Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
unsloth
sft
conversational
text-generation-inference
Instructions to use Ba2han/test_CPTlsft2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/test_CPTlsft2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/test_CPTlsft2") 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_CPTlsft2") model = AutoModelForCausalLM.from_pretrained("Ba2han/test_CPTlsft2", 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_CPTlsft2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/test_CPTlsft2" # 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_CPTlsft2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ba2han/test_CPTlsft2
- SGLang
How to use Ba2han/test_CPTlsft2 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_CPTlsft2" \ --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_CPTlsft2", "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_CPTlsft2" \ --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_CPTlsft2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use Ba2han/test_CPTlsft2 with Docker Model Runner:
docker model run hf.co/Ba2han/test_CPTlsft2
Training in progress, step 3444, 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:dc319cde25bbe582d35abeb9a170a88ca8647bd6f884f8e123ad198c66869d41
|
| 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 3631584265
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c7c1c1e737b9e502101566d0fbc6b885929c05ce45b0bbf3cabd91830efcbb8
|
| 3 |
size 3631584265
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d9eb47231e527251c8944f897373cd5b4af8dc621794ac46bf91db10ea36cde
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 1.
|
| 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,
|
|
@@ -10053,6 +10053,2015 @@
|
|
| 10053 |
"learning_rate": 5e-05,
|
| 10054 |
"loss": 1.8651812076568604,
|
| 10055 |
"step": 2870
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10056 |
}
|
| 10057 |
],
|
| 10058 |
"logging_steps": 2,
|
|
@@ -10072,7 +12081,7 @@
|
|
| 10072 |
"attributes": {}
|
| 10073 |
}
|
| 10074 |
},
|
| 10075 |
-
"total_flos":
|
| 10076 |
"train_batch_size": 1,
|
| 10077 |
"trial_name": null,
|
| 10078 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.2008473246508709,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3444,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10053 |
"learning_rate": 5e-05,
|
| 10054 |
"loss": 1.8651812076568604,
|
| 10055 |
"step": 2870
|
| 10056 |
+
},
|
| 10057 |
+
{
|
| 10058 |
+
"epoch": 1.0013947730878532,
|
| 10059 |
+
"grad_norm": 0.31359073519706726,
|
| 10060 |
+
"learning_rate": 5e-05,
|
| 10061 |
+
"loss": 1.829200029373169,
|
| 10062 |
+
"step": 2872
|
| 10063 |
+
},
|
| 10064 |
+
{
|
| 10065 |
+
"epoch": 1.00209215963178,
|
| 10066 |
+
"grad_norm": 0.18494483828544617,
|
| 10067 |
+
"learning_rate": 5e-05,
|
| 10068 |
+
"loss": 1.7781418561935425,
|
| 10069 |
+
"step": 2874
|
| 10070 |
+
},
|
| 10071 |
+
{
|
| 10072 |
+
"epoch": 1.0027895461757066,
|
| 10073 |
+
"grad_norm": 0.21310435235500336,
|
| 10074 |
+
"learning_rate": 5e-05,
|
| 10075 |
+
"loss": 1.9945908784866333,
|
| 10076 |
+
"step": 2876
|
| 10077 |
+
},
|
| 10078 |
+
{
|
| 10079 |
+
"epoch": 1.0034869327196332,
|
| 10080 |
+
"grad_norm": 0.35635262727737427,
|
| 10081 |
+
"learning_rate": 5e-05,
|
| 10082 |
+
"loss": 1.9545801877975464,
|
| 10083 |
+
"step": 2878
|
| 10084 |
+
},
|
| 10085 |
+
{
|
| 10086 |
+
"epoch": 1.0041843192635598,
|
| 10087 |
+
"grad_norm": 0.15053369104862213,
|
| 10088 |
+
"learning_rate": 5e-05,
|
| 10089 |
+
"loss": 1.9538103342056274,
|
| 10090 |
+
"step": 2880
|
| 10091 |
+
},
|
| 10092 |
+
{
|
| 10093 |
+
"epoch": 1.0048817058074864,
|
| 10094 |
+
"grad_norm": 0.1651700884103775,
|
| 10095 |
+
"learning_rate": 5e-05,
|
| 10096 |
+
"loss": 1.8527746200561523,
|
| 10097 |
+
"step": 2882
|
| 10098 |
+
},
|
| 10099 |
+
{
|
| 10100 |
+
"epoch": 1.0055790923514132,
|
| 10101 |
+
"grad_norm": 0.1976553052663803,
|
| 10102 |
+
"learning_rate": 5e-05,
|
| 10103 |
+
"loss": 1.9116666316986084,
|
| 10104 |
+
"step": 2884
|
| 10105 |
+
},
|
| 10106 |
+
{
|
| 10107 |
+
"epoch": 1.0062764788953398,
|
| 10108 |
+
"grad_norm": 0.19889503717422485,
|
| 10109 |
+
"learning_rate": 5e-05,
|
| 10110 |
+
"loss": 1.7965984344482422,
|
| 10111 |
+
"step": 2886
|
| 10112 |
+
},
|
| 10113 |
+
{
|
| 10114 |
+
"epoch": 1.0069738654392664,
|
| 10115 |
+
"grad_norm": 0.2198513001203537,
|
| 10116 |
+
"learning_rate": 5e-05,
|
| 10117 |
+
"loss": 1.806004285812378,
|
| 10118 |
+
"step": 2888
|
| 10119 |
+
},
|
| 10120 |
+
{
|
| 10121 |
+
"epoch": 1.007671251983193,
|
| 10122 |
+
"grad_norm": 0.2889701724052429,
|
| 10123 |
+
"learning_rate": 5e-05,
|
| 10124 |
+
"loss": 1.7720134258270264,
|
| 10125 |
+
"step": 2890
|
| 10126 |
+
},
|
| 10127 |
+
{
|
| 10128 |
+
"epoch": 1.0083686385271196,
|
| 10129 |
+
"grad_norm": 0.36210790276527405,
|
| 10130 |
+
"learning_rate": 5e-05,
|
| 10131 |
+
"loss": 1.713160514831543,
|
| 10132 |
+
"step": 2892
|
| 10133 |
+
},
|
| 10134 |
+
{
|
| 10135 |
+
"epoch": 1.0090660250710461,
|
| 10136 |
+
"grad_norm": 0.276302307844162,
|
| 10137 |
+
"learning_rate": 5e-05,
|
| 10138 |
+
"loss": 1.9835500717163086,
|
| 10139 |
+
"step": 2894
|
| 10140 |
+
},
|
| 10141 |
+
{
|
| 10142 |
+
"epoch": 1.009763411614973,
|
| 10143 |
+
"grad_norm": 0.22598609328269958,
|
| 10144 |
+
"learning_rate": 5e-05,
|
| 10145 |
+
"loss": 1.7208616733551025,
|
| 10146 |
+
"step": 2896
|
| 10147 |
+
},
|
| 10148 |
+
{
|
| 10149 |
+
"epoch": 1.0104607981588996,
|
| 10150 |
+
"grad_norm": 0.24496674537658691,
|
| 10151 |
+
"learning_rate": 5e-05,
|
| 10152 |
+
"loss": 1.9628424644470215,
|
| 10153 |
+
"step": 2898
|
| 10154 |
+
},
|
| 10155 |
+
{
|
| 10156 |
+
"epoch": 1.0111581847028261,
|
| 10157 |
+
"grad_norm": 0.2269727885723114,
|
| 10158 |
+
"learning_rate": 5e-05,
|
| 10159 |
+
"loss": 1.5986348390579224,
|
| 10160 |
+
"step": 2900
|
| 10161 |
+
},
|
| 10162 |
+
{
|
| 10163 |
+
"epoch": 1.0118555712467527,
|
| 10164 |
+
"grad_norm": 0.1923527717590332,
|
| 10165 |
+
"learning_rate": 5e-05,
|
| 10166 |
+
"loss": 1.8378580808639526,
|
| 10167 |
+
"step": 2902
|
| 10168 |
+
},
|
| 10169 |
+
{
|
| 10170 |
+
"epoch": 1.0125529577906793,
|
| 10171 |
+
"grad_norm": 0.28000184893608093,
|
| 10172 |
+
"learning_rate": 5e-05,
|
| 10173 |
+
"loss": 1.9745831489562988,
|
| 10174 |
+
"step": 2904
|
| 10175 |
+
},
|
| 10176 |
+
{
|
| 10177 |
+
"epoch": 1.0132503443346061,
|
| 10178 |
+
"grad_norm": 0.1698903739452362,
|
| 10179 |
+
"learning_rate": 5e-05,
|
| 10180 |
+
"loss": 1.9972134828567505,
|
| 10181 |
+
"step": 2906
|
| 10182 |
+
},
|
| 10183 |
+
{
|
| 10184 |
+
"epoch": 1.0139477308785327,
|
| 10185 |
+
"grad_norm": 0.24956777691841125,
|
| 10186 |
+
"learning_rate": 5e-05,
|
| 10187 |
+
"loss": 1.7017366886138916,
|
| 10188 |
+
"step": 2908
|
| 10189 |
+
},
|
| 10190 |
+
{
|
| 10191 |
+
"epoch": 1.0146451174224593,
|
| 10192 |
+
"grad_norm": 0.2672395408153534,
|
| 10193 |
+
"learning_rate": 5e-05,
|
| 10194 |
+
"loss": 1.9146156311035156,
|
| 10195 |
+
"step": 2910
|
| 10196 |
+
},
|
| 10197 |
+
{
|
| 10198 |
+
"epoch": 1.015342503966386,
|
| 10199 |
+
"grad_norm": 0.2607141435146332,
|
| 10200 |
+
"learning_rate": 5e-05,
|
| 10201 |
+
"loss": 1.779744267463684,
|
| 10202 |
+
"step": 2912
|
| 10203 |
+
},
|
| 10204 |
+
{
|
| 10205 |
+
"epoch": 1.0160398905103125,
|
| 10206 |
+
"grad_norm": 0.24102437496185303,
|
| 10207 |
+
"learning_rate": 5e-05,
|
| 10208 |
+
"loss": 2.057152271270752,
|
| 10209 |
+
"step": 2914
|
| 10210 |
+
},
|
| 10211 |
+
{
|
| 10212 |
+
"epoch": 1.0167372770542393,
|
| 10213 |
+
"grad_norm": 0.27756503224372864,
|
| 10214 |
+
"learning_rate": 5e-05,
|
| 10215 |
+
"loss": 1.8224923610687256,
|
| 10216 |
+
"step": 2916
|
| 10217 |
+
},
|
| 10218 |
+
{
|
| 10219 |
+
"epoch": 1.017434663598166,
|
| 10220 |
+
"grad_norm": 0.22120578587055206,
|
| 10221 |
+
"learning_rate": 5e-05,
|
| 10222 |
+
"loss": 1.9365962743759155,
|
| 10223 |
+
"step": 2918
|
| 10224 |
+
},
|
| 10225 |
+
{
|
| 10226 |
+
"epoch": 1.0181320501420925,
|
| 10227 |
+
"grad_norm": 0.22153885662555695,
|
| 10228 |
+
"learning_rate": 5e-05,
|
| 10229 |
+
"loss": 2.0323996543884277,
|
| 10230 |
+
"step": 2920
|
| 10231 |
+
},
|
| 10232 |
+
{
|
| 10233 |
+
"epoch": 1.018829436686019,
|
| 10234 |
+
"grad_norm": 0.20578232407569885,
|
| 10235 |
+
"learning_rate": 5e-05,
|
| 10236 |
+
"loss": 1.768959403038025,
|
| 10237 |
+
"step": 2922
|
| 10238 |
+
},
|
| 10239 |
+
{
|
| 10240 |
+
"epoch": 1.0195268232299457,
|
| 10241 |
+
"grad_norm": 0.18166182935237885,
|
| 10242 |
+
"learning_rate": 5e-05,
|
| 10243 |
+
"loss": 1.9475005865097046,
|
| 10244 |
+
"step": 2924
|
| 10245 |
+
},
|
| 10246 |
+
{
|
| 10247 |
+
"epoch": 1.0202242097738725,
|
| 10248 |
+
"grad_norm": 0.21352547407150269,
|
| 10249 |
+
"learning_rate": 5e-05,
|
| 10250 |
+
"loss": 1.873194932937622,
|
| 10251 |
+
"step": 2926
|
| 10252 |
+
},
|
| 10253 |
+
{
|
| 10254 |
+
"epoch": 1.020921596317799,
|
| 10255 |
+
"grad_norm": 0.2540004551410675,
|
| 10256 |
+
"learning_rate": 5e-05,
|
| 10257 |
+
"loss": 1.8963227272033691,
|
| 10258 |
+
"step": 2928
|
| 10259 |
+
},
|
| 10260 |
+
{
|
| 10261 |
+
"epoch": 1.0216189828617257,
|
| 10262 |
+
"grad_norm": 0.22230134904384613,
|
| 10263 |
+
"learning_rate": 5e-05,
|
| 10264 |
+
"loss": 1.8723595142364502,
|
| 10265 |
+
"step": 2930
|
| 10266 |
+
},
|
| 10267 |
+
{
|
| 10268 |
+
"epoch": 1.0223163694056523,
|
| 10269 |
+
"grad_norm": 0.20390909910202026,
|
| 10270 |
+
"learning_rate": 5e-05,
|
| 10271 |
+
"loss": 1.8132610321044922,
|
| 10272 |
+
"step": 2932
|
| 10273 |
+
},
|
| 10274 |
+
{
|
| 10275 |
+
"epoch": 1.0230137559495789,
|
| 10276 |
+
"grad_norm": 0.3673308491706848,
|
| 10277 |
+
"learning_rate": 5e-05,
|
| 10278 |
+
"loss": 1.8942395448684692,
|
| 10279 |
+
"step": 2934
|
| 10280 |
+
},
|
| 10281 |
+
{
|
| 10282 |
+
"epoch": 1.0237111424935055,
|
| 10283 |
+
"grad_norm": 0.2985556125640869,
|
| 10284 |
+
"learning_rate": 5e-05,
|
| 10285 |
+
"loss": 1.9247252941131592,
|
| 10286 |
+
"step": 2936
|
| 10287 |
+
},
|
| 10288 |
+
{
|
| 10289 |
+
"epoch": 1.0244085290374323,
|
| 10290 |
+
"grad_norm": 0.21427017450332642,
|
| 10291 |
+
"learning_rate": 5e-05,
|
| 10292 |
+
"loss": 1.9653093814849854,
|
| 10293 |
+
"step": 2938
|
| 10294 |
+
},
|
| 10295 |
+
{
|
| 10296 |
+
"epoch": 1.0251059155813589,
|
| 10297 |
+
"grad_norm": 0.22396492958068848,
|
| 10298 |
+
"learning_rate": 5e-05,
|
| 10299 |
+
"loss": 1.9198822975158691,
|
| 10300 |
+
"step": 2940
|
| 10301 |
+
},
|
| 10302 |
+
{
|
| 10303 |
+
"epoch": 1.0258033021252855,
|
| 10304 |
+
"grad_norm": 0.18185977637767792,
|
| 10305 |
+
"learning_rate": 5e-05,
|
| 10306 |
+
"loss": 1.8885912895202637,
|
| 10307 |
+
"step": 2942
|
| 10308 |
+
},
|
| 10309 |
+
{
|
| 10310 |
+
"epoch": 1.026500688669212,
|
| 10311 |
+
"grad_norm": 0.27587154507637024,
|
| 10312 |
+
"learning_rate": 5e-05,
|
| 10313 |
+
"loss": 2.0981240272521973,
|
| 10314 |
+
"step": 2944
|
| 10315 |
+
},
|
| 10316 |
+
{
|
| 10317 |
+
"epoch": 1.0271980752131387,
|
| 10318 |
+
"grad_norm": 0.19659516215324402,
|
| 10319 |
+
"learning_rate": 5e-05,
|
| 10320 |
+
"loss": 2.030761241912842,
|
| 10321 |
+
"step": 2946
|
| 10322 |
+
},
|
| 10323 |
+
{
|
| 10324 |
+
"epoch": 1.0278954617570655,
|
| 10325 |
+
"grad_norm": 0.2639068067073822,
|
| 10326 |
+
"learning_rate": 5e-05,
|
| 10327 |
+
"loss": 1.906769037246704,
|
| 10328 |
+
"step": 2948
|
| 10329 |
+
},
|
| 10330 |
+
{
|
| 10331 |
+
"epoch": 1.028592848300992,
|
| 10332 |
+
"grad_norm": 0.19530723989009857,
|
| 10333 |
+
"learning_rate": 5e-05,
|
| 10334 |
+
"loss": 1.8872430324554443,
|
| 10335 |
+
"step": 2950
|
| 10336 |
+
},
|
| 10337 |
+
{
|
| 10338 |
+
"epoch": 1.0292902348449187,
|
| 10339 |
+
"grad_norm": 0.3218066096305847,
|
| 10340 |
+
"learning_rate": 5e-05,
|
| 10341 |
+
"loss": 1.8188852071762085,
|
| 10342 |
+
"step": 2952
|
| 10343 |
+
},
|
| 10344 |
+
{
|
| 10345 |
+
"epoch": 1.0299876213888453,
|
| 10346 |
+
"grad_norm": 0.22945411503314972,
|
| 10347 |
+
"learning_rate": 5e-05,
|
| 10348 |
+
"loss": 1.809032917022705,
|
| 10349 |
+
"step": 2954
|
| 10350 |
+
},
|
| 10351 |
+
{
|
| 10352 |
+
"epoch": 1.0306850079327718,
|
| 10353 |
+
"grad_norm": 0.22216176986694336,
|
| 10354 |
+
"learning_rate": 5e-05,
|
| 10355 |
+
"loss": 1.8903319835662842,
|
| 10356 |
+
"step": 2956
|
| 10357 |
+
},
|
| 10358 |
+
{
|
| 10359 |
+
"epoch": 1.0313823944766987,
|
| 10360 |
+
"grad_norm": 0.21097083389759064,
|
| 10361 |
+
"learning_rate": 5e-05,
|
| 10362 |
+
"loss": 2.15557861328125,
|
| 10363 |
+
"step": 2958
|
| 10364 |
+
},
|
| 10365 |
+
{
|
| 10366 |
+
"epoch": 1.0320797810206253,
|
| 10367 |
+
"grad_norm": 0.16663368046283722,
|
| 10368 |
+
"learning_rate": 5e-05,
|
| 10369 |
+
"loss": 1.778777837753296,
|
| 10370 |
+
"step": 2960
|
| 10371 |
+
},
|
| 10372 |
+
{
|
| 10373 |
+
"epoch": 1.0327771675645518,
|
| 10374 |
+
"grad_norm": 0.27202552556991577,
|
| 10375 |
+
"learning_rate": 5e-05,
|
| 10376 |
+
"loss": 1.908647060394287,
|
| 10377 |
+
"step": 2962
|
| 10378 |
+
},
|
| 10379 |
+
{
|
| 10380 |
+
"epoch": 1.0334745541084784,
|
| 10381 |
+
"grad_norm": 0.18464124202728271,
|
| 10382 |
+
"learning_rate": 5e-05,
|
| 10383 |
+
"loss": 1.9011168479919434,
|
| 10384 |
+
"step": 2964
|
| 10385 |
+
},
|
| 10386 |
+
{
|
| 10387 |
+
"epoch": 1.034171940652405,
|
| 10388 |
+
"grad_norm": 0.2257303148508072,
|
| 10389 |
+
"learning_rate": 5e-05,
|
| 10390 |
+
"loss": 1.8555386066436768,
|
| 10391 |
+
"step": 2966
|
| 10392 |
+
},
|
| 10393 |
+
{
|
| 10394 |
+
"epoch": 1.0348693271963318,
|
| 10395 |
+
"grad_norm": 0.3158121109008789,
|
| 10396 |
+
"learning_rate": 5e-05,
|
| 10397 |
+
"loss": 1.880272626876831,
|
| 10398 |
+
"step": 2968
|
| 10399 |
+
},
|
| 10400 |
+
{
|
| 10401 |
+
"epoch": 1.0355667137402584,
|
| 10402 |
+
"grad_norm": 0.15654286742210388,
|
| 10403 |
+
"learning_rate": 5e-05,
|
| 10404 |
+
"loss": 1.8980830907821655,
|
| 10405 |
+
"step": 2970
|
| 10406 |
+
},
|
| 10407 |
+
{
|
| 10408 |
+
"epoch": 1.036264100284185,
|
| 10409 |
+
"grad_norm": 0.20344379544258118,
|
| 10410 |
+
"learning_rate": 5e-05,
|
| 10411 |
+
"loss": 1.9919698238372803,
|
| 10412 |
+
"step": 2972
|
| 10413 |
+
},
|
| 10414 |
+
{
|
| 10415 |
+
"epoch": 1.0369614868281116,
|
| 10416 |
+
"grad_norm": 0.21301423013210297,
|
| 10417 |
+
"learning_rate": 5e-05,
|
| 10418 |
+
"loss": 1.8638865947723389,
|
| 10419 |
+
"step": 2974
|
| 10420 |
+
},
|
| 10421 |
+
{
|
| 10422 |
+
"epoch": 1.0376588733720382,
|
| 10423 |
+
"grad_norm": 0.17934224009513855,
|
| 10424 |
+
"learning_rate": 5e-05,
|
| 10425 |
+
"loss": 1.9926419258117676,
|
| 10426 |
+
"step": 2976
|
| 10427 |
+
},
|
| 10428 |
+
{
|
| 10429 |
+
"epoch": 1.038356259915965,
|
| 10430 |
+
"grad_norm": 0.19874687492847443,
|
| 10431 |
+
"learning_rate": 5e-05,
|
| 10432 |
+
"loss": 1.969261884689331,
|
| 10433 |
+
"step": 2978
|
| 10434 |
+
},
|
| 10435 |
+
{
|
| 10436 |
+
"epoch": 1.0390536464598916,
|
| 10437 |
+
"grad_norm": 0.23959201574325562,
|
| 10438 |
+
"learning_rate": 5e-05,
|
| 10439 |
+
"loss": 1.9629769325256348,
|
| 10440 |
+
"step": 2980
|
| 10441 |
+
},
|
| 10442 |
+
{
|
| 10443 |
+
"epoch": 1.0397510330038182,
|
| 10444 |
+
"grad_norm": 0.18820637464523315,
|
| 10445 |
+
"learning_rate": 5e-05,
|
| 10446 |
+
"loss": 1.990842580795288,
|
| 10447 |
+
"step": 2982
|
| 10448 |
+
},
|
| 10449 |
+
{
|
| 10450 |
+
"epoch": 1.0404484195477448,
|
| 10451 |
+
"grad_norm": 0.3176293671131134,
|
| 10452 |
+
"learning_rate": 5e-05,
|
| 10453 |
+
"loss": 1.7065595388412476,
|
| 10454 |
+
"step": 2984
|
| 10455 |
+
},
|
| 10456 |
+
{
|
| 10457 |
+
"epoch": 1.0411458060916714,
|
| 10458 |
+
"grad_norm": 0.3154110312461853,
|
| 10459 |
+
"learning_rate": 5e-05,
|
| 10460 |
+
"loss": 1.879931926727295,
|
| 10461 |
+
"step": 2986
|
| 10462 |
+
},
|
| 10463 |
+
{
|
| 10464 |
+
"epoch": 1.041843192635598,
|
| 10465 |
+
"grad_norm": 0.18767651915550232,
|
| 10466 |
+
"learning_rate": 5e-05,
|
| 10467 |
+
"loss": 1.9425246715545654,
|
| 10468 |
+
"step": 2988
|
| 10469 |
+
},
|
| 10470 |
+
{
|
| 10471 |
+
"epoch": 1.0425405791795248,
|
| 10472 |
+
"grad_norm": 0.42967626452445984,
|
| 10473 |
+
"learning_rate": 5e-05,
|
| 10474 |
+
"loss": 1.9072425365447998,
|
| 10475 |
+
"step": 2990
|
| 10476 |
+
},
|
| 10477 |
+
{
|
| 10478 |
+
"epoch": 1.0432379657234514,
|
| 10479 |
+
"grad_norm": 0.17276839911937714,
|
| 10480 |
+
"learning_rate": 5e-05,
|
| 10481 |
+
"loss": 1.930345058441162,
|
| 10482 |
+
"step": 2992
|
| 10483 |
+
},
|
| 10484 |
+
{
|
| 10485 |
+
"epoch": 1.043935352267378,
|
| 10486 |
+
"grad_norm": 0.20109118521213531,
|
| 10487 |
+
"learning_rate": 5e-05,
|
| 10488 |
+
"loss": 1.82950758934021,
|
| 10489 |
+
"step": 2994
|
| 10490 |
+
},
|
| 10491 |
+
{
|
| 10492 |
+
"epoch": 1.0446327388113046,
|
| 10493 |
+
"grad_norm": 0.19736596941947937,
|
| 10494 |
+
"learning_rate": 5e-05,
|
| 10495 |
+
"loss": 2.118715763092041,
|
| 10496 |
+
"step": 2996
|
| 10497 |
+
},
|
| 10498 |
+
{
|
| 10499 |
+
"epoch": 1.0453301253552312,
|
| 10500 |
+
"grad_norm": 0.20882341265678406,
|
| 10501 |
+
"learning_rate": 5e-05,
|
| 10502 |
+
"loss": 1.8056647777557373,
|
| 10503 |
+
"step": 2998
|
| 10504 |
+
},
|
| 10505 |
+
{
|
| 10506 |
+
"epoch": 1.046027511899158,
|
| 10507 |
+
"grad_norm": 0.24335800111293793,
|
| 10508 |
+
"learning_rate": 5e-05,
|
| 10509 |
+
"loss": 2.065293073654175,
|
| 10510 |
+
"step": 3000
|
| 10511 |
+
},
|
| 10512 |
+
{
|
| 10513 |
+
"epoch": 1.0467248984430846,
|
| 10514 |
+
"grad_norm": 0.20033885538578033,
|
| 10515 |
+
"learning_rate": 5e-05,
|
| 10516 |
+
"loss": 1.9977822303771973,
|
| 10517 |
+
"step": 3002
|
| 10518 |
+
},
|
| 10519 |
+
{
|
| 10520 |
+
"epoch": 1.0474222849870112,
|
| 10521 |
+
"grad_norm": 0.23461225628852844,
|
| 10522 |
+
"learning_rate": 5e-05,
|
| 10523 |
+
"loss": 1.9835517406463623,
|
| 10524 |
+
"step": 3004
|
| 10525 |
+
},
|
| 10526 |
+
{
|
| 10527 |
+
"epoch": 1.0481196715309378,
|
| 10528 |
+
"grad_norm": 0.18256652355194092,
|
| 10529 |
+
"learning_rate": 5e-05,
|
| 10530 |
+
"loss": 1.7411243915557861,
|
| 10531 |
+
"step": 3006
|
| 10532 |
+
},
|
| 10533 |
+
{
|
| 10534 |
+
"epoch": 1.0488170580748644,
|
| 10535 |
+
"grad_norm": 0.18111863732337952,
|
| 10536 |
+
"learning_rate": 5e-05,
|
| 10537 |
+
"loss": 1.7137845754623413,
|
| 10538 |
+
"step": 3008
|
| 10539 |
+
},
|
| 10540 |
+
{
|
| 10541 |
+
"epoch": 1.0495144446187912,
|
| 10542 |
+
"grad_norm": 0.3122173845767975,
|
| 10543 |
+
"learning_rate": 5e-05,
|
| 10544 |
+
"loss": 1.684222936630249,
|
| 10545 |
+
"step": 3010
|
| 10546 |
+
},
|
| 10547 |
+
{
|
| 10548 |
+
"epoch": 1.0502118311627178,
|
| 10549 |
+
"grad_norm": 0.39914849400520325,
|
| 10550 |
+
"learning_rate": 5e-05,
|
| 10551 |
+
"loss": 1.5934462547302246,
|
| 10552 |
+
"step": 3012
|
| 10553 |
+
},
|
| 10554 |
+
{
|
| 10555 |
+
"epoch": 1.0509092177066444,
|
| 10556 |
+
"grad_norm": 0.17329807579517365,
|
| 10557 |
+
"learning_rate": 5e-05,
|
| 10558 |
+
"loss": 1.8913609981536865,
|
| 10559 |
+
"step": 3014
|
| 10560 |
+
},
|
| 10561 |
+
{
|
| 10562 |
+
"epoch": 1.051606604250571,
|
| 10563 |
+
"grad_norm": 0.24272692203521729,
|
| 10564 |
+
"learning_rate": 5e-05,
|
| 10565 |
+
"loss": 1.8258047103881836,
|
| 10566 |
+
"step": 3016
|
| 10567 |
+
},
|
| 10568 |
+
{
|
| 10569 |
+
"epoch": 1.0523039907944975,
|
| 10570 |
+
"grad_norm": 0.20756541192531586,
|
| 10571 |
+
"learning_rate": 5e-05,
|
| 10572 |
+
"loss": 1.8831913471221924,
|
| 10573 |
+
"step": 3018
|
| 10574 |
+
},
|
| 10575 |
+
{
|
| 10576 |
+
"epoch": 1.0530013773384244,
|
| 10577 |
+
"grad_norm": 0.24580636620521545,
|
| 10578 |
+
"learning_rate": 5e-05,
|
| 10579 |
+
"loss": 1.7874979972839355,
|
| 10580 |
+
"step": 3020
|
| 10581 |
+
},
|
| 10582 |
+
{
|
| 10583 |
+
"epoch": 1.053698763882351,
|
| 10584 |
+
"grad_norm": 0.211761012673378,
|
| 10585 |
+
"learning_rate": 5e-05,
|
| 10586 |
+
"loss": 1.848203420639038,
|
| 10587 |
+
"step": 3022
|
| 10588 |
+
},
|
| 10589 |
+
{
|
| 10590 |
+
"epoch": 1.0543961504262775,
|
| 10591 |
+
"grad_norm": 0.27407196164131165,
|
| 10592 |
+
"learning_rate": 5e-05,
|
| 10593 |
+
"loss": 1.7207894325256348,
|
| 10594 |
+
"step": 3024
|
| 10595 |
+
},
|
| 10596 |
+
{
|
| 10597 |
+
"epoch": 1.0550935369702041,
|
| 10598 |
+
"grad_norm": 0.22823724150657654,
|
| 10599 |
+
"learning_rate": 5e-05,
|
| 10600 |
+
"loss": 1.9045991897583008,
|
| 10601 |
+
"step": 3026
|
| 10602 |
+
},
|
| 10603 |
+
{
|
| 10604 |
+
"epoch": 1.0557909235141307,
|
| 10605 |
+
"grad_norm": 0.3093097507953644,
|
| 10606 |
+
"learning_rate": 5e-05,
|
| 10607 |
+
"loss": 1.8167511224746704,
|
| 10608 |
+
"step": 3028
|
| 10609 |
+
},
|
| 10610 |
+
{
|
| 10611 |
+
"epoch": 1.0564883100580573,
|
| 10612 |
+
"grad_norm": 0.20107699930667877,
|
| 10613 |
+
"learning_rate": 5e-05,
|
| 10614 |
+
"loss": 1.9803643226623535,
|
| 10615 |
+
"step": 3030
|
| 10616 |
+
},
|
| 10617 |
+
{
|
| 10618 |
+
"epoch": 1.0571856966019841,
|
| 10619 |
+
"grad_norm": 0.2670706808567047,
|
| 10620 |
+
"learning_rate": 5e-05,
|
| 10621 |
+
"loss": 1.766595482826233,
|
| 10622 |
+
"step": 3032
|
| 10623 |
+
},
|
| 10624 |
+
{
|
| 10625 |
+
"epoch": 1.0578830831459107,
|
| 10626 |
+
"grad_norm": 0.265388548374176,
|
| 10627 |
+
"learning_rate": 5e-05,
|
| 10628 |
+
"loss": 1.7853655815124512,
|
| 10629 |
+
"step": 3034
|
| 10630 |
+
},
|
| 10631 |
+
{
|
| 10632 |
+
"epoch": 1.0585804696898373,
|
| 10633 |
+
"grad_norm": 0.24559935927391052,
|
| 10634 |
+
"learning_rate": 5e-05,
|
| 10635 |
+
"loss": 1.942050576210022,
|
| 10636 |
+
"step": 3036
|
| 10637 |
+
},
|
| 10638 |
+
{
|
| 10639 |
+
"epoch": 1.059277856233764,
|
| 10640 |
+
"grad_norm": 0.1944202333688736,
|
| 10641 |
+
"learning_rate": 5e-05,
|
| 10642 |
+
"loss": 1.7787821292877197,
|
| 10643 |
+
"step": 3038
|
| 10644 |
+
},
|
| 10645 |
+
{
|
| 10646 |
+
"epoch": 1.0599752427776905,
|
| 10647 |
+
"grad_norm": 0.3455706536769867,
|
| 10648 |
+
"learning_rate": 5e-05,
|
| 10649 |
+
"loss": 1.726896047592163,
|
| 10650 |
+
"step": 3040
|
| 10651 |
+
},
|
| 10652 |
+
{
|
| 10653 |
+
"epoch": 1.0606726293216173,
|
| 10654 |
+
"grad_norm": 0.19156025350093842,
|
| 10655 |
+
"learning_rate": 5e-05,
|
| 10656 |
+
"loss": 1.9844861030578613,
|
| 10657 |
+
"step": 3042
|
| 10658 |
+
},
|
| 10659 |
+
{
|
| 10660 |
+
"epoch": 1.061370015865544,
|
| 10661 |
+
"grad_norm": 0.45266610383987427,
|
| 10662 |
+
"learning_rate": 5e-05,
|
| 10663 |
+
"loss": 1.8766891956329346,
|
| 10664 |
+
"step": 3044
|
| 10665 |
+
},
|
| 10666 |
+
{
|
| 10667 |
+
"epoch": 1.0620674024094705,
|
| 10668 |
+
"grad_norm": 0.2506283223628998,
|
| 10669 |
+
"learning_rate": 5e-05,
|
| 10670 |
+
"loss": 2.065756320953369,
|
| 10671 |
+
"step": 3046
|
| 10672 |
+
},
|
| 10673 |
+
{
|
| 10674 |
+
"epoch": 1.062764788953397,
|
| 10675 |
+
"grad_norm": 0.2267516851425171,
|
| 10676 |
+
"learning_rate": 5e-05,
|
| 10677 |
+
"loss": 1.7935112714767456,
|
| 10678 |
+
"step": 3048
|
| 10679 |
+
},
|
| 10680 |
+
{
|
| 10681 |
+
"epoch": 1.0634621754973237,
|
| 10682 |
+
"grad_norm": 0.2037196010351181,
|
| 10683 |
+
"learning_rate": 5e-05,
|
| 10684 |
+
"loss": 1.9053187370300293,
|
| 10685 |
+
"step": 3050
|
| 10686 |
+
},
|
| 10687 |
+
{
|
| 10688 |
+
"epoch": 1.0641595620412505,
|
| 10689 |
+
"grad_norm": 0.18256697058677673,
|
| 10690 |
+
"learning_rate": 5e-05,
|
| 10691 |
+
"loss": 1.9324783086776733,
|
| 10692 |
+
"step": 3052
|
| 10693 |
+
},
|
| 10694 |
+
{
|
| 10695 |
+
"epoch": 1.064856948585177,
|
| 10696 |
+
"grad_norm": 0.29540106654167175,
|
| 10697 |
+
"learning_rate": 5e-05,
|
| 10698 |
+
"loss": 1.8924736976623535,
|
| 10699 |
+
"step": 3054
|
| 10700 |
+
},
|
| 10701 |
+
{
|
| 10702 |
+
"epoch": 1.0655543351291037,
|
| 10703 |
+
"grad_norm": 0.222468763589859,
|
| 10704 |
+
"learning_rate": 5e-05,
|
| 10705 |
+
"loss": 1.962878942489624,
|
| 10706 |
+
"step": 3056
|
| 10707 |
+
},
|
| 10708 |
+
{
|
| 10709 |
+
"epoch": 1.0662517216730303,
|
| 10710 |
+
"grad_norm": 0.2955968677997589,
|
| 10711 |
+
"learning_rate": 5e-05,
|
| 10712 |
+
"loss": 1.7855193614959717,
|
| 10713 |
+
"step": 3058
|
| 10714 |
+
},
|
| 10715 |
+
{
|
| 10716 |
+
"epoch": 1.0669491082169569,
|
| 10717 |
+
"grad_norm": 0.22217248380184174,
|
| 10718 |
+
"learning_rate": 5e-05,
|
| 10719 |
+
"loss": 2.028803825378418,
|
| 10720 |
+
"step": 3060
|
| 10721 |
+
},
|
| 10722 |
+
{
|
| 10723 |
+
"epoch": 1.0676464947608837,
|
| 10724 |
+
"grad_norm": 0.2518015503883362,
|
| 10725 |
+
"learning_rate": 5e-05,
|
| 10726 |
+
"loss": 1.8943895101547241,
|
| 10727 |
+
"step": 3062
|
| 10728 |
+
},
|
| 10729 |
+
{
|
| 10730 |
+
"epoch": 1.0683438813048103,
|
| 10731 |
+
"grad_norm": 0.20429520308971405,
|
| 10732 |
+
"learning_rate": 5e-05,
|
| 10733 |
+
"loss": 1.837890386581421,
|
| 10734 |
+
"step": 3064
|
| 10735 |
+
},
|
| 10736 |
+
{
|
| 10737 |
+
"epoch": 1.0690412678487369,
|
| 10738 |
+
"grad_norm": 0.28744643926620483,
|
| 10739 |
+
"learning_rate": 5e-05,
|
| 10740 |
+
"loss": 1.9460480213165283,
|
| 10741 |
+
"step": 3066
|
| 10742 |
+
},
|
| 10743 |
+
{
|
| 10744 |
+
"epoch": 1.0697386543926635,
|
| 10745 |
+
"grad_norm": 0.19168125092983246,
|
| 10746 |
+
"learning_rate": 5e-05,
|
| 10747 |
+
"loss": 2.061906337738037,
|
| 10748 |
+
"step": 3068
|
| 10749 |
+
},
|
| 10750 |
+
{
|
| 10751 |
+
"epoch": 1.07043604093659,
|
| 10752 |
+
"grad_norm": 0.19340719282627106,
|
| 10753 |
+
"learning_rate": 5e-05,
|
| 10754 |
+
"loss": 1.8375229835510254,
|
| 10755 |
+
"step": 3070
|
| 10756 |
+
},
|
| 10757 |
+
{
|
| 10758 |
+
"epoch": 1.0711334274805169,
|
| 10759 |
+
"grad_norm": 0.17509004473686218,
|
| 10760 |
+
"learning_rate": 5e-05,
|
| 10761 |
+
"loss": 2.0236008167266846,
|
| 10762 |
+
"step": 3072
|
| 10763 |
+
},
|
| 10764 |
+
{
|
| 10765 |
+
"epoch": 1.0718308140244435,
|
| 10766 |
+
"grad_norm": 0.2244594395160675,
|
| 10767 |
+
"learning_rate": 5e-05,
|
| 10768 |
+
"loss": 1.7777913808822632,
|
| 10769 |
+
"step": 3074
|
| 10770 |
+
},
|
| 10771 |
+
{
|
| 10772 |
+
"epoch": 1.07252820056837,
|
| 10773 |
+
"grad_norm": 0.16912101209163666,
|
| 10774 |
+
"learning_rate": 5e-05,
|
| 10775 |
+
"loss": 1.7235589027404785,
|
| 10776 |
+
"step": 3076
|
| 10777 |
+
},
|
| 10778 |
+
{
|
| 10779 |
+
"epoch": 1.0732255871122967,
|
| 10780 |
+
"grad_norm": 0.1829208880662918,
|
| 10781 |
+
"learning_rate": 5e-05,
|
| 10782 |
+
"loss": 1.9091994762420654,
|
| 10783 |
+
"step": 3078
|
| 10784 |
+
},
|
| 10785 |
+
{
|
| 10786 |
+
"epoch": 1.0739229736562232,
|
| 10787 |
+
"grad_norm": 0.1684057116508484,
|
| 10788 |
+
"learning_rate": 5e-05,
|
| 10789 |
+
"loss": 2.081568479537964,
|
| 10790 |
+
"step": 3080
|
| 10791 |
+
},
|
| 10792 |
+
{
|
| 10793 |
+
"epoch": 1.0746203602001498,
|
| 10794 |
+
"grad_norm": 0.18698105216026306,
|
| 10795 |
+
"learning_rate": 5e-05,
|
| 10796 |
+
"loss": 1.943549633026123,
|
| 10797 |
+
"step": 3082
|
| 10798 |
+
},
|
| 10799 |
+
{
|
| 10800 |
+
"epoch": 1.0753177467440767,
|
| 10801 |
+
"grad_norm": 0.24537481367588043,
|
| 10802 |
+
"learning_rate": 5e-05,
|
| 10803 |
+
"loss": 1.8758091926574707,
|
| 10804 |
+
"step": 3084
|
| 10805 |
+
},
|
| 10806 |
+
{
|
| 10807 |
+
"epoch": 1.0760151332880032,
|
| 10808 |
+
"grad_norm": 0.2622872591018677,
|
| 10809 |
+
"learning_rate": 5e-05,
|
| 10810 |
+
"loss": 1.7700133323669434,
|
| 10811 |
+
"step": 3086
|
| 10812 |
+
},
|
| 10813 |
+
{
|
| 10814 |
+
"epoch": 1.0767125198319298,
|
| 10815 |
+
"grad_norm": 0.18435196578502655,
|
| 10816 |
+
"learning_rate": 5e-05,
|
| 10817 |
+
"loss": 2.1117703914642334,
|
| 10818 |
+
"step": 3088
|
| 10819 |
+
},
|
| 10820 |
+
{
|
| 10821 |
+
"epoch": 1.0774099063758564,
|
| 10822 |
+
"grad_norm": 0.32609033584594727,
|
| 10823 |
+
"learning_rate": 5e-05,
|
| 10824 |
+
"loss": 1.747119426727295,
|
| 10825 |
+
"step": 3090
|
| 10826 |
+
},
|
| 10827 |
+
{
|
| 10828 |
+
"epoch": 1.078107292919783,
|
| 10829 |
+
"grad_norm": 0.1847252994775772,
|
| 10830 |
+
"learning_rate": 5e-05,
|
| 10831 |
+
"loss": 1.8103517293930054,
|
| 10832 |
+
"step": 3092
|
| 10833 |
+
},
|
| 10834 |
+
{
|
| 10835 |
+
"epoch": 1.0788046794637098,
|
| 10836 |
+
"grad_norm": 0.24559560418128967,
|
| 10837 |
+
"learning_rate": 5e-05,
|
| 10838 |
+
"loss": 1.8911972045898438,
|
| 10839 |
+
"step": 3094
|
| 10840 |
+
},
|
| 10841 |
+
{
|
| 10842 |
+
"epoch": 1.0795020660076364,
|
| 10843 |
+
"grad_norm": 0.23133735358715057,
|
| 10844 |
+
"learning_rate": 5e-05,
|
| 10845 |
+
"loss": 2.0859274864196777,
|
| 10846 |
+
"step": 3096
|
| 10847 |
+
},
|
| 10848 |
+
{
|
| 10849 |
+
"epoch": 1.080199452551563,
|
| 10850 |
+
"grad_norm": 0.3087204396724701,
|
| 10851 |
+
"learning_rate": 5e-05,
|
| 10852 |
+
"loss": 2.0171196460723877,
|
| 10853 |
+
"step": 3098
|
| 10854 |
+
},
|
| 10855 |
+
{
|
| 10856 |
+
"epoch": 1.0808968390954896,
|
| 10857 |
+
"grad_norm": 0.1970721334218979,
|
| 10858 |
+
"learning_rate": 5e-05,
|
| 10859 |
+
"loss": 1.945678949356079,
|
| 10860 |
+
"step": 3100
|
| 10861 |
+
},
|
| 10862 |
+
{
|
| 10863 |
+
"epoch": 1.0815942256394162,
|
| 10864 |
+
"grad_norm": 0.33208608627319336,
|
| 10865 |
+
"learning_rate": 5e-05,
|
| 10866 |
+
"loss": 1.496478796005249,
|
| 10867 |
+
"step": 3102
|
| 10868 |
+
},
|
| 10869 |
+
{
|
| 10870 |
+
"epoch": 1.082291612183343,
|
| 10871 |
+
"grad_norm": 0.2139287292957306,
|
| 10872 |
+
"learning_rate": 5e-05,
|
| 10873 |
+
"loss": 1.9864192008972168,
|
| 10874 |
+
"step": 3104
|
| 10875 |
+
},
|
| 10876 |
+
{
|
| 10877 |
+
"epoch": 1.0829889987272696,
|
| 10878 |
+
"grad_norm": 0.19848096370697021,
|
| 10879 |
+
"learning_rate": 5e-05,
|
| 10880 |
+
"loss": 1.962013602256775,
|
| 10881 |
+
"step": 3106
|
| 10882 |
+
},
|
| 10883 |
+
{
|
| 10884 |
+
"epoch": 1.0836863852711962,
|
| 10885 |
+
"grad_norm": 0.27842608094215393,
|
| 10886 |
+
"learning_rate": 5e-05,
|
| 10887 |
+
"loss": 1.8546619415283203,
|
| 10888 |
+
"step": 3108
|
| 10889 |
+
},
|
| 10890 |
+
{
|
| 10891 |
+
"epoch": 1.0843837718151228,
|
| 10892 |
+
"grad_norm": 0.2816014885902405,
|
| 10893 |
+
"learning_rate": 5e-05,
|
| 10894 |
+
"loss": 1.6673271656036377,
|
| 10895 |
+
"step": 3110
|
| 10896 |
+
},
|
| 10897 |
+
{
|
| 10898 |
+
"epoch": 1.0850811583590494,
|
| 10899 |
+
"grad_norm": 0.18917010724544525,
|
| 10900 |
+
"learning_rate": 5e-05,
|
| 10901 |
+
"loss": 1.8602776527404785,
|
| 10902 |
+
"step": 3112
|
| 10903 |
+
},
|
| 10904 |
+
{
|
| 10905 |
+
"epoch": 1.085778544902976,
|
| 10906 |
+
"grad_norm": 0.19316600263118744,
|
| 10907 |
+
"learning_rate": 5e-05,
|
| 10908 |
+
"loss": 1.9155161380767822,
|
| 10909 |
+
"step": 3114
|
| 10910 |
+
},
|
| 10911 |
+
{
|
| 10912 |
+
"epoch": 1.0864759314469028,
|
| 10913 |
+
"grad_norm": 0.2505404055118561,
|
| 10914 |
+
"learning_rate": 5e-05,
|
| 10915 |
+
"loss": 1.8740239143371582,
|
| 10916 |
+
"step": 3116
|
| 10917 |
+
},
|
| 10918 |
+
{
|
| 10919 |
+
"epoch": 1.0871733179908294,
|
| 10920 |
+
"grad_norm": 0.21722301840782166,
|
| 10921 |
+
"learning_rate": 5e-05,
|
| 10922 |
+
"loss": 1.8883038759231567,
|
| 10923 |
+
"step": 3118
|
| 10924 |
+
},
|
| 10925 |
+
{
|
| 10926 |
+
"epoch": 1.087870704534756,
|
| 10927 |
+
"grad_norm": 0.3146092891693115,
|
| 10928 |
+
"learning_rate": 5e-05,
|
| 10929 |
+
"loss": 2.1066112518310547,
|
| 10930 |
+
"step": 3120
|
| 10931 |
+
},
|
| 10932 |
+
{
|
| 10933 |
+
"epoch": 1.0885680910786826,
|
| 10934 |
+
"grad_norm": 0.1916327029466629,
|
| 10935 |
+
"learning_rate": 5e-05,
|
| 10936 |
+
"loss": 1.7462494373321533,
|
| 10937 |
+
"step": 3122
|
| 10938 |
+
},
|
| 10939 |
+
{
|
| 10940 |
+
"epoch": 1.0892654776226092,
|
| 10941 |
+
"grad_norm": 0.23770633339881897,
|
| 10942 |
+
"learning_rate": 5e-05,
|
| 10943 |
+
"loss": 1.9702515602111816,
|
| 10944 |
+
"step": 3124
|
| 10945 |
+
},
|
| 10946 |
+
{
|
| 10947 |
+
"epoch": 1.089962864166536,
|
| 10948 |
+
"grad_norm": 0.2103680968284607,
|
| 10949 |
+
"learning_rate": 5e-05,
|
| 10950 |
+
"loss": 1.9769155979156494,
|
| 10951 |
+
"step": 3126
|
| 10952 |
+
},
|
| 10953 |
+
{
|
| 10954 |
+
"epoch": 1.0906602507104626,
|
| 10955 |
+
"grad_norm": 0.20509839057922363,
|
| 10956 |
+
"learning_rate": 5e-05,
|
| 10957 |
+
"loss": 1.915466070175171,
|
| 10958 |
+
"step": 3128
|
| 10959 |
+
},
|
| 10960 |
+
{
|
| 10961 |
+
"epoch": 1.0913576372543892,
|
| 10962 |
+
"grad_norm": 0.20828916132450104,
|
| 10963 |
+
"learning_rate": 5e-05,
|
| 10964 |
+
"loss": 1.885035753250122,
|
| 10965 |
+
"step": 3130
|
| 10966 |
+
},
|
| 10967 |
+
{
|
| 10968 |
+
"epoch": 1.0920550237983158,
|
| 10969 |
+
"grad_norm": 0.23557862639427185,
|
| 10970 |
+
"learning_rate": 5e-05,
|
| 10971 |
+
"loss": 2.0801403522491455,
|
| 10972 |
+
"step": 3132
|
| 10973 |
+
},
|
| 10974 |
+
{
|
| 10975 |
+
"epoch": 1.0927524103422424,
|
| 10976 |
+
"grad_norm": 0.18909405171871185,
|
| 10977 |
+
"learning_rate": 5e-05,
|
| 10978 |
+
"loss": 2.022665023803711,
|
| 10979 |
+
"step": 3134
|
| 10980 |
+
},
|
| 10981 |
+
{
|
| 10982 |
+
"epoch": 1.0934497968861692,
|
| 10983 |
+
"grad_norm": 0.15867860615253448,
|
| 10984 |
+
"learning_rate": 5e-05,
|
| 10985 |
+
"loss": 1.9656434059143066,
|
| 10986 |
+
"step": 3136
|
| 10987 |
+
},
|
| 10988 |
+
{
|
| 10989 |
+
"epoch": 1.0941471834300958,
|
| 10990 |
+
"grad_norm": 0.18615524470806122,
|
| 10991 |
+
"learning_rate": 5e-05,
|
| 10992 |
+
"loss": 1.851471185684204,
|
| 10993 |
+
"step": 3138
|
| 10994 |
+
},
|
| 10995 |
+
{
|
| 10996 |
+
"epoch": 1.0948445699740224,
|
| 10997 |
+
"grad_norm": 0.1827930510044098,
|
| 10998 |
+
"learning_rate": 5e-05,
|
| 10999 |
+
"loss": 1.811725378036499,
|
| 11000 |
+
"step": 3140
|
| 11001 |
+
},
|
| 11002 |
+
{
|
| 11003 |
+
"epoch": 1.095541956517949,
|
| 11004 |
+
"grad_norm": 0.2323254495859146,
|
| 11005 |
+
"learning_rate": 5e-05,
|
| 11006 |
+
"loss": 1.9539238214492798,
|
| 11007 |
+
"step": 3142
|
| 11008 |
+
},
|
| 11009 |
+
{
|
| 11010 |
+
"epoch": 1.0962393430618755,
|
| 11011 |
+
"grad_norm": 0.20112617313861847,
|
| 11012 |
+
"learning_rate": 5e-05,
|
| 11013 |
+
"loss": 1.9900753498077393,
|
| 11014 |
+
"step": 3144
|
| 11015 |
+
},
|
| 11016 |
+
{
|
| 11017 |
+
"epoch": 1.0969367296058024,
|
| 11018 |
+
"grad_norm": 0.2772871255874634,
|
| 11019 |
+
"learning_rate": 5e-05,
|
| 11020 |
+
"loss": 1.8737435340881348,
|
| 11021 |
+
"step": 3146
|
| 11022 |
+
},
|
| 11023 |
+
{
|
| 11024 |
+
"epoch": 1.097634116149729,
|
| 11025 |
+
"grad_norm": 0.2420884668827057,
|
| 11026 |
+
"learning_rate": 5e-05,
|
| 11027 |
+
"loss": 1.8864036798477173,
|
| 11028 |
+
"step": 3148
|
| 11029 |
+
},
|
| 11030 |
+
{
|
| 11031 |
+
"epoch": 1.0983315026936555,
|
| 11032 |
+
"grad_norm": 0.22212693095207214,
|
| 11033 |
+
"learning_rate": 5e-05,
|
| 11034 |
+
"loss": 1.9165153503417969,
|
| 11035 |
+
"step": 3150
|
| 11036 |
+
},
|
| 11037 |
+
{
|
| 11038 |
+
"epoch": 1.0990288892375821,
|
| 11039 |
+
"grad_norm": 0.17598916590213776,
|
| 11040 |
+
"learning_rate": 5e-05,
|
| 11041 |
+
"loss": 1.9989866018295288,
|
| 11042 |
+
"step": 3152
|
| 11043 |
+
},
|
| 11044 |
+
{
|
| 11045 |
+
"epoch": 1.0997262757815087,
|
| 11046 |
+
"grad_norm": 0.14702627062797546,
|
| 11047 |
+
"learning_rate": 5e-05,
|
| 11048 |
+
"loss": 1.9490489959716797,
|
| 11049 |
+
"step": 3154
|
| 11050 |
+
},
|
| 11051 |
+
{
|
| 11052 |
+
"epoch": 1.1004236623254355,
|
| 11053 |
+
"grad_norm": 0.19959218800067902,
|
| 11054 |
+
"learning_rate": 5e-05,
|
| 11055 |
+
"loss": 1.7468793392181396,
|
| 11056 |
+
"step": 3156
|
| 11057 |
+
},
|
| 11058 |
+
{
|
| 11059 |
+
"epoch": 1.1011210488693621,
|
| 11060 |
+
"grad_norm": 0.19527176022529602,
|
| 11061 |
+
"learning_rate": 5e-05,
|
| 11062 |
+
"loss": 1.9752986431121826,
|
| 11063 |
+
"step": 3158
|
| 11064 |
+
},
|
| 11065 |
+
{
|
| 11066 |
+
"epoch": 1.1018184354132887,
|
| 11067 |
+
"grad_norm": 0.15109111368656158,
|
| 11068 |
+
"learning_rate": 5e-05,
|
| 11069 |
+
"loss": 1.995666742324829,
|
| 11070 |
+
"step": 3160
|
| 11071 |
+
},
|
| 11072 |
+
{
|
| 11073 |
+
"epoch": 1.1025158219572153,
|
| 11074 |
+
"grad_norm": 0.26133108139038086,
|
| 11075 |
+
"learning_rate": 5e-05,
|
| 11076 |
+
"loss": 1.740058422088623,
|
| 11077 |
+
"step": 3162
|
| 11078 |
+
},
|
| 11079 |
+
{
|
| 11080 |
+
"epoch": 1.103213208501142,
|
| 11081 |
+
"grad_norm": 0.24775837361812592,
|
| 11082 |
+
"learning_rate": 5e-05,
|
| 11083 |
+
"loss": 1.9653204679489136,
|
| 11084 |
+
"step": 3164
|
| 11085 |
+
},
|
| 11086 |
+
{
|
| 11087 |
+
"epoch": 1.1039105950450687,
|
| 11088 |
+
"grad_norm": 0.23073656857013702,
|
| 11089 |
+
"learning_rate": 5e-05,
|
| 11090 |
+
"loss": 1.8970496654510498,
|
| 11091 |
+
"step": 3166
|
| 11092 |
+
},
|
| 11093 |
+
{
|
| 11094 |
+
"epoch": 1.1046079815889953,
|
| 11095 |
+
"grad_norm": 0.2658872902393341,
|
| 11096 |
+
"learning_rate": 5e-05,
|
| 11097 |
+
"loss": 1.9253250360488892,
|
| 11098 |
+
"step": 3168
|
| 11099 |
+
},
|
| 11100 |
+
{
|
| 11101 |
+
"epoch": 1.105305368132922,
|
| 11102 |
+
"grad_norm": 0.17600391805171967,
|
| 11103 |
+
"learning_rate": 5e-05,
|
| 11104 |
+
"loss": 2.069902181625366,
|
| 11105 |
+
"step": 3170
|
| 11106 |
+
},
|
| 11107 |
+
{
|
| 11108 |
+
"epoch": 1.1060027546768485,
|
| 11109 |
+
"grad_norm": 0.18817438185214996,
|
| 11110 |
+
"learning_rate": 5e-05,
|
| 11111 |
+
"loss": 2.0579793453216553,
|
| 11112 |
+
"step": 3172
|
| 11113 |
+
},
|
| 11114 |
+
{
|
| 11115 |
+
"epoch": 1.106700141220775,
|
| 11116 |
+
"grad_norm": 0.2382892221212387,
|
| 11117 |
+
"learning_rate": 5e-05,
|
| 11118 |
+
"loss": 1.797858476638794,
|
| 11119 |
+
"step": 3174
|
| 11120 |
+
},
|
| 11121 |
+
{
|
| 11122 |
+
"epoch": 1.1073975277647017,
|
| 11123 |
+
"grad_norm": 0.2064724713563919,
|
| 11124 |
+
"learning_rate": 5e-05,
|
| 11125 |
+
"loss": 1.8315250873565674,
|
| 11126 |
+
"step": 3176
|
| 11127 |
+
},
|
| 11128 |
+
{
|
| 11129 |
+
"epoch": 1.1080949143086285,
|
| 11130 |
+
"grad_norm": 0.26791125535964966,
|
| 11131 |
+
"learning_rate": 5e-05,
|
| 11132 |
+
"loss": 1.9984941482543945,
|
| 11133 |
+
"step": 3178
|
| 11134 |
+
},
|
| 11135 |
+
{
|
| 11136 |
+
"epoch": 1.108792300852555,
|
| 11137 |
+
"grad_norm": 0.20273837447166443,
|
| 11138 |
+
"learning_rate": 5e-05,
|
| 11139 |
+
"loss": 1.9348340034484863,
|
| 11140 |
+
"step": 3180
|
| 11141 |
+
},
|
| 11142 |
+
{
|
| 11143 |
+
"epoch": 1.1094896873964817,
|
| 11144 |
+
"grad_norm": 0.21015384793281555,
|
| 11145 |
+
"learning_rate": 5e-05,
|
| 11146 |
+
"loss": 1.895909070968628,
|
| 11147 |
+
"step": 3182
|
| 11148 |
+
},
|
| 11149 |
+
{
|
| 11150 |
+
"epoch": 1.1101870739404083,
|
| 11151 |
+
"grad_norm": 0.22125685214996338,
|
| 11152 |
+
"learning_rate": 5e-05,
|
| 11153 |
+
"loss": 2.190981149673462,
|
| 11154 |
+
"step": 3184
|
| 11155 |
+
},
|
| 11156 |
+
{
|
| 11157 |
+
"epoch": 1.1108844604843349,
|
| 11158 |
+
"grad_norm": 0.2263241708278656,
|
| 11159 |
+
"learning_rate": 5e-05,
|
| 11160 |
+
"loss": 1.9944695234298706,
|
| 11161 |
+
"step": 3186
|
| 11162 |
+
},
|
| 11163 |
+
{
|
| 11164 |
+
"epoch": 1.1115818470282617,
|
| 11165 |
+
"grad_norm": 0.27125614881515503,
|
| 11166 |
+
"learning_rate": 5e-05,
|
| 11167 |
+
"loss": 1.952336311340332,
|
| 11168 |
+
"step": 3188
|
| 11169 |
+
},
|
| 11170 |
+
{
|
| 11171 |
+
"epoch": 1.1122792335721883,
|
| 11172 |
+
"grad_norm": 0.21309427917003632,
|
| 11173 |
+
"learning_rate": 5e-05,
|
| 11174 |
+
"loss": 1.8668360710144043,
|
| 11175 |
+
"step": 3190
|
| 11176 |
+
},
|
| 11177 |
+
{
|
| 11178 |
+
"epoch": 1.1129766201161149,
|
| 11179 |
+
"grad_norm": 0.20125311613082886,
|
| 11180 |
+
"learning_rate": 5e-05,
|
| 11181 |
+
"loss": 1.8131139278411865,
|
| 11182 |
+
"step": 3192
|
| 11183 |
+
},
|
| 11184 |
+
{
|
| 11185 |
+
"epoch": 1.1136740066600415,
|
| 11186 |
+
"grad_norm": 0.22964510321617126,
|
| 11187 |
+
"learning_rate": 5e-05,
|
| 11188 |
+
"loss": 1.6908190250396729,
|
| 11189 |
+
"step": 3194
|
| 11190 |
+
},
|
| 11191 |
+
{
|
| 11192 |
+
"epoch": 1.114371393203968,
|
| 11193 |
+
"grad_norm": 0.2215379923582077,
|
| 11194 |
+
"learning_rate": 5e-05,
|
| 11195 |
+
"loss": 2.077676296234131,
|
| 11196 |
+
"step": 3196
|
| 11197 |
+
},
|
| 11198 |
+
{
|
| 11199 |
+
"epoch": 1.1150687797478949,
|
| 11200 |
+
"grad_norm": 0.19939805567264557,
|
| 11201 |
+
"learning_rate": 5e-05,
|
| 11202 |
+
"loss": 1.8063565492630005,
|
| 11203 |
+
"step": 3198
|
| 11204 |
+
},
|
| 11205 |
+
{
|
| 11206 |
+
"epoch": 1.1157661662918215,
|
| 11207 |
+
"grad_norm": 0.3067377805709839,
|
| 11208 |
+
"learning_rate": 5e-05,
|
| 11209 |
+
"loss": 1.9783754348754883,
|
| 11210 |
+
"step": 3200
|
| 11211 |
+
},
|
| 11212 |
+
{
|
| 11213 |
+
"epoch": 1.116463552835748,
|
| 11214 |
+
"grad_norm": 0.33919110894203186,
|
| 11215 |
+
"learning_rate": 5e-05,
|
| 11216 |
+
"loss": 1.90299391746521,
|
| 11217 |
+
"step": 3202
|
| 11218 |
+
},
|
| 11219 |
+
{
|
| 11220 |
+
"epoch": 1.1171609393796746,
|
| 11221 |
+
"grad_norm": 0.2887316942214966,
|
| 11222 |
+
"learning_rate": 5e-05,
|
| 11223 |
+
"loss": 1.856370210647583,
|
| 11224 |
+
"step": 3204
|
| 11225 |
+
},
|
| 11226 |
+
{
|
| 11227 |
+
"epoch": 1.1178583259236012,
|
| 11228 |
+
"grad_norm": 0.24907241761684418,
|
| 11229 |
+
"learning_rate": 5e-05,
|
| 11230 |
+
"loss": 1.9177173376083374,
|
| 11231 |
+
"step": 3206
|
| 11232 |
+
},
|
| 11233 |
+
{
|
| 11234 |
+
"epoch": 1.1185557124675278,
|
| 11235 |
+
"grad_norm": 0.23588360846042633,
|
| 11236 |
+
"learning_rate": 5e-05,
|
| 11237 |
+
"loss": 1.893583059310913,
|
| 11238 |
+
"step": 3208
|
| 11239 |
+
},
|
| 11240 |
+
{
|
| 11241 |
+
"epoch": 1.1192530990114546,
|
| 11242 |
+
"grad_norm": 0.3276607096195221,
|
| 11243 |
+
"learning_rate": 5e-05,
|
| 11244 |
+
"loss": 1.797567367553711,
|
| 11245 |
+
"step": 3210
|
| 11246 |
+
},
|
| 11247 |
+
{
|
| 11248 |
+
"epoch": 1.1199504855553812,
|
| 11249 |
+
"grad_norm": 0.24757027626037598,
|
| 11250 |
+
"learning_rate": 5e-05,
|
| 11251 |
+
"loss": 1.9606432914733887,
|
| 11252 |
+
"step": 3212
|
| 11253 |
+
},
|
| 11254 |
+
{
|
| 11255 |
+
"epoch": 1.1206478720993078,
|
| 11256 |
+
"grad_norm": 0.23869870603084564,
|
| 11257 |
+
"learning_rate": 5e-05,
|
| 11258 |
+
"loss": 1.818904161453247,
|
| 11259 |
+
"step": 3214
|
| 11260 |
+
},
|
| 11261 |
+
{
|
| 11262 |
+
"epoch": 1.1213452586432344,
|
| 11263 |
+
"grad_norm": 0.27114957571029663,
|
| 11264 |
+
"learning_rate": 5e-05,
|
| 11265 |
+
"loss": 1.8644049167633057,
|
| 11266 |
+
"step": 3216
|
| 11267 |
+
},
|
| 11268 |
+
{
|
| 11269 |
+
"epoch": 1.122042645187161,
|
| 11270 |
+
"grad_norm": 0.17666642367839813,
|
| 11271 |
+
"learning_rate": 5e-05,
|
| 11272 |
+
"loss": 1.9567948579788208,
|
| 11273 |
+
"step": 3218
|
| 11274 |
+
},
|
| 11275 |
+
{
|
| 11276 |
+
"epoch": 1.1227400317310878,
|
| 11277 |
+
"grad_norm": 0.22872596979141235,
|
| 11278 |
+
"learning_rate": 5e-05,
|
| 11279 |
+
"loss": 1.8192429542541504,
|
| 11280 |
+
"step": 3220
|
| 11281 |
+
},
|
| 11282 |
+
{
|
| 11283 |
+
"epoch": 1.1234374182750144,
|
| 11284 |
+
"grad_norm": 0.17448724806308746,
|
| 11285 |
+
"learning_rate": 5e-05,
|
| 11286 |
+
"loss": 1.9359086751937866,
|
| 11287 |
+
"step": 3222
|
| 11288 |
+
},
|
| 11289 |
+
{
|
| 11290 |
+
"epoch": 1.124134804818941,
|
| 11291 |
+
"grad_norm": 0.1999889314174652,
|
| 11292 |
+
"learning_rate": 5e-05,
|
| 11293 |
+
"loss": 2.0217783451080322,
|
| 11294 |
+
"step": 3224
|
| 11295 |
+
},
|
| 11296 |
+
{
|
| 11297 |
+
"epoch": 1.1248321913628676,
|
| 11298 |
+
"grad_norm": 0.22751814126968384,
|
| 11299 |
+
"learning_rate": 5e-05,
|
| 11300 |
+
"loss": 1.941468358039856,
|
| 11301 |
+
"step": 3226
|
| 11302 |
+
},
|
| 11303 |
+
{
|
| 11304 |
+
"epoch": 1.1255295779067942,
|
| 11305 |
+
"grad_norm": 0.18390969932079315,
|
| 11306 |
+
"learning_rate": 5e-05,
|
| 11307 |
+
"loss": 1.9881794452667236,
|
| 11308 |
+
"step": 3228
|
| 11309 |
+
},
|
| 11310 |
+
{
|
| 11311 |
+
"epoch": 1.126226964450721,
|
| 11312 |
+
"grad_norm": 0.2620185911655426,
|
| 11313 |
+
"learning_rate": 5e-05,
|
| 11314 |
+
"loss": 1.9302098751068115,
|
| 11315 |
+
"step": 3230
|
| 11316 |
+
},
|
| 11317 |
+
{
|
| 11318 |
+
"epoch": 1.1269243509946476,
|
| 11319 |
+
"grad_norm": 0.21205852925777435,
|
| 11320 |
+
"learning_rate": 5e-05,
|
| 11321 |
+
"loss": 1.7991564273834229,
|
| 11322 |
+
"step": 3232
|
| 11323 |
+
},
|
| 11324 |
+
{
|
| 11325 |
+
"epoch": 1.1276217375385742,
|
| 11326 |
+
"grad_norm": 0.2107517570257187,
|
| 11327 |
+
"learning_rate": 5e-05,
|
| 11328 |
+
"loss": 1.7906372547149658,
|
| 11329 |
+
"step": 3234
|
| 11330 |
+
},
|
| 11331 |
+
{
|
| 11332 |
+
"epoch": 1.1283191240825008,
|
| 11333 |
+
"grad_norm": 0.2992035746574402,
|
| 11334 |
+
"learning_rate": 5e-05,
|
| 11335 |
+
"loss": 1.7822850942611694,
|
| 11336 |
+
"step": 3236
|
| 11337 |
+
},
|
| 11338 |
+
{
|
| 11339 |
+
"epoch": 1.1290165106264274,
|
| 11340 |
+
"grad_norm": 0.2746608555316925,
|
| 11341 |
+
"learning_rate": 5e-05,
|
| 11342 |
+
"loss": 1.8279621601104736,
|
| 11343 |
+
"step": 3238
|
| 11344 |
+
},
|
| 11345 |
+
{
|
| 11346 |
+
"epoch": 1.1297138971703542,
|
| 11347 |
+
"grad_norm": 0.20095936954021454,
|
| 11348 |
+
"learning_rate": 5e-05,
|
| 11349 |
+
"loss": 2.232962131500244,
|
| 11350 |
+
"step": 3240
|
| 11351 |
+
},
|
| 11352 |
+
{
|
| 11353 |
+
"epoch": 1.1304112837142808,
|
| 11354 |
+
"grad_norm": 0.17785291373729706,
|
| 11355 |
+
"learning_rate": 5e-05,
|
| 11356 |
+
"loss": 1.9122307300567627,
|
| 11357 |
+
"step": 3242
|
| 11358 |
+
},
|
| 11359 |
+
{
|
| 11360 |
+
"epoch": 1.1311086702582074,
|
| 11361 |
+
"grad_norm": 0.21463751792907715,
|
| 11362 |
+
"learning_rate": 5e-05,
|
| 11363 |
+
"loss": 1.7621231079101562,
|
| 11364 |
+
"step": 3244
|
| 11365 |
+
},
|
| 11366 |
+
{
|
| 11367 |
+
"epoch": 1.131806056802134,
|
| 11368 |
+
"grad_norm": 0.24938708543777466,
|
| 11369 |
+
"learning_rate": 5e-05,
|
| 11370 |
+
"loss": 1.876266598701477,
|
| 11371 |
+
"step": 3246
|
| 11372 |
+
},
|
| 11373 |
+
{
|
| 11374 |
+
"epoch": 1.1325034433460606,
|
| 11375 |
+
"grad_norm": 0.17530113458633423,
|
| 11376 |
+
"learning_rate": 5e-05,
|
| 11377 |
+
"loss": 1.9535584449768066,
|
| 11378 |
+
"step": 3248
|
| 11379 |
+
},
|
| 11380 |
+
{
|
| 11381 |
+
"epoch": 1.1332008298899874,
|
| 11382 |
+
"grad_norm": 0.211569681763649,
|
| 11383 |
+
"learning_rate": 5e-05,
|
| 11384 |
+
"loss": 1.862959384918213,
|
| 11385 |
+
"step": 3250
|
| 11386 |
+
},
|
| 11387 |
+
{
|
| 11388 |
+
"epoch": 1.133898216433914,
|
| 11389 |
+
"grad_norm": 0.17921343445777893,
|
| 11390 |
+
"learning_rate": 5e-05,
|
| 11391 |
+
"loss": 1.8929667472839355,
|
| 11392 |
+
"step": 3252
|
| 11393 |
+
},
|
| 11394 |
+
{
|
| 11395 |
+
"epoch": 1.1345956029778406,
|
| 11396 |
+
"grad_norm": 0.21480803191661835,
|
| 11397 |
+
"learning_rate": 5e-05,
|
| 11398 |
+
"loss": 1.775618076324463,
|
| 11399 |
+
"step": 3254
|
| 11400 |
+
},
|
| 11401 |
+
{
|
| 11402 |
+
"epoch": 1.1352929895217672,
|
| 11403 |
+
"grad_norm": 0.1842929869890213,
|
| 11404 |
+
"learning_rate": 5e-05,
|
| 11405 |
+
"loss": 2.046151876449585,
|
| 11406 |
+
"step": 3256
|
| 11407 |
+
},
|
| 11408 |
+
{
|
| 11409 |
+
"epoch": 1.1359903760656938,
|
| 11410 |
+
"grad_norm": 0.2910834550857544,
|
| 11411 |
+
"learning_rate": 5e-05,
|
| 11412 |
+
"loss": 1.8534057140350342,
|
| 11413 |
+
"step": 3258
|
| 11414 |
+
},
|
| 11415 |
+
{
|
| 11416 |
+
"epoch": 1.1366877626096206,
|
| 11417 |
+
"grad_norm": 0.23228909075260162,
|
| 11418 |
+
"learning_rate": 5e-05,
|
| 11419 |
+
"loss": 2.0110678672790527,
|
| 11420 |
+
"step": 3260
|
| 11421 |
+
},
|
| 11422 |
+
{
|
| 11423 |
+
"epoch": 1.1373851491535472,
|
| 11424 |
+
"grad_norm": 0.16914640367031097,
|
| 11425 |
+
"learning_rate": 5e-05,
|
| 11426 |
+
"loss": 1.95835280418396,
|
| 11427 |
+
"step": 3262
|
| 11428 |
+
},
|
| 11429 |
+
{
|
| 11430 |
+
"epoch": 1.1380825356974738,
|
| 11431 |
+
"grad_norm": 0.2415015995502472,
|
| 11432 |
+
"learning_rate": 5e-05,
|
| 11433 |
+
"loss": 1.965360403060913,
|
| 11434 |
+
"step": 3264
|
| 11435 |
+
},
|
| 11436 |
+
{
|
| 11437 |
+
"epoch": 1.1387799222414003,
|
| 11438 |
+
"grad_norm": 0.188995823264122,
|
| 11439 |
+
"learning_rate": 5e-05,
|
| 11440 |
+
"loss": 1.761688470840454,
|
| 11441 |
+
"step": 3266
|
| 11442 |
+
},
|
| 11443 |
+
{
|
| 11444 |
+
"epoch": 1.139477308785327,
|
| 11445 |
+
"grad_norm": 0.27970463037490845,
|
| 11446 |
+
"learning_rate": 5e-05,
|
| 11447 |
+
"loss": 2.0222902297973633,
|
| 11448 |
+
"step": 3268
|
| 11449 |
+
},
|
| 11450 |
+
{
|
| 11451 |
+
"epoch": 1.1401746953292535,
|
| 11452 |
+
"grad_norm": 0.26102328300476074,
|
| 11453 |
+
"learning_rate": 5e-05,
|
| 11454 |
+
"loss": 1.8212395906448364,
|
| 11455 |
+
"step": 3270
|
| 11456 |
+
},
|
| 11457 |
+
{
|
| 11458 |
+
"epoch": 1.1408720818731803,
|
| 11459 |
+
"grad_norm": 0.218557208776474,
|
| 11460 |
+
"learning_rate": 5e-05,
|
| 11461 |
+
"loss": 1.816208839416504,
|
| 11462 |
+
"step": 3272
|
| 11463 |
+
},
|
| 11464 |
+
{
|
| 11465 |
+
"epoch": 1.141569468417107,
|
| 11466 |
+
"grad_norm": 0.20457427203655243,
|
| 11467 |
+
"learning_rate": 5e-05,
|
| 11468 |
+
"loss": 1.786121129989624,
|
| 11469 |
+
"step": 3274
|
| 11470 |
+
},
|
| 11471 |
+
{
|
| 11472 |
+
"epoch": 1.1422668549610335,
|
| 11473 |
+
"grad_norm": 0.2177436649799347,
|
| 11474 |
+
"learning_rate": 5e-05,
|
| 11475 |
+
"loss": 1.9937255382537842,
|
| 11476 |
+
"step": 3276
|
| 11477 |
+
},
|
| 11478 |
+
{
|
| 11479 |
+
"epoch": 1.1429642415049601,
|
| 11480 |
+
"grad_norm": 0.24371139705181122,
|
| 11481 |
+
"learning_rate": 5e-05,
|
| 11482 |
+
"loss": 1.6575055122375488,
|
| 11483 |
+
"step": 3278
|
| 11484 |
+
},
|
| 11485 |
+
{
|
| 11486 |
+
"epoch": 1.1436616280488867,
|
| 11487 |
+
"grad_norm": 0.22388990223407745,
|
| 11488 |
+
"learning_rate": 5e-05,
|
| 11489 |
+
"loss": 2.0424928665161133,
|
| 11490 |
+
"step": 3280
|
| 11491 |
+
},
|
| 11492 |
+
{
|
| 11493 |
+
"epoch": 1.1443590145928135,
|
| 11494 |
+
"grad_norm": 0.15538032352924347,
|
| 11495 |
+
"learning_rate": 5e-05,
|
| 11496 |
+
"loss": 2.019500494003296,
|
| 11497 |
+
"step": 3282
|
| 11498 |
+
},
|
| 11499 |
+
{
|
| 11500 |
+
"epoch": 1.1450564011367401,
|
| 11501 |
+
"grad_norm": 0.24666345119476318,
|
| 11502 |
+
"learning_rate": 5e-05,
|
| 11503 |
+
"loss": 1.904087781906128,
|
| 11504 |
+
"step": 3284
|
| 11505 |
+
},
|
| 11506 |
+
{
|
| 11507 |
+
"epoch": 1.1457537876806667,
|
| 11508 |
+
"grad_norm": 0.2622423470020294,
|
| 11509 |
+
"learning_rate": 5e-05,
|
| 11510 |
+
"loss": 1.9055876731872559,
|
| 11511 |
+
"step": 3286
|
| 11512 |
+
},
|
| 11513 |
+
{
|
| 11514 |
+
"epoch": 1.1464511742245933,
|
| 11515 |
+
"grad_norm": 0.2091299444437027,
|
| 11516 |
+
"learning_rate": 5e-05,
|
| 11517 |
+
"loss": 1.9555625915527344,
|
| 11518 |
+
"step": 3288
|
| 11519 |
+
},
|
| 11520 |
+
{
|
| 11521 |
+
"epoch": 1.14714856076852,
|
| 11522 |
+
"grad_norm": 0.25040286779403687,
|
| 11523 |
+
"learning_rate": 5e-05,
|
| 11524 |
+
"loss": 1.7698583602905273,
|
| 11525 |
+
"step": 3290
|
| 11526 |
+
},
|
| 11527 |
+
{
|
| 11528 |
+
"epoch": 1.1478459473124465,
|
| 11529 |
+
"grad_norm": 0.22865115106105804,
|
| 11530 |
+
"learning_rate": 5e-05,
|
| 11531 |
+
"loss": 1.8670485019683838,
|
| 11532 |
+
"step": 3292
|
| 11533 |
+
},
|
| 11534 |
+
{
|
| 11535 |
+
"epoch": 1.1485433338563733,
|
| 11536 |
+
"grad_norm": 0.19878660142421722,
|
| 11537 |
+
"learning_rate": 5e-05,
|
| 11538 |
+
"loss": 1.9411699771881104,
|
| 11539 |
+
"step": 3294
|
| 11540 |
+
},
|
| 11541 |
+
{
|
| 11542 |
+
"epoch": 1.1492407204003,
|
| 11543 |
+
"grad_norm": 0.16737036406993866,
|
| 11544 |
+
"learning_rate": 5e-05,
|
| 11545 |
+
"loss": 1.9980804920196533,
|
| 11546 |
+
"step": 3296
|
| 11547 |
+
},
|
| 11548 |
+
{
|
| 11549 |
+
"epoch": 1.1499381069442265,
|
| 11550 |
+
"grad_norm": 0.2788243591785431,
|
| 11551 |
+
"learning_rate": 5e-05,
|
| 11552 |
+
"loss": 1.7748606204986572,
|
| 11553 |
+
"step": 3298
|
| 11554 |
+
},
|
| 11555 |
+
{
|
| 11556 |
+
"epoch": 1.150635493488153,
|
| 11557 |
+
"grad_norm": 0.21569983661174774,
|
| 11558 |
+
"learning_rate": 5e-05,
|
| 11559 |
+
"loss": 1.9681100845336914,
|
| 11560 |
+
"step": 3300
|
| 11561 |
+
},
|
| 11562 |
+
{
|
| 11563 |
+
"epoch": 1.1513328800320797,
|
| 11564 |
+
"grad_norm": 0.23890824615955353,
|
| 11565 |
+
"learning_rate": 5e-05,
|
| 11566 |
+
"loss": 1.9883267879486084,
|
| 11567 |
+
"step": 3302
|
| 11568 |
+
},
|
| 11569 |
+
{
|
| 11570 |
+
"epoch": 1.1520302665760065,
|
| 11571 |
+
"grad_norm": 0.22588355839252472,
|
| 11572 |
+
"learning_rate": 5e-05,
|
| 11573 |
+
"loss": 1.9571938514709473,
|
| 11574 |
+
"step": 3304
|
| 11575 |
+
},
|
| 11576 |
+
{
|
| 11577 |
+
"epoch": 1.152727653119933,
|
| 11578 |
+
"grad_norm": 0.3360740542411804,
|
| 11579 |
+
"learning_rate": 5e-05,
|
| 11580 |
+
"loss": 1.943509578704834,
|
| 11581 |
+
"step": 3306
|
| 11582 |
+
},
|
| 11583 |
+
{
|
| 11584 |
+
"epoch": 1.1534250396638597,
|
| 11585 |
+
"grad_norm": 0.21990825235843658,
|
| 11586 |
+
"learning_rate": 5e-05,
|
| 11587 |
+
"loss": 1.8450465202331543,
|
| 11588 |
+
"step": 3308
|
| 11589 |
+
},
|
| 11590 |
+
{
|
| 11591 |
+
"epoch": 1.1541224262077863,
|
| 11592 |
+
"grad_norm": 0.19391386210918427,
|
| 11593 |
+
"learning_rate": 5e-05,
|
| 11594 |
+
"loss": 1.7713053226470947,
|
| 11595 |
+
"step": 3310
|
| 11596 |
+
},
|
| 11597 |
+
{
|
| 11598 |
+
"epoch": 1.1548198127517129,
|
| 11599 |
+
"grad_norm": 0.20962736010551453,
|
| 11600 |
+
"learning_rate": 5e-05,
|
| 11601 |
+
"loss": 1.9607583284378052,
|
| 11602 |
+
"step": 3312
|
| 11603 |
+
},
|
| 11604 |
+
{
|
| 11605 |
+
"epoch": 1.1555171992956397,
|
| 11606 |
+
"grad_norm": 0.24098530411720276,
|
| 11607 |
+
"learning_rate": 5e-05,
|
| 11608 |
+
"loss": 2.0667452812194824,
|
| 11609 |
+
"step": 3314
|
| 11610 |
+
},
|
| 11611 |
+
{
|
| 11612 |
+
"epoch": 1.1562145858395663,
|
| 11613 |
+
"grad_norm": 0.22169256210327148,
|
| 11614 |
+
"learning_rate": 5e-05,
|
| 11615 |
+
"loss": 1.8432475328445435,
|
| 11616 |
+
"step": 3316
|
| 11617 |
+
},
|
| 11618 |
+
{
|
| 11619 |
+
"epoch": 1.1569119723834929,
|
| 11620 |
+
"grad_norm": 0.2243812382221222,
|
| 11621 |
+
"learning_rate": 5e-05,
|
| 11622 |
+
"loss": 1.9015934467315674,
|
| 11623 |
+
"step": 3318
|
| 11624 |
+
},
|
| 11625 |
+
{
|
| 11626 |
+
"epoch": 1.1576093589274195,
|
| 11627 |
+
"grad_norm": 0.25815683603286743,
|
| 11628 |
+
"learning_rate": 5e-05,
|
| 11629 |
+
"loss": 1.8329825401306152,
|
| 11630 |
+
"step": 3320
|
| 11631 |
+
},
|
| 11632 |
+
{
|
| 11633 |
+
"epoch": 1.158306745471346,
|
| 11634 |
+
"grad_norm": 0.23060393333435059,
|
| 11635 |
+
"learning_rate": 5e-05,
|
| 11636 |
+
"loss": 2.106444835662842,
|
| 11637 |
+
"step": 3322
|
| 11638 |
+
},
|
| 11639 |
+
{
|
| 11640 |
+
"epoch": 1.1590041320152729,
|
| 11641 |
+
"grad_norm": 0.20663411915302277,
|
| 11642 |
+
"learning_rate": 5e-05,
|
| 11643 |
+
"loss": 1.9880495071411133,
|
| 11644 |
+
"step": 3324
|
| 11645 |
+
},
|
| 11646 |
+
{
|
| 11647 |
+
"epoch": 1.1597015185591995,
|
| 11648 |
+
"grad_norm": 0.2329777330160141,
|
| 11649 |
+
"learning_rate": 5e-05,
|
| 11650 |
+
"loss": 2.0308775901794434,
|
| 11651 |
+
"step": 3326
|
| 11652 |
+
},
|
| 11653 |
+
{
|
| 11654 |
+
"epoch": 1.160398905103126,
|
| 11655 |
+
"grad_norm": 0.1757218837738037,
|
| 11656 |
+
"learning_rate": 5e-05,
|
| 11657 |
+
"loss": 2.0551929473876953,
|
| 11658 |
+
"step": 3328
|
| 11659 |
+
},
|
| 11660 |
+
{
|
| 11661 |
+
"epoch": 1.1610962916470526,
|
| 11662 |
+
"grad_norm": 0.23656487464904785,
|
| 11663 |
+
"learning_rate": 4.995848899958489e-05,
|
| 11664 |
+
"loss": 1.6389830112457275,
|
| 11665 |
+
"step": 3330
|
| 11666 |
+
},
|
| 11667 |
+
{
|
| 11668 |
+
"epoch": 1.1617936781909792,
|
| 11669 |
+
"grad_norm": 0.23037122189998627,
|
| 11670 |
+
"learning_rate": 4.991697799916978e-05,
|
| 11671 |
+
"loss": 2.0219359397888184,
|
| 11672 |
+
"step": 3332
|
| 11673 |
+
},
|
| 11674 |
+
{
|
| 11675 |
+
"epoch": 1.162491064734906,
|
| 11676 |
+
"grad_norm": 0.21388943493366241,
|
| 11677 |
+
"learning_rate": 4.987546699875467e-05,
|
| 11678 |
+
"loss": 1.992743730545044,
|
| 11679 |
+
"step": 3334
|
| 11680 |
+
},
|
| 11681 |
+
{
|
| 11682 |
+
"epoch": 1.1631884512788326,
|
| 11683 |
+
"grad_norm": 0.1973319798707962,
|
| 11684 |
+
"learning_rate": 4.983395599833956e-05,
|
| 11685 |
+
"loss": 1.9138026237487793,
|
| 11686 |
+
"step": 3336
|
| 11687 |
+
},
|
| 11688 |
+
{
|
| 11689 |
+
"epoch": 1.1638858378227592,
|
| 11690 |
+
"grad_norm": 0.20198167860507965,
|
| 11691 |
+
"learning_rate": 4.9792444997924455e-05,
|
| 11692 |
+
"loss": 1.9227473735809326,
|
| 11693 |
+
"step": 3338
|
| 11694 |
+
},
|
| 11695 |
+
{
|
| 11696 |
+
"epoch": 1.1645832243666858,
|
| 11697 |
+
"grad_norm": 0.22222770750522614,
|
| 11698 |
+
"learning_rate": 4.975093399750934e-05,
|
| 11699 |
+
"loss": 2.050694465637207,
|
| 11700 |
+
"step": 3340
|
| 11701 |
+
},
|
| 11702 |
+
{
|
| 11703 |
+
"epoch": 1.1652806109106124,
|
| 11704 |
+
"grad_norm": 0.18477162718772888,
|
| 11705 |
+
"learning_rate": 4.9709422997094235e-05,
|
| 11706 |
+
"loss": 1.860036849975586,
|
| 11707 |
+
"step": 3342
|
| 11708 |
+
},
|
| 11709 |
+
{
|
| 11710 |
+
"epoch": 1.1659779974545392,
|
| 11711 |
+
"grad_norm": 0.19846336543560028,
|
| 11712 |
+
"learning_rate": 4.966791199667912e-05,
|
| 11713 |
+
"loss": 1.9285279512405396,
|
| 11714 |
+
"step": 3344
|
| 11715 |
+
},
|
| 11716 |
+
{
|
| 11717 |
+
"epoch": 1.1666753839984658,
|
| 11718 |
+
"grad_norm": 0.23643462359905243,
|
| 11719 |
+
"learning_rate": 4.962640099626401e-05,
|
| 11720 |
+
"loss": 1.7353088855743408,
|
| 11721 |
+
"step": 3346
|
| 11722 |
+
},
|
| 11723 |
+
{
|
| 11724 |
+
"epoch": 1.1673727705423924,
|
| 11725 |
+
"grad_norm": 0.24746716022491455,
|
| 11726 |
+
"learning_rate": 4.95848899958489e-05,
|
| 11727 |
+
"loss": 1.8223083019256592,
|
| 11728 |
+
"step": 3348
|
| 11729 |
+
},
|
| 11730 |
+
{
|
| 11731 |
+
"epoch": 1.168070157086319,
|
| 11732 |
+
"grad_norm": 0.18461313843727112,
|
| 11733 |
+
"learning_rate": 4.9543378995433794e-05,
|
| 11734 |
+
"loss": 2.034353017807007,
|
| 11735 |
+
"step": 3350
|
| 11736 |
+
},
|
| 11737 |
+
{
|
| 11738 |
+
"epoch": 1.1687675436302456,
|
| 11739 |
+
"grad_norm": 0.2313351333141327,
|
| 11740 |
+
"learning_rate": 4.950186799501868e-05,
|
| 11741 |
+
"loss": 1.6369261741638184,
|
| 11742 |
+
"step": 3352
|
| 11743 |
+
},
|
| 11744 |
+
{
|
| 11745 |
+
"epoch": 1.1694649301741724,
|
| 11746 |
+
"grad_norm": 0.21167731285095215,
|
| 11747 |
+
"learning_rate": 4.9460356994603574e-05,
|
| 11748 |
+
"loss": 1.7105915546417236,
|
| 11749 |
+
"step": 3354
|
| 11750 |
+
},
|
| 11751 |
+
{
|
| 11752 |
+
"epoch": 1.170162316718099,
|
| 11753 |
+
"grad_norm": 0.24277447164058685,
|
| 11754 |
+
"learning_rate": 4.941884599418846e-05,
|
| 11755 |
+
"loss": 1.6707457304000854,
|
| 11756 |
+
"step": 3356
|
| 11757 |
+
},
|
| 11758 |
+
{
|
| 11759 |
+
"epoch": 1.1708597032620256,
|
| 11760 |
+
"grad_norm": 0.19461865723133087,
|
| 11761 |
+
"learning_rate": 4.937733499377335e-05,
|
| 11762 |
+
"loss": 1.8322867155075073,
|
| 11763 |
+
"step": 3358
|
| 11764 |
+
},
|
| 11765 |
+
{
|
| 11766 |
+
"epoch": 1.1715570898059522,
|
| 11767 |
+
"grad_norm": 0.23283721506595612,
|
| 11768 |
+
"learning_rate": 4.933582399335824e-05,
|
| 11769 |
+
"loss": 1.699878454208374,
|
| 11770 |
+
"step": 3360
|
| 11771 |
+
},
|
| 11772 |
+
{
|
| 11773 |
+
"epoch": 1.1722544763498788,
|
| 11774 |
+
"grad_norm": 0.2151813805103302,
|
| 11775 |
+
"learning_rate": 4.9294312992943134e-05,
|
| 11776 |
+
"loss": 1.6844890117645264,
|
| 11777 |
+
"step": 3362
|
| 11778 |
+
},
|
| 11779 |
+
{
|
| 11780 |
+
"epoch": 1.1729518628938054,
|
| 11781 |
+
"grad_norm": 0.23241637647151947,
|
| 11782 |
+
"learning_rate": 4.925280199252803e-05,
|
| 11783 |
+
"loss": 1.8825969696044922,
|
| 11784 |
+
"step": 3364
|
| 11785 |
+
},
|
| 11786 |
+
{
|
| 11787 |
+
"epoch": 1.1736492494377322,
|
| 11788 |
+
"grad_norm": 0.25263506174087524,
|
| 11789 |
+
"learning_rate": 4.921129099211291e-05,
|
| 11790 |
+
"loss": 1.5892612934112549,
|
| 11791 |
+
"step": 3366
|
| 11792 |
+
},
|
| 11793 |
+
{
|
| 11794 |
+
"epoch": 1.1743466359816588,
|
| 11795 |
+
"grad_norm": 0.2107447236776352,
|
| 11796 |
+
"learning_rate": 4.91697799916978e-05,
|
| 11797 |
+
"loss": 2.078216552734375,
|
| 11798 |
+
"step": 3368
|
| 11799 |
+
},
|
| 11800 |
+
{
|
| 11801 |
+
"epoch": 1.1750440225255854,
|
| 11802 |
+
"grad_norm": 0.17712299525737762,
|
| 11803 |
+
"learning_rate": 4.912826899128269e-05,
|
| 11804 |
+
"loss": 1.9671437740325928,
|
| 11805 |
+
"step": 3370
|
| 11806 |
+
},
|
| 11807 |
+
{
|
| 11808 |
+
"epoch": 1.175741409069512,
|
| 11809 |
+
"grad_norm": 0.24711324274539948,
|
| 11810 |
+
"learning_rate": 4.908675799086758e-05,
|
| 11811 |
+
"loss": 1.8428316116333008,
|
| 11812 |
+
"step": 3372
|
| 11813 |
+
},
|
| 11814 |
+
{
|
| 11815 |
+
"epoch": 1.1764387956134386,
|
| 11816 |
+
"grad_norm": 0.17892391979694366,
|
| 11817 |
+
"learning_rate": 4.904524699045247e-05,
|
| 11818 |
+
"loss": 2.0459518432617188,
|
| 11819 |
+
"step": 3374
|
| 11820 |
+
},
|
| 11821 |
+
{
|
| 11822 |
+
"epoch": 1.1771361821573652,
|
| 11823 |
+
"grad_norm": 0.22361093759536743,
|
| 11824 |
+
"learning_rate": 4.9003735990037366e-05,
|
| 11825 |
+
"loss": 1.9006704092025757,
|
| 11826 |
+
"step": 3376
|
| 11827 |
+
},
|
| 11828 |
+
{
|
| 11829 |
+
"epoch": 1.177833568701292,
|
| 11830 |
+
"grad_norm": 0.1812906414270401,
|
| 11831 |
+
"learning_rate": 4.896222498962225e-05,
|
| 11832 |
+
"loss": 2.1166930198669434,
|
| 11833 |
+
"step": 3378
|
| 11834 |
+
},
|
| 11835 |
+
{
|
| 11836 |
+
"epoch": 1.1785309552452186,
|
| 11837 |
+
"grad_norm": 0.23143340647220612,
|
| 11838 |
+
"learning_rate": 4.892071398920714e-05,
|
| 11839 |
+
"loss": 2.0069873332977295,
|
| 11840 |
+
"step": 3380
|
| 11841 |
+
},
|
| 11842 |
+
{
|
| 11843 |
+
"epoch": 1.1792283417891452,
|
| 11844 |
+
"grad_norm": 0.18367265164852142,
|
| 11845 |
+
"learning_rate": 4.887920298879203e-05,
|
| 11846 |
+
"loss": 1.997917890548706,
|
| 11847 |
+
"step": 3382
|
| 11848 |
+
},
|
| 11849 |
+
{
|
| 11850 |
+
"epoch": 1.1799257283330717,
|
| 11851 |
+
"grad_norm": 0.20079566538333893,
|
| 11852 |
+
"learning_rate": 4.883769198837692e-05,
|
| 11853 |
+
"loss": 1.9160549640655518,
|
| 11854 |
+
"step": 3384
|
| 11855 |
+
},
|
| 11856 |
+
{
|
| 11857 |
+
"epoch": 1.1806231148769983,
|
| 11858 |
+
"grad_norm": 0.21037310361862183,
|
| 11859 |
+
"learning_rate": 4.879618098796181e-05,
|
| 11860 |
+
"loss": 1.8643665313720703,
|
| 11861 |
+
"step": 3386
|
| 11862 |
+
},
|
| 11863 |
+
{
|
| 11864 |
+
"epoch": 1.1813205014209252,
|
| 11865 |
+
"grad_norm": 0.1846771389245987,
|
| 11866 |
+
"learning_rate": 4.8754669987546705e-05,
|
| 11867 |
+
"loss": 1.8175299167633057,
|
| 11868 |
+
"step": 3388
|
| 11869 |
+
},
|
| 11870 |
+
{
|
| 11871 |
+
"epoch": 1.1820178879648517,
|
| 11872 |
+
"grad_norm": 0.20625488460063934,
|
| 11873 |
+
"learning_rate": 4.871315898713159e-05,
|
| 11874 |
+
"loss": 1.7437139749526978,
|
| 11875 |
+
"step": 3390
|
| 11876 |
+
},
|
| 11877 |
+
{
|
| 11878 |
+
"epoch": 1.1827152745087783,
|
| 11879 |
+
"grad_norm": 0.19118858873844147,
|
| 11880 |
+
"learning_rate": 4.8671647986716485e-05,
|
| 11881 |
+
"loss": 1.9128696918487549,
|
| 11882 |
+
"step": 3392
|
| 11883 |
+
},
|
| 11884 |
+
{
|
| 11885 |
+
"epoch": 1.183412661052705,
|
| 11886 |
+
"grad_norm": 0.18890495598316193,
|
| 11887 |
+
"learning_rate": 4.863013698630137e-05,
|
| 11888 |
+
"loss": 2.0668766498565674,
|
| 11889 |
+
"step": 3394
|
| 11890 |
+
},
|
| 11891 |
+
{
|
| 11892 |
+
"epoch": 1.1841100475966315,
|
| 11893 |
+
"grad_norm": 0.20588761568069458,
|
| 11894 |
+
"learning_rate": 4.858862598588626e-05,
|
| 11895 |
+
"loss": 1.9559204578399658,
|
| 11896 |
+
"step": 3396
|
| 11897 |
+
},
|
| 11898 |
+
{
|
| 11899 |
+
"epoch": 1.1848074341405583,
|
| 11900 |
+
"grad_norm": 0.3991144895553589,
|
| 11901 |
+
"learning_rate": 4.854711498547115e-05,
|
| 11902 |
+
"loss": 1.866858720779419,
|
| 11903 |
+
"step": 3398
|
| 11904 |
+
},
|
| 11905 |
+
{
|
| 11906 |
+
"epoch": 1.185504820684485,
|
| 11907 |
+
"grad_norm": 0.18666256964206696,
|
| 11908 |
+
"learning_rate": 4.8505603985056045e-05,
|
| 11909 |
+
"loss": 1.8842792510986328,
|
| 11910 |
+
"step": 3400
|
| 11911 |
+
},
|
| 11912 |
+
{
|
| 11913 |
+
"epoch": 1.1862022072284115,
|
| 11914 |
+
"grad_norm": 0.18927165865898132,
|
| 11915 |
+
"learning_rate": 4.846409298464093e-05,
|
| 11916 |
+
"loss": 1.8684639930725098,
|
| 11917 |
+
"step": 3402
|
| 11918 |
+
},
|
| 11919 |
+
{
|
| 11920 |
+
"epoch": 1.1868995937723381,
|
| 11921 |
+
"grad_norm": 0.3511774241924286,
|
| 11922 |
+
"learning_rate": 4.8422581984225824e-05,
|
| 11923 |
+
"loss": 1.7085282802581787,
|
| 11924 |
+
"step": 3404
|
| 11925 |
+
},
|
| 11926 |
+
{
|
| 11927 |
+
"epoch": 1.1875969803162647,
|
| 11928 |
+
"grad_norm": 0.169032022356987,
|
| 11929 |
+
"learning_rate": 4.838107098381071e-05,
|
| 11930 |
+
"loss": 1.7434031963348389,
|
| 11931 |
+
"step": 3406
|
| 11932 |
+
},
|
| 11933 |
+
{
|
| 11934 |
+
"epoch": 1.1882943668601915,
|
| 11935 |
+
"grad_norm": 0.18450136482715607,
|
| 11936 |
+
"learning_rate": 4.8339559983395604e-05,
|
| 11937 |
+
"loss": 1.7748292684555054,
|
| 11938 |
+
"step": 3408
|
| 11939 |
+
},
|
| 11940 |
+
{
|
| 11941 |
+
"epoch": 1.1889917534041181,
|
| 11942 |
+
"grad_norm": 0.23342275619506836,
|
| 11943 |
+
"learning_rate": 4.829804898298049e-05,
|
| 11944 |
+
"loss": 2.0023927688598633,
|
| 11945 |
+
"step": 3410
|
| 11946 |
+
},
|
| 11947 |
+
{
|
| 11948 |
+
"epoch": 1.1896891399480447,
|
| 11949 |
+
"grad_norm": 0.3139027953147888,
|
| 11950 |
+
"learning_rate": 4.8256537982565384e-05,
|
| 11951 |
+
"loss": 2.0264627933502197,
|
| 11952 |
+
"step": 3412
|
| 11953 |
+
},
|
| 11954 |
+
{
|
| 11955 |
+
"epoch": 1.1903865264919713,
|
| 11956 |
+
"grad_norm": 0.2475530356168747,
|
| 11957 |
+
"learning_rate": 4.821502698215028e-05,
|
| 11958 |
+
"loss": 1.5474470853805542,
|
| 11959 |
+
"step": 3414
|
| 11960 |
+
},
|
| 11961 |
+
{
|
| 11962 |
+
"epoch": 1.191083913035898,
|
| 11963 |
+
"grad_norm": 0.18853792548179626,
|
| 11964 |
+
"learning_rate": 4.8173515981735164e-05,
|
| 11965 |
+
"loss": 1.721402645111084,
|
| 11966 |
+
"step": 3416
|
| 11967 |
+
},
|
| 11968 |
+
{
|
| 11969 |
+
"epoch": 1.1917812995798247,
|
| 11970 |
+
"grad_norm": 0.2692128121852875,
|
| 11971 |
+
"learning_rate": 4.813200498132005e-05,
|
| 11972 |
+
"loss": 1.8852906227111816,
|
| 11973 |
+
"step": 3418
|
| 11974 |
+
},
|
| 11975 |
+
{
|
| 11976 |
+
"epoch": 1.1924786861237513,
|
| 11977 |
+
"grad_norm": 0.21304844319820404,
|
| 11978 |
+
"learning_rate": 4.809049398090494e-05,
|
| 11979 |
+
"loss": 1.7414357662200928,
|
| 11980 |
+
"step": 3420
|
| 11981 |
+
},
|
| 11982 |
+
{
|
| 11983 |
+
"epoch": 1.193176072667678,
|
| 11984 |
+
"grad_norm": 0.19205497205257416,
|
| 11985 |
+
"learning_rate": 4.804898298048983e-05,
|
| 11986 |
+
"loss": 1.9370068311691284,
|
| 11987 |
+
"step": 3422
|
| 11988 |
+
},
|
| 11989 |
+
{
|
| 11990 |
+
"epoch": 1.1938734592116045,
|
| 11991 |
+
"grad_norm": 0.2279967963695526,
|
| 11992 |
+
"learning_rate": 4.800747198007472e-05,
|
| 11993 |
+
"loss": 2.0227110385894775,
|
| 11994 |
+
"step": 3424
|
| 11995 |
+
},
|
| 11996 |
+
{
|
| 11997 |
+
"epoch": 1.194570845755531,
|
| 11998 |
+
"grad_norm": 0.27181559801101685,
|
| 11999 |
+
"learning_rate": 4.7965960979659616e-05,
|
| 12000 |
+
"loss": 1.662685513496399,
|
| 12001 |
+
"step": 3426
|
| 12002 |
+
},
|
| 12003 |
+
{
|
| 12004 |
+
"epoch": 1.1952682322994579,
|
| 12005 |
+
"grad_norm": 0.20728352665901184,
|
| 12006 |
+
"learning_rate": 4.79244499792445e-05,
|
| 12007 |
+
"loss": 1.686200499534607,
|
| 12008 |
+
"step": 3428
|
| 12009 |
+
},
|
| 12010 |
+
{
|
| 12011 |
+
"epoch": 1.1959656188433845,
|
| 12012 |
+
"grad_norm": 0.2239687591791153,
|
| 12013 |
+
"learning_rate": 4.7882938978829396e-05,
|
| 12014 |
+
"loss": 1.9696838855743408,
|
| 12015 |
+
"step": 3430
|
| 12016 |
+
},
|
| 12017 |
+
{
|
| 12018 |
+
"epoch": 1.196663005387311,
|
| 12019 |
+
"grad_norm": 0.18133199214935303,
|
| 12020 |
+
"learning_rate": 4.784142797841428e-05,
|
| 12021 |
+
"loss": 1.9330344200134277,
|
| 12022 |
+
"step": 3432
|
| 12023 |
+
},
|
| 12024 |
+
{
|
| 12025 |
+
"epoch": 1.1973603919312377,
|
| 12026 |
+
"grad_norm": 0.2646746039390564,
|
| 12027 |
+
"learning_rate": 4.779991697799917e-05,
|
| 12028 |
+
"loss": 1.768394112586975,
|
| 12029 |
+
"step": 3434
|
| 12030 |
+
},
|
| 12031 |
+
{
|
| 12032 |
+
"epoch": 1.1980577784751643,
|
| 12033 |
+
"grad_norm": 0.23626549541950226,
|
| 12034 |
+
"learning_rate": 4.775840597758406e-05,
|
| 12035 |
+
"loss": 1.870558500289917,
|
| 12036 |
+
"step": 3436
|
| 12037 |
+
},
|
| 12038 |
+
{
|
| 12039 |
+
"epoch": 1.198755165019091,
|
| 12040 |
+
"grad_norm": 0.21471337974071503,
|
| 12041 |
+
"learning_rate": 4.7716894977168955e-05,
|
| 12042 |
+
"loss": 1.9804586172103882,
|
| 12043 |
+
"step": 3438
|
| 12044 |
+
},
|
| 12045 |
+
{
|
| 12046 |
+
"epoch": 1.1994525515630177,
|
| 12047 |
+
"grad_norm": 0.1563311368227005,
|
| 12048 |
+
"learning_rate": 4.767538397675384e-05,
|
| 12049 |
+
"loss": 2.023649215698242,
|
| 12050 |
+
"step": 3440
|
| 12051 |
+
},
|
| 12052 |
+
{
|
| 12053 |
+
"epoch": 1.2001499381069443,
|
| 12054 |
+
"grad_norm": 0.22683121263980865,
|
| 12055 |
+
"learning_rate": 4.7633872976338735e-05,
|
| 12056 |
+
"loss": 2.0708491802215576,
|
| 12057 |
+
"step": 3442
|
| 12058 |
+
},
|
| 12059 |
+
{
|
| 12060 |
+
"epoch": 1.2008473246508709,
|
| 12061 |
+
"grad_norm": 0.20178870856761932,
|
| 12062 |
+
"learning_rate": 4.759236197592362e-05,
|
| 12063 |
+
"loss": 2.0271801948547363,
|
| 12064 |
+
"step": 3444
|
| 12065 |
}
|
| 12066 |
],
|
| 12067 |
"logging_steps": 2,
|
|
|
|
| 12081 |
"attributes": {}
|
| 12082 |
}
|
| 12083 |
},
|
| 12084 |
+
"total_flos": 6.17737310217175e+17,
|
| 12085 |
"train_batch_size": 1,
|
| 12086 |
"trial_name": null,
|
| 12087 |
"trial_params": null
|