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 1000
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 sha256:69537360ab95494754b43d6d927cf6daf98fba7b1652300d9ae80777ae978a30
|
| 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 sha256:5b7bd3db4a8510722f32414fd9ffb78cb6b07a9c1f1b4bbad0575b2d0df09582
|
| 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:f8de4ff5d10c1aace494e653126f2accd945123e5df3576d2181544e54d2e856
|
| 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 sha256:5a4f8f5a551f44f749bfa11cf8ff395e7a9ebdd5a9c40df0f7fb3ddc97ae3e76
|
| 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 sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
|
| 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 sha256:7d50edbd83c9559b841349f6b5c3f37145279033d4d5d694b312f396befc5ee7
|
| 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,
|
|
@@ -5640,6 +5640,1414 @@
|
|
| 5640 |
"eval_samples_per_second": 6.168,
|
| 5641 |
"eval_steps_per_second": 0.771,
|
| 5642 |
"step": 800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5643 |
}
|
| 5644 |
],
|
| 5645 |
"logging_steps": 1,
|
|
@@ -5668,7 +7076,7 @@
|
|
| 5668 |
"attributes": {}
|
| 5669 |
}
|
| 5670 |
},
|
| 5671 |
-
"total_flos": 1.
|
| 5672 |
"train_batch_size": 1,
|
| 5673 |
"trial_name": null,
|
| 5674 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 1000,
|
| 3 |
+
"best_metric": 0.4585808515548706,
|
| 4 |
+
"best_model_checkpoint": "/kaggle/working/run/checkpoint-1000",
|
| 5 |
+
"epoch": 0.2738600575106121,
|
| 6 |
"eval_steps": 200,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5640 |
"eval_samples_per_second": 6.168,
|
| 5641 |
"eval_steps_per_second": 0.771,
|
| 5642 |
"step": 800
|
| 5643 |
+
},
|
| 5644 |
+
{
|
| 5645 |
+
"epoch": 0.21936190606600028,
|
| 5646 |
+
"grad_norm": 0.5164449214935303,
|
| 5647 |
+
"learning_rate": 4.546253666446484e-05,
|
| 5648 |
+
"loss": 0.5424915552139282,
|
| 5649 |
+
"step": 801
|
| 5650 |
+
},
|
| 5651 |
+
{
|
| 5652 |
+
"epoch": 0.21963576612351088,
|
| 5653 |
+
"grad_norm": 0.5151954293251038,
|
| 5654 |
+
"learning_rate": 4.544978963565703e-05,
|
| 5655 |
+
"loss": 0.49415168166160583,
|
| 5656 |
+
"step": 802
|
| 5657 |
+
},
|
| 5658 |
+
{
|
| 5659 |
+
"epoch": 0.2199096261810215,
|
| 5660 |
+
"grad_norm": 0.46886005997657776,
|
| 5661 |
+
"learning_rate": 4.5437026519242245e-05,
|
| 5662 |
+
"loss": 0.4499443769454956,
|
| 5663 |
+
"step": 803
|
| 5664 |
+
},
|
| 5665 |
+
{
|
| 5666 |
+
"epoch": 0.22018348623853212,
|
| 5667 |
+
"grad_norm": 0.4735027551651001,
|
| 5668 |
+
"learning_rate": 4.542424732526105e-05,
|
| 5669 |
+
"loss": 0.45108669996261597,
|
| 5670 |
+
"step": 804
|
| 5671 |
+
},
|
| 5672 |
+
{
|
| 5673 |
+
"epoch": 0.22045734629604272,
|
| 5674 |
+
"grad_norm": 0.46727678179740906,
|
| 5675 |
+
"learning_rate": 4.541145206376671e-05,
|
| 5676 |
+
"loss": 0.4407161474227905,
|
| 5677 |
+
"step": 805
|
| 5678 |
+
},
|
| 5679 |
+
{
|
| 5680 |
+
"epoch": 0.22073120635355334,
|
| 5681 |
+
"grad_norm": 0.5024569630622864,
|
| 5682 |
+
"learning_rate": 4.5398640744825106e-05,
|
| 5683 |
+
"loss": 0.5656187534332275,
|
| 5684 |
+
"step": 806
|
| 5685 |
+
},
|
| 5686 |
+
{
|
| 5687 |
+
"epoch": 0.22100506641106393,
|
| 5688 |
+
"grad_norm": 0.5743609666824341,
|
| 5689 |
+
"learning_rate": 4.538581337851474e-05,
|
| 5690 |
+
"loss": 0.5366308689117432,
|
| 5691 |
+
"step": 807
|
| 5692 |
+
},
|
| 5693 |
+
{
|
| 5694 |
+
"epoch": 0.22127892646857455,
|
| 5695 |
+
"grad_norm": 0.5590578317642212,
|
| 5696 |
+
"learning_rate": 4.5372969974926746e-05,
|
| 5697 |
+
"loss": 0.4524023234844208,
|
| 5698 |
+
"step": 808
|
| 5699 |
+
},
|
| 5700 |
+
{
|
| 5701 |
+
"epoch": 0.22155278652608518,
|
| 5702 |
+
"grad_norm": 0.48998427391052246,
|
| 5703 |
+
"learning_rate": 4.5360110544164886e-05,
|
| 5704 |
+
"loss": 0.40552079677581787,
|
| 5705 |
+
"step": 809
|
| 5706 |
+
},
|
| 5707 |
+
{
|
| 5708 |
+
"epoch": 0.22182664658359577,
|
| 5709 |
+
"grad_norm": 0.4898631274700165,
|
| 5710 |
+
"learning_rate": 4.534723509634552e-05,
|
| 5711 |
+
"loss": 0.4591464400291443,
|
| 5712 |
+
"step": 810
|
| 5713 |
+
},
|
| 5714 |
+
{
|
| 5715 |
+
"epoch": 0.2221005066411064,
|
| 5716 |
+
"grad_norm": 0.47904065251350403,
|
| 5717 |
+
"learning_rate": 4.533434364159761e-05,
|
| 5718 |
+
"loss": 0.4144124388694763,
|
| 5719 |
+
"step": 811
|
| 5720 |
+
},
|
| 5721 |
+
{
|
| 5722 |
+
"epoch": 0.22237436669861702,
|
| 5723 |
+
"grad_norm": 0.47434353828430176,
|
| 5724 |
+
"learning_rate": 4.53214361900627e-05,
|
| 5725 |
+
"loss": 0.4588753879070282,
|
| 5726 |
+
"step": 812
|
| 5727 |
+
},
|
| 5728 |
+
{
|
| 5729 |
+
"epoch": 0.2226482267561276,
|
| 5730 |
+
"grad_norm": 0.4803418517112732,
|
| 5731 |
+
"learning_rate": 4.5308512751894946e-05,
|
| 5732 |
+
"loss": 0.47940611839294434,
|
| 5733 |
+
"step": 813
|
| 5734 |
+
},
|
| 5735 |
+
{
|
| 5736 |
+
"epoch": 0.22292208681363823,
|
| 5737 |
+
"grad_norm": 0.5006958842277527,
|
| 5738 |
+
"learning_rate": 4.529557333726106e-05,
|
| 5739 |
+
"loss": 0.4377329349517822,
|
| 5740 |
+
"step": 814
|
| 5741 |
+
},
|
| 5742 |
+
{
|
| 5743 |
+
"epoch": 0.22319594687114885,
|
| 5744 |
+
"grad_norm": 0.4626988470554352,
|
| 5745 |
+
"learning_rate": 4.528261795634032e-05,
|
| 5746 |
+
"loss": 0.48726943135261536,
|
| 5747 |
+
"step": 815
|
| 5748 |
+
},
|
| 5749 |
+
{
|
| 5750 |
+
"epoch": 0.22346980692865945,
|
| 5751 |
+
"grad_norm": 0.46488523483276367,
|
| 5752 |
+
"learning_rate": 4.526964661932457e-05,
|
| 5753 |
+
"loss": 0.4811323881149292,
|
| 5754 |
+
"step": 816
|
| 5755 |
+
},
|
| 5756 |
+
{
|
| 5757 |
+
"epoch": 0.22374366698617007,
|
| 5758 |
+
"grad_norm": 0.5012717843055725,
|
| 5759 |
+
"learning_rate": 4.525665933641821e-05,
|
| 5760 |
+
"loss": 0.5165424346923828,
|
| 5761 |
+
"step": 817
|
| 5762 |
+
},
|
| 5763 |
+
{
|
| 5764 |
+
"epoch": 0.2240175270436807,
|
| 5765 |
+
"grad_norm": 0.45915117859840393,
|
| 5766 |
+
"learning_rate": 4.524365611783818e-05,
|
| 5767 |
+
"loss": 0.42196008563041687,
|
| 5768 |
+
"step": 818
|
| 5769 |
+
},
|
| 5770 |
+
{
|
| 5771 |
+
"epoch": 0.2242913871011913,
|
| 5772 |
+
"grad_norm": 0.446510374546051,
|
| 5773 |
+
"learning_rate": 4.5230636973813964e-05,
|
| 5774 |
+
"loss": 0.5090854167938232,
|
| 5775 |
+
"step": 819
|
| 5776 |
+
},
|
| 5777 |
+
{
|
| 5778 |
+
"epoch": 0.2245652471587019,
|
| 5779 |
+
"grad_norm": 0.45126622915267944,
|
| 5780 |
+
"learning_rate": 4.521760191458756e-05,
|
| 5781 |
+
"loss": 0.4339040517807007,
|
| 5782 |
+
"step": 820
|
| 5783 |
+
},
|
| 5784 |
+
{
|
| 5785 |
+
"epoch": 0.2248391072162125,
|
| 5786 |
+
"grad_norm": 0.5250347256660461,
|
| 5787 |
+
"learning_rate": 4.5204550950413495e-05,
|
| 5788 |
+
"loss": 0.49676966667175293,
|
| 5789 |
+
"step": 821
|
| 5790 |
+
},
|
| 5791 |
+
{
|
| 5792 |
+
"epoch": 0.22511296727372312,
|
| 5793 |
+
"grad_norm": 0.5251480340957642,
|
| 5794 |
+
"learning_rate": 4.519148409155881e-05,
|
| 5795 |
+
"loss": 0.4818600118160248,
|
| 5796 |
+
"step": 822
|
| 5797 |
+
},
|
| 5798 |
+
{
|
| 5799 |
+
"epoch": 0.22538682733123375,
|
| 5800 |
+
"grad_norm": 0.5018237233161926,
|
| 5801 |
+
"learning_rate": 4.517840134830305e-05,
|
| 5802 |
+
"loss": 0.42520880699157715,
|
| 5803 |
+
"step": 823
|
| 5804 |
+
},
|
| 5805 |
+
{
|
| 5806 |
+
"epoch": 0.22566068738874434,
|
| 5807 |
+
"grad_norm": 0.47414010763168335,
|
| 5808 |
+
"learning_rate": 4.516530273093825e-05,
|
| 5809 |
+
"loss": 0.442179799079895,
|
| 5810 |
+
"step": 824
|
| 5811 |
+
},
|
| 5812 |
+
{
|
| 5813 |
+
"epoch": 0.22593454744625496,
|
| 5814 |
+
"grad_norm": 0.517415463924408,
|
| 5815 |
+
"learning_rate": 4.515218824976895e-05,
|
| 5816 |
+
"loss": 0.5362551212310791,
|
| 5817 |
+
"step": 825
|
| 5818 |
+
},
|
| 5819 |
+
{
|
| 5820 |
+
"epoch": 0.22620840750376559,
|
| 5821 |
+
"grad_norm": 0.4961589574813843,
|
| 5822 |
+
"learning_rate": 4.5139057915112135e-05,
|
| 5823 |
+
"loss": 0.4135134220123291,
|
| 5824 |
+
"step": 826
|
| 5825 |
+
},
|
| 5826 |
+
{
|
| 5827 |
+
"epoch": 0.22648226756127618,
|
| 5828 |
+
"grad_norm": 0.5108779072761536,
|
| 5829 |
+
"learning_rate": 4.51259117372973e-05,
|
| 5830 |
+
"loss": 0.4321501553058624,
|
| 5831 |
+
"step": 827
|
| 5832 |
+
},
|
| 5833 |
+
{
|
| 5834 |
+
"epoch": 0.2267561276187868,
|
| 5835 |
+
"grad_norm": 0.4643439054489136,
|
| 5836 |
+
"learning_rate": 4.5112749726666374e-05,
|
| 5837 |
+
"loss": 0.3634212017059326,
|
| 5838 |
+
"step": 828
|
| 5839 |
+
},
|
| 5840 |
+
{
|
| 5841 |
+
"epoch": 0.22702998767629742,
|
| 5842 |
+
"grad_norm": 0.435367226600647,
|
| 5843 |
+
"learning_rate": 4.509957189357377e-05,
|
| 5844 |
+
"loss": 0.3910942077636719,
|
| 5845 |
+
"step": 829
|
| 5846 |
+
},
|
| 5847 |
+
{
|
| 5848 |
+
"epoch": 0.22730384773380802,
|
| 5849 |
+
"grad_norm": 0.44187021255493164,
|
| 5850 |
+
"learning_rate": 4.5086378248386316e-05,
|
| 5851 |
+
"loss": 0.4487096667289734,
|
| 5852 |
+
"step": 830
|
| 5853 |
+
},
|
| 5854 |
+
{
|
| 5855 |
+
"epoch": 0.22757770779131864,
|
| 5856 |
+
"grad_norm": 0.49202170968055725,
|
| 5857 |
+
"learning_rate": 4.507316880148332e-05,
|
| 5858 |
+
"loss": 0.4304705560207367,
|
| 5859 |
+
"step": 831
|
| 5860 |
+
},
|
| 5861 |
+
{
|
| 5862 |
+
"epoch": 0.22785156784882926,
|
| 5863 |
+
"grad_norm": 0.4972386360168457,
|
| 5864 |
+
"learning_rate": 4.5059943563256476e-05,
|
| 5865 |
+
"loss": 0.5486693382263184,
|
| 5866 |
+
"step": 832
|
| 5867 |
+
},
|
| 5868 |
+
{
|
| 5869 |
+
"epoch": 0.22812542790633986,
|
| 5870 |
+
"grad_norm": 0.4814002513885498,
|
| 5871 |
+
"learning_rate": 4.5046702544109926e-05,
|
| 5872 |
+
"loss": 0.48895102739334106,
|
| 5873 |
+
"step": 833
|
| 5874 |
+
},
|
| 5875 |
+
{
|
| 5876 |
+
"epoch": 0.22839928796385048,
|
| 5877 |
+
"grad_norm": 0.4832276701927185,
|
| 5878 |
+
"learning_rate": 4.5033445754460226e-05,
|
| 5879 |
+
"loss": 0.4562426805496216,
|
| 5880 |
+
"step": 834
|
| 5881 |
+
},
|
| 5882 |
+
{
|
| 5883 |
+
"epoch": 0.22867314802136107,
|
| 5884 |
+
"grad_norm": 0.5108863115310669,
|
| 5885 |
+
"learning_rate": 4.502017320473634e-05,
|
| 5886 |
+
"loss": 0.4954681694507599,
|
| 5887 |
+
"step": 835
|
| 5888 |
+
},
|
| 5889 |
+
{
|
| 5890 |
+
"epoch": 0.2289470080788717,
|
| 5891 |
+
"grad_norm": 0.49772900342941284,
|
| 5892 |
+
"learning_rate": 4.500688490537961e-05,
|
| 5893 |
+
"loss": 0.4699568748474121,
|
| 5894 |
+
"step": 836
|
| 5895 |
+
},
|
| 5896 |
+
{
|
| 5897 |
+
"epoch": 0.22922086813638232,
|
| 5898 |
+
"grad_norm": 0.47905483841896057,
|
| 5899 |
+
"learning_rate": 4.499358086684381e-05,
|
| 5900 |
+
"loss": 0.4716885983943939,
|
| 5901 |
+
"step": 837
|
| 5902 |
+
},
|
| 5903 |
+
{
|
| 5904 |
+
"epoch": 0.2294947281938929,
|
| 5905 |
+
"grad_norm": 0.47480443120002747,
|
| 5906 |
+
"learning_rate": 4.498026109959504e-05,
|
| 5907 |
+
"loss": 0.5008630752563477,
|
| 5908 |
+
"step": 838
|
| 5909 |
+
},
|
| 5910 |
+
{
|
| 5911 |
+
"epoch": 0.22976858825140353,
|
| 5912 |
+
"grad_norm": 0.43639075756073,
|
| 5913 |
+
"learning_rate": 4.496692561411182e-05,
|
| 5914 |
+
"loss": 0.39716637134552,
|
| 5915 |
+
"step": 839
|
| 5916 |
+
},
|
| 5917 |
+
{
|
| 5918 |
+
"epoch": 0.23004244830891415,
|
| 5919 |
+
"grad_norm": 0.44964882731437683,
|
| 5920 |
+
"learning_rate": 4.495357442088501e-05,
|
| 5921 |
+
"loss": 0.41342657804489136,
|
| 5922 |
+
"step": 840
|
| 5923 |
+
},
|
| 5924 |
+
{
|
| 5925 |
+
"epoch": 0.23031630836642475,
|
| 5926 |
+
"grad_norm": 0.49829477071762085,
|
| 5927 |
+
"learning_rate": 4.494020753041785e-05,
|
| 5928 |
+
"loss": 0.5038270950317383,
|
| 5929 |
+
"step": 841
|
| 5930 |
+
},
|
| 5931 |
+
{
|
| 5932 |
+
"epoch": 0.23059016842393537,
|
| 5933 |
+
"grad_norm": 0.4703025817871094,
|
| 5934 |
+
"learning_rate": 4.49268249532259e-05,
|
| 5935 |
+
"loss": 0.458679735660553,
|
| 5936 |
+
"step": 842
|
| 5937 |
+
},
|
| 5938 |
+
{
|
| 5939 |
+
"epoch": 0.230864028481446,
|
| 5940 |
+
"grad_norm": 0.44375014305114746,
|
| 5941 |
+
"learning_rate": 4.4913426699837066e-05,
|
| 5942 |
+
"loss": 0.39859527349472046,
|
| 5943 |
+
"step": 843
|
| 5944 |
+
},
|
| 5945 |
+
{
|
| 5946 |
+
"epoch": 0.2311378885389566,
|
| 5947 |
+
"grad_norm": 0.4630894958972931,
|
| 5948 |
+
"learning_rate": 4.490001278079162e-05,
|
| 5949 |
+
"loss": 0.4551583528518677,
|
| 5950 |
+
"step": 844
|
| 5951 |
+
},
|
| 5952 |
+
{
|
| 5953 |
+
"epoch": 0.2314117485964672,
|
| 5954 |
+
"grad_norm": 0.4685797393321991,
|
| 5955 |
+
"learning_rate": 4.488658320664212e-05,
|
| 5956 |
+
"loss": 0.461830198764801,
|
| 5957 |
+
"step": 845
|
| 5958 |
+
},
|
| 5959 |
+
{
|
| 5960 |
+
"epoch": 0.2316856086539778,
|
| 5961 |
+
"grad_norm": 0.4922153651714325,
|
| 5962 |
+
"learning_rate": 4.487313798795346e-05,
|
| 5963 |
+
"loss": 0.4845235347747803,
|
| 5964 |
+
"step": 846
|
| 5965 |
+
},
|
| 5966 |
+
{
|
| 5967 |
+
"epoch": 0.23195946871148843,
|
| 5968 |
+
"grad_norm": 0.552527666091919,
|
| 5969 |
+
"learning_rate": 4.485967713530281e-05,
|
| 5970 |
+
"loss": 0.574547529220581,
|
| 5971 |
+
"step": 847
|
| 5972 |
+
},
|
| 5973 |
+
{
|
| 5974 |
+
"epoch": 0.23223332876899905,
|
| 5975 |
+
"grad_norm": 0.5694705247879028,
|
| 5976 |
+
"learning_rate": 4.48462006592797e-05,
|
| 5977 |
+
"loss": 0.6474007368087769,
|
| 5978 |
+
"step": 848
|
| 5979 |
+
},
|
| 5980 |
+
{
|
| 5981 |
+
"epoch": 0.23250718882650964,
|
| 5982 |
+
"grad_norm": 0.4327588379383087,
|
| 5983 |
+
"learning_rate": 4.483270857048588e-05,
|
| 5984 |
+
"loss": 0.4546425938606262,
|
| 5985 |
+
"step": 849
|
| 5986 |
+
},
|
| 5987 |
+
{
|
| 5988 |
+
"epoch": 0.23278104888402026,
|
| 5989 |
+
"grad_norm": 0.5016552209854126,
|
| 5990 |
+
"learning_rate": 4.481920087953544e-05,
|
| 5991 |
+
"loss": 0.5421531200408936,
|
| 5992 |
+
"step": 850
|
| 5993 |
+
},
|
| 5994 |
+
{
|
| 5995 |
+
"epoch": 0.23305490894153089,
|
| 5996 |
+
"grad_norm": 0.7241258025169373,
|
| 5997 |
+
"learning_rate": 4.480567759705471e-05,
|
| 5998 |
+
"loss": 0.45423275232315063,
|
| 5999 |
+
"step": 851
|
| 6000 |
+
},
|
| 6001 |
+
{
|
| 6002 |
+
"epoch": 0.23332876899904148,
|
| 6003 |
+
"grad_norm": 0.4665621817111969,
|
| 6004 |
+
"learning_rate": 4.479213873368229e-05,
|
| 6005 |
+
"loss": 0.5251611471176147,
|
| 6006 |
+
"step": 852
|
| 6007 |
+
},
|
| 6008 |
+
{
|
| 6009 |
+
"epoch": 0.2336026290565521,
|
| 6010 |
+
"grad_norm": 0.5046409964561462,
|
| 6011 |
+
"learning_rate": 4.477858430006906e-05,
|
| 6012 |
+
"loss": 0.48702311515808105,
|
| 6013 |
+
"step": 853
|
| 6014 |
+
},
|
| 6015 |
+
{
|
| 6016 |
+
"epoch": 0.23387648911406272,
|
| 6017 |
+
"grad_norm": 0.5147388577461243,
|
| 6018 |
+
"learning_rate": 4.476501430687812e-05,
|
| 6019 |
+
"loss": 0.42573967576026917,
|
| 6020 |
+
"step": 854
|
| 6021 |
+
},
|
| 6022 |
+
{
|
| 6023 |
+
"epoch": 0.23415034917157332,
|
| 6024 |
+
"grad_norm": 0.4944581389427185,
|
| 6025 |
+
"learning_rate": 4.475142876478482e-05,
|
| 6026 |
+
"loss": 0.4149600863456726,
|
| 6027 |
+
"step": 855
|
| 6028 |
+
},
|
| 6029 |
+
{
|
| 6030 |
+
"epoch": 0.23442420922908394,
|
| 6031 |
+
"grad_norm": 0.5863413214683533,
|
| 6032 |
+
"learning_rate": 4.473782768447675e-05,
|
| 6033 |
+
"loss": 0.4757280647754669,
|
| 6034 |
+
"step": 856
|
| 6035 |
+
},
|
| 6036 |
+
{
|
| 6037 |
+
"epoch": 0.23469806928659456,
|
| 6038 |
+
"grad_norm": 0.4538358151912689,
|
| 6039 |
+
"learning_rate": 4.472421107665372e-05,
|
| 6040 |
+
"loss": 0.3579934239387512,
|
| 6041 |
+
"step": 857
|
| 6042 |
+
},
|
| 6043 |
+
{
|
| 6044 |
+
"epoch": 0.23497192934410516,
|
| 6045 |
+
"grad_norm": 0.49543511867523193,
|
| 6046 |
+
"learning_rate": 4.4710578952027755e-05,
|
| 6047 |
+
"loss": 0.48725974559783936,
|
| 6048 |
+
"step": 858
|
| 6049 |
+
},
|
| 6050 |
+
{
|
| 6051 |
+
"epoch": 0.23524578940161578,
|
| 6052 |
+
"grad_norm": 0.5261022448539734,
|
| 6053 |
+
"learning_rate": 4.469693132132308e-05,
|
| 6054 |
+
"loss": 0.5929657220840454,
|
| 6055 |
+
"step": 859
|
| 6056 |
+
},
|
| 6057 |
+
{
|
| 6058 |
+
"epoch": 0.23551964945912637,
|
| 6059 |
+
"grad_norm": 0.4711715281009674,
|
| 6060 |
+
"learning_rate": 4.4683268195276126e-05,
|
| 6061 |
+
"loss": 0.4069840908050537,
|
| 6062 |
+
"step": 860
|
| 6063 |
+
},
|
| 6064 |
+
{
|
| 6065 |
+
"epoch": 0.235793509516637,
|
| 6066 |
+
"grad_norm": 0.5164196491241455,
|
| 6067 |
+
"learning_rate": 4.466958958463552e-05,
|
| 6068 |
+
"loss": 0.36889225244522095,
|
| 6069 |
+
"step": 861
|
| 6070 |
+
},
|
| 6071 |
+
{
|
| 6072 |
+
"epoch": 0.23606736957414762,
|
| 6073 |
+
"grad_norm": 0.6555010080337524,
|
| 6074 |
+
"learning_rate": 4.465589550016206e-05,
|
| 6075 |
+
"loss": 0.518142819404602,
|
| 6076 |
+
"step": 862
|
| 6077 |
+
},
|
| 6078 |
+
{
|
| 6079 |
+
"epoch": 0.2363412296316582,
|
| 6080 |
+
"grad_norm": 0.5102429389953613,
|
| 6081 |
+
"learning_rate": 4.4642185952628706e-05,
|
| 6082 |
+
"loss": 0.4534635543823242,
|
| 6083 |
+
"step": 863
|
| 6084 |
+
},
|
| 6085 |
+
{
|
| 6086 |
+
"epoch": 0.23661508968916883,
|
| 6087 |
+
"grad_norm": 0.43155166506767273,
|
| 6088 |
+
"learning_rate": 4.462846095282062e-05,
|
| 6089 |
+
"loss": 0.39799514412879944,
|
| 6090 |
+
"step": 864
|
| 6091 |
+
},
|
| 6092 |
+
{
|
| 6093 |
+
"epoch": 0.23688894974667946,
|
| 6094 |
+
"grad_norm": 0.4947545528411865,
|
| 6095 |
+
"learning_rate": 4.461472051153507e-05,
|
| 6096 |
+
"loss": 0.48190534114837646,
|
| 6097 |
+
"step": 865
|
| 6098 |
+
},
|
| 6099 |
+
{
|
| 6100 |
+
"epoch": 0.23716280980419005,
|
| 6101 |
+
"grad_norm": 0.4311656653881073,
|
| 6102 |
+
"learning_rate": 4.460096463958151e-05,
|
| 6103 |
+
"loss": 0.43214741349220276,
|
| 6104 |
+
"step": 866
|
| 6105 |
+
},
|
| 6106 |
+
{
|
| 6107 |
+
"epoch": 0.23743666986170067,
|
| 6108 |
+
"grad_norm": 0.4407433867454529,
|
| 6109 |
+
"learning_rate": 4.458719334778153e-05,
|
| 6110 |
+
"loss": 0.4846187233924866,
|
| 6111 |
+
"step": 867
|
| 6112 |
+
},
|
| 6113 |
+
{
|
| 6114 |
+
"epoch": 0.2377105299192113,
|
| 6115 |
+
"grad_norm": 0.4896114766597748,
|
| 6116 |
+
"learning_rate": 4.457340664696883e-05,
|
| 6117 |
+
"loss": 0.3969525694847107,
|
| 6118 |
+
"step": 868
|
| 6119 |
+
},
|
| 6120 |
+
{
|
| 6121 |
+
"epoch": 0.2379843899767219,
|
| 6122 |
+
"grad_norm": 0.47406691312789917,
|
| 6123 |
+
"learning_rate": 4.4559604547989256e-05,
|
| 6124 |
+
"loss": 0.3800327181816101,
|
| 6125 |
+
"step": 869
|
| 6126 |
+
},
|
| 6127 |
+
{
|
| 6128 |
+
"epoch": 0.2382582500342325,
|
| 6129 |
+
"grad_norm": 0.5313331484794617,
|
| 6130 |
+
"learning_rate": 4.454578706170075e-05,
|
| 6131 |
+
"loss": 0.4895760715007782,
|
| 6132 |
+
"step": 870
|
| 6133 |
+
},
|
| 6134 |
+
{
|
| 6135 |
+
"epoch": 0.23853211009174313,
|
| 6136 |
+
"grad_norm": 0.49940329790115356,
|
| 6137 |
+
"learning_rate": 4.453195419897336e-05,
|
| 6138 |
+
"loss": 0.4345249831676483,
|
| 6139 |
+
"step": 871
|
| 6140 |
+
},
|
| 6141 |
+
{
|
| 6142 |
+
"epoch": 0.23880597014925373,
|
| 6143 |
+
"grad_norm": 0.5000454783439636,
|
| 6144 |
+
"learning_rate": 4.451810597068923e-05,
|
| 6145 |
+
"loss": 0.45451635122299194,
|
| 6146 |
+
"step": 872
|
| 6147 |
+
},
|
| 6148 |
+
{
|
| 6149 |
+
"epoch": 0.23907983020676435,
|
| 6150 |
+
"grad_norm": 0.4621257483959198,
|
| 6151 |
+
"learning_rate": 4.4504242387742615e-05,
|
| 6152 |
+
"loss": 0.41027265787124634,
|
| 6153 |
+
"step": 873
|
| 6154 |
+
},
|
| 6155 |
+
{
|
| 6156 |
+
"epoch": 0.23935369026427494,
|
| 6157 |
+
"grad_norm": 0.45436975359916687,
|
| 6158 |
+
"learning_rate": 4.449036346103982e-05,
|
| 6159 |
+
"loss": 0.45140087604522705,
|
| 6160 |
+
"step": 874
|
| 6161 |
+
},
|
| 6162 |
+
{
|
| 6163 |
+
"epoch": 0.23962755032178557,
|
| 6164 |
+
"grad_norm": 0.4544520974159241,
|
| 6165 |
+
"learning_rate": 4.4476469201499227e-05,
|
| 6166 |
+
"loss": 0.467523992061615,
|
| 6167 |
+
"step": 875
|
| 6168 |
+
},
|
| 6169 |
+
{
|
| 6170 |
+
"epoch": 0.2399014103792962,
|
| 6171 |
+
"grad_norm": 0.4578162729740143,
|
| 6172 |
+
"learning_rate": 4.4462559620051304e-05,
|
| 6173 |
+
"loss": 0.40984243154525757,
|
| 6174 |
+
"step": 876
|
| 6175 |
+
},
|
| 6176 |
+
{
|
| 6177 |
+
"epoch": 0.24017527043680678,
|
| 6178 |
+
"grad_norm": 0.507501482963562,
|
| 6179 |
+
"learning_rate": 4.444863472763853e-05,
|
| 6180 |
+
"loss": 0.38438743352890015,
|
| 6181 |
+
"step": 877
|
| 6182 |
+
},
|
| 6183 |
+
{
|
| 6184 |
+
"epoch": 0.2404491304943174,
|
| 6185 |
+
"grad_norm": 0.4939959645271301,
|
| 6186 |
+
"learning_rate": 4.443469453521547e-05,
|
| 6187 |
+
"loss": 0.47073307633399963,
|
| 6188 |
+
"step": 878
|
| 6189 |
+
},
|
| 6190 |
+
{
|
| 6191 |
+
"epoch": 0.24072299055182803,
|
| 6192 |
+
"grad_norm": 0.5617396831512451,
|
| 6193 |
+
"learning_rate": 4.442073905374869e-05,
|
| 6194 |
+
"loss": 0.40917837619781494,
|
| 6195 |
+
"step": 879
|
| 6196 |
+
},
|
| 6197 |
+
{
|
| 6198 |
+
"epoch": 0.24099685060933862,
|
| 6199 |
+
"grad_norm": 0.531268298625946,
|
| 6200 |
+
"learning_rate": 4.440676829421683e-05,
|
| 6201 |
+
"loss": 0.5251165628433228,
|
| 6202 |
+
"step": 880
|
| 6203 |
+
},
|
| 6204 |
+
{
|
| 6205 |
+
"epoch": 0.24127071066684924,
|
| 6206 |
+
"grad_norm": 0.5080421566963196,
|
| 6207 |
+
"learning_rate": 4.43927822676105e-05,
|
| 6208 |
+
"loss": 0.3954085409641266,
|
| 6209 |
+
"step": 881
|
| 6210 |
+
},
|
| 6211 |
+
{
|
| 6212 |
+
"epoch": 0.24154457072435986,
|
| 6213 |
+
"grad_norm": 0.5350546836853027,
|
| 6214 |
+
"learning_rate": 4.4378780984932345e-05,
|
| 6215 |
+
"loss": 0.541843831539154,
|
| 6216 |
+
"step": 882
|
| 6217 |
+
},
|
| 6218 |
+
{
|
| 6219 |
+
"epoch": 0.24181843078187046,
|
| 6220 |
+
"grad_norm": 0.47216418385505676,
|
| 6221 |
+
"learning_rate": 4.4364764457197005e-05,
|
| 6222 |
+
"loss": 0.4581572711467743,
|
| 6223 |
+
"step": 883
|
| 6224 |
+
},
|
| 6225 |
+
{
|
| 6226 |
+
"epoch": 0.24209229083938108,
|
| 6227 |
+
"grad_norm": 0.48117968440055847,
|
| 6228 |
+
"learning_rate": 4.435073269543113e-05,
|
| 6229 |
+
"loss": 0.47916626930236816,
|
| 6230 |
+
"step": 884
|
| 6231 |
+
},
|
| 6232 |
+
{
|
| 6233 |
+
"epoch": 0.2423661508968917,
|
| 6234 |
+
"grad_norm": 0.5103263854980469,
|
| 6235 |
+
"learning_rate": 4.433668571067332e-05,
|
| 6236 |
+
"loss": 0.5413877964019775,
|
| 6237 |
+
"step": 885
|
| 6238 |
+
},
|
| 6239 |
+
{
|
| 6240 |
+
"epoch": 0.2426400109544023,
|
| 6241 |
+
"grad_norm": 0.45851409435272217,
|
| 6242 |
+
"learning_rate": 4.432262351397419e-05,
|
| 6243 |
+
"loss": 0.3875007629394531,
|
| 6244 |
+
"step": 886
|
| 6245 |
+
},
|
| 6246 |
+
{
|
| 6247 |
+
"epoch": 0.24291387101191292,
|
| 6248 |
+
"grad_norm": 0.46949756145477295,
|
| 6249 |
+
"learning_rate": 4.430854611639629e-05,
|
| 6250 |
+
"loss": 0.4141821265220642,
|
| 6251 |
+
"step": 887
|
| 6252 |
+
},
|
| 6253 |
+
{
|
| 6254 |
+
"epoch": 0.2431877310694235,
|
| 6255 |
+
"grad_norm": 0.5134388208389282,
|
| 6256 |
+
"learning_rate": 4.429445352901415e-05,
|
| 6257 |
+
"loss": 0.4096881151199341,
|
| 6258 |
+
"step": 888
|
| 6259 |
+
},
|
| 6260 |
+
{
|
| 6261 |
+
"epoch": 0.24346159112693413,
|
| 6262 |
+
"grad_norm": 0.5211209058761597,
|
| 6263 |
+
"learning_rate": 4.428034576291424e-05,
|
| 6264 |
+
"loss": 0.43444597721099854,
|
| 6265 |
+
"step": 889
|
| 6266 |
+
},
|
| 6267 |
+
{
|
| 6268 |
+
"epoch": 0.24373545118444476,
|
| 6269 |
+
"grad_norm": 0.46595892310142517,
|
| 6270 |
+
"learning_rate": 4.426622282919497e-05,
|
| 6271 |
+
"loss": 0.40927958488464355,
|
| 6272 |
+
"step": 890
|
| 6273 |
+
},
|
| 6274 |
+
{
|
| 6275 |
+
"epoch": 0.24400931124195535,
|
| 6276 |
+
"grad_norm": 0.47022342681884766,
|
| 6277 |
+
"learning_rate": 4.425208473896668e-05,
|
| 6278 |
+
"loss": 0.5499156713485718,
|
| 6279 |
+
"step": 891
|
| 6280 |
+
},
|
| 6281 |
+
{
|
| 6282 |
+
"epoch": 0.24428317129946597,
|
| 6283 |
+
"grad_norm": 0.5032419562339783,
|
| 6284 |
+
"learning_rate": 4.423793150335165e-05,
|
| 6285 |
+
"loss": 0.48762619495391846,
|
| 6286 |
+
"step": 892
|
| 6287 |
+
},
|
| 6288 |
+
{
|
| 6289 |
+
"epoch": 0.2445570313569766,
|
| 6290 |
+
"grad_norm": 0.48170772194862366,
|
| 6291 |
+
"learning_rate": 4.422376313348405e-05,
|
| 6292 |
+
"loss": 0.4457756280899048,
|
| 6293 |
+
"step": 893
|
| 6294 |
+
},
|
| 6295 |
+
{
|
| 6296 |
+
"epoch": 0.2448308914144872,
|
| 6297 |
+
"grad_norm": 0.4784587621688843,
|
| 6298 |
+
"learning_rate": 4.420957964050998e-05,
|
| 6299 |
+
"loss": 0.47510433197021484,
|
| 6300 |
+
"step": 894
|
| 6301 |
+
},
|
| 6302 |
+
{
|
| 6303 |
+
"epoch": 0.2451047514719978,
|
| 6304 |
+
"grad_norm": 0.5053473114967346,
|
| 6305 |
+
"learning_rate": 4.419538103558742e-05,
|
| 6306 |
+
"loss": 0.4737446904182434,
|
| 6307 |
+
"step": 895
|
| 6308 |
+
},
|
| 6309 |
+
{
|
| 6310 |
+
"epoch": 0.24537861152950843,
|
| 6311 |
+
"grad_norm": 0.47924986481666565,
|
| 6312 |
+
"learning_rate": 4.4181167329886244e-05,
|
| 6313 |
+
"loss": 0.47503411769866943,
|
| 6314 |
+
"step": 896
|
| 6315 |
+
},
|
| 6316 |
+
{
|
| 6317 |
+
"epoch": 0.24565247158701903,
|
| 6318 |
+
"grad_norm": 0.5334694385528564,
|
| 6319 |
+
"learning_rate": 4.4166938534588205e-05,
|
| 6320 |
+
"loss": 0.3836560547351837,
|
| 6321 |
+
"step": 897
|
| 6322 |
+
},
|
| 6323 |
+
{
|
| 6324 |
+
"epoch": 0.24592633164452965,
|
| 6325 |
+
"grad_norm": 0.5100763440132141,
|
| 6326 |
+
"learning_rate": 4.4152694660886925e-05,
|
| 6327 |
+
"loss": 0.4455469846725464,
|
| 6328 |
+
"step": 898
|
| 6329 |
+
},
|
| 6330 |
+
{
|
| 6331 |
+
"epoch": 0.24620019170204024,
|
| 6332 |
+
"grad_norm": 0.5079872012138367,
|
| 6333 |
+
"learning_rate": 4.41384357199879e-05,
|
| 6334 |
+
"loss": 0.4852294623851776,
|
| 6335 |
+
"step": 899
|
| 6336 |
+
},
|
| 6337 |
+
{
|
| 6338 |
+
"epoch": 0.24647405175955087,
|
| 6339 |
+
"grad_norm": 0.5404118299484253,
|
| 6340 |
+
"learning_rate": 4.4124161723108456e-05,
|
| 6341 |
+
"loss": 0.4704968333244324,
|
| 6342 |
+
"step": 900
|
| 6343 |
+
},
|
| 6344 |
+
{
|
| 6345 |
+
"epoch": 0.2467479118170615,
|
| 6346 |
+
"grad_norm": 0.5363520979881287,
|
| 6347 |
+
"learning_rate": 4.4109872681477796e-05,
|
| 6348 |
+
"loss": 0.3734534680843353,
|
| 6349 |
+
"step": 901
|
| 6350 |
+
},
|
| 6351 |
+
{
|
| 6352 |
+
"epoch": 0.24702177187457208,
|
| 6353 |
+
"grad_norm": 0.44693705439567566,
|
| 6354 |
+
"learning_rate": 4.409556860633692e-05,
|
| 6355 |
+
"loss": 0.4408601224422455,
|
| 6356 |
+
"step": 902
|
| 6357 |
+
},
|
| 6358 |
+
{
|
| 6359 |
+
"epoch": 0.2472956319320827,
|
| 6360 |
+
"grad_norm": 0.482719749212265,
|
| 6361 |
+
"learning_rate": 4.4081249508938684e-05,
|
| 6362 |
+
"loss": 0.46202486753463745,
|
| 6363 |
+
"step": 903
|
| 6364 |
+
},
|
| 6365 |
+
{
|
| 6366 |
+
"epoch": 0.24756949198959333,
|
| 6367 |
+
"grad_norm": 0.4959026873111725,
|
| 6368 |
+
"learning_rate": 4.406691540054775e-05,
|
| 6369 |
+
"loss": 0.3933960199356079,
|
| 6370 |
+
"step": 904
|
| 6371 |
+
},
|
| 6372 |
+
{
|
| 6373 |
+
"epoch": 0.24784335204710392,
|
| 6374 |
+
"grad_norm": 0.49528270959854126,
|
| 6375 |
+
"learning_rate": 4.405256629244059e-05,
|
| 6376 |
+
"loss": 0.5273135304450989,
|
| 6377 |
+
"step": 905
|
| 6378 |
+
},
|
| 6379 |
+
{
|
| 6380 |
+
"epoch": 0.24811721210461454,
|
| 6381 |
+
"grad_norm": 0.5212165713310242,
|
| 6382 |
+
"learning_rate": 4.403820219590548e-05,
|
| 6383 |
+
"loss": 0.5196756720542908,
|
| 6384 |
+
"step": 906
|
| 6385 |
+
},
|
| 6386 |
+
{
|
| 6387 |
+
"epoch": 0.24839107216212516,
|
| 6388 |
+
"grad_norm": 0.46359747648239136,
|
| 6389 |
+
"learning_rate": 4.4023823122242494e-05,
|
| 6390 |
+
"loss": 0.39512985944747925,
|
| 6391 |
+
"step": 907
|
| 6392 |
+
},
|
| 6393 |
+
{
|
| 6394 |
+
"epoch": 0.24866493221963576,
|
| 6395 |
+
"grad_norm": 0.44796088337898254,
|
| 6396 |
+
"learning_rate": 4.400942908276345e-05,
|
| 6397 |
+
"loss": 0.49632421135902405,
|
| 6398 |
+
"step": 908
|
| 6399 |
+
},
|
| 6400 |
+
{
|
| 6401 |
+
"epoch": 0.24893879227714638,
|
| 6402 |
+
"grad_norm": 0.4837903380393982,
|
| 6403 |
+
"learning_rate": 4.3995020088792e-05,
|
| 6404 |
+
"loss": 0.4446862041950226,
|
| 6405 |
+
"step": 909
|
| 6406 |
+
},
|
| 6407 |
+
{
|
| 6408 |
+
"epoch": 0.249212652334657,
|
| 6409 |
+
"grad_norm": 0.511445164680481,
|
| 6410 |
+
"learning_rate": 4.398059615166351e-05,
|
| 6411 |
+
"loss": 0.38483113050460815,
|
| 6412 |
+
"step": 910
|
| 6413 |
+
},
|
| 6414 |
+
{
|
| 6415 |
+
"epoch": 0.2494865123921676,
|
| 6416 |
+
"grad_norm": 0.44030988216400146,
|
| 6417 |
+
"learning_rate": 4.396615728272513e-05,
|
| 6418 |
+
"loss": 0.39433830976486206,
|
| 6419 |
+
"step": 911
|
| 6420 |
+
},
|
| 6421 |
+
{
|
| 6422 |
+
"epoch": 0.24976037244967822,
|
| 6423 |
+
"grad_norm": 0.5199800133705139,
|
| 6424 |
+
"learning_rate": 4.3951703493335735e-05,
|
| 6425 |
+
"loss": 0.39930349588394165,
|
| 6426 |
+
"step": 912
|
| 6427 |
+
},
|
| 6428 |
+
{
|
| 6429 |
+
"epoch": 0.2500342325071888,
|
| 6430 |
+
"grad_norm": 0.45036667585372925,
|
| 6431 |
+
"learning_rate": 4.393723479486595e-05,
|
| 6432 |
+
"loss": 0.4135085940361023,
|
| 6433 |
+
"step": 913
|
| 6434 |
+
},
|
| 6435 |
+
{
|
| 6436 |
+
"epoch": 0.25030809256469944,
|
| 6437 |
+
"grad_norm": 0.509091317653656,
|
| 6438 |
+
"learning_rate": 4.392275119869815e-05,
|
| 6439 |
+
"loss": 0.4960663914680481,
|
| 6440 |
+
"step": 914
|
| 6441 |
+
},
|
| 6442 |
+
{
|
| 6443 |
+
"epoch": 0.25058195262221006,
|
| 6444 |
+
"grad_norm": 0.49768900871276855,
|
| 6445 |
+
"learning_rate": 4.39082527162264e-05,
|
| 6446 |
+
"loss": 0.4079427123069763,
|
| 6447 |
+
"step": 915
|
| 6448 |
+
},
|
| 6449 |
+
{
|
| 6450 |
+
"epoch": 0.2508558126797207,
|
| 6451 |
+
"grad_norm": 0.4825962483882904,
|
| 6452 |
+
"learning_rate": 4.389373935885646e-05,
|
| 6453 |
+
"loss": 0.4101483225822449,
|
| 6454 |
+
"step": 916
|
| 6455 |
+
},
|
| 6456 |
+
{
|
| 6457 |
+
"epoch": 0.2511296727372313,
|
| 6458 |
+
"grad_norm": 0.502393901348114,
|
| 6459 |
+
"learning_rate": 4.387921113800584e-05,
|
| 6460 |
+
"loss": 0.53355473279953,
|
| 6461 |
+
"step": 917
|
| 6462 |
+
},
|
| 6463 |
+
{
|
| 6464 |
+
"epoch": 0.25140353279474187,
|
| 6465 |
+
"grad_norm": 0.46935588121414185,
|
| 6466 |
+
"learning_rate": 4.386466806510372e-05,
|
| 6467 |
+
"loss": 0.40464887022972107,
|
| 6468 |
+
"step": 918
|
| 6469 |
+
},
|
| 6470 |
+
{
|
| 6471 |
+
"epoch": 0.2516773928522525,
|
| 6472 |
+
"grad_norm": 0.6327604651451111,
|
| 6473 |
+
"learning_rate": 4.385011015159095e-05,
|
| 6474 |
+
"loss": 0.5299835801124573,
|
| 6475 |
+
"step": 919
|
| 6476 |
+
},
|
| 6477 |
+
{
|
| 6478 |
+
"epoch": 0.2519512529097631,
|
| 6479 |
+
"grad_norm": 0.5508708357810974,
|
| 6480 |
+
"learning_rate": 4.383553740892007e-05,
|
| 6481 |
+
"loss": 0.4272322952747345,
|
| 6482 |
+
"step": 920
|
| 6483 |
+
},
|
| 6484 |
+
{
|
| 6485 |
+
"epoch": 0.25222511296727373,
|
| 6486 |
+
"grad_norm": 0.5065593719482422,
|
| 6487 |
+
"learning_rate": 4.3820949848555296e-05,
|
| 6488 |
+
"loss": 0.46067407727241516,
|
| 6489 |
+
"step": 921
|
| 6490 |
+
},
|
| 6491 |
+
{
|
| 6492 |
+
"epoch": 0.25249897302478436,
|
| 6493 |
+
"grad_norm": 0.44506505131721497,
|
| 6494 |
+
"learning_rate": 4.380634748197247e-05,
|
| 6495 |
+
"loss": 0.44753000140190125,
|
| 6496 |
+
"step": 922
|
| 6497 |
+
},
|
| 6498 |
+
{
|
| 6499 |
+
"epoch": 0.2527728330822949,
|
| 6500 |
+
"grad_norm": 0.4918462932109833,
|
| 6501 |
+
"learning_rate": 4.379173032065912e-05,
|
| 6502 |
+
"loss": 0.5672247409820557,
|
| 6503 |
+
"step": 923
|
| 6504 |
+
},
|
| 6505 |
+
{
|
| 6506 |
+
"epoch": 0.25304669313980555,
|
| 6507 |
+
"grad_norm": 0.49254485964775085,
|
| 6508 |
+
"learning_rate": 4.377709837611438e-05,
|
| 6509 |
+
"loss": 0.36113977432250977,
|
| 6510 |
+
"step": 924
|
| 6511 |
+
},
|
| 6512 |
+
{
|
| 6513 |
+
"epoch": 0.25332055319731617,
|
| 6514 |
+
"grad_norm": 0.48449045419692993,
|
| 6515 |
+
"learning_rate": 4.376245165984903e-05,
|
| 6516 |
+
"loss": 0.5111361145973206,
|
| 6517 |
+
"step": 925
|
| 6518 |
+
},
|
| 6519 |
+
{
|
| 6520 |
+
"epoch": 0.2535944132548268,
|
| 6521 |
+
"grad_norm": 0.4383421242237091,
|
| 6522 |
+
"learning_rate": 4.374779018338548e-05,
|
| 6523 |
+
"loss": 0.4600907862186432,
|
| 6524 |
+
"step": 926
|
| 6525 |
+
},
|
| 6526 |
+
{
|
| 6527 |
+
"epoch": 0.2538682733123374,
|
| 6528 |
+
"grad_norm": 0.5262776613235474,
|
| 6529 |
+
"learning_rate": 4.373311395825772e-05,
|
| 6530 |
+
"loss": 0.44385844469070435,
|
| 6531 |
+
"step": 927
|
| 6532 |
+
},
|
| 6533 |
+
{
|
| 6534 |
+
"epoch": 0.25414213336984803,
|
| 6535 |
+
"grad_norm": 0.46543368697166443,
|
| 6536 |
+
"learning_rate": 4.371842299601138e-05,
|
| 6537 |
+
"loss": 0.4628157317638397,
|
| 6538 |
+
"step": 928
|
| 6539 |
+
},
|
| 6540 |
+
{
|
| 6541 |
+
"epoch": 0.2544159934273586,
|
| 6542 |
+
"grad_norm": 0.5236104726791382,
|
| 6543 |
+
"learning_rate": 4.370371730820365e-05,
|
| 6544 |
+
"loss": 0.4521007537841797,
|
| 6545 |
+
"step": 929
|
| 6546 |
+
},
|
| 6547 |
+
{
|
| 6548 |
+
"epoch": 0.2546898534848692,
|
| 6549 |
+
"grad_norm": 0.5251491665840149,
|
| 6550 |
+
"learning_rate": 4.3688996906403333e-05,
|
| 6551 |
+
"loss": 0.48008623719215393,
|
| 6552 |
+
"step": 930
|
| 6553 |
+
},
|
| 6554 |
+
{
|
| 6555 |
+
"epoch": 0.25496371354237984,
|
| 6556 |
+
"grad_norm": 0.48778876662254333,
|
| 6557 |
+
"learning_rate": 4.367426180219079e-05,
|
| 6558 |
+
"loss": 0.46159571409225464,
|
| 6559 |
+
"step": 931
|
| 6560 |
+
},
|
| 6561 |
+
{
|
| 6562 |
+
"epoch": 0.25523757359989047,
|
| 6563 |
+
"grad_norm": 0.4852117598056793,
|
| 6564 |
+
"learning_rate": 4.365951200715794e-05,
|
| 6565 |
+
"loss": 0.5507788062095642,
|
| 6566 |
+
"step": 932
|
| 6567 |
+
},
|
| 6568 |
+
{
|
| 6569 |
+
"epoch": 0.2555114336574011,
|
| 6570 |
+
"grad_norm": 0.4518265724182129,
|
| 6571 |
+
"learning_rate": 4.36447475329083e-05,
|
| 6572 |
+
"loss": 0.42873501777648926,
|
| 6573 |
+
"step": 933
|
| 6574 |
+
},
|
| 6575 |
+
{
|
| 6576 |
+
"epoch": 0.25578529371491165,
|
| 6577 |
+
"grad_norm": 0.5396025776863098,
|
| 6578 |
+
"learning_rate": 4.3629968391056883e-05,
|
| 6579 |
+
"loss": 0.4960685074329376,
|
| 6580 |
+
"step": 934
|
| 6581 |
+
},
|
| 6582 |
+
{
|
| 6583 |
+
"epoch": 0.2560591537724223,
|
| 6584 |
+
"grad_norm": 0.49801400303840637,
|
| 6585 |
+
"learning_rate": 4.361517459323027e-05,
|
| 6586 |
+
"loss": 0.4896068572998047,
|
| 6587 |
+
"step": 935
|
| 6588 |
+
},
|
| 6589 |
+
{
|
| 6590 |
+
"epoch": 0.2563330138299329,
|
| 6591 |
+
"grad_norm": 0.5080746412277222,
|
| 6592 |
+
"learning_rate": 4.3600366151066575e-05,
|
| 6593 |
+
"loss": 0.41987794637680054,
|
| 6594 |
+
"step": 936
|
| 6595 |
+
},
|
| 6596 |
+
{
|
| 6597 |
+
"epoch": 0.2566068738874435,
|
| 6598 |
+
"grad_norm": 0.48256418108940125,
|
| 6599 |
+
"learning_rate": 4.358554307621541e-05,
|
| 6600 |
+
"loss": 0.41196075081825256,
|
| 6601 |
+
"step": 937
|
| 6602 |
+
},
|
| 6603 |
+
{
|
| 6604 |
+
"epoch": 0.25688073394495414,
|
| 6605 |
+
"grad_norm": 0.4888422191143036,
|
| 6606 |
+
"learning_rate": 4.3570705380337925e-05,
|
| 6607 |
+
"loss": 0.5071929097175598,
|
| 6608 |
+
"step": 938
|
| 6609 |
+
},
|
| 6610 |
+
{
|
| 6611 |
+
"epoch": 0.25715459400246476,
|
| 6612 |
+
"grad_norm": 0.5343337655067444,
|
| 6613 |
+
"learning_rate": 4.355585307510675e-05,
|
| 6614 |
+
"loss": 0.4475840628147125,
|
| 6615 |
+
"step": 939
|
| 6616 |
+
},
|
| 6617 |
+
{
|
| 6618 |
+
"epoch": 0.25742845405997533,
|
| 6619 |
+
"grad_norm": 0.4837918281555176,
|
| 6620 |
+
"learning_rate": 4.3540986172206024e-05,
|
| 6621 |
+
"loss": 0.4968903958797455,
|
| 6622 |
+
"step": 940
|
| 6623 |
+
},
|
| 6624 |
+
{
|
| 6625 |
+
"epoch": 0.25770231411748595,
|
| 6626 |
+
"grad_norm": 0.43762004375457764,
|
| 6627 |
+
"learning_rate": 4.3526104683331356e-05,
|
| 6628 |
+
"loss": 0.45630592107772827,
|
| 6629 |
+
"step": 941
|
| 6630 |
+
},
|
| 6631 |
+
{
|
| 6632 |
+
"epoch": 0.2579761741749966,
|
| 6633 |
+
"grad_norm": 0.4579359292984009,
|
| 6634 |
+
"learning_rate": 4.3511208620189846e-05,
|
| 6635 |
+
"loss": 0.44708359241485596,
|
| 6636 |
+
"step": 942
|
| 6637 |
+
},
|
| 6638 |
+
{
|
| 6639 |
+
"epoch": 0.2582500342325072,
|
| 6640 |
+
"grad_norm": 0.5096375346183777,
|
| 6641 |
+
"learning_rate": 4.3496297994500046e-05,
|
| 6642 |
+
"loss": 0.3599519729614258,
|
| 6643 |
+
"step": 943
|
| 6644 |
+
},
|
| 6645 |
+
{
|
| 6646 |
+
"epoch": 0.2585238942900178,
|
| 6647 |
+
"grad_norm": 0.43727514147758484,
|
| 6648 |
+
"learning_rate": 4.348137281799197e-05,
|
| 6649 |
+
"loss": 0.3962448239326477,
|
| 6650 |
+
"step": 944
|
| 6651 |
+
},
|
| 6652 |
+
{
|
| 6653 |
+
"epoch": 0.2587977543475284,
|
| 6654 |
+
"grad_norm": 0.43898943066596985,
|
| 6655 |
+
"learning_rate": 4.3466433102407074e-05,
|
| 6656 |
+
"loss": 0.4210021495819092,
|
| 6657 |
+
"step": 945
|
| 6658 |
+
},
|
| 6659 |
+
{
|
| 6660 |
+
"epoch": 0.259071614405039,
|
| 6661 |
+
"grad_norm": 0.4652177095413208,
|
| 6662 |
+
"learning_rate": 4.345147885949825e-05,
|
| 6663 |
+
"loss": 0.4620439410209656,
|
| 6664 |
+
"step": 946
|
| 6665 |
+
},
|
| 6666 |
+
{
|
| 6667 |
+
"epoch": 0.25934547446254963,
|
| 6668 |
+
"grad_norm": 0.4620915949344635,
|
| 6669 |
+
"learning_rate": 4.343651010102984e-05,
|
| 6670 |
+
"loss": 0.4088629186153412,
|
| 6671 |
+
"step": 947
|
| 6672 |
+
},
|
| 6673 |
+
{
|
| 6674 |
+
"epoch": 0.25961933452006025,
|
| 6675 |
+
"grad_norm": 0.46836474537849426,
|
| 6676 |
+
"learning_rate": 4.342152683877757e-05,
|
| 6677 |
+
"loss": 0.42657509446144104,
|
| 6678 |
+
"step": 948
|
| 6679 |
+
},
|
| 6680 |
+
{
|
| 6681 |
+
"epoch": 0.2598931945775709,
|
| 6682 |
+
"grad_norm": 0.5200126767158508,
|
| 6683 |
+
"learning_rate": 4.340652908452861e-05,
|
| 6684 |
+
"loss": 0.4404286742210388,
|
| 6685 |
+
"step": 949
|
| 6686 |
+
},
|
| 6687 |
+
{
|
| 6688 |
+
"epoch": 0.2601670546350815,
|
| 6689 |
+
"grad_norm": 0.4872806966304779,
|
| 6690 |
+
"learning_rate": 4.3391516850081503e-05,
|
| 6691 |
+
"loss": 0.5359296202659607,
|
| 6692 |
+
"step": 950
|
| 6693 |
+
},
|
| 6694 |
+
{
|
| 6695 |
+
"epoch": 0.26044091469259206,
|
| 6696 |
+
"grad_norm": 0.4845404624938965,
|
| 6697 |
+
"learning_rate": 4.337649014724621e-05,
|
| 6698 |
+
"loss": 0.3704652488231659,
|
| 6699 |
+
"step": 951
|
| 6700 |
+
},
|
| 6701 |
+
{
|
| 6702 |
+
"epoch": 0.2607147747501027,
|
| 6703 |
+
"grad_norm": 0.4806290864944458,
|
| 6704 |
+
"learning_rate": 4.336144898784404e-05,
|
| 6705 |
+
"loss": 0.4343326985836029,
|
| 6706 |
+
"step": 952
|
| 6707 |
+
},
|
| 6708 |
+
{
|
| 6709 |
+
"epoch": 0.2609886348076133,
|
| 6710 |
+
"grad_norm": 0.46191534399986267,
|
| 6711 |
+
"learning_rate": 4.334639338370772e-05,
|
| 6712 |
+
"loss": 0.40915483236312866,
|
| 6713 |
+
"step": 953
|
| 6714 |
+
},
|
| 6715 |
+
{
|
| 6716 |
+
"epoch": 0.26126249486512393,
|
| 6717 |
+
"grad_norm": 0.5911896824836731,
|
| 6718 |
+
"learning_rate": 4.333132334668129e-05,
|
| 6719 |
+
"loss": 0.44864869117736816,
|
| 6720 |
+
"step": 954
|
| 6721 |
+
},
|
| 6722 |
+
{
|
| 6723 |
+
"epoch": 0.26153635492263455,
|
| 6724 |
+
"grad_norm": 0.5302111506462097,
|
| 6725 |
+
"learning_rate": 4.3316238888620186e-05,
|
| 6726 |
+
"loss": 0.4688238501548767,
|
| 6727 |
+
"step": 955
|
| 6728 |
+
},
|
| 6729 |
+
{
|
| 6730 |
+
"epoch": 0.2618102149801452,
|
| 6731 |
+
"grad_norm": 0.5174139142036438,
|
| 6732 |
+
"learning_rate": 4.330114002139116e-05,
|
| 6733 |
+
"loss": 0.5307837724685669,
|
| 6734 |
+
"step": 956
|
| 6735 |
+
},
|
| 6736 |
+
{
|
| 6737 |
+
"epoch": 0.26208407503765574,
|
| 6738 |
+
"grad_norm": 0.45109257102012634,
|
| 6739 |
+
"learning_rate": 4.328602675687233e-05,
|
| 6740 |
+
"loss": 0.45362383127212524,
|
| 6741 |
+
"step": 957
|
| 6742 |
+
},
|
| 6743 |
+
{
|
| 6744 |
+
"epoch": 0.26235793509516636,
|
| 6745 |
+
"grad_norm": 0.4765610694885254,
|
| 6746 |
+
"learning_rate": 4.3270899106953105e-05,
|
| 6747 |
+
"loss": 0.41880181431770325,
|
| 6748 |
+
"step": 958
|
| 6749 |
+
},
|
| 6750 |
+
{
|
| 6751 |
+
"epoch": 0.262631795152677,
|
| 6752 |
+
"grad_norm": 0.4803016781806946,
|
| 6753 |
+
"learning_rate": 4.325575708353423e-05,
|
| 6754 |
+
"loss": 0.44433051347732544,
|
| 6755 |
+
"step": 959
|
| 6756 |
+
},
|
| 6757 |
+
{
|
| 6758 |
+
"epoch": 0.2629056552101876,
|
| 6759 |
+
"grad_norm": 0.47367700934410095,
|
| 6760 |
+
"learning_rate": 4.3240600698527764e-05,
|
| 6761 |
+
"loss": 0.43575409054756165,
|
| 6762 |
+
"step": 960
|
| 6763 |
+
},
|
| 6764 |
+
{
|
| 6765 |
+
"epoch": 0.2631795152676982,
|
| 6766 |
+
"grad_norm": 0.46568113565444946,
|
| 6767 |
+
"learning_rate": 4.322542996385705e-05,
|
| 6768 |
+
"loss": 0.49769240617752075,
|
| 6769 |
+
"step": 961
|
| 6770 |
+
},
|
| 6771 |
+
{
|
| 6772 |
+
"epoch": 0.2634533753252088,
|
| 6773 |
+
"grad_norm": 0.5156930685043335,
|
| 6774 |
+
"learning_rate": 4.321024489145673e-05,
|
| 6775 |
+
"loss": 0.47419026494026184,
|
| 6776 |
+
"step": 962
|
| 6777 |
+
},
|
| 6778 |
+
{
|
| 6779 |
+
"epoch": 0.2637272353827194,
|
| 6780 |
+
"grad_norm": 0.5088050961494446,
|
| 6781 |
+
"learning_rate": 4.319504549327271e-05,
|
| 6782 |
+
"loss": 0.4402434825897217,
|
| 6783 |
+
"step": 963
|
| 6784 |
+
},
|
| 6785 |
+
{
|
| 6786 |
+
"epoch": 0.26400109544023004,
|
| 6787 |
+
"grad_norm": 0.4815014898777008,
|
| 6788 |
+
"learning_rate": 4.317983178126218e-05,
|
| 6789 |
+
"loss": 0.5109726190567017,
|
| 6790 |
+
"step": 964
|
| 6791 |
+
},
|
| 6792 |
+
{
|
| 6793 |
+
"epoch": 0.26427495549774066,
|
| 6794 |
+
"grad_norm": 0.5268052220344543,
|
| 6795 |
+
"learning_rate": 4.31646037673936e-05,
|
| 6796 |
+
"loss": 0.4327290654182434,
|
| 6797 |
+
"step": 965
|
| 6798 |
+
},
|
| 6799 |
+
{
|
| 6800 |
+
"epoch": 0.2645488155552513,
|
| 6801 |
+
"grad_norm": 0.48879188299179077,
|
| 6802 |
+
"learning_rate": 4.314936146364665e-05,
|
| 6803 |
+
"loss": 0.45027676224708557,
|
| 6804 |
+
"step": 966
|
| 6805 |
+
},
|
| 6806 |
+
{
|
| 6807 |
+
"epoch": 0.2648226756127619,
|
| 6808 |
+
"grad_norm": 0.49046021699905396,
|
| 6809 |
+
"learning_rate": 4.313410488201227e-05,
|
| 6810 |
+
"loss": 0.45309075713157654,
|
| 6811 |
+
"step": 967
|
| 6812 |
+
},
|
| 6813 |
+
{
|
| 6814 |
+
"epoch": 0.26509653567027247,
|
| 6815 |
+
"grad_norm": 0.4718327224254608,
|
| 6816 |
+
"learning_rate": 4.311883403449264e-05,
|
| 6817 |
+
"loss": 0.39780765771865845,
|
| 6818 |
+
"step": 968
|
| 6819 |
+
},
|
| 6820 |
+
{
|
| 6821 |
+
"epoch": 0.2653703957277831,
|
| 6822 |
+
"grad_norm": 0.4911417067050934,
|
| 6823 |
+
"learning_rate": 4.3103548933101154e-05,
|
| 6824 |
+
"loss": 0.4009256958961487,
|
| 6825 |
+
"step": 969
|
| 6826 |
+
},
|
| 6827 |
+
{
|
| 6828 |
+
"epoch": 0.2656442557852937,
|
| 6829 |
+
"grad_norm": 0.5965861082077026,
|
| 6830 |
+
"learning_rate": 4.308824958986243e-05,
|
| 6831 |
+
"loss": 0.46298202872276306,
|
| 6832 |
+
"step": 970
|
| 6833 |
+
},
|
| 6834 |
+
{
|
| 6835 |
+
"epoch": 0.26591811584280434,
|
| 6836 |
+
"grad_norm": 0.5032942295074463,
|
| 6837 |
+
"learning_rate": 4.307293601681226e-05,
|
| 6838 |
+
"loss": 0.4959346652030945,
|
| 6839 |
+
"step": 971
|
| 6840 |
+
},
|
| 6841 |
+
{
|
| 6842 |
+
"epoch": 0.26619197590031496,
|
| 6843 |
+
"grad_norm": 0.49504294991493225,
|
| 6844 |
+
"learning_rate": 4.305760822599766e-05,
|
| 6845 |
+
"loss": 0.46204841136932373,
|
| 6846 |
+
"step": 972
|
| 6847 |
+
},
|
| 6848 |
+
{
|
| 6849 |
+
"epoch": 0.2664658359578255,
|
| 6850 |
+
"grad_norm": 0.5010042190551758,
|
| 6851 |
+
"learning_rate": 4.304226622947681e-05,
|
| 6852 |
+
"loss": 0.46687525510787964,
|
| 6853 |
+
"step": 973
|
| 6854 |
+
},
|
| 6855 |
+
{
|
| 6856 |
+
"epoch": 0.26673969601533615,
|
| 6857 |
+
"grad_norm": 0.4487892687320709,
|
| 6858 |
+
"learning_rate": 4.30269100393191e-05,
|
| 6859 |
+
"loss": 0.42527151107788086,
|
| 6860 |
+
"step": 974
|
| 6861 |
+
},
|
| 6862 |
+
{
|
| 6863 |
+
"epoch": 0.26701355607284677,
|
| 6864 |
+
"grad_norm": 0.4617379903793335,
|
| 6865 |
+
"learning_rate": 4.301153966760505e-05,
|
| 6866 |
+
"loss": 0.41118812561035156,
|
| 6867 |
+
"step": 975
|
| 6868 |
+
},
|
| 6869 |
+
{
|
| 6870 |
+
"epoch": 0.2672874161303574,
|
| 6871 |
+
"grad_norm": 0.47578489780426025,
|
| 6872 |
+
"learning_rate": 4.299615512642634e-05,
|
| 6873 |
+
"loss": 0.4244149625301361,
|
| 6874 |
+
"step": 976
|
| 6875 |
+
},
|
| 6876 |
+
{
|
| 6877 |
+
"epoch": 0.267561276187868,
|
| 6878 |
+
"grad_norm": 0.45199859142303467,
|
| 6879 |
+
"learning_rate": 4.298075642788583e-05,
|
| 6880 |
+
"loss": 0.40100333094596863,
|
| 6881 |
+
"step": 977
|
| 6882 |
+
},
|
| 6883 |
+
{
|
| 6884 |
+
"epoch": 0.26783513624537864,
|
| 6885 |
+
"grad_norm": 0.46883299946784973,
|
| 6886 |
+
"learning_rate": 4.296534358409746e-05,
|
| 6887 |
+
"loss": 0.42664629220962524,
|
| 6888 |
+
"step": 978
|
| 6889 |
+
},
|
| 6890 |
+
{
|
| 6891 |
+
"epoch": 0.2681089963028892,
|
| 6892 |
+
"grad_norm": 0.5084633231163025,
|
| 6893 |
+
"learning_rate": 4.2949916607186357e-05,
|
| 6894 |
+
"loss": 0.4907737374305725,
|
| 6895 |
+
"step": 979
|
| 6896 |
+
},
|
| 6897 |
+
{
|
| 6898 |
+
"epoch": 0.2683828563603998,
|
| 6899 |
+
"grad_norm": 0.4470442831516266,
|
| 6900 |
+
"learning_rate": 4.2934475509288736e-05,
|
| 6901 |
+
"loss": 0.4026626944541931,
|
| 6902 |
+
"step": 980
|
| 6903 |
+
},
|
| 6904 |
+
{
|
| 6905 |
+
"epoch": 0.26865671641791045,
|
| 6906 |
+
"grad_norm": 0.49613437056541443,
|
| 6907 |
+
"learning_rate": 4.2919020302551924e-05,
|
| 6908 |
+
"loss": 0.4467288851737976,
|
| 6909 |
+
"step": 981
|
| 6910 |
+
},
|
| 6911 |
+
{
|
| 6912 |
+
"epoch": 0.26893057647542107,
|
| 6913 |
+
"grad_norm": 0.4855806529521942,
|
| 6914 |
+
"learning_rate": 4.2903550999134346e-05,
|
| 6915 |
+
"loss": 0.3999844789505005,
|
| 6916 |
+
"step": 982
|
| 6917 |
+
},
|
| 6918 |
+
{
|
| 6919 |
+
"epoch": 0.2692044365329317,
|
| 6920 |
+
"grad_norm": 0.5062927007675171,
|
| 6921 |
+
"learning_rate": 4.288806761120552e-05,
|
| 6922 |
+
"loss": 0.41269317269325256,
|
| 6923 |
+
"step": 983
|
| 6924 |
+
},
|
| 6925 |
+
{
|
| 6926 |
+
"epoch": 0.26947829659044226,
|
| 6927 |
+
"grad_norm": 0.49196985363960266,
|
| 6928 |
+
"learning_rate": 4.2872570150946046e-05,
|
| 6929 |
+
"loss": 0.4269784986972809,
|
| 6930 |
+
"step": 984
|
| 6931 |
+
},
|
| 6932 |
+
{
|
| 6933 |
+
"epoch": 0.2697521566479529,
|
| 6934 |
+
"grad_norm": 0.4999912977218628,
|
| 6935 |
+
"learning_rate": 4.2857058630547594e-05,
|
| 6936 |
+
"loss": 0.46527403593063354,
|
| 6937 |
+
"step": 985
|
| 6938 |
+
},
|
| 6939 |
+
{
|
| 6940 |
+
"epoch": 0.2700260167054635,
|
| 6941 |
+
"grad_norm": 0.5671318769454956,
|
| 6942 |
+
"learning_rate": 4.284153306221289e-05,
|
| 6943 |
+
"loss": 0.531314492225647,
|
| 6944 |
+
"step": 986
|
| 6945 |
+
},
|
| 6946 |
+
{
|
| 6947 |
+
"epoch": 0.2702998767629741,
|
| 6948 |
+
"grad_norm": 0.4482066035270691,
|
| 6949 |
+
"learning_rate": 4.282599345815571e-05,
|
| 6950 |
+
"loss": 0.40302836894989014,
|
| 6951 |
+
"step": 987
|
| 6952 |
+
},
|
| 6953 |
+
{
|
| 6954 |
+
"epoch": 0.27057373682048474,
|
| 6955 |
+
"grad_norm": 0.43117406964302063,
|
| 6956 |
+
"learning_rate": 4.2810439830600894e-05,
|
| 6957 |
+
"loss": 0.42709463834762573,
|
| 6958 |
+
"step": 988
|
| 6959 |
+
},
|
| 6960 |
+
{
|
| 6961 |
+
"epoch": 0.27084759687799537,
|
| 6962 |
+
"grad_norm": 0.46017542481422424,
|
| 6963 |
+
"learning_rate": 4.279487219178427e-05,
|
| 6964 |
+
"loss": 0.4040953516960144,
|
| 6965 |
+
"step": 989
|
| 6966 |
+
},
|
| 6967 |
+
{
|
| 6968 |
+
"epoch": 0.27112145693550593,
|
| 6969 |
+
"grad_norm": 0.5213095545768738,
|
| 6970 |
+
"learning_rate": 4.2779290553952735e-05,
|
| 6971 |
+
"loss": 0.5317548513412476,
|
| 6972 |
+
"step": 990
|
| 6973 |
+
},
|
| 6974 |
+
{
|
| 6975 |
+
"epoch": 0.27139531699301656,
|
| 6976 |
+
"grad_norm": 0.49342650175094604,
|
| 6977 |
+
"learning_rate": 4.2763694929364166e-05,
|
| 6978 |
+
"loss": 0.5525836944580078,
|
| 6979 |
+
"step": 991
|
| 6980 |
+
},
|
| 6981 |
+
{
|
| 6982 |
+
"epoch": 0.2716691770505272,
|
| 6983 |
+
"grad_norm": 0.4744791090488434,
|
| 6984 |
+
"learning_rate": 4.274808533028747e-05,
|
| 6985 |
+
"loss": 0.386430561542511,
|
| 6986 |
+
"step": 992
|
| 6987 |
+
},
|
| 6988 |
+
{
|
| 6989 |
+
"epoch": 0.2719430371080378,
|
| 6990 |
+
"grad_norm": 0.46886998414993286,
|
| 6991 |
+
"learning_rate": 4.273246176900252e-05,
|
| 6992 |
+
"loss": 0.42459994554519653,
|
| 6993 |
+
"step": 993
|
| 6994 |
+
},
|
| 6995 |
+
{
|
| 6996 |
+
"epoch": 0.2722168971655484,
|
| 6997 |
+
"grad_norm": 0.4872593283653259,
|
| 6998 |
+
"learning_rate": 4.27168242578002e-05,
|
| 6999 |
+
"loss": 0.4640480577945709,
|
| 7000 |
+
"step": 994
|
| 7001 |
+
},
|
| 7002 |
+
{
|
| 7003 |
+
"epoch": 0.27249075722305904,
|
| 7004 |
+
"grad_norm": 0.4792447090148926,
|
| 7005 |
+
"learning_rate": 4.270117280898234e-05,
|
| 7006 |
+
"loss": 0.5370936393737793,
|
| 7007 |
+
"step": 995
|
| 7008 |
+
},
|
| 7009 |
+
{
|
| 7010 |
+
"epoch": 0.2727646172805696,
|
| 7011 |
+
"grad_norm": 0.5204771757125854,
|
| 7012 |
+
"learning_rate": 4.268550743486176e-05,
|
| 7013 |
+
"loss": 0.6016427874565125,
|
| 7014 |
+
"step": 996
|
| 7015 |
+
},
|
| 7016 |
+
{
|
| 7017 |
+
"epoch": 0.27303847733808023,
|
| 7018 |
+
"grad_norm": 0.4503135681152344,
|
| 7019 |
+
"learning_rate": 4.2669828147762213e-05,
|
| 7020 |
+
"loss": 0.39240050315856934,
|
| 7021 |
+
"step": 997
|
| 7022 |
+
},
|
| 7023 |
+
{
|
| 7024 |
+
"epoch": 0.27331233739559085,
|
| 7025 |
+
"grad_norm": 0.5029263496398926,
|
| 7026 |
+
"learning_rate": 4.265413496001842e-05,
|
| 7027 |
+
"loss": 0.4952338933944702,
|
| 7028 |
+
"step": 998
|
| 7029 |
+
},
|
| 7030 |
+
{
|
| 7031 |
+
"epoch": 0.2735861974531015,
|
| 7032 |
+
"grad_norm": 0.49242159724235535,
|
| 7033 |
+
"learning_rate": 4.263842788397602e-05,
|
| 7034 |
+
"loss": 0.45531079173088074,
|
| 7035 |
+
"step": 999
|
| 7036 |
+
},
|
| 7037 |
+
{
|
| 7038 |
+
"epoch": 0.2738600575106121,
|
| 7039 |
+
"grad_norm": 0.4938235580921173,
|
| 7040 |
+
"learning_rate": 4.262270693199158e-05,
|
| 7041 |
+
"loss": 0.42565852403640747,
|
| 7042 |
+
"step": 1000
|
| 7043 |
+
},
|
| 7044 |
+
{
|
| 7045 |
+
"epoch": 0.2738600575106121,
|
| 7046 |
+
"eval_loss": 0.4585808515548706,
|
| 7047 |
+
"eval_runtime": 32.4508,
|
| 7048 |
+
"eval_samples_per_second": 6.163,
|
| 7049 |
+
"eval_steps_per_second": 0.77,
|
| 7050 |
+
"step": 1000
|
| 7051 |
}
|
| 7052 |
],
|
| 7053 |
"logging_steps": 1,
|
|
|
|
| 7076 |
"attributes": {}
|
| 7077 |
}
|
| 7078 |
},
|
| 7079 |
+
"total_flos": 1.3571377856512e+17,
|
| 7080 |
"train_batch_size": 1,
|
| 7081 |
"trial_name": null,
|
| 7082 |
"trial_params": null
|