Text Generation
PEFT
Safetensors
Transformers
English
tool-use
function-calling
lora
minicpm
bfcl
python
sft
trl
unsloth
conversational
Instructions to use pmrccs/minicpm5-2b-python-tool-calling-v3-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use pmrccs/minicpm5-2b-python-tool-calling-v3-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM5-2B") model = PeftModel.from_pretrained(base_model, "pmrccs/minicpm5-2b-python-tool-calling-v3-lora") - Transformers
How to use pmrccs/minicpm5-2b-python-tool-calling-v3-lora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="pmrccs/minicpm5-2b-python-tool-calling-v3-lora") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("pmrccs/minicpm5-2b-python-tool-calling-v3-lora", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use pmrccs/minicpm5-2b-python-tool-calling-v3-lora with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "pmrccs/minicpm5-2b-python-tool-calling-v3-lora" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pmrccs/minicpm5-2b-python-tool-calling-v3-lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/pmrccs/minicpm5-2b-python-tool-calling-v3-lora
- SGLang
How to use pmrccs/minicpm5-2b-python-tool-calling-v3-lora 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 "pmrccs/minicpm5-2b-python-tool-calling-v3-lora" \ --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": "pmrccs/minicpm5-2b-python-tool-calling-v3-lora", "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 "pmrccs/minicpm5-2b-python-tool-calling-v3-lora" \ --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": "pmrccs/minicpm5-2b-python-tool-calling-v3-lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use pmrccs/minicpm5-2b-python-tool-calling-v3-lora with Docker Model Runner:
docker model run hf.co/pmrccs/minicpm5-2b-python-tool-calling-v3-lora
checkpoint step 1400
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100544848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a5c835c1b8f2ec49af3c14752f131b66f2d8acc57ed4ca749e45b8d45136f51
|
| 3 |
size 100544848
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 51712981
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c09d483b3d52f9067c580ee1c831a818e44c9c11544ff3feee5a49df02d0447
|
| 3 |
size 51712981
|
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 sha256:9a66f0d207817cfb84e20db5c7b87b23ee5772c14b45064ca40ee073dcc8bcf3
|
| 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:bb82852eca565a1fa31f9fa4a6c113459478874e80d6ec0728d8327586c1996c
|
| 3 |
size 14917
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3b03c8c40e45be48b5956b82e1abb2c1ec5641f4fc77e6fdec0942a77964500
|
| 3 |
size 1383
|
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 sha256:482cbe2efa5c989e1c15f9f83686e2901ef965a2c3488fed18ee0061c81ea4a9
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "/kaggle/working/run/checkpoint-
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 200,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -8456,6 +8456,1414 @@
|
|
| 8456 |
"eval_samples_per_second": 6.14,
|
| 8457 |
"eval_steps_per_second": 0.768,
|
| 8458 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8459 |
}
|
| 8460 |
],
|
| 8461 |
"logging_steps": 1,
|
|
@@ -8484,7 +9892,7 @@
|
|
| 8484 |
"attributes": {}
|
| 8485 |
}
|
| 8486 |
},
|
| 8487 |
-
"total_flos": 1.
|
| 8488 |
"train_batch_size": 1,
|
| 8489 |
"trial_name": null,
|
| 8490 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 1400,
|
| 3 |
+
"best_metric": 0.44383540749549866,
|
| 4 |
+
"best_model_checkpoint": "/kaggle/working/run/checkpoint-1400",
|
| 5 |
+
"epoch": 0.3834040805148569,
|
| 6 |
"eval_steps": 200,
|
| 7 |
+
"global_step": 1400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8456 |
"eval_samples_per_second": 6.14,
|
| 8457 |
"eval_steps_per_second": 0.768,
|
| 8458 |
"step": 1200
|
| 8459 |
+
},
|
| 8460 |
+
{
|
| 8461 |
+
"epoch": 0.32890592907024513,
|
| 8462 |
+
"grad_norm": 0.5093029737472534,
|
| 8463 |
+
"learning_rate": 3.919881103914783e-05,
|
| 8464 |
+
"loss": 0.45603060722351074,
|
| 8465 |
+
"step": 1201
|
| 8466 |
+
},
|
| 8467 |
+
{
|
| 8468 |
+
"epoch": 0.3291797891277557,
|
| 8469 |
+
"grad_norm": 0.5276803970336914,
|
| 8470 |
+
"learning_rate": 3.918055500788043e-05,
|
| 8471 |
+
"loss": 0.5014870762825012,
|
| 8472 |
+
"step": 1202
|
| 8473 |
+
},
|
| 8474 |
+
{
|
| 8475 |
+
"epoch": 0.3294536491852663,
|
| 8476 |
+
"grad_norm": 0.41087207198143005,
|
| 8477 |
+
"learning_rate": 3.916228782093857e-05,
|
| 8478 |
+
"loss": 0.4334317147731781,
|
| 8479 |
+
"step": 1203
|
| 8480 |
+
},
|
| 8481 |
+
{
|
| 8482 |
+
"epoch": 0.32972750924277694,
|
| 8483 |
+
"grad_norm": 0.5073480010032654,
|
| 8484 |
+
"learning_rate": 3.914400949269284e-05,
|
| 8485 |
+
"loss": 0.6235437393188477,
|
| 8486 |
+
"step": 1204
|
| 8487 |
+
},
|
| 8488 |
+
{
|
| 8489 |
+
"epoch": 0.33000136930028756,
|
| 8490 |
+
"grad_norm": 0.5188661217689514,
|
| 8491 |
+
"learning_rate": 3.9125720037522596e-05,
|
| 8492 |
+
"loss": 0.4570923447608948,
|
| 8493 |
+
"step": 1205
|
| 8494 |
+
},
|
| 8495 |
+
{
|
| 8496 |
+
"epoch": 0.3302752293577982,
|
| 8497 |
+
"grad_norm": 0.5492871403694153,
|
| 8498 |
+
"learning_rate": 3.91074194698159e-05,
|
| 8499 |
+
"loss": 0.5060250759124756,
|
| 8500 |
+
"step": 1206
|
| 8501 |
+
},
|
| 8502 |
+
{
|
| 8503 |
+
"epoch": 0.33054908941530875,
|
| 8504 |
+
"grad_norm": 0.4366123080253601,
|
| 8505 |
+
"learning_rate": 3.908910780396962e-05,
|
| 8506 |
+
"loss": 0.4165114462375641,
|
| 8507 |
+
"step": 1207
|
| 8508 |
+
},
|
| 8509 |
+
{
|
| 8510 |
+
"epoch": 0.33082294947281937,
|
| 8511 |
+
"grad_norm": 0.46078726649284363,
|
| 8512 |
+
"learning_rate": 3.907078505438932e-05,
|
| 8513 |
+
"loss": 0.42916232347488403,
|
| 8514 |
+
"step": 1208
|
| 8515 |
+
},
|
| 8516 |
+
{
|
| 8517 |
+
"epoch": 0.33109680953033,
|
| 8518 |
+
"grad_norm": 0.5281908512115479,
|
| 8519 |
+
"learning_rate": 3.9052451235489286e-05,
|
| 8520 |
+
"loss": 0.4631369113922119,
|
| 8521 |
+
"step": 1209
|
| 8522 |
+
},
|
| 8523 |
+
{
|
| 8524 |
+
"epoch": 0.3313706695878406,
|
| 8525 |
+
"grad_norm": 0.49541038274765015,
|
| 8526 |
+
"learning_rate": 3.9034106361692524e-05,
|
| 8527 |
+
"loss": 0.4823800325393677,
|
| 8528 |
+
"step": 1210
|
| 8529 |
+
},
|
| 8530 |
+
{
|
| 8531 |
+
"epoch": 0.33164452964535124,
|
| 8532 |
+
"grad_norm": 0.49072080850601196,
|
| 8533 |
+
"learning_rate": 3.901575044743072e-05,
|
| 8534 |
+
"loss": 0.43409809470176697,
|
| 8535 |
+
"step": 1211
|
| 8536 |
+
},
|
| 8537 |
+
{
|
| 8538 |
+
"epoch": 0.33191838970286186,
|
| 8539 |
+
"grad_norm": 0.5157279372215271,
|
| 8540 |
+
"learning_rate": 3.899738350714425e-05,
|
| 8541 |
+
"loss": 0.4249608814716339,
|
| 8542 |
+
"step": 1212
|
| 8543 |
+
},
|
| 8544 |
+
{
|
| 8545 |
+
"epoch": 0.3321922497603724,
|
| 8546 |
+
"grad_norm": 0.5081192255020142,
|
| 8547 |
+
"learning_rate": 3.897900555528218e-05,
|
| 8548 |
+
"loss": 0.4689486026763916,
|
| 8549 |
+
"step": 1213
|
| 8550 |
+
},
|
| 8551 |
+
{
|
| 8552 |
+
"epoch": 0.33246610981788305,
|
| 8553 |
+
"grad_norm": 0.5101996064186096,
|
| 8554 |
+
"learning_rate": 3.896061660630221e-05,
|
| 8555 |
+
"loss": 0.42869192361831665,
|
| 8556 |
+
"step": 1214
|
| 8557 |
+
},
|
| 8558 |
+
{
|
| 8559 |
+
"epoch": 0.33273996987539367,
|
| 8560 |
+
"grad_norm": 0.5858718156814575,
|
| 8561 |
+
"learning_rate": 3.894221667467074e-05,
|
| 8562 |
+
"loss": 0.5466811060905457,
|
| 8563 |
+
"step": 1215
|
| 8564 |
+
},
|
| 8565 |
+
{
|
| 8566 |
+
"epoch": 0.3330138299329043,
|
| 8567 |
+
"grad_norm": 0.5372413396835327,
|
| 8568 |
+
"learning_rate": 3.892380577486275e-05,
|
| 8569 |
+
"loss": 0.4799969494342804,
|
| 8570 |
+
"step": 1216
|
| 8571 |
+
},
|
| 8572 |
+
{
|
| 8573 |
+
"epoch": 0.3332876899904149,
|
| 8574 |
+
"grad_norm": 0.44514933228492737,
|
| 8575 |
+
"learning_rate": 3.890538392136188e-05,
|
| 8576 |
+
"loss": 0.3876304626464844,
|
| 8577 |
+
"step": 1217
|
| 8578 |
+
},
|
| 8579 |
+
{
|
| 8580 |
+
"epoch": 0.33356155004792554,
|
| 8581 |
+
"grad_norm": 0.4863232970237732,
|
| 8582 |
+
"learning_rate": 3.888695112866039e-05,
|
| 8583 |
+
"loss": 0.4315215051174164,
|
| 8584 |
+
"step": 1218
|
| 8585 |
+
},
|
| 8586 |
+
{
|
| 8587 |
+
"epoch": 0.3338354101054361,
|
| 8588 |
+
"grad_norm": 0.4929295778274536,
|
| 8589 |
+
"learning_rate": 3.8868507411259136e-05,
|
| 8590 |
+
"loss": 0.48230862617492676,
|
| 8591 |
+
"step": 1219
|
| 8592 |
+
},
|
| 8593 |
+
{
|
| 8594 |
+
"epoch": 0.3341092701629467,
|
| 8595 |
+
"grad_norm": 0.4523279070854187,
|
| 8596 |
+
"learning_rate": 3.8850052783667576e-05,
|
| 8597 |
+
"loss": 0.3909027576446533,
|
| 8598 |
+
"step": 1220
|
| 8599 |
+
},
|
| 8600 |
+
{
|
| 8601 |
+
"epoch": 0.33438313022045735,
|
| 8602 |
+
"grad_norm": 0.47148841619491577,
|
| 8603 |
+
"learning_rate": 3.8831587260403746e-05,
|
| 8604 |
+
"loss": 0.365531325340271,
|
| 8605 |
+
"step": 1221
|
| 8606 |
+
},
|
| 8607 |
+
{
|
| 8608 |
+
"epoch": 0.33465699027796797,
|
| 8609 |
+
"grad_norm": 0.5444722175598145,
|
| 8610 |
+
"learning_rate": 3.881311085599425e-05,
|
| 8611 |
+
"loss": 0.5459700226783752,
|
| 8612 |
+
"step": 1222
|
| 8613 |
+
},
|
| 8614 |
+
{
|
| 8615 |
+
"epoch": 0.3349308503354786,
|
| 8616 |
+
"grad_norm": 0.5176328420639038,
|
| 8617 |
+
"learning_rate": 3.8794623584974254e-05,
|
| 8618 |
+
"loss": 0.547359049320221,
|
| 8619 |
+
"step": 1223
|
| 8620 |
+
},
|
| 8621 |
+
{
|
| 8622 |
+
"epoch": 0.33520471039298916,
|
| 8623 |
+
"grad_norm": 0.4887847304344177,
|
| 8624 |
+
"learning_rate": 3.8776125461887484e-05,
|
| 8625 |
+
"loss": 0.46751677989959717,
|
| 8626 |
+
"step": 1224
|
| 8627 |
+
},
|
| 8628 |
+
{
|
| 8629 |
+
"epoch": 0.3354785704504998,
|
| 8630 |
+
"grad_norm": 0.4953182339668274,
|
| 8631 |
+
"learning_rate": 3.875761650128619e-05,
|
| 8632 |
+
"loss": 0.48857349157333374,
|
| 8633 |
+
"step": 1225
|
| 8634 |
+
},
|
| 8635 |
+
{
|
| 8636 |
+
"epoch": 0.3357524305080104,
|
| 8637 |
+
"grad_norm": 0.4538589417934418,
|
| 8638 |
+
"learning_rate": 3.873909671773115e-05,
|
| 8639 |
+
"loss": 0.4708706736564636,
|
| 8640 |
+
"step": 1226
|
| 8641 |
+
},
|
| 8642 |
+
{
|
| 8643 |
+
"epoch": 0.336026290565521,
|
| 8644 |
+
"grad_norm": 0.5201008915901184,
|
| 8645 |
+
"learning_rate": 3.872056612579166e-05,
|
| 8646 |
+
"loss": 0.46376532316207886,
|
| 8647 |
+
"step": 1227
|
| 8648 |
+
},
|
| 8649 |
+
{
|
| 8650 |
+
"epoch": 0.33630015062303165,
|
| 8651 |
+
"grad_norm": 0.44777992367744446,
|
| 8652 |
+
"learning_rate": 3.8702024740045505e-05,
|
| 8653 |
+
"loss": 0.46707645058631897,
|
| 8654 |
+
"step": 1228
|
| 8655 |
+
},
|
| 8656 |
+
{
|
| 8657 |
+
"epoch": 0.33657401068054227,
|
| 8658 |
+
"grad_norm": 0.48003560304641724,
|
| 8659 |
+
"learning_rate": 3.868347257507899e-05,
|
| 8660 |
+
"loss": 0.5051887035369873,
|
| 8661 |
+
"step": 1229
|
| 8662 |
+
},
|
| 8663 |
+
{
|
| 8664 |
+
"epoch": 0.33684787073805283,
|
| 8665 |
+
"grad_norm": 0.4703141450881958,
|
| 8666 |
+
"learning_rate": 3.866490964548689e-05,
|
| 8667 |
+
"loss": 0.4232620596885681,
|
| 8668 |
+
"step": 1230
|
| 8669 |
+
},
|
| 8670 |
+
{
|
| 8671 |
+
"epoch": 0.33712173079556346,
|
| 8672 |
+
"grad_norm": 0.4349907636642456,
|
| 8673 |
+
"learning_rate": 3.8646335965872414e-05,
|
| 8674 |
+
"loss": 0.46825966238975525,
|
| 8675 |
+
"step": 1231
|
| 8676 |
+
},
|
| 8677 |
+
{
|
| 8678 |
+
"epoch": 0.3373955908530741,
|
| 8679 |
+
"grad_norm": 0.5318922996520996,
|
| 8680 |
+
"learning_rate": 3.862775155084728e-05,
|
| 8681 |
+
"loss": 0.45038193464279175,
|
| 8682 |
+
"step": 1232
|
| 8683 |
+
},
|
| 8684 |
+
{
|
| 8685 |
+
"epoch": 0.3376694509105847,
|
| 8686 |
+
"grad_norm": 0.5079306960105896,
|
| 8687 |
+
"learning_rate": 3.860915641503161e-05,
|
| 8688 |
+
"loss": 0.5008682012557983,
|
| 8689 |
+
"step": 1233
|
| 8690 |
+
},
|
| 8691 |
+
{
|
| 8692 |
+
"epoch": 0.3379433109680953,
|
| 8693 |
+
"grad_norm": 0.5097274780273438,
|
| 8694 |
+
"learning_rate": 3.8590550573053994e-05,
|
| 8695 |
+
"loss": 0.42196357250213623,
|
| 8696 |
+
"step": 1234
|
| 8697 |
+
},
|
| 8698 |
+
{
|
| 8699 |
+
"epoch": 0.3382171710256059,
|
| 8700 |
+
"grad_norm": 0.4473101496696472,
|
| 8701 |
+
"learning_rate": 3.8571934039551406e-05,
|
| 8702 |
+
"loss": 0.3886878192424774,
|
| 8703 |
+
"step": 1235
|
| 8704 |
+
},
|
| 8705 |
+
{
|
| 8706 |
+
"epoch": 0.3384910310831165,
|
| 8707 |
+
"grad_norm": 0.4567628502845764,
|
| 8708 |
+
"learning_rate": 3.8553306829169265e-05,
|
| 8709 |
+
"loss": 0.4033932685852051,
|
| 8710 |
+
"step": 1236
|
| 8711 |
+
},
|
| 8712 |
+
{
|
| 8713 |
+
"epoch": 0.33876489114062713,
|
| 8714 |
+
"grad_norm": 0.5126984715461731,
|
| 8715 |
+
"learning_rate": 3.853466895656138e-05,
|
| 8716 |
+
"loss": 0.4274301528930664,
|
| 8717 |
+
"step": 1237
|
| 8718 |
+
},
|
| 8719 |
+
{
|
| 8720 |
+
"epoch": 0.33903875119813776,
|
| 8721 |
+
"grad_norm": 0.480965793132782,
|
| 8722 |
+
"learning_rate": 3.851602043638994e-05,
|
| 8723 |
+
"loss": 0.5206314325332642,
|
| 8724 |
+
"step": 1238
|
| 8725 |
+
},
|
| 8726 |
+
{
|
| 8727 |
+
"epoch": 0.3393126112556484,
|
| 8728 |
+
"grad_norm": 0.5022204518318176,
|
| 8729 |
+
"learning_rate": 3.8497361283325516e-05,
|
| 8730 |
+
"loss": 0.3856828808784485,
|
| 8731 |
+
"step": 1239
|
| 8732 |
+
},
|
| 8733 |
+
{
|
| 8734 |
+
"epoch": 0.339586471313159,
|
| 8735 |
+
"grad_norm": 0.48833727836608887,
|
| 8736 |
+
"learning_rate": 3.847869151204704e-05,
|
| 8737 |
+
"loss": 0.5218378305435181,
|
| 8738 |
+
"step": 1240
|
| 8739 |
+
},
|
| 8740 |
+
{
|
| 8741 |
+
"epoch": 0.33986033137066957,
|
| 8742 |
+
"grad_norm": 0.5617501139640808,
|
| 8743 |
+
"learning_rate": 3.846001113724179e-05,
|
| 8744 |
+
"loss": 0.5969647169113159,
|
| 8745 |
+
"step": 1241
|
| 8746 |
+
},
|
| 8747 |
+
{
|
| 8748 |
+
"epoch": 0.3401341914281802,
|
| 8749 |
+
"grad_norm": 0.44516050815582275,
|
| 8750 |
+
"learning_rate": 3.844132017360541e-05,
|
| 8751 |
+
"loss": 0.4793824851512909,
|
| 8752 |
+
"step": 1242
|
| 8753 |
+
},
|
| 8754 |
+
{
|
| 8755 |
+
"epoch": 0.3404080514856908,
|
| 8756 |
+
"grad_norm": 0.5032813549041748,
|
| 8757 |
+
"learning_rate": 3.842261863584186e-05,
|
| 8758 |
+
"loss": 0.4397889971733093,
|
| 8759 |
+
"step": 1243
|
| 8760 |
+
},
|
| 8761 |
+
{
|
| 8762 |
+
"epoch": 0.34068191154320143,
|
| 8763 |
+
"grad_norm": 0.49116599559783936,
|
| 8764 |
+
"learning_rate": 3.8403906538663416e-05,
|
| 8765 |
+
"loss": 0.43548423051834106,
|
| 8766 |
+
"step": 1244
|
| 8767 |
+
},
|
| 8768 |
+
{
|
| 8769 |
+
"epoch": 0.34095577160071205,
|
| 8770 |
+
"grad_norm": 0.5489189028739929,
|
| 8771 |
+
"learning_rate": 3.838518389679065e-05,
|
| 8772 |
+
"loss": 0.4820830225944519,
|
| 8773 |
+
"step": 1245
|
| 8774 |
+
},
|
| 8775 |
+
{
|
| 8776 |
+
"epoch": 0.3412296316582226,
|
| 8777 |
+
"grad_norm": 0.5229315757751465,
|
| 8778 |
+
"learning_rate": 3.836645072495245e-05,
|
| 8779 |
+
"loss": 0.4579339325428009,
|
| 8780 |
+
"step": 1246
|
| 8781 |
+
},
|
| 8782 |
+
{
|
| 8783 |
+
"epoch": 0.34150349171573324,
|
| 8784 |
+
"grad_norm": 0.5465797781944275,
|
| 8785 |
+
"learning_rate": 3.8347707037885986e-05,
|
| 8786 |
+
"loss": 0.587769091129303,
|
| 8787 |
+
"step": 1247
|
| 8788 |
+
},
|
| 8789 |
+
{
|
| 8790 |
+
"epoch": 0.34177735177324386,
|
| 8791 |
+
"grad_norm": 0.5069483518600464,
|
| 8792 |
+
"learning_rate": 3.8328952850336695e-05,
|
| 8793 |
+
"loss": 0.45743411779403687,
|
| 8794 |
+
"step": 1248
|
| 8795 |
+
},
|
| 8796 |
+
{
|
| 8797 |
+
"epoch": 0.3420512118307545,
|
| 8798 |
+
"grad_norm": 0.45117536187171936,
|
| 8799 |
+
"learning_rate": 3.831018817705827e-05,
|
| 8800 |
+
"loss": 0.40302005410194397,
|
| 8801 |
+
"step": 1249
|
| 8802 |
+
},
|
| 8803 |
+
{
|
| 8804 |
+
"epoch": 0.3423250718882651,
|
| 8805 |
+
"grad_norm": 0.4863901138305664,
|
| 8806 |
+
"learning_rate": 3.829141303281265e-05,
|
| 8807 |
+
"loss": 0.41938668489456177,
|
| 8808 |
+
"step": 1250
|
| 8809 |
+
},
|
| 8810 |
+
{
|
| 8811 |
+
"epoch": 0.34259893194577573,
|
| 8812 |
+
"grad_norm": 0.5007160305976868,
|
| 8813 |
+
"learning_rate": 3.827262743237003e-05,
|
| 8814 |
+
"loss": 0.4390687346458435,
|
| 8815 |
+
"step": 1251
|
| 8816 |
+
},
|
| 8817 |
+
{
|
| 8818 |
+
"epoch": 0.3428727920032863,
|
| 8819 |
+
"grad_norm": 0.4935399293899536,
|
| 8820 |
+
"learning_rate": 3.825383139050881e-05,
|
| 8821 |
+
"loss": 0.41444864869117737,
|
| 8822 |
+
"step": 1252
|
| 8823 |
+
},
|
| 8824 |
+
{
|
| 8825 |
+
"epoch": 0.3431466520607969,
|
| 8826 |
+
"grad_norm": 0.49743470549583435,
|
| 8827 |
+
"learning_rate": 3.823502492201562e-05,
|
| 8828 |
+
"loss": 0.44534939527511597,
|
| 8829 |
+
"step": 1253
|
| 8830 |
+
},
|
| 8831 |
+
{
|
| 8832 |
+
"epoch": 0.34342051211830754,
|
| 8833 |
+
"grad_norm": 0.4710836112499237,
|
| 8834 |
+
"learning_rate": 3.821620804168529e-05,
|
| 8835 |
+
"loss": 0.48468175530433655,
|
| 8836 |
+
"step": 1254
|
| 8837 |
+
},
|
| 8838 |
+
{
|
| 8839 |
+
"epoch": 0.34369437217581816,
|
| 8840 |
+
"grad_norm": 0.47617143392562866,
|
| 8841 |
+
"learning_rate": 3.819738076432081e-05,
|
| 8842 |
+
"loss": 0.43121767044067383,
|
| 8843 |
+
"step": 1255
|
| 8844 |
+
},
|
| 8845 |
+
{
|
| 8846 |
+
"epoch": 0.3439682322333288,
|
| 8847 |
+
"grad_norm": 0.5171325206756592,
|
| 8848 |
+
"learning_rate": 3.817854310473341e-05,
|
| 8849 |
+
"loss": 0.4363159239292145,
|
| 8850 |
+
"step": 1256
|
| 8851 |
+
},
|
| 8852 |
+
{
|
| 8853 |
+
"epoch": 0.3442420922908394,
|
| 8854 |
+
"grad_norm": 0.4890725612640381,
|
| 8855 |
+
"learning_rate": 3.815969507774244e-05,
|
| 8856 |
+
"loss": 0.38662803173065186,
|
| 8857 |
+
"step": 1257
|
| 8858 |
+
},
|
| 8859 |
+
{
|
| 8860 |
+
"epoch": 0.34451595234835,
|
| 8861 |
+
"grad_norm": 0.5731508135795593,
|
| 8862 |
+
"learning_rate": 3.814083669817541e-05,
|
| 8863 |
+
"loss": 0.5147716403007507,
|
| 8864 |
+
"step": 1258
|
| 8865 |
+
},
|
| 8866 |
+
{
|
| 8867 |
+
"epoch": 0.3447898124058606,
|
| 8868 |
+
"grad_norm": 0.5153118371963501,
|
| 8869 |
+
"learning_rate": 3.812196798086799e-05,
|
| 8870 |
+
"loss": 0.407422810792923,
|
| 8871 |
+
"step": 1259
|
| 8872 |
+
},
|
| 8873 |
+
{
|
| 8874 |
+
"epoch": 0.3450636724633712,
|
| 8875 |
+
"grad_norm": 0.4679732024669647,
|
| 8876 |
+
"learning_rate": 3.810308894066399e-05,
|
| 8877 |
+
"loss": 0.37180086970329285,
|
| 8878 |
+
"step": 1260
|
| 8879 |
+
},
|
| 8880 |
+
{
|
| 8881 |
+
"epoch": 0.34533753252088184,
|
| 8882 |
+
"grad_norm": 0.5397917032241821,
|
| 8883 |
+
"learning_rate": 3.8084199592415305e-05,
|
| 8884 |
+
"loss": 0.43410181999206543,
|
| 8885 |
+
"step": 1261
|
| 8886 |
+
},
|
| 8887 |
+
{
|
| 8888 |
+
"epoch": 0.34561139257839246,
|
| 8889 |
+
"grad_norm": 0.5022844076156616,
|
| 8890 |
+
"learning_rate": 3.806529995098197e-05,
|
| 8891 |
+
"loss": 0.4319794774055481,
|
| 8892 |
+
"step": 1262
|
| 8893 |
+
},
|
| 8894 |
+
{
|
| 8895 |
+
"epoch": 0.34588525263590303,
|
| 8896 |
+
"grad_norm": 0.4835938811302185,
|
| 8897 |
+
"learning_rate": 3.804639003123211e-05,
|
| 8898 |
+
"loss": 0.5116240382194519,
|
| 8899 |
+
"step": 1263
|
| 8900 |
+
},
|
| 8901 |
+
{
|
| 8902 |
+
"epoch": 0.34615911269341365,
|
| 8903 |
+
"grad_norm": 0.5120028257369995,
|
| 8904 |
+
"learning_rate": 3.8027469848041936e-05,
|
| 8905 |
+
"loss": 0.4661020040512085,
|
| 8906 |
+
"step": 1264
|
| 8907 |
+
},
|
| 8908 |
+
{
|
| 8909 |
+
"epoch": 0.3464329727509243,
|
| 8910 |
+
"grad_norm": 0.5063124299049377,
|
| 8911 |
+
"learning_rate": 3.800853941629573e-05,
|
| 8912 |
+
"loss": 0.47649818658828735,
|
| 8913 |
+
"step": 1265
|
| 8914 |
+
},
|
| 8915 |
+
{
|
| 8916 |
+
"epoch": 0.3467068328084349,
|
| 8917 |
+
"grad_norm": 0.4893288016319275,
|
| 8918 |
+
"learning_rate": 3.798959875088584e-05,
|
| 8919 |
+
"loss": 0.502692699432373,
|
| 8920 |
+
"step": 1266
|
| 8921 |
+
},
|
| 8922 |
+
{
|
| 8923 |
+
"epoch": 0.3469806928659455,
|
| 8924 |
+
"grad_norm": 0.5663262605667114,
|
| 8925 |
+
"learning_rate": 3.797064786671266e-05,
|
| 8926 |
+
"loss": 0.42376425862312317,
|
| 8927 |
+
"step": 1267
|
| 8928 |
+
},
|
| 8929 |
+
{
|
| 8930 |
+
"epoch": 0.34725455292345614,
|
| 8931 |
+
"grad_norm": 0.5071814060211182,
|
| 8932 |
+
"learning_rate": 3.795168677868463e-05,
|
| 8933 |
+
"loss": 0.48261600732803345,
|
| 8934 |
+
"step": 1268
|
| 8935 |
+
},
|
| 8936 |
+
{
|
| 8937 |
+
"epoch": 0.3475284129809667,
|
| 8938 |
+
"grad_norm": 0.5126127600669861,
|
| 8939 |
+
"learning_rate": 3.7932715501718206e-05,
|
| 8940 |
+
"loss": 0.47943922877311707,
|
| 8941 |
+
"step": 1269
|
| 8942 |
+
},
|
| 8943 |
+
{
|
| 8944 |
+
"epoch": 0.3478022730384773,
|
| 8945 |
+
"grad_norm": 0.5080000162124634,
|
| 8946 |
+
"learning_rate": 3.791373405073787e-05,
|
| 8947 |
+
"loss": 0.48512646555900574,
|
| 8948 |
+
"step": 1270
|
| 8949 |
+
},
|
| 8950 |
+
{
|
| 8951 |
+
"epoch": 0.34807613309598795,
|
| 8952 |
+
"grad_norm": 0.5103537440299988,
|
| 8953 |
+
"learning_rate": 3.7894742440676104e-05,
|
| 8954 |
+
"loss": 0.4268091917037964,
|
| 8955 |
+
"step": 1271
|
| 8956 |
+
},
|
| 8957 |
+
{
|
| 8958 |
+
"epoch": 0.34834999315349857,
|
| 8959 |
+
"grad_norm": 0.5434494614601135,
|
| 8960 |
+
"learning_rate": 3.787574068647338e-05,
|
| 8961 |
+
"loss": 0.4237458109855652,
|
| 8962 |
+
"step": 1272
|
| 8963 |
+
},
|
| 8964 |
+
{
|
| 8965 |
+
"epoch": 0.3486238532110092,
|
| 8966 |
+
"grad_norm": 0.490644246339798,
|
| 8967 |
+
"learning_rate": 3.785672880307817e-05,
|
| 8968 |
+
"loss": 0.41650092601776123,
|
| 8969 |
+
"step": 1273
|
| 8970 |
+
},
|
| 8971 |
+
{
|
| 8972 |
+
"epoch": 0.34889771326851976,
|
| 8973 |
+
"grad_norm": 0.5505414009094238,
|
| 8974 |
+
"learning_rate": 3.783770680544687e-05,
|
| 8975 |
+
"loss": 0.4882046580314636,
|
| 8976 |
+
"step": 1274
|
| 8977 |
+
},
|
| 8978 |
+
{
|
| 8979 |
+
"epoch": 0.3491715733260304,
|
| 8980 |
+
"grad_norm": 0.4645828902721405,
|
| 8981 |
+
"learning_rate": 3.781867470854388e-05,
|
| 8982 |
+
"loss": 0.5480517745018005,
|
| 8983 |
+
"step": 1275
|
| 8984 |
+
},
|
| 8985 |
+
{
|
| 8986 |
+
"epoch": 0.349445433383541,
|
| 8987 |
+
"grad_norm": 0.47438421845436096,
|
| 8988 |
+
"learning_rate": 3.7799632527341514e-05,
|
| 8989 |
+
"loss": 0.3708432614803314,
|
| 8990 |
+
"step": 1276
|
| 8991 |
+
},
|
| 8992 |
+
{
|
| 8993 |
+
"epoch": 0.3497192934410516,
|
| 8994 |
+
"grad_norm": 0.48648422956466675,
|
| 8995 |
+
"learning_rate": 3.778058027682004e-05,
|
| 8996 |
+
"loss": 0.4388870596885681,
|
| 8997 |
+
"step": 1277
|
| 8998 |
+
},
|
| 8999 |
+
{
|
| 9000 |
+
"epoch": 0.34999315349856225,
|
| 9001 |
+
"grad_norm": 0.5161449909210205,
|
| 9002 |
+
"learning_rate": 3.776151797196762e-05,
|
| 9003 |
+
"loss": 0.5039101839065552,
|
| 9004 |
+
"step": 1278
|
| 9005 |
+
},
|
| 9006 |
+
{
|
| 9007 |
+
"epoch": 0.35026701355607287,
|
| 9008 |
+
"grad_norm": 0.4867840111255646,
|
| 9009 |
+
"learning_rate": 3.774244562778036e-05,
|
| 9010 |
+
"loss": 0.39218488335609436,
|
| 9011 |
+
"step": 1279
|
| 9012 |
+
},
|
| 9013 |
+
{
|
| 9014 |
+
"epoch": 0.35054087361358344,
|
| 9015 |
+
"grad_norm": 0.529883623123169,
|
| 9016 |
+
"learning_rate": 3.7723363259262254e-05,
|
| 9017 |
+
"loss": 0.5143795013427734,
|
| 9018 |
+
"step": 1280
|
| 9019 |
+
},
|
| 9020 |
+
{
|
| 9021 |
+
"epoch": 0.35081473367109406,
|
| 9022 |
+
"grad_norm": 0.4833196997642517,
|
| 9023 |
+
"learning_rate": 3.770427088142515e-05,
|
| 9024 |
+
"loss": 0.4271458685398102,
|
| 9025 |
+
"step": 1281
|
| 9026 |
+
},
|
| 9027 |
+
{
|
| 9028 |
+
"epoch": 0.3510885937286047,
|
| 9029 |
+
"grad_norm": 0.5043869018554688,
|
| 9030 |
+
"learning_rate": 3.768516850928881e-05,
|
| 9031 |
+
"loss": 0.45276063680648804,
|
| 9032 |
+
"step": 1282
|
| 9033 |
+
},
|
| 9034 |
+
{
|
| 9035 |
+
"epoch": 0.3513624537861153,
|
| 9036 |
+
"grad_norm": 0.5267980694770813,
|
| 9037 |
+
"learning_rate": 3.7666056157880844e-05,
|
| 9038 |
+
"loss": 0.5511831045150757,
|
| 9039 |
+
"step": 1283
|
| 9040 |
+
},
|
| 9041 |
+
{
|
| 9042 |
+
"epoch": 0.3516363138436259,
|
| 9043 |
+
"grad_norm": 0.4818955957889557,
|
| 9044 |
+
"learning_rate": 3.764693384223671e-05,
|
| 9045 |
+
"loss": 0.45846429467201233,
|
| 9046 |
+
"step": 1284
|
| 9047 |
+
},
|
| 9048 |
+
{
|
| 9049 |
+
"epoch": 0.3519101739011365,
|
| 9050 |
+
"grad_norm": 0.5381810069084167,
|
| 9051 |
+
"learning_rate": 3.76278015773997e-05,
|
| 9052 |
+
"loss": 0.36841803789138794,
|
| 9053 |
+
"step": 1285
|
| 9054 |
+
},
|
| 9055 |
+
{
|
| 9056 |
+
"epoch": 0.3521840339586471,
|
| 9057 |
+
"grad_norm": 0.5437278747558594,
|
| 9058 |
+
"learning_rate": 3.760865937842096e-05,
|
| 9059 |
+
"loss": 0.572014331817627,
|
| 9060 |
+
"step": 1286
|
| 9061 |
+
},
|
| 9062 |
+
{
|
| 9063 |
+
"epoch": 0.35245789401615774,
|
| 9064 |
+
"grad_norm": 0.5240300297737122,
|
| 9065 |
+
"learning_rate": 3.7589507260359404e-05,
|
| 9066 |
+
"loss": 0.5897840857505798,
|
| 9067 |
+
"step": 1287
|
| 9068 |
+
},
|
| 9069 |
+
{
|
| 9070 |
+
"epoch": 0.35273175407366836,
|
| 9071 |
+
"grad_norm": 0.4361365735530853,
|
| 9072 |
+
"learning_rate": 3.75703452382818e-05,
|
| 9073 |
+
"loss": 0.3405730724334717,
|
| 9074 |
+
"step": 1288
|
| 9075 |
+
},
|
| 9076 |
+
{
|
| 9077 |
+
"epoch": 0.353005614131179,
|
| 9078 |
+
"grad_norm": 0.4901905357837677,
|
| 9079 |
+
"learning_rate": 3.7551173327262665e-05,
|
| 9080 |
+
"loss": 0.40754252672195435,
|
| 9081 |
+
"step": 1289
|
| 9082 |
+
},
|
| 9083 |
+
{
|
| 9084 |
+
"epoch": 0.3532794741886896,
|
| 9085 |
+
"grad_norm": 0.46734657883644104,
|
| 9086 |
+
"learning_rate": 3.753199154238433e-05,
|
| 9087 |
+
"loss": 0.3874797821044922,
|
| 9088 |
+
"step": 1290
|
| 9089 |
+
},
|
| 9090 |
+
{
|
| 9091 |
+
"epoch": 0.35355333424620017,
|
| 9092 |
+
"grad_norm": 0.5717946290969849,
|
| 9093 |
+
"learning_rate": 3.751279989873687e-05,
|
| 9094 |
+
"loss": 0.5184738039970398,
|
| 9095 |
+
"step": 1291
|
| 9096 |
+
},
|
| 9097 |
+
{
|
| 9098 |
+
"epoch": 0.3538271943037108,
|
| 9099 |
+
"grad_norm": 0.45746639370918274,
|
| 9100 |
+
"learning_rate": 3.7493598411418117e-05,
|
| 9101 |
+
"loss": 0.41665542125701904,
|
| 9102 |
+
"step": 1292
|
| 9103 |
+
},
|
| 9104 |
+
{
|
| 9105 |
+
"epoch": 0.3541010543612214,
|
| 9106 |
+
"grad_norm": 0.5202240347862244,
|
| 9107 |
+
"learning_rate": 3.747438709553367e-05,
|
| 9108 |
+
"loss": 0.42666923999786377,
|
| 9109 |
+
"step": 1293
|
| 9110 |
+
},
|
| 9111 |
+
{
|
| 9112 |
+
"epoch": 0.35437491441873203,
|
| 9113 |
+
"grad_norm": 0.5001067519187927,
|
| 9114 |
+
"learning_rate": 3.745516596619681e-05,
|
| 9115 |
+
"loss": 0.3253193497657776,
|
| 9116 |
+
"step": 1294
|
| 9117 |
+
},
|
| 9118 |
+
{
|
| 9119 |
+
"epoch": 0.35464877447624266,
|
| 9120 |
+
"grad_norm": 0.5040087699890137,
|
| 9121 |
+
"learning_rate": 3.7435935038528616e-05,
|
| 9122 |
+
"loss": 0.4230794906616211,
|
| 9123 |
+
"step": 1295
|
| 9124 |
+
},
|
| 9125 |
+
{
|
| 9126 |
+
"epoch": 0.3549226345337533,
|
| 9127 |
+
"grad_norm": 0.5337259769439697,
|
| 9128 |
+
"learning_rate": 3.741669432765781e-05,
|
| 9129 |
+
"loss": 0.4002869725227356,
|
| 9130 |
+
"step": 1296
|
| 9131 |
+
},
|
| 9132 |
+
{
|
| 9133 |
+
"epoch": 0.35519649459126384,
|
| 9134 |
+
"grad_norm": 0.4834175705909729,
|
| 9135 |
+
"learning_rate": 3.7397443848720826e-05,
|
| 9136 |
+
"loss": 0.41585642099380493,
|
| 9137 |
+
"step": 1297
|
| 9138 |
+
},
|
| 9139 |
+
{
|
| 9140 |
+
"epoch": 0.35547035464877447,
|
| 9141 |
+
"grad_norm": 0.47829556465148926,
|
| 9142 |
+
"learning_rate": 3.737818361686179e-05,
|
| 9143 |
+
"loss": 0.46697622537612915,
|
| 9144 |
+
"step": 1298
|
| 9145 |
+
},
|
| 9146 |
+
{
|
| 9147 |
+
"epoch": 0.3557442147062851,
|
| 9148 |
+
"grad_norm": 0.4862878620624542,
|
| 9149 |
+
"learning_rate": 3.73589136472325e-05,
|
| 9150 |
+
"loss": 0.4355926513671875,
|
| 9151 |
+
"step": 1299
|
| 9152 |
+
},
|
| 9153 |
+
{
|
| 9154 |
+
"epoch": 0.3560180747637957,
|
| 9155 |
+
"grad_norm": 0.5559048056602478,
|
| 9156 |
+
"learning_rate": 3.733963395499241e-05,
|
| 9157 |
+
"loss": 0.4013769030570984,
|
| 9158 |
+
"step": 1300
|
| 9159 |
+
},
|
| 9160 |
+
{
|
| 9161 |
+
"epoch": 0.35629193482130633,
|
| 9162 |
+
"grad_norm": 0.4943205416202545,
|
| 9163 |
+
"learning_rate": 3.732034455530863e-05,
|
| 9164 |
+
"loss": 0.3790661096572876,
|
| 9165 |
+
"step": 1301
|
| 9166 |
+
},
|
| 9167 |
+
{
|
| 9168 |
+
"epoch": 0.3565657948788169,
|
| 9169 |
+
"grad_norm": 0.47194966673851013,
|
| 9170 |
+
"learning_rate": 3.73010454633559e-05,
|
| 9171 |
+
"loss": 0.40350398421287537,
|
| 9172 |
+
"step": 1302
|
| 9173 |
+
},
|
| 9174 |
+
{
|
| 9175 |
+
"epoch": 0.3568396549363275,
|
| 9176 |
+
"grad_norm": 0.5339755415916443,
|
| 9177 |
+
"learning_rate": 3.728173669431659e-05,
|
| 9178 |
+
"loss": 0.4053725302219391,
|
| 9179 |
+
"step": 1303
|
| 9180 |
+
},
|
| 9181 |
+
{
|
| 9182 |
+
"epoch": 0.35711351499383814,
|
| 9183 |
+
"grad_norm": 0.5074479579925537,
|
| 9184 |
+
"learning_rate": 3.7262418263380673e-05,
|
| 9185 |
+
"loss": 0.45121580362319946,
|
| 9186 |
+
"step": 1304
|
| 9187 |
+
},
|
| 9188 |
+
{
|
| 9189 |
+
"epoch": 0.35738737505134877,
|
| 9190 |
+
"grad_norm": 0.4879530072212219,
|
| 9191 |
+
"learning_rate": 3.724309018574573e-05,
|
| 9192 |
+
"loss": 0.417098730802536,
|
| 9193 |
+
"step": 1305
|
| 9194 |
+
},
|
| 9195 |
+
{
|
| 9196 |
+
"epoch": 0.3576612351088594,
|
| 9197 |
+
"grad_norm": 0.5004150867462158,
|
| 9198 |
+
"learning_rate": 3.722375247661694e-05,
|
| 9199 |
+
"loss": 0.46026700735092163,
|
| 9200 |
+
"step": 1306
|
| 9201 |
+
},
|
| 9202 |
+
{
|
| 9203 |
+
"epoch": 0.35793509516637,
|
| 9204 |
+
"grad_norm": 0.48087188601493835,
|
| 9205 |
+
"learning_rate": 3.7204405151207036e-05,
|
| 9206 |
+
"loss": 0.48908865451812744,
|
| 9207 |
+
"step": 1307
|
| 9208 |
+
},
|
| 9209 |
+
{
|
| 9210 |
+
"epoch": 0.3582089552238806,
|
| 9211 |
+
"grad_norm": 0.44571784138679504,
|
| 9212 |
+
"learning_rate": 3.718504822473634e-05,
|
| 9213 |
+
"loss": 0.42255520820617676,
|
| 9214 |
+
"step": 1308
|
| 9215 |
+
},
|
| 9216 |
+
{
|
| 9217 |
+
"epoch": 0.3584828152813912,
|
| 9218 |
+
"grad_norm": 0.463279128074646,
|
| 9219 |
+
"learning_rate": 3.716568171243271e-05,
|
| 9220 |
+
"loss": 0.4070418179035187,
|
| 9221 |
+
"step": 1309
|
| 9222 |
+
},
|
| 9223 |
+
{
|
| 9224 |
+
"epoch": 0.3587566753389018,
|
| 9225 |
+
"grad_norm": 0.4891701936721802,
|
| 9226 |
+
"learning_rate": 3.714630562953155e-05,
|
| 9227 |
+
"loss": 0.4539220929145813,
|
| 9228 |
+
"step": 1310
|
| 9229 |
+
},
|
| 9230 |
+
{
|
| 9231 |
+
"epoch": 0.35903053539641244,
|
| 9232 |
+
"grad_norm": 0.45751306414604187,
|
| 9233 |
+
"learning_rate": 3.7126919991275805e-05,
|
| 9234 |
+
"loss": 0.3884638547897339,
|
| 9235 |
+
"step": 1311
|
| 9236 |
+
},
|
| 9237 |
+
{
|
| 9238 |
+
"epoch": 0.35930439545392306,
|
| 9239 |
+
"grad_norm": 0.48046591877937317,
|
| 9240 |
+
"learning_rate": 3.710752481291592e-05,
|
| 9241 |
+
"loss": 0.4229041039943695,
|
| 9242 |
+
"step": 1312
|
| 9243 |
+
},
|
| 9244 |
+
{
|
| 9245 |
+
"epoch": 0.35957825551143363,
|
| 9246 |
+
"grad_norm": 0.4385284185409546,
|
| 9247 |
+
"learning_rate": 3.708812010970985e-05,
|
| 9248 |
+
"loss": 0.4166451096534729,
|
| 9249 |
+
"step": 1313
|
| 9250 |
+
},
|
| 9251 |
+
{
|
| 9252 |
+
"epoch": 0.35985211556894425,
|
| 9253 |
+
"grad_norm": 0.5227051377296448,
|
| 9254 |
+
"learning_rate": 3.706870589692305e-05,
|
| 9255 |
+
"loss": 0.4045732021331787,
|
| 9256 |
+
"step": 1314
|
| 9257 |
+
},
|
| 9258 |
+
{
|
| 9259 |
+
"epoch": 0.3601259756264549,
|
| 9260 |
+
"grad_norm": 0.5101045370101929,
|
| 9261 |
+
"learning_rate": 3.704928218982845e-05,
|
| 9262 |
+
"loss": 0.4325561821460724,
|
| 9263 |
+
"step": 1315
|
| 9264 |
+
},
|
| 9265 |
+
{
|
| 9266 |
+
"epoch": 0.3603998356839655,
|
| 9267 |
+
"grad_norm": 0.5624421238899231,
|
| 9268 |
+
"learning_rate": 3.702984900370644e-05,
|
| 9269 |
+
"loss": 0.499100923538208,
|
| 9270 |
+
"step": 1316
|
| 9271 |
+
},
|
| 9272 |
+
{
|
| 9273 |
+
"epoch": 0.3606736957414761,
|
| 9274 |
+
"grad_norm": 0.5007335543632507,
|
| 9275 |
+
"learning_rate": 3.701040635384489e-05,
|
| 9276 |
+
"loss": 0.4622655510902405,
|
| 9277 |
+
"step": 1317
|
| 9278 |
+
},
|
| 9279 |
+
{
|
| 9280 |
+
"epoch": 0.36094755579898674,
|
| 9281 |
+
"grad_norm": 0.4327225983142853,
|
| 9282 |
+
"learning_rate": 3.699095425553909e-05,
|
| 9283 |
+
"loss": 0.37201666831970215,
|
| 9284 |
+
"step": 1318
|
| 9285 |
+
},
|
| 9286 |
+
{
|
| 9287 |
+
"epoch": 0.3612214158564973,
|
| 9288 |
+
"grad_norm": 0.492806077003479,
|
| 9289 |
+
"learning_rate": 3.6971492724091795e-05,
|
| 9290 |
+
"loss": 0.370299756526947,
|
| 9291 |
+
"step": 1319
|
| 9292 |
+
},
|
| 9293 |
+
{
|
| 9294 |
+
"epoch": 0.36149527591400793,
|
| 9295 |
+
"grad_norm": 0.545153021812439,
|
| 9296 |
+
"learning_rate": 3.695202177481314e-05,
|
| 9297 |
+
"loss": 0.3848322629928589,
|
| 9298 |
+
"step": 1320
|
| 9299 |
+
},
|
| 9300 |
+
{
|
| 9301 |
+
"epoch": 0.36176913597151855,
|
| 9302 |
+
"grad_norm": 0.5670954585075378,
|
| 9303 |
+
"learning_rate": 3.693254142302071e-05,
|
| 9304 |
+
"loss": 0.45104020833969116,
|
| 9305 |
+
"step": 1321
|
| 9306 |
+
},
|
| 9307 |
+
{
|
| 9308 |
+
"epoch": 0.3620429960290292,
|
| 9309 |
+
"grad_norm": 0.5173769593238831,
|
| 9310 |
+
"learning_rate": 3.691305168403944e-05,
|
| 9311 |
+
"loss": 0.512470006942749,
|
| 9312 |
+
"step": 1322
|
| 9313 |
+
},
|
| 9314 |
+
{
|
| 9315 |
+
"epoch": 0.3623168560865398,
|
| 9316 |
+
"grad_norm": 0.4675150513648987,
|
| 9317 |
+
"learning_rate": 3.6893552573201694e-05,
|
| 9318 |
+
"loss": 0.45482754707336426,
|
| 9319 |
+
"step": 1323
|
| 9320 |
+
},
|
| 9321 |
+
{
|
| 9322 |
+
"epoch": 0.3625907161440504,
|
| 9323 |
+
"grad_norm": 0.48641857504844666,
|
| 9324 |
+
"learning_rate": 3.6874044105847195e-05,
|
| 9325 |
+
"loss": 0.4778265357017517,
|
| 9326 |
+
"step": 1324
|
| 9327 |
+
},
|
| 9328 |
+
{
|
| 9329 |
+
"epoch": 0.362864576201561,
|
| 9330 |
+
"grad_norm": 0.47990021109580994,
|
| 9331 |
+
"learning_rate": 3.685452629732301e-05,
|
| 9332 |
+
"loss": 0.43550652265548706,
|
| 9333 |
+
"step": 1325
|
| 9334 |
+
},
|
| 9335 |
+
{
|
| 9336 |
+
"epoch": 0.3631384362590716,
|
| 9337 |
+
"grad_norm": 0.4834146201610565,
|
| 9338 |
+
"learning_rate": 3.683499916298357e-05,
|
| 9339 |
+
"loss": 0.4588314890861511,
|
| 9340 |
+
"step": 1326
|
| 9341 |
+
},
|
| 9342 |
+
{
|
| 9343 |
+
"epoch": 0.36341229631658223,
|
| 9344 |
+
"grad_norm": 0.4500870108604431,
|
| 9345 |
+
"learning_rate": 3.681546271819065e-05,
|
| 9346 |
+
"loss": 0.37250393629074097,
|
| 9347 |
+
"step": 1327
|
| 9348 |
+
},
|
| 9349 |
+
{
|
| 9350 |
+
"epoch": 0.36368615637409285,
|
| 9351 |
+
"grad_norm": 0.4590033292770386,
|
| 9352 |
+
"learning_rate": 3.679591697831334e-05,
|
| 9353 |
+
"loss": 0.4177936315536499,
|
| 9354 |
+
"step": 1328
|
| 9355 |
+
},
|
| 9356 |
+
{
|
| 9357 |
+
"epoch": 0.3639600164316035,
|
| 9358 |
+
"grad_norm": 0.49659016728401184,
|
| 9359 |
+
"learning_rate": 3.677636195872802e-05,
|
| 9360 |
+
"loss": 0.4178810715675354,
|
| 9361 |
+
"step": 1329
|
| 9362 |
+
},
|
| 9363 |
+
{
|
| 9364 |
+
"epoch": 0.36423387648911404,
|
| 9365 |
+
"grad_norm": 0.46042147278785706,
|
| 9366 |
+
"learning_rate": 3.675679767481842e-05,
|
| 9367 |
+
"loss": 0.40960928797721863,
|
| 9368 |
+
"step": 1330
|
| 9369 |
+
},
|
| 9370 |
+
{
|
| 9371 |
+
"epoch": 0.36450773654662466,
|
| 9372 |
+
"grad_norm": 0.4750092923641205,
|
| 9373 |
+
"learning_rate": 3.673722414197552e-05,
|
| 9374 |
+
"loss": 0.4692423343658447,
|
| 9375 |
+
"step": 1331
|
| 9376 |
+
},
|
| 9377 |
+
{
|
| 9378 |
+
"epoch": 0.3647815966041353,
|
| 9379 |
+
"grad_norm": 0.5290725231170654,
|
| 9380 |
+
"learning_rate": 3.671764137559757e-05,
|
| 9381 |
+
"loss": 0.4357198476791382,
|
| 9382 |
+
"step": 1332
|
| 9383 |
+
},
|
| 9384 |
+
{
|
| 9385 |
+
"epoch": 0.3650554566616459,
|
| 9386 |
+
"grad_norm": 0.5206736922264099,
|
| 9387 |
+
"learning_rate": 3.669804939109012e-05,
|
| 9388 |
+
"loss": 0.441597044467926,
|
| 9389 |
+
"step": 1333
|
| 9390 |
+
},
|
| 9391 |
+
{
|
| 9392 |
+
"epoch": 0.3653293167191565,
|
| 9393 |
+
"grad_norm": 0.5407825708389282,
|
| 9394 |
+
"learning_rate": 3.6678448203865945e-05,
|
| 9395 |
+
"loss": 0.44571197032928467,
|
| 9396 |
+
"step": 1334
|
| 9397 |
+
},
|
| 9398 |
+
{
|
| 9399 |
+
"epoch": 0.36560317677666715,
|
| 9400 |
+
"grad_norm": 0.46567633748054504,
|
| 9401 |
+
"learning_rate": 3.665883782934507e-05,
|
| 9402 |
+
"loss": 0.37851929664611816,
|
| 9403 |
+
"step": 1335
|
| 9404 |
+
},
|
| 9405 |
+
{
|
| 9406 |
+
"epoch": 0.3658770368341777,
|
| 9407 |
+
"grad_norm": 0.5091806054115295,
|
| 9408 |
+
"learning_rate": 3.663921828295474e-05,
|
| 9409 |
+
"loss": 0.49039971828460693,
|
| 9410 |
+
"step": 1336
|
| 9411 |
+
},
|
| 9412 |
+
{
|
| 9413 |
+
"epoch": 0.36615089689168834,
|
| 9414 |
+
"grad_norm": 0.5392701029777527,
|
| 9415 |
+
"learning_rate": 3.6619589580129424e-05,
|
| 9416 |
+
"loss": 0.5365228056907654,
|
| 9417 |
+
"step": 1337
|
| 9418 |
+
},
|
| 9419 |
+
{
|
| 9420 |
+
"epoch": 0.36642475694919896,
|
| 9421 |
+
"grad_norm": 0.512220561504364,
|
| 9422 |
+
"learning_rate": 3.659995173631078e-05,
|
| 9423 |
+
"loss": 0.5147318840026855,
|
| 9424 |
+
"step": 1338
|
| 9425 |
+
},
|
| 9426 |
+
{
|
| 9427 |
+
"epoch": 0.3666986170067096,
|
| 9428 |
+
"grad_norm": 0.4934576451778412,
|
| 9429 |
+
"learning_rate": 3.658030476694767e-05,
|
| 9430 |
+
"loss": 0.49940282106399536,
|
| 9431 |
+
"step": 1339
|
| 9432 |
+
},
|
| 9433 |
+
{
|
| 9434 |
+
"epoch": 0.3669724770642202,
|
| 9435 |
+
"grad_norm": 0.5440602898597717,
|
| 9436 |
+
"learning_rate": 3.656064868749614e-05,
|
| 9437 |
+
"loss": 0.45560991764068604,
|
| 9438 |
+
"step": 1340
|
| 9439 |
+
},
|
| 9440 |
+
{
|
| 9441 |
+
"epoch": 0.36724633712173077,
|
| 9442 |
+
"grad_norm": 0.4786243438720703,
|
| 9443 |
+
"learning_rate": 3.6540983513419393e-05,
|
| 9444 |
+
"loss": 0.4464971721172333,
|
| 9445 |
+
"step": 1341
|
| 9446 |
+
},
|
| 9447 |
+
{
|
| 9448 |
+
"epoch": 0.3675201971792414,
|
| 9449 |
+
"grad_norm": 0.5171247720718384,
|
| 9450 |
+
"learning_rate": 3.6521309260187776e-05,
|
| 9451 |
+
"loss": 0.41680097579956055,
|
| 9452 |
+
"step": 1342
|
| 9453 |
+
},
|
| 9454 |
+
{
|
| 9455 |
+
"epoch": 0.367794057236752,
|
| 9456 |
+
"grad_norm": 0.5133869647979736,
|
| 9457 |
+
"learning_rate": 3.6501625943278805e-05,
|
| 9458 |
+
"loss": 0.4273906350135803,
|
| 9459 |
+
"step": 1343
|
| 9460 |
+
},
|
| 9461 |
+
{
|
| 9462 |
+
"epoch": 0.36806791729426264,
|
| 9463 |
+
"grad_norm": 0.506430983543396,
|
| 9464 |
+
"learning_rate": 3.6481933578177105e-05,
|
| 9465 |
+
"loss": 0.49195581674575806,
|
| 9466 |
+
"step": 1344
|
| 9467 |
+
},
|
| 9468 |
+
{
|
| 9469 |
+
"epoch": 0.36834177735177326,
|
| 9470 |
+
"grad_norm": 0.5484556555747986,
|
| 9471 |
+
"learning_rate": 3.6462232180374425e-05,
|
| 9472 |
+
"loss": 0.4169536828994751,
|
| 9473 |
+
"step": 1345
|
| 9474 |
+
},
|
| 9475 |
+
{
|
| 9476 |
+
"epoch": 0.3686156374092839,
|
| 9477 |
+
"grad_norm": 0.5015157461166382,
|
| 9478 |
+
"learning_rate": 3.644252176536963e-05,
|
| 9479 |
+
"loss": 0.488889217376709,
|
| 9480 |
+
"step": 1346
|
| 9481 |
+
},
|
| 9482 |
+
{
|
| 9483 |
+
"epoch": 0.36888949746679445,
|
| 9484 |
+
"grad_norm": 0.4740557372570038,
|
| 9485 |
+
"learning_rate": 3.642280234866866e-05,
|
| 9486 |
+
"loss": 0.44339632987976074,
|
| 9487 |
+
"step": 1347
|
| 9488 |
+
},
|
| 9489 |
+
{
|
| 9490 |
+
"epoch": 0.36916335752430507,
|
| 9491 |
+
"grad_norm": 0.5000171661376953,
|
| 9492 |
+
"learning_rate": 3.6403073945784544e-05,
|
| 9493 |
+
"loss": 0.4809257388114929,
|
| 9494 |
+
"step": 1348
|
| 9495 |
+
},
|
| 9496 |
+
{
|
| 9497 |
+
"epoch": 0.3694372175818157,
|
| 9498 |
+
"grad_norm": 0.5162519812583923,
|
| 9499 |
+
"learning_rate": 3.63833365722374e-05,
|
| 9500 |
+
"loss": 0.45299065113067627,
|
| 9501 |
+
"step": 1349
|
| 9502 |
+
},
|
| 9503 |
+
{
|
| 9504 |
+
"epoch": 0.3697110776393263,
|
| 9505 |
+
"grad_norm": 0.5166103839874268,
|
| 9506 |
+
"learning_rate": 3.636359024355436e-05,
|
| 9507 |
+
"loss": 0.46844467520713806,
|
| 9508 |
+
"step": 1350
|
| 9509 |
+
},
|
| 9510 |
+
{
|
| 9511 |
+
"epoch": 0.36998493769683694,
|
| 9512 |
+
"grad_norm": 0.4974619150161743,
|
| 9513 |
+
"learning_rate": 3.6343834975269645e-05,
|
| 9514 |
+
"loss": 0.46222805976867676,
|
| 9515 |
+
"step": 1351
|
| 9516 |
+
},
|
| 9517 |
+
{
|
| 9518 |
+
"epoch": 0.3702587977543475,
|
| 9519 |
+
"grad_norm": 0.481062650680542,
|
| 9520 |
+
"learning_rate": 3.632407078292449e-05,
|
| 9521 |
+
"loss": 0.4054194688796997,
|
| 9522 |
+
"step": 1352
|
| 9523 |
+
},
|
| 9524 |
+
{
|
| 9525 |
+
"epoch": 0.3705326578118581,
|
| 9526 |
+
"grad_norm": 0.5184093713760376,
|
| 9527 |
+
"learning_rate": 3.6304297682067144e-05,
|
| 9528 |
+
"loss": 0.47149768471717834,
|
| 9529 |
+
"step": 1353
|
| 9530 |
+
},
|
| 9531 |
+
{
|
| 9532 |
+
"epoch": 0.37080651786936875,
|
| 9533 |
+
"grad_norm": 0.5308529734611511,
|
| 9534 |
+
"learning_rate": 3.6284515688252876e-05,
|
| 9535 |
+
"loss": 0.4264875650405884,
|
| 9536 |
+
"step": 1354
|
| 9537 |
+
},
|
| 9538 |
+
{
|
| 9539 |
+
"epoch": 0.37108037792687937,
|
| 9540 |
+
"grad_norm": 0.4817298352718353,
|
| 9541 |
+
"learning_rate": 3.626472481704394e-05,
|
| 9542 |
+
"loss": 0.4629805088043213,
|
| 9543 |
+
"step": 1355
|
| 9544 |
+
},
|
| 9545 |
+
{
|
| 9546 |
+
"epoch": 0.37135423798439,
|
| 9547 |
+
"grad_norm": 0.465859055519104,
|
| 9548 |
+
"learning_rate": 3.6244925084009586e-05,
|
| 9549 |
+
"loss": 0.3996428847312927,
|
| 9550 |
+
"step": 1356
|
| 9551 |
+
},
|
| 9552 |
+
{
|
| 9553 |
+
"epoch": 0.3716280980419006,
|
| 9554 |
+
"grad_norm": 0.4674395024776459,
|
| 9555 |
+
"learning_rate": 3.622511650472601e-05,
|
| 9556 |
+
"loss": 0.4802120327949524,
|
| 9557 |
+
"step": 1357
|
| 9558 |
+
},
|
| 9559 |
+
{
|
| 9560 |
+
"epoch": 0.3719019580994112,
|
| 9561 |
+
"grad_norm": 0.46892261505126953,
|
| 9562 |
+
"learning_rate": 3.620529909477642e-05,
|
| 9563 |
+
"loss": 0.42496174573898315,
|
| 9564 |
+
"step": 1358
|
| 9565 |
+
},
|
| 9566 |
+
{
|
| 9567 |
+
"epoch": 0.3721758181569218,
|
| 9568 |
+
"grad_norm": 0.49660390615463257,
|
| 9569 |
+
"learning_rate": 3.618547286975092e-05,
|
| 9570 |
+
"loss": 0.4051979184150696,
|
| 9571 |
+
"step": 1359
|
| 9572 |
+
},
|
| 9573 |
+
{
|
| 9574 |
+
"epoch": 0.3724496782144324,
|
| 9575 |
+
"grad_norm": 0.5395360589027405,
|
| 9576 |
+
"learning_rate": 3.616563784524656e-05,
|
| 9577 |
+
"loss": 0.5629136562347412,
|
| 9578 |
+
"step": 1360
|
| 9579 |
+
},
|
| 9580 |
+
{
|
| 9581 |
+
"epoch": 0.37272353827194304,
|
| 9582 |
+
"grad_norm": 0.4713611900806427,
|
| 9583 |
+
"learning_rate": 3.614579403686733e-05,
|
| 9584 |
+
"loss": 0.46685028076171875,
|
| 9585 |
+
"step": 1361
|
| 9586 |
+
},
|
| 9587 |
+
{
|
| 9588 |
+
"epoch": 0.37299739832945367,
|
| 9589 |
+
"grad_norm": 0.453745573759079,
|
| 9590 |
+
"learning_rate": 3.612594146022411e-05,
|
| 9591 |
+
"loss": 0.4508185088634491,
|
| 9592 |
+
"step": 1362
|
| 9593 |
+
},
|
| 9594 |
+
{
|
| 9595 |
+
"epoch": 0.3732712583869643,
|
| 9596 |
+
"grad_norm": 0.4596969187259674,
|
| 9597 |
+
"learning_rate": 3.610608013093468e-05,
|
| 9598 |
+
"loss": 0.40059199929237366,
|
| 9599 |
+
"step": 1363
|
| 9600 |
+
},
|
| 9601 |
+
{
|
| 9602 |
+
"epoch": 0.37354511844447486,
|
| 9603 |
+
"grad_norm": 0.459282785654068,
|
| 9604 |
+
"learning_rate": 3.608621006462373e-05,
|
| 9605 |
+
"loss": 0.4315662682056427,
|
| 9606 |
+
"step": 1364
|
| 9607 |
+
},
|
| 9608 |
+
{
|
| 9609 |
+
"epoch": 0.3738189785019855,
|
| 9610 |
+
"grad_norm": 0.48288634419441223,
|
| 9611 |
+
"learning_rate": 3.60663312769228e-05,
|
| 9612 |
+
"loss": 0.41357505321502686,
|
| 9613 |
+
"step": 1365
|
| 9614 |
+
},
|
| 9615 |
+
{
|
| 9616 |
+
"epoch": 0.3740928385594961,
|
| 9617 |
+
"grad_norm": 0.5203812122344971,
|
| 9618 |
+
"learning_rate": 3.60464437834703e-05,
|
| 9619 |
+
"loss": 0.36507150530815125,
|
| 9620 |
+
"step": 1366
|
| 9621 |
+
},
|
| 9622 |
+
{
|
| 9623 |
+
"epoch": 0.3743666986170067,
|
| 9624 |
+
"grad_norm": 0.4704032838344574,
|
| 9625 |
+
"learning_rate": 3.6026547599911464e-05,
|
| 9626 |
+
"loss": 0.433904767036438,
|
| 9627 |
+
"step": 1367
|
| 9628 |
+
},
|
| 9629 |
+
{
|
| 9630 |
+
"epoch": 0.37464055867451734,
|
| 9631 |
+
"grad_norm": 0.4995530843734741,
|
| 9632 |
+
"learning_rate": 3.600664274189841e-05,
|
| 9633 |
+
"loss": 0.4510709047317505,
|
| 9634 |
+
"step": 1368
|
| 9635 |
+
},
|
| 9636 |
+
{
|
| 9637 |
+
"epoch": 0.3749144187320279,
|
| 9638 |
+
"grad_norm": 0.5250251889228821,
|
| 9639 |
+
"learning_rate": 3.598672922509004e-05,
|
| 9640 |
+
"loss": 0.3636701703071594,
|
| 9641 |
+
"step": 1369
|
| 9642 |
+
},
|
| 9643 |
+
{
|
| 9644 |
+
"epoch": 0.37518827878953853,
|
| 9645 |
+
"grad_norm": 0.46615102887153625,
|
| 9646 |
+
"learning_rate": 3.596680706515208e-05,
|
| 9647 |
+
"loss": 0.4297676682472229,
|
| 9648 |
+
"step": 1370
|
| 9649 |
+
},
|
| 9650 |
+
{
|
| 9651 |
+
"epoch": 0.37546213884704915,
|
| 9652 |
+
"grad_norm": 0.4597174823284149,
|
| 9653 |
+
"learning_rate": 3.5946876277757066e-05,
|
| 9654 |
+
"loss": 0.4110604226589203,
|
| 9655 |
+
"step": 1371
|
| 9656 |
+
},
|
| 9657 |
+
{
|
| 9658 |
+
"epoch": 0.3757359989045598,
|
| 9659 |
+
"grad_norm": 0.5131960511207581,
|
| 9660 |
+
"learning_rate": 3.59269368785843e-05,
|
| 9661 |
+
"loss": 0.5741070508956909,
|
| 9662 |
+
"step": 1372
|
| 9663 |
+
},
|
| 9664 |
+
{
|
| 9665 |
+
"epoch": 0.3760098589620704,
|
| 9666 |
+
"grad_norm": 0.44912275671958923,
|
| 9667 |
+
"learning_rate": 3.5906988883319894e-05,
|
| 9668 |
+
"loss": 0.39023593068122864,
|
| 9669 |
+
"step": 1373
|
| 9670 |
+
},
|
| 9671 |
+
{
|
| 9672 |
+
"epoch": 0.376283719019581,
|
| 9673 |
+
"grad_norm": 0.4378318786621094,
|
| 9674 |
+
"learning_rate": 3.588703230765666e-05,
|
| 9675 |
+
"loss": 0.39967024326324463,
|
| 9676 |
+
"step": 1374
|
| 9677 |
+
},
|
| 9678 |
+
{
|
| 9679 |
+
"epoch": 0.3765575790770916,
|
| 9680 |
+
"grad_norm": 0.5163923501968384,
|
| 9681 |
+
"learning_rate": 3.586706716729424e-05,
|
| 9682 |
+
"loss": 0.4020618200302124,
|
| 9683 |
+
"step": 1375
|
| 9684 |
+
},
|
| 9685 |
+
{
|
| 9686 |
+
"epoch": 0.3768314391346022,
|
| 9687 |
+
"grad_norm": 0.5061731934547424,
|
| 9688 |
+
"learning_rate": 3.5847093477938956e-05,
|
| 9689 |
+
"loss": 0.47655192017555237,
|
| 9690 |
+
"step": 1376
|
| 9691 |
+
},
|
| 9692 |
+
{
|
| 9693 |
+
"epoch": 0.37710529919211283,
|
| 9694 |
+
"grad_norm": 0.5508501529693604,
|
| 9695 |
+
"learning_rate": 3.5827111255303867e-05,
|
| 9696 |
+
"loss": 0.40664058923721313,
|
| 9697 |
+
"step": 1377
|
| 9698 |
+
},
|
| 9699 |
+
{
|
| 9700 |
+
"epoch": 0.37737915924962345,
|
| 9701 |
+
"grad_norm": 0.492931604385376,
|
| 9702 |
+
"learning_rate": 3.580712051510876e-05,
|
| 9703 |
+
"loss": 0.5683432221412659,
|
| 9704 |
+
"step": 1378
|
| 9705 |
+
},
|
| 9706 |
+
{
|
| 9707 |
+
"epoch": 0.3776530193071341,
|
| 9708 |
+
"grad_norm": 0.4943591058254242,
|
| 9709 |
+
"learning_rate": 3.57871212730801e-05,
|
| 9710 |
+
"loss": 0.41741517186164856,
|
| 9711 |
+
"step": 1379
|
| 9712 |
+
},
|
| 9713 |
+
{
|
| 9714 |
+
"epoch": 0.37792687936464464,
|
| 9715 |
+
"grad_norm": 0.46847257018089294,
|
| 9716 |
+
"learning_rate": 3.576711354495107e-05,
|
| 9717 |
+
"loss": 0.45190566778182983,
|
| 9718 |
+
"step": 1380
|
| 9719 |
+
},
|
| 9720 |
+
{
|
| 9721 |
+
"epoch": 0.37820073942215526,
|
| 9722 |
+
"grad_norm": 0.4895637631416321,
|
| 9723 |
+
"learning_rate": 3.574709734646151e-05,
|
| 9724 |
+
"loss": 0.4647292494773865,
|
| 9725 |
+
"step": 1381
|
| 9726 |
+
},
|
| 9727 |
+
{
|
| 9728 |
+
"epoch": 0.3784745994796659,
|
| 9729 |
+
"grad_norm": 0.507930338382721,
|
| 9730 |
+
"learning_rate": 3.572707269335792e-05,
|
| 9731 |
+
"loss": 0.3979352116584778,
|
| 9732 |
+
"step": 1382
|
| 9733 |
+
},
|
| 9734 |
+
{
|
| 9735 |
+
"epoch": 0.3787484595371765,
|
| 9736 |
+
"grad_norm": 0.5358681678771973,
|
| 9737 |
+
"learning_rate": 3.570703960139345e-05,
|
| 9738 |
+
"loss": 0.5520524978637695,
|
| 9739 |
+
"step": 1383
|
| 9740 |
+
},
|
| 9741 |
+
{
|
| 9742 |
+
"epoch": 0.37902231959468713,
|
| 9743 |
+
"grad_norm": 0.4808170199394226,
|
| 9744 |
+
"learning_rate": 3.568699808632791e-05,
|
| 9745 |
+
"loss": 0.4019317626953125,
|
| 9746 |
+
"step": 1384
|
| 9747 |
+
},
|
| 9748 |
+
{
|
| 9749 |
+
"epoch": 0.37929617965219775,
|
| 9750 |
+
"grad_norm": 0.5156922340393066,
|
| 9751 |
+
"learning_rate": 3.5666948163927716e-05,
|
| 9752 |
+
"loss": 0.5159578323364258,
|
| 9753 |
+
"step": 1385
|
| 9754 |
+
},
|
| 9755 |
+
{
|
| 9756 |
+
"epoch": 0.3795700397097083,
|
| 9757 |
+
"grad_norm": 0.5078458189964294,
|
| 9758 |
+
"learning_rate": 3.5646889849965906e-05,
|
| 9759 |
+
"loss": 0.3799511194229126,
|
| 9760 |
+
"step": 1386
|
| 9761 |
+
},
|
| 9762 |
+
{
|
| 9763 |
+
"epoch": 0.37984389976721894,
|
| 9764 |
+
"grad_norm": 0.4816403388977051,
|
| 9765 |
+
"learning_rate": 3.562682316022211e-05,
|
| 9766 |
+
"loss": 0.4371201992034912,
|
| 9767 |
+
"step": 1387
|
| 9768 |
+
},
|
| 9769 |
+
{
|
| 9770 |
+
"epoch": 0.38011775982472956,
|
| 9771 |
+
"grad_norm": 0.47345370054244995,
|
| 9772 |
+
"learning_rate": 3.560674811048256e-05,
|
| 9773 |
+
"loss": 0.48072949051856995,
|
| 9774 |
+
"step": 1388
|
| 9775 |
+
},
|
| 9776 |
+
{
|
| 9777 |
+
"epoch": 0.3803916198822402,
|
| 9778 |
+
"grad_norm": 0.49592870473861694,
|
| 9779 |
+
"learning_rate": 3.558666471654007e-05,
|
| 9780 |
+
"loss": 0.4534415602684021,
|
| 9781 |
+
"step": 1389
|
| 9782 |
+
},
|
| 9783 |
+
{
|
| 9784 |
+
"epoch": 0.3806654799397508,
|
| 9785 |
+
"grad_norm": 0.5030218958854675,
|
| 9786 |
+
"learning_rate": 3.5566572994193994e-05,
|
| 9787 |
+
"loss": 0.4331713914871216,
|
| 9788 |
+
"step": 1390
|
| 9789 |
+
},
|
| 9790 |
+
{
|
| 9791 |
+
"epoch": 0.3809393399972614,
|
| 9792 |
+
"grad_norm": 0.4984970986843109,
|
| 9793 |
+
"learning_rate": 3.5546472959250263e-05,
|
| 9794 |
+
"loss": 0.4636586904525757,
|
| 9795 |
+
"step": 1391
|
| 9796 |
+
},
|
| 9797 |
+
{
|
| 9798 |
+
"epoch": 0.381213200054772,
|
| 9799 |
+
"grad_norm": 0.5149053931236267,
|
| 9800 |
+
"learning_rate": 3.552636462752132e-05,
|
| 9801 |
+
"loss": 0.4172360301017761,
|
| 9802 |
+
"step": 1392
|
| 9803 |
+
},
|
| 9804 |
+
{
|
| 9805 |
+
"epoch": 0.3814870601122826,
|
| 9806 |
+
"grad_norm": 0.488974004983902,
|
| 9807 |
+
"learning_rate": 3.550624801482617e-05,
|
| 9808 |
+
"loss": 0.4079588055610657,
|
| 9809 |
+
"step": 1393
|
| 9810 |
+
},
|
| 9811 |
+
{
|
| 9812 |
+
"epoch": 0.38176092016979324,
|
| 9813 |
+
"grad_norm": 0.48027437925338745,
|
| 9814 |
+
"learning_rate": 3.548612313699029e-05,
|
| 9815 |
+
"loss": 0.35523316264152527,
|
| 9816 |
+
"step": 1394
|
| 9817 |
+
},
|
| 9818 |
+
{
|
| 9819 |
+
"epoch": 0.38203478022730386,
|
| 9820 |
+
"grad_norm": 0.5580093264579773,
|
| 9821 |
+
"learning_rate": 3.546599000984571e-05,
|
| 9822 |
+
"loss": 0.39263999462127686,
|
| 9823 |
+
"step": 1395
|
| 9824 |
+
},
|
| 9825 |
+
{
|
| 9826 |
+
"epoch": 0.3823086402848145,
|
| 9827 |
+
"grad_norm": 0.6194579005241394,
|
| 9828 |
+
"learning_rate": 3.54458486492309e-05,
|
| 9829 |
+
"loss": 0.40594491362571716,
|
| 9830 |
+
"step": 1396
|
| 9831 |
+
},
|
| 9832 |
+
{
|
| 9833 |
+
"epoch": 0.38258250034232505,
|
| 9834 |
+
"grad_norm": 0.5600871443748474,
|
| 9835 |
+
"learning_rate": 3.542569907099085e-05,
|
| 9836 |
+
"loss": 0.4134121537208557,
|
| 9837 |
+
"step": 1397
|
| 9838 |
+
},
|
| 9839 |
+
{
|
| 9840 |
+
"epoch": 0.38285636039983567,
|
| 9841 |
+
"grad_norm": 0.4755885899066925,
|
| 9842 |
+
"learning_rate": 3.540554129097697e-05,
|
| 9843 |
+
"loss": 0.3903571367263794,
|
| 9844 |
+
"step": 1398
|
| 9845 |
+
},
|
| 9846 |
+
{
|
| 9847 |
+
"epoch": 0.3831302204573463,
|
| 9848 |
+
"grad_norm": 0.4537702202796936,
|
| 9849 |
+
"learning_rate": 3.5385375325047166e-05,
|
| 9850 |
+
"loss": 0.49829381704330444,
|
| 9851 |
+
"step": 1399
|
| 9852 |
+
},
|
| 9853 |
+
{
|
| 9854 |
+
"epoch": 0.3834040805148569,
|
| 9855 |
+
"grad_norm": 0.48542389273643494,
|
| 9856 |
+
"learning_rate": 3.536520118906576e-05,
|
| 9857 |
+
"loss": 0.41858750581741333,
|
| 9858 |
+
"step": 1400
|
| 9859 |
+
},
|
| 9860 |
+
{
|
| 9861 |
+
"epoch": 0.3834040805148569,
|
| 9862 |
+
"eval_loss": 0.44383540749549866,
|
| 9863 |
+
"eval_runtime": 32.6636,
|
| 9864 |
+
"eval_samples_per_second": 6.123,
|
| 9865 |
+
"eval_steps_per_second": 0.765,
|
| 9866 |
+
"step": 1400
|
| 9867 |
}
|
| 9868 |
],
|
| 9869 |
"logging_steps": 1,
|
|
|
|
| 9892 |
"attributes": {}
|
| 9893 |
}
|
| 9894 |
},
|
| 9895 |
+
"total_flos": 1.8970933657285427e+17,
|
| 9896 |
"train_batch_size": 1,
|
| 9897 |
"trial_name": null,
|
| 9898 |
"trial_params": null
|