Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: llama3.1
|
| 4 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: rearc-20k-ablation
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# rearc-20k-ablation
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0641
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 8
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 128
|
| 48 |
+
- total_eval_batch_size: 32
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: cosine
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
+
- num_epochs: 2
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 0.0841 | 0.9966 | 148 | 0.0852 |
|
| 59 |
+
| 0.0774 | 1.9933 | 296 | 0.0641 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.45.0.dev0
|
| 65 |
+
- Pytorch 2.4.0+cu121
|
| 66 |
+
- Datasets 3.0.1
|
| 67 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9932659932659933,
|
| 3 |
+
"total_flos": 1.5329682729109094e+17,
|
| 4 |
+
"train_loss": 0.098479394486325,
|
| 5 |
+
"train_runtime": 5160.5268,
|
| 6 |
+
"train_samples": 18978,
|
| 7 |
+
"train_samples_per_second": 7.355,
|
| 8 |
+
"train_steps_per_second": 0.057
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.45.0.dev0"
|
| 12 |
+
}
|
runs/Sep27_22-18-21_instance-20240926-032616/events.out.tfevents.1727475763.instance-20240926-032616.3513.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81be2a1b9c56475c309178736f7830133abeae7ea7f01f7534d8ee83b60fa008
|
| 3 |
+
size 68704
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9932659932659933,
|
| 3 |
+
"total_flos": 1.5329682729109094e+17,
|
| 4 |
+
"train_loss": 0.098479394486325,
|
| 5 |
+
"train_runtime": 5160.5268,
|
| 6 |
+
"train_samples": 18978,
|
| 7 |
+
"train_samples_per_second": 7.355,
|
| 8 |
+
"train_steps_per_second": 0.057
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9932659932659933,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 296,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.006734006734006734,
|
| 13 |
+
"grad_norm": 10.587559734000028,
|
| 14 |
+
"learning_rate": 3.3333333333333335e-07,
|
| 15 |
+
"loss": 0.3649,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.013468013468013467,
|
| 20 |
+
"grad_norm": 9.693900007266853,
|
| 21 |
+
"learning_rate": 6.666666666666667e-07,
|
| 22 |
+
"loss": 0.3686,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.020202020202020204,
|
| 27 |
+
"grad_norm": 10.061524524104307,
|
| 28 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 29 |
+
"loss": 0.3574,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.026936026936026935,
|
| 34 |
+
"grad_norm": 8.726573115555482,
|
| 35 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 36 |
+
"loss": 0.3702,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03367003367003367,
|
| 41 |
+
"grad_norm": 7.3549146274711585,
|
| 42 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 43 |
+
"loss": 0.309,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04040404040404041,
|
| 48 |
+
"grad_norm": 8.093966841100372,
|
| 49 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 50 |
+
"loss": 0.3129,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04713804713804714,
|
| 55 |
+
"grad_norm": 4.842714262161294,
|
| 56 |
+
"learning_rate": 2.3333333333333336e-06,
|
| 57 |
+
"loss": 0.2599,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.05387205387205387,
|
| 62 |
+
"grad_norm": 3.6588226035329976,
|
| 63 |
+
"learning_rate": 2.666666666666667e-06,
|
| 64 |
+
"loss": 0.2195,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06060606060606061,
|
| 69 |
+
"grad_norm": 4.446495106085817,
|
| 70 |
+
"learning_rate": 3e-06,
|
| 71 |
+
"loss": 0.2421,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.06734006734006734,
|
| 76 |
+
"grad_norm": 2.8148929686162267,
|
| 77 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 78 |
+
"loss": 0.1974,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.07407407407407407,
|
| 83 |
+
"grad_norm": 3.100744939706759,
|
| 84 |
+
"learning_rate": 3.6666666666666666e-06,
|
| 85 |
+
"loss": 0.226,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.08080808080808081,
|
| 90 |
+
"grad_norm": 5.783874426714631,
|
| 91 |
+
"learning_rate": 4.000000000000001e-06,
|
| 92 |
+
"loss": 0.244,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08754208754208755,
|
| 97 |
+
"grad_norm": 3.931311548892614,
|
| 98 |
+
"learning_rate": 4.333333333333334e-06,
|
| 99 |
+
"loss": 0.2085,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.09427609427609428,
|
| 104 |
+
"grad_norm": 3.160745880374999,
|
| 105 |
+
"learning_rate": 4.666666666666667e-06,
|
| 106 |
+
"loss": 0.193,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.10101010101010101,
|
| 111 |
+
"grad_norm": 2.593859671610231,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.1918,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.10774410774410774,
|
| 118 |
+
"grad_norm": 2.3411274601291923,
|
| 119 |
+
"learning_rate": 5.333333333333334e-06,
|
| 120 |
+
"loss": 0.1658,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.11447811447811448,
|
| 125 |
+
"grad_norm": 2.4713577315394915,
|
| 126 |
+
"learning_rate": 5.666666666666667e-06,
|
| 127 |
+
"loss": 0.1631,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.12121212121212122,
|
| 132 |
+
"grad_norm": 1.7868674672717264,
|
| 133 |
+
"learning_rate": 6e-06,
|
| 134 |
+
"loss": 0.1447,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.12794612794612795,
|
| 139 |
+
"grad_norm": 2.691562015290166,
|
| 140 |
+
"learning_rate": 6.333333333333333e-06,
|
| 141 |
+
"loss": 0.1642,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.13468013468013468,
|
| 146 |
+
"grad_norm": 2.656849943102207,
|
| 147 |
+
"learning_rate": 6.666666666666667e-06,
|
| 148 |
+
"loss": 0.1679,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.1414141414141414,
|
| 153 |
+
"grad_norm": 1.8157646932459017,
|
| 154 |
+
"learning_rate": 7e-06,
|
| 155 |
+
"loss": 0.148,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.14814814814814814,
|
| 160 |
+
"grad_norm": 1.8536112319855758,
|
| 161 |
+
"learning_rate": 7.333333333333333e-06,
|
| 162 |
+
"loss": 0.171,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.15488215488215487,
|
| 167 |
+
"grad_norm": 1.7970217082935407,
|
| 168 |
+
"learning_rate": 7.666666666666667e-06,
|
| 169 |
+
"loss": 0.1543,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.16161616161616163,
|
| 174 |
+
"grad_norm": 1.6194461511446632,
|
| 175 |
+
"learning_rate": 8.000000000000001e-06,
|
| 176 |
+
"loss": 0.1331,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.16835016835016836,
|
| 181 |
+
"grad_norm": 1.6671876155213552,
|
| 182 |
+
"learning_rate": 8.333333333333334e-06,
|
| 183 |
+
"loss": 0.1997,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.1750841750841751,
|
| 188 |
+
"grad_norm": 2.8083673280494987,
|
| 189 |
+
"learning_rate": 8.666666666666668e-06,
|
| 190 |
+
"loss": 0.149,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.18181818181818182,
|
| 195 |
+
"grad_norm": 2.3945625699544983,
|
| 196 |
+
"learning_rate": 9e-06,
|
| 197 |
+
"loss": 0.2017,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.18855218855218855,
|
| 202 |
+
"grad_norm": 2.547483046750297,
|
| 203 |
+
"learning_rate": 9.333333333333334e-06,
|
| 204 |
+
"loss": 0.1948,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19528619528619529,
|
| 209 |
+
"grad_norm": 2.1650784865978103,
|
| 210 |
+
"learning_rate": 9.666666666666667e-06,
|
| 211 |
+
"loss": 0.1371,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.20202020202020202,
|
| 216 |
+
"grad_norm": 3.341335706430969,
|
| 217 |
+
"learning_rate": 1e-05,
|
| 218 |
+
"loss": 0.1475,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.20875420875420875,
|
| 223 |
+
"grad_norm": 3.4978479659224306,
|
| 224 |
+
"learning_rate": 9.999651284354774e-06,
|
| 225 |
+
"loss": 0.1742,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.21548821548821548,
|
| 230 |
+
"grad_norm": 2.8495339317165573,
|
| 231 |
+
"learning_rate": 9.998605186060138e-06,
|
| 232 |
+
"loss": 0.1318,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.2222222222222222,
|
| 237 |
+
"grad_norm": 2.4440237950440045,
|
| 238 |
+
"learning_rate": 9.996861851032426e-06,
|
| 239 |
+
"loss": 0.1636,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.22895622895622897,
|
| 244 |
+
"grad_norm": 2.606759351085706,
|
| 245 |
+
"learning_rate": 9.99442152244292e-06,
|
| 246 |
+
"loss": 0.1655,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.2356902356902357,
|
| 251 |
+
"grad_norm": 2.4143459809986276,
|
| 252 |
+
"learning_rate": 9.991284540683922e-06,
|
| 253 |
+
"loss": 0.1492,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.24242424242424243,
|
| 258 |
+
"grad_norm": 2.2585659926066226,
|
| 259 |
+
"learning_rate": 9.98745134332128e-06,
|
| 260 |
+
"loss": 0.1426,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.24915824915824916,
|
| 265 |
+
"grad_norm": 2.2201124689491434,
|
| 266 |
+
"learning_rate": 9.98292246503335e-06,
|
| 267 |
+
"loss": 0.1692,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.2558922558922559,
|
| 272 |
+
"grad_norm": 1.8870018630441274,
|
| 273 |
+
"learning_rate": 9.97769853753642e-06,
|
| 274 |
+
"loss": 0.1139,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.26262626262626265,
|
| 279 |
+
"grad_norm": 1.571794239015075,
|
| 280 |
+
"learning_rate": 9.971780289496585e-06,
|
| 281 |
+
"loss": 0.1301,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.26936026936026936,
|
| 286 |
+
"grad_norm": 1.8448276378849247,
|
| 287 |
+
"learning_rate": 9.965168546428122e-06,
|
| 288 |
+
"loss": 0.1707,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.2760942760942761,
|
| 293 |
+
"grad_norm": 1.739556757210725,
|
| 294 |
+
"learning_rate": 9.95786423057833e-06,
|
| 295 |
+
"loss": 0.1229,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.2828282828282828,
|
| 300 |
+
"grad_norm": 2.3063563017251667,
|
| 301 |
+
"learning_rate": 9.949868360798893e-06,
|
| 302 |
+
"loss": 0.1528,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.2895622895622896,
|
| 307 |
+
"grad_norm": 1.6568054539708137,
|
| 308 |
+
"learning_rate": 9.941182052403768e-06,
|
| 309 |
+
"loss": 0.1402,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.2962962962962963,
|
| 314 |
+
"grad_norm": 2.4925535277590254,
|
| 315 |
+
"learning_rate": 9.931806517013612e-06,
|
| 316 |
+
"loss": 0.1805,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.30303030303030304,
|
| 321 |
+
"grad_norm": 1.4549013854977153,
|
| 322 |
+
"learning_rate": 9.921743062386773e-06,
|
| 323 |
+
"loss": 0.1167,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.30976430976430974,
|
| 328 |
+
"grad_norm": 1.3094244266752977,
|
| 329 |
+
"learning_rate": 9.910993092236878e-06,
|
| 330 |
+
"loss": 0.125,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3164983164983165,
|
| 335 |
+
"grad_norm": 1.7107110369252345,
|
| 336 |
+
"learning_rate": 9.899558106037039e-06,
|
| 337 |
+
"loss": 0.1509,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.32323232323232326,
|
| 342 |
+
"grad_norm": 1.2447980159357512,
|
| 343 |
+
"learning_rate": 9.887439698810694e-06,
|
| 344 |
+
"loss": 0.1101,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.32996632996632996,
|
| 349 |
+
"grad_norm": 1.4004468828469865,
|
| 350 |
+
"learning_rate": 9.874639560909118e-06,
|
| 351 |
+
"loss": 0.1526,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.3367003367003367,
|
| 356 |
+
"grad_norm": 1.7542103007123673,
|
| 357 |
+
"learning_rate": 9.861159477775653e-06,
|
| 358 |
+
"loss": 0.1446,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.3434343434343434,
|
| 363 |
+
"grad_norm": 1.2222510349896305,
|
| 364 |
+
"learning_rate": 9.847001329696653e-06,
|
| 365 |
+
"loss": 0.118,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.3501683501683502,
|
| 370 |
+
"grad_norm": 1.8427984079271709,
|
| 371 |
+
"learning_rate": 9.832167091539215e-06,
|
| 372 |
+
"loss": 0.142,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.3569023569023569,
|
| 377 |
+
"grad_norm": 2.031779034578671,
|
| 378 |
+
"learning_rate": 9.816658832475709e-06,
|
| 379 |
+
"loss": 0.1314,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.36363636363636365,
|
| 384 |
+
"grad_norm": 1.6115001478932334,
|
| 385 |
+
"learning_rate": 9.800478715695165e-06,
|
| 386 |
+
"loss": 0.1389,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.37037037037037035,
|
| 391 |
+
"grad_norm": 1.3977600344091157,
|
| 392 |
+
"learning_rate": 9.783628998101525e-06,
|
| 393 |
+
"loss": 0.1223,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.3771043771043771,
|
| 398 |
+
"grad_norm": 1.2541929470324433,
|
| 399 |
+
"learning_rate": 9.766112029998847e-06,
|
| 400 |
+
"loss": 0.1188,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3838383838383838,
|
| 405 |
+
"grad_norm": 1.1839769901258788,
|
| 406 |
+
"learning_rate": 9.747930254763467e-06,
|
| 407 |
+
"loss": 0.1445,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.39057239057239057,
|
| 412 |
+
"grad_norm": 2.1758765383002476,
|
| 413 |
+
"learning_rate": 9.729086208503174e-06,
|
| 414 |
+
"loss": 0.1361,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.39730639730639733,
|
| 419 |
+
"grad_norm": 1.308302111463449,
|
| 420 |
+
"learning_rate": 9.70958251970347e-06,
|
| 421 |
+
"loss": 0.1206,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.40404040404040403,
|
| 426 |
+
"grad_norm": 1.2548920096786198,
|
| 427 |
+
"learning_rate": 9.689421908860928e-06,
|
| 428 |
+
"loss": 0.1547,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.4107744107744108,
|
| 433 |
+
"grad_norm": 1.8106730974081224,
|
| 434 |
+
"learning_rate": 9.668607188103708e-06,
|
| 435 |
+
"loss": 0.1739,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.4175084175084175,
|
| 440 |
+
"grad_norm": 1.7503742895673335,
|
| 441 |
+
"learning_rate": 9.64714126079933e-06,
|
| 442 |
+
"loss": 0.126,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.42424242424242425,
|
| 447 |
+
"grad_norm": 1.9002464919585416,
|
| 448 |
+
"learning_rate": 9.625027121149665e-06,
|
| 449 |
+
"loss": 0.1209,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.43097643097643096,
|
| 454 |
+
"grad_norm": 1.3005333196675646,
|
| 455 |
+
"learning_rate": 9.602267853773301e-06,
|
| 456 |
+
"loss": 0.1198,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.4377104377104377,
|
| 461 |
+
"grad_norm": 1.534465904527491,
|
| 462 |
+
"learning_rate": 9.578866633275289e-06,
|
| 463 |
+
"loss": 0.1118,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.4444444444444444,
|
| 468 |
+
"grad_norm": 1.2985721012757516,
|
| 469 |
+
"learning_rate": 9.554826723804304e-06,
|
| 470 |
+
"loss": 0.108,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.4511784511784512,
|
| 475 |
+
"grad_norm": 1.7026939587233383,
|
| 476 |
+
"learning_rate": 9.530151478597366e-06,
|
| 477 |
+
"loss": 0.1229,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.45791245791245794,
|
| 482 |
+
"grad_norm": 1.1948241076690054,
|
| 483 |
+
"learning_rate": 9.504844339512096e-06,
|
| 484 |
+
"loss": 0.1221,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.46464646464646464,
|
| 489 |
+
"grad_norm": 1.4429708012011027,
|
| 490 |
+
"learning_rate": 9.478908836546629e-06,
|
| 491 |
+
"loss": 0.1154,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.4713804713804714,
|
| 496 |
+
"grad_norm": 1.3983865141656082,
|
| 497 |
+
"learning_rate": 9.452348587347224e-06,
|
| 498 |
+
"loss": 0.1024,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.4781144781144781,
|
| 503 |
+
"grad_norm": 1.316559372373498,
|
| 504 |
+
"learning_rate": 9.425167296703655e-06,
|
| 505 |
+
"loss": 0.1299,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.48484848484848486,
|
| 510 |
+
"grad_norm": 0.8721397993491847,
|
| 511 |
+
"learning_rate": 9.397368756032445e-06,
|
| 512 |
+
"loss": 0.0838,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.49158249158249157,
|
| 517 |
+
"grad_norm": 2.3999305030312006,
|
| 518 |
+
"learning_rate": 9.368956842848014e-06,
|
| 519 |
+
"loss": 0.1407,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.4983164983164983,
|
| 524 |
+
"grad_norm": 1.2702381897041746,
|
| 525 |
+
"learning_rate": 9.339935520221816e-06,
|
| 526 |
+
"loss": 0.1185,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.5050505050505051,
|
| 531 |
+
"grad_norm": 1.2224610902674924,
|
| 532 |
+
"learning_rate": 9.310308836229548e-06,
|
| 533 |
+
"loss": 0.1044,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.5117845117845118,
|
| 538 |
+
"grad_norm": 1.0145648591712295,
|
| 539 |
+
"learning_rate": 9.280080923386501e-06,
|
| 540 |
+
"loss": 0.0793,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.5185185185185185,
|
| 545 |
+
"grad_norm": 1.8590770931022098,
|
| 546 |
+
"learning_rate": 9.249255998071127e-06,
|
| 547 |
+
"loss": 0.1218,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.5252525252525253,
|
| 552 |
+
"grad_norm": 1.1046753339013544,
|
| 553 |
+
"learning_rate": 9.217838359936914e-06,
|
| 554 |
+
"loss": 0.0982,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.531986531986532,
|
| 559 |
+
"grad_norm": 1.5353842647876887,
|
| 560 |
+
"learning_rate": 9.185832391312644e-06,
|
| 561 |
+
"loss": 0.0976,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.5387205387205387,
|
| 566 |
+
"grad_norm": 1.6322780255697593,
|
| 567 |
+
"learning_rate": 9.153242556591115e-06,
|
| 568 |
+
"loss": 0.1073,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.5454545454545454,
|
| 573 |
+
"grad_norm": 1.4318238106918786,
|
| 574 |
+
"learning_rate": 9.120073401606427e-06,
|
| 575 |
+
"loss": 0.1535,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.5521885521885522,
|
| 580 |
+
"grad_norm": 1.2692358298751287,
|
| 581 |
+
"learning_rate": 9.08632955299989e-06,
|
| 582 |
+
"loss": 0.1162,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.5589225589225589,
|
| 587 |
+
"grad_norm": 0.9386668388367472,
|
| 588 |
+
"learning_rate": 9.052015717574683e-06,
|
| 589 |
+
"loss": 0.0819,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.5656565656565656,
|
| 594 |
+
"grad_norm": 1.578041471845064,
|
| 595 |
+
"learning_rate": 9.017136681639307e-06,
|
| 596 |
+
"loss": 0.1438,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.5723905723905723,
|
| 601 |
+
"grad_norm": 1.3747097561675499,
|
| 602 |
+
"learning_rate": 8.981697310339972e-06,
|
| 603 |
+
"loss": 0.1129,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.5791245791245792,
|
| 608 |
+
"grad_norm": 1.2857978501576468,
|
| 609 |
+
"learning_rate": 8.94570254698197e-06,
|
| 610 |
+
"loss": 0.1153,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.5858585858585859,
|
| 615 |
+
"grad_norm": 1.1071476461695378,
|
| 616 |
+
"learning_rate": 8.90915741234015e-06,
|
| 617 |
+
"loss": 0.1018,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.5925925925925926,
|
| 622 |
+
"grad_norm": 1.1979772322060398,
|
| 623 |
+
"learning_rate": 8.872067003958597e-06,
|
| 624 |
+
"loss": 0.0939,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5993265993265994,
|
| 629 |
+
"grad_norm": 1.4043079567849108,
|
| 630 |
+
"learning_rate": 8.834436495439588e-06,
|
| 631 |
+
"loss": 0.1022,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.6060606060606061,
|
| 636 |
+
"grad_norm": 1.182762910272131,
|
| 637 |
+
"learning_rate": 8.796271135721944e-06,
|
| 638 |
+
"loss": 0.1099,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.6127946127946128,
|
| 643 |
+
"grad_norm": 0.9919737781684954,
|
| 644 |
+
"learning_rate": 8.757576248348883e-06,
|
| 645 |
+
"loss": 0.101,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.6195286195286195,
|
| 650 |
+
"grad_norm": 1.0613946248613535,
|
| 651 |
+
"learning_rate": 8.71835723072545e-06,
|
| 652 |
+
"loss": 0.1074,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.6262626262626263,
|
| 657 |
+
"grad_norm": 1.1119387505650915,
|
| 658 |
+
"learning_rate": 8.67861955336566e-06,
|
| 659 |
+
"loss": 0.0999,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.632996632996633,
|
| 664 |
+
"grad_norm": 1.0663092046509486,
|
| 665 |
+
"learning_rate": 8.638368759129433e-06,
|
| 666 |
+
"loss": 0.1044,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.6397306397306397,
|
| 671 |
+
"grad_norm": 1.5025873764978885,
|
| 672 |
+
"learning_rate": 8.597610462449441e-06,
|
| 673 |
+
"loss": 0.092,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6464646464646465,
|
| 678 |
+
"grad_norm": 1.1482831508449691,
|
| 679 |
+
"learning_rate": 8.556350348547978e-06,
|
| 680 |
+
"loss": 0.099,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.6531986531986532,
|
| 685 |
+
"grad_norm": 1.1531128286621257,
|
| 686 |
+
"learning_rate": 8.514594172643934e-06,
|
| 687 |
+
"loss": 0.1122,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.6599326599326599,
|
| 692 |
+
"grad_norm": 0.92890945229994,
|
| 693 |
+
"learning_rate": 8.472347759150044e-06,
|
| 694 |
+
"loss": 0.0934,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.6666666666666666,
|
| 699 |
+
"grad_norm": 0.8710829747699658,
|
| 700 |
+
"learning_rate": 8.429617000860441e-06,
|
| 701 |
+
"loss": 0.0963,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.6734006734006734,
|
| 706 |
+
"grad_norm": 1.5913618273955719,
|
| 707 |
+
"learning_rate": 8.386407858128707e-06,
|
| 708 |
+
"loss": 0.1017,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.6801346801346801,
|
| 713 |
+
"grad_norm": 2.0477106016376423,
|
| 714 |
+
"learning_rate": 8.342726358036473e-06,
|
| 715 |
+
"loss": 0.1643,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.6868686868686869,
|
| 720 |
+
"grad_norm": 1.310766070822457,
|
| 721 |
+
"learning_rate": 8.298578593552737e-06,
|
| 722 |
+
"loss": 0.1129,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.6936026936026936,
|
| 727 |
+
"grad_norm": 1.0689180927391349,
|
| 728 |
+
"learning_rate": 8.253970722683968e-06,
|
| 729 |
+
"loss": 0.0805,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.7003367003367004,
|
| 734 |
+
"grad_norm": 1.021500128946588,
|
| 735 |
+
"learning_rate": 8.208908967615159e-06,
|
| 736 |
+
"loss": 0.0854,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.7070707070707071,
|
| 741 |
+
"grad_norm": 1.6146318951430105,
|
| 742 |
+
"learning_rate": 8.163399613841903e-06,
|
| 743 |
+
"loss": 0.1026,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.7138047138047138,
|
| 748 |
+
"grad_norm": 1.0430932372821804,
|
| 749 |
+
"learning_rate": 8.117449009293668e-06,
|
| 750 |
+
"loss": 0.0911,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.7205387205387206,
|
| 755 |
+
"grad_norm": 0.9627471656747238,
|
| 756 |
+
"learning_rate": 8.071063563448341e-06,
|
| 757 |
+
"loss": 0.0864,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.7272727272727273,
|
| 762 |
+
"grad_norm": 0.978325652238678,
|
| 763 |
+
"learning_rate": 8.024249746438189e-06,
|
| 764 |
+
"loss": 0.0767,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.734006734006734,
|
| 769 |
+
"grad_norm": 1.5716697095342131,
|
| 770 |
+
"learning_rate": 7.977014088147375e-06,
|
| 771 |
+
"loss": 0.117,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.7407407407407407,
|
| 776 |
+
"grad_norm": 0.9226258206362579,
|
| 777 |
+
"learning_rate": 7.929363177301124e-06,
|
| 778 |
+
"loss": 0.0898,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.7474747474747475,
|
| 783 |
+
"grad_norm": 0.979018465840073,
|
| 784 |
+
"learning_rate": 7.881303660546684e-06,
|
| 785 |
+
"loss": 0.096,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.7542087542087542,
|
| 790 |
+
"grad_norm": 1.405839836354203,
|
| 791 |
+
"learning_rate": 7.832842241526212e-06,
|
| 792 |
+
"loss": 0.0969,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.7609427609427609,
|
| 797 |
+
"grad_norm": 1.7228913938880963,
|
| 798 |
+
"learning_rate": 7.78398567994171e-06,
|
| 799 |
+
"loss": 0.1229,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.7676767676767676,
|
| 804 |
+
"grad_norm": 1.7211262216477865,
|
| 805 |
+
"learning_rate": 7.734740790612137e-06,
|
| 806 |
+
"loss": 0.1156,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.7744107744107744,
|
| 811 |
+
"grad_norm": 1.1471367685176275,
|
| 812 |
+
"learning_rate": 7.685114442522831e-06,
|
| 813 |
+
"loss": 0.0953,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.7811447811447811,
|
| 818 |
+
"grad_norm": 1.0484067219863682,
|
| 819 |
+
"learning_rate": 7.635113557867395e-06,
|
| 820 |
+
"loss": 0.0957,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.7878787878787878,
|
| 825 |
+
"grad_norm": 1.3643749264979563,
|
| 826 |
+
"learning_rate": 7.584745111082128e-06,
|
| 827 |
+
"loss": 0.0985,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.7946127946127947,
|
| 832 |
+
"grad_norm": 1.1409003431687448,
|
| 833 |
+
"learning_rate": 7.5340161278732e-06,
|
| 834 |
+
"loss": 0.0948,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.8013468013468014,
|
| 839 |
+
"grad_norm": 1.1845755031970973,
|
| 840 |
+
"learning_rate": 7.482933684236654e-06,
|
| 841 |
+
"loss": 0.1278,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.8080808080808081,
|
| 846 |
+
"grad_norm": 1.2048614884456728,
|
| 847 |
+
"learning_rate": 7.431504905471407e-06,
|
| 848 |
+
"loss": 0.0866,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.8148148148148148,
|
| 853 |
+
"grad_norm": 1.1024340198116762,
|
| 854 |
+
"learning_rate": 7.379736965185369e-06,
|
| 855 |
+
"loss": 0.0886,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.8215488215488216,
|
| 860 |
+
"grad_norm": 1.1875877764472678,
|
| 861 |
+
"learning_rate": 7.327637084294818e-06,
|
| 862 |
+
"loss": 0.0876,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.8282828282828283,
|
| 867 |
+
"grad_norm": 0.8892335379224572,
|
| 868 |
+
"learning_rate": 7.2752125300171835e-06,
|
| 869 |
+
"loss": 0.0829,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.835016835016835,
|
| 874 |
+
"grad_norm": 1.1503853071251364,
|
| 875 |
+
"learning_rate": 7.22247061485738e-06,
|
| 876 |
+
"loss": 0.0945,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.8417508417508418,
|
| 881 |
+
"grad_norm": 0.9116461855370438,
|
| 882 |
+
"learning_rate": 7.169418695587791e-06,
|
| 883 |
+
"loss": 0.0642,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.8484848484848485,
|
| 888 |
+
"grad_norm": 0.9169291992757941,
|
| 889 |
+
"learning_rate": 7.1160641722221255e-06,
|
| 890 |
+
"loss": 0.0762,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.8552188552188552,
|
| 895 |
+
"grad_norm": 0.8458786678974077,
|
| 896 |
+
"learning_rate": 7.062414486983197e-06,
|
| 897 |
+
"loss": 0.0782,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.8619528619528619,
|
| 902 |
+
"grad_norm": 2.0440916025334688,
|
| 903 |
+
"learning_rate": 7.008477123264849e-06,
|
| 904 |
+
"loss": 0.1654,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.8686868686868687,
|
| 909 |
+
"grad_norm": 1.2692910029856195,
|
| 910 |
+
"learning_rate": 6.954259604588114e-06,
|
| 911 |
+
"loss": 0.0993,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.8754208754208754,
|
| 916 |
+
"grad_norm": 1.0371836145890874,
|
| 917 |
+
"learning_rate": 6.8997694935518e-06,
|
| 918 |
+
"loss": 0.0792,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.8821548821548821,
|
| 923 |
+
"grad_norm": 0.8129848414149057,
|
| 924 |
+
"learning_rate": 6.845014390777595e-06,
|
| 925 |
+
"loss": 0.0631,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.8888888888888888,
|
| 930 |
+
"grad_norm": 1.0818279823466028,
|
| 931 |
+
"learning_rate": 6.7900019338499005e-06,
|
| 932 |
+
"loss": 0.084,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.8956228956228957,
|
| 937 |
+
"grad_norm": 1.2323415448858157,
|
| 938 |
+
"learning_rate": 6.734739796250477e-06,
|
| 939 |
+
"loss": 0.1037,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.9023569023569024,
|
| 944 |
+
"grad_norm": 0.9072503259074285,
|
| 945 |
+
"learning_rate": 6.6792356862881144e-06,
|
| 946 |
+
"loss": 0.1022,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.9090909090909091,
|
| 951 |
+
"grad_norm": 1.0444248401571283,
|
| 952 |
+
"learning_rate": 6.6234973460234184e-06,
|
| 953 |
+
"loss": 0.0952,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.9158249158249159,
|
| 958 |
+
"grad_norm": 0.7905929983463482,
|
| 959 |
+
"learning_rate": 6.567532550188908e-06,
|
| 960 |
+
"loss": 0.0717,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.9225589225589226,
|
| 965 |
+
"grad_norm": 0.7434134587240314,
|
| 966 |
+
"learning_rate": 6.511349105104534e-06,
|
| 967 |
+
"loss": 0.0944,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.9292929292929293,
|
| 972 |
+
"grad_norm": 0.768332895445934,
|
| 973 |
+
"learning_rate": 6.454954847588824e-06,
|
| 974 |
+
"loss": 0.0678,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.936026936026936,
|
| 979 |
+
"grad_norm": 1.0841144826502787,
|
| 980 |
+
"learning_rate": 6.398357643865731e-06,
|
| 981 |
+
"loss": 0.0845,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.9427609427609428,
|
| 986 |
+
"grad_norm": 1.0657965630616948,
|
| 987 |
+
"learning_rate": 6.341565388467425e-06,
|
| 988 |
+
"loss": 0.0845,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.9494949494949495,
|
| 993 |
+
"grad_norm": 0.7896126816989001,
|
| 994 |
+
"learning_rate": 6.284586003133096e-06,
|
| 995 |
+
"loss": 0.0922,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.9562289562289562,
|
| 1000 |
+
"grad_norm": 1.4442123017819188,
|
| 1001 |
+
"learning_rate": 6.227427435703997e-06,
|
| 1002 |
+
"loss": 0.1182,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.9629629629629629,
|
| 1007 |
+
"grad_norm": 0.9662733291916084,
|
| 1008 |
+
"learning_rate": 6.170097659014812e-06,
|
| 1009 |
+
"loss": 0.0915,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.9696969696969697,
|
| 1014 |
+
"grad_norm": 0.9920505746388618,
|
| 1015 |
+
"learning_rate": 6.112604669781572e-06,
|
| 1016 |
+
"loss": 0.093,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.9764309764309764,
|
| 1021 |
+
"grad_norm": 1.09207653298068,
|
| 1022 |
+
"learning_rate": 6.054956487486212e-06,
|
| 1023 |
+
"loss": 0.0919,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.9831649831649831,
|
| 1028 |
+
"grad_norm": 0.7024022249718929,
|
| 1029 |
+
"learning_rate": 5.997161153257963e-06,
|
| 1030 |
+
"loss": 0.0786,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.98989898989899,
|
| 1035 |
+
"grad_norm": 0.8553768429510301,
|
| 1036 |
+
"learning_rate": 5.939226728751733e-06,
|
| 1037 |
+
"loss": 0.091,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.9966329966329966,
|
| 1042 |
+
"grad_norm": 0.7368165994452094,
|
| 1043 |
+
"learning_rate": 5.88116129502361e-06,
|
| 1044 |
+
"loss": 0.0841,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.9966329966329966,
|
| 1049 |
+
"eval_loss": 0.0851789191365242,
|
| 1050 |
+
"eval_runtime": 74.3023,
|
| 1051 |
+
"eval_samples_per_second": 26.89,
|
| 1052 |
+
"eval_steps_per_second": 0.848,
|
| 1053 |
+
"step": 148
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.0033670033670035,
|
| 1057 |
+
"grad_norm": 1.3624837722625542,
|
| 1058 |
+
"learning_rate": 5.82297295140367e-06,
|
| 1059 |
+
"loss": 0.0942,
|
| 1060 |
+
"step": 149
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.0101010101010102,
|
| 1064 |
+
"grad_norm": 0.8091703688887699,
|
| 1065 |
+
"learning_rate": 5.764669814366231e-06,
|
| 1066 |
+
"loss": 0.0673,
|
| 1067 |
+
"step": 150
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.0168350168350169,
|
| 1071 |
+
"grad_norm": 1.1689964332508505,
|
| 1072 |
+
"learning_rate": 5.70626001639771e-06,
|
| 1073 |
+
"loss": 0.0904,
|
| 1074 |
+
"step": 151
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.0235690235690236,
|
| 1078 |
+
"grad_norm": 0.9720282544537069,
|
| 1079 |
+
"learning_rate": 5.647751704862263e-06,
|
| 1080 |
+
"loss": 0.0764,
|
| 1081 |
+
"step": 152
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.0303030303030303,
|
| 1085 |
+
"grad_norm": 0.7814529677090204,
|
| 1086 |
+
"learning_rate": 5.589153040865333e-06,
|
| 1087 |
+
"loss": 0.0766,
|
| 1088 |
+
"step": 153
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.037037037037037,
|
| 1092 |
+
"grad_norm": 0.6208562049624894,
|
| 1093 |
+
"learning_rate": 5.530472198115291e-06,
|
| 1094 |
+
"loss": 0.0546,
|
| 1095 |
+
"step": 154
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.0437710437710437,
|
| 1099 |
+
"grad_norm": 1.0609611170144315,
|
| 1100 |
+
"learning_rate": 5.471717361783312e-06,
|
| 1101 |
+
"loss": 0.0907,
|
| 1102 |
+
"step": 155
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.0505050505050506,
|
| 1106 |
+
"grad_norm": 0.9895862720799716,
|
| 1107 |
+
"learning_rate": 5.412896727361663e-06,
|
| 1108 |
+
"loss": 0.0756,
|
| 1109 |
+
"step": 156
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.0572390572390573,
|
| 1113 |
+
"grad_norm": 0.8283511990419397,
|
| 1114 |
+
"learning_rate": 5.354018499520536e-06,
|
| 1115 |
+
"loss": 0.0733,
|
| 1116 |
+
"step": 157
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.063973063973064,
|
| 1120 |
+
"grad_norm": 0.7064918637395274,
|
| 1121 |
+
"learning_rate": 5.2950908909636144e-06,
|
| 1122 |
+
"loss": 0.0669,
|
| 1123 |
+
"step": 158
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.0707070707070707,
|
| 1127 |
+
"grad_norm": 0.7673084442281245,
|
| 1128 |
+
"learning_rate": 5.2361221212825175e-06,
|
| 1129 |
+
"loss": 0.063,
|
| 1130 |
+
"step": 159
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.0774410774410774,
|
| 1134 |
+
"grad_norm": 0.7418675838307957,
|
| 1135 |
+
"learning_rate": 5.177120415810271e-06,
|
| 1136 |
+
"loss": 0.0556,
|
| 1137 |
+
"step": 160
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.0841750841750841,
|
| 1141 |
+
"grad_norm": 0.9302869463074369,
|
| 1142 |
+
"learning_rate": 5.11809400447399e-06,
|
| 1143 |
+
"loss": 0.0937,
|
| 1144 |
+
"step": 161
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.0909090909090908,
|
| 1148 |
+
"grad_norm": 1.2470452298913122,
|
| 1149 |
+
"learning_rate": 5.059051120646924e-06,
|
| 1150 |
+
"loss": 0.0827,
|
| 1151 |
+
"step": 162
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.0976430976430978,
|
| 1155 |
+
"grad_norm": 0.5572520947809881,
|
| 1156 |
+
"learning_rate": 5e-06,
|
| 1157 |
+
"loss": 0.0537,
|
| 1158 |
+
"step": 163
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.1043771043771045,
|
| 1162 |
+
"grad_norm": 0.9002485043341543,
|
| 1163 |
+
"learning_rate": 4.940948879353078e-06,
|
| 1164 |
+
"loss": 0.088,
|
| 1165 |
+
"step": 164
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.1111111111111112,
|
| 1169 |
+
"grad_norm": 0.7257311476037439,
|
| 1170 |
+
"learning_rate": 4.8819059955260105e-06,
|
| 1171 |
+
"loss": 0.0531,
|
| 1172 |
+
"step": 165
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.1178451178451179,
|
| 1176 |
+
"grad_norm": 0.7312827459622674,
|
| 1177 |
+
"learning_rate": 4.822879584189732e-06,
|
| 1178 |
+
"loss": 0.0734,
|
| 1179 |
+
"step": 166
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.1245791245791246,
|
| 1183 |
+
"grad_norm": 0.6288896372866642,
|
| 1184 |
+
"learning_rate": 4.763877878717484e-06,
|
| 1185 |
+
"loss": 0.0538,
|
| 1186 |
+
"step": 167
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.1313131313131313,
|
| 1190 |
+
"grad_norm": 1.002048278793203,
|
| 1191 |
+
"learning_rate": 4.704909109036387e-06,
|
| 1192 |
+
"loss": 0.0843,
|
| 1193 |
+
"step": 168
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.138047138047138,
|
| 1197 |
+
"grad_norm": 0.7883344068499383,
|
| 1198 |
+
"learning_rate": 4.645981500479466e-06,
|
| 1199 |
+
"loss": 0.0656,
|
| 1200 |
+
"step": 169
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.144781144781145,
|
| 1204 |
+
"grad_norm": 0.8382010718049546,
|
| 1205 |
+
"learning_rate": 4.587103272638339e-06,
|
| 1206 |
+
"loss": 0.0811,
|
| 1207 |
+
"step": 170
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.1515151515151516,
|
| 1211 |
+
"grad_norm": 0.7760482065843696,
|
| 1212 |
+
"learning_rate": 4.528282638216689e-06,
|
| 1213 |
+
"loss": 0.0504,
|
| 1214 |
+
"step": 171
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.1582491582491583,
|
| 1218 |
+
"grad_norm": 0.7830043876217352,
|
| 1219 |
+
"learning_rate": 4.46952780188471e-06,
|
| 1220 |
+
"loss": 0.0715,
|
| 1221 |
+
"step": 172
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.164983164983165,
|
| 1225 |
+
"grad_norm": 1.0630254048827579,
|
| 1226 |
+
"learning_rate": 4.410846959134667e-06,
|
| 1227 |
+
"loss": 0.0947,
|
| 1228 |
+
"step": 173
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.1717171717171717,
|
| 1232 |
+
"grad_norm": 1.0925071520075709,
|
| 1233 |
+
"learning_rate": 4.352248295137739e-06,
|
| 1234 |
+
"loss": 0.0879,
|
| 1235 |
+
"step": 174
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.1784511784511784,
|
| 1239 |
+
"grad_norm": 0.6169774600371488,
|
| 1240 |
+
"learning_rate": 4.293739983602292e-06,
|
| 1241 |
+
"loss": 0.0611,
|
| 1242 |
+
"step": 175
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.1851851851851851,
|
| 1246 |
+
"grad_norm": 0.9939160789185896,
|
| 1247 |
+
"learning_rate": 4.23533018563377e-06,
|
| 1248 |
+
"loss": 0.0883,
|
| 1249 |
+
"step": 176
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.1919191919191918,
|
| 1253 |
+
"grad_norm": 1.1279865240839675,
|
| 1254 |
+
"learning_rate": 4.17702704859633e-06,
|
| 1255 |
+
"loss": 0.0913,
|
| 1256 |
+
"step": 177
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.1986531986531987,
|
| 1260 |
+
"grad_norm": 0.9240576378263561,
|
| 1261 |
+
"learning_rate": 4.118838704976392e-06,
|
| 1262 |
+
"loss": 0.0766,
|
| 1263 |
+
"step": 178
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.2053872053872055,
|
| 1267 |
+
"grad_norm": 1.2001616277657225,
|
| 1268 |
+
"learning_rate": 4.06077327124827e-06,
|
| 1269 |
+
"loss": 0.1161,
|
| 1270 |
+
"step": 179
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.2121212121212122,
|
| 1274 |
+
"grad_norm": 0.8147954747129799,
|
| 1275 |
+
"learning_rate": 4.002838846742039e-06,
|
| 1276 |
+
"loss": 0.0735,
|
| 1277 |
+
"step": 180
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.2188552188552189,
|
| 1281 |
+
"grad_norm": 0.7054084380327903,
|
| 1282 |
+
"learning_rate": 3.94504351251379e-06,
|
| 1283 |
+
"loss": 0.0594,
|
| 1284 |
+
"step": 181
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.2255892255892256,
|
| 1288 |
+
"grad_norm": 1.1137616381347046,
|
| 1289 |
+
"learning_rate": 3.887395330218429e-06,
|
| 1290 |
+
"loss": 0.1081,
|
| 1291 |
+
"step": 182
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.2323232323232323,
|
| 1295 |
+
"grad_norm": 0.671871366714128,
|
| 1296 |
+
"learning_rate": 3.829902340985189e-06,
|
| 1297 |
+
"loss": 0.0697,
|
| 1298 |
+
"step": 183
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.239057239057239,
|
| 1302 |
+
"grad_norm": 0.7473723466728038,
|
| 1303 |
+
"learning_rate": 3.7725725642960047e-06,
|
| 1304 |
+
"loss": 0.0621,
|
| 1305 |
+
"step": 184
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.2457912457912457,
|
| 1309 |
+
"grad_norm": 0.592505978208727,
|
| 1310 |
+
"learning_rate": 3.7154139968669043e-06,
|
| 1311 |
+
"loss": 0.058,
|
| 1312 |
+
"step": 185
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.2525252525252526,
|
| 1316 |
+
"grad_norm": 0.8357383325436504,
|
| 1317 |
+
"learning_rate": 3.658434611532578e-06,
|
| 1318 |
+
"loss": 0.0637,
|
| 1319 |
+
"step": 186
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.2592592592592593,
|
| 1323 |
+
"grad_norm": 0.7866708646652821,
|
| 1324 |
+
"learning_rate": 3.6016423561342707e-06,
|
| 1325 |
+
"loss": 0.0627,
|
| 1326 |
+
"step": 187
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.265993265993266,
|
| 1330 |
+
"grad_norm": 0.714908923134987,
|
| 1331 |
+
"learning_rate": 3.545045152411178e-06,
|
| 1332 |
+
"loss": 0.0632,
|
| 1333 |
+
"step": 188
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.2727272727272727,
|
| 1337 |
+
"grad_norm": 0.5485873177126037,
|
| 1338 |
+
"learning_rate": 3.4886508948954656e-06,
|
| 1339 |
+
"loss": 0.0599,
|
| 1340 |
+
"step": 189
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.2794612794612794,
|
| 1344 |
+
"grad_norm": 1.09587990802126,
|
| 1345 |
+
"learning_rate": 3.4324674498110956e-06,
|
| 1346 |
+
"loss": 0.0613,
|
| 1347 |
+
"step": 190
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.2861952861952861,
|
| 1351 |
+
"grad_norm": 0.8460192690372663,
|
| 1352 |
+
"learning_rate": 3.3765026539765832e-06,
|
| 1353 |
+
"loss": 0.0847,
|
| 1354 |
+
"step": 191
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.2929292929292928,
|
| 1358 |
+
"grad_norm": 0.7434506857298966,
|
| 1359 |
+
"learning_rate": 3.3207643137118872e-06,
|
| 1360 |
+
"loss": 0.0592,
|
| 1361 |
+
"step": 192
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.2996632996632997,
|
| 1365 |
+
"grad_norm": 0.7460450427195592,
|
| 1366 |
+
"learning_rate": 3.2652602037495247e-06,
|
| 1367 |
+
"loss": 0.0579,
|
| 1368 |
+
"step": 193
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.3063973063973064,
|
| 1372 |
+
"grad_norm": 1.1738509828924104,
|
| 1373 |
+
"learning_rate": 3.2099980661501016e-06,
|
| 1374 |
+
"loss": 0.0788,
|
| 1375 |
+
"step": 194
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.3131313131313131,
|
| 1379 |
+
"grad_norm": 0.8215622674250468,
|
| 1380 |
+
"learning_rate": 3.154985609222405e-06,
|
| 1381 |
+
"loss": 0.0656,
|
| 1382 |
+
"step": 195
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.3198653198653199,
|
| 1386 |
+
"grad_norm": 0.7211793878206931,
|
| 1387 |
+
"learning_rate": 3.1002305064482006e-06,
|
| 1388 |
+
"loss": 0.0643,
|
| 1389 |
+
"step": 196
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.3265993265993266,
|
| 1393 |
+
"grad_norm": 0.975561078244494,
|
| 1394 |
+
"learning_rate": 3.045740395411886e-06,
|
| 1395 |
+
"loss": 0.0671,
|
| 1396 |
+
"step": 197
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.3333333333333333,
|
| 1400 |
+
"grad_norm": 0.5847136475401894,
|
| 1401 |
+
"learning_rate": 2.991522876735154e-06,
|
| 1402 |
+
"loss": 0.0483,
|
| 1403 |
+
"step": 198
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.34006734006734,
|
| 1407 |
+
"grad_norm": 0.7843079810152986,
|
| 1408 |
+
"learning_rate": 2.9375855130168046e-06,
|
| 1409 |
+
"loss": 0.0689,
|
| 1410 |
+
"step": 199
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.3468013468013469,
|
| 1414 |
+
"grad_norm": 0.8005399461255156,
|
| 1415 |
+
"learning_rate": 2.8839358277778758e-06,
|
| 1416 |
+
"loss": 0.0664,
|
| 1417 |
+
"step": 200
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.3535353535353536,
|
| 1421 |
+
"grad_norm": 0.6772138624158527,
|
| 1422 |
+
"learning_rate": 2.83058130441221e-06,
|
| 1423 |
+
"loss": 0.0615,
|
| 1424 |
+
"step": 201
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.3602693602693603,
|
| 1428 |
+
"grad_norm": 0.7191213036719818,
|
| 1429 |
+
"learning_rate": 2.7775293851426233e-06,
|
| 1430 |
+
"loss": 0.0774,
|
| 1431 |
+
"step": 202
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.367003367003367,
|
| 1435 |
+
"grad_norm": 0.7605152392156752,
|
| 1436 |
+
"learning_rate": 2.7247874699828186e-06,
|
| 1437 |
+
"loss": 0.0928,
|
| 1438 |
+
"step": 203
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.3737373737373737,
|
| 1442 |
+
"grad_norm": 0.6195090121798972,
|
| 1443 |
+
"learning_rate": 2.6723629157051844e-06,
|
| 1444 |
+
"loss": 0.0596,
|
| 1445 |
+
"step": 204
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.3804713804713804,
|
| 1449 |
+
"grad_norm": 0.6643501098994239,
|
| 1450 |
+
"learning_rate": 2.6202630348146323e-06,
|
| 1451 |
+
"loss": 0.0523,
|
| 1452 |
+
"step": 205
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.387205387205387,
|
| 1456 |
+
"grad_norm": 0.8554198672675404,
|
| 1457 |
+
"learning_rate": 2.5684950945285937e-06,
|
| 1458 |
+
"loss": 0.0903,
|
| 1459 |
+
"step": 206
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.393939393939394,
|
| 1463 |
+
"grad_norm": 0.8364523777121037,
|
| 1464 |
+
"learning_rate": 2.517066315763348e-06,
|
| 1465 |
+
"loss": 0.0758,
|
| 1466 |
+
"step": 207
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.4006734006734007,
|
| 1470 |
+
"grad_norm": 0.7135150317434039,
|
| 1471 |
+
"learning_rate": 2.4659838721268005e-06,
|
| 1472 |
+
"loss": 0.0603,
|
| 1473 |
+
"step": 208
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.4074074074074074,
|
| 1477 |
+
"grad_norm": 0.6321370814051162,
|
| 1478 |
+
"learning_rate": 2.4152548889178722e-06,
|
| 1479 |
+
"loss": 0.093,
|
| 1480 |
+
"step": 209
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.4141414141414141,
|
| 1484 |
+
"grad_norm": 0.600961736861407,
|
| 1485 |
+
"learning_rate": 2.364886442132606e-06,
|
| 1486 |
+
"loss": 0.0443,
|
| 1487 |
+
"step": 210
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.4208754208754208,
|
| 1491 |
+
"grad_norm": 0.9011898089044157,
|
| 1492 |
+
"learning_rate": 2.3148855574771706e-06,
|
| 1493 |
+
"loss": 0.0713,
|
| 1494 |
+
"step": 211
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.4276094276094276,
|
| 1498 |
+
"grad_norm": 0.572568082620369,
|
| 1499 |
+
"learning_rate": 2.265259209387867e-06,
|
| 1500 |
+
"loss": 0.0567,
|
| 1501 |
+
"step": 212
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.4343434343434343,
|
| 1505 |
+
"grad_norm": 0.5810025449791688,
|
| 1506 |
+
"learning_rate": 2.2160143200582906e-06,
|
| 1507 |
+
"loss": 0.0561,
|
| 1508 |
+
"step": 213
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.4410774410774412,
|
| 1512 |
+
"grad_norm": 0.5830304960007473,
|
| 1513 |
+
"learning_rate": 2.16715775847379e-06,
|
| 1514 |
+
"loss": 0.048,
|
| 1515 |
+
"step": 214
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.4478114478114479,
|
| 1519 |
+
"grad_norm": 0.6676748383092154,
|
| 1520 |
+
"learning_rate": 2.1186963394533165e-06,
|
| 1521 |
+
"loss": 0.0593,
|
| 1522 |
+
"step": 215
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.4545454545454546,
|
| 1526 |
+
"grad_norm": 0.6977658852399721,
|
| 1527 |
+
"learning_rate": 2.0706368226988772e-06,
|
| 1528 |
+
"loss": 0.0594,
|
| 1529 |
+
"step": 216
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.4612794612794613,
|
| 1533 |
+
"grad_norm": 0.506749158721991,
|
| 1534 |
+
"learning_rate": 2.0229859118526244e-06,
|
| 1535 |
+
"loss": 0.0556,
|
| 1536 |
+
"step": 217
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.468013468013468,
|
| 1540 |
+
"grad_norm": 0.7142907436715384,
|
| 1541 |
+
"learning_rate": 1.9757502535618137e-06,
|
| 1542 |
+
"loss": 0.0524,
|
| 1543 |
+
"step": 218
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.4747474747474747,
|
| 1547 |
+
"grad_norm": 0.6949958378386697,
|
| 1548 |
+
"learning_rate": 1.928936436551661e-06,
|
| 1549 |
+
"loss": 0.0666,
|
| 1550 |
+
"step": 219
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.4814814814814814,
|
| 1554 |
+
"grad_norm": 0.7555665471689874,
|
| 1555 |
+
"learning_rate": 1.8825509907063328e-06,
|
| 1556 |
+
"loss": 0.0716,
|
| 1557 |
+
"step": 220
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.4882154882154883,
|
| 1561 |
+
"grad_norm": 0.8498899722890332,
|
| 1562 |
+
"learning_rate": 1.8366003861580966e-06,
|
| 1563 |
+
"loss": 0.0521,
|
| 1564 |
+
"step": 221
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.494949494949495,
|
| 1568 |
+
"grad_norm": 0.7857371564300432,
|
| 1569 |
+
"learning_rate": 1.7910910323848435e-06,
|
| 1570 |
+
"loss": 0.0523,
|
| 1571 |
+
"step": 222
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.5016835016835017,
|
| 1575 |
+
"grad_norm": 0.6313660611784068,
|
| 1576 |
+
"learning_rate": 1.7460292773160315e-06,
|
| 1577 |
+
"loss": 0.0485,
|
| 1578 |
+
"step": 223
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.5084175084175084,
|
| 1582 |
+
"grad_norm": 0.790847117411599,
|
| 1583 |
+
"learning_rate": 1.7014214064472646e-06,
|
| 1584 |
+
"loss": 0.0808,
|
| 1585 |
+
"step": 224
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.5151515151515151,
|
| 1589 |
+
"grad_norm": 1.1225175609085682,
|
| 1590 |
+
"learning_rate": 1.6572736419635288e-06,
|
| 1591 |
+
"loss": 0.0875,
|
| 1592 |
+
"step": 225
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.5218855218855218,
|
| 1596 |
+
"grad_norm": 0.8723669974198242,
|
| 1597 |
+
"learning_rate": 1.6135921418712959e-06,
|
| 1598 |
+
"loss": 0.0614,
|
| 1599 |
+
"step": 226
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.5286195286195285,
|
| 1603 |
+
"grad_norm": 0.5803673000386498,
|
| 1604 |
+
"learning_rate": 1.5703829991395602e-06,
|
| 1605 |
+
"loss": 0.0521,
|
| 1606 |
+
"step": 227
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.5353535353535355,
|
| 1610 |
+
"grad_norm": 0.5913655803974819,
|
| 1611 |
+
"learning_rate": 1.5276522408499567e-06,
|
| 1612 |
+
"loss": 0.0567,
|
| 1613 |
+
"step": 228
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.542087542087542,
|
| 1617 |
+
"grad_norm": 0.5913682879212468,
|
| 1618 |
+
"learning_rate": 1.4854058273560667e-06,
|
| 1619 |
+
"loss": 0.0575,
|
| 1620 |
+
"step": 229
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.5488215488215489,
|
| 1624 |
+
"grad_norm": 0.6925238047248119,
|
| 1625 |
+
"learning_rate": 1.4436496514520253e-06,
|
| 1626 |
+
"loss": 0.0582,
|
| 1627 |
+
"step": 230
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.5555555555555556,
|
| 1631 |
+
"grad_norm": 0.6395725970290016,
|
| 1632 |
+
"learning_rate": 1.4023895375505608e-06,
|
| 1633 |
+
"loss": 0.0605,
|
| 1634 |
+
"step": 231
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.5622895622895623,
|
| 1638 |
+
"grad_norm": 0.5799228625915099,
|
| 1639 |
+
"learning_rate": 1.361631240870569e-06,
|
| 1640 |
+
"loss": 0.0572,
|
| 1641 |
+
"step": 232
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.569023569023569,
|
| 1645 |
+
"grad_norm": 1.1307976257157992,
|
| 1646 |
+
"learning_rate": 1.321380446634342e-06,
|
| 1647 |
+
"loss": 0.0683,
|
| 1648 |
+
"step": 233
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.5757575757575757,
|
| 1652 |
+
"grad_norm": 0.53126448503362,
|
| 1653 |
+
"learning_rate": 1.281642769274552e-06,
|
| 1654 |
+
"loss": 0.044,
|
| 1655 |
+
"step": 234
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.5824915824915826,
|
| 1659 |
+
"grad_norm": 0.5123950135517319,
|
| 1660 |
+
"learning_rate": 1.242423751651119e-06,
|
| 1661 |
+
"loss": 0.0804,
|
| 1662 |
+
"step": 235
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.589225589225589,
|
| 1666 |
+
"grad_norm": 0.6099923775928446,
|
| 1667 |
+
"learning_rate": 1.2037288642780575e-06,
|
| 1668 |
+
"loss": 0.0408,
|
| 1669 |
+
"step": 236
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.595959595959596,
|
| 1673 |
+
"grad_norm": 0.6248835012817582,
|
| 1674 |
+
"learning_rate": 1.165563504560413e-06,
|
| 1675 |
+
"loss": 0.0544,
|
| 1676 |
+
"step": 237
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.6026936026936027,
|
| 1680 |
+
"grad_norm": 0.6510387000168023,
|
| 1681 |
+
"learning_rate": 1.1279329960414047e-06,
|
| 1682 |
+
"loss": 0.0815,
|
| 1683 |
+
"step": 238
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.6094276094276094,
|
| 1687 |
+
"grad_norm": 0.6393553382001962,
|
| 1688 |
+
"learning_rate": 1.0908425876598512e-06,
|
| 1689 |
+
"loss": 0.0538,
|
| 1690 |
+
"step": 239
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.6161616161616161,
|
| 1694 |
+
"grad_norm": 0.5759287160512089,
|
| 1695 |
+
"learning_rate": 1.0542974530180327e-06,
|
| 1696 |
+
"loss": 0.0574,
|
| 1697 |
+
"step": 240
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.6228956228956228,
|
| 1701 |
+
"grad_norm": 0.7684356456332082,
|
| 1702 |
+
"learning_rate": 1.0183026896600284e-06,
|
| 1703 |
+
"loss": 0.0704,
|
| 1704 |
+
"step": 241
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.6296296296296298,
|
| 1708 |
+
"grad_norm": 0.7092834204839467,
|
| 1709 |
+
"learning_rate": 9.82863318360695e-07,
|
| 1710 |
+
"loss": 0.0688,
|
| 1711 |
+
"step": 242
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.6363636363636362,
|
| 1715 |
+
"grad_norm": 0.8525774187670475,
|
| 1716 |
+
"learning_rate": 9.479842824253182e-07,
|
| 1717 |
+
"loss": 0.058,
|
| 1718 |
+
"step": 243
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.6430976430976432,
|
| 1722 |
+
"grad_norm": 0.494283557256197,
|
| 1723 |
+
"learning_rate": 9.136704470001101e-07,
|
| 1724 |
+
"loss": 0.0455,
|
| 1725 |
+
"step": 244
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.6498316498316499,
|
| 1729 |
+
"grad_norm": 0.5072796987904575,
|
| 1730 |
+
"learning_rate": 8.799265983935734e-07,
|
| 1731 |
+
"loss": 0.0573,
|
| 1732 |
+
"step": 245
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.6565656565656566,
|
| 1736 |
+
"grad_norm": 0.6544970574576625,
|
| 1737 |
+
"learning_rate": 8.46757443408886e-07,
|
| 1738 |
+
"loss": 0.0606,
|
| 1739 |
+
"step": 246
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.6632996632996633,
|
| 1743 |
+
"grad_norm": 0.5325045241743026,
|
| 1744 |
+
"learning_rate": 8.141676086873574e-07,
|
| 1745 |
+
"loss": 0.0476,
|
| 1746 |
+
"step": 247
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.67003367003367,
|
| 1750 |
+
"grad_norm": 0.571954858670152,
|
| 1751 |
+
"learning_rate": 7.821616400630866e-07,
|
| 1752 |
+
"loss": 0.0553,
|
| 1753 |
+
"step": 248
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.676767676767677,
|
| 1757 |
+
"grad_norm": 0.7124362240685431,
|
| 1758 |
+
"learning_rate": 7.507440019288742e-07,
|
| 1759 |
+
"loss": 0.0648,
|
| 1760 |
+
"step": 249
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.6835016835016834,
|
| 1764 |
+
"grad_norm": 0.8074026482316966,
|
| 1765 |
+
"learning_rate": 7.199190766135001e-07,
|
| 1766 |
+
"loss": 0.0677,
|
| 1767 |
+
"step": 250
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.6902356902356903,
|
| 1771 |
+
"grad_norm": 0.49821428047955796,
|
| 1772 |
+
"learning_rate": 6.896911637704534e-07,
|
| 1773 |
+
"loss": 0.0414,
|
| 1774 |
+
"step": 251
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.696969696969697,
|
| 1778 |
+
"grad_norm": 0.6996554021349439,
|
| 1779 |
+
"learning_rate": 6.600644797781847e-07,
|
| 1780 |
+
"loss": 0.0666,
|
| 1781 |
+
"step": 252
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.7037037037037037,
|
| 1785 |
+
"grad_norm": 0.5640914695952624,
|
| 1786 |
+
"learning_rate": 6.310431571519865e-07,
|
| 1787 |
+
"loss": 0.076,
|
| 1788 |
+
"step": 253
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.7104377104377104,
|
| 1792 |
+
"grad_norm": 0.5394553999404826,
|
| 1793 |
+
"learning_rate": 6.026312439675553e-07,
|
| 1794 |
+
"loss": 0.0498,
|
| 1795 |
+
"step": 254
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.7171717171717171,
|
| 1799 |
+
"grad_norm": 0.47737348342117025,
|
| 1800 |
+
"learning_rate": 5.748327032963464e-07,
|
| 1801 |
+
"loss": 0.0446,
|
| 1802 |
+
"step": 255
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.723905723905724,
|
| 1806 |
+
"grad_norm": 0.5870399819271779,
|
| 1807 |
+
"learning_rate": 5.476514126527771e-07,
|
| 1808 |
+
"loss": 0.085,
|
| 1809 |
+
"step": 256
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.7306397306397305,
|
| 1813 |
+
"grad_norm": 0.6059552958362416,
|
| 1814 |
+
"learning_rate": 5.210911634533722e-07,
|
| 1815 |
+
"loss": 0.0628,
|
| 1816 |
+
"step": 257
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.7373737373737375,
|
| 1820 |
+
"grad_norm": 0.4612493978879547,
|
| 1821 |
+
"learning_rate": 4.951556604879049e-07,
|
| 1822 |
+
"loss": 0.045,
|
| 1823 |
+
"step": 258
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.7441077441077442,
|
| 1827 |
+
"grad_norm": 0.9732831834165256,
|
| 1828 |
+
"learning_rate": 4.698485214026349e-07,
|
| 1829 |
+
"loss": 0.0719,
|
| 1830 |
+
"step": 259
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.7508417508417509,
|
| 1834 |
+
"grad_norm": 0.7084062235433236,
|
| 1835 |
+
"learning_rate": 4.4517327619569784e-07,
|
| 1836 |
+
"loss": 0.0451,
|
| 1837 |
+
"step": 260
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.7575757575757576,
|
| 1841 |
+
"grad_norm": 0.5150893466864267,
|
| 1842 |
+
"learning_rate": 4.211333667247125e-07,
|
| 1843 |
+
"loss": 0.054,
|
| 1844 |
+
"step": 261
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.7643097643097643,
|
| 1848 |
+
"grad_norm": 0.7197694152938333,
|
| 1849 |
+
"learning_rate": 3.9773214622669974e-07,
|
| 1850 |
+
"loss": 0.0528,
|
| 1851 |
+
"step": 262
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.7710437710437712,
|
| 1855 |
+
"grad_norm": 0.7937673202702573,
|
| 1856 |
+
"learning_rate": 3.7497287885033763e-07,
|
| 1857 |
+
"loss": 0.0551,
|
| 1858 |
+
"step": 263
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.7777777777777777,
|
| 1862 |
+
"grad_norm": 0.7807725839915187,
|
| 1863 |
+
"learning_rate": 3.528587392006716e-07,
|
| 1864 |
+
"loss": 0.0503,
|
| 1865 |
+
"step": 264
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.7845117845117846,
|
| 1869 |
+
"grad_norm": 0.5505115937056173,
|
| 1870 |
+
"learning_rate": 3.313928118962906e-07,
|
| 1871 |
+
"loss": 0.0623,
|
| 1872 |
+
"step": 265
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.791245791245791,
|
| 1876 |
+
"grad_norm": 0.6073147135377622,
|
| 1877 |
+
"learning_rate": 3.105780911390738e-07,
|
| 1878 |
+
"loss": 0.0674,
|
| 1879 |
+
"step": 266
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.797979797979798,
|
| 1883 |
+
"grad_norm": 0.4386889000592362,
|
| 1884 |
+
"learning_rate": 2.904174802965293e-07,
|
| 1885 |
+
"loss": 0.0337,
|
| 1886 |
+
"step": 267
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.8047138047138047,
|
| 1890 |
+
"grad_norm": 0.5371720109059138,
|
| 1891 |
+
"learning_rate": 2.7091379149682683e-07,
|
| 1892 |
+
"loss": 0.056,
|
| 1893 |
+
"step": 268
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.8114478114478114,
|
| 1897 |
+
"grad_norm": 0.4897357275916543,
|
| 1898 |
+
"learning_rate": 2.520697452365345e-07,
|
| 1899 |
+
"loss": 0.0442,
|
| 1900 |
+
"step": 269
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.8181818181818183,
|
| 1904 |
+
"grad_norm": 0.6143440216760881,
|
| 1905 |
+
"learning_rate": 2.3388797000115427e-07,
|
| 1906 |
+
"loss": 0.0644,
|
| 1907 |
+
"step": 270
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 1.8249158249158248,
|
| 1911 |
+
"grad_norm": 0.6184051449052006,
|
| 1912 |
+
"learning_rate": 2.163710018984766e-07,
|
| 1913 |
+
"loss": 0.0494,
|
| 1914 |
+
"step": 271
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.8316498316498318,
|
| 1918 |
+
"grad_norm": 0.5174263740286721,
|
| 1919 |
+
"learning_rate": 1.9952128430483718e-07,
|
| 1920 |
+
"loss": 0.0733,
|
| 1921 |
+
"step": 272
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.8383838383838382,
|
| 1925 |
+
"grad_norm": 0.5711547890486989,
|
| 1926 |
+
"learning_rate": 1.8334116752429243e-07,
|
| 1927 |
+
"loss": 0.0546,
|
| 1928 |
+
"step": 273
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.8451178451178452,
|
| 1932 |
+
"grad_norm": 0.543912361463854,
|
| 1933 |
+
"learning_rate": 1.6783290846078714e-07,
|
| 1934 |
+
"loss": 0.0467,
|
| 1935 |
+
"step": 274
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.8518518518518519,
|
| 1939 |
+
"grad_norm": 0.6068680622136619,
|
| 1940 |
+
"learning_rate": 1.5299867030334815e-07,
|
| 1941 |
+
"loss": 0.0569,
|
| 1942 |
+
"step": 275
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.8585858585858586,
|
| 1946 |
+
"grad_norm": 0.5927823999637648,
|
| 1947 |
+
"learning_rate": 1.388405222243472e-07,
|
| 1948 |
+
"loss": 0.0533,
|
| 1949 |
+
"step": 276
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.8653198653198653,
|
| 1953 |
+
"grad_norm": 0.47694438499884656,
|
| 1954 |
+
"learning_rate": 1.253604390908819e-07,
|
| 1955 |
+
"loss": 0.0564,
|
| 1956 |
+
"step": 277
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.872053872053872,
|
| 1960 |
+
"grad_norm": 0.5019664348313649,
|
| 1961 |
+
"learning_rate": 1.1256030118930727e-07,
|
| 1962 |
+
"loss": 0.0421,
|
| 1963 |
+
"step": 278
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 1.878787878787879,
|
| 1967 |
+
"grad_norm": 0.5244072558220748,
|
| 1968 |
+
"learning_rate": 1.0044189396296144e-07,
|
| 1969 |
+
"loss": 0.0443,
|
| 1970 |
+
"step": 279
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.8855218855218854,
|
| 1974 |
+
"grad_norm": 0.5694979771175117,
|
| 1975 |
+
"learning_rate": 8.900690776312282e-08,
|
| 1976 |
+
"loss": 0.0519,
|
| 1977 |
+
"step": 280
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.8922558922558923,
|
| 1981 |
+
"grad_norm": 0.5383345898694687,
|
| 1982 |
+
"learning_rate": 7.825693761322861e-08,
|
| 1983 |
+
"loss": 0.0645,
|
| 1984 |
+
"step": 281
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 1.898989898989899,
|
| 1988 |
+
"grad_norm": 0.58996301402648,
|
| 1989 |
+
"learning_rate": 6.819348298638839e-08,
|
| 1990 |
+
"loss": 0.0534,
|
| 1991 |
+
"step": 282
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.9057239057239057,
|
| 1995 |
+
"grad_norm": 0.4519126591505613,
|
| 1996 |
+
"learning_rate": 5.881794759623194e-08,
|
| 1997 |
+
"loss": 0.0397,
|
| 1998 |
+
"step": 283
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 1.9124579124579124,
|
| 2002 |
+
"grad_norm": 0.459397062343545,
|
| 2003 |
+
"learning_rate": 5.013163920110864e-08,
|
| 2004 |
+
"loss": 0.0562,
|
| 2005 |
+
"step": 284
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 1.9191919191919191,
|
| 2009 |
+
"grad_norm": 0.6692683465122977,
|
| 2010 |
+
"learning_rate": 4.21357694216723e-08,
|
| 2011 |
+
"loss": 0.0536,
|
| 2012 |
+
"step": 285
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.925925925925926,
|
| 2016 |
+
"grad_norm": 0.5515458851174179,
|
| 2017 |
+
"learning_rate": 3.483145357187967e-08,
|
| 2018 |
+
"loss": 0.0709,
|
| 2019 |
+
"step": 286
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.9326599326599325,
|
| 2023 |
+
"grad_norm": 0.7465197849269988,
|
| 2024 |
+
"learning_rate": 2.8219710503416543e-08,
|
| 2025 |
+
"loss": 0.0656,
|
| 2026 |
+
"step": 287
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.9393939393939394,
|
| 2030 |
+
"grad_norm": 0.5871951635424402,
|
| 2031 |
+
"learning_rate": 2.230146246358256e-08,
|
| 2032 |
+
"loss": 0.0667,
|
| 2033 |
+
"step": 288
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.9461279461279462,
|
| 2037 |
+
"grad_norm": 0.4842964057678575,
|
| 2038 |
+
"learning_rate": 1.7077534966650767e-08,
|
| 2039 |
+
"loss": 0.0408,
|
| 2040 |
+
"step": 289
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.9528619528619529,
|
| 2044 |
+
"grad_norm": 0.5849783564235355,
|
| 2045 |
+
"learning_rate": 1.2548656678721404e-08,
|
| 2046 |
+
"loss": 0.067,
|
| 2047 |
+
"step": 290
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.9595959595959596,
|
| 2051 |
+
"grad_norm": 0.6264347265804303,
|
| 2052 |
+
"learning_rate": 8.715459316078756e-09,
|
| 2053 |
+
"loss": 0.0492,
|
| 2054 |
+
"step": 291
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 1.9663299663299663,
|
| 2058 |
+
"grad_norm": 0.5290968473577989,
|
| 2059 |
+
"learning_rate": 5.578477557081074e-09,
|
| 2060 |
+
"loss": 0.0543,
|
| 2061 |
+
"step": 292
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.9730639730639732,
|
| 2065 |
+
"grad_norm": 0.4771694715604212,
|
| 2066 |
+
"learning_rate": 3.1381489675746946e-09,
|
| 2067 |
+
"loss": 0.0419,
|
| 2068 |
+
"step": 293
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 1.9797979797979797,
|
| 2072 |
+
"grad_norm": 0.7387620656079369,
|
| 2073 |
+
"learning_rate": 1.3948139398628492e-09,
|
| 2074 |
+
"loss": 0.0613,
|
| 2075 |
+
"step": 294
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 1.9865319865319866,
|
| 2079 |
+
"grad_norm": 0.5259388355087269,
|
| 2080 |
+
"learning_rate": 3.487156452258722e-10,
|
| 2081 |
+
"loss": 0.0405,
|
| 2082 |
+
"step": 295
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.9932659932659933,
|
| 2086 |
+
"grad_norm": 0.7981313513015809,
|
| 2087 |
+
"learning_rate": 0.0,
|
| 2088 |
+
"loss": 0.0774,
|
| 2089 |
+
"step": 296
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.9932659932659933,
|
| 2093 |
+
"eval_loss": 0.06412597745656967,
|
| 2094 |
+
"eval_runtime": 70.2541,
|
| 2095 |
+
"eval_samples_per_second": 28.44,
|
| 2096 |
+
"eval_steps_per_second": 0.897,
|
| 2097 |
+
"step": 296
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 1.9932659932659933,
|
| 2101 |
+
"step": 296,
|
| 2102 |
+
"total_flos": 1.5329682729109094e+17,
|
| 2103 |
+
"train_loss": 0.098479394486325,
|
| 2104 |
+
"train_runtime": 5160.5268,
|
| 2105 |
+
"train_samples_per_second": 7.355,
|
| 2106 |
+
"train_steps_per_second": 0.057
|
| 2107 |
+
}
|
| 2108 |
+
],
|
| 2109 |
+
"logging_steps": 1,
|
| 2110 |
+
"max_steps": 296,
|
| 2111 |
+
"num_input_tokens_seen": 0,
|
| 2112 |
+
"num_train_epochs": 2,
|
| 2113 |
+
"save_steps": 500,
|
| 2114 |
+
"stateful_callbacks": {
|
| 2115 |
+
"TrainerControl": {
|
| 2116 |
+
"args": {
|
| 2117 |
+
"should_epoch_stop": false,
|
| 2118 |
+
"should_evaluate": false,
|
| 2119 |
+
"should_log": false,
|
| 2120 |
+
"should_save": true,
|
| 2121 |
+
"should_training_stop": true
|
| 2122 |
+
},
|
| 2123 |
+
"attributes": {}
|
| 2124 |
+
}
|
| 2125 |
+
},
|
| 2126 |
+
"total_flos": 1.5329682729109094e+17,
|
| 2127 |
+
"train_batch_size": 8,
|
| 2128 |
+
"trial_name": null,
|
| 2129 |
+
"trial_params": null
|
| 2130 |
+
}
|