Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
unsloth
sft
conversational
text-generation-inference
Instructions to use Ba2han/test_CPTlsft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/test_CPTlsft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/test_CPTlsft") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/test_CPTlsft") model = AutoModelForCausalLM.from_pretrained("Ba2han/test_CPTlsft", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/test_CPTlsft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/test_CPTlsft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/test_CPTlsft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ba2han/test_CPTlsft
- SGLang
How to use Ba2han/test_CPTlsft with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Ba2han/test_CPTlsft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/test_CPTlsft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Ba2han/test_CPTlsft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/test_CPTlsft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use Ba2han/test_CPTlsft with Docker Model Runner:
docker model run hf.co/Ba2han/test_CPTlsft
Training in progress, step 2946, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2934397032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c12392b17cbe6d427373b8df6561a07c49e38f80e2a1753fa47f09dd34a45ed0
|
| 3 |
size 2934397032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1471680120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:906a1b0cbecfbc2c5fb884297cfac3b0d1080d53e1a84cff3a53c9da3fc6bd8c
|
| 3 |
size 1471680120
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9785
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6881a443a178653ccb36e7c297c0ca98cf0c456d97ea532f7ce536fc696a5c47
|
| 3 |
size 9785
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -6882,6 +6882,3443 @@
|
|
| 6882 |
"learning_rate": 0.001,
|
| 6883 |
"loss": 2.350402355194092,
|
| 6884 |
"step": 1964
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6885 |
}
|
| 6886 |
],
|
| 6887 |
"logging_steps": 2,
|
|
@@ -6901,7 +10338,7 @@
|
|
| 6901 |
"attributes": {}
|
| 6902 |
}
|
| 6903 |
},
|
| 6904 |
-
"total_flos":
|
| 6905 |
"train_batch_size": 2,
|
| 6906 |
"trial_name": null,
|
| 6907 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3000290252111966,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2946,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6882 |
"learning_rate": 0.001,
|
| 6883 |
"loss": 2.350402355194092,
|
| 6884 |
"step": 1964
|
| 6885 |
+
},
|
| 6886 |
+
{
|
| 6887 |
+
"epoch": 0.20022303583340548,
|
| 6888 |
+
"grad_norm": 0.1332654058933258,
|
| 6889 |
+
"learning_rate": 0.001,
|
| 6890 |
+
"loss": 2.3518030643463135,
|
| 6891 |
+
"step": 1966
|
| 6892 |
+
},
|
| 6893 |
+
{
|
| 6894 |
+
"epoch": 0.2004267215260132,
|
| 6895 |
+
"grad_norm": 0.13542044162750244,
|
| 6896 |
+
"learning_rate": 0.001,
|
| 6897 |
+
"loss": 2.362475872039795,
|
| 6898 |
+
"step": 1968
|
| 6899 |
+
},
|
| 6900 |
+
{
|
| 6901 |
+
"epoch": 0.20063040721862094,
|
| 6902 |
+
"grad_norm": 0.10843665152788162,
|
| 6903 |
+
"learning_rate": 0.001,
|
| 6904 |
+
"loss": 2.342334508895874,
|
| 6905 |
+
"step": 1970
|
| 6906 |
+
},
|
| 6907 |
+
{
|
| 6908 |
+
"epoch": 0.2008340929112287,
|
| 6909 |
+
"grad_norm": 0.14251796901226044,
|
| 6910 |
+
"learning_rate": 0.001,
|
| 6911 |
+
"loss": 2.289336919784546,
|
| 6912 |
+
"step": 1972
|
| 6913 |
+
},
|
| 6914 |
+
{
|
| 6915 |
+
"epoch": 0.20103777860383643,
|
| 6916 |
+
"grad_norm": 0.18810075521469116,
|
| 6917 |
+
"learning_rate": 0.001,
|
| 6918 |
+
"loss": 2.2337474822998047,
|
| 6919 |
+
"step": 1974
|
| 6920 |
+
},
|
| 6921 |
+
{
|
| 6922 |
+
"epoch": 0.20124146429644416,
|
| 6923 |
+
"grad_norm": 0.13369949162006378,
|
| 6924 |
+
"learning_rate": 0.001,
|
| 6925 |
+
"loss": 2.2457265853881836,
|
| 6926 |
+
"step": 1976
|
| 6927 |
+
},
|
| 6928 |
+
{
|
| 6929 |
+
"epoch": 0.20144514998905189,
|
| 6930 |
+
"grad_norm": 0.13221774995326996,
|
| 6931 |
+
"learning_rate": 0.001,
|
| 6932 |
+
"loss": 2.2601826190948486,
|
| 6933 |
+
"step": 1978
|
| 6934 |
+
},
|
| 6935 |
+
{
|
| 6936 |
+
"epoch": 0.20164883568165964,
|
| 6937 |
+
"grad_norm": 0.129745751619339,
|
| 6938 |
+
"learning_rate": 0.001,
|
| 6939 |
+
"loss": 2.415891170501709,
|
| 6940 |
+
"step": 1980
|
| 6941 |
+
},
|
| 6942 |
+
{
|
| 6943 |
+
"epoch": 0.20185252137426737,
|
| 6944 |
+
"grad_norm": 0.1163729876279831,
|
| 6945 |
+
"learning_rate": 0.001,
|
| 6946 |
+
"loss": 2.1851000785827637,
|
| 6947 |
+
"step": 1982
|
| 6948 |
+
},
|
| 6949 |
+
{
|
| 6950 |
+
"epoch": 0.2020562070668751,
|
| 6951 |
+
"grad_norm": 0.17379450798034668,
|
| 6952 |
+
"learning_rate": 0.001,
|
| 6953 |
+
"loss": 2.3865816593170166,
|
| 6954 |
+
"step": 1984
|
| 6955 |
+
},
|
| 6956 |
+
{
|
| 6957 |
+
"epoch": 0.20225989275948283,
|
| 6958 |
+
"grad_norm": 0.12209579348564148,
|
| 6959 |
+
"learning_rate": 0.001,
|
| 6960 |
+
"loss": 2.319667100906372,
|
| 6961 |
+
"step": 1986
|
| 6962 |
+
},
|
| 6963 |
+
{
|
| 6964 |
+
"epoch": 0.2024635784520906,
|
| 6965 |
+
"grad_norm": 0.15141528844833374,
|
| 6966 |
+
"learning_rate": 0.001,
|
| 6967 |
+
"loss": 2.3105239868164062,
|
| 6968 |
+
"step": 1988
|
| 6969 |
+
},
|
| 6970 |
+
{
|
| 6971 |
+
"epoch": 0.20266726414469832,
|
| 6972 |
+
"grad_norm": 0.13487720489501953,
|
| 6973 |
+
"learning_rate": 0.001,
|
| 6974 |
+
"loss": 2.3425450325012207,
|
| 6975 |
+
"step": 1990
|
| 6976 |
+
},
|
| 6977 |
+
{
|
| 6978 |
+
"epoch": 0.20287094983730605,
|
| 6979 |
+
"grad_norm": 0.11849024146795273,
|
| 6980 |
+
"learning_rate": 0.001,
|
| 6981 |
+
"loss": 2.327389717102051,
|
| 6982 |
+
"step": 1992
|
| 6983 |
+
},
|
| 6984 |
+
{
|
| 6985 |
+
"epoch": 0.20307463552991378,
|
| 6986 |
+
"grad_norm": 0.12061267346143723,
|
| 6987 |
+
"learning_rate": 0.001,
|
| 6988 |
+
"loss": 2.346524953842163,
|
| 6989 |
+
"step": 1994
|
| 6990 |
+
},
|
| 6991 |
+
{
|
| 6992 |
+
"epoch": 0.20327832122252154,
|
| 6993 |
+
"grad_norm": 0.14630869030952454,
|
| 6994 |
+
"learning_rate": 0.001,
|
| 6995 |
+
"loss": 2.277308464050293,
|
| 6996 |
+
"step": 1996
|
| 6997 |
+
},
|
| 6998 |
+
{
|
| 6999 |
+
"epoch": 0.20348200691512927,
|
| 7000 |
+
"grad_norm": 0.15986157953739166,
|
| 7001 |
+
"learning_rate": 0.001,
|
| 7002 |
+
"loss": 2.306529998779297,
|
| 7003 |
+
"step": 1998
|
| 7004 |
+
},
|
| 7005 |
+
{
|
| 7006 |
+
"epoch": 0.203685692607737,
|
| 7007 |
+
"grad_norm": 0.12603764235973358,
|
| 7008 |
+
"learning_rate": 0.001,
|
| 7009 |
+
"loss": 2.1614506244659424,
|
| 7010 |
+
"step": 2000
|
| 7011 |
+
},
|
| 7012 |
+
{
|
| 7013 |
+
"epoch": 0.20388937830034473,
|
| 7014 |
+
"grad_norm": 0.12749092280864716,
|
| 7015 |
+
"learning_rate": 0.001,
|
| 7016 |
+
"loss": 2.2275943756103516,
|
| 7017 |
+
"step": 2002
|
| 7018 |
+
},
|
| 7019 |
+
{
|
| 7020 |
+
"epoch": 0.20409306399295246,
|
| 7021 |
+
"grad_norm": 0.1311330646276474,
|
| 7022 |
+
"learning_rate": 0.001,
|
| 7023 |
+
"loss": 2.215738296508789,
|
| 7024 |
+
"step": 2004
|
| 7025 |
+
},
|
| 7026 |
+
{
|
| 7027 |
+
"epoch": 0.20429674968556022,
|
| 7028 |
+
"grad_norm": 0.10149648040533066,
|
| 7029 |
+
"learning_rate": 0.001,
|
| 7030 |
+
"loss": 2.3582026958465576,
|
| 7031 |
+
"step": 2006
|
| 7032 |
+
},
|
| 7033 |
+
{
|
| 7034 |
+
"epoch": 0.20450043537816795,
|
| 7035 |
+
"grad_norm": 0.1210395023226738,
|
| 7036 |
+
"learning_rate": 0.001,
|
| 7037 |
+
"loss": 2.2181241512298584,
|
| 7038 |
+
"step": 2008
|
| 7039 |
+
},
|
| 7040 |
+
{
|
| 7041 |
+
"epoch": 0.20470412107077568,
|
| 7042 |
+
"grad_norm": 0.13598351180553436,
|
| 7043 |
+
"learning_rate": 0.001,
|
| 7044 |
+
"loss": 2.167415142059326,
|
| 7045 |
+
"step": 2010
|
| 7046 |
+
},
|
| 7047 |
+
{
|
| 7048 |
+
"epoch": 0.2049078067633834,
|
| 7049 |
+
"grad_norm": 0.14506720006465912,
|
| 7050 |
+
"learning_rate": 0.001,
|
| 7051 |
+
"loss": 2.2836151123046875,
|
| 7052 |
+
"step": 2012
|
| 7053 |
+
},
|
| 7054 |
+
{
|
| 7055 |
+
"epoch": 0.20511149245599117,
|
| 7056 |
+
"grad_norm": 0.13037912547588348,
|
| 7057 |
+
"learning_rate": 0.001,
|
| 7058 |
+
"loss": 2.2564404010772705,
|
| 7059 |
+
"step": 2014
|
| 7060 |
+
},
|
| 7061 |
+
{
|
| 7062 |
+
"epoch": 0.2053151781485989,
|
| 7063 |
+
"grad_norm": 0.11640441417694092,
|
| 7064 |
+
"learning_rate": 0.001,
|
| 7065 |
+
"loss": 2.2599525451660156,
|
| 7066 |
+
"step": 2016
|
| 7067 |
+
},
|
| 7068 |
+
{
|
| 7069 |
+
"epoch": 0.20551886384120663,
|
| 7070 |
+
"grad_norm": 0.13348421454429626,
|
| 7071 |
+
"learning_rate": 0.001,
|
| 7072 |
+
"loss": 2.2407541275024414,
|
| 7073 |
+
"step": 2018
|
| 7074 |
+
},
|
| 7075 |
+
{
|
| 7076 |
+
"epoch": 0.20572254953381436,
|
| 7077 |
+
"grad_norm": 0.12687475979328156,
|
| 7078 |
+
"learning_rate": 0.001,
|
| 7079 |
+
"loss": 2.316174030303955,
|
| 7080 |
+
"step": 2020
|
| 7081 |
+
},
|
| 7082 |
+
{
|
| 7083 |
+
"epoch": 0.20592623522642212,
|
| 7084 |
+
"grad_norm": 0.13885043561458588,
|
| 7085 |
+
"learning_rate": 0.001,
|
| 7086 |
+
"loss": 2.2986114025115967,
|
| 7087 |
+
"step": 2022
|
| 7088 |
+
},
|
| 7089 |
+
{
|
| 7090 |
+
"epoch": 0.20612992091902985,
|
| 7091 |
+
"grad_norm": 0.12649931013584137,
|
| 7092 |
+
"learning_rate": 0.001,
|
| 7093 |
+
"loss": 2.3572874069213867,
|
| 7094 |
+
"step": 2024
|
| 7095 |
+
},
|
| 7096 |
+
{
|
| 7097 |
+
"epoch": 0.20633360661163758,
|
| 7098 |
+
"grad_norm": 0.13342230021953583,
|
| 7099 |
+
"learning_rate": 0.001,
|
| 7100 |
+
"loss": 2.0838122367858887,
|
| 7101 |
+
"step": 2026
|
| 7102 |
+
},
|
| 7103 |
+
{
|
| 7104 |
+
"epoch": 0.2065372923042453,
|
| 7105 |
+
"grad_norm": 0.13612042367458344,
|
| 7106 |
+
"learning_rate": 0.001,
|
| 7107 |
+
"loss": 2.2671127319335938,
|
| 7108 |
+
"step": 2028
|
| 7109 |
+
},
|
| 7110 |
+
{
|
| 7111 |
+
"epoch": 0.20674097799685306,
|
| 7112 |
+
"grad_norm": 0.14538002014160156,
|
| 7113 |
+
"learning_rate": 0.001,
|
| 7114 |
+
"loss": 2.2662739753723145,
|
| 7115 |
+
"step": 2030
|
| 7116 |
+
},
|
| 7117 |
+
{
|
| 7118 |
+
"epoch": 0.2069446636894608,
|
| 7119 |
+
"grad_norm": 0.12667714059352875,
|
| 7120 |
+
"learning_rate": 0.001,
|
| 7121 |
+
"loss": 2.2172627449035645,
|
| 7122 |
+
"step": 2032
|
| 7123 |
+
},
|
| 7124 |
+
{
|
| 7125 |
+
"epoch": 0.20714834938206853,
|
| 7126 |
+
"grad_norm": 0.12291267514228821,
|
| 7127 |
+
"learning_rate": 0.001,
|
| 7128 |
+
"loss": 2.1739583015441895,
|
| 7129 |
+
"step": 2034
|
| 7130 |
+
},
|
| 7131 |
+
{
|
| 7132 |
+
"epoch": 0.20735203507467626,
|
| 7133 |
+
"grad_norm": 0.11600970476865768,
|
| 7134 |
+
"learning_rate": 0.001,
|
| 7135 |
+
"loss": 2.2439427375793457,
|
| 7136 |
+
"step": 2036
|
| 7137 |
+
},
|
| 7138 |
+
{
|
| 7139 |
+
"epoch": 0.207555720767284,
|
| 7140 |
+
"grad_norm": 0.13937845826148987,
|
| 7141 |
+
"learning_rate": 0.001,
|
| 7142 |
+
"loss": 2.1982436180114746,
|
| 7143 |
+
"step": 2038
|
| 7144 |
+
},
|
| 7145 |
+
{
|
| 7146 |
+
"epoch": 0.20775940645989174,
|
| 7147 |
+
"grad_norm": 0.11657320708036423,
|
| 7148 |
+
"learning_rate": 0.001,
|
| 7149 |
+
"loss": 2.2145957946777344,
|
| 7150 |
+
"step": 2040
|
| 7151 |
+
},
|
| 7152 |
+
{
|
| 7153 |
+
"epoch": 0.20796309215249947,
|
| 7154 |
+
"grad_norm": 0.1060621589422226,
|
| 7155 |
+
"learning_rate": 0.001,
|
| 7156 |
+
"loss": 2.325204372406006,
|
| 7157 |
+
"step": 2042
|
| 7158 |
+
},
|
| 7159 |
+
{
|
| 7160 |
+
"epoch": 0.2081667778451072,
|
| 7161 |
+
"grad_norm": 0.14791932702064514,
|
| 7162 |
+
"learning_rate": 0.001,
|
| 7163 |
+
"loss": 2.3769519329071045,
|
| 7164 |
+
"step": 2044
|
| 7165 |
+
},
|
| 7166 |
+
{
|
| 7167 |
+
"epoch": 0.20837046353771496,
|
| 7168 |
+
"grad_norm": 0.16861262917518616,
|
| 7169 |
+
"learning_rate": 0.001,
|
| 7170 |
+
"loss": 2.255207061767578,
|
| 7171 |
+
"step": 2046
|
| 7172 |
+
},
|
| 7173 |
+
{
|
| 7174 |
+
"epoch": 0.2085741492303227,
|
| 7175 |
+
"grad_norm": 0.12092728167772293,
|
| 7176 |
+
"learning_rate": 0.001,
|
| 7177 |
+
"loss": 2.2588930130004883,
|
| 7178 |
+
"step": 2048
|
| 7179 |
+
},
|
| 7180 |
+
{
|
| 7181 |
+
"epoch": 0.20877783492293042,
|
| 7182 |
+
"grad_norm": 0.12038931250572205,
|
| 7183 |
+
"learning_rate": 0.001,
|
| 7184 |
+
"loss": 2.318528652191162,
|
| 7185 |
+
"step": 2050
|
| 7186 |
+
},
|
| 7187 |
+
{
|
| 7188 |
+
"epoch": 0.20898152061553815,
|
| 7189 |
+
"grad_norm": 0.12795990705490112,
|
| 7190 |
+
"learning_rate": 0.001,
|
| 7191 |
+
"loss": 2.304769992828369,
|
| 7192 |
+
"step": 2052
|
| 7193 |
+
},
|
| 7194 |
+
{
|
| 7195 |
+
"epoch": 0.2091852063081459,
|
| 7196 |
+
"grad_norm": 0.12296199053525925,
|
| 7197 |
+
"learning_rate": 0.001,
|
| 7198 |
+
"loss": 2.290985584259033,
|
| 7199 |
+
"step": 2054
|
| 7200 |
+
},
|
| 7201 |
+
{
|
| 7202 |
+
"epoch": 0.20938889200075364,
|
| 7203 |
+
"grad_norm": 0.15992136299610138,
|
| 7204 |
+
"learning_rate": 0.001,
|
| 7205 |
+
"loss": 2.3338170051574707,
|
| 7206 |
+
"step": 2056
|
| 7207 |
+
},
|
| 7208 |
+
{
|
| 7209 |
+
"epoch": 0.20959257769336137,
|
| 7210 |
+
"grad_norm": 0.17864419519901276,
|
| 7211 |
+
"learning_rate": 0.001,
|
| 7212 |
+
"loss": 2.1608638763427734,
|
| 7213 |
+
"step": 2058
|
| 7214 |
+
},
|
| 7215 |
+
{
|
| 7216 |
+
"epoch": 0.2097962633859691,
|
| 7217 |
+
"grad_norm": 0.13432948291301727,
|
| 7218 |
+
"learning_rate": 0.001,
|
| 7219 |
+
"loss": 2.2765345573425293,
|
| 7220 |
+
"step": 2060
|
| 7221 |
+
},
|
| 7222 |
+
{
|
| 7223 |
+
"epoch": 0.20999994907857686,
|
| 7224 |
+
"grad_norm": 0.2173418402671814,
|
| 7225 |
+
"learning_rate": 0.001,
|
| 7226 |
+
"loss": 2.237825870513916,
|
| 7227 |
+
"step": 2062
|
| 7228 |
+
},
|
| 7229 |
+
{
|
| 7230 |
+
"epoch": 0.2102036347711846,
|
| 7231 |
+
"grad_norm": 0.2099733054637909,
|
| 7232 |
+
"learning_rate": 0.001,
|
| 7233 |
+
"loss": 2.219252109527588,
|
| 7234 |
+
"step": 2064
|
| 7235 |
+
},
|
| 7236 |
+
{
|
| 7237 |
+
"epoch": 0.21040732046379232,
|
| 7238 |
+
"grad_norm": 0.12270800024271011,
|
| 7239 |
+
"learning_rate": 0.001,
|
| 7240 |
+
"loss": 2.1198623180389404,
|
| 7241 |
+
"step": 2066
|
| 7242 |
+
},
|
| 7243 |
+
{
|
| 7244 |
+
"epoch": 0.21061100615640005,
|
| 7245 |
+
"grad_norm": 0.1364654302597046,
|
| 7246 |
+
"learning_rate": 0.001,
|
| 7247 |
+
"loss": 2.3696980476379395,
|
| 7248 |
+
"step": 2068
|
| 7249 |
+
},
|
| 7250 |
+
{
|
| 7251 |
+
"epoch": 0.2108146918490078,
|
| 7252 |
+
"grad_norm": 0.22015328705310822,
|
| 7253 |
+
"learning_rate": 0.001,
|
| 7254 |
+
"loss": 2.193979263305664,
|
| 7255 |
+
"step": 2070
|
| 7256 |
+
},
|
| 7257 |
+
{
|
| 7258 |
+
"epoch": 0.21101837754161554,
|
| 7259 |
+
"grad_norm": 0.13526102900505066,
|
| 7260 |
+
"learning_rate": 0.001,
|
| 7261 |
+
"loss": 2.296517848968506,
|
| 7262 |
+
"step": 2072
|
| 7263 |
+
},
|
| 7264 |
+
{
|
| 7265 |
+
"epoch": 0.21122206323422327,
|
| 7266 |
+
"grad_norm": 0.11848942190408707,
|
| 7267 |
+
"learning_rate": 0.001,
|
| 7268 |
+
"loss": 2.171509265899658,
|
| 7269 |
+
"step": 2074
|
| 7270 |
+
},
|
| 7271 |
+
{
|
| 7272 |
+
"epoch": 0.211425748926831,
|
| 7273 |
+
"grad_norm": 0.1455782949924469,
|
| 7274 |
+
"learning_rate": 0.001,
|
| 7275 |
+
"loss": 2.246652126312256,
|
| 7276 |
+
"step": 2076
|
| 7277 |
+
},
|
| 7278 |
+
{
|
| 7279 |
+
"epoch": 0.21162943461943876,
|
| 7280 |
+
"grad_norm": 0.2020053267478943,
|
| 7281 |
+
"learning_rate": 0.001,
|
| 7282 |
+
"loss": 2.212353467941284,
|
| 7283 |
+
"step": 2078
|
| 7284 |
+
},
|
| 7285 |
+
{
|
| 7286 |
+
"epoch": 0.21183312031204649,
|
| 7287 |
+
"grad_norm": 0.14376763999462128,
|
| 7288 |
+
"learning_rate": 0.001,
|
| 7289 |
+
"loss": 2.4191670417785645,
|
| 7290 |
+
"step": 2080
|
| 7291 |
+
},
|
| 7292 |
+
{
|
| 7293 |
+
"epoch": 0.21203680600465422,
|
| 7294 |
+
"grad_norm": 0.19415634870529175,
|
| 7295 |
+
"learning_rate": 0.001,
|
| 7296 |
+
"loss": 2.2870001792907715,
|
| 7297 |
+
"step": 2082
|
| 7298 |
+
},
|
| 7299 |
+
{
|
| 7300 |
+
"epoch": 0.21224049169726195,
|
| 7301 |
+
"grad_norm": 0.18984787166118622,
|
| 7302 |
+
"learning_rate": 0.001,
|
| 7303 |
+
"loss": 2.220033645629883,
|
| 7304 |
+
"step": 2084
|
| 7305 |
+
},
|
| 7306 |
+
{
|
| 7307 |
+
"epoch": 0.2124441773898697,
|
| 7308 |
+
"grad_norm": 0.1426749974489212,
|
| 7309 |
+
"learning_rate": 0.001,
|
| 7310 |
+
"loss": 2.190608501434326,
|
| 7311 |
+
"step": 2086
|
| 7312 |
+
},
|
| 7313 |
+
{
|
| 7314 |
+
"epoch": 0.21264786308247743,
|
| 7315 |
+
"grad_norm": 0.1331908255815506,
|
| 7316 |
+
"learning_rate": 0.001,
|
| 7317 |
+
"loss": 2.175689458847046,
|
| 7318 |
+
"step": 2088
|
| 7319 |
+
},
|
| 7320 |
+
{
|
| 7321 |
+
"epoch": 0.21285154877508516,
|
| 7322 |
+
"grad_norm": 0.09822644293308258,
|
| 7323 |
+
"learning_rate": 0.001,
|
| 7324 |
+
"loss": 2.078017234802246,
|
| 7325 |
+
"step": 2090
|
| 7326 |
+
},
|
| 7327 |
+
{
|
| 7328 |
+
"epoch": 0.2130552344676929,
|
| 7329 |
+
"grad_norm": 0.11721331626176834,
|
| 7330 |
+
"learning_rate": 0.001,
|
| 7331 |
+
"loss": 2.1472275257110596,
|
| 7332 |
+
"step": 2092
|
| 7333 |
+
},
|
| 7334 |
+
{
|
| 7335 |
+
"epoch": 0.21325892016030065,
|
| 7336 |
+
"grad_norm": 0.13697774708271027,
|
| 7337 |
+
"learning_rate": 0.001,
|
| 7338 |
+
"loss": 2.119791269302368,
|
| 7339 |
+
"step": 2094
|
| 7340 |
+
},
|
| 7341 |
+
{
|
| 7342 |
+
"epoch": 0.21346260585290838,
|
| 7343 |
+
"grad_norm": 0.12550288438796997,
|
| 7344 |
+
"learning_rate": 0.001,
|
| 7345 |
+
"loss": 2.255849838256836,
|
| 7346 |
+
"step": 2096
|
| 7347 |
+
},
|
| 7348 |
+
{
|
| 7349 |
+
"epoch": 0.2136662915455161,
|
| 7350 |
+
"grad_norm": 0.1347886025905609,
|
| 7351 |
+
"learning_rate": 0.001,
|
| 7352 |
+
"loss": 2.1878976821899414,
|
| 7353 |
+
"step": 2098
|
| 7354 |
+
},
|
| 7355 |
+
{
|
| 7356 |
+
"epoch": 0.21386997723812384,
|
| 7357 |
+
"grad_norm": 0.15933649241924286,
|
| 7358 |
+
"learning_rate": 0.001,
|
| 7359 |
+
"loss": 2.376943826675415,
|
| 7360 |
+
"step": 2100
|
| 7361 |
+
},
|
| 7362 |
+
{
|
| 7363 |
+
"epoch": 0.2140736629307316,
|
| 7364 |
+
"grad_norm": 0.14798781275749207,
|
| 7365 |
+
"learning_rate": 0.001,
|
| 7366 |
+
"loss": 2.406372547149658,
|
| 7367 |
+
"step": 2102
|
| 7368 |
+
},
|
| 7369 |
+
{
|
| 7370 |
+
"epoch": 0.21427734862333933,
|
| 7371 |
+
"grad_norm": 0.11847440153360367,
|
| 7372 |
+
"learning_rate": 0.001,
|
| 7373 |
+
"loss": 2.2349047660827637,
|
| 7374 |
+
"step": 2104
|
| 7375 |
+
},
|
| 7376 |
+
{
|
| 7377 |
+
"epoch": 0.21448103431594706,
|
| 7378 |
+
"grad_norm": 0.14966922998428345,
|
| 7379 |
+
"learning_rate": 0.001,
|
| 7380 |
+
"loss": 2.199357271194458,
|
| 7381 |
+
"step": 2106
|
| 7382 |
+
},
|
| 7383 |
+
{
|
| 7384 |
+
"epoch": 0.2146847200085548,
|
| 7385 |
+
"grad_norm": 0.16093970835208893,
|
| 7386 |
+
"learning_rate": 0.001,
|
| 7387 |
+
"loss": 2.360997438430786,
|
| 7388 |
+
"step": 2108
|
| 7389 |
+
},
|
| 7390 |
+
{
|
| 7391 |
+
"epoch": 0.21488840570116255,
|
| 7392 |
+
"grad_norm": 0.16777126491069794,
|
| 7393 |
+
"learning_rate": 0.001,
|
| 7394 |
+
"loss": 2.127255916595459,
|
| 7395 |
+
"step": 2110
|
| 7396 |
+
},
|
| 7397 |
+
{
|
| 7398 |
+
"epoch": 0.21509209139377028,
|
| 7399 |
+
"grad_norm": 0.18444634974002838,
|
| 7400 |
+
"learning_rate": 0.001,
|
| 7401 |
+
"loss": 2.208926200866699,
|
| 7402 |
+
"step": 2112
|
| 7403 |
+
},
|
| 7404 |
+
{
|
| 7405 |
+
"epoch": 0.215295777086378,
|
| 7406 |
+
"grad_norm": 0.1910533308982849,
|
| 7407 |
+
"learning_rate": 0.001,
|
| 7408 |
+
"loss": 2.2258739471435547,
|
| 7409 |
+
"step": 2114
|
| 7410 |
+
},
|
| 7411 |
+
{
|
| 7412 |
+
"epoch": 0.21549946277898574,
|
| 7413 |
+
"grad_norm": 0.16046257317066193,
|
| 7414 |
+
"learning_rate": 0.001,
|
| 7415 |
+
"loss": 2.3034329414367676,
|
| 7416 |
+
"step": 2116
|
| 7417 |
+
},
|
| 7418 |
+
{
|
| 7419 |
+
"epoch": 0.2157031484715935,
|
| 7420 |
+
"grad_norm": 0.1671079695224762,
|
| 7421 |
+
"learning_rate": 0.001,
|
| 7422 |
+
"loss": 2.203211784362793,
|
| 7423 |
+
"step": 2118
|
| 7424 |
+
},
|
| 7425 |
+
{
|
| 7426 |
+
"epoch": 0.21590683416420123,
|
| 7427 |
+
"grad_norm": 0.13861027359962463,
|
| 7428 |
+
"learning_rate": 0.001,
|
| 7429 |
+
"loss": 2.215731620788574,
|
| 7430 |
+
"step": 2120
|
| 7431 |
+
},
|
| 7432 |
+
{
|
| 7433 |
+
"epoch": 0.21611051985680896,
|
| 7434 |
+
"grad_norm": 0.14537538588047028,
|
| 7435 |
+
"learning_rate": 0.001,
|
| 7436 |
+
"loss": 2.1655242443084717,
|
| 7437 |
+
"step": 2122
|
| 7438 |
+
},
|
| 7439 |
+
{
|
| 7440 |
+
"epoch": 0.2163142055494167,
|
| 7441 |
+
"grad_norm": 0.13189592957496643,
|
| 7442 |
+
"learning_rate": 0.001,
|
| 7443 |
+
"loss": 2.2886962890625,
|
| 7444 |
+
"step": 2124
|
| 7445 |
+
},
|
| 7446 |
+
{
|
| 7447 |
+
"epoch": 0.21651789124202442,
|
| 7448 |
+
"grad_norm": 0.12383344769477844,
|
| 7449 |
+
"learning_rate": 0.001,
|
| 7450 |
+
"loss": 2.3259522914886475,
|
| 7451 |
+
"step": 2126
|
| 7452 |
+
},
|
| 7453 |
+
{
|
| 7454 |
+
"epoch": 0.21672157693463218,
|
| 7455 |
+
"grad_norm": 0.13056810200214386,
|
| 7456 |
+
"learning_rate": 0.001,
|
| 7457 |
+
"loss": 2.2502012252807617,
|
| 7458 |
+
"step": 2128
|
| 7459 |
+
},
|
| 7460 |
+
{
|
| 7461 |
+
"epoch": 0.2169252626272399,
|
| 7462 |
+
"grad_norm": 0.17766277492046356,
|
| 7463 |
+
"learning_rate": 0.001,
|
| 7464 |
+
"loss": 2.281503438949585,
|
| 7465 |
+
"step": 2130
|
| 7466 |
+
},
|
| 7467 |
+
{
|
| 7468 |
+
"epoch": 0.21712894831984764,
|
| 7469 |
+
"grad_norm": 0.14903143048286438,
|
| 7470 |
+
"learning_rate": 0.001,
|
| 7471 |
+
"loss": 2.2841367721557617,
|
| 7472 |
+
"step": 2132
|
| 7473 |
+
},
|
| 7474 |
+
{
|
| 7475 |
+
"epoch": 0.21733263401245537,
|
| 7476 |
+
"grad_norm": 0.12021240592002869,
|
| 7477 |
+
"learning_rate": 0.001,
|
| 7478 |
+
"loss": 2.2492244243621826,
|
| 7479 |
+
"step": 2134
|
| 7480 |
+
},
|
| 7481 |
+
{
|
| 7482 |
+
"epoch": 0.21753631970506312,
|
| 7483 |
+
"grad_norm": 0.11126147955656052,
|
| 7484 |
+
"learning_rate": 0.001,
|
| 7485 |
+
"loss": 2.2749483585357666,
|
| 7486 |
+
"step": 2136
|
| 7487 |
+
},
|
| 7488 |
+
{
|
| 7489 |
+
"epoch": 0.21774000539767085,
|
| 7490 |
+
"grad_norm": 0.10774312913417816,
|
| 7491 |
+
"learning_rate": 0.001,
|
| 7492 |
+
"loss": 2.187044143676758,
|
| 7493 |
+
"step": 2138
|
| 7494 |
+
},
|
| 7495 |
+
{
|
| 7496 |
+
"epoch": 0.21794369109027859,
|
| 7497 |
+
"grad_norm": 0.1213623657822609,
|
| 7498 |
+
"learning_rate": 0.001,
|
| 7499 |
+
"loss": 2.2154085636138916,
|
| 7500 |
+
"step": 2140
|
| 7501 |
+
},
|
| 7502 |
+
{
|
| 7503 |
+
"epoch": 0.21814737678288632,
|
| 7504 |
+
"grad_norm": 0.14465981721878052,
|
| 7505 |
+
"learning_rate": 0.001,
|
| 7506 |
+
"loss": 2.1029224395751953,
|
| 7507 |
+
"step": 2142
|
| 7508 |
+
},
|
| 7509 |
+
{
|
| 7510 |
+
"epoch": 0.21835106247549407,
|
| 7511 |
+
"grad_norm": 0.10764388740062714,
|
| 7512 |
+
"learning_rate": 0.001,
|
| 7513 |
+
"loss": 2.2928218841552734,
|
| 7514 |
+
"step": 2144
|
| 7515 |
+
},
|
| 7516 |
+
{
|
| 7517 |
+
"epoch": 0.2185547481681018,
|
| 7518 |
+
"grad_norm": 0.1555708646774292,
|
| 7519 |
+
"learning_rate": 0.001,
|
| 7520 |
+
"loss": 2.3006021976470947,
|
| 7521 |
+
"step": 2146
|
| 7522 |
+
},
|
| 7523 |
+
{
|
| 7524 |
+
"epoch": 0.21875843386070953,
|
| 7525 |
+
"grad_norm": 0.13192640244960785,
|
| 7526 |
+
"learning_rate": 0.001,
|
| 7527 |
+
"loss": 2.152228355407715,
|
| 7528 |
+
"step": 2148
|
| 7529 |
+
},
|
| 7530 |
+
{
|
| 7531 |
+
"epoch": 0.21896211955331726,
|
| 7532 |
+
"grad_norm": 0.116376593708992,
|
| 7533 |
+
"learning_rate": 0.001,
|
| 7534 |
+
"loss": 2.290051221847534,
|
| 7535 |
+
"step": 2150
|
| 7536 |
+
},
|
| 7537 |
+
{
|
| 7538 |
+
"epoch": 0.21916580524592502,
|
| 7539 |
+
"grad_norm": 0.15078386664390564,
|
| 7540 |
+
"learning_rate": 0.001,
|
| 7541 |
+
"loss": 2.3026695251464844,
|
| 7542 |
+
"step": 2152
|
| 7543 |
+
},
|
| 7544 |
+
{
|
| 7545 |
+
"epoch": 0.21936949093853275,
|
| 7546 |
+
"grad_norm": 0.14644142985343933,
|
| 7547 |
+
"learning_rate": 0.001,
|
| 7548 |
+
"loss": 2.1502597332000732,
|
| 7549 |
+
"step": 2154
|
| 7550 |
+
},
|
| 7551 |
+
{
|
| 7552 |
+
"epoch": 0.21957317663114048,
|
| 7553 |
+
"grad_norm": 0.1318386048078537,
|
| 7554 |
+
"learning_rate": 0.001,
|
| 7555 |
+
"loss": 2.1251206398010254,
|
| 7556 |
+
"step": 2156
|
| 7557 |
+
},
|
| 7558 |
+
{
|
| 7559 |
+
"epoch": 0.2197768623237482,
|
| 7560 |
+
"grad_norm": 0.12190419435501099,
|
| 7561 |
+
"learning_rate": 0.001,
|
| 7562 |
+
"loss": 2.2428131103515625,
|
| 7563 |
+
"step": 2158
|
| 7564 |
+
},
|
| 7565 |
+
{
|
| 7566 |
+
"epoch": 0.21998054801635597,
|
| 7567 |
+
"grad_norm": 0.144894078373909,
|
| 7568 |
+
"learning_rate": 0.001,
|
| 7569 |
+
"loss": 2.134995937347412,
|
| 7570 |
+
"step": 2160
|
| 7571 |
+
},
|
| 7572 |
+
{
|
| 7573 |
+
"epoch": 0.2201842337089637,
|
| 7574 |
+
"grad_norm": 0.11810851097106934,
|
| 7575 |
+
"learning_rate": 0.001,
|
| 7576 |
+
"loss": 2.366105794906616,
|
| 7577 |
+
"step": 2162
|
| 7578 |
+
},
|
| 7579 |
+
{
|
| 7580 |
+
"epoch": 0.22038791940157143,
|
| 7581 |
+
"grad_norm": 0.14622870087623596,
|
| 7582 |
+
"learning_rate": 0.001,
|
| 7583 |
+
"loss": 2.210442066192627,
|
| 7584 |
+
"step": 2164
|
| 7585 |
+
},
|
| 7586 |
+
{
|
| 7587 |
+
"epoch": 0.22059160509417916,
|
| 7588 |
+
"grad_norm": 0.11801375448703766,
|
| 7589 |
+
"learning_rate": 0.001,
|
| 7590 |
+
"loss": 2.2921509742736816,
|
| 7591 |
+
"step": 2166
|
| 7592 |
+
},
|
| 7593 |
+
{
|
| 7594 |
+
"epoch": 0.22079529078678692,
|
| 7595 |
+
"grad_norm": 0.17492353916168213,
|
| 7596 |
+
"learning_rate": 0.001,
|
| 7597 |
+
"loss": 2.2734193801879883,
|
| 7598 |
+
"step": 2168
|
| 7599 |
+
},
|
| 7600 |
+
{
|
| 7601 |
+
"epoch": 0.22099897647939465,
|
| 7602 |
+
"grad_norm": 0.13734686374664307,
|
| 7603 |
+
"learning_rate": 0.001,
|
| 7604 |
+
"loss": 2.3175535202026367,
|
| 7605 |
+
"step": 2170
|
| 7606 |
+
},
|
| 7607 |
+
{
|
| 7608 |
+
"epoch": 0.22120266217200238,
|
| 7609 |
+
"grad_norm": 0.16846592724323273,
|
| 7610 |
+
"learning_rate": 0.001,
|
| 7611 |
+
"loss": 2.186642646789551,
|
| 7612 |
+
"step": 2172
|
| 7613 |
+
},
|
| 7614 |
+
{
|
| 7615 |
+
"epoch": 0.2214063478646101,
|
| 7616 |
+
"grad_norm": 0.13702936470508575,
|
| 7617 |
+
"learning_rate": 0.001,
|
| 7618 |
+
"loss": 2.229022979736328,
|
| 7619 |
+
"step": 2174
|
| 7620 |
+
},
|
| 7621 |
+
{
|
| 7622 |
+
"epoch": 0.22161003355721787,
|
| 7623 |
+
"grad_norm": 0.14587877690792084,
|
| 7624 |
+
"learning_rate": 0.001,
|
| 7625 |
+
"loss": 2.234549045562744,
|
| 7626 |
+
"step": 2176
|
| 7627 |
+
},
|
| 7628 |
+
{
|
| 7629 |
+
"epoch": 0.2218137192498256,
|
| 7630 |
+
"grad_norm": 0.13199906051158905,
|
| 7631 |
+
"learning_rate": 0.001,
|
| 7632 |
+
"loss": 2.260359287261963,
|
| 7633 |
+
"step": 2178
|
| 7634 |
+
},
|
| 7635 |
+
{
|
| 7636 |
+
"epoch": 0.22201740494243333,
|
| 7637 |
+
"grad_norm": 0.12365327775478363,
|
| 7638 |
+
"learning_rate": 0.001,
|
| 7639 |
+
"loss": 2.2838587760925293,
|
| 7640 |
+
"step": 2180
|
| 7641 |
+
},
|
| 7642 |
+
{
|
| 7643 |
+
"epoch": 0.22222109063504106,
|
| 7644 |
+
"grad_norm": 0.14833196997642517,
|
| 7645 |
+
"learning_rate": 0.001,
|
| 7646 |
+
"loss": 2.2439093589782715,
|
| 7647 |
+
"step": 2182
|
| 7648 |
+
},
|
| 7649 |
+
{
|
| 7650 |
+
"epoch": 0.22242477632764882,
|
| 7651 |
+
"grad_norm": 0.12094587832689285,
|
| 7652 |
+
"learning_rate": 0.001,
|
| 7653 |
+
"loss": 2.3266594409942627,
|
| 7654 |
+
"step": 2184
|
| 7655 |
+
},
|
| 7656 |
+
{
|
| 7657 |
+
"epoch": 0.22262846202025655,
|
| 7658 |
+
"grad_norm": 0.14344653487205505,
|
| 7659 |
+
"learning_rate": 0.001,
|
| 7660 |
+
"loss": 2.2581090927124023,
|
| 7661 |
+
"step": 2186
|
| 7662 |
+
},
|
| 7663 |
+
{
|
| 7664 |
+
"epoch": 0.22283214771286428,
|
| 7665 |
+
"grad_norm": 0.16069138050079346,
|
| 7666 |
+
"learning_rate": 0.001,
|
| 7667 |
+
"loss": 2.2626309394836426,
|
| 7668 |
+
"step": 2188
|
| 7669 |
+
},
|
| 7670 |
+
{
|
| 7671 |
+
"epoch": 0.223035833405472,
|
| 7672 |
+
"grad_norm": 0.1205589771270752,
|
| 7673 |
+
"learning_rate": 0.001,
|
| 7674 |
+
"loss": 2.2711329460144043,
|
| 7675 |
+
"step": 2190
|
| 7676 |
+
},
|
| 7677 |
+
{
|
| 7678 |
+
"epoch": 0.22323951909807976,
|
| 7679 |
+
"grad_norm": 0.13031691312789917,
|
| 7680 |
+
"learning_rate": 0.001,
|
| 7681 |
+
"loss": 2.270057201385498,
|
| 7682 |
+
"step": 2192
|
| 7683 |
+
},
|
| 7684 |
+
{
|
| 7685 |
+
"epoch": 0.2234432047906875,
|
| 7686 |
+
"grad_norm": 0.10588197410106659,
|
| 7687 |
+
"learning_rate": 0.001,
|
| 7688 |
+
"loss": 2.179744243621826,
|
| 7689 |
+
"step": 2194
|
| 7690 |
+
},
|
| 7691 |
+
{
|
| 7692 |
+
"epoch": 0.22364689048329522,
|
| 7693 |
+
"grad_norm": 0.11193032562732697,
|
| 7694 |
+
"learning_rate": 0.001,
|
| 7695 |
+
"loss": 2.2466163635253906,
|
| 7696 |
+
"step": 2196
|
| 7697 |
+
},
|
| 7698 |
+
{
|
| 7699 |
+
"epoch": 0.22385057617590295,
|
| 7700 |
+
"grad_norm": 0.1477038413286209,
|
| 7701 |
+
"learning_rate": 0.001,
|
| 7702 |
+
"loss": 2.1967272758483887,
|
| 7703 |
+
"step": 2198
|
| 7704 |
+
},
|
| 7705 |
+
{
|
| 7706 |
+
"epoch": 0.2240542618685107,
|
| 7707 |
+
"grad_norm": 0.14351655542850494,
|
| 7708 |
+
"learning_rate": 0.001,
|
| 7709 |
+
"loss": 2.2262516021728516,
|
| 7710 |
+
"step": 2200
|
| 7711 |
+
},
|
| 7712 |
+
{
|
| 7713 |
+
"epoch": 0.22425794756111844,
|
| 7714 |
+
"grad_norm": 0.1721118539571762,
|
| 7715 |
+
"learning_rate": 0.001,
|
| 7716 |
+
"loss": 2.2458155155181885,
|
| 7717 |
+
"step": 2202
|
| 7718 |
+
},
|
| 7719 |
+
{
|
| 7720 |
+
"epoch": 0.22446163325372617,
|
| 7721 |
+
"grad_norm": 0.10241930931806564,
|
| 7722 |
+
"learning_rate": 0.001,
|
| 7723 |
+
"loss": 2.2978739738464355,
|
| 7724 |
+
"step": 2204
|
| 7725 |
+
},
|
| 7726 |
+
{
|
| 7727 |
+
"epoch": 0.2246653189463339,
|
| 7728 |
+
"grad_norm": 0.16029687225818634,
|
| 7729 |
+
"learning_rate": 0.001,
|
| 7730 |
+
"loss": 2.17799711227417,
|
| 7731 |
+
"step": 2206
|
| 7732 |
+
},
|
| 7733 |
+
{
|
| 7734 |
+
"epoch": 0.22486900463894166,
|
| 7735 |
+
"grad_norm": 0.172994464635849,
|
| 7736 |
+
"learning_rate": 0.001,
|
| 7737 |
+
"loss": 2.331993579864502,
|
| 7738 |
+
"step": 2208
|
| 7739 |
+
},
|
| 7740 |
+
{
|
| 7741 |
+
"epoch": 0.2250726903315494,
|
| 7742 |
+
"grad_norm": 0.12230091542005539,
|
| 7743 |
+
"learning_rate": 0.001,
|
| 7744 |
+
"loss": 2.237166404724121,
|
| 7745 |
+
"step": 2210
|
| 7746 |
+
},
|
| 7747 |
+
{
|
| 7748 |
+
"epoch": 0.22527637602415712,
|
| 7749 |
+
"grad_norm": 0.14420680701732635,
|
| 7750 |
+
"learning_rate": 0.001,
|
| 7751 |
+
"loss": 2.3947150707244873,
|
| 7752 |
+
"step": 2212
|
| 7753 |
+
},
|
| 7754 |
+
{
|
| 7755 |
+
"epoch": 0.22548006171676485,
|
| 7756 |
+
"grad_norm": 0.1573219895362854,
|
| 7757 |
+
"learning_rate": 0.001,
|
| 7758 |
+
"loss": 2.278330087661743,
|
| 7759 |
+
"step": 2214
|
| 7760 |
+
},
|
| 7761 |
+
{
|
| 7762 |
+
"epoch": 0.2256837474093726,
|
| 7763 |
+
"grad_norm": 0.10855304449796677,
|
| 7764 |
+
"learning_rate": 0.001,
|
| 7765 |
+
"loss": 2.2428178787231445,
|
| 7766 |
+
"step": 2216
|
| 7767 |
+
},
|
| 7768 |
+
{
|
| 7769 |
+
"epoch": 0.22588743310198034,
|
| 7770 |
+
"grad_norm": 0.1076224222779274,
|
| 7771 |
+
"learning_rate": 0.001,
|
| 7772 |
+
"loss": 2.3099775314331055,
|
| 7773 |
+
"step": 2218
|
| 7774 |
+
},
|
| 7775 |
+
{
|
| 7776 |
+
"epoch": 0.22609111879458807,
|
| 7777 |
+
"grad_norm": 0.1327914148569107,
|
| 7778 |
+
"learning_rate": 0.001,
|
| 7779 |
+
"loss": 2.2350735664367676,
|
| 7780 |
+
"step": 2220
|
| 7781 |
+
},
|
| 7782 |
+
{
|
| 7783 |
+
"epoch": 0.2262948044871958,
|
| 7784 |
+
"grad_norm": 0.1599942445755005,
|
| 7785 |
+
"learning_rate": 0.001,
|
| 7786 |
+
"loss": 2.3115594387054443,
|
| 7787 |
+
"step": 2222
|
| 7788 |
+
},
|
| 7789 |
+
{
|
| 7790 |
+
"epoch": 0.22649849017980356,
|
| 7791 |
+
"grad_norm": 0.12186815589666367,
|
| 7792 |
+
"learning_rate": 0.001,
|
| 7793 |
+
"loss": 2.142502784729004,
|
| 7794 |
+
"step": 2224
|
| 7795 |
+
},
|
| 7796 |
+
{
|
| 7797 |
+
"epoch": 0.2267021758724113,
|
| 7798 |
+
"grad_norm": 0.11893671751022339,
|
| 7799 |
+
"learning_rate": 0.001,
|
| 7800 |
+
"loss": 2.2509889602661133,
|
| 7801 |
+
"step": 2226
|
| 7802 |
+
},
|
| 7803 |
+
{
|
| 7804 |
+
"epoch": 0.22690586156501902,
|
| 7805 |
+
"grad_norm": 0.12350459396839142,
|
| 7806 |
+
"learning_rate": 0.001,
|
| 7807 |
+
"loss": 2.241121530532837,
|
| 7808 |
+
"step": 2228
|
| 7809 |
+
},
|
| 7810 |
+
{
|
| 7811 |
+
"epoch": 0.22710954725762675,
|
| 7812 |
+
"grad_norm": 0.13305187225341797,
|
| 7813 |
+
"learning_rate": 0.001,
|
| 7814 |
+
"loss": 2.3953404426574707,
|
| 7815 |
+
"step": 2230
|
| 7816 |
+
},
|
| 7817 |
+
{
|
| 7818 |
+
"epoch": 0.2273132329502345,
|
| 7819 |
+
"grad_norm": 0.11953561753034592,
|
| 7820 |
+
"learning_rate": 0.001,
|
| 7821 |
+
"loss": 2.2393741607666016,
|
| 7822 |
+
"step": 2232
|
| 7823 |
+
},
|
| 7824 |
+
{
|
| 7825 |
+
"epoch": 0.22751691864284224,
|
| 7826 |
+
"grad_norm": 0.1264950931072235,
|
| 7827 |
+
"learning_rate": 0.001,
|
| 7828 |
+
"loss": 2.3280367851257324,
|
| 7829 |
+
"step": 2234
|
| 7830 |
+
},
|
| 7831 |
+
{
|
| 7832 |
+
"epoch": 0.22772060433544997,
|
| 7833 |
+
"grad_norm": 0.15629138052463531,
|
| 7834 |
+
"learning_rate": 0.001,
|
| 7835 |
+
"loss": 2.3063459396362305,
|
| 7836 |
+
"step": 2236
|
| 7837 |
+
},
|
| 7838 |
+
{
|
| 7839 |
+
"epoch": 0.2279242900280577,
|
| 7840 |
+
"grad_norm": 0.1287769228219986,
|
| 7841 |
+
"learning_rate": 0.001,
|
| 7842 |
+
"loss": 2.316145896911621,
|
| 7843 |
+
"step": 2238
|
| 7844 |
+
},
|
| 7845 |
+
{
|
| 7846 |
+
"epoch": 0.22812797572066545,
|
| 7847 |
+
"grad_norm": 0.10872452706098557,
|
| 7848 |
+
"learning_rate": 0.001,
|
| 7849 |
+
"loss": 2.0702037811279297,
|
| 7850 |
+
"step": 2240
|
| 7851 |
+
},
|
| 7852 |
+
{
|
| 7853 |
+
"epoch": 0.22833166141327318,
|
| 7854 |
+
"grad_norm": 0.13038697838783264,
|
| 7855 |
+
"learning_rate": 0.001,
|
| 7856 |
+
"loss": 2.2753920555114746,
|
| 7857 |
+
"step": 2242
|
| 7858 |
+
},
|
| 7859 |
+
{
|
| 7860 |
+
"epoch": 0.22853534710588091,
|
| 7861 |
+
"grad_norm": 0.12785492837429047,
|
| 7862 |
+
"learning_rate": 0.001,
|
| 7863 |
+
"loss": 2.1782665252685547,
|
| 7864 |
+
"step": 2244
|
| 7865 |
+
},
|
| 7866 |
+
{
|
| 7867 |
+
"epoch": 0.22873903279848865,
|
| 7868 |
+
"grad_norm": 0.1103779599070549,
|
| 7869 |
+
"learning_rate": 0.001,
|
| 7870 |
+
"loss": 2.1625418663024902,
|
| 7871 |
+
"step": 2246
|
| 7872 |
+
},
|
| 7873 |
+
{
|
| 7874 |
+
"epoch": 0.22894271849109638,
|
| 7875 |
+
"grad_norm": 0.1287870854139328,
|
| 7876 |
+
"learning_rate": 0.001,
|
| 7877 |
+
"loss": 2.1845321655273438,
|
| 7878 |
+
"step": 2248
|
| 7879 |
+
},
|
| 7880 |
+
{
|
| 7881 |
+
"epoch": 0.22914640418370413,
|
| 7882 |
+
"grad_norm": 0.1187158152461052,
|
| 7883 |
+
"learning_rate": 0.001,
|
| 7884 |
+
"loss": 2.261803388595581,
|
| 7885 |
+
"step": 2250
|
| 7886 |
+
},
|
| 7887 |
+
{
|
| 7888 |
+
"epoch": 0.22935008987631186,
|
| 7889 |
+
"grad_norm": 0.12079809606075287,
|
| 7890 |
+
"learning_rate": 0.001,
|
| 7891 |
+
"loss": 2.1906609535217285,
|
| 7892 |
+
"step": 2252
|
| 7893 |
+
},
|
| 7894 |
+
{
|
| 7895 |
+
"epoch": 0.2295537755689196,
|
| 7896 |
+
"grad_norm": 0.14951969683170319,
|
| 7897 |
+
"learning_rate": 0.001,
|
| 7898 |
+
"loss": 2.2447075843811035,
|
| 7899 |
+
"step": 2254
|
| 7900 |
+
},
|
| 7901 |
+
{
|
| 7902 |
+
"epoch": 0.22975746126152732,
|
| 7903 |
+
"grad_norm": 0.1196364238858223,
|
| 7904 |
+
"learning_rate": 0.001,
|
| 7905 |
+
"loss": 2.325568675994873,
|
| 7906 |
+
"step": 2256
|
| 7907 |
+
},
|
| 7908 |
+
{
|
| 7909 |
+
"epoch": 0.22996114695413508,
|
| 7910 |
+
"grad_norm": 0.1726703643798828,
|
| 7911 |
+
"learning_rate": 0.001,
|
| 7912 |
+
"loss": 2.339211940765381,
|
| 7913 |
+
"step": 2258
|
| 7914 |
+
},
|
| 7915 |
+
{
|
| 7916 |
+
"epoch": 0.2301648326467428,
|
| 7917 |
+
"grad_norm": 0.17774413526058197,
|
| 7918 |
+
"learning_rate": 0.001,
|
| 7919 |
+
"loss": 2.2623257637023926,
|
| 7920 |
+
"step": 2260
|
| 7921 |
+
},
|
| 7922 |
+
{
|
| 7923 |
+
"epoch": 0.23036851833935054,
|
| 7924 |
+
"grad_norm": 0.13105565309524536,
|
| 7925 |
+
"learning_rate": 0.001,
|
| 7926 |
+
"loss": 2.3285000324249268,
|
| 7927 |
+
"step": 2262
|
| 7928 |
+
},
|
| 7929 |
+
{
|
| 7930 |
+
"epoch": 0.23057220403195827,
|
| 7931 |
+
"grad_norm": 0.11584489792585373,
|
| 7932 |
+
"learning_rate": 0.001,
|
| 7933 |
+
"loss": 2.1701455116271973,
|
| 7934 |
+
"step": 2264
|
| 7935 |
+
},
|
| 7936 |
+
{
|
| 7937 |
+
"epoch": 0.23077588972456603,
|
| 7938 |
+
"grad_norm": 0.12426963448524475,
|
| 7939 |
+
"learning_rate": 0.001,
|
| 7940 |
+
"loss": 2.1661179065704346,
|
| 7941 |
+
"step": 2266
|
| 7942 |
+
},
|
| 7943 |
+
{
|
| 7944 |
+
"epoch": 0.23097957541717376,
|
| 7945 |
+
"grad_norm": 0.13072186708450317,
|
| 7946 |
+
"learning_rate": 0.001,
|
| 7947 |
+
"loss": 2.2079944610595703,
|
| 7948 |
+
"step": 2268
|
| 7949 |
+
},
|
| 7950 |
+
{
|
| 7951 |
+
"epoch": 0.2311832611097815,
|
| 7952 |
+
"grad_norm": 0.11987145245075226,
|
| 7953 |
+
"learning_rate": 0.001,
|
| 7954 |
+
"loss": 2.238759994506836,
|
| 7955 |
+
"step": 2270
|
| 7956 |
+
},
|
| 7957 |
+
{
|
| 7958 |
+
"epoch": 0.23138694680238922,
|
| 7959 |
+
"grad_norm": 0.1274658888578415,
|
| 7960 |
+
"learning_rate": 0.001,
|
| 7961 |
+
"loss": 2.2876806259155273,
|
| 7962 |
+
"step": 2272
|
| 7963 |
+
},
|
| 7964 |
+
{
|
| 7965 |
+
"epoch": 0.23159063249499698,
|
| 7966 |
+
"grad_norm": 0.13418513536453247,
|
| 7967 |
+
"learning_rate": 0.001,
|
| 7968 |
+
"loss": 2.3080406188964844,
|
| 7969 |
+
"step": 2274
|
| 7970 |
+
},
|
| 7971 |
+
{
|
| 7972 |
+
"epoch": 0.2317943181876047,
|
| 7973 |
+
"grad_norm": 0.11713685095310211,
|
| 7974 |
+
"learning_rate": 0.001,
|
| 7975 |
+
"loss": 2.122743606567383,
|
| 7976 |
+
"step": 2276
|
| 7977 |
+
},
|
| 7978 |
+
{
|
| 7979 |
+
"epoch": 0.23199800388021244,
|
| 7980 |
+
"grad_norm": 0.12808719277381897,
|
| 7981 |
+
"learning_rate": 0.001,
|
| 7982 |
+
"loss": 2.261695384979248,
|
| 7983 |
+
"step": 2278
|
| 7984 |
+
},
|
| 7985 |
+
{
|
| 7986 |
+
"epoch": 0.23220168957282017,
|
| 7987 |
+
"grad_norm": 0.14203794300556183,
|
| 7988 |
+
"learning_rate": 0.001,
|
| 7989 |
+
"loss": 2.342231273651123,
|
| 7990 |
+
"step": 2280
|
| 7991 |
+
},
|
| 7992 |
+
{
|
| 7993 |
+
"epoch": 0.23240537526542793,
|
| 7994 |
+
"grad_norm": 0.12997564673423767,
|
| 7995 |
+
"learning_rate": 0.001,
|
| 7996 |
+
"loss": 2.220278263092041,
|
| 7997 |
+
"step": 2282
|
| 7998 |
+
},
|
| 7999 |
+
{
|
| 8000 |
+
"epoch": 0.23260906095803566,
|
| 8001 |
+
"grad_norm": 0.14943812787532806,
|
| 8002 |
+
"learning_rate": 0.001,
|
| 8003 |
+
"loss": 2.249023914337158,
|
| 8004 |
+
"step": 2284
|
| 8005 |
+
},
|
| 8006 |
+
{
|
| 8007 |
+
"epoch": 0.2328127466506434,
|
| 8008 |
+
"grad_norm": 0.19298604130744934,
|
| 8009 |
+
"learning_rate": 0.001,
|
| 8010 |
+
"loss": 2.246429443359375,
|
| 8011 |
+
"step": 2286
|
| 8012 |
+
},
|
| 8013 |
+
{
|
| 8014 |
+
"epoch": 0.23301643234325112,
|
| 8015 |
+
"grad_norm": 0.12968875467777252,
|
| 8016 |
+
"learning_rate": 0.001,
|
| 8017 |
+
"loss": 2.220607042312622,
|
| 8018 |
+
"step": 2288
|
| 8019 |
+
},
|
| 8020 |
+
{
|
| 8021 |
+
"epoch": 0.23322011803585888,
|
| 8022 |
+
"grad_norm": 0.1168389841914177,
|
| 8023 |
+
"learning_rate": 0.001,
|
| 8024 |
+
"loss": 2.2542152404785156,
|
| 8025 |
+
"step": 2290
|
| 8026 |
+
},
|
| 8027 |
+
{
|
| 8028 |
+
"epoch": 0.2334238037284666,
|
| 8029 |
+
"grad_norm": 0.17614257335662842,
|
| 8030 |
+
"learning_rate": 0.001,
|
| 8031 |
+
"loss": 2.2829504013061523,
|
| 8032 |
+
"step": 2292
|
| 8033 |
+
},
|
| 8034 |
+
{
|
| 8035 |
+
"epoch": 0.23362748942107434,
|
| 8036 |
+
"grad_norm": 0.15027718245983124,
|
| 8037 |
+
"learning_rate": 0.001,
|
| 8038 |
+
"loss": 2.3181204795837402,
|
| 8039 |
+
"step": 2294
|
| 8040 |
+
},
|
| 8041 |
+
{
|
| 8042 |
+
"epoch": 0.23383117511368207,
|
| 8043 |
+
"grad_norm": 0.13256654143333435,
|
| 8044 |
+
"learning_rate": 0.001,
|
| 8045 |
+
"loss": 2.176738739013672,
|
| 8046 |
+
"step": 2296
|
| 8047 |
+
},
|
| 8048 |
+
{
|
| 8049 |
+
"epoch": 0.23403486080628982,
|
| 8050 |
+
"grad_norm": 0.1239066869020462,
|
| 8051 |
+
"learning_rate": 0.001,
|
| 8052 |
+
"loss": 2.3277997970581055,
|
| 8053 |
+
"step": 2298
|
| 8054 |
+
},
|
| 8055 |
+
{
|
| 8056 |
+
"epoch": 0.23423854649889755,
|
| 8057 |
+
"grad_norm": 0.1111677810549736,
|
| 8058 |
+
"learning_rate": 0.001,
|
| 8059 |
+
"loss": 2.2314040660858154,
|
| 8060 |
+
"step": 2300
|
| 8061 |
+
},
|
| 8062 |
+
{
|
| 8063 |
+
"epoch": 0.23444223219150528,
|
| 8064 |
+
"grad_norm": 0.1241074949502945,
|
| 8065 |
+
"learning_rate": 0.001,
|
| 8066 |
+
"loss": 2.3606104850769043,
|
| 8067 |
+
"step": 2302
|
| 8068 |
+
},
|
| 8069 |
+
{
|
| 8070 |
+
"epoch": 0.23464591788411301,
|
| 8071 |
+
"grad_norm": 0.12904836237430573,
|
| 8072 |
+
"learning_rate": 0.001,
|
| 8073 |
+
"loss": 2.134746551513672,
|
| 8074 |
+
"step": 2304
|
| 8075 |
+
},
|
| 8076 |
+
{
|
| 8077 |
+
"epoch": 0.23484960357672077,
|
| 8078 |
+
"grad_norm": 0.10937532037496567,
|
| 8079 |
+
"learning_rate": 0.001,
|
| 8080 |
+
"loss": 2.235872507095337,
|
| 8081 |
+
"step": 2306
|
| 8082 |
+
},
|
| 8083 |
+
{
|
| 8084 |
+
"epoch": 0.2350532892693285,
|
| 8085 |
+
"grad_norm": 0.11524411290884018,
|
| 8086 |
+
"learning_rate": 0.001,
|
| 8087 |
+
"loss": 2.2225921154022217,
|
| 8088 |
+
"step": 2308
|
| 8089 |
+
},
|
| 8090 |
+
{
|
| 8091 |
+
"epoch": 0.23525697496193623,
|
| 8092 |
+
"grad_norm": 0.1091182678937912,
|
| 8093 |
+
"learning_rate": 0.001,
|
| 8094 |
+
"loss": 2.249697208404541,
|
| 8095 |
+
"step": 2310
|
| 8096 |
+
},
|
| 8097 |
+
{
|
| 8098 |
+
"epoch": 0.23546066065454396,
|
| 8099 |
+
"grad_norm": 0.09452769160270691,
|
| 8100 |
+
"learning_rate": 0.001,
|
| 8101 |
+
"loss": 2.1702475547790527,
|
| 8102 |
+
"step": 2312
|
| 8103 |
+
},
|
| 8104 |
+
{
|
| 8105 |
+
"epoch": 0.23566434634715172,
|
| 8106 |
+
"grad_norm": 0.1309838891029358,
|
| 8107 |
+
"learning_rate": 0.001,
|
| 8108 |
+
"loss": 2.3923091888427734,
|
| 8109 |
+
"step": 2314
|
| 8110 |
+
},
|
| 8111 |
+
{
|
| 8112 |
+
"epoch": 0.23586803203975945,
|
| 8113 |
+
"grad_norm": 0.13221074640750885,
|
| 8114 |
+
"learning_rate": 0.001,
|
| 8115 |
+
"loss": 2.2691121101379395,
|
| 8116 |
+
"step": 2316
|
| 8117 |
+
},
|
| 8118 |
+
{
|
| 8119 |
+
"epoch": 0.23607171773236718,
|
| 8120 |
+
"grad_norm": 0.13891996443271637,
|
| 8121 |
+
"learning_rate": 0.001,
|
| 8122 |
+
"loss": 2.258054256439209,
|
| 8123 |
+
"step": 2318
|
| 8124 |
+
},
|
| 8125 |
+
{
|
| 8126 |
+
"epoch": 0.2362754034249749,
|
| 8127 |
+
"grad_norm": 0.12255372107028961,
|
| 8128 |
+
"learning_rate": 0.001,
|
| 8129 |
+
"loss": 2.3149542808532715,
|
| 8130 |
+
"step": 2320
|
| 8131 |
+
},
|
| 8132 |
+
{
|
| 8133 |
+
"epoch": 0.23647908911758267,
|
| 8134 |
+
"grad_norm": 0.13695189356803894,
|
| 8135 |
+
"learning_rate": 0.001,
|
| 8136 |
+
"loss": 2.2831039428710938,
|
| 8137 |
+
"step": 2322
|
| 8138 |
+
},
|
| 8139 |
+
{
|
| 8140 |
+
"epoch": 0.2366827748101904,
|
| 8141 |
+
"grad_norm": 0.12873858213424683,
|
| 8142 |
+
"learning_rate": 0.001,
|
| 8143 |
+
"loss": 2.1129136085510254,
|
| 8144 |
+
"step": 2324
|
| 8145 |
+
},
|
| 8146 |
+
{
|
| 8147 |
+
"epoch": 0.23688646050279813,
|
| 8148 |
+
"grad_norm": 0.11141201853752136,
|
| 8149 |
+
"learning_rate": 0.001,
|
| 8150 |
+
"loss": 2.1697378158569336,
|
| 8151 |
+
"step": 2326
|
| 8152 |
+
},
|
| 8153 |
+
{
|
| 8154 |
+
"epoch": 0.23709014619540586,
|
| 8155 |
+
"grad_norm": 0.11890513449907303,
|
| 8156 |
+
"learning_rate": 0.001,
|
| 8157 |
+
"loss": 2.2880191802978516,
|
| 8158 |
+
"step": 2328
|
| 8159 |
+
},
|
| 8160 |
+
{
|
| 8161 |
+
"epoch": 0.23729383188801362,
|
| 8162 |
+
"grad_norm": 0.10421814769506454,
|
| 8163 |
+
"learning_rate": 0.001,
|
| 8164 |
+
"loss": 2.152355194091797,
|
| 8165 |
+
"step": 2330
|
| 8166 |
+
},
|
| 8167 |
+
{
|
| 8168 |
+
"epoch": 0.23749751758062135,
|
| 8169 |
+
"grad_norm": 0.14245902001857758,
|
| 8170 |
+
"learning_rate": 0.001,
|
| 8171 |
+
"loss": 2.274724006652832,
|
| 8172 |
+
"step": 2332
|
| 8173 |
+
},
|
| 8174 |
+
{
|
| 8175 |
+
"epoch": 0.23770120327322908,
|
| 8176 |
+
"grad_norm": 0.1268816888332367,
|
| 8177 |
+
"learning_rate": 0.001,
|
| 8178 |
+
"loss": 2.3017592430114746,
|
| 8179 |
+
"step": 2334
|
| 8180 |
+
},
|
| 8181 |
+
{
|
| 8182 |
+
"epoch": 0.2379048889658368,
|
| 8183 |
+
"grad_norm": 0.14744152128696442,
|
| 8184 |
+
"learning_rate": 0.001,
|
| 8185 |
+
"loss": 2.2755537033081055,
|
| 8186 |
+
"step": 2336
|
| 8187 |
+
},
|
| 8188 |
+
{
|
| 8189 |
+
"epoch": 0.23810857465844457,
|
| 8190 |
+
"grad_norm": 0.14433081448078156,
|
| 8191 |
+
"learning_rate": 0.001,
|
| 8192 |
+
"loss": 2.187593936920166,
|
| 8193 |
+
"step": 2338
|
| 8194 |
+
},
|
| 8195 |
+
{
|
| 8196 |
+
"epoch": 0.2383122603510523,
|
| 8197 |
+
"grad_norm": 0.134014293551445,
|
| 8198 |
+
"learning_rate": 0.001,
|
| 8199 |
+
"loss": 2.13706636428833,
|
| 8200 |
+
"step": 2340
|
| 8201 |
+
},
|
| 8202 |
+
{
|
| 8203 |
+
"epoch": 0.23851594604366003,
|
| 8204 |
+
"grad_norm": 0.1468515694141388,
|
| 8205 |
+
"learning_rate": 0.001,
|
| 8206 |
+
"loss": 2.2837612628936768,
|
| 8207 |
+
"step": 2342
|
| 8208 |
+
},
|
| 8209 |
+
{
|
| 8210 |
+
"epoch": 0.23871963173626776,
|
| 8211 |
+
"grad_norm": 0.13836735486984253,
|
| 8212 |
+
"learning_rate": 0.001,
|
| 8213 |
+
"loss": 2.2482898235321045,
|
| 8214 |
+
"step": 2344
|
| 8215 |
+
},
|
| 8216 |
+
{
|
| 8217 |
+
"epoch": 0.23892331742887551,
|
| 8218 |
+
"grad_norm": 0.10638038069009781,
|
| 8219 |
+
"learning_rate": 0.001,
|
| 8220 |
+
"loss": 2.148932695388794,
|
| 8221 |
+
"step": 2346
|
| 8222 |
+
},
|
| 8223 |
+
{
|
| 8224 |
+
"epoch": 0.23912700312148324,
|
| 8225 |
+
"grad_norm": 0.16863828897476196,
|
| 8226 |
+
"learning_rate": 0.001,
|
| 8227 |
+
"loss": 2.2510690689086914,
|
| 8228 |
+
"step": 2348
|
| 8229 |
+
},
|
| 8230 |
+
{
|
| 8231 |
+
"epoch": 0.23933068881409097,
|
| 8232 |
+
"grad_norm": 0.12372192740440369,
|
| 8233 |
+
"learning_rate": 0.001,
|
| 8234 |
+
"loss": 2.160264492034912,
|
| 8235 |
+
"step": 2350
|
| 8236 |
+
},
|
| 8237 |
+
{
|
| 8238 |
+
"epoch": 0.2395343745066987,
|
| 8239 |
+
"grad_norm": 0.12689048051834106,
|
| 8240 |
+
"learning_rate": 0.001,
|
| 8241 |
+
"loss": 2.220759868621826,
|
| 8242 |
+
"step": 2352
|
| 8243 |
+
},
|
| 8244 |
+
{
|
| 8245 |
+
"epoch": 0.23973806019930646,
|
| 8246 |
+
"grad_norm": 0.1720622330904007,
|
| 8247 |
+
"learning_rate": 0.001,
|
| 8248 |
+
"loss": 2.120234251022339,
|
| 8249 |
+
"step": 2354
|
| 8250 |
+
},
|
| 8251 |
+
{
|
| 8252 |
+
"epoch": 0.2399417458919142,
|
| 8253 |
+
"grad_norm": 0.16328337788581848,
|
| 8254 |
+
"learning_rate": 0.001,
|
| 8255 |
+
"loss": 2.2486424446105957,
|
| 8256 |
+
"step": 2356
|
| 8257 |
+
},
|
| 8258 |
+
{
|
| 8259 |
+
"epoch": 0.24014543158452192,
|
| 8260 |
+
"grad_norm": 0.13333815336227417,
|
| 8261 |
+
"learning_rate": 0.001,
|
| 8262 |
+
"loss": 2.2202744483947754,
|
| 8263 |
+
"step": 2358
|
| 8264 |
+
},
|
| 8265 |
+
{
|
| 8266 |
+
"epoch": 0.24034911727712965,
|
| 8267 |
+
"grad_norm": 0.11074129492044449,
|
| 8268 |
+
"learning_rate": 0.001,
|
| 8269 |
+
"loss": 2.1337339878082275,
|
| 8270 |
+
"step": 2360
|
| 8271 |
+
},
|
| 8272 |
+
{
|
| 8273 |
+
"epoch": 0.2405528029697374,
|
| 8274 |
+
"grad_norm": 0.11352615058422089,
|
| 8275 |
+
"learning_rate": 0.001,
|
| 8276 |
+
"loss": 2.1236324310302734,
|
| 8277 |
+
"step": 2362
|
| 8278 |
+
},
|
| 8279 |
+
{
|
| 8280 |
+
"epoch": 0.24075648866234514,
|
| 8281 |
+
"grad_norm": 0.12343548983335495,
|
| 8282 |
+
"learning_rate": 0.001,
|
| 8283 |
+
"loss": 2.2955195903778076,
|
| 8284 |
+
"step": 2364
|
| 8285 |
+
},
|
| 8286 |
+
{
|
| 8287 |
+
"epoch": 0.24096017435495287,
|
| 8288 |
+
"grad_norm": 0.1231144592165947,
|
| 8289 |
+
"learning_rate": 0.001,
|
| 8290 |
+
"loss": 2.1093971729278564,
|
| 8291 |
+
"step": 2366
|
| 8292 |
+
},
|
| 8293 |
+
{
|
| 8294 |
+
"epoch": 0.2411638600475606,
|
| 8295 |
+
"grad_norm": 0.11531911045312881,
|
| 8296 |
+
"learning_rate": 0.001,
|
| 8297 |
+
"loss": 2.217890501022339,
|
| 8298 |
+
"step": 2368
|
| 8299 |
+
},
|
| 8300 |
+
{
|
| 8301 |
+
"epoch": 0.24136754574016836,
|
| 8302 |
+
"grad_norm": 0.12205381691455841,
|
| 8303 |
+
"learning_rate": 0.001,
|
| 8304 |
+
"loss": 2.039658784866333,
|
| 8305 |
+
"step": 2370
|
| 8306 |
+
},
|
| 8307 |
+
{
|
| 8308 |
+
"epoch": 0.2415712314327761,
|
| 8309 |
+
"grad_norm": 0.1533801555633545,
|
| 8310 |
+
"learning_rate": 0.001,
|
| 8311 |
+
"loss": 2.228492259979248,
|
| 8312 |
+
"step": 2372
|
| 8313 |
+
},
|
| 8314 |
+
{
|
| 8315 |
+
"epoch": 0.24177491712538382,
|
| 8316 |
+
"grad_norm": 0.12235800921916962,
|
| 8317 |
+
"learning_rate": 0.001,
|
| 8318 |
+
"loss": 2.305098056793213,
|
| 8319 |
+
"step": 2374
|
| 8320 |
+
},
|
| 8321 |
+
{
|
| 8322 |
+
"epoch": 0.24197860281799155,
|
| 8323 |
+
"grad_norm": 0.13657255470752716,
|
| 8324 |
+
"learning_rate": 0.001,
|
| 8325 |
+
"loss": 2.1344902515411377,
|
| 8326 |
+
"step": 2376
|
| 8327 |
+
},
|
| 8328 |
+
{
|
| 8329 |
+
"epoch": 0.24218228851059928,
|
| 8330 |
+
"grad_norm": 0.15733499825000763,
|
| 8331 |
+
"learning_rate": 0.001,
|
| 8332 |
+
"loss": 2.3524599075317383,
|
| 8333 |
+
"step": 2378
|
| 8334 |
+
},
|
| 8335 |
+
{
|
| 8336 |
+
"epoch": 0.24238597420320704,
|
| 8337 |
+
"grad_norm": 0.14680233597755432,
|
| 8338 |
+
"learning_rate": 0.001,
|
| 8339 |
+
"loss": 2.272952079772949,
|
| 8340 |
+
"step": 2380
|
| 8341 |
+
},
|
| 8342 |
+
{
|
| 8343 |
+
"epoch": 0.24258965989581477,
|
| 8344 |
+
"grad_norm": 0.12580932676792145,
|
| 8345 |
+
"learning_rate": 0.001,
|
| 8346 |
+
"loss": 2.330237627029419,
|
| 8347 |
+
"step": 2382
|
| 8348 |
+
},
|
| 8349 |
+
{
|
| 8350 |
+
"epoch": 0.2427933455884225,
|
| 8351 |
+
"grad_norm": 0.11925962567329407,
|
| 8352 |
+
"learning_rate": 0.001,
|
| 8353 |
+
"loss": 2.2972898483276367,
|
| 8354 |
+
"step": 2384
|
| 8355 |
+
},
|
| 8356 |
+
{
|
| 8357 |
+
"epoch": 0.24299703128103023,
|
| 8358 |
+
"grad_norm": 0.10948441177606583,
|
| 8359 |
+
"learning_rate": 0.001,
|
| 8360 |
+
"loss": 2.2953498363494873,
|
| 8361 |
+
"step": 2386
|
| 8362 |
+
},
|
| 8363 |
+
{
|
| 8364 |
+
"epoch": 0.243200716973638,
|
| 8365 |
+
"grad_norm": 0.13907292485237122,
|
| 8366 |
+
"learning_rate": 0.001,
|
| 8367 |
+
"loss": 2.3546230792999268,
|
| 8368 |
+
"step": 2388
|
| 8369 |
+
},
|
| 8370 |
+
{
|
| 8371 |
+
"epoch": 0.24340440266624572,
|
| 8372 |
+
"grad_norm": 0.17448817193508148,
|
| 8373 |
+
"learning_rate": 0.001,
|
| 8374 |
+
"loss": 2.4091057777404785,
|
| 8375 |
+
"step": 2390
|
| 8376 |
+
},
|
| 8377 |
+
{
|
| 8378 |
+
"epoch": 0.24360808835885345,
|
| 8379 |
+
"grad_norm": 0.13512557744979858,
|
| 8380 |
+
"learning_rate": 0.001,
|
| 8381 |
+
"loss": 2.1673364639282227,
|
| 8382 |
+
"step": 2392
|
| 8383 |
+
},
|
| 8384 |
+
{
|
| 8385 |
+
"epoch": 0.24381177405146118,
|
| 8386 |
+
"grad_norm": 0.12703931331634521,
|
| 8387 |
+
"learning_rate": 0.001,
|
| 8388 |
+
"loss": 2.3570284843444824,
|
| 8389 |
+
"step": 2394
|
| 8390 |
+
},
|
| 8391 |
+
{
|
| 8392 |
+
"epoch": 0.24401545974406894,
|
| 8393 |
+
"grad_norm": 0.1330791711807251,
|
| 8394 |
+
"learning_rate": 0.001,
|
| 8395 |
+
"loss": 2.3375802040100098,
|
| 8396 |
+
"step": 2396
|
| 8397 |
+
},
|
| 8398 |
+
{
|
| 8399 |
+
"epoch": 0.24421914543667667,
|
| 8400 |
+
"grad_norm": 0.12423437088727951,
|
| 8401 |
+
"learning_rate": 0.001,
|
| 8402 |
+
"loss": 2.2006168365478516,
|
| 8403 |
+
"step": 2398
|
| 8404 |
+
},
|
| 8405 |
+
{
|
| 8406 |
+
"epoch": 0.2444228311292844,
|
| 8407 |
+
"grad_norm": 0.116011843085289,
|
| 8408 |
+
"learning_rate": 0.001,
|
| 8409 |
+
"loss": 2.3071022033691406,
|
| 8410 |
+
"step": 2400
|
| 8411 |
+
},
|
| 8412 |
+
{
|
| 8413 |
+
"epoch": 0.24462651682189213,
|
| 8414 |
+
"grad_norm": 0.12046250700950623,
|
| 8415 |
+
"learning_rate": 0.001,
|
| 8416 |
+
"loss": 2.2343902587890625,
|
| 8417 |
+
"step": 2402
|
| 8418 |
+
},
|
| 8419 |
+
{
|
| 8420 |
+
"epoch": 0.24483020251449988,
|
| 8421 |
+
"grad_norm": 0.1241685226559639,
|
| 8422 |
+
"learning_rate": 0.001,
|
| 8423 |
+
"loss": 2.3002641201019287,
|
| 8424 |
+
"step": 2404
|
| 8425 |
+
},
|
| 8426 |
+
{
|
| 8427 |
+
"epoch": 0.24503388820710761,
|
| 8428 |
+
"grad_norm": 0.13112609088420868,
|
| 8429 |
+
"learning_rate": 0.001,
|
| 8430 |
+
"loss": 2.2365260124206543,
|
| 8431 |
+
"step": 2406
|
| 8432 |
+
},
|
| 8433 |
+
{
|
| 8434 |
+
"epoch": 0.24523757389971534,
|
| 8435 |
+
"grad_norm": 0.12894590198993683,
|
| 8436 |
+
"learning_rate": 0.001,
|
| 8437 |
+
"loss": 2.2513551712036133,
|
| 8438 |
+
"step": 2408
|
| 8439 |
+
},
|
| 8440 |
+
{
|
| 8441 |
+
"epoch": 0.24544125959232307,
|
| 8442 |
+
"grad_norm": 0.1860557645559311,
|
| 8443 |
+
"learning_rate": 0.001,
|
| 8444 |
+
"loss": 2.249741554260254,
|
| 8445 |
+
"step": 2410
|
| 8446 |
+
},
|
| 8447 |
+
{
|
| 8448 |
+
"epoch": 0.24564494528493083,
|
| 8449 |
+
"grad_norm": 0.17300473153591156,
|
| 8450 |
+
"learning_rate": 0.001,
|
| 8451 |
+
"loss": 2.2818374633789062,
|
| 8452 |
+
"step": 2412
|
| 8453 |
+
},
|
| 8454 |
+
{
|
| 8455 |
+
"epoch": 0.24584863097753856,
|
| 8456 |
+
"grad_norm": 0.1064365804195404,
|
| 8457 |
+
"learning_rate": 0.001,
|
| 8458 |
+
"loss": 2.167818307876587,
|
| 8459 |
+
"step": 2414
|
| 8460 |
+
},
|
| 8461 |
+
{
|
| 8462 |
+
"epoch": 0.2460523166701463,
|
| 8463 |
+
"grad_norm": 0.11387424916028976,
|
| 8464 |
+
"learning_rate": 0.001,
|
| 8465 |
+
"loss": 2.2182374000549316,
|
| 8466 |
+
"step": 2416
|
| 8467 |
+
},
|
| 8468 |
+
{
|
| 8469 |
+
"epoch": 0.24625600236275402,
|
| 8470 |
+
"grad_norm": 0.11281440407037735,
|
| 8471 |
+
"learning_rate": 0.001,
|
| 8472 |
+
"loss": 2.2971351146698,
|
| 8473 |
+
"step": 2418
|
| 8474 |
+
},
|
| 8475 |
+
{
|
| 8476 |
+
"epoch": 0.24645968805536178,
|
| 8477 |
+
"grad_norm": 0.14176355302333832,
|
| 8478 |
+
"learning_rate": 0.001,
|
| 8479 |
+
"loss": 2.28466796875,
|
| 8480 |
+
"step": 2420
|
| 8481 |
+
},
|
| 8482 |
+
{
|
| 8483 |
+
"epoch": 0.2466633737479695,
|
| 8484 |
+
"grad_norm": 0.12202437967061996,
|
| 8485 |
+
"learning_rate": 0.001,
|
| 8486 |
+
"loss": 2.2136001586914062,
|
| 8487 |
+
"step": 2422
|
| 8488 |
+
},
|
| 8489 |
+
{
|
| 8490 |
+
"epoch": 0.24686705944057724,
|
| 8491 |
+
"grad_norm": 0.1930209994316101,
|
| 8492 |
+
"learning_rate": 0.001,
|
| 8493 |
+
"loss": 2.3153481483459473,
|
| 8494 |
+
"step": 2424
|
| 8495 |
+
},
|
| 8496 |
+
{
|
| 8497 |
+
"epoch": 0.24707074513318497,
|
| 8498 |
+
"grad_norm": 0.1590680330991745,
|
| 8499 |
+
"learning_rate": 0.001,
|
| 8500 |
+
"loss": 2.169844627380371,
|
| 8501 |
+
"step": 2426
|
| 8502 |
+
},
|
| 8503 |
+
{
|
| 8504 |
+
"epoch": 0.24727443082579273,
|
| 8505 |
+
"grad_norm": 0.11763955652713776,
|
| 8506 |
+
"learning_rate": 0.001,
|
| 8507 |
+
"loss": 2.2070846557617188,
|
| 8508 |
+
"step": 2428
|
| 8509 |
+
},
|
| 8510 |
+
{
|
| 8511 |
+
"epoch": 0.24747811651840046,
|
| 8512 |
+
"grad_norm": 0.15771201252937317,
|
| 8513 |
+
"learning_rate": 0.001,
|
| 8514 |
+
"loss": 2.281949996948242,
|
| 8515 |
+
"step": 2430
|
| 8516 |
+
},
|
| 8517 |
+
{
|
| 8518 |
+
"epoch": 0.2476818022110082,
|
| 8519 |
+
"grad_norm": 0.11038631945848465,
|
| 8520 |
+
"learning_rate": 0.001,
|
| 8521 |
+
"loss": 2.1789164543151855,
|
| 8522 |
+
"step": 2432
|
| 8523 |
+
},
|
| 8524 |
+
{
|
| 8525 |
+
"epoch": 0.24788548790361592,
|
| 8526 |
+
"grad_norm": 0.1112900897860527,
|
| 8527 |
+
"learning_rate": 0.001,
|
| 8528 |
+
"loss": 2.150944232940674,
|
| 8529 |
+
"step": 2434
|
| 8530 |
+
},
|
| 8531 |
+
{
|
| 8532 |
+
"epoch": 0.24808917359622368,
|
| 8533 |
+
"grad_norm": 0.10558906197547913,
|
| 8534 |
+
"learning_rate": 0.001,
|
| 8535 |
+
"loss": 2.3076682090759277,
|
| 8536 |
+
"step": 2436
|
| 8537 |
+
},
|
| 8538 |
+
{
|
| 8539 |
+
"epoch": 0.2482928592888314,
|
| 8540 |
+
"grad_norm": 0.14115585386753082,
|
| 8541 |
+
"learning_rate": 0.001,
|
| 8542 |
+
"loss": 2.2640576362609863,
|
| 8543 |
+
"step": 2438
|
| 8544 |
+
},
|
| 8545 |
+
{
|
| 8546 |
+
"epoch": 0.24849654498143914,
|
| 8547 |
+
"grad_norm": 0.1521279513835907,
|
| 8548 |
+
"learning_rate": 0.001,
|
| 8549 |
+
"loss": 2.297089099884033,
|
| 8550 |
+
"step": 2440
|
| 8551 |
+
},
|
| 8552 |
+
{
|
| 8553 |
+
"epoch": 0.24870023067404687,
|
| 8554 |
+
"grad_norm": 0.10184413194656372,
|
| 8555 |
+
"learning_rate": 0.001,
|
| 8556 |
+
"loss": 2.2579843997955322,
|
| 8557 |
+
"step": 2442
|
| 8558 |
+
},
|
| 8559 |
+
{
|
| 8560 |
+
"epoch": 0.24890391636665463,
|
| 8561 |
+
"grad_norm": 0.10858550667762756,
|
| 8562 |
+
"learning_rate": 0.001,
|
| 8563 |
+
"loss": 2.1578266620635986,
|
| 8564 |
+
"step": 2444
|
| 8565 |
+
},
|
| 8566 |
+
{
|
| 8567 |
+
"epoch": 0.24910760205926236,
|
| 8568 |
+
"grad_norm": 0.133353129029274,
|
| 8569 |
+
"learning_rate": 0.001,
|
| 8570 |
+
"loss": 2.2211272716522217,
|
| 8571 |
+
"step": 2446
|
| 8572 |
+
},
|
| 8573 |
+
{
|
| 8574 |
+
"epoch": 0.2493112877518701,
|
| 8575 |
+
"grad_norm": 0.13719642162322998,
|
| 8576 |
+
"learning_rate": 0.001,
|
| 8577 |
+
"loss": 2.223576545715332,
|
| 8578 |
+
"step": 2448
|
| 8579 |
+
},
|
| 8580 |
+
{
|
| 8581 |
+
"epoch": 0.24951497344447782,
|
| 8582 |
+
"grad_norm": 0.14417602121829987,
|
| 8583 |
+
"learning_rate": 0.001,
|
| 8584 |
+
"loss": 2.232917308807373,
|
| 8585 |
+
"step": 2450
|
| 8586 |
+
},
|
| 8587 |
+
{
|
| 8588 |
+
"epoch": 0.24971865913708557,
|
| 8589 |
+
"grad_norm": 0.19275414943695068,
|
| 8590 |
+
"learning_rate": 0.001,
|
| 8591 |
+
"loss": 2.2598061561584473,
|
| 8592 |
+
"step": 2452
|
| 8593 |
+
},
|
| 8594 |
+
{
|
| 8595 |
+
"epoch": 0.2499223448296933,
|
| 8596 |
+
"grad_norm": 0.11563865095376968,
|
| 8597 |
+
"learning_rate": 0.001,
|
| 8598 |
+
"loss": 2.0549275875091553,
|
| 8599 |
+
"step": 2454
|
| 8600 |
+
},
|
| 8601 |
+
{
|
| 8602 |
+
"epoch": 0.25012603052230103,
|
| 8603 |
+
"grad_norm": 0.12827977538108826,
|
| 8604 |
+
"learning_rate": 0.001,
|
| 8605 |
+
"loss": 2.158107280731201,
|
| 8606 |
+
"step": 2456
|
| 8607 |
+
},
|
| 8608 |
+
{
|
| 8609 |
+
"epoch": 0.2503297162149088,
|
| 8610 |
+
"grad_norm": 0.1570153385400772,
|
| 8611 |
+
"learning_rate": 0.001,
|
| 8612 |
+
"loss": 2.2887916564941406,
|
| 8613 |
+
"step": 2458
|
| 8614 |
+
},
|
| 8615 |
+
{
|
| 8616 |
+
"epoch": 0.2505334019075165,
|
| 8617 |
+
"grad_norm": 0.1329558789730072,
|
| 8618 |
+
"learning_rate": 0.001,
|
| 8619 |
+
"loss": 2.3444855213165283,
|
| 8620 |
+
"step": 2460
|
| 8621 |
+
},
|
| 8622 |
+
{
|
| 8623 |
+
"epoch": 0.25073708760012425,
|
| 8624 |
+
"grad_norm": 0.1116601973772049,
|
| 8625 |
+
"learning_rate": 0.001,
|
| 8626 |
+
"loss": 2.202824354171753,
|
| 8627 |
+
"step": 2462
|
| 8628 |
+
},
|
| 8629 |
+
{
|
| 8630 |
+
"epoch": 0.250940773292732,
|
| 8631 |
+
"grad_norm": 0.13204801082611084,
|
| 8632 |
+
"learning_rate": 0.001,
|
| 8633 |
+
"loss": 2.1498966217041016,
|
| 8634 |
+
"step": 2464
|
| 8635 |
+
},
|
| 8636 |
+
{
|
| 8637 |
+
"epoch": 0.2511444589853397,
|
| 8638 |
+
"grad_norm": 0.1589539498090744,
|
| 8639 |
+
"learning_rate": 0.001,
|
| 8640 |
+
"loss": 2.1422924995422363,
|
| 8641 |
+
"step": 2466
|
| 8642 |
+
},
|
| 8643 |
+
{
|
| 8644 |
+
"epoch": 0.25134814467794747,
|
| 8645 |
+
"grad_norm": 0.11851079761981964,
|
| 8646 |
+
"learning_rate": 0.001,
|
| 8647 |
+
"loss": 2.159518003463745,
|
| 8648 |
+
"step": 2468
|
| 8649 |
+
},
|
| 8650 |
+
{
|
| 8651 |
+
"epoch": 0.2515518303705552,
|
| 8652 |
+
"grad_norm": 0.14626146852970123,
|
| 8653 |
+
"learning_rate": 0.001,
|
| 8654 |
+
"loss": 2.22283673286438,
|
| 8655 |
+
"step": 2470
|
| 8656 |
+
},
|
| 8657 |
+
{
|
| 8658 |
+
"epoch": 0.25175551606316293,
|
| 8659 |
+
"grad_norm": 0.14713218808174133,
|
| 8660 |
+
"learning_rate": 0.001,
|
| 8661 |
+
"loss": 2.311976909637451,
|
| 8662 |
+
"step": 2472
|
| 8663 |
+
},
|
| 8664 |
+
{
|
| 8665 |
+
"epoch": 0.2519592017557707,
|
| 8666 |
+
"grad_norm": 0.1259654015302658,
|
| 8667 |
+
"learning_rate": 0.001,
|
| 8668 |
+
"loss": 2.3853487968444824,
|
| 8669 |
+
"step": 2474
|
| 8670 |
+
},
|
| 8671 |
+
{
|
| 8672 |
+
"epoch": 0.2521628874483784,
|
| 8673 |
+
"grad_norm": 0.10935270041227341,
|
| 8674 |
+
"learning_rate": 0.001,
|
| 8675 |
+
"loss": 2.216487407684326,
|
| 8676 |
+
"step": 2476
|
| 8677 |
+
},
|
| 8678 |
+
{
|
| 8679 |
+
"epoch": 0.25236657314098615,
|
| 8680 |
+
"grad_norm": 0.11416438221931458,
|
| 8681 |
+
"learning_rate": 0.001,
|
| 8682 |
+
"loss": 2.1839990615844727,
|
| 8683 |
+
"step": 2478
|
| 8684 |
+
},
|
| 8685 |
+
{
|
| 8686 |
+
"epoch": 0.2525702588335939,
|
| 8687 |
+
"grad_norm": 0.11564593762159348,
|
| 8688 |
+
"learning_rate": 0.001,
|
| 8689 |
+
"loss": 2.2234673500061035,
|
| 8690 |
+
"step": 2480
|
| 8691 |
+
},
|
| 8692 |
+
{
|
| 8693 |
+
"epoch": 0.2527739445262016,
|
| 8694 |
+
"grad_norm": 0.15390987694263458,
|
| 8695 |
+
"learning_rate": 0.001,
|
| 8696 |
+
"loss": 2.238325834274292,
|
| 8697 |
+
"step": 2482
|
| 8698 |
+
},
|
| 8699 |
+
{
|
| 8700 |
+
"epoch": 0.25297763021880937,
|
| 8701 |
+
"grad_norm": 0.12190257012844086,
|
| 8702 |
+
"learning_rate": 0.001,
|
| 8703 |
+
"loss": 2.231517791748047,
|
| 8704 |
+
"step": 2484
|
| 8705 |
+
},
|
| 8706 |
+
{
|
| 8707 |
+
"epoch": 0.25318131591141707,
|
| 8708 |
+
"grad_norm": 0.12369199097156525,
|
| 8709 |
+
"learning_rate": 0.001,
|
| 8710 |
+
"loss": 2.1562795639038086,
|
| 8711 |
+
"step": 2486
|
| 8712 |
+
},
|
| 8713 |
+
{
|
| 8714 |
+
"epoch": 0.25338500160402483,
|
| 8715 |
+
"grad_norm": 0.1637447327375412,
|
| 8716 |
+
"learning_rate": 0.001,
|
| 8717 |
+
"loss": 2.193091630935669,
|
| 8718 |
+
"step": 2488
|
| 8719 |
+
},
|
| 8720 |
+
{
|
| 8721 |
+
"epoch": 0.2535886872966326,
|
| 8722 |
+
"grad_norm": 0.11535680294036865,
|
| 8723 |
+
"learning_rate": 0.001,
|
| 8724 |
+
"loss": 2.1275601387023926,
|
| 8725 |
+
"step": 2490
|
| 8726 |
+
},
|
| 8727 |
+
{
|
| 8728 |
+
"epoch": 0.2537923729892403,
|
| 8729 |
+
"grad_norm": 0.1322251260280609,
|
| 8730 |
+
"learning_rate": 0.001,
|
| 8731 |
+
"loss": 2.124635696411133,
|
| 8732 |
+
"step": 2492
|
| 8733 |
+
},
|
| 8734 |
+
{
|
| 8735 |
+
"epoch": 0.25399605868184805,
|
| 8736 |
+
"grad_norm": 0.12674516439437866,
|
| 8737 |
+
"learning_rate": 0.001,
|
| 8738 |
+
"loss": 2.380678653717041,
|
| 8739 |
+
"step": 2494
|
| 8740 |
+
},
|
| 8741 |
+
{
|
| 8742 |
+
"epoch": 0.2541997443744558,
|
| 8743 |
+
"grad_norm": 0.1229044646024704,
|
| 8744 |
+
"learning_rate": 0.001,
|
| 8745 |
+
"loss": 2.294072389602661,
|
| 8746 |
+
"step": 2496
|
| 8747 |
+
},
|
| 8748 |
+
{
|
| 8749 |
+
"epoch": 0.2544034300670635,
|
| 8750 |
+
"grad_norm": 0.1499728113412857,
|
| 8751 |
+
"learning_rate": 0.001,
|
| 8752 |
+
"loss": 2.4008021354675293,
|
| 8753 |
+
"step": 2498
|
| 8754 |
+
},
|
| 8755 |
+
{
|
| 8756 |
+
"epoch": 0.25460711575967127,
|
| 8757 |
+
"grad_norm": 0.14515431225299835,
|
| 8758 |
+
"learning_rate": 0.001,
|
| 8759 |
+
"loss": 2.353992462158203,
|
| 8760 |
+
"step": 2500
|
| 8761 |
+
},
|
| 8762 |
+
{
|
| 8763 |
+
"epoch": 0.25481080145227897,
|
| 8764 |
+
"grad_norm": 0.1462417095899582,
|
| 8765 |
+
"learning_rate": 0.001,
|
| 8766 |
+
"loss": 2.164869785308838,
|
| 8767 |
+
"step": 2502
|
| 8768 |
+
},
|
| 8769 |
+
{
|
| 8770 |
+
"epoch": 0.2550144871448867,
|
| 8771 |
+
"grad_norm": 0.11557002365589142,
|
| 8772 |
+
"learning_rate": 0.001,
|
| 8773 |
+
"loss": 2.2584660053253174,
|
| 8774 |
+
"step": 2504
|
| 8775 |
+
},
|
| 8776 |
+
{
|
| 8777 |
+
"epoch": 0.2552181728374945,
|
| 8778 |
+
"grad_norm": 0.14306089282035828,
|
| 8779 |
+
"learning_rate": 0.001,
|
| 8780 |
+
"loss": 2.2077407836914062,
|
| 8781 |
+
"step": 2506
|
| 8782 |
+
},
|
| 8783 |
+
{
|
| 8784 |
+
"epoch": 0.2554218585301022,
|
| 8785 |
+
"grad_norm": 0.15302926301956177,
|
| 8786 |
+
"learning_rate": 0.001,
|
| 8787 |
+
"loss": 2.244406223297119,
|
| 8788 |
+
"step": 2508
|
| 8789 |
+
},
|
| 8790 |
+
{
|
| 8791 |
+
"epoch": 0.25562554422270994,
|
| 8792 |
+
"grad_norm": 0.12399857491254807,
|
| 8793 |
+
"learning_rate": 0.001,
|
| 8794 |
+
"loss": 2.2401511669158936,
|
| 8795 |
+
"step": 2510
|
| 8796 |
+
},
|
| 8797 |
+
{
|
| 8798 |
+
"epoch": 0.25582922991531765,
|
| 8799 |
+
"grad_norm": 0.12772302329540253,
|
| 8800 |
+
"learning_rate": 0.001,
|
| 8801 |
+
"loss": 2.099644184112549,
|
| 8802 |
+
"step": 2512
|
| 8803 |
+
},
|
| 8804 |
+
{
|
| 8805 |
+
"epoch": 0.2560329156079254,
|
| 8806 |
+
"grad_norm": 0.1432444006204605,
|
| 8807 |
+
"learning_rate": 0.001,
|
| 8808 |
+
"loss": 2.3525986671447754,
|
| 8809 |
+
"step": 2514
|
| 8810 |
+
},
|
| 8811 |
+
{
|
| 8812 |
+
"epoch": 0.25623660130053316,
|
| 8813 |
+
"grad_norm": 0.13702404499053955,
|
| 8814 |
+
"learning_rate": 0.001,
|
| 8815 |
+
"loss": 2.3260555267333984,
|
| 8816 |
+
"step": 2516
|
| 8817 |
+
},
|
| 8818 |
+
{
|
| 8819 |
+
"epoch": 0.25644028699314086,
|
| 8820 |
+
"grad_norm": 0.1140730157494545,
|
| 8821 |
+
"learning_rate": 0.001,
|
| 8822 |
+
"loss": 2.2621805667877197,
|
| 8823 |
+
"step": 2518
|
| 8824 |
+
},
|
| 8825 |
+
{
|
| 8826 |
+
"epoch": 0.2566439726857486,
|
| 8827 |
+
"grad_norm": 0.11614888906478882,
|
| 8828 |
+
"learning_rate": 0.001,
|
| 8829 |
+
"loss": 2.1644275188446045,
|
| 8830 |
+
"step": 2520
|
| 8831 |
+
},
|
| 8832 |
+
{
|
| 8833 |
+
"epoch": 0.2568476583783564,
|
| 8834 |
+
"grad_norm": 0.1176842525601387,
|
| 8835 |
+
"learning_rate": 0.001,
|
| 8836 |
+
"loss": 2.1955811977386475,
|
| 8837 |
+
"step": 2522
|
| 8838 |
+
},
|
| 8839 |
+
{
|
| 8840 |
+
"epoch": 0.2570513440709641,
|
| 8841 |
+
"grad_norm": 0.11319168657064438,
|
| 8842 |
+
"learning_rate": 0.001,
|
| 8843 |
+
"loss": 2.209890842437744,
|
| 8844 |
+
"step": 2524
|
| 8845 |
+
},
|
| 8846 |
+
{
|
| 8847 |
+
"epoch": 0.25725502976357184,
|
| 8848 |
+
"grad_norm": 0.13947781920433044,
|
| 8849 |
+
"learning_rate": 0.001,
|
| 8850 |
+
"loss": 2.2336792945861816,
|
| 8851 |
+
"step": 2526
|
| 8852 |
+
},
|
| 8853 |
+
{
|
| 8854 |
+
"epoch": 0.25745871545617954,
|
| 8855 |
+
"grad_norm": 0.2605893313884735,
|
| 8856 |
+
"learning_rate": 0.001,
|
| 8857 |
+
"loss": 2.3205220699310303,
|
| 8858 |
+
"step": 2528
|
| 8859 |
+
},
|
| 8860 |
+
{
|
| 8861 |
+
"epoch": 0.2576624011487873,
|
| 8862 |
+
"grad_norm": 0.11903031170368195,
|
| 8863 |
+
"learning_rate": 0.001,
|
| 8864 |
+
"loss": 2.265829563140869,
|
| 8865 |
+
"step": 2530
|
| 8866 |
+
},
|
| 8867 |
+
{
|
| 8868 |
+
"epoch": 0.25786608684139506,
|
| 8869 |
+
"grad_norm": 0.15078675746917725,
|
| 8870 |
+
"learning_rate": 0.001,
|
| 8871 |
+
"loss": 2.216618061065674,
|
| 8872 |
+
"step": 2532
|
| 8873 |
+
},
|
| 8874 |
+
{
|
| 8875 |
+
"epoch": 0.25806977253400276,
|
| 8876 |
+
"grad_norm": 0.1161879375576973,
|
| 8877 |
+
"learning_rate": 0.001,
|
| 8878 |
+
"loss": 2.296602725982666,
|
| 8879 |
+
"step": 2534
|
| 8880 |
+
},
|
| 8881 |
+
{
|
| 8882 |
+
"epoch": 0.2582734582266105,
|
| 8883 |
+
"grad_norm": 0.12012317031621933,
|
| 8884 |
+
"learning_rate": 0.001,
|
| 8885 |
+
"loss": 2.2389254570007324,
|
| 8886 |
+
"step": 2536
|
| 8887 |
+
},
|
| 8888 |
+
{
|
| 8889 |
+
"epoch": 0.2584771439192183,
|
| 8890 |
+
"grad_norm": 0.1462898701429367,
|
| 8891 |
+
"learning_rate": 0.001,
|
| 8892 |
+
"loss": 2.378206491470337,
|
| 8893 |
+
"step": 2538
|
| 8894 |
+
},
|
| 8895 |
+
{
|
| 8896 |
+
"epoch": 0.258680829611826,
|
| 8897 |
+
"grad_norm": 0.11691492795944214,
|
| 8898 |
+
"learning_rate": 0.001,
|
| 8899 |
+
"loss": 2.207993984222412,
|
| 8900 |
+
"step": 2540
|
| 8901 |
+
},
|
| 8902 |
+
{
|
| 8903 |
+
"epoch": 0.25888451530443374,
|
| 8904 |
+
"grad_norm": 0.11594048887491226,
|
| 8905 |
+
"learning_rate": 0.001,
|
| 8906 |
+
"loss": 2.3116958141326904,
|
| 8907 |
+
"step": 2542
|
| 8908 |
+
},
|
| 8909 |
+
{
|
| 8910 |
+
"epoch": 0.25908820099704144,
|
| 8911 |
+
"grad_norm": 0.1071212887763977,
|
| 8912 |
+
"learning_rate": 0.001,
|
| 8913 |
+
"loss": 2.2215981483459473,
|
| 8914 |
+
"step": 2544
|
| 8915 |
+
},
|
| 8916 |
+
{
|
| 8917 |
+
"epoch": 0.2592918866896492,
|
| 8918 |
+
"grad_norm": 0.13799069821834564,
|
| 8919 |
+
"learning_rate": 0.001,
|
| 8920 |
+
"loss": 2.171743869781494,
|
| 8921 |
+
"step": 2546
|
| 8922 |
+
},
|
| 8923 |
+
{
|
| 8924 |
+
"epoch": 0.25949557238225696,
|
| 8925 |
+
"grad_norm": 0.10537232458591461,
|
| 8926 |
+
"learning_rate": 0.001,
|
| 8927 |
+
"loss": 2.177974224090576,
|
| 8928 |
+
"step": 2548
|
| 8929 |
+
},
|
| 8930 |
+
{
|
| 8931 |
+
"epoch": 0.25969925807486466,
|
| 8932 |
+
"grad_norm": 0.16781821846961975,
|
| 8933 |
+
"learning_rate": 0.001,
|
| 8934 |
+
"loss": 2.211303472518921,
|
| 8935 |
+
"step": 2550
|
| 8936 |
+
},
|
| 8937 |
+
{
|
| 8938 |
+
"epoch": 0.2599029437674724,
|
| 8939 |
+
"grad_norm": 0.12037919461727142,
|
| 8940 |
+
"learning_rate": 0.001,
|
| 8941 |
+
"loss": 2.1052298545837402,
|
| 8942 |
+
"step": 2552
|
| 8943 |
+
},
|
| 8944 |
+
{
|
| 8945 |
+
"epoch": 0.2601066294600802,
|
| 8946 |
+
"grad_norm": 0.11407136917114258,
|
| 8947 |
+
"learning_rate": 0.001,
|
| 8948 |
+
"loss": 2.2459144592285156,
|
| 8949 |
+
"step": 2554
|
| 8950 |
+
},
|
| 8951 |
+
{
|
| 8952 |
+
"epoch": 0.2603103151526879,
|
| 8953 |
+
"grad_norm": 0.12179651856422424,
|
| 8954 |
+
"learning_rate": 0.001,
|
| 8955 |
+
"loss": 2.2908711433410645,
|
| 8956 |
+
"step": 2556
|
| 8957 |
+
},
|
| 8958 |
+
{
|
| 8959 |
+
"epoch": 0.26051400084529563,
|
| 8960 |
+
"grad_norm": 0.13243801891803741,
|
| 8961 |
+
"learning_rate": 0.001,
|
| 8962 |
+
"loss": 2.249368190765381,
|
| 8963 |
+
"step": 2558
|
| 8964 |
+
},
|
| 8965 |
+
{
|
| 8966 |
+
"epoch": 0.26071768653790334,
|
| 8967 |
+
"grad_norm": 0.14861999452114105,
|
| 8968 |
+
"learning_rate": 0.001,
|
| 8969 |
+
"loss": 2.1337122917175293,
|
| 8970 |
+
"step": 2560
|
| 8971 |
+
},
|
| 8972 |
+
{
|
| 8973 |
+
"epoch": 0.2609213722305111,
|
| 8974 |
+
"grad_norm": 0.11577431112527847,
|
| 8975 |
+
"learning_rate": 0.001,
|
| 8976 |
+
"loss": 2.3043885231018066,
|
| 8977 |
+
"step": 2562
|
| 8978 |
+
},
|
| 8979 |
+
{
|
| 8980 |
+
"epoch": 0.26112505792311885,
|
| 8981 |
+
"grad_norm": 0.14580883085727692,
|
| 8982 |
+
"learning_rate": 0.001,
|
| 8983 |
+
"loss": 2.2461435794830322,
|
| 8984 |
+
"step": 2564
|
| 8985 |
+
},
|
| 8986 |
+
{
|
| 8987 |
+
"epoch": 0.26132874361572656,
|
| 8988 |
+
"grad_norm": 0.1088109016418457,
|
| 8989 |
+
"learning_rate": 0.001,
|
| 8990 |
+
"loss": 2.1832947731018066,
|
| 8991 |
+
"step": 2566
|
| 8992 |
+
},
|
| 8993 |
+
{
|
| 8994 |
+
"epoch": 0.2615324293083343,
|
| 8995 |
+
"grad_norm": 0.11399704217910767,
|
| 8996 |
+
"learning_rate": 0.001,
|
| 8997 |
+
"loss": 2.242194175720215,
|
| 8998 |
+
"step": 2568
|
| 8999 |
+
},
|
| 9000 |
+
{
|
| 9001 |
+
"epoch": 0.26173611500094207,
|
| 9002 |
+
"grad_norm": 0.1680019348859787,
|
| 9003 |
+
"learning_rate": 0.001,
|
| 9004 |
+
"loss": 2.2239298820495605,
|
| 9005 |
+
"step": 2570
|
| 9006 |
+
},
|
| 9007 |
+
{
|
| 9008 |
+
"epoch": 0.2619398006935498,
|
| 9009 |
+
"grad_norm": 0.14158180356025696,
|
| 9010 |
+
"learning_rate": 0.001,
|
| 9011 |
+
"loss": 2.2023544311523438,
|
| 9012 |
+
"step": 2572
|
| 9013 |
+
},
|
| 9014 |
+
{
|
| 9015 |
+
"epoch": 0.26214348638615753,
|
| 9016 |
+
"grad_norm": 0.12665045261383057,
|
| 9017 |
+
"learning_rate": 0.001,
|
| 9018 |
+
"loss": 2.3767213821411133,
|
| 9019 |
+
"step": 2574
|
| 9020 |
+
},
|
| 9021 |
+
{
|
| 9022 |
+
"epoch": 0.26234717207876523,
|
| 9023 |
+
"grad_norm": 0.1360526829957962,
|
| 9024 |
+
"learning_rate": 0.001,
|
| 9025 |
+
"loss": 2.1772518157958984,
|
| 9026 |
+
"step": 2576
|
| 9027 |
+
},
|
| 9028 |
+
{
|
| 9029 |
+
"epoch": 0.262550857771373,
|
| 9030 |
+
"grad_norm": 0.11608131974935532,
|
| 9031 |
+
"learning_rate": 0.001,
|
| 9032 |
+
"loss": 2.171983480453491,
|
| 9033 |
+
"step": 2578
|
| 9034 |
+
},
|
| 9035 |
+
{
|
| 9036 |
+
"epoch": 0.26275454346398075,
|
| 9037 |
+
"grad_norm": 0.11201854050159454,
|
| 9038 |
+
"learning_rate": 0.001,
|
| 9039 |
+
"loss": 2.215081214904785,
|
| 9040 |
+
"step": 2580
|
| 9041 |
+
},
|
| 9042 |
+
{
|
| 9043 |
+
"epoch": 0.26295822915658845,
|
| 9044 |
+
"grad_norm": 0.16245776414871216,
|
| 9045 |
+
"learning_rate": 0.001,
|
| 9046 |
+
"loss": 2.1455609798431396,
|
| 9047 |
+
"step": 2582
|
| 9048 |
+
},
|
| 9049 |
+
{
|
| 9050 |
+
"epoch": 0.2631619148491962,
|
| 9051 |
+
"grad_norm": 0.10045953840017319,
|
| 9052 |
+
"learning_rate": 0.001,
|
| 9053 |
+
"loss": 2.0799124240875244,
|
| 9054 |
+
"step": 2584
|
| 9055 |
+
},
|
| 9056 |
+
{
|
| 9057 |
+
"epoch": 0.26336560054180397,
|
| 9058 |
+
"grad_norm": 0.11225317418575287,
|
| 9059 |
+
"learning_rate": 0.001,
|
| 9060 |
+
"loss": 2.281095027923584,
|
| 9061 |
+
"step": 2586
|
| 9062 |
+
},
|
| 9063 |
+
{
|
| 9064 |
+
"epoch": 0.26356928623441167,
|
| 9065 |
+
"grad_norm": 0.11138707399368286,
|
| 9066 |
+
"learning_rate": 0.001,
|
| 9067 |
+
"loss": 2.293059825897217,
|
| 9068 |
+
"step": 2588
|
| 9069 |
+
},
|
| 9070 |
+
{
|
| 9071 |
+
"epoch": 0.26377297192701943,
|
| 9072 |
+
"grad_norm": 0.13241741061210632,
|
| 9073 |
+
"learning_rate": 0.001,
|
| 9074 |
+
"loss": 2.152883529663086,
|
| 9075 |
+
"step": 2590
|
| 9076 |
+
},
|
| 9077 |
+
{
|
| 9078 |
+
"epoch": 0.26397665761962713,
|
| 9079 |
+
"grad_norm": 0.14563027024269104,
|
| 9080 |
+
"learning_rate": 0.001,
|
| 9081 |
+
"loss": 2.2672085762023926,
|
| 9082 |
+
"step": 2592
|
| 9083 |
+
},
|
| 9084 |
+
{
|
| 9085 |
+
"epoch": 0.2641803433122349,
|
| 9086 |
+
"grad_norm": 0.13751880824565887,
|
| 9087 |
+
"learning_rate": 0.001,
|
| 9088 |
+
"loss": 2.278979778289795,
|
| 9089 |
+
"step": 2594
|
| 9090 |
+
},
|
| 9091 |
+
{
|
| 9092 |
+
"epoch": 0.26438402900484265,
|
| 9093 |
+
"grad_norm": 0.13011743128299713,
|
| 9094 |
+
"learning_rate": 0.001,
|
| 9095 |
+
"loss": 2.1860084533691406,
|
| 9096 |
+
"step": 2596
|
| 9097 |
+
},
|
| 9098 |
+
{
|
| 9099 |
+
"epoch": 0.26458771469745035,
|
| 9100 |
+
"grad_norm": 0.11266366392374039,
|
| 9101 |
+
"learning_rate": 0.001,
|
| 9102 |
+
"loss": 2.1849236488342285,
|
| 9103 |
+
"step": 2598
|
| 9104 |
+
},
|
| 9105 |
+
{
|
| 9106 |
+
"epoch": 0.2647914003900581,
|
| 9107 |
+
"grad_norm": 0.127931147813797,
|
| 9108 |
+
"learning_rate": 0.001,
|
| 9109 |
+
"loss": 2.1793103218078613,
|
| 9110 |
+
"step": 2600
|
| 9111 |
+
},
|
| 9112 |
+
{
|
| 9113 |
+
"epoch": 0.26499508608266586,
|
| 9114 |
+
"grad_norm": 0.10890716314315796,
|
| 9115 |
+
"learning_rate": 0.001,
|
| 9116 |
+
"loss": 2.3062689304351807,
|
| 9117 |
+
"step": 2602
|
| 9118 |
+
},
|
| 9119 |
+
{
|
| 9120 |
+
"epoch": 0.26519877177527357,
|
| 9121 |
+
"grad_norm": 0.16053281724452972,
|
| 9122 |
+
"learning_rate": 0.001,
|
| 9123 |
+
"loss": 2.2867627143859863,
|
| 9124 |
+
"step": 2604
|
| 9125 |
+
},
|
| 9126 |
+
{
|
| 9127 |
+
"epoch": 0.2654024574678813,
|
| 9128 |
+
"grad_norm": 0.11953164637088776,
|
| 9129 |
+
"learning_rate": 0.001,
|
| 9130 |
+
"loss": 2.4339542388916016,
|
| 9131 |
+
"step": 2606
|
| 9132 |
+
},
|
| 9133 |
+
{
|
| 9134 |
+
"epoch": 0.265606143160489,
|
| 9135 |
+
"grad_norm": 0.16321510076522827,
|
| 9136 |
+
"learning_rate": 0.001,
|
| 9137 |
+
"loss": 2.152247428894043,
|
| 9138 |
+
"step": 2608
|
| 9139 |
+
},
|
| 9140 |
+
{
|
| 9141 |
+
"epoch": 0.2658098288530968,
|
| 9142 |
+
"grad_norm": 0.18862083554267883,
|
| 9143 |
+
"learning_rate": 0.001,
|
| 9144 |
+
"loss": 2.3639888763427734,
|
| 9145 |
+
"step": 2610
|
| 9146 |
+
},
|
| 9147 |
+
{
|
| 9148 |
+
"epoch": 0.26601351454570454,
|
| 9149 |
+
"grad_norm": 0.10077431797981262,
|
| 9150 |
+
"learning_rate": 0.001,
|
| 9151 |
+
"loss": 2.0608482360839844,
|
| 9152 |
+
"step": 2612
|
| 9153 |
+
},
|
| 9154 |
+
{
|
| 9155 |
+
"epoch": 0.26621720023831225,
|
| 9156 |
+
"grad_norm": 0.13922734558582306,
|
| 9157 |
+
"learning_rate": 0.001,
|
| 9158 |
+
"loss": 2.2325422763824463,
|
| 9159 |
+
"step": 2614
|
| 9160 |
+
},
|
| 9161 |
+
{
|
| 9162 |
+
"epoch": 0.26642088593092,
|
| 9163 |
+
"grad_norm": 0.12039919942617416,
|
| 9164 |
+
"learning_rate": 0.001,
|
| 9165 |
+
"loss": 2.156432628631592,
|
| 9166 |
+
"step": 2616
|
| 9167 |
+
},
|
| 9168 |
+
{
|
| 9169 |
+
"epoch": 0.26662457162352776,
|
| 9170 |
+
"grad_norm": 0.11588136106729507,
|
| 9171 |
+
"learning_rate": 0.001,
|
| 9172 |
+
"loss": 2.2495508193969727,
|
| 9173 |
+
"step": 2618
|
| 9174 |
+
},
|
| 9175 |
+
{
|
| 9176 |
+
"epoch": 0.26682825731613546,
|
| 9177 |
+
"grad_norm": 0.1091311052441597,
|
| 9178 |
+
"learning_rate": 0.001,
|
| 9179 |
+
"loss": 2.2025794982910156,
|
| 9180 |
+
"step": 2620
|
| 9181 |
+
},
|
| 9182 |
+
{
|
| 9183 |
+
"epoch": 0.2670319430087432,
|
| 9184 |
+
"grad_norm": 0.14030663669109344,
|
| 9185 |
+
"learning_rate": 0.001,
|
| 9186 |
+
"loss": 2.197568893432617,
|
| 9187 |
+
"step": 2622
|
| 9188 |
+
},
|
| 9189 |
+
{
|
| 9190 |
+
"epoch": 0.2672356287013509,
|
| 9191 |
+
"grad_norm": 0.12266213446855545,
|
| 9192 |
+
"learning_rate": 0.001,
|
| 9193 |
+
"loss": 2.289583683013916,
|
| 9194 |
+
"step": 2624
|
| 9195 |
+
},
|
| 9196 |
+
{
|
| 9197 |
+
"epoch": 0.2674393143939587,
|
| 9198 |
+
"grad_norm": 0.18210247159004211,
|
| 9199 |
+
"learning_rate": 0.001,
|
| 9200 |
+
"loss": 2.1881961822509766,
|
| 9201 |
+
"step": 2626
|
| 9202 |
+
},
|
| 9203 |
+
{
|
| 9204 |
+
"epoch": 0.26764300008656644,
|
| 9205 |
+
"grad_norm": 0.11354729533195496,
|
| 9206 |
+
"learning_rate": 0.001,
|
| 9207 |
+
"loss": 2.3412721157073975,
|
| 9208 |
+
"step": 2628
|
| 9209 |
+
},
|
| 9210 |
+
{
|
| 9211 |
+
"epoch": 0.26784668577917414,
|
| 9212 |
+
"grad_norm": 0.115841805934906,
|
| 9213 |
+
"learning_rate": 0.001,
|
| 9214 |
+
"loss": 2.2849974632263184,
|
| 9215 |
+
"step": 2630
|
| 9216 |
+
},
|
| 9217 |
+
{
|
| 9218 |
+
"epoch": 0.2680503714717819,
|
| 9219 |
+
"grad_norm": 0.12043590098619461,
|
| 9220 |
+
"learning_rate": 0.001,
|
| 9221 |
+
"loss": 2.232790470123291,
|
| 9222 |
+
"step": 2632
|
| 9223 |
+
},
|
| 9224 |
+
{
|
| 9225 |
+
"epoch": 0.2682540571643896,
|
| 9226 |
+
"grad_norm": 0.1375025510787964,
|
| 9227 |
+
"learning_rate": 0.001,
|
| 9228 |
+
"loss": 2.1107709407806396,
|
| 9229 |
+
"step": 2634
|
| 9230 |
+
},
|
| 9231 |
+
{
|
| 9232 |
+
"epoch": 0.26845774285699736,
|
| 9233 |
+
"grad_norm": 0.13393042981624603,
|
| 9234 |
+
"learning_rate": 0.001,
|
| 9235 |
+
"loss": 2.335998058319092,
|
| 9236 |
+
"step": 2636
|
| 9237 |
+
},
|
| 9238 |
+
{
|
| 9239 |
+
"epoch": 0.2686614285496051,
|
| 9240 |
+
"grad_norm": 0.13254795968532562,
|
| 9241 |
+
"learning_rate": 0.001,
|
| 9242 |
+
"loss": 2.3033809661865234,
|
| 9243 |
+
"step": 2638
|
| 9244 |
+
},
|
| 9245 |
+
{
|
| 9246 |
+
"epoch": 0.2688651142422128,
|
| 9247 |
+
"grad_norm": 0.12843671441078186,
|
| 9248 |
+
"learning_rate": 0.001,
|
| 9249 |
+
"loss": 2.333094596862793,
|
| 9250 |
+
"step": 2640
|
| 9251 |
+
},
|
| 9252 |
+
{
|
| 9253 |
+
"epoch": 0.2690687999348206,
|
| 9254 |
+
"grad_norm": 0.16022805869579315,
|
| 9255 |
+
"learning_rate": 0.001,
|
| 9256 |
+
"loss": 2.263850688934326,
|
| 9257 |
+
"step": 2642
|
| 9258 |
+
},
|
| 9259 |
+
{
|
| 9260 |
+
"epoch": 0.26927248562742834,
|
| 9261 |
+
"grad_norm": 0.11230074614286423,
|
| 9262 |
+
"learning_rate": 0.001,
|
| 9263 |
+
"loss": 2.2642784118652344,
|
| 9264 |
+
"step": 2644
|
| 9265 |
+
},
|
| 9266 |
+
{
|
| 9267 |
+
"epoch": 0.26947617132003604,
|
| 9268 |
+
"grad_norm": 0.13527797162532806,
|
| 9269 |
+
"learning_rate": 0.001,
|
| 9270 |
+
"loss": 2.193479061126709,
|
| 9271 |
+
"step": 2646
|
| 9272 |
+
},
|
| 9273 |
+
{
|
| 9274 |
+
"epoch": 0.2696798570126438,
|
| 9275 |
+
"grad_norm": 0.1293148547410965,
|
| 9276 |
+
"learning_rate": 0.001,
|
| 9277 |
+
"loss": 2.265923500061035,
|
| 9278 |
+
"step": 2648
|
| 9279 |
+
},
|
| 9280 |
+
{
|
| 9281 |
+
"epoch": 0.2698835427052515,
|
| 9282 |
+
"grad_norm": 0.12284532934427261,
|
| 9283 |
+
"learning_rate": 0.001,
|
| 9284 |
+
"loss": 2.208169460296631,
|
| 9285 |
+
"step": 2650
|
| 9286 |
+
},
|
| 9287 |
+
{
|
| 9288 |
+
"epoch": 0.27008722839785926,
|
| 9289 |
+
"grad_norm": 0.12729403376579285,
|
| 9290 |
+
"learning_rate": 0.001,
|
| 9291 |
+
"loss": 2.37559175491333,
|
| 9292 |
+
"step": 2652
|
| 9293 |
+
},
|
| 9294 |
+
{
|
| 9295 |
+
"epoch": 0.270290914090467,
|
| 9296 |
+
"grad_norm": 0.14475327730178833,
|
| 9297 |
+
"learning_rate": 0.001,
|
| 9298 |
+
"loss": 2.1450417041778564,
|
| 9299 |
+
"step": 2654
|
| 9300 |
+
},
|
| 9301 |
+
{
|
| 9302 |
+
"epoch": 0.2704945997830747,
|
| 9303 |
+
"grad_norm": 0.1124851256608963,
|
| 9304 |
+
"learning_rate": 0.001,
|
| 9305 |
+
"loss": 2.154197931289673,
|
| 9306 |
+
"step": 2656
|
| 9307 |
+
},
|
| 9308 |
+
{
|
| 9309 |
+
"epoch": 0.2706982854756825,
|
| 9310 |
+
"grad_norm": 0.11966680735349655,
|
| 9311 |
+
"learning_rate": 0.001,
|
| 9312 |
+
"loss": 2.3112502098083496,
|
| 9313 |
+
"step": 2658
|
| 9314 |
+
},
|
| 9315 |
+
{
|
| 9316 |
+
"epoch": 0.27090197116829023,
|
| 9317 |
+
"grad_norm": 0.10652370005846024,
|
| 9318 |
+
"learning_rate": 0.001,
|
| 9319 |
+
"loss": 2.2478370666503906,
|
| 9320 |
+
"step": 2660
|
| 9321 |
+
},
|
| 9322 |
+
{
|
| 9323 |
+
"epoch": 0.27110565686089794,
|
| 9324 |
+
"grad_norm": 0.12037665396928787,
|
| 9325 |
+
"learning_rate": 0.001,
|
| 9326 |
+
"loss": 2.200302839279175,
|
| 9327 |
+
"step": 2662
|
| 9328 |
+
},
|
| 9329 |
+
{
|
| 9330 |
+
"epoch": 0.2713093425535057,
|
| 9331 |
+
"grad_norm": 0.12574388086795807,
|
| 9332 |
+
"learning_rate": 0.001,
|
| 9333 |
+
"loss": 2.282327890396118,
|
| 9334 |
+
"step": 2664
|
| 9335 |
+
},
|
| 9336 |
+
{
|
| 9337 |
+
"epoch": 0.2715130282461134,
|
| 9338 |
+
"grad_norm": 0.12543271481990814,
|
| 9339 |
+
"learning_rate": 0.001,
|
| 9340 |
+
"loss": 2.125049591064453,
|
| 9341 |
+
"step": 2666
|
| 9342 |
+
},
|
| 9343 |
+
{
|
| 9344 |
+
"epoch": 0.27171671393872115,
|
| 9345 |
+
"grad_norm": 0.11538044363260269,
|
| 9346 |
+
"learning_rate": 0.001,
|
| 9347 |
+
"loss": 2.1202750205993652,
|
| 9348 |
+
"step": 2668
|
| 9349 |
+
},
|
| 9350 |
+
{
|
| 9351 |
+
"epoch": 0.2719203996313289,
|
| 9352 |
+
"grad_norm": 0.187924325466156,
|
| 9353 |
+
"learning_rate": 0.001,
|
| 9354 |
+
"loss": 2.2101354598999023,
|
| 9355 |
+
"step": 2670
|
| 9356 |
+
},
|
| 9357 |
+
{
|
| 9358 |
+
"epoch": 0.2721240853239366,
|
| 9359 |
+
"grad_norm": 0.14874625205993652,
|
| 9360 |
+
"learning_rate": 0.001,
|
| 9361 |
+
"loss": 2.3126096725463867,
|
| 9362 |
+
"step": 2672
|
| 9363 |
+
},
|
| 9364 |
+
{
|
| 9365 |
+
"epoch": 0.2723277710165444,
|
| 9366 |
+
"grad_norm": 0.14120592176914215,
|
| 9367 |
+
"learning_rate": 0.001,
|
| 9368 |
+
"loss": 2.2418274879455566,
|
| 9369 |
+
"step": 2674
|
| 9370 |
+
},
|
| 9371 |
+
{
|
| 9372 |
+
"epoch": 0.27253145670915213,
|
| 9373 |
+
"grad_norm": 0.1680409014225006,
|
| 9374 |
+
"learning_rate": 0.001,
|
| 9375 |
+
"loss": 2.1097233295440674,
|
| 9376 |
+
"step": 2676
|
| 9377 |
+
},
|
| 9378 |
+
{
|
| 9379 |
+
"epoch": 0.27273514240175983,
|
| 9380 |
+
"grad_norm": 0.1910484880208969,
|
| 9381 |
+
"learning_rate": 0.001,
|
| 9382 |
+
"loss": 2.317147731781006,
|
| 9383 |
+
"step": 2678
|
| 9384 |
+
},
|
| 9385 |
+
{
|
| 9386 |
+
"epoch": 0.2729388280943676,
|
| 9387 |
+
"grad_norm": 0.11034401506185532,
|
| 9388 |
+
"learning_rate": 0.001,
|
| 9389 |
+
"loss": 2.3379340171813965,
|
| 9390 |
+
"step": 2680
|
| 9391 |
+
},
|
| 9392 |
+
{
|
| 9393 |
+
"epoch": 0.2731425137869753,
|
| 9394 |
+
"grad_norm": 0.15769143402576447,
|
| 9395 |
+
"learning_rate": 0.001,
|
| 9396 |
+
"loss": 2.2032222747802734,
|
| 9397 |
+
"step": 2682
|
| 9398 |
+
},
|
| 9399 |
+
{
|
| 9400 |
+
"epoch": 0.27334619947958305,
|
| 9401 |
+
"grad_norm": 0.14189593493938446,
|
| 9402 |
+
"learning_rate": 0.001,
|
| 9403 |
+
"loss": 2.2042741775512695,
|
| 9404 |
+
"step": 2684
|
| 9405 |
+
},
|
| 9406 |
+
{
|
| 9407 |
+
"epoch": 0.2735498851721908,
|
| 9408 |
+
"grad_norm": 0.13151733577251434,
|
| 9409 |
+
"learning_rate": 0.001,
|
| 9410 |
+
"loss": 2.3284454345703125,
|
| 9411 |
+
"step": 2686
|
| 9412 |
+
},
|
| 9413 |
+
{
|
| 9414 |
+
"epoch": 0.2737535708647985,
|
| 9415 |
+
"grad_norm": 0.1409992128610611,
|
| 9416 |
+
"learning_rate": 0.001,
|
| 9417 |
+
"loss": 2.24107027053833,
|
| 9418 |
+
"step": 2688
|
| 9419 |
+
},
|
| 9420 |
+
{
|
| 9421 |
+
"epoch": 0.27395725655740627,
|
| 9422 |
+
"grad_norm": 0.1207733228802681,
|
| 9423 |
+
"learning_rate": 0.001,
|
| 9424 |
+
"loss": 2.1382782459259033,
|
| 9425 |
+
"step": 2690
|
| 9426 |
+
},
|
| 9427 |
+
{
|
| 9428 |
+
"epoch": 0.27416094225001403,
|
| 9429 |
+
"grad_norm": 0.18676437437534332,
|
| 9430 |
+
"learning_rate": 0.001,
|
| 9431 |
+
"loss": 2.124037027359009,
|
| 9432 |
+
"step": 2692
|
| 9433 |
+
},
|
| 9434 |
+
{
|
| 9435 |
+
"epoch": 0.27436462794262173,
|
| 9436 |
+
"grad_norm": 0.1174948513507843,
|
| 9437 |
+
"learning_rate": 0.001,
|
| 9438 |
+
"loss": 2.190953016281128,
|
| 9439 |
+
"step": 2694
|
| 9440 |
+
},
|
| 9441 |
+
{
|
| 9442 |
+
"epoch": 0.2745683136352295,
|
| 9443 |
+
"grad_norm": 0.18644596636295319,
|
| 9444 |
+
"learning_rate": 0.001,
|
| 9445 |
+
"loss": 2.288017749786377,
|
| 9446 |
+
"step": 2696
|
| 9447 |
+
},
|
| 9448 |
+
{
|
| 9449 |
+
"epoch": 0.2747719993278372,
|
| 9450 |
+
"grad_norm": 0.17893360555171967,
|
| 9451 |
+
"learning_rate": 0.001,
|
| 9452 |
+
"loss": 2.196091413497925,
|
| 9453 |
+
"step": 2698
|
| 9454 |
+
},
|
| 9455 |
+
{
|
| 9456 |
+
"epoch": 0.27497568502044495,
|
| 9457 |
+
"grad_norm": 0.12849412858486176,
|
| 9458 |
+
"learning_rate": 0.001,
|
| 9459 |
+
"loss": 2.234558582305908,
|
| 9460 |
+
"step": 2700
|
| 9461 |
+
},
|
| 9462 |
+
{
|
| 9463 |
+
"epoch": 0.2751793707130527,
|
| 9464 |
+
"grad_norm": 0.1161603033542633,
|
| 9465 |
+
"learning_rate": 0.001,
|
| 9466 |
+
"loss": 2.1817355155944824,
|
| 9467 |
+
"step": 2702
|
| 9468 |
+
},
|
| 9469 |
+
{
|
| 9470 |
+
"epoch": 0.2753830564056604,
|
| 9471 |
+
"grad_norm": 0.14464206993579865,
|
| 9472 |
+
"learning_rate": 0.001,
|
| 9473 |
+
"loss": 2.1868491172790527,
|
| 9474 |
+
"step": 2704
|
| 9475 |
+
},
|
| 9476 |
+
{
|
| 9477 |
+
"epoch": 0.27558674209826817,
|
| 9478 |
+
"grad_norm": 0.15228553116321564,
|
| 9479 |
+
"learning_rate": 0.001,
|
| 9480 |
+
"loss": 2.2760324478149414,
|
| 9481 |
+
"step": 2706
|
| 9482 |
+
},
|
| 9483 |
+
{
|
| 9484 |
+
"epoch": 0.2757904277908759,
|
| 9485 |
+
"grad_norm": 0.13040511310100555,
|
| 9486 |
+
"learning_rate": 0.001,
|
| 9487 |
+
"loss": 2.264056444168091,
|
| 9488 |
+
"step": 2708
|
| 9489 |
+
},
|
| 9490 |
+
{
|
| 9491 |
+
"epoch": 0.2759941134834836,
|
| 9492 |
+
"grad_norm": 0.1410803347826004,
|
| 9493 |
+
"learning_rate": 0.001,
|
| 9494 |
+
"loss": 2.3007102012634277,
|
| 9495 |
+
"step": 2710
|
| 9496 |
+
},
|
| 9497 |
+
{
|
| 9498 |
+
"epoch": 0.2761977991760914,
|
| 9499 |
+
"grad_norm": 0.16221722960472107,
|
| 9500 |
+
"learning_rate": 0.001,
|
| 9501 |
+
"loss": 2.198531150817871,
|
| 9502 |
+
"step": 2712
|
| 9503 |
+
},
|
| 9504 |
+
{
|
| 9505 |
+
"epoch": 0.2764014848686991,
|
| 9506 |
+
"grad_norm": 0.11859212070703506,
|
| 9507 |
+
"learning_rate": 0.001,
|
| 9508 |
+
"loss": 2.175461769104004,
|
| 9509 |
+
"step": 2714
|
| 9510 |
+
},
|
| 9511 |
+
{
|
| 9512 |
+
"epoch": 0.27660517056130685,
|
| 9513 |
+
"grad_norm": 0.13209441304206848,
|
| 9514 |
+
"learning_rate": 0.001,
|
| 9515 |
+
"loss": 2.2433438301086426,
|
| 9516 |
+
"step": 2716
|
| 9517 |
+
},
|
| 9518 |
+
{
|
| 9519 |
+
"epoch": 0.2768088562539146,
|
| 9520 |
+
"grad_norm": 0.16816027462482452,
|
| 9521 |
+
"learning_rate": 0.001,
|
| 9522 |
+
"loss": 2.2644829750061035,
|
| 9523 |
+
"step": 2718
|
| 9524 |
+
},
|
| 9525 |
+
{
|
| 9526 |
+
"epoch": 0.2770125419465223,
|
| 9527 |
+
"grad_norm": 0.12626010179519653,
|
| 9528 |
+
"learning_rate": 0.001,
|
| 9529 |
+
"loss": 2.136946201324463,
|
| 9530 |
+
"step": 2720
|
| 9531 |
+
},
|
| 9532 |
+
{
|
| 9533 |
+
"epoch": 0.27721622763913006,
|
| 9534 |
+
"grad_norm": 0.10263483226299286,
|
| 9535 |
+
"learning_rate": 0.001,
|
| 9536 |
+
"loss": 2.080695629119873,
|
| 9537 |
+
"step": 2722
|
| 9538 |
+
},
|
| 9539 |
+
{
|
| 9540 |
+
"epoch": 0.2774199133317378,
|
| 9541 |
+
"grad_norm": 0.13575968146324158,
|
| 9542 |
+
"learning_rate": 0.001,
|
| 9543 |
+
"loss": 2.120053768157959,
|
| 9544 |
+
"step": 2724
|
| 9545 |
+
},
|
| 9546 |
+
{
|
| 9547 |
+
"epoch": 0.2776235990243455,
|
| 9548 |
+
"grad_norm": 0.13683274388313293,
|
| 9549 |
+
"learning_rate": 0.001,
|
| 9550 |
+
"loss": 2.3494646549224854,
|
| 9551 |
+
"step": 2726
|
| 9552 |
+
},
|
| 9553 |
+
{
|
| 9554 |
+
"epoch": 0.2778272847169533,
|
| 9555 |
+
"grad_norm": 0.1262296587228775,
|
| 9556 |
+
"learning_rate": 0.001,
|
| 9557 |
+
"loss": 2.201550006866455,
|
| 9558 |
+
"step": 2728
|
| 9559 |
+
},
|
| 9560 |
+
{
|
| 9561 |
+
"epoch": 0.278030970409561,
|
| 9562 |
+
"grad_norm": 0.12005586922168732,
|
| 9563 |
+
"learning_rate": 0.001,
|
| 9564 |
+
"loss": 2.250321626663208,
|
| 9565 |
+
"step": 2730
|
| 9566 |
+
},
|
| 9567 |
+
{
|
| 9568 |
+
"epoch": 0.27823465610216874,
|
| 9569 |
+
"grad_norm": 0.12513411045074463,
|
| 9570 |
+
"learning_rate": 0.001,
|
| 9571 |
+
"loss": 2.275740146636963,
|
| 9572 |
+
"step": 2732
|
| 9573 |
+
},
|
| 9574 |
+
{
|
| 9575 |
+
"epoch": 0.2784383417947765,
|
| 9576 |
+
"grad_norm": 0.12613843381404877,
|
| 9577 |
+
"learning_rate": 0.001,
|
| 9578 |
+
"loss": 2.195952892303467,
|
| 9579 |
+
"step": 2734
|
| 9580 |
+
},
|
| 9581 |
+
{
|
| 9582 |
+
"epoch": 0.2786420274873842,
|
| 9583 |
+
"grad_norm": 0.13212727010250092,
|
| 9584 |
+
"learning_rate": 0.001,
|
| 9585 |
+
"loss": 2.2753710746765137,
|
| 9586 |
+
"step": 2736
|
| 9587 |
+
},
|
| 9588 |
+
{
|
| 9589 |
+
"epoch": 0.27884571317999196,
|
| 9590 |
+
"grad_norm": 0.11923087388277054,
|
| 9591 |
+
"learning_rate": 0.001,
|
| 9592 |
+
"loss": 2.1646358966827393,
|
| 9593 |
+
"step": 2738
|
| 9594 |
+
},
|
| 9595 |
+
{
|
| 9596 |
+
"epoch": 0.2790493988725997,
|
| 9597 |
+
"grad_norm": 0.11962882429361343,
|
| 9598 |
+
"learning_rate": 0.001,
|
| 9599 |
+
"loss": 2.190734386444092,
|
| 9600 |
+
"step": 2740
|
| 9601 |
+
},
|
| 9602 |
+
{
|
| 9603 |
+
"epoch": 0.2792530845652074,
|
| 9604 |
+
"grad_norm": 0.11848846077919006,
|
| 9605 |
+
"learning_rate": 0.001,
|
| 9606 |
+
"loss": 2.2708523273468018,
|
| 9607 |
+
"step": 2742
|
| 9608 |
+
},
|
| 9609 |
+
{
|
| 9610 |
+
"epoch": 0.2794567702578152,
|
| 9611 |
+
"grad_norm": 0.13870587944984436,
|
| 9612 |
+
"learning_rate": 0.001,
|
| 9613 |
+
"loss": 2.334907054901123,
|
| 9614 |
+
"step": 2744
|
| 9615 |
+
},
|
| 9616 |
+
{
|
| 9617 |
+
"epoch": 0.2796604559504229,
|
| 9618 |
+
"grad_norm": 0.12782078981399536,
|
| 9619 |
+
"learning_rate": 0.001,
|
| 9620 |
+
"loss": 2.426814556121826,
|
| 9621 |
+
"step": 2746
|
| 9622 |
+
},
|
| 9623 |
+
{
|
| 9624 |
+
"epoch": 0.27986414164303064,
|
| 9625 |
+
"grad_norm": 0.1474793404340744,
|
| 9626 |
+
"learning_rate": 0.001,
|
| 9627 |
+
"loss": 2.2919235229492188,
|
| 9628 |
+
"step": 2748
|
| 9629 |
+
},
|
| 9630 |
+
{
|
| 9631 |
+
"epoch": 0.2800678273356384,
|
| 9632 |
+
"grad_norm": 0.15307286381721497,
|
| 9633 |
+
"learning_rate": 0.001,
|
| 9634 |
+
"loss": 2.1787068843841553,
|
| 9635 |
+
"step": 2750
|
| 9636 |
+
},
|
| 9637 |
+
{
|
| 9638 |
+
"epoch": 0.2802715130282461,
|
| 9639 |
+
"grad_norm": 0.21244055032730103,
|
| 9640 |
+
"learning_rate": 0.001,
|
| 9641 |
+
"loss": 2.166435480117798,
|
| 9642 |
+
"step": 2752
|
| 9643 |
+
},
|
| 9644 |
+
{
|
| 9645 |
+
"epoch": 0.28047519872085386,
|
| 9646 |
+
"grad_norm": 0.17185427248477936,
|
| 9647 |
+
"learning_rate": 0.001,
|
| 9648 |
+
"loss": 2.158736228942871,
|
| 9649 |
+
"step": 2754
|
| 9650 |
+
},
|
| 9651 |
+
{
|
| 9652 |
+
"epoch": 0.28067888441346156,
|
| 9653 |
+
"grad_norm": 0.11628913134336472,
|
| 9654 |
+
"learning_rate": 0.001,
|
| 9655 |
+
"loss": 2.369392156600952,
|
| 9656 |
+
"step": 2756
|
| 9657 |
+
},
|
| 9658 |
+
{
|
| 9659 |
+
"epoch": 0.2808825701060693,
|
| 9660 |
+
"grad_norm": 0.13531611859798431,
|
| 9661 |
+
"learning_rate": 0.001,
|
| 9662 |
+
"loss": 2.221059799194336,
|
| 9663 |
+
"step": 2758
|
| 9664 |
+
},
|
| 9665 |
+
{
|
| 9666 |
+
"epoch": 0.2810862557986771,
|
| 9667 |
+
"grad_norm": 0.10144199430942535,
|
| 9668 |
+
"learning_rate": 0.001,
|
| 9669 |
+
"loss": 2.1945834159851074,
|
| 9670 |
+
"step": 2760
|
| 9671 |
+
},
|
| 9672 |
+
{
|
| 9673 |
+
"epoch": 0.2812899414912848,
|
| 9674 |
+
"grad_norm": 0.12250307202339172,
|
| 9675 |
+
"learning_rate": 0.001,
|
| 9676 |
+
"loss": 2.1723380088806152,
|
| 9677 |
+
"step": 2762
|
| 9678 |
+
},
|
| 9679 |
+
{
|
| 9680 |
+
"epoch": 0.28149362718389254,
|
| 9681 |
+
"grad_norm": 0.20078040659427643,
|
| 9682 |
+
"learning_rate": 0.001,
|
| 9683 |
+
"loss": 2.2696096897125244,
|
| 9684 |
+
"step": 2764
|
| 9685 |
+
},
|
| 9686 |
+
{
|
| 9687 |
+
"epoch": 0.2816973128765003,
|
| 9688 |
+
"grad_norm": 0.1168745830655098,
|
| 9689 |
+
"learning_rate": 0.001,
|
| 9690 |
+
"loss": 2.2752878665924072,
|
| 9691 |
+
"step": 2766
|
| 9692 |
+
},
|
| 9693 |
+
{
|
| 9694 |
+
"epoch": 0.281900998569108,
|
| 9695 |
+
"grad_norm": 0.13565461337566376,
|
| 9696 |
+
"learning_rate": 0.001,
|
| 9697 |
+
"loss": 2.1242947578430176,
|
| 9698 |
+
"step": 2768
|
| 9699 |
+
},
|
| 9700 |
+
{
|
| 9701 |
+
"epoch": 0.28210468426171575,
|
| 9702 |
+
"grad_norm": 0.10728311538696289,
|
| 9703 |
+
"learning_rate": 0.001,
|
| 9704 |
+
"loss": 2.1414921283721924,
|
| 9705 |
+
"step": 2770
|
| 9706 |
+
},
|
| 9707 |
+
{
|
| 9708 |
+
"epoch": 0.28230836995432346,
|
| 9709 |
+
"grad_norm": 0.15147177875041962,
|
| 9710 |
+
"learning_rate": 0.001,
|
| 9711 |
+
"loss": 2.3697502613067627,
|
| 9712 |
+
"step": 2772
|
| 9713 |
+
},
|
| 9714 |
+
{
|
| 9715 |
+
"epoch": 0.2825120556469312,
|
| 9716 |
+
"grad_norm": 0.158035010099411,
|
| 9717 |
+
"learning_rate": 0.001,
|
| 9718 |
+
"loss": 2.3428702354431152,
|
| 9719 |
+
"step": 2774
|
| 9720 |
+
},
|
| 9721 |
+
{
|
| 9722 |
+
"epoch": 0.282715741339539,
|
| 9723 |
+
"grad_norm": 0.15726393461227417,
|
| 9724 |
+
"learning_rate": 0.001,
|
| 9725 |
+
"loss": 2.1368656158447266,
|
| 9726 |
+
"step": 2776
|
| 9727 |
+
},
|
| 9728 |
+
{
|
| 9729 |
+
"epoch": 0.2829194270321467,
|
| 9730 |
+
"grad_norm": 0.1746235191822052,
|
| 9731 |
+
"learning_rate": 0.001,
|
| 9732 |
+
"loss": 2.1313743591308594,
|
| 9733 |
+
"step": 2778
|
| 9734 |
+
},
|
| 9735 |
+
{
|
| 9736 |
+
"epoch": 0.28312311272475443,
|
| 9737 |
+
"grad_norm": 0.11663658916950226,
|
| 9738 |
+
"learning_rate": 0.001,
|
| 9739 |
+
"loss": 2.355541944503784,
|
| 9740 |
+
"step": 2780
|
| 9741 |
+
},
|
| 9742 |
+
{
|
| 9743 |
+
"epoch": 0.2833267984173622,
|
| 9744 |
+
"grad_norm": 0.12054722011089325,
|
| 9745 |
+
"learning_rate": 0.001,
|
| 9746 |
+
"loss": 2.1068291664123535,
|
| 9747 |
+
"step": 2782
|
| 9748 |
+
},
|
| 9749 |
+
{
|
| 9750 |
+
"epoch": 0.2835304841099699,
|
| 9751 |
+
"grad_norm": 0.1535932868719101,
|
| 9752 |
+
"learning_rate": 0.001,
|
| 9753 |
+
"loss": 2.2932066917419434,
|
| 9754 |
+
"step": 2784
|
| 9755 |
+
},
|
| 9756 |
+
{
|
| 9757 |
+
"epoch": 0.28373416980257765,
|
| 9758 |
+
"grad_norm": 0.190424844622612,
|
| 9759 |
+
"learning_rate": 0.001,
|
| 9760 |
+
"loss": 2.265789747238159,
|
| 9761 |
+
"step": 2786
|
| 9762 |
+
},
|
| 9763 |
+
{
|
| 9764 |
+
"epoch": 0.28393785549518535,
|
| 9765 |
+
"grad_norm": 0.11368729919195175,
|
| 9766 |
+
"learning_rate": 0.001,
|
| 9767 |
+
"loss": 2.2834763526916504,
|
| 9768 |
+
"step": 2788
|
| 9769 |
+
},
|
| 9770 |
+
{
|
| 9771 |
+
"epoch": 0.2841415411877931,
|
| 9772 |
+
"grad_norm": 0.21125321090221405,
|
| 9773 |
+
"learning_rate": 0.001,
|
| 9774 |
+
"loss": 2.3401148319244385,
|
| 9775 |
+
"step": 2790
|
| 9776 |
+
},
|
| 9777 |
+
{
|
| 9778 |
+
"epoch": 0.28434522688040087,
|
| 9779 |
+
"grad_norm": 0.14262887835502625,
|
| 9780 |
+
"learning_rate": 0.001,
|
| 9781 |
+
"loss": 2.116389751434326,
|
| 9782 |
+
"step": 2792
|
| 9783 |
+
},
|
| 9784 |
+
{
|
| 9785 |
+
"epoch": 0.28454891257300857,
|
| 9786 |
+
"grad_norm": 0.12400005757808685,
|
| 9787 |
+
"learning_rate": 0.001,
|
| 9788 |
+
"loss": 2.2731122970581055,
|
| 9789 |
+
"step": 2794
|
| 9790 |
+
},
|
| 9791 |
+
{
|
| 9792 |
+
"epoch": 0.28475259826561633,
|
| 9793 |
+
"grad_norm": 0.13200870156288147,
|
| 9794 |
+
"learning_rate": 0.001,
|
| 9795 |
+
"loss": 2.3588614463806152,
|
| 9796 |
+
"step": 2796
|
| 9797 |
+
},
|
| 9798 |
+
{
|
| 9799 |
+
"epoch": 0.2849562839582241,
|
| 9800 |
+
"grad_norm": 0.15799500048160553,
|
| 9801 |
+
"learning_rate": 0.001,
|
| 9802 |
+
"loss": 2.207251787185669,
|
| 9803 |
+
"step": 2798
|
| 9804 |
+
},
|
| 9805 |
+
{
|
| 9806 |
+
"epoch": 0.2851599696508318,
|
| 9807 |
+
"grad_norm": 0.12848299741744995,
|
| 9808 |
+
"learning_rate": 0.001,
|
| 9809 |
+
"loss": 2.300833225250244,
|
| 9810 |
+
"step": 2800
|
| 9811 |
+
},
|
| 9812 |
+
{
|
| 9813 |
+
"epoch": 0.28536365534343955,
|
| 9814 |
+
"grad_norm": 0.12269412726163864,
|
| 9815 |
+
"learning_rate": 0.001,
|
| 9816 |
+
"loss": 2.191100597381592,
|
| 9817 |
+
"step": 2802
|
| 9818 |
+
},
|
| 9819 |
+
{
|
| 9820 |
+
"epoch": 0.28556734103604725,
|
| 9821 |
+
"grad_norm": 0.1329207420349121,
|
| 9822 |
+
"learning_rate": 0.001,
|
| 9823 |
+
"loss": 2.1269264221191406,
|
| 9824 |
+
"step": 2804
|
| 9825 |
+
},
|
| 9826 |
+
{
|
| 9827 |
+
"epoch": 0.285771026728655,
|
| 9828 |
+
"grad_norm": 0.14722250401973724,
|
| 9829 |
+
"learning_rate": 0.001,
|
| 9830 |
+
"loss": 2.0932044982910156,
|
| 9831 |
+
"step": 2806
|
| 9832 |
+
},
|
| 9833 |
+
{
|
| 9834 |
+
"epoch": 0.28597471242126277,
|
| 9835 |
+
"grad_norm": 0.16723033785820007,
|
| 9836 |
+
"learning_rate": 0.001,
|
| 9837 |
+
"loss": 2.320561408996582,
|
| 9838 |
+
"step": 2808
|
| 9839 |
+
},
|
| 9840 |
+
{
|
| 9841 |
+
"epoch": 0.28617839811387047,
|
| 9842 |
+
"grad_norm": 0.1321042776107788,
|
| 9843 |
+
"learning_rate": 0.001,
|
| 9844 |
+
"loss": 2.280291795730591,
|
| 9845 |
+
"step": 2810
|
| 9846 |
+
},
|
| 9847 |
+
{
|
| 9848 |
+
"epoch": 0.2863820838064782,
|
| 9849 |
+
"grad_norm": 0.1455741822719574,
|
| 9850 |
+
"learning_rate": 0.001,
|
| 9851 |
+
"loss": 2.1647353172302246,
|
| 9852 |
+
"step": 2812
|
| 9853 |
+
},
|
| 9854 |
+
{
|
| 9855 |
+
"epoch": 0.286585769499086,
|
| 9856 |
+
"grad_norm": 0.12242356687784195,
|
| 9857 |
+
"learning_rate": 0.001,
|
| 9858 |
+
"loss": 2.126441240310669,
|
| 9859 |
+
"step": 2814
|
| 9860 |
+
},
|
| 9861 |
+
{
|
| 9862 |
+
"epoch": 0.2867894551916937,
|
| 9863 |
+
"grad_norm": 0.15124623477458954,
|
| 9864 |
+
"learning_rate": 0.001,
|
| 9865 |
+
"loss": 2.094339370727539,
|
| 9866 |
+
"step": 2816
|
| 9867 |
+
},
|
| 9868 |
+
{
|
| 9869 |
+
"epoch": 0.28699314088430145,
|
| 9870 |
+
"grad_norm": 0.15034911036491394,
|
| 9871 |
+
"learning_rate": 0.001,
|
| 9872 |
+
"loss": 2.0807104110717773,
|
| 9873 |
+
"step": 2818
|
| 9874 |
+
},
|
| 9875 |
+
{
|
| 9876 |
+
"epoch": 0.28719682657690915,
|
| 9877 |
+
"grad_norm": 0.12756751477718353,
|
| 9878 |
+
"learning_rate": 0.001,
|
| 9879 |
+
"loss": 2.2227602005004883,
|
| 9880 |
+
"step": 2820
|
| 9881 |
+
},
|
| 9882 |
+
{
|
| 9883 |
+
"epoch": 0.2874005122695169,
|
| 9884 |
+
"grad_norm": 0.14330913126468658,
|
| 9885 |
+
"learning_rate": 0.001,
|
| 9886 |
+
"loss": 2.2062745094299316,
|
| 9887 |
+
"step": 2822
|
| 9888 |
+
},
|
| 9889 |
+
{
|
| 9890 |
+
"epoch": 0.28760419796212466,
|
| 9891 |
+
"grad_norm": 0.12252888083457947,
|
| 9892 |
+
"learning_rate": 0.001,
|
| 9893 |
+
"loss": 2.273329496383667,
|
| 9894 |
+
"step": 2824
|
| 9895 |
+
},
|
| 9896 |
+
{
|
| 9897 |
+
"epoch": 0.28780788365473237,
|
| 9898 |
+
"grad_norm": 0.13872644305229187,
|
| 9899 |
+
"learning_rate": 0.001,
|
| 9900 |
+
"loss": 2.199389696121216,
|
| 9901 |
+
"step": 2826
|
| 9902 |
+
},
|
| 9903 |
+
{
|
| 9904 |
+
"epoch": 0.2880115693473401,
|
| 9905 |
+
"grad_norm": 0.15420307219028473,
|
| 9906 |
+
"learning_rate": 0.001,
|
| 9907 |
+
"loss": 2.340616226196289,
|
| 9908 |
+
"step": 2828
|
| 9909 |
+
},
|
| 9910 |
+
{
|
| 9911 |
+
"epoch": 0.2882152550399479,
|
| 9912 |
+
"grad_norm": 0.14609819650650024,
|
| 9913 |
+
"learning_rate": 0.001,
|
| 9914 |
+
"loss": 2.2589943408966064,
|
| 9915 |
+
"step": 2830
|
| 9916 |
+
},
|
| 9917 |
+
{
|
| 9918 |
+
"epoch": 0.2884189407325556,
|
| 9919 |
+
"grad_norm": 0.12604065239429474,
|
| 9920 |
+
"learning_rate": 0.001,
|
| 9921 |
+
"loss": 2.3338418006896973,
|
| 9922 |
+
"step": 2832
|
| 9923 |
+
},
|
| 9924 |
+
{
|
| 9925 |
+
"epoch": 0.28862262642516334,
|
| 9926 |
+
"grad_norm": 0.10743481665849686,
|
| 9927 |
+
"learning_rate": 0.001,
|
| 9928 |
+
"loss": 2.1535425186157227,
|
| 9929 |
+
"step": 2834
|
| 9930 |
+
},
|
| 9931 |
+
{
|
| 9932 |
+
"epoch": 0.28882631211777104,
|
| 9933 |
+
"grad_norm": 0.12625005841255188,
|
| 9934 |
+
"learning_rate": 0.001,
|
| 9935 |
+
"loss": 2.217900276184082,
|
| 9936 |
+
"step": 2836
|
| 9937 |
+
},
|
| 9938 |
+
{
|
| 9939 |
+
"epoch": 0.2890299978103788,
|
| 9940 |
+
"grad_norm": 0.11961814016103745,
|
| 9941 |
+
"learning_rate": 0.001,
|
| 9942 |
+
"loss": 2.202756881713867,
|
| 9943 |
+
"step": 2838
|
| 9944 |
+
},
|
| 9945 |
+
{
|
| 9946 |
+
"epoch": 0.28923368350298656,
|
| 9947 |
+
"grad_norm": 0.13313569128513336,
|
| 9948 |
+
"learning_rate": 0.001,
|
| 9949 |
+
"loss": 2.177443504333496,
|
| 9950 |
+
"step": 2840
|
| 9951 |
+
},
|
| 9952 |
+
{
|
| 9953 |
+
"epoch": 0.28943736919559426,
|
| 9954 |
+
"grad_norm": 0.13315175473690033,
|
| 9955 |
+
"learning_rate": 0.001,
|
| 9956 |
+
"loss": 2.159515619277954,
|
| 9957 |
+
"step": 2842
|
| 9958 |
+
},
|
| 9959 |
+
{
|
| 9960 |
+
"epoch": 0.289641054888202,
|
| 9961 |
+
"grad_norm": 0.1236295998096466,
|
| 9962 |
+
"learning_rate": 0.001,
|
| 9963 |
+
"loss": 2.443605899810791,
|
| 9964 |
+
"step": 2844
|
| 9965 |
+
},
|
| 9966 |
+
{
|
| 9967 |
+
"epoch": 0.2898447405808098,
|
| 9968 |
+
"grad_norm": 0.11543665826320648,
|
| 9969 |
+
"learning_rate": 0.001,
|
| 9970 |
+
"loss": 2.161893606185913,
|
| 9971 |
+
"step": 2846
|
| 9972 |
+
},
|
| 9973 |
+
{
|
| 9974 |
+
"epoch": 0.2900484262734175,
|
| 9975 |
+
"grad_norm": 0.13089220225811005,
|
| 9976 |
+
"learning_rate": 0.001,
|
| 9977 |
+
"loss": 2.27069354057312,
|
| 9978 |
+
"step": 2848
|
| 9979 |
+
},
|
| 9980 |
+
{
|
| 9981 |
+
"epoch": 0.29025211196602524,
|
| 9982 |
+
"grad_norm": 0.10956435650587082,
|
| 9983 |
+
"learning_rate": 0.001,
|
| 9984 |
+
"loss": 2.2586164474487305,
|
| 9985 |
+
"step": 2850
|
| 9986 |
+
},
|
| 9987 |
+
{
|
| 9988 |
+
"epoch": 0.29045579765863294,
|
| 9989 |
+
"grad_norm": 0.11617504805326462,
|
| 9990 |
+
"learning_rate": 0.001,
|
| 9991 |
+
"loss": 2.3115572929382324,
|
| 9992 |
+
"step": 2852
|
| 9993 |
+
},
|
| 9994 |
+
{
|
| 9995 |
+
"epoch": 0.2906594833512407,
|
| 9996 |
+
"grad_norm": 0.10935907065868378,
|
| 9997 |
+
"learning_rate": 0.001,
|
| 9998 |
+
"loss": 2.3303041458129883,
|
| 9999 |
+
"step": 2854
|
| 10000 |
+
},
|
| 10001 |
+
{
|
| 10002 |
+
"epoch": 0.29086316904384846,
|
| 10003 |
+
"grad_norm": 0.1102304458618164,
|
| 10004 |
+
"learning_rate": 0.001,
|
| 10005 |
+
"loss": 2.1151766777038574,
|
| 10006 |
+
"step": 2856
|
| 10007 |
+
},
|
| 10008 |
+
{
|
| 10009 |
+
"epoch": 0.29106685473645616,
|
| 10010 |
+
"grad_norm": 0.12016117572784424,
|
| 10011 |
+
"learning_rate": 0.001,
|
| 10012 |
+
"loss": 2.160602569580078,
|
| 10013 |
+
"step": 2858
|
| 10014 |
+
},
|
| 10015 |
+
{
|
| 10016 |
+
"epoch": 0.2912705404290639,
|
| 10017 |
+
"grad_norm": 0.14624397456645966,
|
| 10018 |
+
"learning_rate": 0.001,
|
| 10019 |
+
"loss": 2.324522018432617,
|
| 10020 |
+
"step": 2860
|
| 10021 |
+
},
|
| 10022 |
+
{
|
| 10023 |
+
"epoch": 0.2914742261216717,
|
| 10024 |
+
"grad_norm": 0.1222170814871788,
|
| 10025 |
+
"learning_rate": 0.001,
|
| 10026 |
+
"loss": 2.2811951637268066,
|
| 10027 |
+
"step": 2862
|
| 10028 |
+
},
|
| 10029 |
+
{
|
| 10030 |
+
"epoch": 0.2916779118142794,
|
| 10031 |
+
"grad_norm": 0.11914020031690598,
|
| 10032 |
+
"learning_rate": 0.001,
|
| 10033 |
+
"loss": 2.1276369094848633,
|
| 10034 |
+
"step": 2864
|
| 10035 |
+
},
|
| 10036 |
+
{
|
| 10037 |
+
"epoch": 0.29188159750688714,
|
| 10038 |
+
"grad_norm": 0.13370655477046967,
|
| 10039 |
+
"learning_rate": 0.001,
|
| 10040 |
+
"loss": 2.35481333732605,
|
| 10041 |
+
"step": 2866
|
| 10042 |
+
},
|
| 10043 |
+
{
|
| 10044 |
+
"epoch": 0.29208528319949484,
|
| 10045 |
+
"grad_norm": 0.11148037761449814,
|
| 10046 |
+
"learning_rate": 0.001,
|
| 10047 |
+
"loss": 2.3246665000915527,
|
| 10048 |
+
"step": 2868
|
| 10049 |
+
},
|
| 10050 |
+
{
|
| 10051 |
+
"epoch": 0.2922889688921026,
|
| 10052 |
+
"grad_norm": 0.11772003024816513,
|
| 10053 |
+
"learning_rate": 0.001,
|
| 10054 |
+
"loss": 2.1601624488830566,
|
| 10055 |
+
"step": 2870
|
| 10056 |
+
},
|
| 10057 |
+
{
|
| 10058 |
+
"epoch": 0.29249265458471035,
|
| 10059 |
+
"grad_norm": 0.12403424084186554,
|
| 10060 |
+
"learning_rate": 0.001,
|
| 10061 |
+
"loss": 2.165870189666748,
|
| 10062 |
+
"step": 2872
|
| 10063 |
+
},
|
| 10064 |
+
{
|
| 10065 |
+
"epoch": 0.29269634027731806,
|
| 10066 |
+
"grad_norm": 0.133452907204628,
|
| 10067 |
+
"learning_rate": 0.001,
|
| 10068 |
+
"loss": 2.1149988174438477,
|
| 10069 |
+
"step": 2874
|
| 10070 |
+
},
|
| 10071 |
+
{
|
| 10072 |
+
"epoch": 0.2929000259699258,
|
| 10073 |
+
"grad_norm": 0.12772035598754883,
|
| 10074 |
+
"learning_rate": 0.001,
|
| 10075 |
+
"loss": 2.2353968620300293,
|
| 10076 |
+
"step": 2876
|
| 10077 |
+
},
|
| 10078 |
+
{
|
| 10079 |
+
"epoch": 0.2931037116625335,
|
| 10080 |
+
"grad_norm": 0.11632455885410309,
|
| 10081 |
+
"learning_rate": 0.001,
|
| 10082 |
+
"loss": 2.0372705459594727,
|
| 10083 |
+
"step": 2878
|
| 10084 |
+
},
|
| 10085 |
+
{
|
| 10086 |
+
"epoch": 0.2933073973551413,
|
| 10087 |
+
"grad_norm": 0.16389203071594238,
|
| 10088 |
+
"learning_rate": 0.001,
|
| 10089 |
+
"loss": 2.2925047874450684,
|
| 10090 |
+
"step": 2880
|
| 10091 |
+
},
|
| 10092 |
+
{
|
| 10093 |
+
"epoch": 0.29351108304774903,
|
| 10094 |
+
"grad_norm": 0.14279712736606598,
|
| 10095 |
+
"learning_rate": 0.001,
|
| 10096 |
+
"loss": 2.1901612281799316,
|
| 10097 |
+
"step": 2882
|
| 10098 |
+
},
|
| 10099 |
+
{
|
| 10100 |
+
"epoch": 0.29371476874035674,
|
| 10101 |
+
"grad_norm": 0.1168428286910057,
|
| 10102 |
+
"learning_rate": 0.001,
|
| 10103 |
+
"loss": 2.2323126792907715,
|
| 10104 |
+
"step": 2884
|
| 10105 |
+
},
|
| 10106 |
+
{
|
| 10107 |
+
"epoch": 0.2939184544329645,
|
| 10108 |
+
"grad_norm": 0.13500447571277618,
|
| 10109 |
+
"learning_rate": 0.001,
|
| 10110 |
+
"loss": 2.2118797302246094,
|
| 10111 |
+
"step": 2886
|
| 10112 |
+
},
|
| 10113 |
+
{
|
| 10114 |
+
"epoch": 0.29412214012557225,
|
| 10115 |
+
"grad_norm": 0.1528005748987198,
|
| 10116 |
+
"learning_rate": 0.001,
|
| 10117 |
+
"loss": 2.1339292526245117,
|
| 10118 |
+
"step": 2888
|
| 10119 |
+
},
|
| 10120 |
+
{
|
| 10121 |
+
"epoch": 0.29432582581817995,
|
| 10122 |
+
"grad_norm": 0.12431622296571732,
|
| 10123 |
+
"learning_rate": 0.001,
|
| 10124 |
+
"loss": 2.261763095855713,
|
| 10125 |
+
"step": 2890
|
| 10126 |
+
},
|
| 10127 |
+
{
|
| 10128 |
+
"epoch": 0.2945295115107877,
|
| 10129 |
+
"grad_norm": 0.16758611798286438,
|
| 10130 |
+
"learning_rate": 0.001,
|
| 10131 |
+
"loss": 2.2349653244018555,
|
| 10132 |
+
"step": 2892
|
| 10133 |
+
},
|
| 10134 |
+
{
|
| 10135 |
+
"epoch": 0.2947331972033954,
|
| 10136 |
+
"grad_norm": 0.1324918121099472,
|
| 10137 |
+
"learning_rate": 0.001,
|
| 10138 |
+
"loss": 2.3428568840026855,
|
| 10139 |
+
"step": 2894
|
| 10140 |
+
},
|
| 10141 |
+
{
|
| 10142 |
+
"epoch": 0.29493688289600317,
|
| 10143 |
+
"grad_norm": 0.1220194548368454,
|
| 10144 |
+
"learning_rate": 0.001,
|
| 10145 |
+
"loss": 2.0143094062805176,
|
| 10146 |
+
"step": 2896
|
| 10147 |
+
},
|
| 10148 |
+
{
|
| 10149 |
+
"epoch": 0.29514056858861093,
|
| 10150 |
+
"grad_norm": 0.19227296113967896,
|
| 10151 |
+
"learning_rate": 0.001,
|
| 10152 |
+
"loss": 2.097236156463623,
|
| 10153 |
+
"step": 2898
|
| 10154 |
+
},
|
| 10155 |
+
{
|
| 10156 |
+
"epoch": 0.29534425428121863,
|
| 10157 |
+
"grad_norm": 0.13902077078819275,
|
| 10158 |
+
"learning_rate": 0.001,
|
| 10159 |
+
"loss": 2.2687830924987793,
|
| 10160 |
+
"step": 2900
|
| 10161 |
+
},
|
| 10162 |
+
{
|
| 10163 |
+
"epoch": 0.2955479399738264,
|
| 10164 |
+
"grad_norm": 0.13509751856327057,
|
| 10165 |
+
"learning_rate": 0.001,
|
| 10166 |
+
"loss": 2.2959647178649902,
|
| 10167 |
+
"step": 2902
|
| 10168 |
+
},
|
| 10169 |
+
{
|
| 10170 |
+
"epoch": 0.29575162566643415,
|
| 10171 |
+
"grad_norm": 0.17153140902519226,
|
| 10172 |
+
"learning_rate": 0.001,
|
| 10173 |
+
"loss": 2.3824918270111084,
|
| 10174 |
+
"step": 2904
|
| 10175 |
+
},
|
| 10176 |
+
{
|
| 10177 |
+
"epoch": 0.29595531135904185,
|
| 10178 |
+
"grad_norm": 0.13108821213245392,
|
| 10179 |
+
"learning_rate": 0.001,
|
| 10180 |
+
"loss": 2.208404064178467,
|
| 10181 |
+
"step": 2906
|
| 10182 |
+
},
|
| 10183 |
+
{
|
| 10184 |
+
"epoch": 0.2961589970516496,
|
| 10185 |
+
"grad_norm": 0.13402928411960602,
|
| 10186 |
+
"learning_rate": 0.001,
|
| 10187 |
+
"loss": 2.111860752105713,
|
| 10188 |
+
"step": 2908
|
| 10189 |
+
},
|
| 10190 |
+
{
|
| 10191 |
+
"epoch": 0.2963626827442573,
|
| 10192 |
+
"grad_norm": 0.13126176595687866,
|
| 10193 |
+
"learning_rate": 0.001,
|
| 10194 |
+
"loss": 2.133674383163452,
|
| 10195 |
+
"step": 2910
|
| 10196 |
+
},
|
| 10197 |
+
{
|
| 10198 |
+
"epoch": 0.29656636843686507,
|
| 10199 |
+
"grad_norm": 0.2155710756778717,
|
| 10200 |
+
"learning_rate": 0.001,
|
| 10201 |
+
"loss": 2.2037229537963867,
|
| 10202 |
+
"step": 2912
|
| 10203 |
+
},
|
| 10204 |
+
{
|
| 10205 |
+
"epoch": 0.2967700541294728,
|
| 10206 |
+
"grad_norm": 0.13246358931064606,
|
| 10207 |
+
"learning_rate": 0.001,
|
| 10208 |
+
"loss": 2.3067359924316406,
|
| 10209 |
+
"step": 2914
|
| 10210 |
+
},
|
| 10211 |
+
{
|
| 10212 |
+
"epoch": 0.29697373982208053,
|
| 10213 |
+
"grad_norm": 0.1517786830663681,
|
| 10214 |
+
"learning_rate": 0.001,
|
| 10215 |
+
"loss": 2.1954948902130127,
|
| 10216 |
+
"step": 2916
|
| 10217 |
+
},
|
| 10218 |
+
{
|
| 10219 |
+
"epoch": 0.2971774255146883,
|
| 10220 |
+
"grad_norm": 0.21202431619167328,
|
| 10221 |
+
"learning_rate": 0.001,
|
| 10222 |
+
"loss": 2.288029193878174,
|
| 10223 |
+
"step": 2918
|
| 10224 |
+
},
|
| 10225 |
+
{
|
| 10226 |
+
"epoch": 0.29738111120729604,
|
| 10227 |
+
"grad_norm": 0.1436876654624939,
|
| 10228 |
+
"learning_rate": 0.001,
|
| 10229 |
+
"loss": 2.2964606285095215,
|
| 10230 |
+
"step": 2920
|
| 10231 |
+
},
|
| 10232 |
+
{
|
| 10233 |
+
"epoch": 0.29758479689990375,
|
| 10234 |
+
"grad_norm": 0.10918133705854416,
|
| 10235 |
+
"learning_rate": 0.001,
|
| 10236 |
+
"loss": 2.073823928833008,
|
| 10237 |
+
"step": 2922
|
| 10238 |
+
},
|
| 10239 |
+
{
|
| 10240 |
+
"epoch": 0.2977884825925115,
|
| 10241 |
+
"grad_norm": 0.13685692846775055,
|
| 10242 |
+
"learning_rate": 0.001,
|
| 10243 |
+
"loss": 2.282309055328369,
|
| 10244 |
+
"step": 2924
|
| 10245 |
+
},
|
| 10246 |
+
{
|
| 10247 |
+
"epoch": 0.2979921682851192,
|
| 10248 |
+
"grad_norm": 0.15041635930538177,
|
| 10249 |
+
"learning_rate": 0.001,
|
| 10250 |
+
"loss": 2.103414535522461,
|
| 10251 |
+
"step": 2926
|
| 10252 |
+
},
|
| 10253 |
+
{
|
| 10254 |
+
"epoch": 0.29819585397772697,
|
| 10255 |
+
"grad_norm": 0.118439219892025,
|
| 10256 |
+
"learning_rate": 0.001,
|
| 10257 |
+
"loss": 2.2054033279418945,
|
| 10258 |
+
"step": 2928
|
| 10259 |
+
},
|
| 10260 |
+
{
|
| 10261 |
+
"epoch": 0.2983995396703347,
|
| 10262 |
+
"grad_norm": 0.123115673661232,
|
| 10263 |
+
"learning_rate": 0.001,
|
| 10264 |
+
"loss": 2.221282958984375,
|
| 10265 |
+
"step": 2930
|
| 10266 |
+
},
|
| 10267 |
+
{
|
| 10268 |
+
"epoch": 0.2986032253629424,
|
| 10269 |
+
"grad_norm": 0.13006238639354706,
|
| 10270 |
+
"learning_rate": 0.001,
|
| 10271 |
+
"loss": 2.173612117767334,
|
| 10272 |
+
"step": 2932
|
| 10273 |
+
},
|
| 10274 |
+
{
|
| 10275 |
+
"epoch": 0.2988069110555502,
|
| 10276 |
+
"grad_norm": 0.12799493968486786,
|
| 10277 |
+
"learning_rate": 0.001,
|
| 10278 |
+
"loss": 2.340790271759033,
|
| 10279 |
+
"step": 2934
|
| 10280 |
+
},
|
| 10281 |
+
{
|
| 10282 |
+
"epoch": 0.29901059674815794,
|
| 10283 |
+
"grad_norm": 0.1385725885629654,
|
| 10284 |
+
"learning_rate": 0.001,
|
| 10285 |
+
"loss": 2.2663733959198,
|
| 10286 |
+
"step": 2936
|
| 10287 |
+
},
|
| 10288 |
+
{
|
| 10289 |
+
"epoch": 0.29921428244076564,
|
| 10290 |
+
"grad_norm": 0.11950669437646866,
|
| 10291 |
+
"learning_rate": 0.001,
|
| 10292 |
+
"loss": 2.164724349975586,
|
| 10293 |
+
"step": 2938
|
| 10294 |
+
},
|
| 10295 |
+
{
|
| 10296 |
+
"epoch": 0.2994179681333734,
|
| 10297 |
+
"grad_norm": 0.11369793862104416,
|
| 10298 |
+
"learning_rate": 0.001,
|
| 10299 |
+
"loss": 2.096268653869629,
|
| 10300 |
+
"step": 2940
|
| 10301 |
+
},
|
| 10302 |
+
{
|
| 10303 |
+
"epoch": 0.2996216538259811,
|
| 10304 |
+
"grad_norm": 0.13515204191207886,
|
| 10305 |
+
"learning_rate": 0.001,
|
| 10306 |
+
"loss": 2.3154380321502686,
|
| 10307 |
+
"step": 2942
|
| 10308 |
+
},
|
| 10309 |
+
{
|
| 10310 |
+
"epoch": 0.29982533951858886,
|
| 10311 |
+
"grad_norm": 0.1111815869808197,
|
| 10312 |
+
"learning_rate": 0.001,
|
| 10313 |
+
"loss": 2.045447826385498,
|
| 10314 |
+
"step": 2944
|
| 10315 |
+
},
|
| 10316 |
+
{
|
| 10317 |
+
"epoch": 0.3000290252111966,
|
| 10318 |
+
"grad_norm": 0.10586021095514297,
|
| 10319 |
+
"learning_rate": 0.001,
|
| 10320 |
+
"loss": 2.274158477783203,
|
| 10321 |
+
"step": 2946
|
| 10322 |
}
|
| 10323 |
],
|
| 10324 |
"logging_steps": 2,
|
|
|
|
| 10338 |
"attributes": {}
|
| 10339 |
}
|
| 10340 |
},
|
| 10341 |
+
"total_flos": 9.073461756847718e+17,
|
| 10342 |
"train_batch_size": 2,
|
| 10343 |
"trial_name": null,
|
| 10344 |
"trial_params": null
|