Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
unsloth
sft
conversational
text-generation-inference
Instructions to use Ba2han/test_CPTlsft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/test_CPTlsft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/test_CPTlsft") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/test_CPTlsft") model = AutoModelForCausalLM.from_pretrained("Ba2han/test_CPTlsft", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/test_CPTlsft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/test_CPTlsft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/test_CPTlsft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ba2han/test_CPTlsft
- SGLang
How to use Ba2han/test_CPTlsft with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Ba2han/test_CPTlsft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/test_CPTlsft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Ba2han/test_CPTlsft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/test_CPTlsft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use Ba2han/test_CPTlsft with Docker Model Runner:
docker model run hf.co/Ba2han/test_CPTlsft
Training in progress, step 1539, 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 sha256:6843ebcba159bceff3462b77bb5b00c74c3e1041350735aee90c56e152ebcb3b
|
| 3 |
size 2934397032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1470445304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:110b781cc920cb5dc837b9cd1d333d735cf145ef9f035f9ca5ef930955ccf135
|
| 3 |
size 1470445304
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9785
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4f5e58dccad6cf335c4821881dead95a48123f4a18db94a4f3072ebc8d772de
|
| 3 |
size 9785
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 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,
|
|
@@ -3599,6 +3599,1798 @@
|
|
| 3599 |
"learning_rate": 0.0005,
|
| 3600 |
"loss": 2.6337666511535645,
|
| 3601 |
"step": 1026
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3602 |
}
|
| 3603 |
],
|
| 3604 |
"logging_steps": 2,
|
|
@@ -3618,7 +5410,7 @@
|
|
| 3618 |
"attributes": {}
|
| 3619 |
}
|
| 3620 |
},
|
| 3621 |
-
"total_flos":
|
| 3622 |
"train_batch_size": 6,
|
| 3623 |
"trial_name": null,
|
| 3624 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.300336634629458,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1539,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3599 |
"learning_rate": 0.0005,
|
| 3600 |
"loss": 2.6337666511535645,
|
| 3601 |
"step": 1026
|
| 3602 |
+
},
|
| 3603 |
+
{
|
| 3604 |
+
"epoch": 0.20061472410596673,
|
| 3605 |
+
"grad_norm": 0.15413911640644073,
|
| 3606 |
+
"learning_rate": 0.0005,
|
| 3607 |
+
"loss": 2.666532516479492,
|
| 3608 |
+
"step": 1028
|
| 3609 |
+
},
|
| 3610 |
+
{
|
| 3611 |
+
"epoch": 0.20100502512562815,
|
| 3612 |
+
"grad_norm": 0.1885204315185547,
|
| 3613 |
+
"learning_rate": 0.0005,
|
| 3614 |
+
"loss": 2.6927287578582764,
|
| 3615 |
+
"step": 1030
|
| 3616 |
+
},
|
| 3617 |
+
{
|
| 3618 |
+
"epoch": 0.20139532614528954,
|
| 3619 |
+
"grad_norm": 0.16068106889724731,
|
| 3620 |
+
"learning_rate": 0.0005,
|
| 3621 |
+
"loss": 2.682682514190674,
|
| 3622 |
+
"step": 1032
|
| 3623 |
+
},
|
| 3624 |
+
{
|
| 3625 |
+
"epoch": 0.20178562716495096,
|
| 3626 |
+
"grad_norm": 0.14346016943454742,
|
| 3627 |
+
"learning_rate": 0.0005,
|
| 3628 |
+
"loss": 2.68516206741333,
|
| 3629 |
+
"step": 1034
|
| 3630 |
+
},
|
| 3631 |
+
{
|
| 3632 |
+
"epoch": 0.20217592818461239,
|
| 3633 |
+
"grad_norm": 0.16281655430793762,
|
| 3634 |
+
"learning_rate": 0.0005,
|
| 3635 |
+
"loss": 2.6431190967559814,
|
| 3636 |
+
"step": 1036
|
| 3637 |
+
},
|
| 3638 |
+
{
|
| 3639 |
+
"epoch": 0.2025662292042738,
|
| 3640 |
+
"grad_norm": 0.20559871196746826,
|
| 3641 |
+
"learning_rate": 0.0005,
|
| 3642 |
+
"loss": 2.669055461883545,
|
| 3643 |
+
"step": 1038
|
| 3644 |
+
},
|
| 3645 |
+
{
|
| 3646 |
+
"epoch": 0.2029565302239352,
|
| 3647 |
+
"grad_norm": 0.15205328166484833,
|
| 3648 |
+
"learning_rate": 0.0005,
|
| 3649 |
+
"loss": 2.669562816619873,
|
| 3650 |
+
"step": 1040
|
| 3651 |
+
},
|
| 3652 |
+
{
|
| 3653 |
+
"epoch": 0.20334683124359662,
|
| 3654 |
+
"grad_norm": 0.18271148204803467,
|
| 3655 |
+
"learning_rate": 0.0005,
|
| 3656 |
+
"loss": 2.6906628608703613,
|
| 3657 |
+
"step": 1042
|
| 3658 |
+
},
|
| 3659 |
+
{
|
| 3660 |
+
"epoch": 0.20373713226325804,
|
| 3661 |
+
"grad_norm": 0.1715717762708664,
|
| 3662 |
+
"learning_rate": 0.0005,
|
| 3663 |
+
"loss": 2.6792192459106445,
|
| 3664 |
+
"step": 1044
|
| 3665 |
+
},
|
| 3666 |
+
{
|
| 3667 |
+
"epoch": 0.20412743328291946,
|
| 3668 |
+
"grad_norm": 0.15332698822021484,
|
| 3669 |
+
"learning_rate": 0.0005,
|
| 3670 |
+
"loss": 2.6867852210998535,
|
| 3671 |
+
"step": 1046
|
| 3672 |
+
},
|
| 3673 |
+
{
|
| 3674 |
+
"epoch": 0.20451773430258086,
|
| 3675 |
+
"grad_norm": 0.20917820930480957,
|
| 3676 |
+
"learning_rate": 0.0005,
|
| 3677 |
+
"loss": 2.6028738021850586,
|
| 3678 |
+
"step": 1048
|
| 3679 |
+
},
|
| 3680 |
+
{
|
| 3681 |
+
"epoch": 0.20490803532224228,
|
| 3682 |
+
"grad_norm": 0.1485522985458374,
|
| 3683 |
+
"learning_rate": 0.0005,
|
| 3684 |
+
"loss": 2.644742727279663,
|
| 3685 |
+
"step": 1050
|
| 3686 |
+
},
|
| 3687 |
+
{
|
| 3688 |
+
"epoch": 0.2052983363419037,
|
| 3689 |
+
"grad_norm": 0.1759510487318039,
|
| 3690 |
+
"learning_rate": 0.0005,
|
| 3691 |
+
"loss": 2.6617188453674316,
|
| 3692 |
+
"step": 1052
|
| 3693 |
+
},
|
| 3694 |
+
{
|
| 3695 |
+
"epoch": 0.20568863736156512,
|
| 3696 |
+
"grad_norm": 0.1497969776391983,
|
| 3697 |
+
"learning_rate": 0.0005,
|
| 3698 |
+
"loss": 2.690092086791992,
|
| 3699 |
+
"step": 1054
|
| 3700 |
+
},
|
| 3701 |
+
{
|
| 3702 |
+
"epoch": 0.2060789383812265,
|
| 3703 |
+
"grad_norm": 0.21129240095615387,
|
| 3704 |
+
"learning_rate": 0.0005,
|
| 3705 |
+
"loss": 2.696669578552246,
|
| 3706 |
+
"step": 1056
|
| 3707 |
+
},
|
| 3708 |
+
{
|
| 3709 |
+
"epoch": 0.20646923940088793,
|
| 3710 |
+
"grad_norm": 0.228876993060112,
|
| 3711 |
+
"learning_rate": 0.0005,
|
| 3712 |
+
"loss": 2.668633460998535,
|
| 3713 |
+
"step": 1058
|
| 3714 |
+
},
|
| 3715 |
+
{
|
| 3716 |
+
"epoch": 0.20685954042054935,
|
| 3717 |
+
"grad_norm": 0.16937199234962463,
|
| 3718 |
+
"learning_rate": 0.0005,
|
| 3719 |
+
"loss": 2.6425414085388184,
|
| 3720 |
+
"step": 1060
|
| 3721 |
+
},
|
| 3722 |
+
{
|
| 3723 |
+
"epoch": 0.20724984144021077,
|
| 3724 |
+
"grad_norm": 0.18065789341926575,
|
| 3725 |
+
"learning_rate": 0.0005,
|
| 3726 |
+
"loss": 2.6803669929504395,
|
| 3727 |
+
"step": 1062
|
| 3728 |
+
},
|
| 3729 |
+
{
|
| 3730 |
+
"epoch": 0.20764014245987217,
|
| 3731 |
+
"grad_norm": 0.24902886152267456,
|
| 3732 |
+
"learning_rate": 0.0005,
|
| 3733 |
+
"loss": 2.7086315155029297,
|
| 3734 |
+
"step": 1064
|
| 3735 |
+
},
|
| 3736 |
+
{
|
| 3737 |
+
"epoch": 0.2080304434795336,
|
| 3738 |
+
"grad_norm": 0.1729092299938202,
|
| 3739 |
+
"learning_rate": 0.0005,
|
| 3740 |
+
"loss": 2.695955276489258,
|
| 3741 |
+
"step": 1066
|
| 3742 |
+
},
|
| 3743 |
+
{
|
| 3744 |
+
"epoch": 0.208420744499195,
|
| 3745 |
+
"grad_norm": 0.17853398621082306,
|
| 3746 |
+
"learning_rate": 0.0005,
|
| 3747 |
+
"loss": 2.6311264038085938,
|
| 3748 |
+
"step": 1068
|
| 3749 |
+
},
|
| 3750 |
+
{
|
| 3751 |
+
"epoch": 0.20881104551885643,
|
| 3752 |
+
"grad_norm": 0.13389447331428528,
|
| 3753 |
+
"learning_rate": 0.0005,
|
| 3754 |
+
"loss": 2.684253692626953,
|
| 3755 |
+
"step": 1070
|
| 3756 |
+
},
|
| 3757 |
+
{
|
| 3758 |
+
"epoch": 0.20920134653851782,
|
| 3759 |
+
"grad_norm": 0.19843445718288422,
|
| 3760 |
+
"learning_rate": 0.0005,
|
| 3761 |
+
"loss": 2.628352403640747,
|
| 3762 |
+
"step": 1072
|
| 3763 |
+
},
|
| 3764 |
+
{
|
| 3765 |
+
"epoch": 0.20959164755817924,
|
| 3766 |
+
"grad_norm": 0.2287570685148239,
|
| 3767 |
+
"learning_rate": 0.0005,
|
| 3768 |
+
"loss": 2.6782217025756836,
|
| 3769 |
+
"step": 1074
|
| 3770 |
+
},
|
| 3771 |
+
{
|
| 3772 |
+
"epoch": 0.20998194857784067,
|
| 3773 |
+
"grad_norm": 0.16535478830337524,
|
| 3774 |
+
"learning_rate": 0.0005,
|
| 3775 |
+
"loss": 2.6419677734375,
|
| 3776 |
+
"step": 1076
|
| 3777 |
+
},
|
| 3778 |
+
{
|
| 3779 |
+
"epoch": 0.2103722495975021,
|
| 3780 |
+
"grad_norm": 0.1755470633506775,
|
| 3781 |
+
"learning_rate": 0.0005,
|
| 3782 |
+
"loss": 2.64323353767395,
|
| 3783 |
+
"step": 1078
|
| 3784 |
+
},
|
| 3785 |
+
{
|
| 3786 |
+
"epoch": 0.21076255061716348,
|
| 3787 |
+
"grad_norm": 0.15785405039787292,
|
| 3788 |
+
"learning_rate": 0.0005,
|
| 3789 |
+
"loss": 2.6617074012756348,
|
| 3790 |
+
"step": 1080
|
| 3791 |
+
},
|
| 3792 |
+
{
|
| 3793 |
+
"epoch": 0.2111528516368249,
|
| 3794 |
+
"grad_norm": 0.23155346512794495,
|
| 3795 |
+
"learning_rate": 0.0005,
|
| 3796 |
+
"loss": 2.6483330726623535,
|
| 3797 |
+
"step": 1082
|
| 3798 |
+
},
|
| 3799 |
+
{
|
| 3800 |
+
"epoch": 0.21154315265648632,
|
| 3801 |
+
"grad_norm": 0.15627813339233398,
|
| 3802 |
+
"learning_rate": 0.0005,
|
| 3803 |
+
"loss": 2.655099868774414,
|
| 3804 |
+
"step": 1084
|
| 3805 |
+
},
|
| 3806 |
+
{
|
| 3807 |
+
"epoch": 0.21193345367614774,
|
| 3808 |
+
"grad_norm": 0.1870599240064621,
|
| 3809 |
+
"learning_rate": 0.0005,
|
| 3810 |
+
"loss": 2.6291747093200684,
|
| 3811 |
+
"step": 1086
|
| 3812 |
+
},
|
| 3813 |
+
{
|
| 3814 |
+
"epoch": 0.21232375469580914,
|
| 3815 |
+
"grad_norm": 0.17650118470191956,
|
| 3816 |
+
"learning_rate": 0.0005,
|
| 3817 |
+
"loss": 2.6608781814575195,
|
| 3818 |
+
"step": 1088
|
| 3819 |
+
},
|
| 3820 |
+
{
|
| 3821 |
+
"epoch": 0.21271405571547056,
|
| 3822 |
+
"grad_norm": 0.19932429492473602,
|
| 3823 |
+
"learning_rate": 0.0005,
|
| 3824 |
+
"loss": 2.6752376556396484,
|
| 3825 |
+
"step": 1090
|
| 3826 |
+
},
|
| 3827 |
+
{
|
| 3828 |
+
"epoch": 0.21310435673513198,
|
| 3829 |
+
"grad_norm": 0.232453390955925,
|
| 3830 |
+
"learning_rate": 0.0005,
|
| 3831 |
+
"loss": 2.7143843173980713,
|
| 3832 |
+
"step": 1092
|
| 3833 |
+
},
|
| 3834 |
+
{
|
| 3835 |
+
"epoch": 0.21349465775479337,
|
| 3836 |
+
"grad_norm": 0.15866971015930176,
|
| 3837 |
+
"learning_rate": 0.0005,
|
| 3838 |
+
"loss": 2.6630475521087646,
|
| 3839 |
+
"step": 1094
|
| 3840 |
+
},
|
| 3841 |
+
{
|
| 3842 |
+
"epoch": 0.2138849587744548,
|
| 3843 |
+
"grad_norm": 0.16513587534427643,
|
| 3844 |
+
"learning_rate": 0.0005,
|
| 3845 |
+
"loss": 2.648599863052368,
|
| 3846 |
+
"step": 1096
|
| 3847 |
+
},
|
| 3848 |
+
{
|
| 3849 |
+
"epoch": 0.2142752597941162,
|
| 3850 |
+
"grad_norm": 0.17358270287513733,
|
| 3851 |
+
"learning_rate": 0.0005,
|
| 3852 |
+
"loss": 2.6843364238739014,
|
| 3853 |
+
"step": 1098
|
| 3854 |
+
},
|
| 3855 |
+
{
|
| 3856 |
+
"epoch": 0.21466556081377763,
|
| 3857 |
+
"grad_norm": 0.16818594932556152,
|
| 3858 |
+
"learning_rate": 0.0005,
|
| 3859 |
+
"loss": 2.638847827911377,
|
| 3860 |
+
"step": 1100
|
| 3861 |
+
},
|
| 3862 |
+
{
|
| 3863 |
+
"epoch": 0.21505586183343903,
|
| 3864 |
+
"grad_norm": 0.147896870970726,
|
| 3865 |
+
"learning_rate": 0.0005,
|
| 3866 |
+
"loss": 2.7285327911376953,
|
| 3867 |
+
"step": 1102
|
| 3868 |
+
},
|
| 3869 |
+
{
|
| 3870 |
+
"epoch": 0.21544616285310045,
|
| 3871 |
+
"grad_norm": 0.17403249442577362,
|
| 3872 |
+
"learning_rate": 0.0005,
|
| 3873 |
+
"loss": 2.660133123397827,
|
| 3874 |
+
"step": 1104
|
| 3875 |
+
},
|
| 3876 |
+
{
|
| 3877 |
+
"epoch": 0.21583646387276187,
|
| 3878 |
+
"grad_norm": 0.169234961271286,
|
| 3879 |
+
"learning_rate": 0.0005,
|
| 3880 |
+
"loss": 2.6874406337738037,
|
| 3881 |
+
"step": 1106
|
| 3882 |
+
},
|
| 3883 |
+
{
|
| 3884 |
+
"epoch": 0.2162267648924233,
|
| 3885 |
+
"grad_norm": 0.17236153781414032,
|
| 3886 |
+
"learning_rate": 0.0005,
|
| 3887 |
+
"loss": 2.684095859527588,
|
| 3888 |
+
"step": 1108
|
| 3889 |
+
},
|
| 3890 |
+
{
|
| 3891 |
+
"epoch": 0.21661706591208468,
|
| 3892 |
+
"grad_norm": 0.20823433995246887,
|
| 3893 |
+
"learning_rate": 0.0005,
|
| 3894 |
+
"loss": 2.6941487789154053,
|
| 3895 |
+
"step": 1110
|
| 3896 |
+
},
|
| 3897 |
+
{
|
| 3898 |
+
"epoch": 0.2170073669317461,
|
| 3899 |
+
"grad_norm": 0.17684966325759888,
|
| 3900 |
+
"learning_rate": 0.0005,
|
| 3901 |
+
"loss": 2.6613426208496094,
|
| 3902 |
+
"step": 1112
|
| 3903 |
+
},
|
| 3904 |
+
{
|
| 3905 |
+
"epoch": 0.21739766795140752,
|
| 3906 |
+
"grad_norm": 0.12845249474048615,
|
| 3907 |
+
"learning_rate": 0.0005,
|
| 3908 |
+
"loss": 2.6754093170166016,
|
| 3909 |
+
"step": 1114
|
| 3910 |
+
},
|
| 3911 |
+
{
|
| 3912 |
+
"epoch": 0.21778796897106895,
|
| 3913 |
+
"grad_norm": 0.2090635597705841,
|
| 3914 |
+
"learning_rate": 0.0005,
|
| 3915 |
+
"loss": 2.6931886672973633,
|
| 3916 |
+
"step": 1116
|
| 3917 |
+
},
|
| 3918 |
+
{
|
| 3919 |
+
"epoch": 0.21817826999073034,
|
| 3920 |
+
"grad_norm": 0.1474825143814087,
|
| 3921 |
+
"learning_rate": 0.0005,
|
| 3922 |
+
"loss": 2.684648036956787,
|
| 3923 |
+
"step": 1118
|
| 3924 |
+
},
|
| 3925 |
+
{
|
| 3926 |
+
"epoch": 0.21856857101039176,
|
| 3927 |
+
"grad_norm": 0.15146774053573608,
|
| 3928 |
+
"learning_rate": 0.0005,
|
| 3929 |
+
"loss": 2.659651756286621,
|
| 3930 |
+
"step": 1120
|
| 3931 |
+
},
|
| 3932 |
+
{
|
| 3933 |
+
"epoch": 0.21895887203005318,
|
| 3934 |
+
"grad_norm": 0.14323459565639496,
|
| 3935 |
+
"learning_rate": 0.0005,
|
| 3936 |
+
"loss": 2.646057367324829,
|
| 3937 |
+
"step": 1122
|
| 3938 |
+
},
|
| 3939 |
+
{
|
| 3940 |
+
"epoch": 0.2193491730497146,
|
| 3941 |
+
"grad_norm": 0.16822826862335205,
|
| 3942 |
+
"learning_rate": 0.0005,
|
| 3943 |
+
"loss": 2.7018821239471436,
|
| 3944 |
+
"step": 1124
|
| 3945 |
+
},
|
| 3946 |
+
{
|
| 3947 |
+
"epoch": 0.219739474069376,
|
| 3948 |
+
"grad_norm": 0.18991218507289886,
|
| 3949 |
+
"learning_rate": 0.0005,
|
| 3950 |
+
"loss": 2.5943076610565186,
|
| 3951 |
+
"step": 1126
|
| 3952 |
+
},
|
| 3953 |
+
{
|
| 3954 |
+
"epoch": 0.22012977508903742,
|
| 3955 |
+
"grad_norm": 0.23477086424827576,
|
| 3956 |
+
"learning_rate": 0.0005,
|
| 3957 |
+
"loss": 2.617910385131836,
|
| 3958 |
+
"step": 1128
|
| 3959 |
+
},
|
| 3960 |
+
{
|
| 3961 |
+
"epoch": 0.22052007610869884,
|
| 3962 |
+
"grad_norm": 0.1859017014503479,
|
| 3963 |
+
"learning_rate": 0.0005,
|
| 3964 |
+
"loss": 2.6979408264160156,
|
| 3965 |
+
"step": 1130
|
| 3966 |
+
},
|
| 3967 |
+
{
|
| 3968 |
+
"epoch": 0.22091037712836026,
|
| 3969 |
+
"grad_norm": 0.19023354351520538,
|
| 3970 |
+
"learning_rate": 0.0005,
|
| 3971 |
+
"loss": 2.6010313034057617,
|
| 3972 |
+
"step": 1132
|
| 3973 |
+
},
|
| 3974 |
+
{
|
| 3975 |
+
"epoch": 0.22130067814802165,
|
| 3976 |
+
"grad_norm": 0.13957473635673523,
|
| 3977 |
+
"learning_rate": 0.0005,
|
| 3978 |
+
"loss": 2.719595432281494,
|
| 3979 |
+
"step": 1134
|
| 3980 |
+
},
|
| 3981 |
+
{
|
| 3982 |
+
"epoch": 0.22169097916768307,
|
| 3983 |
+
"grad_norm": 0.19965648651123047,
|
| 3984 |
+
"learning_rate": 0.0005,
|
| 3985 |
+
"loss": 2.6675214767456055,
|
| 3986 |
+
"step": 1136
|
| 3987 |
+
},
|
| 3988 |
+
{
|
| 3989 |
+
"epoch": 0.2220812801873445,
|
| 3990 |
+
"grad_norm": 0.17871396243572235,
|
| 3991 |
+
"learning_rate": 0.0005,
|
| 3992 |
+
"loss": 2.698038339614868,
|
| 3993 |
+
"step": 1138
|
| 3994 |
+
},
|
| 3995 |
+
{
|
| 3996 |
+
"epoch": 0.22247158120700591,
|
| 3997 |
+
"grad_norm": 0.18603584170341492,
|
| 3998 |
+
"learning_rate": 0.0005,
|
| 3999 |
+
"loss": 2.716740608215332,
|
| 4000 |
+
"step": 1140
|
| 4001 |
+
},
|
| 4002 |
+
{
|
| 4003 |
+
"epoch": 0.2228618822266673,
|
| 4004 |
+
"grad_norm": 0.1532956063747406,
|
| 4005 |
+
"learning_rate": 0.0005,
|
| 4006 |
+
"loss": 2.67754864692688,
|
| 4007 |
+
"step": 1142
|
| 4008 |
+
},
|
| 4009 |
+
{
|
| 4010 |
+
"epoch": 0.22325218324632873,
|
| 4011 |
+
"grad_norm": 0.16153095662593842,
|
| 4012 |
+
"learning_rate": 0.0005,
|
| 4013 |
+
"loss": 2.7249271869659424,
|
| 4014 |
+
"step": 1144
|
| 4015 |
+
},
|
| 4016 |
+
{
|
| 4017 |
+
"epoch": 0.22364248426599015,
|
| 4018 |
+
"grad_norm": 0.1905735731124878,
|
| 4019 |
+
"learning_rate": 0.0005,
|
| 4020 |
+
"loss": 2.691530227661133,
|
| 4021 |
+
"step": 1146
|
| 4022 |
+
},
|
| 4023 |
+
{
|
| 4024 |
+
"epoch": 0.22403278528565157,
|
| 4025 |
+
"grad_norm": 0.14802443981170654,
|
| 4026 |
+
"learning_rate": 0.0005,
|
| 4027 |
+
"loss": 2.6735339164733887,
|
| 4028 |
+
"step": 1148
|
| 4029 |
+
},
|
| 4030 |
+
{
|
| 4031 |
+
"epoch": 0.22442308630531296,
|
| 4032 |
+
"grad_norm": 0.22828778624534607,
|
| 4033 |
+
"learning_rate": 0.0005,
|
| 4034 |
+
"loss": 2.659954309463501,
|
| 4035 |
+
"step": 1150
|
| 4036 |
+
},
|
| 4037 |
+
{
|
| 4038 |
+
"epoch": 0.22481338732497438,
|
| 4039 |
+
"grad_norm": 0.23932091891765594,
|
| 4040 |
+
"learning_rate": 0.0005,
|
| 4041 |
+
"loss": 2.7073307037353516,
|
| 4042 |
+
"step": 1152
|
| 4043 |
+
},
|
| 4044 |
+
{
|
| 4045 |
+
"epoch": 0.2252036883446358,
|
| 4046 |
+
"grad_norm": 0.18196122348308563,
|
| 4047 |
+
"learning_rate": 0.0005,
|
| 4048 |
+
"loss": 2.6170496940612793,
|
| 4049 |
+
"step": 1154
|
| 4050 |
+
},
|
| 4051 |
+
{
|
| 4052 |
+
"epoch": 0.22559398936429723,
|
| 4053 |
+
"grad_norm": 0.1779865175485611,
|
| 4054 |
+
"learning_rate": 0.0005,
|
| 4055 |
+
"loss": 2.5817713737487793,
|
| 4056 |
+
"step": 1156
|
| 4057 |
+
},
|
| 4058 |
+
{
|
| 4059 |
+
"epoch": 0.22598429038395862,
|
| 4060 |
+
"grad_norm": 0.18128225207328796,
|
| 4061 |
+
"learning_rate": 0.0005,
|
| 4062 |
+
"loss": 2.673524856567383,
|
| 4063 |
+
"step": 1158
|
| 4064 |
+
},
|
| 4065 |
+
{
|
| 4066 |
+
"epoch": 0.22637459140362004,
|
| 4067 |
+
"grad_norm": 0.23117612302303314,
|
| 4068 |
+
"learning_rate": 0.0005,
|
| 4069 |
+
"loss": 2.631326198577881,
|
| 4070 |
+
"step": 1160
|
| 4071 |
+
},
|
| 4072 |
+
{
|
| 4073 |
+
"epoch": 0.22676489242328146,
|
| 4074 |
+
"grad_norm": 0.1516844928264618,
|
| 4075 |
+
"learning_rate": 0.0005,
|
| 4076 |
+
"loss": 2.6864771842956543,
|
| 4077 |
+
"step": 1162
|
| 4078 |
+
},
|
| 4079 |
+
{
|
| 4080 |
+
"epoch": 0.22715519344294288,
|
| 4081 |
+
"grad_norm": 0.1316230148077011,
|
| 4082 |
+
"learning_rate": 0.0005,
|
| 4083 |
+
"loss": 2.625622272491455,
|
| 4084 |
+
"step": 1164
|
| 4085 |
+
},
|
| 4086 |
+
{
|
| 4087 |
+
"epoch": 0.22754549446260428,
|
| 4088 |
+
"grad_norm": 0.15616853535175323,
|
| 4089 |
+
"learning_rate": 0.0005,
|
| 4090 |
+
"loss": 2.637674331665039,
|
| 4091 |
+
"step": 1166
|
| 4092 |
+
},
|
| 4093 |
+
{
|
| 4094 |
+
"epoch": 0.2279357954822657,
|
| 4095 |
+
"grad_norm": 0.16544879972934723,
|
| 4096 |
+
"learning_rate": 0.0005,
|
| 4097 |
+
"loss": 2.6850900650024414,
|
| 4098 |
+
"step": 1168
|
| 4099 |
+
},
|
| 4100 |
+
{
|
| 4101 |
+
"epoch": 0.22832609650192712,
|
| 4102 |
+
"grad_norm": 0.22623369097709656,
|
| 4103 |
+
"learning_rate": 0.0005,
|
| 4104 |
+
"loss": 2.6753106117248535,
|
| 4105 |
+
"step": 1170
|
| 4106 |
+
},
|
| 4107 |
+
{
|
| 4108 |
+
"epoch": 0.22871639752158854,
|
| 4109 |
+
"grad_norm": 0.1531679630279541,
|
| 4110 |
+
"learning_rate": 0.0005,
|
| 4111 |
+
"loss": 2.699336290359497,
|
| 4112 |
+
"step": 1172
|
| 4113 |
+
},
|
| 4114 |
+
{
|
| 4115 |
+
"epoch": 0.22910669854124993,
|
| 4116 |
+
"grad_norm": 0.20147407054901123,
|
| 4117 |
+
"learning_rate": 0.0005,
|
| 4118 |
+
"loss": 2.6825742721557617,
|
| 4119 |
+
"step": 1174
|
| 4120 |
+
},
|
| 4121 |
+
{
|
| 4122 |
+
"epoch": 0.22949699956091135,
|
| 4123 |
+
"grad_norm": 0.17440174520015717,
|
| 4124 |
+
"learning_rate": 0.0005,
|
| 4125 |
+
"loss": 2.731358289718628,
|
| 4126 |
+
"step": 1176
|
| 4127 |
+
},
|
| 4128 |
+
{
|
| 4129 |
+
"epoch": 0.22988730058057277,
|
| 4130 |
+
"grad_norm": 0.1668044924736023,
|
| 4131 |
+
"learning_rate": 0.0005,
|
| 4132 |
+
"loss": 2.667476177215576,
|
| 4133 |
+
"step": 1178
|
| 4134 |
+
},
|
| 4135 |
+
{
|
| 4136 |
+
"epoch": 0.2302776016002342,
|
| 4137 |
+
"grad_norm": 0.1338946521282196,
|
| 4138 |
+
"learning_rate": 0.0005,
|
| 4139 |
+
"loss": 2.682175636291504,
|
| 4140 |
+
"step": 1180
|
| 4141 |
+
},
|
| 4142 |
+
{
|
| 4143 |
+
"epoch": 0.2306679026198956,
|
| 4144 |
+
"grad_norm": 0.1556786596775055,
|
| 4145 |
+
"learning_rate": 0.0005,
|
| 4146 |
+
"loss": 2.666945457458496,
|
| 4147 |
+
"step": 1182
|
| 4148 |
+
},
|
| 4149 |
+
{
|
| 4150 |
+
"epoch": 0.231058203639557,
|
| 4151 |
+
"grad_norm": 0.14774300158023834,
|
| 4152 |
+
"learning_rate": 0.0005,
|
| 4153 |
+
"loss": 2.6864633560180664,
|
| 4154 |
+
"step": 1184
|
| 4155 |
+
},
|
| 4156 |
+
{
|
| 4157 |
+
"epoch": 0.23144850465921843,
|
| 4158 |
+
"grad_norm": 0.24684716761112213,
|
| 4159 |
+
"learning_rate": 0.0005,
|
| 4160 |
+
"loss": 2.677968978881836,
|
| 4161 |
+
"step": 1186
|
| 4162 |
+
},
|
| 4163 |
+
{
|
| 4164 |
+
"epoch": 0.23183880567887982,
|
| 4165 |
+
"grad_norm": 0.16622044146060944,
|
| 4166 |
+
"learning_rate": 0.0005,
|
| 4167 |
+
"loss": 2.646451950073242,
|
| 4168 |
+
"step": 1188
|
| 4169 |
+
},
|
| 4170 |
+
{
|
| 4171 |
+
"epoch": 0.23222910669854124,
|
| 4172 |
+
"grad_norm": 0.15947335958480835,
|
| 4173 |
+
"learning_rate": 0.0005,
|
| 4174 |
+
"loss": 2.6525235176086426,
|
| 4175 |
+
"step": 1190
|
| 4176 |
+
},
|
| 4177 |
+
{
|
| 4178 |
+
"epoch": 0.23261940771820266,
|
| 4179 |
+
"grad_norm": 0.1693902462720871,
|
| 4180 |
+
"learning_rate": 0.0005,
|
| 4181 |
+
"loss": 2.6310508251190186,
|
| 4182 |
+
"step": 1192
|
| 4183 |
+
},
|
| 4184 |
+
{
|
| 4185 |
+
"epoch": 0.23300970873786409,
|
| 4186 |
+
"grad_norm": 0.15094178915023804,
|
| 4187 |
+
"learning_rate": 0.0005,
|
| 4188 |
+
"loss": 2.6200389862060547,
|
| 4189 |
+
"step": 1194
|
| 4190 |
+
},
|
| 4191 |
+
{
|
| 4192 |
+
"epoch": 0.23340000975752548,
|
| 4193 |
+
"grad_norm": 0.22488941252231598,
|
| 4194 |
+
"learning_rate": 0.0005,
|
| 4195 |
+
"loss": 2.725006103515625,
|
| 4196 |
+
"step": 1196
|
| 4197 |
+
},
|
| 4198 |
+
{
|
| 4199 |
+
"epoch": 0.2337903107771869,
|
| 4200 |
+
"grad_norm": 0.15963996946811676,
|
| 4201 |
+
"learning_rate": 0.0005,
|
| 4202 |
+
"loss": 2.673408269882202,
|
| 4203 |
+
"step": 1198
|
| 4204 |
+
},
|
| 4205 |
+
{
|
| 4206 |
+
"epoch": 0.23418061179684832,
|
| 4207 |
+
"grad_norm": 0.19030654430389404,
|
| 4208 |
+
"learning_rate": 0.0005,
|
| 4209 |
+
"loss": 2.58413028717041,
|
| 4210 |
+
"step": 1200
|
| 4211 |
+
},
|
| 4212 |
+
{
|
| 4213 |
+
"epoch": 0.23457091281650974,
|
| 4214 |
+
"grad_norm": 0.35557857155799866,
|
| 4215 |
+
"learning_rate": 0.0005,
|
| 4216 |
+
"loss": 2.5940866470336914,
|
| 4217 |
+
"step": 1202
|
| 4218 |
+
},
|
| 4219 |
+
{
|
| 4220 |
+
"epoch": 0.23496121383617113,
|
| 4221 |
+
"grad_norm": 0.252509206533432,
|
| 4222 |
+
"learning_rate": 0.0005,
|
| 4223 |
+
"loss": 2.607273578643799,
|
| 4224 |
+
"step": 1204
|
| 4225 |
+
},
|
| 4226 |
+
{
|
| 4227 |
+
"epoch": 0.23535151485583256,
|
| 4228 |
+
"grad_norm": 0.1482771784067154,
|
| 4229 |
+
"learning_rate": 0.0005,
|
| 4230 |
+
"loss": 2.6384530067443848,
|
| 4231 |
+
"step": 1206
|
| 4232 |
+
},
|
| 4233 |
+
{
|
| 4234 |
+
"epoch": 0.23574181587549398,
|
| 4235 |
+
"grad_norm": 0.2045152336359024,
|
| 4236 |
+
"learning_rate": 0.0005,
|
| 4237 |
+
"loss": 2.6572623252868652,
|
| 4238 |
+
"step": 1208
|
| 4239 |
+
},
|
| 4240 |
+
{
|
| 4241 |
+
"epoch": 0.2361321168951554,
|
| 4242 |
+
"grad_norm": 0.2820110023021698,
|
| 4243 |
+
"learning_rate": 0.0005,
|
| 4244 |
+
"loss": 2.6583092212677,
|
| 4245 |
+
"step": 1210
|
| 4246 |
+
},
|
| 4247 |
+
{
|
| 4248 |
+
"epoch": 0.2365224179148168,
|
| 4249 |
+
"grad_norm": 0.13247635960578918,
|
| 4250 |
+
"learning_rate": 0.0005,
|
| 4251 |
+
"loss": 2.645008087158203,
|
| 4252 |
+
"step": 1212
|
| 4253 |
+
},
|
| 4254 |
+
{
|
| 4255 |
+
"epoch": 0.2369127189344782,
|
| 4256 |
+
"grad_norm": 0.1295531690120697,
|
| 4257 |
+
"learning_rate": 0.0005,
|
| 4258 |
+
"loss": 2.6859326362609863,
|
| 4259 |
+
"step": 1214
|
| 4260 |
+
},
|
| 4261 |
+
{
|
| 4262 |
+
"epoch": 0.23730301995413963,
|
| 4263 |
+
"grad_norm": 0.1801522970199585,
|
| 4264 |
+
"learning_rate": 0.0005,
|
| 4265 |
+
"loss": 2.593832015991211,
|
| 4266 |
+
"step": 1216
|
| 4267 |
+
},
|
| 4268 |
+
{
|
| 4269 |
+
"epoch": 0.23769332097380105,
|
| 4270 |
+
"grad_norm": 0.12627647817134857,
|
| 4271 |
+
"learning_rate": 0.0005,
|
| 4272 |
+
"loss": 2.619643449783325,
|
| 4273 |
+
"step": 1218
|
| 4274 |
+
},
|
| 4275 |
+
{
|
| 4276 |
+
"epoch": 0.23808362199346245,
|
| 4277 |
+
"grad_norm": 0.17536495625972748,
|
| 4278 |
+
"learning_rate": 0.0005,
|
| 4279 |
+
"loss": 2.6363515853881836,
|
| 4280 |
+
"step": 1220
|
| 4281 |
+
},
|
| 4282 |
+
{
|
| 4283 |
+
"epoch": 0.23847392301312387,
|
| 4284 |
+
"grad_norm": 0.14926867187023163,
|
| 4285 |
+
"learning_rate": 0.0005,
|
| 4286 |
+
"loss": 2.623610734939575,
|
| 4287 |
+
"step": 1222
|
| 4288 |
+
},
|
| 4289 |
+
{
|
| 4290 |
+
"epoch": 0.2388642240327853,
|
| 4291 |
+
"grad_norm": 0.16004212200641632,
|
| 4292 |
+
"learning_rate": 0.0005,
|
| 4293 |
+
"loss": 2.676762104034424,
|
| 4294 |
+
"step": 1224
|
| 4295 |
+
},
|
| 4296 |
+
{
|
| 4297 |
+
"epoch": 0.2392545250524467,
|
| 4298 |
+
"grad_norm": 0.176863893866539,
|
| 4299 |
+
"learning_rate": 0.0005,
|
| 4300 |
+
"loss": 2.6489977836608887,
|
| 4301 |
+
"step": 1226
|
| 4302 |
+
},
|
| 4303 |
+
{
|
| 4304 |
+
"epoch": 0.2396448260721081,
|
| 4305 |
+
"grad_norm": 0.16090930998325348,
|
| 4306 |
+
"learning_rate": 0.0005,
|
| 4307 |
+
"loss": 2.6437771320343018,
|
| 4308 |
+
"step": 1228
|
| 4309 |
+
},
|
| 4310 |
+
{
|
| 4311 |
+
"epoch": 0.24003512709176952,
|
| 4312 |
+
"grad_norm": 0.20055003464221954,
|
| 4313 |
+
"learning_rate": 0.0005,
|
| 4314 |
+
"loss": 2.6101596355438232,
|
| 4315 |
+
"step": 1230
|
| 4316 |
+
},
|
| 4317 |
+
{
|
| 4318 |
+
"epoch": 0.24042542811143094,
|
| 4319 |
+
"grad_norm": 0.15835244953632355,
|
| 4320 |
+
"learning_rate": 0.0005,
|
| 4321 |
+
"loss": 2.625143527984619,
|
| 4322 |
+
"step": 1232
|
| 4323 |
+
},
|
| 4324 |
+
{
|
| 4325 |
+
"epoch": 0.24081572913109237,
|
| 4326 |
+
"grad_norm": 0.22726507484912872,
|
| 4327 |
+
"learning_rate": 0.0005,
|
| 4328 |
+
"loss": 2.674014091491699,
|
| 4329 |
+
"step": 1234
|
| 4330 |
+
},
|
| 4331 |
+
{
|
| 4332 |
+
"epoch": 0.24120603015075376,
|
| 4333 |
+
"grad_norm": 0.1781259924173355,
|
| 4334 |
+
"learning_rate": 0.0005,
|
| 4335 |
+
"loss": 2.671015977859497,
|
| 4336 |
+
"step": 1236
|
| 4337 |
+
},
|
| 4338 |
+
{
|
| 4339 |
+
"epoch": 0.24159633117041518,
|
| 4340 |
+
"grad_norm": 0.20377010107040405,
|
| 4341 |
+
"learning_rate": 0.0005,
|
| 4342 |
+
"loss": 2.6821393966674805,
|
| 4343 |
+
"step": 1238
|
| 4344 |
+
},
|
| 4345 |
+
{
|
| 4346 |
+
"epoch": 0.2419866321900766,
|
| 4347 |
+
"grad_norm": 0.15436004102230072,
|
| 4348 |
+
"learning_rate": 0.0005,
|
| 4349 |
+
"loss": 2.6761207580566406,
|
| 4350 |
+
"step": 1240
|
| 4351 |
+
},
|
| 4352 |
+
{
|
| 4353 |
+
"epoch": 0.24237693320973802,
|
| 4354 |
+
"grad_norm": 0.17381837964057922,
|
| 4355 |
+
"learning_rate": 0.0005,
|
| 4356 |
+
"loss": 2.6696839332580566,
|
| 4357 |
+
"step": 1242
|
| 4358 |
+
},
|
| 4359 |
+
{
|
| 4360 |
+
"epoch": 0.24276723422939941,
|
| 4361 |
+
"grad_norm": 0.1798633486032486,
|
| 4362 |
+
"learning_rate": 0.0005,
|
| 4363 |
+
"loss": 2.6179513931274414,
|
| 4364 |
+
"step": 1244
|
| 4365 |
+
},
|
| 4366 |
+
{
|
| 4367 |
+
"epoch": 0.24315753524906084,
|
| 4368 |
+
"grad_norm": 0.20496976375579834,
|
| 4369 |
+
"learning_rate": 0.0005,
|
| 4370 |
+
"loss": 2.6625218391418457,
|
| 4371 |
+
"step": 1246
|
| 4372 |
+
},
|
| 4373 |
+
{
|
| 4374 |
+
"epoch": 0.24354783626872226,
|
| 4375 |
+
"grad_norm": 0.26173847913742065,
|
| 4376 |
+
"learning_rate": 0.0005,
|
| 4377 |
+
"loss": 2.604013442993164,
|
| 4378 |
+
"step": 1248
|
| 4379 |
+
},
|
| 4380 |
+
{
|
| 4381 |
+
"epoch": 0.24393813728838368,
|
| 4382 |
+
"grad_norm": 0.21672292053699493,
|
| 4383 |
+
"learning_rate": 0.0005,
|
| 4384 |
+
"loss": 2.600398063659668,
|
| 4385 |
+
"step": 1250
|
| 4386 |
+
},
|
| 4387 |
+
{
|
| 4388 |
+
"epoch": 0.24432843830804507,
|
| 4389 |
+
"grad_norm": 0.1577928364276886,
|
| 4390 |
+
"learning_rate": 0.0005,
|
| 4391 |
+
"loss": 2.6309573650360107,
|
| 4392 |
+
"step": 1252
|
| 4393 |
+
},
|
| 4394 |
+
{
|
| 4395 |
+
"epoch": 0.2447187393277065,
|
| 4396 |
+
"grad_norm": 0.21739424765110016,
|
| 4397 |
+
"learning_rate": 0.0005,
|
| 4398 |
+
"loss": 2.6704516410827637,
|
| 4399 |
+
"step": 1254
|
| 4400 |
+
},
|
| 4401 |
+
{
|
| 4402 |
+
"epoch": 0.2451090403473679,
|
| 4403 |
+
"grad_norm": 0.18137183785438538,
|
| 4404 |
+
"learning_rate": 0.0005,
|
| 4405 |
+
"loss": 2.6786141395568848,
|
| 4406 |
+
"step": 1256
|
| 4407 |
+
},
|
| 4408 |
+
{
|
| 4409 |
+
"epoch": 0.24549934136702933,
|
| 4410 |
+
"grad_norm": 0.16256330907344818,
|
| 4411 |
+
"learning_rate": 0.0005,
|
| 4412 |
+
"loss": 2.6640257835388184,
|
| 4413 |
+
"step": 1258
|
| 4414 |
+
},
|
| 4415 |
+
{
|
| 4416 |
+
"epoch": 0.24588964238669073,
|
| 4417 |
+
"grad_norm": 0.22120048105716705,
|
| 4418 |
+
"learning_rate": 0.0005,
|
| 4419 |
+
"loss": 2.6049139499664307,
|
| 4420 |
+
"step": 1260
|
| 4421 |
+
},
|
| 4422 |
+
{
|
| 4423 |
+
"epoch": 0.24627994340635215,
|
| 4424 |
+
"grad_norm": 0.14366233348846436,
|
| 4425 |
+
"learning_rate": 0.0005,
|
| 4426 |
+
"loss": 2.6682114601135254,
|
| 4427 |
+
"step": 1262
|
| 4428 |
+
},
|
| 4429 |
+
{
|
| 4430 |
+
"epoch": 0.24667024442601357,
|
| 4431 |
+
"grad_norm": 0.1614772379398346,
|
| 4432 |
+
"learning_rate": 0.0005,
|
| 4433 |
+
"loss": 2.6531596183776855,
|
| 4434 |
+
"step": 1264
|
| 4435 |
+
},
|
| 4436 |
+
{
|
| 4437 |
+
"epoch": 0.247060545445675,
|
| 4438 |
+
"grad_norm": 0.2811392843723297,
|
| 4439 |
+
"learning_rate": 0.0005,
|
| 4440 |
+
"loss": 2.653393030166626,
|
| 4441 |
+
"step": 1266
|
| 4442 |
+
},
|
| 4443 |
+
{
|
| 4444 |
+
"epoch": 0.24745084646533638,
|
| 4445 |
+
"grad_norm": 0.20688612759113312,
|
| 4446 |
+
"learning_rate": 0.0005,
|
| 4447 |
+
"loss": 2.6272850036621094,
|
| 4448 |
+
"step": 1268
|
| 4449 |
+
},
|
| 4450 |
+
{
|
| 4451 |
+
"epoch": 0.2478411474849978,
|
| 4452 |
+
"grad_norm": 0.1701081544160843,
|
| 4453 |
+
"learning_rate": 0.0005,
|
| 4454 |
+
"loss": 2.622196674346924,
|
| 4455 |
+
"step": 1270
|
| 4456 |
+
},
|
| 4457 |
+
{
|
| 4458 |
+
"epoch": 0.24823144850465922,
|
| 4459 |
+
"grad_norm": 0.23113785684108734,
|
| 4460 |
+
"learning_rate": 0.0005,
|
| 4461 |
+
"loss": 2.6565871238708496,
|
| 4462 |
+
"step": 1272
|
| 4463 |
+
},
|
| 4464 |
+
{
|
| 4465 |
+
"epoch": 0.24862174952432065,
|
| 4466 |
+
"grad_norm": 0.14760687947273254,
|
| 4467 |
+
"learning_rate": 0.0005,
|
| 4468 |
+
"loss": 2.648200511932373,
|
| 4469 |
+
"step": 1274
|
| 4470 |
+
},
|
| 4471 |
+
{
|
| 4472 |
+
"epoch": 0.24901205054398204,
|
| 4473 |
+
"grad_norm": 0.2061927616596222,
|
| 4474 |
+
"learning_rate": 0.0005,
|
| 4475 |
+
"loss": 2.713320732116699,
|
| 4476 |
+
"step": 1276
|
| 4477 |
+
},
|
| 4478 |
+
{
|
| 4479 |
+
"epoch": 0.24940235156364346,
|
| 4480 |
+
"grad_norm": 0.21676722168922424,
|
| 4481 |
+
"learning_rate": 0.0005,
|
| 4482 |
+
"loss": 2.648419141769409,
|
| 4483 |
+
"step": 1278
|
| 4484 |
+
},
|
| 4485 |
+
{
|
| 4486 |
+
"epoch": 0.24979265258330488,
|
| 4487 |
+
"grad_norm": 0.16173920035362244,
|
| 4488 |
+
"learning_rate": 0.0005,
|
| 4489 |
+
"loss": 2.6689555644989014,
|
| 4490 |
+
"step": 1280
|
| 4491 |
+
},
|
| 4492 |
+
{
|
| 4493 |
+
"epoch": 0.2501829536029663,
|
| 4494 |
+
"grad_norm": 0.19144730269908905,
|
| 4495 |
+
"learning_rate": 0.0005,
|
| 4496 |
+
"loss": 2.6696839332580566,
|
| 4497 |
+
"step": 1282
|
| 4498 |
+
},
|
| 4499 |
+
{
|
| 4500 |
+
"epoch": 0.2505732546226277,
|
| 4501 |
+
"grad_norm": 0.14531807601451874,
|
| 4502 |
+
"learning_rate": 0.0005,
|
| 4503 |
+
"loss": 2.667482852935791,
|
| 4504 |
+
"step": 1284
|
| 4505 |
+
},
|
| 4506 |
+
{
|
| 4507 |
+
"epoch": 0.2509635556422891,
|
| 4508 |
+
"grad_norm": 0.2814357280731201,
|
| 4509 |
+
"learning_rate": 0.0005,
|
| 4510 |
+
"loss": 2.672882556915283,
|
| 4511 |
+
"step": 1286
|
| 4512 |
+
},
|
| 4513 |
+
{
|
| 4514 |
+
"epoch": 0.25135385666195054,
|
| 4515 |
+
"grad_norm": 0.266726016998291,
|
| 4516 |
+
"learning_rate": 0.0005,
|
| 4517 |
+
"loss": 2.6003260612487793,
|
| 4518 |
+
"step": 1288
|
| 4519 |
+
},
|
| 4520 |
+
{
|
| 4521 |
+
"epoch": 0.25174415768161196,
|
| 4522 |
+
"grad_norm": 0.16767925024032593,
|
| 4523 |
+
"learning_rate": 0.0005,
|
| 4524 |
+
"loss": 2.6420040130615234,
|
| 4525 |
+
"step": 1290
|
| 4526 |
+
},
|
| 4527 |
+
{
|
| 4528 |
+
"epoch": 0.2521344587012734,
|
| 4529 |
+
"grad_norm": 0.15360583364963531,
|
| 4530 |
+
"learning_rate": 0.0005,
|
| 4531 |
+
"loss": 2.6700544357299805,
|
| 4532 |
+
"step": 1292
|
| 4533 |
+
},
|
| 4534 |
+
{
|
| 4535 |
+
"epoch": 0.25252475972093474,
|
| 4536 |
+
"grad_norm": 0.2940566837787628,
|
| 4537 |
+
"learning_rate": 0.0005,
|
| 4538 |
+
"loss": 2.6850647926330566,
|
| 4539 |
+
"step": 1294
|
| 4540 |
+
},
|
| 4541 |
+
{
|
| 4542 |
+
"epoch": 0.25291506074059616,
|
| 4543 |
+
"grad_norm": 0.16723941266536713,
|
| 4544 |
+
"learning_rate": 0.0005,
|
| 4545 |
+
"loss": 2.686980724334717,
|
| 4546 |
+
"step": 1296
|
| 4547 |
+
},
|
| 4548 |
+
{
|
| 4549 |
+
"epoch": 0.2533053617602576,
|
| 4550 |
+
"grad_norm": 0.15483099222183228,
|
| 4551 |
+
"learning_rate": 0.0005,
|
| 4552 |
+
"loss": 2.676826000213623,
|
| 4553 |
+
"step": 1298
|
| 4554 |
+
},
|
| 4555 |
+
{
|
| 4556 |
+
"epoch": 0.253695662779919,
|
| 4557 |
+
"grad_norm": 0.18496812880039215,
|
| 4558 |
+
"learning_rate": 0.0005,
|
| 4559 |
+
"loss": 2.669687032699585,
|
| 4560 |
+
"step": 1300
|
| 4561 |
+
},
|
| 4562 |
+
{
|
| 4563 |
+
"epoch": 0.2540859637995804,
|
| 4564 |
+
"grad_norm": 0.17022332549095154,
|
| 4565 |
+
"learning_rate": 0.0005,
|
| 4566 |
+
"loss": 2.622576951980591,
|
| 4567 |
+
"step": 1302
|
| 4568 |
+
},
|
| 4569 |
+
{
|
| 4570 |
+
"epoch": 0.25447626481924185,
|
| 4571 |
+
"grad_norm": 0.16681961715221405,
|
| 4572 |
+
"learning_rate": 0.0005,
|
| 4573 |
+
"loss": 2.6605443954467773,
|
| 4574 |
+
"step": 1304
|
| 4575 |
+
},
|
| 4576 |
+
{
|
| 4577 |
+
"epoch": 0.25486656583890327,
|
| 4578 |
+
"grad_norm": 0.19448845088481903,
|
| 4579 |
+
"learning_rate": 0.0005,
|
| 4580 |
+
"loss": 2.6306300163269043,
|
| 4581 |
+
"step": 1306
|
| 4582 |
+
},
|
| 4583 |
+
{
|
| 4584 |
+
"epoch": 0.2552568668585647,
|
| 4585 |
+
"grad_norm": 0.1415524035692215,
|
| 4586 |
+
"learning_rate": 0.0005,
|
| 4587 |
+
"loss": 2.6361708641052246,
|
| 4588 |
+
"step": 1308
|
| 4589 |
+
},
|
| 4590 |
+
{
|
| 4591 |
+
"epoch": 0.25564716787822606,
|
| 4592 |
+
"grad_norm": 0.23384211957454681,
|
| 4593 |
+
"learning_rate": 0.0005,
|
| 4594 |
+
"loss": 2.6454761028289795,
|
| 4595 |
+
"step": 1310
|
| 4596 |
+
},
|
| 4597 |
+
{
|
| 4598 |
+
"epoch": 0.2560374688978875,
|
| 4599 |
+
"grad_norm": 0.18831941485404968,
|
| 4600 |
+
"learning_rate": 0.0005,
|
| 4601 |
+
"loss": 2.638505697250366,
|
| 4602 |
+
"step": 1312
|
| 4603 |
+
},
|
| 4604 |
+
{
|
| 4605 |
+
"epoch": 0.2564277699175489,
|
| 4606 |
+
"grad_norm": 0.14515143632888794,
|
| 4607 |
+
"learning_rate": 0.0005,
|
| 4608 |
+
"loss": 2.6328768730163574,
|
| 4609 |
+
"step": 1314
|
| 4610 |
+
},
|
| 4611 |
+
{
|
| 4612 |
+
"epoch": 0.2568180709372103,
|
| 4613 |
+
"grad_norm": 0.12116917222738266,
|
| 4614 |
+
"learning_rate": 0.0005,
|
| 4615 |
+
"loss": 2.632913112640381,
|
| 4616 |
+
"step": 1316
|
| 4617 |
+
},
|
| 4618 |
+
{
|
| 4619 |
+
"epoch": 0.25720837195687174,
|
| 4620 |
+
"grad_norm": 0.1678297072649002,
|
| 4621 |
+
"learning_rate": 0.0005,
|
| 4622 |
+
"loss": 2.6378049850463867,
|
| 4623 |
+
"step": 1318
|
| 4624 |
+
},
|
| 4625 |
+
{
|
| 4626 |
+
"epoch": 0.25759867297653316,
|
| 4627 |
+
"grad_norm": 0.22207486629486084,
|
| 4628 |
+
"learning_rate": 0.0005,
|
| 4629 |
+
"loss": 2.6391654014587402,
|
| 4630 |
+
"step": 1320
|
| 4631 |
+
},
|
| 4632 |
+
{
|
| 4633 |
+
"epoch": 0.2579889739961946,
|
| 4634 |
+
"grad_norm": 0.1604643315076828,
|
| 4635 |
+
"learning_rate": 0.0005,
|
| 4636 |
+
"loss": 2.6705923080444336,
|
| 4637 |
+
"step": 1322
|
| 4638 |
+
},
|
| 4639 |
+
{
|
| 4640 |
+
"epoch": 0.258379275015856,
|
| 4641 |
+
"grad_norm": 0.15938599407672882,
|
| 4642 |
+
"learning_rate": 0.0005,
|
| 4643 |
+
"loss": 2.6588027477264404,
|
| 4644 |
+
"step": 1324
|
| 4645 |
+
},
|
| 4646 |
+
{
|
| 4647 |
+
"epoch": 0.25876957603551737,
|
| 4648 |
+
"grad_norm": 0.22103284299373627,
|
| 4649 |
+
"learning_rate": 0.0005,
|
| 4650 |
+
"loss": 2.6964266300201416,
|
| 4651 |
+
"step": 1326
|
| 4652 |
+
},
|
| 4653 |
+
{
|
| 4654 |
+
"epoch": 0.2591598770551788,
|
| 4655 |
+
"grad_norm": 0.1604282110929489,
|
| 4656 |
+
"learning_rate": 0.0005,
|
| 4657 |
+
"loss": 2.582942247390747,
|
| 4658 |
+
"step": 1328
|
| 4659 |
+
},
|
| 4660 |
+
{
|
| 4661 |
+
"epoch": 0.2595501780748402,
|
| 4662 |
+
"grad_norm": 0.18108880519866943,
|
| 4663 |
+
"learning_rate": 0.0005,
|
| 4664 |
+
"loss": 2.697288751602173,
|
| 4665 |
+
"step": 1330
|
| 4666 |
+
},
|
| 4667 |
+
{
|
| 4668 |
+
"epoch": 0.25994047909450163,
|
| 4669 |
+
"grad_norm": 0.19336365163326263,
|
| 4670 |
+
"learning_rate": 0.0005,
|
| 4671 |
+
"loss": 2.6369969844818115,
|
| 4672 |
+
"step": 1332
|
| 4673 |
+
},
|
| 4674 |
+
{
|
| 4675 |
+
"epoch": 0.26033078011416305,
|
| 4676 |
+
"grad_norm": 0.18219086527824402,
|
| 4677 |
+
"learning_rate": 0.0005,
|
| 4678 |
+
"loss": 2.718562602996826,
|
| 4679 |
+
"step": 1334
|
| 4680 |
+
},
|
| 4681 |
+
{
|
| 4682 |
+
"epoch": 0.2607210811338245,
|
| 4683 |
+
"grad_norm": 0.19778351485729218,
|
| 4684 |
+
"learning_rate": 0.0005,
|
| 4685 |
+
"loss": 2.6770052909851074,
|
| 4686 |
+
"step": 1336
|
| 4687 |
+
},
|
| 4688 |
+
{
|
| 4689 |
+
"epoch": 0.2611113821534859,
|
| 4690 |
+
"grad_norm": 0.19296561181545258,
|
| 4691 |
+
"learning_rate": 0.0005,
|
| 4692 |
+
"loss": 2.6657004356384277,
|
| 4693 |
+
"step": 1338
|
| 4694 |
+
},
|
| 4695 |
+
{
|
| 4696 |
+
"epoch": 0.2615016831731473,
|
| 4697 |
+
"grad_norm": 0.19372065365314484,
|
| 4698 |
+
"learning_rate": 0.0005,
|
| 4699 |
+
"loss": 2.6271657943725586,
|
| 4700 |
+
"step": 1340
|
| 4701 |
+
},
|
| 4702 |
+
{
|
| 4703 |
+
"epoch": 0.2618919841928087,
|
| 4704 |
+
"grad_norm": 0.18450450897216797,
|
| 4705 |
+
"learning_rate": 0.0005,
|
| 4706 |
+
"loss": 2.698676824569702,
|
| 4707 |
+
"step": 1342
|
| 4708 |
+
},
|
| 4709 |
+
{
|
| 4710 |
+
"epoch": 0.2622822852124701,
|
| 4711 |
+
"grad_norm": 0.20287057757377625,
|
| 4712 |
+
"learning_rate": 0.0005,
|
| 4713 |
+
"loss": 2.6472983360290527,
|
| 4714 |
+
"step": 1344
|
| 4715 |
+
},
|
| 4716 |
+
{
|
| 4717 |
+
"epoch": 0.2626725862321315,
|
| 4718 |
+
"grad_norm": 0.18925601243972778,
|
| 4719 |
+
"learning_rate": 0.0005,
|
| 4720 |
+
"loss": 2.6287903785705566,
|
| 4721 |
+
"step": 1346
|
| 4722 |
+
},
|
| 4723 |
+
{
|
| 4724 |
+
"epoch": 0.26306288725179294,
|
| 4725 |
+
"grad_norm": 0.18611106276512146,
|
| 4726 |
+
"learning_rate": 0.0005,
|
| 4727 |
+
"loss": 2.638305187225342,
|
| 4728 |
+
"step": 1348
|
| 4729 |
+
},
|
| 4730 |
+
{
|
| 4731 |
+
"epoch": 0.26345318827145436,
|
| 4732 |
+
"grad_norm": 0.14388009905815125,
|
| 4733 |
+
"learning_rate": 0.0005,
|
| 4734 |
+
"loss": 2.6240882873535156,
|
| 4735 |
+
"step": 1350
|
| 4736 |
+
},
|
| 4737 |
+
{
|
| 4738 |
+
"epoch": 0.2638434892911158,
|
| 4739 |
+
"grad_norm": 0.19679521024227142,
|
| 4740 |
+
"learning_rate": 0.0005,
|
| 4741 |
+
"loss": 2.6131560802459717,
|
| 4742 |
+
"step": 1352
|
| 4743 |
+
},
|
| 4744 |
+
{
|
| 4745 |
+
"epoch": 0.2642337903107772,
|
| 4746 |
+
"grad_norm": 0.16213202476501465,
|
| 4747 |
+
"learning_rate": 0.0005,
|
| 4748 |
+
"loss": 2.610975980758667,
|
| 4749 |
+
"step": 1354
|
| 4750 |
+
},
|
| 4751 |
+
{
|
| 4752 |
+
"epoch": 0.2646240913304386,
|
| 4753 |
+
"grad_norm": 0.1776195466518402,
|
| 4754 |
+
"learning_rate": 0.0005,
|
| 4755 |
+
"loss": 2.62451434135437,
|
| 4756 |
+
"step": 1356
|
| 4757 |
+
},
|
| 4758 |
+
{
|
| 4759 |
+
"epoch": 0.2650143923501,
|
| 4760 |
+
"grad_norm": 0.21855784952640533,
|
| 4761 |
+
"learning_rate": 0.0005,
|
| 4762 |
+
"loss": 2.647406578063965,
|
| 4763 |
+
"step": 1358
|
| 4764 |
+
},
|
| 4765 |
+
{
|
| 4766 |
+
"epoch": 0.2654046933697614,
|
| 4767 |
+
"grad_norm": 0.21819362044334412,
|
| 4768 |
+
"learning_rate": 0.0005,
|
| 4769 |
+
"loss": 2.664846420288086,
|
| 4770 |
+
"step": 1360
|
| 4771 |
+
},
|
| 4772 |
+
{
|
| 4773 |
+
"epoch": 0.26579499438942283,
|
| 4774 |
+
"grad_norm": 0.17997337877750397,
|
| 4775 |
+
"learning_rate": 0.0005,
|
| 4776 |
+
"loss": 2.698904037475586,
|
| 4777 |
+
"step": 1362
|
| 4778 |
+
},
|
| 4779 |
+
{
|
| 4780 |
+
"epoch": 0.26618529540908425,
|
| 4781 |
+
"grad_norm": 0.212106853723526,
|
| 4782 |
+
"learning_rate": 0.0005,
|
| 4783 |
+
"loss": 2.693112850189209,
|
| 4784 |
+
"step": 1364
|
| 4785 |
+
},
|
| 4786 |
+
{
|
| 4787 |
+
"epoch": 0.2665755964287457,
|
| 4788 |
+
"grad_norm": 0.15807080268859863,
|
| 4789 |
+
"learning_rate": 0.0005,
|
| 4790 |
+
"loss": 2.6733975410461426,
|
| 4791 |
+
"step": 1366
|
| 4792 |
+
},
|
| 4793 |
+
{
|
| 4794 |
+
"epoch": 0.2669658974484071,
|
| 4795 |
+
"grad_norm": 0.19890554249286652,
|
| 4796 |
+
"learning_rate": 0.0005,
|
| 4797 |
+
"loss": 2.6462106704711914,
|
| 4798 |
+
"step": 1368
|
| 4799 |
+
},
|
| 4800 |
+
{
|
| 4801 |
+
"epoch": 0.2673561984680685,
|
| 4802 |
+
"grad_norm": 0.15021012723445892,
|
| 4803 |
+
"learning_rate": 0.0005,
|
| 4804 |
+
"loss": 2.6667094230651855,
|
| 4805 |
+
"step": 1370
|
| 4806 |
+
},
|
| 4807 |
+
{
|
| 4808 |
+
"epoch": 0.26774649948772994,
|
| 4809 |
+
"grad_norm": 0.20262733101844788,
|
| 4810 |
+
"learning_rate": 0.0005,
|
| 4811 |
+
"loss": 2.632871627807617,
|
| 4812 |
+
"step": 1372
|
| 4813 |
+
},
|
| 4814 |
+
{
|
| 4815 |
+
"epoch": 0.2681368005073913,
|
| 4816 |
+
"grad_norm": 0.14650316536426544,
|
| 4817 |
+
"learning_rate": 0.0005,
|
| 4818 |
+
"loss": 2.699526786804199,
|
| 4819 |
+
"step": 1374
|
| 4820 |
+
},
|
| 4821 |
+
{
|
| 4822 |
+
"epoch": 0.2685271015270527,
|
| 4823 |
+
"grad_norm": 0.16043399274349213,
|
| 4824 |
+
"learning_rate": 0.0005,
|
| 4825 |
+
"loss": 2.6182048320770264,
|
| 4826 |
+
"step": 1376
|
| 4827 |
+
},
|
| 4828 |
+
{
|
| 4829 |
+
"epoch": 0.26891740254671415,
|
| 4830 |
+
"grad_norm": 0.15093420445919037,
|
| 4831 |
+
"learning_rate": 0.0005,
|
| 4832 |
+
"loss": 2.6649489402770996,
|
| 4833 |
+
"step": 1378
|
| 4834 |
+
},
|
| 4835 |
+
{
|
| 4836 |
+
"epoch": 0.26930770356637557,
|
| 4837 |
+
"grad_norm": 0.23913167417049408,
|
| 4838 |
+
"learning_rate": 0.0005,
|
| 4839 |
+
"loss": 2.6263842582702637,
|
| 4840 |
+
"step": 1380
|
| 4841 |
+
},
|
| 4842 |
+
{
|
| 4843 |
+
"epoch": 0.269698004586037,
|
| 4844 |
+
"grad_norm": 0.14618130028247833,
|
| 4845 |
+
"learning_rate": 0.0005,
|
| 4846 |
+
"loss": 2.5898988246917725,
|
| 4847 |
+
"step": 1382
|
| 4848 |
+
},
|
| 4849 |
+
{
|
| 4850 |
+
"epoch": 0.2700883056056984,
|
| 4851 |
+
"grad_norm": 0.17054583132266998,
|
| 4852 |
+
"learning_rate": 0.0005,
|
| 4853 |
+
"loss": 2.6648550033569336,
|
| 4854 |
+
"step": 1384
|
| 4855 |
+
},
|
| 4856 |
+
{
|
| 4857 |
+
"epoch": 0.27047860662535983,
|
| 4858 |
+
"grad_norm": 0.14056921005249023,
|
| 4859 |
+
"learning_rate": 0.0005,
|
| 4860 |
+
"loss": 2.6555585861206055,
|
| 4861 |
+
"step": 1386
|
| 4862 |
+
},
|
| 4863 |
+
{
|
| 4864 |
+
"epoch": 0.2708689076450212,
|
| 4865 |
+
"grad_norm": 0.1835166960954666,
|
| 4866 |
+
"learning_rate": 0.0005,
|
| 4867 |
+
"loss": 2.6208629608154297,
|
| 4868 |
+
"step": 1388
|
| 4869 |
+
},
|
| 4870 |
+
{
|
| 4871 |
+
"epoch": 0.2712592086646826,
|
| 4872 |
+
"grad_norm": 0.14292487502098083,
|
| 4873 |
+
"learning_rate": 0.0005,
|
| 4874 |
+
"loss": 2.6080708503723145,
|
| 4875 |
+
"step": 1390
|
| 4876 |
+
},
|
| 4877 |
+
{
|
| 4878 |
+
"epoch": 0.27164950968434404,
|
| 4879 |
+
"grad_norm": 0.16386844217777252,
|
| 4880 |
+
"learning_rate": 0.0005,
|
| 4881 |
+
"loss": 2.6993231773376465,
|
| 4882 |
+
"step": 1392
|
| 4883 |
+
},
|
| 4884 |
+
{
|
| 4885 |
+
"epoch": 0.27203981070400546,
|
| 4886 |
+
"grad_norm": 0.171889990568161,
|
| 4887 |
+
"learning_rate": 0.0005,
|
| 4888 |
+
"loss": 2.63179874420166,
|
| 4889 |
+
"step": 1394
|
| 4890 |
+
},
|
| 4891 |
+
{
|
| 4892 |
+
"epoch": 0.2724301117236669,
|
| 4893 |
+
"grad_norm": 0.18449833989143372,
|
| 4894 |
+
"learning_rate": 0.0005,
|
| 4895 |
+
"loss": 2.638186454772949,
|
| 4896 |
+
"step": 1396
|
| 4897 |
+
},
|
| 4898 |
+
{
|
| 4899 |
+
"epoch": 0.2728204127433283,
|
| 4900 |
+
"grad_norm": 0.16664357483386993,
|
| 4901 |
+
"learning_rate": 0.0005,
|
| 4902 |
+
"loss": 2.629894256591797,
|
| 4903 |
+
"step": 1398
|
| 4904 |
+
},
|
| 4905 |
+
{
|
| 4906 |
+
"epoch": 0.2732107137629897,
|
| 4907 |
+
"grad_norm": 0.18192005157470703,
|
| 4908 |
+
"learning_rate": 0.0005,
|
| 4909 |
+
"loss": 2.586158275604248,
|
| 4910 |
+
"step": 1400
|
| 4911 |
+
},
|
| 4912 |
+
{
|
| 4913 |
+
"epoch": 0.27360101478265114,
|
| 4914 |
+
"grad_norm": 0.25335222482681274,
|
| 4915 |
+
"learning_rate": 0.0005,
|
| 4916 |
+
"loss": 2.6383070945739746,
|
| 4917 |
+
"step": 1402
|
| 4918 |
+
},
|
| 4919 |
+
{
|
| 4920 |
+
"epoch": 0.2739913158023125,
|
| 4921 |
+
"grad_norm": 0.267530232667923,
|
| 4922 |
+
"learning_rate": 0.0005,
|
| 4923 |
+
"loss": 2.6771538257598877,
|
| 4924 |
+
"step": 1404
|
| 4925 |
+
},
|
| 4926 |
+
{
|
| 4927 |
+
"epoch": 0.27438161682197393,
|
| 4928 |
+
"grad_norm": 0.22987104952335358,
|
| 4929 |
+
"learning_rate": 0.0005,
|
| 4930 |
+
"loss": 2.681781768798828,
|
| 4931 |
+
"step": 1406
|
| 4932 |
+
},
|
| 4933 |
+
{
|
| 4934 |
+
"epoch": 0.27477191784163535,
|
| 4935 |
+
"grad_norm": 0.19172820448875427,
|
| 4936 |
+
"learning_rate": 0.0005,
|
| 4937 |
+
"loss": 2.646531105041504,
|
| 4938 |
+
"step": 1408
|
| 4939 |
+
},
|
| 4940 |
+
{
|
| 4941 |
+
"epoch": 0.27516221886129677,
|
| 4942 |
+
"grad_norm": 0.1427278220653534,
|
| 4943 |
+
"learning_rate": 0.0005,
|
| 4944 |
+
"loss": 2.6387312412261963,
|
| 4945 |
+
"step": 1410
|
| 4946 |
+
},
|
| 4947 |
+
{
|
| 4948 |
+
"epoch": 0.2755525198809582,
|
| 4949 |
+
"grad_norm": 0.15432684123516083,
|
| 4950 |
+
"learning_rate": 0.0005,
|
| 4951 |
+
"loss": 2.627262592315674,
|
| 4952 |
+
"step": 1412
|
| 4953 |
+
},
|
| 4954 |
+
{
|
| 4955 |
+
"epoch": 0.2759428209006196,
|
| 4956 |
+
"grad_norm": 0.17481695115566254,
|
| 4957 |
+
"learning_rate": 0.0005,
|
| 4958 |
+
"loss": 2.6136021614074707,
|
| 4959 |
+
"step": 1414
|
| 4960 |
+
},
|
| 4961 |
+
{
|
| 4962 |
+
"epoch": 0.27633312192028103,
|
| 4963 |
+
"grad_norm": 0.19507373869419098,
|
| 4964 |
+
"learning_rate": 0.0005,
|
| 4965 |
+
"loss": 2.6767396926879883,
|
| 4966 |
+
"step": 1416
|
| 4967 |
+
},
|
| 4968 |
+
{
|
| 4969 |
+
"epoch": 0.27672342293994245,
|
| 4970 |
+
"grad_norm": 0.1460731476545334,
|
| 4971 |
+
"learning_rate": 0.0005,
|
| 4972 |
+
"loss": 2.5625267028808594,
|
| 4973 |
+
"step": 1418
|
| 4974 |
+
},
|
| 4975 |
+
{
|
| 4976 |
+
"epoch": 0.2771137239596038,
|
| 4977 |
+
"grad_norm": 0.1814679354429245,
|
| 4978 |
+
"learning_rate": 0.0005,
|
| 4979 |
+
"loss": 2.578216552734375,
|
| 4980 |
+
"step": 1420
|
| 4981 |
+
},
|
| 4982 |
+
{
|
| 4983 |
+
"epoch": 0.27750402497926524,
|
| 4984 |
+
"grad_norm": 0.14049267768859863,
|
| 4985 |
+
"learning_rate": 0.0005,
|
| 4986 |
+
"loss": 2.666496753692627,
|
| 4987 |
+
"step": 1422
|
| 4988 |
+
},
|
| 4989 |
+
{
|
| 4990 |
+
"epoch": 0.27789432599892666,
|
| 4991 |
+
"grad_norm": 0.17616279423236847,
|
| 4992 |
+
"learning_rate": 0.0005,
|
| 4993 |
+
"loss": 2.675088882446289,
|
| 4994 |
+
"step": 1424
|
| 4995 |
+
},
|
| 4996 |
+
{
|
| 4997 |
+
"epoch": 0.2782846270185881,
|
| 4998 |
+
"grad_norm": 0.1596374213695526,
|
| 4999 |
+
"learning_rate": 0.0005,
|
| 5000 |
+
"loss": 2.6127424240112305,
|
| 5001 |
+
"step": 1426
|
| 5002 |
+
},
|
| 5003 |
+
{
|
| 5004 |
+
"epoch": 0.2786749280382495,
|
| 5005 |
+
"grad_norm": 0.2415485829114914,
|
| 5006 |
+
"learning_rate": 0.0005,
|
| 5007 |
+
"loss": 2.6475510597229004,
|
| 5008 |
+
"step": 1428
|
| 5009 |
+
},
|
| 5010 |
+
{
|
| 5011 |
+
"epoch": 0.2790652290579109,
|
| 5012 |
+
"grad_norm": 0.21824443340301514,
|
| 5013 |
+
"learning_rate": 0.0005,
|
| 5014 |
+
"loss": 2.6739721298217773,
|
| 5015 |
+
"step": 1430
|
| 5016 |
+
},
|
| 5017 |
+
{
|
| 5018 |
+
"epoch": 0.27945553007757234,
|
| 5019 |
+
"grad_norm": 0.15533924102783203,
|
| 5020 |
+
"learning_rate": 0.0005,
|
| 5021 |
+
"loss": 2.634955406188965,
|
| 5022 |
+
"step": 1432
|
| 5023 |
+
},
|
| 5024 |
+
{
|
| 5025 |
+
"epoch": 0.27984583109723377,
|
| 5026 |
+
"grad_norm": 0.20020627975463867,
|
| 5027 |
+
"learning_rate": 0.0005,
|
| 5028 |
+
"loss": 2.6981163024902344,
|
| 5029 |
+
"step": 1434
|
| 5030 |
+
},
|
| 5031 |
+
{
|
| 5032 |
+
"epoch": 0.28023613211689513,
|
| 5033 |
+
"grad_norm": 0.13198453187942505,
|
| 5034 |
+
"learning_rate": 0.0005,
|
| 5035 |
+
"loss": 2.6461915969848633,
|
| 5036 |
+
"step": 1436
|
| 5037 |
+
},
|
| 5038 |
+
{
|
| 5039 |
+
"epoch": 0.28062643313655655,
|
| 5040 |
+
"grad_norm": 0.1408434510231018,
|
| 5041 |
+
"learning_rate": 0.0005,
|
| 5042 |
+
"loss": 2.600557565689087,
|
| 5043 |
+
"step": 1438
|
| 5044 |
+
},
|
| 5045 |
+
{
|
| 5046 |
+
"epoch": 0.281016734156218,
|
| 5047 |
+
"grad_norm": 0.17344576120376587,
|
| 5048 |
+
"learning_rate": 0.0005,
|
| 5049 |
+
"loss": 2.667851448059082,
|
| 5050 |
+
"step": 1440
|
| 5051 |
+
},
|
| 5052 |
+
{
|
| 5053 |
+
"epoch": 0.2814070351758794,
|
| 5054 |
+
"grad_norm": 0.24338749051094055,
|
| 5055 |
+
"learning_rate": 0.0005,
|
| 5056 |
+
"loss": 2.6585168838500977,
|
| 5057 |
+
"step": 1442
|
| 5058 |
+
},
|
| 5059 |
+
{
|
| 5060 |
+
"epoch": 0.2817973361955408,
|
| 5061 |
+
"grad_norm": 0.148707315325737,
|
| 5062 |
+
"learning_rate": 0.0005,
|
| 5063 |
+
"loss": 2.6372299194335938,
|
| 5064 |
+
"step": 1444
|
| 5065 |
+
},
|
| 5066 |
+
{
|
| 5067 |
+
"epoch": 0.28218763721520224,
|
| 5068 |
+
"grad_norm": 0.14963465929031372,
|
| 5069 |
+
"learning_rate": 0.0005,
|
| 5070 |
+
"loss": 2.649763584136963,
|
| 5071 |
+
"step": 1446
|
| 5072 |
+
},
|
| 5073 |
+
{
|
| 5074 |
+
"epoch": 0.28257793823486366,
|
| 5075 |
+
"grad_norm": 0.1544618010520935,
|
| 5076 |
+
"learning_rate": 0.0005,
|
| 5077 |
+
"loss": 2.6491479873657227,
|
| 5078 |
+
"step": 1448
|
| 5079 |
+
},
|
| 5080 |
+
{
|
| 5081 |
+
"epoch": 0.2829682392545251,
|
| 5082 |
+
"grad_norm": 0.16365410387516022,
|
| 5083 |
+
"learning_rate": 0.0005,
|
| 5084 |
+
"loss": 2.6375744342803955,
|
| 5085 |
+
"step": 1450
|
| 5086 |
+
},
|
| 5087 |
+
{
|
| 5088 |
+
"epoch": 0.28335854027418644,
|
| 5089 |
+
"grad_norm": 0.1884186863899231,
|
| 5090 |
+
"learning_rate": 0.0005,
|
| 5091 |
+
"loss": 2.633155345916748,
|
| 5092 |
+
"step": 1452
|
| 5093 |
+
},
|
| 5094 |
+
{
|
| 5095 |
+
"epoch": 0.28374884129384786,
|
| 5096 |
+
"grad_norm": 0.17301738262176514,
|
| 5097 |
+
"learning_rate": 0.0005,
|
| 5098 |
+
"loss": 2.6472535133361816,
|
| 5099 |
+
"step": 1454
|
| 5100 |
+
},
|
| 5101 |
+
{
|
| 5102 |
+
"epoch": 0.2841391423135093,
|
| 5103 |
+
"grad_norm": 0.15670183300971985,
|
| 5104 |
+
"learning_rate": 0.0005,
|
| 5105 |
+
"loss": 2.612581729888916,
|
| 5106 |
+
"step": 1456
|
| 5107 |
+
},
|
| 5108 |
+
{
|
| 5109 |
+
"epoch": 0.2845294433331707,
|
| 5110 |
+
"grad_norm": 0.19180981814861298,
|
| 5111 |
+
"learning_rate": 0.0005,
|
| 5112 |
+
"loss": 2.713303565979004,
|
| 5113 |
+
"step": 1458
|
| 5114 |
+
},
|
| 5115 |
+
{
|
| 5116 |
+
"epoch": 0.2849197443528321,
|
| 5117 |
+
"grad_norm": 0.1664300411939621,
|
| 5118 |
+
"learning_rate": 0.0005,
|
| 5119 |
+
"loss": 2.665194511413574,
|
| 5120 |
+
"step": 1460
|
| 5121 |
+
},
|
| 5122 |
+
{
|
| 5123 |
+
"epoch": 0.28531004537249355,
|
| 5124 |
+
"grad_norm": 0.15772509574890137,
|
| 5125 |
+
"learning_rate": 0.0005,
|
| 5126 |
+
"loss": 2.631179094314575,
|
| 5127 |
+
"step": 1462
|
| 5128 |
+
},
|
| 5129 |
+
{
|
| 5130 |
+
"epoch": 0.28570034639215497,
|
| 5131 |
+
"grad_norm": 0.15448671579360962,
|
| 5132 |
+
"learning_rate": 0.0005,
|
| 5133 |
+
"loss": 2.591111660003662,
|
| 5134 |
+
"step": 1464
|
| 5135 |
+
},
|
| 5136 |
+
{
|
| 5137 |
+
"epoch": 0.2860906474118164,
|
| 5138 |
+
"grad_norm": 0.22612318396568298,
|
| 5139 |
+
"learning_rate": 0.0005,
|
| 5140 |
+
"loss": 2.666761875152588,
|
| 5141 |
+
"step": 1466
|
| 5142 |
+
},
|
| 5143 |
+
{
|
| 5144 |
+
"epoch": 0.28648094843147776,
|
| 5145 |
+
"grad_norm": 0.1750580072402954,
|
| 5146 |
+
"learning_rate": 0.0005,
|
| 5147 |
+
"loss": 2.68807315826416,
|
| 5148 |
+
"step": 1468
|
| 5149 |
+
},
|
| 5150 |
+
{
|
| 5151 |
+
"epoch": 0.2868712494511392,
|
| 5152 |
+
"grad_norm": 0.13825853168964386,
|
| 5153 |
+
"learning_rate": 0.0005,
|
| 5154 |
+
"loss": 2.6087088584899902,
|
| 5155 |
+
"step": 1470
|
| 5156 |
+
},
|
| 5157 |
+
{
|
| 5158 |
+
"epoch": 0.2872615504708006,
|
| 5159 |
+
"grad_norm": 0.2334652543067932,
|
| 5160 |
+
"learning_rate": 0.0005,
|
| 5161 |
+
"loss": 2.660336494445801,
|
| 5162 |
+
"step": 1472
|
| 5163 |
+
},
|
| 5164 |
+
{
|
| 5165 |
+
"epoch": 0.287651851490462,
|
| 5166 |
+
"grad_norm": 0.1441940814256668,
|
| 5167 |
+
"learning_rate": 0.0005,
|
| 5168 |
+
"loss": 2.6621580123901367,
|
| 5169 |
+
"step": 1474
|
| 5170 |
+
},
|
| 5171 |
+
{
|
| 5172 |
+
"epoch": 0.28804215251012344,
|
| 5173 |
+
"grad_norm": 0.14643435180187225,
|
| 5174 |
+
"learning_rate": 0.0005,
|
| 5175 |
+
"loss": 2.6694321632385254,
|
| 5176 |
+
"step": 1476
|
| 5177 |
+
},
|
| 5178 |
+
{
|
| 5179 |
+
"epoch": 0.28843245352978486,
|
| 5180 |
+
"grad_norm": 0.20707924664020538,
|
| 5181 |
+
"learning_rate": 0.0005,
|
| 5182 |
+
"loss": 2.6435389518737793,
|
| 5183 |
+
"step": 1478
|
| 5184 |
+
},
|
| 5185 |
+
{
|
| 5186 |
+
"epoch": 0.2888227545494463,
|
| 5187 |
+
"grad_norm": 0.16502735018730164,
|
| 5188 |
+
"learning_rate": 0.0005,
|
| 5189 |
+
"loss": 2.5641443729400635,
|
| 5190 |
+
"step": 1480
|
| 5191 |
+
},
|
| 5192 |
+
{
|
| 5193 |
+
"epoch": 0.28921305556910765,
|
| 5194 |
+
"grad_norm": 0.15948647260665894,
|
| 5195 |
+
"learning_rate": 0.0005,
|
| 5196 |
+
"loss": 2.653017520904541,
|
| 5197 |
+
"step": 1482
|
| 5198 |
+
},
|
| 5199 |
+
{
|
| 5200 |
+
"epoch": 0.28960335658876907,
|
| 5201 |
+
"grad_norm": 0.17387966811656952,
|
| 5202 |
+
"learning_rate": 0.0005,
|
| 5203 |
+
"loss": 2.6588568687438965,
|
| 5204 |
+
"step": 1484
|
| 5205 |
+
},
|
| 5206 |
+
{
|
| 5207 |
+
"epoch": 0.2899936576084305,
|
| 5208 |
+
"grad_norm": 0.2062239795923233,
|
| 5209 |
+
"learning_rate": 0.0005,
|
| 5210 |
+
"loss": 2.6489620208740234,
|
| 5211 |
+
"step": 1486
|
| 5212 |
+
},
|
| 5213 |
+
{
|
| 5214 |
+
"epoch": 0.2903839586280919,
|
| 5215 |
+
"grad_norm": 0.17745979130268097,
|
| 5216 |
+
"learning_rate": 0.0005,
|
| 5217 |
+
"loss": 2.652431011199951,
|
| 5218 |
+
"step": 1488
|
| 5219 |
+
},
|
| 5220 |
+
{
|
| 5221 |
+
"epoch": 0.29077425964775333,
|
| 5222 |
+
"grad_norm": 0.179817333817482,
|
| 5223 |
+
"learning_rate": 0.0005,
|
| 5224 |
+
"loss": 2.5700745582580566,
|
| 5225 |
+
"step": 1490
|
| 5226 |
+
},
|
| 5227 |
+
{
|
| 5228 |
+
"epoch": 0.29116456066741475,
|
| 5229 |
+
"grad_norm": 0.17727622389793396,
|
| 5230 |
+
"learning_rate": 0.0005,
|
| 5231 |
+
"loss": 2.675889015197754,
|
| 5232 |
+
"step": 1492
|
| 5233 |
+
},
|
| 5234 |
+
{
|
| 5235 |
+
"epoch": 0.29155486168707617,
|
| 5236 |
+
"grad_norm": 0.14784477651119232,
|
| 5237 |
+
"learning_rate": 0.0005,
|
| 5238 |
+
"loss": 2.5987794399261475,
|
| 5239 |
+
"step": 1494
|
| 5240 |
+
},
|
| 5241 |
+
{
|
| 5242 |
+
"epoch": 0.2919451627067376,
|
| 5243 |
+
"grad_norm": 0.276790052652359,
|
| 5244 |
+
"learning_rate": 0.0005,
|
| 5245 |
+
"loss": 2.6098380088806152,
|
| 5246 |
+
"step": 1496
|
| 5247 |
+
},
|
| 5248 |
+
{
|
| 5249 |
+
"epoch": 0.29233546372639896,
|
| 5250 |
+
"grad_norm": 0.19852863252162933,
|
| 5251 |
+
"learning_rate": 0.0005,
|
| 5252 |
+
"loss": 2.6523208618164062,
|
| 5253 |
+
"step": 1498
|
| 5254 |
+
},
|
| 5255 |
+
{
|
| 5256 |
+
"epoch": 0.2927257647460604,
|
| 5257 |
+
"grad_norm": 0.16179384291172028,
|
| 5258 |
+
"learning_rate": 0.0005,
|
| 5259 |
+
"loss": 2.6403732299804688,
|
| 5260 |
+
"step": 1500
|
| 5261 |
+
},
|
| 5262 |
+
{
|
| 5263 |
+
"epoch": 0.2931160657657218,
|
| 5264 |
+
"grad_norm": 0.24509850144386292,
|
| 5265 |
+
"learning_rate": 0.0005,
|
| 5266 |
+
"loss": 2.5754945278167725,
|
| 5267 |
+
"step": 1502
|
| 5268 |
+
},
|
| 5269 |
+
{
|
| 5270 |
+
"epoch": 0.2935063667853832,
|
| 5271 |
+
"grad_norm": 0.14187762141227722,
|
| 5272 |
+
"learning_rate": 0.0005,
|
| 5273 |
+
"loss": 2.6274304389953613,
|
| 5274 |
+
"step": 1504
|
| 5275 |
+
},
|
| 5276 |
+
{
|
| 5277 |
+
"epoch": 0.29389666780504464,
|
| 5278 |
+
"grad_norm": 0.1486518383026123,
|
| 5279 |
+
"learning_rate": 0.0005,
|
| 5280 |
+
"loss": 2.5842506885528564,
|
| 5281 |
+
"step": 1506
|
| 5282 |
+
},
|
| 5283 |
+
{
|
| 5284 |
+
"epoch": 0.29428696882470606,
|
| 5285 |
+
"grad_norm": 0.17727719247341156,
|
| 5286 |
+
"learning_rate": 0.0005,
|
| 5287 |
+
"loss": 2.5887818336486816,
|
| 5288 |
+
"step": 1508
|
| 5289 |
+
},
|
| 5290 |
+
{
|
| 5291 |
+
"epoch": 0.2946772698443675,
|
| 5292 |
+
"grad_norm": 0.16822102665901184,
|
| 5293 |
+
"learning_rate": 0.0005,
|
| 5294 |
+
"loss": 2.581908941268921,
|
| 5295 |
+
"step": 1510
|
| 5296 |
+
},
|
| 5297 |
+
{
|
| 5298 |
+
"epoch": 0.2950675708640289,
|
| 5299 |
+
"grad_norm": 0.15242864191532135,
|
| 5300 |
+
"learning_rate": 0.0005,
|
| 5301 |
+
"loss": 2.655117988586426,
|
| 5302 |
+
"step": 1512
|
| 5303 |
+
},
|
| 5304 |
+
{
|
| 5305 |
+
"epoch": 0.29545787188369027,
|
| 5306 |
+
"grad_norm": 0.16434399783611298,
|
| 5307 |
+
"learning_rate": 0.0005,
|
| 5308 |
+
"loss": 2.620103359222412,
|
| 5309 |
+
"step": 1514
|
| 5310 |
+
},
|
| 5311 |
+
{
|
| 5312 |
+
"epoch": 0.2958481729033517,
|
| 5313 |
+
"grad_norm": 0.21713203191757202,
|
| 5314 |
+
"learning_rate": 0.0005,
|
| 5315 |
+
"loss": 2.6464579105377197,
|
| 5316 |
+
"step": 1516
|
| 5317 |
+
},
|
| 5318 |
+
{
|
| 5319 |
+
"epoch": 0.2962384739230131,
|
| 5320 |
+
"grad_norm": 0.20833119750022888,
|
| 5321 |
+
"learning_rate": 0.0005,
|
| 5322 |
+
"loss": 2.6051602363586426,
|
| 5323 |
+
"step": 1518
|
| 5324 |
+
},
|
| 5325 |
+
{
|
| 5326 |
+
"epoch": 0.29662877494267453,
|
| 5327 |
+
"grad_norm": 0.20915855467319489,
|
| 5328 |
+
"learning_rate": 0.0005,
|
| 5329 |
+
"loss": 2.6383514404296875,
|
| 5330 |
+
"step": 1520
|
| 5331 |
+
},
|
| 5332 |
+
{
|
| 5333 |
+
"epoch": 0.29701907596233595,
|
| 5334 |
+
"grad_norm": 0.17045031487941742,
|
| 5335 |
+
"learning_rate": 0.0005,
|
| 5336 |
+
"loss": 2.6242146492004395,
|
| 5337 |
+
"step": 1522
|
| 5338 |
+
},
|
| 5339 |
+
{
|
| 5340 |
+
"epoch": 0.2974093769819974,
|
| 5341 |
+
"grad_norm": 0.1593632847070694,
|
| 5342 |
+
"learning_rate": 0.0005,
|
| 5343 |
+
"loss": 2.598170518875122,
|
| 5344 |
+
"step": 1524
|
| 5345 |
+
},
|
| 5346 |
+
{
|
| 5347 |
+
"epoch": 0.2977996780016588,
|
| 5348 |
+
"grad_norm": 0.16116036474704742,
|
| 5349 |
+
"learning_rate": 0.0005,
|
| 5350 |
+
"loss": 2.584566116333008,
|
| 5351 |
+
"step": 1526
|
| 5352 |
+
},
|
| 5353 |
+
{
|
| 5354 |
+
"epoch": 0.2981899790213202,
|
| 5355 |
+
"grad_norm": 0.16313987970352173,
|
| 5356 |
+
"learning_rate": 0.0005,
|
| 5357 |
+
"loss": 2.670088768005371,
|
| 5358 |
+
"step": 1528
|
| 5359 |
+
},
|
| 5360 |
+
{
|
| 5361 |
+
"epoch": 0.2985802800409816,
|
| 5362 |
+
"grad_norm": 0.18392567336559296,
|
| 5363 |
+
"learning_rate": 0.0005,
|
| 5364 |
+
"loss": 2.6641993522644043,
|
| 5365 |
+
"step": 1530
|
| 5366 |
+
},
|
| 5367 |
+
{
|
| 5368 |
+
"epoch": 0.298970581060643,
|
| 5369 |
+
"grad_norm": 0.1360444277524948,
|
| 5370 |
+
"learning_rate": 0.0005,
|
| 5371 |
+
"loss": 2.695345878601074,
|
| 5372 |
+
"step": 1532
|
| 5373 |
+
},
|
| 5374 |
+
{
|
| 5375 |
+
"epoch": 0.2993608820803044,
|
| 5376 |
+
"grad_norm": 0.16506779193878174,
|
| 5377 |
+
"learning_rate": 0.0005,
|
| 5378 |
+
"loss": 2.61539363861084,
|
| 5379 |
+
"step": 1534
|
| 5380 |
+
},
|
| 5381 |
+
{
|
| 5382 |
+
"epoch": 0.29975118309996585,
|
| 5383 |
+
"grad_norm": 0.21025502681732178,
|
| 5384 |
+
"learning_rate": 0.0005,
|
| 5385 |
+
"loss": 2.6130847930908203,
|
| 5386 |
+
"step": 1536
|
| 5387 |
+
},
|
| 5388 |
+
{
|
| 5389 |
+
"epoch": 0.30014148411962727,
|
| 5390 |
+
"grad_norm": 0.1540633738040924,
|
| 5391 |
+
"learning_rate": 0.0005,
|
| 5392 |
+
"loss": 2.607491970062256,
|
| 5393 |
+
"step": 1538
|
| 5394 |
}
|
| 5395 |
],
|
| 5396 |
"logging_steps": 2,
|
|
|
|
| 5410 |
"attributes": {}
|
| 5411 |
}
|
| 5412 |
},
|
| 5413 |
+
"total_flos": 4.916575490791178e+17,
|
| 5414 |
"train_batch_size": 6,
|
| 5415 |
"trial_name": null,
|
| 5416 |
"trial_params": null
|