329 |
+
"loss": 2.6068809032440186,
|
| 12330 |
+
"step": 3520
|
| 12331 |
+
},
|
| 12332 |
+
{
|
| 12333 |
+
"epoch": 0.6873200956237498,
|
| 12334 |
+
"grad_norm": 0.16754375398159027,
|
| 12335 |
+
"learning_rate": 0.000271680216802168,
|
| 12336 |
+
"loss": 2.622627019882202,
|
| 12337 |
+
"step": 3522
|
| 12338 |
+
},
|
| 12339 |
+
{
|
| 12340 |
+
"epoch": 0.6877103966434113,
|
| 12341 |
+
"grad_norm": 0.13841623067855835,
|
| 12342 |
+
"learning_rate": 0.00027134146341463417,
|
| 12343 |
+
"loss": 2.5490479469299316,
|
| 12344 |
+
"step": 3524
|
| 12345 |
+
},
|
| 12346 |
+
{
|
| 12347 |
+
"epoch": 0.6881006976630727,
|
| 12348 |
+
"grad_norm": 0.17966364324092865,
|
| 12349 |
+
"learning_rate": 0.00027100271002710027,
|
| 12350 |
+
"loss": 2.641651153564453,
|
| 12351 |
+
"step": 3526
|
| 12352 |
+
},
|
| 12353 |
+
{
|
| 12354 |
+
"epoch": 0.6884909986827341,
|
| 12355 |
+
"grad_norm": 0.15677954256534576,
|
| 12356 |
+
"learning_rate": 0.00027066395663956637,
|
| 12357 |
+
"loss": 2.5848183631896973,
|
| 12358 |
+
"step": 3528
|
| 12359 |
+
},
|
| 12360 |
+
{
|
| 12361 |
+
"epoch": 0.6888812997023954,
|
| 12362 |
+
"grad_norm": 0.17701654136180878,
|
| 12363 |
+
"learning_rate": 0.0002703252032520325,
|
| 12364 |
+
"loss": 2.5867717266082764,
|
| 12365 |
+
"step": 3530
|
| 12366 |
+
},
|
| 12367 |
+
{
|
| 12368 |
+
"epoch": 0.6892716007220568,
|
| 12369 |
+
"grad_norm": 0.15489813685417175,
|
| 12370 |
+
"learning_rate": 0.0002699864498644987,
|
| 12371 |
+
"loss": 2.5462985038757324,
|
| 12372 |
+
"step": 3532
|
| 12373 |
+
},
|
| 12374 |
+
{
|
| 12375 |
+
"epoch": 0.6896619017417183,
|
| 12376 |
+
"grad_norm": 0.15385335683822632,
|
| 12377 |
+
"learning_rate": 0.0002696476964769648,
|
| 12378 |
+
"loss": 2.5650439262390137,
|
| 12379 |
+
"step": 3534
|
| 12380 |
+
},
|
| 12381 |
+
{
|
| 12382 |
+
"epoch": 0.6900522027613797,
|
| 12383 |
+
"grad_norm": 0.18159344792366028,
|
| 12384 |
+
"learning_rate": 0.0002693089430894309,
|
| 12385 |
+
"loss": 2.563570976257324,
|
| 12386 |
+
"step": 3536
|
| 12387 |
+
},
|
| 12388 |
+
{
|
| 12389 |
+
"epoch": 0.6904425037810411,
|
| 12390 |
+
"grad_norm": 0.1906231939792633,
|
| 12391 |
+
"learning_rate": 0.00026897018970189703,
|
| 12392 |
+
"loss": 2.562577724456787,
|
| 12393 |
+
"step": 3538
|
| 12394 |
+
},
|
| 12395 |
+
{
|
| 12396 |
+
"epoch": 0.6908328048007025,
|
| 12397 |
+
"grad_norm": 0.1536346971988678,
|
| 12398 |
+
"learning_rate": 0.00026863143631436314,
|
| 12399 |
+
"loss": 2.560478687286377,
|
| 12400 |
+
"step": 3540
|
| 12401 |
+
},
|
| 12402 |
+
{
|
| 12403 |
+
"epoch": 0.691223105820364,
|
| 12404 |
+
"grad_norm": 0.18079456686973572,
|
| 12405 |
+
"learning_rate": 0.0002682926829268293,
|
| 12406 |
+
"loss": 2.571571111679077,
|
| 12407 |
+
"step": 3542
|
| 12408 |
+
},
|
| 12409 |
+
{
|
| 12410 |
+
"epoch": 0.6916134068400254,
|
| 12411 |
+
"grad_norm": 0.19207918643951416,
|
| 12412 |
+
"learning_rate": 0.0002679539295392954,
|
| 12413 |
+
"loss": 2.5816810131073,
|
| 12414 |
+
"step": 3544
|
| 12415 |
+
},
|
| 12416 |
+
{
|
| 12417 |
+
"epoch": 0.6920037078596868,
|
| 12418 |
+
"grad_norm": 0.21815037727355957,
|
| 12419 |
+
"learning_rate": 0.0002676151761517615,
|
| 12420 |
+
"loss": 2.603482246398926,
|
| 12421 |
+
"step": 3546
|
| 12422 |
+
},
|
| 12423 |
+
{
|
| 12424 |
+
"epoch": 0.6923940088793482,
|
| 12425 |
+
"grad_norm": 0.1413956582546234,
|
| 12426 |
+
"learning_rate": 0.00026727642276422764,
|
| 12427 |
+
"loss": 2.600614070892334,
|
| 12428 |
+
"step": 3548
|
| 12429 |
+
},
|
| 12430 |
+
{
|
| 12431 |
+
"epoch": 0.6927843098990096,
|
| 12432 |
+
"grad_norm": 0.2081175148487091,
|
| 12433 |
+
"learning_rate": 0.0002669376693766938,
|
| 12434 |
+
"loss": 2.588170051574707,
|
| 12435 |
+
"step": 3550
|
| 12436 |
+
},
|
| 12437 |
+
{
|
| 12438 |
+
"epoch": 0.693174610918671,
|
| 12439 |
+
"grad_norm": 0.2094593346118927,
|
| 12440 |
+
"learning_rate": 0.0002665989159891599,
|
| 12441 |
+
"loss": 2.472623586654663,
|
| 12442 |
+
"step": 3552
|
| 12443 |
+
},
|
| 12444 |
+
{
|
| 12445 |
+
"epoch": 0.6935649119383325,
|
| 12446 |
+
"grad_norm": 0.1859416514635086,
|
| 12447 |
+
"learning_rate": 0.000266260162601626,
|
| 12448 |
+
"loss": 2.5173559188842773,
|
| 12449 |
+
"step": 3554
|
| 12450 |
+
},
|
| 12451 |
+
{
|
| 12452 |
+
"epoch": 0.6939552129579939,
|
| 12453 |
+
"grad_norm": 0.19064246118068695,
|
| 12454 |
+
"learning_rate": 0.00026592140921409215,
|
| 12455 |
+
"loss": 2.582230567932129,
|
| 12456 |
+
"step": 3556
|
| 12457 |
+
},
|
| 12458 |
+
{
|
| 12459 |
+
"epoch": 0.6943455139776553,
|
| 12460 |
+
"grad_norm": 0.17520397901535034,
|
| 12461 |
+
"learning_rate": 0.00026558265582655825,
|
| 12462 |
+
"loss": 2.591395378112793,
|
| 12463 |
+
"step": 3558
|
| 12464 |
+
},
|
| 12465 |
+
{
|
| 12466 |
+
"epoch": 0.6947358149973166,
|
| 12467 |
+
"grad_norm": 0.13790354132652283,
|
| 12468 |
+
"learning_rate": 0.0002652439024390244,
|
| 12469 |
+
"loss": 2.549828052520752,
|
| 12470 |
+
"step": 3560
|
| 12471 |
+
},
|
| 12472 |
+
{
|
| 12473 |
+
"epoch": 0.695126116016978,
|
| 12474 |
+
"grad_norm": 0.14600613713264465,
|
| 12475 |
+
"learning_rate": 0.00026490514905149056,
|
| 12476 |
+
"loss": 2.5941295623779297,
|
| 12477 |
+
"step": 3562
|
| 12478 |
+
},
|
| 12479 |
+
{
|
| 12480 |
+
"epoch": 0.6955164170366395,
|
| 12481 |
+
"grad_norm": 0.16445523500442505,
|
| 12482 |
+
"learning_rate": 0.0002645663956639566,
|
| 12483 |
+
"loss": 2.5362086296081543,
|
| 12484 |
+
"step": 3564
|
| 12485 |
+
},
|
| 12486 |
+
{
|
| 12487 |
+
"epoch": 0.6959067180563009,
|
| 12488 |
+
"grad_norm": 0.15439637005329132,
|
| 12489 |
+
"learning_rate": 0.00026422764227642276,
|
| 12490 |
+
"loss": 2.6100807189941406,
|
| 12491 |
+
"step": 3566
|
| 12492 |
+
},
|
| 12493 |
+
{
|
| 12494 |
+
"epoch": 0.6962970190759623,
|
| 12495 |
+
"grad_norm": 0.22319720685482025,
|
| 12496 |
+
"learning_rate": 0.0002638888888888889,
|
| 12497 |
+
"loss": 2.5325236320495605,
|
| 12498 |
+
"step": 3568
|
| 12499 |
+
},
|
| 12500 |
+
{
|
| 12501 |
+
"epoch": 0.6966873200956237,
|
| 12502 |
+
"grad_norm": 0.1382499784231186,
|
| 12503 |
+
"learning_rate": 0.000263550135501355,
|
| 12504 |
+
"loss": 2.552042007446289,
|
| 12505 |
+
"step": 3570
|
| 12506 |
+
},
|
| 12507 |
+
{
|
| 12508 |
+
"epoch": 0.6970776211152852,
|
| 12509 |
+
"grad_norm": 0.2476213276386261,
|
| 12510 |
+
"learning_rate": 0.0002632113821138211,
|
| 12511 |
+
"loss": 2.5923104286193848,
|
| 12512 |
+
"step": 3572
|
| 12513 |
+
},
|
| 12514 |
+
{
|
| 12515 |
+
"epoch": 0.6974679221349466,
|
| 12516 |
+
"grad_norm": 0.1501258760690689,
|
| 12517 |
+
"learning_rate": 0.0002628726287262873,
|
| 12518 |
+
"loss": 2.584646701812744,
|
| 12519 |
+
"step": 3574
|
| 12520 |
+
},
|
| 12521 |
+
{
|
| 12522 |
+
"epoch": 0.697858223154608,
|
| 12523 |
+
"grad_norm": 0.17544013261795044,
|
| 12524 |
+
"learning_rate": 0.0002625338753387534,
|
| 12525 |
+
"loss": 2.4958348274230957,
|
| 12526 |
+
"step": 3576
|
| 12527 |
+
},
|
| 12528 |
+
{
|
| 12529 |
+
"epoch": 0.6982485241742694,
|
| 12530 |
+
"grad_norm": 0.15629850327968597,
|
| 12531 |
+
"learning_rate": 0.00026219512195121953,
|
| 12532 |
+
"loss": 2.5352060794830322,
|
| 12533 |
+
"step": 3578
|
| 12534 |
+
},
|
| 12535 |
+
{
|
| 12536 |
+
"epoch": 0.6986388251939308,
|
| 12537 |
+
"grad_norm": 0.2923874855041504,
|
| 12538 |
+
"learning_rate": 0.0002618563685636857,
|
| 12539 |
+
"loss": 2.5542187690734863,
|
| 12540 |
+
"step": 3580
|
| 12541 |
+
},
|
| 12542 |
+
{
|
| 12543 |
+
"epoch": 0.6990291262135923,
|
| 12544 |
+
"grad_norm": 0.16750425100326538,
|
| 12545 |
+
"learning_rate": 0.00026151761517615173,
|
| 12546 |
+
"loss": 2.6210031509399414,
|
| 12547 |
+
"step": 3582
|
| 12548 |
+
},
|
| 12549 |
+
{
|
| 12550 |
+
"epoch": 0.6994194272332537,
|
| 12551 |
+
"grad_norm": 0.14662767946720123,
|
| 12552 |
+
"learning_rate": 0.0002611788617886179,
|
| 12553 |
+
"loss": 2.5570082664489746,
|
| 12554 |
+
"step": 3584
|
| 12555 |
+
},
|
| 12556 |
+
{
|
| 12557 |
+
"epoch": 0.6998097282529151,
|
| 12558 |
+
"grad_norm": 0.1992248296737671,
|
| 12559 |
+
"learning_rate": 0.00026084010840108404,
|
| 12560 |
+
"loss": 2.597034454345703,
|
| 12561 |
+
"step": 3586
|
| 12562 |
+
},
|
| 12563 |
+
{
|
| 12564 |
+
"epoch": 0.7002000292725765,
|
| 12565 |
+
"grad_norm": 0.16254951059818268,
|
| 12566 |
+
"learning_rate": 0.00026050135501355014,
|
| 12567 |
+
"loss": 2.5396645069122314,
|
| 12568 |
+
"step": 3588
|
| 12569 |
+
},
|
| 12570 |
+
{
|
| 12571 |
+
"epoch": 0.7005903302922379,
|
| 12572 |
+
"grad_norm": 0.13893179595470428,
|
| 12573 |
+
"learning_rate": 0.0002601626016260163,
|
| 12574 |
+
"loss": 2.5957744121551514,
|
| 12575 |
+
"step": 3590
|
| 12576 |
}
|
| 12577 |
],
|
| 12578 |
"logging_steps": 2,
|
|
|
|
| 12592 |
"attributes": {}
|
| 12593 |
}
|
| 12594 |
},
|
| 12595 |
+
"total_flos": 1.1484586882776433e+18,
|
| 12596 |
"train_batch_size": 6,
|
| 12597 |
"trial_name": null,
|
| 12598 |
"trial_params": null
|