Instructions to use shareit/chatbot-supervisor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shareit/chatbot-supervisor with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shareit/chatbot-supervisor", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use shareit/chatbot-supervisor with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for shareit/chatbot-supervisor to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for shareit/chatbot-supervisor to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for shareit/chatbot-supervisor to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="shareit/chatbot-supervisor", max_seq_length=2048, )
Training in progress, step 13800, checkpoint
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 340808816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3aafb57b910d4cccd85ea24209a70be5b99344b88a9876d8830c026cbfc09984
|
| 3 |
size 340808816
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 173247691
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:059f6f8429397406dface628a4284dcb8938551965f3c045168f79f5fba8d08b
|
| 3 |
size 173247691
|
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 sha256:7e55996a4913dc987fc027e04b41b6008152cac112575a6ab3bd719b08b3ee43
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 15.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -94508,6 +94508,2106 @@
|
|
| 94508 |
"learning_rate": 6.824720580318203e-06,
|
| 94509 |
"loss": 0.4935,
|
| 94510 |
"step": 13500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94511 |
}
|
| 94512 |
],
|
| 94513 |
"logging_steps": 1,
|
|
@@ -94527,7 +96627,7 @@
|
|
| 94527 |
"attributes": {}
|
| 94528 |
}
|
| 94529 |
},
|
| 94530 |
-
"total_flos": 7.
|
| 94531 |
"train_batch_size": 8,
|
| 94532 |
"trial_name": null,
|
| 94533 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.717948717948717,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 13800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 94508 |
"learning_rate": 6.824720580318203e-06,
|
| 94509 |
"loss": 0.4935,
|
| 94510 |
"step": 13500
|
| 94511 |
+
},
|
| 94512 |
+
{
|
| 94513 |
+
"epoch": 15.377207977207977,
|
| 94514 |
+
"grad_norm": 0.2545756995677948,
|
| 94515 |
+
"learning_rate": 6.82152178281906e-06,
|
| 94516 |
+
"loss": 0.5802,
|
| 94517 |
+
"step": 13501
|
| 94518 |
+
},
|
| 94519 |
+
{
|
| 94520 |
+
"epoch": 15.378347578347578,
|
| 94521 |
+
"grad_norm": 0.18533293902873993,
|
| 94522 |
+
"learning_rate": 6.81832361670845e-06,
|
| 94523 |
+
"loss": 0.8319,
|
| 94524 |
+
"step": 13502
|
| 94525 |
+
},
|
| 94526 |
+
{
|
| 94527 |
+
"epoch": 15.37948717948718,
|
| 94528 |
+
"grad_norm": 0.17357389628887177,
|
| 94529 |
+
"learning_rate": 6.8151260820974754e-06,
|
| 94530 |
+
"loss": 0.6984,
|
| 94531 |
+
"step": 13503
|
| 94532 |
+
},
|
| 94533 |
+
{
|
| 94534 |
+
"epoch": 15.38062678062678,
|
| 94535 |
+
"grad_norm": 0.21384303271770477,
|
| 94536 |
+
"learning_rate": 6.811929179097173e-06,
|
| 94537 |
+
"loss": 0.6616,
|
| 94538 |
+
"step": 13504
|
| 94539 |
+
},
|
| 94540 |
+
{
|
| 94541 |
+
"epoch": 15.381766381766381,
|
| 94542 |
+
"grad_norm": 0.16954922676086426,
|
| 94543 |
+
"learning_rate": 6.808732907818585e-06,
|
| 94544 |
+
"loss": 0.6801,
|
| 94545 |
+
"step": 13505
|
| 94546 |
+
},
|
| 94547 |
+
{
|
| 94548 |
+
"epoch": 15.382905982905983,
|
| 94549 |
+
"grad_norm": 0.19935904443264008,
|
| 94550 |
+
"learning_rate": 6.805537268372733e-06,
|
| 94551 |
+
"loss": 0.5464,
|
| 94552 |
+
"step": 13506
|
| 94553 |
+
},
|
| 94554 |
+
{
|
| 94555 |
+
"epoch": 15.384045584045584,
|
| 94556 |
+
"grad_norm": 0.22920085489749908,
|
| 94557 |
+
"learning_rate": 6.8023422608706114e-06,
|
| 94558 |
+
"loss": 0.6909,
|
| 94559 |
+
"step": 13507
|
| 94560 |
+
},
|
| 94561 |
+
{
|
| 94562 |
+
"epoch": 15.385185185185184,
|
| 94563 |
+
"grad_norm": 0.17728930711746216,
|
| 94564 |
+
"learning_rate": 6.7991478854231825e-06,
|
| 94565 |
+
"loss": 0.7678,
|
| 94566 |
+
"step": 13508
|
| 94567 |
+
},
|
| 94568 |
+
{
|
| 94569 |
+
"epoch": 15.386324786324787,
|
| 94570 |
+
"grad_norm": 0.2285919189453125,
|
| 94571 |
+
"learning_rate": 6.7959541421413974e-06,
|
| 94572 |
+
"loss": 0.6241,
|
| 94573 |
+
"step": 13509
|
| 94574 |
+
},
|
| 94575 |
+
{
|
| 94576 |
+
"epoch": 15.387464387464387,
|
| 94577 |
+
"grad_norm": 0.2507666349411011,
|
| 94578 |
+
"learning_rate": 6.792761031136189e-06,
|
| 94579 |
+
"loss": 0.4517,
|
| 94580 |
+
"step": 13510
|
| 94581 |
+
},
|
| 94582 |
+
{
|
| 94583 |
+
"epoch": 15.388603988603988,
|
| 94584 |
+
"grad_norm": 0.2384263277053833,
|
| 94585 |
+
"learning_rate": 6.789568552518463e-06,
|
| 94586 |
+
"loss": 0.5156,
|
| 94587 |
+
"step": 13511
|
| 94588 |
+
},
|
| 94589 |
+
{
|
| 94590 |
+
"epoch": 15.38974358974359,
|
| 94591 |
+
"grad_norm": 0.1914670169353485,
|
| 94592 |
+
"learning_rate": 6.786376706399097e-06,
|
| 94593 |
+
"loss": 0.6855,
|
| 94594 |
+
"step": 13512
|
| 94595 |
+
},
|
| 94596 |
+
{
|
| 94597 |
+
"epoch": 15.39088319088319,
|
| 94598 |
+
"grad_norm": 0.18924571573734283,
|
| 94599 |
+
"learning_rate": 6.783185492888947e-06,
|
| 94600 |
+
"loss": 0.5981,
|
| 94601 |
+
"step": 13513
|
| 94602 |
+
},
|
| 94603 |
+
{
|
| 94604 |
+
"epoch": 15.392022792022791,
|
| 94605 |
+
"grad_norm": 0.19691336154937744,
|
| 94606 |
+
"learning_rate": 6.779994912098875e-06,
|
| 94607 |
+
"loss": 0.657,
|
| 94608 |
+
"step": 13514
|
| 94609 |
+
},
|
| 94610 |
+
{
|
| 94611 |
+
"epoch": 15.393162393162394,
|
| 94612 |
+
"grad_norm": 0.17275047302246094,
|
| 94613 |
+
"learning_rate": 6.776804964139677e-06,
|
| 94614 |
+
"loss": 0.8592,
|
| 94615 |
+
"step": 13515
|
| 94616 |
+
},
|
| 94617 |
+
{
|
| 94618 |
+
"epoch": 15.394301994301994,
|
| 94619 |
+
"grad_norm": 0.22531549632549286,
|
| 94620 |
+
"learning_rate": 6.773615649122158e-06,
|
| 94621 |
+
"loss": 0.6171,
|
| 94622 |
+
"step": 13516
|
| 94623 |
+
},
|
| 94624 |
+
{
|
| 94625 |
+
"epoch": 15.395441595441595,
|
| 94626 |
+
"grad_norm": 0.18528665602207184,
|
| 94627 |
+
"learning_rate": 6.7704269671570896e-06,
|
| 94628 |
+
"loss": 0.6811,
|
| 94629 |
+
"step": 13517
|
| 94630 |
+
},
|
| 94631 |
+
{
|
| 94632 |
+
"epoch": 15.396581196581197,
|
| 94633 |
+
"grad_norm": 0.16656826436519623,
|
| 94634 |
+
"learning_rate": 6.767238918355231e-06,
|
| 94635 |
+
"loss": 0.6328,
|
| 94636 |
+
"step": 13518
|
| 94637 |
+
},
|
| 94638 |
+
{
|
| 94639 |
+
"epoch": 15.397720797720797,
|
| 94640 |
+
"grad_norm": 0.20518410205841064,
|
| 94641 |
+
"learning_rate": 6.7640515028272986e-06,
|
| 94642 |
+
"loss": 0.4002,
|
| 94643 |
+
"step": 13519
|
| 94644 |
+
},
|
| 94645 |
+
{
|
| 94646 |
+
"epoch": 15.398860398860398,
|
| 94647 |
+
"grad_norm": 0.19122925400733948,
|
| 94648 |
+
"learning_rate": 6.760864720684007e-06,
|
| 94649 |
+
"loss": 0.7034,
|
| 94650 |
+
"step": 13520
|
| 94651 |
+
},
|
| 94652 |
+
{
|
| 94653 |
+
"epoch": 15.4,
|
| 94654 |
+
"grad_norm": 0.24097371101379395,
|
| 94655 |
+
"learning_rate": 6.7576785720360416e-06,
|
| 94656 |
+
"loss": 0.6354,
|
| 94657 |
+
"step": 13521
|
| 94658 |
+
},
|
| 94659 |
+
{
|
| 94660 |
+
"epoch": 15.401139601139601,
|
| 94661 |
+
"grad_norm": 0.23148728907108307,
|
| 94662 |
+
"learning_rate": 6.754493056994072e-06,
|
| 94663 |
+
"loss": 0.7375,
|
| 94664 |
+
"step": 13522
|
| 94665 |
+
},
|
| 94666 |
+
{
|
| 94667 |
+
"epoch": 15.402279202279201,
|
| 94668 |
+
"grad_norm": 0.16283705830574036,
|
| 94669 |
+
"learning_rate": 6.751308175668727e-06,
|
| 94670 |
+
"loss": 0.7969,
|
| 94671 |
+
"step": 13523
|
| 94672 |
+
},
|
| 94673 |
+
{
|
| 94674 |
+
"epoch": 15.403418803418804,
|
| 94675 |
+
"grad_norm": 0.24585258960723877,
|
| 94676 |
+
"learning_rate": 6.748123928170627e-06,
|
| 94677 |
+
"loss": 0.5324,
|
| 94678 |
+
"step": 13524
|
| 94679 |
+
},
|
| 94680 |
+
{
|
| 94681 |
+
"epoch": 15.404558404558404,
|
| 94682 |
+
"grad_norm": 0.2425752878189087,
|
| 94683 |
+
"learning_rate": 6.744940314610387e-06,
|
| 94684 |
+
"loss": 0.5958,
|
| 94685 |
+
"step": 13525
|
| 94686 |
+
},
|
| 94687 |
+
{
|
| 94688 |
+
"epoch": 15.405698005698005,
|
| 94689 |
+
"grad_norm": 0.17162194848060608,
|
| 94690 |
+
"learning_rate": 6.741757335098567e-06,
|
| 94691 |
+
"loss": 0.6547,
|
| 94692 |
+
"step": 13526
|
| 94693 |
+
},
|
| 94694 |
+
{
|
| 94695 |
+
"epoch": 15.406837606837607,
|
| 94696 |
+
"grad_norm": 0.18037395179271698,
|
| 94697 |
+
"learning_rate": 6.738574989745724e-06,
|
| 94698 |
+
"loss": 0.8093,
|
| 94699 |
+
"step": 13527
|
| 94700 |
+
},
|
| 94701 |
+
{
|
| 94702 |
+
"epoch": 15.407977207977208,
|
| 94703 |
+
"grad_norm": 0.22981791198253632,
|
| 94704 |
+
"learning_rate": 6.7353932786623945e-06,
|
| 94705 |
+
"loss": 0.7284,
|
| 94706 |
+
"step": 13528
|
| 94707 |
+
},
|
| 94708 |
+
{
|
| 94709 |
+
"epoch": 15.40911680911681,
|
| 94710 |
+
"grad_norm": 0.23959402740001678,
|
| 94711 |
+
"learning_rate": 6.732212201959087e-06,
|
| 94712 |
+
"loss": 0.3635,
|
| 94713 |
+
"step": 13529
|
| 94714 |
+
},
|
| 94715 |
+
{
|
| 94716 |
+
"epoch": 15.41025641025641,
|
| 94717 |
+
"grad_norm": 0.2161649465560913,
|
| 94718 |
+
"learning_rate": 6.729031759746282e-06,
|
| 94719 |
+
"loss": 0.5876,
|
| 94720 |
+
"step": 13530
|
| 94721 |
+
},
|
| 94722 |
+
{
|
| 94723 |
+
"epoch": 15.411396011396011,
|
| 94724 |
+
"grad_norm": 0.21092326939105988,
|
| 94725 |
+
"learning_rate": 6.725851952134446e-06,
|
| 94726 |
+
"loss": 0.7228,
|
| 94727 |
+
"step": 13531
|
| 94728 |
+
},
|
| 94729 |
+
{
|
| 94730 |
+
"epoch": 15.412535612535613,
|
| 94731 |
+
"grad_norm": 0.21590463817119598,
|
| 94732 |
+
"learning_rate": 6.72267277923403e-06,
|
| 94733 |
+
"loss": 0.6601,
|
| 94734 |
+
"step": 13532
|
| 94735 |
+
},
|
| 94736 |
+
{
|
| 94737 |
+
"epoch": 15.413675213675214,
|
| 94738 |
+
"grad_norm": 0.22229517996311188,
|
| 94739 |
+
"learning_rate": 6.7194942411554555e-06,
|
| 94740 |
+
"loss": 0.547,
|
| 94741 |
+
"step": 13533
|
| 94742 |
+
},
|
| 94743 |
+
{
|
| 94744 |
+
"epoch": 15.414814814814815,
|
| 94745 |
+
"grad_norm": 0.21258416771888733,
|
| 94746 |
+
"learning_rate": 6.71631633800911e-06,
|
| 94747 |
+
"loss": 0.7539,
|
| 94748 |
+
"step": 13534
|
| 94749 |
+
},
|
| 94750 |
+
{
|
| 94751 |
+
"epoch": 15.415954415954417,
|
| 94752 |
+
"grad_norm": 0.15924860537052155,
|
| 94753 |
+
"learning_rate": 6.713139069905372e-06,
|
| 94754 |
+
"loss": 0.7066,
|
| 94755 |
+
"step": 13535
|
| 94756 |
+
},
|
| 94757 |
+
{
|
| 94758 |
+
"epoch": 15.417094017094017,
|
| 94759 |
+
"grad_norm": 0.16245602071285248,
|
| 94760 |
+
"learning_rate": 6.709962436954612e-06,
|
| 94761 |
+
"loss": 0.6911,
|
| 94762 |
+
"step": 13536
|
| 94763 |
+
},
|
| 94764 |
+
{
|
| 94765 |
+
"epoch": 15.418233618233618,
|
| 94766 |
+
"grad_norm": 0.18839913606643677,
|
| 94767 |
+
"learning_rate": 6.70678643926716e-06,
|
| 94768 |
+
"loss": 0.6721,
|
| 94769 |
+
"step": 13537
|
| 94770 |
+
},
|
| 94771 |
+
{
|
| 94772 |
+
"epoch": 15.41937321937322,
|
| 94773 |
+
"grad_norm": 0.19004669785499573,
|
| 94774 |
+
"learning_rate": 6.703611076953315e-06,
|
| 94775 |
+
"loss": 0.7099,
|
| 94776 |
+
"step": 13538
|
| 94777 |
+
},
|
| 94778 |
+
{
|
| 94779 |
+
"epoch": 15.42051282051282,
|
| 94780 |
+
"grad_norm": 0.23223291337490082,
|
| 94781 |
+
"learning_rate": 6.7004363501233705e-06,
|
| 94782 |
+
"loss": 0.5233,
|
| 94783 |
+
"step": 13539
|
| 94784 |
+
},
|
| 94785 |
+
{
|
| 94786 |
+
"epoch": 15.421652421652421,
|
| 94787 |
+
"grad_norm": 0.18488751351833344,
|
| 94788 |
+
"learning_rate": 6.697262258887596e-06,
|
| 94789 |
+
"loss": 0.7661,
|
| 94790 |
+
"step": 13540
|
| 94791 |
+
},
|
| 94792 |
+
{
|
| 94793 |
+
"epoch": 15.422792022792024,
|
| 94794 |
+
"grad_norm": 0.1790686845779419,
|
| 94795 |
+
"learning_rate": 6.694088803356247e-06,
|
| 94796 |
+
"loss": 0.8949,
|
| 94797 |
+
"step": 13541
|
| 94798 |
+
},
|
| 94799 |
+
{
|
| 94800 |
+
"epoch": 15.423931623931624,
|
| 94801 |
+
"grad_norm": 0.20640535652637482,
|
| 94802 |
+
"learning_rate": 6.690915983639523e-06,
|
| 94803 |
+
"loss": 0.7,
|
| 94804 |
+
"step": 13542
|
| 94805 |
+
},
|
| 94806 |
+
{
|
| 94807 |
+
"epoch": 15.425071225071225,
|
| 94808 |
+
"grad_norm": 0.2872496545314789,
|
| 94809 |
+
"learning_rate": 6.68774379984764e-06,
|
| 94810 |
+
"loss": 0.4593,
|
| 94811 |
+
"step": 13543
|
| 94812 |
+
},
|
| 94813 |
+
{
|
| 94814 |
+
"epoch": 15.426210826210827,
|
| 94815 |
+
"grad_norm": 0.20648087561130524,
|
| 94816 |
+
"learning_rate": 6.684572252090773e-06,
|
| 94817 |
+
"loss": 0.5741,
|
| 94818 |
+
"step": 13544
|
| 94819 |
+
},
|
| 94820 |
+
{
|
| 94821 |
+
"epoch": 15.427350427350428,
|
| 94822 |
+
"grad_norm": 0.16248594224452972,
|
| 94823 |
+
"learning_rate": 6.681401340479087e-06,
|
| 94824 |
+
"loss": 0.9091,
|
| 94825 |
+
"step": 13545
|
| 94826 |
+
},
|
| 94827 |
+
{
|
| 94828 |
+
"epoch": 15.428490028490028,
|
| 94829 |
+
"grad_norm": 0.23793335258960724,
|
| 94830 |
+
"learning_rate": 6.678231065122695e-06,
|
| 94831 |
+
"loss": 0.501,
|
| 94832 |
+
"step": 13546
|
| 94833 |
+
},
|
| 94834 |
+
{
|
| 94835 |
+
"epoch": 15.42962962962963,
|
| 94836 |
+
"grad_norm": 0.1887454092502594,
|
| 94837 |
+
"learning_rate": 6.675061426131729e-06,
|
| 94838 |
+
"loss": 0.4776,
|
| 94839 |
+
"step": 13547
|
| 94840 |
+
},
|
| 94841 |
+
{
|
| 94842 |
+
"epoch": 15.430769230769231,
|
| 94843 |
+
"grad_norm": 0.20787455141544342,
|
| 94844 |
+
"learning_rate": 6.67189242361628e-06,
|
| 94845 |
+
"loss": 0.7284,
|
| 94846 |
+
"step": 13548
|
| 94847 |
+
},
|
| 94848 |
+
{
|
| 94849 |
+
"epoch": 15.431908831908832,
|
| 94850 |
+
"grad_norm": 0.16973797976970673,
|
| 94851 |
+
"learning_rate": 6.668724057686404e-06,
|
| 94852 |
+
"loss": 0.6371,
|
| 94853 |
+
"step": 13549
|
| 94854 |
+
},
|
| 94855 |
+
{
|
| 94856 |
+
"epoch": 15.433048433048434,
|
| 94857 |
+
"grad_norm": 0.209912970662117,
|
| 94858 |
+
"learning_rate": 6.665556328452152e-06,
|
| 94859 |
+
"loss": 0.7062,
|
| 94860 |
+
"step": 13550
|
| 94861 |
+
},
|
| 94862 |
+
{
|
| 94863 |
+
"epoch": 15.434188034188034,
|
| 94864 |
+
"grad_norm": 0.21412673592567444,
|
| 94865 |
+
"learning_rate": 6.66238923602355e-06,
|
| 94866 |
+
"loss": 0.6927,
|
| 94867 |
+
"step": 13551
|
| 94868 |
+
},
|
| 94869 |
+
{
|
| 94870 |
+
"epoch": 15.435327635327635,
|
| 94871 |
+
"grad_norm": 0.18775635957717896,
|
| 94872 |
+
"learning_rate": 6.659222780510605e-06,
|
| 94873 |
+
"loss": 0.4888,
|
| 94874 |
+
"step": 13552
|
| 94875 |
+
},
|
| 94876 |
+
{
|
| 94877 |
+
"epoch": 15.436467236467237,
|
| 94878 |
+
"grad_norm": 0.19604071974754333,
|
| 94879 |
+
"learning_rate": 6.65605696202328e-06,
|
| 94880 |
+
"loss": 0.7704,
|
| 94881 |
+
"step": 13553
|
| 94882 |
+
},
|
| 94883 |
+
{
|
| 94884 |
+
"epoch": 15.437606837606838,
|
| 94885 |
+
"grad_norm": 0.17671994864940643,
|
| 94886 |
+
"learning_rate": 6.652891780671547e-06,
|
| 94887 |
+
"loss": 0.6545,
|
| 94888 |
+
"step": 13554
|
| 94889 |
+
},
|
| 94890 |
+
{
|
| 94891 |
+
"epoch": 15.438746438746438,
|
| 94892 |
+
"grad_norm": 0.2810894548892975,
|
| 94893 |
+
"learning_rate": 6.649727236565334e-06,
|
| 94894 |
+
"loss": 0.6377,
|
| 94895 |
+
"step": 13555
|
| 94896 |
+
},
|
| 94897 |
+
{
|
| 94898 |
+
"epoch": 15.43988603988604,
|
| 94899 |
+
"grad_norm": 0.19777388870716095,
|
| 94900 |
+
"learning_rate": 6.646563329814567e-06,
|
| 94901 |
+
"loss": 0.7028,
|
| 94902 |
+
"step": 13556
|
| 94903 |
+
},
|
| 94904 |
+
{
|
| 94905 |
+
"epoch": 15.441025641025641,
|
| 94906 |
+
"grad_norm": 0.1773541122674942,
|
| 94907 |
+
"learning_rate": 6.643400060529112e-06,
|
| 94908 |
+
"loss": 0.7958,
|
| 94909 |
+
"step": 13557
|
| 94910 |
+
},
|
| 94911 |
+
{
|
| 94912 |
+
"epoch": 15.442165242165242,
|
| 94913 |
+
"grad_norm": 0.2325608879327774,
|
| 94914 |
+
"learning_rate": 6.64023742881886e-06,
|
| 94915 |
+
"loss": 0.8598,
|
| 94916 |
+
"step": 13558
|
| 94917 |
+
},
|
| 94918 |
+
{
|
| 94919 |
+
"epoch": 15.443304843304844,
|
| 94920 |
+
"grad_norm": 0.21778924763202667,
|
| 94921 |
+
"learning_rate": 6.6370754347936605e-06,
|
| 94922 |
+
"loss": 0.6885,
|
| 94923 |
+
"step": 13559
|
| 94924 |
+
},
|
| 94925 |
+
{
|
| 94926 |
+
"epoch": 15.444444444444445,
|
| 94927 |
+
"grad_norm": 0.20094701647758484,
|
| 94928 |
+
"learning_rate": 6.6339140785633215e-06,
|
| 94929 |
+
"loss": 0.6292,
|
| 94930 |
+
"step": 13560
|
| 94931 |
+
},
|
| 94932 |
+
{
|
| 94933 |
+
"epoch": 15.445584045584045,
|
| 94934 |
+
"grad_norm": 0.1571194976568222,
|
| 94935 |
+
"learning_rate": 6.630753360237654e-06,
|
| 94936 |
+
"loss": 0.7107,
|
| 94937 |
+
"step": 13561
|
| 94938 |
+
},
|
| 94939 |
+
{
|
| 94940 |
+
"epoch": 15.446723646723648,
|
| 94941 |
+
"grad_norm": 0.226139634847641,
|
| 94942 |
+
"learning_rate": 6.627593279926439e-06,
|
| 94943 |
+
"loss": 0.4293,
|
| 94944 |
+
"step": 13562
|
| 94945 |
+
},
|
| 94946 |
+
{
|
| 94947 |
+
"epoch": 15.447863247863248,
|
| 94948 |
+
"grad_norm": 0.2584592401981354,
|
| 94949 |
+
"learning_rate": 6.624433837739438e-06,
|
| 94950 |
+
"loss": 0.5004,
|
| 94951 |
+
"step": 13563
|
| 94952 |
+
},
|
| 94953 |
+
{
|
| 94954 |
+
"epoch": 15.449002849002849,
|
| 94955 |
+
"grad_norm": 0.22435049712657928,
|
| 94956 |
+
"learning_rate": 6.621275033786379e-06,
|
| 94957 |
+
"loss": 0.6862,
|
| 94958 |
+
"step": 13564
|
| 94959 |
+
},
|
| 94960 |
+
{
|
| 94961 |
+
"epoch": 15.450142450142451,
|
| 94962 |
+
"grad_norm": 0.17067396640777588,
|
| 94963 |
+
"learning_rate": 6.6181168681769765e-06,
|
| 94964 |
+
"loss": 0.7152,
|
| 94965 |
+
"step": 13565
|
| 94966 |
+
},
|
| 94967 |
+
{
|
| 94968 |
+
"epoch": 15.451282051282051,
|
| 94969 |
+
"grad_norm": 0.15705978870391846,
|
| 94970 |
+
"learning_rate": 6.614959341020929e-06,
|
| 94971 |
+
"loss": 0.9746,
|
| 94972 |
+
"step": 13566
|
| 94973 |
+
},
|
| 94974 |
+
{
|
| 94975 |
+
"epoch": 15.452421652421652,
|
| 94976 |
+
"grad_norm": 0.24600954353809357,
|
| 94977 |
+
"learning_rate": 6.611802452427907e-06,
|
| 94978 |
+
"loss": 0.7185,
|
| 94979 |
+
"step": 13567
|
| 94980 |
+
},
|
| 94981 |
+
{
|
| 94982 |
+
"epoch": 15.453561253561254,
|
| 94983 |
+
"grad_norm": 0.18077035248279572,
|
| 94984 |
+
"learning_rate": 6.60864620250754e-06,
|
| 94985 |
+
"loss": 0.5957,
|
| 94986 |
+
"step": 13568
|
| 94987 |
+
},
|
| 94988 |
+
{
|
| 94989 |
+
"epoch": 15.454700854700855,
|
| 94990 |
+
"grad_norm": 0.23606523871421814,
|
| 94991 |
+
"learning_rate": 6.605490591369473e-06,
|
| 94992 |
+
"loss": 0.6958,
|
| 94993 |
+
"step": 13569
|
| 94994 |
+
},
|
| 94995 |
+
{
|
| 94996 |
+
"epoch": 15.455840455840455,
|
| 94997 |
+
"grad_norm": 0.25060296058654785,
|
| 94998 |
+
"learning_rate": 6.602335619123312e-06,
|
| 94999 |
+
"loss": 0.6264,
|
| 95000 |
+
"step": 13570
|
| 95001 |
+
},
|
| 95002 |
+
{
|
| 95003 |
+
"epoch": 15.456980056980058,
|
| 95004 |
+
"grad_norm": 0.19400660693645477,
|
| 95005 |
+
"learning_rate": 6.599181285878622e-06,
|
| 95006 |
+
"loss": 0.7568,
|
| 95007 |
+
"step": 13571
|
| 95008 |
+
},
|
| 95009 |
+
{
|
| 95010 |
+
"epoch": 15.458119658119658,
|
| 95011 |
+
"grad_norm": 0.2130562663078308,
|
| 95012 |
+
"learning_rate": 6.596027591744966e-06,
|
| 95013 |
+
"loss": 0.5687,
|
| 95014 |
+
"step": 13572
|
| 95015 |
+
},
|
| 95016 |
+
{
|
| 95017 |
+
"epoch": 15.459259259259259,
|
| 95018 |
+
"grad_norm": 0.29239821434020996,
|
| 95019 |
+
"learning_rate": 6.592874536831884e-06,
|
| 95020 |
+
"loss": 0.6646,
|
| 95021 |
+
"step": 13573
|
| 95022 |
+
},
|
| 95023 |
+
{
|
| 95024 |
+
"epoch": 15.460398860398861,
|
| 95025 |
+
"grad_norm": 0.23149274289608002,
|
| 95026 |
+
"learning_rate": 6.5897221212488895e-06,
|
| 95027 |
+
"loss": 0.7832,
|
| 95028 |
+
"step": 13574
|
| 95029 |
+
},
|
| 95030 |
+
{
|
| 95031 |
+
"epoch": 15.461538461538462,
|
| 95032 |
+
"grad_norm": 0.16438227891921997,
|
| 95033 |
+
"learning_rate": 6.58657034510548e-06,
|
| 95034 |
+
"loss": 0.7924,
|
| 95035 |
+
"step": 13575
|
| 95036 |
+
},
|
| 95037 |
+
{
|
| 95038 |
+
"epoch": 15.462678062678062,
|
| 95039 |
+
"grad_norm": 0.2602296471595764,
|
| 95040 |
+
"learning_rate": 6.583419208511113e-06,
|
| 95041 |
+
"loss": 0.3983,
|
| 95042 |
+
"step": 13576
|
| 95043 |
+
},
|
| 95044 |
+
{
|
| 95045 |
+
"epoch": 15.463817663817665,
|
| 95046 |
+
"grad_norm": 0.18291400372982025,
|
| 95047 |
+
"learning_rate": 6.580268711575244e-06,
|
| 95048 |
+
"loss": 0.9553,
|
| 95049 |
+
"step": 13577
|
| 95050 |
+
},
|
| 95051 |
+
{
|
| 95052 |
+
"epoch": 15.464957264957265,
|
| 95053 |
+
"grad_norm": 0.18735671043395996,
|
| 95054 |
+
"learning_rate": 6.577118854407297e-06,
|
| 95055 |
+
"loss": 0.7603,
|
| 95056 |
+
"step": 13578
|
| 95057 |
+
},
|
| 95058 |
+
{
|
| 95059 |
+
"epoch": 15.466096866096866,
|
| 95060 |
+
"grad_norm": 0.2598130404949188,
|
| 95061 |
+
"learning_rate": 6.573969637116673e-06,
|
| 95062 |
+
"loss": 0.7535,
|
| 95063 |
+
"step": 13579
|
| 95064 |
+
},
|
| 95065 |
+
{
|
| 95066 |
+
"epoch": 15.467236467236468,
|
| 95067 |
+
"grad_norm": 0.20607733726501465,
|
| 95068 |
+
"learning_rate": 6.570821059812757e-06,
|
| 95069 |
+
"loss": 0.7439,
|
| 95070 |
+
"step": 13580
|
| 95071 |
+
},
|
| 95072 |
+
{
|
| 95073 |
+
"epoch": 15.468376068376068,
|
| 95074 |
+
"grad_norm": 0.2689054310321808,
|
| 95075 |
+
"learning_rate": 6.5676731226049056e-06,
|
| 95076 |
+
"loss": 0.5412,
|
| 95077 |
+
"step": 13581
|
| 95078 |
+
},
|
| 95079 |
+
{
|
| 95080 |
+
"epoch": 15.469515669515669,
|
| 95081 |
+
"grad_norm": 0.18888936936855316,
|
| 95082 |
+
"learning_rate": 6.564525825602464e-06,
|
| 95083 |
+
"loss": 0.7777,
|
| 95084 |
+
"step": 13582
|
| 95085 |
+
},
|
| 95086 |
+
{
|
| 95087 |
+
"epoch": 15.470655270655271,
|
| 95088 |
+
"grad_norm": 0.25411272048950195,
|
| 95089 |
+
"learning_rate": 6.561379168914731e-06,
|
| 95090 |
+
"loss": 0.4327,
|
| 95091 |
+
"step": 13583
|
| 95092 |
+
},
|
| 95093 |
+
{
|
| 95094 |
+
"epoch": 15.471794871794872,
|
| 95095 |
+
"grad_norm": 0.15883229672908783,
|
| 95096 |
+
"learning_rate": 6.5582331526510026e-06,
|
| 95097 |
+
"loss": 0.5527,
|
| 95098 |
+
"step": 13584
|
| 95099 |
+
},
|
| 95100 |
+
{
|
| 95101 |
+
"epoch": 15.472934472934472,
|
| 95102 |
+
"grad_norm": 0.2070358544588089,
|
| 95103 |
+
"learning_rate": 6.555087776920554e-06,
|
| 95104 |
+
"loss": 0.7144,
|
| 95105 |
+
"step": 13585
|
| 95106 |
+
},
|
| 95107 |
+
{
|
| 95108 |
+
"epoch": 15.474074074074075,
|
| 95109 |
+
"grad_norm": 0.20985698699951172,
|
| 95110 |
+
"learning_rate": 6.55194304183264e-06,
|
| 95111 |
+
"loss": 0.7495,
|
| 95112 |
+
"step": 13586
|
| 95113 |
+
},
|
| 95114 |
+
{
|
| 95115 |
+
"epoch": 15.475213675213675,
|
| 95116 |
+
"grad_norm": 0.23107481002807617,
|
| 95117 |
+
"learning_rate": 6.548798947496465e-06,
|
| 95118 |
+
"loss": 0.6298,
|
| 95119 |
+
"step": 13587
|
| 95120 |
+
},
|
| 95121 |
+
{
|
| 95122 |
+
"epoch": 15.476353276353276,
|
| 95123 |
+
"grad_norm": 0.18231339752674103,
|
| 95124 |
+
"learning_rate": 6.5456554940212465e-06,
|
| 95125 |
+
"loss": 0.7531,
|
| 95126 |
+
"step": 13588
|
| 95127 |
+
},
|
| 95128 |
+
{
|
| 95129 |
+
"epoch": 15.477492877492878,
|
| 95130 |
+
"grad_norm": 0.17274364829063416,
|
| 95131 |
+
"learning_rate": 6.542512681516161e-06,
|
| 95132 |
+
"loss": 0.7785,
|
| 95133 |
+
"step": 13589
|
| 95134 |
+
},
|
| 95135 |
+
{
|
| 95136 |
+
"epoch": 15.478632478632479,
|
| 95137 |
+
"grad_norm": 0.21576517820358276,
|
| 95138 |
+
"learning_rate": 6.53937051009037e-06,
|
| 95139 |
+
"loss": 0.9112,
|
| 95140 |
+
"step": 13590
|
| 95141 |
+
},
|
| 95142 |
+
{
|
| 95143 |
+
"epoch": 15.47977207977208,
|
| 95144 |
+
"grad_norm": 0.20775271952152252,
|
| 95145 |
+
"learning_rate": 6.536228979853007e-06,
|
| 95146 |
+
"loss": 0.8234,
|
| 95147 |
+
"step": 13591
|
| 95148 |
+
},
|
| 95149 |
+
{
|
| 95150 |
+
"epoch": 15.480911680911682,
|
| 95151 |
+
"grad_norm": 0.2606852650642395,
|
| 95152 |
+
"learning_rate": 6.533088090913186e-06,
|
| 95153 |
+
"loss": 0.4991,
|
| 95154 |
+
"step": 13592
|
| 95155 |
+
},
|
| 95156 |
+
{
|
| 95157 |
+
"epoch": 15.482051282051282,
|
| 95158 |
+
"grad_norm": 0.17941322922706604,
|
| 95159 |
+
"learning_rate": 6.52994784338001e-06,
|
| 95160 |
+
"loss": 0.6829,
|
| 95161 |
+
"step": 13593
|
| 95162 |
+
},
|
| 95163 |
+
{
|
| 95164 |
+
"epoch": 15.483190883190883,
|
| 95165 |
+
"grad_norm": 0.1975211352109909,
|
| 95166 |
+
"learning_rate": 6.526808237362528e-06,
|
| 95167 |
+
"loss": 0.4983,
|
| 95168 |
+
"step": 13594
|
| 95169 |
+
},
|
| 95170 |
+
{
|
| 95171 |
+
"epoch": 15.484330484330485,
|
| 95172 |
+
"grad_norm": 0.2171153724193573,
|
| 95173 |
+
"learning_rate": 6.523669272969799e-06,
|
| 95174 |
+
"loss": 0.6357,
|
| 95175 |
+
"step": 13595
|
| 95176 |
+
},
|
| 95177 |
+
{
|
| 95178 |
+
"epoch": 15.485470085470086,
|
| 95179 |
+
"grad_norm": 0.2066015899181366,
|
| 95180 |
+
"learning_rate": 6.520530950310846e-06,
|
| 95181 |
+
"loss": 0.6761,
|
| 95182 |
+
"step": 13596
|
| 95183 |
+
},
|
| 95184 |
+
{
|
| 95185 |
+
"epoch": 15.486609686609686,
|
| 95186 |
+
"grad_norm": 0.24421249330043793,
|
| 95187 |
+
"learning_rate": 6.517393269494679e-06,
|
| 95188 |
+
"loss": 0.67,
|
| 95189 |
+
"step": 13597
|
| 95190 |
+
},
|
| 95191 |
+
{
|
| 95192 |
+
"epoch": 15.487749287749288,
|
| 95193 |
+
"grad_norm": 0.18982775509357452,
|
| 95194 |
+
"learning_rate": 6.514256230630264e-06,
|
| 95195 |
+
"loss": 0.6891,
|
| 95196 |
+
"step": 13598
|
| 95197 |
+
},
|
| 95198 |
+
{
|
| 95199 |
+
"epoch": 15.488888888888889,
|
| 95200 |
+
"grad_norm": 0.2217584252357483,
|
| 95201 |
+
"learning_rate": 6.511119833826567e-06,
|
| 95202 |
+
"loss": 0.5141,
|
| 95203 |
+
"step": 13599
|
| 95204 |
+
},
|
| 95205 |
+
{
|
| 95206 |
+
"epoch": 15.49002849002849,
|
| 95207 |
+
"grad_norm": 0.19728122651576996,
|
| 95208 |
+
"learning_rate": 6.507984079192523e-06,
|
| 95209 |
+
"loss": 0.7819,
|
| 95210 |
+
"step": 13600
|
| 95211 |
+
},
|
| 95212 |
+
{
|
| 95213 |
+
"epoch": 15.491168091168092,
|
| 95214 |
+
"grad_norm": 0.20434993505477905,
|
| 95215 |
+
"learning_rate": 6.504848966837043e-06,
|
| 95216 |
+
"loss": 0.7104,
|
| 95217 |
+
"step": 13601
|
| 95218 |
+
},
|
| 95219 |
+
{
|
| 95220 |
+
"epoch": 15.492307692307692,
|
| 95221 |
+
"grad_norm": 0.2107301652431488,
|
| 95222 |
+
"learning_rate": 6.501714496869021e-06,
|
| 95223 |
+
"loss": 0.8561,
|
| 95224 |
+
"step": 13602
|
| 95225 |
+
},
|
| 95226 |
+
{
|
| 95227 |
+
"epoch": 15.493447293447293,
|
| 95228 |
+
"grad_norm": 0.17963461577892303,
|
| 95229 |
+
"learning_rate": 6.498580669397325e-06,
|
| 95230 |
+
"loss": 0.8131,
|
| 95231 |
+
"step": 13603
|
| 95232 |
+
},
|
| 95233 |
+
{
|
| 95234 |
+
"epoch": 15.494586894586895,
|
| 95235 |
+
"grad_norm": 0.19163499772548676,
|
| 95236 |
+
"learning_rate": 6.495447484530809e-06,
|
| 95237 |
+
"loss": 0.5698,
|
| 95238 |
+
"step": 13604
|
| 95239 |
+
},
|
| 95240 |
+
{
|
| 95241 |
+
"epoch": 15.495726495726496,
|
| 95242 |
+
"grad_norm": 0.1939983367919922,
|
| 95243 |
+
"learning_rate": 6.492314942378283e-06,
|
| 95244 |
+
"loss": 0.8806,
|
| 95245 |
+
"step": 13605
|
| 95246 |
+
},
|
| 95247 |
+
{
|
| 95248 |
+
"epoch": 15.496866096866096,
|
| 95249 |
+
"grad_norm": 0.21192686259746552,
|
| 95250 |
+
"learning_rate": 6.489183043048552e-06,
|
| 95251 |
+
"loss": 0.6066,
|
| 95252 |
+
"step": 13606
|
| 95253 |
+
},
|
| 95254 |
+
{
|
| 95255 |
+
"epoch": 15.498005698005699,
|
| 95256 |
+
"grad_norm": 0.15550144016742706,
|
| 95257 |
+
"learning_rate": 6.486051786650402e-06,
|
| 95258 |
+
"loss": 0.6037,
|
| 95259 |
+
"step": 13607
|
| 95260 |
+
},
|
| 95261 |
+
{
|
| 95262 |
+
"epoch": 15.4991452991453,
|
| 95263 |
+
"grad_norm": 0.19832514226436615,
|
| 95264 |
+
"learning_rate": 6.482921173292595e-06,
|
| 95265 |
+
"loss": 0.6994,
|
| 95266 |
+
"step": 13608
|
| 95267 |
+
},
|
| 95268 |
+
{
|
| 95269 |
+
"epoch": 15.5002849002849,
|
| 95270 |
+
"grad_norm": 0.21604904532432556,
|
| 95271 |
+
"learning_rate": 6.479791203083848e-06,
|
| 95272 |
+
"loss": 0.7685,
|
| 95273 |
+
"step": 13609
|
| 95274 |
+
},
|
| 95275 |
+
{
|
| 95276 |
+
"epoch": 15.501424501424502,
|
| 95277 |
+
"grad_norm": 0.21722885966300964,
|
| 95278 |
+
"learning_rate": 6.476661876132886e-06,
|
| 95279 |
+
"loss": 0.7895,
|
| 95280 |
+
"step": 13610
|
| 95281 |
+
},
|
| 95282 |
+
{
|
| 95283 |
+
"epoch": 15.502564102564103,
|
| 95284 |
+
"grad_norm": 0.2538605034351349,
|
| 95285 |
+
"learning_rate": 6.473533192548395e-06,
|
| 95286 |
+
"loss": 0.4011,
|
| 95287 |
+
"step": 13611
|
| 95288 |
+
},
|
| 95289 |
+
{
|
| 95290 |
+
"epoch": 15.503703703703703,
|
| 95291 |
+
"grad_norm": 0.22261404991149902,
|
| 95292 |
+
"learning_rate": 6.470405152439043e-06,
|
| 95293 |
+
"loss": 0.6813,
|
| 95294 |
+
"step": 13612
|
| 95295 |
+
},
|
| 95296 |
+
{
|
| 95297 |
+
"epoch": 15.504843304843305,
|
| 95298 |
+
"grad_norm": 0.18874602019786835,
|
| 95299 |
+
"learning_rate": 6.467277755913478e-06,
|
| 95300 |
+
"loss": 0.5311,
|
| 95301 |
+
"step": 13613
|
| 95302 |
+
},
|
| 95303 |
+
{
|
| 95304 |
+
"epoch": 15.505982905982906,
|
| 95305 |
+
"grad_norm": 0.24819247424602509,
|
| 95306 |
+
"learning_rate": 6.464151003080321e-06,
|
| 95307 |
+
"loss": 0.5075,
|
| 95308 |
+
"step": 13614
|
| 95309 |
+
},
|
| 95310 |
+
{
|
| 95311 |
+
"epoch": 15.507122507122507,
|
| 95312 |
+
"grad_norm": 0.1872682273387909,
|
| 95313 |
+
"learning_rate": 6.461024894048176e-06,
|
| 95314 |
+
"loss": 0.656,
|
| 95315 |
+
"step": 13615
|
| 95316 |
+
},
|
| 95317 |
+
{
|
| 95318 |
+
"epoch": 15.508262108262109,
|
| 95319 |
+
"grad_norm": 0.19362613558769226,
|
| 95320 |
+
"learning_rate": 6.457899428925624e-06,
|
| 95321 |
+
"loss": 0.7423,
|
| 95322 |
+
"step": 13616
|
| 95323 |
+
},
|
| 95324 |
+
{
|
| 95325 |
+
"epoch": 15.50940170940171,
|
| 95326 |
+
"grad_norm": 0.20935077965259552,
|
| 95327 |
+
"learning_rate": 6.454774607821206e-06,
|
| 95328 |
+
"loss": 0.67,
|
| 95329 |
+
"step": 13617
|
| 95330 |
+
},
|
| 95331 |
+
{
|
| 95332 |
+
"epoch": 15.51054131054131,
|
| 95333 |
+
"grad_norm": 0.15607993304729462,
|
| 95334 |
+
"learning_rate": 6.45165043084347e-06,
|
| 95335 |
+
"loss": 0.7793,
|
| 95336 |
+
"step": 13618
|
| 95337 |
+
},
|
| 95338 |
+
{
|
| 95339 |
+
"epoch": 15.511680911680912,
|
| 95340 |
+
"grad_norm": 0.23192988336086273,
|
| 95341 |
+
"learning_rate": 6.448526898100921e-06,
|
| 95342 |
+
"loss": 0.8127,
|
| 95343 |
+
"step": 13619
|
| 95344 |
+
},
|
| 95345 |
+
{
|
| 95346 |
+
"epoch": 15.512820512820513,
|
| 95347 |
+
"grad_norm": 0.215484619140625,
|
| 95348 |
+
"learning_rate": 6.445404009702055e-06,
|
| 95349 |
+
"loss": 0.7282,
|
| 95350 |
+
"step": 13620
|
| 95351 |
+
},
|
| 95352 |
+
{
|
| 95353 |
+
"epoch": 15.513960113960113,
|
| 95354 |
+
"grad_norm": 0.18776561319828033,
|
| 95355 |
+
"learning_rate": 6.442281765755329e-06,
|
| 95356 |
+
"loss": 0.6589,
|
| 95357 |
+
"step": 13621
|
| 95358 |
+
},
|
| 95359 |
+
{
|
| 95360 |
+
"epoch": 15.515099715099716,
|
| 95361 |
+
"grad_norm": 0.24401643872261047,
|
| 95362 |
+
"learning_rate": 6.43916016636919e-06,
|
| 95363 |
+
"loss": 0.3575,
|
| 95364 |
+
"step": 13622
|
| 95365 |
+
},
|
| 95366 |
+
{
|
| 95367 |
+
"epoch": 15.516239316239316,
|
| 95368 |
+
"grad_norm": 0.18532097339630127,
|
| 95369 |
+
"learning_rate": 6.4360392116520594e-06,
|
| 95370 |
+
"loss": 0.8261,
|
| 95371 |
+
"step": 13623
|
| 95372 |
+
},
|
| 95373 |
+
{
|
| 95374 |
+
"epoch": 15.517378917378917,
|
| 95375 |
+
"grad_norm": 0.24294257164001465,
|
| 95376 |
+
"learning_rate": 6.43291890171234e-06,
|
| 95377 |
+
"loss": 0.7725,
|
| 95378 |
+
"step": 13624
|
| 95379 |
+
},
|
| 95380 |
+
{
|
| 95381 |
+
"epoch": 15.518518518518519,
|
| 95382 |
+
"grad_norm": 0.16897542774677277,
|
| 95383 |
+
"learning_rate": 6.429799236658404e-06,
|
| 95384 |
+
"loss": 0.8488,
|
| 95385 |
+
"step": 13625
|
| 95386 |
+
},
|
| 95387 |
+
{
|
| 95388 |
+
"epoch": 15.51965811965812,
|
| 95389 |
+
"grad_norm": 0.22571931779384613,
|
| 95390 |
+
"learning_rate": 6.426680216598613e-06,
|
| 95391 |
+
"loss": 0.5263,
|
| 95392 |
+
"step": 13626
|
| 95393 |
+
},
|
| 95394 |
+
{
|
| 95395 |
+
"epoch": 15.52079772079772,
|
| 95396 |
+
"grad_norm": 0.18616579473018646,
|
| 95397 |
+
"learning_rate": 6.4235618416412986e-06,
|
| 95398 |
+
"loss": 0.5997,
|
| 95399 |
+
"step": 13627
|
| 95400 |
+
},
|
| 95401 |
+
{
|
| 95402 |
+
"epoch": 15.521937321937322,
|
| 95403 |
+
"grad_norm": 0.1776077151298523,
|
| 95404 |
+
"learning_rate": 6.420444111894761e-06,
|
| 95405 |
+
"loss": 0.5849,
|
| 95406 |
+
"step": 13628
|
| 95407 |
+
},
|
| 95408 |
+
{
|
| 95409 |
+
"epoch": 15.523076923076923,
|
| 95410 |
+
"grad_norm": 0.17871063947677612,
|
| 95411 |
+
"learning_rate": 6.417327027467293e-06,
|
| 95412 |
+
"loss": 0.6076,
|
| 95413 |
+
"step": 13629
|
| 95414 |
+
},
|
| 95415 |
+
{
|
| 95416 |
+
"epoch": 15.524216524216524,
|
| 95417 |
+
"grad_norm": 0.203303724527359,
|
| 95418 |
+
"learning_rate": 6.414210588467162e-06,
|
| 95419 |
+
"loss": 0.6325,
|
| 95420 |
+
"step": 13630
|
| 95421 |
+
},
|
| 95422 |
+
{
|
| 95423 |
+
"epoch": 15.525356125356126,
|
| 95424 |
+
"grad_norm": 0.17372427880764008,
|
| 95425 |
+
"learning_rate": 6.411094795002612e-06,
|
| 95426 |
+
"loss": 0.8,
|
| 95427 |
+
"step": 13631
|
| 95428 |
+
},
|
| 95429 |
+
{
|
| 95430 |
+
"epoch": 15.526495726495726,
|
| 95431 |
+
"grad_norm": 0.22373448312282562,
|
| 95432 |
+
"learning_rate": 6.407979647181855e-06,
|
| 95433 |
+
"loss": 0.735,
|
| 95434 |
+
"step": 13632
|
| 95435 |
+
},
|
| 95436 |
+
{
|
| 95437 |
+
"epoch": 15.527635327635327,
|
| 95438 |
+
"grad_norm": 0.2009502649307251,
|
| 95439 |
+
"learning_rate": 6.404865145113093e-06,
|
| 95440 |
+
"loss": 0.5968,
|
| 95441 |
+
"step": 13633
|
| 95442 |
+
},
|
| 95443 |
+
{
|
| 95444 |
+
"epoch": 15.52877492877493,
|
| 95445 |
+
"grad_norm": 0.24295362830162048,
|
| 95446 |
+
"learning_rate": 6.401751288904498e-06,
|
| 95447 |
+
"loss": 0.616,
|
| 95448 |
+
"step": 13634
|
| 95449 |
+
},
|
| 95450 |
+
{
|
| 95451 |
+
"epoch": 15.52991452991453,
|
| 95452 |
+
"grad_norm": 0.2393190711736679,
|
| 95453 |
+
"learning_rate": 6.398638078664229e-06,
|
| 95454 |
+
"loss": 0.7765,
|
| 95455 |
+
"step": 13635
|
| 95456 |
+
},
|
| 95457 |
+
{
|
| 95458 |
+
"epoch": 15.53105413105413,
|
| 95459 |
+
"grad_norm": 0.1962868869304657,
|
| 95460 |
+
"learning_rate": 6.3955255145004135e-06,
|
| 95461 |
+
"loss": 0.6915,
|
| 95462 |
+
"step": 13636
|
| 95463 |
+
},
|
| 95464 |
+
{
|
| 95465 |
+
"epoch": 15.532193732193733,
|
| 95466 |
+
"grad_norm": 0.34747734665870667,
|
| 95467 |
+
"learning_rate": 6.3924135965211605e-06,
|
| 95468 |
+
"loss": 0.8085,
|
| 95469 |
+
"step": 13637
|
| 95470 |
+
},
|
| 95471 |
+
{
|
| 95472 |
+
"epoch": 15.533333333333333,
|
| 95473 |
+
"grad_norm": 0.20524170994758606,
|
| 95474 |
+
"learning_rate": 6.389302324834559e-06,
|
| 95475 |
+
"loss": 0.742,
|
| 95476 |
+
"step": 13638
|
| 95477 |
+
},
|
| 95478 |
+
{
|
| 95479 |
+
"epoch": 15.534472934472934,
|
| 95480 |
+
"grad_norm": 0.2063647210597992,
|
| 95481 |
+
"learning_rate": 6.38619169954866e-06,
|
| 95482 |
+
"loss": 0.5466,
|
| 95483 |
+
"step": 13639
|
| 95484 |
+
},
|
| 95485 |
+
{
|
| 95486 |
+
"epoch": 15.535612535612536,
|
| 95487 |
+
"grad_norm": 0.2075195014476776,
|
| 95488 |
+
"learning_rate": 6.383081720771514e-06,
|
| 95489 |
+
"loss": 0.7451,
|
| 95490 |
+
"step": 13640
|
| 95491 |
+
},
|
| 95492 |
+
{
|
| 95493 |
+
"epoch": 15.536752136752137,
|
| 95494 |
+
"grad_norm": 0.17599990963935852,
|
| 95495 |
+
"learning_rate": 6.379972388611136e-06,
|
| 95496 |
+
"loss": 0.698,
|
| 95497 |
+
"step": 13641
|
| 95498 |
+
},
|
| 95499 |
+
{
|
| 95500 |
+
"epoch": 15.537891737891737,
|
| 95501 |
+
"grad_norm": 0.19163137674331665,
|
| 95502 |
+
"learning_rate": 6.376863703175528e-06,
|
| 95503 |
+
"loss": 0.8553,
|
| 95504 |
+
"step": 13642
|
| 95505 |
+
},
|
| 95506 |
+
{
|
| 95507 |
+
"epoch": 15.53903133903134,
|
| 95508 |
+
"grad_norm": 0.18536020815372467,
|
| 95509 |
+
"learning_rate": 6.37375566457265e-06,
|
| 95510 |
+
"loss": 0.635,
|
| 95511 |
+
"step": 13643
|
| 95512 |
+
},
|
| 95513 |
+
{
|
| 95514 |
+
"epoch": 15.54017094017094,
|
| 95515 |
+
"grad_norm": 0.22451657056808472,
|
| 95516 |
+
"learning_rate": 6.370648272910462e-06,
|
| 95517 |
+
"loss": 0.5601,
|
| 95518 |
+
"step": 13644
|
| 95519 |
+
},
|
| 95520 |
+
{
|
| 95521 |
+
"epoch": 15.54131054131054,
|
| 95522 |
+
"grad_norm": 0.2571554481983185,
|
| 95523 |
+
"learning_rate": 6.367541528296889e-06,
|
| 95524 |
+
"loss": 0.6696,
|
| 95525 |
+
"step": 13645
|
| 95526 |
+
},
|
| 95527 |
+
{
|
| 95528 |
+
"epoch": 15.542450142450143,
|
| 95529 |
+
"grad_norm": 1.3970999717712402,
|
| 95530 |
+
"learning_rate": 6.364435430839838e-06,
|
| 95531 |
+
"loss": 0.6399,
|
| 95532 |
+
"step": 13646
|
| 95533 |
+
},
|
| 95534 |
+
{
|
| 95535 |
+
"epoch": 15.543589743589743,
|
| 95536 |
+
"grad_norm": 0.21825458109378815,
|
| 95537 |
+
"learning_rate": 6.361329980647194e-06,
|
| 95538 |
+
"loss": 0.704,
|
| 95539 |
+
"step": 13647
|
| 95540 |
+
},
|
| 95541 |
+
{
|
| 95542 |
+
"epoch": 15.544729344729344,
|
| 95543 |
+
"grad_norm": 0.16594573855400085,
|
| 95544 |
+
"learning_rate": 6.358225177826812e-06,
|
| 95545 |
+
"loss": 0.6154,
|
| 95546 |
+
"step": 13648
|
| 95547 |
+
},
|
| 95548 |
+
{
|
| 95549 |
+
"epoch": 15.545868945868946,
|
| 95550 |
+
"grad_norm": 0.1690720170736313,
|
| 95551 |
+
"learning_rate": 6.355121022486546e-06,
|
| 95552 |
+
"loss": 0.9228,
|
| 95553 |
+
"step": 13649
|
| 95554 |
+
},
|
| 95555 |
+
{
|
| 95556 |
+
"epoch": 15.547008547008547,
|
| 95557 |
+
"grad_norm": 0.23778723180294037,
|
| 95558 |
+
"learning_rate": 6.352017514734193e-06,
|
| 95559 |
+
"loss": 0.4943,
|
| 95560 |
+
"step": 13650
|
| 95561 |
+
},
|
| 95562 |
+
{
|
| 95563 |
+
"epoch": 15.548148148148147,
|
| 95564 |
+
"grad_norm": 0.23354555666446686,
|
| 95565 |
+
"learning_rate": 6.348914654677554e-06,
|
| 95566 |
+
"loss": 0.3579,
|
| 95567 |
+
"step": 13651
|
| 95568 |
+
},
|
| 95569 |
+
{
|
| 95570 |
+
"epoch": 15.54928774928775,
|
| 95571 |
+
"grad_norm": 0.22613407671451569,
|
| 95572 |
+
"learning_rate": 6.345812442424398e-06,
|
| 95573 |
+
"loss": 0.552,
|
| 95574 |
+
"step": 13652
|
| 95575 |
+
},
|
| 95576 |
+
{
|
| 95577 |
+
"epoch": 15.55042735042735,
|
| 95578 |
+
"grad_norm": 0.19844311475753784,
|
| 95579 |
+
"learning_rate": 6.342710878082478e-06,
|
| 95580 |
+
"loss": 0.7388,
|
| 95581 |
+
"step": 13653
|
| 95582 |
+
},
|
| 95583 |
+
{
|
| 95584 |
+
"epoch": 15.55156695156695,
|
| 95585 |
+
"grad_norm": 0.17051514983177185,
|
| 95586 |
+
"learning_rate": 6.339609961759521e-06,
|
| 95587 |
+
"loss": 0.7468,
|
| 95588 |
+
"step": 13654
|
| 95589 |
+
},
|
| 95590 |
+
{
|
| 95591 |
+
"epoch": 15.552706552706553,
|
| 95592 |
+
"grad_norm": 0.2350083738565445,
|
| 95593 |
+
"learning_rate": 6.33650969356322e-06,
|
| 95594 |
+
"loss": 0.6674,
|
| 95595 |
+
"step": 13655
|
| 95596 |
+
},
|
| 95597 |
+
{
|
| 95598 |
+
"epoch": 15.553846153846154,
|
| 95599 |
+
"grad_norm": 0.21361273527145386,
|
| 95600 |
+
"learning_rate": 6.3334100736012644e-06,
|
| 95601 |
+
"loss": 0.5688,
|
| 95602 |
+
"step": 13656
|
| 95603 |
+
},
|
| 95604 |
+
{
|
| 95605 |
+
"epoch": 15.554985754985754,
|
| 95606 |
+
"grad_norm": 0.18314236402511597,
|
| 95607 |
+
"learning_rate": 6.330311101981307e-06,
|
| 95608 |
+
"loss": 0.6635,
|
| 95609 |
+
"step": 13657
|
| 95610 |
+
},
|
| 95611 |
+
{
|
| 95612 |
+
"epoch": 15.556125356125357,
|
| 95613 |
+
"grad_norm": 0.2125498503446579,
|
| 95614 |
+
"learning_rate": 6.32721277881099e-06,
|
| 95615 |
+
"loss": 0.5927,
|
| 95616 |
+
"step": 13658
|
| 95617 |
+
},
|
| 95618 |
+
{
|
| 95619 |
+
"epoch": 15.557264957264957,
|
| 95620 |
+
"grad_norm": 0.21594832837581635,
|
| 95621 |
+
"learning_rate": 6.324115104197919e-06,
|
| 95622 |
+
"loss": 0.6365,
|
| 95623 |
+
"step": 13659
|
| 95624 |
+
},
|
| 95625 |
+
{
|
| 95626 |
+
"epoch": 15.558404558404558,
|
| 95627 |
+
"grad_norm": 0.2782728374004364,
|
| 95628 |
+
"learning_rate": 6.321018078249693e-06,
|
| 95629 |
+
"loss": 0.6943,
|
| 95630 |
+
"step": 13660
|
| 95631 |
+
},
|
| 95632 |
+
{
|
| 95633 |
+
"epoch": 15.55954415954416,
|
| 95634 |
+
"grad_norm": 0.18271590769290924,
|
| 95635 |
+
"learning_rate": 6.317921701073884e-06,
|
| 95636 |
+
"loss": 0.7358,
|
| 95637 |
+
"step": 13661
|
| 95638 |
+
},
|
| 95639 |
+
{
|
| 95640 |
+
"epoch": 15.56068376068376,
|
| 95641 |
+
"grad_norm": 0.19562652707099915,
|
| 95642 |
+
"learning_rate": 6.314825972778022e-06,
|
| 95643 |
+
"loss": 0.6251,
|
| 95644 |
+
"step": 13662
|
| 95645 |
+
},
|
| 95646 |
+
{
|
| 95647 |
+
"epoch": 15.561823361823361,
|
| 95648 |
+
"grad_norm": 0.2306443750858307,
|
| 95649 |
+
"learning_rate": 6.311730893469636e-06,
|
| 95650 |
+
"loss": 0.5493,
|
| 95651 |
+
"step": 13663
|
| 95652 |
+
},
|
| 95653 |
+
{
|
| 95654 |
+
"epoch": 15.562962962962963,
|
| 95655 |
+
"grad_norm": 0.2782440781593323,
|
| 95656 |
+
"learning_rate": 6.3086364632562316e-06,
|
| 95657 |
+
"loss": 0.6875,
|
| 95658 |
+
"step": 13664
|
| 95659 |
+
},
|
| 95660 |
+
{
|
| 95661 |
+
"epoch": 15.564102564102564,
|
| 95662 |
+
"grad_norm": 0.16360704600811005,
|
| 95663 |
+
"learning_rate": 6.305542682245291e-06,
|
| 95664 |
+
"loss": 0.6351,
|
| 95665 |
+
"step": 13665
|
| 95666 |
+
},
|
| 95667 |
+
{
|
| 95668 |
+
"epoch": 15.565242165242164,
|
| 95669 |
+
"grad_norm": 0.2210601568222046,
|
| 95670 |
+
"learning_rate": 6.302449550544256e-06,
|
| 95671 |
+
"loss": 0.5766,
|
| 95672 |
+
"step": 13666
|
| 95673 |
+
},
|
| 95674 |
+
{
|
| 95675 |
+
"epoch": 15.566381766381767,
|
| 95676 |
+
"grad_norm": 0.22705049812793732,
|
| 95677 |
+
"learning_rate": 6.299357068260567e-06,
|
| 95678 |
+
"loss": 0.3935,
|
| 95679 |
+
"step": 13667
|
| 95680 |
+
},
|
| 95681 |
+
{
|
| 95682 |
+
"epoch": 15.567521367521367,
|
| 95683 |
+
"grad_norm": 0.2909753620624542,
|
| 95684 |
+
"learning_rate": 6.296265235501634e-06,
|
| 95685 |
+
"loss": 0.4501,
|
| 95686 |
+
"step": 13668
|
| 95687 |
+
},
|
| 95688 |
+
{
|
| 95689 |
+
"epoch": 15.568660968660968,
|
| 95690 |
+
"grad_norm": 0.23857071995735168,
|
| 95691 |
+
"learning_rate": 6.293174052374845e-06,
|
| 95692 |
+
"loss": 0.586,
|
| 95693 |
+
"step": 13669
|
| 95694 |
+
},
|
| 95695 |
+
{
|
| 95696 |
+
"epoch": 15.56980056980057,
|
| 95697 |
+
"grad_norm": 0.19779235124588013,
|
| 95698 |
+
"learning_rate": 6.290083518987563e-06,
|
| 95699 |
+
"loss": 0.4547,
|
| 95700 |
+
"step": 13670
|
| 95701 |
+
},
|
| 95702 |
+
{
|
| 95703 |
+
"epoch": 15.57094017094017,
|
| 95704 |
+
"grad_norm": 0.2003849744796753,
|
| 95705 |
+
"learning_rate": 6.286993635447136e-06,
|
| 95706 |
+
"loss": 0.7345,
|
| 95707 |
+
"step": 13671
|
| 95708 |
+
},
|
| 95709 |
+
{
|
| 95710 |
+
"epoch": 15.572079772079771,
|
| 95711 |
+
"grad_norm": 0.188863605260849,
|
| 95712 |
+
"learning_rate": 6.283904401860885e-06,
|
| 95713 |
+
"loss": 0.6969,
|
| 95714 |
+
"step": 13672
|
| 95715 |
+
},
|
| 95716 |
+
{
|
| 95717 |
+
"epoch": 15.573219373219374,
|
| 95718 |
+
"grad_norm": 0.23119278252124786,
|
| 95719 |
+
"learning_rate": 6.2808158183361e-06,
|
| 95720 |
+
"loss": 0.5791,
|
| 95721 |
+
"step": 13673
|
| 95722 |
+
},
|
| 95723 |
+
{
|
| 95724 |
+
"epoch": 15.574358974358974,
|
| 95725 |
+
"grad_norm": 0.19105198979377747,
|
| 95726 |
+
"learning_rate": 6.277727884980056e-06,
|
| 95727 |
+
"loss": 0.5908,
|
| 95728 |
+
"step": 13674
|
| 95729 |
+
},
|
| 95730 |
+
{
|
| 95731 |
+
"epoch": 15.575498575498575,
|
| 95732 |
+
"grad_norm": 0.20295053720474243,
|
| 95733 |
+
"learning_rate": 6.274640601900012e-06,
|
| 95734 |
+
"loss": 0.5843,
|
| 95735 |
+
"step": 13675
|
| 95736 |
+
},
|
| 95737 |
+
{
|
| 95738 |
+
"epoch": 15.576638176638177,
|
| 95739 |
+
"grad_norm": 0.18536078929901123,
|
| 95740 |
+
"learning_rate": 6.2715539692032e-06,
|
| 95741 |
+
"loss": 0.723,
|
| 95742 |
+
"step": 13676
|
| 95743 |
+
},
|
| 95744 |
+
{
|
| 95745 |
+
"epoch": 15.577777777777778,
|
| 95746 |
+
"grad_norm": 0.18521544337272644,
|
| 95747 |
+
"learning_rate": 6.2684679869968145e-06,
|
| 95748 |
+
"loss": 0.8696,
|
| 95749 |
+
"step": 13677
|
| 95750 |
+
},
|
| 95751 |
+
{
|
| 95752 |
+
"epoch": 15.578917378917378,
|
| 95753 |
+
"grad_norm": 0.19663411378860474,
|
| 95754 |
+
"learning_rate": 6.26538265538805e-06,
|
| 95755 |
+
"loss": 0.9285,
|
| 95756 |
+
"step": 13678
|
| 95757 |
+
},
|
| 95758 |
+
{
|
| 95759 |
+
"epoch": 15.58005698005698,
|
| 95760 |
+
"grad_norm": 0.22954058647155762,
|
| 95761 |
+
"learning_rate": 6.262297974484063e-06,
|
| 95762 |
+
"loss": 0.4636,
|
| 95763 |
+
"step": 13679
|
| 95764 |
+
},
|
| 95765 |
+
{
|
| 95766 |
+
"epoch": 15.581196581196581,
|
| 95767 |
+
"grad_norm": 0.19672894477844238,
|
| 95768 |
+
"learning_rate": 6.259213944392001e-06,
|
| 95769 |
+
"loss": 0.6554,
|
| 95770 |
+
"step": 13680
|
| 95771 |
+
},
|
| 95772 |
+
{
|
| 95773 |
+
"epoch": 15.582336182336181,
|
| 95774 |
+
"grad_norm": 0.23419034481048584,
|
| 95775 |
+
"learning_rate": 6.256130565218971e-06,
|
| 95776 |
+
"loss": 0.4539,
|
| 95777 |
+
"step": 13681
|
| 95778 |
+
},
|
| 95779 |
+
{
|
| 95780 |
+
"epoch": 15.583475783475784,
|
| 95781 |
+
"grad_norm": 0.16873398423194885,
|
| 95782 |
+
"learning_rate": 6.2530478370720765e-06,
|
| 95783 |
+
"loss": 0.4983,
|
| 95784 |
+
"step": 13682
|
| 95785 |
+
},
|
| 95786 |
+
{
|
| 95787 |
+
"epoch": 15.584615384615384,
|
| 95788 |
+
"grad_norm": 0.22072651982307434,
|
| 95789 |
+
"learning_rate": 6.249965760058391e-06,
|
| 95790 |
+
"loss": 0.5829,
|
| 95791 |
+
"step": 13683
|
| 95792 |
+
},
|
| 95793 |
+
{
|
| 95794 |
+
"epoch": 15.585754985754985,
|
| 95795 |
+
"grad_norm": 0.18701456487178802,
|
| 95796 |
+
"learning_rate": 6.246884334284947e-06,
|
| 95797 |
+
"loss": 0.8002,
|
| 95798 |
+
"step": 13684
|
| 95799 |
+
},
|
| 95800 |
+
{
|
| 95801 |
+
"epoch": 15.586894586894587,
|
| 95802 |
+
"grad_norm": 0.1927860826253891,
|
| 95803 |
+
"learning_rate": 6.243803559858785e-06,
|
| 95804 |
+
"loss": 0.6156,
|
| 95805 |
+
"step": 13685
|
| 95806 |
+
},
|
| 95807 |
+
{
|
| 95808 |
+
"epoch": 15.588034188034188,
|
| 95809 |
+
"grad_norm": 0.22001326084136963,
|
| 95810 |
+
"learning_rate": 6.240723436886903e-06,
|
| 95811 |
+
"loss": 0.6379,
|
| 95812 |
+
"step": 13686
|
| 95813 |
+
},
|
| 95814 |
+
{
|
| 95815 |
+
"epoch": 15.589173789173788,
|
| 95816 |
+
"grad_norm": 0.18028047680854797,
|
| 95817 |
+
"learning_rate": 6.237643965476292e-06,
|
| 95818 |
+
"loss": 0.8061,
|
| 95819 |
+
"step": 13687
|
| 95820 |
+
},
|
| 95821 |
+
{
|
| 95822 |
+
"epoch": 15.59031339031339,
|
| 95823 |
+
"grad_norm": 0.20484380424022675,
|
| 95824 |
+
"learning_rate": 6.234565145733898e-06,
|
| 95825 |
+
"loss": 0.6586,
|
| 95826 |
+
"step": 13688
|
| 95827 |
+
},
|
| 95828 |
+
{
|
| 95829 |
+
"epoch": 15.591452991452991,
|
| 95830 |
+
"grad_norm": 0.2841224670410156,
|
| 95831 |
+
"learning_rate": 6.231486977766657e-06,
|
| 95832 |
+
"loss": 0.4662,
|
| 95833 |
+
"step": 13689
|
| 95834 |
+
},
|
| 95835 |
+
{
|
| 95836 |
+
"epoch": 15.592592592592592,
|
| 95837 |
+
"grad_norm": 0.27535203099250793,
|
| 95838 |
+
"learning_rate": 6.228409461681484e-06,
|
| 95839 |
+
"loss": 0.7547,
|
| 95840 |
+
"step": 13690
|
| 95841 |
+
},
|
| 95842 |
+
{
|
| 95843 |
+
"epoch": 15.593732193732194,
|
| 95844 |
+
"grad_norm": 0.23370136320590973,
|
| 95845 |
+
"learning_rate": 6.2253325975852844e-06,
|
| 95846 |
+
"loss": 0.6202,
|
| 95847 |
+
"step": 13691
|
| 95848 |
+
},
|
| 95849 |
+
{
|
| 95850 |
+
"epoch": 15.594871794871795,
|
| 95851 |
+
"grad_norm": 0.20593878626823425,
|
| 95852 |
+
"learning_rate": 6.222256385584907e-06,
|
| 95853 |
+
"loss": 0.4472,
|
| 95854 |
+
"step": 13692
|
| 95855 |
+
},
|
| 95856 |
+
{
|
| 95857 |
+
"epoch": 15.596011396011395,
|
| 95858 |
+
"grad_norm": 0.17125186324119568,
|
| 95859 |
+
"learning_rate": 6.219180825787204e-06,
|
| 95860 |
+
"loss": 0.7245,
|
| 95861 |
+
"step": 13693
|
| 95862 |
+
},
|
| 95863 |
+
{
|
| 95864 |
+
"epoch": 15.597150997150997,
|
| 95865 |
+
"grad_norm": 0.19655224680900574,
|
| 95866 |
+
"learning_rate": 6.216105918299e-06,
|
| 95867 |
+
"loss": 0.5892,
|
| 95868 |
+
"step": 13694
|
| 95869 |
+
},
|
| 95870 |
+
{
|
| 95871 |
+
"epoch": 15.598290598290598,
|
| 95872 |
+
"grad_norm": 0.17949378490447998,
|
| 95873 |
+
"learning_rate": 6.2130316632271e-06,
|
| 95874 |
+
"loss": 0.4656,
|
| 95875 |
+
"step": 13695
|
| 95876 |
+
},
|
| 95877 |
+
{
|
| 95878 |
+
"epoch": 15.5994301994302,
|
| 95879 |
+
"grad_norm": 0.17048440873622894,
|
| 95880 |
+
"learning_rate": 6.20995806067827e-06,
|
| 95881 |
+
"loss": 0.6455,
|
| 95882 |
+
"step": 13696
|
| 95883 |
+
},
|
| 95884 |
+
{
|
| 95885 |
+
"epoch": 15.6005698005698,
|
| 95886 |
+
"grad_norm": 0.16665752232074738,
|
| 95887 |
+
"learning_rate": 6.2068851107592645e-06,
|
| 95888 |
+
"loss": 0.7673,
|
| 95889 |
+
"step": 13697
|
| 95890 |
+
},
|
| 95891 |
+
{
|
| 95892 |
+
"epoch": 15.601709401709401,
|
| 95893 |
+
"grad_norm": 0.22793520987033844,
|
| 95894 |
+
"learning_rate": 6.203812813576823e-06,
|
| 95895 |
+
"loss": 0.7257,
|
| 95896 |
+
"step": 13698
|
| 95897 |
+
},
|
| 95898 |
+
{
|
| 95899 |
+
"epoch": 15.602849002849004,
|
| 95900 |
+
"grad_norm": 0.20825371146202087,
|
| 95901 |
+
"learning_rate": 6.200741169237659e-06,
|
| 95902 |
+
"loss": 0.519,
|
| 95903 |
+
"step": 13699
|
| 95904 |
+
},
|
| 95905 |
+
{
|
| 95906 |
+
"epoch": 15.603988603988604,
|
| 95907 |
+
"grad_norm": 0.22275830805301666,
|
| 95908 |
+
"learning_rate": 6.197670177848447e-06,
|
| 95909 |
+
"loss": 0.5398,
|
| 95910 |
+
"step": 13700
|
| 95911 |
+
},
|
| 95912 |
+
{
|
| 95913 |
+
"epoch": 15.605128205128205,
|
| 95914 |
+
"grad_norm": 0.16599951684474945,
|
| 95915 |
+
"learning_rate": 6.194599839515846e-06,
|
| 95916 |
+
"loss": 0.8594,
|
| 95917 |
+
"step": 13701
|
| 95918 |
+
},
|
| 95919 |
+
{
|
| 95920 |
+
"epoch": 15.606267806267807,
|
| 95921 |
+
"grad_norm": 0.20247229933738708,
|
| 95922 |
+
"learning_rate": 6.191530154346523e-06,
|
| 95923 |
+
"loss": 0.9489,
|
| 95924 |
+
"step": 13702
|
| 95925 |
+
},
|
| 95926 |
+
{
|
| 95927 |
+
"epoch": 15.607407407407408,
|
| 95928 |
+
"grad_norm": 0.19792650640010834,
|
| 95929 |
+
"learning_rate": 6.188461122447075e-06,
|
| 95930 |
+
"loss": 0.5835,
|
| 95931 |
+
"step": 13703
|
| 95932 |
+
},
|
| 95933 |
+
{
|
| 95934 |
+
"epoch": 15.608547008547008,
|
| 95935 |
+
"grad_norm": 0.1858179271221161,
|
| 95936 |
+
"learning_rate": 6.185392743924104e-06,
|
| 95937 |
+
"loss": 0.651,
|
| 95938 |
+
"step": 13704
|
| 95939 |
+
},
|
| 95940 |
+
{
|
| 95941 |
+
"epoch": 15.60968660968661,
|
| 95942 |
+
"grad_norm": 0.1663610339164734,
|
| 95943 |
+
"learning_rate": 6.182325018884183e-06,
|
| 95944 |
+
"loss": 0.5449,
|
| 95945 |
+
"step": 13705
|
| 95946 |
+
},
|
| 95947 |
+
{
|
| 95948 |
+
"epoch": 15.610826210826211,
|
| 95949 |
+
"grad_norm": 0.19580359756946564,
|
| 95950 |
+
"learning_rate": 6.17925794743387e-06,
|
| 95951 |
+
"loss": 0.6482,
|
| 95952 |
+
"step": 13706
|
| 95953 |
+
},
|
| 95954 |
+
{
|
| 95955 |
+
"epoch": 15.611965811965812,
|
| 95956 |
+
"grad_norm": 0.21123597025871277,
|
| 95957 |
+
"learning_rate": 6.176191529679678e-06,
|
| 95958 |
+
"loss": 0.6836,
|
| 95959 |
+
"step": 13707
|
| 95960 |
+
},
|
| 95961 |
+
{
|
| 95962 |
+
"epoch": 15.613105413105414,
|
| 95963 |
+
"grad_norm": 0.18846312165260315,
|
| 95964 |
+
"learning_rate": 6.173125765728122e-06,
|
| 95965 |
+
"loss": 0.5522,
|
| 95966 |
+
"step": 13708
|
| 95967 |
+
},
|
| 95968 |
+
{
|
| 95969 |
+
"epoch": 15.614245014245014,
|
| 95970 |
+
"grad_norm": 0.1801503747701645,
|
| 95971 |
+
"learning_rate": 6.1700606556856805e-06,
|
| 95972 |
+
"loss": 0.7241,
|
| 95973 |
+
"step": 13709
|
| 95974 |
+
},
|
| 95975 |
+
{
|
| 95976 |
+
"epoch": 15.615384615384615,
|
| 95977 |
+
"grad_norm": 0.2200639843940735,
|
| 95978 |
+
"learning_rate": 6.1669961996588195e-06,
|
| 95979 |
+
"loss": 0.7103,
|
| 95980 |
+
"step": 13710
|
| 95981 |
+
},
|
| 95982 |
+
{
|
| 95983 |
+
"epoch": 15.616524216524217,
|
| 95984 |
+
"grad_norm": 0.19399894773960114,
|
| 95985 |
+
"learning_rate": 6.163932397753969e-06,
|
| 95986 |
+
"loss": 0.6425,
|
| 95987 |
+
"step": 13711
|
| 95988 |
+
},
|
| 95989 |
+
{
|
| 95990 |
+
"epoch": 15.617663817663818,
|
| 95991 |
+
"grad_norm": 0.2099304497241974,
|
| 95992 |
+
"learning_rate": 6.160869250077536e-06,
|
| 95993 |
+
"loss": 0.74,
|
| 95994 |
+
"step": 13712
|
| 95995 |
+
},
|
| 95996 |
+
{
|
| 95997 |
+
"epoch": 15.618803418803418,
|
| 95998 |
+
"grad_norm": 0.2581200897693634,
|
| 95999 |
+
"learning_rate": 6.157806756735937e-06,
|
| 96000 |
+
"loss": 0.5516,
|
| 96001 |
+
"step": 13713
|
| 96002 |
+
},
|
| 96003 |
+
{
|
| 96004 |
+
"epoch": 15.61994301994302,
|
| 96005 |
+
"grad_norm": 0.21245378255844116,
|
| 96006 |
+
"learning_rate": 6.1547449178355174e-06,
|
| 96007 |
+
"loss": 0.4188,
|
| 96008 |
+
"step": 13714
|
| 96009 |
+
},
|
| 96010 |
+
{
|
| 96011 |
+
"epoch": 15.621082621082621,
|
| 96012 |
+
"grad_norm": 0.225898876786232,
|
| 96013 |
+
"learning_rate": 6.151683733482633e-06,
|
| 96014 |
+
"loss": 0.7311,
|
| 96015 |
+
"step": 13715
|
| 96016 |
+
},
|
| 96017 |
+
{
|
| 96018 |
+
"epoch": 15.622222222222222,
|
| 96019 |
+
"grad_norm": 0.1864606887102127,
|
| 96020 |
+
"learning_rate": 6.148623203783605e-06,
|
| 96021 |
+
"loss": 0.6569,
|
| 96022 |
+
"step": 13716
|
| 96023 |
+
},
|
| 96024 |
+
{
|
| 96025 |
+
"epoch": 15.623361823361824,
|
| 96026 |
+
"grad_norm": 0.2043372094631195,
|
| 96027 |
+
"learning_rate": 6.145563328844742e-06,
|
| 96028 |
+
"loss": 0.5602,
|
| 96029 |
+
"step": 13717
|
| 96030 |
+
},
|
| 96031 |
+
{
|
| 96032 |
+
"epoch": 15.624501424501425,
|
| 96033 |
+
"grad_norm": 0.22436149418354034,
|
| 96034 |
+
"learning_rate": 6.142504108772307e-06,
|
| 96035 |
+
"loss": 0.7941,
|
| 96036 |
+
"step": 13718
|
| 96037 |
+
},
|
| 96038 |
+
{
|
| 96039 |
+
"epoch": 15.625641025641025,
|
| 96040 |
+
"grad_norm": 0.20962457358837128,
|
| 96041 |
+
"learning_rate": 6.139445543672562e-06,
|
| 96042 |
+
"loss": 0.6914,
|
| 96043 |
+
"step": 13719
|
| 96044 |
+
},
|
| 96045 |
+
{
|
| 96046 |
+
"epoch": 15.626780626780628,
|
| 96047 |
+
"grad_norm": 0.3241886496543884,
|
| 96048 |
+
"learning_rate": 6.136387633651741e-06,
|
| 96049 |
+
"loss": 0.4077,
|
| 96050 |
+
"step": 13720
|
| 96051 |
+
},
|
| 96052 |
+
{
|
| 96053 |
+
"epoch": 15.627920227920228,
|
| 96054 |
+
"grad_norm": 0.20413905382156372,
|
| 96055 |
+
"learning_rate": 6.133330378816057e-06,
|
| 96056 |
+
"loss": 0.5582,
|
| 96057 |
+
"step": 13721
|
| 96058 |
+
},
|
| 96059 |
+
{
|
| 96060 |
+
"epoch": 15.629059829059829,
|
| 96061 |
+
"grad_norm": 0.2374972552061081,
|
| 96062 |
+
"learning_rate": 6.1302737792716895e-06,
|
| 96063 |
+
"loss": 0.6637,
|
| 96064 |
+
"step": 13722
|
| 96065 |
+
},
|
| 96066 |
+
{
|
| 96067 |
+
"epoch": 15.630199430199431,
|
| 96068 |
+
"grad_norm": 0.16341468691825867,
|
| 96069 |
+
"learning_rate": 6.127217835124796e-06,
|
| 96070 |
+
"loss": 0.7038,
|
| 96071 |
+
"step": 13723
|
| 96072 |
+
},
|
| 96073 |
+
{
|
| 96074 |
+
"epoch": 15.631339031339031,
|
| 96075 |
+
"grad_norm": 0.2513233423233032,
|
| 96076 |
+
"learning_rate": 6.124162546481543e-06,
|
| 96077 |
+
"loss": 0.5117,
|
| 96078 |
+
"step": 13724
|
| 96079 |
+
},
|
| 96080 |
+
{
|
| 96081 |
+
"epoch": 15.632478632478632,
|
| 96082 |
+
"grad_norm": 0.19655568897724152,
|
| 96083 |
+
"learning_rate": 6.121107913448024e-06,
|
| 96084 |
+
"loss": 0.7148,
|
| 96085 |
+
"step": 13725
|
| 96086 |
+
},
|
| 96087 |
+
{
|
| 96088 |
+
"epoch": 15.633618233618234,
|
| 96089 |
+
"grad_norm": 0.1788332313299179,
|
| 96090 |
+
"learning_rate": 6.118053936130347e-06,
|
| 96091 |
+
"loss": 0.6445,
|
| 96092 |
+
"step": 13726
|
| 96093 |
+
},
|
| 96094 |
+
{
|
| 96095 |
+
"epoch": 15.634757834757835,
|
| 96096 |
+
"grad_norm": 0.21004877984523773,
|
| 96097 |
+
"learning_rate": 6.115000614634581e-06,
|
| 96098 |
+
"loss": 0.7228,
|
| 96099 |
+
"step": 13727
|
| 96100 |
+
},
|
| 96101 |
+
{
|
| 96102 |
+
"epoch": 15.635897435897435,
|
| 96103 |
+
"grad_norm": 0.23008368909358978,
|
| 96104 |
+
"learning_rate": 6.111947949066784e-06,
|
| 96105 |
+
"loss": 0.5885,
|
| 96106 |
+
"step": 13728
|
| 96107 |
+
},
|
| 96108 |
+
{
|
| 96109 |
+
"epoch": 15.637037037037038,
|
| 96110 |
+
"grad_norm": 0.20609422028064728,
|
| 96111 |
+
"learning_rate": 6.108895939532972e-06,
|
| 96112 |
+
"loss": 0.6035,
|
| 96113 |
+
"step": 13729
|
| 96114 |
+
},
|
| 96115 |
+
{
|
| 96116 |
+
"epoch": 15.638176638176638,
|
| 96117 |
+
"grad_norm": 0.20903274416923523,
|
| 96118 |
+
"learning_rate": 6.105844586139154e-06,
|
| 96119 |
+
"loss": 0.7254,
|
| 96120 |
+
"step": 13730
|
| 96121 |
+
},
|
| 96122 |
+
{
|
| 96123 |
+
"epoch": 15.639316239316239,
|
| 96124 |
+
"grad_norm": 0.1961694359779358,
|
| 96125 |
+
"learning_rate": 6.102793888991312e-06,
|
| 96126 |
+
"loss": 0.3647,
|
| 96127 |
+
"step": 13731
|
| 96128 |
+
},
|
| 96129 |
+
{
|
| 96130 |
+
"epoch": 15.640455840455841,
|
| 96131 |
+
"grad_norm": 0.23456496000289917,
|
| 96132 |
+
"learning_rate": 6.099743848195408e-06,
|
| 96133 |
+
"loss": 0.6749,
|
| 96134 |
+
"step": 13732
|
| 96135 |
+
},
|
| 96136 |
+
{
|
| 96137 |
+
"epoch": 15.641595441595442,
|
| 96138 |
+
"grad_norm": 0.19131501019001007,
|
| 96139 |
+
"learning_rate": 6.096694463857381e-06,
|
| 96140 |
+
"loss": 0.6785,
|
| 96141 |
+
"step": 13733
|
| 96142 |
+
},
|
| 96143 |
+
{
|
| 96144 |
+
"epoch": 15.642735042735042,
|
| 96145 |
+
"grad_norm": 0.17733091115951538,
|
| 96146 |
+
"learning_rate": 6.0936457360831256e-06,
|
| 96147 |
+
"loss": 0.6629,
|
| 96148 |
+
"step": 13734
|
| 96149 |
+
},
|
| 96150 |
+
{
|
| 96151 |
+
"epoch": 15.643874643874645,
|
| 96152 |
+
"grad_norm": 0.2198195606470108,
|
| 96153 |
+
"learning_rate": 6.090597664978553e-06,
|
| 96154 |
+
"loss": 0.589,
|
| 96155 |
+
"step": 13735
|
| 96156 |
+
},
|
| 96157 |
+
{
|
| 96158 |
+
"epoch": 15.645014245014245,
|
| 96159 |
+
"grad_norm": 0.179597869515419,
|
| 96160 |
+
"learning_rate": 6.087550250649532e-06,
|
| 96161 |
+
"loss": 0.6942,
|
| 96162 |
+
"step": 13736
|
| 96163 |
+
},
|
| 96164 |
+
{
|
| 96165 |
+
"epoch": 15.646153846153846,
|
| 96166 |
+
"grad_norm": 0.20365090668201447,
|
| 96167 |
+
"learning_rate": 6.084503493201893e-06,
|
| 96168 |
+
"loss": 0.6757,
|
| 96169 |
+
"step": 13737
|
| 96170 |
+
},
|
| 96171 |
+
{
|
| 96172 |
+
"epoch": 15.647293447293448,
|
| 96173 |
+
"grad_norm": 0.2194930911064148,
|
| 96174 |
+
"learning_rate": 6.081457392741466e-06,
|
| 96175 |
+
"loss": 0.7845,
|
| 96176 |
+
"step": 13738
|
| 96177 |
+
},
|
| 96178 |
+
{
|
| 96179 |
+
"epoch": 15.648433048433048,
|
| 96180 |
+
"grad_norm": 0.19855773448944092,
|
| 96181 |
+
"learning_rate": 6.078411949374049e-06,
|
| 96182 |
+
"loss": 0.5702,
|
| 96183 |
+
"step": 13739
|
| 96184 |
+
},
|
| 96185 |
+
{
|
| 96186 |
+
"epoch": 15.649572649572649,
|
| 96187 |
+
"grad_norm": 0.1931416541337967,
|
| 96188 |
+
"learning_rate": 6.075367163205428e-06,
|
| 96189 |
+
"loss": 0.6954,
|
| 96190 |
+
"step": 13740
|
| 96191 |
+
},
|
| 96192 |
+
{
|
| 96193 |
+
"epoch": 15.650712250712251,
|
| 96194 |
+
"grad_norm": 0.19040903449058533,
|
| 96195 |
+
"learning_rate": 6.072323034341343e-06,
|
| 96196 |
+
"loss": 0.6878,
|
| 96197 |
+
"step": 13741
|
| 96198 |
+
},
|
| 96199 |
+
{
|
| 96200 |
+
"epoch": 15.651851851851852,
|
| 96201 |
+
"grad_norm": 0.20580269396305084,
|
| 96202 |
+
"learning_rate": 6.0692795628875286e-06,
|
| 96203 |
+
"loss": 0.6766,
|
| 96204 |
+
"step": 13742
|
| 96205 |
+
},
|
| 96206 |
+
{
|
| 96207 |
+
"epoch": 15.652991452991452,
|
| 96208 |
+
"grad_norm": 0.22299405932426453,
|
| 96209 |
+
"learning_rate": 6.066236748949691e-06,
|
| 96210 |
+
"loss": 0.5875,
|
| 96211 |
+
"step": 13743
|
| 96212 |
+
},
|
| 96213 |
+
{
|
| 96214 |
+
"epoch": 15.654131054131055,
|
| 96215 |
+
"grad_norm": 0.2034991979598999,
|
| 96216 |
+
"learning_rate": 6.063194592633531e-06,
|
| 96217 |
+
"loss": 0.6345,
|
| 96218 |
+
"step": 13744
|
| 96219 |
+
},
|
| 96220 |
+
{
|
| 96221 |
+
"epoch": 15.655270655270655,
|
| 96222 |
+
"grad_norm": 0.1856851428747177,
|
| 96223 |
+
"learning_rate": 6.060153094044682e-06,
|
| 96224 |
+
"loss": 0.7327,
|
| 96225 |
+
"step": 13745
|
| 96226 |
+
},
|
| 96227 |
+
{
|
| 96228 |
+
"epoch": 15.656410256410256,
|
| 96229 |
+
"grad_norm": 0.18239708244800568,
|
| 96230 |
+
"learning_rate": 6.0571122532888106e-06,
|
| 96231 |
+
"loss": 0.6735,
|
| 96232 |
+
"step": 13746
|
| 96233 |
+
},
|
| 96234 |
+
{
|
| 96235 |
+
"epoch": 15.657549857549858,
|
| 96236 |
+
"grad_norm": 0.21312111616134644,
|
| 96237 |
+
"learning_rate": 6.054072070471531e-06,
|
| 96238 |
+
"loss": 0.5746,
|
| 96239 |
+
"step": 13747
|
| 96240 |
+
},
|
| 96241 |
+
{
|
| 96242 |
+
"epoch": 15.658689458689459,
|
| 96243 |
+
"grad_norm": 0.17315645515918732,
|
| 96244 |
+
"learning_rate": 6.051032545698421e-06,
|
| 96245 |
+
"loss": 0.893,
|
| 96246 |
+
"step": 13748
|
| 96247 |
+
},
|
| 96248 |
+
{
|
| 96249 |
+
"epoch": 15.65982905982906,
|
| 96250 |
+
"grad_norm": 0.21159929037094116,
|
| 96251 |
+
"learning_rate": 6.047993679075059e-06,
|
| 96252 |
+
"loss": 0.5457,
|
| 96253 |
+
"step": 13749
|
| 96254 |
+
},
|
| 96255 |
+
{
|
| 96256 |
+
"epoch": 15.660968660968662,
|
| 96257 |
+
"grad_norm": 0.2133578658103943,
|
| 96258 |
+
"learning_rate": 6.044955470706997e-06,
|
| 96259 |
+
"loss": 0.8786,
|
| 96260 |
+
"step": 13750
|
| 96261 |
+
},
|
| 96262 |
+
{
|
| 96263 |
+
"epoch": 15.662108262108262,
|
| 96264 |
+
"grad_norm": 0.20090807974338531,
|
| 96265 |
+
"learning_rate": 6.0419179206997664e-06,
|
| 96266 |
+
"loss": 0.7035,
|
| 96267 |
+
"step": 13751
|
| 96268 |
+
},
|
| 96269 |
+
{
|
| 96270 |
+
"epoch": 15.663247863247863,
|
| 96271 |
+
"grad_norm": 0.17659156024456024,
|
| 96272 |
+
"learning_rate": 6.038881029158852e-06,
|
| 96273 |
+
"loss": 0.7067,
|
| 96274 |
+
"step": 13752
|
| 96275 |
+
},
|
| 96276 |
+
{
|
| 96277 |
+
"epoch": 15.664387464387465,
|
| 96278 |
+
"grad_norm": 0.235539972782135,
|
| 96279 |
+
"learning_rate": 6.035844796189743e-06,
|
| 96280 |
+
"loss": 0.5339,
|
| 96281 |
+
"step": 13753
|
| 96282 |
+
},
|
| 96283 |
+
{
|
| 96284 |
+
"epoch": 15.665527065527066,
|
| 96285 |
+
"grad_norm": 0.18721574544906616,
|
| 96286 |
+
"learning_rate": 6.032809221897898e-06,
|
| 96287 |
+
"loss": 0.8193,
|
| 96288 |
+
"step": 13754
|
| 96289 |
+
},
|
| 96290 |
+
{
|
| 96291 |
+
"epoch": 15.666666666666666,
|
| 96292 |
+
"grad_norm": 0.21573007106781006,
|
| 96293 |
+
"learning_rate": 6.029774306388753e-06,
|
| 96294 |
+
"loss": 0.6192,
|
| 96295 |
+
"step": 13755
|
| 96296 |
+
},
|
| 96297 |
+
{
|
| 96298 |
+
"epoch": 15.667806267806268,
|
| 96299 |
+
"grad_norm": 0.2722488343715668,
|
| 96300 |
+
"learning_rate": 6.026740049767701e-06,
|
| 96301 |
+
"loss": 0.7024,
|
| 96302 |
+
"step": 13756
|
| 96303 |
+
},
|
| 96304 |
+
{
|
| 96305 |
+
"epoch": 15.668945868945869,
|
| 96306 |
+
"grad_norm": 0.21313630044460297,
|
| 96307 |
+
"learning_rate": 6.0237064521401515e-06,
|
| 96308 |
+
"loss": 0.7763,
|
| 96309 |
+
"step": 13757
|
| 96310 |
+
},
|
| 96311 |
+
{
|
| 96312 |
+
"epoch": 15.67008547008547,
|
| 96313 |
+
"grad_norm": 0.16580374538898468,
|
| 96314 |
+
"learning_rate": 6.020673513611469e-06,
|
| 96315 |
+
"loss": 0.8544,
|
| 96316 |
+
"step": 13758
|
| 96317 |
+
},
|
| 96318 |
+
{
|
| 96319 |
+
"epoch": 15.671225071225072,
|
| 96320 |
+
"grad_norm": 0.24010197818279266,
|
| 96321 |
+
"learning_rate": 6.017641234286983e-06,
|
| 96322 |
+
"loss": 0.3291,
|
| 96323 |
+
"step": 13759
|
| 96324 |
+
},
|
| 96325 |
+
{
|
| 96326 |
+
"epoch": 15.672364672364672,
|
| 96327 |
+
"grad_norm": 0.2201775759458542,
|
| 96328 |
+
"learning_rate": 6.014609614272018e-06,
|
| 96329 |
+
"loss": 0.7122,
|
| 96330 |
+
"step": 13760
|
| 96331 |
+
},
|
| 96332 |
+
{
|
| 96333 |
+
"epoch": 15.673504273504273,
|
| 96334 |
+
"grad_norm": 0.19828544557094574,
|
| 96335 |
+
"learning_rate": 6.0115786536718705e-06,
|
| 96336 |
+
"loss": 0.4014,
|
| 96337 |
+
"step": 13761
|
| 96338 |
+
},
|
| 96339 |
+
{
|
| 96340 |
+
"epoch": 15.674643874643875,
|
| 96341 |
+
"grad_norm": 0.20189552009105682,
|
| 96342 |
+
"learning_rate": 6.00854835259182e-06,
|
| 96343 |
+
"loss": 0.5587,
|
| 96344 |
+
"step": 13762
|
| 96345 |
+
},
|
| 96346 |
+
{
|
| 96347 |
+
"epoch": 15.675783475783476,
|
| 96348 |
+
"grad_norm": 0.17917750775814056,
|
| 96349 |
+
"learning_rate": 6.005518711137106e-06,
|
| 96350 |
+
"loss": 0.8163,
|
| 96351 |
+
"step": 13763
|
| 96352 |
+
},
|
| 96353 |
+
{
|
| 96354 |
+
"epoch": 15.676923076923076,
|
| 96355 |
+
"grad_norm": 0.17694270610809326,
|
| 96356 |
+
"learning_rate": 6.002489729412963e-06,
|
| 96357 |
+
"loss": 0.7236,
|
| 96358 |
+
"step": 13764
|
| 96359 |
+
},
|
| 96360 |
+
{
|
| 96361 |
+
"epoch": 15.678062678062679,
|
| 96362 |
+
"grad_norm": 0.204745352268219,
|
| 96363 |
+
"learning_rate": 5.999461407524596e-06,
|
| 96364 |
+
"loss": 0.5852,
|
| 96365 |
+
"step": 13765
|
| 96366 |
+
},
|
| 96367 |
+
{
|
| 96368 |
+
"epoch": 15.67920227920228,
|
| 96369 |
+
"grad_norm": 0.23212666809558868,
|
| 96370 |
+
"learning_rate": 5.99643374557719e-06,
|
| 96371 |
+
"loss": 0.6488,
|
| 96372 |
+
"step": 13766
|
| 96373 |
+
},
|
| 96374 |
+
{
|
| 96375 |
+
"epoch": 15.68034188034188,
|
| 96376 |
+
"grad_norm": 0.20231904089450836,
|
| 96377 |
+
"learning_rate": 5.993406743675889e-06,
|
| 96378 |
+
"loss": 0.6721,
|
| 96379 |
+
"step": 13767
|
| 96380 |
+
},
|
| 96381 |
+
{
|
| 96382 |
+
"epoch": 15.681481481481482,
|
| 96383 |
+
"grad_norm": 0.2235812097787857,
|
| 96384 |
+
"learning_rate": 5.990380401925847e-06,
|
| 96385 |
+
"loss": 0.5575,
|
| 96386 |
+
"step": 13768
|
| 96387 |
+
},
|
| 96388 |
+
{
|
| 96389 |
+
"epoch": 15.682621082621083,
|
| 96390 |
+
"grad_norm": 0.20220504701137543,
|
| 96391 |
+
"learning_rate": 5.987354720432167e-06,
|
| 96392 |
+
"loss": 0.6535,
|
| 96393 |
+
"step": 13769
|
| 96394 |
+
},
|
| 96395 |
+
{
|
| 96396 |
+
"epoch": 15.683760683760683,
|
| 96397 |
+
"grad_norm": 0.17467883229255676,
|
| 96398 |
+
"learning_rate": 5.984329699299954e-06,
|
| 96399 |
+
"loss": 0.738,
|
| 96400 |
+
"step": 13770
|
| 96401 |
+
},
|
| 96402 |
+
{
|
| 96403 |
+
"epoch": 15.684900284900285,
|
| 96404 |
+
"grad_norm": 0.18006768822669983,
|
| 96405 |
+
"learning_rate": 5.981305338634255e-06,
|
| 96406 |
+
"loss": 0.6707,
|
| 96407 |
+
"step": 13771
|
| 96408 |
+
},
|
| 96409 |
+
{
|
| 96410 |
+
"epoch": 15.686039886039886,
|
| 96411 |
+
"grad_norm": 0.21668808162212372,
|
| 96412 |
+
"learning_rate": 5.97828163854012e-06,
|
| 96413 |
+
"loss": 0.5729,
|
| 96414 |
+
"step": 13772
|
| 96415 |
+
},
|
| 96416 |
+
{
|
| 96417 |
+
"epoch": 15.687179487179487,
|
| 96418 |
+
"grad_norm": 0.1905527114868164,
|
| 96419 |
+
"learning_rate": 5.975258599122577e-06,
|
| 96420 |
+
"loss": 0.7817,
|
| 96421 |
+
"step": 13773
|
| 96422 |
+
},
|
| 96423 |
+
{
|
| 96424 |
+
"epoch": 15.688319088319089,
|
| 96425 |
+
"grad_norm": 0.20768201351165771,
|
| 96426 |
+
"learning_rate": 5.97223622048663e-06,
|
| 96427 |
+
"loss": 0.7568,
|
| 96428 |
+
"step": 13774
|
| 96429 |
+
},
|
| 96430 |
+
{
|
| 96431 |
+
"epoch": 15.68945868945869,
|
| 96432 |
+
"grad_norm": 0.28116485476493835,
|
| 96433 |
+
"learning_rate": 5.969214502737233e-06,
|
| 96434 |
+
"loss": 0.4476,
|
| 96435 |
+
"step": 13775
|
| 96436 |
+
},
|
| 96437 |
+
{
|
| 96438 |
+
"epoch": 15.69059829059829,
|
| 96439 |
+
"grad_norm": 0.21743696928024292,
|
| 96440 |
+
"learning_rate": 5.966193445979357e-06,
|
| 96441 |
+
"loss": 0.7654,
|
| 96442 |
+
"step": 13776
|
| 96443 |
+
},
|
| 96444 |
+
{
|
| 96445 |
+
"epoch": 15.691737891737892,
|
| 96446 |
+
"grad_norm": 0.17984333634376526,
|
| 96447 |
+
"learning_rate": 5.963173050317921e-06,
|
| 96448 |
+
"loss": 0.7383,
|
| 96449 |
+
"step": 13777
|
| 96450 |
+
},
|
| 96451 |
+
{
|
| 96452 |
+
"epoch": 15.692877492877493,
|
| 96453 |
+
"grad_norm": 0.2137390673160553,
|
| 96454 |
+
"learning_rate": 5.960153315857839e-06,
|
| 96455 |
+
"loss": 0.6606,
|
| 96456 |
+
"step": 13778
|
| 96457 |
+
},
|
| 96458 |
+
{
|
| 96459 |
+
"epoch": 15.694017094017093,
|
| 96460 |
+
"grad_norm": 0.1965833157300949,
|
| 96461 |
+
"learning_rate": 5.957134242703991e-06,
|
| 96462 |
+
"loss": 0.8008,
|
| 96463 |
+
"step": 13779
|
| 96464 |
+
},
|
| 96465 |
+
{
|
| 96466 |
+
"epoch": 15.695156695156696,
|
| 96467 |
+
"grad_norm": 0.22292731702327728,
|
| 96468 |
+
"learning_rate": 5.9541158309612404e-06,
|
| 96469 |
+
"loss": 0.7107,
|
| 96470 |
+
"step": 13780
|
| 96471 |
+
},
|
| 96472 |
+
{
|
| 96473 |
+
"epoch": 15.696296296296296,
|
| 96474 |
+
"grad_norm": 0.24760042130947113,
|
| 96475 |
+
"learning_rate": 5.9510980807344295e-06,
|
| 96476 |
+
"loss": 0.5346,
|
| 96477 |
+
"step": 13781
|
| 96478 |
+
},
|
| 96479 |
+
{
|
| 96480 |
+
"epoch": 15.697435897435897,
|
| 96481 |
+
"grad_norm": 0.2328803688287735,
|
| 96482 |
+
"learning_rate": 5.948080992128361e-06,
|
| 96483 |
+
"loss": 0.4708,
|
| 96484 |
+
"step": 13782
|
| 96485 |
+
},
|
| 96486 |
+
{
|
| 96487 |
+
"epoch": 15.698575498575499,
|
| 96488 |
+
"grad_norm": 0.21508914232254028,
|
| 96489 |
+
"learning_rate": 5.945064565247829e-06,
|
| 96490 |
+
"loss": 0.6997,
|
| 96491 |
+
"step": 13783
|
| 96492 |
+
},
|
| 96493 |
+
{
|
| 96494 |
+
"epoch": 15.6997150997151,
|
| 96495 |
+
"grad_norm": 0.1934168040752411,
|
| 96496 |
+
"learning_rate": 5.942048800197611e-06,
|
| 96497 |
+
"loss": 0.593,
|
| 96498 |
+
"step": 13784
|
| 96499 |
+
},
|
| 96500 |
+
{
|
| 96501 |
+
"epoch": 15.7008547008547,
|
| 96502 |
+
"grad_norm": 0.1619928926229477,
|
| 96503 |
+
"learning_rate": 5.939033697082453e-06,
|
| 96504 |
+
"loss": 0.5503,
|
| 96505 |
+
"step": 13785
|
| 96506 |
+
},
|
| 96507 |
+
{
|
| 96508 |
+
"epoch": 15.701994301994302,
|
| 96509 |
+
"grad_norm": 0.18001818656921387,
|
| 96510 |
+
"learning_rate": 5.936019256007063e-06,
|
| 96511 |
+
"loss": 0.3774,
|
| 96512 |
+
"step": 13786
|
| 96513 |
+
},
|
| 96514 |
+
{
|
| 96515 |
+
"epoch": 15.703133903133903,
|
| 96516 |
+
"grad_norm": 0.18391923606395721,
|
| 96517 |
+
"learning_rate": 5.933005477076151e-06,
|
| 96518 |
+
"loss": 0.7215,
|
| 96519 |
+
"step": 13787
|
| 96520 |
+
},
|
| 96521 |
+
{
|
| 96522 |
+
"epoch": 15.704273504273504,
|
| 96523 |
+
"grad_norm": 0.16934546828269958,
|
| 96524 |
+
"learning_rate": 5.929992360394396e-06,
|
| 96525 |
+
"loss": 0.6671,
|
| 96526 |
+
"step": 13788
|
| 96527 |
+
},
|
| 96528 |
+
{
|
| 96529 |
+
"epoch": 15.705413105413106,
|
| 96530 |
+
"grad_norm": 0.2290726751089096,
|
| 96531 |
+
"learning_rate": 5.926979906066446e-06,
|
| 96532 |
+
"loss": 0.7625,
|
| 96533 |
+
"step": 13789
|
| 96534 |
+
},
|
| 96535 |
+
{
|
| 96536 |
+
"epoch": 15.706552706552706,
|
| 96537 |
+
"grad_norm": 0.18426409363746643,
|
| 96538 |
+
"learning_rate": 5.923968114196937e-06,
|
| 96539 |
+
"loss": 0.6394,
|
| 96540 |
+
"step": 13790
|
| 96541 |
+
},
|
| 96542 |
+
{
|
| 96543 |
+
"epoch": 15.707692307692307,
|
| 96544 |
+
"grad_norm": 0.20047087967395782,
|
| 96545 |
+
"learning_rate": 5.920956984890474e-06,
|
| 96546 |
+
"loss": 0.5195,
|
| 96547 |
+
"step": 13791
|
| 96548 |
+
},
|
| 96549 |
+
{
|
| 96550 |
+
"epoch": 15.70883190883191,
|
| 96551 |
+
"grad_norm": 0.1657576560974121,
|
| 96552 |
+
"learning_rate": 5.917946518251649e-06,
|
| 96553 |
+
"loss": 0.6565,
|
| 96554 |
+
"step": 13792
|
| 96555 |
+
},
|
| 96556 |
+
{
|
| 96557 |
+
"epoch": 15.70997150997151,
|
| 96558 |
+
"grad_norm": 0.21902921795845032,
|
| 96559 |
+
"learning_rate": 5.914936714385011e-06,
|
| 96560 |
+
"loss": 0.7981,
|
| 96561 |
+
"step": 13793
|
| 96562 |
+
},
|
| 96563 |
+
{
|
| 96564 |
+
"epoch": 15.71111111111111,
|
| 96565 |
+
"grad_norm": 0.19958922266960144,
|
| 96566 |
+
"learning_rate": 5.911927573395104e-06,
|
| 96567 |
+
"loss": 0.6652,
|
| 96568 |
+
"step": 13794
|
| 96569 |
+
},
|
| 96570 |
+
{
|
| 96571 |
+
"epoch": 15.712250712250713,
|
| 96572 |
+
"grad_norm": 0.23519207537174225,
|
| 96573 |
+
"learning_rate": 5.908919095386445e-06,
|
| 96574 |
+
"loss": 0.7342,
|
| 96575 |
+
"step": 13795
|
| 96576 |
+
},
|
| 96577 |
+
{
|
| 96578 |
+
"epoch": 15.713390313390313,
|
| 96579 |
+
"grad_norm": 0.16713076829910278,
|
| 96580 |
+
"learning_rate": 5.905911280463536e-06,
|
| 96581 |
+
"loss": 0.7188,
|
| 96582 |
+
"step": 13796
|
| 96583 |
+
},
|
| 96584 |
+
{
|
| 96585 |
+
"epoch": 15.714529914529914,
|
| 96586 |
+
"grad_norm": 0.18714037537574768,
|
| 96587 |
+
"learning_rate": 5.902904128730826e-06,
|
| 96588 |
+
"loss": 0.7061,
|
| 96589 |
+
"step": 13797
|
| 96590 |
+
},
|
| 96591 |
+
{
|
| 96592 |
+
"epoch": 15.715669515669516,
|
| 96593 |
+
"grad_norm": 0.18389609456062317,
|
| 96594 |
+
"learning_rate": 5.899897640292776e-06,
|
| 96595 |
+
"loss": 0.6432,
|
| 96596 |
+
"step": 13798
|
| 96597 |
+
},
|
| 96598 |
+
{
|
| 96599 |
+
"epoch": 15.716809116809117,
|
| 96600 |
+
"grad_norm": 0.18872186541557312,
|
| 96601 |
+
"learning_rate": 5.896891815253805e-06,
|
| 96602 |
+
"loss": 0.6875,
|
| 96603 |
+
"step": 13799
|
| 96604 |
+
},
|
| 96605 |
+
{
|
| 96606 |
+
"epoch": 15.717948717948717,
|
| 96607 |
+
"grad_norm": 0.2201945185661316,
|
| 96608 |
+
"learning_rate": 5.893886653718317e-06,
|
| 96609 |
+
"loss": 0.7302,
|
| 96610 |
+
"step": 13800
|
| 96611 |
}
|
| 96612 |
],
|
| 96613 |
"logging_steps": 1,
|
|
|
|
| 96627 |
"attributes": {}
|
| 96628 |
}
|
| 96629 |
},
|
| 96630 |
+
"total_flos": 7.715994433344258e+19,
|
| 96631 |
"train_batch_size": 8,
|
| 96632 |
"trial_name": null,
|
| 96633 |
"trial_params": null
|