Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
sft
unsloth
trl
conversational
text-generation-inference
Instructions to use Ba2han/TR_SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/TR_SFT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/TR_SFT") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/TR_SFT") model = AutoModelForCausalLM.from_pretrained("Ba2han/TR_SFT", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/TR_SFT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/TR_SFT" # 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/TR_SFT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ba2han/TR_SFT
- SGLang
How to use Ba2han/TR_SFT 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/TR_SFT" \ --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/TR_SFT", "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/TR_SFT" \ --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/TR_SFT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use Ba2han/TR_SFT with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/TR_SFT to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/TR_SFT to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ba2han/TR_SFT to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Ba2han/TR_SFT", max_seq_length=2048, ) - Docker Model Runner
How to use Ba2han/TR_SFT with Docker Model Runner:
docker model run hf.co/Ba2han/TR_SFT
Training in progress, step 4740, 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 2519929824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2be05f0947b809cc2de317e158cf2764844d62f707856f4fb34db9131eecf71
|
| 3 |
size 2519929824
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262848364
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41ea59a87b004653cf32b962eab21e3e64e3697e9b34177a9453d247697cf6ad
|
| 3 |
size 1262848364
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d895ccae2b55d4ea213653ca4a80d00de131463e105716eab1b7022906f260bf
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10233
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e81a0b2afa59686ef1860543e0c430e9f2158cb60d3f799023a1619c5009270
|
| 3 |
size 10233
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 948,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -14971,6 +14971,1673 @@
|
|
| 14971 |
"learning_rate": 8.527827648114902e-05,
|
| 14972 |
"loss": 1.9751338958740234,
|
| 14973 |
"step": 4266
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14974 |
}
|
| 14975 |
],
|
| 14976 |
"logging_steps": 2,
|
|
@@ -14985,12 +16652,12 @@
|
|
| 14985 |
"should_evaluate": false,
|
| 14986 |
"should_log": false,
|
| 14987 |
"should_save": true,
|
| 14988 |
-
"should_training_stop":
|
| 14989 |
},
|
| 14990 |
"attributes": {}
|
| 14991 |
}
|
| 14992 |
},
|
| 14993 |
-
"total_flos":
|
| 14994 |
"train_batch_size": 8,
|
| 14995 |
"trial_name": null,
|
| 14996 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
"eval_steps": 948,
|
| 7 |
+
"global_step": 4740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14971 |
"learning_rate": 8.527827648114902e-05,
|
| 14972 |
"loss": 1.9751338958740234,
|
| 14973 |
"step": 4266
|
| 14974 |
+
},
|
| 14975 |
+
{
|
| 14976 |
+
"epoch": 0.9004931824775166,
|
| 14977 |
+
"grad_norm": 0.10884717106819153,
|
| 14978 |
+
"learning_rate": 8.491921005385997e-05,
|
| 14979 |
+
"loss": 1.9218369722366333,
|
| 14980 |
+
"step": 4268
|
| 14981 |
+
},
|
| 14982 |
+
{
|
| 14983 |
+
"epoch": 0.9009151567898305,
|
| 14984 |
+
"grad_norm": 0.10807453095912933,
|
| 14985 |
+
"learning_rate": 8.456014362657093e-05,
|
| 14986 |
+
"loss": 1.9406864643096924,
|
| 14987 |
+
"step": 4270
|
| 14988 |
+
},
|
| 14989 |
+
{
|
| 14990 |
+
"epoch": 0.9013371311021442,
|
| 14991 |
+
"grad_norm": 0.10760314017534256,
|
| 14992 |
+
"learning_rate": 8.420107719928187e-05,
|
| 14993 |
+
"loss": 2.030202627182007,
|
| 14994 |
+
"step": 4272
|
| 14995 |
+
},
|
| 14996 |
+
{
|
| 14997 |
+
"epoch": 0.9017591054144579,
|
| 14998 |
+
"grad_norm": 0.10374918580055237,
|
| 14999 |
+
"learning_rate": 8.384201077199282e-05,
|
| 15000 |
+
"loss": 1.944858193397522,
|
| 15001 |
+
"step": 4274
|
| 15002 |
+
},
|
| 15003 |
+
{
|
| 15004 |
+
"epoch": 0.9021810797267716,
|
| 15005 |
+
"grad_norm": 0.11201688647270203,
|
| 15006 |
+
"learning_rate": 8.348294434470378e-05,
|
| 15007 |
+
"loss": 1.99154794216156,
|
| 15008 |
+
"step": 4276
|
| 15009 |
+
},
|
| 15010 |
+
{
|
| 15011 |
+
"epoch": 0.9026030540390854,
|
| 15012 |
+
"grad_norm": 0.09922835230827332,
|
| 15013 |
+
"learning_rate": 8.312387791741473e-05,
|
| 15014 |
+
"loss": 1.9297547340393066,
|
| 15015 |
+
"step": 4278
|
| 15016 |
+
},
|
| 15017 |
+
{
|
| 15018 |
+
"epoch": 0.9030250283513991,
|
| 15019 |
+
"grad_norm": 0.10309100151062012,
|
| 15020 |
+
"learning_rate": 8.276481149012569e-05,
|
| 15021 |
+
"loss": 1.9827690124511719,
|
| 15022 |
+
"step": 4280
|
| 15023 |
+
},
|
| 15024 |
+
{
|
| 15025 |
+
"epoch": 0.9034470026637128,
|
| 15026 |
+
"grad_norm": 0.10575927048921585,
|
| 15027 |
+
"learning_rate": 8.240574506283663e-05,
|
| 15028 |
+
"loss": 2.0133469104766846,
|
| 15029 |
+
"step": 4282
|
| 15030 |
+
},
|
| 15031 |
+
{
|
| 15032 |
+
"epoch": 0.9038689769760266,
|
| 15033 |
+
"grad_norm": 0.11572188884019852,
|
| 15034 |
+
"learning_rate": 8.204667863554759e-05,
|
| 15035 |
+
"loss": 1.942476749420166,
|
| 15036 |
+
"step": 4284
|
| 15037 |
+
},
|
| 15038 |
+
{
|
| 15039 |
+
"epoch": 0.9042909512883404,
|
| 15040 |
+
"grad_norm": 0.10649754852056503,
|
| 15041 |
+
"learning_rate": 8.168761220825854e-05,
|
| 15042 |
+
"loss": 1.9683701992034912,
|
| 15043 |
+
"step": 4286
|
| 15044 |
+
},
|
| 15045 |
+
{
|
| 15046 |
+
"epoch": 0.9047129256006541,
|
| 15047 |
+
"grad_norm": 0.11013828217983246,
|
| 15048 |
+
"learning_rate": 8.132854578096948e-05,
|
| 15049 |
+
"loss": 1.9389806985855103,
|
| 15050 |
+
"step": 4288
|
| 15051 |
+
},
|
| 15052 |
+
{
|
| 15053 |
+
"epoch": 0.9051348999129678,
|
| 15054 |
+
"grad_norm": 0.09807085990905762,
|
| 15055 |
+
"learning_rate": 8.096947935368044e-05,
|
| 15056 |
+
"loss": 1.9025166034698486,
|
| 15057 |
+
"step": 4290
|
| 15058 |
+
},
|
| 15059 |
+
{
|
| 15060 |
+
"epoch": 0.9055568742252815,
|
| 15061 |
+
"grad_norm": 0.10324486345052719,
|
| 15062 |
+
"learning_rate": 8.061041292639139e-05,
|
| 15063 |
+
"loss": 2.0151143074035645,
|
| 15064 |
+
"step": 4292
|
| 15065 |
+
},
|
| 15066 |
+
{
|
| 15067 |
+
"epoch": 0.9059788485375952,
|
| 15068 |
+
"grad_norm": 0.11508278548717499,
|
| 15069 |
+
"learning_rate": 8.025134649910235e-05,
|
| 15070 |
+
"loss": 1.9715490341186523,
|
| 15071 |
+
"step": 4294
|
| 15072 |
+
},
|
| 15073 |
+
{
|
| 15074 |
+
"epoch": 0.906400822849909,
|
| 15075 |
+
"grad_norm": 0.10184572637081146,
|
| 15076 |
+
"learning_rate": 7.989228007181329e-05,
|
| 15077 |
+
"loss": 1.9775052070617676,
|
| 15078 |
+
"step": 4296
|
| 15079 |
+
},
|
| 15080 |
+
{
|
| 15081 |
+
"epoch": 0.9068227971622228,
|
| 15082 |
+
"grad_norm": 0.10934049636125565,
|
| 15083 |
+
"learning_rate": 7.953321364452424e-05,
|
| 15084 |
+
"loss": 1.9419037103652954,
|
| 15085 |
+
"step": 4298
|
| 15086 |
+
},
|
| 15087 |
+
{
|
| 15088 |
+
"epoch": 0.9072447714745365,
|
| 15089 |
+
"grad_norm": 0.11035382747650146,
|
| 15090 |
+
"learning_rate": 7.91741472172352e-05,
|
| 15091 |
+
"loss": 2.0245814323425293,
|
| 15092 |
+
"step": 4300
|
| 15093 |
+
},
|
| 15094 |
+
{
|
| 15095 |
+
"epoch": 0.9076667457868502,
|
| 15096 |
+
"grad_norm": 0.1122780591249466,
|
| 15097 |
+
"learning_rate": 7.881508078994614e-05,
|
| 15098 |
+
"loss": 1.9756752252578735,
|
| 15099 |
+
"step": 4302
|
| 15100 |
+
},
|
| 15101 |
+
{
|
| 15102 |
+
"epoch": 0.908088720099164,
|
| 15103 |
+
"grad_norm": 0.10943111032247543,
|
| 15104 |
+
"learning_rate": 7.84560143626571e-05,
|
| 15105 |
+
"loss": 1.9726569652557373,
|
| 15106 |
+
"step": 4304
|
| 15107 |
+
},
|
| 15108 |
+
{
|
| 15109 |
+
"epoch": 0.9085106944114777,
|
| 15110 |
+
"grad_norm": 0.11035355925559998,
|
| 15111 |
+
"learning_rate": 7.809694793536805e-05,
|
| 15112 |
+
"loss": 2.0262718200683594,
|
| 15113 |
+
"step": 4306
|
| 15114 |
+
},
|
| 15115 |
+
{
|
| 15116 |
+
"epoch": 0.9089326687237914,
|
| 15117 |
+
"grad_norm": 0.10763981193304062,
|
| 15118 |
+
"learning_rate": 7.7737881508079e-05,
|
| 15119 |
+
"loss": 1.9832899570465088,
|
| 15120 |
+
"step": 4308
|
| 15121 |
+
},
|
| 15122 |
+
{
|
| 15123 |
+
"epoch": 0.9093546430361051,
|
| 15124 |
+
"grad_norm": 0.10239090770483017,
|
| 15125 |
+
"learning_rate": 7.737881508078995e-05,
|
| 15126 |
+
"loss": 1.9645538330078125,
|
| 15127 |
+
"step": 4310
|
| 15128 |
+
},
|
| 15129 |
+
{
|
| 15130 |
+
"epoch": 0.909776617348419,
|
| 15131 |
+
"grad_norm": 0.109678253531456,
|
| 15132 |
+
"learning_rate": 7.70197486535009e-05,
|
| 15133 |
+
"loss": 1.9875560998916626,
|
| 15134 |
+
"step": 4312
|
| 15135 |
+
},
|
| 15136 |
+
{
|
| 15137 |
+
"epoch": 0.9101985916607327,
|
| 15138 |
+
"grad_norm": 0.12480778247117996,
|
| 15139 |
+
"learning_rate": 7.666068222621186e-05,
|
| 15140 |
+
"loss": 1.9042906761169434,
|
| 15141 |
+
"step": 4314
|
| 15142 |
+
},
|
| 15143 |
+
{
|
| 15144 |
+
"epoch": 0.9106205659730464,
|
| 15145 |
+
"grad_norm": 0.10408678650856018,
|
| 15146 |
+
"learning_rate": 7.630161579892281e-05,
|
| 15147 |
+
"loss": 2.029926300048828,
|
| 15148 |
+
"step": 4316
|
| 15149 |
+
},
|
| 15150 |
+
{
|
| 15151 |
+
"epoch": 0.9110425402853601,
|
| 15152 |
+
"grad_norm": 0.1103670671582222,
|
| 15153 |
+
"learning_rate": 7.594254937163375e-05,
|
| 15154 |
+
"loss": 1.989965558052063,
|
| 15155 |
+
"step": 4318
|
| 15156 |
+
},
|
| 15157 |
+
{
|
| 15158 |
+
"epoch": 0.9114645145976739,
|
| 15159 |
+
"grad_norm": 0.10089827328920364,
|
| 15160 |
+
"learning_rate": 7.558348294434471e-05,
|
| 15161 |
+
"loss": 1.9067894220352173,
|
| 15162 |
+
"step": 4320
|
| 15163 |
+
},
|
| 15164 |
+
{
|
| 15165 |
+
"epoch": 0.9118864889099876,
|
| 15166 |
+
"grad_norm": 0.10455714166164398,
|
| 15167 |
+
"learning_rate": 7.522441651705567e-05,
|
| 15168 |
+
"loss": 1.9374706745147705,
|
| 15169 |
+
"step": 4322
|
| 15170 |
+
},
|
| 15171 |
+
{
|
| 15172 |
+
"epoch": 0.9123084632223013,
|
| 15173 |
+
"grad_norm": 0.12277254462242126,
|
| 15174 |
+
"learning_rate": 7.48653500897666e-05,
|
| 15175 |
+
"loss": 1.9924230575561523,
|
| 15176 |
+
"step": 4324
|
| 15177 |
+
},
|
| 15178 |
+
{
|
| 15179 |
+
"epoch": 0.9127304375346151,
|
| 15180 |
+
"grad_norm": 0.10296517610549927,
|
| 15181 |
+
"learning_rate": 7.450628366247756e-05,
|
| 15182 |
+
"loss": 1.976456880569458,
|
| 15183 |
+
"step": 4326
|
| 15184 |
+
},
|
| 15185 |
+
{
|
| 15186 |
+
"epoch": 0.9131524118469289,
|
| 15187 |
+
"grad_norm": 0.09838514775037766,
|
| 15188 |
+
"learning_rate": 7.414721723518852e-05,
|
| 15189 |
+
"loss": 1.8516685962677002,
|
| 15190 |
+
"step": 4328
|
| 15191 |
+
},
|
| 15192 |
+
{
|
| 15193 |
+
"epoch": 0.9135743861592426,
|
| 15194 |
+
"grad_norm": 0.10393622517585754,
|
| 15195 |
+
"learning_rate": 7.378815080789947e-05,
|
| 15196 |
+
"loss": 1.9571295976638794,
|
| 15197 |
+
"step": 4330
|
| 15198 |
+
},
|
| 15199 |
+
{
|
| 15200 |
+
"epoch": 0.9139963604715563,
|
| 15201 |
+
"grad_norm": 0.10954293608665466,
|
| 15202 |
+
"learning_rate": 7.342908438061041e-05,
|
| 15203 |
+
"loss": 1.977062463760376,
|
| 15204 |
+
"step": 4332
|
| 15205 |
+
},
|
| 15206 |
+
{
|
| 15207 |
+
"epoch": 0.91441833478387,
|
| 15208 |
+
"grad_norm": 0.11800585687160492,
|
| 15209 |
+
"learning_rate": 7.307001795332137e-05,
|
| 15210 |
+
"loss": 1.9611639976501465,
|
| 15211 |
+
"step": 4334
|
| 15212 |
+
},
|
| 15213 |
+
{
|
| 15214 |
+
"epoch": 0.9148403090961837,
|
| 15215 |
+
"grad_norm": 0.11380811035633087,
|
| 15216 |
+
"learning_rate": 7.271095152603232e-05,
|
| 15217 |
+
"loss": 1.9709993600845337,
|
| 15218 |
+
"step": 4336
|
| 15219 |
+
},
|
| 15220 |
+
{
|
| 15221 |
+
"epoch": 0.9152622834084975,
|
| 15222 |
+
"grad_norm": 0.1055958941578865,
|
| 15223 |
+
"learning_rate": 7.235188509874327e-05,
|
| 15224 |
+
"loss": 2.0279035568237305,
|
| 15225 |
+
"step": 4338
|
| 15226 |
+
},
|
| 15227 |
+
{
|
| 15228 |
+
"epoch": 0.9156842577208113,
|
| 15229 |
+
"grad_norm": 0.10484731197357178,
|
| 15230 |
+
"learning_rate": 7.199281867145422e-05,
|
| 15231 |
+
"loss": 2.00527286529541,
|
| 15232 |
+
"step": 4340
|
| 15233 |
+
},
|
| 15234 |
+
{
|
| 15235 |
+
"epoch": 0.916106232033125,
|
| 15236 |
+
"grad_norm": 0.10349317640066147,
|
| 15237 |
+
"learning_rate": 7.163375224416518e-05,
|
| 15238 |
+
"loss": 1.9561049938201904,
|
| 15239 |
+
"step": 4342
|
| 15240 |
+
},
|
| 15241 |
+
{
|
| 15242 |
+
"epoch": 0.9165282063454387,
|
| 15243 |
+
"grad_norm": 0.10680350661277771,
|
| 15244 |
+
"learning_rate": 7.127468581687613e-05,
|
| 15245 |
+
"loss": 2.0026931762695312,
|
| 15246 |
+
"step": 4344
|
| 15247 |
+
},
|
| 15248 |
+
{
|
| 15249 |
+
"epoch": 0.9169501806577525,
|
| 15250 |
+
"grad_norm": 0.12091751396656036,
|
| 15251 |
+
"learning_rate": 7.091561938958707e-05,
|
| 15252 |
+
"loss": 1.9692943096160889,
|
| 15253 |
+
"step": 4346
|
| 15254 |
+
},
|
| 15255 |
+
{
|
| 15256 |
+
"epoch": 0.9173721549700662,
|
| 15257 |
+
"grad_norm": 0.12316521257162094,
|
| 15258 |
+
"learning_rate": 7.055655296229803e-05,
|
| 15259 |
+
"loss": 1.918934941291809,
|
| 15260 |
+
"step": 4348
|
| 15261 |
+
},
|
| 15262 |
+
{
|
| 15263 |
+
"epoch": 0.9177941292823799,
|
| 15264 |
+
"grad_norm": 0.10428337007761002,
|
| 15265 |
+
"learning_rate": 7.019748653500898e-05,
|
| 15266 |
+
"loss": 2.015747547149658,
|
| 15267 |
+
"step": 4350
|
| 15268 |
+
},
|
| 15269 |
+
{
|
| 15270 |
+
"epoch": 0.9182161035946936,
|
| 15271 |
+
"grad_norm": 0.11164549738168716,
|
| 15272 |
+
"learning_rate": 6.983842010771992e-05,
|
| 15273 |
+
"loss": 2.01839017868042,
|
| 15274 |
+
"step": 4352
|
| 15275 |
+
},
|
| 15276 |
+
{
|
| 15277 |
+
"epoch": 0.9186380779070074,
|
| 15278 |
+
"grad_norm": 0.10518519580364227,
|
| 15279 |
+
"learning_rate": 6.947935368043088e-05,
|
| 15280 |
+
"loss": 1.9499198198318481,
|
| 15281 |
+
"step": 4354
|
| 15282 |
+
},
|
| 15283 |
+
{
|
| 15284 |
+
"epoch": 0.9190600522193212,
|
| 15285 |
+
"grad_norm": 0.10779891163110733,
|
| 15286 |
+
"learning_rate": 6.912028725314183e-05,
|
| 15287 |
+
"loss": 1.9888851642608643,
|
| 15288 |
+
"step": 4356
|
| 15289 |
+
},
|
| 15290 |
+
{
|
| 15291 |
+
"epoch": 0.9194820265316349,
|
| 15292 |
+
"grad_norm": 0.10748085379600525,
|
| 15293 |
+
"learning_rate": 6.876122082585279e-05,
|
| 15294 |
+
"loss": 2.006067991256714,
|
| 15295 |
+
"step": 4358
|
| 15296 |
+
},
|
| 15297 |
+
{
|
| 15298 |
+
"epoch": 0.9199040008439486,
|
| 15299 |
+
"grad_norm": 0.11628947407007217,
|
| 15300 |
+
"learning_rate": 6.840215439856373e-05,
|
| 15301 |
+
"loss": 1.9224172830581665,
|
| 15302 |
+
"step": 4360
|
| 15303 |
+
},
|
| 15304 |
+
{
|
| 15305 |
+
"epoch": 0.9203259751562624,
|
| 15306 |
+
"grad_norm": 0.10497194528579712,
|
| 15307 |
+
"learning_rate": 6.804308797127469e-05,
|
| 15308 |
+
"loss": 1.9339981079101562,
|
| 15309 |
+
"step": 4362
|
| 15310 |
+
},
|
| 15311 |
+
{
|
| 15312 |
+
"epoch": 0.9207479494685761,
|
| 15313 |
+
"grad_norm": 0.1023145467042923,
|
| 15314 |
+
"learning_rate": 6.768402154398564e-05,
|
| 15315 |
+
"loss": 1.9809895753860474,
|
| 15316 |
+
"step": 4364
|
| 15317 |
+
},
|
| 15318 |
+
{
|
| 15319 |
+
"epoch": 0.9211699237808898,
|
| 15320 |
+
"grad_norm": 0.1136220321059227,
|
| 15321 |
+
"learning_rate": 6.73249551166966e-05,
|
| 15322 |
+
"loss": 2.0420050621032715,
|
| 15323 |
+
"step": 4366
|
| 15324 |
+
},
|
| 15325 |
+
{
|
| 15326 |
+
"epoch": 0.9215918980932035,
|
| 15327 |
+
"grad_norm": 0.09812942147254944,
|
| 15328 |
+
"learning_rate": 6.696588868940754e-05,
|
| 15329 |
+
"loss": 1.9726718664169312,
|
| 15330 |
+
"step": 4368
|
| 15331 |
+
},
|
| 15332 |
+
{
|
| 15333 |
+
"epoch": 0.9220138724055174,
|
| 15334 |
+
"grad_norm": 0.11689987778663635,
|
| 15335 |
+
"learning_rate": 6.66068222621185e-05,
|
| 15336 |
+
"loss": 2.007542371749878,
|
| 15337 |
+
"step": 4370
|
| 15338 |
+
},
|
| 15339 |
+
{
|
| 15340 |
+
"epoch": 0.9224358467178311,
|
| 15341 |
+
"grad_norm": 0.1088201105594635,
|
| 15342 |
+
"learning_rate": 6.624775583482945e-05,
|
| 15343 |
+
"loss": 1.9895540475845337,
|
| 15344 |
+
"step": 4372
|
| 15345 |
+
},
|
| 15346 |
+
{
|
| 15347 |
+
"epoch": 0.9228578210301448,
|
| 15348 |
+
"grad_norm": 0.11217056214809418,
|
| 15349 |
+
"learning_rate": 6.588868940754039e-05,
|
| 15350 |
+
"loss": 1.9780479669570923,
|
| 15351 |
+
"step": 4374
|
| 15352 |
+
},
|
| 15353 |
+
{
|
| 15354 |
+
"epoch": 0.9232797953424585,
|
| 15355 |
+
"grad_norm": 0.11308541148900986,
|
| 15356 |
+
"learning_rate": 6.552962298025135e-05,
|
| 15357 |
+
"loss": 1.9641718864440918,
|
| 15358 |
+
"step": 4376
|
| 15359 |
+
},
|
| 15360 |
+
{
|
| 15361 |
+
"epoch": 0.9237017696547722,
|
| 15362 |
+
"grad_norm": 0.10051889717578888,
|
| 15363 |
+
"learning_rate": 6.51705565529623e-05,
|
| 15364 |
+
"loss": 1.9247889518737793,
|
| 15365 |
+
"step": 4378
|
| 15366 |
+
},
|
| 15367 |
+
{
|
| 15368 |
+
"epoch": 0.924123743967086,
|
| 15369 |
+
"grad_norm": 0.11950184404850006,
|
| 15370 |
+
"learning_rate": 6.481149012567326e-05,
|
| 15371 |
+
"loss": 1.9736049175262451,
|
| 15372 |
+
"step": 4380
|
| 15373 |
+
},
|
| 15374 |
+
{
|
| 15375 |
+
"epoch": 0.9245457182793997,
|
| 15376 |
+
"grad_norm": 0.09528274834156036,
|
| 15377 |
+
"learning_rate": 6.44524236983842e-05,
|
| 15378 |
+
"loss": 1.9767588376998901,
|
| 15379 |
+
"step": 4382
|
| 15380 |
+
},
|
| 15381 |
+
{
|
| 15382 |
+
"epoch": 0.9249676925917135,
|
| 15383 |
+
"grad_norm": 0.11856667697429657,
|
| 15384 |
+
"learning_rate": 6.409335727109515e-05,
|
| 15385 |
+
"loss": 1.9190655946731567,
|
| 15386 |
+
"step": 4384
|
| 15387 |
+
},
|
| 15388 |
+
{
|
| 15389 |
+
"epoch": 0.9253896669040272,
|
| 15390 |
+
"grad_norm": 0.09872009605169296,
|
| 15391 |
+
"learning_rate": 6.373429084380611e-05,
|
| 15392 |
+
"loss": 2.026851177215576,
|
| 15393 |
+
"step": 4386
|
| 15394 |
+
},
|
| 15395 |
+
{
|
| 15396 |
+
"epoch": 0.925811641216341,
|
| 15397 |
+
"grad_norm": 0.11413022875785828,
|
| 15398 |
+
"learning_rate": 6.337522441651705e-05,
|
| 15399 |
+
"loss": 1.9873367547988892,
|
| 15400 |
+
"step": 4388
|
| 15401 |
+
},
|
| 15402 |
+
{
|
| 15403 |
+
"epoch": 0.9262336155286547,
|
| 15404 |
+
"grad_norm": 0.1007830798625946,
|
| 15405 |
+
"learning_rate": 6.3016157989228e-05,
|
| 15406 |
+
"loss": 1.9649474620819092,
|
| 15407 |
+
"step": 4390
|
| 15408 |
+
},
|
| 15409 |
+
{
|
| 15410 |
+
"epoch": 0.9266555898409684,
|
| 15411 |
+
"grad_norm": 0.11300705373287201,
|
| 15412 |
+
"learning_rate": 6.265709156193896e-05,
|
| 15413 |
+
"loss": 1.9788988828659058,
|
| 15414 |
+
"step": 4392
|
| 15415 |
+
},
|
| 15416 |
+
{
|
| 15417 |
+
"epoch": 0.9270775641532821,
|
| 15418 |
+
"grad_norm": 0.10901802778244019,
|
| 15419 |
+
"learning_rate": 6.229802513464991e-05,
|
| 15420 |
+
"loss": 1.8743146657943726,
|
| 15421 |
+
"step": 4394
|
| 15422 |
+
},
|
| 15423 |
+
{
|
| 15424 |
+
"epoch": 0.9274995384655959,
|
| 15425 |
+
"grad_norm": 0.10092721879482269,
|
| 15426 |
+
"learning_rate": 6.193895870736086e-05,
|
| 15427 |
+
"loss": 1.9390665292739868,
|
| 15428 |
+
"step": 4396
|
| 15429 |
+
},
|
| 15430 |
+
{
|
| 15431 |
+
"epoch": 0.9279215127779097,
|
| 15432 |
+
"grad_norm": 0.12116295844316483,
|
| 15433 |
+
"learning_rate": 6.157989228007181e-05,
|
| 15434 |
+
"loss": 1.8761729001998901,
|
| 15435 |
+
"step": 4398
|
| 15436 |
+
},
|
| 15437 |
+
{
|
| 15438 |
+
"epoch": 0.9283434870902234,
|
| 15439 |
+
"grad_norm": 0.11722904443740845,
|
| 15440 |
+
"learning_rate": 6.122082585278277e-05,
|
| 15441 |
+
"loss": 1.9988369941711426,
|
| 15442 |
+
"step": 4400
|
| 15443 |
+
},
|
| 15444 |
+
{
|
| 15445 |
+
"epoch": 0.9287654614025371,
|
| 15446 |
+
"grad_norm": 0.11201320588588715,
|
| 15447 |
+
"learning_rate": 6.0861759425493715e-05,
|
| 15448 |
+
"loss": 1.963629961013794,
|
| 15449 |
+
"step": 4402
|
| 15450 |
+
},
|
| 15451 |
+
{
|
| 15452 |
+
"epoch": 0.9291874357148509,
|
| 15453 |
+
"grad_norm": 0.1068640798330307,
|
| 15454 |
+
"learning_rate": 6.050269299820467e-05,
|
| 15455 |
+
"loss": 1.992313027381897,
|
| 15456 |
+
"step": 4404
|
| 15457 |
+
},
|
| 15458 |
+
{
|
| 15459 |
+
"epoch": 0.9296094100271646,
|
| 15460 |
+
"grad_norm": 0.09950323402881622,
|
| 15461 |
+
"learning_rate": 6.0143626570915625e-05,
|
| 15462 |
+
"loss": 1.986338496208191,
|
| 15463 |
+
"step": 4406
|
| 15464 |
+
},
|
| 15465 |
+
{
|
| 15466 |
+
"epoch": 0.9300313843394783,
|
| 15467 |
+
"grad_norm": 0.10620663315057755,
|
| 15468 |
+
"learning_rate": 5.978456014362658e-05,
|
| 15469 |
+
"loss": 1.8992366790771484,
|
| 15470 |
+
"step": 4408
|
| 15471 |
+
},
|
| 15472 |
+
{
|
| 15473 |
+
"epoch": 0.930453358651792,
|
| 15474 |
+
"grad_norm": 0.10992123186588287,
|
| 15475 |
+
"learning_rate": 5.942549371633752e-05,
|
| 15476 |
+
"loss": 1.971193552017212,
|
| 15477 |
+
"step": 4410
|
| 15478 |
+
},
|
| 15479 |
+
{
|
| 15480 |
+
"epoch": 0.9308753329641059,
|
| 15481 |
+
"grad_norm": 0.11310093104839325,
|
| 15482 |
+
"learning_rate": 5.906642728904848e-05,
|
| 15483 |
+
"loss": 1.9978446960449219,
|
| 15484 |
+
"step": 4412
|
| 15485 |
+
},
|
| 15486 |
+
{
|
| 15487 |
+
"epoch": 0.9312973072764196,
|
| 15488 |
+
"grad_norm": 0.10823677480220795,
|
| 15489 |
+
"learning_rate": 5.870736086175943e-05,
|
| 15490 |
+
"loss": 1.9941303730010986,
|
| 15491 |
+
"step": 4414
|
| 15492 |
+
},
|
| 15493 |
+
{
|
| 15494 |
+
"epoch": 0.9317192815887333,
|
| 15495 |
+
"grad_norm": 0.10390577465295792,
|
| 15496 |
+
"learning_rate": 5.834829443447039e-05,
|
| 15497 |
+
"loss": 1.983245611190796,
|
| 15498 |
+
"step": 4416
|
| 15499 |
+
},
|
| 15500 |
+
{
|
| 15501 |
+
"epoch": 0.932141255901047,
|
| 15502 |
+
"grad_norm": 0.1217908039689064,
|
| 15503 |
+
"learning_rate": 5.798922800718133e-05,
|
| 15504 |
+
"loss": 2.067887544631958,
|
| 15505 |
+
"step": 4418
|
| 15506 |
+
},
|
| 15507 |
+
{
|
| 15508 |
+
"epoch": 0.9325632302133607,
|
| 15509 |
+
"grad_norm": 0.1062224730849266,
|
| 15510 |
+
"learning_rate": 5.7630161579892284e-05,
|
| 15511 |
+
"loss": 1.9372761249542236,
|
| 15512 |
+
"step": 4420
|
| 15513 |
+
},
|
| 15514 |
+
{
|
| 15515 |
+
"epoch": 0.9329852045256745,
|
| 15516 |
+
"grad_norm": 0.11350486427545547,
|
| 15517 |
+
"learning_rate": 5.727109515260324e-05,
|
| 15518 |
+
"loss": 1.9175602197647095,
|
| 15519 |
+
"step": 4422
|
| 15520 |
+
},
|
| 15521 |
+
{
|
| 15522 |
+
"epoch": 0.9334071788379882,
|
| 15523 |
+
"grad_norm": 0.11135926097631454,
|
| 15524 |
+
"learning_rate": 5.691202872531418e-05,
|
| 15525 |
+
"loss": 2.0014498233795166,
|
| 15526 |
+
"step": 4424
|
| 15527 |
+
},
|
| 15528 |
+
{
|
| 15529 |
+
"epoch": 0.933829153150302,
|
| 15530 |
+
"grad_norm": 0.10471297800540924,
|
| 15531 |
+
"learning_rate": 5.6552962298025136e-05,
|
| 15532 |
+
"loss": 1.9817594289779663,
|
| 15533 |
+
"step": 4426
|
| 15534 |
+
},
|
| 15535 |
+
{
|
| 15536 |
+
"epoch": 0.9342511274626157,
|
| 15537 |
+
"grad_norm": 0.10763347893953323,
|
| 15538 |
+
"learning_rate": 5.619389587073609e-05,
|
| 15539 |
+
"loss": 1.969205379486084,
|
| 15540 |
+
"step": 4428
|
| 15541 |
+
},
|
| 15542 |
+
{
|
| 15543 |
+
"epoch": 0.9346731017749295,
|
| 15544 |
+
"grad_norm": 0.10730740427970886,
|
| 15545 |
+
"learning_rate": 5.5834829443447046e-05,
|
| 15546 |
+
"loss": 1.9536798000335693,
|
| 15547 |
+
"step": 4430
|
| 15548 |
+
},
|
| 15549 |
+
{
|
| 15550 |
+
"epoch": 0.9350950760872432,
|
| 15551 |
+
"grad_norm": 0.11071805655956268,
|
| 15552 |
+
"learning_rate": 5.547576301615799e-05,
|
| 15553 |
+
"loss": 1.995632290840149,
|
| 15554 |
+
"step": 4432
|
| 15555 |
+
},
|
| 15556 |
+
{
|
| 15557 |
+
"epoch": 0.9355170503995569,
|
| 15558 |
+
"grad_norm": 0.1172584667801857,
|
| 15559 |
+
"learning_rate": 5.511669658886894e-05,
|
| 15560 |
+
"loss": 1.9432746171951294,
|
| 15561 |
+
"step": 4434
|
| 15562 |
+
},
|
| 15563 |
+
{
|
| 15564 |
+
"epoch": 0.9359390247118706,
|
| 15565 |
+
"grad_norm": 0.10111786425113678,
|
| 15566 |
+
"learning_rate": 5.47576301615799e-05,
|
| 15567 |
+
"loss": 1.9635210037231445,
|
| 15568 |
+
"step": 4436
|
| 15569 |
+
},
|
| 15570 |
+
{
|
| 15571 |
+
"epoch": 0.9363609990241843,
|
| 15572 |
+
"grad_norm": 0.1115003377199173,
|
| 15573 |
+
"learning_rate": 5.439856373429084e-05,
|
| 15574 |
+
"loss": 1.9342033863067627,
|
| 15575 |
+
"step": 4438
|
| 15576 |
+
},
|
| 15577 |
+
{
|
| 15578 |
+
"epoch": 0.9367829733364982,
|
| 15579 |
+
"grad_norm": 0.11682593077421188,
|
| 15580 |
+
"learning_rate": 5.4039497307001794e-05,
|
| 15581 |
+
"loss": 1.9311261177062988,
|
| 15582 |
+
"step": 4440
|
| 15583 |
+
},
|
| 15584 |
+
{
|
| 15585 |
+
"epoch": 0.9372049476488119,
|
| 15586 |
+
"grad_norm": 0.10311296582221985,
|
| 15587 |
+
"learning_rate": 5.368043087971275e-05,
|
| 15588 |
+
"loss": 1.9469839334487915,
|
| 15589 |
+
"step": 4442
|
| 15590 |
+
},
|
| 15591 |
+
{
|
| 15592 |
+
"epoch": 0.9376269219611256,
|
| 15593 |
+
"grad_norm": 0.105555459856987,
|
| 15594 |
+
"learning_rate": 5.3321364452423705e-05,
|
| 15595 |
+
"loss": 1.9866645336151123,
|
| 15596 |
+
"step": 4444
|
| 15597 |
+
},
|
| 15598 |
+
{
|
| 15599 |
+
"epoch": 0.9380488962734393,
|
| 15600 |
+
"grad_norm": 0.10601339489221573,
|
| 15601 |
+
"learning_rate": 5.2962298025134646e-05,
|
| 15602 |
+
"loss": 2.021909475326538,
|
| 15603 |
+
"step": 4446
|
| 15604 |
+
},
|
| 15605 |
+
{
|
| 15606 |
+
"epoch": 0.9384708705857531,
|
| 15607 |
+
"grad_norm": 0.10167314112186432,
|
| 15608 |
+
"learning_rate": 5.26032315978456e-05,
|
| 15609 |
+
"loss": 1.940483570098877,
|
| 15610 |
+
"step": 4448
|
| 15611 |
+
},
|
| 15612 |
+
{
|
| 15613 |
+
"epoch": 0.9388928448980668,
|
| 15614 |
+
"grad_norm": 0.11554458737373352,
|
| 15615 |
+
"learning_rate": 5.2244165170556557e-05,
|
| 15616 |
+
"loss": 2.0332086086273193,
|
| 15617 |
+
"step": 4450
|
| 15618 |
+
},
|
| 15619 |
+
{
|
| 15620 |
+
"epoch": 0.9393148192103805,
|
| 15621 |
+
"grad_norm": 0.10473091155290604,
|
| 15622 |
+
"learning_rate": 5.1885098743267505e-05,
|
| 15623 |
+
"loss": 1.9359129667282104,
|
| 15624 |
+
"step": 4452
|
| 15625 |
+
},
|
| 15626 |
+
{
|
| 15627 |
+
"epoch": 0.9397367935226943,
|
| 15628 |
+
"grad_norm": 0.10217129439115524,
|
| 15629 |
+
"learning_rate": 5.152603231597845e-05,
|
| 15630 |
+
"loss": 2.0070266723632812,
|
| 15631 |
+
"step": 4454
|
| 15632 |
+
},
|
| 15633 |
+
{
|
| 15634 |
+
"epoch": 0.9401587678350081,
|
| 15635 |
+
"grad_norm": 0.1090213879942894,
|
| 15636 |
+
"learning_rate": 5.116696588868941e-05,
|
| 15637 |
+
"loss": 1.93622624874115,
|
| 15638 |
+
"step": 4456
|
| 15639 |
+
},
|
| 15640 |
+
{
|
| 15641 |
+
"epoch": 0.9405807421473218,
|
| 15642 |
+
"grad_norm": 0.10054320096969604,
|
| 15643 |
+
"learning_rate": 5.0807899461400364e-05,
|
| 15644 |
+
"loss": 1.9456861019134521,
|
| 15645 |
+
"step": 4458
|
| 15646 |
+
},
|
| 15647 |
+
{
|
| 15648 |
+
"epoch": 0.9410027164596355,
|
| 15649 |
+
"grad_norm": 0.1286977082490921,
|
| 15650 |
+
"learning_rate": 5.044883303411131e-05,
|
| 15651 |
+
"loss": 1.9709253311157227,
|
| 15652 |
+
"step": 4460
|
| 15653 |
+
},
|
| 15654 |
+
{
|
| 15655 |
+
"epoch": 0.9414246907719492,
|
| 15656 |
+
"grad_norm": 0.11071281880140305,
|
| 15657 |
+
"learning_rate": 5.008976660682227e-05,
|
| 15658 |
+
"loss": 1.9578603506088257,
|
| 15659 |
+
"step": 4462
|
| 15660 |
+
},
|
| 15661 |
+
{
|
| 15662 |
+
"epoch": 0.941846665084263,
|
| 15663 |
+
"grad_norm": 0.10554347932338715,
|
| 15664 |
+
"learning_rate": 4.9730700179533215e-05,
|
| 15665 |
+
"loss": 1.9619337320327759,
|
| 15666 |
+
"step": 4464
|
| 15667 |
+
},
|
| 15668 |
+
{
|
| 15669 |
+
"epoch": 0.9422686393965767,
|
| 15670 |
+
"grad_norm": 0.1077689677476883,
|
| 15671 |
+
"learning_rate": 4.937163375224417e-05,
|
| 15672 |
+
"loss": 1.9693071842193604,
|
| 15673 |
+
"step": 4466
|
| 15674 |
+
},
|
| 15675 |
+
{
|
| 15676 |
+
"epoch": 0.9426906137088905,
|
| 15677 |
+
"grad_norm": 0.10029803216457367,
|
| 15678 |
+
"learning_rate": 4.901256732495512e-05,
|
| 15679 |
+
"loss": 1.9795218706130981,
|
| 15680 |
+
"step": 4468
|
| 15681 |
+
},
|
| 15682 |
+
{
|
| 15683 |
+
"epoch": 0.9431125880212042,
|
| 15684 |
+
"grad_norm": 0.09988780319690704,
|
| 15685 |
+
"learning_rate": 4.8653500897666074e-05,
|
| 15686 |
+
"loss": 1.8700910806655884,
|
| 15687 |
+
"step": 4470
|
| 15688 |
+
},
|
| 15689 |
+
{
|
| 15690 |
+
"epoch": 0.943534562333518,
|
| 15691 |
+
"grad_norm": 0.11808252334594727,
|
| 15692 |
+
"learning_rate": 4.829443447037702e-05,
|
| 15693 |
+
"loss": 1.9545581340789795,
|
| 15694 |
+
"step": 4472
|
| 15695 |
+
},
|
| 15696 |
+
{
|
| 15697 |
+
"epoch": 0.9439565366458317,
|
| 15698 |
+
"grad_norm": 0.10970522463321686,
|
| 15699 |
+
"learning_rate": 4.793536804308798e-05,
|
| 15700 |
+
"loss": 1.9331252574920654,
|
| 15701 |
+
"step": 4474
|
| 15702 |
+
},
|
| 15703 |
+
{
|
| 15704 |
+
"epoch": 0.9443785109581454,
|
| 15705 |
+
"grad_norm": 0.11361062526702881,
|
| 15706 |
+
"learning_rate": 4.7576301615798926e-05,
|
| 15707 |
+
"loss": 1.9802976846694946,
|
| 15708 |
+
"step": 4476
|
| 15709 |
+
},
|
| 15710 |
+
{
|
| 15711 |
+
"epoch": 0.9448004852704591,
|
| 15712 |
+
"grad_norm": 0.10900110751390457,
|
| 15713 |
+
"learning_rate": 4.721723518850988e-05,
|
| 15714 |
+
"loss": 1.9315359592437744,
|
| 15715 |
+
"step": 4478
|
| 15716 |
+
},
|
| 15717 |
+
{
|
| 15718 |
+
"epoch": 0.9452224595827728,
|
| 15719 |
+
"grad_norm": 0.0988907590508461,
|
| 15720 |
+
"learning_rate": 4.685816876122083e-05,
|
| 15721 |
+
"loss": 1.9867444038391113,
|
| 15722 |
+
"step": 4480
|
| 15723 |
+
},
|
| 15724 |
+
{
|
| 15725 |
+
"epoch": 0.9456444338950867,
|
| 15726 |
+
"grad_norm": 0.10760052502155304,
|
| 15727 |
+
"learning_rate": 4.6499102333931784e-05,
|
| 15728 |
+
"loss": 1.968553900718689,
|
| 15729 |
+
"step": 4482
|
| 15730 |
+
},
|
| 15731 |
+
{
|
| 15732 |
+
"epoch": 0.9460664082074004,
|
| 15733 |
+
"grad_norm": 0.11219218373298645,
|
| 15734 |
+
"learning_rate": 4.614003590664273e-05,
|
| 15735 |
+
"loss": 1.9957237243652344,
|
| 15736 |
+
"step": 4484
|
| 15737 |
+
},
|
| 15738 |
+
{
|
| 15739 |
+
"epoch": 0.9464883825197141,
|
| 15740 |
+
"grad_norm": 0.1125212013721466,
|
| 15741 |
+
"learning_rate": 4.578096947935368e-05,
|
| 15742 |
+
"loss": 1.9893512725830078,
|
| 15743 |
+
"step": 4486
|
| 15744 |
+
},
|
| 15745 |
+
{
|
| 15746 |
+
"epoch": 0.9469103568320278,
|
| 15747 |
+
"grad_norm": 0.10519126057624817,
|
| 15748 |
+
"learning_rate": 4.5421903052064636e-05,
|
| 15749 |
+
"loss": 1.9717342853546143,
|
| 15750 |
+
"step": 4488
|
| 15751 |
+
},
|
| 15752 |
+
{
|
| 15753 |
+
"epoch": 0.9473323311443416,
|
| 15754 |
+
"grad_norm": 0.10098539292812347,
|
| 15755 |
+
"learning_rate": 4.5062836624775585e-05,
|
| 15756 |
+
"loss": 1.9890072345733643,
|
| 15757 |
+
"step": 4490
|
| 15758 |
+
},
|
| 15759 |
+
{
|
| 15760 |
+
"epoch": 0.9477543054566553,
|
| 15761 |
+
"grad_norm": 0.10550697147846222,
|
| 15762 |
+
"learning_rate": 4.470377019748654e-05,
|
| 15763 |
+
"loss": 2.011085033416748,
|
| 15764 |
+
"step": 4492
|
| 15765 |
+
},
|
| 15766 |
+
{
|
| 15767 |
+
"epoch": 0.948176279768969,
|
| 15768 |
+
"grad_norm": 0.11036745458841324,
|
| 15769 |
+
"learning_rate": 4.434470377019749e-05,
|
| 15770 |
+
"loss": 1.934899926185608,
|
| 15771 |
+
"step": 4494
|
| 15772 |
+
},
|
| 15773 |
+
{
|
| 15774 |
+
"epoch": 0.9485982540812828,
|
| 15775 |
+
"grad_norm": 0.09455365687608719,
|
| 15776 |
+
"learning_rate": 4.398563734290844e-05,
|
| 15777 |
+
"loss": 2.016329050064087,
|
| 15778 |
+
"step": 4496
|
| 15779 |
+
},
|
| 15780 |
+
{
|
| 15781 |
+
"epoch": 0.9490202283935966,
|
| 15782 |
+
"grad_norm": 0.15500092506408691,
|
| 15783 |
+
"learning_rate": 4.362657091561939e-05,
|
| 15784 |
+
"loss": 1.994697093963623,
|
| 15785 |
+
"step": 4498
|
| 15786 |
+
},
|
| 15787 |
+
{
|
| 15788 |
+
"epoch": 0.9494422027059103,
|
| 15789 |
+
"grad_norm": 0.106009341776371,
|
| 15790 |
+
"learning_rate": 4.326750448833034e-05,
|
| 15791 |
+
"loss": 1.9954835176467896,
|
| 15792 |
+
"step": 4500
|
| 15793 |
+
},
|
| 15794 |
+
{
|
| 15795 |
+
"epoch": 0.949864177018224,
|
| 15796 |
+
"grad_norm": 0.10341881960630417,
|
| 15797 |
+
"learning_rate": 4.2908438061041295e-05,
|
| 15798 |
+
"loss": 1.8403732776641846,
|
| 15799 |
+
"step": 4502
|
| 15800 |
+
},
|
| 15801 |
+
{
|
| 15802 |
+
"epoch": 0.9502861513305377,
|
| 15803 |
+
"grad_norm": 0.10378289222717285,
|
| 15804 |
+
"learning_rate": 4.2549371633752244e-05,
|
| 15805 |
+
"loss": 2.003725528717041,
|
| 15806 |
+
"step": 4504
|
| 15807 |
+
},
|
| 15808 |
+
{
|
| 15809 |
+
"epoch": 0.9507081256428515,
|
| 15810 |
+
"grad_norm": 0.11462432146072388,
|
| 15811 |
+
"learning_rate": 4.21903052064632e-05,
|
| 15812 |
+
"loss": 1.9470783472061157,
|
| 15813 |
+
"step": 4506
|
| 15814 |
+
},
|
| 15815 |
+
{
|
| 15816 |
+
"epoch": 0.9511300999551652,
|
| 15817 |
+
"grad_norm": 0.09759571403265,
|
| 15818 |
+
"learning_rate": 4.183123877917415e-05,
|
| 15819 |
+
"loss": 1.948257565498352,
|
| 15820 |
+
"step": 4508
|
| 15821 |
+
},
|
| 15822 |
+
{
|
| 15823 |
+
"epoch": 0.951552074267479,
|
| 15824 |
+
"grad_norm": 0.1090717762708664,
|
| 15825 |
+
"learning_rate": 4.14721723518851e-05,
|
| 15826 |
+
"loss": 1.9400941133499146,
|
| 15827 |
+
"step": 4510
|
| 15828 |
+
},
|
| 15829 |
+
{
|
| 15830 |
+
"epoch": 0.9519740485797927,
|
| 15831 |
+
"grad_norm": 0.10372298210859299,
|
| 15832 |
+
"learning_rate": 4.111310592459605e-05,
|
| 15833 |
+
"loss": 1.8825671672821045,
|
| 15834 |
+
"step": 4512
|
| 15835 |
+
},
|
| 15836 |
+
{
|
| 15837 |
+
"epoch": 0.9523960228921065,
|
| 15838 |
+
"grad_norm": 0.10764601826667786,
|
| 15839 |
+
"learning_rate": 4.0754039497307006e-05,
|
| 15840 |
+
"loss": 1.8693889379501343,
|
| 15841 |
+
"step": 4514
|
| 15842 |
+
},
|
| 15843 |
+
{
|
| 15844 |
+
"epoch": 0.9528179972044202,
|
| 15845 |
+
"grad_norm": 0.10617853701114655,
|
| 15846 |
+
"learning_rate": 4.0394973070017954e-05,
|
| 15847 |
+
"loss": 1.9854592084884644,
|
| 15848 |
+
"step": 4516
|
| 15849 |
+
},
|
| 15850 |
+
{
|
| 15851 |
+
"epoch": 0.9532399715167339,
|
| 15852 |
+
"grad_norm": 0.10256534069776535,
|
| 15853 |
+
"learning_rate": 4.00359066427289e-05,
|
| 15854 |
+
"loss": 1.898912787437439,
|
| 15855 |
+
"step": 4518
|
| 15856 |
+
},
|
| 15857 |
+
{
|
| 15858 |
+
"epoch": 0.9536619458290476,
|
| 15859 |
+
"grad_norm": 0.10808218270540237,
|
| 15860 |
+
"learning_rate": 3.967684021543986e-05,
|
| 15861 |
+
"loss": 1.93253493309021,
|
| 15862 |
+
"step": 4520
|
| 15863 |
+
},
|
| 15864 |
+
{
|
| 15865 |
+
"epoch": 0.9540839201413613,
|
| 15866 |
+
"grad_norm": 0.11648982018232346,
|
| 15867 |
+
"learning_rate": 3.9317773788150806e-05,
|
| 15868 |
+
"loss": 1.9380801916122437,
|
| 15869 |
+
"step": 4522
|
| 15870 |
+
},
|
| 15871 |
+
{
|
| 15872 |
+
"epoch": 0.9545058944536752,
|
| 15873 |
+
"grad_norm": 0.09977971762418747,
|
| 15874 |
+
"learning_rate": 3.895870736086176e-05,
|
| 15875 |
+
"loss": 1.9927090406417847,
|
| 15876 |
+
"step": 4524
|
| 15877 |
+
},
|
| 15878 |
+
{
|
| 15879 |
+
"epoch": 0.9549278687659889,
|
| 15880 |
+
"grad_norm": 0.10238093137741089,
|
| 15881 |
+
"learning_rate": 3.859964093357271e-05,
|
| 15882 |
+
"loss": 1.9616984128952026,
|
| 15883 |
+
"step": 4526
|
| 15884 |
+
},
|
| 15885 |
+
{
|
| 15886 |
+
"epoch": 0.9553498430783026,
|
| 15887 |
+
"grad_norm": 0.10674754530191422,
|
| 15888 |
+
"learning_rate": 3.8240574506283664e-05,
|
| 15889 |
+
"loss": 1.979896903038025,
|
| 15890 |
+
"step": 4528
|
| 15891 |
+
},
|
| 15892 |
+
{
|
| 15893 |
+
"epoch": 0.9557718173906163,
|
| 15894 |
+
"grad_norm": 0.10306009650230408,
|
| 15895 |
+
"learning_rate": 3.788150807899461e-05,
|
| 15896 |
+
"loss": 1.8982036113739014,
|
| 15897 |
+
"step": 4530
|
| 15898 |
+
},
|
| 15899 |
+
{
|
| 15900 |
+
"epoch": 0.9561937917029301,
|
| 15901 |
+
"grad_norm": 0.11265920847654343,
|
| 15902 |
+
"learning_rate": 3.752244165170557e-05,
|
| 15903 |
+
"loss": 1.9744625091552734,
|
| 15904 |
+
"step": 4532
|
| 15905 |
+
},
|
| 15906 |
+
{
|
| 15907 |
+
"epoch": 0.9566157660152438,
|
| 15908 |
+
"grad_norm": 0.11647281795740128,
|
| 15909 |
+
"learning_rate": 3.7163375224416516e-05,
|
| 15910 |
+
"loss": 1.9784642457962036,
|
| 15911 |
+
"step": 4534
|
| 15912 |
+
},
|
| 15913 |
+
{
|
| 15914 |
+
"epoch": 0.9570377403275575,
|
| 15915 |
+
"grad_norm": 0.11191514134407043,
|
| 15916 |
+
"learning_rate": 3.6804308797127465e-05,
|
| 15917 |
+
"loss": 1.9690855741500854,
|
| 15918 |
+
"step": 4536
|
| 15919 |
+
},
|
| 15920 |
+
{
|
| 15921 |
+
"epoch": 0.9574597146398713,
|
| 15922 |
+
"grad_norm": 0.1162935197353363,
|
| 15923 |
+
"learning_rate": 3.644524236983842e-05,
|
| 15924 |
+
"loss": 1.9823527336120605,
|
| 15925 |
+
"step": 4538
|
| 15926 |
+
},
|
| 15927 |
+
{
|
| 15928 |
+
"epoch": 0.9578816889521851,
|
| 15929 |
+
"grad_norm": 0.10934937745332718,
|
| 15930 |
+
"learning_rate": 3.6086175942549375e-05,
|
| 15931 |
+
"loss": 1.9947012662887573,
|
| 15932 |
+
"step": 4540
|
| 15933 |
+
},
|
| 15934 |
+
{
|
| 15935 |
+
"epoch": 0.9583036632644988,
|
| 15936 |
+
"grad_norm": 0.10031798481941223,
|
| 15937 |
+
"learning_rate": 3.572710951526032e-05,
|
| 15938 |
+
"loss": 1.9506831169128418,
|
| 15939 |
+
"step": 4542
|
| 15940 |
+
},
|
| 15941 |
+
{
|
| 15942 |
+
"epoch": 0.9587256375768125,
|
| 15943 |
+
"grad_norm": 0.13115912675857544,
|
| 15944 |
+
"learning_rate": 3.536804308797128e-05,
|
| 15945 |
+
"loss": 1.993109107017517,
|
| 15946 |
+
"step": 4544
|
| 15947 |
+
},
|
| 15948 |
+
{
|
| 15949 |
+
"epoch": 0.9591476118891262,
|
| 15950 |
+
"grad_norm": 0.11059731245040894,
|
| 15951 |
+
"learning_rate": 3.500897666068223e-05,
|
| 15952 |
+
"loss": 1.9159808158874512,
|
| 15953 |
+
"step": 4546
|
| 15954 |
+
},
|
| 15955 |
+
{
|
| 15956 |
+
"epoch": 0.95956958620144,
|
| 15957 |
+
"grad_norm": 0.10525340586900711,
|
| 15958 |
+
"learning_rate": 3.464991023339318e-05,
|
| 15959 |
+
"loss": 1.9480326175689697,
|
| 15960 |
+
"step": 4548
|
| 15961 |
+
},
|
| 15962 |
+
{
|
| 15963 |
+
"epoch": 0.9599915605137537,
|
| 15964 |
+
"grad_norm": 0.11978833377361298,
|
| 15965 |
+
"learning_rate": 3.429084380610413e-05,
|
| 15966 |
+
"loss": 1.9725160598754883,
|
| 15967 |
+
"step": 4550
|
| 15968 |
+
},
|
| 15969 |
+
{
|
| 15970 |
+
"epoch": 0.9604135348260675,
|
| 15971 |
+
"grad_norm": 0.10969995707273483,
|
| 15972 |
+
"learning_rate": 3.3931777378815085e-05,
|
| 15973 |
+
"loss": 2.004603147506714,
|
| 15974 |
+
"step": 4552
|
| 15975 |
+
},
|
| 15976 |
+
{
|
| 15977 |
+
"epoch": 0.9608355091383812,
|
| 15978 |
+
"grad_norm": 0.10642252117395401,
|
| 15979 |
+
"learning_rate": 3.3572710951526034e-05,
|
| 15980 |
+
"loss": 2.0019936561584473,
|
| 15981 |
+
"step": 4554
|
| 15982 |
+
},
|
| 15983 |
+
{
|
| 15984 |
+
"epoch": 0.961257483450695,
|
| 15985 |
+
"grad_norm": 0.11324192583560944,
|
| 15986 |
+
"learning_rate": 3.321364452423699e-05,
|
| 15987 |
+
"loss": 1.9790276288986206,
|
| 15988 |
+
"step": 4556
|
| 15989 |
+
},
|
| 15990 |
+
{
|
| 15991 |
+
"epoch": 0.9616794577630087,
|
| 15992 |
+
"grad_norm": 0.10698672384023666,
|
| 15993 |
+
"learning_rate": 3.285457809694794e-05,
|
| 15994 |
+
"loss": 2.0339720249176025,
|
| 15995 |
+
"step": 4558
|
| 15996 |
+
},
|
| 15997 |
+
{
|
| 15998 |
+
"epoch": 0.9621014320753224,
|
| 15999 |
+
"grad_norm": 0.12763382494449615,
|
| 16000 |
+
"learning_rate": 3.249551166965889e-05,
|
| 16001 |
+
"loss": 1.988168716430664,
|
| 16002 |
+
"step": 4560
|
| 16003 |
+
},
|
| 16004 |
+
{
|
| 16005 |
+
"epoch": 0.9625234063876361,
|
| 16006 |
+
"grad_norm": 0.11609788239002228,
|
| 16007 |
+
"learning_rate": 3.213644524236984e-05,
|
| 16008 |
+
"loss": 2.009946346282959,
|
| 16009 |
+
"step": 4562
|
| 16010 |
+
},
|
| 16011 |
+
{
|
| 16012 |
+
"epoch": 0.9629453806999498,
|
| 16013 |
+
"grad_norm": 0.10954302549362183,
|
| 16014 |
+
"learning_rate": 3.1777378815080796e-05,
|
| 16015 |
+
"loss": 1.935221791267395,
|
| 16016 |
+
"step": 4564
|
| 16017 |
+
},
|
| 16018 |
+
{
|
| 16019 |
+
"epoch": 0.9633673550122637,
|
| 16020 |
+
"grad_norm": 0.09643895924091339,
|
| 16021 |
+
"learning_rate": 3.1418312387791744e-05,
|
| 16022 |
+
"loss": 2.0139708518981934,
|
| 16023 |
+
"step": 4566
|
| 16024 |
+
},
|
| 16025 |
+
{
|
| 16026 |
+
"epoch": 0.9637893293245774,
|
| 16027 |
+
"grad_norm": 0.10529980808496475,
|
| 16028 |
+
"learning_rate": 3.105924596050269e-05,
|
| 16029 |
+
"loss": 1.9843734502792358,
|
| 16030 |
+
"step": 4568
|
| 16031 |
+
},
|
| 16032 |
+
{
|
| 16033 |
+
"epoch": 0.9642113036368911,
|
| 16034 |
+
"grad_norm": 0.10969899594783783,
|
| 16035 |
+
"learning_rate": 3.070017953321365e-05,
|
| 16036 |
+
"loss": 2.025578737258911,
|
| 16037 |
+
"step": 4570
|
| 16038 |
+
},
|
| 16039 |
+
{
|
| 16040 |
+
"epoch": 0.9646332779492048,
|
| 16041 |
+
"grad_norm": 0.10554074496030807,
|
| 16042 |
+
"learning_rate": 3.0341113105924596e-05,
|
| 16043 |
+
"loss": 1.946641445159912,
|
| 16044 |
+
"step": 4572
|
| 16045 |
+
},
|
| 16046 |
+
{
|
| 16047 |
+
"epoch": 0.9650552522615186,
|
| 16048 |
+
"grad_norm": 0.11176867038011551,
|
| 16049 |
+
"learning_rate": 2.998204667863555e-05,
|
| 16050 |
+
"loss": 1.9374874830245972,
|
| 16051 |
+
"step": 4574
|
| 16052 |
+
},
|
| 16053 |
+
{
|
| 16054 |
+
"epoch": 0.9654772265738323,
|
| 16055 |
+
"grad_norm": 0.11251261830329895,
|
| 16056 |
+
"learning_rate": 2.96229802513465e-05,
|
| 16057 |
+
"loss": 1.8668239116668701,
|
| 16058 |
+
"step": 4576
|
| 16059 |
+
},
|
| 16060 |
+
{
|
| 16061 |
+
"epoch": 0.965899200886146,
|
| 16062 |
+
"grad_norm": 0.1133284792304039,
|
| 16063 |
+
"learning_rate": 2.9263913824057455e-05,
|
| 16064 |
+
"loss": 1.98781156539917,
|
| 16065 |
+
"step": 4578
|
| 16066 |
+
},
|
| 16067 |
+
{
|
| 16068 |
+
"epoch": 0.9663211751984598,
|
| 16069 |
+
"grad_norm": 0.10248855501413345,
|
| 16070 |
+
"learning_rate": 2.8904847396768403e-05,
|
| 16071 |
+
"loss": 2.0073838233947754,
|
| 16072 |
+
"step": 4580
|
| 16073 |
+
},
|
| 16074 |
+
{
|
| 16075 |
+
"epoch": 0.9667431495107736,
|
| 16076 |
+
"grad_norm": 0.12220220267772675,
|
| 16077 |
+
"learning_rate": 2.8545780969479358e-05,
|
| 16078 |
+
"loss": 2.0011730194091797,
|
| 16079 |
+
"step": 4582
|
| 16080 |
+
},
|
| 16081 |
+
{
|
| 16082 |
+
"epoch": 0.9671651238230873,
|
| 16083 |
+
"grad_norm": 0.10336542874574661,
|
| 16084 |
+
"learning_rate": 2.8186714542190307e-05,
|
| 16085 |
+
"loss": 1.9912590980529785,
|
| 16086 |
+
"step": 4584
|
| 16087 |
+
},
|
| 16088 |
+
{
|
| 16089 |
+
"epoch": 0.967587098135401,
|
| 16090 |
+
"grad_norm": 0.10533387213945389,
|
| 16091 |
+
"learning_rate": 2.7827648114901255e-05,
|
| 16092 |
+
"loss": 1.966177225112915,
|
| 16093 |
+
"step": 4586
|
| 16094 |
+
},
|
| 16095 |
+
{
|
| 16096 |
+
"epoch": 0.9680090724477147,
|
| 16097 |
+
"grad_norm": 0.10882163792848587,
|
| 16098 |
+
"learning_rate": 2.746858168761221e-05,
|
| 16099 |
+
"loss": 1.9780558347702026,
|
| 16100 |
+
"step": 4588
|
| 16101 |
+
},
|
| 16102 |
+
{
|
| 16103 |
+
"epoch": 0.9684310467600284,
|
| 16104 |
+
"grad_norm": 0.10504578799009323,
|
| 16105 |
+
"learning_rate": 2.710951526032316e-05,
|
| 16106 |
+
"loss": 1.9288051128387451,
|
| 16107 |
+
"step": 4590
|
| 16108 |
+
},
|
| 16109 |
+
{
|
| 16110 |
+
"epoch": 0.9688530210723422,
|
| 16111 |
+
"grad_norm": 0.10803225636482239,
|
| 16112 |
+
"learning_rate": 2.6750448833034114e-05,
|
| 16113 |
+
"loss": 1.9908766746520996,
|
| 16114 |
+
"step": 4592
|
| 16115 |
+
},
|
| 16116 |
+
{
|
| 16117 |
+
"epoch": 0.969274995384656,
|
| 16118 |
+
"grad_norm": 0.11677280813455582,
|
| 16119 |
+
"learning_rate": 2.6391382405745062e-05,
|
| 16120 |
+
"loss": 2.025902032852173,
|
| 16121 |
+
"step": 4594
|
| 16122 |
+
},
|
| 16123 |
+
{
|
| 16124 |
+
"epoch": 0.9696969696969697,
|
| 16125 |
+
"grad_norm": 0.110410176217556,
|
| 16126 |
+
"learning_rate": 2.6032315978456017e-05,
|
| 16127 |
+
"loss": 2.0003957748413086,
|
| 16128 |
+
"step": 4596
|
| 16129 |
+
},
|
| 16130 |
+
{
|
| 16131 |
+
"epoch": 0.9701189440092834,
|
| 16132 |
+
"grad_norm": 0.10641536116600037,
|
| 16133 |
+
"learning_rate": 2.5673249551166965e-05,
|
| 16134 |
+
"loss": 1.9546582698822021,
|
| 16135 |
+
"step": 4598
|
| 16136 |
+
},
|
| 16137 |
+
{
|
| 16138 |
+
"epoch": 0.9705409183215972,
|
| 16139 |
+
"grad_norm": 0.1778954565525055,
|
| 16140 |
+
"learning_rate": 2.5314183123877917e-05,
|
| 16141 |
+
"loss": 1.9980928897857666,
|
| 16142 |
+
"step": 4600
|
| 16143 |
+
},
|
| 16144 |
+
{
|
| 16145 |
+
"epoch": 0.9709628926339109,
|
| 16146 |
+
"grad_norm": 0.11043521016836166,
|
| 16147 |
+
"learning_rate": 2.495511669658887e-05,
|
| 16148 |
+
"loss": 2.0226240158081055,
|
| 16149 |
+
"step": 4602
|
| 16150 |
+
},
|
| 16151 |
+
{
|
| 16152 |
+
"epoch": 0.9713848669462246,
|
| 16153 |
+
"grad_norm": 0.12288088351488113,
|
| 16154 |
+
"learning_rate": 2.4596050269299824e-05,
|
| 16155 |
+
"loss": 1.9354668855667114,
|
| 16156 |
+
"step": 4604
|
| 16157 |
+
},
|
| 16158 |
+
{
|
| 16159 |
+
"epoch": 0.9718068412585383,
|
| 16160 |
+
"grad_norm": 0.11611411720514297,
|
| 16161 |
+
"learning_rate": 2.4236983842010776e-05,
|
| 16162 |
+
"loss": 1.9873931407928467,
|
| 16163 |
+
"step": 4606
|
| 16164 |
+
},
|
| 16165 |
+
{
|
| 16166 |
+
"epoch": 0.9722288155708522,
|
| 16167 |
+
"grad_norm": 0.10628348588943481,
|
| 16168 |
+
"learning_rate": 2.3877917414721724e-05,
|
| 16169 |
+
"loss": 1.9681874513626099,
|
| 16170 |
+
"step": 4608
|
| 16171 |
+
},
|
| 16172 |
+
{
|
| 16173 |
+
"epoch": 0.9726507898831659,
|
| 16174 |
+
"grad_norm": 0.10231490433216095,
|
| 16175 |
+
"learning_rate": 2.3518850987432676e-05,
|
| 16176 |
+
"loss": 2.0011558532714844,
|
| 16177 |
+
"step": 4610
|
| 16178 |
+
},
|
| 16179 |
+
{
|
| 16180 |
+
"epoch": 0.9730727641954796,
|
| 16181 |
+
"grad_norm": 0.11022770404815674,
|
| 16182 |
+
"learning_rate": 2.3159784560143628e-05,
|
| 16183 |
+
"loss": 1.9592645168304443,
|
| 16184 |
+
"step": 4612
|
| 16185 |
+
},
|
| 16186 |
+
{
|
| 16187 |
+
"epoch": 0.9734947385077933,
|
| 16188 |
+
"grad_norm": 0.10896950215101242,
|
| 16189 |
+
"learning_rate": 2.280071813285458e-05,
|
| 16190 |
+
"loss": 1.9518122673034668,
|
| 16191 |
+
"step": 4614
|
| 16192 |
+
},
|
| 16193 |
+
{
|
| 16194 |
+
"epoch": 0.9739167128201071,
|
| 16195 |
+
"grad_norm": 0.10292213410139084,
|
| 16196 |
+
"learning_rate": 2.244165170556553e-05,
|
| 16197 |
+
"loss": 2.0716841220855713,
|
| 16198 |
+
"step": 4616
|
| 16199 |
+
},
|
| 16200 |
+
{
|
| 16201 |
+
"epoch": 0.9743386871324208,
|
| 16202 |
+
"grad_norm": 0.10210495442152023,
|
| 16203 |
+
"learning_rate": 2.2082585278276483e-05,
|
| 16204 |
+
"loss": 1.9209129810333252,
|
| 16205 |
+
"step": 4618
|
| 16206 |
+
},
|
| 16207 |
+
{
|
| 16208 |
+
"epoch": 0.9747606614447345,
|
| 16209 |
+
"grad_norm": 0.10981930792331696,
|
| 16210 |
+
"learning_rate": 2.1723518850987435e-05,
|
| 16211 |
+
"loss": 2.009765148162842,
|
| 16212 |
+
"step": 4620
|
| 16213 |
+
},
|
| 16214 |
+
{
|
| 16215 |
+
"epoch": 0.9751826357570483,
|
| 16216 |
+
"grad_norm": 0.13394322991371155,
|
| 16217 |
+
"learning_rate": 2.1364452423698386e-05,
|
| 16218 |
+
"loss": 1.9774208068847656,
|
| 16219 |
+
"step": 4622
|
| 16220 |
+
},
|
| 16221 |
+
{
|
| 16222 |
+
"epoch": 0.975604610069362,
|
| 16223 |
+
"grad_norm": 0.10786944627761841,
|
| 16224 |
+
"learning_rate": 2.1005385996409338e-05,
|
| 16225 |
+
"loss": 1.996282696723938,
|
| 16226 |
+
"step": 4624
|
| 16227 |
+
},
|
| 16228 |
+
{
|
| 16229 |
+
"epoch": 0.9760265843816758,
|
| 16230 |
+
"grad_norm": 0.09994073212146759,
|
| 16231 |
+
"learning_rate": 2.0646319569120286e-05,
|
| 16232 |
+
"loss": 1.9573900699615479,
|
| 16233 |
+
"step": 4626
|
| 16234 |
+
},
|
| 16235 |
+
{
|
| 16236 |
+
"epoch": 0.9764485586939895,
|
| 16237 |
+
"grad_norm": 0.10520496219396591,
|
| 16238 |
+
"learning_rate": 2.0287253141831238e-05,
|
| 16239 |
+
"loss": 1.9692916870117188,
|
| 16240 |
+
"step": 4628
|
| 16241 |
+
},
|
| 16242 |
+
{
|
| 16243 |
+
"epoch": 0.9768705330063032,
|
| 16244 |
+
"grad_norm": 0.11642242968082428,
|
| 16245 |
+
"learning_rate": 1.992818671454219e-05,
|
| 16246 |
+
"loss": 1.9627984762191772,
|
| 16247 |
+
"step": 4630
|
| 16248 |
+
},
|
| 16249 |
+
{
|
| 16250 |
+
"epoch": 0.9772925073186169,
|
| 16251 |
+
"grad_norm": 0.11063104122877121,
|
| 16252 |
+
"learning_rate": 1.9569120287253142e-05,
|
| 16253 |
+
"loss": 1.983302354812622,
|
| 16254 |
+
"step": 4632
|
| 16255 |
+
},
|
| 16256 |
+
{
|
| 16257 |
+
"epoch": 0.9777144816309307,
|
| 16258 |
+
"grad_norm": 0.11088722944259644,
|
| 16259 |
+
"learning_rate": 1.9210053859964093e-05,
|
| 16260 |
+
"loss": 2.0288641452789307,
|
| 16261 |
+
"step": 4634
|
| 16262 |
+
},
|
| 16263 |
+
{
|
| 16264 |
+
"epoch": 0.9781364559432445,
|
| 16265 |
+
"grad_norm": 0.10941636562347412,
|
| 16266 |
+
"learning_rate": 1.8850987432675045e-05,
|
| 16267 |
+
"loss": 1.9927992820739746,
|
| 16268 |
+
"step": 4636
|
| 16269 |
+
},
|
| 16270 |
+
{
|
| 16271 |
+
"epoch": 0.9785584302555582,
|
| 16272 |
+
"grad_norm": 0.10383333265781403,
|
| 16273 |
+
"learning_rate": 1.8491921005385997e-05,
|
| 16274 |
+
"loss": 2.0099031925201416,
|
| 16275 |
+
"step": 4638
|
| 16276 |
+
},
|
| 16277 |
+
{
|
| 16278 |
+
"epoch": 0.9789804045678719,
|
| 16279 |
+
"grad_norm": 0.10626033693552017,
|
| 16280 |
+
"learning_rate": 1.813285457809695e-05,
|
| 16281 |
+
"loss": 1.9769357442855835,
|
| 16282 |
+
"step": 4640
|
| 16283 |
+
},
|
| 16284 |
+
{
|
| 16285 |
+
"epoch": 0.9794023788801857,
|
| 16286 |
+
"grad_norm": 0.12086393684148788,
|
| 16287 |
+
"learning_rate": 1.77737881508079e-05,
|
| 16288 |
+
"loss": 2.0133321285247803,
|
| 16289 |
+
"step": 4642
|
| 16290 |
+
},
|
| 16291 |
+
{
|
| 16292 |
+
"epoch": 0.9798243531924994,
|
| 16293 |
+
"grad_norm": 0.10567011684179306,
|
| 16294 |
+
"learning_rate": 1.7414721723518852e-05,
|
| 16295 |
+
"loss": 2.023261308670044,
|
| 16296 |
+
"step": 4644
|
| 16297 |
+
},
|
| 16298 |
+
{
|
| 16299 |
+
"epoch": 0.9802463275048131,
|
| 16300 |
+
"grad_norm": 0.10585828125476837,
|
| 16301 |
+
"learning_rate": 1.7055655296229804e-05,
|
| 16302 |
+
"loss": 1.963270902633667,
|
| 16303 |
+
"step": 4646
|
| 16304 |
+
},
|
| 16305 |
+
{
|
| 16306 |
+
"epoch": 0.9806683018171268,
|
| 16307 |
+
"grad_norm": 0.10608888417482376,
|
| 16308 |
+
"learning_rate": 1.6696588868940756e-05,
|
| 16309 |
+
"loss": 1.9312522411346436,
|
| 16310 |
+
"step": 4648
|
| 16311 |
+
},
|
| 16312 |
+
{
|
| 16313 |
+
"epoch": 0.9810902761294407,
|
| 16314 |
+
"grad_norm": 0.1118353009223938,
|
| 16315 |
+
"learning_rate": 1.6337522441651707e-05,
|
| 16316 |
+
"loss": 1.9820836782455444,
|
| 16317 |
+
"step": 4650
|
| 16318 |
+
},
|
| 16319 |
+
{
|
| 16320 |
+
"epoch": 0.9815122504417544,
|
| 16321 |
+
"grad_norm": 0.11541516333818436,
|
| 16322 |
+
"learning_rate": 1.597845601436266e-05,
|
| 16323 |
+
"loss": 1.9589990377426147,
|
| 16324 |
+
"step": 4652
|
| 16325 |
+
},
|
| 16326 |
+
{
|
| 16327 |
+
"epoch": 0.9819342247540681,
|
| 16328 |
+
"grad_norm": 0.12044358253479004,
|
| 16329 |
+
"learning_rate": 1.561938958707361e-05,
|
| 16330 |
+
"loss": 2.009178638458252,
|
| 16331 |
+
"step": 4654
|
| 16332 |
+
},
|
| 16333 |
+
{
|
| 16334 |
+
"epoch": 0.9823561990663818,
|
| 16335 |
+
"grad_norm": 0.11771586537361145,
|
| 16336 |
+
"learning_rate": 1.5260323159784563e-05,
|
| 16337 |
+
"loss": 1.905807614326477,
|
| 16338 |
+
"step": 4656
|
| 16339 |
+
},
|
| 16340 |
+
{
|
| 16341 |
+
"epoch": 0.9827781733786956,
|
| 16342 |
+
"grad_norm": 0.09837169200181961,
|
| 16343 |
+
"learning_rate": 1.4901256732495511e-05,
|
| 16344 |
+
"loss": 2.0050885677337646,
|
| 16345 |
+
"step": 4658
|
| 16346 |
+
},
|
| 16347 |
+
{
|
| 16348 |
+
"epoch": 0.9832001476910093,
|
| 16349 |
+
"grad_norm": 0.10805536806583405,
|
| 16350 |
+
"learning_rate": 1.4542190305206463e-05,
|
| 16351 |
+
"loss": 1.9015088081359863,
|
| 16352 |
+
"step": 4660
|
| 16353 |
+
},
|
| 16354 |
+
{
|
| 16355 |
+
"epoch": 0.983622122003323,
|
| 16356 |
+
"grad_norm": 0.13526605069637299,
|
| 16357 |
+
"learning_rate": 1.4183123877917415e-05,
|
| 16358 |
+
"loss": 1.9025412797927856,
|
| 16359 |
+
"step": 4662
|
| 16360 |
+
},
|
| 16361 |
+
{
|
| 16362 |
+
"epoch": 0.9840440963156368,
|
| 16363 |
+
"grad_norm": 0.11049235612154007,
|
| 16364 |
+
"learning_rate": 1.3824057450628366e-05,
|
| 16365 |
+
"loss": 1.9939558506011963,
|
| 16366 |
+
"step": 4664
|
| 16367 |
+
},
|
| 16368 |
+
{
|
| 16369 |
+
"epoch": 0.9844660706279506,
|
| 16370 |
+
"grad_norm": 0.11036085337400436,
|
| 16371 |
+
"learning_rate": 1.3464991023339318e-05,
|
| 16372 |
+
"loss": 1.9329862594604492,
|
| 16373 |
+
"step": 4666
|
| 16374 |
+
},
|
| 16375 |
+
{
|
| 16376 |
+
"epoch": 0.9848880449402643,
|
| 16377 |
+
"grad_norm": 0.10211043059825897,
|
| 16378 |
+
"learning_rate": 1.310592459605027e-05,
|
| 16379 |
+
"loss": 1.9791620969772339,
|
| 16380 |
+
"step": 4668
|
| 16381 |
+
},
|
| 16382 |
+
{
|
| 16383 |
+
"epoch": 0.985310019252578,
|
| 16384 |
+
"grad_norm": 0.10017786175012589,
|
| 16385 |
+
"learning_rate": 1.2746858168761221e-05,
|
| 16386 |
+
"loss": 2.033644437789917,
|
| 16387 |
+
"step": 4670
|
| 16388 |
+
},
|
| 16389 |
+
{
|
| 16390 |
+
"epoch": 0.9857319935648917,
|
| 16391 |
+
"grad_norm": 0.11860562115907669,
|
| 16392 |
+
"learning_rate": 1.2387791741472173e-05,
|
| 16393 |
+
"loss": 1.9536200761795044,
|
| 16394 |
+
"step": 4672
|
| 16395 |
+
},
|
| 16396 |
+
{
|
| 16397 |
+
"epoch": 0.9861539678772054,
|
| 16398 |
+
"grad_norm": 0.1107722818851471,
|
| 16399 |
+
"learning_rate": 1.2028725314183125e-05,
|
| 16400 |
+
"loss": 1.9566007852554321,
|
| 16401 |
+
"step": 4674
|
| 16402 |
+
},
|
| 16403 |
+
{
|
| 16404 |
+
"epoch": 0.9865759421895192,
|
| 16405 |
+
"grad_norm": 0.09551042318344116,
|
| 16406 |
+
"learning_rate": 1.1669658886894077e-05,
|
| 16407 |
+
"loss": 2.0149271488189697,
|
| 16408 |
+
"step": 4676
|
| 16409 |
+
},
|
| 16410 |
+
{
|
| 16411 |
+
"epoch": 0.986997916501833,
|
| 16412 |
+
"grad_norm": 0.10458600521087646,
|
| 16413 |
+
"learning_rate": 1.1310592459605028e-05,
|
| 16414 |
+
"loss": 1.9659817218780518,
|
| 16415 |
+
"step": 4678
|
| 16416 |
+
},
|
| 16417 |
+
{
|
| 16418 |
+
"epoch": 0.9874198908141467,
|
| 16419 |
+
"grad_norm": 0.10398183763027191,
|
| 16420 |
+
"learning_rate": 1.0951526032315979e-05,
|
| 16421 |
+
"loss": 2.0331315994262695,
|
| 16422 |
+
"step": 4680
|
| 16423 |
+
},
|
| 16424 |
+
{
|
| 16425 |
+
"epoch": 0.9878418651264604,
|
| 16426 |
+
"grad_norm": 0.10857747495174408,
|
| 16427 |
+
"learning_rate": 1.059245960502693e-05,
|
| 16428 |
+
"loss": 1.999959111213684,
|
| 16429 |
+
"step": 4682
|
| 16430 |
+
},
|
| 16431 |
+
{
|
| 16432 |
+
"epoch": 0.9882638394387742,
|
| 16433 |
+
"grad_norm": 0.09563376754522324,
|
| 16434 |
+
"learning_rate": 1.0233393177737882e-05,
|
| 16435 |
+
"loss": 2.0447683334350586,
|
| 16436 |
+
"step": 4684
|
| 16437 |
+
},
|
| 16438 |
+
{
|
| 16439 |
+
"epoch": 0.9886858137510879,
|
| 16440 |
+
"grad_norm": 0.12259466201066971,
|
| 16441 |
+
"learning_rate": 9.874326750448834e-06,
|
| 16442 |
+
"loss": 1.9301782846450806,
|
| 16443 |
+
"step": 4686
|
| 16444 |
+
},
|
| 16445 |
+
{
|
| 16446 |
+
"epoch": 0.9891077880634016,
|
| 16447 |
+
"grad_norm": 0.11285020411014557,
|
| 16448 |
+
"learning_rate": 9.515260323159784e-06,
|
| 16449 |
+
"loss": 2.033548355102539,
|
| 16450 |
+
"step": 4688
|
| 16451 |
+
},
|
| 16452 |
+
{
|
| 16453 |
+
"epoch": 0.9895297623757153,
|
| 16454 |
+
"grad_norm": 0.10428531467914581,
|
| 16455 |
+
"learning_rate": 9.156193895870736e-06,
|
| 16456 |
+
"loss": 1.9834178686141968,
|
| 16457 |
+
"step": 4690
|
| 16458 |
+
},
|
| 16459 |
+
{
|
| 16460 |
+
"epoch": 0.9899517366880292,
|
| 16461 |
+
"grad_norm": 0.10745920985937119,
|
| 16462 |
+
"learning_rate": 8.797127468581689e-06,
|
| 16463 |
+
"loss": 1.9925299882888794,
|
| 16464 |
+
"step": 4692
|
| 16465 |
+
},
|
| 16466 |
+
{
|
| 16467 |
+
"epoch": 0.9903737110003429,
|
| 16468 |
+
"grad_norm": 0.09838896244764328,
|
| 16469 |
+
"learning_rate": 8.43806104129264e-06,
|
| 16470 |
+
"loss": 1.9267971515655518,
|
| 16471 |
+
"step": 4694
|
| 16472 |
+
},
|
| 16473 |
+
{
|
| 16474 |
+
"epoch": 0.9907956853126566,
|
| 16475 |
+
"grad_norm": 0.11232728511095047,
|
| 16476 |
+
"learning_rate": 8.07899461400359e-06,
|
| 16477 |
+
"loss": 1.9885969161987305,
|
| 16478 |
+
"step": 4696
|
| 16479 |
+
},
|
| 16480 |
+
{
|
| 16481 |
+
"epoch": 0.9912176596249703,
|
| 16482 |
+
"grad_norm": 0.10153519362211227,
|
| 16483 |
+
"learning_rate": 7.719928186714543e-06,
|
| 16484 |
+
"loss": 1.965550184249878,
|
| 16485 |
+
"step": 4698
|
| 16486 |
+
},
|
| 16487 |
+
{
|
| 16488 |
+
"epoch": 0.991639633937284,
|
| 16489 |
+
"grad_norm": 0.10343014448881149,
|
| 16490 |
+
"learning_rate": 7.360861759425494e-06,
|
| 16491 |
+
"loss": 1.9578814506530762,
|
| 16492 |
+
"step": 4700
|
| 16493 |
+
},
|
| 16494 |
+
{
|
| 16495 |
+
"epoch": 0.9920616082495978,
|
| 16496 |
+
"grad_norm": 0.11567633599042892,
|
| 16497 |
+
"learning_rate": 7.001795332136446e-06,
|
| 16498 |
+
"loss": 2.0264432430267334,
|
| 16499 |
+
"step": 4702
|
| 16500 |
+
},
|
| 16501 |
+
{
|
| 16502 |
+
"epoch": 0.9924835825619115,
|
| 16503 |
+
"grad_norm": 0.11094778776168823,
|
| 16504 |
+
"learning_rate": 6.642728904847396e-06,
|
| 16505 |
+
"loss": 1.9655907154083252,
|
| 16506 |
+
"step": 4704
|
| 16507 |
+
},
|
| 16508 |
+
{
|
| 16509 |
+
"epoch": 0.9929055568742253,
|
| 16510 |
+
"grad_norm": 0.10449371486902237,
|
| 16511 |
+
"learning_rate": 6.283662477558349e-06,
|
| 16512 |
+
"loss": 1.949964165687561,
|
| 16513 |
+
"step": 4706
|
| 16514 |
+
},
|
| 16515 |
+
{
|
| 16516 |
+
"epoch": 0.993327531186539,
|
| 16517 |
+
"grad_norm": 0.11244763433933258,
|
| 16518 |
+
"learning_rate": 5.9245960502693004e-06,
|
| 16519 |
+
"loss": 2.024744749069214,
|
| 16520 |
+
"step": 4708
|
| 16521 |
+
},
|
| 16522 |
+
{
|
| 16523 |
+
"epoch": 0.9937495054988528,
|
| 16524 |
+
"grad_norm": 0.10339177399873734,
|
| 16525 |
+
"learning_rate": 5.565529622980251e-06,
|
| 16526 |
+
"loss": 2.0018577575683594,
|
| 16527 |
+
"step": 4710
|
| 16528 |
+
},
|
| 16529 |
+
{
|
| 16530 |
+
"epoch": 0.9941714798111665,
|
| 16531 |
+
"grad_norm": 0.11212055385112762,
|
| 16532 |
+
"learning_rate": 5.206463195691203e-06,
|
| 16533 |
+
"loss": 1.9637234210968018,
|
| 16534 |
+
"step": 4712
|
| 16535 |
+
},
|
| 16536 |
+
{
|
| 16537 |
+
"epoch": 0.9945934541234802,
|
| 16538 |
+
"grad_norm": 0.1078438013792038,
|
| 16539 |
+
"learning_rate": 4.847396768402154e-06,
|
| 16540 |
+
"loss": 2.0055603981018066,
|
| 16541 |
+
"step": 4714
|
| 16542 |
+
},
|
| 16543 |
+
{
|
| 16544 |
+
"epoch": 0.9950154284357939,
|
| 16545 |
+
"grad_norm": 0.1065535768866539,
|
| 16546 |
+
"learning_rate": 4.488330341113106e-06,
|
| 16547 |
+
"loss": 1.9720178842544556,
|
| 16548 |
+
"step": 4716
|
| 16549 |
+
},
|
| 16550 |
+
{
|
| 16551 |
+
"epoch": 0.9954374027481077,
|
| 16552 |
+
"grad_norm": 0.10319648683071136,
|
| 16553 |
+
"learning_rate": 4.129263913824058e-06,
|
| 16554 |
+
"loss": 2.0201807022094727,
|
| 16555 |
+
"step": 4718
|
| 16556 |
+
},
|
| 16557 |
+
{
|
| 16558 |
+
"epoch": 0.9958593770604215,
|
| 16559 |
+
"grad_norm": 0.10053250938653946,
|
| 16560 |
+
"learning_rate": 3.770197486535009e-06,
|
| 16561 |
+
"loss": 1.988191843032837,
|
| 16562 |
+
"step": 4720
|
| 16563 |
+
},
|
| 16564 |
+
{
|
| 16565 |
+
"epoch": 0.9962813513727352,
|
| 16566 |
+
"grad_norm": 0.11511623859405518,
|
| 16567 |
+
"learning_rate": 3.411131059245961e-06,
|
| 16568 |
+
"loss": 1.93172287940979,
|
| 16569 |
+
"step": 4722
|
| 16570 |
+
},
|
| 16571 |
+
{
|
| 16572 |
+
"epoch": 0.9967033256850489,
|
| 16573 |
+
"grad_norm": 0.1131865456700325,
|
| 16574 |
+
"learning_rate": 3.0520646319569123e-06,
|
| 16575 |
+
"loss": 1.9372680187225342,
|
| 16576 |
+
"step": 4724
|
| 16577 |
+
},
|
| 16578 |
+
{
|
| 16579 |
+
"epoch": 0.9971252999973627,
|
| 16580 |
+
"grad_norm": 0.09997057169675827,
|
| 16581 |
+
"learning_rate": 2.6929982046678636e-06,
|
| 16582 |
+
"loss": 1.9457156658172607,
|
| 16583 |
+
"step": 4726
|
| 16584 |
+
},
|
| 16585 |
+
{
|
| 16586 |
+
"epoch": 0.9975472743096764,
|
| 16587 |
+
"grad_norm": 0.09570550173521042,
|
| 16588 |
+
"learning_rate": 2.333931777378815e-06,
|
| 16589 |
+
"loss": 1.9646587371826172,
|
| 16590 |
+
"step": 4728
|
| 16591 |
+
},
|
| 16592 |
+
{
|
| 16593 |
+
"epoch": 0.9979692486219901,
|
| 16594 |
+
"grad_norm": 0.10176803916692734,
|
| 16595 |
+
"learning_rate": 1.9748653500897667e-06,
|
| 16596 |
+
"loss": 1.9580981731414795,
|
| 16597 |
+
"step": 4730
|
| 16598 |
+
},
|
| 16599 |
+
{
|
| 16600 |
+
"epoch": 0.9983912229343038,
|
| 16601 |
+
"grad_norm": 0.10773016512393951,
|
| 16602 |
+
"learning_rate": 1.6157989228007182e-06,
|
| 16603 |
+
"loss": 1.9681389331817627,
|
| 16604 |
+
"step": 4732
|
| 16605 |
+
},
|
| 16606 |
+
{
|
| 16607 |
+
"epoch": 0.9988131972466177,
|
| 16608 |
+
"grad_norm": 0.11025076359510422,
|
| 16609 |
+
"learning_rate": 1.2567324955116697e-06,
|
| 16610 |
+
"loss": 2.0080111026763916,
|
| 16611 |
+
"step": 4734
|
| 16612 |
+
},
|
| 16613 |
+
{
|
| 16614 |
+
"epoch": 0.9992351715589314,
|
| 16615 |
+
"grad_norm": 0.10569436848163605,
|
| 16616 |
+
"learning_rate": 8.976660682226213e-07,
|
| 16617 |
+
"loss": 1.917080283164978,
|
| 16618 |
+
"step": 4736
|
| 16619 |
+
},
|
| 16620 |
+
{
|
| 16621 |
+
"epoch": 0.9996571458712451,
|
| 16622 |
+
"grad_norm": 0.11203278601169586,
|
| 16623 |
+
"learning_rate": 5.385996409335728e-07,
|
| 16624 |
+
"loss": 1.8714354038238525,
|
| 16625 |
+
"step": 4738
|
| 16626 |
+
},
|
| 16627 |
+
{
|
| 16628 |
+
"epoch": 1.0,
|
| 16629 |
+
"grad_norm": 0.11829442530870438,
|
| 16630 |
+
"learning_rate": 1.7953321364452426e-07,
|
| 16631 |
+
"loss": 1.9940471649169922,
|
| 16632 |
+
"step": 4740
|
| 16633 |
+
},
|
| 16634 |
+
{
|
| 16635 |
+
"epoch": 1.0,
|
| 16636 |
+
"eval_loss": 1.9716895818710327,
|
| 16637 |
+
"eval_runtime": 85.9928,
|
| 16638 |
+
"eval_samples_per_second": 35.631,
|
| 16639 |
+
"eval_steps_per_second": 4.454,
|
| 16640 |
+
"step": 4740
|
| 16641 |
}
|
| 16642 |
],
|
| 16643 |
"logging_steps": 2,
|
|
|
|
| 16652 |
"should_evaluate": false,
|
| 16653 |
"should_log": false,
|
| 16654 |
"should_save": true,
|
| 16655 |
+
"should_training_stop": true
|
| 16656 |
},
|
| 16657 |
"attributes": {}
|
| 16658 |
}
|
| 16659 |
},
|
| 16660 |
+
"total_flos": 4.2140322727104123e+18,
|
| 16661 |
"train_batch_size": 8,
|
| 16662 |
"trial_name": null,
|
| 16663 |
"trial_params": null
|