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 5125, 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:d60c4683957bf030377f7e0ccfc0bcb3169d7196e1c1ffc0dd52469b90af3c7c
|
| 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 sha256:97666c591cf30855e40c4c105a3c0341f867ecf38af6c143653a55b4e5c8172e
|
| 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 sha256:074459a53ccd5d2c3d1c09ffb175934bc5ced53f55e424b16fd9072b315bad52
|
| 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":
|
| 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,
|
|
@@ -16164,6 +16164,1784 @@
|
|
| 16164 |
"learning_rate": 8.638211382113821e-05,
|
| 16165 |
"loss": 2.438394546508789,
|
| 16166 |
"step": 4616
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16167 |
}
|
| 16168 |
],
|
| 16169 |
"logging_steps": 2,
|
|
@@ -16178,12 +17956,12 @@
|
|
| 16178 |
"should_evaluate": false,
|
| 16179 |
"should_log": false,
|
| 16180 |
"should_save": true,
|
| 16181 |
-
"should_training_stop":
|
| 16182 |
},
|
| 16183 |
"attributes": {}
|
| 16184 |
}
|
| 16185 |
},
|
| 16186 |
-
"total_flos": 1.
|
| 16187 |
"train_batch_size": 6,
|
| 16188 |
"trial_name": null,
|
| 16189 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5125,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16164 |
"learning_rate": 8.638211382113821e-05,
|
| 16165 |
"loss": 2.438394546508789,
|
| 16166 |
"step": 4616
|
| 16167 |
+
},
|
| 16168 |
+
{
|
| 16169 |
+
"epoch": 0.9012050543982046,
|
| 16170 |
+
"grad_norm": 0.16943885385990143,
|
| 16171 |
+
"learning_rate": 8.604336043360434e-05,
|
| 16172 |
+
"loss": 2.5942296981811523,
|
| 16173 |
+
"step": 4618
|
| 16174 |
+
},
|
| 16175 |
+
{
|
| 16176 |
+
"epoch": 0.9015953554178661,
|
| 16177 |
+
"grad_norm": 0.15032587945461273,
|
| 16178 |
+
"learning_rate": 8.570460704607045e-05,
|
| 16179 |
+
"loss": 2.6136271953582764,
|
| 16180 |
+
"step": 4620
|
| 16181 |
+
},
|
| 16182 |
+
{
|
| 16183 |
+
"epoch": 0.9019856564375275,
|
| 16184 |
+
"grad_norm": 0.16384389996528625,
|
| 16185 |
+
"learning_rate": 8.53658536585366e-05,
|
| 16186 |
+
"loss": 2.5482611656188965,
|
| 16187 |
+
"step": 4622
|
| 16188 |
+
},
|
| 16189 |
+
{
|
| 16190 |
+
"epoch": 0.9023759574571889,
|
| 16191 |
+
"grad_norm": 0.1677098125219345,
|
| 16192 |
+
"learning_rate": 8.502710027100272e-05,
|
| 16193 |
+
"loss": 2.599621295928955,
|
| 16194 |
+
"step": 4624
|
| 16195 |
+
},
|
| 16196 |
+
{
|
| 16197 |
+
"epoch": 0.9027662584768503,
|
| 16198 |
+
"grad_norm": 0.18057939410209656,
|
| 16199 |
+
"learning_rate": 8.468834688346883e-05,
|
| 16200 |
+
"loss": 2.5810976028442383,
|
| 16201 |
+
"step": 4626
|
| 16202 |
+
},
|
| 16203 |
+
{
|
| 16204 |
+
"epoch": 0.9031565594965116,
|
| 16205 |
+
"grad_norm": 0.19252265989780426,
|
| 16206 |
+
"learning_rate": 8.434959349593496e-05,
|
| 16207 |
+
"loss": 2.556244373321533,
|
| 16208 |
+
"step": 4628
|
| 16209 |
+
},
|
| 16210 |
+
{
|
| 16211 |
+
"epoch": 0.9035468605161731,
|
| 16212 |
+
"grad_norm": 0.18770740926265717,
|
| 16213 |
+
"learning_rate": 8.401084010840109e-05,
|
| 16214 |
+
"loss": 2.5428380966186523,
|
| 16215 |
+
"step": 4630
|
| 16216 |
+
},
|
| 16217 |
+
{
|
| 16218 |
+
"epoch": 0.9039371615358345,
|
| 16219 |
+
"grad_norm": 0.16976773738861084,
|
| 16220 |
+
"learning_rate": 8.36720867208672e-05,
|
| 16221 |
+
"loss": 2.5711145401000977,
|
| 16222 |
+
"step": 4632
|
| 16223 |
+
},
|
| 16224 |
+
{
|
| 16225 |
+
"epoch": 0.9043274625554959,
|
| 16226 |
+
"grad_norm": 0.12525327503681183,
|
| 16227 |
+
"learning_rate": 8.333333333333333e-05,
|
| 16228 |
+
"loss": 2.5705628395080566,
|
| 16229 |
+
"step": 4634
|
| 16230 |
+
},
|
| 16231 |
+
{
|
| 16232 |
+
"epoch": 0.9047177635751573,
|
| 16233 |
+
"grad_norm": 0.25657546520233154,
|
| 16234 |
+
"learning_rate": 8.299457994579946e-05,
|
| 16235 |
+
"loss": 2.5968027114868164,
|
| 16236 |
+
"step": 4636
|
| 16237 |
+
},
|
| 16238 |
+
{
|
| 16239 |
+
"epoch": 0.9051080645948187,
|
| 16240 |
+
"grad_norm": 0.157669797539711,
|
| 16241 |
+
"learning_rate": 8.265582655826559e-05,
|
| 16242 |
+
"loss": 2.584488868713379,
|
| 16243 |
+
"step": 4638
|
| 16244 |
+
},
|
| 16245 |
+
{
|
| 16246 |
+
"epoch": 0.9054983656144802,
|
| 16247 |
+
"grad_norm": 0.1437220573425293,
|
| 16248 |
+
"learning_rate": 8.231707317073171e-05,
|
| 16249 |
+
"loss": 2.558593273162842,
|
| 16250 |
+
"step": 4640
|
| 16251 |
+
},
|
| 16252 |
+
{
|
| 16253 |
+
"epoch": 0.9058886666341416,
|
| 16254 |
+
"grad_norm": 0.17887970805168152,
|
| 16255 |
+
"learning_rate": 8.197831978319784e-05,
|
| 16256 |
+
"loss": 2.6402454376220703,
|
| 16257 |
+
"step": 4642
|
| 16258 |
+
},
|
| 16259 |
+
{
|
| 16260 |
+
"epoch": 0.906278967653803,
|
| 16261 |
+
"grad_norm": 0.14819514751434326,
|
| 16262 |
+
"learning_rate": 8.163956639566395e-05,
|
| 16263 |
+
"loss": 2.5442566871643066,
|
| 16264 |
+
"step": 4644
|
| 16265 |
+
},
|
| 16266 |
+
{
|
| 16267 |
+
"epoch": 0.9066692686734644,
|
| 16268 |
+
"grad_norm": 0.15977245569229126,
|
| 16269 |
+
"learning_rate": 8.130081300813008e-05,
|
| 16270 |
+
"loss": 2.5326080322265625,
|
| 16271 |
+
"step": 4646
|
| 16272 |
+
},
|
| 16273 |
+
{
|
| 16274 |
+
"epoch": 0.9070595696931258,
|
| 16275 |
+
"grad_norm": 0.18827304244041443,
|
| 16276 |
+
"learning_rate": 8.096205962059621e-05,
|
| 16277 |
+
"loss": 2.583770275115967,
|
| 16278 |
+
"step": 4648
|
| 16279 |
+
},
|
| 16280 |
+
{
|
| 16281 |
+
"epoch": 0.9074498707127873,
|
| 16282 |
+
"grad_norm": 0.13711051642894745,
|
| 16283 |
+
"learning_rate": 8.062330623306232e-05,
|
| 16284 |
+
"loss": 2.572483539581299,
|
| 16285 |
+
"step": 4650
|
| 16286 |
+
},
|
| 16287 |
+
{
|
| 16288 |
+
"epoch": 0.9078401717324487,
|
| 16289 |
+
"grad_norm": 0.16362741589546204,
|
| 16290 |
+
"learning_rate": 8.028455284552846e-05,
|
| 16291 |
+
"loss": 2.584352970123291,
|
| 16292 |
+
"step": 4652
|
| 16293 |
+
},
|
| 16294 |
+
{
|
| 16295 |
+
"epoch": 0.9082304727521101,
|
| 16296 |
+
"grad_norm": 0.18929623067378998,
|
| 16297 |
+
"learning_rate": 7.994579945799459e-05,
|
| 16298 |
+
"loss": 2.6057310104370117,
|
| 16299 |
+
"step": 4654
|
| 16300 |
+
},
|
| 16301 |
+
{
|
| 16302 |
+
"epoch": 0.9086207737717715,
|
| 16303 |
+
"grad_norm": 0.13849975168704987,
|
| 16304 |
+
"learning_rate": 7.96070460704607e-05,
|
| 16305 |
+
"loss": 2.56952166557312,
|
| 16306 |
+
"step": 4656
|
| 16307 |
+
},
|
| 16308 |
+
{
|
| 16309 |
+
"epoch": 0.9090110747914328,
|
| 16310 |
+
"grad_norm": 0.1494431495666504,
|
| 16311 |
+
"learning_rate": 7.926829268292683e-05,
|
| 16312 |
+
"loss": 2.5646748542785645,
|
| 16313 |
+
"step": 4658
|
| 16314 |
+
},
|
| 16315 |
+
{
|
| 16316 |
+
"epoch": 0.9094013758110943,
|
| 16317 |
+
"grad_norm": 0.18398723006248474,
|
| 16318 |
+
"learning_rate": 7.892953929539296e-05,
|
| 16319 |
+
"loss": 2.549011468887329,
|
| 16320 |
+
"step": 4660
|
| 16321 |
+
},
|
| 16322 |
+
{
|
| 16323 |
+
"epoch": 0.9097916768307557,
|
| 16324 |
+
"grad_norm": 0.1974457949399948,
|
| 16325 |
+
"learning_rate": 7.859078590785907e-05,
|
| 16326 |
+
"loss": 2.5659356117248535,
|
| 16327 |
+
"step": 4662
|
| 16328 |
+
},
|
| 16329 |
+
{
|
| 16330 |
+
"epoch": 0.9101819778504171,
|
| 16331 |
+
"grad_norm": 0.17245379090309143,
|
| 16332 |
+
"learning_rate": 7.82520325203252e-05,
|
| 16333 |
+
"loss": 2.5429718494415283,
|
| 16334 |
+
"step": 4664
|
| 16335 |
+
},
|
| 16336 |
+
{
|
| 16337 |
+
"epoch": 0.9105722788700785,
|
| 16338 |
+
"grad_norm": 0.16907775402069092,
|
| 16339 |
+
"learning_rate": 7.791327913279133e-05,
|
| 16340 |
+
"loss": 2.5612359046936035,
|
| 16341 |
+
"step": 4666
|
| 16342 |
+
},
|
| 16343 |
+
{
|
| 16344 |
+
"epoch": 0.9109625798897399,
|
| 16345 |
+
"grad_norm": 0.2431991845369339,
|
| 16346 |
+
"learning_rate": 7.757452574525746e-05,
|
| 16347 |
+
"loss": 2.5915679931640625,
|
| 16348 |
+
"step": 4668
|
| 16349 |
+
},
|
| 16350 |
+
{
|
| 16351 |
+
"epoch": 0.9113528809094014,
|
| 16352 |
+
"grad_norm": 0.17103075981140137,
|
| 16353 |
+
"learning_rate": 7.723577235772358e-05,
|
| 16354 |
+
"loss": 2.5920112133026123,
|
| 16355 |
+
"step": 4670
|
| 16356 |
+
},
|
| 16357 |
+
{
|
| 16358 |
+
"epoch": 0.9117431819290628,
|
| 16359 |
+
"grad_norm": 0.15199171006679535,
|
| 16360 |
+
"learning_rate": 7.689701897018971e-05,
|
| 16361 |
+
"loss": 2.570117950439453,
|
| 16362 |
+
"step": 4672
|
| 16363 |
+
},
|
| 16364 |
+
{
|
| 16365 |
+
"epoch": 0.9121334829487242,
|
| 16366 |
+
"grad_norm": 0.16495178639888763,
|
| 16367 |
+
"learning_rate": 7.655826558265582e-05,
|
| 16368 |
+
"loss": 2.5385091304779053,
|
| 16369 |
+
"step": 4674
|
| 16370 |
+
},
|
| 16371 |
+
{
|
| 16372 |
+
"epoch": 0.9125237839683856,
|
| 16373 |
+
"grad_norm": 0.18258130550384521,
|
| 16374 |
+
"learning_rate": 7.621951219512195e-05,
|
| 16375 |
+
"loss": 2.5684828758239746,
|
| 16376 |
+
"step": 4676
|
| 16377 |
+
},
|
| 16378 |
+
{
|
| 16379 |
+
"epoch": 0.912914084988047,
|
| 16380 |
+
"grad_norm": 0.15398654341697693,
|
| 16381 |
+
"learning_rate": 7.588075880758808e-05,
|
| 16382 |
+
"loss": 2.5487618446350098,
|
| 16383 |
+
"step": 4678
|
| 16384 |
+
},
|
| 16385 |
+
{
|
| 16386 |
+
"epoch": 0.9133043860077085,
|
| 16387 |
+
"grad_norm": 0.15192687511444092,
|
| 16388 |
+
"learning_rate": 7.554200542005419e-05,
|
| 16389 |
+
"loss": 2.5798897743225098,
|
| 16390 |
+
"step": 4680
|
| 16391 |
+
},
|
| 16392 |
+
{
|
| 16393 |
+
"epoch": 0.9136946870273699,
|
| 16394 |
+
"grad_norm": 0.23239099979400635,
|
| 16395 |
+
"learning_rate": 7.520325203252033e-05,
|
| 16396 |
+
"loss": 2.5574707984924316,
|
| 16397 |
+
"step": 4682
|
| 16398 |
+
},
|
| 16399 |
+
{
|
| 16400 |
+
"epoch": 0.9140849880470313,
|
| 16401 |
+
"grad_norm": 0.16236330568790436,
|
| 16402 |
+
"learning_rate": 7.486449864498646e-05,
|
| 16403 |
+
"loss": 2.563300132751465,
|
| 16404 |
+
"step": 4684
|
| 16405 |
+
},
|
| 16406 |
+
{
|
| 16407 |
+
"epoch": 0.9144752890666927,
|
| 16408 |
+
"grad_norm": 0.19603270292282104,
|
| 16409 |
+
"learning_rate": 7.452574525745257e-05,
|
| 16410 |
+
"loss": 2.590676784515381,
|
| 16411 |
+
"step": 4686
|
| 16412 |
+
},
|
| 16413 |
+
{
|
| 16414 |
+
"epoch": 0.9148655900863542,
|
| 16415 |
+
"grad_norm": 0.16204723715782166,
|
| 16416 |
+
"learning_rate": 7.41869918699187e-05,
|
| 16417 |
+
"loss": 2.594759702682495,
|
| 16418 |
+
"step": 4688
|
| 16419 |
+
},
|
| 16420 |
+
{
|
| 16421 |
+
"epoch": 0.9152558911060155,
|
| 16422 |
+
"grad_norm": 0.17281579971313477,
|
| 16423 |
+
"learning_rate": 7.384823848238483e-05,
|
| 16424 |
+
"loss": 2.5529732704162598,
|
| 16425 |
+
"step": 4690
|
| 16426 |
+
},
|
| 16427 |
+
{
|
| 16428 |
+
"epoch": 0.9156461921256769,
|
| 16429 |
+
"grad_norm": 0.16970066726207733,
|
| 16430 |
+
"learning_rate": 7.350948509485094e-05,
|
| 16431 |
+
"loss": 2.5648865699768066,
|
| 16432 |
+
"step": 4692
|
| 16433 |
+
},
|
| 16434 |
+
{
|
| 16435 |
+
"epoch": 0.9160364931453383,
|
| 16436 |
+
"grad_norm": 0.1715918928384781,
|
| 16437 |
+
"learning_rate": 7.317073170731707e-05,
|
| 16438 |
+
"loss": 2.594778060913086,
|
| 16439 |
+
"step": 4694
|
| 16440 |
+
},
|
| 16441 |
+
{
|
| 16442 |
+
"epoch": 0.9164267941649997,
|
| 16443 |
+
"grad_norm": 0.1570514440536499,
|
| 16444 |
+
"learning_rate": 7.28319783197832e-05,
|
| 16445 |
+
"loss": 2.6048998832702637,
|
| 16446 |
+
"step": 4696
|
| 16447 |
+
},
|
| 16448 |
+
{
|
| 16449 |
+
"epoch": 0.9168170951846611,
|
| 16450 |
+
"grad_norm": 0.15604351460933685,
|
| 16451 |
+
"learning_rate": 7.249322493224933e-05,
|
| 16452 |
+
"loss": 2.5294651985168457,
|
| 16453 |
+
"step": 4698
|
| 16454 |
+
},
|
| 16455 |
+
{
|
| 16456 |
+
"epoch": 0.9172073962043226,
|
| 16457 |
+
"grad_norm": 0.19740237295627594,
|
| 16458 |
+
"learning_rate": 7.215447154471545e-05,
|
| 16459 |
+
"loss": 2.536189556121826,
|
| 16460 |
+
"step": 4700
|
| 16461 |
+
},
|
| 16462 |
+
{
|
| 16463 |
+
"epoch": 0.917597697223984,
|
| 16464 |
+
"grad_norm": 0.15487682819366455,
|
| 16465 |
+
"learning_rate": 7.181571815718158e-05,
|
| 16466 |
+
"loss": 2.582629919052124,
|
| 16467 |
+
"step": 4702
|
| 16468 |
+
},
|
| 16469 |
+
{
|
| 16470 |
+
"epoch": 0.9179879982436454,
|
| 16471 |
+
"grad_norm": 0.20343619585037231,
|
| 16472 |
+
"learning_rate": 7.14769647696477e-05,
|
| 16473 |
+
"loss": 2.5573770999908447,
|
| 16474 |
+
"step": 4704
|
| 16475 |
+
},
|
| 16476 |
+
{
|
| 16477 |
+
"epoch": 0.9183782992633068,
|
| 16478 |
+
"grad_norm": 0.16743403673171997,
|
| 16479 |
+
"learning_rate": 7.113821138211382e-05,
|
| 16480 |
+
"loss": 2.672092914581299,
|
| 16481 |
+
"step": 4706
|
| 16482 |
+
},
|
| 16483 |
+
{
|
| 16484 |
+
"epoch": 0.9187686002829683,
|
| 16485 |
+
"grad_norm": 0.15218350291252136,
|
| 16486 |
+
"learning_rate": 7.079945799457995e-05,
|
| 16487 |
+
"loss": 2.542736530303955,
|
| 16488 |
+
"step": 4708
|
| 16489 |
+
},
|
| 16490 |
+
{
|
| 16491 |
+
"epoch": 0.9191589013026297,
|
| 16492 |
+
"grad_norm": 0.14628981053829193,
|
| 16493 |
+
"learning_rate": 7.046070460704606e-05,
|
| 16494 |
+
"loss": 2.5473785400390625,
|
| 16495 |
+
"step": 4710
|
| 16496 |
+
},
|
| 16497 |
+
{
|
| 16498 |
+
"epoch": 0.9195492023222911,
|
| 16499 |
+
"grad_norm": 0.17520691454410553,
|
| 16500 |
+
"learning_rate": 7.01219512195122e-05,
|
| 16501 |
+
"loss": 2.591827392578125,
|
| 16502 |
+
"step": 4712
|
| 16503 |
+
},
|
| 16504 |
+
{
|
| 16505 |
+
"epoch": 0.9199395033419525,
|
| 16506 |
+
"grad_norm": 0.15614348649978638,
|
| 16507 |
+
"learning_rate": 6.978319783197833e-05,
|
| 16508 |
+
"loss": 2.5766422748565674,
|
| 16509 |
+
"step": 4714
|
| 16510 |
+
},
|
| 16511 |
+
{
|
| 16512 |
+
"epoch": 0.9203298043616139,
|
| 16513 |
+
"grad_norm": 0.14300835132598877,
|
| 16514 |
+
"learning_rate": 6.944444444444444e-05,
|
| 16515 |
+
"loss": 2.6365792751312256,
|
| 16516 |
+
"step": 4716
|
| 16517 |
+
},
|
| 16518 |
+
{
|
| 16519 |
+
"epoch": 0.9207201053812754,
|
| 16520 |
+
"grad_norm": 0.14077895879745483,
|
| 16521 |
+
"learning_rate": 6.910569105691057e-05,
|
| 16522 |
+
"loss": 2.562073230743408,
|
| 16523 |
+
"step": 4718
|
| 16524 |
+
},
|
| 16525 |
+
{
|
| 16526 |
+
"epoch": 0.9211104064009368,
|
| 16527 |
+
"grad_norm": 0.17817562818527222,
|
| 16528 |
+
"learning_rate": 6.87669376693767e-05,
|
| 16529 |
+
"loss": 2.5390942096710205,
|
| 16530 |
+
"step": 4720
|
| 16531 |
+
},
|
| 16532 |
+
{
|
| 16533 |
+
"epoch": 0.9215007074205981,
|
| 16534 |
+
"grad_norm": 0.142636239528656,
|
| 16535 |
+
"learning_rate": 6.842818428184281e-05,
|
| 16536 |
+
"loss": 2.5878231525421143,
|
| 16537 |
+
"step": 4722
|
| 16538 |
+
},
|
| 16539 |
+
{
|
| 16540 |
+
"epoch": 0.9218910084402595,
|
| 16541 |
+
"grad_norm": 0.13555508852005005,
|
| 16542 |
+
"learning_rate": 6.808943089430894e-05,
|
| 16543 |
+
"loss": 2.579864978790283,
|
| 16544 |
+
"step": 4724
|
| 16545 |
+
},
|
| 16546 |
+
{
|
| 16547 |
+
"epoch": 0.9222813094599209,
|
| 16548 |
+
"grad_norm": 0.14985239505767822,
|
| 16549 |
+
"learning_rate": 6.775067750677507e-05,
|
| 16550 |
+
"loss": 2.5979127883911133,
|
| 16551 |
+
"step": 4726
|
| 16552 |
+
},
|
| 16553 |
+
{
|
| 16554 |
+
"epoch": 0.9226716104795823,
|
| 16555 |
+
"grad_norm": 0.18525880575180054,
|
| 16556 |
+
"learning_rate": 6.74119241192412e-05,
|
| 16557 |
+
"loss": 2.5460829734802246,
|
| 16558 |
+
"step": 4728
|
| 16559 |
+
},
|
| 16560 |
+
{
|
| 16561 |
+
"epoch": 0.9230619114992438,
|
| 16562 |
+
"grad_norm": 0.15723088383674622,
|
| 16563 |
+
"learning_rate": 6.707317073170732e-05,
|
| 16564 |
+
"loss": 2.584132432937622,
|
| 16565 |
+
"step": 4730
|
| 16566 |
+
},
|
| 16567 |
+
{
|
| 16568 |
+
"epoch": 0.9234522125189052,
|
| 16569 |
+
"grad_norm": 0.15766890347003937,
|
| 16570 |
+
"learning_rate": 6.673441734417345e-05,
|
| 16571 |
+
"loss": 2.5738768577575684,
|
| 16572 |
+
"step": 4732
|
| 16573 |
+
},
|
| 16574 |
+
{
|
| 16575 |
+
"epoch": 0.9238425135385666,
|
| 16576 |
+
"grad_norm": 0.1749323159456253,
|
| 16577 |
+
"learning_rate": 6.639566395663956e-05,
|
| 16578 |
+
"loss": 2.5526082515716553,
|
| 16579 |
+
"step": 4734
|
| 16580 |
+
},
|
| 16581 |
+
{
|
| 16582 |
+
"epoch": 0.924232814558228,
|
| 16583 |
+
"grad_norm": 0.16892434656620026,
|
| 16584 |
+
"learning_rate": 6.605691056910569e-05,
|
| 16585 |
+
"loss": 2.6028804779052734,
|
| 16586 |
+
"step": 4736
|
| 16587 |
+
},
|
| 16588 |
+
{
|
| 16589 |
+
"epoch": 0.9246231155778895,
|
| 16590 |
+
"grad_norm": 0.2056511789560318,
|
| 16591 |
+
"learning_rate": 6.571815718157182e-05,
|
| 16592 |
+
"loss": 2.575904607772827,
|
| 16593 |
+
"step": 4738
|
| 16594 |
+
},
|
| 16595 |
+
{
|
| 16596 |
+
"epoch": 0.9250134165975509,
|
| 16597 |
+
"grad_norm": 0.21136285364627838,
|
| 16598 |
+
"learning_rate": 6.537940379403793e-05,
|
| 16599 |
+
"loss": 2.587528705596924,
|
| 16600 |
+
"step": 4740
|
| 16601 |
+
},
|
| 16602 |
+
{
|
| 16603 |
+
"epoch": 0.9254037176172123,
|
| 16604 |
+
"grad_norm": 0.24338743090629578,
|
| 16605 |
+
"learning_rate": 6.504065040650407e-05,
|
| 16606 |
+
"loss": 2.5849242210388184,
|
| 16607 |
+
"step": 4742
|
| 16608 |
+
},
|
| 16609 |
+
{
|
| 16610 |
+
"epoch": 0.9257940186368737,
|
| 16611 |
+
"grad_norm": 0.13979430496692657,
|
| 16612 |
+
"learning_rate": 6.47018970189702e-05,
|
| 16613 |
+
"loss": 2.562948226928711,
|
| 16614 |
+
"step": 4744
|
| 16615 |
+
},
|
| 16616 |
+
{
|
| 16617 |
+
"epoch": 0.9261843196565351,
|
| 16618 |
+
"grad_norm": 0.14291426539421082,
|
| 16619 |
+
"learning_rate": 6.436314363143631e-05,
|
| 16620 |
+
"loss": 2.5824522972106934,
|
| 16621 |
+
"step": 4746
|
| 16622 |
+
},
|
| 16623 |
+
{
|
| 16624 |
+
"epoch": 0.9265746206761966,
|
| 16625 |
+
"grad_norm": 0.14352884888648987,
|
| 16626 |
+
"learning_rate": 6.402439024390244e-05,
|
| 16627 |
+
"loss": 2.6119565963745117,
|
| 16628 |
+
"step": 4748
|
| 16629 |
+
},
|
| 16630 |
+
{
|
| 16631 |
+
"epoch": 0.926964921695858,
|
| 16632 |
+
"grad_norm": 0.1821078062057495,
|
| 16633 |
+
"learning_rate": 6.368563685636857e-05,
|
| 16634 |
+
"loss": 2.5556588172912598,
|
| 16635 |
+
"step": 4750
|
| 16636 |
+
},
|
| 16637 |
+
{
|
| 16638 |
+
"epoch": 0.9273552227155193,
|
| 16639 |
+
"grad_norm": 0.19114242494106293,
|
| 16640 |
+
"learning_rate": 6.334688346883468e-05,
|
| 16641 |
+
"loss": 2.543853282928467,
|
| 16642 |
+
"step": 4752
|
| 16643 |
+
},
|
| 16644 |
+
{
|
| 16645 |
+
"epoch": 0.9277455237351807,
|
| 16646 |
+
"grad_norm": 0.13402321934700012,
|
| 16647 |
+
"learning_rate": 6.300813008130081e-05,
|
| 16648 |
+
"loss": 2.5283071994781494,
|
| 16649 |
+
"step": 4754
|
| 16650 |
+
},
|
| 16651 |
+
{
|
| 16652 |
+
"epoch": 0.9281358247548421,
|
| 16653 |
+
"grad_norm": 0.27668893337249756,
|
| 16654 |
+
"learning_rate": 6.266937669376694e-05,
|
| 16655 |
+
"loss": 2.56765079498291,
|
| 16656 |
+
"step": 4756
|
| 16657 |
+
},
|
| 16658 |
+
{
|
| 16659 |
+
"epoch": 0.9285261257745036,
|
| 16660 |
+
"grad_norm": 0.17165039479732513,
|
| 16661 |
+
"learning_rate": 6.233062330623306e-05,
|
| 16662 |
+
"loss": 2.569085121154785,
|
| 16663 |
+
"step": 4758
|
| 16664 |
+
},
|
| 16665 |
+
{
|
| 16666 |
+
"epoch": 0.928916426794165,
|
| 16667 |
+
"grad_norm": 0.1456623524427414,
|
| 16668 |
+
"learning_rate": 6.199186991869918e-05,
|
| 16669 |
+
"loss": 2.597381114959717,
|
| 16670 |
+
"step": 4760
|
| 16671 |
+
},
|
| 16672 |
+
{
|
| 16673 |
+
"epoch": 0.9293067278138264,
|
| 16674 |
+
"grad_norm": 0.1356220245361328,
|
| 16675 |
+
"learning_rate": 6.165311653116532e-05,
|
| 16676 |
+
"loss": 2.5524120330810547,
|
| 16677 |
+
"step": 4762
|
| 16678 |
+
},
|
| 16679 |
+
{
|
| 16680 |
+
"epoch": 0.9296970288334878,
|
| 16681 |
+
"grad_norm": 0.17173008620738983,
|
| 16682 |
+
"learning_rate": 6.131436314363143e-05,
|
| 16683 |
+
"loss": 2.5864102840423584,
|
| 16684 |
+
"step": 4764
|
| 16685 |
+
},
|
| 16686 |
+
{
|
| 16687 |
+
"epoch": 0.9300873298531492,
|
| 16688 |
+
"grad_norm": 0.18196311593055725,
|
| 16689 |
+
"learning_rate": 6.097560975609756e-05,
|
| 16690 |
+
"loss": 2.629669427871704,
|
| 16691 |
+
"step": 4766
|
| 16692 |
+
},
|
| 16693 |
+
{
|
| 16694 |
+
"epoch": 0.9304776308728107,
|
| 16695 |
+
"grad_norm": 0.19576209783554077,
|
| 16696 |
+
"learning_rate": 6.063685636856368e-05,
|
| 16697 |
+
"loss": 2.5695695877075195,
|
| 16698 |
+
"step": 4768
|
| 16699 |
+
},
|
| 16700 |
+
{
|
| 16701 |
+
"epoch": 0.9308679318924721,
|
| 16702 |
+
"grad_norm": 0.16827604174613953,
|
| 16703 |
+
"learning_rate": 6.0298102981029816e-05,
|
| 16704 |
+
"loss": 2.616455316543579,
|
| 16705 |
+
"step": 4770
|
| 16706 |
+
},
|
| 16707 |
+
{
|
| 16708 |
+
"epoch": 0.9312582329121335,
|
| 16709 |
+
"grad_norm": 0.1655803769826889,
|
| 16710 |
+
"learning_rate": 5.9959349593495936e-05,
|
| 16711 |
+
"loss": 2.6270055770874023,
|
| 16712 |
+
"step": 4772
|
| 16713 |
+
},
|
| 16714 |
+
{
|
| 16715 |
+
"epoch": 0.9316485339317949,
|
| 16716 |
+
"grad_norm": 0.16777759790420532,
|
| 16717 |
+
"learning_rate": 5.962059620596206e-05,
|
| 16718 |
+
"loss": 2.58109450340271,
|
| 16719 |
+
"step": 4774
|
| 16720 |
+
},
|
| 16721 |
+
{
|
| 16722 |
+
"epoch": 0.9320388349514563,
|
| 16723 |
+
"grad_norm": 0.1688891500234604,
|
| 16724 |
+
"learning_rate": 5.928184281842819e-05,
|
| 16725 |
+
"loss": 2.562847852706909,
|
| 16726 |
+
"step": 4776
|
| 16727 |
+
},
|
| 16728 |
+
{
|
| 16729 |
+
"epoch": 0.9324291359711178,
|
| 16730 |
+
"grad_norm": 0.1742626279592514,
|
| 16731 |
+
"learning_rate": 5.894308943089431e-05,
|
| 16732 |
+
"loss": 2.537230968475342,
|
| 16733 |
+
"step": 4778
|
| 16734 |
+
},
|
| 16735 |
+
{
|
| 16736 |
+
"epoch": 0.9328194369907792,
|
| 16737 |
+
"grad_norm": 0.17129458487033844,
|
| 16738 |
+
"learning_rate": 5.860433604336043e-05,
|
| 16739 |
+
"loss": 2.582958221435547,
|
| 16740 |
+
"step": 4780
|
| 16741 |
+
},
|
| 16742 |
+
{
|
| 16743 |
+
"epoch": 0.9332097380104406,
|
| 16744 |
+
"grad_norm": 0.16853067278862,
|
| 16745 |
+
"learning_rate": 5.826558265582656e-05,
|
| 16746 |
+
"loss": 2.598271369934082,
|
| 16747 |
+
"step": 4782
|
| 16748 |
+
},
|
| 16749 |
+
{
|
| 16750 |
+
"epoch": 0.9336000390301019,
|
| 16751 |
+
"grad_norm": 0.20755670964717865,
|
| 16752 |
+
"learning_rate": 5.792682926829269e-05,
|
| 16753 |
+
"loss": 2.5932936668395996,
|
| 16754 |
+
"step": 4784
|
| 16755 |
+
},
|
| 16756 |
+
{
|
| 16757 |
+
"epoch": 0.9339903400497633,
|
| 16758 |
+
"grad_norm": 0.19650299847126007,
|
| 16759 |
+
"learning_rate": 5.758807588075881e-05,
|
| 16760 |
+
"loss": 2.5676321983337402,
|
| 16761 |
+
"step": 4786
|
| 16762 |
+
},
|
| 16763 |
+
{
|
| 16764 |
+
"epoch": 0.9343806410694248,
|
| 16765 |
+
"grad_norm": 0.1455581784248352,
|
| 16766 |
+
"learning_rate": 5.7249322493224935e-05,
|
| 16767 |
+
"loss": 2.5976409912109375,
|
| 16768 |
+
"step": 4788
|
| 16769 |
+
},
|
| 16770 |
+
{
|
| 16771 |
+
"epoch": 0.9347709420890862,
|
| 16772 |
+
"grad_norm": 0.160209059715271,
|
| 16773 |
+
"learning_rate": 5.6910569105691056e-05,
|
| 16774 |
+
"loss": 2.601961612701416,
|
| 16775 |
+
"step": 4790
|
| 16776 |
+
},
|
| 16777 |
+
{
|
| 16778 |
+
"epoch": 0.9351612431087476,
|
| 16779 |
+
"grad_norm": 0.15131083130836487,
|
| 16780 |
+
"learning_rate": 5.657181571815718e-05,
|
| 16781 |
+
"loss": 2.5952608585357666,
|
| 16782 |
+
"step": 4792
|
| 16783 |
+
},
|
| 16784 |
+
{
|
| 16785 |
+
"epoch": 0.935551544128409,
|
| 16786 |
+
"grad_norm": 0.18619593977928162,
|
| 16787 |
+
"learning_rate": 5.623306233062331e-05,
|
| 16788 |
+
"loss": 2.5440404415130615,
|
| 16789 |
+
"step": 4794
|
| 16790 |
+
},
|
| 16791 |
+
{
|
| 16792 |
+
"epoch": 0.9359418451480704,
|
| 16793 |
+
"grad_norm": 0.1671157330274582,
|
| 16794 |
+
"learning_rate": 5.589430894308943e-05,
|
| 16795 |
+
"loss": 2.6606240272521973,
|
| 16796 |
+
"step": 4796
|
| 16797 |
+
},
|
| 16798 |
+
{
|
| 16799 |
+
"epoch": 0.9363321461677319,
|
| 16800 |
+
"grad_norm": 0.15247267484664917,
|
| 16801 |
+
"learning_rate": 5.555555555555555e-05,
|
| 16802 |
+
"loss": 2.5759055614471436,
|
| 16803 |
+
"step": 4798
|
| 16804 |
+
},
|
| 16805 |
+
{
|
| 16806 |
+
"epoch": 0.9367224471873933,
|
| 16807 |
+
"grad_norm": 0.19602476060390472,
|
| 16808 |
+
"learning_rate": 5.5216802168021686e-05,
|
| 16809 |
+
"loss": 2.523782730102539,
|
| 16810 |
+
"step": 4800
|
| 16811 |
+
},
|
| 16812 |
+
{
|
| 16813 |
+
"epoch": 0.9371127482070547,
|
| 16814 |
+
"grad_norm": 0.17173968255519867,
|
| 16815 |
+
"learning_rate": 5.4878048780487806e-05,
|
| 16816 |
+
"loss": 2.647266387939453,
|
| 16817 |
+
"step": 4802
|
| 16818 |
+
},
|
| 16819 |
+
{
|
| 16820 |
+
"epoch": 0.9375030492267161,
|
| 16821 |
+
"grad_norm": 0.17117303609848022,
|
| 16822 |
+
"learning_rate": 5.453929539295393e-05,
|
| 16823 |
+
"loss": 2.5890398025512695,
|
| 16824 |
+
"step": 4804
|
| 16825 |
+
},
|
| 16826 |
+
{
|
| 16827 |
+
"epoch": 0.9378933502463775,
|
| 16828 |
+
"grad_norm": 0.1738191843032837,
|
| 16829 |
+
"learning_rate": 5.420054200542006e-05,
|
| 16830 |
+
"loss": 2.5833048820495605,
|
| 16831 |
+
"step": 4806
|
| 16832 |
+
},
|
| 16833 |
+
{
|
| 16834 |
+
"epoch": 0.938283651266039,
|
| 16835 |
+
"grad_norm": 0.17709487676620483,
|
| 16836 |
+
"learning_rate": 5.386178861788618e-05,
|
| 16837 |
+
"loss": 2.558600902557373,
|
| 16838 |
+
"step": 4808
|
| 16839 |
+
},
|
| 16840 |
+
{
|
| 16841 |
+
"epoch": 0.9386739522857004,
|
| 16842 |
+
"grad_norm": 0.17818902432918549,
|
| 16843 |
+
"learning_rate": 5.35230352303523e-05,
|
| 16844 |
+
"loss": 2.569079875946045,
|
| 16845 |
+
"step": 4810
|
| 16846 |
+
},
|
| 16847 |
+
{
|
| 16848 |
+
"epoch": 0.9390642533053618,
|
| 16849 |
+
"grad_norm": 0.17096801102161407,
|
| 16850 |
+
"learning_rate": 5.318428184281843e-05,
|
| 16851 |
+
"loss": 2.582000732421875,
|
| 16852 |
+
"step": 4812
|
| 16853 |
+
},
|
| 16854 |
+
{
|
| 16855 |
+
"epoch": 0.9394545543250232,
|
| 16856 |
+
"grad_norm": 0.21249280869960785,
|
| 16857 |
+
"learning_rate": 5.284552845528456e-05,
|
| 16858 |
+
"loss": 2.5956339836120605,
|
| 16859 |
+
"step": 4814
|
| 16860 |
+
},
|
| 16861 |
+
{
|
| 16862 |
+
"epoch": 0.9398448553446845,
|
| 16863 |
+
"grad_norm": 0.2422473430633545,
|
| 16864 |
+
"learning_rate": 5.250677506775068e-05,
|
| 16865 |
+
"loss": 2.577719211578369,
|
| 16866 |
+
"step": 4816
|
| 16867 |
+
},
|
| 16868 |
+
{
|
| 16869 |
+
"epoch": 0.940235156364346,
|
| 16870 |
+
"grad_norm": 0.14729157090187073,
|
| 16871 |
+
"learning_rate": 5.2168021680216805e-05,
|
| 16872 |
+
"loss": 2.5664117336273193,
|
| 16873 |
+
"step": 4818
|
| 16874 |
+
},
|
| 16875 |
+
{
|
| 16876 |
+
"epoch": 0.9406254573840074,
|
| 16877 |
+
"grad_norm": 0.16829639673233032,
|
| 16878 |
+
"learning_rate": 5.1829268292682925e-05,
|
| 16879 |
+
"loss": 2.56571102142334,
|
| 16880 |
+
"step": 4820
|
| 16881 |
+
},
|
| 16882 |
+
{
|
| 16883 |
+
"epoch": 0.9410157584036688,
|
| 16884 |
+
"grad_norm": 0.17123524844646454,
|
| 16885 |
+
"learning_rate": 5.149051490514905e-05,
|
| 16886 |
+
"loss": 2.6217241287231445,
|
| 16887 |
+
"step": 4822
|
| 16888 |
+
},
|
| 16889 |
+
{
|
| 16890 |
+
"epoch": 0.9414060594233302,
|
| 16891 |
+
"grad_norm": 0.1751905083656311,
|
| 16892 |
+
"learning_rate": 5.115176151761518e-05,
|
| 16893 |
+
"loss": 2.559985637664795,
|
| 16894 |
+
"step": 4824
|
| 16895 |
+
},
|
| 16896 |
+
{
|
| 16897 |
+
"epoch": 0.9417963604429916,
|
| 16898 |
+
"grad_norm": 0.20410211384296417,
|
| 16899 |
+
"learning_rate": 5.08130081300813e-05,
|
| 16900 |
+
"loss": 2.592573642730713,
|
| 16901 |
+
"step": 4826
|
| 16902 |
+
},
|
| 16903 |
+
{
|
| 16904 |
+
"epoch": 0.9421866614626531,
|
| 16905 |
+
"grad_norm": 0.16879971325397491,
|
| 16906 |
+
"learning_rate": 5.047425474254742e-05,
|
| 16907 |
+
"loss": 2.630952835083008,
|
| 16908 |
+
"step": 4828
|
| 16909 |
+
},
|
| 16910 |
+
{
|
| 16911 |
+
"epoch": 0.9425769624823145,
|
| 16912 |
+
"grad_norm": 0.2159586399793625,
|
| 16913 |
+
"learning_rate": 5.0135501355013556e-05,
|
| 16914 |
+
"loss": 2.573737144470215,
|
| 16915 |
+
"step": 4830
|
| 16916 |
+
},
|
| 16917 |
+
{
|
| 16918 |
+
"epoch": 0.9429672635019759,
|
| 16919 |
+
"grad_norm": 0.16993483901023865,
|
| 16920 |
+
"learning_rate": 4.9796747967479676e-05,
|
| 16921 |
+
"loss": 2.6071619987487793,
|
| 16922 |
+
"step": 4832
|
| 16923 |
+
},
|
| 16924 |
+
{
|
| 16925 |
+
"epoch": 0.9433575645216373,
|
| 16926 |
+
"grad_norm": 0.14976678788661957,
|
| 16927 |
+
"learning_rate": 4.94579945799458e-05,
|
| 16928 |
+
"loss": 2.6290626525878906,
|
| 16929 |
+
"step": 4834
|
| 16930 |
+
},
|
| 16931 |
+
{
|
| 16932 |
+
"epoch": 0.9437478655412987,
|
| 16933 |
+
"grad_norm": 0.18720822036266327,
|
| 16934 |
+
"learning_rate": 4.9119241192411924e-05,
|
| 16935 |
+
"loss": 2.4897043704986572,
|
| 16936 |
+
"step": 4836
|
| 16937 |
+
},
|
| 16938 |
+
{
|
| 16939 |
+
"epoch": 0.9441381665609602,
|
| 16940 |
+
"grad_norm": 0.17143869400024414,
|
| 16941 |
+
"learning_rate": 4.878048780487805e-05,
|
| 16942 |
+
"loss": 2.5574746131896973,
|
| 16943 |
+
"step": 4838
|
| 16944 |
+
},
|
| 16945 |
+
{
|
| 16946 |
+
"epoch": 0.9445284675806216,
|
| 16947 |
+
"grad_norm": 0.16021029651165009,
|
| 16948 |
+
"learning_rate": 4.844173441734417e-05,
|
| 16949 |
+
"loss": 2.6072940826416016,
|
| 16950 |
+
"step": 4840
|
| 16951 |
+
},
|
| 16952 |
+
{
|
| 16953 |
+
"epoch": 0.944918768600283,
|
| 16954 |
+
"grad_norm": 0.22244895994663239,
|
| 16955 |
+
"learning_rate": 4.81029810298103e-05,
|
| 16956 |
+
"loss": 2.562277317047119,
|
| 16957 |
+
"step": 4842
|
| 16958 |
+
},
|
| 16959 |
+
{
|
| 16960 |
+
"epoch": 0.9453090696199444,
|
| 16961 |
+
"grad_norm": 0.18291804194450378,
|
| 16962 |
+
"learning_rate": 4.776422764227643e-05,
|
| 16963 |
+
"loss": 2.5470457077026367,
|
| 16964 |
+
"step": 4844
|
| 16965 |
+
},
|
| 16966 |
+
{
|
| 16967 |
+
"epoch": 0.9456993706396057,
|
| 16968 |
+
"grad_norm": 0.16934505105018616,
|
| 16969 |
+
"learning_rate": 4.742547425474255e-05,
|
| 16970 |
+
"loss": 2.5407357215881348,
|
| 16971 |
+
"step": 4846
|
| 16972 |
+
},
|
| 16973 |
+
{
|
| 16974 |
+
"epoch": 0.9460896716592672,
|
| 16975 |
+
"grad_norm": 0.1388915479183197,
|
| 16976 |
+
"learning_rate": 4.7086720867208675e-05,
|
| 16977 |
+
"loss": 2.596344470977783,
|
| 16978 |
+
"step": 4848
|
| 16979 |
+
},
|
| 16980 |
+
{
|
| 16981 |
+
"epoch": 0.9464799726789286,
|
| 16982 |
+
"grad_norm": 0.2038460373878479,
|
| 16983 |
+
"learning_rate": 4.6747967479674795e-05,
|
| 16984 |
+
"loss": 2.545109987258911,
|
| 16985 |
+
"step": 4850
|
| 16986 |
+
},
|
| 16987 |
+
{
|
| 16988 |
+
"epoch": 0.94687027369859,
|
| 16989 |
+
"grad_norm": 0.14533986151218414,
|
| 16990 |
+
"learning_rate": 4.640921409214092e-05,
|
| 16991 |
+
"loss": 2.6103439331054688,
|
| 16992 |
+
"step": 4852
|
| 16993 |
+
},
|
| 16994 |
+
{
|
| 16995 |
+
"epoch": 0.9472605747182514,
|
| 16996 |
+
"grad_norm": 0.22329600155353546,
|
| 16997 |
+
"learning_rate": 4.607046070460705e-05,
|
| 16998 |
+
"loss": 2.56807279586792,
|
| 16999 |
+
"step": 4854
|
| 17000 |
+
},
|
| 17001 |
+
{
|
| 17002 |
+
"epoch": 0.9476508757379128,
|
| 17003 |
+
"grad_norm": 0.19113874435424805,
|
| 17004 |
+
"learning_rate": 4.573170731707317e-05,
|
| 17005 |
+
"loss": 2.5562338829040527,
|
| 17006 |
+
"step": 4856
|
| 17007 |
+
},
|
| 17008 |
+
{
|
| 17009 |
+
"epoch": 0.9480411767575743,
|
| 17010 |
+
"grad_norm": 0.15866073966026306,
|
| 17011 |
+
"learning_rate": 4.539295392953929e-05,
|
| 17012 |
+
"loss": 2.5344109535217285,
|
| 17013 |
+
"step": 4858
|
| 17014 |
+
},
|
| 17015 |
+
{
|
| 17016 |
+
"epoch": 0.9484314777772357,
|
| 17017 |
+
"grad_norm": 0.18805697560310364,
|
| 17018 |
+
"learning_rate": 4.5054200542005425e-05,
|
| 17019 |
+
"loss": 2.554793357849121,
|
| 17020 |
+
"step": 4860
|
| 17021 |
+
},
|
| 17022 |
+
{
|
| 17023 |
+
"epoch": 0.9488217787968971,
|
| 17024 |
+
"grad_norm": 0.18908806145191193,
|
| 17025 |
+
"learning_rate": 4.4715447154471546e-05,
|
| 17026 |
+
"loss": 2.597529172897339,
|
| 17027 |
+
"step": 4862
|
| 17028 |
+
},
|
| 17029 |
+
{
|
| 17030 |
+
"epoch": 0.9492120798165585,
|
| 17031 |
+
"grad_norm": 0.17313823103904724,
|
| 17032 |
+
"learning_rate": 4.437669376693767e-05,
|
| 17033 |
+
"loss": 2.589522361755371,
|
| 17034 |
+
"step": 4864
|
| 17035 |
+
},
|
| 17036 |
+
{
|
| 17037 |
+
"epoch": 0.94960238083622,
|
| 17038 |
+
"grad_norm": 0.1789850890636444,
|
| 17039 |
+
"learning_rate": 4.4037940379403794e-05,
|
| 17040 |
+
"loss": 2.5667901039123535,
|
| 17041 |
+
"step": 4866
|
| 17042 |
+
},
|
| 17043 |
+
{
|
| 17044 |
+
"epoch": 0.9499926818558814,
|
| 17045 |
+
"grad_norm": 0.16788390278816223,
|
| 17046 |
+
"learning_rate": 4.369918699186992e-05,
|
| 17047 |
+
"loss": 2.5835652351379395,
|
| 17048 |
+
"step": 4868
|
| 17049 |
+
},
|
| 17050 |
+
{
|
| 17051 |
+
"epoch": 0.9503829828755428,
|
| 17052 |
+
"grad_norm": 0.29421135783195496,
|
| 17053 |
+
"learning_rate": 4.336043360433604e-05,
|
| 17054 |
+
"loss": 2.593390703201294,
|
| 17055 |
+
"step": 4870
|
| 17056 |
+
},
|
| 17057 |
+
{
|
| 17058 |
+
"epoch": 0.9507732838952042,
|
| 17059 |
+
"grad_norm": 0.1868540495634079,
|
| 17060 |
+
"learning_rate": 4.302168021680217e-05,
|
| 17061 |
+
"loss": 2.5259900093078613,
|
| 17062 |
+
"step": 4872
|
| 17063 |
+
},
|
| 17064 |
+
{
|
| 17065 |
+
"epoch": 0.9511635849148656,
|
| 17066 |
+
"grad_norm": 0.16197246313095093,
|
| 17067 |
+
"learning_rate": 4.26829268292683e-05,
|
| 17068 |
+
"loss": 2.5334649085998535,
|
| 17069 |
+
"step": 4874
|
| 17070 |
+
},
|
| 17071 |
+
{
|
| 17072 |
+
"epoch": 0.951553885934527,
|
| 17073 |
+
"grad_norm": 0.13944344222545624,
|
| 17074 |
+
"learning_rate": 4.234417344173442e-05,
|
| 17075 |
+
"loss": 2.580684185028076,
|
| 17076 |
+
"step": 4876
|
| 17077 |
+
},
|
| 17078 |
+
{
|
| 17079 |
+
"epoch": 0.9519441869541884,
|
| 17080 |
+
"grad_norm": 0.21285387873649597,
|
| 17081 |
+
"learning_rate": 4.2005420054200545e-05,
|
| 17082 |
+
"loss": 2.5619115829467773,
|
| 17083 |
+
"step": 4878
|
| 17084 |
+
},
|
| 17085 |
+
{
|
| 17086 |
+
"epoch": 0.9523344879738498,
|
| 17087 |
+
"grad_norm": 0.16594146192073822,
|
| 17088 |
+
"learning_rate": 4.1666666666666665e-05,
|
| 17089 |
+
"loss": 2.5315935611724854,
|
| 17090 |
+
"step": 4880
|
| 17091 |
+
},
|
| 17092 |
+
{
|
| 17093 |
+
"epoch": 0.9527247889935112,
|
| 17094 |
+
"grad_norm": 0.14595693349838257,
|
| 17095 |
+
"learning_rate": 4.132791327913279e-05,
|
| 17096 |
+
"loss": 2.611408233642578,
|
| 17097 |
+
"step": 4882
|
| 17098 |
+
},
|
| 17099 |
+
{
|
| 17100 |
+
"epoch": 0.9531150900131726,
|
| 17101 |
+
"grad_norm": 0.17948345839977264,
|
| 17102 |
+
"learning_rate": 4.098915989159892e-05,
|
| 17103 |
+
"loss": 2.6048150062561035,
|
| 17104 |
+
"step": 4884
|
| 17105 |
+
},
|
| 17106 |
+
{
|
| 17107 |
+
"epoch": 0.953505391032834,
|
| 17108 |
+
"grad_norm": 0.20561298727989197,
|
| 17109 |
+
"learning_rate": 4.065040650406504e-05,
|
| 17110 |
+
"loss": 2.6310954093933105,
|
| 17111 |
+
"step": 4886
|
| 17112 |
+
},
|
| 17113 |
+
{
|
| 17114 |
+
"epoch": 0.9538956920524955,
|
| 17115 |
+
"grad_norm": 0.1696900576353073,
|
| 17116 |
+
"learning_rate": 4.031165311653116e-05,
|
| 17117 |
+
"loss": 2.549074649810791,
|
| 17118 |
+
"step": 4888
|
| 17119 |
+
},
|
| 17120 |
+
{
|
| 17121 |
+
"epoch": 0.9542859930721569,
|
| 17122 |
+
"grad_norm": 0.22045093774795532,
|
| 17123 |
+
"learning_rate": 3.9972899728997295e-05,
|
| 17124 |
+
"loss": 2.592576503753662,
|
| 17125 |
+
"step": 4890
|
| 17126 |
+
},
|
| 17127 |
+
{
|
| 17128 |
+
"epoch": 0.9546762940918183,
|
| 17129 |
+
"grad_norm": 0.16594217717647552,
|
| 17130 |
+
"learning_rate": 3.9634146341463416e-05,
|
| 17131 |
+
"loss": 2.5946779251098633,
|
| 17132 |
+
"step": 4892
|
| 17133 |
+
},
|
| 17134 |
+
{
|
| 17135 |
+
"epoch": 0.9550665951114797,
|
| 17136 |
+
"grad_norm": 0.15289542078971863,
|
| 17137 |
+
"learning_rate": 3.9295392953929537e-05,
|
| 17138 |
+
"loss": 2.5887444019317627,
|
| 17139 |
+
"step": 4894
|
| 17140 |
+
},
|
| 17141 |
+
{
|
| 17142 |
+
"epoch": 0.9554568961311412,
|
| 17143 |
+
"grad_norm": 0.15567757189273834,
|
| 17144 |
+
"learning_rate": 3.8956639566395664e-05,
|
| 17145 |
+
"loss": 2.600339412689209,
|
| 17146 |
+
"step": 4896
|
| 17147 |
+
},
|
| 17148 |
+
{
|
| 17149 |
+
"epoch": 0.9558471971508026,
|
| 17150 |
+
"grad_norm": 0.2143499106168747,
|
| 17151 |
+
"learning_rate": 3.861788617886179e-05,
|
| 17152 |
+
"loss": 2.5576634407043457,
|
| 17153 |
+
"step": 4898
|
| 17154 |
+
},
|
| 17155 |
+
{
|
| 17156 |
+
"epoch": 0.956237498170464,
|
| 17157 |
+
"grad_norm": 0.14033572375774384,
|
| 17158 |
+
"learning_rate": 3.827913279132791e-05,
|
| 17159 |
+
"loss": 2.60825777053833,
|
| 17160 |
+
"step": 4900
|
| 17161 |
+
},
|
| 17162 |
+
{
|
| 17163 |
+
"epoch": 0.9566277991901254,
|
| 17164 |
+
"grad_norm": 0.19166924059391022,
|
| 17165 |
+
"learning_rate": 3.794037940379404e-05,
|
| 17166 |
+
"loss": 2.551809310913086,
|
| 17167 |
+
"step": 4902
|
| 17168 |
+
},
|
| 17169 |
+
{
|
| 17170 |
+
"epoch": 0.9570181002097868,
|
| 17171 |
+
"grad_norm": 0.22014275193214417,
|
| 17172 |
+
"learning_rate": 3.760162601626017e-05,
|
| 17173 |
+
"loss": 2.5368428230285645,
|
| 17174 |
+
"step": 4904
|
| 17175 |
+
},
|
| 17176 |
+
{
|
| 17177 |
+
"epoch": 0.9574084012294483,
|
| 17178 |
+
"grad_norm": 0.15895509719848633,
|
| 17179 |
+
"learning_rate": 3.726287262872629e-05,
|
| 17180 |
+
"loss": 2.580507278442383,
|
| 17181 |
+
"step": 4906
|
| 17182 |
+
},
|
| 17183 |
+
{
|
| 17184 |
+
"epoch": 0.9577987022491097,
|
| 17185 |
+
"grad_norm": 0.15019026398658752,
|
| 17186 |
+
"learning_rate": 3.6924119241192415e-05,
|
| 17187 |
+
"loss": 2.5479543209075928,
|
| 17188 |
+
"step": 4908
|
| 17189 |
+
},
|
| 17190 |
+
{
|
| 17191 |
+
"epoch": 0.958189003268771,
|
| 17192 |
+
"grad_norm": 0.15676747262477875,
|
| 17193 |
+
"learning_rate": 3.6585365853658535e-05,
|
| 17194 |
+
"loss": 2.6061673164367676,
|
| 17195 |
+
"step": 4910
|
| 17196 |
+
},
|
| 17197 |
+
{
|
| 17198 |
+
"epoch": 0.9585793042884324,
|
| 17199 |
+
"grad_norm": 0.1433609277009964,
|
| 17200 |
+
"learning_rate": 3.624661246612466e-05,
|
| 17201 |
+
"loss": 2.589252471923828,
|
| 17202 |
+
"step": 4912
|
| 17203 |
+
},
|
| 17204 |
+
{
|
| 17205 |
+
"epoch": 0.9589696053080938,
|
| 17206 |
+
"grad_norm": 0.16273698210716248,
|
| 17207 |
+
"learning_rate": 3.590785907859079e-05,
|
| 17208 |
+
"loss": 2.6341400146484375,
|
| 17209 |
+
"step": 4914
|
| 17210 |
+
},
|
| 17211 |
+
{
|
| 17212 |
+
"epoch": 0.9593599063277553,
|
| 17213 |
+
"grad_norm": 0.23153796792030334,
|
| 17214 |
+
"learning_rate": 3.556910569105691e-05,
|
| 17215 |
+
"loss": 2.5165722370147705,
|
| 17216 |
+
"step": 4916
|
| 17217 |
+
},
|
| 17218 |
+
{
|
| 17219 |
+
"epoch": 0.9597502073474167,
|
| 17220 |
+
"grad_norm": 0.2124078869819641,
|
| 17221 |
+
"learning_rate": 3.523035230352303e-05,
|
| 17222 |
+
"loss": 2.5734310150146484,
|
| 17223 |
+
"step": 4918
|
| 17224 |
+
},
|
| 17225 |
+
{
|
| 17226 |
+
"epoch": 0.9601405083670781,
|
| 17227 |
+
"grad_norm": 0.14259904623031616,
|
| 17228 |
+
"learning_rate": 3.4891598915989165e-05,
|
| 17229 |
+
"loss": 2.58728289604187,
|
| 17230 |
+
"step": 4920
|
| 17231 |
+
},
|
| 17232 |
+
{
|
| 17233 |
+
"epoch": 0.9605308093867395,
|
| 17234 |
+
"grad_norm": 0.15181533992290497,
|
| 17235 |
+
"learning_rate": 3.4552845528455286e-05,
|
| 17236 |
+
"loss": 2.626335620880127,
|
| 17237 |
+
"step": 4922
|
| 17238 |
+
},
|
| 17239 |
+
{
|
| 17240 |
+
"epoch": 0.9609211104064009,
|
| 17241 |
+
"grad_norm": 0.17763164639472961,
|
| 17242 |
+
"learning_rate": 3.4214092140921406e-05,
|
| 17243 |
+
"loss": 2.57848858833313,
|
| 17244 |
+
"step": 4924
|
| 17245 |
+
},
|
| 17246 |
+
{
|
| 17247 |
+
"epoch": 0.9613114114260624,
|
| 17248 |
+
"grad_norm": 0.14168651401996613,
|
| 17249 |
+
"learning_rate": 3.3875338753387534e-05,
|
| 17250 |
+
"loss": 2.562469482421875,
|
| 17251 |
+
"step": 4926
|
| 17252 |
+
},
|
| 17253 |
+
{
|
| 17254 |
+
"epoch": 0.9617017124457238,
|
| 17255 |
+
"grad_norm": 0.12468063831329346,
|
| 17256 |
+
"learning_rate": 3.353658536585366e-05,
|
| 17257 |
+
"loss": 2.5426790714263916,
|
| 17258 |
+
"step": 4928
|
| 17259 |
+
},
|
| 17260 |
+
{
|
| 17261 |
+
"epoch": 0.9620920134653852,
|
| 17262 |
+
"grad_norm": 0.18018177151679993,
|
| 17263 |
+
"learning_rate": 3.319783197831978e-05,
|
| 17264 |
+
"loss": 2.582167148590088,
|
| 17265 |
+
"step": 4930
|
| 17266 |
+
},
|
| 17267 |
+
{
|
| 17268 |
+
"epoch": 0.9624823144850466,
|
| 17269 |
+
"grad_norm": 0.19353936612606049,
|
| 17270 |
+
"learning_rate": 3.285907859078591e-05,
|
| 17271 |
+
"loss": 2.4774746894836426,
|
| 17272 |
+
"step": 4932
|
| 17273 |
+
},
|
| 17274 |
+
{
|
| 17275 |
+
"epoch": 0.962872615504708,
|
| 17276 |
+
"grad_norm": 0.16525185108184814,
|
| 17277 |
+
"learning_rate": 3.2520325203252037e-05,
|
| 17278 |
+
"loss": 2.5844781398773193,
|
| 17279 |
+
"step": 4934
|
| 17280 |
+
},
|
| 17281 |
+
{
|
| 17282 |
+
"epoch": 0.9632629165243695,
|
| 17283 |
+
"grad_norm": 0.189486563205719,
|
| 17284 |
+
"learning_rate": 3.218157181571816e-05,
|
| 17285 |
+
"loss": 2.5854885578155518,
|
| 17286 |
+
"step": 4936
|
| 17287 |
+
},
|
| 17288 |
+
{
|
| 17289 |
+
"epoch": 0.9636532175440309,
|
| 17290 |
+
"grad_norm": 0.16245070099830627,
|
| 17291 |
+
"learning_rate": 3.1842818428184285e-05,
|
| 17292 |
+
"loss": 2.574592113494873,
|
| 17293 |
+
"step": 4938
|
| 17294 |
+
},
|
| 17295 |
+
{
|
| 17296 |
+
"epoch": 0.9640435185636922,
|
| 17297 |
+
"grad_norm": 0.19609013199806213,
|
| 17298 |
+
"learning_rate": 3.1504065040650405e-05,
|
| 17299 |
+
"loss": 2.5558524131774902,
|
| 17300 |
+
"step": 4940
|
| 17301 |
+
},
|
| 17302 |
+
{
|
| 17303 |
+
"epoch": 0.9644338195833536,
|
| 17304 |
+
"grad_norm": 0.18833185732364655,
|
| 17305 |
+
"learning_rate": 3.116531165311653e-05,
|
| 17306 |
+
"loss": 2.5779995918273926,
|
| 17307 |
+
"step": 4942
|
| 17308 |
+
},
|
| 17309 |
+
{
|
| 17310 |
+
"epoch": 0.964824120603015,
|
| 17311 |
+
"grad_norm": 0.1414237767457962,
|
| 17312 |
+
"learning_rate": 3.082655826558266e-05,
|
| 17313 |
+
"loss": 2.5434627532958984,
|
| 17314 |
+
"step": 4944
|
| 17315 |
+
},
|
| 17316 |
+
{
|
| 17317 |
+
"epoch": 0.9652144216226765,
|
| 17318 |
+
"grad_norm": 0.16449035704135895,
|
| 17319 |
+
"learning_rate": 3.048780487804878e-05,
|
| 17320 |
+
"loss": 2.58113956451416,
|
| 17321 |
+
"step": 4946
|
| 17322 |
+
},
|
| 17323 |
+
{
|
| 17324 |
+
"epoch": 0.9656047226423379,
|
| 17325 |
+
"grad_norm": 0.14490605890750885,
|
| 17326 |
+
"learning_rate": 3.0149051490514908e-05,
|
| 17327 |
+
"loss": 2.5862481594085693,
|
| 17328 |
+
"step": 4948
|
| 17329 |
+
},
|
| 17330 |
+
{
|
| 17331 |
+
"epoch": 0.9659950236619993,
|
| 17332 |
+
"grad_norm": 0.16666492819786072,
|
| 17333 |
+
"learning_rate": 2.981029810298103e-05,
|
| 17334 |
+
"loss": 2.571815013885498,
|
| 17335 |
+
"step": 4950
|
| 17336 |
+
},
|
| 17337 |
+
{
|
| 17338 |
+
"epoch": 0.9663853246816607,
|
| 17339 |
+
"grad_norm": 0.17023544013500214,
|
| 17340 |
+
"learning_rate": 2.9471544715447156e-05,
|
| 17341 |
+
"loss": 2.5660228729248047,
|
| 17342 |
+
"step": 4952
|
| 17343 |
+
},
|
| 17344 |
+
{
|
| 17345 |
+
"epoch": 0.9667756257013221,
|
| 17346 |
+
"grad_norm": 0.15035828948020935,
|
| 17347 |
+
"learning_rate": 2.913279132791328e-05,
|
| 17348 |
+
"loss": 2.575751781463623,
|
| 17349 |
+
"step": 4954
|
| 17350 |
+
},
|
| 17351 |
+
{
|
| 17352 |
+
"epoch": 0.9671659267209836,
|
| 17353 |
+
"grad_norm": 0.22045069932937622,
|
| 17354 |
+
"learning_rate": 2.8794037940379404e-05,
|
| 17355 |
+
"loss": 2.4977893829345703,
|
| 17356 |
+
"step": 4956
|
| 17357 |
+
},
|
| 17358 |
+
{
|
| 17359 |
+
"epoch": 0.967556227740645,
|
| 17360 |
+
"grad_norm": 0.16292375326156616,
|
| 17361 |
+
"learning_rate": 2.8455284552845528e-05,
|
| 17362 |
+
"loss": 2.5806493759155273,
|
| 17363 |
+
"step": 4958
|
| 17364 |
+
},
|
| 17365 |
+
{
|
| 17366 |
+
"epoch": 0.9679465287603064,
|
| 17367 |
+
"grad_norm": 0.17287801206111908,
|
| 17368 |
+
"learning_rate": 2.8116531165311655e-05,
|
| 17369 |
+
"loss": 2.5709176063537598,
|
| 17370 |
+
"step": 4960
|
| 17371 |
+
},
|
| 17372 |
+
{
|
| 17373 |
+
"epoch": 0.9683368297799678,
|
| 17374 |
+
"grad_norm": 0.19513541460037231,
|
| 17375 |
+
"learning_rate": 2.7777777777777776e-05,
|
| 17376 |
+
"loss": 2.5926332473754883,
|
| 17377 |
+
"step": 4962
|
| 17378 |
+
},
|
| 17379 |
+
{
|
| 17380 |
+
"epoch": 0.9687271307996292,
|
| 17381 |
+
"grad_norm": 0.1306929737329483,
|
| 17382 |
+
"learning_rate": 2.7439024390243903e-05,
|
| 17383 |
+
"loss": 2.5636510848999023,
|
| 17384 |
+
"step": 4964
|
| 17385 |
+
},
|
| 17386 |
+
{
|
| 17387 |
+
"epoch": 0.9691174318192907,
|
| 17388 |
+
"grad_norm": 0.14540204405784607,
|
| 17389 |
+
"learning_rate": 2.710027100271003e-05,
|
| 17390 |
+
"loss": 2.5999629497528076,
|
| 17391 |
+
"step": 4966
|
| 17392 |
+
},
|
| 17393 |
+
{
|
| 17394 |
+
"epoch": 0.9695077328389521,
|
| 17395 |
+
"grad_norm": 0.15513111650943756,
|
| 17396 |
+
"learning_rate": 2.676151761517615e-05,
|
| 17397 |
+
"loss": 2.54514217376709,
|
| 17398 |
+
"step": 4968
|
| 17399 |
+
},
|
| 17400 |
+
{
|
| 17401 |
+
"epoch": 0.9698980338586135,
|
| 17402 |
+
"grad_norm": 0.17834393680095673,
|
| 17403 |
+
"learning_rate": 2.642276422764228e-05,
|
| 17404 |
+
"loss": 2.5647592544555664,
|
| 17405 |
+
"step": 4970
|
| 17406 |
+
},
|
| 17407 |
+
{
|
| 17408 |
+
"epoch": 0.9702883348782748,
|
| 17409 |
+
"grad_norm": 0.17628046870231628,
|
| 17410 |
+
"learning_rate": 2.6084010840108402e-05,
|
| 17411 |
+
"loss": 2.5286927223205566,
|
| 17412 |
+
"step": 4972
|
| 17413 |
+
},
|
| 17414 |
+
{
|
| 17415 |
+
"epoch": 0.9706786358979362,
|
| 17416 |
+
"grad_norm": 0.14456549286842346,
|
| 17417 |
+
"learning_rate": 2.5745257452574526e-05,
|
| 17418 |
+
"loss": 2.597411870956421,
|
| 17419 |
+
"step": 4974
|
| 17420 |
+
},
|
| 17421 |
+
{
|
| 17422 |
+
"epoch": 0.9710689369175977,
|
| 17423 |
+
"grad_norm": 0.14736810326576233,
|
| 17424 |
+
"learning_rate": 2.540650406504065e-05,
|
| 17425 |
+
"loss": 2.5691375732421875,
|
| 17426 |
+
"step": 4976
|
| 17427 |
+
},
|
| 17428 |
+
{
|
| 17429 |
+
"epoch": 0.9714592379372591,
|
| 17430 |
+
"grad_norm": 0.1905648112297058,
|
| 17431 |
+
"learning_rate": 2.5067750677506778e-05,
|
| 17432 |
+
"loss": 2.64494252204895,
|
| 17433 |
+
"step": 4978
|
| 17434 |
+
},
|
| 17435 |
+
{
|
| 17436 |
+
"epoch": 0.9718495389569205,
|
| 17437 |
+
"grad_norm": 0.19548925757408142,
|
| 17438 |
+
"learning_rate": 2.47289972899729e-05,
|
| 17439 |
+
"loss": 2.5649099349975586,
|
| 17440 |
+
"step": 4980
|
| 17441 |
+
},
|
| 17442 |
+
{
|
| 17443 |
+
"epoch": 0.9722398399765819,
|
| 17444 |
+
"grad_norm": 0.1377575844526291,
|
| 17445 |
+
"learning_rate": 2.4390243902439026e-05,
|
| 17446 |
+
"loss": 2.614043712615967,
|
| 17447 |
+
"step": 4982
|
| 17448 |
+
},
|
| 17449 |
+
{
|
| 17450 |
+
"epoch": 0.9726301409962433,
|
| 17451 |
+
"grad_norm": 0.16652578115463257,
|
| 17452 |
+
"learning_rate": 2.405149051490515e-05,
|
| 17453 |
+
"loss": 2.613285541534424,
|
| 17454 |
+
"step": 4984
|
| 17455 |
+
},
|
| 17456 |
+
{
|
| 17457 |
+
"epoch": 0.9730204420159048,
|
| 17458 |
+
"grad_norm": 0.14840146899223328,
|
| 17459 |
+
"learning_rate": 2.3712737127371274e-05,
|
| 17460 |
+
"loss": 2.555727005004883,
|
| 17461 |
+
"step": 4986
|
| 17462 |
+
},
|
| 17463 |
+
{
|
| 17464 |
+
"epoch": 0.9734107430355662,
|
| 17465 |
+
"grad_norm": 0.157876119017601,
|
| 17466 |
+
"learning_rate": 2.3373983739837398e-05,
|
| 17467 |
+
"loss": 2.5705251693725586,
|
| 17468 |
+
"step": 4988
|
| 17469 |
+
},
|
| 17470 |
+
{
|
| 17471 |
+
"epoch": 0.9738010440552276,
|
| 17472 |
+
"grad_norm": 0.15810854732990265,
|
| 17473 |
+
"learning_rate": 2.3035230352303525e-05,
|
| 17474 |
+
"loss": 2.610093832015991,
|
| 17475 |
+
"step": 4990
|
| 17476 |
+
},
|
| 17477 |
+
{
|
| 17478 |
+
"epoch": 0.974191345074889,
|
| 17479 |
+
"grad_norm": 0.16577023267745972,
|
| 17480 |
+
"learning_rate": 2.2696476964769646e-05,
|
| 17481 |
+
"loss": 2.6076619625091553,
|
| 17482 |
+
"step": 4992
|
| 17483 |
+
},
|
| 17484 |
+
{
|
| 17485 |
+
"epoch": 0.9745816460945504,
|
| 17486 |
+
"grad_norm": 0.13530617952346802,
|
| 17487 |
+
"learning_rate": 2.2357723577235773e-05,
|
| 17488 |
+
"loss": 2.51572322845459,
|
| 17489 |
+
"step": 4994
|
| 17490 |
+
},
|
| 17491 |
+
{
|
| 17492 |
+
"epoch": 0.9749719471142119,
|
| 17493 |
+
"grad_norm": 0.21427880227565765,
|
| 17494 |
+
"learning_rate": 2.2018970189701897e-05,
|
| 17495 |
+
"loss": 2.5873918533325195,
|
| 17496 |
+
"step": 4996
|
| 17497 |
+
},
|
| 17498 |
+
{
|
| 17499 |
+
"epoch": 0.9753622481338733,
|
| 17500 |
+
"grad_norm": 0.21905489265918732,
|
| 17501 |
+
"learning_rate": 2.168021680216802e-05,
|
| 17502 |
+
"loss": 2.6120481491088867,
|
| 17503 |
+
"step": 4998
|
| 17504 |
+
},
|
| 17505 |
+
{
|
| 17506 |
+
"epoch": 0.9757525491535347,
|
| 17507 |
+
"grad_norm": 0.17322804033756256,
|
| 17508 |
+
"learning_rate": 2.134146341463415e-05,
|
| 17509 |
+
"loss": 2.6308951377868652,
|
| 17510 |
+
"step": 5000
|
| 17511 |
+
},
|
| 17512 |
+
{
|
| 17513 |
+
"epoch": 0.9761428501731961,
|
| 17514 |
+
"grad_norm": 0.13365858793258667,
|
| 17515 |
+
"learning_rate": 2.1002710027100272e-05,
|
| 17516 |
+
"loss": 2.6267309188842773,
|
| 17517 |
+
"step": 5002
|
| 17518 |
+
},
|
| 17519 |
+
{
|
| 17520 |
+
"epoch": 0.9765331511928574,
|
| 17521 |
+
"grad_norm": 0.16150684654712677,
|
| 17522 |
+
"learning_rate": 2.0663956639566396e-05,
|
| 17523 |
+
"loss": 2.512974262237549,
|
| 17524 |
+
"step": 5004
|
| 17525 |
+
},
|
| 17526 |
+
{
|
| 17527 |
+
"epoch": 0.9769234522125189,
|
| 17528 |
+
"grad_norm": 0.16009357571601868,
|
| 17529 |
+
"learning_rate": 2.032520325203252e-05,
|
| 17530 |
+
"loss": 2.5780484676361084,
|
| 17531 |
+
"step": 5006
|
| 17532 |
+
},
|
| 17533 |
+
{
|
| 17534 |
+
"epoch": 0.9773137532321803,
|
| 17535 |
+
"grad_norm": 0.1807524561882019,
|
| 17536 |
+
"learning_rate": 1.9986449864498648e-05,
|
| 17537 |
+
"loss": 2.5390701293945312,
|
| 17538 |
+
"step": 5008
|
| 17539 |
+
},
|
| 17540 |
+
{
|
| 17541 |
+
"epoch": 0.9777040542518417,
|
| 17542 |
+
"grad_norm": 0.23311179876327515,
|
| 17543 |
+
"learning_rate": 1.9647696476964768e-05,
|
| 17544 |
+
"loss": 2.5898184776306152,
|
| 17545 |
+
"step": 5010
|
| 17546 |
+
},
|
| 17547 |
+
{
|
| 17548 |
+
"epoch": 0.9780943552715031,
|
| 17549 |
+
"grad_norm": 0.16348180174827576,
|
| 17550 |
+
"learning_rate": 1.9308943089430896e-05,
|
| 17551 |
+
"loss": 2.563554525375366,
|
| 17552 |
+
"step": 5012
|
| 17553 |
+
},
|
| 17554 |
+
{
|
| 17555 |
+
"epoch": 0.9784846562911645,
|
| 17556 |
+
"grad_norm": 0.17406176030635834,
|
| 17557 |
+
"learning_rate": 1.897018970189702e-05,
|
| 17558 |
+
"loss": 2.5800747871398926,
|
| 17559 |
+
"step": 5014
|
| 17560 |
+
},
|
| 17561 |
+
{
|
| 17562 |
+
"epoch": 0.978874957310826,
|
| 17563 |
+
"grad_norm": 0.15913774073123932,
|
| 17564 |
+
"learning_rate": 1.8631436314363144e-05,
|
| 17565 |
+
"loss": 2.5959348678588867,
|
| 17566 |
+
"step": 5016
|
| 17567 |
+
},
|
| 17568 |
+
{
|
| 17569 |
+
"epoch": 0.9792652583304874,
|
| 17570 |
+
"grad_norm": 0.1931382715702057,
|
| 17571 |
+
"learning_rate": 1.8292682926829268e-05,
|
| 17572 |
+
"loss": 2.571011781692505,
|
| 17573 |
+
"step": 5018
|
| 17574 |
+
},
|
| 17575 |
+
{
|
| 17576 |
+
"epoch": 0.9796555593501488,
|
| 17577 |
+
"grad_norm": 0.15889587998390198,
|
| 17578 |
+
"learning_rate": 1.7953929539295395e-05,
|
| 17579 |
+
"loss": 2.5408077239990234,
|
| 17580 |
+
"step": 5020
|
| 17581 |
+
},
|
| 17582 |
+
{
|
| 17583 |
+
"epoch": 0.9800458603698102,
|
| 17584 |
+
"grad_norm": 0.19335567951202393,
|
| 17585 |
+
"learning_rate": 1.7615176151761516e-05,
|
| 17586 |
+
"loss": 2.5995779037475586,
|
| 17587 |
+
"step": 5022
|
| 17588 |
+
},
|
| 17589 |
+
{
|
| 17590 |
+
"epoch": 0.9804361613894716,
|
| 17591 |
+
"grad_norm": 0.14959239959716797,
|
| 17592 |
+
"learning_rate": 1.7276422764227643e-05,
|
| 17593 |
+
"loss": 2.537475109100342,
|
| 17594 |
+
"step": 5024
|
| 17595 |
+
},
|
| 17596 |
+
{
|
| 17597 |
+
"epoch": 0.9808264624091331,
|
| 17598 |
+
"grad_norm": 0.1398703008890152,
|
| 17599 |
+
"learning_rate": 1.6937669376693767e-05,
|
| 17600 |
+
"loss": 2.5391650199890137,
|
| 17601 |
+
"step": 5026
|
| 17602 |
+
},
|
| 17603 |
+
{
|
| 17604 |
+
"epoch": 0.9812167634287945,
|
| 17605 |
+
"grad_norm": 0.16997550427913666,
|
| 17606 |
+
"learning_rate": 1.659891598915989e-05,
|
| 17607 |
+
"loss": 2.5865190029144287,
|
| 17608 |
+
"step": 5028
|
| 17609 |
+
},
|
| 17610 |
+
{
|
| 17611 |
+
"epoch": 0.9816070644484559,
|
| 17612 |
+
"grad_norm": 0.23041141033172607,
|
| 17613 |
+
"learning_rate": 1.6260162601626018e-05,
|
| 17614 |
+
"loss": 2.6241695880889893,
|
| 17615 |
+
"step": 5030
|
| 17616 |
+
},
|
| 17617 |
+
{
|
| 17618 |
+
"epoch": 0.9819973654681173,
|
| 17619 |
+
"grad_norm": 0.15086184442043304,
|
| 17620 |
+
"learning_rate": 1.5921409214092142e-05,
|
| 17621 |
+
"loss": 2.5816216468811035,
|
| 17622 |
+
"step": 5032
|
| 17623 |
+
},
|
| 17624 |
+
{
|
| 17625 |
+
"epoch": 0.9823876664877788,
|
| 17626 |
+
"grad_norm": 0.16164544224739075,
|
| 17627 |
+
"learning_rate": 1.5582655826558266e-05,
|
| 17628 |
+
"loss": 2.534278392791748,
|
| 17629 |
+
"step": 5034
|
| 17630 |
+
},
|
| 17631 |
+
{
|
| 17632 |
+
"epoch": 0.9827779675074401,
|
| 17633 |
+
"grad_norm": 0.19758284091949463,
|
| 17634 |
+
"learning_rate": 1.524390243902439e-05,
|
| 17635 |
+
"loss": 2.558823823928833,
|
| 17636 |
+
"step": 5036
|
| 17637 |
+
},
|
| 17638 |
+
{
|
| 17639 |
+
"epoch": 0.9831682685271015,
|
| 17640 |
+
"grad_norm": 0.1831168383359909,
|
| 17641 |
+
"learning_rate": 1.4905149051490514e-05,
|
| 17642 |
+
"loss": 2.6115078926086426,
|
| 17643 |
+
"step": 5038
|
| 17644 |
+
},
|
| 17645 |
+
{
|
| 17646 |
+
"epoch": 0.9835585695467629,
|
| 17647 |
+
"grad_norm": 0.13932181894779205,
|
| 17648 |
+
"learning_rate": 1.456639566395664e-05,
|
| 17649 |
+
"loss": 2.5520267486572266,
|
| 17650 |
+
"step": 5040
|
| 17651 |
+
},
|
| 17652 |
+
{
|
| 17653 |
+
"epoch": 0.9839488705664243,
|
| 17654 |
+
"grad_norm": 0.14670678973197937,
|
| 17655 |
+
"learning_rate": 1.4227642276422764e-05,
|
| 17656 |
+
"loss": 2.576571464538574,
|
| 17657 |
+
"step": 5042
|
| 17658 |
+
},
|
| 17659 |
+
{
|
| 17660 |
+
"epoch": 0.9843391715860857,
|
| 17661 |
+
"grad_norm": 0.22335804998874664,
|
| 17662 |
+
"learning_rate": 1.3888888888888888e-05,
|
| 17663 |
+
"loss": 2.5275158882141113,
|
| 17664 |
+
"step": 5044
|
| 17665 |
+
},
|
| 17666 |
+
{
|
| 17667 |
+
"epoch": 0.9847294726057472,
|
| 17668 |
+
"grad_norm": 0.14851082861423492,
|
| 17669 |
+
"learning_rate": 1.3550135501355015e-05,
|
| 17670 |
+
"loss": 2.588679790496826,
|
| 17671 |
+
"step": 5046
|
| 17672 |
+
},
|
| 17673 |
+
{
|
| 17674 |
+
"epoch": 0.9851197736254086,
|
| 17675 |
+
"grad_norm": 0.1559106409549713,
|
| 17676 |
+
"learning_rate": 1.321138211382114e-05,
|
| 17677 |
+
"loss": 2.600008964538574,
|
| 17678 |
+
"step": 5048
|
| 17679 |
+
},
|
| 17680 |
+
{
|
| 17681 |
+
"epoch": 0.98551007464507,
|
| 17682 |
+
"grad_norm": 0.17948253452777863,
|
| 17683 |
+
"learning_rate": 1.2872628726287263e-05,
|
| 17684 |
+
"loss": 2.5887107849121094,
|
| 17685 |
+
"step": 5050
|
| 17686 |
+
},
|
| 17687 |
+
{
|
| 17688 |
+
"epoch": 0.9859003756647314,
|
| 17689 |
+
"grad_norm": 0.19872087240219116,
|
| 17690 |
+
"learning_rate": 1.2533875338753389e-05,
|
| 17691 |
+
"loss": 2.6023573875427246,
|
| 17692 |
+
"step": 5052
|
| 17693 |
+
},
|
| 17694 |
+
{
|
| 17695 |
+
"epoch": 0.9862906766843929,
|
| 17696 |
+
"grad_norm": 0.16350743174552917,
|
| 17697 |
+
"learning_rate": 1.2195121951219513e-05,
|
| 17698 |
+
"loss": 2.623094081878662,
|
| 17699 |
+
"step": 5054
|
| 17700 |
+
},
|
| 17701 |
+
{
|
| 17702 |
+
"epoch": 0.9866809777040543,
|
| 17703 |
+
"grad_norm": 0.19693568348884583,
|
| 17704 |
+
"learning_rate": 1.1856368563685637e-05,
|
| 17705 |
+
"loss": 2.6325011253356934,
|
| 17706 |
+
"step": 5056
|
| 17707 |
+
},
|
| 17708 |
+
{
|
| 17709 |
+
"epoch": 0.9870712787237157,
|
| 17710 |
+
"grad_norm": 0.22773385047912598,
|
| 17711 |
+
"learning_rate": 1.1517615176151763e-05,
|
| 17712 |
+
"loss": 2.532865524291992,
|
| 17713 |
+
"step": 5058
|
| 17714 |
+
},
|
| 17715 |
+
{
|
| 17716 |
+
"epoch": 0.9874615797433771,
|
| 17717 |
+
"grad_norm": 0.15598197281360626,
|
| 17718 |
+
"learning_rate": 1.1178861788617887e-05,
|
| 17719 |
+
"loss": 2.5442066192626953,
|
| 17720 |
+
"step": 5060
|
| 17721 |
+
},
|
| 17722 |
+
{
|
| 17723 |
+
"epoch": 0.9878518807630385,
|
| 17724 |
+
"grad_norm": 0.13534830510616302,
|
| 17725 |
+
"learning_rate": 1.084010840108401e-05,
|
| 17726 |
+
"loss": 2.5364434719085693,
|
| 17727 |
+
"step": 5062
|
| 17728 |
+
},
|
| 17729 |
+
{
|
| 17730 |
+
"epoch": 0.9882421817827,
|
| 17731 |
+
"grad_norm": 0.18987397849559784,
|
| 17732 |
+
"learning_rate": 1.0501355013550136e-05,
|
| 17733 |
+
"loss": 2.6263599395751953,
|
| 17734 |
+
"step": 5064
|
| 17735 |
+
},
|
| 17736 |
+
{
|
| 17737 |
+
"epoch": 0.9886324828023613,
|
| 17738 |
+
"grad_norm": 0.17654915153980255,
|
| 17739 |
+
"learning_rate": 1.016260162601626e-05,
|
| 17740 |
+
"loss": 2.542428970336914,
|
| 17741 |
+
"step": 5066
|
| 17742 |
+
},
|
| 17743 |
+
{
|
| 17744 |
+
"epoch": 0.9890227838220227,
|
| 17745 |
+
"grad_norm": 0.16015943884849548,
|
| 17746 |
+
"learning_rate": 9.823848238482384e-06,
|
| 17747 |
+
"loss": 2.5899300575256348,
|
| 17748 |
+
"step": 5068
|
| 17749 |
+
},
|
| 17750 |
+
{
|
| 17751 |
+
"epoch": 0.9894130848416841,
|
| 17752 |
+
"grad_norm": 0.16919350624084473,
|
| 17753 |
+
"learning_rate": 9.48509485094851e-06,
|
| 17754 |
+
"loss": 2.590996026992798,
|
| 17755 |
+
"step": 5070
|
| 17756 |
+
},
|
| 17757 |
+
{
|
| 17758 |
+
"epoch": 0.9898033858613455,
|
| 17759 |
+
"grad_norm": 0.1706431657075882,
|
| 17760 |
+
"learning_rate": 9.146341463414634e-06,
|
| 17761 |
+
"loss": 2.5790464878082275,
|
| 17762 |
+
"step": 5072
|
| 17763 |
+
},
|
| 17764 |
+
{
|
| 17765 |
+
"epoch": 0.990193686881007,
|
| 17766 |
+
"grad_norm": 0.1716560423374176,
|
| 17767 |
+
"learning_rate": 8.807588075880758e-06,
|
| 17768 |
+
"loss": 2.5644493103027344,
|
| 17769 |
+
"step": 5074
|
| 17770 |
+
},
|
| 17771 |
+
{
|
| 17772 |
+
"epoch": 0.9905839879006684,
|
| 17773 |
+
"grad_norm": 0.19562166929244995,
|
| 17774 |
+
"learning_rate": 8.468834688346883e-06,
|
| 17775 |
+
"loss": 2.57351016998291,
|
| 17776 |
+
"step": 5076
|
| 17777 |
+
},
|
| 17778 |
+
{
|
| 17779 |
+
"epoch": 0.9909742889203298,
|
| 17780 |
+
"grad_norm": 0.21192876994609833,
|
| 17781 |
+
"learning_rate": 8.130081300813009e-06,
|
| 17782 |
+
"loss": 2.503335952758789,
|
| 17783 |
+
"step": 5078
|
| 17784 |
+
},
|
| 17785 |
+
{
|
| 17786 |
+
"epoch": 0.9913645899399912,
|
| 17787 |
+
"grad_norm": 0.15477780997753143,
|
| 17788 |
+
"learning_rate": 7.791327913279133e-06,
|
| 17789 |
+
"loss": 2.525804042816162,
|
| 17790 |
+
"step": 5080
|
| 17791 |
+
},
|
| 17792 |
+
{
|
| 17793 |
+
"epoch": 0.9917548909596526,
|
| 17794 |
+
"grad_norm": 0.1447765976190567,
|
| 17795 |
+
"learning_rate": 7.452574525745257e-06,
|
| 17796 |
+
"loss": 2.6027469635009766,
|
| 17797 |
+
"step": 5082
|
| 17798 |
+
},
|
| 17799 |
+
{
|
| 17800 |
+
"epoch": 0.9921451919793141,
|
| 17801 |
+
"grad_norm": 0.1933865249156952,
|
| 17802 |
+
"learning_rate": 7.113821138211382e-06,
|
| 17803 |
+
"loss": 2.551764488220215,
|
| 17804 |
+
"step": 5084
|
| 17805 |
+
},
|
| 17806 |
+
{
|
| 17807 |
+
"epoch": 0.9925354929989755,
|
| 17808 |
+
"grad_norm": 0.12649878859519958,
|
| 17809 |
+
"learning_rate": 6.775067750677508e-06,
|
| 17810 |
+
"loss": 2.5209808349609375,
|
| 17811 |
+
"step": 5086
|
| 17812 |
+
},
|
| 17813 |
+
{
|
| 17814 |
+
"epoch": 0.9929257940186369,
|
| 17815 |
+
"grad_norm": 0.20427054166793823,
|
| 17816 |
+
"learning_rate": 6.436314363143632e-06,
|
| 17817 |
+
"loss": 2.5445170402526855,
|
| 17818 |
+
"step": 5088
|
| 17819 |
+
},
|
| 17820 |
+
{
|
| 17821 |
+
"epoch": 0.9933160950382983,
|
| 17822 |
+
"grad_norm": 0.17093248665332794,
|
| 17823 |
+
"learning_rate": 6.0975609756097564e-06,
|
| 17824 |
+
"loss": 2.5537328720092773,
|
| 17825 |
+
"step": 5090
|
| 17826 |
+
},
|
| 17827 |
+
{
|
| 17828 |
+
"epoch": 0.9937063960579597,
|
| 17829 |
+
"grad_norm": 0.13963879644870758,
|
| 17830 |
+
"learning_rate": 5.758807588075881e-06,
|
| 17831 |
+
"loss": 2.592904567718506,
|
| 17832 |
+
"step": 5092
|
| 17833 |
+
},
|
| 17834 |
+
{
|
| 17835 |
+
"epoch": 0.9940966970776212,
|
| 17836 |
+
"grad_norm": 0.16705256700515747,
|
| 17837 |
+
"learning_rate": 5.420054200542005e-06,
|
| 17838 |
+
"loss": 2.599637031555176,
|
| 17839 |
+
"step": 5094
|
| 17840 |
+
},
|
| 17841 |
+
{
|
| 17842 |
+
"epoch": 0.9944869980972826,
|
| 17843 |
+
"grad_norm": 0.14347223937511444,
|
| 17844 |
+
"learning_rate": 5.08130081300813e-06,
|
| 17845 |
+
"loss": 2.5402767658233643,
|
| 17846 |
+
"step": 5096
|
| 17847 |
+
},
|
| 17848 |
+
{
|
| 17849 |
+
"epoch": 0.9948772991169439,
|
| 17850 |
+
"grad_norm": 0.17874565720558167,
|
| 17851 |
+
"learning_rate": 4.742547425474255e-06,
|
| 17852 |
+
"loss": 2.5734915733337402,
|
| 17853 |
+
"step": 5098
|
| 17854 |
+
},
|
| 17855 |
+
{
|
| 17856 |
+
"epoch": 0.9952676001366053,
|
| 17857 |
+
"grad_norm": 0.15956880152225494,
|
| 17858 |
+
"learning_rate": 4.403794037940379e-06,
|
| 17859 |
+
"loss": 2.6002964973449707,
|
| 17860 |
+
"step": 5100
|
| 17861 |
+
},
|
| 17862 |
+
{
|
| 17863 |
+
"epoch": 0.9956579011562667,
|
| 17864 |
+
"grad_norm": 0.1698477864265442,
|
| 17865 |
+
"learning_rate": 4.0650406504065046e-06,
|
| 17866 |
+
"loss": 2.530668020248413,
|
| 17867 |
+
"step": 5102
|
| 17868 |
+
},
|
| 17869 |
+
{
|
| 17870 |
+
"epoch": 0.9960482021759282,
|
| 17871 |
+
"grad_norm": 0.1682293713092804,
|
| 17872 |
+
"learning_rate": 3.7262872628726286e-06,
|
| 17873 |
+
"loss": 2.5551860332489014,
|
| 17874 |
+
"step": 5104
|
| 17875 |
+
},
|
| 17876 |
+
{
|
| 17877 |
+
"epoch": 0.9964385031955896,
|
| 17878 |
+
"grad_norm": 0.13594436645507812,
|
| 17879 |
+
"learning_rate": 3.387533875338754e-06,
|
| 17880 |
+
"loss": 2.5827760696411133,
|
| 17881 |
+
"step": 5106
|
| 17882 |
+
},
|
| 17883 |
+
{
|
| 17884 |
+
"epoch": 0.996828804215251,
|
| 17885 |
+
"grad_norm": 0.14943188428878784,
|
| 17886 |
+
"learning_rate": 3.0487804878048782e-06,
|
| 17887 |
+
"loss": 2.6085495948791504,
|
| 17888 |
+
"step": 5108
|
| 17889 |
+
},
|
| 17890 |
+
{
|
| 17891 |
+
"epoch": 0.9972191052349124,
|
| 17892 |
+
"grad_norm": 0.17643921077251434,
|
| 17893 |
+
"learning_rate": 2.7100271002710026e-06,
|
| 17894 |
+
"loss": 2.5217554569244385,
|
| 17895 |
+
"step": 5110
|
| 17896 |
+
},
|
| 17897 |
+
{
|
| 17898 |
+
"epoch": 0.9976094062545738,
|
| 17899 |
+
"grad_norm": 0.15645772218704224,
|
| 17900 |
+
"learning_rate": 2.3712737127371275e-06,
|
| 17901 |
+
"loss": 2.553799629211426,
|
| 17902 |
+
"step": 5112
|
| 17903 |
+
},
|
| 17904 |
+
{
|
| 17905 |
+
"epoch": 0.9979997072742353,
|
| 17906 |
+
"grad_norm": 0.16386376321315765,
|
| 17907 |
+
"learning_rate": 2.0325203252032523e-06,
|
| 17908 |
+
"loss": 2.601832389831543,
|
| 17909 |
+
"step": 5114
|
| 17910 |
+
},
|
| 17911 |
+
{
|
| 17912 |
+
"epoch": 0.9983900082938967,
|
| 17913 |
+
"grad_norm": 0.1857491284608841,
|
| 17914 |
+
"learning_rate": 1.693766937669377e-06,
|
| 17915 |
+
"loss": 2.5522873401641846,
|
| 17916 |
+
"step": 5116
|
| 17917 |
+
},
|
| 17918 |
+
{
|
| 17919 |
+
"epoch": 0.9987803093135581,
|
| 17920 |
+
"grad_norm": 0.14997225999832153,
|
| 17921 |
+
"learning_rate": 1.3550135501355013e-06,
|
| 17922 |
+
"loss": 2.523294687271118,
|
| 17923 |
+
"step": 5118
|
| 17924 |
+
},
|
| 17925 |
+
{
|
| 17926 |
+
"epoch": 0.9991706103332195,
|
| 17927 |
+
"grad_norm": 0.18511369824409485,
|
| 17928 |
+
"learning_rate": 1.0162601626016261e-06,
|
| 17929 |
+
"loss": 2.5799448490142822,
|
| 17930 |
+
"step": 5120
|
| 17931 |
+
},
|
| 17932 |
+
{
|
| 17933 |
+
"epoch": 0.9995609113528809,
|
| 17934 |
+
"grad_norm": 0.17572902143001556,
|
| 17935 |
+
"learning_rate": 6.775067750677507e-07,
|
| 17936 |
+
"loss": 2.536534309387207,
|
| 17937 |
+
"step": 5122
|
| 17938 |
+
},
|
| 17939 |
+
{
|
| 17940 |
+
"epoch": 0.9999512123725424,
|
| 17941 |
+
"grad_norm": 0.17535321414470673,
|
| 17942 |
+
"learning_rate": 3.3875338753387533e-07,
|
| 17943 |
+
"loss": 2.602551221847534,
|
| 17944 |
+
"step": 5124
|
| 17945 |
}
|
| 17946 |
],
|
| 17947 |
"logging_steps": 2,
|
|
|
|
| 17956 |
"should_evaluate": false,
|
| 17957 |
"should_log": false,
|
| 17958 |
"should_save": true,
|
| 17959 |
+
"should_training_stop": true
|
| 17960 |
},
|
| 17961 |
"attributes": {}
|
| 17962 |
}
|
| 17963 |
},
|
| 17964 |
+
"total_flos": 1.6393008141429637e+18,
|
| 17965 |
"train_batch_size": 6,
|
| 17966 |
"trial_name": null,
|
| 17967 |
"trial_params": null
|