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 13500, 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 sha256:15f08f8378aadab8b59db4f6adbc2b2825af3c71523ea74b65b22b376c782814
|
| 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 sha256:3ec5322734300b03a7e2f43159639b13b792d99af4110f719aeff510f82e7236
|
| 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 sha256:685522f72316a66965188607b4cfb56965263e003cfa06a3b49b287294bac146
|
| 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,
|
|
@@ -92408,6 +92408,2106 @@
|
|
| 92408 |
"learning_rate": 7.812354677854688e-06,
|
| 92409 |
"loss": 0.4224,
|
| 92410 |
"step": 13200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92411 |
}
|
| 92412 |
],
|
| 92413 |
"logging_steps": 1,
|
|
@@ -92427,7 +94527,7 @@
|
|
| 92427 |
"attributes": {}
|
| 92428 |
}
|
| 92429 |
},
|
| 92430 |
-
"total_flos": 7.
|
| 92431 |
"train_batch_size": 8,
|
| 92432 |
"trial_name": null,
|
| 92433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.376068376068377,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 13500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 92408 |
"learning_rate": 7.812354677854688e-06,
|
| 92409 |
"loss": 0.4224,
|
| 92410 |
"step": 13200
|
| 92411 |
+
},
|
| 92412 |
+
{
|
| 92413 |
+
"epoch": 15.035327635327635,
|
| 92414 |
+
"grad_norm": 0.20608681440353394,
|
| 92415 |
+
"learning_rate": 7.808971577452618e-06,
|
| 92416 |
+
"loss": 0.7248,
|
| 92417 |
+
"step": 13201
|
| 92418 |
+
},
|
| 92419 |
+
{
|
| 92420 |
+
"epoch": 15.036467236467237,
|
| 92421 |
+
"grad_norm": 0.35443320870399475,
|
| 92422 |
+
"learning_rate": 7.805589074142236e-06,
|
| 92423 |
+
"loss": 0.7227,
|
| 92424 |
+
"step": 13202
|
| 92425 |
+
},
|
| 92426 |
+
{
|
| 92427 |
+
"epoch": 15.037606837606837,
|
| 92428 |
+
"grad_norm": 0.2172495424747467,
|
| 92429 |
+
"learning_rate": 7.802207168041042e-06,
|
| 92430 |
+
"loss": 0.8817,
|
| 92431 |
+
"step": 13203
|
| 92432 |
+
},
|
| 92433 |
+
{
|
| 92434 |
+
"epoch": 15.038746438746438,
|
| 92435 |
+
"grad_norm": 0.1786259412765503,
|
| 92436 |
+
"learning_rate": 7.79882585926647e-06,
|
| 92437 |
+
"loss": 0.7133,
|
| 92438 |
+
"step": 13204
|
| 92439 |
+
},
|
| 92440 |
+
{
|
| 92441 |
+
"epoch": 15.03988603988604,
|
| 92442 |
+
"grad_norm": 0.19469647109508514,
|
| 92443 |
+
"learning_rate": 7.795445147935986e-06,
|
| 92444 |
+
"loss": 0.5264,
|
| 92445 |
+
"step": 13205
|
| 92446 |
+
},
|
| 92447 |
+
{
|
| 92448 |
+
"epoch": 15.04102564102564,
|
| 92449 |
+
"grad_norm": 0.22203053534030914,
|
| 92450 |
+
"learning_rate": 7.792065034167014e-06,
|
| 92451 |
+
"loss": 0.6028,
|
| 92452 |
+
"step": 13206
|
| 92453 |
+
},
|
| 92454 |
+
{
|
| 92455 |
+
"epoch": 15.042165242165241,
|
| 92456 |
+
"grad_norm": 0.17859232425689697,
|
| 92457 |
+
"learning_rate": 7.788685518076938e-06,
|
| 92458 |
+
"loss": 0.8592,
|
| 92459 |
+
"step": 13207
|
| 92460 |
+
},
|
| 92461 |
+
{
|
| 92462 |
+
"epoch": 15.043304843304844,
|
| 92463 |
+
"grad_norm": 0.16376741230487823,
|
| 92464 |
+
"learning_rate": 7.785306599783144e-06,
|
| 92465 |
+
"loss": 0.7242,
|
| 92466 |
+
"step": 13208
|
| 92467 |
+
},
|
| 92468 |
+
{
|
| 92469 |
+
"epoch": 15.044444444444444,
|
| 92470 |
+
"grad_norm": 0.21637587249279022,
|
| 92471 |
+
"learning_rate": 7.781928279402992e-06,
|
| 92472 |
+
"loss": 0.6116,
|
| 92473 |
+
"step": 13209
|
| 92474 |
+
},
|
| 92475 |
+
{
|
| 92476 |
+
"epoch": 15.045584045584045,
|
| 92477 |
+
"grad_norm": 0.21050210297107697,
|
| 92478 |
+
"learning_rate": 7.778550557053829e-06,
|
| 92479 |
+
"loss": 0.8039,
|
| 92480 |
+
"step": 13210
|
| 92481 |
+
},
|
| 92482 |
+
{
|
| 92483 |
+
"epoch": 15.046723646723647,
|
| 92484 |
+
"grad_norm": 0.20630396902561188,
|
| 92485 |
+
"learning_rate": 7.775173432852958e-06,
|
| 92486 |
+
"loss": 0.8097,
|
| 92487 |
+
"step": 13211
|
| 92488 |
+
},
|
| 92489 |
+
{
|
| 92490 |
+
"epoch": 15.047863247863248,
|
| 92491 |
+
"grad_norm": 0.28566041588783264,
|
| 92492 |
+
"learning_rate": 7.77179690691768e-06,
|
| 92493 |
+
"loss": 0.3769,
|
| 92494 |
+
"step": 13212
|
| 92495 |
+
},
|
| 92496 |
+
{
|
| 92497 |
+
"epoch": 15.049002849002848,
|
| 92498 |
+
"grad_norm": 0.17649933695793152,
|
| 92499 |
+
"learning_rate": 7.768420979365277e-06,
|
| 92500 |
+
"loss": 0.8097,
|
| 92501 |
+
"step": 13213
|
| 92502 |
+
},
|
| 92503 |
+
{
|
| 92504 |
+
"epoch": 15.05014245014245,
|
| 92505 |
+
"grad_norm": 0.1777004599571228,
|
| 92506 |
+
"learning_rate": 7.765045650313005e-06,
|
| 92507 |
+
"loss": 0.7521,
|
| 92508 |
+
"step": 13214
|
| 92509 |
+
},
|
| 92510 |
+
{
|
| 92511 |
+
"epoch": 15.051282051282051,
|
| 92512 |
+
"grad_norm": 0.20190858840942383,
|
| 92513 |
+
"learning_rate": 7.761670919878077e-06,
|
| 92514 |
+
"loss": 0.7145,
|
| 92515 |
+
"step": 13215
|
| 92516 |
+
},
|
| 92517 |
+
{
|
| 92518 |
+
"epoch": 15.052421652421652,
|
| 92519 |
+
"grad_norm": 0.28934812545776367,
|
| 92520 |
+
"learning_rate": 7.758296788177733e-06,
|
| 92521 |
+
"loss": 0.3552,
|
| 92522 |
+
"step": 13216
|
| 92523 |
+
},
|
| 92524 |
+
{
|
| 92525 |
+
"epoch": 15.053561253561254,
|
| 92526 |
+
"grad_norm": 0.1863059401512146,
|
| 92527 |
+
"learning_rate": 7.754923255329167e-06,
|
| 92528 |
+
"loss": 0.7675,
|
| 92529 |
+
"step": 13217
|
| 92530 |
+
},
|
| 92531 |
+
{
|
| 92532 |
+
"epoch": 15.054700854700855,
|
| 92533 |
+
"grad_norm": 0.2047613114118576,
|
| 92534 |
+
"learning_rate": 7.751550321449527e-06,
|
| 92535 |
+
"loss": 0.7593,
|
| 92536 |
+
"step": 13218
|
| 92537 |
+
},
|
| 92538 |
+
{
|
| 92539 |
+
"epoch": 15.055840455840455,
|
| 92540 |
+
"grad_norm": 0.1818694770336151,
|
| 92541 |
+
"learning_rate": 7.748177986655983e-06,
|
| 92542 |
+
"loss": 0.734,
|
| 92543 |
+
"step": 13219
|
| 92544 |
+
},
|
| 92545 |
+
{
|
| 92546 |
+
"epoch": 15.056980056980057,
|
| 92547 |
+
"grad_norm": 0.191678985953331,
|
| 92548 |
+
"learning_rate": 7.744806251065657e-06,
|
| 92549 |
+
"loss": 0.6582,
|
| 92550 |
+
"step": 13220
|
| 92551 |
+
},
|
| 92552 |
+
{
|
| 92553 |
+
"epoch": 15.058119658119658,
|
| 92554 |
+
"grad_norm": 0.17697349190711975,
|
| 92555 |
+
"learning_rate": 7.741435114795662e-06,
|
| 92556 |
+
"loss": 0.5432,
|
| 92557 |
+
"step": 13221
|
| 92558 |
+
},
|
| 92559 |
+
{
|
| 92560 |
+
"epoch": 15.059259259259258,
|
| 92561 |
+
"grad_norm": 0.18738119304180145,
|
| 92562 |
+
"learning_rate": 7.738064577963097e-06,
|
| 92563 |
+
"loss": 0.8128,
|
| 92564 |
+
"step": 13222
|
| 92565 |
+
},
|
| 92566 |
+
{
|
| 92567 |
+
"epoch": 15.06039886039886,
|
| 92568 |
+
"grad_norm": 0.17838743329048157,
|
| 92569 |
+
"learning_rate": 7.734694640685009e-06,
|
| 92570 |
+
"loss": 0.8135,
|
| 92571 |
+
"step": 13223
|
| 92572 |
+
},
|
| 92573 |
+
{
|
| 92574 |
+
"epoch": 15.061538461538461,
|
| 92575 |
+
"grad_norm": 0.18243756890296936,
|
| 92576 |
+
"learning_rate": 7.731325303078456e-06,
|
| 92577 |
+
"loss": 0.8034,
|
| 92578 |
+
"step": 13224
|
| 92579 |
+
},
|
| 92580 |
+
{
|
| 92581 |
+
"epoch": 15.062678062678062,
|
| 92582 |
+
"grad_norm": 0.2645007371902466,
|
| 92583 |
+
"learning_rate": 7.727956565260467e-06,
|
| 92584 |
+
"loss": 0.6103,
|
| 92585 |
+
"step": 13225
|
| 92586 |
+
},
|
| 92587 |
+
{
|
| 92588 |
+
"epoch": 15.063817663817664,
|
| 92589 |
+
"grad_norm": 0.168042853474617,
|
| 92590 |
+
"learning_rate": 7.724588427348042e-06,
|
| 92591 |
+
"loss": 0.6509,
|
| 92592 |
+
"step": 13226
|
| 92593 |
+
},
|
| 92594 |
+
{
|
| 92595 |
+
"epoch": 15.064957264957265,
|
| 92596 |
+
"grad_norm": 0.21104352176189423,
|
| 92597 |
+
"learning_rate": 7.72122088945817e-06,
|
| 92598 |
+
"loss": 0.6717,
|
| 92599 |
+
"step": 13227
|
| 92600 |
+
},
|
| 92601 |
+
{
|
| 92602 |
+
"epoch": 15.066096866096865,
|
| 92603 |
+
"grad_norm": 0.20439642667770386,
|
| 92604 |
+
"learning_rate": 7.717853951707813e-06,
|
| 92605 |
+
"loss": 0.7022,
|
| 92606 |
+
"step": 13228
|
| 92607 |
+
},
|
| 92608 |
+
{
|
| 92609 |
+
"epoch": 15.067236467236468,
|
| 92610 |
+
"grad_norm": 0.20428550243377686,
|
| 92611 |
+
"learning_rate": 7.714487614213922e-06,
|
| 92612 |
+
"loss": 0.7572,
|
| 92613 |
+
"step": 13229
|
| 92614 |
+
},
|
| 92615 |
+
{
|
| 92616 |
+
"epoch": 15.068376068376068,
|
| 92617 |
+
"grad_norm": 0.21032805740833282,
|
| 92618 |
+
"learning_rate": 7.711121877093405e-06,
|
| 92619 |
+
"loss": 0.6847,
|
| 92620 |
+
"step": 13230
|
| 92621 |
+
},
|
| 92622 |
+
{
|
| 92623 |
+
"epoch": 15.069515669515669,
|
| 92624 |
+
"grad_norm": 0.2351704090833664,
|
| 92625 |
+
"learning_rate": 7.707756740463167e-06,
|
| 92626 |
+
"loss": 0.708,
|
| 92627 |
+
"step": 13231
|
| 92628 |
+
},
|
| 92629 |
+
{
|
| 92630 |
+
"epoch": 15.070655270655271,
|
| 92631 |
+
"grad_norm": 0.19543321430683136,
|
| 92632 |
+
"learning_rate": 7.704392204440094e-06,
|
| 92633 |
+
"loss": 0.6966,
|
| 92634 |
+
"step": 13232
|
| 92635 |
+
},
|
| 92636 |
+
{
|
| 92637 |
+
"epoch": 15.071794871794872,
|
| 92638 |
+
"grad_norm": 0.22169937193393707,
|
| 92639 |
+
"learning_rate": 7.701028269141051e-06,
|
| 92640 |
+
"loss": 0.6904,
|
| 92641 |
+
"step": 13233
|
| 92642 |
+
},
|
| 92643 |
+
{
|
| 92644 |
+
"epoch": 15.072934472934472,
|
| 92645 |
+
"grad_norm": 0.20034444332122803,
|
| 92646 |
+
"learning_rate": 7.697664934682859e-06,
|
| 92647 |
+
"loss": 0.5926,
|
| 92648 |
+
"step": 13234
|
| 92649 |
+
},
|
| 92650 |
+
{
|
| 92651 |
+
"epoch": 15.074074074074074,
|
| 92652 |
+
"grad_norm": 0.21546687185764313,
|
| 92653 |
+
"learning_rate": 7.694302201182343e-06,
|
| 92654 |
+
"loss": 0.5675,
|
| 92655 |
+
"step": 13235
|
| 92656 |
+
},
|
| 92657 |
+
{
|
| 92658 |
+
"epoch": 15.075213675213675,
|
| 92659 |
+
"grad_norm": 0.20143888890743256,
|
| 92660 |
+
"learning_rate": 7.690940068756308e-06,
|
| 92661 |
+
"loss": 0.714,
|
| 92662 |
+
"step": 13236
|
| 92663 |
+
},
|
| 92664 |
+
{
|
| 92665 |
+
"epoch": 15.076353276353275,
|
| 92666 |
+
"grad_norm": 0.19900089502334595,
|
| 92667 |
+
"learning_rate": 7.68757853752152e-06,
|
| 92668 |
+
"loss": 0.7343,
|
| 92669 |
+
"step": 13237
|
| 92670 |
+
},
|
| 92671 |
+
{
|
| 92672 |
+
"epoch": 15.077492877492878,
|
| 92673 |
+
"grad_norm": 0.23945918679237366,
|
| 92674 |
+
"learning_rate": 7.684217607594741e-06,
|
| 92675 |
+
"loss": 0.5449,
|
| 92676 |
+
"step": 13238
|
| 92677 |
+
},
|
| 92678 |
+
{
|
| 92679 |
+
"epoch": 15.078632478632478,
|
| 92680 |
+
"grad_norm": 0.2190757691860199,
|
| 92681 |
+
"learning_rate": 7.680857279092701e-06,
|
| 92682 |
+
"loss": 0.674,
|
| 92683 |
+
"step": 13239
|
| 92684 |
+
},
|
| 92685 |
+
{
|
| 92686 |
+
"epoch": 15.079772079772079,
|
| 92687 |
+
"grad_norm": 0.21157409250736237,
|
| 92688 |
+
"learning_rate": 7.677497552132125e-06,
|
| 92689 |
+
"loss": 0.8033,
|
| 92690 |
+
"step": 13240
|
| 92691 |
+
},
|
| 92692 |
+
{
|
| 92693 |
+
"epoch": 15.080911680911681,
|
| 92694 |
+
"grad_norm": 0.1564355343580246,
|
| 92695 |
+
"learning_rate": 7.674138426829688e-06,
|
| 92696 |
+
"loss": 0.7209,
|
| 92697 |
+
"step": 13241
|
| 92698 |
+
},
|
| 92699 |
+
{
|
| 92700 |
+
"epoch": 15.082051282051282,
|
| 92701 |
+
"grad_norm": 0.24544627964496613,
|
| 92702 |
+
"learning_rate": 7.670779903302071e-06,
|
| 92703 |
+
"loss": 0.6977,
|
| 92704 |
+
"step": 13242
|
| 92705 |
+
},
|
| 92706 |
+
{
|
| 92707 |
+
"epoch": 15.083190883190884,
|
| 92708 |
+
"grad_norm": 0.18262211978435516,
|
| 92709 |
+
"learning_rate": 7.667421981665923e-06,
|
| 92710 |
+
"loss": 0.924,
|
| 92711 |
+
"step": 13243
|
| 92712 |
+
},
|
| 92713 |
+
{
|
| 92714 |
+
"epoch": 15.084330484330485,
|
| 92715 |
+
"grad_norm": 0.23551349341869354,
|
| 92716 |
+
"learning_rate": 7.664064662037882e-06,
|
| 92717 |
+
"loss": 0.4392,
|
| 92718 |
+
"step": 13244
|
| 92719 |
+
},
|
| 92720 |
+
{
|
| 92721 |
+
"epoch": 15.085470085470085,
|
| 92722 |
+
"grad_norm": 0.21138112246990204,
|
| 92723 |
+
"learning_rate": 7.660707944534539e-06,
|
| 92724 |
+
"loss": 0.4933,
|
| 92725 |
+
"step": 13245
|
| 92726 |
+
},
|
| 92727 |
+
{
|
| 92728 |
+
"epoch": 15.086609686609687,
|
| 92729 |
+
"grad_norm": 0.18942241370677948,
|
| 92730 |
+
"learning_rate": 7.657351829272496e-06,
|
| 92731 |
+
"loss": 0.6874,
|
| 92732 |
+
"step": 13246
|
| 92733 |
+
},
|
| 92734 |
+
{
|
| 92735 |
+
"epoch": 15.087749287749288,
|
| 92736 |
+
"grad_norm": 0.16392655670642853,
|
| 92737 |
+
"learning_rate": 7.653996316368314e-06,
|
| 92738 |
+
"loss": 0.865,
|
| 92739 |
+
"step": 13247
|
| 92740 |
+
},
|
| 92741 |
+
{
|
| 92742 |
+
"epoch": 15.088888888888889,
|
| 92743 |
+
"grad_norm": 0.16634123027324677,
|
| 92744 |
+
"learning_rate": 7.65064140593854e-06,
|
| 92745 |
+
"loss": 0.7992,
|
| 92746 |
+
"step": 13248
|
| 92747 |
+
},
|
| 92748 |
+
{
|
| 92749 |
+
"epoch": 15.090028490028491,
|
| 92750 |
+
"grad_norm": 0.19082193076610565,
|
| 92751 |
+
"learning_rate": 7.647287098099707e-06,
|
| 92752 |
+
"loss": 0.407,
|
| 92753 |
+
"step": 13249
|
| 92754 |
+
},
|
| 92755 |
+
{
|
| 92756 |
+
"epoch": 15.091168091168091,
|
| 92757 |
+
"grad_norm": 0.19843685626983643,
|
| 92758 |
+
"learning_rate": 7.643933392968308e-06,
|
| 92759 |
+
"loss": 0.6434,
|
| 92760 |
+
"step": 13250
|
| 92761 |
+
},
|
| 92762 |
+
{
|
| 92763 |
+
"epoch": 15.092307692307692,
|
| 92764 |
+
"grad_norm": 0.21986281871795654,
|
| 92765 |
+
"learning_rate": 7.64058029066084e-06,
|
| 92766 |
+
"loss": 0.6239,
|
| 92767 |
+
"step": 13251
|
| 92768 |
+
},
|
| 92769 |
+
{
|
| 92770 |
+
"epoch": 15.093447293447294,
|
| 92771 |
+
"grad_norm": 0.24562717974185944,
|
| 92772 |
+
"learning_rate": 7.637227791293752e-06,
|
| 92773 |
+
"loss": 0.5732,
|
| 92774 |
+
"step": 13252
|
| 92775 |
+
},
|
| 92776 |
+
{
|
| 92777 |
+
"epoch": 15.094586894586895,
|
| 92778 |
+
"grad_norm": 0.2094041258096695,
|
| 92779 |
+
"learning_rate": 7.633875894983489e-06,
|
| 92780 |
+
"loss": 0.6639,
|
| 92781 |
+
"step": 13253
|
| 92782 |
+
},
|
| 92783 |
+
{
|
| 92784 |
+
"epoch": 15.095726495726495,
|
| 92785 |
+
"grad_norm": 0.24959199130535126,
|
| 92786 |
+
"learning_rate": 7.630524601846472e-06,
|
| 92787 |
+
"loss": 0.3085,
|
| 92788 |
+
"step": 13254
|
| 92789 |
+
},
|
| 92790 |
+
{
|
| 92791 |
+
"epoch": 15.096866096866098,
|
| 92792 |
+
"grad_norm": 0.18908515572547913,
|
| 92793 |
+
"learning_rate": 7.627173911999111e-06,
|
| 92794 |
+
"loss": 0.7597,
|
| 92795 |
+
"step": 13255
|
| 92796 |
+
},
|
| 92797 |
+
{
|
| 92798 |
+
"epoch": 15.098005698005698,
|
| 92799 |
+
"grad_norm": 0.21889039874076843,
|
| 92800 |
+
"learning_rate": 7.623823825557766e-06,
|
| 92801 |
+
"loss": 0.3345,
|
| 92802 |
+
"step": 13256
|
| 92803 |
+
},
|
| 92804 |
+
{
|
| 92805 |
+
"epoch": 15.099145299145299,
|
| 92806 |
+
"grad_norm": 0.21106140315532684,
|
| 92807 |
+
"learning_rate": 7.620474342638806e-06,
|
| 92808 |
+
"loss": 0.6758,
|
| 92809 |
+
"step": 13257
|
| 92810 |
+
},
|
| 92811 |
+
{
|
| 92812 |
+
"epoch": 15.100284900284901,
|
| 92813 |
+
"grad_norm": 0.23992294073104858,
|
| 92814 |
+
"learning_rate": 7.617125463358565e-06,
|
| 92815 |
+
"loss": 0.7788,
|
| 92816 |
+
"step": 13258
|
| 92817 |
+
},
|
| 92818 |
+
{
|
| 92819 |
+
"epoch": 15.101424501424502,
|
| 92820 |
+
"grad_norm": 0.2021246999502182,
|
| 92821 |
+
"learning_rate": 7.613777187833363e-06,
|
| 92822 |
+
"loss": 0.733,
|
| 92823 |
+
"step": 13259
|
| 92824 |
+
},
|
| 92825 |
+
{
|
| 92826 |
+
"epoch": 15.102564102564102,
|
| 92827 |
+
"grad_norm": 0.24441534280776978,
|
| 92828 |
+
"learning_rate": 7.610429516179488e-06,
|
| 92829 |
+
"loss": 0.641,
|
| 92830 |
+
"step": 13260
|
| 92831 |
+
},
|
| 92832 |
+
{
|
| 92833 |
+
"epoch": 15.103703703703705,
|
| 92834 |
+
"grad_norm": 0.194869726896286,
|
| 92835 |
+
"learning_rate": 7.607082448513217e-06,
|
| 92836 |
+
"loss": 0.7236,
|
| 92837 |
+
"step": 13261
|
| 92838 |
+
},
|
| 92839 |
+
{
|
| 92840 |
+
"epoch": 15.104843304843305,
|
| 92841 |
+
"grad_norm": 0.23420466482639313,
|
| 92842 |
+
"learning_rate": 7.603735984950805e-06,
|
| 92843 |
+
"loss": 0.7169,
|
| 92844 |
+
"step": 13262
|
| 92845 |
+
},
|
| 92846 |
+
{
|
| 92847 |
+
"epoch": 15.105982905982906,
|
| 92848 |
+
"grad_norm": 0.1979341059923172,
|
| 92849 |
+
"learning_rate": 7.60039012560849e-06,
|
| 92850 |
+
"loss": 0.7052,
|
| 92851 |
+
"step": 13263
|
| 92852 |
+
},
|
| 92853 |
+
{
|
| 92854 |
+
"epoch": 15.107122507122508,
|
| 92855 |
+
"grad_norm": 0.2143956869840622,
|
| 92856 |
+
"learning_rate": 7.5970448706024655e-06,
|
| 92857 |
+
"loss": 0.579,
|
| 92858 |
+
"step": 13264
|
| 92859 |
+
},
|
| 92860 |
+
{
|
| 92861 |
+
"epoch": 15.108262108262108,
|
| 92862 |
+
"grad_norm": 0.16880324482917786,
|
| 92863 |
+
"learning_rate": 7.5937002200489324e-06,
|
| 92864 |
+
"loss": 0.6357,
|
| 92865 |
+
"step": 13265
|
| 92866 |
+
},
|
| 92867 |
+
{
|
| 92868 |
+
"epoch": 15.109401709401709,
|
| 92869 |
+
"grad_norm": 0.1926845759153366,
|
| 92870 |
+
"learning_rate": 7.590356174064059e-06,
|
| 92871 |
+
"loss": 0.7423,
|
| 92872 |
+
"step": 13266
|
| 92873 |
+
},
|
| 92874 |
+
{
|
| 92875 |
+
"epoch": 15.110541310541311,
|
| 92876 |
+
"grad_norm": 0.21125121414661407,
|
| 92877 |
+
"learning_rate": 7.587012732763999e-06,
|
| 92878 |
+
"loss": 0.5724,
|
| 92879 |
+
"step": 13267
|
| 92880 |
+
},
|
| 92881 |
+
{
|
| 92882 |
+
"epoch": 15.111680911680912,
|
| 92883 |
+
"grad_norm": 0.23667533695697784,
|
| 92884 |
+
"learning_rate": 7.583669896264864e-06,
|
| 92885 |
+
"loss": 0.8051,
|
| 92886 |
+
"step": 13268
|
| 92887 |
+
},
|
| 92888 |
+
{
|
| 92889 |
+
"epoch": 15.112820512820512,
|
| 92890 |
+
"grad_norm": 0.17306900024414062,
|
| 92891 |
+
"learning_rate": 7.580327664682768e-06,
|
| 92892 |
+
"loss": 0.9573,
|
| 92893 |
+
"step": 13269
|
| 92894 |
+
},
|
| 92895 |
+
{
|
| 92896 |
+
"epoch": 15.113960113960115,
|
| 92897 |
+
"grad_norm": 0.20057110488414764,
|
| 92898 |
+
"learning_rate": 7.576986038133799e-06,
|
| 92899 |
+
"loss": 0.4748,
|
| 92900 |
+
"step": 13270
|
| 92901 |
+
},
|
| 92902 |
+
{
|
| 92903 |
+
"epoch": 15.115099715099715,
|
| 92904 |
+
"grad_norm": 0.17408953607082367,
|
| 92905 |
+
"learning_rate": 7.573645016734018e-06,
|
| 92906 |
+
"loss": 0.5414,
|
| 92907 |
+
"step": 13271
|
| 92908 |
+
},
|
| 92909 |
+
{
|
| 92910 |
+
"epoch": 15.116239316239316,
|
| 92911 |
+
"grad_norm": 0.2110489159822464,
|
| 92912 |
+
"learning_rate": 7.570304600599468e-06,
|
| 92913 |
+
"loss": 0.6668,
|
| 92914 |
+
"step": 13272
|
| 92915 |
+
},
|
| 92916 |
+
{
|
| 92917 |
+
"epoch": 15.117378917378918,
|
| 92918 |
+
"grad_norm": 0.1887875348329544,
|
| 92919 |
+
"learning_rate": 7.5669647898461705e-06,
|
| 92920 |
+
"loss": 0.4897,
|
| 92921 |
+
"step": 13273
|
| 92922 |
+
},
|
| 92923 |
+
{
|
| 92924 |
+
"epoch": 15.118518518518519,
|
| 92925 |
+
"grad_norm": 0.2168729603290558,
|
| 92926 |
+
"learning_rate": 7.563625584590134e-06,
|
| 92927 |
+
"loss": 0.618,
|
| 92928 |
+
"step": 13274
|
| 92929 |
+
},
|
| 92930 |
+
{
|
| 92931 |
+
"epoch": 15.11965811965812,
|
| 92932 |
+
"grad_norm": 0.23232001066207886,
|
| 92933 |
+
"learning_rate": 7.560286984947326e-06,
|
| 92934 |
+
"loss": 0.6055,
|
| 92935 |
+
"step": 13275
|
| 92936 |
+
},
|
| 92937 |
+
{
|
| 92938 |
+
"epoch": 15.120797720797722,
|
| 92939 |
+
"grad_norm": 0.1825498789548874,
|
| 92940 |
+
"learning_rate": 7.556948991033708e-06,
|
| 92941 |
+
"loss": 0.5826,
|
| 92942 |
+
"step": 13276
|
| 92943 |
+
},
|
| 92944 |
+
{
|
| 92945 |
+
"epoch": 15.121937321937322,
|
| 92946 |
+
"grad_norm": 0.18917182087898254,
|
| 92947 |
+
"learning_rate": 7.5536116029652215e-06,
|
| 92948 |
+
"loss": 0.7733,
|
| 92949 |
+
"step": 13277
|
| 92950 |
+
},
|
| 92951 |
+
{
|
| 92952 |
+
"epoch": 15.123076923076923,
|
| 92953 |
+
"grad_norm": 0.20644721388816833,
|
| 92954 |
+
"learning_rate": 7.550274820857789e-06,
|
| 92955 |
+
"loss": 0.7803,
|
| 92956 |
+
"step": 13278
|
| 92957 |
+
},
|
| 92958 |
+
{
|
| 92959 |
+
"epoch": 15.124216524216525,
|
| 92960 |
+
"grad_norm": 0.20011848211288452,
|
| 92961 |
+
"learning_rate": 7.546938644827289e-06,
|
| 92962 |
+
"loss": 0.6496,
|
| 92963 |
+
"step": 13279
|
| 92964 |
+
},
|
| 92965 |
+
{
|
| 92966 |
+
"epoch": 15.125356125356126,
|
| 92967 |
+
"grad_norm": 0.2278977930545807,
|
| 92968 |
+
"learning_rate": 7.543603074989608e-06,
|
| 92969 |
+
"loss": 0.5138,
|
| 92970 |
+
"step": 13280
|
| 92971 |
+
},
|
| 92972 |
+
{
|
| 92973 |
+
"epoch": 15.126495726495726,
|
| 92974 |
+
"grad_norm": 0.18745478987693787,
|
| 92975 |
+
"learning_rate": 7.540268111460599e-06,
|
| 92976 |
+
"loss": 0.5401,
|
| 92977 |
+
"step": 13281
|
| 92978 |
+
},
|
| 92979 |
+
{
|
| 92980 |
+
"epoch": 15.127635327635328,
|
| 92981 |
+
"grad_norm": 0.18297061324119568,
|
| 92982 |
+
"learning_rate": 7.53693375435609e-06,
|
| 92983 |
+
"loss": 0.6971,
|
| 92984 |
+
"step": 13282
|
| 92985 |
+
},
|
| 92986 |
+
{
|
| 92987 |
+
"epoch": 15.128774928774929,
|
| 92988 |
+
"grad_norm": 0.1973070651292801,
|
| 92989 |
+
"learning_rate": 7.5336000037918965e-06,
|
| 92990 |
+
"loss": 0.5205,
|
| 92991 |
+
"step": 13283
|
| 92992 |
+
},
|
| 92993 |
+
{
|
| 92994 |
+
"epoch": 15.12991452991453,
|
| 92995 |
+
"grad_norm": 0.22368676960468292,
|
| 92996 |
+
"learning_rate": 7.5302668598838085e-06,
|
| 92997 |
+
"loss": 0.7489,
|
| 92998 |
+
"step": 13284
|
| 92999 |
+
},
|
| 93000 |
+
{
|
| 93001 |
+
"epoch": 15.131054131054132,
|
| 93002 |
+
"grad_norm": 0.2430863231420517,
|
| 93003 |
+
"learning_rate": 7.526934322747603e-06,
|
| 93004 |
+
"loss": 0.7293,
|
| 93005 |
+
"step": 13285
|
| 93006 |
+
},
|
| 93007 |
+
{
|
| 93008 |
+
"epoch": 15.132193732193732,
|
| 93009 |
+
"grad_norm": 0.17869368195533752,
|
| 93010 |
+
"learning_rate": 7.5236023924990105e-06,
|
| 93011 |
+
"loss": 0.7587,
|
| 93012 |
+
"step": 13286
|
| 93013 |
+
},
|
| 93014 |
+
{
|
| 93015 |
+
"epoch": 15.133333333333333,
|
| 93016 |
+
"grad_norm": 0.21526575088500977,
|
| 93017 |
+
"learning_rate": 7.520271069253765e-06,
|
| 93018 |
+
"loss": 0.6364,
|
| 93019 |
+
"step": 13287
|
| 93020 |
+
},
|
| 93021 |
+
{
|
| 93022 |
+
"epoch": 15.134472934472935,
|
| 93023 |
+
"grad_norm": 0.19106706976890564,
|
| 93024 |
+
"learning_rate": 7.516940353127577e-06,
|
| 93025 |
+
"loss": 0.7858,
|
| 93026 |
+
"step": 13288
|
| 93027 |
+
},
|
| 93028 |
+
{
|
| 93029 |
+
"epoch": 15.135612535612536,
|
| 93030 |
+
"grad_norm": 0.17700304090976715,
|
| 93031 |
+
"learning_rate": 7.513610244236138e-06,
|
| 93032 |
+
"loss": 0.7265,
|
| 93033 |
+
"step": 13289
|
| 93034 |
+
},
|
| 93035 |
+
{
|
| 93036 |
+
"epoch": 15.136752136752136,
|
| 93037 |
+
"grad_norm": 0.18937309086322784,
|
| 93038 |
+
"learning_rate": 7.510280742695092e-06,
|
| 93039 |
+
"loss": 0.6815,
|
| 93040 |
+
"step": 13290
|
| 93041 |
+
},
|
| 93042 |
+
{
|
| 93043 |
+
"epoch": 15.137891737891739,
|
| 93044 |
+
"grad_norm": 0.18945249915122986,
|
| 93045 |
+
"learning_rate": 7.506951848620094e-06,
|
| 93046 |
+
"loss": 0.6224,
|
| 93047 |
+
"step": 13291
|
| 93048 |
+
},
|
| 93049 |
+
{
|
| 93050 |
+
"epoch": 15.13903133903134,
|
| 93051 |
+
"grad_norm": 0.22184334695339203,
|
| 93052 |
+
"learning_rate": 7.503623562126766e-06,
|
| 93053 |
+
"loss": 0.6988,
|
| 93054 |
+
"step": 13292
|
| 93055 |
+
},
|
| 93056 |
+
{
|
| 93057 |
+
"epoch": 15.14017094017094,
|
| 93058 |
+
"grad_norm": 0.2096634954214096,
|
| 93059 |
+
"learning_rate": 7.5002958833307075e-06,
|
| 93060 |
+
"loss": 0.8174,
|
| 93061 |
+
"step": 13293
|
| 93062 |
+
},
|
| 93063 |
+
{
|
| 93064 |
+
"epoch": 15.141310541310542,
|
| 93065 |
+
"grad_norm": 0.19907282292842865,
|
| 93066 |
+
"learning_rate": 7.496968812347494e-06,
|
| 93067 |
+
"loss": 0.5364,
|
| 93068 |
+
"step": 13294
|
| 93069 |
+
},
|
| 93070 |
+
{
|
| 93071 |
+
"epoch": 15.142450142450143,
|
| 93072 |
+
"grad_norm": 0.24593563377857208,
|
| 93073 |
+
"learning_rate": 7.49364234929269e-06,
|
| 93074 |
+
"loss": 0.649,
|
| 93075 |
+
"step": 13295
|
| 93076 |
+
},
|
| 93077 |
+
{
|
| 93078 |
+
"epoch": 15.143589743589743,
|
| 93079 |
+
"grad_norm": 0.22036831080913544,
|
| 93080 |
+
"learning_rate": 7.490316494281835e-06,
|
| 93081 |
+
"loss": 0.6822,
|
| 93082 |
+
"step": 13296
|
| 93083 |
+
},
|
| 93084 |
+
{
|
| 93085 |
+
"epoch": 15.144729344729345,
|
| 93086 |
+
"grad_norm": 0.224491149187088,
|
| 93087 |
+
"learning_rate": 7.486991247430433e-06,
|
| 93088 |
+
"loss": 0.6195,
|
| 93089 |
+
"step": 13297
|
| 93090 |
+
},
|
| 93091 |
+
{
|
| 93092 |
+
"epoch": 15.145868945868946,
|
| 93093 |
+
"grad_norm": 0.18605081737041473,
|
| 93094 |
+
"learning_rate": 7.483666608853987e-06,
|
| 93095 |
+
"loss": 0.4838,
|
| 93096 |
+
"step": 13298
|
| 93097 |
+
},
|
| 93098 |
+
{
|
| 93099 |
+
"epoch": 15.147008547008546,
|
| 93100 |
+
"grad_norm": 0.19752785563468933,
|
| 93101 |
+
"learning_rate": 7.4803425786679705e-06,
|
| 93102 |
+
"loss": 0.6153,
|
| 93103 |
+
"step": 13299
|
| 93104 |
+
},
|
| 93105 |
+
{
|
| 93106 |
+
"epoch": 15.148148148148149,
|
| 93107 |
+
"grad_norm": 0.17299829423427582,
|
| 93108 |
+
"learning_rate": 7.477019156987835e-06,
|
| 93109 |
+
"loss": 0.4304,
|
| 93110 |
+
"step": 13300
|
| 93111 |
+
},
|
| 93112 |
+
{
|
| 93113 |
+
"epoch": 15.14928774928775,
|
| 93114 |
+
"grad_norm": 0.2041027992963791,
|
| 93115 |
+
"learning_rate": 7.473696343929018e-06,
|
| 93116 |
+
"loss": 0.7166,
|
| 93117 |
+
"step": 13301
|
| 93118 |
+
},
|
| 93119 |
+
{
|
| 93120 |
+
"epoch": 15.15042735042735,
|
| 93121 |
+
"grad_norm": 0.22014085948467255,
|
| 93122 |
+
"learning_rate": 7.47037413960692e-06,
|
| 93123 |
+
"loss": 0.4789,
|
| 93124 |
+
"step": 13302
|
| 93125 |
+
},
|
| 93126 |
+
{
|
| 93127 |
+
"epoch": 15.151566951566952,
|
| 93128 |
+
"grad_norm": 0.2193816602230072,
|
| 93129 |
+
"learning_rate": 7.4670525441369236e-06,
|
| 93130 |
+
"loss": 0.7827,
|
| 93131 |
+
"step": 13303
|
| 93132 |
+
},
|
| 93133 |
+
{
|
| 93134 |
+
"epoch": 15.152706552706553,
|
| 93135 |
+
"grad_norm": 0.21887926757335663,
|
| 93136 |
+
"learning_rate": 7.463731557634426e-06,
|
| 93137 |
+
"loss": 0.5464,
|
| 93138 |
+
"step": 13304
|
| 93139 |
+
},
|
| 93140 |
+
{
|
| 93141 |
+
"epoch": 15.153846153846153,
|
| 93142 |
+
"grad_norm": 0.158628910779953,
|
| 93143 |
+
"learning_rate": 7.460411180214749e-06,
|
| 93144 |
+
"loss": 0.836,
|
| 93145 |
+
"step": 13305
|
| 93146 |
+
},
|
| 93147 |
+
{
|
| 93148 |
+
"epoch": 15.154985754985756,
|
| 93149 |
+
"grad_norm": 0.24886372685432434,
|
| 93150 |
+
"learning_rate": 7.457091411993225e-06,
|
| 93151 |
+
"loss": 0.6018,
|
| 93152 |
+
"step": 13306
|
| 93153 |
+
},
|
| 93154 |
+
{
|
| 93155 |
+
"epoch": 15.156125356125356,
|
| 93156 |
+
"grad_norm": 0.20588864386081696,
|
| 93157 |
+
"learning_rate": 7.453772253085159e-06,
|
| 93158 |
+
"loss": 0.6703,
|
| 93159 |
+
"step": 13307
|
| 93160 |
+
},
|
| 93161 |
+
{
|
| 93162 |
+
"epoch": 15.157264957264957,
|
| 93163 |
+
"grad_norm": 0.17586199939250946,
|
| 93164 |
+
"learning_rate": 7.450453703605845e-06,
|
| 93165 |
+
"loss": 0.821,
|
| 93166 |
+
"step": 13308
|
| 93167 |
+
},
|
| 93168 |
+
{
|
| 93169 |
+
"epoch": 15.158404558404559,
|
| 93170 |
+
"grad_norm": 0.22378386557102203,
|
| 93171 |
+
"learning_rate": 7.447135763670524e-06,
|
| 93172 |
+
"loss": 0.6723,
|
| 93173 |
+
"step": 13309
|
| 93174 |
+
},
|
| 93175 |
+
{
|
| 93176 |
+
"epoch": 15.15954415954416,
|
| 93177 |
+
"grad_norm": 0.2398693561553955,
|
| 93178 |
+
"learning_rate": 7.443818433394451e-06,
|
| 93179 |
+
"loss": 0.6561,
|
| 93180 |
+
"step": 13310
|
| 93181 |
+
},
|
| 93182 |
+
{
|
| 93183 |
+
"epoch": 15.16068376068376,
|
| 93184 |
+
"grad_norm": 0.280377060174942,
|
| 93185 |
+
"learning_rate": 7.440501712892842e-06,
|
| 93186 |
+
"loss": 0.6986,
|
| 93187 |
+
"step": 13311
|
| 93188 |
+
},
|
| 93189 |
+
{
|
| 93190 |
+
"epoch": 15.161823361823362,
|
| 93191 |
+
"grad_norm": 0.19695614278316498,
|
| 93192 |
+
"learning_rate": 7.437185602280905e-06,
|
| 93193 |
+
"loss": 0.6489,
|
| 93194 |
+
"step": 13312
|
| 93195 |
+
},
|
| 93196 |
+
{
|
| 93197 |
+
"epoch": 15.162962962962963,
|
| 93198 |
+
"grad_norm": 0.22838595509529114,
|
| 93199 |
+
"learning_rate": 7.433870101673804e-06,
|
| 93200 |
+
"loss": 0.6227,
|
| 93201 |
+
"step": 13313
|
| 93202 |
+
},
|
| 93203 |
+
{
|
| 93204 |
+
"epoch": 15.164102564102564,
|
| 93205 |
+
"grad_norm": 0.21671253442764282,
|
| 93206 |
+
"learning_rate": 7.43055521118669e-06,
|
| 93207 |
+
"loss": 0.551,
|
| 93208 |
+
"step": 13314
|
| 93209 |
+
},
|
| 93210 |
+
{
|
| 93211 |
+
"epoch": 15.165242165242166,
|
| 93212 |
+
"grad_norm": 0.16176068782806396,
|
| 93213 |
+
"learning_rate": 7.427240930934729e-06,
|
| 93214 |
+
"loss": 0.8505,
|
| 93215 |
+
"step": 13315
|
| 93216 |
+
},
|
| 93217 |
+
{
|
| 93218 |
+
"epoch": 15.166381766381766,
|
| 93219 |
+
"grad_norm": 0.21151845157146454,
|
| 93220 |
+
"learning_rate": 7.423927261033006e-06,
|
| 93221 |
+
"loss": 0.6639,
|
| 93222 |
+
"step": 13316
|
| 93223 |
+
},
|
| 93224 |
+
{
|
| 93225 |
+
"epoch": 15.167521367521367,
|
| 93226 |
+
"grad_norm": 0.20331384241580963,
|
| 93227 |
+
"learning_rate": 7.420614201596626e-06,
|
| 93228 |
+
"loss": 0.5958,
|
| 93229 |
+
"step": 13317
|
| 93230 |
+
},
|
| 93231 |
+
{
|
| 93232 |
+
"epoch": 15.16866096866097,
|
| 93233 |
+
"grad_norm": 0.2182028889656067,
|
| 93234 |
+
"learning_rate": 7.417301752740655e-06,
|
| 93235 |
+
"loss": 0.777,
|
| 93236 |
+
"step": 13318
|
| 93237 |
+
},
|
| 93238 |
+
{
|
| 93239 |
+
"epoch": 15.16980056980057,
|
| 93240 |
+
"grad_norm": 0.23227620124816895,
|
| 93241 |
+
"learning_rate": 7.4139899145801576e-06,
|
| 93242 |
+
"loss": 0.4787,
|
| 93243 |
+
"step": 13319
|
| 93244 |
+
},
|
| 93245 |
+
{
|
| 93246 |
+
"epoch": 15.17094017094017,
|
| 93247 |
+
"grad_norm": 0.2299741953611374,
|
| 93248 |
+
"learning_rate": 7.4106786872301434e-06,
|
| 93249 |
+
"loss": 0.7904,
|
| 93250 |
+
"step": 13320
|
| 93251 |
+
},
|
| 93252 |
+
{
|
| 93253 |
+
"epoch": 15.172079772079773,
|
| 93254 |
+
"grad_norm": 0.217166006565094,
|
| 93255 |
+
"learning_rate": 7.407368070805628e-06,
|
| 93256 |
+
"loss": 0.6805,
|
| 93257 |
+
"step": 13321
|
| 93258 |
+
},
|
| 93259 |
+
{
|
| 93260 |
+
"epoch": 15.173219373219373,
|
| 93261 |
+
"grad_norm": 0.1870729923248291,
|
| 93262 |
+
"learning_rate": 7.404058065421599e-06,
|
| 93263 |
+
"loss": 0.6697,
|
| 93264 |
+
"step": 13322
|
| 93265 |
+
},
|
| 93266 |
+
{
|
| 93267 |
+
"epoch": 15.174358974358974,
|
| 93268 |
+
"grad_norm": 0.18819458782672882,
|
| 93269 |
+
"learning_rate": 7.400748671193034e-06,
|
| 93270 |
+
"loss": 0.6807,
|
| 93271 |
+
"step": 13323
|
| 93272 |
+
},
|
| 93273 |
+
{
|
| 93274 |
+
"epoch": 15.175498575498576,
|
| 93275 |
+
"grad_norm": 0.2323538362979889,
|
| 93276 |
+
"learning_rate": 7.397439888234853e-06,
|
| 93277 |
+
"loss": 0.5102,
|
| 93278 |
+
"step": 13324
|
| 93279 |
+
},
|
| 93280 |
+
{
|
| 93281 |
+
"epoch": 15.176638176638177,
|
| 93282 |
+
"grad_norm": 0.25649964809417725,
|
| 93283 |
+
"learning_rate": 7.394131716661987e-06,
|
| 93284 |
+
"loss": 0.5656,
|
| 93285 |
+
"step": 13325
|
| 93286 |
+
},
|
| 93287 |
+
{
|
| 93288 |
+
"epoch": 15.177777777777777,
|
| 93289 |
+
"grad_norm": 0.19201435148715973,
|
| 93290 |
+
"learning_rate": 7.3908241565893575e-06,
|
| 93291 |
+
"loss": 0.6959,
|
| 93292 |
+
"step": 13326
|
| 93293 |
+
},
|
| 93294 |
+
{
|
| 93295 |
+
"epoch": 15.17891737891738,
|
| 93296 |
+
"grad_norm": 0.19382207095623016,
|
| 93297 |
+
"learning_rate": 7.387517208131823e-06,
|
| 93298 |
+
"loss": 0.5518,
|
| 93299 |
+
"step": 13327
|
| 93300 |
+
},
|
| 93301 |
+
{
|
| 93302 |
+
"epoch": 15.18005698005698,
|
| 93303 |
+
"grad_norm": 0.2733919322490692,
|
| 93304 |
+
"learning_rate": 7.384210871404251e-06,
|
| 93305 |
+
"loss": 0.5729,
|
| 93306 |
+
"step": 13328
|
| 93307 |
+
},
|
| 93308 |
+
{
|
| 93309 |
+
"epoch": 15.18119658119658,
|
| 93310 |
+
"grad_norm": 0.24027517437934875,
|
| 93311 |
+
"learning_rate": 7.380905146521477e-06,
|
| 93312 |
+
"loss": 0.4685,
|
| 93313 |
+
"step": 13329
|
| 93314 |
+
},
|
| 93315 |
+
{
|
| 93316 |
+
"epoch": 15.182336182336183,
|
| 93317 |
+
"grad_norm": 0.22657380998134613,
|
| 93318 |
+
"learning_rate": 7.377600033598331e-06,
|
| 93319 |
+
"loss": 0.6801,
|
| 93320 |
+
"step": 13330
|
| 93321 |
+
},
|
| 93322 |
+
{
|
| 93323 |
+
"epoch": 15.183475783475783,
|
| 93324 |
+
"grad_norm": 0.17790141701698303,
|
| 93325 |
+
"learning_rate": 7.374295532749586e-06,
|
| 93326 |
+
"loss": 0.7821,
|
| 93327 |
+
"step": 13331
|
| 93328 |
+
},
|
| 93329 |
+
{
|
| 93330 |
+
"epoch": 15.184615384615384,
|
| 93331 |
+
"grad_norm": 0.22210240364074707,
|
| 93332 |
+
"learning_rate": 7.37099164409003e-06,
|
| 93333 |
+
"loss": 0.7127,
|
| 93334 |
+
"step": 13332
|
| 93335 |
+
},
|
| 93336 |
+
{
|
| 93337 |
+
"epoch": 15.185754985754986,
|
| 93338 |
+
"grad_norm": 0.19975833594799042,
|
| 93339 |
+
"learning_rate": 7.367688367734415e-06,
|
| 93340 |
+
"loss": 0.7258,
|
| 93341 |
+
"step": 13333
|
| 93342 |
+
},
|
| 93343 |
+
{
|
| 93344 |
+
"epoch": 15.186894586894587,
|
| 93345 |
+
"grad_norm": 0.2221197634935379,
|
| 93346 |
+
"learning_rate": 7.36438570379748e-06,
|
| 93347 |
+
"loss": 0.4842,
|
| 93348 |
+
"step": 13334
|
| 93349 |
+
},
|
| 93350 |
+
{
|
| 93351 |
+
"epoch": 15.188034188034187,
|
| 93352 |
+
"grad_norm": 0.15724675357341766,
|
| 93353 |
+
"learning_rate": 7.361083652393919e-06,
|
| 93354 |
+
"loss": 0.7987,
|
| 93355 |
+
"step": 13335
|
| 93356 |
+
},
|
| 93357 |
+
{
|
| 93358 |
+
"epoch": 15.18917378917379,
|
| 93359 |
+
"grad_norm": 0.18950201570987701,
|
| 93360 |
+
"learning_rate": 7.3577822136384204e-06,
|
| 93361 |
+
"loss": 0.7515,
|
| 93362 |
+
"step": 13336
|
| 93363 |
+
},
|
| 93364 |
+
{
|
| 93365 |
+
"epoch": 15.19031339031339,
|
| 93366 |
+
"grad_norm": 0.19062010943889618,
|
| 93367 |
+
"learning_rate": 7.354481387645673e-06,
|
| 93368 |
+
"loss": 0.5944,
|
| 93369 |
+
"step": 13337
|
| 93370 |
+
},
|
| 93371 |
+
{
|
| 93372 |
+
"epoch": 15.19145299145299,
|
| 93373 |
+
"grad_norm": 0.22277235984802246,
|
| 93374 |
+
"learning_rate": 7.351181174530317e-06,
|
| 93375 |
+
"loss": 0.6526,
|
| 93376 |
+
"step": 13338
|
| 93377 |
+
},
|
| 93378 |
+
{
|
| 93379 |
+
"epoch": 15.192592592592593,
|
| 93380 |
+
"grad_norm": 0.16412495076656342,
|
| 93381 |
+
"learning_rate": 7.347881574406967e-06,
|
| 93382 |
+
"loss": 0.8125,
|
| 93383 |
+
"step": 13339
|
| 93384 |
+
},
|
| 93385 |
+
{
|
| 93386 |
+
"epoch": 15.193732193732194,
|
| 93387 |
+
"grad_norm": 0.19410619139671326,
|
| 93388 |
+
"learning_rate": 7.344582587390234e-06,
|
| 93389 |
+
"loss": 0.7798,
|
| 93390 |
+
"step": 13340
|
| 93391 |
+
},
|
| 93392 |
+
{
|
| 93393 |
+
"epoch": 15.194871794871794,
|
| 93394 |
+
"grad_norm": 0.17703565955162048,
|
| 93395 |
+
"learning_rate": 7.341284213594698e-06,
|
| 93396 |
+
"loss": 0.6936,
|
| 93397 |
+
"step": 13341
|
| 93398 |
+
},
|
| 93399 |
+
{
|
| 93400 |
+
"epoch": 15.196011396011396,
|
| 93401 |
+
"grad_norm": 0.18267908692359924,
|
| 93402 |
+
"learning_rate": 7.337986453134935e-06,
|
| 93403 |
+
"loss": 0.6342,
|
| 93404 |
+
"step": 13342
|
| 93405 |
+
},
|
| 93406 |
+
{
|
| 93407 |
+
"epoch": 15.197150997150997,
|
| 93408 |
+
"grad_norm": 0.20167747139930725,
|
| 93409 |
+
"learning_rate": 7.334689306125461e-06,
|
| 93410 |
+
"loss": 0.7808,
|
| 93411 |
+
"step": 13343
|
| 93412 |
+
},
|
| 93413 |
+
{
|
| 93414 |
+
"epoch": 15.198290598290598,
|
| 93415 |
+
"grad_norm": 0.1822354644536972,
|
| 93416 |
+
"learning_rate": 7.331392772680809e-06,
|
| 93417 |
+
"loss": 0.5235,
|
| 93418 |
+
"step": 13344
|
| 93419 |
+
},
|
| 93420 |
+
{
|
| 93421 |
+
"epoch": 15.1994301994302,
|
| 93422 |
+
"grad_norm": 0.18686936795711517,
|
| 93423 |
+
"learning_rate": 7.328096852915475e-06,
|
| 93424 |
+
"loss": 0.6758,
|
| 93425 |
+
"step": 13345
|
| 93426 |
+
},
|
| 93427 |
+
{
|
| 93428 |
+
"epoch": 15.2005698005698,
|
| 93429 |
+
"grad_norm": 0.19524578750133514,
|
| 93430 |
+
"learning_rate": 7.324801546943944e-06,
|
| 93431 |
+
"loss": 0.4665,
|
| 93432 |
+
"step": 13346
|
| 93433 |
+
},
|
| 93434 |
+
{
|
| 93435 |
+
"epoch": 15.201709401709401,
|
| 93436 |
+
"grad_norm": 0.19947238266468048,
|
| 93437 |
+
"learning_rate": 7.321506854880644e-06,
|
| 93438 |
+
"loss": 0.4769,
|
| 93439 |
+
"step": 13347
|
| 93440 |
+
},
|
| 93441 |
+
{
|
| 93442 |
+
"epoch": 15.202849002849003,
|
| 93443 |
+
"grad_norm": 0.24945421516895294,
|
| 93444 |
+
"learning_rate": 7.318212776840036e-06,
|
| 93445 |
+
"loss": 0.5923,
|
| 93446 |
+
"step": 13348
|
| 93447 |
+
},
|
| 93448 |
+
{
|
| 93449 |
+
"epoch": 15.203988603988604,
|
| 93450 |
+
"grad_norm": 0.17447318136692047,
|
| 93451 |
+
"learning_rate": 7.314919312936533e-06,
|
| 93452 |
+
"loss": 0.5977,
|
| 93453 |
+
"step": 13349
|
| 93454 |
+
},
|
| 93455 |
+
{
|
| 93456 |
+
"epoch": 15.205128205128204,
|
| 93457 |
+
"grad_norm": 0.21766497194766998,
|
| 93458 |
+
"learning_rate": 7.311626463284504e-06,
|
| 93459 |
+
"loss": 0.5435,
|
| 93460 |
+
"step": 13350
|
| 93461 |
+
},
|
| 93462 |
+
{
|
| 93463 |
+
"epoch": 15.206267806267807,
|
| 93464 |
+
"grad_norm": 0.23319518566131592,
|
| 93465 |
+
"learning_rate": 7.3083342279983365e-06,
|
| 93466 |
+
"loss": 0.5095,
|
| 93467 |
+
"step": 13351
|
| 93468 |
+
},
|
| 93469 |
+
{
|
| 93470 |
+
"epoch": 15.207407407407407,
|
| 93471 |
+
"grad_norm": 0.1703135073184967,
|
| 93472 |
+
"learning_rate": 7.305042607192369e-06,
|
| 93473 |
+
"loss": 0.7992,
|
| 93474 |
+
"step": 13352
|
| 93475 |
+
},
|
| 93476 |
+
{
|
| 93477 |
+
"epoch": 15.208547008547008,
|
| 93478 |
+
"grad_norm": 0.1810133010149002,
|
| 93479 |
+
"learning_rate": 7.301751600980944e-06,
|
| 93480 |
+
"loss": 0.8067,
|
| 93481 |
+
"step": 13353
|
| 93482 |
+
},
|
| 93483 |
+
{
|
| 93484 |
+
"epoch": 15.20968660968661,
|
| 93485 |
+
"grad_norm": 0.22245138883590698,
|
| 93486 |
+
"learning_rate": 7.298461209478349e-06,
|
| 93487 |
+
"loss": 0.608,
|
| 93488 |
+
"step": 13354
|
| 93489 |
+
},
|
| 93490 |
+
{
|
| 93491 |
+
"epoch": 15.21082621082621,
|
| 93492 |
+
"grad_norm": 0.1670108139514923,
|
| 93493 |
+
"learning_rate": 7.295171432798872e-06,
|
| 93494 |
+
"loss": 0.8941,
|
| 93495 |
+
"step": 13355
|
| 93496 |
+
},
|
| 93497 |
+
{
|
| 93498 |
+
"epoch": 15.211965811965811,
|
| 93499 |
+
"grad_norm": 0.2086310088634491,
|
| 93500 |
+
"learning_rate": 7.291882271056783e-06,
|
| 93501 |
+
"loss": 0.5176,
|
| 93502 |
+
"step": 13356
|
| 93503 |
+
},
|
| 93504 |
+
{
|
| 93505 |
+
"epoch": 15.213105413105414,
|
| 93506 |
+
"grad_norm": 0.18529261648654938,
|
| 93507 |
+
"learning_rate": 7.288593724366327e-06,
|
| 93508 |
+
"loss": 0.8927,
|
| 93509 |
+
"step": 13357
|
| 93510 |
+
},
|
| 93511 |
+
{
|
| 93512 |
+
"epoch": 15.214245014245014,
|
| 93513 |
+
"grad_norm": 0.1824301779270172,
|
| 93514 |
+
"learning_rate": 7.285305792841701e-06,
|
| 93515 |
+
"loss": 0.7053,
|
| 93516 |
+
"step": 13358
|
| 93517 |
+
},
|
| 93518 |
+
{
|
| 93519 |
+
"epoch": 15.215384615384615,
|
| 93520 |
+
"grad_norm": 0.1776217371225357,
|
| 93521 |
+
"learning_rate": 7.28201847659713e-06,
|
| 93522 |
+
"loss": 0.57,
|
| 93523 |
+
"step": 13359
|
| 93524 |
+
},
|
| 93525 |
+
{
|
| 93526 |
+
"epoch": 15.216524216524217,
|
| 93527 |
+
"grad_norm": 0.19689984619617462,
|
| 93528 |
+
"learning_rate": 7.278731775746789e-06,
|
| 93529 |
+
"loss": 0.6868,
|
| 93530 |
+
"step": 13360
|
| 93531 |
+
},
|
| 93532 |
+
{
|
| 93533 |
+
"epoch": 15.217663817663817,
|
| 93534 |
+
"grad_norm": 0.21592627465724945,
|
| 93535 |
+
"learning_rate": 7.275445690404817e-06,
|
| 93536 |
+
"loss": 0.5144,
|
| 93537 |
+
"step": 13361
|
| 93538 |
+
},
|
| 93539 |
+
{
|
| 93540 |
+
"epoch": 15.218803418803418,
|
| 93541 |
+
"grad_norm": 0.2437269538640976,
|
| 93542 |
+
"learning_rate": 7.272160220685362e-06,
|
| 93543 |
+
"loss": 0.5688,
|
| 93544 |
+
"step": 13362
|
| 93545 |
+
},
|
| 93546 |
+
{
|
| 93547 |
+
"epoch": 15.21994301994302,
|
| 93548 |
+
"grad_norm": 0.19515958428382874,
|
| 93549 |
+
"learning_rate": 7.268875366702532e-06,
|
| 93550 |
+
"loss": 0.7549,
|
| 93551 |
+
"step": 13363
|
| 93552 |
+
},
|
| 93553 |
+
{
|
| 93554 |
+
"epoch": 15.221082621082621,
|
| 93555 |
+
"grad_norm": 0.18477806448936462,
|
| 93556 |
+
"learning_rate": 7.265591128570431e-06,
|
| 93557 |
+
"loss": 0.4052,
|
| 93558 |
+
"step": 13364
|
| 93559 |
+
},
|
| 93560 |
+
{
|
| 93561 |
+
"epoch": 15.222222222222221,
|
| 93562 |
+
"grad_norm": 0.17877839505672455,
|
| 93563 |
+
"learning_rate": 7.262307506403113e-06,
|
| 93564 |
+
"loss": 0.8298,
|
| 93565 |
+
"step": 13365
|
| 93566 |
+
},
|
| 93567 |
+
{
|
| 93568 |
+
"epoch": 15.223361823361824,
|
| 93569 |
+
"grad_norm": 0.17731106281280518,
|
| 93570 |
+
"learning_rate": 7.259024500314632e-06,
|
| 93571 |
+
"loss": 0.6849,
|
| 93572 |
+
"step": 13366
|
| 93573 |
+
},
|
| 93574 |
+
{
|
| 93575 |
+
"epoch": 15.224501424501424,
|
| 93576 |
+
"grad_norm": 0.17548824846744537,
|
| 93577 |
+
"learning_rate": 7.255742110419017e-06,
|
| 93578 |
+
"loss": 0.6393,
|
| 93579 |
+
"step": 13367
|
| 93580 |
+
},
|
| 93581 |
+
{
|
| 93582 |
+
"epoch": 15.225641025641025,
|
| 93583 |
+
"grad_norm": 0.21052774786949158,
|
| 93584 |
+
"learning_rate": 7.252460336830286e-06,
|
| 93585 |
+
"loss": 0.7747,
|
| 93586 |
+
"step": 13368
|
| 93587 |
+
},
|
| 93588 |
+
{
|
| 93589 |
+
"epoch": 15.226780626780627,
|
| 93590 |
+
"grad_norm": 0.2353142499923706,
|
| 93591 |
+
"learning_rate": 7.249179179662397e-06,
|
| 93592 |
+
"loss": 0.5368,
|
| 93593 |
+
"step": 13369
|
| 93594 |
+
},
|
| 93595 |
+
{
|
| 93596 |
+
"epoch": 15.227920227920228,
|
| 93597 |
+
"grad_norm": 0.2377912402153015,
|
| 93598 |
+
"learning_rate": 7.245898639029336e-06,
|
| 93599 |
+
"loss": 0.4894,
|
| 93600 |
+
"step": 13370
|
| 93601 |
+
},
|
| 93602 |
+
{
|
| 93603 |
+
"epoch": 15.229059829059828,
|
| 93604 |
+
"grad_norm": 0.20241715013980865,
|
| 93605 |
+
"learning_rate": 7.24261871504505e-06,
|
| 93606 |
+
"loss": 0.6448,
|
| 93607 |
+
"step": 13371
|
| 93608 |
+
},
|
| 93609 |
+
{
|
| 93610 |
+
"epoch": 15.23019943019943,
|
| 93611 |
+
"grad_norm": 0.22061561048030853,
|
| 93612 |
+
"learning_rate": 7.239339407823437e-06,
|
| 93613 |
+
"loss": 0.4698,
|
| 93614 |
+
"step": 13372
|
| 93615 |
+
},
|
| 93616 |
+
{
|
| 93617 |
+
"epoch": 15.231339031339031,
|
| 93618 |
+
"grad_norm": 0.19990026950836182,
|
| 93619 |
+
"learning_rate": 7.2360607174784124e-06,
|
| 93620 |
+
"loss": 0.7864,
|
| 93621 |
+
"step": 13373
|
| 93622 |
+
},
|
| 93623 |
+
{
|
| 93624 |
+
"epoch": 15.232478632478632,
|
| 93625 |
+
"grad_norm": 0.16054971516132355,
|
| 93626 |
+
"learning_rate": 7.232782644123848e-06,
|
| 93627 |
+
"loss": 0.7828,
|
| 93628 |
+
"step": 13374
|
| 93629 |
+
},
|
| 93630 |
+
{
|
| 93631 |
+
"epoch": 15.233618233618234,
|
| 93632 |
+
"grad_norm": 0.20575302839279175,
|
| 93633 |
+
"learning_rate": 7.229505187873611e-06,
|
| 93634 |
+
"loss": 0.7156,
|
| 93635 |
+
"step": 13375
|
| 93636 |
+
},
|
| 93637 |
+
{
|
| 93638 |
+
"epoch": 15.234757834757835,
|
| 93639 |
+
"grad_norm": 0.27407199144363403,
|
| 93640 |
+
"learning_rate": 7.226228348841518e-06,
|
| 93641 |
+
"loss": 0.5875,
|
| 93642 |
+
"step": 13376
|
| 93643 |
+
},
|
| 93644 |
+
{
|
| 93645 |
+
"epoch": 15.235897435897435,
|
| 93646 |
+
"grad_norm": 0.1809110790491104,
|
| 93647 |
+
"learning_rate": 7.222952127141397e-06,
|
| 93648 |
+
"loss": 0.7659,
|
| 93649 |
+
"step": 13377
|
| 93650 |
+
},
|
| 93651 |
+
{
|
| 93652 |
+
"epoch": 15.237037037037037,
|
| 93653 |
+
"grad_norm": 0.21950261294841766,
|
| 93654 |
+
"learning_rate": 7.219676522887031e-06,
|
| 93655 |
+
"loss": 0.6556,
|
| 93656 |
+
"step": 13378
|
| 93657 |
+
},
|
| 93658 |
+
{
|
| 93659 |
+
"epoch": 15.238176638176638,
|
| 93660 |
+
"grad_norm": 0.19694559276103973,
|
| 93661 |
+
"learning_rate": 7.216401536192199e-06,
|
| 93662 |
+
"loss": 0.7612,
|
| 93663 |
+
"step": 13379
|
| 93664 |
+
},
|
| 93665 |
+
{
|
| 93666 |
+
"epoch": 15.239316239316238,
|
| 93667 |
+
"grad_norm": 0.19548237323760986,
|
| 93668 |
+
"learning_rate": 7.213127167170644e-06,
|
| 93669 |
+
"loss": 0.7912,
|
| 93670 |
+
"step": 13380
|
| 93671 |
+
},
|
| 93672 |
+
{
|
| 93673 |
+
"epoch": 15.24045584045584,
|
| 93674 |
+
"grad_norm": 0.22181104123592377,
|
| 93675 |
+
"learning_rate": 7.2098534159361e-06,
|
| 93676 |
+
"loss": 0.6947,
|
| 93677 |
+
"step": 13381
|
| 93678 |
+
},
|
| 93679 |
+
{
|
| 93680 |
+
"epoch": 15.241595441595441,
|
| 93681 |
+
"grad_norm": 0.19053779542446136,
|
| 93682 |
+
"learning_rate": 7.206580282602266e-06,
|
| 93683 |
+
"loss": 0.7365,
|
| 93684 |
+
"step": 13382
|
| 93685 |
+
},
|
| 93686 |
+
{
|
| 93687 |
+
"epoch": 15.242735042735042,
|
| 93688 |
+
"grad_norm": 0.20558376610279083,
|
| 93689 |
+
"learning_rate": 7.2033077672828404e-06,
|
| 93690 |
+
"loss": 0.6269,
|
| 93691 |
+
"step": 13383
|
| 93692 |
+
},
|
| 93693 |
+
{
|
| 93694 |
+
"epoch": 15.243874643874644,
|
| 93695 |
+
"grad_norm": 0.18020299077033997,
|
| 93696 |
+
"learning_rate": 7.200035870091471e-06,
|
| 93697 |
+
"loss": 0.656,
|
| 93698 |
+
"step": 13384
|
| 93699 |
+
},
|
| 93700 |
+
{
|
| 93701 |
+
"epoch": 15.245014245014245,
|
| 93702 |
+
"grad_norm": 0.21702425181865692,
|
| 93703 |
+
"learning_rate": 7.196764591141802e-06,
|
| 93704 |
+
"loss": 0.5239,
|
| 93705 |
+
"step": 13385
|
| 93706 |
+
},
|
| 93707 |
+
{
|
| 93708 |
+
"epoch": 15.246153846153845,
|
| 93709 |
+
"grad_norm": 0.22578953206539154,
|
| 93710 |
+
"learning_rate": 7.193493930547462e-06,
|
| 93711 |
+
"loss": 0.3689,
|
| 93712 |
+
"step": 13386
|
| 93713 |
+
},
|
| 93714 |
+
{
|
| 93715 |
+
"epoch": 15.247293447293448,
|
| 93716 |
+
"grad_norm": 0.2162429541349411,
|
| 93717 |
+
"learning_rate": 7.1902238884220516e-06,
|
| 93718 |
+
"loss": 0.7994,
|
| 93719 |
+
"step": 13387
|
| 93720 |
+
},
|
| 93721 |
+
{
|
| 93722 |
+
"epoch": 15.248433048433048,
|
| 93723 |
+
"grad_norm": 0.2074805051088333,
|
| 93724 |
+
"learning_rate": 7.186954464879136e-06,
|
| 93725 |
+
"loss": 0.7104,
|
| 93726 |
+
"step": 13388
|
| 93727 |
+
},
|
| 93728 |
+
{
|
| 93729 |
+
"epoch": 15.249572649572649,
|
| 93730 |
+
"grad_norm": 0.17333164811134338,
|
| 93731 |
+
"learning_rate": 7.1836856600322775e-06,
|
| 93732 |
+
"loss": 0.698,
|
| 93733 |
+
"step": 13389
|
| 93734 |
+
},
|
| 93735 |
+
{
|
| 93736 |
+
"epoch": 15.250712250712251,
|
| 93737 |
+
"grad_norm": 0.193593367934227,
|
| 93738 |
+
"learning_rate": 7.1804174739950105e-06,
|
| 93739 |
+
"loss": 0.4865,
|
| 93740 |
+
"step": 13390
|
| 93741 |
+
},
|
| 93742 |
+
{
|
| 93743 |
+
"epoch": 15.251851851851852,
|
| 93744 |
+
"grad_norm": 0.1828693002462387,
|
| 93745 |
+
"learning_rate": 7.177149906880848e-06,
|
| 93746 |
+
"loss": 0.7006,
|
| 93747 |
+
"step": 13391
|
| 93748 |
+
},
|
| 93749 |
+
{
|
| 93750 |
+
"epoch": 15.252991452991452,
|
| 93751 |
+
"grad_norm": 0.19954030215740204,
|
| 93752 |
+
"learning_rate": 7.173882958803282e-06,
|
| 93753 |
+
"loss": 0.5624,
|
| 93754 |
+
"step": 13392
|
| 93755 |
+
},
|
| 93756 |
+
{
|
| 93757 |
+
"epoch": 15.254131054131054,
|
| 93758 |
+
"grad_norm": 0.19160442054271698,
|
| 93759 |
+
"learning_rate": 7.170616629875784e-06,
|
| 93760 |
+
"loss": 0.7892,
|
| 93761 |
+
"step": 13393
|
| 93762 |
+
},
|
| 93763 |
+
{
|
| 93764 |
+
"epoch": 15.255270655270655,
|
| 93765 |
+
"grad_norm": 0.224081888794899,
|
| 93766 |
+
"learning_rate": 7.16735092021181e-06,
|
| 93767 |
+
"loss": 0.6121,
|
| 93768 |
+
"step": 13394
|
| 93769 |
+
},
|
| 93770 |
+
{
|
| 93771 |
+
"epoch": 15.256410256410255,
|
| 93772 |
+
"grad_norm": 0.1943773776292801,
|
| 93773 |
+
"learning_rate": 7.1640858299247684e-06,
|
| 93774 |
+
"loss": 0.6284,
|
| 93775 |
+
"step": 13395
|
| 93776 |
+
},
|
| 93777 |
+
{
|
| 93778 |
+
"epoch": 15.257549857549858,
|
| 93779 |
+
"grad_norm": 0.1929141879081726,
|
| 93780 |
+
"learning_rate": 7.160821359128078e-06,
|
| 93781 |
+
"loss": 0.8806,
|
| 93782 |
+
"step": 13396
|
| 93783 |
+
},
|
| 93784 |
+
{
|
| 93785 |
+
"epoch": 15.258689458689458,
|
| 93786 |
+
"grad_norm": 0.27313852310180664,
|
| 93787 |
+
"learning_rate": 7.157557507935117e-06,
|
| 93788 |
+
"loss": 0.4549,
|
| 93789 |
+
"step": 13397
|
| 93790 |
+
},
|
| 93791 |
+
{
|
| 93792 |
+
"epoch": 15.25982905982906,
|
| 93793 |
+
"grad_norm": 0.4554316997528076,
|
| 93794 |
+
"learning_rate": 7.154294276459258e-06,
|
| 93795 |
+
"loss": 0.6778,
|
| 93796 |
+
"step": 13398
|
| 93797 |
+
},
|
| 93798 |
+
{
|
| 93799 |
+
"epoch": 15.260968660968661,
|
| 93800 |
+
"grad_norm": 0.19258996844291687,
|
| 93801 |
+
"learning_rate": 7.151031664813829e-06,
|
| 93802 |
+
"loss": 0.7,
|
| 93803 |
+
"step": 13399
|
| 93804 |
+
},
|
| 93805 |
+
{
|
| 93806 |
+
"epoch": 15.262108262108262,
|
| 93807 |
+
"grad_norm": 0.24250654876232147,
|
| 93808 |
+
"learning_rate": 7.1477696731121565e-06,
|
| 93809 |
+
"loss": 0.6825,
|
| 93810 |
+
"step": 13400
|
| 93811 |
+
},
|
| 93812 |
+
{
|
| 93813 |
+
"epoch": 15.263247863247864,
|
| 93814 |
+
"grad_norm": 0.2219674438238144,
|
| 93815 |
+
"learning_rate": 7.144508301467534e-06,
|
| 93816 |
+
"loss": 0.8407,
|
| 93817 |
+
"step": 13401
|
| 93818 |
+
},
|
| 93819 |
+
{
|
| 93820 |
+
"epoch": 15.264387464387465,
|
| 93821 |
+
"grad_norm": 0.2358654886484146,
|
| 93822 |
+
"learning_rate": 7.141247549993241e-06,
|
| 93823 |
+
"loss": 0.5774,
|
| 93824 |
+
"step": 13402
|
| 93825 |
+
},
|
| 93826 |
+
{
|
| 93827 |
+
"epoch": 15.265527065527065,
|
| 93828 |
+
"grad_norm": 0.20805026590824127,
|
| 93829 |
+
"learning_rate": 7.137987418802533e-06,
|
| 93830 |
+
"loss": 0.6997,
|
| 93831 |
+
"step": 13403
|
| 93832 |
+
},
|
| 93833 |
+
{
|
| 93834 |
+
"epoch": 15.266666666666667,
|
| 93835 |
+
"grad_norm": 0.19631749391555786,
|
| 93836 |
+
"learning_rate": 7.134727908008645e-06,
|
| 93837 |
+
"loss": 0.6452,
|
| 93838 |
+
"step": 13404
|
| 93839 |
+
},
|
| 93840 |
+
{
|
| 93841 |
+
"epoch": 15.267806267806268,
|
| 93842 |
+
"grad_norm": 0.19085797667503357,
|
| 93843 |
+
"learning_rate": 7.1314690177247925e-06,
|
| 93844 |
+
"loss": 0.87,
|
| 93845 |
+
"step": 13405
|
| 93846 |
+
},
|
| 93847 |
+
{
|
| 93848 |
+
"epoch": 15.268945868945869,
|
| 93849 |
+
"grad_norm": 0.16966448724269867,
|
| 93850 |
+
"learning_rate": 7.128210748064151e-06,
|
| 93851 |
+
"loss": 0.6457,
|
| 93852 |
+
"step": 13406
|
| 93853 |
+
},
|
| 93854 |
+
{
|
| 93855 |
+
"epoch": 15.270085470085471,
|
| 93856 |
+
"grad_norm": 0.22518151998519897,
|
| 93857 |
+
"learning_rate": 7.1249530991398974e-06,
|
| 93858 |
+
"loss": 0.6048,
|
| 93859 |
+
"step": 13407
|
| 93860 |
+
},
|
| 93861 |
+
{
|
| 93862 |
+
"epoch": 15.271225071225071,
|
| 93863 |
+
"grad_norm": 0.1851891130208969,
|
| 93864 |
+
"learning_rate": 7.1216960710651815e-06,
|
| 93865 |
+
"loss": 0.564,
|
| 93866 |
+
"step": 13408
|
| 93867 |
+
},
|
| 93868 |
+
{
|
| 93869 |
+
"epoch": 15.272364672364672,
|
| 93870 |
+
"grad_norm": 0.20710742473602295,
|
| 93871 |
+
"learning_rate": 7.118439663953133e-06,
|
| 93872 |
+
"loss": 0.5152,
|
| 93873 |
+
"step": 13409
|
| 93874 |
+
},
|
| 93875 |
+
{
|
| 93876 |
+
"epoch": 15.273504273504274,
|
| 93877 |
+
"grad_norm": 0.1835888773202896,
|
| 93878 |
+
"learning_rate": 7.115183877916842e-06,
|
| 93879 |
+
"loss": 0.5819,
|
| 93880 |
+
"step": 13410
|
| 93881 |
+
},
|
| 93882 |
+
{
|
| 93883 |
+
"epoch": 15.274643874643875,
|
| 93884 |
+
"grad_norm": 0.1785074919462204,
|
| 93885 |
+
"learning_rate": 7.111928713069399e-06,
|
| 93886 |
+
"loss": 0.8095,
|
| 93887 |
+
"step": 13411
|
| 93888 |
+
},
|
| 93889 |
+
{
|
| 93890 |
+
"epoch": 15.275783475783475,
|
| 93891 |
+
"grad_norm": 0.19669075310230255,
|
| 93892 |
+
"learning_rate": 7.108674169523863e-06,
|
| 93893 |
+
"loss": 0.6795,
|
| 93894 |
+
"step": 13412
|
| 93895 |
+
},
|
| 93896 |
+
{
|
| 93897 |
+
"epoch": 15.276923076923078,
|
| 93898 |
+
"grad_norm": 0.2427806556224823,
|
| 93899 |
+
"learning_rate": 7.1054202473932825e-06,
|
| 93900 |
+
"loss": 0.6465,
|
| 93901 |
+
"step": 13413
|
| 93902 |
+
},
|
| 93903 |
+
{
|
| 93904 |
+
"epoch": 15.278062678062678,
|
| 93905 |
+
"grad_norm": 0.1938008964061737,
|
| 93906 |
+
"learning_rate": 7.102166946790651e-06,
|
| 93907 |
+
"loss": 0.6594,
|
| 93908 |
+
"step": 13414
|
| 93909 |
+
},
|
| 93910 |
+
{
|
| 93911 |
+
"epoch": 15.279202279202279,
|
| 93912 |
+
"grad_norm": 0.21511799097061157,
|
| 93913 |
+
"learning_rate": 7.09891426782899e-06,
|
| 93914 |
+
"loss": 0.7886,
|
| 93915 |
+
"step": 13415
|
| 93916 |
+
},
|
| 93917 |
+
{
|
| 93918 |
+
"epoch": 15.280341880341881,
|
| 93919 |
+
"grad_norm": 0.19147200882434845,
|
| 93920 |
+
"learning_rate": 7.095662210621262e-06,
|
| 93921 |
+
"loss": 0.6507,
|
| 93922 |
+
"step": 13416
|
| 93923 |
+
},
|
| 93924 |
+
{
|
| 93925 |
+
"epoch": 15.281481481481482,
|
| 93926 |
+
"grad_norm": 0.21382924914360046,
|
| 93927 |
+
"learning_rate": 7.092410775280434e-06,
|
| 93928 |
+
"loss": 0.6097,
|
| 93929 |
+
"step": 13417
|
| 93930 |
+
},
|
| 93931 |
+
{
|
| 93932 |
+
"epoch": 15.282621082621082,
|
| 93933 |
+
"grad_norm": 0.20031499862670898,
|
| 93934 |
+
"learning_rate": 7.089159961919414e-06,
|
| 93935 |
+
"loss": 0.5536,
|
| 93936 |
+
"step": 13418
|
| 93937 |
+
},
|
| 93938 |
+
{
|
| 93939 |
+
"epoch": 15.283760683760685,
|
| 93940 |
+
"grad_norm": 0.2048831731081009,
|
| 93941 |
+
"learning_rate": 7.085909770651128e-06,
|
| 93942 |
+
"loss": 0.8472,
|
| 93943 |
+
"step": 13419
|
| 93944 |
+
},
|
| 93945 |
+
{
|
| 93946 |
+
"epoch": 15.284900284900285,
|
| 93947 |
+
"grad_norm": 0.19666039943695068,
|
| 93948 |
+
"learning_rate": 7.0826602015884566e-06,
|
| 93949 |
+
"loss": 0.7362,
|
| 93950 |
+
"step": 13420
|
| 93951 |
+
},
|
| 93952 |
+
{
|
| 93953 |
+
"epoch": 15.286039886039886,
|
| 93954 |
+
"grad_norm": 0.17590700089931488,
|
| 93955 |
+
"learning_rate": 7.079411254844276e-06,
|
| 93956 |
+
"loss": 0.6823,
|
| 93957 |
+
"step": 13421
|
| 93958 |
+
},
|
| 93959 |
+
{
|
| 93960 |
+
"epoch": 15.287179487179488,
|
| 93961 |
+
"grad_norm": 0.17183063924312592,
|
| 93962 |
+
"learning_rate": 7.076162930531418e-06,
|
| 93963 |
+
"loss": 0.7005,
|
| 93964 |
+
"step": 13422
|
| 93965 |
+
},
|
| 93966 |
+
{
|
| 93967 |
+
"epoch": 15.288319088319088,
|
| 93968 |
+
"grad_norm": 0.2370138019323349,
|
| 93969 |
+
"learning_rate": 7.072915228762714e-06,
|
| 93970 |
+
"loss": 0.5092,
|
| 93971 |
+
"step": 13423
|
| 93972 |
+
},
|
| 93973 |
+
{
|
| 93974 |
+
"epoch": 15.289458689458689,
|
| 93975 |
+
"grad_norm": 0.16556316614151,
|
| 93976 |
+
"learning_rate": 7.069668149650962e-06,
|
| 93977 |
+
"loss": 0.6152,
|
| 93978 |
+
"step": 13424
|
| 93979 |
+
},
|
| 93980 |
+
{
|
| 93981 |
+
"epoch": 15.290598290598291,
|
| 93982 |
+
"grad_norm": 0.1977030485868454,
|
| 93983 |
+
"learning_rate": 7.066421693308945e-06,
|
| 93984 |
+
"loss": 0.6643,
|
| 93985 |
+
"step": 13425
|
| 93986 |
+
},
|
| 93987 |
+
{
|
| 93988 |
+
"epoch": 15.291737891737892,
|
| 93989 |
+
"grad_norm": 0.19474047422409058,
|
| 93990 |
+
"learning_rate": 7.063175859849419e-06,
|
| 93991 |
+
"loss": 0.5826,
|
| 93992 |
+
"step": 13426
|
| 93993 |
+
},
|
| 93994 |
+
{
|
| 93995 |
+
"epoch": 15.292877492877492,
|
| 93996 |
+
"grad_norm": 0.1902286559343338,
|
| 93997 |
+
"learning_rate": 7.059930649385122e-06,
|
| 93998 |
+
"loss": 0.622,
|
| 93999 |
+
"step": 13427
|
| 94000 |
+
},
|
| 94001 |
+
{
|
| 94002 |
+
"epoch": 15.294017094017095,
|
| 94003 |
+
"grad_norm": 0.252772718667984,
|
| 94004 |
+
"learning_rate": 7.056686062028775e-06,
|
| 94005 |
+
"loss": 0.548,
|
| 94006 |
+
"step": 13428
|
| 94007 |
+
},
|
| 94008 |
+
{
|
| 94009 |
+
"epoch": 15.295156695156695,
|
| 94010 |
+
"grad_norm": 0.21062877774238586,
|
| 94011 |
+
"learning_rate": 7.05344209789306e-06,
|
| 94012 |
+
"loss": 0.4934,
|
| 94013 |
+
"step": 13429
|
| 94014 |
+
},
|
| 94015 |
+
{
|
| 94016 |
+
"epoch": 15.296296296296296,
|
| 94017 |
+
"grad_norm": 0.2218659371137619,
|
| 94018 |
+
"learning_rate": 7.050198757090653e-06,
|
| 94019 |
+
"loss": 0.6007,
|
| 94020 |
+
"step": 13430
|
| 94021 |
+
},
|
| 94022 |
+
{
|
| 94023 |
+
"epoch": 15.297435897435898,
|
| 94024 |
+
"grad_norm": 0.3193570375442505,
|
| 94025 |
+
"learning_rate": 7.046956039734206e-06,
|
| 94026 |
+
"loss": 0.2876,
|
| 94027 |
+
"step": 13431
|
| 94028 |
+
},
|
| 94029 |
+
{
|
| 94030 |
+
"epoch": 15.298575498575499,
|
| 94031 |
+
"grad_norm": 0.19239835441112518,
|
| 94032 |
+
"learning_rate": 7.0437139459363535e-06,
|
| 94033 |
+
"loss": 0.8156,
|
| 94034 |
+
"step": 13432
|
| 94035 |
+
},
|
| 94036 |
+
{
|
| 94037 |
+
"epoch": 15.2997150997151,
|
| 94038 |
+
"grad_norm": 0.21255037188529968,
|
| 94039 |
+
"learning_rate": 7.04047247580969e-06,
|
| 94040 |
+
"loss": 0.6548,
|
| 94041 |
+
"step": 13433
|
| 94042 |
+
},
|
| 94043 |
+
{
|
| 94044 |
+
"epoch": 15.300854700854702,
|
| 94045 |
+
"grad_norm": 0.22222843766212463,
|
| 94046 |
+
"learning_rate": 7.037231629466804e-06,
|
| 94047 |
+
"loss": 0.6232,
|
| 94048 |
+
"step": 13434
|
| 94049 |
+
},
|
| 94050 |
+
{
|
| 94051 |
+
"epoch": 15.301994301994302,
|
| 94052 |
+
"grad_norm": 0.21897831559181213,
|
| 94053 |
+
"learning_rate": 7.0339914070202625e-06,
|
| 94054 |
+
"loss": 0.7452,
|
| 94055 |
+
"step": 13435
|
| 94056 |
+
},
|
| 94057 |
+
{
|
| 94058 |
+
"epoch": 15.303133903133903,
|
| 94059 |
+
"grad_norm": 0.19468940794467926,
|
| 94060 |
+
"learning_rate": 7.0307518085826055e-06,
|
| 94061 |
+
"loss": 0.6738,
|
| 94062 |
+
"step": 13436
|
| 94063 |
+
},
|
| 94064 |
+
{
|
| 94065 |
+
"epoch": 15.304273504273505,
|
| 94066 |
+
"grad_norm": 0.2297879457473755,
|
| 94067 |
+
"learning_rate": 7.0275128342663536e-06,
|
| 94068 |
+
"loss": 0.4746,
|
| 94069 |
+
"step": 13437
|
| 94070 |
+
},
|
| 94071 |
+
{
|
| 94072 |
+
"epoch": 15.305413105413106,
|
| 94073 |
+
"grad_norm": 0.20002175867557526,
|
| 94074 |
+
"learning_rate": 7.024274484184007e-06,
|
| 94075 |
+
"loss": 0.43,
|
| 94076 |
+
"step": 13438
|
| 94077 |
+
},
|
| 94078 |
+
{
|
| 94079 |
+
"epoch": 15.306552706552706,
|
| 94080 |
+
"grad_norm": 0.21483980119228363,
|
| 94081 |
+
"learning_rate": 7.0210367584480465e-06,
|
| 94082 |
+
"loss": 0.6486,
|
| 94083 |
+
"step": 13439
|
| 94084 |
+
},
|
| 94085 |
+
{
|
| 94086 |
+
"epoch": 15.307692307692308,
|
| 94087 |
+
"grad_norm": 0.17824262380599976,
|
| 94088 |
+
"learning_rate": 7.017799657170918e-06,
|
| 94089 |
+
"loss": 0.9038,
|
| 94090 |
+
"step": 13440
|
| 94091 |
+
},
|
| 94092 |
+
{
|
| 94093 |
+
"epoch": 15.308831908831909,
|
| 94094 |
+
"grad_norm": 0.20306964218616486,
|
| 94095 |
+
"learning_rate": 7.014563180465055e-06,
|
| 94096 |
+
"loss": 0.6428,
|
| 94097 |
+
"step": 13441
|
| 94098 |
+
},
|
| 94099 |
+
{
|
| 94100 |
+
"epoch": 15.30997150997151,
|
| 94101 |
+
"grad_norm": 0.15465456247329712,
|
| 94102 |
+
"learning_rate": 7.011327328442874e-06,
|
| 94103 |
+
"loss": 0.4822,
|
| 94104 |
+
"step": 13442
|
| 94105 |
+
},
|
| 94106 |
+
{
|
| 94107 |
+
"epoch": 15.311111111111112,
|
| 94108 |
+
"grad_norm": 0.19104813039302826,
|
| 94109 |
+
"learning_rate": 7.008092101216771e-06,
|
| 94110 |
+
"loss": 0.7172,
|
| 94111 |
+
"step": 13443
|
| 94112 |
+
},
|
| 94113 |
+
{
|
| 94114 |
+
"epoch": 15.312250712250712,
|
| 94115 |
+
"grad_norm": 0.18439635634422302,
|
| 94116 |
+
"learning_rate": 7.0048574988991e-06,
|
| 94117 |
+
"loss": 0.6679,
|
| 94118 |
+
"step": 13444
|
| 94119 |
+
},
|
| 94120 |
+
{
|
| 94121 |
+
"epoch": 15.313390313390313,
|
| 94122 |
+
"grad_norm": 0.19624824821949005,
|
| 94123 |
+
"learning_rate": 7.001623521602216e-06,
|
| 94124 |
+
"loss": 0.676,
|
| 94125 |
+
"step": 13445
|
| 94126 |
+
},
|
| 94127 |
+
{
|
| 94128 |
+
"epoch": 15.314529914529915,
|
| 94129 |
+
"grad_norm": 0.20672352612018585,
|
| 94130 |
+
"learning_rate": 6.99839016943844e-06,
|
| 94131 |
+
"loss": 0.7165,
|
| 94132 |
+
"step": 13446
|
| 94133 |
+
},
|
| 94134 |
+
{
|
| 94135 |
+
"epoch": 15.315669515669516,
|
| 94136 |
+
"grad_norm": 0.21458734571933746,
|
| 94137 |
+
"learning_rate": 6.995157442520081e-06,
|
| 94138 |
+
"loss": 0.7422,
|
| 94139 |
+
"step": 13447
|
| 94140 |
+
},
|
| 94141 |
+
{
|
| 94142 |
+
"epoch": 15.316809116809116,
|
| 94143 |
+
"grad_norm": 0.18510808050632477,
|
| 94144 |
+
"learning_rate": 6.9919253409594155e-06,
|
| 94145 |
+
"loss": 0.671,
|
| 94146 |
+
"step": 13448
|
| 94147 |
+
},
|
| 94148 |
+
{
|
| 94149 |
+
"epoch": 15.317948717948719,
|
| 94150 |
+
"grad_norm": 0.20022939145565033,
|
| 94151 |
+
"learning_rate": 6.988693864868706e-06,
|
| 94152 |
+
"loss": 0.7407,
|
| 94153 |
+
"step": 13449
|
| 94154 |
+
},
|
| 94155 |
+
{
|
| 94156 |
+
"epoch": 15.31908831908832,
|
| 94157 |
+
"grad_norm": 0.22099626064300537,
|
| 94158 |
+
"learning_rate": 6.985463014360197e-06,
|
| 94159 |
+
"loss": 0.5132,
|
| 94160 |
+
"step": 13450
|
| 94161 |
+
},
|
| 94162 |
+
{
|
| 94163 |
+
"epoch": 15.32022792022792,
|
| 94164 |
+
"grad_norm": 0.1770186424255371,
|
| 94165 |
+
"learning_rate": 6.982232789546092e-06,
|
| 94166 |
+
"loss": 0.59,
|
| 94167 |
+
"step": 13451
|
| 94168 |
+
},
|
| 94169 |
+
{
|
| 94170 |
+
"epoch": 15.321367521367522,
|
| 94171 |
+
"grad_norm": 0.17203353345394135,
|
| 94172 |
+
"learning_rate": 6.979003190538588e-06,
|
| 94173 |
+
"loss": 0.8341,
|
| 94174 |
+
"step": 13452
|
| 94175 |
+
},
|
| 94176 |
+
{
|
| 94177 |
+
"epoch": 15.322507122507123,
|
| 94178 |
+
"grad_norm": 0.1846415251493454,
|
| 94179 |
+
"learning_rate": 6.975774217449865e-06,
|
| 94180 |
+
"loss": 0.6996,
|
| 94181 |
+
"step": 13453
|
| 94182 |
+
},
|
| 94183 |
+
{
|
| 94184 |
+
"epoch": 15.323646723646723,
|
| 94185 |
+
"grad_norm": 0.21757927536964417,
|
| 94186 |
+
"learning_rate": 6.972545870392075e-06,
|
| 94187 |
+
"loss": 0.5245,
|
| 94188 |
+
"step": 13454
|
| 94189 |
+
},
|
| 94190 |
+
{
|
| 94191 |
+
"epoch": 15.324786324786325,
|
| 94192 |
+
"grad_norm": 0.1696988046169281,
|
| 94193 |
+
"learning_rate": 6.969318149477336e-06,
|
| 94194 |
+
"loss": 0.5843,
|
| 94195 |
+
"step": 13455
|
| 94196 |
+
},
|
| 94197 |
+
{
|
| 94198 |
+
"epoch": 15.325925925925926,
|
| 94199 |
+
"grad_norm": 0.1950981318950653,
|
| 94200 |
+
"learning_rate": 6.966091054817764e-06,
|
| 94201 |
+
"loss": 0.8791,
|
| 94202 |
+
"step": 13456
|
| 94203 |
+
},
|
| 94204 |
+
{
|
| 94205 |
+
"epoch": 15.327065527065526,
|
| 94206 |
+
"grad_norm": 0.1883671134710312,
|
| 94207 |
+
"learning_rate": 6.962864586525439e-06,
|
| 94208 |
+
"loss": 0.7896,
|
| 94209 |
+
"step": 13457
|
| 94210 |
+
},
|
| 94211 |
+
{
|
| 94212 |
+
"epoch": 15.328205128205129,
|
| 94213 |
+
"grad_norm": 0.23657511174678802,
|
| 94214 |
+
"learning_rate": 6.959638744712432e-06,
|
| 94215 |
+
"loss": 0.5707,
|
| 94216 |
+
"step": 13458
|
| 94217 |
+
},
|
| 94218 |
+
{
|
| 94219 |
+
"epoch": 15.32934472934473,
|
| 94220 |
+
"grad_norm": 0.17644041776657104,
|
| 94221 |
+
"learning_rate": 6.956413529490782e-06,
|
| 94222 |
+
"loss": 0.6035,
|
| 94223 |
+
"step": 13459
|
| 94224 |
+
},
|
| 94225 |
+
{
|
| 94226 |
+
"epoch": 15.33048433048433,
|
| 94227 |
+
"grad_norm": 0.16345062851905823,
|
| 94228 |
+
"learning_rate": 6.953188940972511e-06,
|
| 94229 |
+
"loss": 0.7362,
|
| 94230 |
+
"step": 13460
|
| 94231 |
+
},
|
| 94232 |
+
{
|
| 94233 |
+
"epoch": 15.331623931623932,
|
| 94234 |
+
"grad_norm": 0.20905448496341705,
|
| 94235 |
+
"learning_rate": 6.949964979269616e-06,
|
| 94236 |
+
"loss": 0.7829,
|
| 94237 |
+
"step": 13461
|
| 94238 |
+
},
|
| 94239 |
+
{
|
| 94240 |
+
"epoch": 15.332763532763533,
|
| 94241 |
+
"grad_norm": 0.1936965137720108,
|
| 94242 |
+
"learning_rate": 6.946741644494084e-06,
|
| 94243 |
+
"loss": 0.6073,
|
| 94244 |
+
"step": 13462
|
| 94245 |
+
},
|
| 94246 |
+
{
|
| 94247 |
+
"epoch": 15.333903133903133,
|
| 94248 |
+
"grad_norm": 0.19706177711486816,
|
| 94249 |
+
"learning_rate": 6.94351893675785e-06,
|
| 94250 |
+
"loss": 0.8126,
|
| 94251 |
+
"step": 13463
|
| 94252 |
+
},
|
| 94253 |
+
{
|
| 94254 |
+
"epoch": 15.335042735042736,
|
| 94255 |
+
"grad_norm": 0.22282631695270538,
|
| 94256 |
+
"learning_rate": 6.940296856172862e-06,
|
| 94257 |
+
"loss": 0.4836,
|
| 94258 |
+
"step": 13464
|
| 94259 |
+
},
|
| 94260 |
+
{
|
| 94261 |
+
"epoch": 15.336182336182336,
|
| 94262 |
+
"grad_norm": 0.19140516221523285,
|
| 94263 |
+
"learning_rate": 6.937075402851029e-06,
|
| 94264 |
+
"loss": 0.7697,
|
| 94265 |
+
"step": 13465
|
| 94266 |
+
},
|
| 94267 |
+
{
|
| 94268 |
+
"epoch": 15.337321937321937,
|
| 94269 |
+
"grad_norm": 0.18049626052379608,
|
| 94270 |
+
"learning_rate": 6.933854576904248e-06,
|
| 94271 |
+
"loss": 0.8117,
|
| 94272 |
+
"step": 13466
|
| 94273 |
+
},
|
| 94274 |
+
{
|
| 94275 |
+
"epoch": 15.338461538461539,
|
| 94276 |
+
"grad_norm": 0.2209792137145996,
|
| 94277 |
+
"learning_rate": 6.93063437844437e-06,
|
| 94278 |
+
"loss": 0.718,
|
| 94279 |
+
"step": 13467
|
| 94280 |
+
},
|
| 94281 |
+
{
|
| 94282 |
+
"epoch": 15.33960113960114,
|
| 94283 |
+
"grad_norm": 0.16232642531394958,
|
| 94284 |
+
"learning_rate": 6.927414807583252e-06,
|
| 94285 |
+
"loss": 0.7753,
|
| 94286 |
+
"step": 13468
|
| 94287 |
+
},
|
| 94288 |
+
{
|
| 94289 |
+
"epoch": 15.34074074074074,
|
| 94290 |
+
"grad_norm": 0.17342950403690338,
|
| 94291 |
+
"learning_rate": 6.924195864432717e-06,
|
| 94292 |
+
"loss": 0.8164,
|
| 94293 |
+
"step": 13469
|
| 94294 |
+
},
|
| 94295 |
+
{
|
| 94296 |
+
"epoch": 15.341880341880342,
|
| 94297 |
+
"grad_norm": 0.1576143354177475,
|
| 94298 |
+
"learning_rate": 6.9209775491045705e-06,
|
| 94299 |
+
"loss": 0.638,
|
| 94300 |
+
"step": 13470
|
| 94301 |
+
},
|
| 94302 |
+
{
|
| 94303 |
+
"epoch": 15.343019943019943,
|
| 94304 |
+
"grad_norm": 0.21170037984848022,
|
| 94305 |
+
"learning_rate": 6.91775986171059e-06,
|
| 94306 |
+
"loss": 0.5737,
|
| 94307 |
+
"step": 13471
|
| 94308 |
+
},
|
| 94309 |
+
{
|
| 94310 |
+
"epoch": 15.344159544159544,
|
| 94311 |
+
"grad_norm": 0.21984083950519562,
|
| 94312 |
+
"learning_rate": 6.9145428023625365e-06,
|
| 94313 |
+
"loss": 0.6241,
|
| 94314 |
+
"step": 13472
|
| 94315 |
+
},
|
| 94316 |
+
{
|
| 94317 |
+
"epoch": 15.345299145299146,
|
| 94318 |
+
"grad_norm": 0.19216473400592804,
|
| 94319 |
+
"learning_rate": 6.911326371172153e-06,
|
| 94320 |
+
"loss": 0.5762,
|
| 94321 |
+
"step": 13473
|
| 94322 |
+
},
|
| 94323 |
+
{
|
| 94324 |
+
"epoch": 15.346438746438746,
|
| 94325 |
+
"grad_norm": 0.17950469255447388,
|
| 94326 |
+
"learning_rate": 6.908110568251141e-06,
|
| 94327 |
+
"loss": 0.7806,
|
| 94328 |
+
"step": 13474
|
| 94329 |
+
},
|
| 94330 |
+
{
|
| 94331 |
+
"epoch": 15.347578347578347,
|
| 94332 |
+
"grad_norm": 0.28059157729148865,
|
| 94333 |
+
"learning_rate": 6.904895393711203e-06,
|
| 94334 |
+
"loss": 0.5223,
|
| 94335 |
+
"step": 13475
|
| 94336 |
+
},
|
| 94337 |
+
{
|
| 94338 |
+
"epoch": 15.34871794871795,
|
| 94339 |
+
"grad_norm": 0.25041908025741577,
|
| 94340 |
+
"learning_rate": 6.901680847664008e-06,
|
| 94341 |
+
"loss": 0.5838,
|
| 94342 |
+
"step": 13476
|
| 94343 |
+
},
|
| 94344 |
+
{
|
| 94345 |
+
"epoch": 15.34985754985755,
|
| 94346 |
+
"grad_norm": 0.2188163548707962,
|
| 94347 |
+
"learning_rate": 6.898466930221217e-06,
|
| 94348 |
+
"loss": 0.5893,
|
| 94349 |
+
"step": 13477
|
| 94350 |
+
},
|
| 94351 |
+
{
|
| 94352 |
+
"epoch": 15.35099715099715,
|
| 94353 |
+
"grad_norm": 0.22686757147312164,
|
| 94354 |
+
"learning_rate": 6.89525364149444e-06,
|
| 94355 |
+
"loss": 0.8098,
|
| 94356 |
+
"step": 13478
|
| 94357 |
+
},
|
| 94358 |
+
{
|
| 94359 |
+
"epoch": 15.352136752136753,
|
| 94360 |
+
"grad_norm": 0.2084110975265503,
|
| 94361 |
+
"learning_rate": 6.892040981595294e-06,
|
| 94362 |
+
"loss": 0.5571,
|
| 94363 |
+
"step": 13479
|
| 94364 |
+
},
|
| 94365 |
+
{
|
| 94366 |
+
"epoch": 15.353276353276353,
|
| 94367 |
+
"grad_norm": 0.16481290757656097,
|
| 94368 |
+
"learning_rate": 6.88882895063536e-06,
|
| 94369 |
+
"loss": 0.7637,
|
| 94370 |
+
"step": 13480
|
| 94371 |
+
},
|
| 94372 |
+
{
|
| 94373 |
+
"epoch": 15.354415954415954,
|
| 94374 |
+
"grad_norm": 0.2415093630552292,
|
| 94375 |
+
"learning_rate": 6.885617548726203e-06,
|
| 94376 |
+
"loss": 0.4873,
|
| 94377 |
+
"step": 13481
|
| 94378 |
+
},
|
| 94379 |
+
{
|
| 94380 |
+
"epoch": 15.355555555555556,
|
| 94381 |
+
"grad_norm": 0.2453286200761795,
|
| 94382 |
+
"learning_rate": 6.882406775979363e-06,
|
| 94383 |
+
"loss": 0.4265,
|
| 94384 |
+
"step": 13482
|
| 94385 |
+
},
|
| 94386 |
+
{
|
| 94387 |
+
"epoch": 15.356695156695157,
|
| 94388 |
+
"grad_norm": 0.2449209839105606,
|
| 94389 |
+
"learning_rate": 6.87919663250636e-06,
|
| 94390 |
+
"loss": 0.5711,
|
| 94391 |
+
"step": 13483
|
| 94392 |
+
},
|
| 94393 |
+
{
|
| 94394 |
+
"epoch": 15.357834757834757,
|
| 94395 |
+
"grad_norm": 0.16910892724990845,
|
| 94396 |
+
"learning_rate": 6.875987118418698e-06,
|
| 94397 |
+
"loss": 0.8142,
|
| 94398 |
+
"step": 13484
|
| 94399 |
+
},
|
| 94400 |
+
{
|
| 94401 |
+
"epoch": 15.35897435897436,
|
| 94402 |
+
"grad_norm": 0.2112656682729721,
|
| 94403 |
+
"learning_rate": 6.8727782338278364e-06,
|
| 94404 |
+
"loss": 0.6616,
|
| 94405 |
+
"step": 13485
|
| 94406 |
+
},
|
| 94407 |
+
{
|
| 94408 |
+
"epoch": 15.36011396011396,
|
| 94409 |
+
"grad_norm": 0.23164135217666626,
|
| 94410 |
+
"learning_rate": 6.869569978845236e-06,
|
| 94411 |
+
"loss": 0.7478,
|
| 94412 |
+
"step": 13486
|
| 94413 |
+
},
|
| 94414 |
+
{
|
| 94415 |
+
"epoch": 15.36125356125356,
|
| 94416 |
+
"grad_norm": 0.23191292583942413,
|
| 94417 |
+
"learning_rate": 6.866362353582331e-06,
|
| 94418 |
+
"loss": 0.4085,
|
| 94419 |
+
"step": 13487
|
| 94420 |
+
},
|
| 94421 |
+
{
|
| 94422 |
+
"epoch": 15.362393162393163,
|
| 94423 |
+
"grad_norm": 0.1655510514974594,
|
| 94424 |
+
"learning_rate": 6.863155358150536e-06,
|
| 94425 |
+
"loss": 0.7969,
|
| 94426 |
+
"step": 13488
|
| 94427 |
+
},
|
| 94428 |
+
{
|
| 94429 |
+
"epoch": 15.363532763532763,
|
| 94430 |
+
"grad_norm": 0.26377928256988525,
|
| 94431 |
+
"learning_rate": 6.859948992661224e-06,
|
| 94432 |
+
"loss": 0.6692,
|
| 94433 |
+
"step": 13489
|
| 94434 |
+
},
|
| 94435 |
+
{
|
| 94436 |
+
"epoch": 15.364672364672364,
|
| 94437 |
+
"grad_norm": 0.20556597411632538,
|
| 94438 |
+
"learning_rate": 6.856743257225767e-06,
|
| 94439 |
+
"loss": 0.7595,
|
| 94440 |
+
"step": 13490
|
| 94441 |
+
},
|
| 94442 |
+
{
|
| 94443 |
+
"epoch": 15.365811965811966,
|
| 94444 |
+
"grad_norm": 0.2174561470746994,
|
| 94445 |
+
"learning_rate": 6.853538151955508e-06,
|
| 94446 |
+
"loss": 0.3178,
|
| 94447 |
+
"step": 13491
|
| 94448 |
+
},
|
| 94449 |
+
{
|
| 94450 |
+
"epoch": 15.366951566951567,
|
| 94451 |
+
"grad_norm": 0.16128693521022797,
|
| 94452 |
+
"learning_rate": 6.850333676961784e-06,
|
| 94453 |
+
"loss": 0.9294,
|
| 94454 |
+
"step": 13492
|
| 94455 |
+
},
|
| 94456 |
+
{
|
| 94457 |
+
"epoch": 15.368091168091167,
|
| 94458 |
+
"grad_norm": 0.2202058583498001,
|
| 94459 |
+
"learning_rate": 6.847129832355876e-06,
|
| 94460 |
+
"loss": 0.799,
|
| 94461 |
+
"step": 13493
|
| 94462 |
+
},
|
| 94463 |
+
{
|
| 94464 |
+
"epoch": 15.36923076923077,
|
| 94465 |
+
"grad_norm": 0.1866167187690735,
|
| 94466 |
+
"learning_rate": 6.843926618249069e-06,
|
| 94467 |
+
"loss": 0.7674,
|
| 94468 |
+
"step": 13494
|
| 94469 |
+
},
|
| 94470 |
+
{
|
| 94471 |
+
"epoch": 15.37037037037037,
|
| 94472 |
+
"grad_norm": 0.1961738020181656,
|
| 94473 |
+
"learning_rate": 6.840724034752621e-06,
|
| 94474 |
+
"loss": 0.6597,
|
| 94475 |
+
"step": 13495
|
| 94476 |
+
},
|
| 94477 |
+
{
|
| 94478 |
+
"epoch": 15.37150997150997,
|
| 94479 |
+
"grad_norm": 0.22003182768821716,
|
| 94480 |
+
"learning_rate": 6.837522081977771e-06,
|
| 94481 |
+
"loss": 0.5568,
|
| 94482 |
+
"step": 13496
|
| 94483 |
+
},
|
| 94484 |
+
{
|
| 94485 |
+
"epoch": 15.372649572649573,
|
| 94486 |
+
"grad_norm": 0.19237026572227478,
|
| 94487 |
+
"learning_rate": 6.83432076003572e-06,
|
| 94488 |
+
"loss": 0.7058,
|
| 94489 |
+
"step": 13497
|
| 94490 |
+
},
|
| 94491 |
+
{
|
| 94492 |
+
"epoch": 15.373789173789174,
|
| 94493 |
+
"grad_norm": 0.2223634421825409,
|
| 94494 |
+
"learning_rate": 6.831120069037666e-06,
|
| 94495 |
+
"loss": 0.579,
|
| 94496 |
+
"step": 13498
|
| 94497 |
+
},
|
| 94498 |
+
{
|
| 94499 |
+
"epoch": 15.374928774928774,
|
| 94500 |
+
"grad_norm": 0.19303710758686066,
|
| 94501 |
+
"learning_rate": 6.827920009094774e-06,
|
| 94502 |
+
"loss": 0.6463,
|
| 94503 |
+
"step": 13499
|
| 94504 |
+
},
|
| 94505 |
+
{
|
| 94506 |
+
"epoch": 15.376068376068377,
|
| 94507 |
+
"grad_norm": 0.23518739640712738,
|
| 94508 |
+
"learning_rate": 6.824720580318203e-06,
|
| 94509 |
+
"loss": 0.4935,
|
| 94510 |
+
"step": 13500
|
| 94511 |
}
|
| 94512 |
],
|
| 94513 |
"logging_steps": 1,
|
|
|
|
| 94527 |
"attributes": {}
|
| 94528 |
}
|
| 94529 |
},
|
| 94530 |
+
"total_flos": 7.548157591547757e+19,
|
| 94531 |
"train_batch_size": 8,
|
| 94532 |
"trial_name": null,
|
| 94533 |
"trial_params": null
|