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 2390, 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:e52655733435b3d4ce3efdc524503203ef0ec2c0988a0a1282941070246603c8
|
| 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 1474334008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:460eb56bcdef88f21157bad81ceefe42e223941776c38881bd9cad6b305dceaf
|
| 3 |
size 1474334008
|
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 sha256:383ec48274162b7e8046e33e14f9cb751289b419a0f1fdc8fb2dde9ca4aaf4f1
|
| 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,
|
|
@@ -6700,6 +6700,1679 @@
|
|
| 6700 |
"learning_rate": 0.001,
|
| 6701 |
"loss": 1.5750374794006348,
|
| 6702 |
"step": 1912
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6703 |
}
|
| 6704 |
],
|
| 6705 |
"logging_steps": 2,
|
|
@@ -6719,7 +8392,7 @@
|
|
| 6719 |
"attributes": {}
|
| 6720 |
}
|
| 6721 |
},
|
| 6722 |
-
"total_flos":
|
| 6723 |
"train_batch_size": 1,
|
| 6724 |
"trial_name": null,
|
| 6725 |
"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": 2390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6700 |
"learning_rate": 0.001,
|
| 6701 |
"loss": 1.5750374794006348,
|
| 6702 |
"step": 1912
|
| 6703 |
+
},
|
| 6704 |
+
{
|
| 6705 |
+
"epoch": 0.8008787070453476,
|
| 6706 |
+
"grad_norm": 0.18541859090328217,
|
| 6707 |
+
"learning_rate": 0.001,
|
| 6708 |
+
"loss": 1.7187250852584839,
|
| 6709 |
+
"step": 1914
|
| 6710 |
+
},
|
| 6711 |
+
{
|
| 6712 |
+
"epoch": 0.8017155708980596,
|
| 6713 |
+
"grad_norm": 0.15337243676185608,
|
| 6714 |
+
"learning_rate": 0.001,
|
| 6715 |
+
"loss": 1.4911010265350342,
|
| 6716 |
+
"step": 1916
|
| 6717 |
+
},
|
| 6718 |
+
{
|
| 6719 |
+
"epoch": 0.8025524347507715,
|
| 6720 |
+
"grad_norm": 0.19465510547161102,
|
| 6721 |
+
"learning_rate": 0.001,
|
| 6722 |
+
"loss": 1.812168836593628,
|
| 6723 |
+
"step": 1918
|
| 6724 |
+
},
|
| 6725 |
+
{
|
| 6726 |
+
"epoch": 0.8033892986034834,
|
| 6727 |
+
"grad_norm": 0.19044692814350128,
|
| 6728 |
+
"learning_rate": 0.001,
|
| 6729 |
+
"loss": 1.7399373054504395,
|
| 6730 |
+
"step": 1920
|
| 6731 |
+
},
|
| 6732 |
+
{
|
| 6733 |
+
"epoch": 0.8042261624561954,
|
| 6734 |
+
"grad_norm": 0.1593402475118637,
|
| 6735 |
+
"learning_rate": 0.001,
|
| 6736 |
+
"loss": 1.8201937675476074,
|
| 6737 |
+
"step": 1922
|
| 6738 |
+
},
|
| 6739 |
+
{
|
| 6740 |
+
"epoch": 0.8050630263089074,
|
| 6741 |
+
"grad_norm": 0.18783608078956604,
|
| 6742 |
+
"learning_rate": 0.001,
|
| 6743 |
+
"loss": 1.7749743461608887,
|
| 6744 |
+
"step": 1924
|
| 6745 |
+
},
|
| 6746 |
+
{
|
| 6747 |
+
"epoch": 0.8058998901616193,
|
| 6748 |
+
"grad_norm": 0.19125783443450928,
|
| 6749 |
+
"learning_rate": 0.001,
|
| 6750 |
+
"loss": 1.787301778793335,
|
| 6751 |
+
"step": 1926
|
| 6752 |
+
},
|
| 6753 |
+
{
|
| 6754 |
+
"epoch": 0.8067367540143313,
|
| 6755 |
+
"grad_norm": 0.16956788301467896,
|
| 6756 |
+
"learning_rate": 0.001,
|
| 6757 |
+
"loss": 1.6546812057495117,
|
| 6758 |
+
"step": 1928
|
| 6759 |
+
},
|
| 6760 |
+
{
|
| 6761 |
+
"epoch": 0.8075736178670433,
|
| 6762 |
+
"grad_norm": 0.1768587827682495,
|
| 6763 |
+
"learning_rate": 0.001,
|
| 6764 |
+
"loss": 1.7468822002410889,
|
| 6765 |
+
"step": 1930
|
| 6766 |
+
},
|
| 6767 |
+
{
|
| 6768 |
+
"epoch": 0.8084104817197553,
|
| 6769 |
+
"grad_norm": 0.179947167634964,
|
| 6770 |
+
"learning_rate": 0.001,
|
| 6771 |
+
"loss": 1.6684801578521729,
|
| 6772 |
+
"step": 1932
|
| 6773 |
+
},
|
| 6774 |
+
{
|
| 6775 |
+
"epoch": 0.8092473455724671,
|
| 6776 |
+
"grad_norm": 0.13531339168548584,
|
| 6777 |
+
"learning_rate": 0.001,
|
| 6778 |
+
"loss": 1.769582748413086,
|
| 6779 |
+
"step": 1934
|
| 6780 |
+
},
|
| 6781 |
+
{
|
| 6782 |
+
"epoch": 0.8100842094251791,
|
| 6783 |
+
"grad_norm": 0.1797044724225998,
|
| 6784 |
+
"learning_rate": 0.001,
|
| 6785 |
+
"loss": 1.7164082527160645,
|
| 6786 |
+
"step": 1936
|
| 6787 |
+
},
|
| 6788 |
+
{
|
| 6789 |
+
"epoch": 0.8109210732778911,
|
| 6790 |
+
"grad_norm": 0.19026069343090057,
|
| 6791 |
+
"learning_rate": 0.001,
|
| 6792 |
+
"loss": 1.8381576538085938,
|
| 6793 |
+
"step": 1938
|
| 6794 |
+
},
|
| 6795 |
+
{
|
| 6796 |
+
"epoch": 0.8117579371306031,
|
| 6797 |
+
"grad_norm": 0.22501768171787262,
|
| 6798 |
+
"learning_rate": 0.001,
|
| 6799 |
+
"loss": 1.5857188701629639,
|
| 6800 |
+
"step": 1940
|
| 6801 |
+
},
|
| 6802 |
+
{
|
| 6803 |
+
"epoch": 0.812594800983315,
|
| 6804 |
+
"grad_norm": 0.2411017119884491,
|
| 6805 |
+
"learning_rate": 0.001,
|
| 6806 |
+
"loss": 1.8458359241485596,
|
| 6807 |
+
"step": 1942
|
| 6808 |
+
},
|
| 6809 |
+
{
|
| 6810 |
+
"epoch": 0.813431664836027,
|
| 6811 |
+
"grad_norm": 0.1693858802318573,
|
| 6812 |
+
"learning_rate": 0.001,
|
| 6813 |
+
"loss": 1.5694079399108887,
|
| 6814 |
+
"step": 1944
|
| 6815 |
+
},
|
| 6816 |
+
{
|
| 6817 |
+
"epoch": 0.814268528688739,
|
| 6818 |
+
"grad_norm": 0.17372514307498932,
|
| 6819 |
+
"learning_rate": 0.001,
|
| 6820 |
+
"loss": 1.7988512516021729,
|
| 6821 |
+
"step": 1946
|
| 6822 |
+
},
|
| 6823 |
+
{
|
| 6824 |
+
"epoch": 0.8151053925414509,
|
| 6825 |
+
"grad_norm": 0.16449512541294098,
|
| 6826 |
+
"learning_rate": 0.001,
|
| 6827 |
+
"loss": 1.5474469661712646,
|
| 6828 |
+
"step": 1948
|
| 6829 |
+
},
|
| 6830 |
+
{
|
| 6831 |
+
"epoch": 0.8159422563941628,
|
| 6832 |
+
"grad_norm": 0.1963464915752411,
|
| 6833 |
+
"learning_rate": 0.001,
|
| 6834 |
+
"loss": 1.7922284603118896,
|
| 6835 |
+
"step": 1950
|
| 6836 |
+
},
|
| 6837 |
+
{
|
| 6838 |
+
"epoch": 0.8167791202468748,
|
| 6839 |
+
"grad_norm": 0.21369586884975433,
|
| 6840 |
+
"learning_rate": 0.001,
|
| 6841 |
+
"loss": 1.6690380573272705,
|
| 6842 |
+
"step": 1952
|
| 6843 |
+
},
|
| 6844 |
+
{
|
| 6845 |
+
"epoch": 0.8176159840995868,
|
| 6846 |
+
"grad_norm": 0.219883993268013,
|
| 6847 |
+
"learning_rate": 0.001,
|
| 6848 |
+
"loss": 1.6787605285644531,
|
| 6849 |
+
"step": 1954
|
| 6850 |
+
},
|
| 6851 |
+
{
|
| 6852 |
+
"epoch": 0.8184528479522988,
|
| 6853 |
+
"grad_norm": 0.22343574464321136,
|
| 6854 |
+
"learning_rate": 0.001,
|
| 6855 |
+
"loss": 1.77901029586792,
|
| 6856 |
+
"step": 1956
|
| 6857 |
+
},
|
| 6858 |
+
{
|
| 6859 |
+
"epoch": 0.8192897118050108,
|
| 6860 |
+
"grad_norm": 0.17340721189975739,
|
| 6861 |
+
"learning_rate": 0.001,
|
| 6862 |
+
"loss": 1.7961761951446533,
|
| 6863 |
+
"step": 1958
|
| 6864 |
+
},
|
| 6865 |
+
{
|
| 6866 |
+
"epoch": 0.8201265756577227,
|
| 6867 |
+
"grad_norm": 0.13291603326797485,
|
| 6868 |
+
"learning_rate": 0.001,
|
| 6869 |
+
"loss": 1.7875564098358154,
|
| 6870 |
+
"step": 1960
|
| 6871 |
+
},
|
| 6872 |
+
{
|
| 6873 |
+
"epoch": 0.8209634395104346,
|
| 6874 |
+
"grad_norm": 0.1644572615623474,
|
| 6875 |
+
"learning_rate": 0.001,
|
| 6876 |
+
"loss": 1.5640647411346436,
|
| 6877 |
+
"step": 1962
|
| 6878 |
+
},
|
| 6879 |
+
{
|
| 6880 |
+
"epoch": 0.8218003033631466,
|
| 6881 |
+
"grad_norm": 0.22481782734394073,
|
| 6882 |
+
"learning_rate": 0.001,
|
| 6883 |
+
"loss": 1.80521821975708,
|
| 6884 |
+
"step": 1964
|
| 6885 |
+
},
|
| 6886 |
+
{
|
| 6887 |
+
"epoch": 0.8226371672158586,
|
| 6888 |
+
"grad_norm": 0.15211613476276398,
|
| 6889 |
+
"learning_rate": 0.001,
|
| 6890 |
+
"loss": 1.7417306900024414,
|
| 6891 |
+
"step": 1966
|
| 6892 |
+
},
|
| 6893 |
+
{
|
| 6894 |
+
"epoch": 0.8234740310685705,
|
| 6895 |
+
"grad_norm": 0.2112610638141632,
|
| 6896 |
+
"learning_rate": 0.001,
|
| 6897 |
+
"loss": 1.7976791858673096,
|
| 6898 |
+
"step": 1968
|
| 6899 |
+
},
|
| 6900 |
+
{
|
| 6901 |
+
"epoch": 0.8243108949212825,
|
| 6902 |
+
"grad_norm": 0.1616300791501999,
|
| 6903 |
+
"learning_rate": 0.001,
|
| 6904 |
+
"loss": 1.7184109687805176,
|
| 6905 |
+
"step": 1970
|
| 6906 |
+
},
|
| 6907 |
+
{
|
| 6908 |
+
"epoch": 0.8251477587739945,
|
| 6909 |
+
"grad_norm": 0.21595650911331177,
|
| 6910 |
+
"learning_rate": 0.001,
|
| 6911 |
+
"loss": 1.8706190586090088,
|
| 6912 |
+
"step": 1972
|
| 6913 |
+
},
|
| 6914 |
+
{
|
| 6915 |
+
"epoch": 0.8259846226267065,
|
| 6916 |
+
"grad_norm": 0.23136265575885773,
|
| 6917 |
+
"learning_rate": 0.001,
|
| 6918 |
+
"loss": 1.6742208003997803,
|
| 6919 |
+
"step": 1974
|
| 6920 |
+
},
|
| 6921 |
+
{
|
| 6922 |
+
"epoch": 0.8268214864794183,
|
| 6923 |
+
"grad_norm": 0.16773709654808044,
|
| 6924 |
+
"learning_rate": 0.001,
|
| 6925 |
+
"loss": 1.7967098951339722,
|
| 6926 |
+
"step": 1976
|
| 6927 |
+
},
|
| 6928 |
+
{
|
| 6929 |
+
"epoch": 0.8276583503321303,
|
| 6930 |
+
"grad_norm": 0.1996687650680542,
|
| 6931 |
+
"learning_rate": 0.001,
|
| 6932 |
+
"loss": 1.840228796005249,
|
| 6933 |
+
"step": 1978
|
| 6934 |
+
},
|
| 6935 |
+
{
|
| 6936 |
+
"epoch": 0.8284952141848423,
|
| 6937 |
+
"grad_norm": 0.1655055731534958,
|
| 6938 |
+
"learning_rate": 0.001,
|
| 6939 |
+
"loss": 1.7580664157867432,
|
| 6940 |
+
"step": 1980
|
| 6941 |
+
},
|
| 6942 |
+
{
|
| 6943 |
+
"epoch": 0.8293320780375543,
|
| 6944 |
+
"grad_norm": 0.14678531885147095,
|
| 6945 |
+
"learning_rate": 0.001,
|
| 6946 |
+
"loss": 1.8079349994659424,
|
| 6947 |
+
"step": 1982
|
| 6948 |
+
},
|
| 6949 |
+
{
|
| 6950 |
+
"epoch": 0.8301689418902662,
|
| 6951 |
+
"grad_norm": 0.13893921673297882,
|
| 6952 |
+
"learning_rate": 0.001,
|
| 6953 |
+
"loss": 1.8913166522979736,
|
| 6954 |
+
"step": 1984
|
| 6955 |
+
},
|
| 6956 |
+
{
|
| 6957 |
+
"epoch": 0.8310058057429782,
|
| 6958 |
+
"grad_norm": 0.15185657143592834,
|
| 6959 |
+
"learning_rate": 0.001,
|
| 6960 |
+
"loss": 1.783323049545288,
|
| 6961 |
+
"step": 1986
|
| 6962 |
+
},
|
| 6963 |
+
{
|
| 6964 |
+
"epoch": 0.8318426695956902,
|
| 6965 |
+
"grad_norm": 0.17148081958293915,
|
| 6966 |
+
"learning_rate": 0.001,
|
| 6967 |
+
"loss": 1.854668378829956,
|
| 6968 |
+
"step": 1988
|
| 6969 |
+
},
|
| 6970 |
+
{
|
| 6971 |
+
"epoch": 0.8326795334484021,
|
| 6972 |
+
"grad_norm": 0.17217256128787994,
|
| 6973 |
+
"learning_rate": 0.001,
|
| 6974 |
+
"loss": 1.8561267852783203,
|
| 6975 |
+
"step": 1990
|
| 6976 |
+
},
|
| 6977 |
+
{
|
| 6978 |
+
"epoch": 0.833516397301114,
|
| 6979 |
+
"grad_norm": 0.1572037935256958,
|
| 6980 |
+
"learning_rate": 0.001,
|
| 6981 |
+
"loss": 1.8157644271850586,
|
| 6982 |
+
"step": 1992
|
| 6983 |
+
},
|
| 6984 |
+
{
|
| 6985 |
+
"epoch": 0.834353261153826,
|
| 6986 |
+
"grad_norm": 0.17767813801765442,
|
| 6987 |
+
"learning_rate": 0.001,
|
| 6988 |
+
"loss": 1.9732893705368042,
|
| 6989 |
+
"step": 1994
|
| 6990 |
+
},
|
| 6991 |
+
{
|
| 6992 |
+
"epoch": 0.835190125006538,
|
| 6993 |
+
"grad_norm": 0.15681202709674835,
|
| 6994 |
+
"learning_rate": 0.001,
|
| 6995 |
+
"loss": 1.5723509788513184,
|
| 6996 |
+
"step": 1996
|
| 6997 |
+
},
|
| 6998 |
+
{
|
| 6999 |
+
"epoch": 0.83602698885925,
|
| 7000 |
+
"grad_norm": 0.2063862383365631,
|
| 7001 |
+
"learning_rate": 0.001,
|
| 7002 |
+
"loss": 1.719078779220581,
|
| 7003 |
+
"step": 1998
|
| 7004 |
+
},
|
| 7005 |
+
{
|
| 7006 |
+
"epoch": 0.836863852711962,
|
| 7007 |
+
"grad_norm": 0.20288808643817902,
|
| 7008 |
+
"learning_rate": 0.001,
|
| 7009 |
+
"loss": 1.7376391887664795,
|
| 7010 |
+
"step": 2000
|
| 7011 |
+
},
|
| 7012 |
+
{
|
| 7013 |
+
"epoch": 0.8377007165646739,
|
| 7014 |
+
"grad_norm": 0.2052176296710968,
|
| 7015 |
+
"learning_rate": 0.001,
|
| 7016 |
+
"loss": 1.9078187942504883,
|
| 7017 |
+
"step": 2002
|
| 7018 |
+
},
|
| 7019 |
+
{
|
| 7020 |
+
"epoch": 0.8385375804173858,
|
| 7021 |
+
"grad_norm": 0.17048625648021698,
|
| 7022 |
+
"learning_rate": 0.001,
|
| 7023 |
+
"loss": 1.8494555950164795,
|
| 7024 |
+
"step": 2004
|
| 7025 |
+
},
|
| 7026 |
+
{
|
| 7027 |
+
"epoch": 0.8393744442700978,
|
| 7028 |
+
"grad_norm": 0.1995612233877182,
|
| 7029 |
+
"learning_rate": 0.001,
|
| 7030 |
+
"loss": 1.8631731271743774,
|
| 7031 |
+
"step": 2006
|
| 7032 |
+
},
|
| 7033 |
+
{
|
| 7034 |
+
"epoch": 0.8402113081228098,
|
| 7035 |
+
"grad_norm": 0.1468971222639084,
|
| 7036 |
+
"learning_rate": 0.001,
|
| 7037 |
+
"loss": 1.823561191558838,
|
| 7038 |
+
"step": 2008
|
| 7039 |
+
},
|
| 7040 |
+
{
|
| 7041 |
+
"epoch": 0.8410481719755217,
|
| 7042 |
+
"grad_norm": 0.22361773252487183,
|
| 7043 |
+
"learning_rate": 0.001,
|
| 7044 |
+
"loss": 1.732271432876587,
|
| 7045 |
+
"step": 2010
|
| 7046 |
+
},
|
| 7047 |
+
{
|
| 7048 |
+
"epoch": 0.8418850358282337,
|
| 7049 |
+
"grad_norm": 0.15663482248783112,
|
| 7050 |
+
"learning_rate": 0.001,
|
| 7051 |
+
"loss": 1.9358609914779663,
|
| 7052 |
+
"step": 2012
|
| 7053 |
+
},
|
| 7054 |
+
{
|
| 7055 |
+
"epoch": 0.8427218996809457,
|
| 7056 |
+
"grad_norm": 0.12529081106185913,
|
| 7057 |
+
"learning_rate": 0.001,
|
| 7058 |
+
"loss": 1.8782525062561035,
|
| 7059 |
+
"step": 2014
|
| 7060 |
+
},
|
| 7061 |
+
{
|
| 7062 |
+
"epoch": 0.8435587635336577,
|
| 7063 |
+
"grad_norm": 0.19204527139663696,
|
| 7064 |
+
"learning_rate": 0.001,
|
| 7065 |
+
"loss": 1.9156935214996338,
|
| 7066 |
+
"step": 2016
|
| 7067 |
+
},
|
| 7068 |
+
{
|
| 7069 |
+
"epoch": 0.8443956273863695,
|
| 7070 |
+
"grad_norm": 0.18922653794288635,
|
| 7071 |
+
"learning_rate": 0.001,
|
| 7072 |
+
"loss": 1.7407567501068115,
|
| 7073 |
+
"step": 2018
|
| 7074 |
+
},
|
| 7075 |
+
{
|
| 7076 |
+
"epoch": 0.8452324912390815,
|
| 7077 |
+
"grad_norm": 0.15841731429100037,
|
| 7078 |
+
"learning_rate": 0.001,
|
| 7079 |
+
"loss": 1.8612581491470337,
|
| 7080 |
+
"step": 2020
|
| 7081 |
+
},
|
| 7082 |
+
{
|
| 7083 |
+
"epoch": 0.8460693550917935,
|
| 7084 |
+
"grad_norm": 0.15407481789588928,
|
| 7085 |
+
"learning_rate": 0.001,
|
| 7086 |
+
"loss": 1.8040993213653564,
|
| 7087 |
+
"step": 2022
|
| 7088 |
+
},
|
| 7089 |
+
{
|
| 7090 |
+
"epoch": 0.8469062189445055,
|
| 7091 |
+
"grad_norm": 0.18015125393867493,
|
| 7092 |
+
"learning_rate": 0.001,
|
| 7093 |
+
"loss": 1.641503095626831,
|
| 7094 |
+
"step": 2024
|
| 7095 |
+
},
|
| 7096 |
+
{
|
| 7097 |
+
"epoch": 0.8477430827972174,
|
| 7098 |
+
"grad_norm": 0.16279159486293793,
|
| 7099 |
+
"learning_rate": 0.001,
|
| 7100 |
+
"loss": 1.7744803428649902,
|
| 7101 |
+
"step": 2026
|
| 7102 |
+
},
|
| 7103 |
+
{
|
| 7104 |
+
"epoch": 0.8485799466499294,
|
| 7105 |
+
"grad_norm": 0.18269069492816925,
|
| 7106 |
+
"learning_rate": 0.001,
|
| 7107 |
+
"loss": 1.8258600234985352,
|
| 7108 |
+
"step": 2028
|
| 7109 |
+
},
|
| 7110 |
+
{
|
| 7111 |
+
"epoch": 0.8494168105026414,
|
| 7112 |
+
"grad_norm": 0.1297500878572464,
|
| 7113 |
+
"learning_rate": 0.001,
|
| 7114 |
+
"loss": 1.8746222257614136,
|
| 7115 |
+
"step": 2030
|
| 7116 |
+
},
|
| 7117 |
+
{
|
| 7118 |
+
"epoch": 0.8502536743553533,
|
| 7119 |
+
"grad_norm": 0.15231531858444214,
|
| 7120 |
+
"learning_rate": 0.001,
|
| 7121 |
+
"loss": 1.805553913116455,
|
| 7122 |
+
"step": 2032
|
| 7123 |
+
},
|
| 7124 |
+
{
|
| 7125 |
+
"epoch": 0.8510905382080652,
|
| 7126 |
+
"grad_norm": 0.158281147480011,
|
| 7127 |
+
"learning_rate": 0.001,
|
| 7128 |
+
"loss": 1.931082844734192,
|
| 7129 |
+
"step": 2034
|
| 7130 |
+
},
|
| 7131 |
+
{
|
| 7132 |
+
"epoch": 0.8519274020607772,
|
| 7133 |
+
"grad_norm": 0.25840476155281067,
|
| 7134 |
+
"learning_rate": 0.001,
|
| 7135 |
+
"loss": 1.7289047241210938,
|
| 7136 |
+
"step": 2036
|
| 7137 |
+
},
|
| 7138 |
+
{
|
| 7139 |
+
"epoch": 0.8527642659134892,
|
| 7140 |
+
"grad_norm": 0.17197325825691223,
|
| 7141 |
+
"learning_rate": 0.001,
|
| 7142 |
+
"loss": 1.970015287399292,
|
| 7143 |
+
"step": 2038
|
| 7144 |
+
},
|
| 7145 |
+
{
|
| 7146 |
+
"epoch": 0.8536011297662012,
|
| 7147 |
+
"grad_norm": 0.14023809134960175,
|
| 7148 |
+
"learning_rate": 0.001,
|
| 7149 |
+
"loss": 1.6440021991729736,
|
| 7150 |
+
"step": 2040
|
| 7151 |
+
},
|
| 7152 |
+
{
|
| 7153 |
+
"epoch": 0.8544379936189131,
|
| 7154 |
+
"grad_norm": 0.1766403317451477,
|
| 7155 |
+
"learning_rate": 0.001,
|
| 7156 |
+
"loss": 1.8277117013931274,
|
| 7157 |
+
"step": 2042
|
| 7158 |
+
},
|
| 7159 |
+
{
|
| 7160 |
+
"epoch": 0.8552748574716251,
|
| 7161 |
+
"grad_norm": 0.13199423253536224,
|
| 7162 |
+
"learning_rate": 0.001,
|
| 7163 |
+
"loss": 1.8313090801239014,
|
| 7164 |
+
"step": 2044
|
| 7165 |
+
},
|
| 7166 |
+
{
|
| 7167 |
+
"epoch": 0.856111721324337,
|
| 7168 |
+
"grad_norm": 0.14533200860023499,
|
| 7169 |
+
"learning_rate": 0.001,
|
| 7170 |
+
"loss": 1.856020212173462,
|
| 7171 |
+
"step": 2046
|
| 7172 |
+
},
|
| 7173 |
+
{
|
| 7174 |
+
"epoch": 0.856948585177049,
|
| 7175 |
+
"grad_norm": 0.1710338592529297,
|
| 7176 |
+
"learning_rate": 0.001,
|
| 7177 |
+
"loss": 1.8515350818634033,
|
| 7178 |
+
"step": 2048
|
| 7179 |
+
},
|
| 7180 |
+
{
|
| 7181 |
+
"epoch": 0.857785449029761,
|
| 7182 |
+
"grad_norm": 0.1507275104522705,
|
| 7183 |
+
"learning_rate": 0.001,
|
| 7184 |
+
"loss": 1.9485504627227783,
|
| 7185 |
+
"step": 2050
|
| 7186 |
+
},
|
| 7187 |
+
{
|
| 7188 |
+
"epoch": 0.8586223128824729,
|
| 7189 |
+
"grad_norm": 0.1707591712474823,
|
| 7190 |
+
"learning_rate": 0.001,
|
| 7191 |
+
"loss": 1.6432266235351562,
|
| 7192 |
+
"step": 2052
|
| 7193 |
+
},
|
| 7194 |
+
{
|
| 7195 |
+
"epoch": 0.8594591767351849,
|
| 7196 |
+
"grad_norm": 0.16228087246418,
|
| 7197 |
+
"learning_rate": 0.001,
|
| 7198 |
+
"loss": 1.6685106754302979,
|
| 7199 |
+
"step": 2054
|
| 7200 |
+
},
|
| 7201 |
+
{
|
| 7202 |
+
"epoch": 0.8602960405878969,
|
| 7203 |
+
"grad_norm": 0.1753338873386383,
|
| 7204 |
+
"learning_rate": 0.001,
|
| 7205 |
+
"loss": 1.7731640338897705,
|
| 7206 |
+
"step": 2056
|
| 7207 |
+
},
|
| 7208 |
+
{
|
| 7209 |
+
"epoch": 0.8611329044406089,
|
| 7210 |
+
"grad_norm": 0.13992726802825928,
|
| 7211 |
+
"learning_rate": 0.001,
|
| 7212 |
+
"loss": 1.732918381690979,
|
| 7213 |
+
"step": 2058
|
| 7214 |
+
},
|
| 7215 |
+
{
|
| 7216 |
+
"epoch": 0.8619697682933207,
|
| 7217 |
+
"grad_norm": 0.1424381583929062,
|
| 7218 |
+
"learning_rate": 0.001,
|
| 7219 |
+
"loss": 1.7127492427825928,
|
| 7220 |
+
"step": 2060
|
| 7221 |
+
},
|
| 7222 |
+
{
|
| 7223 |
+
"epoch": 0.8628066321460327,
|
| 7224 |
+
"grad_norm": 0.1462409794330597,
|
| 7225 |
+
"learning_rate": 0.001,
|
| 7226 |
+
"loss": 1.995692491531372,
|
| 7227 |
+
"step": 2062
|
| 7228 |
+
},
|
| 7229 |
+
{
|
| 7230 |
+
"epoch": 0.8636434959987447,
|
| 7231 |
+
"grad_norm": 0.24198666214942932,
|
| 7232 |
+
"learning_rate": 0.001,
|
| 7233 |
+
"loss": 1.7832610607147217,
|
| 7234 |
+
"step": 2064
|
| 7235 |
+
},
|
| 7236 |
+
{
|
| 7237 |
+
"epoch": 0.8644803598514567,
|
| 7238 |
+
"grad_norm": 0.15131376683712006,
|
| 7239 |
+
"learning_rate": 0.001,
|
| 7240 |
+
"loss": 1.807303547859192,
|
| 7241 |
+
"step": 2066
|
| 7242 |
+
},
|
| 7243 |
+
{
|
| 7244 |
+
"epoch": 0.8653172237041686,
|
| 7245 |
+
"grad_norm": 0.15203239023685455,
|
| 7246 |
+
"learning_rate": 0.001,
|
| 7247 |
+
"loss": 1.8433125019073486,
|
| 7248 |
+
"step": 2068
|
| 7249 |
+
},
|
| 7250 |
+
{
|
| 7251 |
+
"epoch": 0.8661540875568806,
|
| 7252 |
+
"grad_norm": 0.12948307394981384,
|
| 7253 |
+
"learning_rate": 0.001,
|
| 7254 |
+
"loss": 1.8733514547348022,
|
| 7255 |
+
"step": 2070
|
| 7256 |
+
},
|
| 7257 |
+
{
|
| 7258 |
+
"epoch": 0.8669909514095926,
|
| 7259 |
+
"grad_norm": 0.22463731467723846,
|
| 7260 |
+
"learning_rate": 0.001,
|
| 7261 |
+
"loss": 1.6698576211929321,
|
| 7262 |
+
"step": 2072
|
| 7263 |
+
},
|
| 7264 |
+
{
|
| 7265 |
+
"epoch": 0.8678278152623045,
|
| 7266 |
+
"grad_norm": 0.1957893669605255,
|
| 7267 |
+
"learning_rate": 0.001,
|
| 7268 |
+
"loss": 1.8365139961242676,
|
| 7269 |
+
"step": 2074
|
| 7270 |
+
},
|
| 7271 |
+
{
|
| 7272 |
+
"epoch": 0.8686646791150164,
|
| 7273 |
+
"grad_norm": 0.1871940791606903,
|
| 7274 |
+
"learning_rate": 0.001,
|
| 7275 |
+
"loss": 1.8016531467437744,
|
| 7276 |
+
"step": 2076
|
| 7277 |
+
},
|
| 7278 |
+
{
|
| 7279 |
+
"epoch": 0.8695015429677284,
|
| 7280 |
+
"grad_norm": 0.144826278090477,
|
| 7281 |
+
"learning_rate": 0.001,
|
| 7282 |
+
"loss": 1.7277615070343018,
|
| 7283 |
+
"step": 2078
|
| 7284 |
+
},
|
| 7285 |
+
{
|
| 7286 |
+
"epoch": 0.8703384068204404,
|
| 7287 |
+
"grad_norm": 0.24124889075756073,
|
| 7288 |
+
"learning_rate": 0.001,
|
| 7289 |
+
"loss": 1.6914912462234497,
|
| 7290 |
+
"step": 2080
|
| 7291 |
+
},
|
| 7292 |
+
{
|
| 7293 |
+
"epoch": 0.8711752706731524,
|
| 7294 |
+
"grad_norm": 0.19697104394435883,
|
| 7295 |
+
"learning_rate": 0.001,
|
| 7296 |
+
"loss": 1.757760763168335,
|
| 7297 |
+
"step": 2082
|
| 7298 |
+
},
|
| 7299 |
+
{
|
| 7300 |
+
"epoch": 0.8720121345258643,
|
| 7301 |
+
"grad_norm": 0.2218928188085556,
|
| 7302 |
+
"learning_rate": 0.001,
|
| 7303 |
+
"loss": 1.794978380203247,
|
| 7304 |
+
"step": 2084
|
| 7305 |
+
},
|
| 7306 |
+
{
|
| 7307 |
+
"epoch": 0.8728489983785763,
|
| 7308 |
+
"grad_norm": 0.1601993590593338,
|
| 7309 |
+
"learning_rate": 0.001,
|
| 7310 |
+
"loss": 1.9281600713729858,
|
| 7311 |
+
"step": 2086
|
| 7312 |
+
},
|
| 7313 |
+
{
|
| 7314 |
+
"epoch": 0.8736858622312883,
|
| 7315 |
+
"grad_norm": 0.22936826944351196,
|
| 7316 |
+
"learning_rate": 0.001,
|
| 7317 |
+
"loss": 1.8702476024627686,
|
| 7318 |
+
"step": 2088
|
| 7319 |
+
},
|
| 7320 |
+
{
|
| 7321 |
+
"epoch": 0.8745227260840002,
|
| 7322 |
+
"grad_norm": 0.2923980951309204,
|
| 7323 |
+
"learning_rate": 0.001,
|
| 7324 |
+
"loss": 1.8755650520324707,
|
| 7325 |
+
"step": 2090
|
| 7326 |
+
},
|
| 7327 |
+
{
|
| 7328 |
+
"epoch": 0.8753595899367121,
|
| 7329 |
+
"grad_norm": 0.20953232049942017,
|
| 7330 |
+
"learning_rate": 0.001,
|
| 7331 |
+
"loss": 1.7643380165100098,
|
| 7332 |
+
"step": 2092
|
| 7333 |
+
},
|
| 7334 |
+
{
|
| 7335 |
+
"epoch": 0.8761964537894241,
|
| 7336 |
+
"grad_norm": 0.20394261181354523,
|
| 7337 |
+
"learning_rate": 0.001,
|
| 7338 |
+
"loss": 1.6504666805267334,
|
| 7339 |
+
"step": 2094
|
| 7340 |
+
},
|
| 7341 |
+
{
|
| 7342 |
+
"epoch": 0.8770333176421361,
|
| 7343 |
+
"grad_norm": 0.20065777003765106,
|
| 7344 |
+
"learning_rate": 0.001,
|
| 7345 |
+
"loss": 1.612877368927002,
|
| 7346 |
+
"step": 2096
|
| 7347 |
+
},
|
| 7348 |
+
{
|
| 7349 |
+
"epoch": 0.8778701814948481,
|
| 7350 |
+
"grad_norm": 0.17852096259593964,
|
| 7351 |
+
"learning_rate": 0.001,
|
| 7352 |
+
"loss": 1.7216291427612305,
|
| 7353 |
+
"step": 2098
|
| 7354 |
+
},
|
| 7355 |
+
{
|
| 7356 |
+
"epoch": 0.8787070453475601,
|
| 7357 |
+
"grad_norm": 0.17607370018959045,
|
| 7358 |
+
"learning_rate": 0.001,
|
| 7359 |
+
"loss": 1.8312411308288574,
|
| 7360 |
+
"step": 2100
|
| 7361 |
+
},
|
| 7362 |
+
{
|
| 7363 |
+
"epoch": 0.879543909200272,
|
| 7364 |
+
"grad_norm": 0.13718557357788086,
|
| 7365 |
+
"learning_rate": 0.001,
|
| 7366 |
+
"loss": 1.9145517349243164,
|
| 7367 |
+
"step": 2102
|
| 7368 |
+
},
|
| 7369 |
+
{
|
| 7370 |
+
"epoch": 0.8803807730529839,
|
| 7371 |
+
"grad_norm": 0.1588200330734253,
|
| 7372 |
+
"learning_rate": 0.001,
|
| 7373 |
+
"loss": 1.7832763195037842,
|
| 7374 |
+
"step": 2104
|
| 7375 |
+
},
|
| 7376 |
+
{
|
| 7377 |
+
"epoch": 0.8812176369056959,
|
| 7378 |
+
"grad_norm": 0.1565677970647812,
|
| 7379 |
+
"learning_rate": 0.001,
|
| 7380 |
+
"loss": 1.8550148010253906,
|
| 7381 |
+
"step": 2106
|
| 7382 |
+
},
|
| 7383 |
+
{
|
| 7384 |
+
"epoch": 0.8820545007584079,
|
| 7385 |
+
"grad_norm": 0.14876368641853333,
|
| 7386 |
+
"learning_rate": 0.001,
|
| 7387 |
+
"loss": 1.7219643592834473,
|
| 7388 |
+
"step": 2108
|
| 7389 |
+
},
|
| 7390 |
+
{
|
| 7391 |
+
"epoch": 0.8828913646111198,
|
| 7392 |
+
"grad_norm": 0.1576692759990692,
|
| 7393 |
+
"learning_rate": 0.001,
|
| 7394 |
+
"loss": 1.6406712532043457,
|
| 7395 |
+
"step": 2110
|
| 7396 |
+
},
|
| 7397 |
+
{
|
| 7398 |
+
"epoch": 0.8837282284638318,
|
| 7399 |
+
"grad_norm": 0.20295579731464386,
|
| 7400 |
+
"learning_rate": 0.001,
|
| 7401 |
+
"loss": 1.7512174844741821,
|
| 7402 |
+
"step": 2112
|
| 7403 |
+
},
|
| 7404 |
+
{
|
| 7405 |
+
"epoch": 0.8845650923165438,
|
| 7406 |
+
"grad_norm": 0.1610012948513031,
|
| 7407 |
+
"learning_rate": 0.001,
|
| 7408 |
+
"loss": 1.724219799041748,
|
| 7409 |
+
"step": 2114
|
| 7410 |
+
},
|
| 7411 |
+
{
|
| 7412 |
+
"epoch": 0.8854019561692558,
|
| 7413 |
+
"grad_norm": 0.17259804904460907,
|
| 7414 |
+
"learning_rate": 0.001,
|
| 7415 |
+
"loss": 1.9398645162582397,
|
| 7416 |
+
"step": 2116
|
| 7417 |
+
},
|
| 7418 |
+
{
|
| 7419 |
+
"epoch": 0.8862388200219676,
|
| 7420 |
+
"grad_norm": 0.15903180837631226,
|
| 7421 |
+
"learning_rate": 0.001,
|
| 7422 |
+
"loss": 1.727034091949463,
|
| 7423 |
+
"step": 2118
|
| 7424 |
+
},
|
| 7425 |
+
{
|
| 7426 |
+
"epoch": 0.8870756838746796,
|
| 7427 |
+
"grad_norm": 0.21106839179992676,
|
| 7428 |
+
"learning_rate": 0.001,
|
| 7429 |
+
"loss": 1.5464601516723633,
|
| 7430 |
+
"step": 2120
|
| 7431 |
+
},
|
| 7432 |
+
{
|
| 7433 |
+
"epoch": 0.8879125477273916,
|
| 7434 |
+
"grad_norm": 0.15949273109436035,
|
| 7435 |
+
"learning_rate": 0.001,
|
| 7436 |
+
"loss": 1.9381368160247803,
|
| 7437 |
+
"step": 2122
|
| 7438 |
+
},
|
| 7439 |
+
{
|
| 7440 |
+
"epoch": 0.8887494115801036,
|
| 7441 |
+
"grad_norm": 0.14287099242210388,
|
| 7442 |
+
"learning_rate": 0.001,
|
| 7443 |
+
"loss": 1.8063201904296875,
|
| 7444 |
+
"step": 2124
|
| 7445 |
+
},
|
| 7446 |
+
{
|
| 7447 |
+
"epoch": 0.8895862754328155,
|
| 7448 |
+
"grad_norm": 0.18078364431858063,
|
| 7449 |
+
"learning_rate": 0.001,
|
| 7450 |
+
"loss": 1.4792810678482056,
|
| 7451 |
+
"step": 2126
|
| 7452 |
+
},
|
| 7453 |
+
{
|
| 7454 |
+
"epoch": 0.8904231392855275,
|
| 7455 |
+
"grad_norm": 0.2070651650428772,
|
| 7456 |
+
"learning_rate": 0.001,
|
| 7457 |
+
"loss": 1.7082228660583496,
|
| 7458 |
+
"step": 2128
|
| 7459 |
+
},
|
| 7460 |
+
{
|
| 7461 |
+
"epoch": 0.8912600031382395,
|
| 7462 |
+
"grad_norm": 0.13688793778419495,
|
| 7463 |
+
"learning_rate": 0.001,
|
| 7464 |
+
"loss": 1.8253896236419678,
|
| 7465 |
+
"step": 2130
|
| 7466 |
+
},
|
| 7467 |
+
{
|
| 7468 |
+
"epoch": 0.8920968669909514,
|
| 7469 |
+
"grad_norm": 0.1539553850889206,
|
| 7470 |
+
"learning_rate": 0.001,
|
| 7471 |
+
"loss": 1.8372070789337158,
|
| 7472 |
+
"step": 2132
|
| 7473 |
+
},
|
| 7474 |
+
{
|
| 7475 |
+
"epoch": 0.8929337308436633,
|
| 7476 |
+
"grad_norm": 0.1336880475282669,
|
| 7477 |
+
"learning_rate": 0.001,
|
| 7478 |
+
"loss": 1.635019063949585,
|
| 7479 |
+
"step": 2134
|
| 7480 |
+
},
|
| 7481 |
+
{
|
| 7482 |
+
"epoch": 0.8937705946963753,
|
| 7483 |
+
"grad_norm": 0.156386598944664,
|
| 7484 |
+
"learning_rate": 0.001,
|
| 7485 |
+
"loss": 1.7926678657531738,
|
| 7486 |
+
"step": 2136
|
| 7487 |
+
},
|
| 7488 |
+
{
|
| 7489 |
+
"epoch": 0.8946074585490873,
|
| 7490 |
+
"grad_norm": 0.20281647145748138,
|
| 7491 |
+
"learning_rate": 0.001,
|
| 7492 |
+
"loss": 1.7687244415283203,
|
| 7493 |
+
"step": 2138
|
| 7494 |
+
},
|
| 7495 |
+
{
|
| 7496 |
+
"epoch": 0.8954443224017993,
|
| 7497 |
+
"grad_norm": 0.1615990698337555,
|
| 7498 |
+
"learning_rate": 0.001,
|
| 7499 |
+
"loss": 1.6741787195205688,
|
| 7500 |
+
"step": 2140
|
| 7501 |
+
},
|
| 7502 |
+
{
|
| 7503 |
+
"epoch": 0.8962811862545113,
|
| 7504 |
+
"grad_norm": 0.17278769612312317,
|
| 7505 |
+
"learning_rate": 0.001,
|
| 7506 |
+
"loss": 1.6995149850845337,
|
| 7507 |
+
"step": 2142
|
| 7508 |
+
},
|
| 7509 |
+
{
|
| 7510 |
+
"epoch": 0.8971180501072232,
|
| 7511 |
+
"grad_norm": 0.17499259114265442,
|
| 7512 |
+
"learning_rate": 0.001,
|
| 7513 |
+
"loss": 1.7690184116363525,
|
| 7514 |
+
"step": 2144
|
| 7515 |
+
},
|
| 7516 |
+
{
|
| 7517 |
+
"epoch": 0.8979549139599351,
|
| 7518 |
+
"grad_norm": 0.14089493453502655,
|
| 7519 |
+
"learning_rate": 0.001,
|
| 7520 |
+
"loss": 1.8492329120635986,
|
| 7521 |
+
"step": 2146
|
| 7522 |
+
},
|
| 7523 |
+
{
|
| 7524 |
+
"epoch": 0.8987917778126471,
|
| 7525 |
+
"grad_norm": 0.1868445873260498,
|
| 7526 |
+
"learning_rate": 0.001,
|
| 7527 |
+
"loss": 1.7989699840545654,
|
| 7528 |
+
"step": 2148
|
| 7529 |
+
},
|
| 7530 |
+
{
|
| 7531 |
+
"epoch": 0.899628641665359,
|
| 7532 |
+
"grad_norm": 0.12193990498781204,
|
| 7533 |
+
"learning_rate": 0.001,
|
| 7534 |
+
"loss": 1.7744450569152832,
|
| 7535 |
+
"step": 2150
|
| 7536 |
+
},
|
| 7537 |
+
{
|
| 7538 |
+
"epoch": 0.900465505518071,
|
| 7539 |
+
"grad_norm": 0.17956677079200745,
|
| 7540 |
+
"learning_rate": 0.001,
|
| 7541 |
+
"loss": 1.8929543495178223,
|
| 7542 |
+
"step": 2152
|
| 7543 |
+
},
|
| 7544 |
+
{
|
| 7545 |
+
"epoch": 0.901302369370783,
|
| 7546 |
+
"grad_norm": 0.14579693973064423,
|
| 7547 |
+
"learning_rate": 0.001,
|
| 7548 |
+
"loss": 1.9915413856506348,
|
| 7549 |
+
"step": 2154
|
| 7550 |
+
},
|
| 7551 |
+
{
|
| 7552 |
+
"epoch": 0.902139233223495,
|
| 7553 |
+
"grad_norm": 0.11498692631721497,
|
| 7554 |
+
"learning_rate": 0.001,
|
| 7555 |
+
"loss": 1.7558211088180542,
|
| 7556 |
+
"step": 2156
|
| 7557 |
+
},
|
| 7558 |
+
{
|
| 7559 |
+
"epoch": 0.902976097076207,
|
| 7560 |
+
"grad_norm": 0.16237817704677582,
|
| 7561 |
+
"learning_rate": 0.001,
|
| 7562 |
+
"loss": 1.7932456731796265,
|
| 7563 |
+
"step": 2158
|
| 7564 |
+
},
|
| 7565 |
+
{
|
| 7566 |
+
"epoch": 0.9038129609289188,
|
| 7567 |
+
"grad_norm": 0.14826151728630066,
|
| 7568 |
+
"learning_rate": 0.001,
|
| 7569 |
+
"loss": 1.584397315979004,
|
| 7570 |
+
"step": 2160
|
| 7571 |
+
},
|
| 7572 |
+
{
|
| 7573 |
+
"epoch": 0.9046498247816308,
|
| 7574 |
+
"grad_norm": 0.15252980589866638,
|
| 7575 |
+
"learning_rate": 0.001,
|
| 7576 |
+
"loss": 1.4794797897338867,
|
| 7577 |
+
"step": 2162
|
| 7578 |
+
},
|
| 7579 |
+
{
|
| 7580 |
+
"epoch": 0.9054866886343428,
|
| 7581 |
+
"grad_norm": 0.13470305502414703,
|
| 7582 |
+
"learning_rate": 0.001,
|
| 7583 |
+
"loss": 1.8857436180114746,
|
| 7584 |
+
"step": 2164
|
| 7585 |
+
},
|
| 7586 |
+
{
|
| 7587 |
+
"epoch": 0.9063235524870548,
|
| 7588 |
+
"grad_norm": 0.14886556565761566,
|
| 7589 |
+
"learning_rate": 0.001,
|
| 7590 |
+
"loss": 1.7412769794464111,
|
| 7591 |
+
"step": 2166
|
| 7592 |
+
},
|
| 7593 |
+
{
|
| 7594 |
+
"epoch": 0.9071604163397667,
|
| 7595 |
+
"grad_norm": 0.16052448749542236,
|
| 7596 |
+
"learning_rate": 0.001,
|
| 7597 |
+
"loss": 1.6856763362884521,
|
| 7598 |
+
"step": 2168
|
| 7599 |
+
},
|
| 7600 |
+
{
|
| 7601 |
+
"epoch": 0.9079972801924787,
|
| 7602 |
+
"grad_norm": 0.17563699185848236,
|
| 7603 |
+
"learning_rate": 0.001,
|
| 7604 |
+
"loss": 1.6072168350219727,
|
| 7605 |
+
"step": 2170
|
| 7606 |
+
},
|
| 7607 |
+
{
|
| 7608 |
+
"epoch": 0.9088341440451907,
|
| 7609 |
+
"grad_norm": 0.12243790179491043,
|
| 7610 |
+
"learning_rate": 0.001,
|
| 7611 |
+
"loss": 1.8757920265197754,
|
| 7612 |
+
"step": 2172
|
| 7613 |
+
},
|
| 7614 |
+
{
|
| 7615 |
+
"epoch": 0.9096710078979026,
|
| 7616 |
+
"grad_norm": 0.12501704692840576,
|
| 7617 |
+
"learning_rate": 0.001,
|
| 7618 |
+
"loss": 1.8963994979858398,
|
| 7619 |
+
"step": 2174
|
| 7620 |
+
},
|
| 7621 |
+
{
|
| 7622 |
+
"epoch": 0.9105078717506145,
|
| 7623 |
+
"grad_norm": 0.20857881009578705,
|
| 7624 |
+
"learning_rate": 0.001,
|
| 7625 |
+
"loss": 1.8366215229034424,
|
| 7626 |
+
"step": 2176
|
| 7627 |
+
},
|
| 7628 |
+
{
|
| 7629 |
+
"epoch": 0.9113447356033265,
|
| 7630 |
+
"grad_norm": 0.20094241201877594,
|
| 7631 |
+
"learning_rate": 0.001,
|
| 7632 |
+
"loss": 1.6471312046051025,
|
| 7633 |
+
"step": 2178
|
| 7634 |
+
},
|
| 7635 |
+
{
|
| 7636 |
+
"epoch": 0.9121815994560385,
|
| 7637 |
+
"grad_norm": 0.14105327427387238,
|
| 7638 |
+
"learning_rate": 0.001,
|
| 7639 |
+
"loss": 1.860098958015442,
|
| 7640 |
+
"step": 2180
|
| 7641 |
+
},
|
| 7642 |
+
{
|
| 7643 |
+
"epoch": 0.9130184633087505,
|
| 7644 |
+
"grad_norm": 0.2128383219242096,
|
| 7645 |
+
"learning_rate": 0.001,
|
| 7646 |
+
"loss": 1.7795486450195312,
|
| 7647 |
+
"step": 2182
|
| 7648 |
+
},
|
| 7649 |
+
{
|
| 7650 |
+
"epoch": 0.9138553271614624,
|
| 7651 |
+
"grad_norm": 0.17474426329135895,
|
| 7652 |
+
"learning_rate": 0.001,
|
| 7653 |
+
"loss": 1.776687502861023,
|
| 7654 |
+
"step": 2184
|
| 7655 |
+
},
|
| 7656 |
+
{
|
| 7657 |
+
"epoch": 0.9146921910141744,
|
| 7658 |
+
"grad_norm": 0.1948438286781311,
|
| 7659 |
+
"learning_rate": 0.001,
|
| 7660 |
+
"loss": 1.8852334022521973,
|
| 7661 |
+
"step": 2186
|
| 7662 |
+
},
|
| 7663 |
+
{
|
| 7664 |
+
"epoch": 0.9155290548668863,
|
| 7665 |
+
"grad_norm": 0.15436647832393646,
|
| 7666 |
+
"learning_rate": 0.001,
|
| 7667 |
+
"loss": 1.83412504196167,
|
| 7668 |
+
"step": 2188
|
| 7669 |
+
},
|
| 7670 |
+
{
|
| 7671 |
+
"epoch": 0.9163659187195983,
|
| 7672 |
+
"grad_norm": 0.13561472296714783,
|
| 7673 |
+
"learning_rate": 0.001,
|
| 7674 |
+
"loss": 2.0936477184295654,
|
| 7675 |
+
"step": 2190
|
| 7676 |
+
},
|
| 7677 |
+
{
|
| 7678 |
+
"epoch": 0.9172027825723102,
|
| 7679 |
+
"grad_norm": 0.13945993781089783,
|
| 7680 |
+
"learning_rate": 0.001,
|
| 7681 |
+
"loss": 1.8204548358917236,
|
| 7682 |
+
"step": 2192
|
| 7683 |
+
},
|
| 7684 |
+
{
|
| 7685 |
+
"epoch": 0.9180396464250222,
|
| 7686 |
+
"grad_norm": 0.18486107885837555,
|
| 7687 |
+
"learning_rate": 0.001,
|
| 7688 |
+
"loss": 1.8775601387023926,
|
| 7689 |
+
"step": 2194
|
| 7690 |
+
},
|
| 7691 |
+
{
|
| 7692 |
+
"epoch": 0.9188765102777342,
|
| 7693 |
+
"grad_norm": 0.14845120906829834,
|
| 7694 |
+
"learning_rate": 0.001,
|
| 7695 |
+
"loss": 1.8602032661437988,
|
| 7696 |
+
"step": 2196
|
| 7697 |
+
},
|
| 7698 |
+
{
|
| 7699 |
+
"epoch": 0.9197133741304462,
|
| 7700 |
+
"grad_norm": 0.1462036371231079,
|
| 7701 |
+
"learning_rate": 0.001,
|
| 7702 |
+
"loss": 1.682769536972046,
|
| 7703 |
+
"step": 2198
|
| 7704 |
+
},
|
| 7705 |
+
{
|
| 7706 |
+
"epoch": 0.9205502379831582,
|
| 7707 |
+
"grad_norm": 0.12343576550483704,
|
| 7708 |
+
"learning_rate": 0.001,
|
| 7709 |
+
"loss": 1.680022120475769,
|
| 7710 |
+
"step": 2200
|
| 7711 |
+
},
|
| 7712 |
+
{
|
| 7713 |
+
"epoch": 0.92138710183587,
|
| 7714 |
+
"grad_norm": 0.18544532358646393,
|
| 7715 |
+
"learning_rate": 0.001,
|
| 7716 |
+
"loss": 1.562916874885559,
|
| 7717 |
+
"step": 2202
|
| 7718 |
+
},
|
| 7719 |
+
{
|
| 7720 |
+
"epoch": 0.922223965688582,
|
| 7721 |
+
"grad_norm": 0.12597911059856415,
|
| 7722 |
+
"learning_rate": 0.001,
|
| 7723 |
+
"loss": 1.9792215824127197,
|
| 7724 |
+
"step": 2204
|
| 7725 |
+
},
|
| 7726 |
+
{
|
| 7727 |
+
"epoch": 0.923060829541294,
|
| 7728 |
+
"grad_norm": 0.16657863557338715,
|
| 7729 |
+
"learning_rate": 0.001,
|
| 7730 |
+
"loss": 1.746931552886963,
|
| 7731 |
+
"step": 2206
|
| 7732 |
+
},
|
| 7733 |
+
{
|
| 7734 |
+
"epoch": 0.923897693394006,
|
| 7735 |
+
"grad_norm": 0.1881045550107956,
|
| 7736 |
+
"learning_rate": 0.001,
|
| 7737 |
+
"loss": 1.9043378829956055,
|
| 7738 |
+
"step": 2208
|
| 7739 |
+
},
|
| 7740 |
+
{
|
| 7741 |
+
"epoch": 0.9247345572467179,
|
| 7742 |
+
"grad_norm": 0.14851748943328857,
|
| 7743 |
+
"learning_rate": 0.001,
|
| 7744 |
+
"loss": 1.9416903257369995,
|
| 7745 |
+
"step": 2210
|
| 7746 |
+
},
|
| 7747 |
+
{
|
| 7748 |
+
"epoch": 0.9255714210994299,
|
| 7749 |
+
"grad_norm": 0.1394720822572708,
|
| 7750 |
+
"learning_rate": 0.001,
|
| 7751 |
+
"loss": 1.814441204071045,
|
| 7752 |
+
"step": 2212
|
| 7753 |
+
},
|
| 7754 |
+
{
|
| 7755 |
+
"epoch": 0.9264082849521419,
|
| 7756 |
+
"grad_norm": 0.19278284907341003,
|
| 7757 |
+
"learning_rate": 0.001,
|
| 7758 |
+
"loss": 1.8847565650939941,
|
| 7759 |
+
"step": 2214
|
| 7760 |
+
},
|
| 7761 |
+
{
|
| 7762 |
+
"epoch": 0.9272451488048538,
|
| 7763 |
+
"grad_norm": 0.15319499373435974,
|
| 7764 |
+
"learning_rate": 0.001,
|
| 7765 |
+
"loss": 1.7429678440093994,
|
| 7766 |
+
"step": 2216
|
| 7767 |
+
},
|
| 7768 |
+
{
|
| 7769 |
+
"epoch": 0.9280820126575657,
|
| 7770 |
+
"grad_norm": 0.17457795143127441,
|
| 7771 |
+
"learning_rate": 0.001,
|
| 7772 |
+
"loss": 1.7072155475616455,
|
| 7773 |
+
"step": 2218
|
| 7774 |
+
},
|
| 7775 |
+
{
|
| 7776 |
+
"epoch": 0.9289188765102777,
|
| 7777 |
+
"grad_norm": 0.14801710844039917,
|
| 7778 |
+
"learning_rate": 0.001,
|
| 7779 |
+
"loss": 1.7221653461456299,
|
| 7780 |
+
"step": 2220
|
| 7781 |
+
},
|
| 7782 |
+
{
|
| 7783 |
+
"epoch": 0.9297557403629897,
|
| 7784 |
+
"grad_norm": 0.1352171003818512,
|
| 7785 |
+
"learning_rate": 0.001,
|
| 7786 |
+
"loss": 1.6415488719940186,
|
| 7787 |
+
"step": 2222
|
| 7788 |
+
},
|
| 7789 |
+
{
|
| 7790 |
+
"epoch": 0.9305926042157017,
|
| 7791 |
+
"grad_norm": 0.22232243418693542,
|
| 7792 |
+
"learning_rate": 0.001,
|
| 7793 |
+
"loss": 1.6169863939285278,
|
| 7794 |
+
"step": 2224
|
| 7795 |
+
},
|
| 7796 |
+
{
|
| 7797 |
+
"epoch": 0.9314294680684136,
|
| 7798 |
+
"grad_norm": 0.1535181850194931,
|
| 7799 |
+
"learning_rate": 0.001,
|
| 7800 |
+
"loss": 1.6853687763214111,
|
| 7801 |
+
"step": 2226
|
| 7802 |
+
},
|
| 7803 |
+
{
|
| 7804 |
+
"epoch": 0.9322663319211256,
|
| 7805 |
+
"grad_norm": 0.1976948380470276,
|
| 7806 |
+
"learning_rate": 0.001,
|
| 7807 |
+
"loss": 1.6605194807052612,
|
| 7808 |
+
"step": 2228
|
| 7809 |
+
},
|
| 7810 |
+
{
|
| 7811 |
+
"epoch": 0.9331031957738375,
|
| 7812 |
+
"grad_norm": 0.16368044912815094,
|
| 7813 |
+
"learning_rate": 0.001,
|
| 7814 |
+
"loss": 1.5667176246643066,
|
| 7815 |
+
"step": 2230
|
| 7816 |
+
},
|
| 7817 |
+
{
|
| 7818 |
+
"epoch": 0.9339400596265495,
|
| 7819 |
+
"grad_norm": 0.16502605378627777,
|
| 7820 |
+
"learning_rate": 0.001,
|
| 7821 |
+
"loss": 1.7962485551834106,
|
| 7822 |
+
"step": 2232
|
| 7823 |
+
},
|
| 7824 |
+
{
|
| 7825 |
+
"epoch": 0.9347769234792614,
|
| 7826 |
+
"grad_norm": 0.12575078010559082,
|
| 7827 |
+
"learning_rate": 0.001,
|
| 7828 |
+
"loss": 1.6512104272842407,
|
| 7829 |
+
"step": 2234
|
| 7830 |
+
},
|
| 7831 |
+
{
|
| 7832 |
+
"epoch": 0.9356137873319734,
|
| 7833 |
+
"grad_norm": 0.20270049571990967,
|
| 7834 |
+
"learning_rate": 0.001,
|
| 7835 |
+
"loss": 2.0745935440063477,
|
| 7836 |
+
"step": 2236
|
| 7837 |
+
},
|
| 7838 |
+
{
|
| 7839 |
+
"epoch": 0.9364506511846854,
|
| 7840 |
+
"grad_norm": 0.15469059348106384,
|
| 7841 |
+
"learning_rate": 0.001,
|
| 7842 |
+
"loss": 1.7359304428100586,
|
| 7843 |
+
"step": 2238
|
| 7844 |
+
},
|
| 7845 |
+
{
|
| 7846 |
+
"epoch": 0.9372875150373974,
|
| 7847 |
+
"grad_norm": 0.28041937947273254,
|
| 7848 |
+
"learning_rate": 0.001,
|
| 7849 |
+
"loss": 1.8423943519592285,
|
| 7850 |
+
"step": 2240
|
| 7851 |
+
},
|
| 7852 |
+
{
|
| 7853 |
+
"epoch": 0.9381243788901094,
|
| 7854 |
+
"grad_norm": 0.19254353642463684,
|
| 7855 |
+
"learning_rate": 0.001,
|
| 7856 |
+
"loss": 1.7136001586914062,
|
| 7857 |
+
"step": 2242
|
| 7858 |
+
},
|
| 7859 |
+
{
|
| 7860 |
+
"epoch": 0.9389612427428212,
|
| 7861 |
+
"grad_norm": 0.2116895467042923,
|
| 7862 |
+
"learning_rate": 0.001,
|
| 7863 |
+
"loss": 1.6672697067260742,
|
| 7864 |
+
"step": 2244
|
| 7865 |
+
},
|
| 7866 |
+
{
|
| 7867 |
+
"epoch": 0.9397981065955332,
|
| 7868 |
+
"grad_norm": 0.15302026271820068,
|
| 7869 |
+
"learning_rate": 0.001,
|
| 7870 |
+
"loss": 1.6999967098236084,
|
| 7871 |
+
"step": 2246
|
| 7872 |
+
},
|
| 7873 |
+
{
|
| 7874 |
+
"epoch": 0.9406349704482452,
|
| 7875 |
+
"grad_norm": 0.17118774354457855,
|
| 7876 |
+
"learning_rate": 0.001,
|
| 7877 |
+
"loss": 1.7615493535995483,
|
| 7878 |
+
"step": 2248
|
| 7879 |
+
},
|
| 7880 |
+
{
|
| 7881 |
+
"epoch": 0.9414718343009572,
|
| 7882 |
+
"grad_norm": 0.1692219078540802,
|
| 7883 |
+
"learning_rate": 0.001,
|
| 7884 |
+
"loss": 1.8158268928527832,
|
| 7885 |
+
"step": 2250
|
| 7886 |
+
},
|
| 7887 |
+
{
|
| 7888 |
+
"epoch": 0.9423086981536691,
|
| 7889 |
+
"grad_norm": 0.1482219696044922,
|
| 7890 |
+
"learning_rate": 0.001,
|
| 7891 |
+
"loss": 1.743995189666748,
|
| 7892 |
+
"step": 2252
|
| 7893 |
+
},
|
| 7894 |
+
{
|
| 7895 |
+
"epoch": 0.9431455620063811,
|
| 7896 |
+
"grad_norm": 0.18909083306789398,
|
| 7897 |
+
"learning_rate": 0.001,
|
| 7898 |
+
"loss": 1.685924768447876,
|
| 7899 |
+
"step": 2254
|
| 7900 |
+
},
|
| 7901 |
+
{
|
| 7902 |
+
"epoch": 0.9439824258590931,
|
| 7903 |
+
"grad_norm": 0.14254391193389893,
|
| 7904 |
+
"learning_rate": 0.001,
|
| 7905 |
+
"loss": 1.675020694732666,
|
| 7906 |
+
"step": 2256
|
| 7907 |
+
},
|
| 7908 |
+
{
|
| 7909 |
+
"epoch": 0.9448192897118051,
|
| 7910 |
+
"grad_norm": 0.1463528722524643,
|
| 7911 |
+
"learning_rate": 0.001,
|
| 7912 |
+
"loss": 1.6764702796936035,
|
| 7913 |
+
"step": 2258
|
| 7914 |
+
},
|
| 7915 |
+
{
|
| 7916 |
+
"epoch": 0.9456561535645169,
|
| 7917 |
+
"grad_norm": 0.18095387518405914,
|
| 7918 |
+
"learning_rate": 0.001,
|
| 7919 |
+
"loss": 1.6801321506500244,
|
| 7920 |
+
"step": 2260
|
| 7921 |
+
},
|
| 7922 |
+
{
|
| 7923 |
+
"epoch": 0.9464930174172289,
|
| 7924 |
+
"grad_norm": 0.21140393614768982,
|
| 7925 |
+
"learning_rate": 0.001,
|
| 7926 |
+
"loss": 1.6887340545654297,
|
| 7927 |
+
"step": 2262
|
| 7928 |
+
},
|
| 7929 |
+
{
|
| 7930 |
+
"epoch": 0.9473298812699409,
|
| 7931 |
+
"grad_norm": 0.15899649262428284,
|
| 7932 |
+
"learning_rate": 0.001,
|
| 7933 |
+
"loss": 1.9275522232055664,
|
| 7934 |
+
"step": 2264
|
| 7935 |
+
},
|
| 7936 |
+
{
|
| 7937 |
+
"epoch": 0.9481667451226529,
|
| 7938 |
+
"grad_norm": 0.18951623141765594,
|
| 7939 |
+
"learning_rate": 0.001,
|
| 7940 |
+
"loss": 1.651792287826538,
|
| 7941 |
+
"step": 2266
|
| 7942 |
+
},
|
| 7943 |
+
{
|
| 7944 |
+
"epoch": 0.9490036089753648,
|
| 7945 |
+
"grad_norm": 0.186489075422287,
|
| 7946 |
+
"learning_rate": 0.001,
|
| 7947 |
+
"loss": 1.6591260433197021,
|
| 7948 |
+
"step": 2268
|
| 7949 |
+
},
|
| 7950 |
+
{
|
| 7951 |
+
"epoch": 0.9498404728280768,
|
| 7952 |
+
"grad_norm": 0.16518957912921906,
|
| 7953 |
+
"learning_rate": 0.001,
|
| 7954 |
+
"loss": 1.6168091297149658,
|
| 7955 |
+
"step": 2270
|
| 7956 |
+
},
|
| 7957 |
+
{
|
| 7958 |
+
"epoch": 0.9506773366807888,
|
| 7959 |
+
"grad_norm": 0.1578168272972107,
|
| 7960 |
+
"learning_rate": 0.001,
|
| 7961 |
+
"loss": 1.8189584016799927,
|
| 7962 |
+
"step": 2272
|
| 7963 |
+
},
|
| 7964 |
+
{
|
| 7965 |
+
"epoch": 0.9515142005335007,
|
| 7966 |
+
"grad_norm": 0.14082765579223633,
|
| 7967 |
+
"learning_rate": 0.001,
|
| 7968 |
+
"loss": 1.790959358215332,
|
| 7969 |
+
"step": 2274
|
| 7970 |
+
},
|
| 7971 |
+
{
|
| 7972 |
+
"epoch": 0.9523510643862126,
|
| 7973 |
+
"grad_norm": 0.18604081869125366,
|
| 7974 |
+
"learning_rate": 0.001,
|
| 7975 |
+
"loss": 1.9324309825897217,
|
| 7976 |
+
"step": 2276
|
| 7977 |
+
},
|
| 7978 |
+
{
|
| 7979 |
+
"epoch": 0.9531879282389246,
|
| 7980 |
+
"grad_norm": 0.157945916056633,
|
| 7981 |
+
"learning_rate": 0.001,
|
| 7982 |
+
"loss": 1.7626545429229736,
|
| 7983 |
+
"step": 2278
|
| 7984 |
+
},
|
| 7985 |
+
{
|
| 7986 |
+
"epoch": 0.9540247920916366,
|
| 7987 |
+
"grad_norm": 0.13825370371341705,
|
| 7988 |
+
"learning_rate": 0.001,
|
| 7989 |
+
"loss": 1.8637577295303345,
|
| 7990 |
+
"step": 2280
|
| 7991 |
+
},
|
| 7992 |
+
{
|
| 7993 |
+
"epoch": 0.9548616559443486,
|
| 7994 |
+
"grad_norm": 0.14420157670974731,
|
| 7995 |
+
"learning_rate": 0.001,
|
| 7996 |
+
"loss": 1.8060953617095947,
|
| 7997 |
+
"step": 2282
|
| 7998 |
+
},
|
| 7999 |
+
{
|
| 8000 |
+
"epoch": 0.9556985197970606,
|
| 8001 |
+
"grad_norm": 0.11855071783065796,
|
| 8002 |
+
"learning_rate": 0.001,
|
| 8003 |
+
"loss": 1.9194179773330688,
|
| 8004 |
+
"step": 2284
|
| 8005 |
+
},
|
| 8006 |
+
{
|
| 8007 |
+
"epoch": 0.9565353836497725,
|
| 8008 |
+
"grad_norm": 0.15913037955760956,
|
| 8009 |
+
"learning_rate": 0.001,
|
| 8010 |
+
"loss": 1.924431324005127,
|
| 8011 |
+
"step": 2286
|
| 8012 |
+
},
|
| 8013 |
+
{
|
| 8014 |
+
"epoch": 0.9573722475024844,
|
| 8015 |
+
"grad_norm": 0.2492927759885788,
|
| 8016 |
+
"learning_rate": 0.001,
|
| 8017 |
+
"loss": 1.7248079776763916,
|
| 8018 |
+
"step": 2288
|
| 8019 |
+
},
|
| 8020 |
+
{
|
| 8021 |
+
"epoch": 0.9582091113551964,
|
| 8022 |
+
"grad_norm": 0.17722591757774353,
|
| 8023 |
+
"learning_rate": 0.001,
|
| 8024 |
+
"loss": 1.9538564682006836,
|
| 8025 |
+
"step": 2290
|
| 8026 |
+
},
|
| 8027 |
+
{
|
| 8028 |
+
"epoch": 0.9590459752079084,
|
| 8029 |
+
"grad_norm": 0.2376166731119156,
|
| 8030 |
+
"learning_rate": 0.001,
|
| 8031 |
+
"loss": 1.7679381370544434,
|
| 8032 |
+
"step": 2292
|
| 8033 |
+
},
|
| 8034 |
+
{
|
| 8035 |
+
"epoch": 0.9598828390606203,
|
| 8036 |
+
"grad_norm": 0.1590910702943802,
|
| 8037 |
+
"learning_rate": 0.001,
|
| 8038 |
+
"loss": 1.8226380348205566,
|
| 8039 |
+
"step": 2294
|
| 8040 |
+
},
|
| 8041 |
+
{
|
| 8042 |
+
"epoch": 0.9607197029133323,
|
| 8043 |
+
"grad_norm": 0.18827907741069794,
|
| 8044 |
+
"learning_rate": 0.001,
|
| 8045 |
+
"loss": 1.792297601699829,
|
| 8046 |
+
"step": 2296
|
| 8047 |
+
},
|
| 8048 |
+
{
|
| 8049 |
+
"epoch": 0.9615565667660443,
|
| 8050 |
+
"grad_norm": 0.18025733530521393,
|
| 8051 |
+
"learning_rate": 0.001,
|
| 8052 |
+
"loss": 1.878666877746582,
|
| 8053 |
+
"step": 2298
|
| 8054 |
+
},
|
| 8055 |
+
{
|
| 8056 |
+
"epoch": 0.9623934306187563,
|
| 8057 |
+
"grad_norm": 0.2118266373872757,
|
| 8058 |
+
"learning_rate": 0.001,
|
| 8059 |
+
"loss": 1.8201663494110107,
|
| 8060 |
+
"step": 2300
|
| 8061 |
+
},
|
| 8062 |
+
{
|
| 8063 |
+
"epoch": 0.9632302944714681,
|
| 8064 |
+
"grad_norm": 0.16395042836666107,
|
| 8065 |
+
"learning_rate": 0.001,
|
| 8066 |
+
"loss": 1.9368658065795898,
|
| 8067 |
+
"step": 2302
|
| 8068 |
+
},
|
| 8069 |
+
{
|
| 8070 |
+
"epoch": 0.9640671583241801,
|
| 8071 |
+
"grad_norm": 0.19479355216026306,
|
| 8072 |
+
"learning_rate": 0.001,
|
| 8073 |
+
"loss": 1.7580039501190186,
|
| 8074 |
+
"step": 2304
|
| 8075 |
+
},
|
| 8076 |
+
{
|
| 8077 |
+
"epoch": 0.9649040221768921,
|
| 8078 |
+
"grad_norm": 0.13842609524726868,
|
| 8079 |
+
"learning_rate": 0.001,
|
| 8080 |
+
"loss": 1.8223036527633667,
|
| 8081 |
+
"step": 2306
|
| 8082 |
+
},
|
| 8083 |
+
{
|
| 8084 |
+
"epoch": 0.9657408860296041,
|
| 8085 |
+
"grad_norm": 0.1536252498626709,
|
| 8086 |
+
"learning_rate": 0.001,
|
| 8087 |
+
"loss": 1.7448561191558838,
|
| 8088 |
+
"step": 2308
|
| 8089 |
+
},
|
| 8090 |
+
{
|
| 8091 |
+
"epoch": 0.966577749882316,
|
| 8092 |
+
"grad_norm": 0.14604398608207703,
|
| 8093 |
+
"learning_rate": 0.001,
|
| 8094 |
+
"loss": 1.695833444595337,
|
| 8095 |
+
"step": 2310
|
| 8096 |
+
},
|
| 8097 |
+
{
|
| 8098 |
+
"epoch": 0.967414613735028,
|
| 8099 |
+
"grad_norm": 0.14182166755199432,
|
| 8100 |
+
"learning_rate": 0.001,
|
| 8101 |
+
"loss": 1.6607015132904053,
|
| 8102 |
+
"step": 2312
|
| 8103 |
+
},
|
| 8104 |
+
{
|
| 8105 |
+
"epoch": 0.96825147758774,
|
| 8106 |
+
"grad_norm": 0.14658622443675995,
|
| 8107 |
+
"learning_rate": 0.001,
|
| 8108 |
+
"loss": 1.7706737518310547,
|
| 8109 |
+
"step": 2314
|
| 8110 |
+
},
|
| 8111 |
+
{
|
| 8112 |
+
"epoch": 0.9690883414404519,
|
| 8113 |
+
"grad_norm": 0.16125091910362244,
|
| 8114 |
+
"learning_rate": 0.001,
|
| 8115 |
+
"loss": 1.7303478717803955,
|
| 8116 |
+
"step": 2316
|
| 8117 |
+
},
|
| 8118 |
+
{
|
| 8119 |
+
"epoch": 0.9699252052931638,
|
| 8120 |
+
"grad_norm": 0.15371491014957428,
|
| 8121 |
+
"learning_rate": 0.001,
|
| 8122 |
+
"loss": 1.931710958480835,
|
| 8123 |
+
"step": 2318
|
| 8124 |
+
},
|
| 8125 |
+
{
|
| 8126 |
+
"epoch": 0.9707620691458758,
|
| 8127 |
+
"grad_norm": 0.14118391275405884,
|
| 8128 |
+
"learning_rate": 0.001,
|
| 8129 |
+
"loss": 2.0130863189697266,
|
| 8130 |
+
"step": 2320
|
| 8131 |
+
},
|
| 8132 |
+
{
|
| 8133 |
+
"epoch": 0.9715989329985878,
|
| 8134 |
+
"grad_norm": 0.15739081799983978,
|
| 8135 |
+
"learning_rate": 0.001,
|
| 8136 |
+
"loss": 1.9382615089416504,
|
| 8137 |
+
"step": 2322
|
| 8138 |
+
},
|
| 8139 |
+
{
|
| 8140 |
+
"epoch": 0.9724357968512998,
|
| 8141 |
+
"grad_norm": 0.19725753366947174,
|
| 8142 |
+
"learning_rate": 0.001,
|
| 8143 |
+
"loss": 1.654850721359253,
|
| 8144 |
+
"step": 2324
|
| 8145 |
+
},
|
| 8146 |
+
{
|
| 8147 |
+
"epoch": 0.9732726607040117,
|
| 8148 |
+
"grad_norm": 0.16194036602973938,
|
| 8149 |
+
"learning_rate": 0.001,
|
| 8150 |
+
"loss": 1.7618460655212402,
|
| 8151 |
+
"step": 2326
|
| 8152 |
+
},
|
| 8153 |
+
{
|
| 8154 |
+
"epoch": 0.9741095245567237,
|
| 8155 |
+
"grad_norm": 0.15334229171276093,
|
| 8156 |
+
"learning_rate": 0.001,
|
| 8157 |
+
"loss": 1.7884609699249268,
|
| 8158 |
+
"step": 2328
|
| 8159 |
+
},
|
| 8160 |
+
{
|
| 8161 |
+
"epoch": 0.9749463884094356,
|
| 8162 |
+
"grad_norm": 0.15143629908561707,
|
| 8163 |
+
"learning_rate": 0.001,
|
| 8164 |
+
"loss": 1.9000864028930664,
|
| 8165 |
+
"step": 2330
|
| 8166 |
+
},
|
| 8167 |
+
{
|
| 8168 |
+
"epoch": 0.9757832522621476,
|
| 8169 |
+
"grad_norm": 0.18041492998600006,
|
| 8170 |
+
"learning_rate": 0.001,
|
| 8171 |
+
"loss": 1.5406476259231567,
|
| 8172 |
+
"step": 2332
|
| 8173 |
+
},
|
| 8174 |
+
{
|
| 8175 |
+
"epoch": 0.9766201161148595,
|
| 8176 |
+
"grad_norm": 0.17635753750801086,
|
| 8177 |
+
"learning_rate": 0.001,
|
| 8178 |
+
"loss": 1.6799423694610596,
|
| 8179 |
+
"step": 2334
|
| 8180 |
+
},
|
| 8181 |
+
{
|
| 8182 |
+
"epoch": 0.9774569799675715,
|
| 8183 |
+
"grad_norm": 0.18360395729541779,
|
| 8184 |
+
"learning_rate": 0.001,
|
| 8185 |
+
"loss": 1.9708590507507324,
|
| 8186 |
+
"step": 2336
|
| 8187 |
+
},
|
| 8188 |
+
{
|
| 8189 |
+
"epoch": 0.9782938438202835,
|
| 8190 |
+
"grad_norm": 0.17834937572479248,
|
| 8191 |
+
"learning_rate": 0.001,
|
| 8192 |
+
"loss": 1.8932498693466187,
|
| 8193 |
+
"step": 2338
|
| 8194 |
+
},
|
| 8195 |
+
{
|
| 8196 |
+
"epoch": 0.9791307076729955,
|
| 8197 |
+
"grad_norm": 0.19395795464515686,
|
| 8198 |
+
"learning_rate": 0.001,
|
| 8199 |
+
"loss": 1.547823190689087,
|
| 8200 |
+
"step": 2340
|
| 8201 |
+
},
|
| 8202 |
+
{
|
| 8203 |
+
"epoch": 0.9799675715257075,
|
| 8204 |
+
"grad_norm": 0.1597231775522232,
|
| 8205 |
+
"learning_rate": 0.001,
|
| 8206 |
+
"loss": 1.776328444480896,
|
| 8207 |
+
"step": 2342
|
| 8208 |
+
},
|
| 8209 |
+
{
|
| 8210 |
+
"epoch": 0.9808044353784193,
|
| 8211 |
+
"grad_norm": 0.14532804489135742,
|
| 8212 |
+
"learning_rate": 0.001,
|
| 8213 |
+
"loss": 1.9299194812774658,
|
| 8214 |
+
"step": 2344
|
| 8215 |
+
},
|
| 8216 |
+
{
|
| 8217 |
+
"epoch": 0.9816412992311313,
|
| 8218 |
+
"grad_norm": 0.1633855700492859,
|
| 8219 |
+
"learning_rate": 0.001,
|
| 8220 |
+
"loss": 1.620832920074463,
|
| 8221 |
+
"step": 2346
|
| 8222 |
+
},
|
| 8223 |
+
{
|
| 8224 |
+
"epoch": 0.9824781630838433,
|
| 8225 |
+
"grad_norm": 0.16614995896816254,
|
| 8226 |
+
"learning_rate": 0.001,
|
| 8227 |
+
"loss": 1.9577127695083618,
|
| 8228 |
+
"step": 2348
|
| 8229 |
+
},
|
| 8230 |
+
{
|
| 8231 |
+
"epoch": 0.9833150269365553,
|
| 8232 |
+
"grad_norm": 0.1668742150068283,
|
| 8233 |
+
"learning_rate": 0.001,
|
| 8234 |
+
"loss": 1.7494750022888184,
|
| 8235 |
+
"step": 2350
|
| 8236 |
+
},
|
| 8237 |
+
{
|
| 8238 |
+
"epoch": 0.9841518907892672,
|
| 8239 |
+
"grad_norm": 0.1709330677986145,
|
| 8240 |
+
"learning_rate": 0.001,
|
| 8241 |
+
"loss": 1.7774887084960938,
|
| 8242 |
+
"step": 2352
|
| 8243 |
+
},
|
| 8244 |
+
{
|
| 8245 |
+
"epoch": 0.9849887546419792,
|
| 8246 |
+
"grad_norm": 0.1570654809474945,
|
| 8247 |
+
"learning_rate": 0.001,
|
| 8248 |
+
"loss": 1.7664926052093506,
|
| 8249 |
+
"step": 2354
|
| 8250 |
+
},
|
| 8251 |
+
{
|
| 8252 |
+
"epoch": 0.9858256184946912,
|
| 8253 |
+
"grad_norm": 0.23913079500198364,
|
| 8254 |
+
"learning_rate": 0.001,
|
| 8255 |
+
"loss": 1.7952555418014526,
|
| 8256 |
+
"step": 2356
|
| 8257 |
+
},
|
| 8258 |
+
{
|
| 8259 |
+
"epoch": 0.9866624823474031,
|
| 8260 |
+
"grad_norm": 0.15034550428390503,
|
| 8261 |
+
"learning_rate": 0.001,
|
| 8262 |
+
"loss": 1.7732383012771606,
|
| 8263 |
+
"step": 2358
|
| 8264 |
+
},
|
| 8265 |
+
{
|
| 8266 |
+
"epoch": 0.987499346200115,
|
| 8267 |
+
"grad_norm": 0.17077398300170898,
|
| 8268 |
+
"learning_rate": 0.001,
|
| 8269 |
+
"loss": 1.6835296154022217,
|
| 8270 |
+
"step": 2360
|
| 8271 |
+
},
|
| 8272 |
+
{
|
| 8273 |
+
"epoch": 0.988336210052827,
|
| 8274 |
+
"grad_norm": 0.16865044832229614,
|
| 8275 |
+
"learning_rate": 0.001,
|
| 8276 |
+
"loss": 1.7741029262542725,
|
| 8277 |
+
"step": 2362
|
| 8278 |
+
},
|
| 8279 |
+
{
|
| 8280 |
+
"epoch": 0.989173073905539,
|
| 8281 |
+
"grad_norm": 0.1816924810409546,
|
| 8282 |
+
"learning_rate": 0.001,
|
| 8283 |
+
"loss": 1.812211036682129,
|
| 8284 |
+
"step": 2364
|
| 8285 |
+
},
|
| 8286 |
+
{
|
| 8287 |
+
"epoch": 0.990009937758251,
|
| 8288 |
+
"grad_norm": 0.17185509204864502,
|
| 8289 |
+
"learning_rate": 0.001,
|
| 8290 |
+
"loss": 1.734316349029541,
|
| 8291 |
+
"step": 2366
|
| 8292 |
+
},
|
| 8293 |
+
{
|
| 8294 |
+
"epoch": 0.990846801610963,
|
| 8295 |
+
"grad_norm": 0.14011302590370178,
|
| 8296 |
+
"learning_rate": 0.001,
|
| 8297 |
+
"loss": 1.743484616279602,
|
| 8298 |
+
"step": 2368
|
| 8299 |
+
},
|
| 8300 |
+
{
|
| 8301 |
+
"epoch": 0.9916836654636749,
|
| 8302 |
+
"grad_norm": 0.1877838373184204,
|
| 8303 |
+
"learning_rate": 0.001,
|
| 8304 |
+
"loss": 1.688406229019165,
|
| 8305 |
+
"step": 2370
|
| 8306 |
+
},
|
| 8307 |
+
{
|
| 8308 |
+
"epoch": 0.9925205293163868,
|
| 8309 |
+
"grad_norm": 0.13024172186851501,
|
| 8310 |
+
"learning_rate": 0.001,
|
| 8311 |
+
"loss": 2.0837178230285645,
|
| 8312 |
+
"step": 2372
|
| 8313 |
+
},
|
| 8314 |
+
{
|
| 8315 |
+
"epoch": 0.9933573931690988,
|
| 8316 |
+
"grad_norm": 0.18704289197921753,
|
| 8317 |
+
"learning_rate": 0.001,
|
| 8318 |
+
"loss": 1.752204418182373,
|
| 8319 |
+
"step": 2374
|
| 8320 |
+
},
|
| 8321 |
+
{
|
| 8322 |
+
"epoch": 0.9941942570218107,
|
| 8323 |
+
"grad_norm": 0.14076274633407593,
|
| 8324 |
+
"learning_rate": 0.001,
|
| 8325 |
+
"loss": 1.7421479225158691,
|
| 8326 |
+
"step": 2376
|
| 8327 |
+
},
|
| 8328 |
+
{
|
| 8329 |
+
"epoch": 0.9950311208745227,
|
| 8330 |
+
"grad_norm": 0.1593211144208908,
|
| 8331 |
+
"learning_rate": 0.001,
|
| 8332 |
+
"loss": 1.9137558937072754,
|
| 8333 |
+
"step": 2378
|
| 8334 |
+
},
|
| 8335 |
+
{
|
| 8336 |
+
"epoch": 0.9958679847272347,
|
| 8337 |
+
"grad_norm": 0.14093244075775146,
|
| 8338 |
+
"learning_rate": 0.001,
|
| 8339 |
+
"loss": 1.4920547008514404,
|
| 8340 |
+
"step": 2380
|
| 8341 |
+
},
|
| 8342 |
+
{
|
| 8343 |
+
"epoch": 0.9967048485799467,
|
| 8344 |
+
"grad_norm": 0.15649160742759705,
|
| 8345 |
+
"learning_rate": 0.001,
|
| 8346 |
+
"loss": 1.962348222732544,
|
| 8347 |
+
"step": 2382
|
| 8348 |
+
},
|
| 8349 |
+
{
|
| 8350 |
+
"epoch": 0.9975417124326587,
|
| 8351 |
+
"grad_norm": 0.1779119074344635,
|
| 8352 |
+
"learning_rate": 0.001,
|
| 8353 |
+
"loss": 1.7434918880462646,
|
| 8354 |
+
"step": 2384
|
| 8355 |
+
},
|
| 8356 |
+
{
|
| 8357 |
+
"epoch": 0.9983785762853705,
|
| 8358 |
+
"grad_norm": 0.150917187333107,
|
| 8359 |
+
"learning_rate": 0.001,
|
| 8360 |
+
"loss": 1.836576223373413,
|
| 8361 |
+
"step": 2386
|
| 8362 |
+
},
|
| 8363 |
+
{
|
| 8364 |
+
"epoch": 0.9992154401380825,
|
| 8365 |
+
"grad_norm": 0.12839116156101227,
|
| 8366 |
+
"learning_rate": 0.001,
|
| 8367 |
+
"loss": 1.9482123851776123,
|
| 8368 |
+
"step": 2388
|
| 8369 |
+
},
|
| 8370 |
+
{
|
| 8371 |
+
"epoch": 1.0,
|
| 8372 |
+
"grad_norm": 0.18662364780902863,
|
| 8373 |
+
"learning_rate": 0.001,
|
| 8374 |
+
"loss": 1.7965145111083984,
|
| 8375 |
+
"step": 2390
|
| 8376 |
}
|
| 8377 |
],
|
| 8378 |
"logging_steps": 2,
|
|
|
|
| 8392 |
"attributes": {}
|
| 8393 |
}
|
| 8394 |
},
|
| 8395 |
+
"total_flos": 5.1314519457765786e+17,
|
| 8396 |
"train_batch_size": 1,
|
| 8397 |
"trial_name": null,
|
| 8398 |
"trial_params": null
|