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 4104, 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 sha256:72b288210ad316b7565629b2cd0a7ae9ff0c93f7e830bac63df538770b8000a1
|
| 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:e7bfea93e85dd3c98867d1f4b478596a805e1f7f2009e4cc020e935ba09219b0
|
| 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:d83a089e45caadf4c2f5dc032185dd681b836d7a47cf0ab8f08dadd60193ec33
|
| 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,
|
|
@@ -12573,6 +12573,1805 @@
|
|
| 12573 |
"learning_rate": 0.0002601626016260163,
|
| 12574 |
"loss": 2.5957744121551514,
|
| 12575 |
"step": 3590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12576 |
}
|
| 12577 |
],
|
| 12578 |
"logging_steps": 2,
|
|
@@ -12592,7 +14391,7 @@
|
|
| 12592 |
"attributes": {}
|
| 12593 |
}
|
| 12594 |
},
|
| 12595 |
-
"total_flos": 1.
|
| 12596 |
"train_batch_size": 6,
|
| 12597 |
"trial_name": null,
|
| 12598 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8008976923452212,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4104,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12573 |
"learning_rate": 0.0002601626016260163,
|
| 12574 |
"loss": 2.5957744121551514,
|
| 12575 |
"step": 3590
|
| 12576 |
+
},
|
| 12577 |
+
{
|
| 12578 |
+
"epoch": 0.7009806313118992,
|
| 12579 |
+
"grad_norm": 0.1754528284072876,
|
| 12580 |
+
"learning_rate": 0.0002598238482384824,
|
| 12581 |
+
"loss": 2.613527774810791,
|
| 12582 |
+
"step": 3592
|
| 12583 |
+
},
|
| 12584 |
+
{
|
| 12585 |
+
"epoch": 0.7013709323315607,
|
| 12586 |
+
"grad_norm": 0.17513103783130646,
|
| 12587 |
+
"learning_rate": 0.0002594850948509485,
|
| 12588 |
+
"loss": 2.579082489013672,
|
| 12589 |
+
"step": 3594
|
| 12590 |
+
},
|
| 12591 |
+
{
|
| 12592 |
+
"epoch": 0.7017612333512221,
|
| 12593 |
+
"grad_norm": 0.16171076893806458,
|
| 12594 |
+
"learning_rate": 0.00025914634146341465,
|
| 12595 |
+
"loss": 2.5725207328796387,
|
| 12596 |
+
"step": 3596
|
| 12597 |
+
},
|
| 12598 |
+
{
|
| 12599 |
+
"epoch": 0.7021515343708835,
|
| 12600 |
+
"grad_norm": 0.19073346257209778,
|
| 12601 |
+
"learning_rate": 0.0002588075880758808,
|
| 12602 |
+
"loss": 2.567526340484619,
|
| 12603 |
+
"step": 3598
|
| 12604 |
+
},
|
| 12605 |
+
{
|
| 12606 |
+
"epoch": 0.7025418353905449,
|
| 12607 |
+
"grad_norm": 0.15010946989059448,
|
| 12608 |
+
"learning_rate": 0.00025846883468834685,
|
| 12609 |
+
"loss": 2.5593767166137695,
|
| 12610 |
+
"step": 3600
|
| 12611 |
+
},
|
| 12612 |
+
{
|
| 12613 |
+
"epoch": 0.7029321364102064,
|
| 12614 |
+
"grad_norm": 0.150939479470253,
|
| 12615 |
+
"learning_rate": 0.000258130081300813,
|
| 12616 |
+
"loss": 2.5957326889038086,
|
| 12617 |
+
"step": 3602
|
| 12618 |
+
},
|
| 12619 |
+
{
|
| 12620 |
+
"epoch": 0.7033224374298678,
|
| 12621 |
+
"grad_norm": 0.1960722953081131,
|
| 12622 |
+
"learning_rate": 0.00025779132791327916,
|
| 12623 |
+
"loss": 2.572622299194336,
|
| 12624 |
+
"step": 3604
|
| 12625 |
+
},
|
| 12626 |
+
{
|
| 12627 |
+
"epoch": 0.7037127384495292,
|
| 12628 |
+
"grad_norm": 0.19099275767803192,
|
| 12629 |
+
"learning_rate": 0.00025745257452574526,
|
| 12630 |
+
"loss": 2.5430288314819336,
|
| 12631 |
+
"step": 3606
|
| 12632 |
+
},
|
| 12633 |
+
{
|
| 12634 |
+
"epoch": 0.7041030394691906,
|
| 12635 |
+
"grad_norm": 0.16275644302368164,
|
| 12636 |
+
"learning_rate": 0.0002571138211382114,
|
| 12637 |
+
"loss": 2.62909197807312,
|
| 12638 |
+
"step": 3608
|
| 12639 |
+
},
|
| 12640 |
+
{
|
| 12641 |
+
"epoch": 0.704493340488852,
|
| 12642 |
+
"grad_norm": 0.15047980844974518,
|
| 12643 |
+
"learning_rate": 0.0002567750677506775,
|
| 12644 |
+
"loss": 2.4940528869628906,
|
| 12645 |
+
"step": 3610
|
| 12646 |
+
},
|
| 12647 |
+
{
|
| 12648 |
+
"epoch": 0.7048836415085135,
|
| 12649 |
+
"grad_norm": 0.17918576300144196,
|
| 12650 |
+
"learning_rate": 0.0002564363143631436,
|
| 12651 |
+
"loss": 2.5835700035095215,
|
| 12652 |
+
"step": 3612
|
| 12653 |
+
},
|
| 12654 |
+
{
|
| 12655 |
+
"epoch": 0.7052739425281749,
|
| 12656 |
+
"grad_norm": 0.1997525691986084,
|
| 12657 |
+
"learning_rate": 0.00025609756097560977,
|
| 12658 |
+
"loss": 2.6007537841796875,
|
| 12659 |
+
"step": 3614
|
| 12660 |
+
},
|
| 12661 |
+
{
|
| 12662 |
+
"epoch": 0.7056642435478363,
|
| 12663 |
+
"grad_norm": 0.18122833967208862,
|
| 12664 |
+
"learning_rate": 0.0002557588075880759,
|
| 12665 |
+
"loss": 2.540205955505371,
|
| 12666 |
+
"step": 3616
|
| 12667 |
+
},
|
| 12668 |
+
{
|
| 12669 |
+
"epoch": 0.7060545445674977,
|
| 12670 |
+
"grad_norm": 0.17545130848884583,
|
| 12671 |
+
"learning_rate": 0.00025542005420054197,
|
| 12672 |
+
"loss": 2.619096279144287,
|
| 12673 |
+
"step": 3618
|
| 12674 |
+
},
|
| 12675 |
+
{
|
| 12676 |
+
"epoch": 0.7064448455871591,
|
| 12677 |
+
"grad_norm": 0.16146087646484375,
|
| 12678 |
+
"learning_rate": 0.0002550813008130081,
|
| 12679 |
+
"loss": 2.592935085296631,
|
| 12680 |
+
"step": 3620
|
| 12681 |
+
},
|
| 12682 |
+
{
|
| 12683 |
+
"epoch": 0.7068351466068206,
|
| 12684 |
+
"grad_norm": 0.20610985159873962,
|
| 12685 |
+
"learning_rate": 0.0002547425474254743,
|
| 12686 |
+
"loss": 2.5900044441223145,
|
| 12687 |
+
"step": 3622
|
| 12688 |
+
},
|
| 12689 |
+
{
|
| 12690 |
+
"epoch": 0.7072254476264819,
|
| 12691 |
+
"grad_norm": 0.16959741711616516,
|
| 12692 |
+
"learning_rate": 0.0002544037940379404,
|
| 12693 |
+
"loss": 2.5836760997772217,
|
| 12694 |
+
"step": 3624
|
| 12695 |
+
},
|
| 12696 |
+
{
|
| 12697 |
+
"epoch": 0.7076157486461433,
|
| 12698 |
+
"grad_norm": 0.18046683073043823,
|
| 12699 |
+
"learning_rate": 0.00025406504065040653,
|
| 12700 |
+
"loss": 2.616224765777588,
|
| 12701 |
+
"step": 3626
|
| 12702 |
+
},
|
| 12703 |
+
{
|
| 12704 |
+
"epoch": 0.7080060496658047,
|
| 12705 |
+
"grad_norm": 0.13885509967803955,
|
| 12706 |
+
"learning_rate": 0.00025372628726287263,
|
| 12707 |
+
"loss": 2.619539737701416,
|
| 12708 |
+
"step": 3628
|
| 12709 |
+
},
|
| 12710 |
+
{
|
| 12711 |
+
"epoch": 0.7083963506854661,
|
| 12712 |
+
"grad_norm": 0.19657820463180542,
|
| 12713 |
+
"learning_rate": 0.00025338753387533873,
|
| 12714 |
+
"loss": 2.549527168273926,
|
| 12715 |
+
"step": 3630
|
| 12716 |
+
},
|
| 12717 |
+
{
|
| 12718 |
+
"epoch": 0.7087866517051276,
|
| 12719 |
+
"grad_norm": 0.17390896379947662,
|
| 12720 |
+
"learning_rate": 0.0002530487804878049,
|
| 12721 |
+
"loss": 2.530850887298584,
|
| 12722 |
+
"step": 3632
|
| 12723 |
+
},
|
| 12724 |
+
{
|
| 12725 |
+
"epoch": 0.709176952724789,
|
| 12726 |
+
"grad_norm": 0.14743547141551971,
|
| 12727 |
+
"learning_rate": 0.00025271002710027104,
|
| 12728 |
+
"loss": 2.5349106788635254,
|
| 12729 |
+
"step": 3634
|
| 12730 |
+
},
|
| 12731 |
+
{
|
| 12732 |
+
"epoch": 0.7095672537444504,
|
| 12733 |
+
"grad_norm": 0.14968833327293396,
|
| 12734 |
+
"learning_rate": 0.00025237127371273714,
|
| 12735 |
+
"loss": 2.591017961502075,
|
| 12736 |
+
"step": 3636
|
| 12737 |
+
},
|
| 12738 |
+
{
|
| 12739 |
+
"epoch": 0.7099575547641118,
|
| 12740 |
+
"grad_norm": 0.18333618342876434,
|
| 12741 |
+
"learning_rate": 0.00025203252032520324,
|
| 12742 |
+
"loss": 2.5644774436950684,
|
| 12743 |
+
"step": 3638
|
| 12744 |
+
},
|
| 12745 |
+
{
|
| 12746 |
+
"epoch": 0.7103478557837732,
|
| 12747 |
+
"grad_norm": 0.17144332826137543,
|
| 12748 |
+
"learning_rate": 0.0002516937669376694,
|
| 12749 |
+
"loss": 2.5768604278564453,
|
| 12750 |
+
"step": 3640
|
| 12751 |
+
},
|
| 12752 |
+
{
|
| 12753 |
+
"epoch": 0.7107381568034347,
|
| 12754 |
+
"grad_norm": 0.1740250587463379,
|
| 12755 |
+
"learning_rate": 0.0002513550135501355,
|
| 12756 |
+
"loss": 2.5115652084350586,
|
| 12757 |
+
"step": 3642
|
| 12758 |
+
},
|
| 12759 |
+
{
|
| 12760 |
+
"epoch": 0.7111284578230961,
|
| 12761 |
+
"grad_norm": 0.1626097410917282,
|
| 12762 |
+
"learning_rate": 0.00025101626016260165,
|
| 12763 |
+
"loss": 2.537477493286133,
|
| 12764 |
+
"step": 3644
|
| 12765 |
+
},
|
| 12766 |
+
{
|
| 12767 |
+
"epoch": 0.7115187588427575,
|
| 12768 |
+
"grad_norm": 0.19681110978126526,
|
| 12769 |
+
"learning_rate": 0.00025067750677506775,
|
| 12770 |
+
"loss": 2.6046791076660156,
|
| 12771 |
+
"step": 3646
|
| 12772 |
+
},
|
| 12773 |
+
{
|
| 12774 |
+
"epoch": 0.7119090598624189,
|
| 12775 |
+
"grad_norm": 0.18500809371471405,
|
| 12776 |
+
"learning_rate": 0.00025033875338753385,
|
| 12777 |
+
"loss": 2.5758230686187744,
|
| 12778 |
+
"step": 3648
|
| 12779 |
+
},
|
| 12780 |
+
{
|
| 12781 |
+
"epoch": 0.7122993608820803,
|
| 12782 |
+
"grad_norm": 0.1448865383863449,
|
| 12783 |
+
"learning_rate": 0.00025,
|
| 12784 |
+
"loss": 2.6039533615112305,
|
| 12785 |
+
"step": 3650
|
| 12786 |
+
},
|
| 12787 |
+
{
|
| 12788 |
+
"epoch": 0.7126896619017418,
|
| 12789 |
+
"grad_norm": 0.19092422723770142,
|
| 12790 |
+
"learning_rate": 0.00024966124661246616,
|
| 12791 |
+
"loss": 2.6012842655181885,
|
| 12792 |
+
"step": 3652
|
| 12793 |
+
},
|
| 12794 |
+
{
|
| 12795 |
+
"epoch": 0.7130799629214032,
|
| 12796 |
+
"grad_norm": 0.14865967631340027,
|
| 12797 |
+
"learning_rate": 0.00024932249322493226,
|
| 12798 |
+
"loss": 2.56658673286438,
|
| 12799 |
+
"step": 3654
|
| 12800 |
+
},
|
| 12801 |
+
{
|
| 12802 |
+
"epoch": 0.7134702639410645,
|
| 12803 |
+
"grad_norm": 0.14403767883777618,
|
| 12804 |
+
"learning_rate": 0.0002489837398373984,
|
| 12805 |
+
"loss": 2.5634608268737793,
|
| 12806 |
+
"step": 3656
|
| 12807 |
+
},
|
| 12808 |
+
{
|
| 12809 |
+
"epoch": 0.7138605649607259,
|
| 12810 |
+
"grad_norm": 0.20479664206504822,
|
| 12811 |
+
"learning_rate": 0.0002486449864498645,
|
| 12812 |
+
"loss": 2.5688934326171875,
|
| 12813 |
+
"step": 3658
|
| 12814 |
+
},
|
| 12815 |
+
{
|
| 12816 |
+
"epoch": 0.7142508659803873,
|
| 12817 |
+
"grad_norm": 0.1600894033908844,
|
| 12818 |
+
"learning_rate": 0.0002483062330623306,
|
| 12819 |
+
"loss": 2.538386106491089,
|
| 12820 |
+
"step": 3660
|
| 12821 |
+
},
|
| 12822 |
+
{
|
| 12823 |
+
"epoch": 0.7146411670000488,
|
| 12824 |
+
"grad_norm": 0.2378336638212204,
|
| 12825 |
+
"learning_rate": 0.0002479674796747967,
|
| 12826 |
+
"loss": 2.5765857696533203,
|
| 12827 |
+
"step": 3662
|
| 12828 |
+
},
|
| 12829 |
+
{
|
| 12830 |
+
"epoch": 0.7150314680197102,
|
| 12831 |
+
"grad_norm": 0.17111937701702118,
|
| 12832 |
+
"learning_rate": 0.00024762872628726287,
|
| 12833 |
+
"loss": 2.5072760581970215,
|
| 12834 |
+
"step": 3664
|
| 12835 |
+
},
|
| 12836 |
+
{
|
| 12837 |
+
"epoch": 0.7154217690393716,
|
| 12838 |
+
"grad_norm": 0.17559227347373962,
|
| 12839 |
+
"learning_rate": 0.000247289972899729,
|
| 12840 |
+
"loss": 2.6031670570373535,
|
| 12841 |
+
"step": 3666
|
| 12842 |
+
},
|
| 12843 |
+
{
|
| 12844 |
+
"epoch": 0.715812070059033,
|
| 12845 |
+
"grad_norm": 0.16444411873817444,
|
| 12846 |
+
"learning_rate": 0.0002469512195121951,
|
| 12847 |
+
"loss": 2.575005531311035,
|
| 12848 |
+
"step": 3668
|
| 12849 |
+
},
|
| 12850 |
+
{
|
| 12851 |
+
"epoch": 0.7162023710786944,
|
| 12852 |
+
"grad_norm": 0.18452920019626617,
|
| 12853 |
+
"learning_rate": 0.0002466124661246613,
|
| 12854 |
+
"loss": 2.630385398864746,
|
| 12855 |
+
"step": 3670
|
| 12856 |
+
},
|
| 12857 |
+
{
|
| 12858 |
+
"epoch": 0.7165926720983559,
|
| 12859 |
+
"grad_norm": 0.22301085293293,
|
| 12860 |
+
"learning_rate": 0.0002462737127371274,
|
| 12861 |
+
"loss": 2.5558409690856934,
|
| 12862 |
+
"step": 3672
|
| 12863 |
+
},
|
| 12864 |
+
{
|
| 12865 |
+
"epoch": 0.7169829731180173,
|
| 12866 |
+
"grad_norm": 0.1794136017560959,
|
| 12867 |
+
"learning_rate": 0.00024593495934959353,
|
| 12868 |
+
"loss": 2.58769154548645,
|
| 12869 |
+
"step": 3674
|
| 12870 |
+
},
|
| 12871 |
+
{
|
| 12872 |
+
"epoch": 0.7173732741376787,
|
| 12873 |
+
"grad_norm": 0.19131971895694733,
|
| 12874 |
+
"learning_rate": 0.00024559620596205963,
|
| 12875 |
+
"loss": 2.5675930976867676,
|
| 12876 |
+
"step": 3676
|
| 12877 |
+
},
|
| 12878 |
+
{
|
| 12879 |
+
"epoch": 0.7177635751573401,
|
| 12880 |
+
"grad_norm": 0.23116534948349,
|
| 12881 |
+
"learning_rate": 0.00024525745257452573,
|
| 12882 |
+
"loss": 2.5806403160095215,
|
| 12883 |
+
"step": 3678
|
| 12884 |
+
},
|
| 12885 |
+
{
|
| 12886 |
+
"epoch": 0.7181538761770015,
|
| 12887 |
+
"grad_norm": 0.19743885099887848,
|
| 12888 |
+
"learning_rate": 0.00024491869918699183,
|
| 12889 |
+
"loss": 2.559718608856201,
|
| 12890 |
+
"step": 3680
|
| 12891 |
+
},
|
| 12892 |
+
{
|
| 12893 |
+
"epoch": 0.718544177196663,
|
| 12894 |
+
"grad_norm": 0.14672979712486267,
|
| 12895 |
+
"learning_rate": 0.000244579945799458,
|
| 12896 |
+
"loss": 2.5845065116882324,
|
| 12897 |
+
"step": 3682
|
| 12898 |
+
},
|
| 12899 |
+
{
|
| 12900 |
+
"epoch": 0.7189344782163244,
|
| 12901 |
+
"grad_norm": 0.23574891686439514,
|
| 12902 |
+
"learning_rate": 0.00024424119241192414,
|
| 12903 |
+
"loss": 2.545740842819214,
|
| 12904 |
+
"step": 3684
|
| 12905 |
+
},
|
| 12906 |
+
{
|
| 12907 |
+
"epoch": 0.7193247792359857,
|
| 12908 |
+
"grad_norm": 0.2071792334318161,
|
| 12909 |
+
"learning_rate": 0.00024390243902439024,
|
| 12910 |
+
"loss": 2.614464044570923,
|
| 12911 |
+
"step": 3686
|
| 12912 |
+
},
|
| 12913 |
+
{
|
| 12914 |
+
"epoch": 0.7197150802556471,
|
| 12915 |
+
"grad_norm": 0.16471944749355316,
|
| 12916 |
+
"learning_rate": 0.00024356368563685637,
|
| 12917 |
+
"loss": 2.5603036880493164,
|
| 12918 |
+
"step": 3688
|
| 12919 |
+
},
|
| 12920 |
+
{
|
| 12921 |
+
"epoch": 0.7201053812753085,
|
| 12922 |
+
"grad_norm": 0.1726536899805069,
|
| 12923 |
+
"learning_rate": 0.0002432249322493225,
|
| 12924 |
+
"loss": 2.5491695404052734,
|
| 12925 |
+
"step": 3690
|
| 12926 |
+
},
|
| 12927 |
+
{
|
| 12928 |
+
"epoch": 0.72049568229497,
|
| 12929 |
+
"grad_norm": 0.18844875693321228,
|
| 12930 |
+
"learning_rate": 0.00024288617886178863,
|
| 12931 |
+
"loss": 2.5796914100646973,
|
| 12932 |
+
"step": 3692
|
| 12933 |
+
},
|
| 12934 |
+
{
|
| 12935 |
+
"epoch": 0.7208859833146314,
|
| 12936 |
+
"grad_norm": 0.2086610347032547,
|
| 12937 |
+
"learning_rate": 0.00024254742547425473,
|
| 12938 |
+
"loss": 2.584871292114258,
|
| 12939 |
+
"step": 3694
|
| 12940 |
+
},
|
| 12941 |
+
{
|
| 12942 |
+
"epoch": 0.7212762843342928,
|
| 12943 |
+
"grad_norm": 0.19103746116161346,
|
| 12944 |
+
"learning_rate": 0.00024220867208672088,
|
| 12945 |
+
"loss": 2.4664528369903564,
|
| 12946 |
+
"step": 3696
|
| 12947 |
+
},
|
| 12948 |
+
{
|
| 12949 |
+
"epoch": 0.7216665853539542,
|
| 12950 |
+
"grad_norm": 0.14016501605510712,
|
| 12951 |
+
"learning_rate": 0.000241869918699187,
|
| 12952 |
+
"loss": 2.565579891204834,
|
| 12953 |
+
"step": 3698
|
| 12954 |
+
},
|
| 12955 |
+
{
|
| 12956 |
+
"epoch": 0.7220568863736156,
|
| 12957 |
+
"grad_norm": 0.1511334925889969,
|
| 12958 |
+
"learning_rate": 0.0002415311653116531,
|
| 12959 |
+
"loss": 2.583969831466675,
|
| 12960 |
+
"step": 3700
|
| 12961 |
+
},
|
| 12962 |
+
{
|
| 12963 |
+
"epoch": 0.7224471873932771,
|
| 12964 |
+
"grad_norm": 0.23370778560638428,
|
| 12965 |
+
"learning_rate": 0.00024119241192411926,
|
| 12966 |
+
"loss": 2.522264003753662,
|
| 12967 |
+
"step": 3702
|
| 12968 |
+
},
|
| 12969 |
+
{
|
| 12970 |
+
"epoch": 0.7228374884129385,
|
| 12971 |
+
"grad_norm": 0.13391512632369995,
|
| 12972 |
+
"learning_rate": 0.00024085365853658536,
|
| 12973 |
+
"loss": 2.558168649673462,
|
| 12974 |
+
"step": 3704
|
| 12975 |
+
},
|
| 12976 |
+
{
|
| 12977 |
+
"epoch": 0.7232277894325999,
|
| 12978 |
+
"grad_norm": 0.20801013708114624,
|
| 12979 |
+
"learning_rate": 0.0002405149051490515,
|
| 12980 |
+
"loss": 2.623211622238159,
|
| 12981 |
+
"step": 3706
|
| 12982 |
+
},
|
| 12983 |
+
{
|
| 12984 |
+
"epoch": 0.7236180904522613,
|
| 12985 |
+
"grad_norm": 0.1598731130361557,
|
| 12986 |
+
"learning_rate": 0.00024017615176151762,
|
| 12987 |
+
"loss": 2.5809688568115234,
|
| 12988 |
+
"step": 3708
|
| 12989 |
+
},
|
| 12990 |
+
{
|
| 12991 |
+
"epoch": 0.7240083914719228,
|
| 12992 |
+
"grad_norm": 0.1559130847454071,
|
| 12993 |
+
"learning_rate": 0.00023983739837398375,
|
| 12994 |
+
"loss": 2.5299980640411377,
|
| 12995 |
+
"step": 3710
|
| 12996 |
+
},
|
| 12997 |
+
{
|
| 12998 |
+
"epoch": 0.7243986924915842,
|
| 12999 |
+
"grad_norm": 0.18892396986484528,
|
| 13000 |
+
"learning_rate": 0.00023949864498644987,
|
| 13001 |
+
"loss": 2.5959625244140625,
|
| 13002 |
+
"step": 3712
|
| 13003 |
+
},
|
| 13004 |
+
{
|
| 13005 |
+
"epoch": 0.7247889935112456,
|
| 13006 |
+
"grad_norm": 0.18594689667224884,
|
| 13007 |
+
"learning_rate": 0.000239159891598916,
|
| 13008 |
+
"loss": 2.566007614135742,
|
| 13009 |
+
"step": 3714
|
| 13010 |
+
},
|
| 13011 |
+
{
|
| 13012 |
+
"epoch": 0.725179294530907,
|
| 13013 |
+
"grad_norm": 0.18966060876846313,
|
| 13014 |
+
"learning_rate": 0.00023882113821138213,
|
| 13015 |
+
"loss": 2.585193157196045,
|
| 13016 |
+
"step": 3716
|
| 13017 |
+
},
|
| 13018 |
+
{
|
| 13019 |
+
"epoch": 0.7255695955505683,
|
| 13020 |
+
"grad_norm": 0.17218399047851562,
|
| 13021 |
+
"learning_rate": 0.00023848238482384823,
|
| 13022 |
+
"loss": 2.5584897994995117,
|
| 13023 |
+
"step": 3718
|
| 13024 |
+
},
|
| 13025 |
+
{
|
| 13026 |
+
"epoch": 0.7259598965702297,
|
| 13027 |
+
"grad_norm": 0.16350500285625458,
|
| 13028 |
+
"learning_rate": 0.00023814363143631438,
|
| 13029 |
+
"loss": 2.576380968093872,
|
| 13030 |
+
"step": 3720
|
| 13031 |
+
},
|
| 13032 |
+
{
|
| 13033 |
+
"epoch": 0.7263501975898912,
|
| 13034 |
+
"grad_norm": 0.2409660667181015,
|
| 13035 |
+
"learning_rate": 0.00023780487804878048,
|
| 13036 |
+
"loss": 2.576275587081909,
|
| 13037 |
+
"step": 3722
|
| 13038 |
+
},
|
| 13039 |
+
{
|
| 13040 |
+
"epoch": 0.7267404986095526,
|
| 13041 |
+
"grad_norm": 0.17562013864517212,
|
| 13042 |
+
"learning_rate": 0.0002374661246612466,
|
| 13043 |
+
"loss": 2.5714926719665527,
|
| 13044 |
+
"step": 3724
|
| 13045 |
+
},
|
| 13046 |
+
{
|
| 13047 |
+
"epoch": 0.727130799629214,
|
| 13048 |
+
"grad_norm": 0.16816650331020355,
|
| 13049 |
+
"learning_rate": 0.00023712737127371276,
|
| 13050 |
+
"loss": 2.593493938446045,
|
| 13051 |
+
"step": 3726
|
| 13052 |
+
},
|
| 13053 |
+
{
|
| 13054 |
+
"epoch": 0.7275211006488754,
|
| 13055 |
+
"grad_norm": 0.13196778297424316,
|
| 13056 |
+
"learning_rate": 0.00023678861788617886,
|
| 13057 |
+
"loss": 2.525681972503662,
|
| 13058 |
+
"step": 3728
|
| 13059 |
+
},
|
| 13060 |
+
{
|
| 13061 |
+
"epoch": 0.7279114016685369,
|
| 13062 |
+
"grad_norm": 0.1828942447900772,
|
| 13063 |
+
"learning_rate": 0.000236449864498645,
|
| 13064 |
+
"loss": 2.5915775299072266,
|
| 13065 |
+
"step": 3730
|
| 13066 |
+
},
|
| 13067 |
+
{
|
| 13068 |
+
"epoch": 0.7283017026881983,
|
| 13069 |
+
"grad_norm": 0.167177215218544,
|
| 13070 |
+
"learning_rate": 0.00023611111111111112,
|
| 13071 |
+
"loss": 2.589087724685669,
|
| 13072 |
+
"step": 3732
|
| 13073 |
+
},
|
| 13074 |
+
{
|
| 13075 |
+
"epoch": 0.7286920037078597,
|
| 13076 |
+
"grad_norm": 0.18648870289325714,
|
| 13077 |
+
"learning_rate": 0.00023577235772357725,
|
| 13078 |
+
"loss": 2.6418356895446777,
|
| 13079 |
+
"step": 3734
|
| 13080 |
+
},
|
| 13081 |
+
{
|
| 13082 |
+
"epoch": 0.7290823047275211,
|
| 13083 |
+
"grad_norm": 0.15209832787513733,
|
| 13084 |
+
"learning_rate": 0.00023543360433604335,
|
| 13085 |
+
"loss": 2.6101040840148926,
|
| 13086 |
+
"step": 3736
|
| 13087 |
+
},
|
| 13088 |
+
{
|
| 13089 |
+
"epoch": 0.7294726057471825,
|
| 13090 |
+
"grad_norm": 0.13956190645694733,
|
| 13091 |
+
"learning_rate": 0.0002350948509485095,
|
| 13092 |
+
"loss": 2.5516486167907715,
|
| 13093 |
+
"step": 3738
|
| 13094 |
+
},
|
| 13095 |
+
{
|
| 13096 |
+
"epoch": 0.729862906766844,
|
| 13097 |
+
"grad_norm": 0.15245820581912994,
|
| 13098 |
+
"learning_rate": 0.0002347560975609756,
|
| 13099 |
+
"loss": 2.6034088134765625,
|
| 13100 |
+
"step": 3740
|
| 13101 |
+
},
|
| 13102 |
+
{
|
| 13103 |
+
"epoch": 0.7302532077865054,
|
| 13104 |
+
"grad_norm": 0.20651909708976746,
|
| 13105 |
+
"learning_rate": 0.00023441734417344173,
|
| 13106 |
+
"loss": 2.58943247795105,
|
| 13107 |
+
"step": 3742
|
| 13108 |
+
},
|
| 13109 |
+
{
|
| 13110 |
+
"epoch": 0.7306435088061668,
|
| 13111 |
+
"grad_norm": 0.18454326689243317,
|
| 13112 |
+
"learning_rate": 0.00023407859078590788,
|
| 13113 |
+
"loss": 2.541945457458496,
|
| 13114 |
+
"step": 3744
|
| 13115 |
+
},
|
| 13116 |
+
{
|
| 13117 |
+
"epoch": 0.7310338098258282,
|
| 13118 |
+
"grad_norm": 0.21141330897808075,
|
| 13119 |
+
"learning_rate": 0.00023373983739837398,
|
| 13120 |
+
"loss": 2.549893856048584,
|
| 13121 |
+
"step": 3746
|
| 13122 |
+
},
|
| 13123 |
+
{
|
| 13124 |
+
"epoch": 0.7314241108454896,
|
| 13125 |
+
"grad_norm": 0.17100749909877777,
|
| 13126 |
+
"learning_rate": 0.0002334010840108401,
|
| 13127 |
+
"loss": 2.5992016792297363,
|
| 13128 |
+
"step": 3748
|
| 13129 |
+
},
|
| 13130 |
+
{
|
| 13131 |
+
"epoch": 0.731814411865151,
|
| 13132 |
+
"grad_norm": 0.19100318849086761,
|
| 13133 |
+
"learning_rate": 0.00023306233062330624,
|
| 13134 |
+
"loss": 2.547199010848999,
|
| 13135 |
+
"step": 3750
|
| 13136 |
+
},
|
| 13137 |
+
{
|
| 13138 |
+
"epoch": 0.7322047128848124,
|
| 13139 |
+
"grad_norm": 0.15620185434818268,
|
| 13140 |
+
"learning_rate": 0.00023272357723577237,
|
| 13141 |
+
"loss": 2.5576610565185547,
|
| 13142 |
+
"step": 3752
|
| 13143 |
+
},
|
| 13144 |
+
{
|
| 13145 |
+
"epoch": 0.7325950139044738,
|
| 13146 |
+
"grad_norm": 0.17232976853847504,
|
| 13147 |
+
"learning_rate": 0.00023238482384823847,
|
| 13148 |
+
"loss": 2.6053466796875,
|
| 13149 |
+
"step": 3754
|
| 13150 |
+
},
|
| 13151 |
+
{
|
| 13152 |
+
"epoch": 0.7329853149241352,
|
| 13153 |
+
"grad_norm": 0.1580606997013092,
|
| 13154 |
+
"learning_rate": 0.00023204607046070462,
|
| 13155 |
+
"loss": 2.5998289585113525,
|
| 13156 |
+
"step": 3756
|
| 13157 |
+
},
|
| 13158 |
+
{
|
| 13159 |
+
"epoch": 0.7333756159437966,
|
| 13160 |
+
"grad_norm": 0.1601296216249466,
|
| 13161 |
+
"learning_rate": 0.00023170731707317075,
|
| 13162 |
+
"loss": 2.632892608642578,
|
| 13163 |
+
"step": 3758
|
| 13164 |
+
},
|
| 13165 |
+
{
|
| 13166 |
+
"epoch": 0.733765916963458,
|
| 13167 |
+
"grad_norm": 0.16067874431610107,
|
| 13168 |
+
"learning_rate": 0.00023136856368563685,
|
| 13169 |
+
"loss": 2.5668389797210693,
|
| 13170 |
+
"step": 3760
|
| 13171 |
+
},
|
| 13172 |
+
{
|
| 13173 |
+
"epoch": 0.7341562179831195,
|
| 13174 |
+
"grad_norm": 0.14233550429344177,
|
| 13175 |
+
"learning_rate": 0.000231029810298103,
|
| 13176 |
+
"loss": 2.5435807704925537,
|
| 13177 |
+
"step": 3762
|
| 13178 |
+
},
|
| 13179 |
+
{
|
| 13180 |
+
"epoch": 0.7345465190027809,
|
| 13181 |
+
"grad_norm": 0.1608455926179886,
|
| 13182 |
+
"learning_rate": 0.0002306910569105691,
|
| 13183 |
+
"loss": 2.559410572052002,
|
| 13184 |
+
"step": 3764
|
| 13185 |
+
},
|
| 13186 |
+
{
|
| 13187 |
+
"epoch": 0.7349368200224423,
|
| 13188 |
+
"grad_norm": 0.1960258036851883,
|
| 13189 |
+
"learning_rate": 0.00023035230352303523,
|
| 13190 |
+
"loss": 2.5418760776519775,
|
| 13191 |
+
"step": 3766
|
| 13192 |
+
},
|
| 13193 |
+
{
|
| 13194 |
+
"epoch": 0.7353271210421037,
|
| 13195 |
+
"grad_norm": 0.20010501146316528,
|
| 13196 |
+
"learning_rate": 0.00023001355013550136,
|
| 13197 |
+
"loss": 2.5552968978881836,
|
| 13198 |
+
"step": 3768
|
| 13199 |
+
},
|
| 13200 |
+
{
|
| 13201 |
+
"epoch": 0.7357174220617652,
|
| 13202 |
+
"grad_norm": 0.16965314745903015,
|
| 13203 |
+
"learning_rate": 0.00022967479674796748,
|
| 13204 |
+
"loss": 2.5741820335388184,
|
| 13205 |
+
"step": 3770
|
| 13206 |
+
},
|
| 13207 |
+
{
|
| 13208 |
+
"epoch": 0.7361077230814266,
|
| 13209 |
+
"grad_norm": 0.15460222959518433,
|
| 13210 |
+
"learning_rate": 0.0002293360433604336,
|
| 13211 |
+
"loss": 2.6608054637908936,
|
| 13212 |
+
"step": 3772
|
| 13213 |
+
},
|
| 13214 |
+
{
|
| 13215 |
+
"epoch": 0.736498024101088,
|
| 13216 |
+
"grad_norm": 0.1612243503332138,
|
| 13217 |
+
"learning_rate": 0.00022899728997289974,
|
| 13218 |
+
"loss": 2.519094467163086,
|
| 13219 |
+
"step": 3774
|
| 13220 |
+
},
|
| 13221 |
+
{
|
| 13222 |
+
"epoch": 0.7368883251207494,
|
| 13223 |
+
"grad_norm": 0.15695582330226898,
|
| 13224 |
+
"learning_rate": 0.00022865853658536587,
|
| 13225 |
+
"loss": 2.5763187408447266,
|
| 13226 |
+
"step": 3776
|
| 13227 |
+
},
|
| 13228 |
+
{
|
| 13229 |
+
"epoch": 0.7372786261404108,
|
| 13230 |
+
"grad_norm": 0.19170358777046204,
|
| 13231 |
+
"learning_rate": 0.00022831978319783197,
|
| 13232 |
+
"loss": 2.6136386394500732,
|
| 13233 |
+
"step": 3778
|
| 13234 |
+
},
|
| 13235 |
+
{
|
| 13236 |
+
"epoch": 0.7376689271600722,
|
| 13237 |
+
"grad_norm": 0.1500522792339325,
|
| 13238 |
+
"learning_rate": 0.00022798102981029812,
|
| 13239 |
+
"loss": 2.5883750915527344,
|
| 13240 |
+
"step": 3780
|
| 13241 |
+
},
|
| 13242 |
+
{
|
| 13243 |
+
"epoch": 0.7380592281797336,
|
| 13244 |
+
"grad_norm": 0.14444859325885773,
|
| 13245 |
+
"learning_rate": 0.00022764227642276422,
|
| 13246 |
+
"loss": 2.5046677589416504,
|
| 13247 |
+
"step": 3782
|
| 13248 |
+
},
|
| 13249 |
+
{
|
| 13250 |
+
"epoch": 0.738449529199395,
|
| 13251 |
+
"grad_norm": 0.15762977302074432,
|
| 13252 |
+
"learning_rate": 0.00022730352303523035,
|
| 13253 |
+
"loss": 2.596222400665283,
|
| 13254 |
+
"step": 3784
|
| 13255 |
+
},
|
| 13256 |
+
{
|
| 13257 |
+
"epoch": 0.7388398302190564,
|
| 13258 |
+
"grad_norm": 0.16943491995334625,
|
| 13259 |
+
"learning_rate": 0.0002269647696476965,
|
| 13260 |
+
"loss": 2.593855857849121,
|
| 13261 |
+
"step": 3786
|
| 13262 |
+
},
|
| 13263 |
+
{
|
| 13264 |
+
"epoch": 0.7392301312387178,
|
| 13265 |
+
"grad_norm": 0.22718113660812378,
|
| 13266 |
+
"learning_rate": 0.0002266260162601626,
|
| 13267 |
+
"loss": 2.584428310394287,
|
| 13268 |
+
"step": 3788
|
| 13269 |
+
},
|
| 13270 |
+
{
|
| 13271 |
+
"epoch": 0.7396204322583793,
|
| 13272 |
+
"grad_norm": 0.1707637459039688,
|
| 13273 |
+
"learning_rate": 0.00022628726287262873,
|
| 13274 |
+
"loss": 2.6002535820007324,
|
| 13275 |
+
"step": 3790
|
| 13276 |
+
},
|
| 13277 |
+
{
|
| 13278 |
+
"epoch": 0.7400107332780407,
|
| 13279 |
+
"grad_norm": 0.18670061230659485,
|
| 13280 |
+
"learning_rate": 0.00022594850948509486,
|
| 13281 |
+
"loss": 2.591188907623291,
|
| 13282 |
+
"step": 3792
|
| 13283 |
+
},
|
| 13284 |
+
{
|
| 13285 |
+
"epoch": 0.7404010342977021,
|
| 13286 |
+
"grad_norm": 0.1586286574602127,
|
| 13287 |
+
"learning_rate": 0.00022560975609756099,
|
| 13288 |
+
"loss": 2.5578956604003906,
|
| 13289 |
+
"step": 3794
|
| 13290 |
+
},
|
| 13291 |
+
{
|
| 13292 |
+
"epoch": 0.7407913353173635,
|
| 13293 |
+
"grad_norm": 0.1399455964565277,
|
| 13294 |
+
"learning_rate": 0.0002252710027100271,
|
| 13295 |
+
"loss": 2.5943212509155273,
|
| 13296 |
+
"step": 3796
|
| 13297 |
+
},
|
| 13298 |
+
{
|
| 13299 |
+
"epoch": 0.7411816363370249,
|
| 13300 |
+
"grad_norm": 0.18433824181556702,
|
| 13301 |
+
"learning_rate": 0.00022493224932249324,
|
| 13302 |
+
"loss": 2.6078855991363525,
|
| 13303 |
+
"step": 3798
|
| 13304 |
+
},
|
| 13305 |
+
{
|
| 13306 |
+
"epoch": 0.7415719373566864,
|
| 13307 |
+
"grad_norm": 0.15389202535152435,
|
| 13308 |
+
"learning_rate": 0.00022459349593495934,
|
| 13309 |
+
"loss": 2.612149953842163,
|
| 13310 |
+
"step": 3800
|
| 13311 |
+
},
|
| 13312 |
+
{
|
| 13313 |
+
"epoch": 0.7419622383763478,
|
| 13314 |
+
"grad_norm": 0.1663869470357895,
|
| 13315 |
+
"learning_rate": 0.00022425474254742547,
|
| 13316 |
+
"loss": 2.5993995666503906,
|
| 13317 |
+
"step": 3802
|
| 13318 |
+
},
|
| 13319 |
+
{
|
| 13320 |
+
"epoch": 0.7423525393960092,
|
| 13321 |
+
"grad_norm": 0.19003599882125854,
|
| 13322 |
+
"learning_rate": 0.00022391598915989162,
|
| 13323 |
+
"loss": 2.577406883239746,
|
| 13324 |
+
"step": 3804
|
| 13325 |
+
},
|
| 13326 |
+
{
|
| 13327 |
+
"epoch": 0.7427428404156706,
|
| 13328 |
+
"grad_norm": 0.21762073040008545,
|
| 13329 |
+
"learning_rate": 0.00022357723577235772,
|
| 13330 |
+
"loss": 2.5459766387939453,
|
| 13331 |
+
"step": 3806
|
| 13332 |
+
},
|
| 13333 |
+
{
|
| 13334 |
+
"epoch": 0.743133141435332,
|
| 13335 |
+
"grad_norm": 0.17764461040496826,
|
| 13336 |
+
"learning_rate": 0.00022323848238482385,
|
| 13337 |
+
"loss": 2.590576171875,
|
| 13338 |
+
"step": 3808
|
| 13339 |
+
},
|
| 13340 |
+
{
|
| 13341 |
+
"epoch": 0.7435234424549935,
|
| 13342 |
+
"grad_norm": 0.17868053913116455,
|
| 13343 |
+
"learning_rate": 0.00022289972899728998,
|
| 13344 |
+
"loss": 2.5675408840179443,
|
| 13345 |
+
"step": 3810
|
| 13346 |
+
},
|
| 13347 |
+
{
|
| 13348 |
+
"epoch": 0.7439137434746548,
|
| 13349 |
+
"grad_norm": 0.18061724305152893,
|
| 13350 |
+
"learning_rate": 0.0002225609756097561,
|
| 13351 |
+
"loss": 2.5606496334075928,
|
| 13352 |
+
"step": 3812
|
| 13353 |
+
},
|
| 13354 |
+
{
|
| 13355 |
+
"epoch": 0.7443040444943162,
|
| 13356 |
+
"grad_norm": 0.16410815715789795,
|
| 13357 |
+
"learning_rate": 0.0002222222222222222,
|
| 13358 |
+
"loss": 2.594193458557129,
|
| 13359 |
+
"step": 3814
|
| 13360 |
+
},
|
| 13361 |
+
{
|
| 13362 |
+
"epoch": 0.7446943455139776,
|
| 13363 |
+
"grad_norm": 0.1758735477924347,
|
| 13364 |
+
"learning_rate": 0.00022188346883468836,
|
| 13365 |
+
"loss": 2.629559278488159,
|
| 13366 |
+
"step": 3816
|
| 13367 |
+
},
|
| 13368 |
+
{
|
| 13369 |
+
"epoch": 0.745084646533639,
|
| 13370 |
+
"grad_norm": 0.18014933168888092,
|
| 13371 |
+
"learning_rate": 0.0002215447154471545,
|
| 13372 |
+
"loss": 2.597836971282959,
|
| 13373 |
+
"step": 3818
|
| 13374 |
+
},
|
| 13375 |
+
{
|
| 13376 |
+
"epoch": 0.7454749475533005,
|
| 13377 |
+
"grad_norm": 0.19547505676746368,
|
| 13378 |
+
"learning_rate": 0.0002212059620596206,
|
| 13379 |
+
"loss": 2.5763936042785645,
|
| 13380 |
+
"step": 3820
|
| 13381 |
+
},
|
| 13382 |
+
{
|
| 13383 |
+
"epoch": 0.7458652485729619,
|
| 13384 |
+
"grad_norm": 0.19461897015571594,
|
| 13385 |
+
"learning_rate": 0.00022086720867208674,
|
| 13386 |
+
"loss": 2.5482707023620605,
|
| 13387 |
+
"step": 3822
|
| 13388 |
+
},
|
| 13389 |
+
{
|
| 13390 |
+
"epoch": 0.7462555495926233,
|
| 13391 |
+
"grad_norm": 0.14711827039718628,
|
| 13392 |
+
"learning_rate": 0.00022052845528455284,
|
| 13393 |
+
"loss": 2.5310771465301514,
|
| 13394 |
+
"step": 3824
|
| 13395 |
+
},
|
| 13396 |
+
{
|
| 13397 |
+
"epoch": 0.7466458506122847,
|
| 13398 |
+
"grad_norm": 0.20974712073802948,
|
| 13399 |
+
"learning_rate": 0.00022018970189701897,
|
| 13400 |
+
"loss": 2.5745248794555664,
|
| 13401 |
+
"step": 3826
|
| 13402 |
+
},
|
| 13403 |
+
{
|
| 13404 |
+
"epoch": 0.7470361516319461,
|
| 13405 |
+
"grad_norm": 0.17560338973999023,
|
| 13406 |
+
"learning_rate": 0.0002198509485094851,
|
| 13407 |
+
"loss": 2.5030999183654785,
|
| 13408 |
+
"step": 3828
|
| 13409 |
+
},
|
| 13410 |
+
{
|
| 13411 |
+
"epoch": 0.7474264526516076,
|
| 13412 |
+
"grad_norm": 0.19719818234443665,
|
| 13413 |
+
"learning_rate": 0.00021951219512195122,
|
| 13414 |
+
"loss": 2.512880802154541,
|
| 13415 |
+
"step": 3830
|
| 13416 |
+
},
|
| 13417 |
+
{
|
| 13418 |
+
"epoch": 0.747816753671269,
|
| 13419 |
+
"grad_norm": 0.1590634286403656,
|
| 13420 |
+
"learning_rate": 0.00021917344173441735,
|
| 13421 |
+
"loss": 2.563493251800537,
|
| 13422 |
+
"step": 3832
|
| 13423 |
+
},
|
| 13424 |
+
{
|
| 13425 |
+
"epoch": 0.7482070546909304,
|
| 13426 |
+
"grad_norm": 0.16284126043319702,
|
| 13427 |
+
"learning_rate": 0.00021883468834688348,
|
| 13428 |
+
"loss": 2.584259510040283,
|
| 13429 |
+
"step": 3834
|
| 13430 |
+
},
|
| 13431 |
+
{
|
| 13432 |
+
"epoch": 0.7485973557105918,
|
| 13433 |
+
"grad_norm": 0.1650046855211258,
|
| 13434 |
+
"learning_rate": 0.0002184959349593496,
|
| 13435 |
+
"loss": 2.563936233520508,
|
| 13436 |
+
"step": 3836
|
| 13437 |
+
},
|
| 13438 |
+
{
|
| 13439 |
+
"epoch": 0.7489876567302532,
|
| 13440 |
+
"grad_norm": 0.20722222328186035,
|
| 13441 |
+
"learning_rate": 0.0002181571815718157,
|
| 13442 |
+
"loss": 2.5984208583831787,
|
| 13443 |
+
"step": 3838
|
| 13444 |
+
},
|
| 13445 |
+
{
|
| 13446 |
+
"epoch": 0.7493779577499147,
|
| 13447 |
+
"grad_norm": 0.20577353239059448,
|
| 13448 |
+
"learning_rate": 0.00021781842818428186,
|
| 13449 |
+
"loss": 2.5736212730407715,
|
| 13450 |
+
"step": 3840
|
| 13451 |
+
},
|
| 13452 |
+
{
|
| 13453 |
+
"epoch": 0.7497682587695761,
|
| 13454 |
+
"grad_norm": 0.20333300530910492,
|
| 13455 |
+
"learning_rate": 0.00021747967479674796,
|
| 13456 |
+
"loss": 2.6499671936035156,
|
| 13457 |
+
"step": 3842
|
| 13458 |
+
},
|
| 13459 |
+
{
|
| 13460 |
+
"epoch": 0.7501585597892374,
|
| 13461 |
+
"grad_norm": 0.18774324655532837,
|
| 13462 |
+
"learning_rate": 0.0002171409214092141,
|
| 13463 |
+
"loss": 2.579308271408081,
|
| 13464 |
+
"step": 3844
|
| 13465 |
+
},
|
| 13466 |
+
{
|
| 13467 |
+
"epoch": 0.7505488608088988,
|
| 13468 |
+
"grad_norm": 0.1767909824848175,
|
| 13469 |
+
"learning_rate": 0.00021680216802168024,
|
| 13470 |
+
"loss": 2.5725417137145996,
|
| 13471 |
+
"step": 3846
|
| 13472 |
+
},
|
| 13473 |
+
{
|
| 13474 |
+
"epoch": 0.7509391618285602,
|
| 13475 |
+
"grad_norm": 0.23386360704898834,
|
| 13476 |
+
"learning_rate": 0.00021646341463414634,
|
| 13477 |
+
"loss": 2.562321186065674,
|
| 13478 |
+
"step": 3848
|
| 13479 |
+
},
|
| 13480 |
+
{
|
| 13481 |
+
"epoch": 0.7513294628482217,
|
| 13482 |
+
"grad_norm": 0.18519845604896545,
|
| 13483 |
+
"learning_rate": 0.00021612466124661247,
|
| 13484 |
+
"loss": 2.565164566040039,
|
| 13485 |
+
"step": 3850
|
| 13486 |
+
},
|
| 13487 |
+
{
|
| 13488 |
+
"epoch": 0.7517197638678831,
|
| 13489 |
+
"grad_norm": 0.21817472577095032,
|
| 13490 |
+
"learning_rate": 0.0002157859078590786,
|
| 13491 |
+
"loss": 2.569627285003662,
|
| 13492 |
+
"step": 3852
|
| 13493 |
+
},
|
| 13494 |
+
{
|
| 13495 |
+
"epoch": 0.7521100648875445,
|
| 13496 |
+
"grad_norm": 0.17733028531074524,
|
| 13497 |
+
"learning_rate": 0.00021544715447154473,
|
| 13498 |
+
"loss": 2.5537843704223633,
|
| 13499 |
+
"step": 3854
|
| 13500 |
+
},
|
| 13501 |
+
{
|
| 13502 |
+
"epoch": 0.7525003659072059,
|
| 13503 |
+
"grad_norm": 0.16365699470043182,
|
| 13504 |
+
"learning_rate": 0.00021510840108401083,
|
| 13505 |
+
"loss": 2.5836331844329834,
|
| 13506 |
+
"step": 3856
|
| 13507 |
+
},
|
| 13508 |
+
{
|
| 13509 |
+
"epoch": 0.7528906669268673,
|
| 13510 |
+
"grad_norm": 0.15659679472446442,
|
| 13511 |
+
"learning_rate": 0.00021476964769647698,
|
| 13512 |
+
"loss": 2.572005033493042,
|
| 13513 |
+
"step": 3858
|
| 13514 |
+
},
|
| 13515 |
+
{
|
| 13516 |
+
"epoch": 0.7532809679465288,
|
| 13517 |
+
"grad_norm": 0.1724509447813034,
|
| 13518 |
+
"learning_rate": 0.00021443089430894308,
|
| 13519 |
+
"loss": 2.5763282775878906,
|
| 13520 |
+
"step": 3860
|
| 13521 |
+
},
|
| 13522 |
+
{
|
| 13523 |
+
"epoch": 0.7536712689661902,
|
| 13524 |
+
"grad_norm": 0.173537477850914,
|
| 13525 |
+
"learning_rate": 0.0002140921409214092,
|
| 13526 |
+
"loss": 2.5832414627075195,
|
| 13527 |
+
"step": 3862
|
| 13528 |
+
},
|
| 13529 |
+
{
|
| 13530 |
+
"epoch": 0.7540615699858516,
|
| 13531 |
+
"grad_norm": 0.19807596504688263,
|
| 13532 |
+
"learning_rate": 0.00021375338753387536,
|
| 13533 |
+
"loss": 2.5919413566589355,
|
| 13534 |
+
"step": 3864
|
| 13535 |
+
},
|
| 13536 |
+
{
|
| 13537 |
+
"epoch": 0.754451871005513,
|
| 13538 |
+
"grad_norm": 0.16080211102962494,
|
| 13539 |
+
"learning_rate": 0.00021341463414634146,
|
| 13540 |
+
"loss": 2.6304545402526855,
|
| 13541 |
+
"step": 3866
|
| 13542 |
+
},
|
| 13543 |
+
{
|
| 13544 |
+
"epoch": 0.7548421720251745,
|
| 13545 |
+
"grad_norm": 0.14884315431118011,
|
| 13546 |
+
"learning_rate": 0.0002130758807588076,
|
| 13547 |
+
"loss": 2.5764431953430176,
|
| 13548 |
+
"step": 3868
|
| 13549 |
+
},
|
| 13550 |
+
{
|
| 13551 |
+
"epoch": 0.7552324730448359,
|
| 13552 |
+
"grad_norm": 0.2054700404405594,
|
| 13553 |
+
"learning_rate": 0.00021273712737127372,
|
| 13554 |
+
"loss": 2.5686445236206055,
|
| 13555 |
+
"step": 3870
|
| 13556 |
+
},
|
| 13557 |
+
{
|
| 13558 |
+
"epoch": 0.7556227740644973,
|
| 13559 |
+
"grad_norm": 0.1694842427968979,
|
| 13560 |
+
"learning_rate": 0.00021239837398373985,
|
| 13561 |
+
"loss": 2.573896646499634,
|
| 13562 |
+
"step": 3872
|
| 13563 |
+
},
|
| 13564 |
+
{
|
| 13565 |
+
"epoch": 0.7560130750841586,
|
| 13566 |
+
"grad_norm": 0.1520727276802063,
|
| 13567 |
+
"learning_rate": 0.00021205962059620595,
|
| 13568 |
+
"loss": 2.639799118041992,
|
| 13569 |
+
"step": 3874
|
| 13570 |
+
},
|
| 13571 |
+
{
|
| 13572 |
+
"epoch": 0.75640337610382,
|
| 13573 |
+
"grad_norm": 0.24052155017852783,
|
| 13574 |
+
"learning_rate": 0.0002117208672086721,
|
| 13575 |
+
"loss": 2.5131959915161133,
|
| 13576 |
+
"step": 3876
|
| 13577 |
+
},
|
| 13578 |
+
{
|
| 13579 |
+
"epoch": 0.7567936771234814,
|
| 13580 |
+
"grad_norm": 0.167377308011055,
|
| 13581 |
+
"learning_rate": 0.00021138211382113823,
|
| 13582 |
+
"loss": 2.5519752502441406,
|
| 13583 |
+
"step": 3878
|
| 13584 |
+
},
|
| 13585 |
+
{
|
| 13586 |
+
"epoch": 0.7571839781431429,
|
| 13587 |
+
"grad_norm": 0.19060377776622772,
|
| 13588 |
+
"learning_rate": 0.00021104336043360433,
|
| 13589 |
+
"loss": 2.605872392654419,
|
| 13590 |
+
"step": 3880
|
| 13591 |
+
},
|
| 13592 |
+
{
|
| 13593 |
+
"epoch": 0.7575742791628043,
|
| 13594 |
+
"grad_norm": 0.16378478705883026,
|
| 13595 |
+
"learning_rate": 0.00021070460704607048,
|
| 13596 |
+
"loss": 2.6059672832489014,
|
| 13597 |
+
"step": 3882
|
| 13598 |
+
},
|
| 13599 |
+
{
|
| 13600 |
+
"epoch": 0.7579645801824657,
|
| 13601 |
+
"grad_norm": 0.14329124987125397,
|
| 13602 |
+
"learning_rate": 0.00021036585365853658,
|
| 13603 |
+
"loss": 2.5882139205932617,
|
| 13604 |
+
"step": 3884
|
| 13605 |
+
},
|
| 13606 |
+
{
|
| 13607 |
+
"epoch": 0.7583548812021271,
|
| 13608 |
+
"grad_norm": 0.15297037363052368,
|
| 13609 |
+
"learning_rate": 0.0002100271002710027,
|
| 13610 |
+
"loss": 2.6128435134887695,
|
| 13611 |
+
"step": 3886
|
| 13612 |
+
},
|
| 13613 |
+
{
|
| 13614 |
+
"epoch": 0.7587451822217885,
|
| 13615 |
+
"grad_norm": 0.18271620571613312,
|
| 13616 |
+
"learning_rate": 0.00020968834688346884,
|
| 13617 |
+
"loss": 2.5710296630859375,
|
| 13618 |
+
"step": 3888
|
| 13619 |
+
},
|
| 13620 |
+
{
|
| 13621 |
+
"epoch": 0.75913548324145,
|
| 13622 |
+
"grad_norm": 0.2210632860660553,
|
| 13623 |
+
"learning_rate": 0.00020934959349593496,
|
| 13624 |
+
"loss": 2.6258575916290283,
|
| 13625 |
+
"step": 3890
|
| 13626 |
+
},
|
| 13627 |
+
{
|
| 13628 |
+
"epoch": 0.7595257842611114,
|
| 13629 |
+
"grad_norm": 0.2208152711391449,
|
| 13630 |
+
"learning_rate": 0.0002090108401084011,
|
| 13631 |
+
"loss": 2.567505359649658,
|
| 13632 |
+
"step": 3892
|
| 13633 |
+
},
|
| 13634 |
+
{
|
| 13635 |
+
"epoch": 0.7599160852807728,
|
| 13636 |
+
"grad_norm": 0.16831575334072113,
|
| 13637 |
+
"learning_rate": 0.00020867208672086722,
|
| 13638 |
+
"loss": 2.5931057929992676,
|
| 13639 |
+
"step": 3894
|
| 13640 |
+
},
|
| 13641 |
+
{
|
| 13642 |
+
"epoch": 0.7603063863004342,
|
| 13643 |
+
"grad_norm": 0.1569042056798935,
|
| 13644 |
+
"learning_rate": 0.00020833333333333335,
|
| 13645 |
+
"loss": 2.6167545318603516,
|
| 13646 |
+
"step": 3896
|
| 13647 |
+
},
|
| 13648 |
+
{
|
| 13649 |
+
"epoch": 0.7606966873200957,
|
| 13650 |
+
"grad_norm": 0.22460554540157318,
|
| 13651 |
+
"learning_rate": 0.00020799457994579945,
|
| 13652 |
+
"loss": 2.583001136779785,
|
| 13653 |
+
"step": 3898
|
| 13654 |
+
},
|
| 13655 |
+
{
|
| 13656 |
+
"epoch": 0.7610869883397571,
|
| 13657 |
+
"grad_norm": 0.2024400532245636,
|
| 13658 |
+
"learning_rate": 0.0002076558265582656,
|
| 13659 |
+
"loss": 2.5173022747039795,
|
| 13660 |
+
"step": 3900
|
| 13661 |
+
},
|
| 13662 |
+
{
|
| 13663 |
+
"epoch": 0.7614772893594185,
|
| 13664 |
+
"grad_norm": 0.2059406191110611,
|
| 13665 |
+
"learning_rate": 0.0002073170731707317,
|
| 13666 |
+
"loss": 2.585331439971924,
|
| 13667 |
+
"step": 3902
|
| 13668 |
+
},
|
| 13669 |
+
{
|
| 13670 |
+
"epoch": 0.7618675903790799,
|
| 13671 |
+
"grad_norm": 0.1542789787054062,
|
| 13672 |
+
"learning_rate": 0.00020697831978319783,
|
| 13673 |
+
"loss": 2.5177769660949707,
|
| 13674 |
+
"step": 3904
|
| 13675 |
+
},
|
| 13676 |
+
{
|
| 13677 |
+
"epoch": 0.7622578913987412,
|
| 13678 |
+
"grad_norm": 0.15535862743854523,
|
| 13679 |
+
"learning_rate": 0.00020663956639566396,
|
| 13680 |
+
"loss": 2.5843775272369385,
|
| 13681 |
+
"step": 3906
|
| 13682 |
+
},
|
| 13683 |
+
{
|
| 13684 |
+
"epoch": 0.7626481924184026,
|
| 13685 |
+
"grad_norm": 0.18861402571201324,
|
| 13686 |
+
"learning_rate": 0.00020630081300813008,
|
| 13687 |
+
"loss": 2.571636915206909,
|
| 13688 |
+
"step": 3908
|
| 13689 |
+
},
|
| 13690 |
+
{
|
| 13691 |
+
"epoch": 0.7630384934380641,
|
| 13692 |
+
"grad_norm": 0.1428379863500595,
|
| 13693 |
+
"learning_rate": 0.0002059620596205962,
|
| 13694 |
+
"loss": 2.595207691192627,
|
| 13695 |
+
"step": 3910
|
| 13696 |
+
},
|
| 13697 |
+
{
|
| 13698 |
+
"epoch": 0.7634287944577255,
|
| 13699 |
+
"grad_norm": 0.1492442488670349,
|
| 13700 |
+
"learning_rate": 0.00020562330623306234,
|
| 13701 |
+
"loss": 2.5797009468078613,
|
| 13702 |
+
"step": 3912
|
| 13703 |
+
},
|
| 13704 |
+
{
|
| 13705 |
+
"epoch": 0.7638190954773869,
|
| 13706 |
+
"grad_norm": 0.21506793797016144,
|
| 13707 |
+
"learning_rate": 0.00020528455284552847,
|
| 13708 |
+
"loss": 2.511481761932373,
|
| 13709 |
+
"step": 3914
|
| 13710 |
+
},
|
| 13711 |
+
{
|
| 13712 |
+
"epoch": 0.7642093964970483,
|
| 13713 |
+
"grad_norm": 0.16646669805049896,
|
| 13714 |
+
"learning_rate": 0.00020494579945799457,
|
| 13715 |
+
"loss": 2.5840537548065186,
|
| 13716 |
+
"step": 3916
|
| 13717 |
+
},
|
| 13718 |
+
{
|
| 13719 |
+
"epoch": 0.7645996975167098,
|
| 13720 |
+
"grad_norm": 0.1910133957862854,
|
| 13721 |
+
"learning_rate": 0.00020460704607046072,
|
| 13722 |
+
"loss": 2.496142625808716,
|
| 13723 |
+
"step": 3918
|
| 13724 |
+
},
|
| 13725 |
+
{
|
| 13726 |
+
"epoch": 0.7649899985363712,
|
| 13727 |
+
"grad_norm": 0.16084598004817963,
|
| 13728 |
+
"learning_rate": 0.00020426829268292682,
|
| 13729 |
+
"loss": 2.555075168609619,
|
| 13730 |
+
"step": 3920
|
| 13731 |
+
},
|
| 13732 |
+
{
|
| 13733 |
+
"epoch": 0.7653802995560326,
|
| 13734 |
+
"grad_norm": 0.16996021568775177,
|
| 13735 |
+
"learning_rate": 0.00020392953929539295,
|
| 13736 |
+
"loss": 2.588319778442383,
|
| 13737 |
+
"step": 3922
|
| 13738 |
+
},
|
| 13739 |
+
{
|
| 13740 |
+
"epoch": 0.765770600575694,
|
| 13741 |
+
"grad_norm": 0.20485281944274902,
|
| 13742 |
+
"learning_rate": 0.0002035907859078591,
|
| 13743 |
+
"loss": 2.5906286239624023,
|
| 13744 |
+
"step": 3924
|
| 13745 |
+
},
|
| 13746 |
+
{
|
| 13747 |
+
"epoch": 0.7661609015953554,
|
| 13748 |
+
"grad_norm": 0.17223875224590302,
|
| 13749 |
+
"learning_rate": 0.0002032520325203252,
|
| 13750 |
+
"loss": 2.531831741333008,
|
| 13751 |
+
"step": 3926
|
| 13752 |
+
},
|
| 13753 |
+
{
|
| 13754 |
+
"epoch": 0.7665512026150169,
|
| 13755 |
+
"grad_norm": 0.15181618928909302,
|
| 13756 |
+
"learning_rate": 0.00020291327913279133,
|
| 13757 |
+
"loss": 2.5901434421539307,
|
| 13758 |
+
"step": 3928
|
| 13759 |
+
},
|
| 13760 |
+
{
|
| 13761 |
+
"epoch": 0.7669415036346783,
|
| 13762 |
+
"grad_norm": 0.17268791794776917,
|
| 13763 |
+
"learning_rate": 0.00020257452574525746,
|
| 13764 |
+
"loss": 2.588291645050049,
|
| 13765 |
+
"step": 3930
|
| 13766 |
+
},
|
| 13767 |
+
{
|
| 13768 |
+
"epoch": 0.7673318046543397,
|
| 13769 |
+
"grad_norm": 0.17045532166957855,
|
| 13770 |
+
"learning_rate": 0.00020223577235772359,
|
| 13771 |
+
"loss": 2.59537935256958,
|
| 13772 |
+
"step": 3932
|
| 13773 |
+
},
|
| 13774 |
+
{
|
| 13775 |
+
"epoch": 0.7677221056740011,
|
| 13776 |
+
"grad_norm": 0.1883518546819687,
|
| 13777 |
+
"learning_rate": 0.00020189701897018969,
|
| 13778 |
+
"loss": 2.5058236122131348,
|
| 13779 |
+
"step": 3934
|
| 13780 |
+
},
|
| 13781 |
+
{
|
| 13782 |
+
"epoch": 0.7681124066936625,
|
| 13783 |
+
"grad_norm": 0.18484701216220856,
|
| 13784 |
+
"learning_rate": 0.00020155826558265584,
|
| 13785 |
+
"loss": 2.5812807083129883,
|
| 13786 |
+
"step": 3936
|
| 13787 |
+
},
|
| 13788 |
+
{
|
| 13789 |
+
"epoch": 0.7685027077133239,
|
| 13790 |
+
"grad_norm": 0.14973048865795135,
|
| 13791 |
+
"learning_rate": 0.00020121951219512197,
|
| 13792 |
+
"loss": 2.571558713912964,
|
| 13793 |
+
"step": 3938
|
| 13794 |
+
},
|
| 13795 |
+
{
|
| 13796 |
+
"epoch": 0.7688930087329853,
|
| 13797 |
+
"grad_norm": 0.20014400780200958,
|
| 13798 |
+
"learning_rate": 0.00020088075880758807,
|
| 13799 |
+
"loss": 2.623805522918701,
|
| 13800 |
+
"step": 3940
|
| 13801 |
+
},
|
| 13802 |
+
{
|
| 13803 |
+
"epoch": 0.7692833097526467,
|
| 13804 |
+
"grad_norm": 0.1652064323425293,
|
| 13805 |
+
"learning_rate": 0.00020054200542005422,
|
| 13806 |
+
"loss": 2.5386557579040527,
|
| 13807 |
+
"step": 3942
|
| 13808 |
+
},
|
| 13809 |
+
{
|
| 13810 |
+
"epoch": 0.7696736107723081,
|
| 13811 |
+
"grad_norm": 0.1760433316230774,
|
| 13812 |
+
"learning_rate": 0.00020020325203252032,
|
| 13813 |
+
"loss": 2.593710422515869,
|
| 13814 |
+
"step": 3944
|
| 13815 |
+
},
|
| 13816 |
+
{
|
| 13817 |
+
"epoch": 0.7700639117919695,
|
| 13818 |
+
"grad_norm": 0.1889323741197586,
|
| 13819 |
+
"learning_rate": 0.00019986449864498645,
|
| 13820 |
+
"loss": 2.6240687370300293,
|
| 13821 |
+
"step": 3946
|
| 13822 |
+
},
|
| 13823 |
+
{
|
| 13824 |
+
"epoch": 0.770454212811631,
|
| 13825 |
+
"grad_norm": 0.1653689742088318,
|
| 13826 |
+
"learning_rate": 0.00019952574525745258,
|
| 13827 |
+
"loss": 2.5755746364593506,
|
| 13828 |
+
"step": 3948
|
| 13829 |
+
},
|
| 13830 |
+
{
|
| 13831 |
+
"epoch": 0.7708445138312924,
|
| 13832 |
+
"grad_norm": 0.2080065906047821,
|
| 13833 |
+
"learning_rate": 0.0001991869918699187,
|
| 13834 |
+
"loss": 2.579733371734619,
|
| 13835 |
+
"step": 3950
|
| 13836 |
+
},
|
| 13837 |
+
{
|
| 13838 |
+
"epoch": 0.7712348148509538,
|
| 13839 |
+
"grad_norm": 0.15270163118839264,
|
| 13840 |
+
"learning_rate": 0.00019884823848238483,
|
| 13841 |
+
"loss": 2.5039401054382324,
|
| 13842 |
+
"step": 3952
|
| 13843 |
+
},
|
| 13844 |
+
{
|
| 13845 |
+
"epoch": 0.7716251158706152,
|
| 13846 |
+
"grad_norm": 0.14053085446357727,
|
| 13847 |
+
"learning_rate": 0.00019850948509485096,
|
| 13848 |
+
"loss": 2.5028557777404785,
|
| 13849 |
+
"step": 3954
|
| 13850 |
+
},
|
| 13851 |
+
{
|
| 13852 |
+
"epoch": 0.7720154168902766,
|
| 13853 |
+
"grad_norm": 0.23985590040683746,
|
| 13854 |
+
"learning_rate": 0.0001981707317073171,
|
| 13855 |
+
"loss": 2.644167900085449,
|
| 13856 |
+
"step": 3956
|
| 13857 |
+
},
|
| 13858 |
+
{
|
| 13859 |
+
"epoch": 0.7724057179099381,
|
| 13860 |
+
"grad_norm": 0.17447930574417114,
|
| 13861 |
+
"learning_rate": 0.0001978319783197832,
|
| 13862 |
+
"loss": 2.5589020252227783,
|
| 13863 |
+
"step": 3958
|
| 13864 |
+
},
|
| 13865 |
+
{
|
| 13866 |
+
"epoch": 0.7727960189295995,
|
| 13867 |
+
"grad_norm": 0.14550235867500305,
|
| 13868 |
+
"learning_rate": 0.00019749322493224934,
|
| 13869 |
+
"loss": 2.565448045730591,
|
| 13870 |
+
"step": 3960
|
| 13871 |
+
},
|
| 13872 |
+
{
|
| 13873 |
+
"epoch": 0.7731863199492609,
|
| 13874 |
+
"grad_norm": 0.17985431849956512,
|
| 13875 |
+
"learning_rate": 0.00019715447154471544,
|
| 13876 |
+
"loss": 2.583143472671509,
|
| 13877 |
+
"step": 3962
|
| 13878 |
+
},
|
| 13879 |
+
{
|
| 13880 |
+
"epoch": 0.7735766209689223,
|
| 13881 |
+
"grad_norm": 0.15800729393959045,
|
| 13882 |
+
"learning_rate": 0.00019681571815718157,
|
| 13883 |
+
"loss": 2.5206446647644043,
|
| 13884 |
+
"step": 3964
|
| 13885 |
+
},
|
| 13886 |
+
{
|
| 13887 |
+
"epoch": 0.7739669219885837,
|
| 13888 |
+
"grad_norm": 0.16690972447395325,
|
| 13889 |
+
"learning_rate": 0.0001964769647696477,
|
| 13890 |
+
"loss": 2.6022424697875977,
|
| 13891 |
+
"step": 3966
|
| 13892 |
+
},
|
| 13893 |
+
{
|
| 13894 |
+
"epoch": 0.774357223008245,
|
| 13895 |
+
"grad_norm": 0.24519841372966766,
|
| 13896 |
+
"learning_rate": 0.00019613821138211382,
|
| 13897 |
+
"loss": 2.5993103981018066,
|
| 13898 |
+
"step": 3968
|
| 13899 |
+
},
|
| 13900 |
+
{
|
| 13901 |
+
"epoch": 0.7747475240279065,
|
| 13902 |
+
"grad_norm": 0.14829537272453308,
|
| 13903 |
+
"learning_rate": 0.00019579945799457995,
|
| 13904 |
+
"loss": 2.6016294956207275,
|
| 13905 |
+
"step": 3970
|
| 13906 |
+
},
|
| 13907 |
+
{
|
| 13908 |
+
"epoch": 0.7751378250475679,
|
| 13909 |
+
"grad_norm": 0.19064044952392578,
|
| 13910 |
+
"learning_rate": 0.00019546070460704608,
|
| 13911 |
+
"loss": 2.576812744140625,
|
| 13912 |
+
"step": 3972
|
| 13913 |
+
},
|
| 13914 |
+
{
|
| 13915 |
+
"epoch": 0.7755281260672293,
|
| 13916 |
+
"grad_norm": 0.15719428658485413,
|
| 13917 |
+
"learning_rate": 0.0001951219512195122,
|
| 13918 |
+
"loss": 2.571805000305176,
|
| 13919 |
+
"step": 3974
|
| 13920 |
+
},
|
| 13921 |
+
{
|
| 13922 |
+
"epoch": 0.7759184270868907,
|
| 13923 |
+
"grad_norm": 0.15593615174293518,
|
| 13924 |
+
"learning_rate": 0.0001947831978319783,
|
| 13925 |
+
"loss": 2.561352014541626,
|
| 13926 |
+
"step": 3976
|
| 13927 |
+
},
|
| 13928 |
+
{
|
| 13929 |
+
"epoch": 0.7763087281065522,
|
| 13930 |
+
"grad_norm": 0.31411251425743103,
|
| 13931 |
+
"learning_rate": 0.00019444444444444446,
|
| 13932 |
+
"loss": 2.5556774139404297,
|
| 13933 |
+
"step": 3978
|
| 13934 |
+
},
|
| 13935 |
+
{
|
| 13936 |
+
"epoch": 0.7766990291262136,
|
| 13937 |
+
"grad_norm": 0.1931598037481308,
|
| 13938 |
+
"learning_rate": 0.00019410569105691056,
|
| 13939 |
+
"loss": 2.5170183181762695,
|
| 13940 |
+
"step": 3980
|
| 13941 |
+
},
|
| 13942 |
+
{
|
| 13943 |
+
"epoch": 0.777089330145875,
|
| 13944 |
+
"grad_norm": 0.18125686049461365,
|
| 13945 |
+
"learning_rate": 0.0001937669376693767,
|
| 13946 |
+
"loss": 2.6378984451293945,
|
| 13947 |
+
"step": 3982
|
| 13948 |
+
},
|
| 13949 |
+
{
|
| 13950 |
+
"epoch": 0.7774796311655364,
|
| 13951 |
+
"grad_norm": 0.16872069239616394,
|
| 13952 |
+
"learning_rate": 0.00019342818428184284,
|
| 13953 |
+
"loss": 2.627153158187866,
|
| 13954 |
+
"step": 3984
|
| 13955 |
+
},
|
| 13956 |
+
{
|
| 13957 |
+
"epoch": 0.7778699321851978,
|
| 13958 |
+
"grad_norm": 0.14563177525997162,
|
| 13959 |
+
"learning_rate": 0.00019308943089430894,
|
| 13960 |
+
"loss": 2.5798354148864746,
|
| 13961 |
+
"step": 3986
|
| 13962 |
+
},
|
| 13963 |
+
{
|
| 13964 |
+
"epoch": 0.7782602332048593,
|
| 13965 |
+
"grad_norm": 0.19168442487716675,
|
| 13966 |
+
"learning_rate": 0.00019275067750677507,
|
| 13967 |
+
"loss": 2.5680952072143555,
|
| 13968 |
+
"step": 3988
|
| 13969 |
+
},
|
| 13970 |
+
{
|
| 13971 |
+
"epoch": 0.7786505342245207,
|
| 13972 |
+
"grad_norm": 0.22101518511772156,
|
| 13973 |
+
"learning_rate": 0.0001924119241192412,
|
| 13974 |
+
"loss": 2.5749154090881348,
|
| 13975 |
+
"step": 3990
|
| 13976 |
+
},
|
| 13977 |
+
{
|
| 13978 |
+
"epoch": 0.7790408352441821,
|
| 13979 |
+
"grad_norm": 0.24324040114879608,
|
| 13980 |
+
"learning_rate": 0.00019207317073170733,
|
| 13981 |
+
"loss": 2.6560585498809814,
|
| 13982 |
+
"step": 3992
|
| 13983 |
+
},
|
| 13984 |
+
{
|
| 13985 |
+
"epoch": 0.7794311362638435,
|
| 13986 |
+
"grad_norm": 0.21770967543125153,
|
| 13987 |
+
"learning_rate": 0.00019173441734417343,
|
| 13988 |
+
"loss": 2.5669169425964355,
|
| 13989 |
+
"step": 3994
|
| 13990 |
+
},
|
| 13991 |
+
{
|
| 13992 |
+
"epoch": 0.779821437283505,
|
| 13993 |
+
"grad_norm": 0.19748254120349884,
|
| 13994 |
+
"learning_rate": 0.00019139566395663958,
|
| 13995 |
+
"loss": 2.603724956512451,
|
| 13996 |
+
"step": 3996
|
| 13997 |
+
},
|
| 13998 |
+
{
|
| 13999 |
+
"epoch": 0.7802117383031664,
|
| 14000 |
+
"grad_norm": 0.17681244015693665,
|
| 14001 |
+
"learning_rate": 0.0001910569105691057,
|
| 14002 |
+
"loss": 2.5790457725524902,
|
| 14003 |
+
"step": 3998
|
| 14004 |
+
},
|
| 14005 |
+
{
|
| 14006 |
+
"epoch": 0.7806020393228277,
|
| 14007 |
+
"grad_norm": 0.1567000448703766,
|
| 14008 |
+
"learning_rate": 0.0001907181571815718,
|
| 14009 |
+
"loss": 2.592257499694824,
|
| 14010 |
+
"step": 4000
|
| 14011 |
+
},
|
| 14012 |
+
{
|
| 14013 |
+
"epoch": 0.7809923403424891,
|
| 14014 |
+
"grad_norm": 0.15929359197616577,
|
| 14015 |
+
"learning_rate": 0.00019037940379403796,
|
| 14016 |
+
"loss": 2.556138038635254,
|
| 14017 |
+
"step": 4002
|
| 14018 |
+
},
|
| 14019 |
+
{
|
| 14020 |
+
"epoch": 0.7813826413621505,
|
| 14021 |
+
"grad_norm": 0.1429731696844101,
|
| 14022 |
+
"learning_rate": 0.00019004065040650406,
|
| 14023 |
+
"loss": 2.5789794921875,
|
| 14024 |
+
"step": 4004
|
| 14025 |
+
},
|
| 14026 |
+
{
|
| 14027 |
+
"epoch": 0.7817729423818119,
|
| 14028 |
+
"grad_norm": 0.15262185037136078,
|
| 14029 |
+
"learning_rate": 0.0001897018970189702,
|
| 14030 |
+
"loss": 2.589235782623291,
|
| 14031 |
+
"step": 4006
|
| 14032 |
+
},
|
| 14033 |
+
{
|
| 14034 |
+
"epoch": 0.7821632434014734,
|
| 14035 |
+
"grad_norm": 0.1307385414838791,
|
| 14036 |
+
"learning_rate": 0.00018936314363143632,
|
| 14037 |
+
"loss": 2.581735610961914,
|
| 14038 |
+
"step": 4008
|
| 14039 |
+
},
|
| 14040 |
+
{
|
| 14041 |
+
"epoch": 0.7825535444211348,
|
| 14042 |
+
"grad_norm": 0.1898825615644455,
|
| 14043 |
+
"learning_rate": 0.00018902439024390244,
|
| 14044 |
+
"loss": 2.561002254486084,
|
| 14045 |
+
"step": 4010
|
| 14046 |
+
},
|
| 14047 |
+
{
|
| 14048 |
+
"epoch": 0.7829438454407962,
|
| 14049 |
+
"grad_norm": 0.15590326488018036,
|
| 14050 |
+
"learning_rate": 0.00018868563685636857,
|
| 14051 |
+
"loss": 2.565084934234619,
|
| 14052 |
+
"step": 4012
|
| 14053 |
+
},
|
| 14054 |
+
{
|
| 14055 |
+
"epoch": 0.7833341464604576,
|
| 14056 |
+
"grad_norm": 0.15165594220161438,
|
| 14057 |
+
"learning_rate": 0.0001883468834688347,
|
| 14058 |
+
"loss": 2.624667167663574,
|
| 14059 |
+
"step": 4014
|
| 14060 |
+
},
|
| 14061 |
+
{
|
| 14062 |
+
"epoch": 0.783724447480119,
|
| 14063 |
+
"grad_norm": 0.1737259477376938,
|
| 14064 |
+
"learning_rate": 0.00018800813008130083,
|
| 14065 |
+
"loss": 2.5539889335632324,
|
| 14066 |
+
"step": 4016
|
| 14067 |
+
},
|
| 14068 |
+
{
|
| 14069 |
+
"epoch": 0.7841147484997805,
|
| 14070 |
+
"grad_norm": 0.22598309814929962,
|
| 14071 |
+
"learning_rate": 0.00018766937669376693,
|
| 14072 |
+
"loss": 2.5518367290496826,
|
| 14073 |
+
"step": 4018
|
| 14074 |
+
},
|
| 14075 |
+
{
|
| 14076 |
+
"epoch": 0.7845050495194419,
|
| 14077 |
+
"grad_norm": 0.16865494847297668,
|
| 14078 |
+
"learning_rate": 0.00018733062330623308,
|
| 14079 |
+
"loss": 2.5833606719970703,
|
| 14080 |
+
"step": 4020
|
| 14081 |
+
},
|
| 14082 |
+
{
|
| 14083 |
+
"epoch": 0.7848953505391033,
|
| 14084 |
+
"grad_norm": 0.2132740169763565,
|
| 14085 |
+
"learning_rate": 0.00018699186991869918,
|
| 14086 |
+
"loss": 2.5591073036193848,
|
| 14087 |
+
"step": 4022
|
| 14088 |
+
},
|
| 14089 |
+
{
|
| 14090 |
+
"epoch": 0.7852856515587647,
|
| 14091 |
+
"grad_norm": 0.18102803826332092,
|
| 14092 |
+
"learning_rate": 0.0001866531165311653,
|
| 14093 |
+
"loss": 2.63320255279541,
|
| 14094 |
+
"step": 4024
|
| 14095 |
+
},
|
| 14096 |
+
{
|
| 14097 |
+
"epoch": 0.7856759525784262,
|
| 14098 |
+
"grad_norm": 0.17100101709365845,
|
| 14099 |
+
"learning_rate": 0.00018631436314363144,
|
| 14100 |
+
"loss": 2.5652432441711426,
|
| 14101 |
+
"step": 4026
|
| 14102 |
+
},
|
| 14103 |
+
{
|
| 14104 |
+
"epoch": 0.7860662535980876,
|
| 14105 |
+
"grad_norm": 0.20948129892349243,
|
| 14106 |
+
"learning_rate": 0.00018597560975609756,
|
| 14107 |
+
"loss": 2.56374454498291,
|
| 14108 |
+
"step": 4028
|
| 14109 |
+
},
|
| 14110 |
+
{
|
| 14111 |
+
"epoch": 0.786456554617749,
|
| 14112 |
+
"grad_norm": 0.15448376536369324,
|
| 14113 |
+
"learning_rate": 0.0001856368563685637,
|
| 14114 |
+
"loss": 2.6028807163238525,
|
| 14115 |
+
"step": 4030
|
| 14116 |
+
},
|
| 14117 |
+
{
|
| 14118 |
+
"epoch": 0.7868468556374103,
|
| 14119 |
+
"grad_norm": 0.20010800659656525,
|
| 14120 |
+
"learning_rate": 0.00018529810298102982,
|
| 14121 |
+
"loss": 2.6111092567443848,
|
| 14122 |
+
"step": 4032
|
| 14123 |
+
},
|
| 14124 |
+
{
|
| 14125 |
+
"epoch": 0.7872371566570717,
|
| 14126 |
+
"grad_norm": 0.17586562037467957,
|
| 14127 |
+
"learning_rate": 0.00018495934959349595,
|
| 14128 |
+
"loss": 2.552945613861084,
|
| 14129 |
+
"step": 4034
|
| 14130 |
+
},
|
| 14131 |
+
{
|
| 14132 |
+
"epoch": 0.7876274576767331,
|
| 14133 |
+
"grad_norm": 0.14558599889278412,
|
| 14134 |
+
"learning_rate": 0.00018462059620596205,
|
| 14135 |
+
"loss": 2.524658679962158,
|
| 14136 |
+
"step": 4036
|
| 14137 |
+
},
|
| 14138 |
+
{
|
| 14139 |
+
"epoch": 0.7880177586963946,
|
| 14140 |
+
"grad_norm": 0.1485646367073059,
|
| 14141 |
+
"learning_rate": 0.0001842818428184282,
|
| 14142 |
+
"loss": 2.601583957672119,
|
| 14143 |
+
"step": 4038
|
| 14144 |
+
},
|
| 14145 |
+
{
|
| 14146 |
+
"epoch": 0.788408059716056,
|
| 14147 |
+
"grad_norm": 0.13467849791049957,
|
| 14148 |
+
"learning_rate": 0.0001839430894308943,
|
| 14149 |
+
"loss": 2.542520523071289,
|
| 14150 |
+
"step": 4040
|
| 14151 |
+
},
|
| 14152 |
+
{
|
| 14153 |
+
"epoch": 0.7887983607357174,
|
| 14154 |
+
"grad_norm": 0.1708490550518036,
|
| 14155 |
+
"learning_rate": 0.00018360433604336043,
|
| 14156 |
+
"loss": 2.5417308807373047,
|
| 14157 |
+
"step": 4042
|
| 14158 |
+
},
|
| 14159 |
+
{
|
| 14160 |
+
"epoch": 0.7891886617553788,
|
| 14161 |
+
"grad_norm": 0.1759440004825592,
|
| 14162 |
+
"learning_rate": 0.00018326558265582658,
|
| 14163 |
+
"loss": 2.592266321182251,
|
| 14164 |
+
"step": 4044
|
| 14165 |
+
},
|
| 14166 |
+
{
|
| 14167 |
+
"epoch": 0.7895789627750402,
|
| 14168 |
+
"grad_norm": 0.1724332720041275,
|
| 14169 |
+
"learning_rate": 0.00018292682926829268,
|
| 14170 |
+
"loss": 2.589890718460083,
|
| 14171 |
+
"step": 4046
|
| 14172 |
+
},
|
| 14173 |
+
{
|
| 14174 |
+
"epoch": 0.7899692637947017,
|
| 14175 |
+
"grad_norm": 0.1412181705236435,
|
| 14176 |
+
"learning_rate": 0.0001825880758807588,
|
| 14177 |
+
"loss": 2.5618956089019775,
|
| 14178 |
+
"step": 4048
|
| 14179 |
+
},
|
| 14180 |
+
{
|
| 14181 |
+
"epoch": 0.7903595648143631,
|
| 14182 |
+
"grad_norm": 0.16985617578029633,
|
| 14183 |
+
"learning_rate": 0.00018224932249322494,
|
| 14184 |
+
"loss": 2.6115341186523438,
|
| 14185 |
+
"step": 4050
|
| 14186 |
+
},
|
| 14187 |
+
{
|
| 14188 |
+
"epoch": 0.7907498658340245,
|
| 14189 |
+
"grad_norm": 0.20384512841701508,
|
| 14190 |
+
"learning_rate": 0.00018191056910569106,
|
| 14191 |
+
"loss": 2.6510531902313232,
|
| 14192 |
+
"step": 4052
|
| 14193 |
+
},
|
| 14194 |
+
{
|
| 14195 |
+
"epoch": 0.7911401668536859,
|
| 14196 |
+
"grad_norm": 0.19361013174057007,
|
| 14197 |
+
"learning_rate": 0.00018157181571815717,
|
| 14198 |
+
"loss": 2.557359457015991,
|
| 14199 |
+
"step": 4054
|
| 14200 |
+
},
|
| 14201 |
+
{
|
| 14202 |
+
"epoch": 0.7915304678733474,
|
| 14203 |
+
"grad_norm": 0.19707530736923218,
|
| 14204 |
+
"learning_rate": 0.00018123306233062332,
|
| 14205 |
+
"loss": 2.5668225288391113,
|
| 14206 |
+
"step": 4056
|
| 14207 |
+
},
|
| 14208 |
+
{
|
| 14209 |
+
"epoch": 0.7919207688930088,
|
| 14210 |
+
"grad_norm": 0.22480398416519165,
|
| 14211 |
+
"learning_rate": 0.00018089430894308945,
|
| 14212 |
+
"loss": 2.546961784362793,
|
| 14213 |
+
"step": 4058
|
| 14214 |
+
},
|
| 14215 |
+
{
|
| 14216 |
+
"epoch": 0.7923110699126702,
|
| 14217 |
+
"grad_norm": 0.18314160406589508,
|
| 14218 |
+
"learning_rate": 0.00018055555555555555,
|
| 14219 |
+
"loss": 2.5718512535095215,
|
| 14220 |
+
"step": 4060
|
| 14221 |
+
},
|
| 14222 |
+
{
|
| 14223 |
+
"epoch": 0.7927013709323315,
|
| 14224 |
+
"grad_norm": 0.15981733798980713,
|
| 14225 |
+
"learning_rate": 0.0001802168021680217,
|
| 14226 |
+
"loss": 2.565263271331787,
|
| 14227 |
+
"step": 4062
|
| 14228 |
+
},
|
| 14229 |
+
{
|
| 14230 |
+
"epoch": 0.7930916719519929,
|
| 14231 |
+
"grad_norm": 0.16741172969341278,
|
| 14232 |
+
"learning_rate": 0.0001798780487804878,
|
| 14233 |
+
"loss": 2.570672035217285,
|
| 14234 |
+
"step": 4064
|
| 14235 |
+
},
|
| 14236 |
+
{
|
| 14237 |
+
"epoch": 0.7934819729716543,
|
| 14238 |
+
"grad_norm": 0.2083830088376999,
|
| 14239 |
+
"learning_rate": 0.00017953929539295393,
|
| 14240 |
+
"loss": 2.633359909057617,
|
| 14241 |
+
"step": 4066
|
| 14242 |
+
},
|
| 14243 |
+
{
|
| 14244 |
+
"epoch": 0.7938722739913158,
|
| 14245 |
+
"grad_norm": 0.13357391953468323,
|
| 14246 |
+
"learning_rate": 0.00017920054200542006,
|
| 14247 |
+
"loss": 2.5295464992523193,
|
| 14248 |
+
"step": 4068
|
| 14249 |
+
},
|
| 14250 |
+
{
|
| 14251 |
+
"epoch": 0.7942625750109772,
|
| 14252 |
+
"grad_norm": 0.208669975399971,
|
| 14253 |
+
"learning_rate": 0.00017886178861788618,
|
| 14254 |
+
"loss": 2.5854387283325195,
|
| 14255 |
+
"step": 4070
|
| 14256 |
+
},
|
| 14257 |
+
{
|
| 14258 |
+
"epoch": 0.7946528760306386,
|
| 14259 |
+
"grad_norm": 0.15506263077259064,
|
| 14260 |
+
"learning_rate": 0.0001785230352303523,
|
| 14261 |
+
"loss": 2.5552585124969482,
|
| 14262 |
+
"step": 4072
|
| 14263 |
+
},
|
| 14264 |
+
{
|
| 14265 |
+
"epoch": 0.7950431770503,
|
| 14266 |
+
"grad_norm": 0.1718740016222,
|
| 14267 |
+
"learning_rate": 0.00017818428184281844,
|
| 14268 |
+
"loss": 2.620704174041748,
|
| 14269 |
+
"step": 4074
|
| 14270 |
+
},
|
| 14271 |
+
{
|
| 14272 |
+
"epoch": 0.7954334780699615,
|
| 14273 |
+
"grad_norm": 0.1663367748260498,
|
| 14274 |
+
"learning_rate": 0.00017784552845528457,
|
| 14275 |
+
"loss": 2.5669777393341064,
|
| 14276 |
+
"step": 4076
|
| 14277 |
+
},
|
| 14278 |
+
{
|
| 14279 |
+
"epoch": 0.7958237790896229,
|
| 14280 |
+
"grad_norm": 0.20067662000656128,
|
| 14281 |
+
"learning_rate": 0.00017750677506775067,
|
| 14282 |
+
"loss": 2.586366891860962,
|
| 14283 |
+
"step": 4078
|
| 14284 |
+
},
|
| 14285 |
+
{
|
| 14286 |
+
"epoch": 0.7962140801092843,
|
| 14287 |
+
"grad_norm": 0.143747940659523,
|
| 14288 |
+
"learning_rate": 0.00017716802168021682,
|
| 14289 |
+
"loss": 2.512115955352783,
|
| 14290 |
+
"step": 4080
|
| 14291 |
+
},
|
| 14292 |
+
{
|
| 14293 |
+
"epoch": 0.7966043811289457,
|
| 14294 |
+
"grad_norm": 0.18528424203395844,
|
| 14295 |
+
"learning_rate": 0.00017682926829268292,
|
| 14296 |
+
"loss": 2.617609977722168,
|
| 14297 |
+
"step": 4082
|
| 14298 |
+
},
|
| 14299 |
+
{
|
| 14300 |
+
"epoch": 0.7969946821486071,
|
| 14301 |
+
"grad_norm": 0.15560515224933624,
|
| 14302 |
+
"learning_rate": 0.00017649051490514905,
|
| 14303 |
+
"loss": 2.6140503883361816,
|
| 14304 |
+
"step": 4084
|
| 14305 |
+
},
|
| 14306 |
+
{
|
| 14307 |
+
"epoch": 0.7973849831682686,
|
| 14308 |
+
"grad_norm": 0.22667734324932098,
|
| 14309 |
+
"learning_rate": 0.00017615176151761518,
|
| 14310 |
+
"loss": 2.5920169353485107,
|
| 14311 |
+
"step": 4086
|
| 14312 |
+
},
|
| 14313 |
+
{
|
| 14314 |
+
"epoch": 0.79777528418793,
|
| 14315 |
+
"grad_norm": 0.18524600565433502,
|
| 14316 |
+
"learning_rate": 0.0001758130081300813,
|
| 14317 |
+
"loss": 2.5360119342803955,
|
| 14318 |
+
"step": 4088
|
| 14319 |
+
},
|
| 14320 |
+
{
|
| 14321 |
+
"epoch": 0.7981655852075914,
|
| 14322 |
+
"grad_norm": 0.18081827461719513,
|
| 14323 |
+
"learning_rate": 0.00017547425474254743,
|
| 14324 |
+
"loss": 2.55692982673645,
|
| 14325 |
+
"step": 4090
|
| 14326 |
+
},
|
| 14327 |
+
{
|
| 14328 |
+
"epoch": 0.7985558862272528,
|
| 14329 |
+
"grad_norm": 0.17460519075393677,
|
| 14330 |
+
"learning_rate": 0.00017513550135501356,
|
| 14331 |
+
"loss": 2.563039779663086,
|
| 14332 |
+
"step": 4092
|
| 14333 |
+
},
|
| 14334 |
+
{
|
| 14335 |
+
"epoch": 0.7989461872469141,
|
| 14336 |
+
"grad_norm": 0.14853926002979279,
|
| 14337 |
+
"learning_rate": 0.00017479674796747969,
|
| 14338 |
+
"loss": 2.559640407562256,
|
| 14339 |
+
"step": 4094
|
| 14340 |
+
},
|
| 14341 |
+
{
|
| 14342 |
+
"epoch": 0.7993364882665756,
|
| 14343 |
+
"grad_norm": 0.16719399392604828,
|
| 14344 |
+
"learning_rate": 0.00017445799457994579,
|
| 14345 |
+
"loss": 2.606109142303467,
|
| 14346 |
+
"step": 4096
|
| 14347 |
+
},
|
| 14348 |
+
{
|
| 14349 |
+
"epoch": 0.799726789286237,
|
| 14350 |
+
"grad_norm": 0.14068223536014557,
|
| 14351 |
+
"learning_rate": 0.00017411924119241194,
|
| 14352 |
+
"loss": 2.5343856811523438,
|
| 14353 |
+
"step": 4098
|
| 14354 |
+
},
|
| 14355 |
+
{
|
| 14356 |
+
"epoch": 0.8001170903058984,
|
| 14357 |
+
"grad_norm": 0.22857992351055145,
|
| 14358 |
+
"learning_rate": 0.00017378048780487804,
|
| 14359 |
+
"loss": 2.656184196472168,
|
| 14360 |
+
"step": 4100
|
| 14361 |
+
},
|
| 14362 |
+
{
|
| 14363 |
+
"epoch": 0.8005073913255598,
|
| 14364 |
+
"grad_norm": 0.17621064186096191,
|
| 14365 |
+
"learning_rate": 0.00017344173441734417,
|
| 14366 |
+
"loss": 2.6049177646636963,
|
| 14367 |
+
"step": 4102
|
| 14368 |
+
},
|
| 14369 |
+
{
|
| 14370 |
+
"epoch": 0.8008976923452212,
|
| 14371 |
+
"grad_norm": 0.1604859083890915,
|
| 14372 |
+
"learning_rate": 0.00017310298102981032,
|
| 14373 |
+
"loss": 2.5735831260681152,
|
| 14374 |
+
"step": 4104
|
| 14375 |
}
|
| 14376 |
],
|
| 14377 |
"logging_steps": 2,
|
|
|
|
| 14391 |
"attributes": {}
|
| 14392 |
}
|
| 14393 |
},
|
| 14394 |
+
"total_flos": 1.312389215853478e+18,
|
| 14395 |
"train_batch_size": 6,
|
| 14396 |
"trial_name": null,
|
| 14397 |
"trial_params": null
|