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)# 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=40) 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 Studio
How to use Ba2han/test_CPTlsft2 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/test_CPTlsft2 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/test_CPTlsft2 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ba2han/test_CPTlsft2 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Ba2han/test_CPTlsft2", max_seq_length=2048, ) - 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 2296, 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 sha256:01ba775e59fa02529237071be1294ed7c816cb0c19e53e584f8b84891d495d0e
|
| 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 sha256:002a1660467419a33f0f48b82b00ddaef808068e25d10733f10978b2f3f201f2
|
| 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:aa8e94abe03f34ed07e6602e243cbcb9ad3cfa6dfe2205ed01961882ff143b74
|
| 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": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -6035,6 +6035,2015 @@
|
|
| 6035 |
"learning_rate": 5e-05,
|
| 6036 |
"loss": 1.9182190895080566,
|
| 6037 |
"step": 1722
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6038 |
}
|
| 6039 |
],
|
| 6040 |
"logging_steps": 2,
|
|
@@ -6054,7 +8063,7 @@
|
|
| 6054 |
"attributes": {}
|
| 6055 |
}
|
| 6056 |
},
|
| 6057 |
-
"total_flos":
|
| 6058 |
"train_batch_size": 1,
|
| 6059 |
"trial_name": null,
|
| 6060 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8005997524277769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2296,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6035 |
"learning_rate": 5e-05,
|
| 6036 |
"loss": 1.9182190895080566,
|
| 6037 |
"step": 1722
|
| 6038 |
+
},
|
| 6039 |
+
{
|
| 6040 |
+
"epoch": 0.6011472008647594,
|
| 6041 |
+
"grad_norm": 0.1572408676147461,
|
| 6042 |
+
"learning_rate": 5e-05,
|
| 6043 |
+
"loss": 1.959277868270874,
|
| 6044 |
+
"step": 1724
|
| 6045 |
+
},
|
| 6046 |
+
{
|
| 6047 |
+
"epoch": 0.601844587408686,
|
| 6048 |
+
"grad_norm": 0.21377843618392944,
|
| 6049 |
+
"learning_rate": 5e-05,
|
| 6050 |
+
"loss": 2.175769567489624,
|
| 6051 |
+
"step": 1726
|
| 6052 |
+
},
|
| 6053 |
+
{
|
| 6054 |
+
"epoch": 0.6025419739526126,
|
| 6055 |
+
"grad_norm": 0.2010141909122467,
|
| 6056 |
+
"learning_rate": 5e-05,
|
| 6057 |
+
"loss": 2.1774816513061523,
|
| 6058 |
+
"step": 1728
|
| 6059 |
+
},
|
| 6060 |
+
{
|
| 6061 |
+
"epoch": 0.6032393604965393,
|
| 6062 |
+
"grad_norm": 0.2195289582014084,
|
| 6063 |
+
"learning_rate": 5e-05,
|
| 6064 |
+
"loss": 1.7632919549942017,
|
| 6065 |
+
"step": 1730
|
| 6066 |
+
},
|
| 6067 |
+
{
|
| 6068 |
+
"epoch": 0.6039367470404658,
|
| 6069 |
+
"grad_norm": 0.21566610038280487,
|
| 6070 |
+
"learning_rate": 5e-05,
|
| 6071 |
+
"loss": 1.9510669708251953,
|
| 6072 |
+
"step": 1732
|
| 6073 |
+
},
|
| 6074 |
+
{
|
| 6075 |
+
"epoch": 0.6046341335843924,
|
| 6076 |
+
"grad_norm": 0.18458028137683868,
|
| 6077 |
+
"learning_rate": 5e-05,
|
| 6078 |
+
"loss": 2.1417834758758545,
|
| 6079 |
+
"step": 1734
|
| 6080 |
+
},
|
| 6081 |
+
{
|
| 6082 |
+
"epoch": 0.6053315201283191,
|
| 6083 |
+
"grad_norm": 0.27364224195480347,
|
| 6084 |
+
"learning_rate": 5e-05,
|
| 6085 |
+
"loss": 2.0847959518432617,
|
| 6086 |
+
"step": 1736
|
| 6087 |
+
},
|
| 6088 |
+
{
|
| 6089 |
+
"epoch": 0.6060289066722457,
|
| 6090 |
+
"grad_norm": 0.20937108993530273,
|
| 6091 |
+
"learning_rate": 5e-05,
|
| 6092 |
+
"loss": 2.1932859420776367,
|
| 6093 |
+
"step": 1738
|
| 6094 |
+
},
|
| 6095 |
+
{
|
| 6096 |
+
"epoch": 0.6067262932161724,
|
| 6097 |
+
"grad_norm": 0.24981026351451874,
|
| 6098 |
+
"learning_rate": 5e-05,
|
| 6099 |
+
"loss": 1.7620201110839844,
|
| 6100 |
+
"step": 1740
|
| 6101 |
+
},
|
| 6102 |
+
{
|
| 6103 |
+
"epoch": 0.607423679760099,
|
| 6104 |
+
"grad_norm": 0.22395093739032745,
|
| 6105 |
+
"learning_rate": 5e-05,
|
| 6106 |
+
"loss": 1.9993212223052979,
|
| 6107 |
+
"step": 1742
|
| 6108 |
+
},
|
| 6109 |
+
{
|
| 6110 |
+
"epoch": 0.6081210663040256,
|
| 6111 |
+
"grad_norm": 0.27337807416915894,
|
| 6112 |
+
"learning_rate": 5e-05,
|
| 6113 |
+
"loss": 2.0806846618652344,
|
| 6114 |
+
"step": 1744
|
| 6115 |
+
},
|
| 6116 |
+
{
|
| 6117 |
+
"epoch": 0.6088184528479523,
|
| 6118 |
+
"grad_norm": 0.226410910487175,
|
| 6119 |
+
"learning_rate": 5e-05,
|
| 6120 |
+
"loss": 1.8875980377197266,
|
| 6121 |
+
"step": 1746
|
| 6122 |
+
},
|
| 6123 |
+
{
|
| 6124 |
+
"epoch": 0.6095158393918789,
|
| 6125 |
+
"grad_norm": 0.22300706803798676,
|
| 6126 |
+
"learning_rate": 5e-05,
|
| 6127 |
+
"loss": 1.537036418914795,
|
| 6128 |
+
"step": 1748
|
| 6129 |
+
},
|
| 6130 |
+
{
|
| 6131 |
+
"epoch": 0.6102132259358055,
|
| 6132 |
+
"grad_norm": 0.1922428160905838,
|
| 6133 |
+
"learning_rate": 5e-05,
|
| 6134 |
+
"loss": 1.8651649951934814,
|
| 6135 |
+
"step": 1750
|
| 6136 |
+
},
|
| 6137 |
+
{
|
| 6138 |
+
"epoch": 0.6109106124797322,
|
| 6139 |
+
"grad_norm": 0.15310291945934296,
|
| 6140 |
+
"learning_rate": 5e-05,
|
| 6141 |
+
"loss": 1.9449410438537598,
|
| 6142 |
+
"step": 1752
|
| 6143 |
+
},
|
| 6144 |
+
{
|
| 6145 |
+
"epoch": 0.6116079990236588,
|
| 6146 |
+
"grad_norm": 0.2211032658815384,
|
| 6147 |
+
"learning_rate": 5e-05,
|
| 6148 |
+
"loss": 2.1581153869628906,
|
| 6149 |
+
"step": 1754
|
| 6150 |
+
},
|
| 6151 |
+
{
|
| 6152 |
+
"epoch": 0.6123053855675855,
|
| 6153 |
+
"grad_norm": 0.2677195966243744,
|
| 6154 |
+
"learning_rate": 5e-05,
|
| 6155 |
+
"loss": 1.9254250526428223,
|
| 6156 |
+
"step": 1756
|
| 6157 |
+
},
|
| 6158 |
+
{
|
| 6159 |
+
"epoch": 0.6130027721115121,
|
| 6160 |
+
"grad_norm": 0.18960987031459808,
|
| 6161 |
+
"learning_rate": 5e-05,
|
| 6162 |
+
"loss": 1.7236549854278564,
|
| 6163 |
+
"step": 1758
|
| 6164 |
+
},
|
| 6165 |
+
{
|
| 6166 |
+
"epoch": 0.6137001586554387,
|
| 6167 |
+
"grad_norm": 0.31510594487190247,
|
| 6168 |
+
"learning_rate": 5e-05,
|
| 6169 |
+
"loss": 1.95664644241333,
|
| 6170 |
+
"step": 1760
|
| 6171 |
+
},
|
| 6172 |
+
{
|
| 6173 |
+
"epoch": 0.6143975451993654,
|
| 6174 |
+
"grad_norm": 0.21830137073993683,
|
| 6175 |
+
"learning_rate": 5e-05,
|
| 6176 |
+
"loss": 2.088205575942993,
|
| 6177 |
+
"step": 1762
|
| 6178 |
+
},
|
| 6179 |
+
{
|
| 6180 |
+
"epoch": 0.615094931743292,
|
| 6181 |
+
"grad_norm": 0.23890633881092072,
|
| 6182 |
+
"learning_rate": 5e-05,
|
| 6183 |
+
"loss": 1.9173531532287598,
|
| 6184 |
+
"step": 1764
|
| 6185 |
+
},
|
| 6186 |
+
{
|
| 6187 |
+
"epoch": 0.6157923182872187,
|
| 6188 |
+
"grad_norm": 0.24494515359401703,
|
| 6189 |
+
"learning_rate": 5e-05,
|
| 6190 |
+
"loss": 1.929988145828247,
|
| 6191 |
+
"step": 1766
|
| 6192 |
+
},
|
| 6193 |
+
{
|
| 6194 |
+
"epoch": 0.6164897048311453,
|
| 6195 |
+
"grad_norm": 0.21958190202713013,
|
| 6196 |
+
"learning_rate": 5e-05,
|
| 6197 |
+
"loss": 1.8340654373168945,
|
| 6198 |
+
"step": 1768
|
| 6199 |
+
},
|
| 6200 |
+
{
|
| 6201 |
+
"epoch": 0.6171870913750719,
|
| 6202 |
+
"grad_norm": 0.20597727596759796,
|
| 6203 |
+
"learning_rate": 5e-05,
|
| 6204 |
+
"loss": 2.064466953277588,
|
| 6205 |
+
"step": 1770
|
| 6206 |
+
},
|
| 6207 |
+
{
|
| 6208 |
+
"epoch": 0.6178844779189986,
|
| 6209 |
+
"grad_norm": 0.21612513065338135,
|
| 6210 |
+
"learning_rate": 5e-05,
|
| 6211 |
+
"loss": 1.9843177795410156,
|
| 6212 |
+
"step": 1772
|
| 6213 |
+
},
|
| 6214 |
+
{
|
| 6215 |
+
"epoch": 0.6185818644629252,
|
| 6216 |
+
"grad_norm": 0.24421793222427368,
|
| 6217 |
+
"learning_rate": 5e-05,
|
| 6218 |
+
"loss": 1.828315019607544,
|
| 6219 |
+
"step": 1774
|
| 6220 |
+
},
|
| 6221 |
+
{
|
| 6222 |
+
"epoch": 0.6192792510068518,
|
| 6223 |
+
"grad_norm": 0.2955434322357178,
|
| 6224 |
+
"learning_rate": 5e-05,
|
| 6225 |
+
"loss": 1.9416334629058838,
|
| 6226 |
+
"step": 1776
|
| 6227 |
+
},
|
| 6228 |
+
{
|
| 6229 |
+
"epoch": 0.6199766375507785,
|
| 6230 |
+
"grad_norm": 0.3074122667312622,
|
| 6231 |
+
"learning_rate": 5e-05,
|
| 6232 |
+
"loss": 1.8622162342071533,
|
| 6233 |
+
"step": 1778
|
| 6234 |
+
},
|
| 6235 |
+
{
|
| 6236 |
+
"epoch": 0.6206740240947051,
|
| 6237 |
+
"grad_norm": 0.2642528712749481,
|
| 6238 |
+
"learning_rate": 5e-05,
|
| 6239 |
+
"loss": 1.8647794723510742,
|
| 6240 |
+
"step": 1780
|
| 6241 |
+
},
|
| 6242 |
+
{
|
| 6243 |
+
"epoch": 0.6213714106386318,
|
| 6244 |
+
"grad_norm": 0.2782607674598694,
|
| 6245 |
+
"learning_rate": 5e-05,
|
| 6246 |
+
"loss": 1.934777021408081,
|
| 6247 |
+
"step": 1782
|
| 6248 |
+
},
|
| 6249 |
+
{
|
| 6250 |
+
"epoch": 0.6220687971825584,
|
| 6251 |
+
"grad_norm": 0.16562847793102264,
|
| 6252 |
+
"learning_rate": 5e-05,
|
| 6253 |
+
"loss": 2.0389959812164307,
|
| 6254 |
+
"step": 1784
|
| 6255 |
+
},
|
| 6256 |
+
{
|
| 6257 |
+
"epoch": 0.622766183726485,
|
| 6258 |
+
"grad_norm": 0.18666969239711761,
|
| 6259 |
+
"learning_rate": 5e-05,
|
| 6260 |
+
"loss": 1.9525014162063599,
|
| 6261 |
+
"step": 1786
|
| 6262 |
+
},
|
| 6263 |
+
{
|
| 6264 |
+
"epoch": 0.6234635702704117,
|
| 6265 |
+
"grad_norm": 0.19193722307682037,
|
| 6266 |
+
"learning_rate": 5e-05,
|
| 6267 |
+
"loss": 1.802701711654663,
|
| 6268 |
+
"step": 1788
|
| 6269 |
+
},
|
| 6270 |
+
{
|
| 6271 |
+
"epoch": 0.6241609568143383,
|
| 6272 |
+
"grad_norm": 0.1893835961818695,
|
| 6273 |
+
"learning_rate": 5e-05,
|
| 6274 |
+
"loss": 1.9322786331176758,
|
| 6275 |
+
"step": 1790
|
| 6276 |
+
},
|
| 6277 |
+
{
|
| 6278 |
+
"epoch": 0.624858343358265,
|
| 6279 |
+
"grad_norm": 0.15804891288280487,
|
| 6280 |
+
"learning_rate": 5e-05,
|
| 6281 |
+
"loss": 2.237478256225586,
|
| 6282 |
+
"step": 1792
|
| 6283 |
+
},
|
| 6284 |
+
{
|
| 6285 |
+
"epoch": 0.6255557299021915,
|
| 6286 |
+
"grad_norm": 0.28472012281417847,
|
| 6287 |
+
"learning_rate": 5e-05,
|
| 6288 |
+
"loss": 1.8306212425231934,
|
| 6289 |
+
"step": 1794
|
| 6290 |
+
},
|
| 6291 |
+
{
|
| 6292 |
+
"epoch": 0.6262531164461181,
|
| 6293 |
+
"grad_norm": 0.18115119636058807,
|
| 6294 |
+
"learning_rate": 5e-05,
|
| 6295 |
+
"loss": 2.118734121322632,
|
| 6296 |
+
"step": 1796
|
| 6297 |
+
},
|
| 6298 |
+
{
|
| 6299 |
+
"epoch": 0.6269505029900448,
|
| 6300 |
+
"grad_norm": 0.17225264012813568,
|
| 6301 |
+
"learning_rate": 5e-05,
|
| 6302 |
+
"loss": 2.08634090423584,
|
| 6303 |
+
"step": 1798
|
| 6304 |
+
},
|
| 6305 |
+
{
|
| 6306 |
+
"epoch": 0.6276478895339714,
|
| 6307 |
+
"grad_norm": 0.19024088978767395,
|
| 6308 |
+
"learning_rate": 5e-05,
|
| 6309 |
+
"loss": 1.741422176361084,
|
| 6310 |
+
"step": 1800
|
| 6311 |
+
},
|
| 6312 |
+
{
|
| 6313 |
+
"epoch": 0.628345276077898,
|
| 6314 |
+
"grad_norm": 0.19031323492527008,
|
| 6315 |
+
"learning_rate": 5e-05,
|
| 6316 |
+
"loss": 1.8494441509246826,
|
| 6317 |
+
"step": 1802
|
| 6318 |
+
},
|
| 6319 |
+
{
|
| 6320 |
+
"epoch": 0.6290426626218247,
|
| 6321 |
+
"grad_norm": 0.21968109905719757,
|
| 6322 |
+
"learning_rate": 5e-05,
|
| 6323 |
+
"loss": 1.9487123489379883,
|
| 6324 |
+
"step": 1804
|
| 6325 |
+
},
|
| 6326 |
+
{
|
| 6327 |
+
"epoch": 0.6297400491657513,
|
| 6328 |
+
"grad_norm": 0.2162948101758957,
|
| 6329 |
+
"learning_rate": 5e-05,
|
| 6330 |
+
"loss": 1.8762587308883667,
|
| 6331 |
+
"step": 1806
|
| 6332 |
+
},
|
| 6333 |
+
{
|
| 6334 |
+
"epoch": 0.630437435709678,
|
| 6335 |
+
"grad_norm": 0.1916320025920868,
|
| 6336 |
+
"learning_rate": 5e-05,
|
| 6337 |
+
"loss": 2.0723886489868164,
|
| 6338 |
+
"step": 1808
|
| 6339 |
+
},
|
| 6340 |
+
{
|
| 6341 |
+
"epoch": 0.6311348222536046,
|
| 6342 |
+
"grad_norm": 0.22107599675655365,
|
| 6343 |
+
"learning_rate": 5e-05,
|
| 6344 |
+
"loss": 1.8572006225585938,
|
| 6345 |
+
"step": 1810
|
| 6346 |
+
},
|
| 6347 |
+
{
|
| 6348 |
+
"epoch": 0.6318322087975312,
|
| 6349 |
+
"grad_norm": 0.17048195004463196,
|
| 6350 |
+
"learning_rate": 5e-05,
|
| 6351 |
+
"loss": 2.0992026329040527,
|
| 6352 |
+
"step": 1812
|
| 6353 |
+
},
|
| 6354 |
+
{
|
| 6355 |
+
"epoch": 0.6325295953414579,
|
| 6356 |
+
"grad_norm": 0.1760718822479248,
|
| 6357 |
+
"learning_rate": 5e-05,
|
| 6358 |
+
"loss": 2.106672763824463,
|
| 6359 |
+
"step": 1814
|
| 6360 |
+
},
|
| 6361 |
+
{
|
| 6362 |
+
"epoch": 0.6332269818853845,
|
| 6363 |
+
"grad_norm": 0.28058508038520813,
|
| 6364 |
+
"learning_rate": 5e-05,
|
| 6365 |
+
"loss": 1.952498197555542,
|
| 6366 |
+
"step": 1816
|
| 6367 |
+
},
|
| 6368 |
+
{
|
| 6369 |
+
"epoch": 0.6339243684293111,
|
| 6370 |
+
"grad_norm": 0.20093607902526855,
|
| 6371 |
+
"learning_rate": 5e-05,
|
| 6372 |
+
"loss": 1.8791782855987549,
|
| 6373 |
+
"step": 1818
|
| 6374 |
+
},
|
| 6375 |
+
{
|
| 6376 |
+
"epoch": 0.6346217549732378,
|
| 6377 |
+
"grad_norm": 0.18365196883678436,
|
| 6378 |
+
"learning_rate": 5e-05,
|
| 6379 |
+
"loss": 1.9621028900146484,
|
| 6380 |
+
"step": 1820
|
| 6381 |
+
},
|
| 6382 |
+
{
|
| 6383 |
+
"epoch": 0.6353191415171644,
|
| 6384 |
+
"grad_norm": 0.22643136978149414,
|
| 6385 |
+
"learning_rate": 5e-05,
|
| 6386 |
+
"loss": 2.0192811489105225,
|
| 6387 |
+
"step": 1822
|
| 6388 |
+
},
|
| 6389 |
+
{
|
| 6390 |
+
"epoch": 0.6360165280610911,
|
| 6391 |
+
"grad_norm": 0.24730263650417328,
|
| 6392 |
+
"learning_rate": 5e-05,
|
| 6393 |
+
"loss": 1.8804388046264648,
|
| 6394 |
+
"step": 1824
|
| 6395 |
+
},
|
| 6396 |
+
{
|
| 6397 |
+
"epoch": 0.6367139146050177,
|
| 6398 |
+
"grad_norm": 0.22289031744003296,
|
| 6399 |
+
"learning_rate": 5e-05,
|
| 6400 |
+
"loss": 1.768578290939331,
|
| 6401 |
+
"step": 1826
|
| 6402 |
+
},
|
| 6403 |
+
{
|
| 6404 |
+
"epoch": 0.6374113011489443,
|
| 6405 |
+
"grad_norm": 0.2560635209083557,
|
| 6406 |
+
"learning_rate": 5e-05,
|
| 6407 |
+
"loss": 1.7840062379837036,
|
| 6408 |
+
"step": 1828
|
| 6409 |
+
},
|
| 6410 |
+
{
|
| 6411 |
+
"epoch": 0.638108687692871,
|
| 6412 |
+
"grad_norm": 0.17455683648586273,
|
| 6413 |
+
"learning_rate": 5e-05,
|
| 6414 |
+
"loss": 1.9665637016296387,
|
| 6415 |
+
"step": 1830
|
| 6416 |
+
},
|
| 6417 |
+
{
|
| 6418 |
+
"epoch": 0.6388060742367976,
|
| 6419 |
+
"grad_norm": 0.26289793848991394,
|
| 6420 |
+
"learning_rate": 5e-05,
|
| 6421 |
+
"loss": 2.072192668914795,
|
| 6422 |
+
"step": 1832
|
| 6423 |
+
},
|
| 6424 |
+
{
|
| 6425 |
+
"epoch": 0.6395034607807243,
|
| 6426 |
+
"grad_norm": 0.1808442771434784,
|
| 6427 |
+
"learning_rate": 5e-05,
|
| 6428 |
+
"loss": 1.9312012195587158,
|
| 6429 |
+
"step": 1834
|
| 6430 |
+
},
|
| 6431 |
+
{
|
| 6432 |
+
"epoch": 0.6402008473246509,
|
| 6433 |
+
"grad_norm": 0.21631719172000885,
|
| 6434 |
+
"learning_rate": 5e-05,
|
| 6435 |
+
"loss": 1.7907676696777344,
|
| 6436 |
+
"step": 1836
|
| 6437 |
+
},
|
| 6438 |
+
{
|
| 6439 |
+
"epoch": 0.6408982338685775,
|
| 6440 |
+
"grad_norm": 0.22999930381774902,
|
| 6441 |
+
"learning_rate": 5e-05,
|
| 6442 |
+
"loss": 1.7535853385925293,
|
| 6443 |
+
"step": 1838
|
| 6444 |
+
},
|
| 6445 |
+
{
|
| 6446 |
+
"epoch": 0.6415956204125042,
|
| 6447 |
+
"grad_norm": 0.2047368735074997,
|
| 6448 |
+
"learning_rate": 5e-05,
|
| 6449 |
+
"loss": 1.8089340925216675,
|
| 6450 |
+
"step": 1840
|
| 6451 |
+
},
|
| 6452 |
+
{
|
| 6453 |
+
"epoch": 0.6422930069564308,
|
| 6454 |
+
"grad_norm": 0.1811462640762329,
|
| 6455 |
+
"learning_rate": 5e-05,
|
| 6456 |
+
"loss": 1.8642290830612183,
|
| 6457 |
+
"step": 1842
|
| 6458 |
+
},
|
| 6459 |
+
{
|
| 6460 |
+
"epoch": 0.6429903935003574,
|
| 6461 |
+
"grad_norm": 0.24953307211399078,
|
| 6462 |
+
"learning_rate": 5e-05,
|
| 6463 |
+
"loss": 2.032365083694458,
|
| 6464 |
+
"step": 1844
|
| 6465 |
+
},
|
| 6466 |
+
{
|
| 6467 |
+
"epoch": 0.6436877800442841,
|
| 6468 |
+
"grad_norm": 0.22790861129760742,
|
| 6469 |
+
"learning_rate": 5e-05,
|
| 6470 |
+
"loss": 1.9307947158813477,
|
| 6471 |
+
"step": 1846
|
| 6472 |
+
},
|
| 6473 |
+
{
|
| 6474 |
+
"epoch": 0.6443851665882107,
|
| 6475 |
+
"grad_norm": 0.19640816748142242,
|
| 6476 |
+
"learning_rate": 5e-05,
|
| 6477 |
+
"loss": 1.737766981124878,
|
| 6478 |
+
"step": 1848
|
| 6479 |
+
},
|
| 6480 |
+
{
|
| 6481 |
+
"epoch": 0.6450825531321374,
|
| 6482 |
+
"grad_norm": 0.1855265349149704,
|
| 6483 |
+
"learning_rate": 5e-05,
|
| 6484 |
+
"loss": 1.901891827583313,
|
| 6485 |
+
"step": 1850
|
| 6486 |
+
},
|
| 6487 |
+
{
|
| 6488 |
+
"epoch": 0.645779939676064,
|
| 6489 |
+
"grad_norm": 0.1998153030872345,
|
| 6490 |
+
"learning_rate": 5e-05,
|
| 6491 |
+
"loss": 2.0288705825805664,
|
| 6492 |
+
"step": 1852
|
| 6493 |
+
},
|
| 6494 |
+
{
|
| 6495 |
+
"epoch": 0.6464773262199905,
|
| 6496 |
+
"grad_norm": 0.2204006016254425,
|
| 6497 |
+
"learning_rate": 5e-05,
|
| 6498 |
+
"loss": 2.0266761779785156,
|
| 6499 |
+
"step": 1854
|
| 6500 |
+
},
|
| 6501 |
+
{
|
| 6502 |
+
"epoch": 0.6471747127639172,
|
| 6503 |
+
"grad_norm": 0.29964593052864075,
|
| 6504 |
+
"learning_rate": 5e-05,
|
| 6505 |
+
"loss": 1.8914623260498047,
|
| 6506 |
+
"step": 1856
|
| 6507 |
+
},
|
| 6508 |
+
{
|
| 6509 |
+
"epoch": 0.6478720993078438,
|
| 6510 |
+
"grad_norm": 0.217330202460289,
|
| 6511 |
+
"learning_rate": 5e-05,
|
| 6512 |
+
"loss": 1.7957367897033691,
|
| 6513 |
+
"step": 1858
|
| 6514 |
+
},
|
| 6515 |
+
{
|
| 6516 |
+
"epoch": 0.6485694858517705,
|
| 6517 |
+
"grad_norm": 0.26452746987342834,
|
| 6518 |
+
"learning_rate": 5e-05,
|
| 6519 |
+
"loss": 1.915511131286621,
|
| 6520 |
+
"step": 1860
|
| 6521 |
+
},
|
| 6522 |
+
{
|
| 6523 |
+
"epoch": 0.6492668723956971,
|
| 6524 |
+
"grad_norm": 0.2192654311656952,
|
| 6525 |
+
"learning_rate": 5e-05,
|
| 6526 |
+
"loss": 1.7861742973327637,
|
| 6527 |
+
"step": 1862
|
| 6528 |
+
},
|
| 6529 |
+
{
|
| 6530 |
+
"epoch": 0.6499642589396237,
|
| 6531 |
+
"grad_norm": 0.27159371972084045,
|
| 6532 |
+
"learning_rate": 5e-05,
|
| 6533 |
+
"loss": 1.8134348392486572,
|
| 6534 |
+
"step": 1864
|
| 6535 |
+
},
|
| 6536 |
+
{
|
| 6537 |
+
"epoch": 0.6506616454835504,
|
| 6538 |
+
"grad_norm": 0.20807760953903198,
|
| 6539 |
+
"learning_rate": 5e-05,
|
| 6540 |
+
"loss": 2.0074868202209473,
|
| 6541 |
+
"step": 1866
|
| 6542 |
+
},
|
| 6543 |
+
{
|
| 6544 |
+
"epoch": 0.651359032027477,
|
| 6545 |
+
"grad_norm": 0.24914826452732086,
|
| 6546 |
+
"learning_rate": 5e-05,
|
| 6547 |
+
"loss": 1.935471534729004,
|
| 6548 |
+
"step": 1868
|
| 6549 |
+
},
|
| 6550 |
+
{
|
| 6551 |
+
"epoch": 0.6520564185714036,
|
| 6552 |
+
"grad_norm": 0.18474753201007843,
|
| 6553 |
+
"learning_rate": 5e-05,
|
| 6554 |
+
"loss": 1.9731979370117188,
|
| 6555 |
+
"step": 1870
|
| 6556 |
+
},
|
| 6557 |
+
{
|
| 6558 |
+
"epoch": 0.6527538051153303,
|
| 6559 |
+
"grad_norm": 0.1931002289056778,
|
| 6560 |
+
"learning_rate": 5e-05,
|
| 6561 |
+
"loss": 2.050971508026123,
|
| 6562 |
+
"step": 1872
|
| 6563 |
+
},
|
| 6564 |
+
{
|
| 6565 |
+
"epoch": 0.6534511916592569,
|
| 6566 |
+
"grad_norm": 0.19344626367092133,
|
| 6567 |
+
"learning_rate": 5e-05,
|
| 6568 |
+
"loss": 2.109586238861084,
|
| 6569 |
+
"step": 1874
|
| 6570 |
+
},
|
| 6571 |
+
{
|
| 6572 |
+
"epoch": 0.6541485782031836,
|
| 6573 |
+
"grad_norm": 0.19569675624370575,
|
| 6574 |
+
"learning_rate": 5e-05,
|
| 6575 |
+
"loss": 2.15287184715271,
|
| 6576 |
+
"step": 1876
|
| 6577 |
+
},
|
| 6578 |
+
{
|
| 6579 |
+
"epoch": 0.6548459647471102,
|
| 6580 |
+
"grad_norm": 0.24006061255931854,
|
| 6581 |
+
"learning_rate": 5e-05,
|
| 6582 |
+
"loss": 1.9154243469238281,
|
| 6583 |
+
"step": 1878
|
| 6584 |
+
},
|
| 6585 |
+
{
|
| 6586 |
+
"epoch": 0.6555433512910368,
|
| 6587 |
+
"grad_norm": 0.2992076575756073,
|
| 6588 |
+
"learning_rate": 5e-05,
|
| 6589 |
+
"loss": 2.059971809387207,
|
| 6590 |
+
"step": 1880
|
| 6591 |
+
},
|
| 6592 |
+
{
|
| 6593 |
+
"epoch": 0.6562407378349635,
|
| 6594 |
+
"grad_norm": 0.1879195272922516,
|
| 6595 |
+
"learning_rate": 5e-05,
|
| 6596 |
+
"loss": 1.972310185432434,
|
| 6597 |
+
"step": 1882
|
| 6598 |
+
},
|
| 6599 |
+
{
|
| 6600 |
+
"epoch": 0.6569381243788901,
|
| 6601 |
+
"grad_norm": 0.1923721581697464,
|
| 6602 |
+
"learning_rate": 5e-05,
|
| 6603 |
+
"loss": 1.8213950395584106,
|
| 6604 |
+
"step": 1884
|
| 6605 |
+
},
|
| 6606 |
+
{
|
| 6607 |
+
"epoch": 0.6576355109228167,
|
| 6608 |
+
"grad_norm": 0.31093233823776245,
|
| 6609 |
+
"learning_rate": 5e-05,
|
| 6610 |
+
"loss": 1.8817036151885986,
|
| 6611 |
+
"step": 1886
|
| 6612 |
+
},
|
| 6613 |
+
{
|
| 6614 |
+
"epoch": 0.6583328974667434,
|
| 6615 |
+
"grad_norm": 0.285758376121521,
|
| 6616 |
+
"learning_rate": 5e-05,
|
| 6617 |
+
"loss": 2.0484776496887207,
|
| 6618 |
+
"step": 1888
|
| 6619 |
+
},
|
| 6620 |
+
{
|
| 6621 |
+
"epoch": 0.65903028401067,
|
| 6622 |
+
"grad_norm": 0.22534774243831635,
|
| 6623 |
+
"learning_rate": 5e-05,
|
| 6624 |
+
"loss": 1.7124214172363281,
|
| 6625 |
+
"step": 1890
|
| 6626 |
+
},
|
| 6627 |
+
{
|
| 6628 |
+
"epoch": 0.6597276705545967,
|
| 6629 |
+
"grad_norm": 0.2966947853565216,
|
| 6630 |
+
"learning_rate": 5e-05,
|
| 6631 |
+
"loss": 1.831843376159668,
|
| 6632 |
+
"step": 1892
|
| 6633 |
+
},
|
| 6634 |
+
{
|
| 6635 |
+
"epoch": 0.6604250570985233,
|
| 6636 |
+
"grad_norm": 0.20267023146152496,
|
| 6637 |
+
"learning_rate": 5e-05,
|
| 6638 |
+
"loss": 1.9030438661575317,
|
| 6639 |
+
"step": 1894
|
| 6640 |
+
},
|
| 6641 |
+
{
|
| 6642 |
+
"epoch": 0.6611224436424499,
|
| 6643 |
+
"grad_norm": 0.26224076747894287,
|
| 6644 |
+
"learning_rate": 5e-05,
|
| 6645 |
+
"loss": 1.999426245689392,
|
| 6646 |
+
"step": 1896
|
| 6647 |
+
},
|
| 6648 |
+
{
|
| 6649 |
+
"epoch": 0.6618198301863766,
|
| 6650 |
+
"grad_norm": 0.3326214551925659,
|
| 6651 |
+
"learning_rate": 5e-05,
|
| 6652 |
+
"loss": 1.6982316970825195,
|
| 6653 |
+
"step": 1898
|
| 6654 |
+
},
|
| 6655 |
+
{
|
| 6656 |
+
"epoch": 0.6625172167303032,
|
| 6657 |
+
"grad_norm": 0.18656374514102936,
|
| 6658 |
+
"learning_rate": 5e-05,
|
| 6659 |
+
"loss": 2.2021312713623047,
|
| 6660 |
+
"step": 1900
|
| 6661 |
+
},
|
| 6662 |
+
{
|
| 6663 |
+
"epoch": 0.6632146032742299,
|
| 6664 |
+
"grad_norm": 0.21671637892723083,
|
| 6665 |
+
"learning_rate": 5e-05,
|
| 6666 |
+
"loss": 1.9708503484725952,
|
| 6667 |
+
"step": 1902
|
| 6668 |
+
},
|
| 6669 |
+
{
|
| 6670 |
+
"epoch": 0.6639119898181565,
|
| 6671 |
+
"grad_norm": 0.18599572777748108,
|
| 6672 |
+
"learning_rate": 5e-05,
|
| 6673 |
+
"loss": 2.0492098331451416,
|
| 6674 |
+
"step": 1904
|
| 6675 |
+
},
|
| 6676 |
+
{
|
| 6677 |
+
"epoch": 0.6646093763620831,
|
| 6678 |
+
"grad_norm": 0.22860100865364075,
|
| 6679 |
+
"learning_rate": 5e-05,
|
| 6680 |
+
"loss": 1.881263017654419,
|
| 6681 |
+
"step": 1906
|
| 6682 |
+
},
|
| 6683 |
+
{
|
| 6684 |
+
"epoch": 0.6653067629060098,
|
| 6685 |
+
"grad_norm": 0.22557629644870758,
|
| 6686 |
+
"learning_rate": 5e-05,
|
| 6687 |
+
"loss": 1.8670588731765747,
|
| 6688 |
+
"step": 1908
|
| 6689 |
+
},
|
| 6690 |
+
{
|
| 6691 |
+
"epoch": 0.6660041494499364,
|
| 6692 |
+
"grad_norm": 0.1576979160308838,
|
| 6693 |
+
"learning_rate": 5e-05,
|
| 6694 |
+
"loss": 2.156865119934082,
|
| 6695 |
+
"step": 1910
|
| 6696 |
+
},
|
| 6697 |
+
{
|
| 6698 |
+
"epoch": 0.666701535993863,
|
| 6699 |
+
"grad_norm": 0.20873196423053741,
|
| 6700 |
+
"learning_rate": 5e-05,
|
| 6701 |
+
"loss": 2.1637001037597656,
|
| 6702 |
+
"step": 1912
|
| 6703 |
+
},
|
| 6704 |
+
{
|
| 6705 |
+
"epoch": 0.6673989225377897,
|
| 6706 |
+
"grad_norm": 0.21369338035583496,
|
| 6707 |
+
"learning_rate": 5e-05,
|
| 6708 |
+
"loss": 2.092163324356079,
|
| 6709 |
+
"step": 1914
|
| 6710 |
+
},
|
| 6711 |
+
{
|
| 6712 |
+
"epoch": 0.6680963090817162,
|
| 6713 |
+
"grad_norm": 0.2540096044540405,
|
| 6714 |
+
"learning_rate": 5e-05,
|
| 6715 |
+
"loss": 1.9079657793045044,
|
| 6716 |
+
"step": 1916
|
| 6717 |
+
},
|
| 6718 |
+
{
|
| 6719 |
+
"epoch": 0.668793695625643,
|
| 6720 |
+
"grad_norm": 0.19144493341445923,
|
| 6721 |
+
"learning_rate": 5e-05,
|
| 6722 |
+
"loss": 1.9168627262115479,
|
| 6723 |
+
"step": 1918
|
| 6724 |
+
},
|
| 6725 |
+
{
|
| 6726 |
+
"epoch": 0.6694910821695695,
|
| 6727 |
+
"grad_norm": 0.20210625231266022,
|
| 6728 |
+
"learning_rate": 5e-05,
|
| 6729 |
+
"loss": 1.975937843322754,
|
| 6730 |
+
"step": 1920
|
| 6731 |
+
},
|
| 6732 |
+
{
|
| 6733 |
+
"epoch": 0.6701884687134961,
|
| 6734 |
+
"grad_norm": 0.1825406700372696,
|
| 6735 |
+
"learning_rate": 5e-05,
|
| 6736 |
+
"loss": 1.977008581161499,
|
| 6737 |
+
"step": 1922
|
| 6738 |
+
},
|
| 6739 |
+
{
|
| 6740 |
+
"epoch": 0.6708858552574228,
|
| 6741 |
+
"grad_norm": 0.17887762188911438,
|
| 6742 |
+
"learning_rate": 5e-05,
|
| 6743 |
+
"loss": 1.9100210666656494,
|
| 6744 |
+
"step": 1924
|
| 6745 |
+
},
|
| 6746 |
+
{
|
| 6747 |
+
"epoch": 0.6715832418013494,
|
| 6748 |
+
"grad_norm": 0.23779994249343872,
|
| 6749 |
+
"learning_rate": 5e-05,
|
| 6750 |
+
"loss": 2.093499183654785,
|
| 6751 |
+
"step": 1926
|
| 6752 |
+
},
|
| 6753 |
+
{
|
| 6754 |
+
"epoch": 0.6722806283452761,
|
| 6755 |
+
"grad_norm": 0.1986411213874817,
|
| 6756 |
+
"learning_rate": 5e-05,
|
| 6757 |
+
"loss": 1.8822386264801025,
|
| 6758 |
+
"step": 1928
|
| 6759 |
+
},
|
| 6760 |
+
{
|
| 6761 |
+
"epoch": 0.6729780148892027,
|
| 6762 |
+
"grad_norm": 0.24904435873031616,
|
| 6763 |
+
"learning_rate": 5e-05,
|
| 6764 |
+
"loss": 2.098172903060913,
|
| 6765 |
+
"step": 1930
|
| 6766 |
+
},
|
| 6767 |
+
{
|
| 6768 |
+
"epoch": 0.6736754014331293,
|
| 6769 |
+
"grad_norm": 0.220512256026268,
|
| 6770 |
+
"learning_rate": 5e-05,
|
| 6771 |
+
"loss": 1.8210785388946533,
|
| 6772 |
+
"step": 1932
|
| 6773 |
+
},
|
| 6774 |
+
{
|
| 6775 |
+
"epoch": 0.674372787977056,
|
| 6776 |
+
"grad_norm": 0.202888622879982,
|
| 6777 |
+
"learning_rate": 5e-05,
|
| 6778 |
+
"loss": 1.8291442394256592,
|
| 6779 |
+
"step": 1934
|
| 6780 |
+
},
|
| 6781 |
+
{
|
| 6782 |
+
"epoch": 0.6750701745209826,
|
| 6783 |
+
"grad_norm": 0.17567485570907593,
|
| 6784 |
+
"learning_rate": 5e-05,
|
| 6785 |
+
"loss": 1.904573917388916,
|
| 6786 |
+
"step": 1936
|
| 6787 |
+
},
|
| 6788 |
+
{
|
| 6789 |
+
"epoch": 0.6757675610649092,
|
| 6790 |
+
"grad_norm": 0.1913834512233734,
|
| 6791 |
+
"learning_rate": 5e-05,
|
| 6792 |
+
"loss": 1.8033437728881836,
|
| 6793 |
+
"step": 1938
|
| 6794 |
+
},
|
| 6795 |
+
{
|
| 6796 |
+
"epoch": 0.6764649476088359,
|
| 6797 |
+
"grad_norm": 0.25764867663383484,
|
| 6798 |
+
"learning_rate": 5e-05,
|
| 6799 |
+
"loss": 1.8059159517288208,
|
| 6800 |
+
"step": 1940
|
| 6801 |
+
},
|
| 6802 |
+
{
|
| 6803 |
+
"epoch": 0.6771623341527625,
|
| 6804 |
+
"grad_norm": 0.19583149254322052,
|
| 6805 |
+
"learning_rate": 5e-05,
|
| 6806 |
+
"loss": 1.9165745973587036,
|
| 6807 |
+
"step": 1942
|
| 6808 |
+
},
|
| 6809 |
+
{
|
| 6810 |
+
"epoch": 0.6778597206966892,
|
| 6811 |
+
"grad_norm": 0.23066437244415283,
|
| 6812 |
+
"learning_rate": 5e-05,
|
| 6813 |
+
"loss": 1.9404631853103638,
|
| 6814 |
+
"step": 1944
|
| 6815 |
+
},
|
| 6816 |
+
{
|
| 6817 |
+
"epoch": 0.6785571072406158,
|
| 6818 |
+
"grad_norm": 0.13939902186393738,
|
| 6819 |
+
"learning_rate": 5e-05,
|
| 6820 |
+
"loss": 1.7981820106506348,
|
| 6821 |
+
"step": 1946
|
| 6822 |
+
},
|
| 6823 |
+
{
|
| 6824 |
+
"epoch": 0.6792544937845424,
|
| 6825 |
+
"grad_norm": 0.20038597285747528,
|
| 6826 |
+
"learning_rate": 5e-05,
|
| 6827 |
+
"loss": 2.0496368408203125,
|
| 6828 |
+
"step": 1948
|
| 6829 |
+
},
|
| 6830 |
+
{
|
| 6831 |
+
"epoch": 0.6799518803284691,
|
| 6832 |
+
"grad_norm": 0.21413299441337585,
|
| 6833 |
+
"learning_rate": 5e-05,
|
| 6834 |
+
"loss": 2.1031856536865234,
|
| 6835 |
+
"step": 1950
|
| 6836 |
+
},
|
| 6837 |
+
{
|
| 6838 |
+
"epoch": 0.6806492668723957,
|
| 6839 |
+
"grad_norm": 0.204486683011055,
|
| 6840 |
+
"learning_rate": 5e-05,
|
| 6841 |
+
"loss": 1.8733688592910767,
|
| 6842 |
+
"step": 1952
|
| 6843 |
+
},
|
| 6844 |
+
{
|
| 6845 |
+
"epoch": 0.6813466534163223,
|
| 6846 |
+
"grad_norm": 0.21280021965503693,
|
| 6847 |
+
"learning_rate": 5e-05,
|
| 6848 |
+
"loss": 1.9597742557525635,
|
| 6849 |
+
"step": 1954
|
| 6850 |
+
},
|
| 6851 |
+
{
|
| 6852 |
+
"epoch": 0.682044039960249,
|
| 6853 |
+
"grad_norm": 0.2817871570587158,
|
| 6854 |
+
"learning_rate": 5e-05,
|
| 6855 |
+
"loss": 1.8568202257156372,
|
| 6856 |
+
"step": 1956
|
| 6857 |
+
},
|
| 6858 |
+
{
|
| 6859 |
+
"epoch": 0.6827414265041756,
|
| 6860 |
+
"grad_norm": 0.2650154232978821,
|
| 6861 |
+
"learning_rate": 5e-05,
|
| 6862 |
+
"loss": 1.953235387802124,
|
| 6863 |
+
"step": 1958
|
| 6864 |
+
},
|
| 6865 |
+
{
|
| 6866 |
+
"epoch": 0.6834388130481023,
|
| 6867 |
+
"grad_norm": 0.22025105357170105,
|
| 6868 |
+
"learning_rate": 5e-05,
|
| 6869 |
+
"loss": 1.9382929801940918,
|
| 6870 |
+
"step": 1960
|
| 6871 |
+
},
|
| 6872 |
+
{
|
| 6873 |
+
"epoch": 0.6841361995920289,
|
| 6874 |
+
"grad_norm": 0.2663877606391907,
|
| 6875 |
+
"learning_rate": 5e-05,
|
| 6876 |
+
"loss": 2.135603189468384,
|
| 6877 |
+
"step": 1962
|
| 6878 |
+
},
|
| 6879 |
+
{
|
| 6880 |
+
"epoch": 0.6848335861359555,
|
| 6881 |
+
"grad_norm": 0.17246317863464355,
|
| 6882 |
+
"learning_rate": 5e-05,
|
| 6883 |
+
"loss": 2.0259571075439453,
|
| 6884 |
+
"step": 1964
|
| 6885 |
+
},
|
| 6886 |
+
{
|
| 6887 |
+
"epoch": 0.6855309726798822,
|
| 6888 |
+
"grad_norm": 0.16565921902656555,
|
| 6889 |
+
"learning_rate": 5e-05,
|
| 6890 |
+
"loss": 2.1059682369232178,
|
| 6891 |
+
"step": 1966
|
| 6892 |
+
},
|
| 6893 |
+
{
|
| 6894 |
+
"epoch": 0.6862283592238088,
|
| 6895 |
+
"grad_norm": 0.2343938946723938,
|
| 6896 |
+
"learning_rate": 5e-05,
|
| 6897 |
+
"loss": 2.0088436603546143,
|
| 6898 |
+
"step": 1968
|
| 6899 |
+
},
|
| 6900 |
+
{
|
| 6901 |
+
"epoch": 0.6869257457677355,
|
| 6902 |
+
"grad_norm": 0.19023862481117249,
|
| 6903 |
+
"learning_rate": 5e-05,
|
| 6904 |
+
"loss": 1.8418056964874268,
|
| 6905 |
+
"step": 1970
|
| 6906 |
+
},
|
| 6907 |
+
{
|
| 6908 |
+
"epoch": 0.687623132311662,
|
| 6909 |
+
"grad_norm": 0.17515328526496887,
|
| 6910 |
+
"learning_rate": 5e-05,
|
| 6911 |
+
"loss": 1.9040826559066772,
|
| 6912 |
+
"step": 1972
|
| 6913 |
+
},
|
| 6914 |
+
{
|
| 6915 |
+
"epoch": 0.6883205188555886,
|
| 6916 |
+
"grad_norm": 0.26450735330581665,
|
| 6917 |
+
"learning_rate": 5e-05,
|
| 6918 |
+
"loss": 1.8515355587005615,
|
| 6919 |
+
"step": 1974
|
| 6920 |
+
},
|
| 6921 |
+
{
|
| 6922 |
+
"epoch": 0.6890179053995154,
|
| 6923 |
+
"grad_norm": 0.24569930136203766,
|
| 6924 |
+
"learning_rate": 5e-05,
|
| 6925 |
+
"loss": 1.948767900466919,
|
| 6926 |
+
"step": 1976
|
| 6927 |
+
},
|
| 6928 |
+
{
|
| 6929 |
+
"epoch": 0.6897152919434419,
|
| 6930 |
+
"grad_norm": 0.2716074585914612,
|
| 6931 |
+
"learning_rate": 5e-05,
|
| 6932 |
+
"loss": 1.9467777013778687,
|
| 6933 |
+
"step": 1978
|
| 6934 |
+
},
|
| 6935 |
+
{
|
| 6936 |
+
"epoch": 0.6904126784873685,
|
| 6937 |
+
"grad_norm": 0.23883529007434845,
|
| 6938 |
+
"learning_rate": 5e-05,
|
| 6939 |
+
"loss": 1.912539005279541,
|
| 6940 |
+
"step": 1980
|
| 6941 |
+
},
|
| 6942 |
+
{
|
| 6943 |
+
"epoch": 0.6911100650312952,
|
| 6944 |
+
"grad_norm": 0.18049849569797516,
|
| 6945 |
+
"learning_rate": 5e-05,
|
| 6946 |
+
"loss": 1.9098021984100342,
|
| 6947 |
+
"step": 1982
|
| 6948 |
+
},
|
| 6949 |
+
{
|
| 6950 |
+
"epoch": 0.6918074515752218,
|
| 6951 |
+
"grad_norm": 0.2253192514181137,
|
| 6952 |
+
"learning_rate": 5e-05,
|
| 6953 |
+
"loss": 1.8988468647003174,
|
| 6954 |
+
"step": 1984
|
| 6955 |
+
},
|
| 6956 |
+
{
|
| 6957 |
+
"epoch": 0.6925048381191485,
|
| 6958 |
+
"grad_norm": 0.22085651755332947,
|
| 6959 |
+
"learning_rate": 5e-05,
|
| 6960 |
+
"loss": 2.098668336868286,
|
| 6961 |
+
"step": 1986
|
| 6962 |
+
},
|
| 6963 |
+
{
|
| 6964 |
+
"epoch": 0.6932022246630751,
|
| 6965 |
+
"grad_norm": 0.2529553472995758,
|
| 6966 |
+
"learning_rate": 5e-05,
|
| 6967 |
+
"loss": 1.877577304840088,
|
| 6968 |
+
"step": 1988
|
| 6969 |
+
},
|
| 6970 |
+
{
|
| 6971 |
+
"epoch": 0.6938996112070017,
|
| 6972 |
+
"grad_norm": 0.20500746369361877,
|
| 6973 |
+
"learning_rate": 5e-05,
|
| 6974 |
+
"loss": 1.9987249374389648,
|
| 6975 |
+
"step": 1990
|
| 6976 |
+
},
|
| 6977 |
+
{
|
| 6978 |
+
"epoch": 0.6945969977509284,
|
| 6979 |
+
"grad_norm": 0.4637402594089508,
|
| 6980 |
+
"learning_rate": 5e-05,
|
| 6981 |
+
"loss": 1.9278911352157593,
|
| 6982 |
+
"step": 1992
|
| 6983 |
+
},
|
| 6984 |
+
{
|
| 6985 |
+
"epoch": 0.695294384294855,
|
| 6986 |
+
"grad_norm": 0.243018239736557,
|
| 6987 |
+
"learning_rate": 5e-05,
|
| 6988 |
+
"loss": 1.951491117477417,
|
| 6989 |
+
"step": 1994
|
| 6990 |
+
},
|
| 6991 |
+
{
|
| 6992 |
+
"epoch": 0.6959917708387817,
|
| 6993 |
+
"grad_norm": 0.22801651060581207,
|
| 6994 |
+
"learning_rate": 5e-05,
|
| 6995 |
+
"loss": 1.8762612342834473,
|
| 6996 |
+
"step": 1996
|
| 6997 |
+
},
|
| 6998 |
+
{
|
| 6999 |
+
"epoch": 0.6966891573827083,
|
| 7000 |
+
"grad_norm": 0.2254435420036316,
|
| 7001 |
+
"learning_rate": 5e-05,
|
| 7002 |
+
"loss": 1.997175931930542,
|
| 7003 |
+
"step": 1998
|
| 7004 |
+
},
|
| 7005 |
+
{
|
| 7006 |
+
"epoch": 0.6973865439266349,
|
| 7007 |
+
"grad_norm": 0.17995749413967133,
|
| 7008 |
+
"learning_rate": 5e-05,
|
| 7009 |
+
"loss": 1.8036714792251587,
|
| 7010 |
+
"step": 2000
|
| 7011 |
+
},
|
| 7012 |
+
{
|
| 7013 |
+
"epoch": 0.6980839304705616,
|
| 7014 |
+
"grad_norm": 0.3124207556247711,
|
| 7015 |
+
"learning_rate": 5e-05,
|
| 7016 |
+
"loss": 1.9937630891799927,
|
| 7017 |
+
"step": 2002
|
| 7018 |
+
},
|
| 7019 |
+
{
|
| 7020 |
+
"epoch": 0.6987813170144882,
|
| 7021 |
+
"grad_norm": 0.20657879114151,
|
| 7022 |
+
"learning_rate": 5e-05,
|
| 7023 |
+
"loss": 2.1100950241088867,
|
| 7024 |
+
"step": 2004
|
| 7025 |
+
},
|
| 7026 |
+
{
|
| 7027 |
+
"epoch": 0.6994787035584148,
|
| 7028 |
+
"grad_norm": 0.25729361176490784,
|
| 7029 |
+
"learning_rate": 5e-05,
|
| 7030 |
+
"loss": 1.8586134910583496,
|
| 7031 |
+
"step": 2006
|
| 7032 |
+
},
|
| 7033 |
+
{
|
| 7034 |
+
"epoch": 0.7001760901023415,
|
| 7035 |
+
"grad_norm": 0.17236414551734924,
|
| 7036 |
+
"learning_rate": 5e-05,
|
| 7037 |
+
"loss": 2.2024800777435303,
|
| 7038 |
+
"step": 2008
|
| 7039 |
+
},
|
| 7040 |
+
{
|
| 7041 |
+
"epoch": 0.7008734766462681,
|
| 7042 |
+
"grad_norm": 0.19207501411437988,
|
| 7043 |
+
"learning_rate": 5e-05,
|
| 7044 |
+
"loss": 1.9439852237701416,
|
| 7045 |
+
"step": 2010
|
| 7046 |
+
},
|
| 7047 |
+
{
|
| 7048 |
+
"epoch": 0.7015708631901948,
|
| 7049 |
+
"grad_norm": 0.20738041400909424,
|
| 7050 |
+
"learning_rate": 5e-05,
|
| 7051 |
+
"loss": 1.8800491094589233,
|
| 7052 |
+
"step": 2012
|
| 7053 |
+
},
|
| 7054 |
+
{
|
| 7055 |
+
"epoch": 0.7022682497341214,
|
| 7056 |
+
"grad_norm": 0.17762541770935059,
|
| 7057 |
+
"learning_rate": 5e-05,
|
| 7058 |
+
"loss": 1.9378938674926758,
|
| 7059 |
+
"step": 2014
|
| 7060 |
+
},
|
| 7061 |
+
{
|
| 7062 |
+
"epoch": 0.702965636278048,
|
| 7063 |
+
"grad_norm": 0.2435765415430069,
|
| 7064 |
+
"learning_rate": 5e-05,
|
| 7065 |
+
"loss": 2.0488927364349365,
|
| 7066 |
+
"step": 2016
|
| 7067 |
+
},
|
| 7068 |
+
{
|
| 7069 |
+
"epoch": 0.7036630228219747,
|
| 7070 |
+
"grad_norm": 0.25711968541145325,
|
| 7071 |
+
"learning_rate": 5e-05,
|
| 7072 |
+
"loss": 1.8337585926055908,
|
| 7073 |
+
"step": 2018
|
| 7074 |
+
},
|
| 7075 |
+
{
|
| 7076 |
+
"epoch": 0.7043604093659013,
|
| 7077 |
+
"grad_norm": 0.272570937871933,
|
| 7078 |
+
"learning_rate": 5e-05,
|
| 7079 |
+
"loss": 1.7698662281036377,
|
| 7080 |
+
"step": 2020
|
| 7081 |
+
},
|
| 7082 |
+
{
|
| 7083 |
+
"epoch": 0.7050577959098279,
|
| 7084 |
+
"grad_norm": 0.1944895088672638,
|
| 7085 |
+
"learning_rate": 5e-05,
|
| 7086 |
+
"loss": 1.9470655918121338,
|
| 7087 |
+
"step": 2022
|
| 7088 |
+
},
|
| 7089 |
+
{
|
| 7090 |
+
"epoch": 0.7057551824537546,
|
| 7091 |
+
"grad_norm": 0.20459075272083282,
|
| 7092 |
+
"learning_rate": 5e-05,
|
| 7093 |
+
"loss": 1.9057765007019043,
|
| 7094 |
+
"step": 2024
|
| 7095 |
+
},
|
| 7096 |
+
{
|
| 7097 |
+
"epoch": 0.7064525689976812,
|
| 7098 |
+
"grad_norm": 0.2992056906223297,
|
| 7099 |
+
"learning_rate": 5e-05,
|
| 7100 |
+
"loss": 1.9368441104888916,
|
| 7101 |
+
"step": 2026
|
| 7102 |
+
},
|
| 7103 |
+
{
|
| 7104 |
+
"epoch": 0.7071499555416079,
|
| 7105 |
+
"grad_norm": 0.24994510412216187,
|
| 7106 |
+
"learning_rate": 5e-05,
|
| 7107 |
+
"loss": 1.867093563079834,
|
| 7108 |
+
"step": 2028
|
| 7109 |
+
},
|
| 7110 |
+
{
|
| 7111 |
+
"epoch": 0.7078473420855345,
|
| 7112 |
+
"grad_norm": 0.18913321197032928,
|
| 7113 |
+
"learning_rate": 5e-05,
|
| 7114 |
+
"loss": 2.0641443729400635,
|
| 7115 |
+
"step": 2030
|
| 7116 |
+
},
|
| 7117 |
+
{
|
| 7118 |
+
"epoch": 0.708544728629461,
|
| 7119 |
+
"grad_norm": 0.3258306384086609,
|
| 7120 |
+
"learning_rate": 5e-05,
|
| 7121 |
+
"loss": 1.8863120079040527,
|
| 7122 |
+
"step": 2032
|
| 7123 |
+
},
|
| 7124 |
+
{
|
| 7125 |
+
"epoch": 0.7092421151733878,
|
| 7126 |
+
"grad_norm": 0.2451459914445877,
|
| 7127 |
+
"learning_rate": 5e-05,
|
| 7128 |
+
"loss": 1.8047946691513062,
|
| 7129 |
+
"step": 2034
|
| 7130 |
+
},
|
| 7131 |
+
{
|
| 7132 |
+
"epoch": 0.7099395017173143,
|
| 7133 |
+
"grad_norm": 0.21692386269569397,
|
| 7134 |
+
"learning_rate": 5e-05,
|
| 7135 |
+
"loss": 1.965606451034546,
|
| 7136 |
+
"step": 2036
|
| 7137 |
+
},
|
| 7138 |
+
{
|
| 7139 |
+
"epoch": 0.710636888261241,
|
| 7140 |
+
"grad_norm": 0.21653258800506592,
|
| 7141 |
+
"learning_rate": 5e-05,
|
| 7142 |
+
"loss": 2.1215691566467285,
|
| 7143 |
+
"step": 2038
|
| 7144 |
+
},
|
| 7145 |
+
{
|
| 7146 |
+
"epoch": 0.7113342748051676,
|
| 7147 |
+
"grad_norm": 0.25049927830696106,
|
| 7148 |
+
"learning_rate": 5e-05,
|
| 7149 |
+
"loss": 1.8238928318023682,
|
| 7150 |
+
"step": 2040
|
| 7151 |
+
},
|
| 7152 |
+
{
|
| 7153 |
+
"epoch": 0.7120316613490942,
|
| 7154 |
+
"grad_norm": 0.23914234340190887,
|
| 7155 |
+
"learning_rate": 5e-05,
|
| 7156 |
+
"loss": 1.9403655529022217,
|
| 7157 |
+
"step": 2042
|
| 7158 |
+
},
|
| 7159 |
+
{
|
| 7160 |
+
"epoch": 0.7127290478930209,
|
| 7161 |
+
"grad_norm": 0.2210332304239273,
|
| 7162 |
+
"learning_rate": 5e-05,
|
| 7163 |
+
"loss": 1.9609662294387817,
|
| 7164 |
+
"step": 2044
|
| 7165 |
+
},
|
| 7166 |
+
{
|
| 7167 |
+
"epoch": 0.7134264344369475,
|
| 7168 |
+
"grad_norm": 0.25324663519859314,
|
| 7169 |
+
"learning_rate": 5e-05,
|
| 7170 |
+
"loss": 2.0118846893310547,
|
| 7171 |
+
"step": 2046
|
| 7172 |
+
},
|
| 7173 |
+
{
|
| 7174 |
+
"epoch": 0.7141238209808741,
|
| 7175 |
+
"grad_norm": 0.23050567507743835,
|
| 7176 |
+
"learning_rate": 5e-05,
|
| 7177 |
+
"loss": 2.155590295791626,
|
| 7178 |
+
"step": 2048
|
| 7179 |
+
},
|
| 7180 |
+
{
|
| 7181 |
+
"epoch": 0.7148212075248008,
|
| 7182 |
+
"grad_norm": 0.27442628145217896,
|
| 7183 |
+
"learning_rate": 5e-05,
|
| 7184 |
+
"loss": 1.8701404333114624,
|
| 7185 |
+
"step": 2050
|
| 7186 |
+
},
|
| 7187 |
+
{
|
| 7188 |
+
"epoch": 0.7155185940687274,
|
| 7189 |
+
"grad_norm": 0.19824662804603577,
|
| 7190 |
+
"learning_rate": 5e-05,
|
| 7191 |
+
"loss": 1.9632997512817383,
|
| 7192 |
+
"step": 2052
|
| 7193 |
+
},
|
| 7194 |
+
{
|
| 7195 |
+
"epoch": 0.7162159806126541,
|
| 7196 |
+
"grad_norm": 0.17668820917606354,
|
| 7197 |
+
"learning_rate": 5e-05,
|
| 7198 |
+
"loss": 2.0120043754577637,
|
| 7199 |
+
"step": 2054
|
| 7200 |
+
},
|
| 7201 |
+
{
|
| 7202 |
+
"epoch": 0.7169133671565807,
|
| 7203 |
+
"grad_norm": 0.231851264834404,
|
| 7204 |
+
"learning_rate": 5e-05,
|
| 7205 |
+
"loss": 2.0922467708587646,
|
| 7206 |
+
"step": 2056
|
| 7207 |
+
},
|
| 7208 |
+
{
|
| 7209 |
+
"epoch": 0.7176107537005073,
|
| 7210 |
+
"grad_norm": 0.2536415159702301,
|
| 7211 |
+
"learning_rate": 5e-05,
|
| 7212 |
+
"loss": 1.9578828811645508,
|
| 7213 |
+
"step": 2058
|
| 7214 |
+
},
|
| 7215 |
+
{
|
| 7216 |
+
"epoch": 0.718308140244434,
|
| 7217 |
+
"grad_norm": 0.20625193417072296,
|
| 7218 |
+
"learning_rate": 5e-05,
|
| 7219 |
+
"loss": 2.0224688053131104,
|
| 7220 |
+
"step": 2060
|
| 7221 |
+
},
|
| 7222 |
+
{
|
| 7223 |
+
"epoch": 0.7190055267883606,
|
| 7224 |
+
"grad_norm": 0.16995298862457275,
|
| 7225 |
+
"learning_rate": 5e-05,
|
| 7226 |
+
"loss": 1.9539906978607178,
|
| 7227 |
+
"step": 2062
|
| 7228 |
+
},
|
| 7229 |
+
{
|
| 7230 |
+
"epoch": 0.7197029133322873,
|
| 7231 |
+
"grad_norm": 0.21072250604629517,
|
| 7232 |
+
"learning_rate": 5e-05,
|
| 7233 |
+
"loss": 1.9282296895980835,
|
| 7234 |
+
"step": 2064
|
| 7235 |
+
},
|
| 7236 |
+
{
|
| 7237 |
+
"epoch": 0.7204002998762139,
|
| 7238 |
+
"grad_norm": 0.16904211044311523,
|
| 7239 |
+
"learning_rate": 5e-05,
|
| 7240 |
+
"loss": 2.323582649230957,
|
| 7241 |
+
"step": 2066
|
| 7242 |
+
},
|
| 7243 |
+
{
|
| 7244 |
+
"epoch": 0.7210976864201405,
|
| 7245 |
+
"grad_norm": 0.20240511000156403,
|
| 7246 |
+
"learning_rate": 5e-05,
|
| 7247 |
+
"loss": 1.7976229190826416,
|
| 7248 |
+
"step": 2068
|
| 7249 |
+
},
|
| 7250 |
+
{
|
| 7251 |
+
"epoch": 0.7217950729640672,
|
| 7252 |
+
"grad_norm": 0.21417611837387085,
|
| 7253 |
+
"learning_rate": 5e-05,
|
| 7254 |
+
"loss": 1.943137526512146,
|
| 7255 |
+
"step": 2070
|
| 7256 |
+
},
|
| 7257 |
+
{
|
| 7258 |
+
"epoch": 0.7224924595079938,
|
| 7259 |
+
"grad_norm": 0.23913216590881348,
|
| 7260 |
+
"learning_rate": 5e-05,
|
| 7261 |
+
"loss": 1.892772912979126,
|
| 7262 |
+
"step": 2072
|
| 7263 |
+
},
|
| 7264 |
+
{
|
| 7265 |
+
"epoch": 0.7231898460519204,
|
| 7266 |
+
"grad_norm": 0.210185244679451,
|
| 7267 |
+
"learning_rate": 5e-05,
|
| 7268 |
+
"loss": 2.1655025482177734,
|
| 7269 |
+
"step": 2074
|
| 7270 |
+
},
|
| 7271 |
+
{
|
| 7272 |
+
"epoch": 0.7238872325958471,
|
| 7273 |
+
"grad_norm": 0.29644832015037537,
|
| 7274 |
+
"learning_rate": 5e-05,
|
| 7275 |
+
"loss": 1.9400770664215088,
|
| 7276 |
+
"step": 2076
|
| 7277 |
+
},
|
| 7278 |
+
{
|
| 7279 |
+
"epoch": 0.7245846191397737,
|
| 7280 |
+
"grad_norm": 0.21575401723384857,
|
| 7281 |
+
"learning_rate": 5e-05,
|
| 7282 |
+
"loss": 1.8323345184326172,
|
| 7283 |
+
"step": 2078
|
| 7284 |
+
},
|
| 7285 |
+
{
|
| 7286 |
+
"epoch": 0.7252820056837004,
|
| 7287 |
+
"grad_norm": 0.26795539259910583,
|
| 7288 |
+
"learning_rate": 5e-05,
|
| 7289 |
+
"loss": 1.9135476350784302,
|
| 7290 |
+
"step": 2080
|
| 7291 |
+
},
|
| 7292 |
+
{
|
| 7293 |
+
"epoch": 0.725979392227627,
|
| 7294 |
+
"grad_norm": 0.21470215916633606,
|
| 7295 |
+
"learning_rate": 5e-05,
|
| 7296 |
+
"loss": 1.8226373195648193,
|
| 7297 |
+
"step": 2082
|
| 7298 |
+
},
|
| 7299 |
+
{
|
| 7300 |
+
"epoch": 0.7266767787715536,
|
| 7301 |
+
"grad_norm": 0.23065048456192017,
|
| 7302 |
+
"learning_rate": 5e-05,
|
| 7303 |
+
"loss": 1.7718195915222168,
|
| 7304 |
+
"step": 2084
|
| 7305 |
+
},
|
| 7306 |
+
{
|
| 7307 |
+
"epoch": 0.7273741653154803,
|
| 7308 |
+
"grad_norm": 0.23382049798965454,
|
| 7309 |
+
"learning_rate": 5e-05,
|
| 7310 |
+
"loss": 1.9421563148498535,
|
| 7311 |
+
"step": 2086
|
| 7312 |
+
},
|
| 7313 |
+
{
|
| 7314 |
+
"epoch": 0.7280715518594069,
|
| 7315 |
+
"grad_norm": 0.20786328613758087,
|
| 7316 |
+
"learning_rate": 5e-05,
|
| 7317 |
+
"loss": 1.8556504249572754,
|
| 7318 |
+
"step": 2088
|
| 7319 |
+
},
|
| 7320 |
+
{
|
| 7321 |
+
"epoch": 0.7287689384033335,
|
| 7322 |
+
"grad_norm": 0.2664857506752014,
|
| 7323 |
+
"learning_rate": 5e-05,
|
| 7324 |
+
"loss": 2.020401954650879,
|
| 7325 |
+
"step": 2090
|
| 7326 |
+
},
|
| 7327 |
+
{
|
| 7328 |
+
"epoch": 0.7294663249472602,
|
| 7329 |
+
"grad_norm": 0.18101157248020172,
|
| 7330 |
+
"learning_rate": 5e-05,
|
| 7331 |
+
"loss": 1.9485325813293457,
|
| 7332 |
+
"step": 2092
|
| 7333 |
+
},
|
| 7334 |
+
{
|
| 7335 |
+
"epoch": 0.7301637114911868,
|
| 7336 |
+
"grad_norm": 0.19057531654834747,
|
| 7337 |
+
"learning_rate": 5e-05,
|
| 7338 |
+
"loss": 1.931412696838379,
|
| 7339 |
+
"step": 2094
|
| 7340 |
+
},
|
| 7341 |
+
{
|
| 7342 |
+
"epoch": 0.7308610980351135,
|
| 7343 |
+
"grad_norm": 0.20870794355869293,
|
| 7344 |
+
"learning_rate": 5e-05,
|
| 7345 |
+
"loss": 1.9227871894836426,
|
| 7346 |
+
"step": 2096
|
| 7347 |
+
},
|
| 7348 |
+
{
|
| 7349 |
+
"epoch": 0.73155848457904,
|
| 7350 |
+
"grad_norm": 0.2855563461780548,
|
| 7351 |
+
"learning_rate": 5e-05,
|
| 7352 |
+
"loss": 1.9840281009674072,
|
| 7353 |
+
"step": 2098
|
| 7354 |
+
},
|
| 7355 |
+
{
|
| 7356 |
+
"epoch": 0.7322558711229666,
|
| 7357 |
+
"grad_norm": 0.2462751567363739,
|
| 7358 |
+
"learning_rate": 5e-05,
|
| 7359 |
+
"loss": 1.9993574619293213,
|
| 7360 |
+
"step": 2100
|
| 7361 |
+
},
|
| 7362 |
+
{
|
| 7363 |
+
"epoch": 0.7329532576668933,
|
| 7364 |
+
"grad_norm": 0.2574477791786194,
|
| 7365 |
+
"learning_rate": 5e-05,
|
| 7366 |
+
"loss": 2.060620069503784,
|
| 7367 |
+
"step": 2102
|
| 7368 |
+
},
|
| 7369 |
+
{
|
| 7370 |
+
"epoch": 0.7336506442108199,
|
| 7371 |
+
"grad_norm": 0.1800810545682907,
|
| 7372 |
+
"learning_rate": 5e-05,
|
| 7373 |
+
"loss": 2.0911858081817627,
|
| 7374 |
+
"step": 2104
|
| 7375 |
+
},
|
| 7376 |
+
{
|
| 7377 |
+
"epoch": 0.7343480307547466,
|
| 7378 |
+
"grad_norm": 0.17857886850833893,
|
| 7379 |
+
"learning_rate": 5e-05,
|
| 7380 |
+
"loss": 1.7908296585083008,
|
| 7381 |
+
"step": 2106
|
| 7382 |
+
},
|
| 7383 |
+
{
|
| 7384 |
+
"epoch": 0.7350454172986732,
|
| 7385 |
+
"grad_norm": 0.2516303062438965,
|
| 7386 |
+
"learning_rate": 5e-05,
|
| 7387 |
+
"loss": 1.7887701988220215,
|
| 7388 |
+
"step": 2108
|
| 7389 |
+
},
|
| 7390 |
+
{
|
| 7391 |
+
"epoch": 0.7357428038425998,
|
| 7392 |
+
"grad_norm": 0.20800773799419403,
|
| 7393 |
+
"learning_rate": 5e-05,
|
| 7394 |
+
"loss": 1.734657883644104,
|
| 7395 |
+
"step": 2110
|
| 7396 |
+
},
|
| 7397 |
+
{
|
| 7398 |
+
"epoch": 0.7364401903865265,
|
| 7399 |
+
"grad_norm": 0.19409075379371643,
|
| 7400 |
+
"learning_rate": 5e-05,
|
| 7401 |
+
"loss": 1.9594202041625977,
|
| 7402 |
+
"step": 2112
|
| 7403 |
+
},
|
| 7404 |
+
{
|
| 7405 |
+
"epoch": 0.7371375769304531,
|
| 7406 |
+
"grad_norm": 0.17825016379356384,
|
| 7407 |
+
"learning_rate": 5e-05,
|
| 7408 |
+
"loss": 1.9487360715866089,
|
| 7409 |
+
"step": 2114
|
| 7410 |
+
},
|
| 7411 |
+
{
|
| 7412 |
+
"epoch": 0.7378349634743797,
|
| 7413 |
+
"grad_norm": 0.18024425208568573,
|
| 7414 |
+
"learning_rate": 5e-05,
|
| 7415 |
+
"loss": 2.1237568855285645,
|
| 7416 |
+
"step": 2116
|
| 7417 |
+
},
|
| 7418 |
+
{
|
| 7419 |
+
"epoch": 0.7385323500183064,
|
| 7420 |
+
"grad_norm": 0.22989214956760406,
|
| 7421 |
+
"learning_rate": 5e-05,
|
| 7422 |
+
"loss": 1.931516408920288,
|
| 7423 |
+
"step": 2118
|
| 7424 |
+
},
|
| 7425 |
+
{
|
| 7426 |
+
"epoch": 0.739229736562233,
|
| 7427 |
+
"grad_norm": 0.20000092685222626,
|
| 7428 |
+
"learning_rate": 5e-05,
|
| 7429 |
+
"loss": 2.03963041305542,
|
| 7430 |
+
"step": 2120
|
| 7431 |
+
},
|
| 7432 |
+
{
|
| 7433 |
+
"epoch": 0.7399271231061597,
|
| 7434 |
+
"grad_norm": 0.24111893773078918,
|
| 7435 |
+
"learning_rate": 5e-05,
|
| 7436 |
+
"loss": 2.027360439300537,
|
| 7437 |
+
"step": 2122
|
| 7438 |
+
},
|
| 7439 |
+
{
|
| 7440 |
+
"epoch": 0.7406245096500863,
|
| 7441 |
+
"grad_norm": 0.20106832683086395,
|
| 7442 |
+
"learning_rate": 5e-05,
|
| 7443 |
+
"loss": 1.915521502494812,
|
| 7444 |
+
"step": 2124
|
| 7445 |
+
},
|
| 7446 |
+
{
|
| 7447 |
+
"epoch": 0.7413218961940129,
|
| 7448 |
+
"grad_norm": 0.2090524286031723,
|
| 7449 |
+
"learning_rate": 5e-05,
|
| 7450 |
+
"loss": 1.9295654296875,
|
| 7451 |
+
"step": 2126
|
| 7452 |
+
},
|
| 7453 |
+
{
|
| 7454 |
+
"epoch": 0.7420192827379396,
|
| 7455 |
+
"grad_norm": 0.176246777176857,
|
| 7456 |
+
"learning_rate": 5e-05,
|
| 7457 |
+
"loss": 1.9641776084899902,
|
| 7458 |
+
"step": 2128
|
| 7459 |
+
},
|
| 7460 |
+
{
|
| 7461 |
+
"epoch": 0.7427166692818662,
|
| 7462 |
+
"grad_norm": 0.24356651306152344,
|
| 7463 |
+
"learning_rate": 5e-05,
|
| 7464 |
+
"loss": 1.9602073431015015,
|
| 7465 |
+
"step": 2130
|
| 7466 |
+
},
|
| 7467 |
+
{
|
| 7468 |
+
"epoch": 0.7434140558257929,
|
| 7469 |
+
"grad_norm": 0.18876545131206512,
|
| 7470 |
+
"learning_rate": 5e-05,
|
| 7471 |
+
"loss": 2.029855489730835,
|
| 7472 |
+
"step": 2132
|
| 7473 |
+
},
|
| 7474 |
+
{
|
| 7475 |
+
"epoch": 0.7441114423697195,
|
| 7476 |
+
"grad_norm": 0.21620714664459229,
|
| 7477 |
+
"learning_rate": 5e-05,
|
| 7478 |
+
"loss": 2.163750648498535,
|
| 7479 |
+
"step": 2134
|
| 7480 |
+
},
|
| 7481 |
+
{
|
| 7482 |
+
"epoch": 0.7448088289136461,
|
| 7483 |
+
"grad_norm": 0.21363040804862976,
|
| 7484 |
+
"learning_rate": 5e-05,
|
| 7485 |
+
"loss": 1.8749510049819946,
|
| 7486 |
+
"step": 2136
|
| 7487 |
+
},
|
| 7488 |
+
{
|
| 7489 |
+
"epoch": 0.7455062154575728,
|
| 7490 |
+
"grad_norm": 0.2743799090385437,
|
| 7491 |
+
"learning_rate": 5e-05,
|
| 7492 |
+
"loss": 2.015801191329956,
|
| 7493 |
+
"step": 2138
|
| 7494 |
+
},
|
| 7495 |
+
{
|
| 7496 |
+
"epoch": 0.7462036020014994,
|
| 7497 |
+
"grad_norm": 0.259393572807312,
|
| 7498 |
+
"learning_rate": 5e-05,
|
| 7499 |
+
"loss": 1.896141767501831,
|
| 7500 |
+
"step": 2140
|
| 7501 |
+
},
|
| 7502 |
+
{
|
| 7503 |
+
"epoch": 0.746900988545426,
|
| 7504 |
+
"grad_norm": 0.19506627321243286,
|
| 7505 |
+
"learning_rate": 5e-05,
|
| 7506 |
+
"loss": 1.6852531433105469,
|
| 7507 |
+
"step": 2142
|
| 7508 |
+
},
|
| 7509 |
+
{
|
| 7510 |
+
"epoch": 0.7475983750893527,
|
| 7511 |
+
"grad_norm": 0.2716883420944214,
|
| 7512 |
+
"learning_rate": 5e-05,
|
| 7513 |
+
"loss": 1.9007842540740967,
|
| 7514 |
+
"step": 2144
|
| 7515 |
+
},
|
| 7516 |
+
{
|
| 7517 |
+
"epoch": 0.7482957616332793,
|
| 7518 |
+
"grad_norm": 0.23826134204864502,
|
| 7519 |
+
"learning_rate": 5e-05,
|
| 7520 |
+
"loss": 2.0209457874298096,
|
| 7521 |
+
"step": 2146
|
| 7522 |
+
},
|
| 7523 |
+
{
|
| 7524 |
+
"epoch": 0.748993148177206,
|
| 7525 |
+
"grad_norm": 0.16911599040031433,
|
| 7526 |
+
"learning_rate": 5e-05,
|
| 7527 |
+
"loss": 1.9810214042663574,
|
| 7528 |
+
"step": 2148
|
| 7529 |
+
},
|
| 7530 |
+
{
|
| 7531 |
+
"epoch": 0.7496905347211326,
|
| 7532 |
+
"grad_norm": 0.21925072371959686,
|
| 7533 |
+
"learning_rate": 5e-05,
|
| 7534 |
+
"loss": 2.1360256671905518,
|
| 7535 |
+
"step": 2150
|
| 7536 |
+
},
|
| 7537 |
+
{
|
| 7538 |
+
"epoch": 0.7503879212650592,
|
| 7539 |
+
"grad_norm": 0.1755322813987732,
|
| 7540 |
+
"learning_rate": 5e-05,
|
| 7541 |
+
"loss": 2.0105040073394775,
|
| 7542 |
+
"step": 2152
|
| 7543 |
+
},
|
| 7544 |
+
{
|
| 7545 |
+
"epoch": 0.7510853078089859,
|
| 7546 |
+
"grad_norm": 0.2572018504142761,
|
| 7547 |
+
"learning_rate": 5e-05,
|
| 7548 |
+
"loss": 1.8643507957458496,
|
| 7549 |
+
"step": 2154
|
| 7550 |
+
},
|
| 7551 |
+
{
|
| 7552 |
+
"epoch": 0.7517826943529125,
|
| 7553 |
+
"grad_norm": 0.23412656784057617,
|
| 7554 |
+
"learning_rate": 5e-05,
|
| 7555 |
+
"loss": 2.103471040725708,
|
| 7556 |
+
"step": 2156
|
| 7557 |
+
},
|
| 7558 |
+
{
|
| 7559 |
+
"epoch": 0.752480080896839,
|
| 7560 |
+
"grad_norm": 0.22634395956993103,
|
| 7561 |
+
"learning_rate": 5e-05,
|
| 7562 |
+
"loss": 2.0817770957946777,
|
| 7563 |
+
"step": 2158
|
| 7564 |
+
},
|
| 7565 |
+
{
|
| 7566 |
+
"epoch": 0.7531774674407657,
|
| 7567 |
+
"grad_norm": 0.18061764538288116,
|
| 7568 |
+
"learning_rate": 5e-05,
|
| 7569 |
+
"loss": 1.993519902229309,
|
| 7570 |
+
"step": 2160
|
| 7571 |
+
},
|
| 7572 |
+
{
|
| 7573 |
+
"epoch": 0.7538748539846923,
|
| 7574 |
+
"grad_norm": 0.2553674280643463,
|
| 7575 |
+
"learning_rate": 5e-05,
|
| 7576 |
+
"loss": 2.0109446048736572,
|
| 7577 |
+
"step": 2162
|
| 7578 |
+
},
|
| 7579 |
+
{
|
| 7580 |
+
"epoch": 0.754572240528619,
|
| 7581 |
+
"grad_norm": 0.19744637608528137,
|
| 7582 |
+
"learning_rate": 5e-05,
|
| 7583 |
+
"loss": 1.9850050210952759,
|
| 7584 |
+
"step": 2164
|
| 7585 |
+
},
|
| 7586 |
+
{
|
| 7587 |
+
"epoch": 0.7552696270725456,
|
| 7588 |
+
"grad_norm": 0.17519602179527283,
|
| 7589 |
+
"learning_rate": 5e-05,
|
| 7590 |
+
"loss": 2.0965726375579834,
|
| 7591 |
+
"step": 2166
|
| 7592 |
+
},
|
| 7593 |
+
{
|
| 7594 |
+
"epoch": 0.7559670136164722,
|
| 7595 |
+
"grad_norm": 0.16751813888549805,
|
| 7596 |
+
"learning_rate": 5e-05,
|
| 7597 |
+
"loss": 1.9219980239868164,
|
| 7598 |
+
"step": 2168
|
| 7599 |
+
},
|
| 7600 |
+
{
|
| 7601 |
+
"epoch": 0.7566644001603989,
|
| 7602 |
+
"grad_norm": 0.24096159636974335,
|
| 7603 |
+
"learning_rate": 5e-05,
|
| 7604 |
+
"loss": 1.8713510036468506,
|
| 7605 |
+
"step": 2170
|
| 7606 |
+
},
|
| 7607 |
+
{
|
| 7608 |
+
"epoch": 0.7573617867043255,
|
| 7609 |
+
"grad_norm": 0.24218828976154327,
|
| 7610 |
+
"learning_rate": 5e-05,
|
| 7611 |
+
"loss": 1.9764506816864014,
|
| 7612 |
+
"step": 2172
|
| 7613 |
+
},
|
| 7614 |
+
{
|
| 7615 |
+
"epoch": 0.7580591732482522,
|
| 7616 |
+
"grad_norm": 0.1704159528017044,
|
| 7617 |
+
"learning_rate": 5e-05,
|
| 7618 |
+
"loss": 1.879757285118103,
|
| 7619 |
+
"step": 2174
|
| 7620 |
+
},
|
| 7621 |
+
{
|
| 7622 |
+
"epoch": 0.7587565597921788,
|
| 7623 |
+
"grad_norm": 0.19566938281059265,
|
| 7624 |
+
"learning_rate": 5e-05,
|
| 7625 |
+
"loss": 1.9094607830047607,
|
| 7626 |
+
"step": 2176
|
| 7627 |
+
},
|
| 7628 |
+
{
|
| 7629 |
+
"epoch": 0.7594539463361054,
|
| 7630 |
+
"grad_norm": 0.21699845790863037,
|
| 7631 |
+
"learning_rate": 5e-05,
|
| 7632 |
+
"loss": 1.8993353843688965,
|
| 7633 |
+
"step": 2178
|
| 7634 |
+
},
|
| 7635 |
+
{
|
| 7636 |
+
"epoch": 0.7601513328800321,
|
| 7637 |
+
"grad_norm": 0.25892215967178345,
|
| 7638 |
+
"learning_rate": 5e-05,
|
| 7639 |
+
"loss": 1.811294436454773,
|
| 7640 |
+
"step": 2180
|
| 7641 |
+
},
|
| 7642 |
+
{
|
| 7643 |
+
"epoch": 0.7608487194239587,
|
| 7644 |
+
"grad_norm": 0.23539891839027405,
|
| 7645 |
+
"learning_rate": 5e-05,
|
| 7646 |
+
"loss": 1.9238123893737793,
|
| 7647 |
+
"step": 2182
|
| 7648 |
+
},
|
| 7649 |
+
{
|
| 7650 |
+
"epoch": 0.7615461059678853,
|
| 7651 |
+
"grad_norm": 0.20322979986667633,
|
| 7652 |
+
"learning_rate": 5e-05,
|
| 7653 |
+
"loss": 1.942223072052002,
|
| 7654 |
+
"step": 2184
|
| 7655 |
+
},
|
| 7656 |
+
{
|
| 7657 |
+
"epoch": 0.762243492511812,
|
| 7658 |
+
"grad_norm": 0.1692976951599121,
|
| 7659 |
+
"learning_rate": 5e-05,
|
| 7660 |
+
"loss": 1.976067066192627,
|
| 7661 |
+
"step": 2186
|
| 7662 |
+
},
|
| 7663 |
+
{
|
| 7664 |
+
"epoch": 0.7629408790557386,
|
| 7665 |
+
"grad_norm": 0.2596499025821686,
|
| 7666 |
+
"learning_rate": 5e-05,
|
| 7667 |
+
"loss": 1.8981826305389404,
|
| 7668 |
+
"step": 2188
|
| 7669 |
+
},
|
| 7670 |
+
{
|
| 7671 |
+
"epoch": 0.7636382655996653,
|
| 7672 |
+
"grad_norm": 0.17991489171981812,
|
| 7673 |
+
"learning_rate": 5e-05,
|
| 7674 |
+
"loss": 2.1444361209869385,
|
| 7675 |
+
"step": 2190
|
| 7676 |
+
},
|
| 7677 |
+
{
|
| 7678 |
+
"epoch": 0.7643356521435919,
|
| 7679 |
+
"grad_norm": 0.19914187490940094,
|
| 7680 |
+
"learning_rate": 5e-05,
|
| 7681 |
+
"loss": 2.042095422744751,
|
| 7682 |
+
"step": 2192
|
| 7683 |
+
},
|
| 7684 |
+
{
|
| 7685 |
+
"epoch": 0.7650330386875185,
|
| 7686 |
+
"grad_norm": 0.2698531448841095,
|
| 7687 |
+
"learning_rate": 5e-05,
|
| 7688 |
+
"loss": 1.787888765335083,
|
| 7689 |
+
"step": 2194
|
| 7690 |
+
},
|
| 7691 |
+
{
|
| 7692 |
+
"epoch": 0.7657304252314452,
|
| 7693 |
+
"grad_norm": 0.2817508578300476,
|
| 7694 |
+
"learning_rate": 5e-05,
|
| 7695 |
+
"loss": 2.0970849990844727,
|
| 7696 |
+
"step": 2196
|
| 7697 |
+
},
|
| 7698 |
+
{
|
| 7699 |
+
"epoch": 0.7664278117753718,
|
| 7700 |
+
"grad_norm": 0.23461763560771942,
|
| 7701 |
+
"learning_rate": 5e-05,
|
| 7702 |
+
"loss": 1.9004498720169067,
|
| 7703 |
+
"step": 2198
|
| 7704 |
+
},
|
| 7705 |
+
{
|
| 7706 |
+
"epoch": 0.7671251983192984,
|
| 7707 |
+
"grad_norm": 0.2059352993965149,
|
| 7708 |
+
"learning_rate": 5e-05,
|
| 7709 |
+
"loss": 1.7717727422714233,
|
| 7710 |
+
"step": 2200
|
| 7711 |
+
},
|
| 7712 |
+
{
|
| 7713 |
+
"epoch": 0.7678225848632251,
|
| 7714 |
+
"grad_norm": 0.2654406726360321,
|
| 7715 |
+
"learning_rate": 5e-05,
|
| 7716 |
+
"loss": 1.8539447784423828,
|
| 7717 |
+
"step": 2202
|
| 7718 |
+
},
|
| 7719 |
+
{
|
| 7720 |
+
"epoch": 0.7685199714071517,
|
| 7721 |
+
"grad_norm": 0.18033595383167267,
|
| 7722 |
+
"learning_rate": 5e-05,
|
| 7723 |
+
"loss": 1.951402187347412,
|
| 7724 |
+
"step": 2204
|
| 7725 |
+
},
|
| 7726 |
+
{
|
| 7727 |
+
"epoch": 0.7692173579510784,
|
| 7728 |
+
"grad_norm": 0.2133253514766693,
|
| 7729 |
+
"learning_rate": 5e-05,
|
| 7730 |
+
"loss": 1.9016897678375244,
|
| 7731 |
+
"step": 2206
|
| 7732 |
+
},
|
| 7733 |
+
{
|
| 7734 |
+
"epoch": 0.769914744495005,
|
| 7735 |
+
"grad_norm": 0.33630532026290894,
|
| 7736 |
+
"learning_rate": 5e-05,
|
| 7737 |
+
"loss": 1.8270273208618164,
|
| 7738 |
+
"step": 2208
|
| 7739 |
+
},
|
| 7740 |
+
{
|
| 7741 |
+
"epoch": 0.7706121310389316,
|
| 7742 |
+
"grad_norm": 0.2575637698173523,
|
| 7743 |
+
"learning_rate": 5e-05,
|
| 7744 |
+
"loss": 1.9425978660583496,
|
| 7745 |
+
"step": 2210
|
| 7746 |
+
},
|
| 7747 |
+
{
|
| 7748 |
+
"epoch": 0.7713095175828583,
|
| 7749 |
+
"grad_norm": 0.20577408373355865,
|
| 7750 |
+
"learning_rate": 5e-05,
|
| 7751 |
+
"loss": 1.9617164134979248,
|
| 7752 |
+
"step": 2212
|
| 7753 |
+
},
|
| 7754 |
+
{
|
| 7755 |
+
"epoch": 0.7720069041267849,
|
| 7756 |
+
"grad_norm": 0.20532967150211334,
|
| 7757 |
+
"learning_rate": 5e-05,
|
| 7758 |
+
"loss": 2.038666248321533,
|
| 7759 |
+
"step": 2214
|
| 7760 |
+
},
|
| 7761 |
+
{
|
| 7762 |
+
"epoch": 0.7727042906707116,
|
| 7763 |
+
"grad_norm": 0.18110215663909912,
|
| 7764 |
+
"learning_rate": 5e-05,
|
| 7765 |
+
"loss": 1.6460938453674316,
|
| 7766 |
+
"step": 2216
|
| 7767 |
+
},
|
| 7768 |
+
{
|
| 7769 |
+
"epoch": 0.7734016772146382,
|
| 7770 |
+
"grad_norm": 0.21534425020217896,
|
| 7771 |
+
"learning_rate": 5e-05,
|
| 7772 |
+
"loss": 1.9891645908355713,
|
| 7773 |
+
"step": 2218
|
| 7774 |
+
},
|
| 7775 |
+
{
|
| 7776 |
+
"epoch": 0.7740990637585647,
|
| 7777 |
+
"grad_norm": 0.16367346048355103,
|
| 7778 |
+
"learning_rate": 5e-05,
|
| 7779 |
+
"loss": 2.038942813873291,
|
| 7780 |
+
"step": 2220
|
| 7781 |
+
},
|
| 7782 |
+
{
|
| 7783 |
+
"epoch": 0.7747964503024914,
|
| 7784 |
+
"grad_norm": 0.2003421038389206,
|
| 7785 |
+
"learning_rate": 5e-05,
|
| 7786 |
+
"loss": 1.862746238708496,
|
| 7787 |
+
"step": 2222
|
| 7788 |
+
},
|
| 7789 |
+
{
|
| 7790 |
+
"epoch": 0.775493836846418,
|
| 7791 |
+
"grad_norm": 0.20611684024333954,
|
| 7792 |
+
"learning_rate": 5e-05,
|
| 7793 |
+
"loss": 1.5451436042785645,
|
| 7794 |
+
"step": 2224
|
| 7795 |
+
},
|
| 7796 |
+
{
|
| 7797 |
+
"epoch": 0.7761912233903446,
|
| 7798 |
+
"grad_norm": 0.24627675116062164,
|
| 7799 |
+
"learning_rate": 5e-05,
|
| 7800 |
+
"loss": 1.7264751195907593,
|
| 7801 |
+
"step": 2226
|
| 7802 |
+
},
|
| 7803 |
+
{
|
| 7804 |
+
"epoch": 0.7768886099342713,
|
| 7805 |
+
"grad_norm": 0.26181432604789734,
|
| 7806 |
+
"learning_rate": 5e-05,
|
| 7807 |
+
"loss": 1.7415522336959839,
|
| 7808 |
+
"step": 2228
|
| 7809 |
+
},
|
| 7810 |
+
{
|
| 7811 |
+
"epoch": 0.7775859964781979,
|
| 7812 |
+
"grad_norm": 0.1756943166255951,
|
| 7813 |
+
"learning_rate": 5e-05,
|
| 7814 |
+
"loss": 1.9747660160064697,
|
| 7815 |
+
"step": 2230
|
| 7816 |
+
},
|
| 7817 |
+
{
|
| 7818 |
+
"epoch": 0.7782833830221246,
|
| 7819 |
+
"grad_norm": 0.21931739151477814,
|
| 7820 |
+
"learning_rate": 5e-05,
|
| 7821 |
+
"loss": 1.9190582036972046,
|
| 7822 |
+
"step": 2232
|
| 7823 |
+
},
|
| 7824 |
+
{
|
| 7825 |
+
"epoch": 0.7789807695660512,
|
| 7826 |
+
"grad_norm": 0.24526743590831757,
|
| 7827 |
+
"learning_rate": 5e-05,
|
| 7828 |
+
"loss": 1.6226704120635986,
|
| 7829 |
+
"step": 2234
|
| 7830 |
+
},
|
| 7831 |
+
{
|
| 7832 |
+
"epoch": 0.7796781561099778,
|
| 7833 |
+
"grad_norm": 0.21926890313625336,
|
| 7834 |
+
"learning_rate": 5e-05,
|
| 7835 |
+
"loss": 1.9680263996124268,
|
| 7836 |
+
"step": 2236
|
| 7837 |
+
},
|
| 7838 |
+
{
|
| 7839 |
+
"epoch": 0.7803755426539045,
|
| 7840 |
+
"grad_norm": 0.3071652948856354,
|
| 7841 |
+
"learning_rate": 5e-05,
|
| 7842 |
+
"loss": 1.639426350593567,
|
| 7843 |
+
"step": 2238
|
| 7844 |
+
},
|
| 7845 |
+
{
|
| 7846 |
+
"epoch": 0.7810729291978311,
|
| 7847 |
+
"grad_norm": 0.20577116310596466,
|
| 7848 |
+
"learning_rate": 5e-05,
|
| 7849 |
+
"loss": 1.8001503944396973,
|
| 7850 |
+
"step": 2240
|
| 7851 |
+
},
|
| 7852 |
+
{
|
| 7853 |
+
"epoch": 0.7817703157417578,
|
| 7854 |
+
"grad_norm": 0.1559043526649475,
|
| 7855 |
+
"learning_rate": 5e-05,
|
| 7856 |
+
"loss": 1.6160184144973755,
|
| 7857 |
+
"step": 2242
|
| 7858 |
+
},
|
| 7859 |
+
{
|
| 7860 |
+
"epoch": 0.7824677022856844,
|
| 7861 |
+
"grad_norm": 0.2791428565979004,
|
| 7862 |
+
"learning_rate": 5e-05,
|
| 7863 |
+
"loss": 1.816514492034912,
|
| 7864 |
+
"step": 2244
|
| 7865 |
+
},
|
| 7866 |
+
{
|
| 7867 |
+
"epoch": 0.783165088829611,
|
| 7868 |
+
"grad_norm": 0.21342822909355164,
|
| 7869 |
+
"learning_rate": 5e-05,
|
| 7870 |
+
"loss": 1.8380680084228516,
|
| 7871 |
+
"step": 2246
|
| 7872 |
+
},
|
| 7873 |
+
{
|
| 7874 |
+
"epoch": 0.7838624753735377,
|
| 7875 |
+
"grad_norm": 0.19591249525547028,
|
| 7876 |
+
"learning_rate": 5e-05,
|
| 7877 |
+
"loss": 1.8789033889770508,
|
| 7878 |
+
"step": 2248
|
| 7879 |
+
},
|
| 7880 |
+
{
|
| 7881 |
+
"epoch": 0.7845598619174643,
|
| 7882 |
+
"grad_norm": 0.23627856373786926,
|
| 7883 |
+
"learning_rate": 5e-05,
|
| 7884 |
+
"loss": 2.068758726119995,
|
| 7885 |
+
"step": 2250
|
| 7886 |
+
},
|
| 7887 |
+
{
|
| 7888 |
+
"epoch": 0.7852572484613909,
|
| 7889 |
+
"grad_norm": 0.28036272525787354,
|
| 7890 |
+
"learning_rate": 5e-05,
|
| 7891 |
+
"loss": 1.8976188898086548,
|
| 7892 |
+
"step": 2252
|
| 7893 |
+
},
|
| 7894 |
+
{
|
| 7895 |
+
"epoch": 0.7859546350053176,
|
| 7896 |
+
"grad_norm": 0.24042636156082153,
|
| 7897 |
+
"learning_rate": 5e-05,
|
| 7898 |
+
"loss": 1.973801612854004,
|
| 7899 |
+
"step": 2254
|
| 7900 |
+
},
|
| 7901 |
+
{
|
| 7902 |
+
"epoch": 0.7866520215492442,
|
| 7903 |
+
"grad_norm": 0.19923457503318787,
|
| 7904 |
+
"learning_rate": 5e-05,
|
| 7905 |
+
"loss": 1.9272568225860596,
|
| 7906 |
+
"step": 2256
|
| 7907 |
+
},
|
| 7908 |
+
{
|
| 7909 |
+
"epoch": 0.7873494080931709,
|
| 7910 |
+
"grad_norm": 0.1986333131790161,
|
| 7911 |
+
"learning_rate": 5e-05,
|
| 7912 |
+
"loss": 1.8647773265838623,
|
| 7913 |
+
"step": 2258
|
| 7914 |
+
},
|
| 7915 |
+
{
|
| 7916 |
+
"epoch": 0.7880467946370975,
|
| 7917 |
+
"grad_norm": 0.2959451675415039,
|
| 7918 |
+
"learning_rate": 5e-05,
|
| 7919 |
+
"loss": 1.822899341583252,
|
| 7920 |
+
"step": 2260
|
| 7921 |
+
},
|
| 7922 |
+
{
|
| 7923 |
+
"epoch": 0.7887441811810241,
|
| 7924 |
+
"grad_norm": 0.21408234536647797,
|
| 7925 |
+
"learning_rate": 5e-05,
|
| 7926 |
+
"loss": 2.083057403564453,
|
| 7927 |
+
"step": 2262
|
| 7928 |
+
},
|
| 7929 |
+
{
|
| 7930 |
+
"epoch": 0.7894415677249508,
|
| 7931 |
+
"grad_norm": 0.24847257137298584,
|
| 7932 |
+
"learning_rate": 5e-05,
|
| 7933 |
+
"loss": 2.041271686553955,
|
| 7934 |
+
"step": 2264
|
| 7935 |
+
},
|
| 7936 |
+
{
|
| 7937 |
+
"epoch": 0.7901389542688774,
|
| 7938 |
+
"grad_norm": 0.2285429835319519,
|
| 7939 |
+
"learning_rate": 5e-05,
|
| 7940 |
+
"loss": 1.8865199089050293,
|
| 7941 |
+
"step": 2266
|
| 7942 |
+
},
|
| 7943 |
+
{
|
| 7944 |
+
"epoch": 0.790836340812804,
|
| 7945 |
+
"grad_norm": 0.2242038995027542,
|
| 7946 |
+
"learning_rate": 5e-05,
|
| 7947 |
+
"loss": 1.7470977306365967,
|
| 7948 |
+
"step": 2268
|
| 7949 |
+
},
|
| 7950 |
+
{
|
| 7951 |
+
"epoch": 0.7915337273567307,
|
| 7952 |
+
"grad_norm": 0.23584255576133728,
|
| 7953 |
+
"learning_rate": 5e-05,
|
| 7954 |
+
"loss": 1.9168062210083008,
|
| 7955 |
+
"step": 2270
|
| 7956 |
+
},
|
| 7957 |
+
{
|
| 7958 |
+
"epoch": 0.7922311139006573,
|
| 7959 |
+
"grad_norm": 0.18825343251228333,
|
| 7960 |
+
"learning_rate": 5e-05,
|
| 7961 |
+
"loss": 1.99519944190979,
|
| 7962 |
+
"step": 2272
|
| 7963 |
+
},
|
| 7964 |
+
{
|
| 7965 |
+
"epoch": 0.792928500444584,
|
| 7966 |
+
"grad_norm": 0.31738072633743286,
|
| 7967 |
+
"learning_rate": 5e-05,
|
| 7968 |
+
"loss": 1.750924825668335,
|
| 7969 |
+
"step": 2274
|
| 7970 |
+
},
|
| 7971 |
+
{
|
| 7972 |
+
"epoch": 0.7936258869885106,
|
| 7973 |
+
"grad_norm": 0.1915413737297058,
|
| 7974 |
+
"learning_rate": 5e-05,
|
| 7975 |
+
"loss": 2.1374001502990723,
|
| 7976 |
+
"step": 2276
|
| 7977 |
+
},
|
| 7978 |
+
{
|
| 7979 |
+
"epoch": 0.7943232735324371,
|
| 7980 |
+
"grad_norm": 0.20662441849708557,
|
| 7981 |
+
"learning_rate": 5e-05,
|
| 7982 |
+
"loss": 1.8818833827972412,
|
| 7983 |
+
"step": 2278
|
| 7984 |
+
},
|
| 7985 |
+
{
|
| 7986 |
+
"epoch": 0.7950206600763638,
|
| 7987 |
+
"grad_norm": 0.2140003889799118,
|
| 7988 |
+
"learning_rate": 5e-05,
|
| 7989 |
+
"loss": 2.065359115600586,
|
| 7990 |
+
"step": 2280
|
| 7991 |
+
},
|
| 7992 |
+
{
|
| 7993 |
+
"epoch": 0.7957180466202904,
|
| 7994 |
+
"grad_norm": 0.22776512801647186,
|
| 7995 |
+
"learning_rate": 5e-05,
|
| 7996 |
+
"loss": 1.9953523874282837,
|
| 7997 |
+
"step": 2282
|
| 7998 |
+
},
|
| 7999 |
+
{
|
| 8000 |
+
"epoch": 0.7964154331642171,
|
| 8001 |
+
"grad_norm": 0.3272683918476105,
|
| 8002 |
+
"learning_rate": 5e-05,
|
| 8003 |
+
"loss": 1.8373709917068481,
|
| 8004 |
+
"step": 2284
|
| 8005 |
+
},
|
| 8006 |
+
{
|
| 8007 |
+
"epoch": 0.7971128197081437,
|
| 8008 |
+
"grad_norm": 0.278938889503479,
|
| 8009 |
+
"learning_rate": 5e-05,
|
| 8010 |
+
"loss": 1.9822043180465698,
|
| 8011 |
+
"step": 2286
|
| 8012 |
+
},
|
| 8013 |
+
{
|
| 8014 |
+
"epoch": 0.7978102062520703,
|
| 8015 |
+
"grad_norm": 0.2507492005825043,
|
| 8016 |
+
"learning_rate": 5e-05,
|
| 8017 |
+
"loss": 2.0197887420654297,
|
| 8018 |
+
"step": 2288
|
| 8019 |
+
},
|
| 8020 |
+
{
|
| 8021 |
+
"epoch": 0.798507592795997,
|
| 8022 |
+
"grad_norm": 0.29306724667549133,
|
| 8023 |
+
"learning_rate": 5e-05,
|
| 8024 |
+
"loss": 1.9630277156829834,
|
| 8025 |
+
"step": 2290
|
| 8026 |
+
},
|
| 8027 |
+
{
|
| 8028 |
+
"epoch": 0.7992049793399236,
|
| 8029 |
+
"grad_norm": 0.22105816006660461,
|
| 8030 |
+
"learning_rate": 5e-05,
|
| 8031 |
+
"loss": 2.0450775623321533,
|
| 8032 |
+
"step": 2292
|
| 8033 |
+
},
|
| 8034 |
+
{
|
| 8035 |
+
"epoch": 0.7999023658838502,
|
| 8036 |
+
"grad_norm": 0.3041655421257019,
|
| 8037 |
+
"learning_rate": 5e-05,
|
| 8038 |
+
"loss": 1.637634038925171,
|
| 8039 |
+
"step": 2294
|
| 8040 |
+
},
|
| 8041 |
+
{
|
| 8042 |
+
"epoch": 0.8005997524277769,
|
| 8043 |
+
"grad_norm": 0.2233806550502777,
|
| 8044 |
+
"learning_rate": 5e-05,
|
| 8045 |
+
"loss": 1.8702466487884521,
|
| 8046 |
+
"step": 2296
|
| 8047 |
}
|
| 8048 |
],
|
| 8049 |
"logging_steps": 2,
|
|
|
|
| 8063 |
"attributes": {}
|
| 8064 |
}
|
| 8065 |
},
|
| 8066 |
+
"total_flos": 4.109304377250939e+17,
|
| 8067 |
"train_batch_size": 1,
|
| 8068 |
"trial_name": null,
|
| 8069 |
"trial_params": null
|