Model save
Browse files- README.md +70 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +3102 -0
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: zephyr-7b-sft-qlora
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/statking/huggingface/runs/dnr1n96z)
|
| 20 |
+
# zephyr-7b-sft-qlora
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.9439
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 0.0002
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
+
- eval_batch_size: 16
|
| 46 |
+
- seed: 42
|
| 47 |
+
- distributed_type: multi-GPU
|
| 48 |
+
- num_devices: 4
|
| 49 |
+
- gradient_accumulation_steps: 2
|
| 50 |
+
- total_train_batch_size: 64
|
| 51 |
+
- total_eval_batch_size: 64
|
| 52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
+
- lr_scheduler_type: cosine
|
| 54 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 55 |
+
- num_epochs: 1
|
| 56 |
+
|
| 57 |
+
### Training results
|
| 58 |
+
|
| 59 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 60 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 61 |
+
| 0.9454 | 1.0 | 2179 | 0.9439 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- PEFT 0.10.0
|
| 67 |
+
- Transformers 4.41.0.dev0
|
| 68 |
+
- Pytorch 2.3.0+cu121
|
| 69 |
+
- Datasets 2.19.1
|
| 70 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12c1d62683baa1fbbf5c320f26a5bdf29a730052d413bd59948c4e6e4b3ef98b
|
| 3 |
size 83946192
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 3.4589037545127936e+16,
|
| 4 |
+
"train_loss": 0.9514529290906111,
|
| 5 |
+
"train_runtime": 33671.5063,
|
| 6 |
+
"train_samples": 207864,
|
| 7 |
+
"train_samples_per_second": 4.141,
|
| 8 |
+
"train_steps_per_second": 0.065
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 3.4589037545127936e+16,
|
| 4 |
+
"train_loss": 0.9514529290906111,
|
| 5 |
+
"train_runtime": 33671.5063,
|
| 6 |
+
"train_samples": 207864,
|
| 7 |
+
"train_samples_per_second": 4.141,
|
| 8 |
+
"train_steps_per_second": 0.065
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2179,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0004589261128958238,
|
| 13 |
+
"grad_norm": 0.24931495636064183,
|
| 14 |
+
"learning_rate": 9.174311926605506e-07,
|
| 15 |
+
"loss": 1.1206,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002294630564479119,
|
| 20 |
+
"grad_norm": 0.26866738165199944,
|
| 21 |
+
"learning_rate": 4.587155963302753e-06,
|
| 22 |
+
"loss": 1.1242,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.004589261128958238,
|
| 27 |
+
"grad_norm": 0.2706384220584976,
|
| 28 |
+
"learning_rate": 9.174311926605506e-06,
|
| 29 |
+
"loss": 1.1504,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.006883891693437357,
|
| 34 |
+
"grad_norm": 0.22472049733931831,
|
| 35 |
+
"learning_rate": 1.3761467889908258e-05,
|
| 36 |
+
"loss": 1.1168,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.009178522257916476,
|
| 41 |
+
"grad_norm": 0.20645077000731837,
|
| 42 |
+
"learning_rate": 1.834862385321101e-05,
|
| 43 |
+
"loss": 1.0668,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.011473152822395595,
|
| 48 |
+
"grad_norm": 0.17022030208338307,
|
| 49 |
+
"learning_rate": 2.2935779816513765e-05,
|
| 50 |
+
"loss": 1.0672,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.013767783386874713,
|
| 55 |
+
"grad_norm": 0.15571207235273762,
|
| 56 |
+
"learning_rate": 2.7522935779816515e-05,
|
| 57 |
+
"loss": 1.0782,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.016062413951353834,
|
| 62 |
+
"grad_norm": 0.1146172388400534,
|
| 63 |
+
"learning_rate": 3.211009174311927e-05,
|
| 64 |
+
"loss": 1.0178,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.018357044515832952,
|
| 69 |
+
"grad_norm": 0.10569957850527,
|
| 70 |
+
"learning_rate": 3.669724770642202e-05,
|
| 71 |
+
"loss": 1.0347,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02065167508031207,
|
| 76 |
+
"grad_norm": 0.10758552876940583,
|
| 77 |
+
"learning_rate": 4.1284403669724776e-05,
|
| 78 |
+
"loss": 1.0464,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02294630564479119,
|
| 83 |
+
"grad_norm": 0.12022433488838774,
|
| 84 |
+
"learning_rate": 4.587155963302753e-05,
|
| 85 |
+
"loss": 0.9938,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.025240936209270308,
|
| 90 |
+
"grad_norm": 0.12413949810603703,
|
| 91 |
+
"learning_rate": 5.0458715596330276e-05,
|
| 92 |
+
"loss": 1.0116,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.027535566773749427,
|
| 97 |
+
"grad_norm": 0.11089749594093384,
|
| 98 |
+
"learning_rate": 5.504587155963303e-05,
|
| 99 |
+
"loss": 1.0099,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.029830197338228545,
|
| 104 |
+
"grad_norm": 0.11116787947934133,
|
| 105 |
+
"learning_rate": 5.9633027522935784e-05,
|
| 106 |
+
"loss": 1.0123,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.03212482790270767,
|
| 111 |
+
"grad_norm": 0.1045508356848914,
|
| 112 |
+
"learning_rate": 6.422018348623854e-05,
|
| 113 |
+
"loss": 0.9922,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.03441945846718678,
|
| 118 |
+
"grad_norm": 0.11419989748358071,
|
| 119 |
+
"learning_rate": 6.880733944954129e-05,
|
| 120 |
+
"loss": 1.0221,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.036714089031665904,
|
| 125 |
+
"grad_norm": 0.11920093762065691,
|
| 126 |
+
"learning_rate": 7.339449541284404e-05,
|
| 127 |
+
"loss": 0.9903,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.03900871959614502,
|
| 132 |
+
"grad_norm": 0.1205539032721293,
|
| 133 |
+
"learning_rate": 7.79816513761468e-05,
|
| 134 |
+
"loss": 0.9892,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.04130335016062414,
|
| 139 |
+
"grad_norm": 0.1153297215401342,
|
| 140 |
+
"learning_rate": 8.256880733944955e-05,
|
| 141 |
+
"loss": 0.9801,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.04359798072510326,
|
| 146 |
+
"grad_norm": 0.11168014813048414,
|
| 147 |
+
"learning_rate": 8.715596330275229e-05,
|
| 148 |
+
"loss": 0.9927,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.04589261128958238,
|
| 153 |
+
"grad_norm": 0.11609074160199676,
|
| 154 |
+
"learning_rate": 9.174311926605506e-05,
|
| 155 |
+
"loss": 0.9794,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.048187241854061494,
|
| 160 |
+
"grad_norm": 0.11950825569103571,
|
| 161 |
+
"learning_rate": 9.63302752293578e-05,
|
| 162 |
+
"loss": 0.9818,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.050481872418540616,
|
| 167 |
+
"grad_norm": 0.11880725497478824,
|
| 168 |
+
"learning_rate": 0.00010091743119266055,
|
| 169 |
+
"loss": 0.9986,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.05277650298301973,
|
| 174 |
+
"grad_norm": 0.11245311133827594,
|
| 175 |
+
"learning_rate": 0.00010550458715596329,
|
| 176 |
+
"loss": 1.0082,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.05507113354749885,
|
| 181 |
+
"grad_norm": 0.11463279657110968,
|
| 182 |
+
"learning_rate": 0.00011009174311926606,
|
| 183 |
+
"loss": 0.9701,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.05736576411197797,
|
| 188 |
+
"grad_norm": 0.1147080076997952,
|
| 189 |
+
"learning_rate": 0.00011467889908256881,
|
| 190 |
+
"loss": 0.9561,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.05966039467645709,
|
| 195 |
+
"grad_norm": 0.10731908295172292,
|
| 196 |
+
"learning_rate": 0.00011926605504587157,
|
| 197 |
+
"loss": 0.9806,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.06195502524093621,
|
| 202 |
+
"grad_norm": 0.11772654963107822,
|
| 203 |
+
"learning_rate": 0.00012385321100917432,
|
| 204 |
+
"loss": 0.9781,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.06424965580541533,
|
| 209 |
+
"grad_norm": 0.10616965717110965,
|
| 210 |
+
"learning_rate": 0.00012844036697247707,
|
| 211 |
+
"loss": 0.9575,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.06654428636989444,
|
| 216 |
+
"grad_norm": 0.11403517689802216,
|
| 217 |
+
"learning_rate": 0.00013302752293577983,
|
| 218 |
+
"loss": 0.9967,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.06883891693437356,
|
| 223 |
+
"grad_norm": 0.12124685445241375,
|
| 224 |
+
"learning_rate": 0.00013761467889908258,
|
| 225 |
+
"loss": 0.962,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.07113354749885269,
|
| 230 |
+
"grad_norm": 0.11004755929686598,
|
| 231 |
+
"learning_rate": 0.0001422018348623853,
|
| 232 |
+
"loss": 0.9458,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.07342817806333181,
|
| 237 |
+
"grad_norm": 0.11198046801850037,
|
| 238 |
+
"learning_rate": 0.0001467889908256881,
|
| 239 |
+
"loss": 0.9853,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.07572280862781092,
|
| 244 |
+
"grad_norm": 0.10851191328572089,
|
| 245 |
+
"learning_rate": 0.00015137614678899084,
|
| 246 |
+
"loss": 0.9599,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.07801743919229004,
|
| 251 |
+
"grad_norm": 0.1027573560837855,
|
| 252 |
+
"learning_rate": 0.0001559633027522936,
|
| 253 |
+
"loss": 0.9705,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.08031206975676916,
|
| 258 |
+
"grad_norm": 0.09904618883874605,
|
| 259 |
+
"learning_rate": 0.00016055045871559632,
|
| 260 |
+
"loss": 0.9607,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.08260670032124828,
|
| 265 |
+
"grad_norm": 0.10960846096179629,
|
| 266 |
+
"learning_rate": 0.0001651376146788991,
|
| 267 |
+
"loss": 1.0047,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.08490133088572739,
|
| 272 |
+
"grad_norm": 0.10544676605226945,
|
| 273 |
+
"learning_rate": 0.00016972477064220186,
|
| 274 |
+
"loss": 0.9894,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.08719596145020651,
|
| 279 |
+
"grad_norm": 0.10229698437978632,
|
| 280 |
+
"learning_rate": 0.00017431192660550458,
|
| 281 |
+
"loss": 0.9764,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.08949059201468564,
|
| 286 |
+
"grad_norm": 0.09568938580281933,
|
| 287 |
+
"learning_rate": 0.00017889908256880734,
|
| 288 |
+
"loss": 0.9618,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.09178522257916476,
|
| 293 |
+
"grad_norm": 0.10024788325345245,
|
| 294 |
+
"learning_rate": 0.00018348623853211012,
|
| 295 |
+
"loss": 0.953,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.09407985314364388,
|
| 300 |
+
"grad_norm": 0.09773114551334808,
|
| 301 |
+
"learning_rate": 0.00018807339449541284,
|
| 302 |
+
"loss": 0.9775,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.09637448370812299,
|
| 307 |
+
"grad_norm": 0.103651995811559,
|
| 308 |
+
"learning_rate": 0.0001926605504587156,
|
| 309 |
+
"loss": 0.9621,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.09866911427260211,
|
| 314 |
+
"grad_norm": 0.10031363164526642,
|
| 315 |
+
"learning_rate": 0.00019724770642201835,
|
| 316 |
+
"loss": 0.9771,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.10096374483708123,
|
| 321 |
+
"grad_norm": 0.09400862481398278,
|
| 322 |
+
"learning_rate": 0.00019999948669655127,
|
| 323 |
+
"loss": 0.9685,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.10325837540156035,
|
| 328 |
+
"grad_norm": 0.09148587705607365,
|
| 329 |
+
"learning_rate": 0.00019999371209327089,
|
| 330 |
+
"loss": 0.9472,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.10555300596603946,
|
| 335 |
+
"grad_norm": 0.1000742259516268,
|
| 336 |
+
"learning_rate": 0.00019998152162914806,
|
| 337 |
+
"loss": 0.9601,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.10784763653051858,
|
| 342 |
+
"grad_norm": 0.099276599123678,
|
| 343 |
+
"learning_rate": 0.00019996291608635525,
|
| 344 |
+
"loss": 0.9597,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.1101422670949977,
|
| 349 |
+
"grad_norm": 0.09100711111755377,
|
| 350 |
+
"learning_rate": 0.00019993789665867314,
|
| 351 |
+
"loss": 0.9427,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.11243689765947683,
|
| 356 |
+
"grad_norm": 0.09143444839325382,
|
| 357 |
+
"learning_rate": 0.00019990646495141444,
|
| 358 |
+
"loss": 0.9521,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.11473152822395594,
|
| 363 |
+
"grad_norm": 0.09469721895906218,
|
| 364 |
+
"learning_rate": 0.0001998686229813205,
|
| 365 |
+
"loss": 0.9642,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.11702615878843506,
|
| 370 |
+
"grad_norm": 0.09530573435158946,
|
| 371 |
+
"learning_rate": 0.00019982437317643217,
|
| 372 |
+
"loss": 0.9475,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.11932078935291418,
|
| 377 |
+
"grad_norm": 0.09537227174416016,
|
| 378 |
+
"learning_rate": 0.0001997737183759338,
|
| 379 |
+
"loss": 0.9596,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.1216154199173933,
|
| 384 |
+
"grad_norm": 0.09276269113129716,
|
| 385 |
+
"learning_rate": 0.00019971666182997137,
|
| 386 |
+
"loss": 0.9264,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.12391005048187242,
|
| 391 |
+
"grad_norm": 0.09602318064837084,
|
| 392 |
+
"learning_rate": 0.00019965320719944366,
|
| 393 |
+
"loss": 0.9388,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.12620468104635155,
|
| 398 |
+
"grad_norm": 0.08888849048667083,
|
| 399 |
+
"learning_rate": 0.00019958335855576738,
|
| 400 |
+
"loss": 0.9631,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.12849931161083067,
|
| 405 |
+
"grad_norm": 0.08994328067689368,
|
| 406 |
+
"learning_rate": 0.00019950712038061617,
|
| 407 |
+
"loss": 0.9481,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.13079394217530976,
|
| 412 |
+
"grad_norm": 0.0897263586822677,
|
| 413 |
+
"learning_rate": 0.00019942449756563279,
|
| 414 |
+
"loss": 0.9566,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.13308857273978889,
|
| 419 |
+
"grad_norm": 0.08889749103510053,
|
| 420 |
+
"learning_rate": 0.00019933549541211552,
|
| 421 |
+
"loss": 0.965,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.135383203304268,
|
| 426 |
+
"grad_norm": 0.09008585580167996,
|
| 427 |
+
"learning_rate": 0.00019924011963067765,
|
| 428 |
+
"loss": 0.9489,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.13767783386874713,
|
| 433 |
+
"grad_norm": 0.08978334358331166,
|
| 434 |
+
"learning_rate": 0.00019913837634088144,
|
| 435 |
+
"loss": 0.9591,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.13997246443322625,
|
| 440 |
+
"grad_norm": 0.08869912275141656,
|
| 441 |
+
"learning_rate": 0.00019903027207084523,
|
| 442 |
+
"loss": 0.9647,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.14226709499770537,
|
| 447 |
+
"grad_norm": 0.08650660717454736,
|
| 448 |
+
"learning_rate": 0.00019891581375682473,
|
| 449 |
+
"loss": 0.9877,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.1445617255621845,
|
| 454 |
+
"grad_norm": 0.08750656685685948,
|
| 455 |
+
"learning_rate": 0.00019879500874276786,
|
| 456 |
+
"loss": 0.9654,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.14685635612666362,
|
| 461 |
+
"grad_norm": 0.08617919321649241,
|
| 462 |
+
"learning_rate": 0.00019866786477984357,
|
| 463 |
+
"loss": 0.965,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.14915098669114274,
|
| 468 |
+
"grad_norm": 0.08483226196137736,
|
| 469 |
+
"learning_rate": 0.0001985343900259446,
|
| 470 |
+
"loss": 0.9677,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.15144561725562183,
|
| 475 |
+
"grad_norm": 0.09712002013315797,
|
| 476 |
+
"learning_rate": 0.0001983945930451639,
|
| 477 |
+
"loss": 0.9845,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.15374024782010096,
|
| 482 |
+
"grad_norm": 0.08834848603530239,
|
| 483 |
+
"learning_rate": 0.0001982484828072452,
|
| 484 |
+
"loss": 0.9551,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.15603487838458008,
|
| 489 |
+
"grad_norm": 0.08706421027052569,
|
| 490 |
+
"learning_rate": 0.00019809606868700756,
|
| 491 |
+
"loss": 0.9725,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.1583295089490592,
|
| 496 |
+
"grad_norm": 0.08948100664780789,
|
| 497 |
+
"learning_rate": 0.00019793736046374373,
|
| 498 |
+
"loss": 0.9537,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.16062413951353832,
|
| 503 |
+
"grad_norm": 0.08854849269535629,
|
| 504 |
+
"learning_rate": 0.0001977723683205928,
|
| 505 |
+
"loss": 0.9826,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.16291877007801744,
|
| 510 |
+
"grad_norm": 0.09035742208671649,
|
| 511 |
+
"learning_rate": 0.00019760110284388667,
|
| 512 |
+
"loss": 0.9685,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.16521340064249657,
|
| 517 |
+
"grad_norm": 0.2078369241555783,
|
| 518 |
+
"learning_rate": 0.00019742357502247103,
|
| 519 |
+
"loss": 0.953,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.1675080312069757,
|
| 524 |
+
"grad_norm": 0.08496387083805744,
|
| 525 |
+
"learning_rate": 0.00019723979624700004,
|
| 526 |
+
"loss": 0.9551,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.16980266177145478,
|
| 531 |
+
"grad_norm": 0.09478873291884332,
|
| 532 |
+
"learning_rate": 0.0001970497783092057,
|
| 533 |
+
"loss": 0.9744,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.1720972923359339,
|
| 538 |
+
"grad_norm": 0.08984634771176177,
|
| 539 |
+
"learning_rate": 0.00019685353340114103,
|
| 540 |
+
"loss": 0.9564,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.17439192290041303,
|
| 545 |
+
"grad_norm": 0.09065621901432767,
|
| 546 |
+
"learning_rate": 0.00019665107411439805,
|
| 547 |
+
"loss": 0.9807,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.17668655346489215,
|
| 552 |
+
"grad_norm": 0.08667656345676594,
|
| 553 |
+
"learning_rate": 0.00019644241343929966,
|
| 554 |
+
"loss": 0.9426,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.17898118402937127,
|
| 559 |
+
"grad_norm": 0.09114781451954795,
|
| 560 |
+
"learning_rate": 0.00019622756476406626,
|
| 561 |
+
"loss": 0.9551,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.1812758145938504,
|
| 566 |
+
"grad_norm": 0.09037110088641298,
|
| 567 |
+
"learning_rate": 0.00019600654187395663,
|
| 568 |
+
"loss": 0.9345,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.18357044515832951,
|
| 573 |
+
"grad_norm": 0.09611180100762262,
|
| 574 |
+
"learning_rate": 0.00019577935895038361,
|
| 575 |
+
"loss": 0.9565,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.18586507572280864,
|
| 580 |
+
"grad_norm": 0.09346105169502975,
|
| 581 |
+
"learning_rate": 0.00019554603057000397,
|
| 582 |
+
"loss": 0.9607,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.18815970628728776,
|
| 587 |
+
"grad_norm": 0.08669880613701339,
|
| 588 |
+
"learning_rate": 0.0001953065717037832,
|
| 589 |
+
"loss": 0.9434,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.19045433685176685,
|
| 594 |
+
"grad_norm": 0.09074513235696971,
|
| 595 |
+
"learning_rate": 0.00019506099771603513,
|
| 596 |
+
"loss": 0.9539,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.19274896741624598,
|
| 601 |
+
"grad_norm": 0.08770031036399964,
|
| 602 |
+
"learning_rate": 0.00019480932436343582,
|
| 603 |
+
"loss": 0.9466,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.1950435979807251,
|
| 608 |
+
"grad_norm": 0.08915513286930843,
|
| 609 |
+
"learning_rate": 0.00019455156779401265,
|
| 610 |
+
"loss": 0.9628,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.19733822854520422,
|
| 615 |
+
"grad_norm": 0.08790684691806365,
|
| 616 |
+
"learning_rate": 0.00019428774454610843,
|
| 617 |
+
"loss": 0.9598,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.19963285910968334,
|
| 622 |
+
"grad_norm": 0.08895484944044536,
|
| 623 |
+
"learning_rate": 0.00019401787154731993,
|
| 624 |
+
"loss": 0.9553,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.20192748967416246,
|
| 629 |
+
"grad_norm": 0.08798273269859104,
|
| 630 |
+
"learning_rate": 0.0001937419661134121,
|
| 631 |
+
"loss": 0.9796,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.20422212023864159,
|
| 636 |
+
"grad_norm": 0.08777210421997016,
|
| 637 |
+
"learning_rate": 0.00019346004594720669,
|
| 638 |
+
"loss": 0.9495,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.2065167508031207,
|
| 643 |
+
"grad_norm": 0.08564705845641755,
|
| 644 |
+
"learning_rate": 0.0001931721291374467,
|
| 645 |
+
"loss": 0.9501,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.20881138136759983,
|
| 650 |
+
"grad_norm": 0.09474670359706922,
|
| 651 |
+
"learning_rate": 0.00019287823415763553,
|
| 652 |
+
"loss": 0.9559,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.21110601193207892,
|
| 657 |
+
"grad_norm": 0.08777147268242179,
|
| 658 |
+
"learning_rate": 0.00019257837986485187,
|
| 659 |
+
"loss": 0.9828,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.21340064249655805,
|
| 664 |
+
"grad_norm": 0.09274202152499614,
|
| 665 |
+
"learning_rate": 0.0001922725854985396,
|
| 666 |
+
"loss": 0.943,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.21569527306103717,
|
| 671 |
+
"grad_norm": 0.08906570334946029,
|
| 672 |
+
"learning_rate": 0.0001919608706792735,
|
| 673 |
+
"loss": 0.963,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.2179899036255163,
|
| 678 |
+
"grad_norm": 0.09431879186087927,
|
| 679 |
+
"learning_rate": 0.00019164325540750016,
|
| 680 |
+
"loss": 0.976,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.2202845341899954,
|
| 685 |
+
"grad_norm": 0.0880885330404675,
|
| 686 |
+
"learning_rate": 0.00019131976006225488,
|
| 687 |
+
"loss": 0.934,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.22257916475447453,
|
| 692 |
+
"grad_norm": 0.09001487242711557,
|
| 693 |
+
"learning_rate": 0.00019099040539985394,
|
| 694 |
+
"loss": 0.9608,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.22487379531895366,
|
| 699 |
+
"grad_norm": 0.08632949578437538,
|
| 700 |
+
"learning_rate": 0.00019065521255256298,
|
| 701 |
+
"loss": 0.9489,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.22716842588343278,
|
| 706 |
+
"grad_norm": 0.08860042188251825,
|
| 707 |
+
"learning_rate": 0.00019031420302724096,
|
| 708 |
+
"loss": 0.9539,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.22946305644791187,
|
| 713 |
+
"grad_norm": 0.09204792889480558,
|
| 714 |
+
"learning_rate": 0.00018996739870396026,
|
| 715 |
+
"loss": 0.9455,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.231757687012391,
|
| 720 |
+
"grad_norm": 0.0907813137121107,
|
| 721 |
+
"learning_rate": 0.00018961482183460282,
|
| 722 |
+
"loss": 0.9455,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.23405231757687012,
|
| 727 |
+
"grad_norm": 0.09123445749023676,
|
| 728 |
+
"learning_rate": 0.00018925649504143244,
|
| 729 |
+
"loss": 0.9386,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.23634694814134924,
|
| 734 |
+
"grad_norm": 0.08933477090645768,
|
| 735 |
+
"learning_rate": 0.0001888924413156432,
|
| 736 |
+
"loss": 0.9566,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.23864157870582836,
|
| 741 |
+
"grad_norm": 0.08928138581489246,
|
| 742 |
+
"learning_rate": 0.0001885226840158843,
|
| 743 |
+
"loss": 0.9617,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.24093620927030748,
|
| 748 |
+
"grad_norm": 0.1274731933313709,
|
| 749 |
+
"learning_rate": 0.00018814724686676133,
|
| 750 |
+
"loss": 0.9596,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.2432308398347866,
|
| 755 |
+
"grad_norm": 0.0905076097730417,
|
| 756 |
+
"learning_rate": 0.00018776615395731398,
|
| 757 |
+
"loss": 0.9438,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.24552547039926573,
|
| 762 |
+
"grad_norm": 0.08684198828453624,
|
| 763 |
+
"learning_rate": 0.0001873794297394706,
|
| 764 |
+
"loss": 0.9601,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.24782010096374485,
|
| 769 |
+
"grad_norm": 0.0888276936189942,
|
| 770 |
+
"learning_rate": 0.00018698709902647902,
|
| 771 |
+
"loss": 0.9276,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.25011473152822394,
|
| 776 |
+
"grad_norm": 0.09323508497961805,
|
| 777 |
+
"learning_rate": 0.00018658918699131468,
|
| 778 |
+
"loss": 0.9767,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.2524093620927031,
|
| 783 |
+
"grad_norm": 0.0881344870799144,
|
| 784 |
+
"learning_rate": 0.00018618571916506545,
|
| 785 |
+
"loss": 0.9604,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.2547039926571822,
|
| 790 |
+
"grad_norm": 0.08872071593430497,
|
| 791 |
+
"learning_rate": 0.00018577672143529336,
|
| 792 |
+
"loss": 0.9587,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.25699862322166134,
|
| 797 |
+
"grad_norm": 0.08503719828368154,
|
| 798 |
+
"learning_rate": 0.00018536222004437368,
|
| 799 |
+
"loss": 0.9589,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.25929325378614043,
|
| 804 |
+
"grad_norm": 0.08844948896045982,
|
| 805 |
+
"learning_rate": 0.0001849422415878112,
|
| 806 |
+
"loss": 0.9611,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.2615878843506195,
|
| 811 |
+
"grad_norm": 0.08833201695867715,
|
| 812 |
+
"learning_rate": 0.00018451681301253362,
|
| 813 |
+
"loss": 0.9619,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.2638825149150987,
|
| 818 |
+
"grad_norm": 0.08789348466222431,
|
| 819 |
+
"learning_rate": 0.00018408596161516267,
|
| 820 |
+
"loss": 0.9732,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.26617714547957777,
|
| 825 |
+
"grad_norm": 0.09007398961819005,
|
| 826 |
+
"learning_rate": 0.00018364971504026273,
|
| 827 |
+
"loss": 0.9546,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.2684717760440569,
|
| 832 |
+
"grad_norm": 0.09389996335115901,
|
| 833 |
+
"learning_rate": 0.00018320810127856705,
|
| 834 |
+
"loss": 0.9394,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.270766406608536,
|
| 839 |
+
"grad_norm": 0.08615315931672284,
|
| 840 |
+
"learning_rate": 0.00018276114866518168,
|
| 841 |
+
"loss": 0.956,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.27306103717301516,
|
| 846 |
+
"grad_norm": 0.08933240638639854,
|
| 847 |
+
"learning_rate": 0.00018230888587776755,
|
| 848 |
+
"loss": 0.9688,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.27535566773749426,
|
| 853 |
+
"grad_norm": 0.09191231486736685,
|
| 854 |
+
"learning_rate": 0.00018185134193470043,
|
| 855 |
+
"loss": 0.9504,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.2776502983019734,
|
| 860 |
+
"grad_norm": 0.08712371583759838,
|
| 861 |
+
"learning_rate": 0.00018138854619320893,
|
| 862 |
+
"loss": 0.9682,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.2799449288664525,
|
| 867 |
+
"grad_norm": 0.08901746734004592,
|
| 868 |
+
"learning_rate": 0.00018092052834749094,
|
| 869 |
+
"loss": 0.9402,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.2822395594309316,
|
| 874 |
+
"grad_norm": 0.08840589666910355,
|
| 875 |
+
"learning_rate": 0.0001804473184268084,
|
| 876 |
+
"loss": 0.9768,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.28453418999541075,
|
| 881 |
+
"grad_norm": 0.08481006585653182,
|
| 882 |
+
"learning_rate": 0.0001799689467935604,
|
| 883 |
+
"loss": 0.9567,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.28682882055988984,
|
| 888 |
+
"grad_norm": 0.08497095117377013,
|
| 889 |
+
"learning_rate": 0.00017948544414133534,
|
| 890 |
+
"loss": 0.9502,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.289123451124369,
|
| 895 |
+
"grad_norm": 0.08990180476167892,
|
| 896 |
+
"learning_rate": 0.00017899684149294117,
|
| 897 |
+
"loss": 0.9736,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.2914180816888481,
|
| 902 |
+
"grad_norm": 0.08740257994079272,
|
| 903 |
+
"learning_rate": 0.00017850317019841514,
|
| 904 |
+
"loss": 0.9452,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.29371271225332723,
|
| 909 |
+
"grad_norm": 0.09168725176770938,
|
| 910 |
+
"learning_rate": 0.00017800446193301227,
|
| 911 |
+
"loss": 0.9584,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.29600734281780633,
|
| 916 |
+
"grad_norm": 0.0854935785988436,
|
| 917 |
+
"learning_rate": 0.00017750074869517284,
|
| 918 |
+
"loss": 0.9498,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.2983019733822855,
|
| 923 |
+
"grad_norm": 0.08713641806146565,
|
| 924 |
+
"learning_rate": 0.00017699206280446953,
|
| 925 |
+
"loss": 0.9781,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.3005966039467646,
|
| 930 |
+
"grad_norm": 0.08670609625106108,
|
| 931 |
+
"learning_rate": 0.00017647843689953352,
|
| 932 |
+
"loss": 0.9436,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.30289123451124367,
|
| 937 |
+
"grad_norm": 0.08793355472500575,
|
| 938 |
+
"learning_rate": 0.00017595990393596026,
|
| 939 |
+
"loss": 0.9526,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.3051858650757228,
|
| 944 |
+
"grad_norm": 0.09193899666963108,
|
| 945 |
+
"learning_rate": 0.0001754364971841952,
|
| 946 |
+
"loss": 0.9558,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.3074804956402019,
|
| 951 |
+
"grad_norm": 0.08520469387571077,
|
| 952 |
+
"learning_rate": 0.0001749082502273988,
|
| 953 |
+
"loss": 0.9384,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.30977512620468106,
|
| 958 |
+
"grad_norm": 0.08632463244243371,
|
| 959 |
+
"learning_rate": 0.00017437519695929194,
|
| 960 |
+
"loss": 0.9349,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.31206975676916016,
|
| 965 |
+
"grad_norm": 0.08898391879883893,
|
| 966 |
+
"learning_rate": 0.0001738373715819811,
|
| 967 |
+
"loss": 0.9851,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.3143643873336393,
|
| 972 |
+
"grad_norm": 0.08743602323721172,
|
| 973 |
+
"learning_rate": 0.00017329480860376391,
|
| 974 |
+
"loss": 0.9684,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.3166590178981184,
|
| 979 |
+
"grad_norm": 0.0884272891415175,
|
| 980 |
+
"learning_rate": 0.00017274754283691504,
|
| 981 |
+
"loss": 0.9513,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.3189536484625975,
|
| 986 |
+
"grad_norm": 0.0829396476234397,
|
| 987 |
+
"learning_rate": 0.00017219560939545246,
|
| 988 |
+
"loss": 0.9227,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.32124827902707664,
|
| 993 |
+
"grad_norm": 0.08812333013019032,
|
| 994 |
+
"learning_rate": 0.00017163904369288445,
|
| 995 |
+
"loss": 0.9266,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.32354290959155574,
|
| 1000 |
+
"grad_norm": 0.08790955029633435,
|
| 1001 |
+
"learning_rate": 0.00017107788143993743,
|
| 1002 |
+
"loss": 0.9645,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.3258375401560349,
|
| 1007 |
+
"grad_norm": 0.08662253079337641,
|
| 1008 |
+
"learning_rate": 0.00017051215864226469,
|
| 1009 |
+
"loss": 0.9636,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.328132170720514,
|
| 1014 |
+
"grad_norm": 0.08662254032383067,
|
| 1015 |
+
"learning_rate": 0.0001699419115981361,
|
| 1016 |
+
"loss": 0.9461,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.33042680128499313,
|
| 1021 |
+
"grad_norm": 0.08795758448530268,
|
| 1022 |
+
"learning_rate": 0.00016936717689610903,
|
| 1023 |
+
"loss": 0.933,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.3327214318494722,
|
| 1028 |
+
"grad_norm": 0.08428350308511785,
|
| 1029 |
+
"learning_rate": 0.00016878799141268106,
|
| 1030 |
+
"loss": 0.9368,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.3350160624139514,
|
| 1035 |
+
"grad_norm": 0.08616657609346429,
|
| 1036 |
+
"learning_rate": 0.00016820439230992343,
|
| 1037 |
+
"loss": 0.9621,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.33731069297843047,
|
| 1042 |
+
"grad_norm": 0.08578062404208871,
|
| 1043 |
+
"learning_rate": 0.00016761641703309704,
|
| 1044 |
+
"loss": 0.9503,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.33960532354290957,
|
| 1049 |
+
"grad_norm": 0.08875908176879958,
|
| 1050 |
+
"learning_rate": 0.00016702410330824962,
|
| 1051 |
+
"loss": 0.9377,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.3418999541073887,
|
| 1056 |
+
"grad_norm": 0.08739702470553666,
|
| 1057 |
+
"learning_rate": 0.00016642748913979513,
|
| 1058 |
+
"loss": 0.9604,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.3441945846718678,
|
| 1063 |
+
"grad_norm": 0.08662264283634206,
|
| 1064 |
+
"learning_rate": 0.00016582661280807552,
|
| 1065 |
+
"loss": 0.9765,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.34648921523634696,
|
| 1070 |
+
"grad_norm": 0.08704277951624015,
|
| 1071 |
+
"learning_rate": 0.0001652215128669042,
|
| 1072 |
+
"loss": 0.962,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.34878384580082605,
|
| 1077 |
+
"grad_norm": 0.08627254433727607,
|
| 1078 |
+
"learning_rate": 0.00016461222814109268,
|
| 1079 |
+
"loss": 0.9503,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.3510784763653052,
|
| 1084 |
+
"grad_norm": 0.08968065039630777,
|
| 1085 |
+
"learning_rate": 0.00016399879772395915,
|
| 1086 |
+
"loss": 0.9694,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.3533731069297843,
|
| 1091 |
+
"grad_norm": 0.08992120522770167,
|
| 1092 |
+
"learning_rate": 0.00016338126097482057,
|
| 1093 |
+
"loss": 0.9425,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.35566773749426345,
|
| 1098 |
+
"grad_norm": 0.08636178728280854,
|
| 1099 |
+
"learning_rate": 0.0001627596575164668,
|
| 1100 |
+
"loss": 0.9486,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.35796236805874254,
|
| 1105 |
+
"grad_norm": 0.08955961975585672,
|
| 1106 |
+
"learning_rate": 0.0001621340272326185,
|
| 1107 |
+
"loss": 0.9545,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.36025699862322164,
|
| 1112 |
+
"grad_norm": 0.09696892159638587,
|
| 1113 |
+
"learning_rate": 0.00016150441026536823,
|
| 1114 |
+
"loss": 0.9541,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.3625516291877008,
|
| 1119 |
+
"grad_norm": 0.0931806547196916,
|
| 1120 |
+
"learning_rate": 0.00016087084701260466,
|
| 1121 |
+
"loss": 0.9338,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.3648462597521799,
|
| 1126 |
+
"grad_norm": 0.08965151017485885,
|
| 1127 |
+
"learning_rate": 0.00016023337812542048,
|
| 1128 |
+
"loss": 0.9337,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.36714089031665903,
|
| 1133 |
+
"grad_norm": 0.08623125405498211,
|
| 1134 |
+
"learning_rate": 0.00015959204450550428,
|
| 1135 |
+
"loss": 0.9602,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.3694355208811381,
|
| 1140 |
+
"grad_norm": 0.08928739936481382,
|
| 1141 |
+
"learning_rate": 0.00015894688730251614,
|
| 1142 |
+
"loss": 0.9453,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.3717301514456173,
|
| 1147 |
+
"grad_norm": 0.08612949012161293,
|
| 1148 |
+
"learning_rate": 0.0001582979479114472,
|
| 1149 |
+
"loss": 0.9454,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.37402478201009637,
|
| 1154 |
+
"grad_norm": 0.08768044431530787,
|
| 1155 |
+
"learning_rate": 0.000157645267969964,
|
| 1156 |
+
"loss": 0.9429,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.3763194125745755,
|
| 1161 |
+
"grad_norm": 0.08907644899471728,
|
| 1162 |
+
"learning_rate": 0.0001569888893557365,
|
| 1163 |
+
"loss": 0.9459,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.3786140431390546,
|
| 1168 |
+
"grad_norm": 0.08749252420425255,
|
| 1169 |
+
"learning_rate": 0.00015632885418375136,
|
| 1170 |
+
"loss": 0.9585,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.3809086737035337,
|
| 1175 |
+
"grad_norm": 0.08988996586262392,
|
| 1176 |
+
"learning_rate": 0.00015566520480360957,
|
| 1177 |
+
"loss": 0.9663,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.38320330426801286,
|
| 1182 |
+
"grad_norm": 0.08784510387671604,
|
| 1183 |
+
"learning_rate": 0.0001549979837968094,
|
| 1184 |
+
"loss": 0.9562,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.38549793483249195,
|
| 1189 |
+
"grad_norm": 0.0863284429643144,
|
| 1190 |
+
"learning_rate": 0.00015432723397401405,
|
| 1191 |
+
"loss": 0.9507,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.3877925653969711,
|
| 1196 |
+
"grad_norm": 0.08716881362564995,
|
| 1197 |
+
"learning_rate": 0.00015365299837230483,
|
| 1198 |
+
"loss": 0.9436,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.3900871959614502,
|
| 1203 |
+
"grad_norm": 0.09125631926968461,
|
| 1204 |
+
"learning_rate": 0.00015297532025241992,
|
| 1205 |
+
"loss": 0.9326,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.39238182652592934,
|
| 1210 |
+
"grad_norm": 0.08538626816667327,
|
| 1211 |
+
"learning_rate": 0.00015229424309597852,
|
| 1212 |
+
"loss": 0.9458,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.39467645709040844,
|
| 1217 |
+
"grad_norm": 0.09072041145807094,
|
| 1218 |
+
"learning_rate": 0.00015160981060269107,
|
| 1219 |
+
"loss": 0.9893,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.3969710876548876,
|
| 1224 |
+
"grad_norm": 0.0856815427930852,
|
| 1225 |
+
"learning_rate": 0.00015092206668755517,
|
| 1226 |
+
"loss": 0.9249,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.3992657182193667,
|
| 1231 |
+
"grad_norm": 0.09070757596561506,
|
| 1232 |
+
"learning_rate": 0.00015023105547803806,
|
| 1233 |
+
"loss": 0.9618,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.4015603487838458,
|
| 1238 |
+
"grad_norm": 0.08729844078361124,
|
| 1239 |
+
"learning_rate": 0.00014953682131124528,
|
| 1240 |
+
"loss": 0.9617,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.4038549793483249,
|
| 1245 |
+
"grad_norm": 0.08727964740364995,
|
| 1246 |
+
"learning_rate": 0.0001488394087310757,
|
| 1247 |
+
"loss": 0.9347,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.406149609912804,
|
| 1252 |
+
"grad_norm": 0.08472455072190438,
|
| 1253 |
+
"learning_rate": 0.00014813886248536375,
|
| 1254 |
+
"loss": 0.9407,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.40844424047728317,
|
| 1259 |
+
"grad_norm": 0.08766621771656237,
|
| 1260 |
+
"learning_rate": 0.00014743522752300793,
|
| 1261 |
+
"loss": 0.9483,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.41073887104176227,
|
| 1266 |
+
"grad_norm": 0.09000327025386383,
|
| 1267 |
+
"learning_rate": 0.00014672854899108718,
|
| 1268 |
+
"loss": 0.951,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.4130335016062414,
|
| 1273 |
+
"grad_norm": 0.08539102749160071,
|
| 1274 |
+
"learning_rate": 0.00014601887223196372,
|
| 1275 |
+
"loss": 0.9439,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.4153281321707205,
|
| 1280 |
+
"grad_norm": 0.08868715226055852,
|
| 1281 |
+
"learning_rate": 0.00014530624278037406,
|
| 1282 |
+
"loss": 0.9511,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.41762276273519966,
|
| 1287 |
+
"grad_norm": 0.08710262112773155,
|
| 1288 |
+
"learning_rate": 0.0001445907063605072,
|
| 1289 |
+
"loss": 0.941,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.41991739329967875,
|
| 1294 |
+
"grad_norm": 0.09153632726865457,
|
| 1295 |
+
"learning_rate": 0.00014387230888307097,
|
| 1296 |
+
"loss": 0.935,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.42221202386415785,
|
| 1301 |
+
"grad_norm": 0.08807434203845403,
|
| 1302 |
+
"learning_rate": 0.0001431510964423462,
|
| 1303 |
+
"loss": 0.9618,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.424506654428637,
|
| 1308 |
+
"grad_norm": 0.08735092148978792,
|
| 1309 |
+
"learning_rate": 0.0001424271153132291,
|
| 1310 |
+
"loss": 0.9697,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.4268012849931161,
|
| 1315 |
+
"grad_norm": 0.08909879626027925,
|
| 1316 |
+
"learning_rate": 0.00014170041194826248,
|
| 1317 |
+
"loss": 0.958,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.42909591555759524,
|
| 1322 |
+
"grad_norm": 0.08915959240120495,
|
| 1323 |
+
"learning_rate": 0.0001409710329746547,
|
| 1324 |
+
"loss": 0.9423,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.43139054612207434,
|
| 1329 |
+
"grad_norm": 0.08869687131713624,
|
| 1330 |
+
"learning_rate": 0.0001402390251912885,
|
| 1331 |
+
"loss": 0.9633,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.4336851766865535,
|
| 1336 |
+
"grad_norm": 0.0881776336437586,
|
| 1337 |
+
"learning_rate": 0.00013950443556571778,
|
| 1338 |
+
"loss": 0.9548,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.4359798072510326,
|
| 1343 |
+
"grad_norm": 0.09157715163747275,
|
| 1344 |
+
"learning_rate": 0.0001387673112311545,
|
| 1345 |
+
"loss": 0.9284,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.4382744378155117,
|
| 1350 |
+
"grad_norm": 0.08636314894179382,
|
| 1351 |
+
"learning_rate": 0.00013802769948344405,
|
| 1352 |
+
"loss": 0.975,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.4405690683799908,
|
| 1357 |
+
"grad_norm": 0.08623157739774547,
|
| 1358 |
+
"learning_rate": 0.00013728564777803088,
|
| 1359 |
+
"loss": 0.9482,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.4428636989444699,
|
| 1364 |
+
"grad_norm": 0.0922928322489806,
|
| 1365 |
+
"learning_rate": 0.0001365412037269136,
|
| 1366 |
+
"loss": 0.9359,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.44515832950894907,
|
| 1371 |
+
"grad_norm": 0.08868079382090867,
|
| 1372 |
+
"learning_rate": 0.00013579441509559004,
|
| 1373 |
+
"loss": 0.9612,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.44745296007342816,
|
| 1378 |
+
"grad_norm": 0.08869466662618647,
|
| 1379 |
+
"learning_rate": 0.0001350453297999925,
|
| 1380 |
+
"loss": 0.9547,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.4497475906379073,
|
| 1385 |
+
"grad_norm": 0.08994785511659796,
|
| 1386 |
+
"learning_rate": 0.00013429399590341324,
|
| 1387 |
+
"loss": 0.9294,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.4520422212023864,
|
| 1392 |
+
"grad_norm": 0.08806701296884258,
|
| 1393 |
+
"learning_rate": 0.00013354046161342085,
|
| 1394 |
+
"loss": 0.9401,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.45433685176686556,
|
| 1399 |
+
"grad_norm": 0.08441148992282059,
|
| 1400 |
+
"learning_rate": 0.0001327847752787669,
|
| 1401 |
+
"loss": 0.942,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.45663148233134465,
|
| 1406 |
+
"grad_norm": 0.08891059913792923,
|
| 1407 |
+
"learning_rate": 0.00013202698538628376,
|
| 1408 |
+
"loss": 0.9729,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.45892611289582375,
|
| 1413 |
+
"grad_norm": 0.11772466765874874,
|
| 1414 |
+
"learning_rate": 0.00013126714055777377,
|
| 1415 |
+
"loss": 0.947,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.4612207434603029,
|
| 1420 |
+
"grad_norm": 0.08689924689552052,
|
| 1421 |
+
"learning_rate": 0.0001305052895468893,
|
| 1422 |
+
"loss": 0.9459,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.463515374024782,
|
| 1427 |
+
"grad_norm": 0.08769974762625138,
|
| 1428 |
+
"learning_rate": 0.00012974148123600477,
|
| 1429 |
+
"loss": 0.9256,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.46581000458926114,
|
| 1434 |
+
"grad_norm": 0.08612855828244712,
|
| 1435 |
+
"learning_rate": 0.00012897576463307997,
|
| 1436 |
+
"loss": 0.9506,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.46810463515374023,
|
| 1441 |
+
"grad_norm": 0.08750477475758126,
|
| 1442 |
+
"learning_rate": 0.00012820818886851598,
|
| 1443 |
+
"loss": 0.9601,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.4703992657182194,
|
| 1448 |
+
"grad_norm": 0.08517063132537664,
|
| 1449 |
+
"learning_rate": 0.00012743880319200242,
|
| 1450 |
+
"loss": 0.9678,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.4726938962826985,
|
| 1455 |
+
"grad_norm": 0.08974912157026026,
|
| 1456 |
+
"learning_rate": 0.00012666765696935773,
|
| 1457 |
+
"loss": 0.9448,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.47498852684717763,
|
| 1462 |
+
"grad_norm": 0.08899338914543631,
|
| 1463 |
+
"learning_rate": 0.0001258947996793616,
|
| 1464 |
+
"loss": 0.9585,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.4772831574116567,
|
| 1469 |
+
"grad_norm": 0.08848650886885345,
|
| 1470 |
+
"learning_rate": 0.00012512028091058044,
|
| 1471 |
+
"loss": 0.9526,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.4795777879761358,
|
| 1476 |
+
"grad_norm": 0.08563509332051665,
|
| 1477 |
+
"learning_rate": 0.00012434415035818535,
|
| 1478 |
+
"loss": 0.941,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.48187241854061497,
|
| 1483 |
+
"grad_norm": 0.08828671373838473,
|
| 1484 |
+
"learning_rate": 0.00012356645782076383,
|
| 1485 |
+
"loss": 0.9486,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.48416704910509406,
|
| 1490 |
+
"grad_norm": 0.08751318444476795,
|
| 1491 |
+
"learning_rate": 0.00012278725319712447,
|
| 1492 |
+
"loss": 0.9617,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.4864616796695732,
|
| 1497 |
+
"grad_norm": 0.08565511827085842,
|
| 1498 |
+
"learning_rate": 0.00012200658648309531,
|
| 1499 |
+
"loss": 0.9741,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.4887563102340523,
|
| 1504 |
+
"grad_norm": 0.085745763510799,
|
| 1505 |
+
"learning_rate": 0.00012122450776831594,
|
| 1506 |
+
"loss": 0.9353,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.49105094079853145,
|
| 1511 |
+
"grad_norm": 0.08682740835362232,
|
| 1512 |
+
"learning_rate": 0.00012044106723302364,
|
| 1513 |
+
"loss": 0.9276,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.49334557136301055,
|
| 1518 |
+
"grad_norm": 0.08892634949977557,
|
| 1519 |
+
"learning_rate": 0.00011965631514483375,
|
| 1520 |
+
"loss": 0.9241,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.4956402019274897,
|
| 1525 |
+
"grad_norm": 0.08726407422876443,
|
| 1526 |
+
"learning_rate": 0.00011887030185551426,
|
| 1527 |
+
"loss": 0.9563,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.4979348324919688,
|
| 1532 |
+
"grad_norm": 0.08689400522409962,
|
| 1533 |
+
"learning_rate": 0.00011808307779775518,
|
| 1534 |
+
"loss": 0.9622,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.5002294630564479,
|
| 1539 |
+
"grad_norm": 0.08645950072651667,
|
| 1540 |
+
"learning_rate": 0.00011729469348193262,
|
| 1541 |
+
"loss": 0.9346,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.502524093620927,
|
| 1546 |
+
"grad_norm": 0.0869325513465856,
|
| 1547 |
+
"learning_rate": 0.00011650519949286795,
|
| 1548 |
+
"loss": 0.934,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.5048187241854062,
|
| 1553 |
+
"grad_norm": 0.08804258211646028,
|
| 1554 |
+
"learning_rate": 0.00011571464648658201,
|
| 1555 |
+
"loss": 0.9204,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.5071133547498853,
|
| 1560 |
+
"grad_norm": 0.08652733765274413,
|
| 1561 |
+
"learning_rate": 0.00011492308518704506,
|
| 1562 |
+
"loss": 0.9355,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.5094079853143644,
|
| 1567 |
+
"grad_norm": 0.08731670771279552,
|
| 1568 |
+
"learning_rate": 0.00011413056638292215,
|
| 1569 |
+
"loss": 0.9376,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.5117026158788435,
|
| 1574 |
+
"grad_norm": 0.0876288621678255,
|
| 1575 |
+
"learning_rate": 0.00011333714092431423,
|
| 1576 |
+
"loss": 0.9434,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.5139972464433227,
|
| 1581 |
+
"grad_norm": 0.08842497197396523,
|
| 1582 |
+
"learning_rate": 0.00011254285971949574,
|
| 1583 |
+
"loss": 0.9466,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.5162918770078018,
|
| 1588 |
+
"grad_norm": 0.08833124212553112,
|
| 1589 |
+
"learning_rate": 0.00011174777373164798,
|
| 1590 |
+
"loss": 0.9424,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.5185865075722809,
|
| 1595 |
+
"grad_norm": 0.08843181606902133,
|
| 1596 |
+
"learning_rate": 0.0001109519339755893,
|
| 1597 |
+
"loss": 0.9532,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.52088113813676,
|
| 1602 |
+
"grad_norm": 0.0913721070189569,
|
| 1603 |
+
"learning_rate": 0.00011015539151450172,
|
| 1604 |
+
"loss": 0.9568,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.523175768701239,
|
| 1609 |
+
"grad_norm": 0.090062313572945,
|
| 1610 |
+
"learning_rate": 0.00010935819745665477,
|
| 1611 |
+
"loss": 0.9365,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.5254703992657183,
|
| 1616 |
+
"grad_norm": 0.08718333029104089,
|
| 1617 |
+
"learning_rate": 0.00010856040295212612,
|
| 1618 |
+
"loss": 0.9609,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.5277650298301974,
|
| 1623 |
+
"grad_norm": 0.08762141136978818,
|
| 1624 |
+
"learning_rate": 0.00010776205918951969,
|
| 1625 |
+
"loss": 0.947,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.5300596603946764,
|
| 1630 |
+
"grad_norm": 0.09288381777131122,
|
| 1631 |
+
"learning_rate": 0.00010696321739268121,
|
| 1632 |
+
"loss": 0.95,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.5323542909591555,
|
| 1637 |
+
"grad_norm": 0.08690475691948375,
|
| 1638 |
+
"learning_rate": 0.00010616392881741166,
|
| 1639 |
+
"loss": 0.9259,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.5346489215236347,
|
| 1644 |
+
"grad_norm": 0.08761053817275535,
|
| 1645 |
+
"learning_rate": 0.00010536424474817847,
|
| 1646 |
+
"loss": 0.9257,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.5369435520881138,
|
| 1651 |
+
"grad_norm": 0.08580794325150348,
|
| 1652 |
+
"learning_rate": 0.00010456421649482502,
|
| 1653 |
+
"loss": 0.9491,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.5392381826525929,
|
| 1658 |
+
"grad_norm": 0.08875803785646835,
|
| 1659 |
+
"learning_rate": 0.0001037638953892784,
|
| 1660 |
+
"loss": 0.9611,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.541532813217072,
|
| 1665 |
+
"grad_norm": 0.08822711832526892,
|
| 1666 |
+
"learning_rate": 0.00010296333278225599,
|
| 1667 |
+
"loss": 0.9466,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.5438274437815511,
|
| 1672 |
+
"grad_norm": 0.08973140268678324,
|
| 1673 |
+
"learning_rate": 0.00010216258003997043,
|
| 1674 |
+
"loss": 0.9707,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.5461220743460303,
|
| 1679 |
+
"grad_norm": 0.08753068797299891,
|
| 1680 |
+
"learning_rate": 0.00010136168854083402,
|
| 1681 |
+
"loss": 0.9042,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.5484167049105094,
|
| 1686 |
+
"grad_norm": 0.08919024988233984,
|
| 1687 |
+
"learning_rate": 0.00010056070967216198,
|
| 1688 |
+
"loss": 0.9366,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.5507113354749885,
|
| 1693 |
+
"grad_norm": 0.088157407581,
|
| 1694 |
+
"learning_rate": 9.975969482687547e-05,
|
| 1695 |
+
"loss": 0.9258,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.5530059660394676,
|
| 1700 |
+
"grad_norm": 0.08612555956203556,
|
| 1701 |
+
"learning_rate": 9.8958695400204e-05,
|
| 1702 |
+
"loss": 0.9428,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.5553005966039468,
|
| 1707 |
+
"grad_norm": 0.08863199154938804,
|
| 1708 |
+
"learning_rate": 9.815776278638771e-05,
|
| 1709 |
+
"loss": 0.9659,
|
| 1710 |
+
"step": 1210
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.5575952271684259,
|
| 1714 |
+
"grad_norm": 0.0877396299101558,
|
| 1715 |
+
"learning_rate": 9.735694837537993e-05,
|
| 1716 |
+
"loss": 0.9146,
|
| 1717 |
+
"step": 1215
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.559889857732905,
|
| 1721 |
+
"grad_norm": 0.10016922577996923,
|
| 1722 |
+
"learning_rate": 9.655630354954974e-05,
|
| 1723 |
+
"loss": 0.9344,
|
| 1724 |
+
"step": 1220
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.5621844882973841,
|
| 1728 |
+
"grad_norm": 0.08776498802340123,
|
| 1729 |
+
"learning_rate": 9.57558796803852e-05,
|
| 1730 |
+
"loss": 0.9508,
|
| 1731 |
+
"step": 1225
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.5644791188618632,
|
| 1735 |
+
"grad_norm": 0.08576773127748236,
|
| 1736 |
+
"learning_rate": 9.495572812519718e-05,
|
| 1737 |
+
"loss": 0.9367,
|
| 1738 |
+
"step": 1230
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.5667737494263424,
|
| 1742 |
+
"grad_norm": 0.090860993764857,
|
| 1743 |
+
"learning_rate": 9.415590022382419e-05,
|
| 1744 |
+
"loss": 0.9482,
|
| 1745 |
+
"step": 1235
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.5690683799908215,
|
| 1749 |
+
"grad_norm": 0.08739072969654303,
|
| 1750 |
+
"learning_rate": 9.33564472953383e-05,
|
| 1751 |
+
"loss": 0.9296,
|
| 1752 |
+
"step": 1240
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.5713630105553006,
|
| 1756 |
+
"grad_norm": 0.0861680762249506,
|
| 1757 |
+
"learning_rate": 9.255742063475228e-05,
|
| 1758 |
+
"loss": 0.9474,
|
| 1759 |
+
"step": 1245
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.5736576411197797,
|
| 1763 |
+
"grad_norm": 0.09031291699160855,
|
| 1764 |
+
"learning_rate": 9.175887150972841e-05,
|
| 1765 |
+
"loss": 0.9347,
|
| 1766 |
+
"step": 1250
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.5759522716842589,
|
| 1770 |
+
"grad_norm": 0.08782934008281447,
|
| 1771 |
+
"learning_rate": 9.096085115728902e-05,
|
| 1772 |
+
"loss": 0.9254,
|
| 1773 |
+
"step": 1255
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.578246902248738,
|
| 1777 |
+
"grad_norm": 0.08672572395996989,
|
| 1778 |
+
"learning_rate": 9.016341078052908e-05,
|
| 1779 |
+
"loss": 0.924,
|
| 1780 |
+
"step": 1260
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.5805415328132171,
|
| 1784 |
+
"grad_norm": 0.08848493722986495,
|
| 1785 |
+
"learning_rate": 8.936660154533069e-05,
|
| 1786 |
+
"loss": 0.9398,
|
| 1787 |
+
"step": 1265
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.5828361633776962,
|
| 1791 |
+
"grad_norm": 0.08795360842845397,
|
| 1792 |
+
"learning_rate": 8.857047457708023e-05,
|
| 1793 |
+
"loss": 0.9408,
|
| 1794 |
+
"step": 1270
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.5851307939421753,
|
| 1798 |
+
"grad_norm": 0.0860614623181383,
|
| 1799 |
+
"learning_rate": 8.777508095738818e-05,
|
| 1800 |
+
"loss": 0.9334,
|
| 1801 |
+
"step": 1275
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.5874254245066545,
|
| 1805 |
+
"grad_norm": 0.09151871492029366,
|
| 1806 |
+
"learning_rate": 8.698047172081128e-05,
|
| 1807 |
+
"loss": 0.9372,
|
| 1808 |
+
"step": 1280
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.5897200550711336,
|
| 1812 |
+
"grad_norm": 0.08719515886726915,
|
| 1813 |
+
"learning_rate": 8.618669785157825e-05,
|
| 1814 |
+
"loss": 0.9346,
|
| 1815 |
+
"step": 1285
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.5920146856356127,
|
| 1819 |
+
"grad_norm": 0.08602811823889805,
|
| 1820 |
+
"learning_rate": 8.539381028031837e-05,
|
| 1821 |
+
"loss": 0.95,
|
| 1822 |
+
"step": 1290
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.5943093162000918,
|
| 1826 |
+
"grad_norm": 0.09010753852396704,
|
| 1827 |
+
"learning_rate": 8.460185988079379e-05,
|
| 1828 |
+
"loss": 0.9623,
|
| 1829 |
+
"step": 1295
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.596603946764571,
|
| 1833 |
+
"grad_norm": 0.08768581543675588,
|
| 1834 |
+
"learning_rate": 8.381089746663517e-05,
|
| 1835 |
+
"loss": 0.9391,
|
| 1836 |
+
"step": 1300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.59889857732905,
|
| 1840 |
+
"grad_norm": 0.08992597459848777,
|
| 1841 |
+
"learning_rate": 8.302097378808146e-05,
|
| 1842 |
+
"loss": 0.9436,
|
| 1843 |
+
"step": 1305
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.6011932078935291,
|
| 1847 |
+
"grad_norm": 0.08897797699662331,
|
| 1848 |
+
"learning_rate": 8.223213952872353e-05,
|
| 1849 |
+
"loss": 0.9466,
|
| 1850 |
+
"step": 1310
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.6034878384580082,
|
| 1854 |
+
"grad_norm": 0.08711970422648517,
|
| 1855 |
+
"learning_rate": 8.144444530225236e-05,
|
| 1856 |
+
"loss": 0.9602,
|
| 1857 |
+
"step": 1315
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.6057824690224873,
|
| 1861 |
+
"grad_norm": 0.08744571704998887,
|
| 1862 |
+
"learning_rate": 8.065794164921128e-05,
|
| 1863 |
+
"loss": 0.9609,
|
| 1864 |
+
"step": 1320
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.6080770995869665,
|
| 1868 |
+
"grad_norm": 0.08732342917773199,
|
| 1869 |
+
"learning_rate": 7.987267903375332e-05,
|
| 1870 |
+
"loss": 0.9388,
|
| 1871 |
+
"step": 1325
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.6103717301514456,
|
| 1875 |
+
"grad_norm": 0.08634671243153437,
|
| 1876 |
+
"learning_rate": 7.90887078404033e-05,
|
| 1877 |
+
"loss": 0.9379,
|
| 1878 |
+
"step": 1330
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.6126663607159247,
|
| 1882 |
+
"grad_norm": 0.08792026326901815,
|
| 1883 |
+
"learning_rate": 7.830607837082493e-05,
|
| 1884 |
+
"loss": 0.9364,
|
| 1885 |
+
"step": 1335
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.6149609912804038,
|
| 1889 |
+
"grad_norm": 0.08657044899326832,
|
| 1890 |
+
"learning_rate": 7.75248408405934e-05,
|
| 1891 |
+
"loss": 0.9502,
|
| 1892 |
+
"step": 1340
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.617255621844883,
|
| 1896 |
+
"grad_norm": 0.08924319703176266,
|
| 1897 |
+
"learning_rate": 7.674504537597336e-05,
|
| 1898 |
+
"loss": 0.9431,
|
| 1899 |
+
"step": 1345
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.6195502524093621,
|
| 1903 |
+
"grad_norm": 0.08777369904115767,
|
| 1904 |
+
"learning_rate": 7.596674201070282e-05,
|
| 1905 |
+
"loss": 0.9507,
|
| 1906 |
+
"step": 1350
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.6218448829738412,
|
| 1910 |
+
"grad_norm": 0.08822604258128913,
|
| 1911 |
+
"learning_rate": 7.518998068278266e-05,
|
| 1912 |
+
"loss": 0.9389,
|
| 1913 |
+
"step": 1355
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.6241395135383203,
|
| 1917 |
+
"grad_norm": 0.0872584357855511,
|
| 1918 |
+
"learning_rate": 7.441481123127257e-05,
|
| 1919 |
+
"loss": 0.9272,
|
| 1920 |
+
"step": 1360
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.6264341441027994,
|
| 1924 |
+
"grad_norm": 0.09420031727135263,
|
| 1925 |
+
"learning_rate": 7.364128339309326e-05,
|
| 1926 |
+
"loss": 0.9496,
|
| 1927 |
+
"step": 1365
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.6287287746672786,
|
| 1931 |
+
"grad_norm": 0.09178449177995368,
|
| 1932 |
+
"learning_rate": 7.28694467998352e-05,
|
| 1933 |
+
"loss": 0.9272,
|
| 1934 |
+
"step": 1370
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.6310234052317577,
|
| 1938 |
+
"grad_norm": 0.08547328194451309,
|
| 1939 |
+
"learning_rate": 7.209935097457413e-05,
|
| 1940 |
+
"loss": 0.943,
|
| 1941 |
+
"step": 1375
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.6333180357962368,
|
| 1945 |
+
"grad_norm": 0.08867995753938929,
|
| 1946 |
+
"learning_rate": 7.133104532869342e-05,
|
| 1947 |
+
"loss": 0.963,
|
| 1948 |
+
"step": 1380
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.6356126663607159,
|
| 1952 |
+
"grad_norm": 0.08966519220883923,
|
| 1953 |
+
"learning_rate": 7.056457915871399e-05,
|
| 1954 |
+
"loss": 0.9317,
|
| 1955 |
+
"step": 1385
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.637907296925195,
|
| 1959 |
+
"grad_norm": 0.08882768063994861,
|
| 1960 |
+
"learning_rate": 6.980000164313093e-05,
|
| 1961 |
+
"loss": 0.9226,
|
| 1962 |
+
"step": 1390
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.6402019274896742,
|
| 1966 |
+
"grad_norm": 0.08837784094850205,
|
| 1967 |
+
"learning_rate": 6.903736183925835e-05,
|
| 1968 |
+
"loss": 0.939,
|
| 1969 |
+
"step": 1395
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.6424965580541533,
|
| 1973 |
+
"grad_norm": 0.08678715695619918,
|
| 1974 |
+
"learning_rate": 6.827670868008171e-05,
|
| 1975 |
+
"loss": 0.9574,
|
| 1976 |
+
"step": 1400
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.6447911886186324,
|
| 1980 |
+
"grad_norm": 0.08687361153125922,
|
| 1981 |
+
"learning_rate": 6.751809097111798e-05,
|
| 1982 |
+
"loss": 0.9608,
|
| 1983 |
+
"step": 1405
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.6470858191831115,
|
| 1987 |
+
"grad_norm": 0.09043663200344924,
|
| 1988 |
+
"learning_rate": 6.676155738728438e-05,
|
| 1989 |
+
"loss": 0.9454,
|
| 1990 |
+
"step": 1410
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.6493804497475907,
|
| 1994 |
+
"grad_norm": 0.08587170447948225,
|
| 1995 |
+
"learning_rate": 6.600715646977502e-05,
|
| 1996 |
+
"loss": 0.9436,
|
| 1997 |
+
"step": 1415
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.6516750803120698,
|
| 2001 |
+
"grad_norm": 0.08747748944349737,
|
| 2002 |
+
"learning_rate": 6.525493662294668e-05,
|
| 2003 |
+
"loss": 0.9433,
|
| 2004 |
+
"step": 1420
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.6539697108765489,
|
| 2008 |
+
"grad_norm": 0.08644951356394669,
|
| 2009 |
+
"learning_rate": 6.450494611121273e-05,
|
| 2010 |
+
"loss": 0.9544,
|
| 2011 |
+
"step": 1425
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.656264341441028,
|
| 2015 |
+
"grad_norm": 0.08616266377880767,
|
| 2016 |
+
"learning_rate": 6.375723305594658e-05,
|
| 2017 |
+
"loss": 0.9502,
|
| 2018 |
+
"step": 1430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.6585589720055071,
|
| 2022 |
+
"grad_norm": 0.08828640675025567,
|
| 2023 |
+
"learning_rate": 6.301184543239398e-05,
|
| 2024 |
+
"loss": 0.9397,
|
| 2025 |
+
"step": 1435
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.6608536025699863,
|
| 2029 |
+
"grad_norm": 0.08766906251082068,
|
| 2030 |
+
"learning_rate": 6.226883106659485e-05,
|
| 2031 |
+
"loss": 0.966,
|
| 2032 |
+
"step": 1440
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.6631482331344654,
|
| 2036 |
+
"grad_norm": 0.0901196932930806,
|
| 2037 |
+
"learning_rate": 6.152823763231463e-05,
|
| 2038 |
+
"loss": 0.9307,
|
| 2039 |
+
"step": 1445
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.6654428636989445,
|
| 2043 |
+
"grad_norm": 0.08653082781266369,
|
| 2044 |
+
"learning_rate": 6.079011264798534e-05,
|
| 2045 |
+
"loss": 0.9362,
|
| 2046 |
+
"step": 1450
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.6677374942634235,
|
| 2050 |
+
"grad_norm": 0.08851540125345415,
|
| 2051 |
+
"learning_rate": 6.005450347365687e-05,
|
| 2052 |
+
"loss": 0.9575,
|
| 2053 |
+
"step": 1455
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.6700321248279028,
|
| 2057 |
+
"grad_norm": 0.0898855821818352,
|
| 2058 |
+
"learning_rate": 5.932145730795793e-05,
|
| 2059 |
+
"loss": 0.94,
|
| 2060 |
+
"step": 1460
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.6723267553923818,
|
| 2064 |
+
"grad_norm": 0.08793133426546608,
|
| 2065 |
+
"learning_rate": 5.8591021185067876e-05,
|
| 2066 |
+
"loss": 0.9307,
|
| 2067 |
+
"step": 1465
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.6746213859568609,
|
| 2071 |
+
"grad_norm": 0.09185643968705434,
|
| 2072 |
+
"learning_rate": 5.786324197169887e-05,
|
| 2073 |
+
"loss": 0.9603,
|
| 2074 |
+
"step": 1470
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.67691601652134,
|
| 2078 |
+
"grad_norm": 0.08642240102898958,
|
| 2079 |
+
"learning_rate": 5.7138166364088705e-05,
|
| 2080 |
+
"loss": 0.9417,
|
| 2081 |
+
"step": 1475
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.6792106470858191,
|
| 2085 |
+
"grad_norm": 0.08511965941194902,
|
| 2086 |
+
"learning_rate": 5.641584088500461e-05,
|
| 2087 |
+
"loss": 0.94,
|
| 2088 |
+
"step": 1480
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.6815052776502983,
|
| 2092 |
+
"grad_norm": 0.08723628225521773,
|
| 2093 |
+
"learning_rate": 5.569631188075841e-05,
|
| 2094 |
+
"loss": 0.9248,
|
| 2095 |
+
"step": 1485
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.6837999082147774,
|
| 2099 |
+
"grad_norm": 0.08633274736360919,
|
| 2100 |
+
"learning_rate": 5.497962551823266e-05,
|
| 2101 |
+
"loss": 0.9469,
|
| 2102 |
+
"step": 1490
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.6860945387792565,
|
| 2106 |
+
"grad_norm": 0.09266736313451518,
|
| 2107 |
+
"learning_rate": 5.4265827781918576e-05,
|
| 2108 |
+
"loss": 0.9692,
|
| 2109 |
+
"step": 1495
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.6883891693437356,
|
| 2113 |
+
"grad_norm": 0.08989480494070151,
|
| 2114 |
+
"learning_rate": 5.355496447096533e-05,
|
| 2115 |
+
"loss": 0.969,
|
| 2116 |
+
"step": 1500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.6906837999082148,
|
| 2120 |
+
"grad_norm": 0.08776725254212203,
|
| 2121 |
+
"learning_rate": 5.284708119624173e-05,
|
| 2122 |
+
"loss": 0.9655,
|
| 2123 |
+
"step": 1505
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.6929784304726939,
|
| 2127 |
+
"grad_norm": 0.0858923659739521,
|
| 2128 |
+
"learning_rate": 5.214222337740962e-05,
|
| 2129 |
+
"loss": 0.9364,
|
| 2130 |
+
"step": 1510
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.695273061037173,
|
| 2134 |
+
"grad_norm": 0.08991893131765896,
|
| 2135 |
+
"learning_rate": 5.144043624000944e-05,
|
| 2136 |
+
"loss": 0.8978,
|
| 2137 |
+
"step": 1515
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.6975676916016521,
|
| 2141 |
+
"grad_norm": 0.08502238183879142,
|
| 2142 |
+
"learning_rate": 5.0741764812558724e-05,
|
| 2143 |
+
"loss": 0.9402,
|
| 2144 |
+
"step": 1520
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.6998623221661312,
|
| 2148 |
+
"grad_norm": 0.08668719280033117,
|
| 2149 |
+
"learning_rate": 5.00462539236628e-05,
|
| 2150 |
+
"loss": 0.9471,
|
| 2151 |
+
"step": 1525
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.7021569527306104,
|
| 2155 |
+
"grad_norm": 0.08462698467850949,
|
| 2156 |
+
"learning_rate": 4.935394819913849e-05,
|
| 2157 |
+
"loss": 0.9249,
|
| 2158 |
+
"step": 1530
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.7044515832950895,
|
| 2162 |
+
"grad_norm": 0.08607092895236686,
|
| 2163 |
+
"learning_rate": 4.8664892059150723e-05,
|
| 2164 |
+
"loss": 0.9602,
|
| 2165 |
+
"step": 1535
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.7067462138595686,
|
| 2169 |
+
"grad_norm": 0.08935744366472125,
|
| 2170 |
+
"learning_rate": 4.7979129715362626e-05,
|
| 2171 |
+
"loss": 0.9798,
|
| 2172 |
+
"step": 1540
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.7090408444240477,
|
| 2176 |
+
"grad_norm": 0.0854376252471685,
|
| 2177 |
+
"learning_rate": 4.72967051680985e-05,
|
| 2178 |
+
"loss": 0.9393,
|
| 2179 |
+
"step": 1545
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.7113354749885269,
|
| 2183 |
+
"grad_norm": 0.08935720877957573,
|
| 2184 |
+
"learning_rate": 4.661766220352097e-05,
|
| 2185 |
+
"loss": 0.9224,
|
| 2186 |
+
"step": 1550
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.713630105553006,
|
| 2190 |
+
"grad_norm": 0.08985254696056548,
|
| 2191 |
+
"learning_rate": 4.5942044390821214e-05,
|
| 2192 |
+
"loss": 0.9561,
|
| 2193 |
+
"step": 1555
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.7159247361174851,
|
| 2197 |
+
"grad_norm": 0.08908651127378205,
|
| 2198 |
+
"learning_rate": 4.526989507942374e-05,
|
| 2199 |
+
"loss": 0.9339,
|
| 2200 |
+
"step": 1560
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.7182193666819642,
|
| 2204 |
+
"grad_norm": 0.08630595159367531,
|
| 2205 |
+
"learning_rate": 4.460125739620479e-05,
|
| 2206 |
+
"loss": 0.9338,
|
| 2207 |
+
"step": 1565
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.7205139972464433,
|
| 2211 |
+
"grad_norm": 0.08857577901710953,
|
| 2212 |
+
"learning_rate": 4.393617424272527e-05,
|
| 2213 |
+
"loss": 0.9493,
|
| 2214 |
+
"step": 1570
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.7228086278109225,
|
| 2218 |
+
"grad_norm": 0.08887546613261192,
|
| 2219 |
+
"learning_rate": 4.3274688292478106e-05,
|
| 2220 |
+
"loss": 0.9469,
|
| 2221 |
+
"step": 1575
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.7251032583754016,
|
| 2225 |
+
"grad_norm": 0.08719401842713113,
|
| 2226 |
+
"learning_rate": 4.261684198815003e-05,
|
| 2227 |
+
"loss": 0.9444,
|
| 2228 |
+
"step": 1580
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.7273978889398807,
|
| 2232 |
+
"grad_norm": 0.08619407541853812,
|
| 2233 |
+
"learning_rate": 4.1962677538898645e-05,
|
| 2234 |
+
"loss": 0.944,
|
| 2235 |
+
"step": 1585
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.7296925195043598,
|
| 2239 |
+
"grad_norm": 0.08443943693203552,
|
| 2240 |
+
"learning_rate": 4.131223691764383e-05,
|
| 2241 |
+
"loss": 0.9225,
|
| 2242 |
+
"step": 1590
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.731987150068839,
|
| 2246 |
+
"grad_norm": 0.08565149963984416,
|
| 2247 |
+
"learning_rate": 4.0665561858374934e-05,
|
| 2248 |
+
"loss": 0.9289,
|
| 2249 |
+
"step": 1595
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.7342817806333181,
|
| 2253 |
+
"grad_norm": 0.0878443494214115,
|
| 2254 |
+
"learning_rate": 4.0022693853472884e-05,
|
| 2255 |
+
"loss": 0.9111,
|
| 2256 |
+
"step": 1600
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.7365764111977972,
|
| 2260 |
+
"grad_norm": 0.08904194669918195,
|
| 2261 |
+
"learning_rate": 3.938367415104793e-05,
|
| 2262 |
+
"loss": 0.9531,
|
| 2263 |
+
"step": 1605
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.7388710417622762,
|
| 2267 |
+
"grad_norm": 0.08893651456090547,
|
| 2268 |
+
"learning_rate": 3.8748543752293e-05,
|
| 2269 |
+
"loss": 0.9584,
|
| 2270 |
+
"step": 1610
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.7411656723267553,
|
| 2274 |
+
"grad_norm": 0.08897315588461706,
|
| 2275 |
+
"learning_rate": 3.8117343408853127e-05,
|
| 2276 |
+
"loss": 0.9319,
|
| 2277 |
+
"step": 1615
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.7434603028912345,
|
| 2281 |
+
"grad_norm": 0.08616983463133208,
|
| 2282 |
+
"learning_rate": 3.7490113620210485e-05,
|
| 2283 |
+
"loss": 0.9146,
|
| 2284 |
+
"step": 1620
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.7457549334557136,
|
| 2288 |
+
"grad_norm": 0.0873842160083806,
|
| 2289 |
+
"learning_rate": 3.686689463108608e-05,
|
| 2290 |
+
"loss": 0.9431,
|
| 2291 |
+
"step": 1625
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.7480495640201927,
|
| 2295 |
+
"grad_norm": 0.08712124349433248,
|
| 2296 |
+
"learning_rate": 3.624772642885734e-05,
|
| 2297 |
+
"loss": 0.923,
|
| 2298 |
+
"step": 1630
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.7503441945846718,
|
| 2302 |
+
"grad_norm": 0.08857054628390904,
|
| 2303 |
+
"learning_rate": 3.563264874099258e-05,
|
| 2304 |
+
"loss": 0.9537,
|
| 2305 |
+
"step": 1635
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.752638825149151,
|
| 2309 |
+
"grad_norm": 0.08430268133869642,
|
| 2310 |
+
"learning_rate": 3.502170103250177e-05,
|
| 2311 |
+
"loss": 0.9093,
|
| 2312 |
+
"step": 1640
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.7549334557136301,
|
| 2316 |
+
"grad_norm": 0.08778596880519368,
|
| 2317 |
+
"learning_rate": 3.441492250340461e-05,
|
| 2318 |
+
"loss": 0.9361,
|
| 2319 |
+
"step": 1645
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.7572280862781092,
|
| 2323 |
+
"grad_norm": 0.08734144942203491,
|
| 2324 |
+
"learning_rate": 3.381235208621522e-05,
|
| 2325 |
+
"loss": 0.9259,
|
| 2326 |
+
"step": 1650
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.7595227168425883,
|
| 2330 |
+
"grad_norm": 0.08734310507948465,
|
| 2331 |
+
"learning_rate": 3.3214028443444036e-05,
|
| 2332 |
+
"loss": 0.9354,
|
| 2333 |
+
"step": 1655
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.7618173474070674,
|
| 2337 |
+
"grad_norm": 0.08820927771902966,
|
| 2338 |
+
"learning_rate": 3.2619989965117356e-05,
|
| 2339 |
+
"loss": 0.9134,
|
| 2340 |
+
"step": 1660
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.7641119779715466,
|
| 2344 |
+
"grad_norm": 0.0890839295904084,
|
| 2345 |
+
"learning_rate": 3.2030274766313865e-05,
|
| 2346 |
+
"loss": 0.9326,
|
| 2347 |
+
"step": 1665
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.7664066085360257,
|
| 2351 |
+
"grad_norm": 0.0930961939643943,
|
| 2352 |
+
"learning_rate": 3.1444920684719394e-05,
|
| 2353 |
+
"loss": 0.9347,
|
| 2354 |
+
"step": 1670
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.7687012391005048,
|
| 2358 |
+
"grad_norm": 0.0870955697496051,
|
| 2359 |
+
"learning_rate": 3.086396527819876e-05,
|
| 2360 |
+
"loss": 0.9264,
|
| 2361 |
+
"step": 1675
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.7709958696649839,
|
| 2365 |
+
"grad_norm": 0.0899287105378734,
|
| 2366 |
+
"learning_rate": 3.028744582238633e-05,
|
| 2367 |
+
"loss": 0.9407,
|
| 2368 |
+
"step": 1680
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.7732905002294631,
|
| 2372 |
+
"grad_norm": 0.09021085870835642,
|
| 2373 |
+
"learning_rate": 2.9715399308294e-05,
|
| 2374 |
+
"loss": 0.9652,
|
| 2375 |
+
"step": 1685
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.7755851307939422,
|
| 2379 |
+
"grad_norm": 0.08809579986676752,
|
| 2380 |
+
"learning_rate": 2.914786243993808e-05,
|
| 2381 |
+
"loss": 0.9271,
|
| 2382 |
+
"step": 1690
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.7778797613584213,
|
| 2386 |
+
"grad_norm": 0.08806930004292979,
|
| 2387 |
+
"learning_rate": 2.8584871631983888e-05,
|
| 2388 |
+
"loss": 0.9353,
|
| 2389 |
+
"step": 1695
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.7801743919229004,
|
| 2393 |
+
"grad_norm": 0.08874560139452363,
|
| 2394 |
+
"learning_rate": 2.8026463007409664e-05,
|
| 2395 |
+
"loss": 0.9364,
|
| 2396 |
+
"step": 1700
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.7824690224873795,
|
| 2400 |
+
"grad_norm": 0.09095899541023127,
|
| 2401 |
+
"learning_rate": 2.747267239518857e-05,
|
| 2402 |
+
"loss": 0.9432,
|
| 2403 |
+
"step": 1705
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.7847636530518587,
|
| 2407 |
+
"grad_norm": 0.08597962745032185,
|
| 2408 |
+
"learning_rate": 2.6923535327989924e-05,
|
| 2409 |
+
"loss": 0.9365,
|
| 2410 |
+
"step": 1710
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.7870582836163378,
|
| 2414 |
+
"grad_norm": 0.08728499968023844,
|
| 2415 |
+
"learning_rate": 2.637908703989924e-05,
|
| 2416 |
+
"loss": 0.9546,
|
| 2417 |
+
"step": 1715
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.7893529141808169,
|
| 2421 |
+
"grad_norm": 0.0865310427946889,
|
| 2422 |
+
"learning_rate": 2.5839362464157634e-05,
|
| 2423 |
+
"loss": 0.9444,
|
| 2424 |
+
"step": 1720
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.791647544745296,
|
| 2428 |
+
"grad_norm": 0.08952067073529965,
|
| 2429 |
+
"learning_rate": 2.5304396230920345e-05,
|
| 2430 |
+
"loss": 0.9551,
|
| 2431 |
+
"step": 1725
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.7939421753097752,
|
| 2435 |
+
"grad_norm": 0.08590487479214523,
|
| 2436 |
+
"learning_rate": 2.477422266503473e-05,
|
| 2437 |
+
"loss": 0.9416,
|
| 2438 |
+
"step": 1730
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.7962368058742543,
|
| 2442 |
+
"grad_norm": 0.08843022208186156,
|
| 2443 |
+
"learning_rate": 2.4248875783837987e-05,
|
| 2444 |
+
"loss": 0.9401,
|
| 2445 |
+
"step": 1735
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.7985314364387334,
|
| 2449 |
+
"grad_norm": 0.08728520520911832,
|
| 2450 |
+
"learning_rate": 2.3728389294974475e-05,
|
| 2451 |
+
"loss": 0.954,
|
| 2452 |
+
"step": 1740
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.8008260670032125,
|
| 2456 |
+
"grad_norm": 0.09169106802431096,
|
| 2457 |
+
"learning_rate": 2.3212796594232943e-05,
|
| 2458 |
+
"loss": 0.9592,
|
| 2459 |
+
"step": 1745
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.8031206975676916,
|
| 2463 |
+
"grad_norm": 0.08931921878894941,
|
| 2464 |
+
"learning_rate": 2.2702130763403673e-05,
|
| 2465 |
+
"loss": 0.9406,
|
| 2466 |
+
"step": 1750
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.8054153281321708,
|
| 2470 |
+
"grad_norm": 0.08764598773379657,
|
| 2471 |
+
"learning_rate": 2.2196424568156073e-05,
|
| 2472 |
+
"loss": 0.9384,
|
| 2473 |
+
"step": 1755
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.8077099586966499,
|
| 2477 |
+
"grad_norm": 0.08855507556833625,
|
| 2478 |
+
"learning_rate": 2.1695710455936115e-05,
|
| 2479 |
+
"loss": 0.9433,
|
| 2480 |
+
"step": 1760
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.810004589261129,
|
| 2484 |
+
"grad_norm": 0.08532871067750841,
|
| 2485 |
+
"learning_rate": 2.1200020553884604e-05,
|
| 2486 |
+
"loss": 0.9346,
|
| 2487 |
+
"step": 1765
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.812299219825608,
|
| 2491 |
+
"grad_norm": 0.08966754551907985,
|
| 2492 |
+
"learning_rate": 2.070938666677573e-05,
|
| 2493 |
+
"loss": 0.9508,
|
| 2494 |
+
"step": 1770
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.8145938503900872,
|
| 2498 |
+
"grad_norm": 0.09025156831747091,
|
| 2499 |
+
"learning_rate": 2.0223840274976413e-05,
|
| 2500 |
+
"loss": 0.9809,
|
| 2501 |
+
"step": 1775
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.8168884809545663,
|
| 2505 |
+
"grad_norm": 0.08854265504832948,
|
| 2506 |
+
"learning_rate": 1.974341253242635e-05,
|
| 2507 |
+
"loss": 0.9191,
|
| 2508 |
+
"step": 1780
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.8191831115190454,
|
| 2512 |
+
"grad_norm": 0.08884601227475634,
|
| 2513 |
+
"learning_rate": 1.9268134264639272e-05,
|
| 2514 |
+
"loss": 0.9446,
|
| 2515 |
+
"step": 1785
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.8214777420835245,
|
| 2519 |
+
"grad_norm": 0.0900014724971187,
|
| 2520 |
+
"learning_rate": 1.879803596672497e-05,
|
| 2521 |
+
"loss": 0.9569,
|
| 2522 |
+
"step": 1790
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.8237723726480036,
|
| 2526 |
+
"grad_norm": 0.08586515698037704,
|
| 2527 |
+
"learning_rate": 1.8333147801432614e-05,
|
| 2528 |
+
"loss": 0.9237,
|
| 2529 |
+
"step": 1795
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.8260670032124828,
|
| 2533 |
+
"grad_norm": 0.08704559914739361,
|
| 2534 |
+
"learning_rate": 1.7873499597215604e-05,
|
| 2535 |
+
"loss": 0.9146,
|
| 2536 |
+
"step": 1800
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.8283616337769619,
|
| 2540 |
+
"grad_norm": 0.08957226377233579,
|
| 2541 |
+
"learning_rate": 1.741912084631746e-05,
|
| 2542 |
+
"loss": 0.9495,
|
| 2543 |
+
"step": 1805
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.830656264341441,
|
| 2547 |
+
"grad_norm": 0.0862080402115559,
|
| 2548 |
+
"learning_rate": 1.697004070287982e-05,
|
| 2549 |
+
"loss": 0.9089,
|
| 2550 |
+
"step": 1810
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.8329508949059201,
|
| 2554 |
+
"grad_norm": 0.08632960573186395,
|
| 2555 |
+
"learning_rate": 1.6526287981071475e-05,
|
| 2556 |
+
"loss": 0.9157,
|
| 2557 |
+
"step": 1815
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.8352455254703993,
|
| 2561 |
+
"grad_norm": 0.08440907866960998,
|
| 2562 |
+
"learning_rate": 1.608789115323993e-05,
|
| 2563 |
+
"loss": 0.9658,
|
| 2564 |
+
"step": 1820
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.8375401560348784,
|
| 2568 |
+
"grad_norm": 0.08731523817505203,
|
| 2569 |
+
"learning_rate": 1.5654878348084244e-05,
|
| 2570 |
+
"loss": 0.9551,
|
| 2571 |
+
"step": 1825
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.8398347865993575,
|
| 2575 |
+
"grad_norm": 0.08915491610885863,
|
| 2576 |
+
"learning_rate": 1.5227277348850466e-05,
|
| 2577 |
+
"loss": 0.9446,
|
| 2578 |
+
"step": 1830
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.8421294171638366,
|
| 2582 |
+
"grad_norm": 0.0869732185667195,
|
| 2583 |
+
"learning_rate": 1.4805115591548746e-05,
|
| 2584 |
+
"loss": 0.9225,
|
| 2585 |
+
"step": 1835
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.8444240477283157,
|
| 2589 |
+
"grad_norm": 0.08670718205091706,
|
| 2590 |
+
"learning_rate": 1.4388420163193217e-05,
|
| 2591 |
+
"loss": 0.9261,
|
| 2592 |
+
"step": 1840
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.8467186782927949,
|
| 2596 |
+
"grad_norm": 0.09137885764266358,
|
| 2597 |
+
"learning_rate": 1.3977217800063846e-05,
|
| 2598 |
+
"loss": 0.9469,
|
| 2599 |
+
"step": 1845
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.849013308857274,
|
| 2603 |
+
"grad_norm": 0.08818902846204707,
|
| 2604 |
+
"learning_rate": 1.3571534885991044e-05,
|
| 2605 |
+
"loss": 0.9192,
|
| 2606 |
+
"step": 1850
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.8513079394217531,
|
| 2610 |
+
"grad_norm": 0.08515505179393418,
|
| 2611 |
+
"learning_rate": 1.3171397450662715e-05,
|
| 2612 |
+
"loss": 0.9322,
|
| 2613 |
+
"step": 1855
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.8536025699862322,
|
| 2617 |
+
"grad_norm": 0.09793678826450831,
|
| 2618 |
+
"learning_rate": 1.277683116795425e-05,
|
| 2619 |
+
"loss": 0.9209,
|
| 2620 |
+
"step": 1860
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.8558972005507114,
|
| 2624 |
+
"grad_norm": 0.08921313107573868,
|
| 2625 |
+
"learning_rate": 1.2387861354281194e-05,
|
| 2626 |
+
"loss": 0.9459,
|
| 2627 |
+
"step": 1865
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.8581918311151905,
|
| 2631 |
+
"grad_norm": 0.08675456932143413,
|
| 2632 |
+
"learning_rate": 1.2004512966974745e-05,
|
| 2633 |
+
"loss": 0.9341,
|
| 2634 |
+
"step": 1870
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.8604864616796696,
|
| 2638 |
+
"grad_norm": 0.08853376406641464,
|
| 2639 |
+
"learning_rate": 1.162681060268065e-05,
|
| 2640 |
+
"loss": 0.9358,
|
| 2641 |
+
"step": 1875
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.8627810922441487,
|
| 2645 |
+
"grad_norm": 0.08772170537544985,
|
| 2646 |
+
"learning_rate": 1.1254778495780748e-05,
|
| 2647 |
+
"loss": 0.9462,
|
| 2648 |
+
"step": 1880
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.8650757228086278,
|
| 2652 |
+
"grad_norm": 0.087438966238015,
|
| 2653 |
+
"learning_rate": 1.0888440516838373e-05,
|
| 2654 |
+
"loss": 0.9371,
|
| 2655 |
+
"step": 1885
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.867370353373107,
|
| 2659 |
+
"grad_norm": 0.08774570416471039,
|
| 2660 |
+
"learning_rate": 1.0527820171066372e-05,
|
| 2661 |
+
"loss": 0.9616,
|
| 2662 |
+
"step": 1890
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.8696649839375861,
|
| 2666 |
+
"grad_norm": 0.09079641508572181,
|
| 2667 |
+
"learning_rate": 1.0172940596819259e-05,
|
| 2668 |
+
"loss": 0.9203,
|
| 2669 |
+
"step": 1895
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.8719596145020652,
|
| 2673 |
+
"grad_norm": 0.08682703034420731,
|
| 2674 |
+
"learning_rate": 9.823824564108408e-06,
|
| 2675 |
+
"loss": 0.9572,
|
| 2676 |
+
"step": 1900
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.8742542450665443,
|
| 2680 |
+
"grad_norm": 0.08884587029741915,
|
| 2681 |
+
"learning_rate": 9.480494473141188e-06,
|
| 2682 |
+
"loss": 0.9565,
|
| 2683 |
+
"step": 1905
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.8765488756310233,
|
| 2687 |
+
"grad_norm": 0.08810947120591099,
|
| 2688 |
+
"learning_rate": 9.142972352883594e-06,
|
| 2689 |
+
"loss": 0.9452,
|
| 2690 |
+
"step": 1910
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.8788435061955026,
|
| 2694 |
+
"grad_norm": 0.08431726449593704,
|
| 2695 |
+
"learning_rate": 8.811279859646915e-06,
|
| 2696 |
+
"loss": 0.9275,
|
| 2697 |
+
"step": 1915
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.8811381367599816,
|
| 2701 |
+
"grad_norm": 0.08783013214009486,
|
| 2702 |
+
"learning_rate": 8.485438275698154e-06,
|
| 2703 |
+
"loss": 0.9344,
|
| 2704 |
+
"step": 1920
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.8834327673244607,
|
| 2708 |
+
"grad_norm": 0.0877811337071556,
|
| 2709 |
+
"learning_rate": 8.165468507894514e-06,
|
| 2710 |
+
"loss": 0.9422,
|
| 2711 |
+
"step": 1925
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.8857273978889398,
|
| 2715 |
+
"grad_norm": 0.08918928300947922,
|
| 2716 |
+
"learning_rate": 7.851391086341952e-06,
|
| 2717 |
+
"loss": 0.923,
|
| 2718 |
+
"step": 1930
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.888022028453419,
|
| 2722 |
+
"grad_norm": 0.08684462019085216,
|
| 2723 |
+
"learning_rate": 7.543226163077899e-06,
|
| 2724 |
+
"loss": 0.9501,
|
| 2725 |
+
"step": 1935
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.8903166590178981,
|
| 2729 |
+
"grad_norm": 0.08897290874527142,
|
| 2730 |
+
"learning_rate": 7.240993510778305e-06,
|
| 2731 |
+
"loss": 0.9468,
|
| 2732 |
+
"step": 1940
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.8926112895823772,
|
| 2736 |
+
"grad_norm": 0.08848785350377304,
|
| 2737 |
+
"learning_rate": 6.9447125214888835e-06,
|
| 2738 |
+
"loss": 0.9407,
|
| 2739 |
+
"step": 1945
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.8949059201468563,
|
| 2743 |
+
"grad_norm": 0.08850978272970857,
|
| 2744 |
+
"learning_rate": 6.65440220538096e-06,
|
| 2745 |
+
"loss": 0.9467,
|
| 2746 |
+
"step": 1950
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.8972005507113354,
|
| 2750 |
+
"grad_norm": 0.08764525689057708,
|
| 2751 |
+
"learning_rate": 6.370081189531707e-06,
|
| 2752 |
+
"loss": 0.9183,
|
| 2753 |
+
"step": 1955
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.8994951812758146,
|
| 2757 |
+
"grad_norm": 0.09111687142640715,
|
| 2758 |
+
"learning_rate": 6.091767716728924e-06,
|
| 2759 |
+
"loss": 0.9337,
|
| 2760 |
+
"step": 1960
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.9017898118402937,
|
| 2764 |
+
"grad_norm": 0.09082638866765445,
|
| 2765 |
+
"learning_rate": 5.819479644300563e-06,
|
| 2766 |
+
"loss": 0.9311,
|
| 2767 |
+
"step": 1965
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.9040844424047728,
|
| 2771 |
+
"grad_norm": 0.08768468656217991,
|
| 2772 |
+
"learning_rate": 5.553234442969013e-06,
|
| 2773 |
+
"loss": 0.9382,
|
| 2774 |
+
"step": 1970
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.9063790729692519,
|
| 2778 |
+
"grad_norm": 0.08591220062356768,
|
| 2779 |
+
"learning_rate": 5.293049195730038e-06,
|
| 2780 |
+
"loss": 0.9363,
|
| 2781 |
+
"step": 1975
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.9086737035337311,
|
| 2785 |
+
"grad_norm": 0.0892059058046249,
|
| 2786 |
+
"learning_rate": 5.038940596756747e-06,
|
| 2787 |
+
"loss": 0.9562,
|
| 2788 |
+
"step": 1980
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.9109683340982102,
|
| 2792 |
+
"grad_norm": 0.08874849077210194,
|
| 2793 |
+
"learning_rate": 4.790924950328435e-06,
|
| 2794 |
+
"loss": 0.9528,
|
| 2795 |
+
"step": 1985
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.9132629646626893,
|
| 2799 |
+
"grad_norm": 0.08444810522115238,
|
| 2800 |
+
"learning_rate": 4.5490181697844916e-06,
|
| 2801 |
+
"loss": 0.9037,
|
| 2802 |
+
"step": 1990
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.9155575952271684,
|
| 2806 |
+
"grad_norm": 0.0860541394012721,
|
| 2807 |
+
"learning_rate": 4.313235776503244e-06,
|
| 2808 |
+
"loss": 0.9153,
|
| 2809 |
+
"step": 1995
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 0.9178522257916475,
|
| 2813 |
+
"grad_norm": 0.08677442991318424,
|
| 2814 |
+
"learning_rate": 4.08359289890623e-06,
|
| 2815 |
+
"loss": 0.9402,
|
| 2816 |
+
"step": 2000
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 0.9201468563561267,
|
| 2820 |
+
"grad_norm": 0.09013856091786,
|
| 2821 |
+
"learning_rate": 3.860104271487397e-06,
|
| 2822 |
+
"loss": 0.9529,
|
| 2823 |
+
"step": 2005
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 0.9224414869206058,
|
| 2827 |
+
"grad_norm": 0.08509499257002519,
|
| 2828 |
+
"learning_rate": 3.6427842338677352e-06,
|
| 2829 |
+
"loss": 0.9323,
|
| 2830 |
+
"step": 2010
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 0.9247361174850849,
|
| 2834 |
+
"grad_norm": 0.08719834616969914,
|
| 2835 |
+
"learning_rate": 3.4316467298752263e-06,
|
| 2836 |
+
"loss": 0.9392,
|
| 2837 |
+
"step": 2015
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 0.927030748049564,
|
| 2841 |
+
"grad_norm": 0.08697447693662008,
|
| 2842 |
+
"learning_rate": 3.226705306650113e-06,
|
| 2843 |
+
"loss": 0.9446,
|
| 2844 |
+
"step": 2020
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 0.9293253786140432,
|
| 2848 |
+
"grad_norm": 0.08969207347043825,
|
| 2849 |
+
"learning_rate": 3.0279731137757948e-06,
|
| 2850 |
+
"loss": 0.9119,
|
| 2851 |
+
"step": 2025
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 0.9316200091785223,
|
| 2855 |
+
"grad_norm": 0.08694060973009726,
|
| 2856 |
+
"learning_rate": 2.835462902434971e-06,
|
| 2857 |
+
"loss": 0.9081,
|
| 2858 |
+
"step": 2030
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 0.9339146397430014,
|
| 2862 |
+
"grad_norm": 0.08665729431202235,
|
| 2863 |
+
"learning_rate": 2.649187024591604e-06,
|
| 2864 |
+
"loss": 0.9491,
|
| 2865 |
+
"step": 2035
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 0.9362092703074805,
|
| 2869 |
+
"grad_norm": 0.08529555353847522,
|
| 2870 |
+
"learning_rate": 2.4691574321983215e-06,
|
| 2871 |
+
"loss": 0.9545,
|
| 2872 |
+
"step": 2040
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 0.9385039008719596,
|
| 2876 |
+
"grad_norm": 0.08638294723774989,
|
| 2877 |
+
"learning_rate": 2.2953856764295624e-06,
|
| 2878 |
+
"loss": 0.9433,
|
| 2879 |
+
"step": 2045
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 0.9407985314364388,
|
| 2883 |
+
"grad_norm": 0.08509058036503529,
|
| 2884 |
+
"learning_rate": 2.1278829069404484e-06,
|
| 2885 |
+
"loss": 0.8975,
|
| 2886 |
+
"step": 2050
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 0.9430931620009179,
|
| 2890 |
+
"grad_norm": 0.09005898438040956,
|
| 2891 |
+
"learning_rate": 1.966659871151366e-06,
|
| 2892 |
+
"loss": 0.9441,
|
| 2893 |
+
"step": 2055
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 0.945387792565397,
|
| 2897 |
+
"grad_norm": 0.0913580806589797,
|
| 2898 |
+
"learning_rate": 1.811726913558387e-06,
|
| 2899 |
+
"loss": 0.9383,
|
| 2900 |
+
"step": 2060
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 0.947682423129876,
|
| 2904 |
+
"grad_norm": 0.08996121201187086,
|
| 2905 |
+
"learning_rate": 1.6630939750695519e-06,
|
| 2906 |
+
"loss": 0.9266,
|
| 2907 |
+
"step": 2065
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 0.9499770536943553,
|
| 2911 |
+
"grad_norm": 0.08735684631954084,
|
| 2912 |
+
"learning_rate": 1.5207705923670157e-06,
|
| 2913 |
+
"loss": 0.9374,
|
| 2914 |
+
"step": 2070
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 0.9522716842588343,
|
| 2918 |
+
"grad_norm": 0.08782321872428674,
|
| 2919 |
+
"learning_rate": 1.3847658972951483e-06,
|
| 2920 |
+
"loss": 0.9393,
|
| 2921 |
+
"step": 2075
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 0.9545663148233134,
|
| 2925 |
+
"grad_norm": 0.08638359940423465,
|
| 2926 |
+
"learning_rate": 1.2550886162746467e-06,
|
| 2927 |
+
"loss": 0.9542,
|
| 2928 |
+
"step": 2080
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 0.9568609453877925,
|
| 2932 |
+
"grad_norm": 0.08816158923371066,
|
| 2933 |
+
"learning_rate": 1.1317470697425837e-06,
|
| 2934 |
+
"loss": 0.9553,
|
| 2935 |
+
"step": 2085
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 0.9591555759522716,
|
| 2939 |
+
"grad_norm": 0.0869294153247488,
|
| 2940 |
+
"learning_rate": 1.0147491716185676e-06,
|
| 2941 |
+
"loss": 0.9338,
|
| 2942 |
+
"step": 2090
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 0.9614502065167508,
|
| 2946 |
+
"grad_norm": 0.08669044776728387,
|
| 2947 |
+
"learning_rate": 9.04102428796949e-07,
|
| 2948 |
+
"loss": 0.9598,
|
| 2949 |
+
"step": 2095
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 0.9637448370812299,
|
| 2953 |
+
"grad_norm": 0.08623247272425665,
|
| 2954 |
+
"learning_rate": 7.99813940665195e-07,
|
| 2955 |
+
"loss": 0.9373,
|
| 2956 |
+
"step": 2100
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 0.966039467645709,
|
| 2960 |
+
"grad_norm": 0.08874393697081741,
|
| 2961 |
+
"learning_rate": 7.018903986483083e-07,
|
| 2962 |
+
"loss": 0.9415,
|
| 2963 |
+
"step": 2105
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 0.9683340982101881,
|
| 2967 |
+
"grad_norm": 0.08826549132097718,
|
| 2968 |
+
"learning_rate": 6.103380857795604e-07,
|
| 2969 |
+
"loss": 0.9509,
|
| 2970 |
+
"step": 2110
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 0.9706287287746673,
|
| 2974 |
+
"grad_norm": 0.08811680099621978,
|
| 2975 |
+
"learning_rate": 5.251628762972916e-07,
|
| 2976 |
+
"loss": 0.9307,
|
| 2977 |
+
"step": 2115
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 0.9729233593391464,
|
| 2981 |
+
"grad_norm": 0.0855595252734913,
|
| 2982 |
+
"learning_rate": 4.463702352680787e-07,
|
| 2983 |
+
"loss": 0.9272,
|
| 2984 |
+
"step": 2120
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 0.9752179899036255,
|
| 2988 |
+
"grad_norm": 0.086175580567214,
|
| 2989 |
+
"learning_rate": 3.7396521823600537e-07,
|
| 2990 |
+
"loss": 0.9209,
|
| 2991 |
+
"step": 2125
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 0.9775126204681046,
|
| 2995 |
+
"grad_norm": 0.08552971051081726,
|
| 2996 |
+
"learning_rate": 3.079524708983095e-07,
|
| 2997 |
+
"loss": 0.9297,
|
| 2998 |
+
"step": 2130
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 0.9798072510325837,
|
| 3002 |
+
"grad_norm": 0.0887704339359113,
|
| 3003 |
+
"learning_rate": 2.483362288073443e-07,
|
| 3004 |
+
"loss": 0.9283,
|
| 3005 |
+
"step": 2135
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 0.9821018815970629,
|
| 3009 |
+
"grad_norm": 0.08671129007392188,
|
| 3010 |
+
"learning_rate": 1.9512031709874035e-07,
|
| 3011 |
+
"loss": 0.9332,
|
| 3012 |
+
"step": 2140
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 0.984396512161542,
|
| 3016 |
+
"grad_norm": 0.08984732497930137,
|
| 3017 |
+
"learning_rate": 1.4830815024606815e-07,
|
| 3018 |
+
"loss": 0.9247,
|
| 3019 |
+
"step": 2145
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 0.9866911427260211,
|
| 3023 |
+
"grad_norm": 0.0894694714684205,
|
| 3024 |
+
"learning_rate": 1.0790273184164701e-07,
|
| 3025 |
+
"loss": 0.9074,
|
| 3026 |
+
"step": 2150
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 0.9889857732905002,
|
| 3030 |
+
"grad_norm": 0.0890952939852077,
|
| 3031 |
+
"learning_rate": 7.390665440393241e-08,
|
| 3032 |
+
"loss": 0.9366,
|
| 3033 |
+
"step": 2155
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 0.9912804038549794,
|
| 3037 |
+
"grad_norm": 0.08892399654551203,
|
| 3038 |
+
"learning_rate": 4.632209921107134e-08,
|
| 3039 |
+
"loss": 0.9486,
|
| 3040 |
+
"step": 2160
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 0.9935750344194585,
|
| 3044 |
+
"grad_norm": 0.09036079277558923,
|
| 3045 |
+
"learning_rate": 2.5150836161058622e-08,
|
| 3046 |
+
"loss": 0.9386,
|
| 3047 |
+
"step": 2165
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 0.9958696649839376,
|
| 3051 |
+
"grad_norm": 0.0874025371093686,
|
| 3052 |
+
"learning_rate": 1.03942236580723e-08,
|
| 3053 |
+
"loss": 0.9373,
|
| 3054 |
+
"step": 2170
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 0.9981642955484167,
|
| 3058 |
+
"grad_norm": 0.0950153209645722,
|
| 3059 |
+
"learning_rate": 2.053208525365502e-09,
|
| 3060 |
+
"loss": 0.9454,
|
| 3061 |
+
"step": 2175
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 1.0,
|
| 3065 |
+
"eval_loss": 0.943856418132782,
|
| 3066 |
+
"eval_runtime": 822.8687,
|
| 3067 |
+
"eval_samples_per_second": 18.753,
|
| 3068 |
+
"eval_steps_per_second": 0.294,
|
| 3069 |
+
"step": 2179
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 1.0,
|
| 3073 |
+
"step": 2179,
|
| 3074 |
+
"total_flos": 3.4589037545127936e+16,
|
| 3075 |
+
"train_loss": 0.9514529290906111,
|
| 3076 |
+
"train_runtime": 33671.5063,
|
| 3077 |
+
"train_samples_per_second": 4.141,
|
| 3078 |
+
"train_steps_per_second": 0.065
|
| 3079 |
+
}
|
| 3080 |
+
],
|
| 3081 |
+
"logging_steps": 5,
|
| 3082 |
+
"max_steps": 2179,
|
| 3083 |
+
"num_input_tokens_seen": 0,
|
| 3084 |
+
"num_train_epochs": 1,
|
| 3085 |
+
"save_steps": 100,
|
| 3086 |
+
"stateful_callbacks": {
|
| 3087 |
+
"TrainerControl": {
|
| 3088 |
+
"args": {
|
| 3089 |
+
"should_epoch_stop": false,
|
| 3090 |
+
"should_evaluate": false,
|
| 3091 |
+
"should_log": false,
|
| 3092 |
+
"should_save": true,
|
| 3093 |
+
"should_training_stop": false
|
| 3094 |
+
},
|
| 3095 |
+
"attributes": {}
|
| 3096 |
+
}
|
| 3097 |
+
},
|
| 3098 |
+
"total_flos": 3.4589037545127936e+16,
|
| 3099 |
+
"train_batch_size": 8,
|
| 3100 |
+
"trial_name": null,
|
| 3101 |
+
"trial_params": null
|
| 3102 |
+
}
|