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 1722, 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:f7ce566d5e6b96446e5450efe0bed2cc10375e8d75c00565f66614d12cb259f4
|
| 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:f863b3c9f2eea0b1c45dc6d63a29bf8fbb066259d435907b7e709c88370f0aad
|
| 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 sha256:43236203a4d8e4c799b39d32440e5b1c0fe4418a50daa925e767de759fddee2d
|
| 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,
|
|
@@ -4026,6 +4026,2015 @@
|
|
| 4026 |
"learning_rate": 5e-05,
|
| 4027 |
"loss": 2.1917271614074707,
|
| 4028 |
"step": 1148
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4029 |
}
|
| 4030 |
],
|
| 4031 |
"logging_steps": 2,
|
|
@@ -4045,7 +6054,7 @@
|
|
| 4045 |
"attributes": {}
|
| 4046 |
}
|
| 4047 |
},
|
| 4048 |
-
"total_flos":
|
| 4049 |
"train_batch_size": 1,
|
| 4050 |
"trial_name": null,
|
| 4051 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6004498143208327,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1722,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4026 |
"learning_rate": 5e-05,
|
| 4027 |
"loss": 2.1917271614074707,
|
| 4028 |
"step": 1148
|
| 4029 |
+
},
|
| 4030 |
+
{
|
| 4031 |
+
"epoch": 0.4009972627578151,
|
| 4032 |
+
"grad_norm": 0.2637289762496948,
|
| 4033 |
+
"learning_rate": 5e-05,
|
| 4034 |
+
"loss": 2.018184185028076,
|
| 4035 |
+
"step": 1150
|
| 4036 |
+
},
|
| 4037 |
+
{
|
| 4038 |
+
"epoch": 0.4016946493017417,
|
| 4039 |
+
"grad_norm": 0.23698849976062775,
|
| 4040 |
+
"learning_rate": 5e-05,
|
| 4041 |
+
"loss": 1.897341012954712,
|
| 4042 |
+
"step": 1152
|
| 4043 |
+
},
|
| 4044 |
+
{
|
| 4045 |
+
"epoch": 0.40239203584566835,
|
| 4046 |
+
"grad_norm": 0.2660623788833618,
|
| 4047 |
+
"learning_rate": 5e-05,
|
| 4048 |
+
"loss": 2.0587849617004395,
|
| 4049 |
+
"step": 1154
|
| 4050 |
+
},
|
| 4051 |
+
{
|
| 4052 |
+
"epoch": 0.403089422389595,
|
| 4053 |
+
"grad_norm": 0.19925248622894287,
|
| 4054 |
+
"learning_rate": 5e-05,
|
| 4055 |
+
"loss": 2.0214662551879883,
|
| 4056 |
+
"step": 1156
|
| 4057 |
+
},
|
| 4058 |
+
{
|
| 4059 |
+
"epoch": 0.40378680893352165,
|
| 4060 |
+
"grad_norm": 0.24144220352172852,
|
| 4061 |
+
"learning_rate": 5e-05,
|
| 4062 |
+
"loss": 2.018463611602783,
|
| 4063 |
+
"step": 1158
|
| 4064 |
+
},
|
| 4065 |
+
{
|
| 4066 |
+
"epoch": 0.40448419547744824,
|
| 4067 |
+
"grad_norm": 0.1997368037700653,
|
| 4068 |
+
"learning_rate": 5e-05,
|
| 4069 |
+
"loss": 2.16738224029541,
|
| 4070 |
+
"step": 1160
|
| 4071 |
+
},
|
| 4072 |
+
{
|
| 4073 |
+
"epoch": 0.4051815820213749,
|
| 4074 |
+
"grad_norm": 0.2711610794067383,
|
| 4075 |
+
"learning_rate": 5e-05,
|
| 4076 |
+
"loss": 2.0850989818573,
|
| 4077 |
+
"step": 1162
|
| 4078 |
+
},
|
| 4079 |
+
{
|
| 4080 |
+
"epoch": 0.40587896856530153,
|
| 4081 |
+
"grad_norm": 0.23238755762577057,
|
| 4082 |
+
"learning_rate": 5e-05,
|
| 4083 |
+
"loss": 1.8553071022033691,
|
| 4084 |
+
"step": 1164
|
| 4085 |
+
},
|
| 4086 |
+
{
|
| 4087 |
+
"epoch": 0.4065763551092282,
|
| 4088 |
+
"grad_norm": 0.19778624176979065,
|
| 4089 |
+
"learning_rate": 5e-05,
|
| 4090 |
+
"loss": 2.267437696456909,
|
| 4091 |
+
"step": 1166
|
| 4092 |
+
},
|
| 4093 |
+
{
|
| 4094 |
+
"epoch": 0.4072737416531548,
|
| 4095 |
+
"grad_norm": 0.18753691017627716,
|
| 4096 |
+
"learning_rate": 5e-05,
|
| 4097 |
+
"loss": 1.9425708055496216,
|
| 4098 |
+
"step": 1168
|
| 4099 |
+
},
|
| 4100 |
+
{
|
| 4101 |
+
"epoch": 0.4079711281970814,
|
| 4102 |
+
"grad_norm": 0.1919858753681183,
|
| 4103 |
+
"learning_rate": 5e-05,
|
| 4104 |
+
"loss": 2.0795068740844727,
|
| 4105 |
+
"step": 1170
|
| 4106 |
+
},
|
| 4107 |
+
{
|
| 4108 |
+
"epoch": 0.40866851474100807,
|
| 4109 |
+
"grad_norm": 0.2890529930591583,
|
| 4110 |
+
"learning_rate": 5e-05,
|
| 4111 |
+
"loss": 2.067218780517578,
|
| 4112 |
+
"step": 1172
|
| 4113 |
+
},
|
| 4114 |
+
{
|
| 4115 |
+
"epoch": 0.4093659012849347,
|
| 4116 |
+
"grad_norm": 0.28386932611465454,
|
| 4117 |
+
"learning_rate": 5e-05,
|
| 4118 |
+
"loss": 2.009732723236084,
|
| 4119 |
+
"step": 1174
|
| 4120 |
+
},
|
| 4121 |
+
{
|
| 4122 |
+
"epoch": 0.41006328782886137,
|
| 4123 |
+
"grad_norm": 0.22415214776992798,
|
| 4124 |
+
"learning_rate": 5e-05,
|
| 4125 |
+
"loss": 2.1026344299316406,
|
| 4126 |
+
"step": 1176
|
| 4127 |
+
},
|
| 4128 |
+
{
|
| 4129 |
+
"epoch": 0.41076067437278796,
|
| 4130 |
+
"grad_norm": 0.2018672227859497,
|
| 4131 |
+
"learning_rate": 5e-05,
|
| 4132 |
+
"loss": 2.120260715484619,
|
| 4133 |
+
"step": 1178
|
| 4134 |
+
},
|
| 4135 |
+
{
|
| 4136 |
+
"epoch": 0.4114580609167146,
|
| 4137 |
+
"grad_norm": 0.2746317386627197,
|
| 4138 |
+
"learning_rate": 5e-05,
|
| 4139 |
+
"loss": 1.9730490446090698,
|
| 4140 |
+
"step": 1180
|
| 4141 |
+
},
|
| 4142 |
+
{
|
| 4143 |
+
"epoch": 0.41215544746064126,
|
| 4144 |
+
"grad_norm": 0.24063794314861298,
|
| 4145 |
+
"learning_rate": 5e-05,
|
| 4146 |
+
"loss": 2.0942440032958984,
|
| 4147 |
+
"step": 1182
|
| 4148 |
+
},
|
| 4149 |
+
{
|
| 4150 |
+
"epoch": 0.4128528340045679,
|
| 4151 |
+
"grad_norm": 0.24473215639591217,
|
| 4152 |
+
"learning_rate": 5e-05,
|
| 4153 |
+
"loss": 2.0083141326904297,
|
| 4154 |
+
"step": 1184
|
| 4155 |
+
},
|
| 4156 |
+
{
|
| 4157 |
+
"epoch": 0.4135502205484945,
|
| 4158 |
+
"grad_norm": 0.27954408526420593,
|
| 4159 |
+
"learning_rate": 5e-05,
|
| 4160 |
+
"loss": 1.9019955396652222,
|
| 4161 |
+
"step": 1186
|
| 4162 |
+
},
|
| 4163 |
+
{
|
| 4164 |
+
"epoch": 0.41424760709242114,
|
| 4165 |
+
"grad_norm": 0.21032820641994476,
|
| 4166 |
+
"learning_rate": 5e-05,
|
| 4167 |
+
"loss": 2.0116095542907715,
|
| 4168 |
+
"step": 1188
|
| 4169 |
+
},
|
| 4170 |
+
{
|
| 4171 |
+
"epoch": 0.4149449936363478,
|
| 4172 |
+
"grad_norm": 0.29512640833854675,
|
| 4173 |
+
"learning_rate": 5e-05,
|
| 4174 |
+
"loss": 2.1200222969055176,
|
| 4175 |
+
"step": 1190
|
| 4176 |
+
},
|
| 4177 |
+
{
|
| 4178 |
+
"epoch": 0.41564238018027444,
|
| 4179 |
+
"grad_norm": 0.184640035033226,
|
| 4180 |
+
"learning_rate": 5e-05,
|
| 4181 |
+
"loss": 2.117198944091797,
|
| 4182 |
+
"step": 1192
|
| 4183 |
+
},
|
| 4184 |
+
{
|
| 4185 |
+
"epoch": 0.41633976672420103,
|
| 4186 |
+
"grad_norm": 0.2741994559764862,
|
| 4187 |
+
"learning_rate": 5e-05,
|
| 4188 |
+
"loss": 1.9714668989181519,
|
| 4189 |
+
"step": 1194
|
| 4190 |
+
},
|
| 4191 |
+
{
|
| 4192 |
+
"epoch": 0.4170371532681277,
|
| 4193 |
+
"grad_norm": 0.3104700446128845,
|
| 4194 |
+
"learning_rate": 5e-05,
|
| 4195 |
+
"loss": 1.955941081047058,
|
| 4196 |
+
"step": 1196
|
| 4197 |
+
},
|
| 4198 |
+
{
|
| 4199 |
+
"epoch": 0.41773453981205433,
|
| 4200 |
+
"grad_norm": 0.25845324993133545,
|
| 4201 |
+
"learning_rate": 5e-05,
|
| 4202 |
+
"loss": 2.067126512527466,
|
| 4203 |
+
"step": 1198
|
| 4204 |
+
},
|
| 4205 |
+
{
|
| 4206 |
+
"epoch": 0.418431926355981,
|
| 4207 |
+
"grad_norm": 0.16517043113708496,
|
| 4208 |
+
"learning_rate": 5e-05,
|
| 4209 |
+
"loss": 2.07180118560791,
|
| 4210 |
+
"step": 1200
|
| 4211 |
+
},
|
| 4212 |
+
{
|
| 4213 |
+
"epoch": 0.41912931289990757,
|
| 4214 |
+
"grad_norm": 0.15481635928153992,
|
| 4215 |
+
"learning_rate": 5e-05,
|
| 4216 |
+
"loss": 2.18418550491333,
|
| 4217 |
+
"step": 1202
|
| 4218 |
+
},
|
| 4219 |
+
{
|
| 4220 |
+
"epoch": 0.4198266994438342,
|
| 4221 |
+
"grad_norm": 0.2163589596748352,
|
| 4222 |
+
"learning_rate": 5e-05,
|
| 4223 |
+
"loss": 2.1593503952026367,
|
| 4224 |
+
"step": 1204
|
| 4225 |
+
},
|
| 4226 |
+
{
|
| 4227 |
+
"epoch": 0.42052408598776087,
|
| 4228 |
+
"grad_norm": 0.2110627144575119,
|
| 4229 |
+
"learning_rate": 5e-05,
|
| 4230 |
+
"loss": 1.9078938961029053,
|
| 4231 |
+
"step": 1206
|
| 4232 |
+
},
|
| 4233 |
+
{
|
| 4234 |
+
"epoch": 0.4212214725316875,
|
| 4235 |
+
"grad_norm": 0.2240639328956604,
|
| 4236 |
+
"learning_rate": 5e-05,
|
| 4237 |
+
"loss": 1.9624361991882324,
|
| 4238 |
+
"step": 1208
|
| 4239 |
+
},
|
| 4240 |
+
{
|
| 4241 |
+
"epoch": 0.42191885907561416,
|
| 4242 |
+
"grad_norm": 0.18361057341098785,
|
| 4243 |
+
"learning_rate": 5e-05,
|
| 4244 |
+
"loss": 2.1403841972351074,
|
| 4245 |
+
"step": 1210
|
| 4246 |
+
},
|
| 4247 |
+
{
|
| 4248 |
+
"epoch": 0.42261624561954075,
|
| 4249 |
+
"grad_norm": 0.29115167260169983,
|
| 4250 |
+
"learning_rate": 5e-05,
|
| 4251 |
+
"loss": 2.0681142807006836,
|
| 4252 |
+
"step": 1212
|
| 4253 |
+
},
|
| 4254 |
+
{
|
| 4255 |
+
"epoch": 0.4233136321634674,
|
| 4256 |
+
"grad_norm": 0.3003404140472412,
|
| 4257 |
+
"learning_rate": 5e-05,
|
| 4258 |
+
"loss": 2.1037189960479736,
|
| 4259 |
+
"step": 1214
|
| 4260 |
+
},
|
| 4261 |
+
{
|
| 4262 |
+
"epoch": 0.42401101870739405,
|
| 4263 |
+
"grad_norm": 0.2676253020763397,
|
| 4264 |
+
"learning_rate": 5e-05,
|
| 4265 |
+
"loss": 2.052903175354004,
|
| 4266 |
+
"step": 1216
|
| 4267 |
+
},
|
| 4268 |
+
{
|
| 4269 |
+
"epoch": 0.4247084052513207,
|
| 4270 |
+
"grad_norm": 0.19431860744953156,
|
| 4271 |
+
"learning_rate": 5e-05,
|
| 4272 |
+
"loss": 1.8593212366104126,
|
| 4273 |
+
"step": 1218
|
| 4274 |
+
},
|
| 4275 |
+
{
|
| 4276 |
+
"epoch": 0.4254057917952473,
|
| 4277 |
+
"grad_norm": 0.2959866523742676,
|
| 4278 |
+
"learning_rate": 5e-05,
|
| 4279 |
+
"loss": 2.089138984680176,
|
| 4280 |
+
"step": 1220
|
| 4281 |
+
},
|
| 4282 |
+
{
|
| 4283 |
+
"epoch": 0.42610317833917394,
|
| 4284 |
+
"grad_norm": 0.21319754421710968,
|
| 4285 |
+
"learning_rate": 5e-05,
|
| 4286 |
+
"loss": 2.118983268737793,
|
| 4287 |
+
"step": 1222
|
| 4288 |
+
},
|
| 4289 |
+
{
|
| 4290 |
+
"epoch": 0.4268005648831006,
|
| 4291 |
+
"grad_norm": 0.2284935712814331,
|
| 4292 |
+
"learning_rate": 5e-05,
|
| 4293 |
+
"loss": 2.0338568687438965,
|
| 4294 |
+
"step": 1224
|
| 4295 |
+
},
|
| 4296 |
+
{
|
| 4297 |
+
"epoch": 0.42749795142702723,
|
| 4298 |
+
"grad_norm": 0.20905207097530365,
|
| 4299 |
+
"learning_rate": 5e-05,
|
| 4300 |
+
"loss": 2.126631498336792,
|
| 4301 |
+
"step": 1226
|
| 4302 |
+
},
|
| 4303 |
+
{
|
| 4304 |
+
"epoch": 0.4281953379709538,
|
| 4305 |
+
"grad_norm": 0.21172241866588593,
|
| 4306 |
+
"learning_rate": 5e-05,
|
| 4307 |
+
"loss": 2.0528483390808105,
|
| 4308 |
+
"step": 1228
|
| 4309 |
+
},
|
| 4310 |
+
{
|
| 4311 |
+
"epoch": 0.4288927245148805,
|
| 4312 |
+
"grad_norm": 0.2142503708600998,
|
| 4313 |
+
"learning_rate": 5e-05,
|
| 4314 |
+
"loss": 2.0093178749084473,
|
| 4315 |
+
"step": 1230
|
| 4316 |
+
},
|
| 4317 |
+
{
|
| 4318 |
+
"epoch": 0.4295901110588071,
|
| 4319 |
+
"grad_norm": 0.2018240988254547,
|
| 4320 |
+
"learning_rate": 5e-05,
|
| 4321 |
+
"loss": 2.0821194648742676,
|
| 4322 |
+
"step": 1232
|
| 4323 |
+
},
|
| 4324 |
+
{
|
| 4325 |
+
"epoch": 0.43028749760273377,
|
| 4326 |
+
"grad_norm": 0.26273906230926514,
|
| 4327 |
+
"learning_rate": 5e-05,
|
| 4328 |
+
"loss": 2.0322070121765137,
|
| 4329 |
+
"step": 1234
|
| 4330 |
+
},
|
| 4331 |
+
{
|
| 4332 |
+
"epoch": 0.43098488414666036,
|
| 4333 |
+
"grad_norm": 0.2783421277999878,
|
| 4334 |
+
"learning_rate": 5e-05,
|
| 4335 |
+
"loss": 2.0080924034118652,
|
| 4336 |
+
"step": 1236
|
| 4337 |
+
},
|
| 4338 |
+
{
|
| 4339 |
+
"epoch": 0.431682270690587,
|
| 4340 |
+
"grad_norm": 0.1750483363866806,
|
| 4341 |
+
"learning_rate": 5e-05,
|
| 4342 |
+
"loss": 2.006192684173584,
|
| 4343 |
+
"step": 1238
|
| 4344 |
+
},
|
| 4345 |
+
{
|
| 4346 |
+
"epoch": 0.43237965723451366,
|
| 4347 |
+
"grad_norm": 0.2582997679710388,
|
| 4348 |
+
"learning_rate": 5e-05,
|
| 4349 |
+
"loss": 1.858557105064392,
|
| 4350 |
+
"step": 1240
|
| 4351 |
+
},
|
| 4352 |
+
{
|
| 4353 |
+
"epoch": 0.4330770437784403,
|
| 4354 |
+
"grad_norm": 0.17965590953826904,
|
| 4355 |
+
"learning_rate": 5e-05,
|
| 4356 |
+
"loss": 2.3109617233276367,
|
| 4357 |
+
"step": 1242
|
| 4358 |
+
},
|
| 4359 |
+
{
|
| 4360 |
+
"epoch": 0.43377443032236696,
|
| 4361 |
+
"grad_norm": 0.21540866792201996,
|
| 4362 |
+
"learning_rate": 5e-05,
|
| 4363 |
+
"loss": 2.129401683807373,
|
| 4364 |
+
"step": 1244
|
| 4365 |
+
},
|
| 4366 |
+
{
|
| 4367 |
+
"epoch": 0.43447181686629355,
|
| 4368 |
+
"grad_norm": 0.21578910946846008,
|
| 4369 |
+
"learning_rate": 5e-05,
|
| 4370 |
+
"loss": 2.101186752319336,
|
| 4371 |
+
"step": 1246
|
| 4372 |
+
},
|
| 4373 |
+
{
|
| 4374 |
+
"epoch": 0.4351692034102202,
|
| 4375 |
+
"grad_norm": 0.3152891993522644,
|
| 4376 |
+
"learning_rate": 5e-05,
|
| 4377 |
+
"loss": 1.7350882291793823,
|
| 4378 |
+
"step": 1248
|
| 4379 |
+
},
|
| 4380 |
+
{
|
| 4381 |
+
"epoch": 0.43586658995414684,
|
| 4382 |
+
"grad_norm": 0.1738380789756775,
|
| 4383 |
+
"learning_rate": 5e-05,
|
| 4384 |
+
"loss": 1.8759608268737793,
|
| 4385 |
+
"step": 1250
|
| 4386 |
+
},
|
| 4387 |
+
{
|
| 4388 |
+
"epoch": 0.4365639764980735,
|
| 4389 |
+
"grad_norm": 0.1779043972492218,
|
| 4390 |
+
"learning_rate": 5e-05,
|
| 4391 |
+
"loss": 1.8695545196533203,
|
| 4392 |
+
"step": 1252
|
| 4393 |
+
},
|
| 4394 |
+
{
|
| 4395 |
+
"epoch": 0.4372613630420001,
|
| 4396 |
+
"grad_norm": 0.22195081412792206,
|
| 4397 |
+
"learning_rate": 5e-05,
|
| 4398 |
+
"loss": 1.7950637340545654,
|
| 4399 |
+
"step": 1254
|
| 4400 |
+
},
|
| 4401 |
+
{
|
| 4402 |
+
"epoch": 0.43795874958592673,
|
| 4403 |
+
"grad_norm": 0.19365878403186798,
|
| 4404 |
+
"learning_rate": 5e-05,
|
| 4405 |
+
"loss": 2.0437979698181152,
|
| 4406 |
+
"step": 1256
|
| 4407 |
+
},
|
| 4408 |
+
{
|
| 4409 |
+
"epoch": 0.4386561361298534,
|
| 4410 |
+
"grad_norm": 0.15562410652637482,
|
| 4411 |
+
"learning_rate": 5e-05,
|
| 4412 |
+
"loss": 1.8667664527893066,
|
| 4413 |
+
"step": 1258
|
| 4414 |
+
},
|
| 4415 |
+
{
|
| 4416 |
+
"epoch": 0.43935352267378003,
|
| 4417 |
+
"grad_norm": 0.2590292692184448,
|
| 4418 |
+
"learning_rate": 5e-05,
|
| 4419 |
+
"loss": 1.9112123250961304,
|
| 4420 |
+
"step": 1260
|
| 4421 |
+
},
|
| 4422 |
+
{
|
| 4423 |
+
"epoch": 0.4400509092177066,
|
| 4424 |
+
"grad_norm": 0.25530561804771423,
|
| 4425 |
+
"learning_rate": 5e-05,
|
| 4426 |
+
"loss": 1.7089579105377197,
|
| 4427 |
+
"step": 1262
|
| 4428 |
+
},
|
| 4429 |
+
{
|
| 4430 |
+
"epoch": 0.44074829576163327,
|
| 4431 |
+
"grad_norm": 0.18177051842212677,
|
| 4432 |
+
"learning_rate": 5e-05,
|
| 4433 |
+
"loss": 2.036484956741333,
|
| 4434 |
+
"step": 1264
|
| 4435 |
+
},
|
| 4436 |
+
{
|
| 4437 |
+
"epoch": 0.4414456823055599,
|
| 4438 |
+
"grad_norm": 0.23425745964050293,
|
| 4439 |
+
"learning_rate": 5e-05,
|
| 4440 |
+
"loss": 2.0025293827056885,
|
| 4441 |
+
"step": 1266
|
| 4442 |
+
},
|
| 4443 |
+
{
|
| 4444 |
+
"epoch": 0.44214306884948656,
|
| 4445 |
+
"grad_norm": 0.18502822518348694,
|
| 4446 |
+
"learning_rate": 5e-05,
|
| 4447 |
+
"loss": 1.8278251886367798,
|
| 4448 |
+
"step": 1268
|
| 4449 |
+
},
|
| 4450 |
+
{
|
| 4451 |
+
"epoch": 0.44284045539341316,
|
| 4452 |
+
"grad_norm": 0.3032926917076111,
|
| 4453 |
+
"learning_rate": 5e-05,
|
| 4454 |
+
"loss": 1.9995391368865967,
|
| 4455 |
+
"step": 1270
|
| 4456 |
+
},
|
| 4457 |
+
{
|
| 4458 |
+
"epoch": 0.4435378419373398,
|
| 4459 |
+
"grad_norm": 0.19650033116340637,
|
| 4460 |
+
"learning_rate": 5e-05,
|
| 4461 |
+
"loss": 2.086463451385498,
|
| 4462 |
+
"step": 1272
|
| 4463 |
+
},
|
| 4464 |
+
{
|
| 4465 |
+
"epoch": 0.44423522848126645,
|
| 4466 |
+
"grad_norm": 0.313363641500473,
|
| 4467 |
+
"learning_rate": 5e-05,
|
| 4468 |
+
"loss": 1.9883931875228882,
|
| 4469 |
+
"step": 1274
|
| 4470 |
+
},
|
| 4471 |
+
{
|
| 4472 |
+
"epoch": 0.4449326150251931,
|
| 4473 |
+
"grad_norm": 0.26909589767456055,
|
| 4474 |
+
"learning_rate": 5e-05,
|
| 4475 |
+
"loss": 2.0722873210906982,
|
| 4476 |
+
"step": 1276
|
| 4477 |
+
},
|
| 4478 |
+
{
|
| 4479 |
+
"epoch": 0.44563000156911975,
|
| 4480 |
+
"grad_norm": 0.17645885050296783,
|
| 4481 |
+
"learning_rate": 5e-05,
|
| 4482 |
+
"loss": 2.0468873977661133,
|
| 4483 |
+
"step": 1278
|
| 4484 |
+
},
|
| 4485 |
+
{
|
| 4486 |
+
"epoch": 0.44632738811304634,
|
| 4487 |
+
"grad_norm": 0.21794313192367554,
|
| 4488 |
+
"learning_rate": 5e-05,
|
| 4489 |
+
"loss": 1.936154842376709,
|
| 4490 |
+
"step": 1280
|
| 4491 |
+
},
|
| 4492 |
+
{
|
| 4493 |
+
"epoch": 0.447024774656973,
|
| 4494 |
+
"grad_norm": 0.21685075759887695,
|
| 4495 |
+
"learning_rate": 5e-05,
|
| 4496 |
+
"loss": 2.084484577178955,
|
| 4497 |
+
"step": 1282
|
| 4498 |
+
},
|
| 4499 |
+
{
|
| 4500 |
+
"epoch": 0.44772216120089964,
|
| 4501 |
+
"grad_norm": 0.2649660110473633,
|
| 4502 |
+
"learning_rate": 5e-05,
|
| 4503 |
+
"loss": 2.0763959884643555,
|
| 4504 |
+
"step": 1284
|
| 4505 |
+
},
|
| 4506 |
+
{
|
| 4507 |
+
"epoch": 0.4484195477448263,
|
| 4508 |
+
"grad_norm": 0.2876056134700775,
|
| 4509 |
+
"learning_rate": 5e-05,
|
| 4510 |
+
"loss": 2.029877185821533,
|
| 4511 |
+
"step": 1286
|
| 4512 |
+
},
|
| 4513 |
+
{
|
| 4514 |
+
"epoch": 0.4491169342887529,
|
| 4515 |
+
"grad_norm": 0.2842501103878021,
|
| 4516 |
+
"learning_rate": 5e-05,
|
| 4517 |
+
"loss": 1.8488447666168213,
|
| 4518 |
+
"step": 1288
|
| 4519 |
+
},
|
| 4520 |
+
{
|
| 4521 |
+
"epoch": 0.4498143208326795,
|
| 4522 |
+
"grad_norm": 0.31609490513801575,
|
| 4523 |
+
"learning_rate": 5e-05,
|
| 4524 |
+
"loss": 1.6472361087799072,
|
| 4525 |
+
"step": 1290
|
| 4526 |
+
},
|
| 4527 |
+
{
|
| 4528 |
+
"epoch": 0.4505117073766062,
|
| 4529 |
+
"grad_norm": 0.18136271834373474,
|
| 4530 |
+
"learning_rate": 5e-05,
|
| 4531 |
+
"loss": 1.9367755651474,
|
| 4532 |
+
"step": 1292
|
| 4533 |
+
},
|
| 4534 |
+
{
|
| 4535 |
+
"epoch": 0.4512090939205328,
|
| 4536 |
+
"grad_norm": 0.18368104100227356,
|
| 4537 |
+
"learning_rate": 5e-05,
|
| 4538 |
+
"loss": 2.182744026184082,
|
| 4539 |
+
"step": 1294
|
| 4540 |
+
},
|
| 4541 |
+
{
|
| 4542 |
+
"epoch": 0.4519064804644594,
|
| 4543 |
+
"grad_norm": 0.2922597825527191,
|
| 4544 |
+
"learning_rate": 5e-05,
|
| 4545 |
+
"loss": 2.1172962188720703,
|
| 4546 |
+
"step": 1296
|
| 4547 |
+
},
|
| 4548 |
+
{
|
| 4549 |
+
"epoch": 0.45260386700838606,
|
| 4550 |
+
"grad_norm": 0.18549898266792297,
|
| 4551 |
+
"learning_rate": 5e-05,
|
| 4552 |
+
"loss": 1.8879756927490234,
|
| 4553 |
+
"step": 1298
|
| 4554 |
+
},
|
| 4555 |
+
{
|
| 4556 |
+
"epoch": 0.4533012535523127,
|
| 4557 |
+
"grad_norm": 0.2708760201931,
|
| 4558 |
+
"learning_rate": 5e-05,
|
| 4559 |
+
"loss": 1.9968003034591675,
|
| 4560 |
+
"step": 1300
|
| 4561 |
+
},
|
| 4562 |
+
{
|
| 4563 |
+
"epoch": 0.45399864009623936,
|
| 4564 |
+
"grad_norm": 0.18067607283592224,
|
| 4565 |
+
"learning_rate": 5e-05,
|
| 4566 |
+
"loss": 1.9076361656188965,
|
| 4567 |
+
"step": 1302
|
| 4568 |
+
},
|
| 4569 |
+
{
|
| 4570 |
+
"epoch": 0.45469602664016595,
|
| 4571 |
+
"grad_norm": 0.17177116870880127,
|
| 4572 |
+
"learning_rate": 5e-05,
|
| 4573 |
+
"loss": 2.058980941772461,
|
| 4574 |
+
"step": 1304
|
| 4575 |
+
},
|
| 4576 |
+
{
|
| 4577 |
+
"epoch": 0.4553934131840926,
|
| 4578 |
+
"grad_norm": 0.21306143701076508,
|
| 4579 |
+
"learning_rate": 5e-05,
|
| 4580 |
+
"loss": 2.1413674354553223,
|
| 4581 |
+
"step": 1306
|
| 4582 |
+
},
|
| 4583 |
+
{
|
| 4584 |
+
"epoch": 0.45609079972801925,
|
| 4585 |
+
"grad_norm": 0.2684168815612793,
|
| 4586 |
+
"learning_rate": 5e-05,
|
| 4587 |
+
"loss": 1.8674421310424805,
|
| 4588 |
+
"step": 1308
|
| 4589 |
+
},
|
| 4590 |
+
{
|
| 4591 |
+
"epoch": 0.4567881862719459,
|
| 4592 |
+
"grad_norm": 0.1928548961877823,
|
| 4593 |
+
"learning_rate": 5e-05,
|
| 4594 |
+
"loss": 2.109370231628418,
|
| 4595 |
+
"step": 1310
|
| 4596 |
+
},
|
| 4597 |
+
{
|
| 4598 |
+
"epoch": 0.45748557281587254,
|
| 4599 |
+
"grad_norm": 0.22075115144252777,
|
| 4600 |
+
"learning_rate": 5e-05,
|
| 4601 |
+
"loss": 2.0332212448120117,
|
| 4602 |
+
"step": 1312
|
| 4603 |
+
},
|
| 4604 |
+
{
|
| 4605 |
+
"epoch": 0.45818295935979914,
|
| 4606 |
+
"grad_norm": 0.22620245814323425,
|
| 4607 |
+
"learning_rate": 5e-05,
|
| 4608 |
+
"loss": 1.9118460416793823,
|
| 4609 |
+
"step": 1314
|
| 4610 |
+
},
|
| 4611 |
+
{
|
| 4612 |
+
"epoch": 0.4588803459037258,
|
| 4613 |
+
"grad_norm": 0.17279599606990814,
|
| 4614 |
+
"learning_rate": 5e-05,
|
| 4615 |
+
"loss": 1.975062370300293,
|
| 4616 |
+
"step": 1316
|
| 4617 |
+
},
|
| 4618 |
+
{
|
| 4619 |
+
"epoch": 0.45957773244765243,
|
| 4620 |
+
"grad_norm": 0.22477290034294128,
|
| 4621 |
+
"learning_rate": 5e-05,
|
| 4622 |
+
"loss": 2.146522045135498,
|
| 4623 |
+
"step": 1318
|
| 4624 |
+
},
|
| 4625 |
+
{
|
| 4626 |
+
"epoch": 0.4602751189915791,
|
| 4627 |
+
"grad_norm": 0.30667194724082947,
|
| 4628 |
+
"learning_rate": 5e-05,
|
| 4629 |
+
"loss": 1.933511734008789,
|
| 4630 |
+
"step": 1320
|
| 4631 |
+
},
|
| 4632 |
+
{
|
| 4633 |
+
"epoch": 0.46097250553550567,
|
| 4634 |
+
"grad_norm": 0.21251042187213898,
|
| 4635 |
+
"learning_rate": 5e-05,
|
| 4636 |
+
"loss": 2.0979998111724854,
|
| 4637 |
+
"step": 1322
|
| 4638 |
+
},
|
| 4639 |
+
{
|
| 4640 |
+
"epoch": 0.4616698920794323,
|
| 4641 |
+
"grad_norm": 0.21532893180847168,
|
| 4642 |
+
"learning_rate": 5e-05,
|
| 4643 |
+
"loss": 1.8038239479064941,
|
| 4644 |
+
"step": 1324
|
| 4645 |
+
},
|
| 4646 |
+
{
|
| 4647 |
+
"epoch": 0.46236727862335897,
|
| 4648 |
+
"grad_norm": 0.2114000916481018,
|
| 4649 |
+
"learning_rate": 5e-05,
|
| 4650 |
+
"loss": 2.008584499359131,
|
| 4651 |
+
"step": 1326
|
| 4652 |
+
},
|
| 4653 |
+
{
|
| 4654 |
+
"epoch": 0.4630646651672856,
|
| 4655 |
+
"grad_norm": 0.16026270389556885,
|
| 4656 |
+
"learning_rate": 5e-05,
|
| 4657 |
+
"loss": 2.036628246307373,
|
| 4658 |
+
"step": 1328
|
| 4659 |
+
},
|
| 4660 |
+
{
|
| 4661 |
+
"epoch": 0.4637620517112122,
|
| 4662 |
+
"grad_norm": 0.2072455734014511,
|
| 4663 |
+
"learning_rate": 5e-05,
|
| 4664 |
+
"loss": 1.9640253782272339,
|
| 4665 |
+
"step": 1330
|
| 4666 |
+
},
|
| 4667 |
+
{
|
| 4668 |
+
"epoch": 0.46445943825513886,
|
| 4669 |
+
"grad_norm": 0.2008819282054901,
|
| 4670 |
+
"learning_rate": 5e-05,
|
| 4671 |
+
"loss": 2.1391754150390625,
|
| 4672 |
+
"step": 1332
|
| 4673 |
+
},
|
| 4674 |
+
{
|
| 4675 |
+
"epoch": 0.4651568247990655,
|
| 4676 |
+
"grad_norm": 0.15363521873950958,
|
| 4677 |
+
"learning_rate": 5e-05,
|
| 4678 |
+
"loss": 2.21854305267334,
|
| 4679 |
+
"step": 1334
|
| 4680 |
+
},
|
| 4681 |
+
{
|
| 4682 |
+
"epoch": 0.46585421134299215,
|
| 4683 |
+
"grad_norm": 0.30436429381370544,
|
| 4684 |
+
"learning_rate": 5e-05,
|
| 4685 |
+
"loss": 2.0346920490264893,
|
| 4686 |
+
"step": 1336
|
| 4687 |
+
},
|
| 4688 |
+
{
|
| 4689 |
+
"epoch": 0.46655159788691875,
|
| 4690 |
+
"grad_norm": 0.20182740688323975,
|
| 4691 |
+
"learning_rate": 5e-05,
|
| 4692 |
+
"loss": 1.9244691133499146,
|
| 4693 |
+
"step": 1338
|
| 4694 |
+
},
|
| 4695 |
+
{
|
| 4696 |
+
"epoch": 0.4672489844308454,
|
| 4697 |
+
"grad_norm": 0.27045613527297974,
|
| 4698 |
+
"learning_rate": 5e-05,
|
| 4699 |
+
"loss": 2.037353038787842,
|
| 4700 |
+
"step": 1340
|
| 4701 |
+
},
|
| 4702 |
+
{
|
| 4703 |
+
"epoch": 0.46794637097477204,
|
| 4704 |
+
"grad_norm": 0.1664476990699768,
|
| 4705 |
+
"learning_rate": 5e-05,
|
| 4706 |
+
"loss": 2.0294156074523926,
|
| 4707 |
+
"step": 1342
|
| 4708 |
+
},
|
| 4709 |
+
{
|
| 4710 |
+
"epoch": 0.4686437575186987,
|
| 4711 |
+
"grad_norm": 0.20976664125919342,
|
| 4712 |
+
"learning_rate": 5e-05,
|
| 4713 |
+
"loss": 1.9494667053222656,
|
| 4714 |
+
"step": 1344
|
| 4715 |
+
},
|
| 4716 |
+
{
|
| 4717 |
+
"epoch": 0.46934114406262534,
|
| 4718 |
+
"grad_norm": 0.22498564422130585,
|
| 4719 |
+
"learning_rate": 5e-05,
|
| 4720 |
+
"loss": 1.9336860179901123,
|
| 4721 |
+
"step": 1346
|
| 4722 |
+
},
|
| 4723 |
+
{
|
| 4724 |
+
"epoch": 0.47003853060655193,
|
| 4725 |
+
"grad_norm": 0.17451924085617065,
|
| 4726 |
+
"learning_rate": 5e-05,
|
| 4727 |
+
"loss": 2.027860641479492,
|
| 4728 |
+
"step": 1348
|
| 4729 |
+
},
|
| 4730 |
+
{
|
| 4731 |
+
"epoch": 0.4707359171504786,
|
| 4732 |
+
"grad_norm": 0.28990885615348816,
|
| 4733 |
+
"learning_rate": 5e-05,
|
| 4734 |
+
"loss": 1.8952656984329224,
|
| 4735 |
+
"step": 1350
|
| 4736 |
+
},
|
| 4737 |
+
{
|
| 4738 |
+
"epoch": 0.4714333036944052,
|
| 4739 |
+
"grad_norm": 0.2333941012620926,
|
| 4740 |
+
"learning_rate": 5e-05,
|
| 4741 |
+
"loss": 1.7821979522705078,
|
| 4742 |
+
"step": 1352
|
| 4743 |
+
},
|
| 4744 |
+
{
|
| 4745 |
+
"epoch": 0.4721306902383319,
|
| 4746 |
+
"grad_norm": 0.231252983212471,
|
| 4747 |
+
"learning_rate": 5e-05,
|
| 4748 |
+
"loss": 1.9425376653671265,
|
| 4749 |
+
"step": 1354
|
| 4750 |
+
},
|
| 4751 |
+
{
|
| 4752 |
+
"epoch": 0.47282807678225847,
|
| 4753 |
+
"grad_norm": 0.21064279973506927,
|
| 4754 |
+
"learning_rate": 5e-05,
|
| 4755 |
+
"loss": 1.7968411445617676,
|
| 4756 |
+
"step": 1356
|
| 4757 |
+
},
|
| 4758 |
+
{
|
| 4759 |
+
"epoch": 0.4735254633261851,
|
| 4760 |
+
"grad_norm": 0.2252817004919052,
|
| 4761 |
+
"learning_rate": 5e-05,
|
| 4762 |
+
"loss": 1.9492859840393066,
|
| 4763 |
+
"step": 1358
|
| 4764 |
+
},
|
| 4765 |
+
{
|
| 4766 |
+
"epoch": 0.47422284987011176,
|
| 4767 |
+
"grad_norm": 0.2374482899904251,
|
| 4768 |
+
"learning_rate": 5e-05,
|
| 4769 |
+
"loss": 2.0691514015197754,
|
| 4770 |
+
"step": 1360
|
| 4771 |
+
},
|
| 4772 |
+
{
|
| 4773 |
+
"epoch": 0.4749202364140384,
|
| 4774 |
+
"grad_norm": 0.16628314554691315,
|
| 4775 |
+
"learning_rate": 5e-05,
|
| 4776 |
+
"loss": 1.9889640808105469,
|
| 4777 |
+
"step": 1362
|
| 4778 |
+
},
|
| 4779 |
+
{
|
| 4780 |
+
"epoch": 0.475617622957965,
|
| 4781 |
+
"grad_norm": 0.23188260197639465,
|
| 4782 |
+
"learning_rate": 5e-05,
|
| 4783 |
+
"loss": 1.826238989830017,
|
| 4784 |
+
"step": 1364
|
| 4785 |
+
},
|
| 4786 |
+
{
|
| 4787 |
+
"epoch": 0.47631500950189165,
|
| 4788 |
+
"grad_norm": 0.23864124715328217,
|
| 4789 |
+
"learning_rate": 5e-05,
|
| 4790 |
+
"loss": 1.8316365480422974,
|
| 4791 |
+
"step": 1366
|
| 4792 |
+
},
|
| 4793 |
+
{
|
| 4794 |
+
"epoch": 0.4770123960458183,
|
| 4795 |
+
"grad_norm": 0.17230239510536194,
|
| 4796 |
+
"learning_rate": 5e-05,
|
| 4797 |
+
"loss": 2.108180522918701,
|
| 4798 |
+
"step": 1368
|
| 4799 |
+
},
|
| 4800 |
+
{
|
| 4801 |
+
"epoch": 0.47770978258974495,
|
| 4802 |
+
"grad_norm": 0.3431381583213806,
|
| 4803 |
+
"learning_rate": 5e-05,
|
| 4804 |
+
"loss": 1.927293062210083,
|
| 4805 |
+
"step": 1370
|
| 4806 |
+
},
|
| 4807 |
+
{
|
| 4808 |
+
"epoch": 0.47840716913367154,
|
| 4809 |
+
"grad_norm": 0.1808742880821228,
|
| 4810 |
+
"learning_rate": 5e-05,
|
| 4811 |
+
"loss": 2.0206215381622314,
|
| 4812 |
+
"step": 1372
|
| 4813 |
+
},
|
| 4814 |
+
{
|
| 4815 |
+
"epoch": 0.4791045556775982,
|
| 4816 |
+
"grad_norm": 0.19927719235420227,
|
| 4817 |
+
"learning_rate": 5e-05,
|
| 4818 |
+
"loss": 2.071760654449463,
|
| 4819 |
+
"step": 1374
|
| 4820 |
+
},
|
| 4821 |
+
{
|
| 4822 |
+
"epoch": 0.47980194222152484,
|
| 4823 |
+
"grad_norm": 0.23531778156757355,
|
| 4824 |
+
"learning_rate": 5e-05,
|
| 4825 |
+
"loss": 2.0391430854797363,
|
| 4826 |
+
"step": 1376
|
| 4827 |
+
},
|
| 4828 |
+
{
|
| 4829 |
+
"epoch": 0.4804993287654515,
|
| 4830 |
+
"grad_norm": 0.1925334483385086,
|
| 4831 |
+
"learning_rate": 5e-05,
|
| 4832 |
+
"loss": 1.8715038299560547,
|
| 4833 |
+
"step": 1378
|
| 4834 |
+
},
|
| 4835 |
+
{
|
| 4836 |
+
"epoch": 0.48119671530937813,
|
| 4837 |
+
"grad_norm": 0.17263978719711304,
|
| 4838 |
+
"learning_rate": 5e-05,
|
| 4839 |
+
"loss": 2.0224063396453857,
|
| 4840 |
+
"step": 1380
|
| 4841 |
+
},
|
| 4842 |
+
{
|
| 4843 |
+
"epoch": 0.4818941018533047,
|
| 4844 |
+
"grad_norm": 0.24466554820537567,
|
| 4845 |
+
"learning_rate": 5e-05,
|
| 4846 |
+
"loss": 2.037820339202881,
|
| 4847 |
+
"step": 1382
|
| 4848 |
+
},
|
| 4849 |
+
{
|
| 4850 |
+
"epoch": 0.48259148839723137,
|
| 4851 |
+
"grad_norm": 0.3562721014022827,
|
| 4852 |
+
"learning_rate": 5e-05,
|
| 4853 |
+
"loss": 1.962568998336792,
|
| 4854 |
+
"step": 1384
|
| 4855 |
+
},
|
| 4856 |
+
{
|
| 4857 |
+
"epoch": 0.483288874941158,
|
| 4858 |
+
"grad_norm": 0.19220297038555145,
|
| 4859 |
+
"learning_rate": 5e-05,
|
| 4860 |
+
"loss": 2.120224952697754,
|
| 4861 |
+
"step": 1386
|
| 4862 |
+
},
|
| 4863 |
+
{
|
| 4864 |
+
"epoch": 0.48398626148508467,
|
| 4865 |
+
"grad_norm": 0.17400771379470825,
|
| 4866 |
+
"learning_rate": 5e-05,
|
| 4867 |
+
"loss": 1.9022951126098633,
|
| 4868 |
+
"step": 1388
|
| 4869 |
+
},
|
| 4870 |
+
{
|
| 4871 |
+
"epoch": 0.48468364802901126,
|
| 4872 |
+
"grad_norm": 0.2036677896976471,
|
| 4873 |
+
"learning_rate": 5e-05,
|
| 4874 |
+
"loss": 2.034552574157715,
|
| 4875 |
+
"step": 1390
|
| 4876 |
+
},
|
| 4877 |
+
{
|
| 4878 |
+
"epoch": 0.4853810345729379,
|
| 4879 |
+
"grad_norm": 0.23469923436641693,
|
| 4880 |
+
"learning_rate": 5e-05,
|
| 4881 |
+
"loss": 2.1075315475463867,
|
| 4882 |
+
"step": 1392
|
| 4883 |
+
},
|
| 4884 |
+
{
|
| 4885 |
+
"epoch": 0.48607842111686456,
|
| 4886 |
+
"grad_norm": 0.19877077639102936,
|
| 4887 |
+
"learning_rate": 5e-05,
|
| 4888 |
+
"loss": 2.0443668365478516,
|
| 4889 |
+
"step": 1394
|
| 4890 |
+
},
|
| 4891 |
+
{
|
| 4892 |
+
"epoch": 0.4867758076607912,
|
| 4893 |
+
"grad_norm": 0.21028253436088562,
|
| 4894 |
+
"learning_rate": 5e-05,
|
| 4895 |
+
"loss": 2.05700421333313,
|
| 4896 |
+
"step": 1396
|
| 4897 |
+
},
|
| 4898 |
+
{
|
| 4899 |
+
"epoch": 0.4874731942047178,
|
| 4900 |
+
"grad_norm": 0.2600529193878174,
|
| 4901 |
+
"learning_rate": 5e-05,
|
| 4902 |
+
"loss": 1.984779715538025,
|
| 4903 |
+
"step": 1398
|
| 4904 |
+
},
|
| 4905 |
+
{
|
| 4906 |
+
"epoch": 0.48817058074864444,
|
| 4907 |
+
"grad_norm": 0.2925497591495514,
|
| 4908 |
+
"learning_rate": 5e-05,
|
| 4909 |
+
"loss": 1.9900577068328857,
|
| 4910 |
+
"step": 1400
|
| 4911 |
+
},
|
| 4912 |
+
{
|
| 4913 |
+
"epoch": 0.4888679672925711,
|
| 4914 |
+
"grad_norm": 0.21559077501296997,
|
| 4915 |
+
"learning_rate": 5e-05,
|
| 4916 |
+
"loss": 1.9484243392944336,
|
| 4917 |
+
"step": 1402
|
| 4918 |
+
},
|
| 4919 |
+
{
|
| 4920 |
+
"epoch": 0.48956535383649774,
|
| 4921 |
+
"grad_norm": 0.22062966227531433,
|
| 4922 |
+
"learning_rate": 5e-05,
|
| 4923 |
+
"loss": 1.7250257730484009,
|
| 4924 |
+
"step": 1404
|
| 4925 |
+
},
|
| 4926 |
+
{
|
| 4927 |
+
"epoch": 0.49026274038042433,
|
| 4928 |
+
"grad_norm": 0.2718144357204437,
|
| 4929 |
+
"learning_rate": 5e-05,
|
| 4930 |
+
"loss": 2.0089738368988037,
|
| 4931 |
+
"step": 1406
|
| 4932 |
+
},
|
| 4933 |
+
{
|
| 4934 |
+
"epoch": 0.490960126924351,
|
| 4935 |
+
"grad_norm": 0.21445487439632416,
|
| 4936 |
+
"learning_rate": 5e-05,
|
| 4937 |
+
"loss": 1.8109028339385986,
|
| 4938 |
+
"step": 1408
|
| 4939 |
+
},
|
| 4940 |
+
{
|
| 4941 |
+
"epoch": 0.49165751346827763,
|
| 4942 |
+
"grad_norm": 0.28173160552978516,
|
| 4943 |
+
"learning_rate": 5e-05,
|
| 4944 |
+
"loss": 1.964066743850708,
|
| 4945 |
+
"step": 1410
|
| 4946 |
+
},
|
| 4947 |
+
{
|
| 4948 |
+
"epoch": 0.4923549000122043,
|
| 4949 |
+
"grad_norm": 0.23372000455856323,
|
| 4950 |
+
"learning_rate": 5e-05,
|
| 4951 |
+
"loss": 1.9023646116256714,
|
| 4952 |
+
"step": 1412
|
| 4953 |
+
},
|
| 4954 |
+
{
|
| 4955 |
+
"epoch": 0.4930522865561309,
|
| 4956 |
+
"grad_norm": 0.20902119576931,
|
| 4957 |
+
"learning_rate": 5e-05,
|
| 4958 |
+
"loss": 1.8483302593231201,
|
| 4959 |
+
"step": 1414
|
| 4960 |
+
},
|
| 4961 |
+
{
|
| 4962 |
+
"epoch": 0.4937496731000575,
|
| 4963 |
+
"grad_norm": 0.20217423141002655,
|
| 4964 |
+
"learning_rate": 5e-05,
|
| 4965 |
+
"loss": 2.0042505264282227,
|
| 4966 |
+
"step": 1416
|
| 4967 |
+
},
|
| 4968 |
+
{
|
| 4969 |
+
"epoch": 0.49444705964398417,
|
| 4970 |
+
"grad_norm": 0.1686791032552719,
|
| 4971 |
+
"learning_rate": 5e-05,
|
| 4972 |
+
"loss": 2.167377233505249,
|
| 4973 |
+
"step": 1418
|
| 4974 |
+
},
|
| 4975 |
+
{
|
| 4976 |
+
"epoch": 0.4951444461879108,
|
| 4977 |
+
"grad_norm": 0.21020229160785675,
|
| 4978 |
+
"learning_rate": 5e-05,
|
| 4979 |
+
"loss": 1.88352370262146,
|
| 4980 |
+
"step": 1420
|
| 4981 |
+
},
|
| 4982 |
+
{
|
| 4983 |
+
"epoch": 0.49584183273183746,
|
| 4984 |
+
"grad_norm": 0.16124327480793,
|
| 4985 |
+
"learning_rate": 5e-05,
|
| 4986 |
+
"loss": 1.8495641946792603,
|
| 4987 |
+
"step": 1422
|
| 4988 |
+
},
|
| 4989 |
+
{
|
| 4990 |
+
"epoch": 0.49653921927576405,
|
| 4991 |
+
"grad_norm": 0.19446009397506714,
|
| 4992 |
+
"learning_rate": 5e-05,
|
| 4993 |
+
"loss": 1.8798768520355225,
|
| 4994 |
+
"step": 1424
|
| 4995 |
+
},
|
| 4996 |
+
{
|
| 4997 |
+
"epoch": 0.4972366058196907,
|
| 4998 |
+
"grad_norm": 0.17021384835243225,
|
| 4999 |
+
"learning_rate": 5e-05,
|
| 5000 |
+
"loss": 2.11187744140625,
|
| 5001 |
+
"step": 1426
|
| 5002 |
+
},
|
| 5003 |
+
{
|
| 5004 |
+
"epoch": 0.49793399236361735,
|
| 5005 |
+
"grad_norm": 0.20835986733436584,
|
| 5006 |
+
"learning_rate": 5e-05,
|
| 5007 |
+
"loss": 1.9984071254730225,
|
| 5008 |
+
"step": 1428
|
| 5009 |
+
},
|
| 5010 |
+
{
|
| 5011 |
+
"epoch": 0.498631378907544,
|
| 5012 |
+
"grad_norm": 0.18223054707050323,
|
| 5013 |
+
"learning_rate": 5e-05,
|
| 5014 |
+
"loss": 1.721818208694458,
|
| 5015 |
+
"step": 1430
|
| 5016 |
+
},
|
| 5017 |
+
{
|
| 5018 |
+
"epoch": 0.4993287654514706,
|
| 5019 |
+
"grad_norm": 0.202471524477005,
|
| 5020 |
+
"learning_rate": 5e-05,
|
| 5021 |
+
"loss": 2.026165723800659,
|
| 5022 |
+
"step": 1432
|
| 5023 |
+
},
|
| 5024 |
+
{
|
| 5025 |
+
"epoch": 0.5000261519953972,
|
| 5026 |
+
"grad_norm": 0.16094128787517548,
|
| 5027 |
+
"learning_rate": 5e-05,
|
| 5028 |
+
"loss": 1.8392627239227295,
|
| 5029 |
+
"step": 1434
|
| 5030 |
+
},
|
| 5031 |
+
{
|
| 5032 |
+
"epoch": 0.5007235385393238,
|
| 5033 |
+
"grad_norm": 0.36537352204322815,
|
| 5034 |
+
"learning_rate": 5e-05,
|
| 5035 |
+
"loss": 1.818052887916565,
|
| 5036 |
+
"step": 1436
|
| 5037 |
+
},
|
| 5038 |
+
{
|
| 5039 |
+
"epoch": 0.5014209250832505,
|
| 5040 |
+
"grad_norm": 0.3065716326236725,
|
| 5041 |
+
"learning_rate": 5e-05,
|
| 5042 |
+
"loss": 1.5908174514770508,
|
| 5043 |
+
"step": 1438
|
| 5044 |
+
},
|
| 5045 |
+
{
|
| 5046 |
+
"epoch": 0.5021183116271771,
|
| 5047 |
+
"grad_norm": 0.315999835729599,
|
| 5048 |
+
"learning_rate": 5e-05,
|
| 5049 |
+
"loss": 2.0305862426757812,
|
| 5050 |
+
"step": 1440
|
| 5051 |
+
},
|
| 5052 |
+
{
|
| 5053 |
+
"epoch": 0.5028156981711038,
|
| 5054 |
+
"grad_norm": 0.22419418394565582,
|
| 5055 |
+
"learning_rate": 5e-05,
|
| 5056 |
+
"loss": 2.0770304203033447,
|
| 5057 |
+
"step": 1442
|
| 5058 |
+
},
|
| 5059 |
+
{
|
| 5060 |
+
"epoch": 0.5035130847150304,
|
| 5061 |
+
"grad_norm": 0.19013993442058563,
|
| 5062 |
+
"learning_rate": 5e-05,
|
| 5063 |
+
"loss": 1.9330451488494873,
|
| 5064 |
+
"step": 1444
|
| 5065 |
+
},
|
| 5066 |
+
{
|
| 5067 |
+
"epoch": 0.504210471258957,
|
| 5068 |
+
"grad_norm": 0.23034580051898956,
|
| 5069 |
+
"learning_rate": 5e-05,
|
| 5070 |
+
"loss": 2.0115108489990234,
|
| 5071 |
+
"step": 1446
|
| 5072 |
+
},
|
| 5073 |
+
{
|
| 5074 |
+
"epoch": 0.5049078578028837,
|
| 5075 |
+
"grad_norm": 0.22189804911613464,
|
| 5076 |
+
"learning_rate": 5e-05,
|
| 5077 |
+
"loss": 1.9059724807739258,
|
| 5078 |
+
"step": 1448
|
| 5079 |
+
},
|
| 5080 |
+
{
|
| 5081 |
+
"epoch": 0.5056052443468103,
|
| 5082 |
+
"grad_norm": 0.24250493943691254,
|
| 5083 |
+
"learning_rate": 5e-05,
|
| 5084 |
+
"loss": 1.9216318130493164,
|
| 5085 |
+
"step": 1450
|
| 5086 |
+
},
|
| 5087 |
+
{
|
| 5088 |
+
"epoch": 0.506302630890737,
|
| 5089 |
+
"grad_norm": 0.1884554922580719,
|
| 5090 |
+
"learning_rate": 5e-05,
|
| 5091 |
+
"loss": 2.0774998664855957,
|
| 5092 |
+
"step": 1452
|
| 5093 |
+
},
|
| 5094 |
+
{
|
| 5095 |
+
"epoch": 0.5070000174346636,
|
| 5096 |
+
"grad_norm": 0.32978472113609314,
|
| 5097 |
+
"learning_rate": 5e-05,
|
| 5098 |
+
"loss": 1.7872614860534668,
|
| 5099 |
+
"step": 1454
|
| 5100 |
+
},
|
| 5101 |
+
{
|
| 5102 |
+
"epoch": 0.5076974039785902,
|
| 5103 |
+
"grad_norm": 0.20328378677368164,
|
| 5104 |
+
"learning_rate": 5e-05,
|
| 5105 |
+
"loss": 2.087057590484619,
|
| 5106 |
+
"step": 1456
|
| 5107 |
+
},
|
| 5108 |
+
{
|
| 5109 |
+
"epoch": 0.5083947905225169,
|
| 5110 |
+
"grad_norm": 0.1932574063539505,
|
| 5111 |
+
"learning_rate": 5e-05,
|
| 5112 |
+
"loss": 1.9663078784942627,
|
| 5113 |
+
"step": 1458
|
| 5114 |
+
},
|
| 5115 |
+
{
|
| 5116 |
+
"epoch": 0.5090921770664435,
|
| 5117 |
+
"grad_norm": 0.2333851009607315,
|
| 5118 |
+
"learning_rate": 5e-05,
|
| 5119 |
+
"loss": 2.114800453186035,
|
| 5120 |
+
"step": 1460
|
| 5121 |
+
},
|
| 5122 |
+
{
|
| 5123 |
+
"epoch": 0.5097895636103701,
|
| 5124 |
+
"grad_norm": 0.2896854877471924,
|
| 5125 |
+
"learning_rate": 5e-05,
|
| 5126 |
+
"loss": 1.821686863899231,
|
| 5127 |
+
"step": 1462
|
| 5128 |
+
},
|
| 5129 |
+
{
|
| 5130 |
+
"epoch": 0.5104869501542968,
|
| 5131 |
+
"grad_norm": 0.15735310316085815,
|
| 5132 |
+
"learning_rate": 5e-05,
|
| 5133 |
+
"loss": 2.0014073848724365,
|
| 5134 |
+
"step": 1464
|
| 5135 |
+
},
|
| 5136 |
+
{
|
| 5137 |
+
"epoch": 0.5111843366982234,
|
| 5138 |
+
"grad_norm": 0.20952001214027405,
|
| 5139 |
+
"learning_rate": 5e-05,
|
| 5140 |
+
"loss": 1.9321421384811401,
|
| 5141 |
+
"step": 1466
|
| 5142 |
+
},
|
| 5143 |
+
{
|
| 5144 |
+
"epoch": 0.5118817232421501,
|
| 5145 |
+
"grad_norm": 0.26672106981277466,
|
| 5146 |
+
"learning_rate": 5e-05,
|
| 5147 |
+
"loss": 2.0439276695251465,
|
| 5148 |
+
"step": 1468
|
| 5149 |
+
},
|
| 5150 |
+
{
|
| 5151 |
+
"epoch": 0.5125791097860767,
|
| 5152 |
+
"grad_norm": 0.24956052005290985,
|
| 5153 |
+
"learning_rate": 5e-05,
|
| 5154 |
+
"loss": 2.0869853496551514,
|
| 5155 |
+
"step": 1470
|
| 5156 |
+
},
|
| 5157 |
+
{
|
| 5158 |
+
"epoch": 0.5132764963300033,
|
| 5159 |
+
"grad_norm": 0.1717880517244339,
|
| 5160 |
+
"learning_rate": 5e-05,
|
| 5161 |
+
"loss": 1.9398398399353027,
|
| 5162 |
+
"step": 1472
|
| 5163 |
+
},
|
| 5164 |
+
{
|
| 5165 |
+
"epoch": 0.51397388287393,
|
| 5166 |
+
"grad_norm": 0.22402872145175934,
|
| 5167 |
+
"learning_rate": 5e-05,
|
| 5168 |
+
"loss": 1.7385175228118896,
|
| 5169 |
+
"step": 1474
|
| 5170 |
+
},
|
| 5171 |
+
{
|
| 5172 |
+
"epoch": 0.5146712694178566,
|
| 5173 |
+
"grad_norm": 0.22106806933879852,
|
| 5174 |
+
"learning_rate": 5e-05,
|
| 5175 |
+
"loss": 2.1921401023864746,
|
| 5176 |
+
"step": 1476
|
| 5177 |
+
},
|
| 5178 |
+
{
|
| 5179 |
+
"epoch": 0.5153686559617832,
|
| 5180 |
+
"grad_norm": 0.21225227415561676,
|
| 5181 |
+
"learning_rate": 5e-05,
|
| 5182 |
+
"loss": 1.813704490661621,
|
| 5183 |
+
"step": 1478
|
| 5184 |
+
},
|
| 5185 |
+
{
|
| 5186 |
+
"epoch": 0.5160660425057099,
|
| 5187 |
+
"grad_norm": 0.24747970700263977,
|
| 5188 |
+
"learning_rate": 5e-05,
|
| 5189 |
+
"loss": 2.0386838912963867,
|
| 5190 |
+
"step": 1480
|
| 5191 |
+
},
|
| 5192 |
+
{
|
| 5193 |
+
"epoch": 0.5167634290496365,
|
| 5194 |
+
"grad_norm": 0.2071690410375595,
|
| 5195 |
+
"learning_rate": 5e-05,
|
| 5196 |
+
"loss": 1.9998681545257568,
|
| 5197 |
+
"step": 1482
|
| 5198 |
+
},
|
| 5199 |
+
{
|
| 5200 |
+
"epoch": 0.5174608155935632,
|
| 5201 |
+
"grad_norm": 0.19989708065986633,
|
| 5202 |
+
"learning_rate": 5e-05,
|
| 5203 |
+
"loss": 1.9855647087097168,
|
| 5204 |
+
"step": 1484
|
| 5205 |
+
},
|
| 5206 |
+
{
|
| 5207 |
+
"epoch": 0.5181582021374898,
|
| 5208 |
+
"grad_norm": 0.37738072872161865,
|
| 5209 |
+
"learning_rate": 5e-05,
|
| 5210 |
+
"loss": 1.9317657947540283,
|
| 5211 |
+
"step": 1486
|
| 5212 |
+
},
|
| 5213 |
+
{
|
| 5214 |
+
"epoch": 0.5188555886814163,
|
| 5215 |
+
"grad_norm": 0.19475798308849335,
|
| 5216 |
+
"learning_rate": 5e-05,
|
| 5217 |
+
"loss": 2.1612281799316406,
|
| 5218 |
+
"step": 1488
|
| 5219 |
+
},
|
| 5220 |
+
{
|
| 5221 |
+
"epoch": 0.519552975225343,
|
| 5222 |
+
"grad_norm": 0.16933269798755646,
|
| 5223 |
+
"learning_rate": 5e-05,
|
| 5224 |
+
"loss": 1.8891172409057617,
|
| 5225 |
+
"step": 1490
|
| 5226 |
+
},
|
| 5227 |
+
{
|
| 5228 |
+
"epoch": 0.5202503617692696,
|
| 5229 |
+
"grad_norm": 0.2092454433441162,
|
| 5230 |
+
"learning_rate": 5e-05,
|
| 5231 |
+
"loss": 1.9128150939941406,
|
| 5232 |
+
"step": 1492
|
| 5233 |
+
},
|
| 5234 |
+
{
|
| 5235 |
+
"epoch": 0.5209477483131963,
|
| 5236 |
+
"grad_norm": 0.1707553267478943,
|
| 5237 |
+
"learning_rate": 5e-05,
|
| 5238 |
+
"loss": 2.026205539703369,
|
| 5239 |
+
"step": 1494
|
| 5240 |
+
},
|
| 5241 |
+
{
|
| 5242 |
+
"epoch": 0.5216451348571229,
|
| 5243 |
+
"grad_norm": 0.26486045122146606,
|
| 5244 |
+
"learning_rate": 5e-05,
|
| 5245 |
+
"loss": 1.932251214981079,
|
| 5246 |
+
"step": 1496
|
| 5247 |
+
},
|
| 5248 |
+
{
|
| 5249 |
+
"epoch": 0.5223425214010495,
|
| 5250 |
+
"grad_norm": 0.24055586755275726,
|
| 5251 |
+
"learning_rate": 5e-05,
|
| 5252 |
+
"loss": 2.102813482284546,
|
| 5253 |
+
"step": 1498
|
| 5254 |
+
},
|
| 5255 |
+
{
|
| 5256 |
+
"epoch": 0.5230399079449762,
|
| 5257 |
+
"grad_norm": 0.22778025269508362,
|
| 5258 |
+
"learning_rate": 5e-05,
|
| 5259 |
+
"loss": 2.025139093399048,
|
| 5260 |
+
"step": 1500
|
| 5261 |
+
},
|
| 5262 |
+
{
|
| 5263 |
+
"epoch": 0.5237372944889028,
|
| 5264 |
+
"grad_norm": 0.21262387931346893,
|
| 5265 |
+
"learning_rate": 5e-05,
|
| 5266 |
+
"loss": 1.9433798789978027,
|
| 5267 |
+
"step": 1502
|
| 5268 |
+
},
|
| 5269 |
+
{
|
| 5270 |
+
"epoch": 0.5244346810328294,
|
| 5271 |
+
"grad_norm": 0.22720636427402496,
|
| 5272 |
+
"learning_rate": 5e-05,
|
| 5273 |
+
"loss": 1.8567476272583008,
|
| 5274 |
+
"step": 1504
|
| 5275 |
+
},
|
| 5276 |
+
{
|
| 5277 |
+
"epoch": 0.5251320675767561,
|
| 5278 |
+
"grad_norm": 0.21710364520549774,
|
| 5279 |
+
"learning_rate": 5e-05,
|
| 5280 |
+
"loss": 1.9706692695617676,
|
| 5281 |
+
"step": 1506
|
| 5282 |
+
},
|
| 5283 |
+
{
|
| 5284 |
+
"epoch": 0.5258294541206827,
|
| 5285 |
+
"grad_norm": 0.16479766368865967,
|
| 5286 |
+
"learning_rate": 5e-05,
|
| 5287 |
+
"loss": 2.0109052658081055,
|
| 5288 |
+
"step": 1508
|
| 5289 |
+
},
|
| 5290 |
+
{
|
| 5291 |
+
"epoch": 0.5265268406646094,
|
| 5292 |
+
"grad_norm": 0.2113187611103058,
|
| 5293 |
+
"learning_rate": 5e-05,
|
| 5294 |
+
"loss": 1.8496572971343994,
|
| 5295 |
+
"step": 1510
|
| 5296 |
+
},
|
| 5297 |
+
{
|
| 5298 |
+
"epoch": 0.527224227208536,
|
| 5299 |
+
"grad_norm": 0.2933638095855713,
|
| 5300 |
+
"learning_rate": 5e-05,
|
| 5301 |
+
"loss": 2.052328586578369,
|
| 5302 |
+
"step": 1512
|
| 5303 |
+
},
|
| 5304 |
+
{
|
| 5305 |
+
"epoch": 0.5279216137524626,
|
| 5306 |
+
"grad_norm": 0.2246863842010498,
|
| 5307 |
+
"learning_rate": 5e-05,
|
| 5308 |
+
"loss": 1.9460456371307373,
|
| 5309 |
+
"step": 1514
|
| 5310 |
+
},
|
| 5311 |
+
{
|
| 5312 |
+
"epoch": 0.5286190002963893,
|
| 5313 |
+
"grad_norm": 0.1951591968536377,
|
| 5314 |
+
"learning_rate": 5e-05,
|
| 5315 |
+
"loss": 1.9435811042785645,
|
| 5316 |
+
"step": 1516
|
| 5317 |
+
},
|
| 5318 |
+
{
|
| 5319 |
+
"epoch": 0.5293163868403159,
|
| 5320 |
+
"grad_norm": 0.20596501231193542,
|
| 5321 |
+
"learning_rate": 5e-05,
|
| 5322 |
+
"loss": 1.9414966106414795,
|
| 5323 |
+
"step": 1518
|
| 5324 |
+
},
|
| 5325 |
+
{
|
| 5326 |
+
"epoch": 0.5300137733842426,
|
| 5327 |
+
"grad_norm": 0.21787771582603455,
|
| 5328 |
+
"learning_rate": 5e-05,
|
| 5329 |
+
"loss": 1.9627716541290283,
|
| 5330 |
+
"step": 1520
|
| 5331 |
+
},
|
| 5332 |
+
{
|
| 5333 |
+
"epoch": 0.5307111599281692,
|
| 5334 |
+
"grad_norm": 0.24987459182739258,
|
| 5335 |
+
"learning_rate": 5e-05,
|
| 5336 |
+
"loss": 2.041393280029297,
|
| 5337 |
+
"step": 1522
|
| 5338 |
+
},
|
| 5339 |
+
{
|
| 5340 |
+
"epoch": 0.5314085464720958,
|
| 5341 |
+
"grad_norm": 0.22474417090415955,
|
| 5342 |
+
"learning_rate": 5e-05,
|
| 5343 |
+
"loss": 2.2523980140686035,
|
| 5344 |
+
"step": 1524
|
| 5345 |
+
},
|
| 5346 |
+
{
|
| 5347 |
+
"epoch": 0.5321059330160225,
|
| 5348 |
+
"grad_norm": 0.2154618799686432,
|
| 5349 |
+
"learning_rate": 5e-05,
|
| 5350 |
+
"loss": 1.9683117866516113,
|
| 5351 |
+
"step": 1526
|
| 5352 |
+
},
|
| 5353 |
+
{
|
| 5354 |
+
"epoch": 0.5328033195599491,
|
| 5355 |
+
"grad_norm": 0.2014053463935852,
|
| 5356 |
+
"learning_rate": 5e-05,
|
| 5357 |
+
"loss": 1.9071648120880127,
|
| 5358 |
+
"step": 1528
|
| 5359 |
+
},
|
| 5360 |
+
{
|
| 5361 |
+
"epoch": 0.5335007061038757,
|
| 5362 |
+
"grad_norm": 0.2900610864162445,
|
| 5363 |
+
"learning_rate": 5e-05,
|
| 5364 |
+
"loss": 2.0379743576049805,
|
| 5365 |
+
"step": 1530
|
| 5366 |
+
},
|
| 5367 |
+
{
|
| 5368 |
+
"epoch": 0.5341980926478024,
|
| 5369 |
+
"grad_norm": 0.19507604837417603,
|
| 5370 |
+
"learning_rate": 5e-05,
|
| 5371 |
+
"loss": 1.7710990905761719,
|
| 5372 |
+
"step": 1532
|
| 5373 |
+
},
|
| 5374 |
+
{
|
| 5375 |
+
"epoch": 0.534895479191729,
|
| 5376 |
+
"grad_norm": 0.25735238194465637,
|
| 5377 |
+
"learning_rate": 5e-05,
|
| 5378 |
+
"loss": 1.878333568572998,
|
| 5379 |
+
"step": 1534
|
| 5380 |
+
},
|
| 5381 |
+
{
|
| 5382 |
+
"epoch": 0.5355928657356557,
|
| 5383 |
+
"grad_norm": 0.23907451331615448,
|
| 5384 |
+
"learning_rate": 5e-05,
|
| 5385 |
+
"loss": 1.968424677848816,
|
| 5386 |
+
"step": 1536
|
| 5387 |
+
},
|
| 5388 |
+
{
|
| 5389 |
+
"epoch": 0.5362902522795823,
|
| 5390 |
+
"grad_norm": 0.29978978633880615,
|
| 5391 |
+
"learning_rate": 5e-05,
|
| 5392 |
+
"loss": 1.9405322074890137,
|
| 5393 |
+
"step": 1538
|
| 5394 |
+
},
|
| 5395 |
+
{
|
| 5396 |
+
"epoch": 0.5369876388235089,
|
| 5397 |
+
"grad_norm": 0.19385389983654022,
|
| 5398 |
+
"learning_rate": 5e-05,
|
| 5399 |
+
"loss": 1.9528419971466064,
|
| 5400 |
+
"step": 1540
|
| 5401 |
+
},
|
| 5402 |
+
{
|
| 5403 |
+
"epoch": 0.5376850253674356,
|
| 5404 |
+
"grad_norm": 0.23425279557704926,
|
| 5405 |
+
"learning_rate": 5e-05,
|
| 5406 |
+
"loss": 2.1229302883148193,
|
| 5407 |
+
"step": 1542
|
| 5408 |
+
},
|
| 5409 |
+
{
|
| 5410 |
+
"epoch": 0.5383824119113622,
|
| 5411 |
+
"grad_norm": 0.21549579501152039,
|
| 5412 |
+
"learning_rate": 5e-05,
|
| 5413 |
+
"loss": 2.018282890319824,
|
| 5414 |
+
"step": 1544
|
| 5415 |
+
},
|
| 5416 |
+
{
|
| 5417 |
+
"epoch": 0.5390797984552888,
|
| 5418 |
+
"grad_norm": 0.28046560287475586,
|
| 5419 |
+
"learning_rate": 5e-05,
|
| 5420 |
+
"loss": 1.7114261388778687,
|
| 5421 |
+
"step": 1546
|
| 5422 |
+
},
|
| 5423 |
+
{
|
| 5424 |
+
"epoch": 0.5397771849992155,
|
| 5425 |
+
"grad_norm": 0.24298356473445892,
|
| 5426 |
+
"learning_rate": 5e-05,
|
| 5427 |
+
"loss": 2.050609588623047,
|
| 5428 |
+
"step": 1548
|
| 5429 |
+
},
|
| 5430 |
+
{
|
| 5431 |
+
"epoch": 0.540474571543142,
|
| 5432 |
+
"grad_norm": 0.18314428627490997,
|
| 5433 |
+
"learning_rate": 5e-05,
|
| 5434 |
+
"loss": 2.1509413719177246,
|
| 5435 |
+
"step": 1550
|
| 5436 |
+
},
|
| 5437 |
+
{
|
| 5438 |
+
"epoch": 0.5411719580870687,
|
| 5439 |
+
"grad_norm": 0.24424991011619568,
|
| 5440 |
+
"learning_rate": 5e-05,
|
| 5441 |
+
"loss": 1.9574331045150757,
|
| 5442 |
+
"step": 1552
|
| 5443 |
+
},
|
| 5444 |
+
{
|
| 5445 |
+
"epoch": 0.5418693446309953,
|
| 5446 |
+
"grad_norm": 0.20439790189266205,
|
| 5447 |
+
"learning_rate": 5e-05,
|
| 5448 |
+
"loss": 1.9486185312271118,
|
| 5449 |
+
"step": 1554
|
| 5450 |
+
},
|
| 5451 |
+
{
|
| 5452 |
+
"epoch": 0.5425667311749219,
|
| 5453 |
+
"grad_norm": 0.18379662930965424,
|
| 5454 |
+
"learning_rate": 5e-05,
|
| 5455 |
+
"loss": 1.8366260528564453,
|
| 5456 |
+
"step": 1556
|
| 5457 |
+
},
|
| 5458 |
+
{
|
| 5459 |
+
"epoch": 0.5432641177188486,
|
| 5460 |
+
"grad_norm": 0.2572096884250641,
|
| 5461 |
+
"learning_rate": 5e-05,
|
| 5462 |
+
"loss": 1.8434381484985352,
|
| 5463 |
+
"step": 1558
|
| 5464 |
+
},
|
| 5465 |
+
{
|
| 5466 |
+
"epoch": 0.5439615042627752,
|
| 5467 |
+
"grad_norm": 0.2464679777622223,
|
| 5468 |
+
"learning_rate": 5e-05,
|
| 5469 |
+
"loss": 1.802624225616455,
|
| 5470 |
+
"step": 1560
|
| 5471 |
+
},
|
| 5472 |
+
{
|
| 5473 |
+
"epoch": 0.5446588908067019,
|
| 5474 |
+
"grad_norm": 0.17593611776828766,
|
| 5475 |
+
"learning_rate": 5e-05,
|
| 5476 |
+
"loss": 1.893507480621338,
|
| 5477 |
+
"step": 1562
|
| 5478 |
+
},
|
| 5479 |
+
{
|
| 5480 |
+
"epoch": 0.5453562773506285,
|
| 5481 |
+
"grad_norm": 0.320984423160553,
|
| 5482 |
+
"learning_rate": 5e-05,
|
| 5483 |
+
"loss": 1.7396756410598755,
|
| 5484 |
+
"step": 1564
|
| 5485 |
+
},
|
| 5486 |
+
{
|
| 5487 |
+
"epoch": 0.5460536638945551,
|
| 5488 |
+
"grad_norm": 0.23846492171287537,
|
| 5489 |
+
"learning_rate": 5e-05,
|
| 5490 |
+
"loss": 1.8965473175048828,
|
| 5491 |
+
"step": 1566
|
| 5492 |
+
},
|
| 5493 |
+
{
|
| 5494 |
+
"epoch": 0.5467510504384818,
|
| 5495 |
+
"grad_norm": 0.1506342887878418,
|
| 5496 |
+
"learning_rate": 5e-05,
|
| 5497 |
+
"loss": 1.9256426095962524,
|
| 5498 |
+
"step": 1568
|
| 5499 |
+
},
|
| 5500 |
+
{
|
| 5501 |
+
"epoch": 0.5474484369824084,
|
| 5502 |
+
"grad_norm": 0.17887084186077118,
|
| 5503 |
+
"learning_rate": 5e-05,
|
| 5504 |
+
"loss": 2.072817802429199,
|
| 5505 |
+
"step": 1570
|
| 5506 |
+
},
|
| 5507 |
+
{
|
| 5508 |
+
"epoch": 0.548145823526335,
|
| 5509 |
+
"grad_norm": 0.20621606707572937,
|
| 5510 |
+
"learning_rate": 5e-05,
|
| 5511 |
+
"loss": 1.6939451694488525,
|
| 5512 |
+
"step": 1572
|
| 5513 |
+
},
|
| 5514 |
+
{
|
| 5515 |
+
"epoch": 0.5488432100702617,
|
| 5516 |
+
"grad_norm": 0.27097389101982117,
|
| 5517 |
+
"learning_rate": 5e-05,
|
| 5518 |
+
"loss": 1.9146214723587036,
|
| 5519 |
+
"step": 1574
|
| 5520 |
+
},
|
| 5521 |
+
{
|
| 5522 |
+
"epoch": 0.5495405966141883,
|
| 5523 |
+
"grad_norm": 0.16874749958515167,
|
| 5524 |
+
"learning_rate": 5e-05,
|
| 5525 |
+
"loss": 2.0716683864593506,
|
| 5526 |
+
"step": 1576
|
| 5527 |
+
},
|
| 5528 |
+
{
|
| 5529 |
+
"epoch": 0.550237983158115,
|
| 5530 |
+
"grad_norm": 0.200093075633049,
|
| 5531 |
+
"learning_rate": 5e-05,
|
| 5532 |
+
"loss": 1.9811136722564697,
|
| 5533 |
+
"step": 1578
|
| 5534 |
+
},
|
| 5535 |
+
{
|
| 5536 |
+
"epoch": 0.5509353697020416,
|
| 5537 |
+
"grad_norm": 0.2207585871219635,
|
| 5538 |
+
"learning_rate": 5e-05,
|
| 5539 |
+
"loss": 1.954552173614502,
|
| 5540 |
+
"step": 1580
|
| 5541 |
+
},
|
| 5542 |
+
{
|
| 5543 |
+
"epoch": 0.5516327562459682,
|
| 5544 |
+
"grad_norm": 0.2329169660806656,
|
| 5545 |
+
"learning_rate": 5e-05,
|
| 5546 |
+
"loss": 2.050635576248169,
|
| 5547 |
+
"step": 1582
|
| 5548 |
+
},
|
| 5549 |
+
{
|
| 5550 |
+
"epoch": 0.5523301427898949,
|
| 5551 |
+
"grad_norm": 0.21007491648197174,
|
| 5552 |
+
"learning_rate": 5e-05,
|
| 5553 |
+
"loss": 1.982131004333496,
|
| 5554 |
+
"step": 1584
|
| 5555 |
+
},
|
| 5556 |
+
{
|
| 5557 |
+
"epoch": 0.5530275293338215,
|
| 5558 |
+
"grad_norm": 0.15652252733707428,
|
| 5559 |
+
"learning_rate": 5e-05,
|
| 5560 |
+
"loss": 1.9359612464904785,
|
| 5561 |
+
"step": 1586
|
| 5562 |
+
},
|
| 5563 |
+
{
|
| 5564 |
+
"epoch": 0.5537249158777482,
|
| 5565 |
+
"grad_norm": 0.21786396205425262,
|
| 5566 |
+
"learning_rate": 5e-05,
|
| 5567 |
+
"loss": 1.7455949783325195,
|
| 5568 |
+
"step": 1588
|
| 5569 |
+
},
|
| 5570 |
+
{
|
| 5571 |
+
"epoch": 0.5544223024216748,
|
| 5572 |
+
"grad_norm": 0.20270538330078125,
|
| 5573 |
+
"learning_rate": 5e-05,
|
| 5574 |
+
"loss": 1.8889861106872559,
|
| 5575 |
+
"step": 1590
|
| 5576 |
+
},
|
| 5577 |
+
{
|
| 5578 |
+
"epoch": 0.5551196889656014,
|
| 5579 |
+
"grad_norm": 0.26479393243789673,
|
| 5580 |
+
"learning_rate": 5e-05,
|
| 5581 |
+
"loss": 1.8715715408325195,
|
| 5582 |
+
"step": 1592
|
| 5583 |
+
},
|
| 5584 |
+
{
|
| 5585 |
+
"epoch": 0.5558170755095281,
|
| 5586 |
+
"grad_norm": 0.25771623849868774,
|
| 5587 |
+
"learning_rate": 5e-05,
|
| 5588 |
+
"loss": 1.8482694625854492,
|
| 5589 |
+
"step": 1594
|
| 5590 |
+
},
|
| 5591 |
+
{
|
| 5592 |
+
"epoch": 0.5565144620534547,
|
| 5593 |
+
"grad_norm": 0.210859015583992,
|
| 5594 |
+
"learning_rate": 5e-05,
|
| 5595 |
+
"loss": 1.9231295585632324,
|
| 5596 |
+
"step": 1596
|
| 5597 |
+
},
|
| 5598 |
+
{
|
| 5599 |
+
"epoch": 0.5572118485973813,
|
| 5600 |
+
"grad_norm": 0.2072077989578247,
|
| 5601 |
+
"learning_rate": 5e-05,
|
| 5602 |
+
"loss": 1.7906043529510498,
|
| 5603 |
+
"step": 1598
|
| 5604 |
+
},
|
| 5605 |
+
{
|
| 5606 |
+
"epoch": 0.557909235141308,
|
| 5607 |
+
"grad_norm": 0.29259616136550903,
|
| 5608 |
+
"learning_rate": 5e-05,
|
| 5609 |
+
"loss": 1.9715745449066162,
|
| 5610 |
+
"step": 1600
|
| 5611 |
+
},
|
| 5612 |
+
{
|
| 5613 |
+
"epoch": 0.5586066216852346,
|
| 5614 |
+
"grad_norm": 0.24774612486362457,
|
| 5615 |
+
"learning_rate": 5e-05,
|
| 5616 |
+
"loss": 2.081681728363037,
|
| 5617 |
+
"step": 1602
|
| 5618 |
+
},
|
| 5619 |
+
{
|
| 5620 |
+
"epoch": 0.5593040082291613,
|
| 5621 |
+
"grad_norm": 0.24854712188243866,
|
| 5622 |
+
"learning_rate": 5e-05,
|
| 5623 |
+
"loss": 1.833552598953247,
|
| 5624 |
+
"step": 1604
|
| 5625 |
+
},
|
| 5626 |
+
{
|
| 5627 |
+
"epoch": 0.5600013947730879,
|
| 5628 |
+
"grad_norm": 0.2399366796016693,
|
| 5629 |
+
"learning_rate": 5e-05,
|
| 5630 |
+
"loss": 2.124068021774292,
|
| 5631 |
+
"step": 1606
|
| 5632 |
+
},
|
| 5633 |
+
{
|
| 5634 |
+
"epoch": 0.5606987813170144,
|
| 5635 |
+
"grad_norm": 0.18966670334339142,
|
| 5636 |
+
"learning_rate": 5e-05,
|
| 5637 |
+
"loss": 1.7892274856567383,
|
| 5638 |
+
"step": 1608
|
| 5639 |
+
},
|
| 5640 |
+
{
|
| 5641 |
+
"epoch": 0.5613961678609412,
|
| 5642 |
+
"grad_norm": 0.23364785313606262,
|
| 5643 |
+
"learning_rate": 5e-05,
|
| 5644 |
+
"loss": 1.8081241846084595,
|
| 5645 |
+
"step": 1610
|
| 5646 |
+
},
|
| 5647 |
+
{
|
| 5648 |
+
"epoch": 0.5620935544048677,
|
| 5649 |
+
"grad_norm": 0.18954408168792725,
|
| 5650 |
+
"learning_rate": 5e-05,
|
| 5651 |
+
"loss": 2.034299373626709,
|
| 5652 |
+
"step": 1612
|
| 5653 |
+
},
|
| 5654 |
+
{
|
| 5655 |
+
"epoch": 0.5627909409487943,
|
| 5656 |
+
"grad_norm": 0.1632585972547531,
|
| 5657 |
+
"learning_rate": 5e-05,
|
| 5658 |
+
"loss": 1.9397029876708984,
|
| 5659 |
+
"step": 1614
|
| 5660 |
+
},
|
| 5661 |
+
{
|
| 5662 |
+
"epoch": 0.563488327492721,
|
| 5663 |
+
"grad_norm": 0.2352249175310135,
|
| 5664 |
+
"learning_rate": 5e-05,
|
| 5665 |
+
"loss": 1.9451236724853516,
|
| 5666 |
+
"step": 1616
|
| 5667 |
+
},
|
| 5668 |
+
{
|
| 5669 |
+
"epoch": 0.5641857140366476,
|
| 5670 |
+
"grad_norm": 0.2975192070007324,
|
| 5671 |
+
"learning_rate": 5e-05,
|
| 5672 |
+
"loss": 1.8692302703857422,
|
| 5673 |
+
"step": 1618
|
| 5674 |
+
},
|
| 5675 |
+
{
|
| 5676 |
+
"epoch": 0.5648831005805743,
|
| 5677 |
+
"grad_norm": 0.25654807686805725,
|
| 5678 |
+
"learning_rate": 5e-05,
|
| 5679 |
+
"loss": 1.9424086809158325,
|
| 5680 |
+
"step": 1620
|
| 5681 |
+
},
|
| 5682 |
+
{
|
| 5683 |
+
"epoch": 0.5655804871245009,
|
| 5684 |
+
"grad_norm": 0.2531231641769409,
|
| 5685 |
+
"learning_rate": 5e-05,
|
| 5686 |
+
"loss": 2.043811082839966,
|
| 5687 |
+
"step": 1622
|
| 5688 |
+
},
|
| 5689 |
+
{
|
| 5690 |
+
"epoch": 0.5662778736684275,
|
| 5691 |
+
"grad_norm": 0.189333975315094,
|
| 5692 |
+
"learning_rate": 5e-05,
|
| 5693 |
+
"loss": 1.906083345413208,
|
| 5694 |
+
"step": 1624
|
| 5695 |
+
},
|
| 5696 |
+
{
|
| 5697 |
+
"epoch": 0.5669752602123542,
|
| 5698 |
+
"grad_norm": 0.2502206861972809,
|
| 5699 |
+
"learning_rate": 5e-05,
|
| 5700 |
+
"loss": 2.0286500453948975,
|
| 5701 |
+
"step": 1626
|
| 5702 |
+
},
|
| 5703 |
+
{
|
| 5704 |
+
"epoch": 0.5676726467562808,
|
| 5705 |
+
"grad_norm": 0.19187211990356445,
|
| 5706 |
+
"learning_rate": 5e-05,
|
| 5707 |
+
"loss": 1.9105477333068848,
|
| 5708 |
+
"step": 1628
|
| 5709 |
+
},
|
| 5710 |
+
{
|
| 5711 |
+
"epoch": 0.5683700333002075,
|
| 5712 |
+
"grad_norm": 0.19181573390960693,
|
| 5713 |
+
"learning_rate": 5e-05,
|
| 5714 |
+
"loss": 1.9919695854187012,
|
| 5715 |
+
"step": 1630
|
| 5716 |
+
},
|
| 5717 |
+
{
|
| 5718 |
+
"epoch": 0.5690674198441341,
|
| 5719 |
+
"grad_norm": 0.25628000497817993,
|
| 5720 |
+
"learning_rate": 5e-05,
|
| 5721 |
+
"loss": 1.9693403244018555,
|
| 5722 |
+
"step": 1632
|
| 5723 |
+
},
|
| 5724 |
+
{
|
| 5725 |
+
"epoch": 0.5697648063880607,
|
| 5726 |
+
"grad_norm": 0.29909878969192505,
|
| 5727 |
+
"learning_rate": 5e-05,
|
| 5728 |
+
"loss": 1.9884252548217773,
|
| 5729 |
+
"step": 1634
|
| 5730 |
+
},
|
| 5731 |
+
{
|
| 5732 |
+
"epoch": 0.5704621929319874,
|
| 5733 |
+
"grad_norm": 0.1668253093957901,
|
| 5734 |
+
"learning_rate": 5e-05,
|
| 5735 |
+
"loss": 1.8667051792144775,
|
| 5736 |
+
"step": 1636
|
| 5737 |
+
},
|
| 5738 |
+
{
|
| 5739 |
+
"epoch": 0.571159579475914,
|
| 5740 |
+
"grad_norm": 0.3491284251213074,
|
| 5741 |
+
"learning_rate": 5e-05,
|
| 5742 |
+
"loss": 1.781627893447876,
|
| 5743 |
+
"step": 1638
|
| 5744 |
+
},
|
| 5745 |
+
{
|
| 5746 |
+
"epoch": 0.5718569660198406,
|
| 5747 |
+
"grad_norm": 0.20913377404212952,
|
| 5748 |
+
"learning_rate": 5e-05,
|
| 5749 |
+
"loss": 2.139101505279541,
|
| 5750 |
+
"step": 1640
|
| 5751 |
+
},
|
| 5752 |
+
{
|
| 5753 |
+
"epoch": 0.5725543525637673,
|
| 5754 |
+
"grad_norm": 0.19669152796268463,
|
| 5755 |
+
"learning_rate": 5e-05,
|
| 5756 |
+
"loss": 1.9148974418640137,
|
| 5757 |
+
"step": 1642
|
| 5758 |
+
},
|
| 5759 |
+
{
|
| 5760 |
+
"epoch": 0.5732517391076939,
|
| 5761 |
+
"grad_norm": 0.3062213957309723,
|
| 5762 |
+
"learning_rate": 5e-05,
|
| 5763 |
+
"loss": 1.8412705659866333,
|
| 5764 |
+
"step": 1644
|
| 5765 |
+
},
|
| 5766 |
+
{
|
| 5767 |
+
"epoch": 0.5739491256516206,
|
| 5768 |
+
"grad_norm": 0.2283291071653366,
|
| 5769 |
+
"learning_rate": 5e-05,
|
| 5770 |
+
"loss": 1.8515138626098633,
|
| 5771 |
+
"step": 1646
|
| 5772 |
+
},
|
| 5773 |
+
{
|
| 5774 |
+
"epoch": 0.5746465121955472,
|
| 5775 |
+
"grad_norm": 0.25086915493011475,
|
| 5776 |
+
"learning_rate": 5e-05,
|
| 5777 |
+
"loss": 1.9342883825302124,
|
| 5778 |
+
"step": 1648
|
| 5779 |
+
},
|
| 5780 |
+
{
|
| 5781 |
+
"epoch": 0.5753438987394738,
|
| 5782 |
+
"grad_norm": 0.20395423471927643,
|
| 5783 |
+
"learning_rate": 5e-05,
|
| 5784 |
+
"loss": 2.053553819656372,
|
| 5785 |
+
"step": 1650
|
| 5786 |
+
},
|
| 5787 |
+
{
|
| 5788 |
+
"epoch": 0.5760412852834005,
|
| 5789 |
+
"grad_norm": 0.29043474793434143,
|
| 5790 |
+
"learning_rate": 5e-05,
|
| 5791 |
+
"loss": 1.9286761283874512,
|
| 5792 |
+
"step": 1652
|
| 5793 |
+
},
|
| 5794 |
+
{
|
| 5795 |
+
"epoch": 0.5767386718273271,
|
| 5796 |
+
"grad_norm": 0.3165014982223511,
|
| 5797 |
+
"learning_rate": 5e-05,
|
| 5798 |
+
"loss": 1.993572473526001,
|
| 5799 |
+
"step": 1654
|
| 5800 |
+
},
|
| 5801 |
+
{
|
| 5802 |
+
"epoch": 0.5774360583712538,
|
| 5803 |
+
"grad_norm": 0.3387148082256317,
|
| 5804 |
+
"learning_rate": 5e-05,
|
| 5805 |
+
"loss": 1.8471314907073975,
|
| 5806 |
+
"step": 1656
|
| 5807 |
+
},
|
| 5808 |
+
{
|
| 5809 |
+
"epoch": 0.5781334449151804,
|
| 5810 |
+
"grad_norm": 0.2811840772628784,
|
| 5811 |
+
"learning_rate": 5e-05,
|
| 5812 |
+
"loss": 1.8386205434799194,
|
| 5813 |
+
"step": 1658
|
| 5814 |
+
},
|
| 5815 |
+
{
|
| 5816 |
+
"epoch": 0.578830831459107,
|
| 5817 |
+
"grad_norm": 0.22342753410339355,
|
| 5818 |
+
"learning_rate": 5e-05,
|
| 5819 |
+
"loss": 2.005929470062256,
|
| 5820 |
+
"step": 1660
|
| 5821 |
+
},
|
| 5822 |
+
{
|
| 5823 |
+
"epoch": 0.5795282180030337,
|
| 5824 |
+
"grad_norm": 0.25924915075302124,
|
| 5825 |
+
"learning_rate": 5e-05,
|
| 5826 |
+
"loss": 1.7976369857788086,
|
| 5827 |
+
"step": 1662
|
| 5828 |
+
},
|
| 5829 |
+
{
|
| 5830 |
+
"epoch": 0.5802256045469603,
|
| 5831 |
+
"grad_norm": 0.24489231407642365,
|
| 5832 |
+
"learning_rate": 5e-05,
|
| 5833 |
+
"loss": 1.8548369407653809,
|
| 5834 |
+
"step": 1664
|
| 5835 |
+
},
|
| 5836 |
+
{
|
| 5837 |
+
"epoch": 0.5809229910908869,
|
| 5838 |
+
"grad_norm": 0.20547856390476227,
|
| 5839 |
+
"learning_rate": 5e-05,
|
| 5840 |
+
"loss": 1.8978731632232666,
|
| 5841 |
+
"step": 1666
|
| 5842 |
+
},
|
| 5843 |
+
{
|
| 5844 |
+
"epoch": 0.5816203776348136,
|
| 5845 |
+
"grad_norm": 0.4370429515838623,
|
| 5846 |
+
"learning_rate": 5e-05,
|
| 5847 |
+
"loss": 1.8970003128051758,
|
| 5848 |
+
"step": 1668
|
| 5849 |
+
},
|
| 5850 |
+
{
|
| 5851 |
+
"epoch": 0.5823177641787401,
|
| 5852 |
+
"grad_norm": 0.1849474310874939,
|
| 5853 |
+
"learning_rate": 5e-05,
|
| 5854 |
+
"loss": 2.0585944652557373,
|
| 5855 |
+
"step": 1670
|
| 5856 |
+
},
|
| 5857 |
+
{
|
| 5858 |
+
"epoch": 0.5830151507226669,
|
| 5859 |
+
"grad_norm": 0.19704462587833405,
|
| 5860 |
+
"learning_rate": 5e-05,
|
| 5861 |
+
"loss": 1.732386827468872,
|
| 5862 |
+
"step": 1672
|
| 5863 |
+
},
|
| 5864 |
+
{
|
| 5865 |
+
"epoch": 0.5837125372665934,
|
| 5866 |
+
"grad_norm": 0.43086493015289307,
|
| 5867 |
+
"learning_rate": 5e-05,
|
| 5868 |
+
"loss": 1.7718791961669922,
|
| 5869 |
+
"step": 1674
|
| 5870 |
+
},
|
| 5871 |
+
{
|
| 5872 |
+
"epoch": 0.58440992381052,
|
| 5873 |
+
"grad_norm": 0.20836947858333588,
|
| 5874 |
+
"learning_rate": 5e-05,
|
| 5875 |
+
"loss": 2.006824016571045,
|
| 5876 |
+
"step": 1676
|
| 5877 |
+
},
|
| 5878 |
+
{
|
| 5879 |
+
"epoch": 0.5851073103544467,
|
| 5880 |
+
"grad_norm": 0.2442089021205902,
|
| 5881 |
+
"learning_rate": 5e-05,
|
| 5882 |
+
"loss": 2.077127456665039,
|
| 5883 |
+
"step": 1678
|
| 5884 |
+
},
|
| 5885 |
+
{
|
| 5886 |
+
"epoch": 0.5858046968983733,
|
| 5887 |
+
"grad_norm": 0.22404621541500092,
|
| 5888 |
+
"learning_rate": 5e-05,
|
| 5889 |
+
"loss": 2.043806552886963,
|
| 5890 |
+
"step": 1680
|
| 5891 |
+
},
|
| 5892 |
+
{
|
| 5893 |
+
"epoch": 0.5865020834422999,
|
| 5894 |
+
"grad_norm": 0.21961356699466705,
|
| 5895 |
+
"learning_rate": 5e-05,
|
| 5896 |
+
"loss": 1.772026777267456,
|
| 5897 |
+
"step": 1682
|
| 5898 |
+
},
|
| 5899 |
+
{
|
| 5900 |
+
"epoch": 0.5871994699862266,
|
| 5901 |
+
"grad_norm": 0.3041599690914154,
|
| 5902 |
+
"learning_rate": 5e-05,
|
| 5903 |
+
"loss": 1.7471873760223389,
|
| 5904 |
+
"step": 1684
|
| 5905 |
+
},
|
| 5906 |
+
{
|
| 5907 |
+
"epoch": 0.5878968565301532,
|
| 5908 |
+
"grad_norm": 0.2028559297323227,
|
| 5909 |
+
"learning_rate": 5e-05,
|
| 5910 |
+
"loss": 1.827317476272583,
|
| 5911 |
+
"step": 1686
|
| 5912 |
+
},
|
| 5913 |
+
{
|
| 5914 |
+
"epoch": 0.5885942430740799,
|
| 5915 |
+
"grad_norm": 0.20505206286907196,
|
| 5916 |
+
"learning_rate": 5e-05,
|
| 5917 |
+
"loss": 1.9476141929626465,
|
| 5918 |
+
"step": 1688
|
| 5919 |
+
},
|
| 5920 |
+
{
|
| 5921 |
+
"epoch": 0.5892916296180065,
|
| 5922 |
+
"grad_norm": 0.23087021708488464,
|
| 5923 |
+
"learning_rate": 5e-05,
|
| 5924 |
+
"loss": 2.1552538871765137,
|
| 5925 |
+
"step": 1690
|
| 5926 |
+
},
|
| 5927 |
+
{
|
| 5928 |
+
"epoch": 0.5899890161619331,
|
| 5929 |
+
"grad_norm": 0.15803898870944977,
|
| 5930 |
+
"learning_rate": 5e-05,
|
| 5931 |
+
"loss": 2.1053948402404785,
|
| 5932 |
+
"step": 1692
|
| 5933 |
+
},
|
| 5934 |
+
{
|
| 5935 |
+
"epoch": 0.5906864027058598,
|
| 5936 |
+
"grad_norm": 0.21020828187465668,
|
| 5937 |
+
"learning_rate": 5e-05,
|
| 5938 |
+
"loss": 2.0307366847991943,
|
| 5939 |
+
"step": 1694
|
| 5940 |
+
},
|
| 5941 |
+
{
|
| 5942 |
+
"epoch": 0.5913837892497864,
|
| 5943 |
+
"grad_norm": 0.1724986732006073,
|
| 5944 |
+
"learning_rate": 5e-05,
|
| 5945 |
+
"loss": 2.0489397048950195,
|
| 5946 |
+
"step": 1696
|
| 5947 |
+
},
|
| 5948 |
+
{
|
| 5949 |
+
"epoch": 0.5920811757937131,
|
| 5950 |
+
"grad_norm": 0.19490469992160797,
|
| 5951 |
+
"learning_rate": 5e-05,
|
| 5952 |
+
"loss": 1.923473834991455,
|
| 5953 |
+
"step": 1698
|
| 5954 |
+
},
|
| 5955 |
+
{
|
| 5956 |
+
"epoch": 0.5927785623376397,
|
| 5957 |
+
"grad_norm": 0.21006463468074799,
|
| 5958 |
+
"learning_rate": 5e-05,
|
| 5959 |
+
"loss": 2.0133984088897705,
|
| 5960 |
+
"step": 1700
|
| 5961 |
+
},
|
| 5962 |
+
{
|
| 5963 |
+
"epoch": 0.5934759488815663,
|
| 5964 |
+
"grad_norm": 0.3003818094730377,
|
| 5965 |
+
"learning_rate": 5e-05,
|
| 5966 |
+
"loss": 1.8472903966903687,
|
| 5967 |
+
"step": 1702
|
| 5968 |
+
},
|
| 5969 |
+
{
|
| 5970 |
+
"epoch": 0.594173335425493,
|
| 5971 |
+
"grad_norm": 0.1842869371175766,
|
| 5972 |
+
"learning_rate": 5e-05,
|
| 5973 |
+
"loss": 1.8047981262207031,
|
| 5974 |
+
"step": 1704
|
| 5975 |
+
},
|
| 5976 |
+
{
|
| 5977 |
+
"epoch": 0.5948707219694196,
|
| 5978 |
+
"grad_norm": 0.2461615949869156,
|
| 5979 |
+
"learning_rate": 5e-05,
|
| 5980 |
+
"loss": 2.078711986541748,
|
| 5981 |
+
"step": 1706
|
| 5982 |
+
},
|
| 5983 |
+
{
|
| 5984 |
+
"epoch": 0.5955681085133462,
|
| 5985 |
+
"grad_norm": 0.2864431142807007,
|
| 5986 |
+
"learning_rate": 5e-05,
|
| 5987 |
+
"loss": 1.946295976638794,
|
| 5988 |
+
"step": 1708
|
| 5989 |
+
},
|
| 5990 |
+
{
|
| 5991 |
+
"epoch": 0.5962654950572729,
|
| 5992 |
+
"grad_norm": 0.2841217517852783,
|
| 5993 |
+
"learning_rate": 5e-05,
|
| 5994 |
+
"loss": 1.9858349561691284,
|
| 5995 |
+
"step": 1710
|
| 5996 |
+
},
|
| 5997 |
+
{
|
| 5998 |
+
"epoch": 0.5969628816011995,
|
| 5999 |
+
"grad_norm": 0.19433815777301788,
|
| 6000 |
+
"learning_rate": 5e-05,
|
| 6001 |
+
"loss": 1.826880931854248,
|
| 6002 |
+
"step": 1712
|
| 6003 |
+
},
|
| 6004 |
+
{
|
| 6005 |
+
"epoch": 0.5976602681451262,
|
| 6006 |
+
"grad_norm": 0.22107480466365814,
|
| 6007 |
+
"learning_rate": 5e-05,
|
| 6008 |
+
"loss": 1.8655105829238892,
|
| 6009 |
+
"step": 1714
|
| 6010 |
+
},
|
| 6011 |
+
{
|
| 6012 |
+
"epoch": 0.5983576546890528,
|
| 6013 |
+
"grad_norm": 0.28393471240997314,
|
| 6014 |
+
"learning_rate": 5e-05,
|
| 6015 |
+
"loss": 1.908822774887085,
|
| 6016 |
+
"step": 1716
|
| 6017 |
+
},
|
| 6018 |
+
{
|
| 6019 |
+
"epoch": 0.5990550412329794,
|
| 6020 |
+
"grad_norm": 0.2021571695804596,
|
| 6021 |
+
"learning_rate": 5e-05,
|
| 6022 |
+
"loss": 1.929540753364563,
|
| 6023 |
+
"step": 1718
|
| 6024 |
+
},
|
| 6025 |
+
{
|
| 6026 |
+
"epoch": 0.5997524277769061,
|
| 6027 |
+
"grad_norm": 0.23796068131923676,
|
| 6028 |
+
"learning_rate": 5e-05,
|
| 6029 |
+
"loss": 2.007427930831909,
|
| 6030 |
+
"step": 1720
|
| 6031 |
+
},
|
| 6032 |
+
{
|
| 6033 |
+
"epoch": 0.6004498143208327,
|
| 6034 |
+
"grad_norm": 0.24815872311592102,
|
| 6035 |
+
"learning_rate": 5e-05,
|
| 6036 |
+
"loss": 1.9182190895080566,
|
| 6037 |
+
"step": 1722
|
| 6038 |
}
|
| 6039 |
],
|
| 6040 |
"logging_steps": 2,
|
|
|
|
| 6054 |
"attributes": {}
|
| 6055 |
}
|
| 6056 |
},
|
| 6057 |
+
"total_flos": 3.070517930434232e+17,
|
| 6058 |
"train_batch_size": 1,
|
| 6059 |
"trial_name": null,
|
| 6060 |
"trial_params": null
|