Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
sft
unsloth
conversational
text-generation-inference
Instructions to use Ba2han/experimental5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/experimental5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/experimental5") 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/experimental5") model = AutoModelForCausalLM.from_pretrained("Ba2han/experimental5", 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/experimental5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/experimental5" # 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/experimental5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ba2han/experimental5
- SGLang
How to use Ba2han/experimental5 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/experimental5" \ --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/experimental5", "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/experimental5" \ --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/experimental5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use Ba2han/experimental5 with Docker Model Runner:
docker model run hf.co/Ba2han/experimental5
Training in progress, step 3288, 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 2190147328
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53bf686b67dcd5ff12d4ae5e079cba486397b53433fe2524ec4b155b0f4500f8
|
| 3 |
size 2190147328
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2724634321
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6237d95004badf527f6d1bebed032db5cd6ea5360b10e77ed87355712d8b0b9d
|
| 3 |
size 2724634321
|
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 sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
|
| 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 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0419bc3bd9b31b190a7cec52e9ef5309c3a8c1eac2387a4a37854efe559c167
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 3288,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -8639,6 +8639,2891 @@
|
|
| 8639 |
"learning_rate": 9.491954909459895e-05,
|
| 8640 |
"loss": 2.0838968753814697,
|
| 8641 |
"step": 2466
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8642 |
}
|
| 8643 |
],
|
| 8644 |
"logging_steps": 2,
|
|
@@ -8658,7 +11543,7 @@
|
|
| 8658 |
"attributes": {}
|
| 8659 |
}
|
| 8660 |
},
|
| 8661 |
-
"total_flos":
|
| 8662 |
"train_batch_size": 4,
|
| 8663 |
"trial_name": null,
|
| 8664 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.20000304140878056,
|
| 6 |
"eval_steps": 3288,
|
| 7 |
+
"global_step": 3288,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8639 |
"learning_rate": 9.491954909459895e-05,
|
| 8640 |
"loss": 2.0838968753814697,
|
| 8641 |
"step": 2466
|
| 8642 |
+
},
|
| 8643 |
+
{
|
| 8644 |
+
"epoch": 0.1501239374078073,
|
| 8645 |
+
"grad_norm": 0.13698236644268036,
|
| 8646 |
+
"learning_rate": 9.491110160754519e-05,
|
| 8647 |
+
"loss": 2.0219814777374268,
|
| 8648 |
+
"step": 2468
|
| 8649 |
+
},
|
| 8650 |
+
{
|
| 8651 |
+
"epoch": 0.15024559375902918,
|
| 8652 |
+
"grad_norm": 0.17712143063545227,
|
| 8653 |
+
"learning_rate": 9.490264747986061e-05,
|
| 8654 |
+
"loss": 2.122936964035034,
|
| 8655 |
+
"step": 2470
|
| 8656 |
+
},
|
| 8657 |
+
{
|
| 8658 |
+
"epoch": 0.15036725011025107,
|
| 8659 |
+
"grad_norm": 0.1394660323858261,
|
| 8660 |
+
"learning_rate": 9.48941867127953e-05,
|
| 8661 |
+
"loss": 2.120865821838379,
|
| 8662 |
+
"step": 2472
|
| 8663 |
+
},
|
| 8664 |
+
{
|
| 8665 |
+
"epoch": 0.15048890646147295,
|
| 8666 |
+
"grad_norm": 0.16149233281612396,
|
| 8667 |
+
"learning_rate": 9.488571930760028e-05,
|
| 8668 |
+
"loss": 2.1130435466766357,
|
| 8669 |
+
"step": 2474
|
| 8670 |
+
},
|
| 8671 |
+
{
|
| 8672 |
+
"epoch": 0.15061056281269483,
|
| 8673 |
+
"grad_norm": 0.1282273828983307,
|
| 8674 |
+
"learning_rate": 9.487724526552753e-05,
|
| 8675 |
+
"loss": 2.0814614295959473,
|
| 8676 |
+
"step": 2476
|
| 8677 |
+
},
|
| 8678 |
+
{
|
| 8679 |
+
"epoch": 0.15073221916391671,
|
| 8680 |
+
"grad_norm": 0.17177602648735046,
|
| 8681 |
+
"learning_rate": 9.486876458783003e-05,
|
| 8682 |
+
"loss": 2.1031408309936523,
|
| 8683 |
+
"step": 2478
|
| 8684 |
+
},
|
| 8685 |
+
{
|
| 8686 |
+
"epoch": 0.15085387551513862,
|
| 8687 |
+
"grad_norm": 0.15521597862243652,
|
| 8688 |
+
"learning_rate": 9.486027727576177e-05,
|
| 8689 |
+
"loss": 1.9748567342758179,
|
| 8690 |
+
"step": 2480
|
| 8691 |
+
},
|
| 8692 |
+
{
|
| 8693 |
+
"epoch": 0.1509755318663605,
|
| 8694 |
+
"grad_norm": 0.13781146705150604,
|
| 8695 |
+
"learning_rate": 9.485178333057768e-05,
|
| 8696 |
+
"loss": 2.103341579437256,
|
| 8697 |
+
"step": 2482
|
| 8698 |
+
},
|
| 8699 |
+
{
|
| 8700 |
+
"epoch": 0.1510971882175824,
|
| 8701 |
+
"grad_norm": 0.178104966878891,
|
| 8702 |
+
"learning_rate": 9.484328275353371e-05,
|
| 8703 |
+
"loss": 2.0593364238739014,
|
| 8704 |
+
"step": 2484
|
| 8705 |
+
},
|
| 8706 |
+
{
|
| 8707 |
+
"epoch": 0.15121884456880427,
|
| 8708 |
+
"grad_norm": 0.16929981112480164,
|
| 8709 |
+
"learning_rate": 9.483477554588675e-05,
|
| 8710 |
+
"loss": 2.0654308795928955,
|
| 8711 |
+
"step": 2486
|
| 8712 |
+
},
|
| 8713 |
+
{
|
| 8714 |
+
"epoch": 0.15134050092002616,
|
| 8715 |
+
"grad_norm": 0.1896613985300064,
|
| 8716 |
+
"learning_rate": 9.48262617088947e-05,
|
| 8717 |
+
"loss": 2.1320035457611084,
|
| 8718 |
+
"step": 2488
|
| 8719 |
+
},
|
| 8720 |
+
{
|
| 8721 |
+
"epoch": 0.15146215727124804,
|
| 8722 |
+
"grad_norm": 0.14681246876716614,
|
| 8723 |
+
"learning_rate": 9.481774124381643e-05,
|
| 8724 |
+
"loss": 2.121796131134033,
|
| 8725 |
+
"step": 2490
|
| 8726 |
+
},
|
| 8727 |
+
{
|
| 8728 |
+
"epoch": 0.15158381362246992,
|
| 8729 |
+
"grad_norm": 0.1427050679922104,
|
| 8730 |
+
"learning_rate": 9.48092141519118e-05,
|
| 8731 |
+
"loss": 2.119422674179077,
|
| 8732 |
+
"step": 2492
|
| 8733 |
+
},
|
| 8734 |
+
{
|
| 8735 |
+
"epoch": 0.1517054699736918,
|
| 8736 |
+
"grad_norm": 0.1508098989725113,
|
| 8737 |
+
"learning_rate": 9.48006804344416e-05,
|
| 8738 |
+
"loss": 2.1290247440338135,
|
| 8739 |
+
"step": 2494
|
| 8740 |
+
},
|
| 8741 |
+
{
|
| 8742 |
+
"epoch": 0.1518271263249137,
|
| 8743 |
+
"grad_norm": 0.14888300001621246,
|
| 8744 |
+
"learning_rate": 9.47921400926677e-05,
|
| 8745 |
+
"loss": 2.0412940979003906,
|
| 8746 |
+
"step": 2496
|
| 8747 |
+
},
|
| 8748 |
+
{
|
| 8749 |
+
"epoch": 0.1519487826761356,
|
| 8750 |
+
"grad_norm": 0.14567025005817413,
|
| 8751 |
+
"learning_rate": 9.478359312785285e-05,
|
| 8752 |
+
"loss": 2.076780319213867,
|
| 8753 |
+
"step": 2498
|
| 8754 |
+
},
|
| 8755 |
+
{
|
| 8756 |
+
"epoch": 0.15207043902735748,
|
| 8757 |
+
"grad_norm": 0.153510183095932,
|
| 8758 |
+
"learning_rate": 9.477503954126081e-05,
|
| 8759 |
+
"loss": 2.0732147693634033,
|
| 8760 |
+
"step": 2500
|
| 8761 |
+
},
|
| 8762 |
+
{
|
| 8763 |
+
"epoch": 0.15219209537857936,
|
| 8764 |
+
"grad_norm": 0.16615235805511475,
|
| 8765 |
+
"learning_rate": 9.476647933415637e-05,
|
| 8766 |
+
"loss": 2.1023876667022705,
|
| 8767 |
+
"step": 2502
|
| 8768 |
+
},
|
| 8769 |
+
{
|
| 8770 |
+
"epoch": 0.15231375172980124,
|
| 8771 |
+
"grad_norm": 0.16918940842151642,
|
| 8772 |
+
"learning_rate": 9.475791250780521e-05,
|
| 8773 |
+
"loss": 2.071882724761963,
|
| 8774 |
+
"step": 2504
|
| 8775 |
+
},
|
| 8776 |
+
{
|
| 8777 |
+
"epoch": 0.15243540808102313,
|
| 8778 |
+
"grad_norm": 0.17003268003463745,
|
| 8779 |
+
"learning_rate": 9.474933906347406e-05,
|
| 8780 |
+
"loss": 2.0584335327148438,
|
| 8781 |
+
"step": 2506
|
| 8782 |
+
},
|
| 8783 |
+
{
|
| 8784 |
+
"epoch": 0.152557064432245,
|
| 8785 |
+
"grad_norm": 0.15305311977863312,
|
| 8786 |
+
"learning_rate": 9.47407590024306e-05,
|
| 8787 |
+
"loss": 2.0838401317596436,
|
| 8788 |
+
"step": 2508
|
| 8789 |
+
},
|
| 8790 |
+
{
|
| 8791 |
+
"epoch": 0.1526787207834669,
|
| 8792 |
+
"grad_norm": 0.1609611213207245,
|
| 8793 |
+
"learning_rate": 9.47321723259435e-05,
|
| 8794 |
+
"loss": 2.098411798477173,
|
| 8795 |
+
"step": 2510
|
| 8796 |
+
},
|
| 8797 |
+
{
|
| 8798 |
+
"epoch": 0.15280037713468878,
|
| 8799 |
+
"grad_norm": 0.14556053280830383,
|
| 8800 |
+
"learning_rate": 9.472357903528239e-05,
|
| 8801 |
+
"loss": 2.1233408451080322,
|
| 8802 |
+
"step": 2512
|
| 8803 |
+
},
|
| 8804 |
+
{
|
| 8805 |
+
"epoch": 0.15292203348591069,
|
| 8806 |
+
"grad_norm": 0.16678616404533386,
|
| 8807 |
+
"learning_rate": 9.471497913171789e-05,
|
| 8808 |
+
"loss": 2.1352264881134033,
|
| 8809 |
+
"step": 2514
|
| 8810 |
+
},
|
| 8811 |
+
{
|
| 8812 |
+
"epoch": 0.15304368983713257,
|
| 8813 |
+
"grad_norm": 0.1557064950466156,
|
| 8814 |
+
"learning_rate": 9.470637261652159e-05,
|
| 8815 |
+
"loss": 2.02162766456604,
|
| 8816 |
+
"step": 2516
|
| 8817 |
+
},
|
| 8818 |
+
{
|
| 8819 |
+
"epoch": 0.15316534618835445,
|
| 8820 |
+
"grad_norm": 0.1399521678686142,
|
| 8821 |
+
"learning_rate": 9.469775949096607e-05,
|
| 8822 |
+
"loss": 2.0299978256225586,
|
| 8823 |
+
"step": 2518
|
| 8824 |
+
},
|
| 8825 |
+
{
|
| 8826 |
+
"epoch": 0.15328700253957633,
|
| 8827 |
+
"grad_norm": 0.1566038429737091,
|
| 8828 |
+
"learning_rate": 9.468913975632488e-05,
|
| 8829 |
+
"loss": 1.981571078300476,
|
| 8830 |
+
"step": 2520
|
| 8831 |
+
},
|
| 8832 |
+
{
|
| 8833 |
+
"epoch": 0.15340865889079822,
|
| 8834 |
+
"grad_norm": 0.15691065788269043,
|
| 8835 |
+
"learning_rate": 9.468051341387257e-05,
|
| 8836 |
+
"loss": 2.1621129512786865,
|
| 8837 |
+
"step": 2522
|
| 8838 |
+
},
|
| 8839 |
+
{
|
| 8840 |
+
"epoch": 0.1535303152420201,
|
| 8841 |
+
"grad_norm": 0.1605062186717987,
|
| 8842 |
+
"learning_rate": 9.46718804648846e-05,
|
| 8843 |
+
"loss": 2.1346304416656494,
|
| 8844 |
+
"step": 2524
|
| 8845 |
+
},
|
| 8846 |
+
{
|
| 8847 |
+
"epoch": 0.15365197159324198,
|
| 8848 |
+
"grad_norm": 0.14539454877376556,
|
| 8849 |
+
"learning_rate": 9.466324091063749e-05,
|
| 8850 |
+
"loss": 2.065591335296631,
|
| 8851 |
+
"step": 2526
|
| 8852 |
+
},
|
| 8853 |
+
{
|
| 8854 |
+
"epoch": 0.15377362794446386,
|
| 8855 |
+
"grad_norm": 0.16157037019729614,
|
| 8856 |
+
"learning_rate": 9.46545947524087e-05,
|
| 8857 |
+
"loss": 2.153754711151123,
|
| 8858 |
+
"step": 2528
|
| 8859 |
+
},
|
| 8860 |
+
{
|
| 8861 |
+
"epoch": 0.15389528429568577,
|
| 8862 |
+
"grad_norm": 0.14384056627750397,
|
| 8863 |
+
"learning_rate": 9.464594199147663e-05,
|
| 8864 |
+
"loss": 1.9207017421722412,
|
| 8865 |
+
"step": 2530
|
| 8866 |
+
},
|
| 8867 |
+
{
|
| 8868 |
+
"epoch": 0.15401694064690766,
|
| 8869 |
+
"grad_norm": 0.13855235278606415,
|
| 8870 |
+
"learning_rate": 9.463728262912073e-05,
|
| 8871 |
+
"loss": 2.092803478240967,
|
| 8872 |
+
"step": 2532
|
| 8873 |
+
},
|
| 8874 |
+
{
|
| 8875 |
+
"epoch": 0.15413859699812954,
|
| 8876 |
+
"grad_norm": 0.14607185125350952,
|
| 8877 |
+
"learning_rate": 9.462861666662136e-05,
|
| 8878 |
+
"loss": 2.0306973457336426,
|
| 8879 |
+
"step": 2534
|
| 8880 |
+
},
|
| 8881 |
+
{
|
| 8882 |
+
"epoch": 0.15426025334935142,
|
| 8883 |
+
"grad_norm": 0.18411967158317566,
|
| 8884 |
+
"learning_rate": 9.461994410525991e-05,
|
| 8885 |
+
"loss": 2.0940756797790527,
|
| 8886 |
+
"step": 2536
|
| 8887 |
+
},
|
| 8888 |
+
{
|
| 8889 |
+
"epoch": 0.1543819097005733,
|
| 8890 |
+
"grad_norm": 0.15593470633029938,
|
| 8891 |
+
"learning_rate": 9.461126494631869e-05,
|
| 8892 |
+
"loss": 2.100522994995117,
|
| 8893 |
+
"step": 2538
|
| 8894 |
+
},
|
| 8895 |
+
{
|
| 8896 |
+
"epoch": 0.1545035660517952,
|
| 8897 |
+
"grad_norm": 0.15559330582618713,
|
| 8898 |
+
"learning_rate": 9.460257919108104e-05,
|
| 8899 |
+
"loss": 2.103457450866699,
|
| 8900 |
+
"step": 2540
|
| 8901 |
+
},
|
| 8902 |
+
{
|
| 8903 |
+
"epoch": 0.15462522240301707,
|
| 8904 |
+
"grad_norm": 0.1584291309118271,
|
| 8905 |
+
"learning_rate": 9.459388684083123e-05,
|
| 8906 |
+
"loss": 2.1416940689086914,
|
| 8907 |
+
"step": 2542
|
| 8908 |
+
},
|
| 8909 |
+
{
|
| 8910 |
+
"epoch": 0.15474687875423895,
|
| 8911 |
+
"grad_norm": 0.16263510286808014,
|
| 8912 |
+
"learning_rate": 9.458518789685456e-05,
|
| 8913 |
+
"loss": 2.147287130355835,
|
| 8914 |
+
"step": 2544
|
| 8915 |
+
},
|
| 8916 |
+
{
|
| 8917 |
+
"epoch": 0.15486853510546084,
|
| 8918 |
+
"grad_norm": 0.17573049664497375,
|
| 8919 |
+
"learning_rate": 9.457648236043722e-05,
|
| 8920 |
+
"loss": 2.189533233642578,
|
| 8921 |
+
"step": 2546
|
| 8922 |
+
},
|
| 8923 |
+
{
|
| 8924 |
+
"epoch": 0.15499019145668275,
|
| 8925 |
+
"grad_norm": 0.153211310505867,
|
| 8926 |
+
"learning_rate": 9.456777023286646e-05,
|
| 8927 |
+
"loss": 2.0940945148468018,
|
| 8928 |
+
"step": 2548
|
| 8929 |
+
},
|
| 8930 |
+
{
|
| 8931 |
+
"epoch": 0.15511184780790463,
|
| 8932 |
+
"grad_norm": 0.15909793972969055,
|
| 8933 |
+
"learning_rate": 9.455905151543047e-05,
|
| 8934 |
+
"loss": 2.0908422470092773,
|
| 8935 |
+
"step": 2550
|
| 8936 |
+
},
|
| 8937 |
+
{
|
| 8938 |
+
"epoch": 0.1552335041591265,
|
| 8939 |
+
"grad_norm": 0.13952219486236572,
|
| 8940 |
+
"learning_rate": 9.45503262094184e-05,
|
| 8941 |
+
"loss": 2.0918593406677246,
|
| 8942 |
+
"step": 2552
|
| 8943 |
+
},
|
| 8944 |
+
{
|
| 8945 |
+
"epoch": 0.1553551605103484,
|
| 8946 |
+
"grad_norm": 0.15962132811546326,
|
| 8947 |
+
"learning_rate": 9.45415943161204e-05,
|
| 8948 |
+
"loss": 2.1802899837493896,
|
| 8949 |
+
"step": 2554
|
| 8950 |
+
},
|
| 8951 |
+
{
|
| 8952 |
+
"epoch": 0.15547681686157028,
|
| 8953 |
+
"grad_norm": 0.14169152081012726,
|
| 8954 |
+
"learning_rate": 9.453285583682756e-05,
|
| 8955 |
+
"loss": 2.0940661430358887,
|
| 8956 |
+
"step": 2556
|
| 8957 |
+
},
|
| 8958 |
+
{
|
| 8959 |
+
"epoch": 0.15559847321279216,
|
| 8960 |
+
"grad_norm": 0.14945219457149506,
|
| 8961 |
+
"learning_rate": 9.452411077283199e-05,
|
| 8962 |
+
"loss": 2.061657667160034,
|
| 8963 |
+
"step": 2558
|
| 8964 |
+
},
|
| 8965 |
+
{
|
| 8966 |
+
"epoch": 0.15572012956401404,
|
| 8967 |
+
"grad_norm": 0.17380546033382416,
|
| 8968 |
+
"learning_rate": 9.451535912542676e-05,
|
| 8969 |
+
"loss": 1.93306303024292,
|
| 8970 |
+
"step": 2560
|
| 8971 |
+
},
|
| 8972 |
+
{
|
| 8973 |
+
"epoch": 0.15584178591523593,
|
| 8974 |
+
"grad_norm": 0.1529255360364914,
|
| 8975 |
+
"learning_rate": 9.450660089590586e-05,
|
| 8976 |
+
"loss": 2.04657244682312,
|
| 8977 |
+
"step": 2562
|
| 8978 |
+
},
|
| 8979 |
+
{
|
| 8980 |
+
"epoch": 0.15596344226645784,
|
| 8981 |
+
"grad_norm": 0.15088124573230743,
|
| 8982 |
+
"learning_rate": 9.449783608556433e-05,
|
| 8983 |
+
"loss": 2.1165966987609863,
|
| 8984 |
+
"step": 2564
|
| 8985 |
+
},
|
| 8986 |
+
{
|
| 8987 |
+
"epoch": 0.15608509861767972,
|
| 8988 |
+
"grad_norm": 0.15748639404773712,
|
| 8989 |
+
"learning_rate": 9.448906469569815e-05,
|
| 8990 |
+
"loss": 2.01537823677063,
|
| 8991 |
+
"step": 2566
|
| 8992 |
+
},
|
| 8993 |
+
{
|
| 8994 |
+
"epoch": 0.1562067549689016,
|
| 8995 |
+
"grad_norm": 0.1711074858903885,
|
| 8996 |
+
"learning_rate": 9.448028672760426e-05,
|
| 8997 |
+
"loss": 2.078158140182495,
|
| 8998 |
+
"step": 2568
|
| 8999 |
+
},
|
| 9000 |
+
{
|
| 9001 |
+
"epoch": 0.15632841132012348,
|
| 9002 |
+
"grad_norm": 0.15637166798114777,
|
| 9003 |
+
"learning_rate": 9.447150218258058e-05,
|
| 9004 |
+
"loss": 2.0414087772369385,
|
| 9005 |
+
"step": 2570
|
| 9006 |
+
},
|
| 9007 |
+
{
|
| 9008 |
+
"epoch": 0.15645006767134537,
|
| 9009 |
+
"grad_norm": 0.15362007915973663,
|
| 9010 |
+
"learning_rate": 9.446271106192603e-05,
|
| 9011 |
+
"loss": 2.1606252193450928,
|
| 9012 |
+
"step": 2572
|
| 9013 |
+
},
|
| 9014 |
+
{
|
| 9015 |
+
"epoch": 0.15657172402256725,
|
| 9016 |
+
"grad_norm": 0.14094997942447662,
|
| 9017 |
+
"learning_rate": 9.445391336694047e-05,
|
| 9018 |
+
"loss": 2.0836477279663086,
|
| 9019 |
+
"step": 2574
|
| 9020 |
+
},
|
| 9021 |
+
{
|
| 9022 |
+
"epoch": 0.15669338037378913,
|
| 9023 |
+
"grad_norm": 0.1755836009979248,
|
| 9024 |
+
"learning_rate": 9.444510909892473e-05,
|
| 9025 |
+
"loss": 2.0433008670806885,
|
| 9026 |
+
"step": 2576
|
| 9027 |
+
},
|
| 9028 |
+
{
|
| 9029 |
+
"epoch": 0.15681503672501101,
|
| 9030 |
+
"grad_norm": 0.17318519949913025,
|
| 9031 |
+
"learning_rate": 9.443629825918063e-05,
|
| 9032 |
+
"loss": 2.1740190982818604,
|
| 9033 |
+
"step": 2578
|
| 9034 |
+
},
|
| 9035 |
+
{
|
| 9036 |
+
"epoch": 0.15693669307623292,
|
| 9037 |
+
"grad_norm": 0.1575072705745697,
|
| 9038 |
+
"learning_rate": 9.442748084901097e-05,
|
| 9039 |
+
"loss": 2.1058366298675537,
|
| 9040 |
+
"step": 2580
|
| 9041 |
+
},
|
| 9042 |
+
{
|
| 9043 |
+
"epoch": 0.1570583494274548,
|
| 9044 |
+
"grad_norm": 0.18523457646369934,
|
| 9045 |
+
"learning_rate": 9.441865686971947e-05,
|
| 9046 |
+
"loss": 2.0838866233825684,
|
| 9047 |
+
"step": 2582
|
| 9048 |
+
},
|
| 9049 |
+
{
|
| 9050 |
+
"epoch": 0.1571800057786767,
|
| 9051 |
+
"grad_norm": 0.15263622999191284,
|
| 9052 |
+
"learning_rate": 9.44098263226109e-05,
|
| 9053 |
+
"loss": 2.002534866333008,
|
| 9054 |
+
"step": 2584
|
| 9055 |
+
},
|
| 9056 |
+
{
|
| 9057 |
+
"epoch": 0.15730166212989857,
|
| 9058 |
+
"grad_norm": 0.14991115033626556,
|
| 9059 |
+
"learning_rate": 9.440098920899094e-05,
|
| 9060 |
+
"loss": 2.0473458766937256,
|
| 9061 |
+
"step": 2586
|
| 9062 |
+
},
|
| 9063 |
+
{
|
| 9064 |
+
"epoch": 0.15742331848112046,
|
| 9065 |
+
"grad_norm": 0.1543298065662384,
|
| 9066 |
+
"learning_rate": 9.439214553016626e-05,
|
| 9067 |
+
"loss": 2.0370945930480957,
|
| 9068 |
+
"step": 2588
|
| 9069 |
+
},
|
| 9070 |
+
{
|
| 9071 |
+
"epoch": 0.15754497483234234,
|
| 9072 |
+
"grad_norm": 0.16891197860240936,
|
| 9073 |
+
"learning_rate": 9.438329528744451e-05,
|
| 9074 |
+
"loss": 2.0419514179229736,
|
| 9075 |
+
"step": 2590
|
| 9076 |
+
},
|
| 9077 |
+
{
|
| 9078 |
+
"epoch": 0.15766663118356422,
|
| 9079 |
+
"grad_norm": 0.1583983451128006,
|
| 9080 |
+
"learning_rate": 9.437443848213431e-05,
|
| 9081 |
+
"loss": 2.0280776023864746,
|
| 9082 |
+
"step": 2592
|
| 9083 |
+
},
|
| 9084 |
+
{
|
| 9085 |
+
"epoch": 0.1577882875347861,
|
| 9086 |
+
"grad_norm": 0.14703738689422607,
|
| 9087 |
+
"learning_rate": 9.436557511554522e-05,
|
| 9088 |
+
"loss": 2.1020872592926025,
|
| 9089 |
+
"step": 2594
|
| 9090 |
+
},
|
| 9091 |
+
{
|
| 9092 |
+
"epoch": 0.157909943886008,
|
| 9093 |
+
"grad_norm": 0.14275288581848145,
|
| 9094 |
+
"learning_rate": 9.435670518898779e-05,
|
| 9095 |
+
"loss": 2.113313674926758,
|
| 9096 |
+
"step": 2596
|
| 9097 |
+
},
|
| 9098 |
+
{
|
| 9099 |
+
"epoch": 0.1580316002372299,
|
| 9100 |
+
"grad_norm": 0.16897869110107422,
|
| 9101 |
+
"learning_rate": 9.434782870377357e-05,
|
| 9102 |
+
"loss": 2.110163927078247,
|
| 9103 |
+
"step": 2598
|
| 9104 |
+
},
|
| 9105 |
+
{
|
| 9106 |
+
"epoch": 0.15815325658845178,
|
| 9107 |
+
"grad_norm": 0.17133255302906036,
|
| 9108 |
+
"learning_rate": 9.433894566121502e-05,
|
| 9109 |
+
"loss": 2.094851016998291,
|
| 9110 |
+
"step": 2600
|
| 9111 |
+
},
|
| 9112 |
+
{
|
| 9113 |
+
"epoch": 0.15827491293967366,
|
| 9114 |
+
"grad_norm": 0.13771849870681763,
|
| 9115 |
+
"learning_rate": 9.433005606262561e-05,
|
| 9116 |
+
"loss": 2.1017041206359863,
|
| 9117 |
+
"step": 2602
|
| 9118 |
+
},
|
| 9119 |
+
{
|
| 9120 |
+
"epoch": 0.15839656929089554,
|
| 9121 |
+
"grad_norm": 0.13902068138122559,
|
| 9122 |
+
"learning_rate": 9.432115990931979e-05,
|
| 9123 |
+
"loss": 2.1915903091430664,
|
| 9124 |
+
"step": 2604
|
| 9125 |
+
},
|
| 9126 |
+
{
|
| 9127 |
+
"epoch": 0.15851822564211743,
|
| 9128 |
+
"grad_norm": 0.15080049633979797,
|
| 9129 |
+
"learning_rate": 9.431225720261294e-05,
|
| 9130 |
+
"loss": 2.138369560241699,
|
| 9131 |
+
"step": 2606
|
| 9132 |
+
},
|
| 9133 |
+
{
|
| 9134 |
+
"epoch": 0.1586398819933393,
|
| 9135 |
+
"grad_norm": 0.17003124952316284,
|
| 9136 |
+
"learning_rate": 9.430334794382145e-05,
|
| 9137 |
+
"loss": 2.1625418663024902,
|
| 9138 |
+
"step": 2608
|
| 9139 |
+
},
|
| 9140 |
+
{
|
| 9141 |
+
"epoch": 0.1587615383445612,
|
| 9142 |
+
"grad_norm": 0.15700474381446838,
|
| 9143 |
+
"learning_rate": 9.429443213426263e-05,
|
| 9144 |
+
"loss": 2.0508041381835938,
|
| 9145 |
+
"step": 2610
|
| 9146 |
+
},
|
| 9147 |
+
{
|
| 9148 |
+
"epoch": 0.15888319469578308,
|
| 9149 |
+
"grad_norm": 0.15280267596244812,
|
| 9150 |
+
"learning_rate": 9.428550977525481e-05,
|
| 9151 |
+
"loss": 2.0111336708068848,
|
| 9152 |
+
"step": 2612
|
| 9153 |
+
},
|
| 9154 |
+
{
|
| 9155 |
+
"epoch": 0.15900485104700499,
|
| 9156 |
+
"grad_norm": 0.15159858763217926,
|
| 9157 |
+
"learning_rate": 9.427658086811725e-05,
|
| 9158 |
+
"loss": 2.120317220687866,
|
| 9159 |
+
"step": 2614
|
| 9160 |
+
},
|
| 9161 |
+
{
|
| 9162 |
+
"epoch": 0.15912650739822687,
|
| 9163 |
+
"grad_norm": 0.17874091863632202,
|
| 9164 |
+
"learning_rate": 9.42676454141702e-05,
|
| 9165 |
+
"loss": 2.1072616577148438,
|
| 9166 |
+
"step": 2616
|
| 9167 |
+
},
|
| 9168 |
+
{
|
| 9169 |
+
"epoch": 0.15924816374944875,
|
| 9170 |
+
"grad_norm": 0.17065158486366272,
|
| 9171 |
+
"learning_rate": 9.425870341473487e-05,
|
| 9172 |
+
"loss": 2.1158394813537598,
|
| 9173 |
+
"step": 2618
|
| 9174 |
+
},
|
| 9175 |
+
{
|
| 9176 |
+
"epoch": 0.15936982010067063,
|
| 9177 |
+
"grad_norm": 0.1505609154701233,
|
| 9178 |
+
"learning_rate": 9.424975487113344e-05,
|
| 9179 |
+
"loss": 2.0952696800231934,
|
| 9180 |
+
"step": 2620
|
| 9181 |
+
},
|
| 9182 |
+
{
|
| 9183 |
+
"epoch": 0.15949147645189252,
|
| 9184 |
+
"grad_norm": 0.16104713082313538,
|
| 9185 |
+
"learning_rate": 9.424079978468907e-05,
|
| 9186 |
+
"loss": 2.1366639137268066,
|
| 9187 |
+
"step": 2622
|
| 9188 |
+
},
|
| 9189 |
+
{
|
| 9190 |
+
"epoch": 0.1596131328031144,
|
| 9191 |
+
"grad_norm": 0.15939518809318542,
|
| 9192 |
+
"learning_rate": 9.423183815672585e-05,
|
| 9193 |
+
"loss": 2.146383762359619,
|
| 9194 |
+
"step": 2624
|
| 9195 |
+
},
|
| 9196 |
+
{
|
| 9197 |
+
"epoch": 0.15973478915433628,
|
| 9198 |
+
"grad_norm": 0.1566299945116043,
|
| 9199 |
+
"learning_rate": 9.422286998856886e-05,
|
| 9200 |
+
"loss": 2.0865111351013184,
|
| 9201 |
+
"step": 2626
|
| 9202 |
+
},
|
| 9203 |
+
{
|
| 9204 |
+
"epoch": 0.15985644550555816,
|
| 9205 |
+
"grad_norm": 0.14970451593399048,
|
| 9206 |
+
"learning_rate": 9.421389528154417e-05,
|
| 9207 |
+
"loss": 2.152747631072998,
|
| 9208 |
+
"step": 2628
|
| 9209 |
+
},
|
| 9210 |
+
{
|
| 9211 |
+
"epoch": 0.15997810185678005,
|
| 9212 |
+
"grad_norm": 0.15223272144794464,
|
| 9213 |
+
"learning_rate": 9.420491403697879e-05,
|
| 9214 |
+
"loss": 2.0806756019592285,
|
| 9215 |
+
"step": 2630
|
| 9216 |
+
},
|
| 9217 |
+
{
|
| 9218 |
+
"epoch": 0.16009975820800196,
|
| 9219 |
+
"grad_norm": 0.16197781264781952,
|
| 9220 |
+
"learning_rate": 9.419592625620069e-05,
|
| 9221 |
+
"loss": 2.11051869392395,
|
| 9222 |
+
"step": 2632
|
| 9223 |
+
},
|
| 9224 |
+
{
|
| 9225 |
+
"epoch": 0.16022141455922384,
|
| 9226 |
+
"grad_norm": 0.14744442701339722,
|
| 9227 |
+
"learning_rate": 9.418693194053883e-05,
|
| 9228 |
+
"loss": 2.1473028659820557,
|
| 9229 |
+
"step": 2634
|
| 9230 |
+
},
|
| 9231 |
+
{
|
| 9232 |
+
"epoch": 0.16034307091044572,
|
| 9233 |
+
"grad_norm": 0.15032216906547546,
|
| 9234 |
+
"learning_rate": 9.417793109132312e-05,
|
| 9235 |
+
"loss": 2.0599539279937744,
|
| 9236 |
+
"step": 2636
|
| 9237 |
+
},
|
| 9238 |
+
{
|
| 9239 |
+
"epoch": 0.1604647272616676,
|
| 9240 |
+
"grad_norm": 0.16936413943767548,
|
| 9241 |
+
"learning_rate": 9.416892370988444e-05,
|
| 9242 |
+
"loss": 2.1228411197662354,
|
| 9243 |
+
"step": 2638
|
| 9244 |
+
},
|
| 9245 |
+
{
|
| 9246 |
+
"epoch": 0.1605863836128895,
|
| 9247 |
+
"grad_norm": 0.16562367975711823,
|
| 9248 |
+
"learning_rate": 9.415990979755463e-05,
|
| 9249 |
+
"loss": 2.1872854232788086,
|
| 9250 |
+
"step": 2640
|
| 9251 |
+
},
|
| 9252 |
+
{
|
| 9253 |
+
"epoch": 0.16070803996411137,
|
| 9254 |
+
"grad_norm": 0.16552571952342987,
|
| 9255 |
+
"learning_rate": 9.415088935566652e-05,
|
| 9256 |
+
"loss": 2.0971407890319824,
|
| 9257 |
+
"step": 2642
|
| 9258 |
+
},
|
| 9259 |
+
{
|
| 9260 |
+
"epoch": 0.16082969631533325,
|
| 9261 |
+
"grad_norm": 0.15087798237800598,
|
| 9262 |
+
"learning_rate": 9.414186238555387e-05,
|
| 9263 |
+
"loss": 2.1516966819763184,
|
| 9264 |
+
"step": 2644
|
| 9265 |
+
},
|
| 9266 |
+
{
|
| 9267 |
+
"epoch": 0.16095135266655514,
|
| 9268 |
+
"grad_norm": 0.18510277569293976,
|
| 9269 |
+
"learning_rate": 9.413282888855142e-05,
|
| 9270 |
+
"loss": 2.196718692779541,
|
| 9271 |
+
"step": 2646
|
| 9272 |
+
},
|
| 9273 |
+
{
|
| 9274 |
+
"epoch": 0.16107300901777705,
|
| 9275 |
+
"grad_norm": 0.15703165531158447,
|
| 9276 |
+
"learning_rate": 9.412378886599491e-05,
|
| 9277 |
+
"loss": 2.069314479827881,
|
| 9278 |
+
"step": 2648
|
| 9279 |
+
},
|
| 9280 |
+
{
|
| 9281 |
+
"epoch": 0.16119466536899893,
|
| 9282 |
+
"grad_norm": 0.1710774004459381,
|
| 9283 |
+
"learning_rate": 9.411474231922097e-05,
|
| 9284 |
+
"loss": 2.0276851654052734,
|
| 9285 |
+
"step": 2650
|
| 9286 |
+
},
|
| 9287 |
+
{
|
| 9288 |
+
"epoch": 0.1613163217202208,
|
| 9289 |
+
"grad_norm": 0.14928919076919556,
|
| 9290 |
+
"learning_rate": 9.410568924956729e-05,
|
| 9291 |
+
"loss": 2.195276975631714,
|
| 9292 |
+
"step": 2652
|
| 9293 |
+
},
|
| 9294 |
+
{
|
| 9295 |
+
"epoch": 0.1614379780714427,
|
| 9296 |
+
"grad_norm": 0.18814489245414734,
|
| 9297 |
+
"learning_rate": 9.40966296583724e-05,
|
| 9298 |
+
"loss": 2.1018505096435547,
|
| 9299 |
+
"step": 2654
|
| 9300 |
+
},
|
| 9301 |
+
{
|
| 9302 |
+
"epoch": 0.16155963442266458,
|
| 9303 |
+
"grad_norm": 0.16511280834674835,
|
| 9304 |
+
"learning_rate": 9.408756354697594e-05,
|
| 9305 |
+
"loss": 2.178497314453125,
|
| 9306 |
+
"step": 2656
|
| 9307 |
+
},
|
| 9308 |
+
{
|
| 9309 |
+
"epoch": 0.16168129077388646,
|
| 9310 |
+
"grad_norm": 0.16446106135845184,
|
| 9311 |
+
"learning_rate": 9.407849091671838e-05,
|
| 9312 |
+
"loss": 2.1532320976257324,
|
| 9313 |
+
"step": 2658
|
| 9314 |
+
},
|
| 9315 |
+
{
|
| 9316 |
+
"epoch": 0.16180294712510834,
|
| 9317 |
+
"grad_norm": 0.16314704716205597,
|
| 9318 |
+
"learning_rate": 9.406941176894126e-05,
|
| 9319 |
+
"loss": 2.118274211883545,
|
| 9320 |
+
"step": 2660
|
| 9321 |
+
},
|
| 9322 |
+
{
|
| 9323 |
+
"epoch": 0.16192460347633023,
|
| 9324 |
+
"grad_norm": 0.14210686087608337,
|
| 9325 |
+
"learning_rate": 9.406032610498703e-05,
|
| 9326 |
+
"loss": 2.059508800506592,
|
| 9327 |
+
"step": 2662
|
| 9328 |
+
},
|
| 9329 |
+
{
|
| 9330 |
+
"epoch": 0.16204625982755214,
|
| 9331 |
+
"grad_norm": 0.16135714948177338,
|
| 9332 |
+
"learning_rate": 9.405123392619907e-05,
|
| 9333 |
+
"loss": 2.161588668823242,
|
| 9334 |
+
"step": 2664
|
| 9335 |
+
},
|
| 9336 |
+
{
|
| 9337 |
+
"epoch": 0.16216791617877402,
|
| 9338 |
+
"grad_norm": 0.1945061981678009,
|
| 9339 |
+
"learning_rate": 9.404213523392183e-05,
|
| 9340 |
+
"loss": 2.1644296646118164,
|
| 9341 |
+
"step": 2666
|
| 9342 |
+
},
|
| 9343 |
+
{
|
| 9344 |
+
"epoch": 0.1622895725299959,
|
| 9345 |
+
"grad_norm": 0.1448889672756195,
|
| 9346 |
+
"learning_rate": 9.403303002950059e-05,
|
| 9347 |
+
"loss": 2.0714328289031982,
|
| 9348 |
+
"step": 2668
|
| 9349 |
+
},
|
| 9350 |
+
{
|
| 9351 |
+
"epoch": 0.16241122888121778,
|
| 9352 |
+
"grad_norm": 0.1639811396598816,
|
| 9353 |
+
"learning_rate": 9.402391831428172e-05,
|
| 9354 |
+
"loss": 2.1386122703552246,
|
| 9355 |
+
"step": 2670
|
| 9356 |
+
},
|
| 9357 |
+
{
|
| 9358 |
+
"epoch": 0.16253288523243967,
|
| 9359 |
+
"grad_norm": 0.1867406815290451,
|
| 9360 |
+
"learning_rate": 9.401480008961245e-05,
|
| 9361 |
+
"loss": 2.0828731060028076,
|
| 9362 |
+
"step": 2672
|
| 9363 |
+
},
|
| 9364 |
+
{
|
| 9365 |
+
"epoch": 0.16265454158366155,
|
| 9366 |
+
"grad_norm": 0.14344386756420135,
|
| 9367 |
+
"learning_rate": 9.400567535684105e-05,
|
| 9368 |
+
"loss": 2.105694055557251,
|
| 9369 |
+
"step": 2674
|
| 9370 |
+
},
|
| 9371 |
+
{
|
| 9372 |
+
"epoch": 0.16277619793488343,
|
| 9373 |
+
"grad_norm": 0.13579468429088593,
|
| 9374 |
+
"learning_rate": 9.399654411731669e-05,
|
| 9375 |
+
"loss": 1.9500064849853516,
|
| 9376 |
+
"step": 2676
|
| 9377 |
+
},
|
| 9378 |
+
{
|
| 9379 |
+
"epoch": 0.16289785428610531,
|
| 9380 |
+
"grad_norm": 0.14930644631385803,
|
| 9381 |
+
"learning_rate": 9.398740637238955e-05,
|
| 9382 |
+
"loss": 2.0797319412231445,
|
| 9383 |
+
"step": 2678
|
| 9384 |
+
},
|
| 9385 |
+
{
|
| 9386 |
+
"epoch": 0.1630195106373272,
|
| 9387 |
+
"grad_norm": 0.14782030880451202,
|
| 9388 |
+
"learning_rate": 9.397826212341075e-05,
|
| 9389 |
+
"loss": 2.0689735412597656,
|
| 9390 |
+
"step": 2680
|
| 9391 |
+
},
|
| 9392 |
+
{
|
| 9393 |
+
"epoch": 0.1631411669885491,
|
| 9394 |
+
"grad_norm": 0.1571684330701828,
|
| 9395 |
+
"learning_rate": 9.396911137173236e-05,
|
| 9396 |
+
"loss": 2.1586484909057617,
|
| 9397 |
+
"step": 2682
|
| 9398 |
+
},
|
| 9399 |
+
{
|
| 9400 |
+
"epoch": 0.163262823339771,
|
| 9401 |
+
"grad_norm": 0.15532144904136658,
|
| 9402 |
+
"learning_rate": 9.395995411870743e-05,
|
| 9403 |
+
"loss": 2.0964314937591553,
|
| 9404 |
+
"step": 2684
|
| 9405 |
+
},
|
| 9406 |
+
{
|
| 9407 |
+
"epoch": 0.16338447969099287,
|
| 9408 |
+
"grad_norm": 0.14501845836639404,
|
| 9409 |
+
"learning_rate": 9.395079036568999e-05,
|
| 9410 |
+
"loss": 2.0862271785736084,
|
| 9411 |
+
"step": 2686
|
| 9412 |
+
},
|
| 9413 |
+
{
|
| 9414 |
+
"epoch": 0.16350613604221476,
|
| 9415 |
+
"grad_norm": 0.17680218815803528,
|
| 9416 |
+
"learning_rate": 9.394162011403498e-05,
|
| 9417 |
+
"loss": 2.1578896045684814,
|
| 9418 |
+
"step": 2688
|
| 9419 |
+
},
|
| 9420 |
+
{
|
| 9421 |
+
"epoch": 0.16362779239343664,
|
| 9422 |
+
"grad_norm": 0.15774433314800262,
|
| 9423 |
+
"learning_rate": 9.393244336509832e-05,
|
| 9424 |
+
"loss": 2.0683059692382812,
|
| 9425 |
+
"step": 2690
|
| 9426 |
+
},
|
| 9427 |
+
{
|
| 9428 |
+
"epoch": 0.16374944874465852,
|
| 9429 |
+
"grad_norm": 0.1375741809606552,
|
| 9430 |
+
"learning_rate": 9.392326012023694e-05,
|
| 9431 |
+
"loss": 2.0200445652008057,
|
| 9432 |
+
"step": 2692
|
| 9433 |
+
},
|
| 9434 |
+
{
|
| 9435 |
+
"epoch": 0.1638711050958804,
|
| 9436 |
+
"grad_norm": 0.16762664914131165,
|
| 9437 |
+
"learning_rate": 9.391407038080867e-05,
|
| 9438 |
+
"loss": 2.0943288803100586,
|
| 9439 |
+
"step": 2694
|
| 9440 |
+
},
|
| 9441 |
+
{
|
| 9442 |
+
"epoch": 0.1639927614471023,
|
| 9443 |
+
"grad_norm": 0.17912378907203674,
|
| 9444 |
+
"learning_rate": 9.39048741481723e-05,
|
| 9445 |
+
"loss": 2.157824754714966,
|
| 9446 |
+
"step": 2696
|
| 9447 |
+
},
|
| 9448 |
+
{
|
| 9449 |
+
"epoch": 0.1641144177983242,
|
| 9450 |
+
"grad_norm": 0.15225601196289062,
|
| 9451 |
+
"learning_rate": 9.389567142368763e-05,
|
| 9452 |
+
"loss": 2.0460124015808105,
|
| 9453 |
+
"step": 2698
|
| 9454 |
+
},
|
| 9455 |
+
{
|
| 9456 |
+
"epoch": 0.16423607414954608,
|
| 9457 |
+
"grad_norm": 0.15969541668891907,
|
| 9458 |
+
"learning_rate": 9.388646220871538e-05,
|
| 9459 |
+
"loss": 2.0949158668518066,
|
| 9460 |
+
"step": 2700
|
| 9461 |
+
},
|
| 9462 |
+
{
|
| 9463 |
+
"epoch": 0.16435773050076796,
|
| 9464 |
+
"grad_norm": 0.16702432930469513,
|
| 9465 |
+
"learning_rate": 9.387724650461722e-05,
|
| 9466 |
+
"loss": 2.155531406402588,
|
| 9467 |
+
"step": 2702
|
| 9468 |
+
},
|
| 9469 |
+
{
|
| 9470 |
+
"epoch": 0.16447938685198984,
|
| 9471 |
+
"grad_norm": 0.15166586637496948,
|
| 9472 |
+
"learning_rate": 9.386802431275585e-05,
|
| 9473 |
+
"loss": 2.0874252319335938,
|
| 9474 |
+
"step": 2704
|
| 9475 |
+
},
|
| 9476 |
+
{
|
| 9477 |
+
"epoch": 0.16460104320321173,
|
| 9478 |
+
"grad_norm": 0.13939829170703888,
|
| 9479 |
+
"learning_rate": 9.385879563449482e-05,
|
| 9480 |
+
"loss": 2.0122268199920654,
|
| 9481 |
+
"step": 2706
|
| 9482 |
+
},
|
| 9483 |
+
{
|
| 9484 |
+
"epoch": 0.1647226995544336,
|
| 9485 |
+
"grad_norm": 0.14624623954296112,
|
| 9486 |
+
"learning_rate": 9.384956047119872e-05,
|
| 9487 |
+
"loss": 2.03910756111145,
|
| 9488 |
+
"step": 2708
|
| 9489 |
+
},
|
| 9490 |
+
{
|
| 9491 |
+
"epoch": 0.1648443559056555,
|
| 9492 |
+
"grad_norm": 0.15732645988464355,
|
| 9493 |
+
"learning_rate": 9.38403188242331e-05,
|
| 9494 |
+
"loss": 2.0288021564483643,
|
| 9495 |
+
"step": 2710
|
| 9496 |
+
},
|
| 9497 |
+
{
|
| 9498 |
+
"epoch": 0.16496601225687738,
|
| 9499 |
+
"grad_norm": 0.16048960387706757,
|
| 9500 |
+
"learning_rate": 9.383107069496441e-05,
|
| 9501 |
+
"loss": 2.080328941345215,
|
| 9502 |
+
"step": 2712
|
| 9503 |
+
},
|
| 9504 |
+
{
|
| 9505 |
+
"epoch": 0.16508766860809926,
|
| 9506 |
+
"grad_norm": 0.15933027863502502,
|
| 9507 |
+
"learning_rate": 9.382181608476013e-05,
|
| 9508 |
+
"loss": 2.044390916824341,
|
| 9509 |
+
"step": 2714
|
| 9510 |
+
},
|
| 9511 |
+
{
|
| 9512 |
+
"epoch": 0.16520932495932117,
|
| 9513 |
+
"grad_norm": 0.16338936984539032,
|
| 9514 |
+
"learning_rate": 9.381255499498865e-05,
|
| 9515 |
+
"loss": 2.088326930999756,
|
| 9516 |
+
"step": 2716
|
| 9517 |
+
},
|
| 9518 |
+
{
|
| 9519 |
+
"epoch": 0.16533098131054305,
|
| 9520 |
+
"grad_norm": 0.1474781036376953,
|
| 9521 |
+
"learning_rate": 9.380328742701929e-05,
|
| 9522 |
+
"loss": 2.09079909324646,
|
| 9523 |
+
"step": 2718
|
| 9524 |
+
},
|
| 9525 |
+
{
|
| 9526 |
+
"epoch": 0.16545263766176493,
|
| 9527 |
+
"grad_norm": 0.16018523275852203,
|
| 9528 |
+
"learning_rate": 9.379401338222242e-05,
|
| 9529 |
+
"loss": 2.1092944145202637,
|
| 9530 |
+
"step": 2720
|
| 9531 |
+
},
|
| 9532 |
+
{
|
| 9533 |
+
"epoch": 0.16557429401298682,
|
| 9534 |
+
"grad_norm": 0.13321106135845184,
|
| 9535 |
+
"learning_rate": 9.37847328619693e-05,
|
| 9536 |
+
"loss": 2.0796661376953125,
|
| 9537 |
+
"step": 2722
|
| 9538 |
+
},
|
| 9539 |
+
{
|
| 9540 |
+
"epoch": 0.1656959503642087,
|
| 9541 |
+
"grad_norm": 0.1538192331790924,
|
| 9542 |
+
"learning_rate": 9.377544586763215e-05,
|
| 9543 |
+
"loss": 2.137936592102051,
|
| 9544 |
+
"step": 2724
|
| 9545 |
+
},
|
| 9546 |
+
{
|
| 9547 |
+
"epoch": 0.16581760671543058,
|
| 9548 |
+
"grad_norm": 0.15901167690753937,
|
| 9549 |
+
"learning_rate": 9.376615240058417e-05,
|
| 9550 |
+
"loss": 2.1907033920288086,
|
| 9551 |
+
"step": 2726
|
| 9552 |
+
},
|
| 9553 |
+
{
|
| 9554 |
+
"epoch": 0.16593926306665246,
|
| 9555 |
+
"grad_norm": 0.15559428930282593,
|
| 9556 |
+
"learning_rate": 9.375685246219952e-05,
|
| 9557 |
+
"loss": 1.9804441928863525,
|
| 9558 |
+
"step": 2728
|
| 9559 |
+
},
|
| 9560 |
+
{
|
| 9561 |
+
"epoch": 0.16606091941787435,
|
| 9562 |
+
"grad_norm": 0.17726674675941467,
|
| 9563 |
+
"learning_rate": 9.374754605385328e-05,
|
| 9564 |
+
"loss": 2.154228925704956,
|
| 9565 |
+
"step": 2730
|
| 9566 |
+
},
|
| 9567 |
+
{
|
| 9568 |
+
"epoch": 0.16618257576909626,
|
| 9569 |
+
"grad_norm": 0.1823355108499527,
|
| 9570 |
+
"learning_rate": 9.373823317692154e-05,
|
| 9571 |
+
"loss": 2.1484804153442383,
|
| 9572 |
+
"step": 2732
|
| 9573 |
+
},
|
| 9574 |
+
{
|
| 9575 |
+
"epoch": 0.16630423212031814,
|
| 9576 |
+
"grad_norm": 0.15099388360977173,
|
| 9577 |
+
"learning_rate": 9.372891383278128e-05,
|
| 9578 |
+
"loss": 2.0331571102142334,
|
| 9579 |
+
"step": 2734
|
| 9580 |
+
},
|
| 9581 |
+
{
|
| 9582 |
+
"epoch": 0.16642588847154002,
|
| 9583 |
+
"grad_norm": 0.15392713248729706,
|
| 9584 |
+
"learning_rate": 9.371958802281051e-05,
|
| 9585 |
+
"loss": 2.091447353363037,
|
| 9586 |
+
"step": 2736
|
| 9587 |
+
},
|
| 9588 |
+
{
|
| 9589 |
+
"epoch": 0.1665475448227619,
|
| 9590 |
+
"grad_norm": 0.18031907081604004,
|
| 9591 |
+
"learning_rate": 9.371025574838815e-05,
|
| 9592 |
+
"loss": 2.216172695159912,
|
| 9593 |
+
"step": 2738
|
| 9594 |
+
},
|
| 9595 |
+
{
|
| 9596 |
+
"epoch": 0.1666692011739838,
|
| 9597 |
+
"grad_norm": 0.1446572244167328,
|
| 9598 |
+
"learning_rate": 9.370091701089407e-05,
|
| 9599 |
+
"loss": 2.0451884269714355,
|
| 9600 |
+
"step": 2740
|
| 9601 |
+
},
|
| 9602 |
+
{
|
| 9603 |
+
"epoch": 0.16679085752520567,
|
| 9604 |
+
"grad_norm": 0.15798494219779968,
|
| 9605 |
+
"learning_rate": 9.369157181170913e-05,
|
| 9606 |
+
"loss": 2.068049430847168,
|
| 9607 |
+
"step": 2742
|
| 9608 |
+
},
|
| 9609 |
+
{
|
| 9610 |
+
"epoch": 0.16691251387642755,
|
| 9611 |
+
"grad_norm": 0.14877812564373016,
|
| 9612 |
+
"learning_rate": 9.36822201522151e-05,
|
| 9613 |
+
"loss": 1.9997955560684204,
|
| 9614 |
+
"step": 2744
|
| 9615 |
+
},
|
| 9616 |
+
{
|
| 9617 |
+
"epoch": 0.16703417022764944,
|
| 9618 |
+
"grad_norm": 0.16442742943763733,
|
| 9619 |
+
"learning_rate": 9.367286203379478e-05,
|
| 9620 |
+
"loss": 2.0022788047790527,
|
| 9621 |
+
"step": 2746
|
| 9622 |
+
},
|
| 9623 |
+
{
|
| 9624 |
+
"epoch": 0.16715582657887132,
|
| 9625 |
+
"grad_norm": 0.13488022983074188,
|
| 9626 |
+
"learning_rate": 9.366349745783183e-05,
|
| 9627 |
+
"loss": 1.9913398027420044,
|
| 9628 |
+
"step": 2748
|
| 9629 |
+
},
|
| 9630 |
+
{
|
| 9631 |
+
"epoch": 0.16727748293009323,
|
| 9632 |
+
"grad_norm": 0.16253864765167236,
|
| 9633 |
+
"learning_rate": 9.365412642571095e-05,
|
| 9634 |
+
"loss": 2.063626527786255,
|
| 9635 |
+
"step": 2750
|
| 9636 |
+
},
|
| 9637 |
+
{
|
| 9638 |
+
"epoch": 0.1673991392813151,
|
| 9639 |
+
"grad_norm": 0.17226657271385193,
|
| 9640 |
+
"learning_rate": 9.364474893881771e-05,
|
| 9641 |
+
"loss": 2.0674407482147217,
|
| 9642 |
+
"step": 2752
|
| 9643 |
+
},
|
| 9644 |
+
{
|
| 9645 |
+
"epoch": 0.167520795632537,
|
| 9646 |
+
"grad_norm": 0.16619066894054413,
|
| 9647 |
+
"learning_rate": 9.363536499853872e-05,
|
| 9648 |
+
"loss": 2.016131639480591,
|
| 9649 |
+
"step": 2754
|
| 9650 |
+
},
|
| 9651 |
+
{
|
| 9652 |
+
"epoch": 0.16764245198375888,
|
| 9653 |
+
"grad_norm": 0.1653183251619339,
|
| 9654 |
+
"learning_rate": 9.36259746062615e-05,
|
| 9655 |
+
"loss": 2.067972183227539,
|
| 9656 |
+
"step": 2756
|
| 9657 |
+
},
|
| 9658 |
+
{
|
| 9659 |
+
"epoch": 0.16776410833498076,
|
| 9660 |
+
"grad_norm": 0.174674853682518,
|
| 9661 |
+
"learning_rate": 9.361657776337452e-05,
|
| 9662 |
+
"loss": 2.115912675857544,
|
| 9663 |
+
"step": 2758
|
| 9664 |
+
},
|
| 9665 |
+
{
|
| 9666 |
+
"epoch": 0.16788576468620264,
|
| 9667 |
+
"grad_norm": 0.15653590857982635,
|
| 9668 |
+
"learning_rate": 9.36071744712672e-05,
|
| 9669 |
+
"loss": 2.0367801189422607,
|
| 9670 |
+
"step": 2760
|
| 9671 |
+
},
|
| 9672 |
+
{
|
| 9673 |
+
"epoch": 0.16800742103742453,
|
| 9674 |
+
"grad_norm": 0.15400086343288422,
|
| 9675 |
+
"learning_rate": 9.359776473132996e-05,
|
| 9676 |
+
"loss": 2.0227510929107666,
|
| 9677 |
+
"step": 2762
|
| 9678 |
+
},
|
| 9679 |
+
{
|
| 9680 |
+
"epoch": 0.1681290773886464,
|
| 9681 |
+
"grad_norm": 0.15130622684955597,
|
| 9682 |
+
"learning_rate": 9.35883485449541e-05,
|
| 9683 |
+
"loss": 2.053504228591919,
|
| 9684 |
+
"step": 2764
|
| 9685 |
+
},
|
| 9686 |
+
{
|
| 9687 |
+
"epoch": 0.16825073373986832,
|
| 9688 |
+
"grad_norm": 0.15595117211341858,
|
| 9689 |
+
"learning_rate": 9.357892591353195e-05,
|
| 9690 |
+
"loss": 2.1719632148742676,
|
| 9691 |
+
"step": 2766
|
| 9692 |
+
},
|
| 9693 |
+
{
|
| 9694 |
+
"epoch": 0.1683723900910902,
|
| 9695 |
+
"grad_norm": 0.15297071635723114,
|
| 9696 |
+
"learning_rate": 9.356949683845675e-05,
|
| 9697 |
+
"loss": 2.1700451374053955,
|
| 9698 |
+
"step": 2768
|
| 9699 |
+
},
|
| 9700 |
+
{
|
| 9701 |
+
"epoch": 0.16849404644231208,
|
| 9702 |
+
"grad_norm": 0.16934838891029358,
|
| 9703 |
+
"learning_rate": 9.356006132112268e-05,
|
| 9704 |
+
"loss": 2.0959911346435547,
|
| 9705 |
+
"step": 2770
|
| 9706 |
+
},
|
| 9707 |
+
{
|
| 9708 |
+
"epoch": 0.16861570279353397,
|
| 9709 |
+
"grad_norm": 0.1778026968240738,
|
| 9710 |
+
"learning_rate": 9.355061936292489e-05,
|
| 9711 |
+
"loss": 2.0094456672668457,
|
| 9712 |
+
"step": 2772
|
| 9713 |
+
},
|
| 9714 |
+
{
|
| 9715 |
+
"epoch": 0.16873735914475585,
|
| 9716 |
+
"grad_norm": 0.1801193505525589,
|
| 9717 |
+
"learning_rate": 9.35411709652595e-05,
|
| 9718 |
+
"loss": 2.0303282737731934,
|
| 9719 |
+
"step": 2774
|
| 9720 |
+
},
|
| 9721 |
+
{
|
| 9722 |
+
"epoch": 0.16885901549597773,
|
| 9723 |
+
"grad_norm": 0.14120468497276306,
|
| 9724 |
+
"learning_rate": 9.353171612952357e-05,
|
| 9725 |
+
"loss": 2.0660786628723145,
|
| 9726 |
+
"step": 2776
|
| 9727 |
+
},
|
| 9728 |
+
{
|
| 9729 |
+
"epoch": 0.16898067184719961,
|
| 9730 |
+
"grad_norm": 0.1503477841615677,
|
| 9731 |
+
"learning_rate": 9.35222548571151e-05,
|
| 9732 |
+
"loss": 2.090090036392212,
|
| 9733 |
+
"step": 2778
|
| 9734 |
+
},
|
| 9735 |
+
{
|
| 9736 |
+
"epoch": 0.1691023281984215,
|
| 9737 |
+
"grad_norm": 0.1723472774028778,
|
| 9738 |
+
"learning_rate": 9.351278714943303e-05,
|
| 9739 |
+
"loss": 2.0928685665130615,
|
| 9740 |
+
"step": 2780
|
| 9741 |
+
},
|
| 9742 |
+
{
|
| 9743 |
+
"epoch": 0.1692239845496434,
|
| 9744 |
+
"grad_norm": 0.14953789114952087,
|
| 9745 |
+
"learning_rate": 9.350331300787731e-05,
|
| 9746 |
+
"loss": 2.1203725337982178,
|
| 9747 |
+
"step": 2782
|
| 9748 |
+
},
|
| 9749 |
+
{
|
| 9750 |
+
"epoch": 0.1693456409008653,
|
| 9751 |
+
"grad_norm": 0.17308631539344788,
|
| 9752 |
+
"learning_rate": 9.349383243384877e-05,
|
| 9753 |
+
"loss": 2.094586133956909,
|
| 9754 |
+
"step": 2784
|
| 9755 |
+
},
|
| 9756 |
+
{
|
| 9757 |
+
"epoch": 0.16946729725208717,
|
| 9758 |
+
"grad_norm": 0.17215277254581451,
|
| 9759 |
+
"learning_rate": 9.348434542874925e-05,
|
| 9760 |
+
"loss": 2.1007320880889893,
|
| 9761 |
+
"step": 2786
|
| 9762 |
+
},
|
| 9763 |
+
{
|
| 9764 |
+
"epoch": 0.16958895360330906,
|
| 9765 |
+
"grad_norm": 0.1525467038154602,
|
| 9766 |
+
"learning_rate": 9.347485199398148e-05,
|
| 9767 |
+
"loss": 2.0224854946136475,
|
| 9768 |
+
"step": 2788
|
| 9769 |
+
},
|
| 9770 |
+
{
|
| 9771 |
+
"epoch": 0.16971060995453094,
|
| 9772 |
+
"grad_norm": 0.16187797486782074,
|
| 9773 |
+
"learning_rate": 9.34653521309492e-05,
|
| 9774 |
+
"loss": 2.0039517879486084,
|
| 9775 |
+
"step": 2790
|
| 9776 |
+
},
|
| 9777 |
+
{
|
| 9778 |
+
"epoch": 0.16983226630575282,
|
| 9779 |
+
"grad_norm": 0.14212310314178467,
|
| 9780 |
+
"learning_rate": 9.345584584105707e-05,
|
| 9781 |
+
"loss": 2.1627557277679443,
|
| 9782 |
+
"step": 2792
|
| 9783 |
+
},
|
| 9784 |
+
{
|
| 9785 |
+
"epoch": 0.1699539226569747,
|
| 9786 |
+
"grad_norm": 0.1490509957075119,
|
| 9787 |
+
"learning_rate": 9.34463331257107e-05,
|
| 9788 |
+
"loss": 2.039886951446533,
|
| 9789 |
+
"step": 2794
|
| 9790 |
+
},
|
| 9791 |
+
{
|
| 9792 |
+
"epoch": 0.1700755790081966,
|
| 9793 |
+
"grad_norm": 0.17150302231311798,
|
| 9794 |
+
"learning_rate": 9.343681398631667e-05,
|
| 9795 |
+
"loss": 2.105815887451172,
|
| 9796 |
+
"step": 2796
|
| 9797 |
+
},
|
| 9798 |
+
{
|
| 9799 |
+
"epoch": 0.17019723535941847,
|
| 9800 |
+
"grad_norm": 0.13078537583351135,
|
| 9801 |
+
"learning_rate": 9.34272884242825e-05,
|
| 9802 |
+
"loss": 1.97078537940979,
|
| 9803 |
+
"step": 2798
|
| 9804 |
+
},
|
| 9805 |
+
{
|
| 9806 |
+
"epoch": 0.17031889171064038,
|
| 9807 |
+
"grad_norm": 0.18178807199001312,
|
| 9808 |
+
"learning_rate": 9.341775644101664e-05,
|
| 9809 |
+
"loss": 2.0293374061584473,
|
| 9810 |
+
"step": 2800
|
| 9811 |
+
},
|
| 9812 |
+
{
|
| 9813 |
+
"epoch": 0.17044054806186226,
|
| 9814 |
+
"grad_norm": 0.15262551605701447,
|
| 9815 |
+
"learning_rate": 9.34082180379285e-05,
|
| 9816 |
+
"loss": 2.1245832443237305,
|
| 9817 |
+
"step": 2802
|
| 9818 |
+
},
|
| 9819 |
+
{
|
| 9820 |
+
"epoch": 0.17056220441308415,
|
| 9821 |
+
"grad_norm": 0.16709105670452118,
|
| 9822 |
+
"learning_rate": 9.339867321642846e-05,
|
| 9823 |
+
"loss": 2.112614393234253,
|
| 9824 |
+
"step": 2804
|
| 9825 |
+
},
|
| 9826 |
+
{
|
| 9827 |
+
"epoch": 0.17068386076430603,
|
| 9828 |
+
"grad_norm": 0.16781049966812134,
|
| 9829 |
+
"learning_rate": 9.338912197792782e-05,
|
| 9830 |
+
"loss": 2.154905319213867,
|
| 9831 |
+
"step": 2806
|
| 9832 |
+
},
|
| 9833 |
+
{
|
| 9834 |
+
"epoch": 0.1708055171155279,
|
| 9835 |
+
"grad_norm": 0.1495530605316162,
|
| 9836 |
+
"learning_rate": 9.337956432383885e-05,
|
| 9837 |
+
"loss": 2.087728261947632,
|
| 9838 |
+
"step": 2808
|
| 9839 |
+
},
|
| 9840 |
+
{
|
| 9841 |
+
"epoch": 0.1709271734667498,
|
| 9842 |
+
"grad_norm": 0.17653630673885345,
|
| 9843 |
+
"learning_rate": 9.337000025557476e-05,
|
| 9844 |
+
"loss": 2.086104154586792,
|
| 9845 |
+
"step": 2810
|
| 9846 |
+
},
|
| 9847 |
+
{
|
| 9848 |
+
"epoch": 0.17104882981797168,
|
| 9849 |
+
"grad_norm": 0.14131523668766022,
|
| 9850 |
+
"learning_rate": 9.33604297745497e-05,
|
| 9851 |
+
"loss": 2.07147479057312,
|
| 9852 |
+
"step": 2812
|
| 9853 |
+
},
|
| 9854 |
+
{
|
| 9855 |
+
"epoch": 0.17117048616919356,
|
| 9856 |
+
"grad_norm": 0.15751592814922333,
|
| 9857 |
+
"learning_rate": 9.335085288217881e-05,
|
| 9858 |
+
"loss": 2.062695026397705,
|
| 9859 |
+
"step": 2814
|
| 9860 |
+
},
|
| 9861 |
+
{
|
| 9862 |
+
"epoch": 0.17129214252041547,
|
| 9863 |
+
"grad_norm": 0.15987326204776764,
|
| 9864 |
+
"learning_rate": 9.334126957987811e-05,
|
| 9865 |
+
"loss": 2.136624813079834,
|
| 9866 |
+
"step": 2816
|
| 9867 |
+
},
|
| 9868 |
+
{
|
| 9869 |
+
"epoch": 0.17141379887163735,
|
| 9870 |
+
"grad_norm": 0.15183961391448975,
|
| 9871 |
+
"learning_rate": 9.333167986906462e-05,
|
| 9872 |
+
"loss": 2.145448684692383,
|
| 9873 |
+
"step": 2818
|
| 9874 |
+
},
|
| 9875 |
+
{
|
| 9876 |
+
"epoch": 0.17153545522285923,
|
| 9877 |
+
"grad_norm": 0.17574505507946014,
|
| 9878 |
+
"learning_rate": 9.332208375115628e-05,
|
| 9879 |
+
"loss": 2.0201098918914795,
|
| 9880 |
+
"step": 2820
|
| 9881 |
+
},
|
| 9882 |
+
{
|
| 9883 |
+
"epoch": 0.17165711157408112,
|
| 9884 |
+
"grad_norm": 0.15998318791389465,
|
| 9885 |
+
"learning_rate": 9.3312481227572e-05,
|
| 9886 |
+
"loss": 2.056654691696167,
|
| 9887 |
+
"step": 2822
|
| 9888 |
+
},
|
| 9889 |
+
{
|
| 9890 |
+
"epoch": 0.171778767925303,
|
| 9891 |
+
"grad_norm": 0.1562260538339615,
|
| 9892 |
+
"learning_rate": 9.33028722997316e-05,
|
| 9893 |
+
"loss": 2.1010334491729736,
|
| 9894 |
+
"step": 2824
|
| 9895 |
+
},
|
| 9896 |
+
{
|
| 9897 |
+
"epoch": 0.17190042427652488,
|
| 9898 |
+
"grad_norm": 0.15508662164211273,
|
| 9899 |
+
"learning_rate": 9.329325696905591e-05,
|
| 9900 |
+
"loss": 2.0610907077789307,
|
| 9901 |
+
"step": 2826
|
| 9902 |
+
},
|
| 9903 |
+
{
|
| 9904 |
+
"epoch": 0.17202208062774677,
|
| 9905 |
+
"grad_norm": 0.14239385724067688,
|
| 9906 |
+
"learning_rate": 9.328363523696663e-05,
|
| 9907 |
+
"loss": 1.9806830883026123,
|
| 9908 |
+
"step": 2828
|
| 9909 |
+
},
|
| 9910 |
+
{
|
| 9911 |
+
"epoch": 0.17214373697896865,
|
| 9912 |
+
"grad_norm": 0.18262407183647156,
|
| 9913 |
+
"learning_rate": 9.327400710488648e-05,
|
| 9914 |
+
"loss": 2.1149754524230957,
|
| 9915 |
+
"step": 2830
|
| 9916 |
+
},
|
| 9917 |
+
{
|
| 9918 |
+
"epoch": 0.17226539333019053,
|
| 9919 |
+
"grad_norm": 0.15846283733844757,
|
| 9920 |
+
"learning_rate": 9.326437257423907e-05,
|
| 9921 |
+
"loss": 2.119049549102783,
|
| 9922 |
+
"step": 2832
|
| 9923 |
+
},
|
| 9924 |
+
{
|
| 9925 |
+
"epoch": 0.17238704968141244,
|
| 9926 |
+
"grad_norm": 0.1393856704235077,
|
| 9927 |
+
"learning_rate": 9.325473164644899e-05,
|
| 9928 |
+
"loss": 2.057464599609375,
|
| 9929 |
+
"step": 2834
|
| 9930 |
+
},
|
| 9931 |
+
{
|
| 9932 |
+
"epoch": 0.17250870603263432,
|
| 9933 |
+
"grad_norm": 0.15421925485134125,
|
| 9934 |
+
"learning_rate": 9.324508432294177e-05,
|
| 9935 |
+
"loss": 2.1468605995178223,
|
| 9936 |
+
"step": 2836
|
| 9937 |
+
},
|
| 9938 |
+
{
|
| 9939 |
+
"epoch": 0.1726303623838562,
|
| 9940 |
+
"grad_norm": 0.16766716539859772,
|
| 9941 |
+
"learning_rate": 9.323543060514384e-05,
|
| 9942 |
+
"loss": 2.047592878341675,
|
| 9943 |
+
"step": 2838
|
| 9944 |
+
},
|
| 9945 |
+
{
|
| 9946 |
+
"epoch": 0.1727520187350781,
|
| 9947 |
+
"grad_norm": 0.15131503343582153,
|
| 9948 |
+
"learning_rate": 9.322577049448267e-05,
|
| 9949 |
+
"loss": 2.012986421585083,
|
| 9950 |
+
"step": 2840
|
| 9951 |
+
},
|
| 9952 |
+
{
|
| 9953 |
+
"epoch": 0.17287367508629997,
|
| 9954 |
+
"grad_norm": 0.1688108742237091,
|
| 9955 |
+
"learning_rate": 9.321610399238657e-05,
|
| 9956 |
+
"loss": 2.033419370651245,
|
| 9957 |
+
"step": 2842
|
| 9958 |
+
},
|
| 9959 |
+
{
|
| 9960 |
+
"epoch": 0.17299533143752185,
|
| 9961 |
+
"grad_norm": 0.1771407276391983,
|
| 9962 |
+
"learning_rate": 9.320643110028488e-05,
|
| 9963 |
+
"loss": 2.0646443367004395,
|
| 9964 |
+
"step": 2844
|
| 9965 |
+
},
|
| 9966 |
+
{
|
| 9967 |
+
"epoch": 0.17311698778874374,
|
| 9968 |
+
"grad_norm": 0.15921801328659058,
|
| 9969 |
+
"learning_rate": 9.319675181960784e-05,
|
| 9970 |
+
"loss": 2.093667984008789,
|
| 9971 |
+
"step": 2846
|
| 9972 |
+
},
|
| 9973 |
+
{
|
| 9974 |
+
"epoch": 0.17323864413996562,
|
| 9975 |
+
"grad_norm": 0.1723555475473404,
|
| 9976 |
+
"learning_rate": 9.318706615178665e-05,
|
| 9977 |
+
"loss": 2.175293445587158,
|
| 9978 |
+
"step": 2848
|
| 9979 |
+
},
|
| 9980 |
+
{
|
| 9981 |
+
"epoch": 0.17336030049118753,
|
| 9982 |
+
"grad_norm": 0.14801360666751862,
|
| 9983 |
+
"learning_rate": 9.317737409825343e-05,
|
| 9984 |
+
"loss": 2.0281178951263428,
|
| 9985 |
+
"step": 2850
|
| 9986 |
+
},
|
| 9987 |
+
{
|
| 9988 |
+
"epoch": 0.1734819568424094,
|
| 9989 |
+
"grad_norm": 0.1504800021648407,
|
| 9990 |
+
"learning_rate": 9.316767566044128e-05,
|
| 9991 |
+
"loss": 1.9643665552139282,
|
| 9992 |
+
"step": 2852
|
| 9993 |
+
},
|
| 9994 |
+
{
|
| 9995 |
+
"epoch": 0.1736036131936313,
|
| 9996 |
+
"grad_norm": 0.1575300693511963,
|
| 9997 |
+
"learning_rate": 9.315797083978422e-05,
|
| 9998 |
+
"loss": 2.0389740467071533,
|
| 9999 |
+
"step": 2854
|
| 10000 |
+
},
|
| 10001 |
+
{
|
| 10002 |
+
"epoch": 0.17372526954485318,
|
| 10003 |
+
"grad_norm": 0.147572860121727,
|
| 10004 |
+
"learning_rate": 9.314825963771723e-05,
|
| 10005 |
+
"loss": 2.105109691619873,
|
| 10006 |
+
"step": 2856
|
| 10007 |
+
},
|
| 10008 |
+
{
|
| 10009 |
+
"epoch": 0.17384692589607506,
|
| 10010 |
+
"grad_norm": 0.1558130830526352,
|
| 10011 |
+
"learning_rate": 9.31385420556762e-05,
|
| 10012 |
+
"loss": 2.0779778957366943,
|
| 10013 |
+
"step": 2858
|
| 10014 |
+
},
|
| 10015 |
+
{
|
| 10016 |
+
"epoch": 0.17396858224729694,
|
| 10017 |
+
"grad_norm": 0.1753120869398117,
|
| 10018 |
+
"learning_rate": 9.312881809509802e-05,
|
| 10019 |
+
"loss": 2.12373423576355,
|
| 10020 |
+
"step": 2860
|
| 10021 |
+
},
|
| 10022 |
+
{
|
| 10023 |
+
"epoch": 0.17409023859851883,
|
| 10024 |
+
"grad_norm": 0.16890741884708405,
|
| 10025 |
+
"learning_rate": 9.311908775742049e-05,
|
| 10026 |
+
"loss": 2.09800386428833,
|
| 10027 |
+
"step": 2862
|
| 10028 |
+
},
|
| 10029 |
+
{
|
| 10030 |
+
"epoch": 0.1742118949497407,
|
| 10031 |
+
"grad_norm": 0.13341522216796875,
|
| 10032 |
+
"learning_rate": 9.310935104408232e-05,
|
| 10033 |
+
"loss": 2.0344979763031006,
|
| 10034 |
+
"step": 2864
|
| 10035 |
+
},
|
| 10036 |
+
{
|
| 10037 |
+
"epoch": 0.17433355130096262,
|
| 10038 |
+
"grad_norm": 0.16898418962955475,
|
| 10039 |
+
"learning_rate": 9.309960795652324e-05,
|
| 10040 |
+
"loss": 2.044205665588379,
|
| 10041 |
+
"step": 2866
|
| 10042 |
+
},
|
| 10043 |
+
{
|
| 10044 |
+
"epoch": 0.1744552076521845,
|
| 10045 |
+
"grad_norm": 0.15276406705379486,
|
| 10046 |
+
"learning_rate": 9.308985849618384e-05,
|
| 10047 |
+
"loss": 2.124019145965576,
|
| 10048 |
+
"step": 2868
|
| 10049 |
+
},
|
| 10050 |
+
{
|
| 10051 |
+
"epoch": 0.17457686400340638,
|
| 10052 |
+
"grad_norm": 0.17222371697425842,
|
| 10053 |
+
"learning_rate": 9.30801026645057e-05,
|
| 10054 |
+
"loss": 2.0084471702575684,
|
| 10055 |
+
"step": 2870
|
| 10056 |
+
},
|
| 10057 |
+
{
|
| 10058 |
+
"epoch": 0.17469852035462827,
|
| 10059 |
+
"grad_norm": 0.17148537933826447,
|
| 10060 |
+
"learning_rate": 9.307034046293137e-05,
|
| 10061 |
+
"loss": 2.116849184036255,
|
| 10062 |
+
"step": 2872
|
| 10063 |
+
},
|
| 10064 |
+
{
|
| 10065 |
+
"epoch": 0.17482017670585015,
|
| 10066 |
+
"grad_norm": 0.15251988172531128,
|
| 10067 |
+
"learning_rate": 9.306057189290427e-05,
|
| 10068 |
+
"loss": 2.1294260025024414,
|
| 10069 |
+
"step": 2874
|
| 10070 |
+
},
|
| 10071 |
+
{
|
| 10072 |
+
"epoch": 0.17494183305707203,
|
| 10073 |
+
"grad_norm": 0.18297535181045532,
|
| 10074 |
+
"learning_rate": 9.30507969558688e-05,
|
| 10075 |
+
"loss": 2.0963072776794434,
|
| 10076 |
+
"step": 2876
|
| 10077 |
+
},
|
| 10078 |
+
{
|
| 10079 |
+
"epoch": 0.17506348940829392,
|
| 10080 |
+
"grad_norm": 0.1804608255624771,
|
| 10081 |
+
"learning_rate": 9.30410156532703e-05,
|
| 10082 |
+
"loss": 2.041205883026123,
|
| 10083 |
+
"step": 2878
|
| 10084 |
+
},
|
| 10085 |
+
{
|
| 10086 |
+
"epoch": 0.1751851457595158,
|
| 10087 |
+
"grad_norm": 0.15246586501598358,
|
| 10088 |
+
"learning_rate": 9.303122798655506e-05,
|
| 10089 |
+
"loss": 1.9762080907821655,
|
| 10090 |
+
"step": 2880
|
| 10091 |
+
},
|
| 10092 |
+
{
|
| 10093 |
+
"epoch": 0.17530680211073768,
|
| 10094 |
+
"grad_norm": 0.15697988867759705,
|
| 10095 |
+
"learning_rate": 9.302143395717029e-05,
|
| 10096 |
+
"loss": 2.1045212745666504,
|
| 10097 |
+
"step": 2882
|
| 10098 |
+
},
|
| 10099 |
+
{
|
| 10100 |
+
"epoch": 0.1754284584619596,
|
| 10101 |
+
"grad_norm": 0.15354035794734955,
|
| 10102 |
+
"learning_rate": 9.301163356656414e-05,
|
| 10103 |
+
"loss": 2.06335186958313,
|
| 10104 |
+
"step": 2884
|
| 10105 |
+
},
|
| 10106 |
+
{
|
| 10107 |
+
"epoch": 0.17555011481318147,
|
| 10108 |
+
"grad_norm": 0.14449061453342438,
|
| 10109 |
+
"learning_rate": 9.300182681618576e-05,
|
| 10110 |
+
"loss": 2.0579984188079834,
|
| 10111 |
+
"step": 2886
|
| 10112 |
+
},
|
| 10113 |
+
{
|
| 10114 |
+
"epoch": 0.17567177116440336,
|
| 10115 |
+
"grad_norm": 0.15983065962791443,
|
| 10116 |
+
"learning_rate": 9.299201370748516e-05,
|
| 10117 |
+
"loss": 2.1442713737487793,
|
| 10118 |
+
"step": 2888
|
| 10119 |
+
},
|
| 10120 |
+
{
|
| 10121 |
+
"epoch": 0.17579342751562524,
|
| 10122 |
+
"grad_norm": 0.15116539597511292,
|
| 10123 |
+
"learning_rate": 9.29821942419133e-05,
|
| 10124 |
+
"loss": 2.1216819286346436,
|
| 10125 |
+
"step": 2890
|
| 10126 |
+
},
|
| 10127 |
+
{
|
| 10128 |
+
"epoch": 0.17591508386684712,
|
| 10129 |
+
"grad_norm": 0.15570664405822754,
|
| 10130 |
+
"learning_rate": 9.297236842092214e-05,
|
| 10131 |
+
"loss": 2.0728743076324463,
|
| 10132 |
+
"step": 2892
|
| 10133 |
+
},
|
| 10134 |
+
{
|
| 10135 |
+
"epoch": 0.176036740218069,
|
| 10136 |
+
"grad_norm": 0.15027475357055664,
|
| 10137 |
+
"learning_rate": 9.296253624596453e-05,
|
| 10138 |
+
"loss": 2.0611486434936523,
|
| 10139 |
+
"step": 2894
|
| 10140 |
+
},
|
| 10141 |
+
{
|
| 10142 |
+
"epoch": 0.1761583965692909,
|
| 10143 |
+
"grad_norm": 0.14677296578884125,
|
| 10144 |
+
"learning_rate": 9.295269771849427e-05,
|
| 10145 |
+
"loss": 2.028994083404541,
|
| 10146 |
+
"step": 2896
|
| 10147 |
+
},
|
| 10148 |
+
{
|
| 10149 |
+
"epoch": 0.17628005292051277,
|
| 10150 |
+
"grad_norm": 0.14934836328029633,
|
| 10151 |
+
"learning_rate": 9.29428528399661e-05,
|
| 10152 |
+
"loss": 2.115628242492676,
|
| 10153 |
+
"step": 2898
|
| 10154 |
+
},
|
| 10155 |
+
{
|
| 10156 |
+
"epoch": 0.17640170927173468,
|
| 10157 |
+
"grad_norm": 0.15938854217529297,
|
| 10158 |
+
"learning_rate": 9.293300161183569e-05,
|
| 10159 |
+
"loss": 2.0563950538635254,
|
| 10160 |
+
"step": 2900
|
| 10161 |
+
},
|
| 10162 |
+
{
|
| 10163 |
+
"epoch": 0.17652336562295656,
|
| 10164 |
+
"grad_norm": 0.19593612849712372,
|
| 10165 |
+
"learning_rate": 9.292314403555969e-05,
|
| 10166 |
+
"loss": 2.189702033996582,
|
| 10167 |
+
"step": 2902
|
| 10168 |
+
},
|
| 10169 |
+
{
|
| 10170 |
+
"epoch": 0.17664502197417845,
|
| 10171 |
+
"grad_norm": 0.1451563686132431,
|
| 10172 |
+
"learning_rate": 9.291328011259563e-05,
|
| 10173 |
+
"loss": 2.119995355606079,
|
| 10174 |
+
"step": 2904
|
| 10175 |
+
},
|
| 10176 |
+
{
|
| 10177 |
+
"epoch": 0.17676667832540033,
|
| 10178 |
+
"grad_norm": 0.1752976030111313,
|
| 10179 |
+
"learning_rate": 9.290340984440202e-05,
|
| 10180 |
+
"loss": 2.070091962814331,
|
| 10181 |
+
"step": 2906
|
| 10182 |
+
},
|
| 10183 |
+
{
|
| 10184 |
+
"epoch": 0.1768883346766222,
|
| 10185 |
+
"grad_norm": 0.17230407893657684,
|
| 10186 |
+
"learning_rate": 9.289353323243827e-05,
|
| 10187 |
+
"loss": 2.1801466941833496,
|
| 10188 |
+
"step": 2908
|
| 10189 |
+
},
|
| 10190 |
+
{
|
| 10191 |
+
"epoch": 0.1770099910278441,
|
| 10192 |
+
"grad_norm": 0.17809873819351196,
|
| 10193 |
+
"learning_rate": 9.28836502781648e-05,
|
| 10194 |
+
"loss": 2.1564300060272217,
|
| 10195 |
+
"step": 2910
|
| 10196 |
+
},
|
| 10197 |
+
{
|
| 10198 |
+
"epoch": 0.17713164737906598,
|
| 10199 |
+
"grad_norm": 0.18281328678131104,
|
| 10200 |
+
"learning_rate": 9.287376098304287e-05,
|
| 10201 |
+
"loss": 2.144195556640625,
|
| 10202 |
+
"step": 2912
|
| 10203 |
+
},
|
| 10204 |
+
{
|
| 10205 |
+
"epoch": 0.17725330373028786,
|
| 10206 |
+
"grad_norm": 0.16261836886405945,
|
| 10207 |
+
"learning_rate": 9.286386534853477e-05,
|
| 10208 |
+
"loss": 2.0593984127044678,
|
| 10209 |
+
"step": 2914
|
| 10210 |
+
},
|
| 10211 |
+
{
|
| 10212 |
+
"epoch": 0.17737496008150974,
|
| 10213 |
+
"grad_norm": 0.1840709149837494,
|
| 10214 |
+
"learning_rate": 9.285396337610364e-05,
|
| 10215 |
+
"loss": 2.1947648525238037,
|
| 10216 |
+
"step": 2916
|
| 10217 |
+
},
|
| 10218 |
+
{
|
| 10219 |
+
"epoch": 0.17749661643273165,
|
| 10220 |
+
"grad_norm": 0.1472083479166031,
|
| 10221 |
+
"learning_rate": 9.284405506721364e-05,
|
| 10222 |
+
"loss": 1.9376956224441528,
|
| 10223 |
+
"step": 2918
|
| 10224 |
+
},
|
| 10225 |
+
{
|
| 10226 |
+
"epoch": 0.17761827278395353,
|
| 10227 |
+
"grad_norm": 0.14573213458061218,
|
| 10228 |
+
"learning_rate": 9.283414042332982e-05,
|
| 10229 |
+
"loss": 2.0947344303131104,
|
| 10230 |
+
"step": 2920
|
| 10231 |
+
},
|
| 10232 |
+
{
|
| 10233 |
+
"epoch": 0.17773992913517542,
|
| 10234 |
+
"grad_norm": 0.14972378313541412,
|
| 10235 |
+
"learning_rate": 9.282421944591817e-05,
|
| 10236 |
+
"loss": 2.038442611694336,
|
| 10237 |
+
"step": 2922
|
| 10238 |
+
},
|
| 10239 |
+
{
|
| 10240 |
+
"epoch": 0.1778615854863973,
|
| 10241 |
+
"grad_norm": 0.1530238389968872,
|
| 10242 |
+
"learning_rate": 9.281429213644562e-05,
|
| 10243 |
+
"loss": 2.0633976459503174,
|
| 10244 |
+
"step": 2924
|
| 10245 |
+
},
|
| 10246 |
+
{
|
| 10247 |
+
"epoch": 0.17798324183761918,
|
| 10248 |
+
"grad_norm": 0.1509263664484024,
|
| 10249 |
+
"learning_rate": 9.280435849638004e-05,
|
| 10250 |
+
"loss": 2.0354504585266113,
|
| 10251 |
+
"step": 2926
|
| 10252 |
+
},
|
| 10253 |
+
{
|
| 10254 |
+
"epoch": 0.17810489818884107,
|
| 10255 |
+
"grad_norm": 0.16290120780467987,
|
| 10256 |
+
"learning_rate": 9.279441852719025e-05,
|
| 10257 |
+
"loss": 2.0142221450805664,
|
| 10258 |
+
"step": 2928
|
| 10259 |
+
},
|
| 10260 |
+
{
|
| 10261 |
+
"epoch": 0.17822655454006295,
|
| 10262 |
+
"grad_norm": 0.16288620233535767,
|
| 10263 |
+
"learning_rate": 9.278447223034597e-05,
|
| 10264 |
+
"loss": 1.982060194015503,
|
| 10265 |
+
"step": 2930
|
| 10266 |
+
},
|
| 10267 |
+
{
|
| 10268 |
+
"epoch": 0.17834821089128483,
|
| 10269 |
+
"grad_norm": 0.17249248921871185,
|
| 10270 |
+
"learning_rate": 9.277451960731788e-05,
|
| 10271 |
+
"loss": 2.075594425201416,
|
| 10272 |
+
"step": 2932
|
| 10273 |
+
},
|
| 10274 |
+
{
|
| 10275 |
+
"epoch": 0.17846986724250674,
|
| 10276 |
+
"grad_norm": 0.14352066814899445,
|
| 10277 |
+
"learning_rate": 9.276456065957761e-05,
|
| 10278 |
+
"loss": 2.0962443351745605,
|
| 10279 |
+
"step": 2934
|
| 10280 |
+
},
|
| 10281 |
+
{
|
| 10282 |
+
"epoch": 0.17859152359372862,
|
| 10283 |
+
"grad_norm": 0.14511366188526154,
|
| 10284 |
+
"learning_rate": 9.275459538859769e-05,
|
| 10285 |
+
"loss": 2.0815815925598145,
|
| 10286 |
+
"step": 2936
|
| 10287 |
+
},
|
| 10288 |
+
{
|
| 10289 |
+
"epoch": 0.1787131799449505,
|
| 10290 |
+
"grad_norm": 0.19560548663139343,
|
| 10291 |
+
"learning_rate": 9.27446237958516e-05,
|
| 10292 |
+
"loss": 2.1475958824157715,
|
| 10293 |
+
"step": 2938
|
| 10294 |
+
},
|
| 10295 |
+
{
|
| 10296 |
+
"epoch": 0.1788348362961724,
|
| 10297 |
+
"grad_norm": 0.1742640733718872,
|
| 10298 |
+
"learning_rate": 9.273464588281375e-05,
|
| 10299 |
+
"loss": 2.0598056316375732,
|
| 10300 |
+
"step": 2940
|
| 10301 |
+
},
|
| 10302 |
+
{
|
| 10303 |
+
"epoch": 0.17895649264739427,
|
| 10304 |
+
"grad_norm": 0.1622392237186432,
|
| 10305 |
+
"learning_rate": 9.272466165095953e-05,
|
| 10306 |
+
"loss": 2.0511343479156494,
|
| 10307 |
+
"step": 2942
|
| 10308 |
+
},
|
| 10309 |
+
{
|
| 10310 |
+
"epoch": 0.17907814899861615,
|
| 10311 |
+
"grad_norm": 0.1377253532409668,
|
| 10312 |
+
"learning_rate": 9.271467110176518e-05,
|
| 10313 |
+
"loss": 2.007451295852661,
|
| 10314 |
+
"step": 2944
|
| 10315 |
+
},
|
| 10316 |
+
{
|
| 10317 |
+
"epoch": 0.17919980534983804,
|
| 10318 |
+
"grad_norm": 0.1764858365058899,
|
| 10319 |
+
"learning_rate": 9.270467423670793e-05,
|
| 10320 |
+
"loss": 2.1618711948394775,
|
| 10321 |
+
"step": 2946
|
| 10322 |
+
},
|
| 10323 |
+
{
|
| 10324 |
+
"epoch": 0.17932146170105992,
|
| 10325 |
+
"grad_norm": 0.16716891527175903,
|
| 10326 |
+
"learning_rate": 9.269467105726594e-05,
|
| 10327 |
+
"loss": 2.067059278488159,
|
| 10328 |
+
"step": 2948
|
| 10329 |
+
},
|
| 10330 |
+
{
|
| 10331 |
+
"epoch": 0.17944311805228183,
|
| 10332 |
+
"grad_norm": 0.15834634006023407,
|
| 10333 |
+
"learning_rate": 9.26846615649183e-05,
|
| 10334 |
+
"loss": 2.1560702323913574,
|
| 10335 |
+
"step": 2950
|
| 10336 |
+
},
|
| 10337 |
+
{
|
| 10338 |
+
"epoch": 0.1795647744035037,
|
| 10339 |
+
"grad_norm": 0.1402539163827896,
|
| 10340 |
+
"learning_rate": 9.267464576114502e-05,
|
| 10341 |
+
"loss": 2.1255438327789307,
|
| 10342 |
+
"step": 2952
|
| 10343 |
+
},
|
| 10344 |
+
{
|
| 10345 |
+
"epoch": 0.1796864307547256,
|
| 10346 |
+
"grad_norm": 0.15849460661411285,
|
| 10347 |
+
"learning_rate": 9.266462364742707e-05,
|
| 10348 |
+
"loss": 2.024935245513916,
|
| 10349 |
+
"step": 2954
|
| 10350 |
+
},
|
| 10351 |
+
{
|
| 10352 |
+
"epoch": 0.17980808710594748,
|
| 10353 |
+
"grad_norm": 0.17481809854507446,
|
| 10354 |
+
"learning_rate": 9.265459522524633e-05,
|
| 10355 |
+
"loss": 2.052027463912964,
|
| 10356 |
+
"step": 2956
|
| 10357 |
+
},
|
| 10358 |
+
{
|
| 10359 |
+
"epoch": 0.17992974345716936,
|
| 10360 |
+
"grad_norm": 0.1401110589504242,
|
| 10361 |
+
"learning_rate": 9.264456049608561e-05,
|
| 10362 |
+
"loss": 2.054912567138672,
|
| 10363 |
+
"step": 2958
|
| 10364 |
+
},
|
| 10365 |
+
{
|
| 10366 |
+
"epoch": 0.18005139980839124,
|
| 10367 |
+
"grad_norm": 0.16525866091251373,
|
| 10368 |
+
"learning_rate": 9.263451946142867e-05,
|
| 10369 |
+
"loss": 2.1011197566986084,
|
| 10370 |
+
"step": 2960
|
| 10371 |
+
},
|
| 10372 |
+
{
|
| 10373 |
+
"epoch": 0.18017305615961313,
|
| 10374 |
+
"grad_norm": 0.16090115904808044,
|
| 10375 |
+
"learning_rate": 9.26244721227602e-05,
|
| 10376 |
+
"loss": 2.1933302879333496,
|
| 10377 |
+
"step": 2962
|
| 10378 |
+
},
|
| 10379 |
+
{
|
| 10380 |
+
"epoch": 0.180294712510835,
|
| 10381 |
+
"grad_norm": 0.17080508172512054,
|
| 10382 |
+
"learning_rate": 9.261441848156578e-05,
|
| 10383 |
+
"loss": 2.1148719787597656,
|
| 10384 |
+
"step": 2964
|
| 10385 |
+
},
|
| 10386 |
+
{
|
| 10387 |
+
"epoch": 0.1804163688620569,
|
| 10388 |
+
"grad_norm": 0.16376133263111115,
|
| 10389 |
+
"learning_rate": 9.260435853933202e-05,
|
| 10390 |
+
"loss": 2.076955795288086,
|
| 10391 |
+
"step": 2966
|
| 10392 |
+
},
|
| 10393 |
+
{
|
| 10394 |
+
"epoch": 0.1805380252132788,
|
| 10395 |
+
"grad_norm": 0.16250218451023102,
|
| 10396 |
+
"learning_rate": 9.259429229754634e-05,
|
| 10397 |
+
"loss": 2.0967984199523926,
|
| 10398 |
+
"step": 2968
|
| 10399 |
+
},
|
| 10400 |
+
{
|
| 10401 |
+
"epoch": 0.18065968156450068,
|
| 10402 |
+
"grad_norm": 0.1619189828634262,
|
| 10403 |
+
"learning_rate": 9.25842197576972e-05,
|
| 10404 |
+
"loss": 2.1762402057647705,
|
| 10405 |
+
"step": 2970
|
| 10406 |
+
},
|
| 10407 |
+
{
|
| 10408 |
+
"epoch": 0.18078133791572257,
|
| 10409 |
+
"grad_norm": 0.16992130875587463,
|
| 10410 |
+
"learning_rate": 9.257414092127392e-05,
|
| 10411 |
+
"loss": 2.0973551273345947,
|
| 10412 |
+
"step": 2972
|
| 10413 |
+
},
|
| 10414 |
+
{
|
| 10415 |
+
"epoch": 0.18090299426694445,
|
| 10416 |
+
"grad_norm": 0.16166116297245026,
|
| 10417 |
+
"learning_rate": 9.256405578976677e-05,
|
| 10418 |
+
"loss": 2.0574028491973877,
|
| 10419 |
+
"step": 2974
|
| 10420 |
+
},
|
| 10421 |
+
{
|
| 10422 |
+
"epoch": 0.18102465061816633,
|
| 10423 |
+
"grad_norm": 0.16019807755947113,
|
| 10424 |
+
"learning_rate": 9.255396436466695e-05,
|
| 10425 |
+
"loss": 2.067601442337036,
|
| 10426 |
+
"step": 2976
|
| 10427 |
+
},
|
| 10428 |
+
{
|
| 10429 |
+
"epoch": 0.18114630696938822,
|
| 10430 |
+
"grad_norm": 0.14906394481658936,
|
| 10431 |
+
"learning_rate": 9.254386664746661e-05,
|
| 10432 |
+
"loss": 2.10903000831604,
|
| 10433 |
+
"step": 2978
|
| 10434 |
+
},
|
| 10435 |
+
{
|
| 10436 |
+
"epoch": 0.1812679633206101,
|
| 10437 |
+
"grad_norm": 0.16792547702789307,
|
| 10438 |
+
"learning_rate": 9.253376263965881e-05,
|
| 10439 |
+
"loss": 2.2362258434295654,
|
| 10440 |
+
"step": 2980
|
| 10441 |
+
},
|
| 10442 |
+
{
|
| 10443 |
+
"epoch": 0.18138961967183198,
|
| 10444 |
+
"grad_norm": 0.15041287243366241,
|
| 10445 |
+
"learning_rate": 9.252365234273755e-05,
|
| 10446 |
+
"loss": 1.9772720336914062,
|
| 10447 |
+
"step": 2982
|
| 10448 |
+
},
|
| 10449 |
+
{
|
| 10450 |
+
"epoch": 0.1815112760230539,
|
| 10451 |
+
"grad_norm": 0.150487020611763,
|
| 10452 |
+
"learning_rate": 9.251353575819775e-05,
|
| 10453 |
+
"loss": 2.0626516342163086,
|
| 10454 |
+
"step": 2984
|
| 10455 |
+
},
|
| 10456 |
+
{
|
| 10457 |
+
"epoch": 0.18163293237427577,
|
| 10458 |
+
"grad_norm": 0.13736064732074738,
|
| 10459 |
+
"learning_rate": 9.250341288753526e-05,
|
| 10460 |
+
"loss": 2.1368982791900635,
|
| 10461 |
+
"step": 2986
|
| 10462 |
+
},
|
| 10463 |
+
{
|
| 10464 |
+
"epoch": 0.18175458872549766,
|
| 10465 |
+
"grad_norm": 0.15326203405857086,
|
| 10466 |
+
"learning_rate": 9.249328373224685e-05,
|
| 10467 |
+
"loss": 2.1143743991851807,
|
| 10468 |
+
"step": 2988
|
| 10469 |
+
},
|
| 10470 |
+
{
|
| 10471 |
+
"epoch": 0.18187624507671954,
|
| 10472 |
+
"grad_norm": 0.16214096546173096,
|
| 10473 |
+
"learning_rate": 9.248314829383029e-05,
|
| 10474 |
+
"loss": 2.0291507244110107,
|
| 10475 |
+
"step": 2990
|
| 10476 |
+
},
|
| 10477 |
+
{
|
| 10478 |
+
"epoch": 0.18199790142794142,
|
| 10479 |
+
"grad_norm": 0.14697091281414032,
|
| 10480 |
+
"learning_rate": 9.247300657378417e-05,
|
| 10481 |
+
"loss": 2.1071178913116455,
|
| 10482 |
+
"step": 2992
|
| 10483 |
+
},
|
| 10484 |
+
{
|
| 10485 |
+
"epoch": 0.1821195577791633,
|
| 10486 |
+
"grad_norm": 0.13936279714107513,
|
| 10487 |
+
"learning_rate": 9.246285857360808e-05,
|
| 10488 |
+
"loss": 1.9532145261764526,
|
| 10489 |
+
"step": 2994
|
| 10490 |
+
},
|
| 10491 |
+
{
|
| 10492 |
+
"epoch": 0.1822412141303852,
|
| 10493 |
+
"grad_norm": 0.1796867996454239,
|
| 10494 |
+
"learning_rate": 9.245270429480253e-05,
|
| 10495 |
+
"loss": 2.0024266242980957,
|
| 10496 |
+
"step": 2996
|
| 10497 |
+
},
|
| 10498 |
+
{
|
| 10499 |
+
"epoch": 0.18236287048160707,
|
| 10500 |
+
"grad_norm": 0.1742398887872696,
|
| 10501 |
+
"learning_rate": 9.244254373886892e-05,
|
| 10502 |
+
"loss": 2.104998826980591,
|
| 10503 |
+
"step": 2998
|
| 10504 |
+
},
|
| 10505 |
+
{
|
| 10506 |
+
"epoch": 0.18248452683282895,
|
| 10507 |
+
"grad_norm": 0.17882226407527924,
|
| 10508 |
+
"learning_rate": 9.243237690730964e-05,
|
| 10509 |
+
"loss": 2.12605619430542,
|
| 10510 |
+
"step": 3000
|
| 10511 |
+
},
|
| 10512 |
+
{
|
| 10513 |
+
"epoch": 0.18260618318405086,
|
| 10514 |
+
"grad_norm": 0.17434051632881165,
|
| 10515 |
+
"learning_rate": 9.242220380162793e-05,
|
| 10516 |
+
"loss": 2.12789249420166,
|
| 10517 |
+
"step": 3002
|
| 10518 |
+
},
|
| 10519 |
+
{
|
| 10520 |
+
"epoch": 0.18272783953527275,
|
| 10521 |
+
"grad_norm": 0.16977143287658691,
|
| 10522 |
+
"learning_rate": 9.241202442332806e-05,
|
| 10523 |
+
"loss": 2.068354606628418,
|
| 10524 |
+
"step": 3004
|
| 10525 |
+
},
|
| 10526 |
+
{
|
| 10527 |
+
"epoch": 0.18284949588649463,
|
| 10528 |
+
"grad_norm": 0.14969497919082642,
|
| 10529 |
+
"learning_rate": 9.240183877391514e-05,
|
| 10530 |
+
"loss": 2.0638794898986816,
|
| 10531 |
+
"step": 3006
|
| 10532 |
+
},
|
| 10533 |
+
{
|
| 10534 |
+
"epoch": 0.1829711522377165,
|
| 10535 |
+
"grad_norm": 0.16373783349990845,
|
| 10536 |
+
"learning_rate": 9.239164685489523e-05,
|
| 10537 |
+
"loss": 2.0769171714782715,
|
| 10538 |
+
"step": 3008
|
| 10539 |
+
},
|
| 10540 |
+
{
|
| 10541 |
+
"epoch": 0.1830928085889384,
|
| 10542 |
+
"grad_norm": 0.1705874502658844,
|
| 10543 |
+
"learning_rate": 9.238144866777535e-05,
|
| 10544 |
+
"loss": 2.0815982818603516,
|
| 10545 |
+
"step": 3010
|
| 10546 |
+
},
|
| 10547 |
+
{
|
| 10548 |
+
"epoch": 0.18321446494016028,
|
| 10549 |
+
"grad_norm": 0.1595509946346283,
|
| 10550 |
+
"learning_rate": 9.237124421406337e-05,
|
| 10551 |
+
"loss": 2.051429510116577,
|
| 10552 |
+
"step": 3012
|
| 10553 |
+
},
|
| 10554 |
+
{
|
| 10555 |
+
"epoch": 0.18333612129138216,
|
| 10556 |
+
"grad_norm": 0.160701185464859,
|
| 10557 |
+
"learning_rate": 9.23610334952682e-05,
|
| 10558 |
+
"loss": 2.095954418182373,
|
| 10559 |
+
"step": 3014
|
| 10560 |
+
},
|
| 10561 |
+
{
|
| 10562 |
+
"epoch": 0.18345777764260404,
|
| 10563 |
+
"grad_norm": 0.16506709158420563,
|
| 10564 |
+
"learning_rate": 9.235081651289958e-05,
|
| 10565 |
+
"loss": 2.105992078781128,
|
| 10566 |
+
"step": 3016
|
| 10567 |
+
},
|
| 10568 |
+
{
|
| 10569 |
+
"epoch": 0.18357943399382595,
|
| 10570 |
+
"grad_norm": 0.15706484019756317,
|
| 10571 |
+
"learning_rate": 9.23405932684682e-05,
|
| 10572 |
+
"loss": 2.0181517601013184,
|
| 10573 |
+
"step": 3018
|
| 10574 |
+
},
|
| 10575 |
+
{
|
| 10576 |
+
"epoch": 0.18370109034504783,
|
| 10577 |
+
"grad_norm": 0.1531086415052414,
|
| 10578 |
+
"learning_rate": 9.233036376348573e-05,
|
| 10579 |
+
"loss": 2.029548406600952,
|
| 10580 |
+
"step": 3020
|
| 10581 |
+
},
|
| 10582 |
+
{
|
| 10583 |
+
"epoch": 0.18382274669626972,
|
| 10584 |
+
"grad_norm": 0.15340201556682587,
|
| 10585 |
+
"learning_rate": 9.232012799946468e-05,
|
| 10586 |
+
"loss": 2.1259427070617676,
|
| 10587 |
+
"step": 3022
|
| 10588 |
+
},
|
| 10589 |
+
{
|
| 10590 |
+
"epoch": 0.1839444030474916,
|
| 10591 |
+
"grad_norm": 0.13382305204868317,
|
| 10592 |
+
"learning_rate": 9.230988597791854e-05,
|
| 10593 |
+
"loss": 1.8879046440124512,
|
| 10594 |
+
"step": 3024
|
| 10595 |
+
},
|
| 10596 |
+
{
|
| 10597 |
+
"epoch": 0.18406605939871348,
|
| 10598 |
+
"grad_norm": 0.13477101922035217,
|
| 10599 |
+
"learning_rate": 9.229963770036172e-05,
|
| 10600 |
+
"loss": 2.1079204082489014,
|
| 10601 |
+
"step": 3026
|
| 10602 |
+
},
|
| 10603 |
+
{
|
| 10604 |
+
"epoch": 0.18418771574993537,
|
| 10605 |
+
"grad_norm": 0.1506386399269104,
|
| 10606 |
+
"learning_rate": 9.228938316830952e-05,
|
| 10607 |
+
"loss": 1.9698679447174072,
|
| 10608 |
+
"step": 3028
|
| 10609 |
+
},
|
| 10610 |
+
{
|
| 10611 |
+
"epoch": 0.18430937210115725,
|
| 10612 |
+
"grad_norm": 0.14220163226127625,
|
| 10613 |
+
"learning_rate": 9.227912238327825e-05,
|
| 10614 |
+
"loss": 2.0569026470184326,
|
| 10615 |
+
"step": 3030
|
| 10616 |
+
},
|
| 10617 |
+
{
|
| 10618 |
+
"epoch": 0.18443102845237913,
|
| 10619 |
+
"grad_norm": 0.14630374312400818,
|
| 10620 |
+
"learning_rate": 9.226885534678502e-05,
|
| 10621 |
+
"loss": 2.0405826568603516,
|
| 10622 |
+
"step": 3032
|
| 10623 |
+
},
|
| 10624 |
+
{
|
| 10625 |
+
"epoch": 0.18455268480360104,
|
| 10626 |
+
"grad_norm": 0.16472630202770233,
|
| 10627 |
+
"learning_rate": 9.225858206034797e-05,
|
| 10628 |
+
"loss": 2.150320529937744,
|
| 10629 |
+
"step": 3034
|
| 10630 |
+
},
|
| 10631 |
+
{
|
| 10632 |
+
"epoch": 0.18467434115482292,
|
| 10633 |
+
"grad_norm": 0.13798794150352478,
|
| 10634 |
+
"learning_rate": 9.224830252548611e-05,
|
| 10635 |
+
"loss": 2.000694513320923,
|
| 10636 |
+
"step": 3036
|
| 10637 |
+
},
|
| 10638 |
+
{
|
| 10639 |
+
"epoch": 0.1847959975060448,
|
| 10640 |
+
"grad_norm": 0.15449902415275574,
|
| 10641 |
+
"learning_rate": 9.223801674371941e-05,
|
| 10642 |
+
"loss": 2.155466079711914,
|
| 10643 |
+
"step": 3038
|
| 10644 |
+
},
|
| 10645 |
+
{
|
| 10646 |
+
"epoch": 0.1849176538572667,
|
| 10647 |
+
"grad_norm": 0.1621233969926834,
|
| 10648 |
+
"learning_rate": 9.222772471656874e-05,
|
| 10649 |
+
"loss": 2.0278639793395996,
|
| 10650 |
+
"step": 3040
|
| 10651 |
+
},
|
| 10652 |
+
{
|
| 10653 |
+
"epoch": 0.18503931020848857,
|
| 10654 |
+
"grad_norm": 0.15173837542533875,
|
| 10655 |
+
"learning_rate": 9.221742644555584e-05,
|
| 10656 |
+
"loss": 2.137974262237549,
|
| 10657 |
+
"step": 3042
|
| 10658 |
+
},
|
| 10659 |
+
{
|
| 10660 |
+
"epoch": 0.18516096655971045,
|
| 10661 |
+
"grad_norm": 0.17174281179904938,
|
| 10662 |
+
"learning_rate": 9.220712193220352e-05,
|
| 10663 |
+
"loss": 2.0074028968811035,
|
| 10664 |
+
"step": 3044
|
| 10665 |
+
},
|
| 10666 |
+
{
|
| 10667 |
+
"epoch": 0.18528262291093234,
|
| 10668 |
+
"grad_norm": 0.14388415217399597,
|
| 10669 |
+
"learning_rate": 9.219681117803536e-05,
|
| 10670 |
+
"loss": 2.1762332916259766,
|
| 10671 |
+
"step": 3046
|
| 10672 |
+
},
|
| 10673 |
+
{
|
| 10674 |
+
"epoch": 0.18540427926215422,
|
| 10675 |
+
"grad_norm": 0.15398667752742767,
|
| 10676 |
+
"learning_rate": 9.218649418457594e-05,
|
| 10677 |
+
"loss": 2.098560094833374,
|
| 10678 |
+
"step": 3048
|
| 10679 |
+
},
|
| 10680 |
+
{
|
| 10681 |
+
"epoch": 0.1855259356133761,
|
| 10682 |
+
"grad_norm": 0.15230685472488403,
|
| 10683 |
+
"learning_rate": 9.217617095335075e-05,
|
| 10684 |
+
"loss": 1.8948500156402588,
|
| 10685 |
+
"step": 3050
|
| 10686 |
+
},
|
| 10687 |
+
{
|
| 10688 |
+
"epoch": 0.185647591964598,
|
| 10689 |
+
"grad_norm": 0.1653442680835724,
|
| 10690 |
+
"learning_rate": 9.21658414858862e-05,
|
| 10691 |
+
"loss": 2.0776336193084717,
|
| 10692 |
+
"step": 3052
|
| 10693 |
+
},
|
| 10694 |
+
{
|
| 10695 |
+
"epoch": 0.1857692483158199,
|
| 10696 |
+
"grad_norm": 0.17349126935005188,
|
| 10697 |
+
"learning_rate": 9.215550578370963e-05,
|
| 10698 |
+
"loss": 2.032862663269043,
|
| 10699 |
+
"step": 3054
|
| 10700 |
+
},
|
| 10701 |
+
{
|
| 10702 |
+
"epoch": 0.18589090466704178,
|
| 10703 |
+
"grad_norm": 0.13948071002960205,
|
| 10704 |
+
"learning_rate": 9.21451638483493e-05,
|
| 10705 |
+
"loss": 2.1505844593048096,
|
| 10706 |
+
"step": 3056
|
| 10707 |
+
},
|
| 10708 |
+
{
|
| 10709 |
+
"epoch": 0.18601256101826366,
|
| 10710 |
+
"grad_norm": 0.1593850553035736,
|
| 10711 |
+
"learning_rate": 9.213481568133435e-05,
|
| 10712 |
+
"loss": 2.0260066986083984,
|
| 10713 |
+
"step": 3058
|
| 10714 |
+
},
|
| 10715 |
+
{
|
| 10716 |
+
"epoch": 0.18613421736948554,
|
| 10717 |
+
"grad_norm": 0.17583389580249786,
|
| 10718 |
+
"learning_rate": 9.212446128419492e-05,
|
| 10719 |
+
"loss": 1.9790751934051514,
|
| 10720 |
+
"step": 3060
|
| 10721 |
+
},
|
| 10722 |
+
{
|
| 10723 |
+
"epoch": 0.18625587372070743,
|
| 10724 |
+
"grad_norm": 0.13803540170192719,
|
| 10725 |
+
"learning_rate": 9.2114100658462e-05,
|
| 10726 |
+
"loss": 2.00736141204834,
|
| 10727 |
+
"step": 3062
|
| 10728 |
+
},
|
| 10729 |
+
{
|
| 10730 |
+
"epoch": 0.1863775300719293,
|
| 10731 |
+
"grad_norm": 0.13416406512260437,
|
| 10732 |
+
"learning_rate": 9.210373380566754e-05,
|
| 10733 |
+
"loss": 2.023026943206787,
|
| 10734 |
+
"step": 3064
|
| 10735 |
+
},
|
| 10736 |
+
{
|
| 10737 |
+
"epoch": 0.1864991864231512,
|
| 10738 |
+
"grad_norm": 0.15031670033931732,
|
| 10739 |
+
"learning_rate": 9.20933607273444e-05,
|
| 10740 |
+
"loss": 2.0823071002960205,
|
| 10741 |
+
"step": 3066
|
| 10742 |
+
},
|
| 10743 |
+
{
|
| 10744 |
+
"epoch": 0.1866208427743731,
|
| 10745 |
+
"grad_norm": 0.15524935722351074,
|
| 10746 |
+
"learning_rate": 9.208298142502636e-05,
|
| 10747 |
+
"loss": 2.064546823501587,
|
| 10748 |
+
"step": 3068
|
| 10749 |
+
},
|
| 10750 |
+
{
|
| 10751 |
+
"epoch": 0.18674249912559499,
|
| 10752 |
+
"grad_norm": 0.1553504317998886,
|
| 10753 |
+
"learning_rate": 9.207259590024813e-05,
|
| 10754 |
+
"loss": 2.0962131023406982,
|
| 10755 |
+
"step": 3070
|
| 10756 |
+
},
|
| 10757 |
+
{
|
| 10758 |
+
"epoch": 0.18686415547681687,
|
| 10759 |
+
"grad_norm": 0.1508629471063614,
|
| 10760 |
+
"learning_rate": 9.20622041545453e-05,
|
| 10761 |
+
"loss": 2.135586977005005,
|
| 10762 |
+
"step": 3072
|
| 10763 |
+
},
|
| 10764 |
+
{
|
| 10765 |
+
"epoch": 0.18698581182803875,
|
| 10766 |
+
"grad_norm": 0.15360039472579956,
|
| 10767 |
+
"learning_rate": 9.205180618945444e-05,
|
| 10768 |
+
"loss": 2.1250205039978027,
|
| 10769 |
+
"step": 3074
|
| 10770 |
+
},
|
| 10771 |
+
{
|
| 10772 |
+
"epoch": 0.18710746817926063,
|
| 10773 |
+
"grad_norm": 0.15666425228118896,
|
| 10774 |
+
"learning_rate": 9.204140200651302e-05,
|
| 10775 |
+
"loss": 2.113894462585449,
|
| 10776 |
+
"step": 3076
|
| 10777 |
+
},
|
| 10778 |
+
{
|
| 10779 |
+
"epoch": 0.18722912453048252,
|
| 10780 |
+
"grad_norm": 0.15287920832633972,
|
| 10781 |
+
"learning_rate": 9.203099160725938e-05,
|
| 10782 |
+
"loss": 2.0573551654815674,
|
| 10783 |
+
"step": 3078
|
| 10784 |
+
},
|
| 10785 |
+
{
|
| 10786 |
+
"epoch": 0.1873507808817044,
|
| 10787 |
+
"grad_norm": 0.15016549825668335,
|
| 10788 |
+
"learning_rate": 9.202057499323287e-05,
|
| 10789 |
+
"loss": 2.0701677799224854,
|
| 10790 |
+
"step": 3080
|
| 10791 |
+
},
|
| 10792 |
+
{
|
| 10793 |
+
"epoch": 0.18747243723292628,
|
| 10794 |
+
"grad_norm": 0.15757302939891815,
|
| 10795 |
+
"learning_rate": 9.201015216597366e-05,
|
| 10796 |
+
"loss": 2.091252565383911,
|
| 10797 |
+
"step": 3082
|
| 10798 |
+
},
|
| 10799 |
+
{
|
| 10800 |
+
"epoch": 0.18759409358414816,
|
| 10801 |
+
"grad_norm": 0.1756596565246582,
|
| 10802 |
+
"learning_rate": 9.199972312702291e-05,
|
| 10803 |
+
"loss": 2.11965012550354,
|
| 10804 |
+
"step": 3084
|
| 10805 |
+
},
|
| 10806 |
+
{
|
| 10807 |
+
"epoch": 0.18771574993537007,
|
| 10808 |
+
"grad_norm": 0.17362424731254578,
|
| 10809 |
+
"learning_rate": 9.198928787792269e-05,
|
| 10810 |
+
"loss": 2.0596673488616943,
|
| 10811 |
+
"step": 3086
|
| 10812 |
+
},
|
| 10813 |
+
{
|
| 10814 |
+
"epoch": 0.18783740628659196,
|
| 10815 |
+
"grad_norm": 0.15001235902309418,
|
| 10816 |
+
"learning_rate": 9.197884642021595e-05,
|
| 10817 |
+
"loss": 1.9640834331512451,
|
| 10818 |
+
"step": 3088
|
| 10819 |
+
},
|
| 10820 |
+
{
|
| 10821 |
+
"epoch": 0.18795906263781384,
|
| 10822 |
+
"grad_norm": 0.15887504816055298,
|
| 10823 |
+
"learning_rate": 9.196839875544659e-05,
|
| 10824 |
+
"loss": 2.152367353439331,
|
| 10825 |
+
"step": 3090
|
| 10826 |
+
},
|
| 10827 |
+
{
|
| 10828 |
+
"epoch": 0.18808071898903572,
|
| 10829 |
+
"grad_norm": 0.15407595038414001,
|
| 10830 |
+
"learning_rate": 9.19579448851594e-05,
|
| 10831 |
+
"loss": 2.136662006378174,
|
| 10832 |
+
"step": 3092
|
| 10833 |
+
},
|
| 10834 |
+
{
|
| 10835 |
+
"epoch": 0.1882023753402576,
|
| 10836 |
+
"grad_norm": 0.14389760792255402,
|
| 10837 |
+
"learning_rate": 9.194748481090013e-05,
|
| 10838 |
+
"loss": 2.065310478210449,
|
| 10839 |
+
"step": 3094
|
| 10840 |
+
},
|
| 10841 |
+
{
|
| 10842 |
+
"epoch": 0.1883240316914795,
|
| 10843 |
+
"grad_norm": 0.15747514367103577,
|
| 10844 |
+
"learning_rate": 9.193701853421542e-05,
|
| 10845 |
+
"loss": 2.1043713092803955,
|
| 10846 |
+
"step": 3096
|
| 10847 |
+
},
|
| 10848 |
+
{
|
| 10849 |
+
"epoch": 0.18844568804270137,
|
| 10850 |
+
"grad_norm": 0.16584165394306183,
|
| 10851 |
+
"learning_rate": 9.192654605665283e-05,
|
| 10852 |
+
"loss": 2.1538448333740234,
|
| 10853 |
+
"step": 3098
|
| 10854 |
+
},
|
| 10855 |
+
{
|
| 10856 |
+
"epoch": 0.18856734439392325,
|
| 10857 |
+
"grad_norm": 0.148215651512146,
|
| 10858 |
+
"learning_rate": 9.191606737976083e-05,
|
| 10859 |
+
"loss": 2.2274787425994873,
|
| 10860 |
+
"step": 3100
|
| 10861 |
+
},
|
| 10862 |
+
{
|
| 10863 |
+
"epoch": 0.18868900074514516,
|
| 10864 |
+
"grad_norm": 0.16820217669010162,
|
| 10865 |
+
"learning_rate": 9.190558250508882e-05,
|
| 10866 |
+
"loss": 2.1717071533203125,
|
| 10867 |
+
"step": 3102
|
| 10868 |
+
},
|
| 10869 |
+
{
|
| 10870 |
+
"epoch": 0.18881065709636705,
|
| 10871 |
+
"grad_norm": 0.15032488107681274,
|
| 10872 |
+
"learning_rate": 9.189509143418713e-05,
|
| 10873 |
+
"loss": 2.104412317276001,
|
| 10874 |
+
"step": 3104
|
| 10875 |
+
},
|
| 10876 |
+
{
|
| 10877 |
+
"epoch": 0.18893231344758893,
|
| 10878 |
+
"grad_norm": 0.13770531117916107,
|
| 10879 |
+
"learning_rate": 9.188459416860698e-05,
|
| 10880 |
+
"loss": 2.075728178024292,
|
| 10881 |
+
"step": 3106
|
| 10882 |
+
},
|
| 10883 |
+
{
|
| 10884 |
+
"epoch": 0.1890539697988108,
|
| 10885 |
+
"grad_norm": 0.14491039514541626,
|
| 10886 |
+
"learning_rate": 9.187409070990047e-05,
|
| 10887 |
+
"loss": 2.126725912094116,
|
| 10888 |
+
"step": 3108
|
| 10889 |
+
},
|
| 10890 |
+
{
|
| 10891 |
+
"epoch": 0.1891756261500327,
|
| 10892 |
+
"grad_norm": 0.14701339602470398,
|
| 10893 |
+
"learning_rate": 9.18635810596207e-05,
|
| 10894 |
+
"loss": 2.0664117336273193,
|
| 10895 |
+
"step": 3110
|
| 10896 |
+
},
|
| 10897 |
+
{
|
| 10898 |
+
"epoch": 0.18929728250125458,
|
| 10899 |
+
"grad_norm": 0.18180522322654724,
|
| 10900 |
+
"learning_rate": 9.185306521932166e-05,
|
| 10901 |
+
"loss": 2.1867058277130127,
|
| 10902 |
+
"step": 3112
|
| 10903 |
+
},
|
| 10904 |
+
{
|
| 10905 |
+
"epoch": 0.18941893885247646,
|
| 10906 |
+
"grad_norm": 0.14353527128696442,
|
| 10907 |
+
"learning_rate": 9.18425431905582e-05,
|
| 10908 |
+
"loss": 2.0611016750335693,
|
| 10909 |
+
"step": 3114
|
| 10910 |
+
},
|
| 10911 |
+
{
|
| 10912 |
+
"epoch": 0.18954059520369834,
|
| 10913 |
+
"grad_norm": 0.17463184893131256,
|
| 10914 |
+
"learning_rate": 9.183201497488614e-05,
|
| 10915 |
+
"loss": 2.217416763305664,
|
| 10916 |
+
"step": 3116
|
| 10917 |
+
},
|
| 10918 |
+
{
|
| 10919 |
+
"epoch": 0.18966225155492025,
|
| 10920 |
+
"grad_norm": 0.17025671899318695,
|
| 10921 |
+
"learning_rate": 9.18214805738622e-05,
|
| 10922 |
+
"loss": 2.0727803707122803,
|
| 10923 |
+
"step": 3118
|
| 10924 |
+
},
|
| 10925 |
+
{
|
| 10926 |
+
"epoch": 0.18978390790614214,
|
| 10927 |
+
"grad_norm": 0.16786907613277435,
|
| 10928 |
+
"learning_rate": 9.181093998904402e-05,
|
| 10929 |
+
"loss": 2.06762957572937,
|
| 10930 |
+
"step": 3120
|
| 10931 |
+
},
|
| 10932 |
+
{
|
| 10933 |
+
"epoch": 0.18990556425736402,
|
| 10934 |
+
"grad_norm": 0.1540597826242447,
|
| 10935 |
+
"learning_rate": 9.180039322199015e-05,
|
| 10936 |
+
"loss": 2.0142693519592285,
|
| 10937 |
+
"step": 3122
|
| 10938 |
+
},
|
| 10939 |
+
{
|
| 10940 |
+
"epoch": 0.1900272206085859,
|
| 10941 |
+
"grad_norm": 0.13677237927913666,
|
| 10942 |
+
"learning_rate": 9.178984027426003e-05,
|
| 10943 |
+
"loss": 2.001255512237549,
|
| 10944 |
+
"step": 3124
|
| 10945 |
+
},
|
| 10946 |
+
{
|
| 10947 |
+
"epoch": 0.19014887695980778,
|
| 10948 |
+
"grad_norm": 0.166865736246109,
|
| 10949 |
+
"learning_rate": 9.177928114741408e-05,
|
| 10950 |
+
"loss": 2.0600335597991943,
|
| 10951 |
+
"step": 3126
|
| 10952 |
+
},
|
| 10953 |
+
{
|
| 10954 |
+
"epoch": 0.19027053331102967,
|
| 10955 |
+
"grad_norm": 0.16388322412967682,
|
| 10956 |
+
"learning_rate": 9.176871584301355e-05,
|
| 10957 |
+
"loss": 2.11749005317688,
|
| 10958 |
+
"step": 3128
|
| 10959 |
+
},
|
| 10960 |
+
{
|
| 10961 |
+
"epoch": 0.19039218966225155,
|
| 10962 |
+
"grad_norm": 0.15483668446540833,
|
| 10963 |
+
"learning_rate": 9.175814436262065e-05,
|
| 10964 |
+
"loss": 2.092123031616211,
|
| 10965 |
+
"step": 3130
|
| 10966 |
+
},
|
| 10967 |
+
{
|
| 10968 |
+
"epoch": 0.19051384601347343,
|
| 10969 |
+
"grad_norm": 0.134673073887825,
|
| 10970 |
+
"learning_rate": 9.174756670779849e-05,
|
| 10971 |
+
"loss": 2.0775160789489746,
|
| 10972 |
+
"step": 3132
|
| 10973 |
+
},
|
| 10974 |
+
{
|
| 10975 |
+
"epoch": 0.19063550236469531,
|
| 10976 |
+
"grad_norm": 0.1495617777109146,
|
| 10977 |
+
"learning_rate": 9.173698288011114e-05,
|
| 10978 |
+
"loss": 2.038184642791748,
|
| 10979 |
+
"step": 3134
|
| 10980 |
+
},
|
| 10981 |
+
{
|
| 10982 |
+
"epoch": 0.19075715871591722,
|
| 10983 |
+
"grad_norm": 0.15301427245140076,
|
| 10984 |
+
"learning_rate": 9.172639288112352e-05,
|
| 10985 |
+
"loss": 2.039091110229492,
|
| 10986 |
+
"step": 3136
|
| 10987 |
+
},
|
| 10988 |
+
{
|
| 10989 |
+
"epoch": 0.1908788150671391,
|
| 10990 |
+
"grad_norm": 0.15856795012950897,
|
| 10991 |
+
"learning_rate": 9.171579671240145e-05,
|
| 10992 |
+
"loss": 2.014887809753418,
|
| 10993 |
+
"step": 3138
|
| 10994 |
+
},
|
| 10995 |
+
{
|
| 10996 |
+
"epoch": 0.191000471418361,
|
| 10997 |
+
"grad_norm": 0.14368149638175964,
|
| 10998 |
+
"learning_rate": 9.170519437551176e-05,
|
| 10999 |
+
"loss": 2.0851023197174072,
|
| 11000 |
+
"step": 3140
|
| 11001 |
+
},
|
| 11002 |
+
{
|
| 11003 |
+
"epoch": 0.19112212776958287,
|
| 11004 |
+
"grad_norm": 0.15436768531799316,
|
| 11005 |
+
"learning_rate": 9.169458587202209e-05,
|
| 11006 |
+
"loss": 2.111650228500366,
|
| 11007 |
+
"step": 3142
|
| 11008 |
+
},
|
| 11009 |
+
{
|
| 11010 |
+
"epoch": 0.19124378412080476,
|
| 11011 |
+
"grad_norm": 0.16153018176555634,
|
| 11012 |
+
"learning_rate": 9.168397120350103e-05,
|
| 11013 |
+
"loss": 2.1455702781677246,
|
| 11014 |
+
"step": 3144
|
| 11015 |
+
},
|
| 11016 |
+
{
|
| 11017 |
+
"epoch": 0.19136544047202664,
|
| 11018 |
+
"grad_norm": 0.15582701563835144,
|
| 11019 |
+
"learning_rate": 9.16733503715181e-05,
|
| 11020 |
+
"loss": 2.0974111557006836,
|
| 11021 |
+
"step": 3146
|
| 11022 |
+
},
|
| 11023 |
+
{
|
| 11024 |
+
"epoch": 0.19148709682324852,
|
| 11025 |
+
"grad_norm": 0.1463816910982132,
|
| 11026 |
+
"learning_rate": 9.16627233776437e-05,
|
| 11027 |
+
"loss": 2.1310253143310547,
|
| 11028 |
+
"step": 3148
|
| 11029 |
+
},
|
| 11030 |
+
{
|
| 11031 |
+
"epoch": 0.1916087531744704,
|
| 11032 |
+
"grad_norm": 0.14270775020122528,
|
| 11033 |
+
"learning_rate": 9.165209022344916e-05,
|
| 11034 |
+
"loss": 1.9228202104568481,
|
| 11035 |
+
"step": 3150
|
| 11036 |
+
},
|
| 11037 |
+
{
|
| 11038 |
+
"epoch": 0.1917304095256923,
|
| 11039 |
+
"grad_norm": 0.15709778666496277,
|
| 11040 |
+
"learning_rate": 9.164145091050671e-05,
|
| 11041 |
+
"loss": 2.1429405212402344,
|
| 11042 |
+
"step": 3152
|
| 11043 |
+
},
|
| 11044 |
+
{
|
| 11045 |
+
"epoch": 0.1918520658769142,
|
| 11046 |
+
"grad_norm": 0.1763908714056015,
|
| 11047 |
+
"learning_rate": 9.163080544038952e-05,
|
| 11048 |
+
"loss": 2.1017160415649414,
|
| 11049 |
+
"step": 3154
|
| 11050 |
+
},
|
| 11051 |
+
{
|
| 11052 |
+
"epoch": 0.19197372222813608,
|
| 11053 |
+
"grad_norm": 0.13346631824970245,
|
| 11054 |
+
"learning_rate": 9.162015381467163e-05,
|
| 11055 |
+
"loss": 2.219287633895874,
|
| 11056 |
+
"step": 3156
|
| 11057 |
+
},
|
| 11058 |
+
{
|
| 11059 |
+
"epoch": 0.19209537857935796,
|
| 11060 |
+
"grad_norm": 0.14444778859615326,
|
| 11061 |
+
"learning_rate": 9.160949603492799e-05,
|
| 11062 |
+
"loss": 2.1195621490478516,
|
| 11063 |
+
"step": 3158
|
| 11064 |
+
},
|
| 11065 |
+
{
|
| 11066 |
+
"epoch": 0.19221703493057984,
|
| 11067 |
+
"grad_norm": 0.15052486956119537,
|
| 11068 |
+
"learning_rate": 9.159883210273451e-05,
|
| 11069 |
+
"loss": 2.0821008682250977,
|
| 11070 |
+
"step": 3160
|
| 11071 |
+
},
|
| 11072 |
+
{
|
| 11073 |
+
"epoch": 0.19233869128180173,
|
| 11074 |
+
"grad_norm": 0.16396041214466095,
|
| 11075 |
+
"learning_rate": 9.158816201966795e-05,
|
| 11076 |
+
"loss": 2.0055370330810547,
|
| 11077 |
+
"step": 3162
|
| 11078 |
+
},
|
| 11079 |
+
{
|
| 11080 |
+
"epoch": 0.1924603476330236,
|
| 11081 |
+
"grad_norm": 0.1584128588438034,
|
| 11082 |
+
"learning_rate": 9.157748578730603e-05,
|
| 11083 |
+
"loss": 2.053201913833618,
|
| 11084 |
+
"step": 3164
|
| 11085 |
+
},
|
| 11086 |
+
{
|
| 11087 |
+
"epoch": 0.1925820039842455,
|
| 11088 |
+
"grad_norm": 0.14122804999351501,
|
| 11089 |
+
"learning_rate": 9.156680340722734e-05,
|
| 11090 |
+
"loss": 2.056497812271118,
|
| 11091 |
+
"step": 3166
|
| 11092 |
+
},
|
| 11093 |
+
{
|
| 11094 |
+
"epoch": 0.19270366033546737,
|
| 11095 |
+
"grad_norm": 0.14394590258598328,
|
| 11096 |
+
"learning_rate": 9.15561148810114e-05,
|
| 11097 |
+
"loss": 2.0755577087402344,
|
| 11098 |
+
"step": 3168
|
| 11099 |
+
},
|
| 11100 |
+
{
|
| 11101 |
+
"epoch": 0.19282531668668929,
|
| 11102 |
+
"grad_norm": 0.1662755161523819,
|
| 11103 |
+
"learning_rate": 9.154542021023863e-05,
|
| 11104 |
+
"loss": 2.118281602859497,
|
| 11105 |
+
"step": 3170
|
| 11106 |
+
},
|
| 11107 |
+
{
|
| 11108 |
+
"epoch": 0.19294697303791117,
|
| 11109 |
+
"grad_norm": 0.15037736296653748,
|
| 11110 |
+
"learning_rate": 9.153471939649037e-05,
|
| 11111 |
+
"loss": 2.1725661754608154,
|
| 11112 |
+
"step": 3172
|
| 11113 |
+
},
|
| 11114 |
+
{
|
| 11115 |
+
"epoch": 0.19306862938913305,
|
| 11116 |
+
"grad_norm": 0.14291289448738098,
|
| 11117 |
+
"learning_rate": 9.152401244134885e-05,
|
| 11118 |
+
"loss": 2.0685431957244873,
|
| 11119 |
+
"step": 3174
|
| 11120 |
+
},
|
| 11121 |
+
{
|
| 11122 |
+
"epoch": 0.19319028574035493,
|
| 11123 |
+
"grad_norm": 0.15150010585784912,
|
| 11124 |
+
"learning_rate": 9.15132993463972e-05,
|
| 11125 |
+
"loss": 2.0273451805114746,
|
| 11126 |
+
"step": 3176
|
| 11127 |
+
},
|
| 11128 |
+
{
|
| 11129 |
+
"epoch": 0.19331194209157682,
|
| 11130 |
+
"grad_norm": 0.15501414239406586,
|
| 11131 |
+
"learning_rate": 9.150258011321953e-05,
|
| 11132 |
+
"loss": 2.107512950897217,
|
| 11133 |
+
"step": 3178
|
| 11134 |
+
},
|
| 11135 |
+
{
|
| 11136 |
+
"epoch": 0.1934335984427987,
|
| 11137 |
+
"grad_norm": 0.1513587087392807,
|
| 11138 |
+
"learning_rate": 9.149185474340077e-05,
|
| 11139 |
+
"loss": 1.9522123336791992,
|
| 11140 |
+
"step": 3180
|
| 11141 |
+
},
|
| 11142 |
+
{
|
| 11143 |
+
"epoch": 0.19355525479402058,
|
| 11144 |
+
"grad_norm": 0.16692040860652924,
|
| 11145 |
+
"learning_rate": 9.148112323852678e-05,
|
| 11146 |
+
"loss": 2.0802178382873535,
|
| 11147 |
+
"step": 3182
|
| 11148 |
+
},
|
| 11149 |
+
{
|
| 11150 |
+
"epoch": 0.19367691114524246,
|
| 11151 |
+
"grad_norm": 0.1589505672454834,
|
| 11152 |
+
"learning_rate": 9.147038560018435e-05,
|
| 11153 |
+
"loss": 2.03009033203125,
|
| 11154 |
+
"step": 3184
|
| 11155 |
+
},
|
| 11156 |
+
{
|
| 11157 |
+
"epoch": 0.19379856749646437,
|
| 11158 |
+
"grad_norm": 0.17276263236999512,
|
| 11159 |
+
"learning_rate": 9.145964182996119e-05,
|
| 11160 |
+
"loss": 2.0778746604919434,
|
| 11161 |
+
"step": 3186
|
| 11162 |
+
},
|
| 11163 |
+
{
|
| 11164 |
+
"epoch": 0.19392022384768626,
|
| 11165 |
+
"grad_norm": 0.16458265483379364,
|
| 11166 |
+
"learning_rate": 9.144889192944584e-05,
|
| 11167 |
+
"loss": 2.0909175872802734,
|
| 11168 |
+
"step": 3188
|
| 11169 |
+
},
|
| 11170 |
+
{
|
| 11171 |
+
"epoch": 0.19404188019890814,
|
| 11172 |
+
"grad_norm": 0.15469470620155334,
|
| 11173 |
+
"learning_rate": 9.143813590022784e-05,
|
| 11174 |
+
"loss": 2.0510611534118652,
|
| 11175 |
+
"step": 3190
|
| 11176 |
+
},
|
| 11177 |
+
{
|
| 11178 |
+
"epoch": 0.19416353655013002,
|
| 11179 |
+
"grad_norm": 0.1618652492761612,
|
| 11180 |
+
"learning_rate": 9.142737374389758e-05,
|
| 11181 |
+
"loss": 2.070446491241455,
|
| 11182 |
+
"step": 3192
|
| 11183 |
+
},
|
| 11184 |
+
{
|
| 11185 |
+
"epoch": 0.1942851929013519,
|
| 11186 |
+
"grad_norm": 0.16551099717617035,
|
| 11187 |
+
"learning_rate": 9.141660546204638e-05,
|
| 11188 |
+
"loss": 2.1122894287109375,
|
| 11189 |
+
"step": 3194
|
| 11190 |
+
},
|
| 11191 |
+
{
|
| 11192 |
+
"epoch": 0.1944068492525738,
|
| 11193 |
+
"grad_norm": 0.1574510633945465,
|
| 11194 |
+
"learning_rate": 9.140583105626643e-05,
|
| 11195 |
+
"loss": 2.150071144104004,
|
| 11196 |
+
"step": 3196
|
| 11197 |
+
},
|
| 11198 |
+
{
|
| 11199 |
+
"epoch": 0.19452850560379567,
|
| 11200 |
+
"grad_norm": 0.16358041763305664,
|
| 11201 |
+
"learning_rate": 9.139505052815089e-05,
|
| 11202 |
+
"loss": 2.109858274459839,
|
| 11203 |
+
"step": 3198
|
| 11204 |
+
},
|
| 11205 |
+
{
|
| 11206 |
+
"epoch": 0.19465016195501755,
|
| 11207 |
+
"grad_norm": 0.15776099264621735,
|
| 11208 |
+
"learning_rate": 9.138426387929375e-05,
|
| 11209 |
+
"loss": 2.066993236541748,
|
| 11210 |
+
"step": 3200
|
| 11211 |
+
},
|
| 11212 |
+
{
|
| 11213 |
+
"epoch": 0.19477181830623946,
|
| 11214 |
+
"grad_norm": 0.14474229514598846,
|
| 11215 |
+
"learning_rate": 9.137347111128997e-05,
|
| 11216 |
+
"loss": 2.044766426086426,
|
| 11217 |
+
"step": 3202
|
| 11218 |
+
},
|
| 11219 |
+
{
|
| 11220 |
+
"epoch": 0.19489347465746135,
|
| 11221 |
+
"grad_norm": 0.1449556052684784,
|
| 11222 |
+
"learning_rate": 9.136267222573537e-05,
|
| 11223 |
+
"loss": 2.1203954219818115,
|
| 11224 |
+
"step": 3204
|
| 11225 |
+
},
|
| 11226 |
+
{
|
| 11227 |
+
"epoch": 0.19501513100868323,
|
| 11228 |
+
"grad_norm": 0.14622889459133148,
|
| 11229 |
+
"learning_rate": 9.13518672242267e-05,
|
| 11230 |
+
"loss": 2.006472587585449,
|
| 11231 |
+
"step": 3206
|
| 11232 |
+
},
|
| 11233 |
+
{
|
| 11234 |
+
"epoch": 0.1951367873599051,
|
| 11235 |
+
"grad_norm": 0.17214973270893097,
|
| 11236 |
+
"learning_rate": 9.134105610836161e-05,
|
| 11237 |
+
"loss": 2.1405484676361084,
|
| 11238 |
+
"step": 3208
|
| 11239 |
+
},
|
| 11240 |
+
{
|
| 11241 |
+
"epoch": 0.195258443711127,
|
| 11242 |
+
"grad_norm": 0.17065711319446564,
|
| 11243 |
+
"learning_rate": 9.133023887973864e-05,
|
| 11244 |
+
"loss": 2.106391668319702,
|
| 11245 |
+
"step": 3210
|
| 11246 |
+
},
|
| 11247 |
+
{
|
| 11248 |
+
"epoch": 0.19538010006234888,
|
| 11249 |
+
"grad_norm": 0.13077431917190552,
|
| 11250 |
+
"learning_rate": 9.131941553995725e-05,
|
| 11251 |
+
"loss": 2.0907785892486572,
|
| 11252 |
+
"step": 3212
|
| 11253 |
+
},
|
| 11254 |
+
{
|
| 11255 |
+
"epoch": 0.19550175641357076,
|
| 11256 |
+
"grad_norm": 0.1568395495414734,
|
| 11257 |
+
"learning_rate": 9.130858609061778e-05,
|
| 11258 |
+
"loss": 2.091794490814209,
|
| 11259 |
+
"step": 3214
|
| 11260 |
+
},
|
| 11261 |
+
{
|
| 11262 |
+
"epoch": 0.19562341276479264,
|
| 11263 |
+
"grad_norm": 0.1786198616027832,
|
| 11264 |
+
"learning_rate": 9.129775053332152e-05,
|
| 11265 |
+
"loss": 2.122870922088623,
|
| 11266 |
+
"step": 3216
|
| 11267 |
+
},
|
| 11268 |
+
{
|
| 11269 |
+
"epoch": 0.19574506911601453,
|
| 11270 |
+
"grad_norm": 0.16783760488033295,
|
| 11271 |
+
"learning_rate": 9.12869088696706e-05,
|
| 11272 |
+
"loss": 1.9935369491577148,
|
| 11273 |
+
"step": 3218
|
| 11274 |
+
},
|
| 11275 |
+
{
|
| 11276 |
+
"epoch": 0.19586672546723644,
|
| 11277 |
+
"grad_norm": 0.1486167311668396,
|
| 11278 |
+
"learning_rate": 9.127606110126811e-05,
|
| 11279 |
+
"loss": 2.128584146499634,
|
| 11280 |
+
"step": 3220
|
| 11281 |
+
},
|
| 11282 |
+
{
|
| 11283 |
+
"epoch": 0.19598838181845832,
|
| 11284 |
+
"grad_norm": 0.1393718719482422,
|
| 11285 |
+
"learning_rate": 9.1265207229718e-05,
|
| 11286 |
+
"loss": 2.125915050506592,
|
| 11287 |
+
"step": 3222
|
| 11288 |
+
},
|
| 11289 |
+
{
|
| 11290 |
+
"epoch": 0.1961100381696802,
|
| 11291 |
+
"grad_norm": 0.14022910594940186,
|
| 11292 |
+
"learning_rate": 9.125434725662518e-05,
|
| 11293 |
+
"loss": 1.8192448616027832,
|
| 11294 |
+
"step": 3224
|
| 11295 |
+
},
|
| 11296 |
+
{
|
| 11297 |
+
"epoch": 0.19623169452090208,
|
| 11298 |
+
"grad_norm": 0.1462293118238449,
|
| 11299 |
+
"learning_rate": 9.124348118359539e-05,
|
| 11300 |
+
"loss": 2.0800962448120117,
|
| 11301 |
+
"step": 3226
|
| 11302 |
+
},
|
| 11303 |
+
{
|
| 11304 |
+
"epoch": 0.19635335087212397,
|
| 11305 |
+
"grad_norm": 0.17092347145080566,
|
| 11306 |
+
"learning_rate": 9.123260901223532e-05,
|
| 11307 |
+
"loss": 2.148357391357422,
|
| 11308 |
+
"step": 3228
|
| 11309 |
+
},
|
| 11310 |
+
{
|
| 11311 |
+
"epoch": 0.19647500722334585,
|
| 11312 |
+
"grad_norm": 0.16465547680854797,
|
| 11313 |
+
"learning_rate": 9.122173074415254e-05,
|
| 11314 |
+
"loss": 2.096529483795166,
|
| 11315 |
+
"step": 3230
|
| 11316 |
+
},
|
| 11317 |
+
{
|
| 11318 |
+
"epoch": 0.19659666357456773,
|
| 11319 |
+
"grad_norm": 0.1533774584531784,
|
| 11320 |
+
"learning_rate": 9.121084638095552e-05,
|
| 11321 |
+
"loss": 2.1384902000427246,
|
| 11322 |
+
"step": 3232
|
| 11323 |
+
},
|
| 11324 |
+
{
|
| 11325 |
+
"epoch": 0.19671831992578961,
|
| 11326 |
+
"grad_norm": 0.14889279007911682,
|
| 11327 |
+
"learning_rate": 9.119995592425366e-05,
|
| 11328 |
+
"loss": 2.116018295288086,
|
| 11329 |
+
"step": 3234
|
| 11330 |
+
},
|
| 11331 |
+
{
|
| 11332 |
+
"epoch": 0.19683997627701152,
|
| 11333 |
+
"grad_norm": 0.16097258031368256,
|
| 11334 |
+
"learning_rate": 9.118905937565722e-05,
|
| 11335 |
+
"loss": 2.033710479736328,
|
| 11336 |
+
"step": 3236
|
| 11337 |
+
},
|
| 11338 |
+
{
|
| 11339 |
+
"epoch": 0.1969616326282334,
|
| 11340 |
+
"grad_norm": 0.16443996131420135,
|
| 11341 |
+
"learning_rate": 9.11781567367774e-05,
|
| 11342 |
+
"loss": 2.04190731048584,
|
| 11343 |
+
"step": 3238
|
| 11344 |
+
},
|
| 11345 |
+
{
|
| 11346 |
+
"epoch": 0.1970832889794553,
|
| 11347 |
+
"grad_norm": 0.147502139210701,
|
| 11348 |
+
"learning_rate": 9.116724800922629e-05,
|
| 11349 |
+
"loss": 2.0523979663848877,
|
| 11350 |
+
"step": 3240
|
| 11351 |
+
},
|
| 11352 |
+
{
|
| 11353 |
+
"epoch": 0.19720494533067717,
|
| 11354 |
+
"grad_norm": 0.14281202852725983,
|
| 11355 |
+
"learning_rate": 9.115633319461686e-05,
|
| 11356 |
+
"loss": 2.0282785892486572,
|
| 11357 |
+
"step": 3242
|
| 11358 |
+
},
|
| 11359 |
+
{
|
| 11360 |
+
"epoch": 0.19732660168189906,
|
| 11361 |
+
"grad_norm": 0.1433916836977005,
|
| 11362 |
+
"learning_rate": 9.114541229456297e-05,
|
| 11363 |
+
"loss": 2.0367181301116943,
|
| 11364 |
+
"step": 3244
|
| 11365 |
+
},
|
| 11366 |
+
{
|
| 11367 |
+
"epoch": 0.19744825803312094,
|
| 11368 |
+
"grad_norm": 0.18052838742733002,
|
| 11369 |
+
"learning_rate": 9.113448531067945e-05,
|
| 11370 |
+
"loss": 2.0667483806610107,
|
| 11371 |
+
"step": 3246
|
| 11372 |
+
},
|
| 11373 |
+
{
|
| 11374 |
+
"epoch": 0.19756991438434282,
|
| 11375 |
+
"grad_norm": 0.14891117811203003,
|
| 11376 |
+
"learning_rate": 9.112355224458193e-05,
|
| 11377 |
+
"loss": 2.021528959274292,
|
| 11378 |
+
"step": 3248
|
| 11379 |
+
},
|
| 11380 |
+
{
|
| 11381 |
+
"epoch": 0.1976915707355647,
|
| 11382 |
+
"grad_norm": 0.14517369866371155,
|
| 11383 |
+
"learning_rate": 9.111261309788704e-05,
|
| 11384 |
+
"loss": 2.0889880657196045,
|
| 11385 |
+
"step": 3250
|
| 11386 |
+
},
|
| 11387 |
+
{
|
| 11388 |
+
"epoch": 0.19781322708678659,
|
| 11389 |
+
"grad_norm": 0.1679687201976776,
|
| 11390 |
+
"learning_rate": 9.110166787221224e-05,
|
| 11391 |
+
"loss": 2.1734111309051514,
|
| 11392 |
+
"step": 3252
|
| 11393 |
+
},
|
| 11394 |
+
{
|
| 11395 |
+
"epoch": 0.1979348834380085,
|
| 11396 |
+
"grad_norm": 0.16331201791763306,
|
| 11397 |
+
"learning_rate": 9.109071656917589e-05,
|
| 11398 |
+
"loss": 2.076995849609375,
|
| 11399 |
+
"step": 3254
|
| 11400 |
+
},
|
| 11401 |
+
{
|
| 11402 |
+
"epoch": 0.19805653978923038,
|
| 11403 |
+
"grad_norm": 0.1454167515039444,
|
| 11404 |
+
"learning_rate": 9.10797591903973e-05,
|
| 11405 |
+
"loss": 2.0727949142456055,
|
| 11406 |
+
"step": 3256
|
| 11407 |
+
},
|
| 11408 |
+
{
|
| 11409 |
+
"epoch": 0.19817819614045226,
|
| 11410 |
+
"grad_norm": 0.1443515419960022,
|
| 11411 |
+
"learning_rate": 9.106879573749662e-05,
|
| 11412 |
+
"loss": 2.153104305267334,
|
| 11413 |
+
"step": 3258
|
| 11414 |
+
},
|
| 11415 |
+
{
|
| 11416 |
+
"epoch": 0.19829985249167414,
|
| 11417 |
+
"grad_norm": 0.14538659155368805,
|
| 11418 |
+
"learning_rate": 9.105782621209495e-05,
|
| 11419 |
+
"loss": 2.053230047225952,
|
| 11420 |
+
"step": 3260
|
| 11421 |
+
},
|
| 11422 |
+
{
|
| 11423 |
+
"epoch": 0.19842150884289603,
|
| 11424 |
+
"grad_norm": 0.15893131494522095,
|
| 11425 |
+
"learning_rate": 9.104685061581426e-05,
|
| 11426 |
+
"loss": 2.134974241256714,
|
| 11427 |
+
"step": 3262
|
| 11428 |
+
},
|
| 11429 |
+
{
|
| 11430 |
+
"epoch": 0.1985431651941179,
|
| 11431 |
+
"grad_norm": 0.16250385344028473,
|
| 11432 |
+
"learning_rate": 9.10358689502774e-05,
|
| 11433 |
+
"loss": 1.9961031675338745,
|
| 11434 |
+
"step": 3264
|
| 11435 |
+
},
|
| 11436 |
+
{
|
| 11437 |
+
"epoch": 0.1986648215453398,
|
| 11438 |
+
"grad_norm": 0.14150312542915344,
|
| 11439 |
+
"learning_rate": 9.102488121710814e-05,
|
| 11440 |
+
"loss": 2.127962827682495,
|
| 11441 |
+
"step": 3266
|
| 11442 |
+
},
|
| 11443 |
+
{
|
| 11444 |
+
"epoch": 0.19878647789656168,
|
| 11445 |
+
"grad_norm": 0.18551573157310486,
|
| 11446 |
+
"learning_rate": 9.101388741793115e-05,
|
| 11447 |
+
"loss": 2.1558353900909424,
|
| 11448 |
+
"step": 3268
|
| 11449 |
+
},
|
| 11450 |
+
{
|
| 11451 |
+
"epoch": 0.19890813424778359,
|
| 11452 |
+
"grad_norm": 0.14207307994365692,
|
| 11453 |
+
"learning_rate": 9.1002887554372e-05,
|
| 11454 |
+
"loss": 2.0433905124664307,
|
| 11455 |
+
"step": 3270
|
| 11456 |
+
},
|
| 11457 |
+
{
|
| 11458 |
+
"epoch": 0.19902979059900547,
|
| 11459 |
+
"grad_norm": 0.15967510640621185,
|
| 11460 |
+
"learning_rate": 9.099188162805715e-05,
|
| 11461 |
+
"loss": 2.108372688293457,
|
| 11462 |
+
"step": 3272
|
| 11463 |
+
},
|
| 11464 |
+
{
|
| 11465 |
+
"epoch": 0.19915144695022735,
|
| 11466 |
+
"grad_norm": 0.1599137932062149,
|
| 11467 |
+
"learning_rate": 9.098086964061394e-05,
|
| 11468 |
+
"loss": 2.1619842052459717,
|
| 11469 |
+
"step": 3274
|
| 11470 |
+
},
|
| 11471 |
+
{
|
| 11472 |
+
"epoch": 0.19927310330144923,
|
| 11473 |
+
"grad_norm": 0.12100580334663391,
|
| 11474 |
+
"learning_rate": 9.096985159367064e-05,
|
| 11475 |
+
"loss": 2.0012800693511963,
|
| 11476 |
+
"step": 3276
|
| 11477 |
+
},
|
| 11478 |
+
{
|
| 11479 |
+
"epoch": 0.19939475965267112,
|
| 11480 |
+
"grad_norm": 0.15873000025749207,
|
| 11481 |
+
"learning_rate": 9.095882748885636e-05,
|
| 11482 |
+
"loss": 2.0063982009887695,
|
| 11483 |
+
"step": 3278
|
| 11484 |
+
},
|
| 11485 |
+
{
|
| 11486 |
+
"epoch": 0.199516416003893,
|
| 11487 |
+
"grad_norm": 0.1408204883337021,
|
| 11488 |
+
"learning_rate": 9.094779732780119e-05,
|
| 11489 |
+
"loss": 2.082160711288452,
|
| 11490 |
+
"step": 3280
|
| 11491 |
+
},
|
| 11492 |
+
{
|
| 11493 |
+
"epoch": 0.19963807235511488,
|
| 11494 |
+
"grad_norm": 0.14888697862625122,
|
| 11495 |
+
"learning_rate": 9.093676111213603e-05,
|
| 11496 |
+
"loss": 2.1292858123779297,
|
| 11497 |
+
"step": 3282
|
| 11498 |
+
},
|
| 11499 |
+
{
|
| 11500 |
+
"epoch": 0.19975972870633676,
|
| 11501 |
+
"grad_norm": 0.1466188132762909,
|
| 11502 |
+
"learning_rate": 9.092571884349273e-05,
|
| 11503 |
+
"loss": 2.0612964630126953,
|
| 11504 |
+
"step": 3284
|
| 11505 |
+
},
|
| 11506 |
+
{
|
| 11507 |
+
"epoch": 0.19988138505755867,
|
| 11508 |
+
"grad_norm": 0.15721186995506287,
|
| 11509 |
+
"learning_rate": 9.091467052350402e-05,
|
| 11510 |
+
"loss": 2.0998237133026123,
|
| 11511 |
+
"step": 3286
|
| 11512 |
+
},
|
| 11513 |
+
{
|
| 11514 |
+
"epoch": 0.20000304140878056,
|
| 11515 |
+
"grad_norm": 0.19420433044433594,
|
| 11516 |
+
"learning_rate": 9.090361615380352e-05,
|
| 11517 |
+
"loss": 2.0541539192199707,
|
| 11518 |
+
"step": 3288
|
| 11519 |
+
},
|
| 11520 |
+
{
|
| 11521 |
+
"epoch": 0.20000304140878056,
|
| 11522 |
+
"eval_loss": 2.0950963497161865,
|
| 11523 |
+
"eval_runtime": 116.5897,
|
| 11524 |
+
"eval_samples_per_second": 45.579,
|
| 11525 |
+
"eval_steps_per_second": 11.399,
|
| 11526 |
+
"step": 3288
|
| 11527 |
}
|
| 11528 |
],
|
| 11529 |
"logging_steps": 2,
|
|
|
|
| 11543 |
"attributes": {}
|
| 11544 |
}
|
| 11545 |
},
|
| 11546 |
+
"total_flos": 3.5210092959044275e+17,
|
| 11547 |
"train_batch_size": 4,
|
| 11548 |
"trial_name": null,
|
| 11549 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bedf64b23f9e2b980974dbee3d64c3aa3b86ab3823cd9d07ba65aea501d5e62
|
| 3 |
+
size 5777
|