Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
unsloth
sft
conversational
text-generation-inference
Instructions to use Ba2han/test_CPTlsft2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/test_CPTlsft2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/test_CPTlsft2") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/test_CPTlsft2") model = AutoModelForCausalLM.from_pretrained("Ba2han/test_CPTlsft2", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/test_CPTlsft2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/test_CPTlsft2" # 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_CPTlsft2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Ba2han/test_CPTlsft2
- SGLang
How to use Ba2han/test_CPTlsft2 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_CPTlsft2" \ --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_CPTlsft2", "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_CPTlsft2" \ --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_CPTlsft2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use Ba2han/test_CPTlsft2 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/test_CPTlsft2 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/test_CPTlsft2 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ba2han/test_CPTlsft2 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Ba2han/test_CPTlsft2", max_seq_length=2048, ) - Docker Model Runner
How to use Ba2han/test_CPTlsft2 with Docker Model Runner:
docker model run hf.co/Ba2han/test_CPTlsft2
Training in progress, step 2870, 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:cf77aa20068301cb450774f6b944fb2c4501bf1b41ee20eebc1349efdd80966a
|
| 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 3631584265
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c1c6c3ed1994e2519cf116a8e9507fa7b6ad6fd987cf397617cd2da5a14082f
|
| 3 |
size 3631584265
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9de537433b473b3b75a3c1b10ca47a1821fdf2b7b6f501ee03adc5caf6563bdf
|
| 3 |
size 14917
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce221981a704f30cfbc27253a165c15733b7002f28ea175255b5730b028be19a
|
| 3 |
size 14917
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54a1e587a4e0b90aec90697cb9aed15fa0c74a3ff4c591ebd759a6bdb884e52e
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 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,
|
|
@@ -8044,6 +8044,2015 @@
|
|
| 8044 |
"learning_rate": 5e-05,
|
| 8045 |
"loss": 1.8702466487884521,
|
| 8046 |
"step": 2296
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8047 |
}
|
| 8048 |
],
|
| 8049 |
"logging_steps": 2,
|
|
@@ -8063,7 +10072,7 @@
|
|
| 8063 |
"attributes": {}
|
| 8064 |
}
|
| 8065 |
},
|
| 8066 |
-
"total_flos":
|
| 8067 |
"train_batch_size": 1,
|
| 8068 |
"trial_name": null,
|
| 8069 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0006973865439266,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2870,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8044 |
"learning_rate": 5e-05,
|
| 8045 |
"loss": 1.8702466487884521,
|
| 8046 |
"step": 2296
|
| 8047 |
+
},
|
| 8048 |
+
{
|
| 8049 |
+
"epoch": 0.8012971389717035,
|
| 8050 |
+
"grad_norm": 0.34665629267692566,
|
| 8051 |
+
"learning_rate": 5e-05,
|
| 8052 |
+
"loss": 1.5512590408325195,
|
| 8053 |
+
"step": 2298
|
| 8054 |
+
},
|
| 8055 |
+
{
|
| 8056 |
+
"epoch": 0.8019945255156302,
|
| 8057 |
+
"grad_norm": 0.2618155777454376,
|
| 8058 |
+
"learning_rate": 5e-05,
|
| 8059 |
+
"loss": 1.8056235313415527,
|
| 8060 |
+
"step": 2300
|
| 8061 |
+
},
|
| 8062 |
+
{
|
| 8063 |
+
"epoch": 0.8026919120595568,
|
| 8064 |
+
"grad_norm": 0.20531056821346283,
|
| 8065 |
+
"learning_rate": 5e-05,
|
| 8066 |
+
"loss": 1.9945034980773926,
|
| 8067 |
+
"step": 2302
|
| 8068 |
+
},
|
| 8069 |
+
{
|
| 8070 |
+
"epoch": 0.8033892986034834,
|
| 8071 |
+
"grad_norm": 0.25889530777931213,
|
| 8072 |
+
"learning_rate": 5e-05,
|
| 8073 |
+
"loss": 1.8921455144882202,
|
| 8074 |
+
"step": 2304
|
| 8075 |
+
},
|
| 8076 |
+
{
|
| 8077 |
+
"epoch": 0.8040866851474101,
|
| 8078 |
+
"grad_norm": 0.1906490921974182,
|
| 8079 |
+
"learning_rate": 5e-05,
|
| 8080 |
+
"loss": 1.982350468635559,
|
| 8081 |
+
"step": 2306
|
| 8082 |
+
},
|
| 8083 |
+
{
|
| 8084 |
+
"epoch": 0.8047840716913367,
|
| 8085 |
+
"grad_norm": 0.3171706795692444,
|
| 8086 |
+
"learning_rate": 5e-05,
|
| 8087 |
+
"loss": 1.8985872268676758,
|
| 8088 |
+
"step": 2308
|
| 8089 |
+
},
|
| 8090 |
+
{
|
| 8091 |
+
"epoch": 0.8054814582352634,
|
| 8092 |
+
"grad_norm": 0.18568949401378632,
|
| 8093 |
+
"learning_rate": 5e-05,
|
| 8094 |
+
"loss": 1.9411725997924805,
|
| 8095 |
+
"step": 2310
|
| 8096 |
+
},
|
| 8097 |
+
{
|
| 8098 |
+
"epoch": 0.80617884477919,
|
| 8099 |
+
"grad_norm": 0.2307809740304947,
|
| 8100 |
+
"learning_rate": 5e-05,
|
| 8101 |
+
"loss": 1.8542625904083252,
|
| 8102 |
+
"step": 2312
|
| 8103 |
+
},
|
| 8104 |
+
{
|
| 8105 |
+
"epoch": 0.8068762313231166,
|
| 8106 |
+
"grad_norm": 0.29474905133247375,
|
| 8107 |
+
"learning_rate": 5e-05,
|
| 8108 |
+
"loss": 1.7415797710418701,
|
| 8109 |
+
"step": 2314
|
| 8110 |
+
},
|
| 8111 |
+
{
|
| 8112 |
+
"epoch": 0.8075736178670433,
|
| 8113 |
+
"grad_norm": 0.1813082993030548,
|
| 8114 |
+
"learning_rate": 5e-05,
|
| 8115 |
+
"loss": 1.8530118465423584,
|
| 8116 |
+
"step": 2316
|
| 8117 |
+
},
|
| 8118 |
+
{
|
| 8119 |
+
"epoch": 0.8082710044109699,
|
| 8120 |
+
"grad_norm": 0.30233779549598694,
|
| 8121 |
+
"learning_rate": 5e-05,
|
| 8122 |
+
"loss": 1.732279658317566,
|
| 8123 |
+
"step": 2318
|
| 8124 |
+
},
|
| 8125 |
+
{
|
| 8126 |
+
"epoch": 0.8089683909548965,
|
| 8127 |
+
"grad_norm": 0.19910310208797455,
|
| 8128 |
+
"learning_rate": 5e-05,
|
| 8129 |
+
"loss": 1.7143280506134033,
|
| 8130 |
+
"step": 2320
|
| 8131 |
+
},
|
| 8132 |
+
{
|
| 8133 |
+
"epoch": 0.8096657774988232,
|
| 8134 |
+
"grad_norm": 0.2825470268726349,
|
| 8135 |
+
"learning_rate": 5e-05,
|
| 8136 |
+
"loss": 1.8623201847076416,
|
| 8137 |
+
"step": 2322
|
| 8138 |
+
},
|
| 8139 |
+
{
|
| 8140 |
+
"epoch": 0.8103631640427498,
|
| 8141 |
+
"grad_norm": 0.1972043663263321,
|
| 8142 |
+
"learning_rate": 5e-05,
|
| 8143 |
+
"loss": 2.0700478553771973,
|
| 8144 |
+
"step": 2324
|
| 8145 |
+
},
|
| 8146 |
+
{
|
| 8147 |
+
"epoch": 0.8110605505866765,
|
| 8148 |
+
"grad_norm": 0.29088762402534485,
|
| 8149 |
+
"learning_rate": 5e-05,
|
| 8150 |
+
"loss": 1.7995343208312988,
|
| 8151 |
+
"step": 2326
|
| 8152 |
+
},
|
| 8153 |
+
{
|
| 8154 |
+
"epoch": 0.8117579371306031,
|
| 8155 |
+
"grad_norm": 0.2989962697029114,
|
| 8156 |
+
"learning_rate": 5e-05,
|
| 8157 |
+
"loss": 1.6743077039718628,
|
| 8158 |
+
"step": 2328
|
| 8159 |
+
},
|
| 8160 |
+
{
|
| 8161 |
+
"epoch": 0.8124553236745297,
|
| 8162 |
+
"grad_norm": 0.24003519117832184,
|
| 8163 |
+
"learning_rate": 5e-05,
|
| 8164 |
+
"loss": 1.9525628089904785,
|
| 8165 |
+
"step": 2330
|
| 8166 |
+
},
|
| 8167 |
+
{
|
| 8168 |
+
"epoch": 0.8131527102184564,
|
| 8169 |
+
"grad_norm": 0.21295663714408875,
|
| 8170 |
+
"learning_rate": 5e-05,
|
| 8171 |
+
"loss": 1.7714589834213257,
|
| 8172 |
+
"step": 2332
|
| 8173 |
+
},
|
| 8174 |
+
{
|
| 8175 |
+
"epoch": 0.813850096762383,
|
| 8176 |
+
"grad_norm": 0.23063835501670837,
|
| 8177 |
+
"learning_rate": 5e-05,
|
| 8178 |
+
"loss": 1.7743947505950928,
|
| 8179 |
+
"step": 2334
|
| 8180 |
+
},
|
| 8181 |
+
{
|
| 8182 |
+
"epoch": 0.8145474833063095,
|
| 8183 |
+
"grad_norm": 0.21624773740768433,
|
| 8184 |
+
"learning_rate": 5e-05,
|
| 8185 |
+
"loss": 1.870970368385315,
|
| 8186 |
+
"step": 2336
|
| 8187 |
+
},
|
| 8188 |
+
{
|
| 8189 |
+
"epoch": 0.8152448698502363,
|
| 8190 |
+
"grad_norm": 0.34053564071655273,
|
| 8191 |
+
"learning_rate": 5e-05,
|
| 8192 |
+
"loss": 1.5913314819335938,
|
| 8193 |
+
"step": 2338
|
| 8194 |
+
},
|
| 8195 |
+
{
|
| 8196 |
+
"epoch": 0.8159422563941628,
|
| 8197 |
+
"grad_norm": 0.20439667999744415,
|
| 8198 |
+
"learning_rate": 5e-05,
|
| 8199 |
+
"loss": 1.9366562366485596,
|
| 8200 |
+
"step": 2340
|
| 8201 |
+
},
|
| 8202 |
+
{
|
| 8203 |
+
"epoch": 0.8166396429380895,
|
| 8204 |
+
"grad_norm": 0.22627848386764526,
|
| 8205 |
+
"learning_rate": 5e-05,
|
| 8206 |
+
"loss": 1.841552495956421,
|
| 8207 |
+
"step": 2342
|
| 8208 |
+
},
|
| 8209 |
+
{
|
| 8210 |
+
"epoch": 0.8173370294820161,
|
| 8211 |
+
"grad_norm": 0.1971031129360199,
|
| 8212 |
+
"learning_rate": 5e-05,
|
| 8213 |
+
"loss": 1.6385873556137085,
|
| 8214 |
+
"step": 2344
|
| 8215 |
+
},
|
| 8216 |
+
{
|
| 8217 |
+
"epoch": 0.8180344160259427,
|
| 8218 |
+
"grad_norm": 0.2172694057226181,
|
| 8219 |
+
"learning_rate": 5e-05,
|
| 8220 |
+
"loss": 1.9489915370941162,
|
| 8221 |
+
"step": 2346
|
| 8222 |
+
},
|
| 8223 |
+
{
|
| 8224 |
+
"epoch": 0.8187318025698694,
|
| 8225 |
+
"grad_norm": 0.4004741609096527,
|
| 8226 |
+
"learning_rate": 5e-05,
|
| 8227 |
+
"loss": 1.983567714691162,
|
| 8228 |
+
"step": 2348
|
| 8229 |
+
},
|
| 8230 |
+
{
|
| 8231 |
+
"epoch": 0.819429189113796,
|
| 8232 |
+
"grad_norm": 0.18114428222179413,
|
| 8233 |
+
"learning_rate": 5e-05,
|
| 8234 |
+
"loss": 1.7686386108398438,
|
| 8235 |
+
"step": 2350
|
| 8236 |
+
},
|
| 8237 |
+
{
|
| 8238 |
+
"epoch": 0.8201265756577227,
|
| 8239 |
+
"grad_norm": 0.1820041537284851,
|
| 8240 |
+
"learning_rate": 5e-05,
|
| 8241 |
+
"loss": 1.9830634593963623,
|
| 8242 |
+
"step": 2352
|
| 8243 |
+
},
|
| 8244 |
+
{
|
| 8245 |
+
"epoch": 0.8208239622016493,
|
| 8246 |
+
"grad_norm": 0.20078644156455994,
|
| 8247 |
+
"learning_rate": 5e-05,
|
| 8248 |
+
"loss": 1.6137222051620483,
|
| 8249 |
+
"step": 2354
|
| 8250 |
+
},
|
| 8251 |
+
{
|
| 8252 |
+
"epoch": 0.8215213487455759,
|
| 8253 |
+
"grad_norm": 0.20240375399589539,
|
| 8254 |
+
"learning_rate": 5e-05,
|
| 8255 |
+
"loss": 1.7961931228637695,
|
| 8256 |
+
"step": 2356
|
| 8257 |
+
},
|
| 8258 |
+
{
|
| 8259 |
+
"epoch": 0.8222187352895026,
|
| 8260 |
+
"grad_norm": 0.2730301022529602,
|
| 8261 |
+
"learning_rate": 5e-05,
|
| 8262 |
+
"loss": 1.9427998065948486,
|
| 8263 |
+
"step": 2358
|
| 8264 |
+
},
|
| 8265 |
+
{
|
| 8266 |
+
"epoch": 0.8229161218334292,
|
| 8267 |
+
"grad_norm": 0.20543934404850006,
|
| 8268 |
+
"learning_rate": 5e-05,
|
| 8269 |
+
"loss": 1.8742575645446777,
|
| 8270 |
+
"step": 2360
|
| 8271 |
+
},
|
| 8272 |
+
{
|
| 8273 |
+
"epoch": 0.8236135083773558,
|
| 8274 |
+
"grad_norm": 0.2649659514427185,
|
| 8275 |
+
"learning_rate": 5e-05,
|
| 8276 |
+
"loss": 1.9555909633636475,
|
| 8277 |
+
"step": 2362
|
| 8278 |
+
},
|
| 8279 |
+
{
|
| 8280 |
+
"epoch": 0.8243108949212825,
|
| 8281 |
+
"grad_norm": 0.2065000981092453,
|
| 8282 |
+
"learning_rate": 5e-05,
|
| 8283 |
+
"loss": 1.8060014247894287,
|
| 8284 |
+
"step": 2364
|
| 8285 |
+
},
|
| 8286 |
+
{
|
| 8287 |
+
"epoch": 0.8250082814652091,
|
| 8288 |
+
"grad_norm": 0.2397371530532837,
|
| 8289 |
+
"learning_rate": 5e-05,
|
| 8290 |
+
"loss": 2.059617042541504,
|
| 8291 |
+
"step": 2366
|
| 8292 |
+
},
|
| 8293 |
+
{
|
| 8294 |
+
"epoch": 0.8257056680091358,
|
| 8295 |
+
"grad_norm": 0.20603303611278534,
|
| 8296 |
+
"learning_rate": 5e-05,
|
| 8297 |
+
"loss": 1.8409523963928223,
|
| 8298 |
+
"step": 2368
|
| 8299 |
+
},
|
| 8300 |
+
{
|
| 8301 |
+
"epoch": 0.8264030545530624,
|
| 8302 |
+
"grad_norm": 0.2540438175201416,
|
| 8303 |
+
"learning_rate": 5e-05,
|
| 8304 |
+
"loss": 1.8821148872375488,
|
| 8305 |
+
"step": 2370
|
| 8306 |
+
},
|
| 8307 |
+
{
|
| 8308 |
+
"epoch": 0.827100441096989,
|
| 8309 |
+
"grad_norm": 0.2622252404689789,
|
| 8310 |
+
"learning_rate": 5e-05,
|
| 8311 |
+
"loss": 1.8382006883621216,
|
| 8312 |
+
"step": 2372
|
| 8313 |
+
},
|
| 8314 |
+
{
|
| 8315 |
+
"epoch": 0.8277978276409157,
|
| 8316 |
+
"grad_norm": 0.26272404193878174,
|
| 8317 |
+
"learning_rate": 5e-05,
|
| 8318 |
+
"loss": 1.9710807800292969,
|
| 8319 |
+
"step": 2374
|
| 8320 |
+
},
|
| 8321 |
+
{
|
| 8322 |
+
"epoch": 0.8284952141848423,
|
| 8323 |
+
"grad_norm": 0.19015145301818848,
|
| 8324 |
+
"learning_rate": 5e-05,
|
| 8325 |
+
"loss": 1.869012713432312,
|
| 8326 |
+
"step": 2376
|
| 8327 |
+
},
|
| 8328 |
+
{
|
| 8329 |
+
"epoch": 0.829192600728769,
|
| 8330 |
+
"grad_norm": 0.2541094422340393,
|
| 8331 |
+
"learning_rate": 5e-05,
|
| 8332 |
+
"loss": 1.9601718187332153,
|
| 8333 |
+
"step": 2378
|
| 8334 |
+
},
|
| 8335 |
+
{
|
| 8336 |
+
"epoch": 0.8298899872726956,
|
| 8337 |
+
"grad_norm": 0.265034019947052,
|
| 8338 |
+
"learning_rate": 5e-05,
|
| 8339 |
+
"loss": 1.7983336448669434,
|
| 8340 |
+
"step": 2380
|
| 8341 |
+
},
|
| 8342 |
+
{
|
| 8343 |
+
"epoch": 0.8305873738166222,
|
| 8344 |
+
"grad_norm": 0.28119009733200073,
|
| 8345 |
+
"learning_rate": 5e-05,
|
| 8346 |
+
"loss": 1.9807533025741577,
|
| 8347 |
+
"step": 2382
|
| 8348 |
+
},
|
| 8349 |
+
{
|
| 8350 |
+
"epoch": 0.8312847603605489,
|
| 8351 |
+
"grad_norm": 0.18375326693058014,
|
| 8352 |
+
"learning_rate": 5e-05,
|
| 8353 |
+
"loss": 1.903433084487915,
|
| 8354 |
+
"step": 2384
|
| 8355 |
+
},
|
| 8356 |
+
{
|
| 8357 |
+
"epoch": 0.8319821469044755,
|
| 8358 |
+
"grad_norm": 0.26467451453208923,
|
| 8359 |
+
"learning_rate": 5e-05,
|
| 8360 |
+
"loss": 1.8559367656707764,
|
| 8361 |
+
"step": 2386
|
| 8362 |
+
},
|
| 8363 |
+
{
|
| 8364 |
+
"epoch": 0.8326795334484021,
|
| 8365 |
+
"grad_norm": 0.21322381496429443,
|
| 8366 |
+
"learning_rate": 5e-05,
|
| 8367 |
+
"loss": 2.0329360961914062,
|
| 8368 |
+
"step": 2388
|
| 8369 |
+
},
|
| 8370 |
+
{
|
| 8371 |
+
"epoch": 0.8333769199923288,
|
| 8372 |
+
"grad_norm": 0.19978481531143188,
|
| 8373 |
+
"learning_rate": 5e-05,
|
| 8374 |
+
"loss": 1.928691029548645,
|
| 8375 |
+
"step": 2390
|
| 8376 |
+
},
|
| 8377 |
+
{
|
| 8378 |
+
"epoch": 0.8340743065362554,
|
| 8379 |
+
"grad_norm": 0.26044854521751404,
|
| 8380 |
+
"learning_rate": 5e-05,
|
| 8381 |
+
"loss": 2.0241265296936035,
|
| 8382 |
+
"step": 2392
|
| 8383 |
+
},
|
| 8384 |
+
{
|
| 8385 |
+
"epoch": 0.8347716930801821,
|
| 8386 |
+
"grad_norm": 0.25593796372413635,
|
| 8387 |
+
"learning_rate": 5e-05,
|
| 8388 |
+
"loss": 1.8040621280670166,
|
| 8389 |
+
"step": 2394
|
| 8390 |
+
},
|
| 8391 |
+
{
|
| 8392 |
+
"epoch": 0.8354690796241087,
|
| 8393 |
+
"grad_norm": 0.2556050419807434,
|
| 8394 |
+
"learning_rate": 5e-05,
|
| 8395 |
+
"loss": 1.8471500873565674,
|
| 8396 |
+
"step": 2396
|
| 8397 |
+
},
|
| 8398 |
+
{
|
| 8399 |
+
"epoch": 0.8361664661680352,
|
| 8400 |
+
"grad_norm": 0.29592692852020264,
|
| 8401 |
+
"learning_rate": 5e-05,
|
| 8402 |
+
"loss": 1.8190295696258545,
|
| 8403 |
+
"step": 2398
|
| 8404 |
+
},
|
| 8405 |
+
{
|
| 8406 |
+
"epoch": 0.836863852711962,
|
| 8407 |
+
"grad_norm": 0.22786323726177216,
|
| 8408 |
+
"learning_rate": 5e-05,
|
| 8409 |
+
"loss": 1.8059440851211548,
|
| 8410 |
+
"step": 2400
|
| 8411 |
+
},
|
| 8412 |
+
{
|
| 8413 |
+
"epoch": 0.8375612392558885,
|
| 8414 |
+
"grad_norm": 0.21543928980827332,
|
| 8415 |
+
"learning_rate": 5e-05,
|
| 8416 |
+
"loss": 1.8659863471984863,
|
| 8417 |
+
"step": 2402
|
| 8418 |
+
},
|
| 8419 |
+
{
|
| 8420 |
+
"epoch": 0.8382586257998151,
|
| 8421 |
+
"grad_norm": 0.24894928932189941,
|
| 8422 |
+
"learning_rate": 5e-05,
|
| 8423 |
+
"loss": 2.1881353855133057,
|
| 8424 |
+
"step": 2404
|
| 8425 |
+
},
|
| 8426 |
+
{
|
| 8427 |
+
"epoch": 0.8389560123437418,
|
| 8428 |
+
"grad_norm": 0.2092692255973816,
|
| 8429 |
+
"learning_rate": 5e-05,
|
| 8430 |
+
"loss": 1.8489896059036255,
|
| 8431 |
+
"step": 2406
|
| 8432 |
+
},
|
| 8433 |
+
{
|
| 8434 |
+
"epoch": 0.8396533988876684,
|
| 8435 |
+
"grad_norm": 0.297468900680542,
|
| 8436 |
+
"learning_rate": 5e-05,
|
| 8437 |
+
"loss": 2.0073957443237305,
|
| 8438 |
+
"step": 2408
|
| 8439 |
+
},
|
| 8440 |
+
{
|
| 8441 |
+
"epoch": 0.8403507854315951,
|
| 8442 |
+
"grad_norm": 0.19659481942653656,
|
| 8443 |
+
"learning_rate": 5e-05,
|
| 8444 |
+
"loss": 1.917393684387207,
|
| 8445 |
+
"step": 2410
|
| 8446 |
+
},
|
| 8447 |
+
{
|
| 8448 |
+
"epoch": 0.8410481719755217,
|
| 8449 |
+
"grad_norm": 0.3369445204734802,
|
| 8450 |
+
"learning_rate": 5e-05,
|
| 8451 |
+
"loss": 1.8730225563049316,
|
| 8452 |
+
"step": 2412
|
| 8453 |
+
},
|
| 8454 |
+
{
|
| 8455 |
+
"epoch": 0.8417455585194483,
|
| 8456 |
+
"grad_norm": 0.14724263548851013,
|
| 8457 |
+
"learning_rate": 5e-05,
|
| 8458 |
+
"loss": 2.0430855751037598,
|
| 8459 |
+
"step": 2414
|
| 8460 |
+
},
|
| 8461 |
+
{
|
| 8462 |
+
"epoch": 0.842442945063375,
|
| 8463 |
+
"grad_norm": 0.19056470692157745,
|
| 8464 |
+
"learning_rate": 5e-05,
|
| 8465 |
+
"loss": 1.980102300643921,
|
| 8466 |
+
"step": 2416
|
| 8467 |
+
},
|
| 8468 |
+
{
|
| 8469 |
+
"epoch": 0.8431403316073016,
|
| 8470 |
+
"grad_norm": 0.1984318494796753,
|
| 8471 |
+
"learning_rate": 5e-05,
|
| 8472 |
+
"loss": 2.017703056335449,
|
| 8473 |
+
"step": 2418
|
| 8474 |
+
},
|
| 8475 |
+
{
|
| 8476 |
+
"epoch": 0.8438377181512283,
|
| 8477 |
+
"grad_norm": 0.1699439436197281,
|
| 8478 |
+
"learning_rate": 5e-05,
|
| 8479 |
+
"loss": 1.795714020729065,
|
| 8480 |
+
"step": 2420
|
| 8481 |
+
},
|
| 8482 |
+
{
|
| 8483 |
+
"epoch": 0.8445351046951549,
|
| 8484 |
+
"grad_norm": 0.29702281951904297,
|
| 8485 |
+
"learning_rate": 5e-05,
|
| 8486 |
+
"loss": 2.1077191829681396,
|
| 8487 |
+
"step": 2422
|
| 8488 |
+
},
|
| 8489 |
+
{
|
| 8490 |
+
"epoch": 0.8452324912390815,
|
| 8491 |
+
"grad_norm": 0.22882135212421417,
|
| 8492 |
+
"learning_rate": 5e-05,
|
| 8493 |
+
"loss": 1.92616605758667,
|
| 8494 |
+
"step": 2424
|
| 8495 |
+
},
|
| 8496 |
+
{
|
| 8497 |
+
"epoch": 0.8459298777830082,
|
| 8498 |
+
"grad_norm": 0.21170425415039062,
|
| 8499 |
+
"learning_rate": 5e-05,
|
| 8500 |
+
"loss": 1.9746460914611816,
|
| 8501 |
+
"step": 2426
|
| 8502 |
+
},
|
| 8503 |
+
{
|
| 8504 |
+
"epoch": 0.8466272643269348,
|
| 8505 |
+
"grad_norm": 0.21631506085395813,
|
| 8506 |
+
"learning_rate": 5e-05,
|
| 8507 |
+
"loss": 1.7190144062042236,
|
| 8508 |
+
"step": 2428
|
| 8509 |
+
},
|
| 8510 |
+
{
|
| 8511 |
+
"epoch": 0.8473246508708614,
|
| 8512 |
+
"grad_norm": 0.21133138239383698,
|
| 8513 |
+
"learning_rate": 5e-05,
|
| 8514 |
+
"loss": 1.7343809604644775,
|
| 8515 |
+
"step": 2430
|
| 8516 |
+
},
|
| 8517 |
+
{
|
| 8518 |
+
"epoch": 0.8480220374147881,
|
| 8519 |
+
"grad_norm": 0.20639613270759583,
|
| 8520 |
+
"learning_rate": 5e-05,
|
| 8521 |
+
"loss": 1.9387023448944092,
|
| 8522 |
+
"step": 2432
|
| 8523 |
+
},
|
| 8524 |
+
{
|
| 8525 |
+
"epoch": 0.8487194239587147,
|
| 8526 |
+
"grad_norm": 0.24656221270561218,
|
| 8527 |
+
"learning_rate": 5e-05,
|
| 8528 |
+
"loss": 1.852571725845337,
|
| 8529 |
+
"step": 2434
|
| 8530 |
+
},
|
| 8531 |
+
{
|
| 8532 |
+
"epoch": 0.8494168105026414,
|
| 8533 |
+
"grad_norm": 0.18058742582798004,
|
| 8534 |
+
"learning_rate": 5e-05,
|
| 8535 |
+
"loss": 2.081359624862671,
|
| 8536 |
+
"step": 2436
|
| 8537 |
+
},
|
| 8538 |
+
{
|
| 8539 |
+
"epoch": 0.850114197046568,
|
| 8540 |
+
"grad_norm": 0.18465012311935425,
|
| 8541 |
+
"learning_rate": 5e-05,
|
| 8542 |
+
"loss": 1.93831467628479,
|
| 8543 |
+
"step": 2438
|
| 8544 |
+
},
|
| 8545 |
+
{
|
| 8546 |
+
"epoch": 0.8508115835904946,
|
| 8547 |
+
"grad_norm": 0.2825033962726593,
|
| 8548 |
+
"learning_rate": 5e-05,
|
| 8549 |
+
"loss": 1.9698466062545776,
|
| 8550 |
+
"step": 2440
|
| 8551 |
+
},
|
| 8552 |
+
{
|
| 8553 |
+
"epoch": 0.8515089701344213,
|
| 8554 |
+
"grad_norm": 0.27780500054359436,
|
| 8555 |
+
"learning_rate": 5e-05,
|
| 8556 |
+
"loss": 1.982361078262329,
|
| 8557 |
+
"step": 2442
|
| 8558 |
+
},
|
| 8559 |
+
{
|
| 8560 |
+
"epoch": 0.8522063566783479,
|
| 8561 |
+
"grad_norm": 0.16493284702301025,
|
| 8562 |
+
"learning_rate": 5e-05,
|
| 8563 |
+
"loss": 1.9893501996994019,
|
| 8564 |
+
"step": 2444
|
| 8565 |
+
},
|
| 8566 |
+
{
|
| 8567 |
+
"epoch": 0.8529037432222746,
|
| 8568 |
+
"grad_norm": 0.1815342903137207,
|
| 8569 |
+
"learning_rate": 5e-05,
|
| 8570 |
+
"loss": 1.9853184223175049,
|
| 8571 |
+
"step": 2446
|
| 8572 |
+
},
|
| 8573 |
+
{
|
| 8574 |
+
"epoch": 0.8536011297662012,
|
| 8575 |
+
"grad_norm": 0.19716495275497437,
|
| 8576 |
+
"learning_rate": 5e-05,
|
| 8577 |
+
"loss": 1.7325427532196045,
|
| 8578 |
+
"step": 2448
|
| 8579 |
+
},
|
| 8580 |
+
{
|
| 8581 |
+
"epoch": 0.8542985163101278,
|
| 8582 |
+
"grad_norm": 0.2385205179452896,
|
| 8583 |
+
"learning_rate": 5e-05,
|
| 8584 |
+
"loss": 1.9826991558074951,
|
| 8585 |
+
"step": 2450
|
| 8586 |
+
},
|
| 8587 |
+
{
|
| 8588 |
+
"epoch": 0.8549959028540545,
|
| 8589 |
+
"grad_norm": 0.19368870556354523,
|
| 8590 |
+
"learning_rate": 5e-05,
|
| 8591 |
+
"loss": 1.8701865673065186,
|
| 8592 |
+
"step": 2452
|
| 8593 |
+
},
|
| 8594 |
+
{
|
| 8595 |
+
"epoch": 0.8556932893979811,
|
| 8596 |
+
"grad_norm": 0.17733433842658997,
|
| 8597 |
+
"learning_rate": 5e-05,
|
| 8598 |
+
"loss": 2.036306381225586,
|
| 8599 |
+
"step": 2454
|
| 8600 |
+
},
|
| 8601 |
+
{
|
| 8602 |
+
"epoch": 0.8563906759419077,
|
| 8603 |
+
"grad_norm": 0.2510242164134979,
|
| 8604 |
+
"learning_rate": 5e-05,
|
| 8605 |
+
"loss": 1.9895774126052856,
|
| 8606 |
+
"step": 2456
|
| 8607 |
+
},
|
| 8608 |
+
{
|
| 8609 |
+
"epoch": 0.8570880624858344,
|
| 8610 |
+
"grad_norm": 0.21947576105594635,
|
| 8611 |
+
"learning_rate": 5e-05,
|
| 8612 |
+
"loss": 1.9222482442855835,
|
| 8613 |
+
"step": 2458
|
| 8614 |
+
},
|
| 8615 |
+
{
|
| 8616 |
+
"epoch": 0.857785449029761,
|
| 8617 |
+
"grad_norm": 0.2402341365814209,
|
| 8618 |
+
"learning_rate": 5e-05,
|
| 8619 |
+
"loss": 2.0680880546569824,
|
| 8620 |
+
"step": 2460
|
| 8621 |
+
},
|
| 8622 |
+
{
|
| 8623 |
+
"epoch": 0.8584828355736877,
|
| 8624 |
+
"grad_norm": 0.2076481431722641,
|
| 8625 |
+
"learning_rate": 5e-05,
|
| 8626 |
+
"loss": 1.7876285314559937,
|
| 8627 |
+
"step": 2462
|
| 8628 |
+
},
|
| 8629 |
+
{
|
| 8630 |
+
"epoch": 0.8591802221176142,
|
| 8631 |
+
"grad_norm": 0.22248335182666779,
|
| 8632 |
+
"learning_rate": 5e-05,
|
| 8633 |
+
"loss": 1.746431827545166,
|
| 8634 |
+
"step": 2464
|
| 8635 |
+
},
|
| 8636 |
+
{
|
| 8637 |
+
"epoch": 0.8598776086615408,
|
| 8638 |
+
"grad_norm": 0.2763570249080658,
|
| 8639 |
+
"learning_rate": 5e-05,
|
| 8640 |
+
"loss": 1.830052137374878,
|
| 8641 |
+
"step": 2466
|
| 8642 |
+
},
|
| 8643 |
+
{
|
| 8644 |
+
"epoch": 0.8605749952054675,
|
| 8645 |
+
"grad_norm": 0.242806538939476,
|
| 8646 |
+
"learning_rate": 5e-05,
|
| 8647 |
+
"loss": 1.820050597190857,
|
| 8648 |
+
"step": 2468
|
| 8649 |
+
},
|
| 8650 |
+
{
|
| 8651 |
+
"epoch": 0.8612723817493941,
|
| 8652 |
+
"grad_norm": 0.19415214657783508,
|
| 8653 |
+
"learning_rate": 5e-05,
|
| 8654 |
+
"loss": 1.8796792030334473,
|
| 8655 |
+
"step": 2470
|
| 8656 |
+
},
|
| 8657 |
+
{
|
| 8658 |
+
"epoch": 0.8619697682933207,
|
| 8659 |
+
"grad_norm": 0.16487431526184082,
|
| 8660 |
+
"learning_rate": 5e-05,
|
| 8661 |
+
"loss": 1.8481247425079346,
|
| 8662 |
+
"step": 2472
|
| 8663 |
+
},
|
| 8664 |
+
{
|
| 8665 |
+
"epoch": 0.8626671548372474,
|
| 8666 |
+
"grad_norm": 0.18796490132808685,
|
| 8667 |
+
"learning_rate": 5e-05,
|
| 8668 |
+
"loss": 2.0668163299560547,
|
| 8669 |
+
"step": 2474
|
| 8670 |
+
},
|
| 8671 |
+
{
|
| 8672 |
+
"epoch": 0.863364541381174,
|
| 8673 |
+
"grad_norm": 0.16939391195774078,
|
| 8674 |
+
"learning_rate": 5e-05,
|
| 8675 |
+
"loss": 1.9822109937667847,
|
| 8676 |
+
"step": 2476
|
| 8677 |
+
},
|
| 8678 |
+
{
|
| 8679 |
+
"epoch": 0.8640619279251007,
|
| 8680 |
+
"grad_norm": 0.22088705003261566,
|
| 8681 |
+
"learning_rate": 5e-05,
|
| 8682 |
+
"loss": 1.8946961164474487,
|
| 8683 |
+
"step": 2478
|
| 8684 |
+
},
|
| 8685 |
+
{
|
| 8686 |
+
"epoch": 0.8647593144690273,
|
| 8687 |
+
"grad_norm": 0.19917675852775574,
|
| 8688 |
+
"learning_rate": 5e-05,
|
| 8689 |
+
"loss": 1.9240469932556152,
|
| 8690 |
+
"step": 2480
|
| 8691 |
+
},
|
| 8692 |
+
{
|
| 8693 |
+
"epoch": 0.8654567010129539,
|
| 8694 |
+
"grad_norm": 0.1673891395330429,
|
| 8695 |
+
"learning_rate": 5e-05,
|
| 8696 |
+
"loss": 2.0632004737854004,
|
| 8697 |
+
"step": 2482
|
| 8698 |
+
},
|
| 8699 |
+
{
|
| 8700 |
+
"epoch": 0.8661540875568806,
|
| 8701 |
+
"grad_norm": 0.18360723555088043,
|
| 8702 |
+
"learning_rate": 5e-05,
|
| 8703 |
+
"loss": 1.8349483013153076,
|
| 8704 |
+
"step": 2484
|
| 8705 |
+
},
|
| 8706 |
+
{
|
| 8707 |
+
"epoch": 0.8668514741008072,
|
| 8708 |
+
"grad_norm": 0.2690318822860718,
|
| 8709 |
+
"learning_rate": 5e-05,
|
| 8710 |
+
"loss": 1.7954403162002563,
|
| 8711 |
+
"step": 2486
|
| 8712 |
+
},
|
| 8713 |
+
{
|
| 8714 |
+
"epoch": 0.8675488606447339,
|
| 8715 |
+
"grad_norm": 0.19765828549861908,
|
| 8716 |
+
"learning_rate": 5e-05,
|
| 8717 |
+
"loss": 2.0164332389831543,
|
| 8718 |
+
"step": 2488
|
| 8719 |
+
},
|
| 8720 |
+
{
|
| 8721 |
+
"epoch": 0.8682462471886605,
|
| 8722 |
+
"grad_norm": 0.26011911034584045,
|
| 8723 |
+
"learning_rate": 5e-05,
|
| 8724 |
+
"loss": 1.8244246244430542,
|
| 8725 |
+
"step": 2490
|
| 8726 |
+
},
|
| 8727 |
+
{
|
| 8728 |
+
"epoch": 0.8689436337325871,
|
| 8729 |
+
"grad_norm": 0.22959889471530914,
|
| 8730 |
+
"learning_rate": 5e-05,
|
| 8731 |
+
"loss": 1.931602120399475,
|
| 8732 |
+
"step": 2492
|
| 8733 |
+
},
|
| 8734 |
+
{
|
| 8735 |
+
"epoch": 0.8696410202765138,
|
| 8736 |
+
"grad_norm": 0.19653260707855225,
|
| 8737 |
+
"learning_rate": 5e-05,
|
| 8738 |
+
"loss": 1.7620649337768555,
|
| 8739 |
+
"step": 2494
|
| 8740 |
+
},
|
| 8741 |
+
{
|
| 8742 |
+
"epoch": 0.8703384068204404,
|
| 8743 |
+
"grad_norm": 0.2762472927570343,
|
| 8744 |
+
"learning_rate": 5e-05,
|
| 8745 |
+
"loss": 1.8492257595062256,
|
| 8746 |
+
"step": 2496
|
| 8747 |
+
},
|
| 8748 |
+
{
|
| 8749 |
+
"epoch": 0.871035793364367,
|
| 8750 |
+
"grad_norm": 0.22183212637901306,
|
| 8751 |
+
"learning_rate": 5e-05,
|
| 8752 |
+
"loss": 1.9420517683029175,
|
| 8753 |
+
"step": 2498
|
| 8754 |
+
},
|
| 8755 |
+
{
|
| 8756 |
+
"epoch": 0.8717331799082937,
|
| 8757 |
+
"grad_norm": 0.24676363170146942,
|
| 8758 |
+
"learning_rate": 5e-05,
|
| 8759 |
+
"loss": 1.8644121885299683,
|
| 8760 |
+
"step": 2500
|
| 8761 |
+
},
|
| 8762 |
+
{
|
| 8763 |
+
"epoch": 0.8724305664522203,
|
| 8764 |
+
"grad_norm": 0.2391708493232727,
|
| 8765 |
+
"learning_rate": 5e-05,
|
| 8766 |
+
"loss": 1.934468150138855,
|
| 8767 |
+
"step": 2502
|
| 8768 |
+
},
|
| 8769 |
+
{
|
| 8770 |
+
"epoch": 0.873127952996147,
|
| 8771 |
+
"grad_norm": 0.15963231027126312,
|
| 8772 |
+
"learning_rate": 5e-05,
|
| 8773 |
+
"loss": 1.9977290630340576,
|
| 8774 |
+
"step": 2504
|
| 8775 |
+
},
|
| 8776 |
+
{
|
| 8777 |
+
"epoch": 0.8738253395400736,
|
| 8778 |
+
"grad_norm": 0.23561052978038788,
|
| 8779 |
+
"learning_rate": 5e-05,
|
| 8780 |
+
"loss": 2.0387420654296875,
|
| 8781 |
+
"step": 2506
|
| 8782 |
+
},
|
| 8783 |
+
{
|
| 8784 |
+
"epoch": 0.8745227260840002,
|
| 8785 |
+
"grad_norm": 0.3309169113636017,
|
| 8786 |
+
"learning_rate": 5e-05,
|
| 8787 |
+
"loss": 1.9751169681549072,
|
| 8788 |
+
"step": 2508
|
| 8789 |
+
},
|
| 8790 |
+
{
|
| 8791 |
+
"epoch": 0.8752201126279269,
|
| 8792 |
+
"grad_norm": 0.26138627529144287,
|
| 8793 |
+
"learning_rate": 5e-05,
|
| 8794 |
+
"loss": 1.903587818145752,
|
| 8795 |
+
"step": 2510
|
| 8796 |
+
},
|
| 8797 |
+
{
|
| 8798 |
+
"epoch": 0.8759174991718535,
|
| 8799 |
+
"grad_norm": 0.20577403903007507,
|
| 8800 |
+
"learning_rate": 5e-05,
|
| 8801 |
+
"loss": 1.7635977268218994,
|
| 8802 |
+
"step": 2512
|
| 8803 |
+
},
|
| 8804 |
+
{
|
| 8805 |
+
"epoch": 0.8766148857157802,
|
| 8806 |
+
"grad_norm": 0.2254587560892105,
|
| 8807 |
+
"learning_rate": 5e-05,
|
| 8808 |
+
"loss": 1.7151050567626953,
|
| 8809 |
+
"step": 2514
|
| 8810 |
+
},
|
| 8811 |
+
{
|
| 8812 |
+
"epoch": 0.8773122722597068,
|
| 8813 |
+
"grad_norm": 0.16640746593475342,
|
| 8814 |
+
"learning_rate": 5e-05,
|
| 8815 |
+
"loss": 1.6992413997650146,
|
| 8816 |
+
"step": 2516
|
| 8817 |
+
},
|
| 8818 |
+
{
|
| 8819 |
+
"epoch": 0.8780096588036334,
|
| 8820 |
+
"grad_norm": 0.252765029668808,
|
| 8821 |
+
"learning_rate": 5e-05,
|
| 8822 |
+
"loss": 1.9397852420806885,
|
| 8823 |
+
"step": 2518
|
| 8824 |
+
},
|
| 8825 |
+
{
|
| 8826 |
+
"epoch": 0.8787070453475601,
|
| 8827 |
+
"grad_norm": 0.21200324594974518,
|
| 8828 |
+
"learning_rate": 5e-05,
|
| 8829 |
+
"loss": 1.9401975870132446,
|
| 8830 |
+
"step": 2520
|
| 8831 |
+
},
|
| 8832 |
+
{
|
| 8833 |
+
"epoch": 0.8794044318914866,
|
| 8834 |
+
"grad_norm": 0.15726792812347412,
|
| 8835 |
+
"learning_rate": 5e-05,
|
| 8836 |
+
"loss": 2.076117992401123,
|
| 8837 |
+
"step": 2522
|
| 8838 |
+
},
|
| 8839 |
+
{
|
| 8840 |
+
"epoch": 0.8801018184354132,
|
| 8841 |
+
"grad_norm": 0.2524771988391876,
|
| 8842 |
+
"learning_rate": 5e-05,
|
| 8843 |
+
"loss": 1.652165174484253,
|
| 8844 |
+
"step": 2524
|
| 8845 |
+
},
|
| 8846 |
+
{
|
| 8847 |
+
"epoch": 0.88079920497934,
|
| 8848 |
+
"grad_norm": 0.23599308729171753,
|
| 8849 |
+
"learning_rate": 5e-05,
|
| 8850 |
+
"loss": 1.9981966018676758,
|
| 8851 |
+
"step": 2526
|
| 8852 |
+
},
|
| 8853 |
+
{
|
| 8854 |
+
"epoch": 0.8814965915232665,
|
| 8855 |
+
"grad_norm": 0.2508905529975891,
|
| 8856 |
+
"learning_rate": 5e-05,
|
| 8857 |
+
"loss": 1.8920555114746094,
|
| 8858 |
+
"step": 2528
|
| 8859 |
+
},
|
| 8860 |
+
{
|
| 8861 |
+
"epoch": 0.8821939780671932,
|
| 8862 |
+
"grad_norm": 0.18876078724861145,
|
| 8863 |
+
"learning_rate": 5e-05,
|
| 8864 |
+
"loss": 1.944885492324829,
|
| 8865 |
+
"step": 2530
|
| 8866 |
+
},
|
| 8867 |
+
{
|
| 8868 |
+
"epoch": 0.8828913646111198,
|
| 8869 |
+
"grad_norm": 0.20604079961776733,
|
| 8870 |
+
"learning_rate": 5e-05,
|
| 8871 |
+
"loss": 1.6713067293167114,
|
| 8872 |
+
"step": 2532
|
| 8873 |
+
},
|
| 8874 |
+
{
|
| 8875 |
+
"epoch": 0.8835887511550464,
|
| 8876 |
+
"grad_norm": 0.21327614784240723,
|
| 8877 |
+
"learning_rate": 5e-05,
|
| 8878 |
+
"loss": 1.9312922954559326,
|
| 8879 |
+
"step": 2534
|
| 8880 |
+
},
|
| 8881 |
+
{
|
| 8882 |
+
"epoch": 0.8842861376989731,
|
| 8883 |
+
"grad_norm": 0.24845241010189056,
|
| 8884 |
+
"learning_rate": 5e-05,
|
| 8885 |
+
"loss": 1.7195186614990234,
|
| 8886 |
+
"step": 2536
|
| 8887 |
+
},
|
| 8888 |
+
{
|
| 8889 |
+
"epoch": 0.8849835242428997,
|
| 8890 |
+
"grad_norm": 0.2645180821418762,
|
| 8891 |
+
"learning_rate": 5e-05,
|
| 8892 |
+
"loss": 1.8852179050445557,
|
| 8893 |
+
"step": 2538
|
| 8894 |
+
},
|
| 8895 |
+
{
|
| 8896 |
+
"epoch": 0.8856809107868263,
|
| 8897 |
+
"grad_norm": 0.16576892137527466,
|
| 8898 |
+
"learning_rate": 5e-05,
|
| 8899 |
+
"loss": 2.1656389236450195,
|
| 8900 |
+
"step": 2540
|
| 8901 |
+
},
|
| 8902 |
+
{
|
| 8903 |
+
"epoch": 0.886378297330753,
|
| 8904 |
+
"grad_norm": 0.3268888592720032,
|
| 8905 |
+
"learning_rate": 5e-05,
|
| 8906 |
+
"loss": 1.7451763153076172,
|
| 8907 |
+
"step": 2542
|
| 8908 |
+
},
|
| 8909 |
+
{
|
| 8910 |
+
"epoch": 0.8870756838746796,
|
| 8911 |
+
"grad_norm": 0.2656945586204529,
|
| 8912 |
+
"learning_rate": 5e-05,
|
| 8913 |
+
"loss": 1.654427409172058,
|
| 8914 |
+
"step": 2544
|
| 8915 |
+
},
|
| 8916 |
+
{
|
| 8917 |
+
"epoch": 0.8877730704186063,
|
| 8918 |
+
"grad_norm": 0.20410767197608948,
|
| 8919 |
+
"learning_rate": 5e-05,
|
| 8920 |
+
"loss": 1.9891842603683472,
|
| 8921 |
+
"step": 2546
|
| 8922 |
+
},
|
| 8923 |
+
{
|
| 8924 |
+
"epoch": 0.8884704569625329,
|
| 8925 |
+
"grad_norm": 0.17035138607025146,
|
| 8926 |
+
"learning_rate": 5e-05,
|
| 8927 |
+
"loss": 1.9926782846450806,
|
| 8928 |
+
"step": 2548
|
| 8929 |
+
},
|
| 8930 |
+
{
|
| 8931 |
+
"epoch": 0.8891678435064595,
|
| 8932 |
+
"grad_norm": 0.37120959162712097,
|
| 8933 |
+
"learning_rate": 5e-05,
|
| 8934 |
+
"loss": 1.6961153745651245,
|
| 8935 |
+
"step": 2550
|
| 8936 |
+
},
|
| 8937 |
+
{
|
| 8938 |
+
"epoch": 0.8898652300503862,
|
| 8939 |
+
"grad_norm": 0.22341012954711914,
|
| 8940 |
+
"learning_rate": 5e-05,
|
| 8941 |
+
"loss": 1.5798993110656738,
|
| 8942 |
+
"step": 2552
|
| 8943 |
+
},
|
| 8944 |
+
{
|
| 8945 |
+
"epoch": 0.8905626165943128,
|
| 8946 |
+
"grad_norm": 0.236846923828125,
|
| 8947 |
+
"learning_rate": 5e-05,
|
| 8948 |
+
"loss": 2.0399224758148193,
|
| 8949 |
+
"step": 2554
|
| 8950 |
+
},
|
| 8951 |
+
{
|
| 8952 |
+
"epoch": 0.8912600031382395,
|
| 8953 |
+
"grad_norm": 0.1636209487915039,
|
| 8954 |
+
"learning_rate": 5e-05,
|
| 8955 |
+
"loss": 1.870794415473938,
|
| 8956 |
+
"step": 2556
|
| 8957 |
+
},
|
| 8958 |
+
{
|
| 8959 |
+
"epoch": 0.8919573896821661,
|
| 8960 |
+
"grad_norm": 0.22900991141796112,
|
| 8961 |
+
"learning_rate": 5e-05,
|
| 8962 |
+
"loss": 1.932793140411377,
|
| 8963 |
+
"step": 2558
|
| 8964 |
+
},
|
| 8965 |
+
{
|
| 8966 |
+
"epoch": 0.8926547762260927,
|
| 8967 |
+
"grad_norm": 0.28880369663238525,
|
| 8968 |
+
"learning_rate": 5e-05,
|
| 8969 |
+
"loss": 1.7882640361785889,
|
| 8970 |
+
"step": 2560
|
| 8971 |
+
},
|
| 8972 |
+
{
|
| 8973 |
+
"epoch": 0.8933521627700194,
|
| 8974 |
+
"grad_norm": 0.19175614416599274,
|
| 8975 |
+
"learning_rate": 5e-05,
|
| 8976 |
+
"loss": 1.9550821781158447,
|
| 8977 |
+
"step": 2562
|
| 8978 |
+
},
|
| 8979 |
+
{
|
| 8980 |
+
"epoch": 0.894049549313946,
|
| 8981 |
+
"grad_norm": 0.23375819623470306,
|
| 8982 |
+
"learning_rate": 5e-05,
|
| 8983 |
+
"loss": 1.7253637313842773,
|
| 8984 |
+
"step": 2564
|
| 8985 |
+
},
|
| 8986 |
+
{
|
| 8987 |
+
"epoch": 0.8947469358578726,
|
| 8988 |
+
"grad_norm": 0.27817198634147644,
|
| 8989 |
+
"learning_rate": 5e-05,
|
| 8990 |
+
"loss": 1.9125609397888184,
|
| 8991 |
+
"step": 2566
|
| 8992 |
+
},
|
| 8993 |
+
{
|
| 8994 |
+
"epoch": 0.8954443224017993,
|
| 8995 |
+
"grad_norm": 0.21705344319343567,
|
| 8996 |
+
"learning_rate": 5e-05,
|
| 8997 |
+
"loss": 1.8138537406921387,
|
| 8998 |
+
"step": 2568
|
| 8999 |
+
},
|
| 9000 |
+
{
|
| 9001 |
+
"epoch": 0.8961417089457259,
|
| 9002 |
+
"grad_norm": 0.3142533600330353,
|
| 9003 |
+
"learning_rate": 5e-05,
|
| 9004 |
+
"loss": 1.692766547203064,
|
| 9005 |
+
"step": 2570
|
| 9006 |
+
},
|
| 9007 |
+
{
|
| 9008 |
+
"epoch": 0.8968390954896526,
|
| 9009 |
+
"grad_norm": 0.22375591099262238,
|
| 9010 |
+
"learning_rate": 5e-05,
|
| 9011 |
+
"loss": 1.9875195026397705,
|
| 9012 |
+
"step": 2572
|
| 9013 |
+
},
|
| 9014 |
+
{
|
| 9015 |
+
"epoch": 0.8975364820335792,
|
| 9016 |
+
"grad_norm": 0.18041948974132538,
|
| 9017 |
+
"learning_rate": 5e-05,
|
| 9018 |
+
"loss": 1.9115439653396606,
|
| 9019 |
+
"step": 2574
|
| 9020 |
+
},
|
| 9021 |
+
{
|
| 9022 |
+
"epoch": 0.8982338685775058,
|
| 9023 |
+
"grad_norm": 0.18039172887802124,
|
| 9024 |
+
"learning_rate": 5e-05,
|
| 9025 |
+
"loss": 1.860901117324829,
|
| 9026 |
+
"step": 2576
|
| 9027 |
+
},
|
| 9028 |
+
{
|
| 9029 |
+
"epoch": 0.8989312551214325,
|
| 9030 |
+
"grad_norm": 0.2053157389163971,
|
| 9031 |
+
"learning_rate": 5e-05,
|
| 9032 |
+
"loss": 1.9434962272644043,
|
| 9033 |
+
"step": 2578
|
| 9034 |
+
},
|
| 9035 |
+
{
|
| 9036 |
+
"epoch": 0.899628641665359,
|
| 9037 |
+
"grad_norm": 0.1571952998638153,
|
| 9038 |
+
"learning_rate": 5e-05,
|
| 9039 |
+
"loss": 1.936698079109192,
|
| 9040 |
+
"step": 2580
|
| 9041 |
+
},
|
| 9042 |
+
{
|
| 9043 |
+
"epoch": 0.9003260282092858,
|
| 9044 |
+
"grad_norm": 0.21368089318275452,
|
| 9045 |
+
"learning_rate": 5e-05,
|
| 9046 |
+
"loss": 2.023897409439087,
|
| 9047 |
+
"step": 2582
|
| 9048 |
+
},
|
| 9049 |
+
{
|
| 9050 |
+
"epoch": 0.9010234147532123,
|
| 9051 |
+
"grad_norm": 0.1864442527294159,
|
| 9052 |
+
"learning_rate": 5e-05,
|
| 9053 |
+
"loss": 2.1277942657470703,
|
| 9054 |
+
"step": 2584
|
| 9055 |
+
},
|
| 9056 |
+
{
|
| 9057 |
+
"epoch": 0.9017208012971389,
|
| 9058 |
+
"grad_norm": 0.2126200795173645,
|
| 9059 |
+
"learning_rate": 5e-05,
|
| 9060 |
+
"loss": 1.7691402435302734,
|
| 9061 |
+
"step": 2586
|
| 9062 |
+
},
|
| 9063 |
+
{
|
| 9064 |
+
"epoch": 0.9024181878410656,
|
| 9065 |
+
"grad_norm": 0.19210372865200043,
|
| 9066 |
+
"learning_rate": 5e-05,
|
| 9067 |
+
"loss": 1.9965739250183105,
|
| 9068 |
+
"step": 2588
|
| 9069 |
+
},
|
| 9070 |
+
{
|
| 9071 |
+
"epoch": 0.9031155743849922,
|
| 9072 |
+
"grad_norm": 0.27291032671928406,
|
| 9073 |
+
"learning_rate": 5e-05,
|
| 9074 |
+
"loss": 1.896301031112671,
|
| 9075 |
+
"step": 2590
|
| 9076 |
+
},
|
| 9077 |
+
{
|
| 9078 |
+
"epoch": 0.9038129609289188,
|
| 9079 |
+
"grad_norm": 0.24564699828624725,
|
| 9080 |
+
"learning_rate": 5e-05,
|
| 9081 |
+
"loss": 1.6648836135864258,
|
| 9082 |
+
"step": 2592
|
| 9083 |
+
},
|
| 9084 |
+
{
|
| 9085 |
+
"epoch": 0.9045103474728455,
|
| 9086 |
+
"grad_norm": 0.2528457045555115,
|
| 9087 |
+
"learning_rate": 5e-05,
|
| 9088 |
+
"loss": 1.587568759918213,
|
| 9089 |
+
"step": 2594
|
| 9090 |
+
},
|
| 9091 |
+
{
|
| 9092 |
+
"epoch": 0.9052077340167721,
|
| 9093 |
+
"grad_norm": 0.21464523673057556,
|
| 9094 |
+
"learning_rate": 5e-05,
|
| 9095 |
+
"loss": 1.9642722606658936,
|
| 9096 |
+
"step": 2596
|
| 9097 |
+
},
|
| 9098 |
+
{
|
| 9099 |
+
"epoch": 0.9059051205606988,
|
| 9100 |
+
"grad_norm": 0.3087773621082306,
|
| 9101 |
+
"learning_rate": 5e-05,
|
| 9102 |
+
"loss": 1.8250300884246826,
|
| 9103 |
+
"step": 2598
|
| 9104 |
+
},
|
| 9105 |
+
{
|
| 9106 |
+
"epoch": 0.9066025071046254,
|
| 9107 |
+
"grad_norm": 0.2622036337852478,
|
| 9108 |
+
"learning_rate": 5e-05,
|
| 9109 |
+
"loss": 1.8403692245483398,
|
| 9110 |
+
"step": 2600
|
| 9111 |
+
},
|
| 9112 |
+
{
|
| 9113 |
+
"epoch": 0.907299893648552,
|
| 9114 |
+
"grad_norm": 0.19684091210365295,
|
| 9115 |
+
"learning_rate": 5e-05,
|
| 9116 |
+
"loss": 1.8768137693405151,
|
| 9117 |
+
"step": 2602
|
| 9118 |
+
},
|
| 9119 |
+
{
|
| 9120 |
+
"epoch": 0.9079972801924787,
|
| 9121 |
+
"grad_norm": 0.23731729388237,
|
| 9122 |
+
"learning_rate": 5e-05,
|
| 9123 |
+
"loss": 1.6398066282272339,
|
| 9124 |
+
"step": 2604
|
| 9125 |
+
},
|
| 9126 |
+
{
|
| 9127 |
+
"epoch": 0.9086946667364053,
|
| 9128 |
+
"grad_norm": 0.1656942069530487,
|
| 9129 |
+
"learning_rate": 5e-05,
|
| 9130 |
+
"loss": 2.0291547775268555,
|
| 9131 |
+
"step": 2606
|
| 9132 |
+
},
|
| 9133 |
+
{
|
| 9134 |
+
"epoch": 0.9093920532803319,
|
| 9135 |
+
"grad_norm": 0.1387060135602951,
|
| 9136 |
+
"learning_rate": 5e-05,
|
| 9137 |
+
"loss": 1.8610889911651611,
|
| 9138 |
+
"step": 2608
|
| 9139 |
+
},
|
| 9140 |
+
{
|
| 9141 |
+
"epoch": 0.9100894398242586,
|
| 9142 |
+
"grad_norm": 0.2080821543931961,
|
| 9143 |
+
"learning_rate": 5e-05,
|
| 9144 |
+
"loss": 2.0375406742095947,
|
| 9145 |
+
"step": 2610
|
| 9146 |
+
},
|
| 9147 |
+
{
|
| 9148 |
+
"epoch": 0.9107868263681852,
|
| 9149 |
+
"grad_norm": 0.20191188156604767,
|
| 9150 |
+
"learning_rate": 5e-05,
|
| 9151 |
+
"loss": 1.9188122749328613,
|
| 9152 |
+
"step": 2612
|
| 9153 |
+
},
|
| 9154 |
+
{
|
| 9155 |
+
"epoch": 0.9114842129121119,
|
| 9156 |
+
"grad_norm": 0.2041167914867401,
|
| 9157 |
+
"learning_rate": 5e-05,
|
| 9158 |
+
"loss": 1.6870101690292358,
|
| 9159 |
+
"step": 2614
|
| 9160 |
+
},
|
| 9161 |
+
{
|
| 9162 |
+
"epoch": 0.9121815994560385,
|
| 9163 |
+
"grad_norm": 0.1676097959280014,
|
| 9164 |
+
"learning_rate": 5e-05,
|
| 9165 |
+
"loss": 2.0055911540985107,
|
| 9166 |
+
"step": 2616
|
| 9167 |
+
},
|
| 9168 |
+
{
|
| 9169 |
+
"epoch": 0.9128789859999651,
|
| 9170 |
+
"grad_norm": 0.25617048144340515,
|
| 9171 |
+
"learning_rate": 5e-05,
|
| 9172 |
+
"loss": 1.8428096771240234,
|
| 9173 |
+
"step": 2618
|
| 9174 |
+
},
|
| 9175 |
+
{
|
| 9176 |
+
"epoch": 0.9135763725438918,
|
| 9177 |
+
"grad_norm": 0.21877171099185944,
|
| 9178 |
+
"learning_rate": 5e-05,
|
| 9179 |
+
"loss": 1.909017562866211,
|
| 9180 |
+
"step": 2620
|
| 9181 |
+
},
|
| 9182 |
+
{
|
| 9183 |
+
"epoch": 0.9142737590878184,
|
| 9184 |
+
"grad_norm": 0.22135400772094727,
|
| 9185 |
+
"learning_rate": 5e-05,
|
| 9186 |
+
"loss": 1.9755818843841553,
|
| 9187 |
+
"step": 2622
|
| 9188 |
+
},
|
| 9189 |
+
{
|
| 9190 |
+
"epoch": 0.9149711456317451,
|
| 9191 |
+
"grad_norm": 0.26330921053886414,
|
| 9192 |
+
"learning_rate": 5e-05,
|
| 9193 |
+
"loss": 2.00614070892334,
|
| 9194 |
+
"step": 2624
|
| 9195 |
+
},
|
| 9196 |
+
{
|
| 9197 |
+
"epoch": 0.9156685321756717,
|
| 9198 |
+
"grad_norm": 0.2363353669643402,
|
| 9199 |
+
"learning_rate": 5e-05,
|
| 9200 |
+
"loss": 1.9779236316680908,
|
| 9201 |
+
"step": 2626
|
| 9202 |
+
},
|
| 9203 |
+
{
|
| 9204 |
+
"epoch": 0.9163659187195983,
|
| 9205 |
+
"grad_norm": 0.1923648715019226,
|
| 9206 |
+
"learning_rate": 5e-05,
|
| 9207 |
+
"loss": 2.1706905364990234,
|
| 9208 |
+
"step": 2628
|
| 9209 |
+
},
|
| 9210 |
+
{
|
| 9211 |
+
"epoch": 0.917063305263525,
|
| 9212 |
+
"grad_norm": 0.2710999846458435,
|
| 9213 |
+
"learning_rate": 5e-05,
|
| 9214 |
+
"loss": 1.9036699533462524,
|
| 9215 |
+
"step": 2630
|
| 9216 |
+
},
|
| 9217 |
+
{
|
| 9218 |
+
"epoch": 0.9177606918074516,
|
| 9219 |
+
"grad_norm": 0.22254317998886108,
|
| 9220 |
+
"learning_rate": 5e-05,
|
| 9221 |
+
"loss": 2.073990821838379,
|
| 9222 |
+
"step": 2632
|
| 9223 |
+
},
|
| 9224 |
+
{
|
| 9225 |
+
"epoch": 0.9184580783513782,
|
| 9226 |
+
"grad_norm": 0.18711015582084656,
|
| 9227 |
+
"learning_rate": 5e-05,
|
| 9228 |
+
"loss": 1.9848815202713013,
|
| 9229 |
+
"step": 2634
|
| 9230 |
+
},
|
| 9231 |
+
{
|
| 9232 |
+
"epoch": 0.9191554648953049,
|
| 9233 |
+
"grad_norm": 0.2281409651041031,
|
| 9234 |
+
"learning_rate": 5e-05,
|
| 9235 |
+
"loss": 1.8835316896438599,
|
| 9236 |
+
"step": 2636
|
| 9237 |
+
},
|
| 9238 |
+
{
|
| 9239 |
+
"epoch": 0.9198528514392315,
|
| 9240 |
+
"grad_norm": 0.19834259152412415,
|
| 9241 |
+
"learning_rate": 5e-05,
|
| 9242 |
+
"loss": 1.7961277961730957,
|
| 9243 |
+
"step": 2638
|
| 9244 |
+
},
|
| 9245 |
+
{
|
| 9246 |
+
"epoch": 0.9205502379831582,
|
| 9247 |
+
"grad_norm": 0.1919710338115692,
|
| 9248 |
+
"learning_rate": 5e-05,
|
| 9249 |
+
"loss": 1.780514121055603,
|
| 9250 |
+
"step": 2640
|
| 9251 |
+
},
|
| 9252 |
+
{
|
| 9253 |
+
"epoch": 0.9212476245270848,
|
| 9254 |
+
"grad_norm": 0.20375385880470276,
|
| 9255 |
+
"learning_rate": 5e-05,
|
| 9256 |
+
"loss": 1.6803020238876343,
|
| 9257 |
+
"step": 2642
|
| 9258 |
+
},
|
| 9259 |
+
{
|
| 9260 |
+
"epoch": 0.9219450110710113,
|
| 9261 |
+
"grad_norm": 0.17505325376987457,
|
| 9262 |
+
"learning_rate": 5e-05,
|
| 9263 |
+
"loss": 2.070007085800171,
|
| 9264 |
+
"step": 2644
|
| 9265 |
+
},
|
| 9266 |
+
{
|
| 9267 |
+
"epoch": 0.922642397614938,
|
| 9268 |
+
"grad_norm": 0.21515130996704102,
|
| 9269 |
+
"learning_rate": 5e-05,
|
| 9270 |
+
"loss": 2.061142921447754,
|
| 9271 |
+
"step": 2646
|
| 9272 |
+
},
|
| 9273 |
+
{
|
| 9274 |
+
"epoch": 0.9233397841588646,
|
| 9275 |
+
"grad_norm": 0.18638178706169128,
|
| 9276 |
+
"learning_rate": 5e-05,
|
| 9277 |
+
"loss": 1.846124529838562,
|
| 9278 |
+
"step": 2648
|
| 9279 |
+
},
|
| 9280 |
+
{
|
| 9281 |
+
"epoch": 0.9240371707027913,
|
| 9282 |
+
"grad_norm": 0.22283639013767242,
|
| 9283 |
+
"learning_rate": 5e-05,
|
| 9284 |
+
"loss": 1.9895353317260742,
|
| 9285 |
+
"step": 2650
|
| 9286 |
+
},
|
| 9287 |
+
{
|
| 9288 |
+
"epoch": 0.9247345572467179,
|
| 9289 |
+
"grad_norm": 0.18122327327728271,
|
| 9290 |
+
"learning_rate": 5e-05,
|
| 9291 |
+
"loss": 2.0273783206939697,
|
| 9292 |
+
"step": 2652
|
| 9293 |
+
},
|
| 9294 |
+
{
|
| 9295 |
+
"epoch": 0.9254319437906445,
|
| 9296 |
+
"grad_norm": 0.1830211579799652,
|
| 9297 |
+
"learning_rate": 5e-05,
|
| 9298 |
+
"loss": 1.9389231204986572,
|
| 9299 |
+
"step": 2654
|
| 9300 |
+
},
|
| 9301 |
+
{
|
| 9302 |
+
"epoch": 0.9261293303345712,
|
| 9303 |
+
"grad_norm": 0.208659827709198,
|
| 9304 |
+
"learning_rate": 5e-05,
|
| 9305 |
+
"loss": 1.9987062215805054,
|
| 9306 |
+
"step": 2656
|
| 9307 |
+
},
|
| 9308 |
+
{
|
| 9309 |
+
"epoch": 0.9268267168784978,
|
| 9310 |
+
"grad_norm": 0.2385203242301941,
|
| 9311 |
+
"learning_rate": 5e-05,
|
| 9312 |
+
"loss": 1.8523343801498413,
|
| 9313 |
+
"step": 2658
|
| 9314 |
+
},
|
| 9315 |
+
{
|
| 9316 |
+
"epoch": 0.9275241034224244,
|
| 9317 |
+
"grad_norm": 0.2189442217350006,
|
| 9318 |
+
"learning_rate": 5e-05,
|
| 9319 |
+
"loss": 1.9014790058135986,
|
| 9320 |
+
"step": 2660
|
| 9321 |
+
},
|
| 9322 |
+
{
|
| 9323 |
+
"epoch": 0.9282214899663511,
|
| 9324 |
+
"grad_norm": 0.2747405171394348,
|
| 9325 |
+
"learning_rate": 5e-05,
|
| 9326 |
+
"loss": 1.873617172241211,
|
| 9327 |
+
"step": 2662
|
| 9328 |
+
},
|
| 9329 |
+
{
|
| 9330 |
+
"epoch": 0.9289188765102777,
|
| 9331 |
+
"grad_norm": 0.24354961514472961,
|
| 9332 |
+
"learning_rate": 5e-05,
|
| 9333 |
+
"loss": 1.7986871004104614,
|
| 9334 |
+
"step": 2664
|
| 9335 |
+
},
|
| 9336 |
+
{
|
| 9337 |
+
"epoch": 0.9296162630542044,
|
| 9338 |
+
"grad_norm": 0.2280634343624115,
|
| 9339 |
+
"learning_rate": 5e-05,
|
| 9340 |
+
"loss": 1.739278793334961,
|
| 9341 |
+
"step": 2666
|
| 9342 |
+
},
|
| 9343 |
+
{
|
| 9344 |
+
"epoch": 0.930313649598131,
|
| 9345 |
+
"grad_norm": 0.3209410011768341,
|
| 9346 |
+
"learning_rate": 5e-05,
|
| 9347 |
+
"loss": 1.8125033378601074,
|
| 9348 |
+
"step": 2668
|
| 9349 |
+
},
|
| 9350 |
+
{
|
| 9351 |
+
"epoch": 0.9310110361420576,
|
| 9352 |
+
"grad_norm": 0.2111290842294693,
|
| 9353 |
+
"learning_rate": 5e-05,
|
| 9354 |
+
"loss": 1.634263515472412,
|
| 9355 |
+
"step": 2670
|
| 9356 |
+
},
|
| 9357 |
+
{
|
| 9358 |
+
"epoch": 0.9317084226859843,
|
| 9359 |
+
"grad_norm": 0.24231672286987305,
|
| 9360 |
+
"learning_rate": 5e-05,
|
| 9361 |
+
"loss": 1.8393033742904663,
|
| 9362 |
+
"step": 2672
|
| 9363 |
+
},
|
| 9364 |
+
{
|
| 9365 |
+
"epoch": 0.9324058092299109,
|
| 9366 |
+
"grad_norm": 0.22962254285812378,
|
| 9367 |
+
"learning_rate": 5e-05,
|
| 9368 |
+
"loss": 1.6657109260559082,
|
| 9369 |
+
"step": 2674
|
| 9370 |
+
},
|
| 9371 |
+
{
|
| 9372 |
+
"epoch": 0.9331031957738375,
|
| 9373 |
+
"grad_norm": 0.22991959750652313,
|
| 9374 |
+
"learning_rate": 5e-05,
|
| 9375 |
+
"loss": 1.7309353351593018,
|
| 9376 |
+
"step": 2676
|
| 9377 |
+
},
|
| 9378 |
+
{
|
| 9379 |
+
"epoch": 0.9338005823177642,
|
| 9380 |
+
"grad_norm": 0.20495624840259552,
|
| 9381 |
+
"learning_rate": 5e-05,
|
| 9382 |
+
"loss": 1.9219999313354492,
|
| 9383 |
+
"step": 2678
|
| 9384 |
+
},
|
| 9385 |
+
{
|
| 9386 |
+
"epoch": 0.9344979688616908,
|
| 9387 |
+
"grad_norm": 0.21537181735038757,
|
| 9388 |
+
"learning_rate": 5e-05,
|
| 9389 |
+
"loss": 1.7155791521072388,
|
| 9390 |
+
"step": 2680
|
| 9391 |
+
},
|
| 9392 |
+
{
|
| 9393 |
+
"epoch": 0.9351953554056175,
|
| 9394 |
+
"grad_norm": 0.16606444120407104,
|
| 9395 |
+
"learning_rate": 5e-05,
|
| 9396 |
+
"loss": 1.9162561893463135,
|
| 9397 |
+
"step": 2682
|
| 9398 |
+
},
|
| 9399 |
+
{
|
| 9400 |
+
"epoch": 0.9358927419495441,
|
| 9401 |
+
"grad_norm": 0.22539839148521423,
|
| 9402 |
+
"learning_rate": 5e-05,
|
| 9403 |
+
"loss": 2.145418167114258,
|
| 9404 |
+
"step": 2684
|
| 9405 |
+
},
|
| 9406 |
+
{
|
| 9407 |
+
"epoch": 0.9365901284934707,
|
| 9408 |
+
"grad_norm": 0.21142470836639404,
|
| 9409 |
+
"learning_rate": 5e-05,
|
| 9410 |
+
"loss": 1.837956428527832,
|
| 9411 |
+
"step": 2686
|
| 9412 |
+
},
|
| 9413 |
+
{
|
| 9414 |
+
"epoch": 0.9372875150373974,
|
| 9415 |
+
"grad_norm": 0.30611351132392883,
|
| 9416 |
+
"learning_rate": 5e-05,
|
| 9417 |
+
"loss": 1.99916672706604,
|
| 9418 |
+
"step": 2688
|
| 9419 |
+
},
|
| 9420 |
+
{
|
| 9421 |
+
"epoch": 0.937984901581324,
|
| 9422 |
+
"grad_norm": 0.2546582520008087,
|
| 9423 |
+
"learning_rate": 5e-05,
|
| 9424 |
+
"loss": 1.8070523738861084,
|
| 9425 |
+
"step": 2690
|
| 9426 |
+
},
|
| 9427 |
+
{
|
| 9428 |
+
"epoch": 0.9386822881252507,
|
| 9429 |
+
"grad_norm": 0.2777990698814392,
|
| 9430 |
+
"learning_rate": 5e-05,
|
| 9431 |
+
"loss": 1.8161311149597168,
|
| 9432 |
+
"step": 2692
|
| 9433 |
+
},
|
| 9434 |
+
{
|
| 9435 |
+
"epoch": 0.9393796746691773,
|
| 9436 |
+
"grad_norm": 0.20838379859924316,
|
| 9437 |
+
"learning_rate": 5e-05,
|
| 9438 |
+
"loss": 1.7788996696472168,
|
| 9439 |
+
"step": 2694
|
| 9440 |
+
},
|
| 9441 |
+
{
|
| 9442 |
+
"epoch": 0.9400770612131039,
|
| 9443 |
+
"grad_norm": 0.23629185557365417,
|
| 9444 |
+
"learning_rate": 5e-05,
|
| 9445 |
+
"loss": 1.9141902923583984,
|
| 9446 |
+
"step": 2696
|
| 9447 |
+
},
|
| 9448 |
+
{
|
| 9449 |
+
"epoch": 0.9407744477570306,
|
| 9450 |
+
"grad_norm": 0.24336197972297668,
|
| 9451 |
+
"learning_rate": 5e-05,
|
| 9452 |
+
"loss": 1.840604543685913,
|
| 9453 |
+
"step": 2698
|
| 9454 |
+
},
|
| 9455 |
+
{
|
| 9456 |
+
"epoch": 0.9414718343009572,
|
| 9457 |
+
"grad_norm": 0.23507782816886902,
|
| 9458 |
+
"learning_rate": 5e-05,
|
| 9459 |
+
"loss": 1.926959753036499,
|
| 9460 |
+
"step": 2700
|
| 9461 |
+
},
|
| 9462 |
+
{
|
| 9463 |
+
"epoch": 0.9421692208448837,
|
| 9464 |
+
"grad_norm": 0.19096162915229797,
|
| 9465 |
+
"learning_rate": 5e-05,
|
| 9466 |
+
"loss": 1.8198974132537842,
|
| 9467 |
+
"step": 2702
|
| 9468 |
+
},
|
| 9469 |
+
{
|
| 9470 |
+
"epoch": 0.9428666073888105,
|
| 9471 |
+
"grad_norm": 0.2538565397262573,
|
| 9472 |
+
"learning_rate": 5e-05,
|
| 9473 |
+
"loss": 1.8042070865631104,
|
| 9474 |
+
"step": 2704
|
| 9475 |
+
},
|
| 9476 |
+
{
|
| 9477 |
+
"epoch": 0.943563993932737,
|
| 9478 |
+
"grad_norm": 0.27375662326812744,
|
| 9479 |
+
"learning_rate": 5e-05,
|
| 9480 |
+
"loss": 1.772554874420166,
|
| 9481 |
+
"step": 2706
|
| 9482 |
+
},
|
| 9483 |
+
{
|
| 9484 |
+
"epoch": 0.9442613804766637,
|
| 9485 |
+
"grad_norm": 0.22935160994529724,
|
| 9486 |
+
"learning_rate": 5e-05,
|
| 9487 |
+
"loss": 1.8237781524658203,
|
| 9488 |
+
"step": 2708
|
| 9489 |
+
},
|
| 9490 |
+
{
|
| 9491 |
+
"epoch": 0.9449587670205903,
|
| 9492 |
+
"grad_norm": 0.2059555947780609,
|
| 9493 |
+
"learning_rate": 5e-05,
|
| 9494 |
+
"loss": 1.8149011135101318,
|
| 9495 |
+
"step": 2710
|
| 9496 |
+
},
|
| 9497 |
+
{
|
| 9498 |
+
"epoch": 0.9456561535645169,
|
| 9499 |
+
"grad_norm": 0.19966955482959747,
|
| 9500 |
+
"learning_rate": 5e-05,
|
| 9501 |
+
"loss": 1.8101370334625244,
|
| 9502 |
+
"step": 2712
|
| 9503 |
+
},
|
| 9504 |
+
{
|
| 9505 |
+
"epoch": 0.9463535401084436,
|
| 9506 |
+
"grad_norm": 0.3353351354598999,
|
| 9507 |
+
"learning_rate": 5e-05,
|
| 9508 |
+
"loss": 1.7129199504852295,
|
| 9509 |
+
"step": 2714
|
| 9510 |
+
},
|
| 9511 |
+
{
|
| 9512 |
+
"epoch": 0.9470509266523702,
|
| 9513 |
+
"grad_norm": 0.19486363232135773,
|
| 9514 |
+
"learning_rate": 5e-05,
|
| 9515 |
+
"loss": 2.043515205383301,
|
| 9516 |
+
"step": 2716
|
| 9517 |
+
},
|
| 9518 |
+
{
|
| 9519 |
+
"epoch": 0.9477483131962969,
|
| 9520 |
+
"grad_norm": 0.22511737048625946,
|
| 9521 |
+
"learning_rate": 5e-05,
|
| 9522 |
+
"loss": 1.916710615158081,
|
| 9523 |
+
"step": 2718
|
| 9524 |
+
},
|
| 9525 |
+
{
|
| 9526 |
+
"epoch": 0.9484456997402235,
|
| 9527 |
+
"grad_norm": 0.27413415908813477,
|
| 9528 |
+
"learning_rate": 5e-05,
|
| 9529 |
+
"loss": 1.7739595174789429,
|
| 9530 |
+
"step": 2720
|
| 9531 |
+
},
|
| 9532 |
+
{
|
| 9533 |
+
"epoch": 0.9491430862841501,
|
| 9534 |
+
"grad_norm": 0.2778632342815399,
|
| 9535 |
+
"learning_rate": 5e-05,
|
| 9536 |
+
"loss": 1.6664798259735107,
|
| 9537 |
+
"step": 2722
|
| 9538 |
+
},
|
| 9539 |
+
{
|
| 9540 |
+
"epoch": 0.9498404728280768,
|
| 9541 |
+
"grad_norm": 0.24520686268806458,
|
| 9542 |
+
"learning_rate": 5e-05,
|
| 9543 |
+
"loss": 1.8128085136413574,
|
| 9544 |
+
"step": 2724
|
| 9545 |
+
},
|
| 9546 |
+
{
|
| 9547 |
+
"epoch": 0.9505378593720034,
|
| 9548 |
+
"grad_norm": 0.22817257046699524,
|
| 9549 |
+
"learning_rate": 5e-05,
|
| 9550 |
+
"loss": 1.9286627769470215,
|
| 9551 |
+
"step": 2726
|
| 9552 |
+
},
|
| 9553 |
+
{
|
| 9554 |
+
"epoch": 0.95123524591593,
|
| 9555 |
+
"grad_norm": 0.22017443180084229,
|
| 9556 |
+
"learning_rate": 5e-05,
|
| 9557 |
+
"loss": 1.917222023010254,
|
| 9558 |
+
"step": 2728
|
| 9559 |
+
},
|
| 9560 |
+
{
|
| 9561 |
+
"epoch": 0.9519326324598567,
|
| 9562 |
+
"grad_norm": 0.2212352454662323,
|
| 9563 |
+
"learning_rate": 5e-05,
|
| 9564 |
+
"loss": 1.952441692352295,
|
| 9565 |
+
"step": 2730
|
| 9566 |
+
},
|
| 9567 |
+
{
|
| 9568 |
+
"epoch": 0.9526300190037833,
|
| 9569 |
+
"grad_norm": 0.23949624598026276,
|
| 9570 |
+
"learning_rate": 5e-05,
|
| 9571 |
+
"loss": 1.938012719154358,
|
| 9572 |
+
"step": 2732
|
| 9573 |
+
},
|
| 9574 |
+
{
|
| 9575 |
+
"epoch": 0.95332740554771,
|
| 9576 |
+
"grad_norm": 0.19075579941272736,
|
| 9577 |
+
"learning_rate": 5e-05,
|
| 9578 |
+
"loss": 1.8858611583709717,
|
| 9579 |
+
"step": 2734
|
| 9580 |
+
},
|
| 9581 |
+
{
|
| 9582 |
+
"epoch": 0.9540247920916366,
|
| 9583 |
+
"grad_norm": 0.19997099041938782,
|
| 9584 |
+
"learning_rate": 5e-05,
|
| 9585 |
+
"loss": 2.013164520263672,
|
| 9586 |
+
"step": 2736
|
| 9587 |
+
},
|
| 9588 |
+
{
|
| 9589 |
+
"epoch": 0.9547221786355632,
|
| 9590 |
+
"grad_norm": 0.19334496557712555,
|
| 9591 |
+
"learning_rate": 5e-05,
|
| 9592 |
+
"loss": 1.986656904220581,
|
| 9593 |
+
"step": 2738
|
| 9594 |
+
},
|
| 9595 |
+
{
|
| 9596 |
+
"epoch": 0.9554195651794899,
|
| 9597 |
+
"grad_norm": 0.2309669405221939,
|
| 9598 |
+
"learning_rate": 5e-05,
|
| 9599 |
+
"loss": 1.9071218967437744,
|
| 9600 |
+
"step": 2740
|
| 9601 |
+
},
|
| 9602 |
+
{
|
| 9603 |
+
"epoch": 0.9561169517234165,
|
| 9604 |
+
"grad_norm": 0.26310646533966064,
|
| 9605 |
+
"learning_rate": 5e-05,
|
| 9606 |
+
"loss": 1.9484144449234009,
|
| 9607 |
+
"step": 2742
|
| 9608 |
+
},
|
| 9609 |
+
{
|
| 9610 |
+
"epoch": 0.9568143382673431,
|
| 9611 |
+
"grad_norm": 0.15794895589351654,
|
| 9612 |
+
"learning_rate": 5e-05,
|
| 9613 |
+
"loss": 2.0087013244628906,
|
| 9614 |
+
"step": 2744
|
| 9615 |
+
},
|
| 9616 |
+
{
|
| 9617 |
+
"epoch": 0.9575117248112698,
|
| 9618 |
+
"grad_norm": 0.2202284038066864,
|
| 9619 |
+
"learning_rate": 5e-05,
|
| 9620 |
+
"loss": 1.9209932088851929,
|
| 9621 |
+
"step": 2746
|
| 9622 |
+
},
|
| 9623 |
+
{
|
| 9624 |
+
"epoch": 0.9582091113551964,
|
| 9625 |
+
"grad_norm": 0.22955642640590668,
|
| 9626 |
+
"learning_rate": 5e-05,
|
| 9627 |
+
"loss": 2.088130474090576,
|
| 9628 |
+
"step": 2748
|
| 9629 |
+
},
|
| 9630 |
+
{
|
| 9631 |
+
"epoch": 0.9589064978991231,
|
| 9632 |
+
"grad_norm": 0.2963087558746338,
|
| 9633 |
+
"learning_rate": 5e-05,
|
| 9634 |
+
"loss": 1.8239340782165527,
|
| 9635 |
+
"step": 2750
|
| 9636 |
+
},
|
| 9637 |
+
{
|
| 9638 |
+
"epoch": 0.9596038844430497,
|
| 9639 |
+
"grad_norm": 0.20487681031227112,
|
| 9640 |
+
"learning_rate": 5e-05,
|
| 9641 |
+
"loss": 2.0583481788635254,
|
| 9642 |
+
"step": 2752
|
| 9643 |
+
},
|
| 9644 |
+
{
|
| 9645 |
+
"epoch": 0.9603012709869763,
|
| 9646 |
+
"grad_norm": 0.20250464975833893,
|
| 9647 |
+
"learning_rate": 5e-05,
|
| 9648 |
+
"loss": 1.787645936012268,
|
| 9649 |
+
"step": 2754
|
| 9650 |
+
},
|
| 9651 |
+
{
|
| 9652 |
+
"epoch": 0.960998657530903,
|
| 9653 |
+
"grad_norm": 0.27794164419174194,
|
| 9654 |
+
"learning_rate": 5e-05,
|
| 9655 |
+
"loss": 1.8390411138534546,
|
| 9656 |
+
"step": 2756
|
| 9657 |
+
},
|
| 9658 |
+
{
|
| 9659 |
+
"epoch": 0.9616960440748296,
|
| 9660 |
+
"grad_norm": 0.2529752254486084,
|
| 9661 |
+
"learning_rate": 5e-05,
|
| 9662 |
+
"loss": 2.0033533573150635,
|
| 9663 |
+
"step": 2758
|
| 9664 |
+
},
|
| 9665 |
+
{
|
| 9666 |
+
"epoch": 0.9623934306187563,
|
| 9667 |
+
"grad_norm": 0.28755611181259155,
|
| 9668 |
+
"learning_rate": 5e-05,
|
| 9669 |
+
"loss": 2.0316929817199707,
|
| 9670 |
+
"step": 2760
|
| 9671 |
+
},
|
| 9672 |
+
{
|
| 9673 |
+
"epoch": 0.9630908171626829,
|
| 9674 |
+
"grad_norm": 0.2371065616607666,
|
| 9675 |
+
"learning_rate": 5e-05,
|
| 9676 |
+
"loss": 1.9719016551971436,
|
| 9677 |
+
"step": 2762
|
| 9678 |
+
},
|
| 9679 |
+
{
|
| 9680 |
+
"epoch": 0.9637882037066094,
|
| 9681 |
+
"grad_norm": 0.22012600302696228,
|
| 9682 |
+
"learning_rate": 5e-05,
|
| 9683 |
+
"loss": 2.0681281089782715,
|
| 9684 |
+
"step": 2764
|
| 9685 |
+
},
|
| 9686 |
+
{
|
| 9687 |
+
"epoch": 0.9644855902505362,
|
| 9688 |
+
"grad_norm": 0.2199879139661789,
|
| 9689 |
+
"learning_rate": 5e-05,
|
| 9690 |
+
"loss": 1.8493678569793701,
|
| 9691 |
+
"step": 2766
|
| 9692 |
+
},
|
| 9693 |
+
{
|
| 9694 |
+
"epoch": 0.9651829767944627,
|
| 9695 |
+
"grad_norm": 0.24364908039569855,
|
| 9696 |
+
"learning_rate": 5e-05,
|
| 9697 |
+
"loss": 1.8051460981369019,
|
| 9698 |
+
"step": 2768
|
| 9699 |
+
},
|
| 9700 |
+
{
|
| 9701 |
+
"epoch": 0.9658803633383893,
|
| 9702 |
+
"grad_norm": 0.24932783842086792,
|
| 9703 |
+
"learning_rate": 5e-05,
|
| 9704 |
+
"loss": 1.8866969347000122,
|
| 9705 |
+
"step": 2770
|
| 9706 |
+
},
|
| 9707 |
+
{
|
| 9708 |
+
"epoch": 0.966577749882316,
|
| 9709 |
+
"grad_norm": 0.2716982066631317,
|
| 9710 |
+
"learning_rate": 5e-05,
|
| 9711 |
+
"loss": 1.857971429824829,
|
| 9712 |
+
"step": 2772
|
| 9713 |
+
},
|
| 9714 |
+
{
|
| 9715 |
+
"epoch": 0.9672751364262426,
|
| 9716 |
+
"grad_norm": 0.2361876666545868,
|
| 9717 |
+
"learning_rate": 5e-05,
|
| 9718 |
+
"loss": 1.664730429649353,
|
| 9719 |
+
"step": 2774
|
| 9720 |
+
},
|
| 9721 |
+
{
|
| 9722 |
+
"epoch": 0.9679725229701693,
|
| 9723 |
+
"grad_norm": 0.17890170216560364,
|
| 9724 |
+
"learning_rate": 5e-05,
|
| 9725 |
+
"loss": 2.040210723876953,
|
| 9726 |
+
"step": 2776
|
| 9727 |
+
},
|
| 9728 |
+
{
|
| 9729 |
+
"epoch": 0.9686699095140959,
|
| 9730 |
+
"grad_norm": 0.3918740451335907,
|
| 9731 |
+
"learning_rate": 5e-05,
|
| 9732 |
+
"loss": 1.542923927307129,
|
| 9733 |
+
"step": 2778
|
| 9734 |
+
},
|
| 9735 |
+
{
|
| 9736 |
+
"epoch": 0.9693672960580225,
|
| 9737 |
+
"grad_norm": 0.2373792678117752,
|
| 9738 |
+
"learning_rate": 5e-05,
|
| 9739 |
+
"loss": 1.9707016944885254,
|
| 9740 |
+
"step": 2780
|
| 9741 |
+
},
|
| 9742 |
+
{
|
| 9743 |
+
"epoch": 0.9700646826019492,
|
| 9744 |
+
"grad_norm": 0.18587234616279602,
|
| 9745 |
+
"learning_rate": 5e-05,
|
| 9746 |
+
"loss": 2.102854013442993,
|
| 9747 |
+
"step": 2782
|
| 9748 |
+
},
|
| 9749 |
+
{
|
| 9750 |
+
"epoch": 0.9707620691458758,
|
| 9751 |
+
"grad_norm": 0.18375499546527863,
|
| 9752 |
+
"learning_rate": 5e-05,
|
| 9753 |
+
"loss": 2.152763843536377,
|
| 9754 |
+
"step": 2784
|
| 9755 |
+
},
|
| 9756 |
+
{
|
| 9757 |
+
"epoch": 0.9714594556898025,
|
| 9758 |
+
"grad_norm": 0.17143887281417847,
|
| 9759 |
+
"learning_rate": 5e-05,
|
| 9760 |
+
"loss": 2.0487704277038574,
|
| 9761 |
+
"step": 2786
|
| 9762 |
+
},
|
| 9763 |
+
{
|
| 9764 |
+
"epoch": 0.9721568422337291,
|
| 9765 |
+
"grad_norm": 0.2904473841190338,
|
| 9766 |
+
"learning_rate": 5e-05,
|
| 9767 |
+
"loss": 1.7972146272659302,
|
| 9768 |
+
"step": 2788
|
| 9769 |
+
},
|
| 9770 |
+
{
|
| 9771 |
+
"epoch": 0.9728542287776557,
|
| 9772 |
+
"grad_norm": 0.20143947005271912,
|
| 9773 |
+
"learning_rate": 5e-05,
|
| 9774 |
+
"loss": 1.8335665464401245,
|
| 9775 |
+
"step": 2790
|
| 9776 |
+
},
|
| 9777 |
+
{
|
| 9778 |
+
"epoch": 0.9735516153215824,
|
| 9779 |
+
"grad_norm": 0.2243218719959259,
|
| 9780 |
+
"learning_rate": 5e-05,
|
| 9781 |
+
"loss": 1.8498470783233643,
|
| 9782 |
+
"step": 2792
|
| 9783 |
+
},
|
| 9784 |
+
{
|
| 9785 |
+
"epoch": 0.974249001865509,
|
| 9786 |
+
"grad_norm": 0.24106721580028534,
|
| 9787 |
+
"learning_rate": 5e-05,
|
| 9788 |
+
"loss": 1.962310552597046,
|
| 9789 |
+
"step": 2794
|
| 9790 |
+
},
|
| 9791 |
+
{
|
| 9792 |
+
"epoch": 0.9749463884094356,
|
| 9793 |
+
"grad_norm": 0.19191642105579376,
|
| 9794 |
+
"learning_rate": 5e-05,
|
| 9795 |
+
"loss": 2.0525314807891846,
|
| 9796 |
+
"step": 2796
|
| 9797 |
+
},
|
| 9798 |
+
{
|
| 9799 |
+
"epoch": 0.9756437749533623,
|
| 9800 |
+
"grad_norm": 0.25365757942199707,
|
| 9801 |
+
"learning_rate": 5e-05,
|
| 9802 |
+
"loss": 1.6377971172332764,
|
| 9803 |
+
"step": 2798
|
| 9804 |
+
},
|
| 9805 |
+
{
|
| 9806 |
+
"epoch": 0.9763411614972889,
|
| 9807 |
+
"grad_norm": 0.30278539657592773,
|
| 9808 |
+
"learning_rate": 5e-05,
|
| 9809 |
+
"loss": 1.7661526203155518,
|
| 9810 |
+
"step": 2800
|
| 9811 |
+
},
|
| 9812 |
+
{
|
| 9813 |
+
"epoch": 0.9770385480412156,
|
| 9814 |
+
"grad_norm": 0.19323121011257172,
|
| 9815 |
+
"learning_rate": 5e-05,
|
| 9816 |
+
"loss": 1.998081922531128,
|
| 9817 |
+
"step": 2802
|
| 9818 |
+
},
|
| 9819 |
+
{
|
| 9820 |
+
"epoch": 0.9777359345851422,
|
| 9821 |
+
"grad_norm": 0.29371944069862366,
|
| 9822 |
+
"learning_rate": 5e-05,
|
| 9823 |
+
"loss": 2.128218412399292,
|
| 9824 |
+
"step": 2804
|
| 9825 |
+
},
|
| 9826 |
+
{
|
| 9827 |
+
"epoch": 0.9784333211290688,
|
| 9828 |
+
"grad_norm": 0.2559215724468231,
|
| 9829 |
+
"learning_rate": 5e-05,
|
| 9830 |
+
"loss": 1.8026628494262695,
|
| 9831 |
+
"step": 2806
|
| 9832 |
+
},
|
| 9833 |
+
{
|
| 9834 |
+
"epoch": 0.9791307076729955,
|
| 9835 |
+
"grad_norm": 0.2080441266298294,
|
| 9836 |
+
"learning_rate": 5e-05,
|
| 9837 |
+
"loss": 1.6901484727859497,
|
| 9838 |
+
"step": 2808
|
| 9839 |
+
},
|
| 9840 |
+
{
|
| 9841 |
+
"epoch": 0.9798280942169221,
|
| 9842 |
+
"grad_norm": 0.24571523070335388,
|
| 9843 |
+
"learning_rate": 5e-05,
|
| 9844 |
+
"loss": 1.9744998216629028,
|
| 9845 |
+
"step": 2810
|
| 9846 |
+
},
|
| 9847 |
+
{
|
| 9848 |
+
"epoch": 0.9805254807608487,
|
| 9849 |
+
"grad_norm": 0.17511089146137238,
|
| 9850 |
+
"learning_rate": 5e-05,
|
| 9851 |
+
"loss": 1.9440521001815796,
|
| 9852 |
+
"step": 2812
|
| 9853 |
+
},
|
| 9854 |
+
{
|
| 9855 |
+
"epoch": 0.9812228673047754,
|
| 9856 |
+
"grad_norm": 0.1670263260602951,
|
| 9857 |
+
"learning_rate": 5e-05,
|
| 9858 |
+
"loss": 1.9503123760223389,
|
| 9859 |
+
"step": 2814
|
| 9860 |
+
},
|
| 9861 |
+
{
|
| 9862 |
+
"epoch": 0.981920253848702,
|
| 9863 |
+
"grad_norm": 0.2044575959444046,
|
| 9864 |
+
"learning_rate": 5e-05,
|
| 9865 |
+
"loss": 1.8517839908599854,
|
| 9866 |
+
"step": 2816
|
| 9867 |
+
},
|
| 9868 |
+
{
|
| 9869 |
+
"epoch": 0.9826176403926287,
|
| 9870 |
+
"grad_norm": 0.23012447357177734,
|
| 9871 |
+
"learning_rate": 5e-05,
|
| 9872 |
+
"loss": 1.9848601818084717,
|
| 9873 |
+
"step": 2818
|
| 9874 |
+
},
|
| 9875 |
+
{
|
| 9876 |
+
"epoch": 0.9833150269365553,
|
| 9877 |
+
"grad_norm": 0.2421187460422516,
|
| 9878 |
+
"learning_rate": 5e-05,
|
| 9879 |
+
"loss": 1.8418478965759277,
|
| 9880 |
+
"step": 2820
|
| 9881 |
+
},
|
| 9882 |
+
{
|
| 9883 |
+
"epoch": 0.9840124134804819,
|
| 9884 |
+
"grad_norm": 0.23758035898208618,
|
| 9885 |
+
"learning_rate": 5e-05,
|
| 9886 |
+
"loss": 1.9044866561889648,
|
| 9887 |
+
"step": 2822
|
| 9888 |
+
},
|
| 9889 |
+
{
|
| 9890 |
+
"epoch": 0.9847098000244086,
|
| 9891 |
+
"grad_norm": 0.2850770056247711,
|
| 9892 |
+
"learning_rate": 5e-05,
|
| 9893 |
+
"loss": 1.841456413269043,
|
| 9894 |
+
"step": 2824
|
| 9895 |
+
},
|
| 9896 |
+
{
|
| 9897 |
+
"epoch": 0.9854071865683351,
|
| 9898 |
+
"grad_norm": 0.15733706951141357,
|
| 9899 |
+
"learning_rate": 5e-05,
|
| 9900 |
+
"loss": 2.027836322784424,
|
| 9901 |
+
"step": 2826
|
| 9902 |
+
},
|
| 9903 |
+
{
|
| 9904 |
+
"epoch": 0.9861045731122619,
|
| 9905 |
+
"grad_norm": 0.1889045536518097,
|
| 9906 |
+
"learning_rate": 5e-05,
|
| 9907 |
+
"loss": 1.814117193222046,
|
| 9908 |
+
"step": 2828
|
| 9909 |
+
},
|
| 9910 |
+
{
|
| 9911 |
+
"epoch": 0.9868019596561884,
|
| 9912 |
+
"grad_norm": 0.19978995621204376,
|
| 9913 |
+
"learning_rate": 5e-05,
|
| 9914 |
+
"loss": 1.9840281009674072,
|
| 9915 |
+
"step": 2830
|
| 9916 |
+
},
|
| 9917 |
+
{
|
| 9918 |
+
"epoch": 0.987499346200115,
|
| 9919 |
+
"grad_norm": 0.2702449858188629,
|
| 9920 |
+
"learning_rate": 5e-05,
|
| 9921 |
+
"loss": 1.6669400930404663,
|
| 9922 |
+
"step": 2832
|
| 9923 |
+
},
|
| 9924 |
+
{
|
| 9925 |
+
"epoch": 0.9881967327440417,
|
| 9926 |
+
"grad_norm": 0.2253396213054657,
|
| 9927 |
+
"learning_rate": 5e-05,
|
| 9928 |
+
"loss": 1.9446139335632324,
|
| 9929 |
+
"step": 2834
|
| 9930 |
+
},
|
| 9931 |
+
{
|
| 9932 |
+
"epoch": 0.9888941192879683,
|
| 9933 |
+
"grad_norm": 0.224853053689003,
|
| 9934 |
+
"learning_rate": 5e-05,
|
| 9935 |
+
"loss": 1.905352234840393,
|
| 9936 |
+
"step": 2836
|
| 9937 |
+
},
|
| 9938 |
+
{
|
| 9939 |
+
"epoch": 0.9895915058318949,
|
| 9940 |
+
"grad_norm": 0.19716063141822815,
|
| 9941 |
+
"learning_rate": 5e-05,
|
| 9942 |
+
"loss": 1.749011516571045,
|
| 9943 |
+
"step": 2838
|
| 9944 |
+
},
|
| 9945 |
+
{
|
| 9946 |
+
"epoch": 0.9902888923758216,
|
| 9947 |
+
"grad_norm": 0.21353597939014435,
|
| 9948 |
+
"learning_rate": 5e-05,
|
| 9949 |
+
"loss": 1.9643821716308594,
|
| 9950 |
+
"step": 2840
|
| 9951 |
+
},
|
| 9952 |
+
{
|
| 9953 |
+
"epoch": 0.9909862789197482,
|
| 9954 |
+
"grad_norm": 0.2148216813802719,
|
| 9955 |
+
"learning_rate": 5e-05,
|
| 9956 |
+
"loss": 1.7480381727218628,
|
| 9957 |
+
"step": 2842
|
| 9958 |
+
},
|
| 9959 |
+
{
|
| 9960 |
+
"epoch": 0.9916836654636749,
|
| 9961 |
+
"grad_norm": 0.23505060374736786,
|
| 9962 |
+
"learning_rate": 5e-05,
|
| 9963 |
+
"loss": 1.9068567752838135,
|
| 9964 |
+
"step": 2844
|
| 9965 |
+
},
|
| 9966 |
+
{
|
| 9967 |
+
"epoch": 0.9923810520076015,
|
| 9968 |
+
"grad_norm": 0.16866576671600342,
|
| 9969 |
+
"learning_rate": 5e-05,
|
| 9970 |
+
"loss": 2.2292630672454834,
|
| 9971 |
+
"step": 2846
|
| 9972 |
+
},
|
| 9973 |
+
{
|
| 9974 |
+
"epoch": 0.9930784385515281,
|
| 9975 |
+
"grad_norm": 0.3207954168319702,
|
| 9976 |
+
"learning_rate": 5e-05,
|
| 9977 |
+
"loss": 1.7519619464874268,
|
| 9978 |
+
"step": 2848
|
| 9979 |
+
},
|
| 9980 |
+
{
|
| 9981 |
+
"epoch": 0.9937758250954548,
|
| 9982 |
+
"grad_norm": 0.21400299668312073,
|
| 9983 |
+
"learning_rate": 5e-05,
|
| 9984 |
+
"loss": 1.864077091217041,
|
| 9985 |
+
"step": 2850
|
| 9986 |
+
},
|
| 9987 |
+
{
|
| 9988 |
+
"epoch": 0.9944732116393814,
|
| 9989 |
+
"grad_norm": 0.1865902990102768,
|
| 9990 |
+
"learning_rate": 5e-05,
|
| 9991 |
+
"loss": 2.105564832687378,
|
| 9992 |
+
"step": 2852
|
| 9993 |
+
},
|
| 9994 |
+
{
|
| 9995 |
+
"epoch": 0.9951705981833081,
|
| 9996 |
+
"grad_norm": 0.18777675926685333,
|
| 9997 |
+
"learning_rate": 5e-05,
|
| 9998 |
+
"loss": 1.8181391954421997,
|
| 9999 |
+
"step": 2854
|
| 10000 |
+
},
|
| 10001 |
+
{
|
| 10002 |
+
"epoch": 0.9958679847272347,
|
| 10003 |
+
"grad_norm": 0.22146295011043549,
|
| 10004 |
+
"learning_rate": 5e-05,
|
| 10005 |
+
"loss": 1.728520393371582,
|
| 10006 |
+
"step": 2856
|
| 10007 |
+
},
|
| 10008 |
+
{
|
| 10009 |
+
"epoch": 0.9965653712711613,
|
| 10010 |
+
"grad_norm": 0.2045009434223175,
|
| 10011 |
+
"learning_rate": 5e-05,
|
| 10012 |
+
"loss": 2.065898895263672,
|
| 10013 |
+
"step": 2858
|
| 10014 |
+
},
|
| 10015 |
+
{
|
| 10016 |
+
"epoch": 0.997262757815088,
|
| 10017 |
+
"grad_norm": 0.32111960649490356,
|
| 10018 |
+
"learning_rate": 5e-05,
|
| 10019 |
+
"loss": 1.8026396036148071,
|
| 10020 |
+
"step": 2860
|
| 10021 |
+
},
|
| 10022 |
+
{
|
| 10023 |
+
"epoch": 0.9979601443590146,
|
| 10024 |
+
"grad_norm": 0.20345966517925262,
|
| 10025 |
+
"learning_rate": 5e-05,
|
| 10026 |
+
"loss": 2.041215419769287,
|
| 10027 |
+
"step": 2862
|
| 10028 |
+
},
|
| 10029 |
+
{
|
| 10030 |
+
"epoch": 0.9986575309029412,
|
| 10031 |
+
"grad_norm": 0.22954697906970978,
|
| 10032 |
+
"learning_rate": 5e-05,
|
| 10033 |
+
"loss": 1.9399595260620117,
|
| 10034 |
+
"step": 2864
|
| 10035 |
+
},
|
| 10036 |
+
{
|
| 10037 |
+
"epoch": 0.9993549174468679,
|
| 10038 |
+
"grad_norm": 0.2561749815940857,
|
| 10039 |
+
"learning_rate": 5e-05,
|
| 10040 |
+
"loss": 1.9872870445251465,
|
| 10041 |
+
"step": 2866
|
| 10042 |
+
},
|
| 10043 |
+
{
|
| 10044 |
+
"epoch": 1.0,
|
| 10045 |
+
"grad_norm": 0.2276153415441513,
|
| 10046 |
+
"learning_rate": 5e-05,
|
| 10047 |
+
"loss": 1.9508090019226074,
|
| 10048 |
+
"step": 2868
|
| 10049 |
+
},
|
| 10050 |
+
{
|
| 10051 |
+
"epoch": 1.0006973865439266,
|
| 10052 |
+
"grad_norm": 0.17299285531044006,
|
| 10053 |
+
"learning_rate": 5e-05,
|
| 10054 |
+
"loss": 1.8651812076568604,
|
| 10055 |
+
"step": 2870
|
| 10056 |
}
|
| 10057 |
],
|
| 10058 |
"logging_steps": 2,
|
|
|
|
| 10072 |
"attributes": {}
|
| 10073 |
}
|
| 10074 |
},
|
| 10075 |
+
"total_flos": 5.13519579176108e+17,
|
| 10076 |
"train_batch_size": 1,
|
| 10077 |
"trial_name": null,
|
| 10078 |
"trial_params": null
|