Model save
Browse files- README.md +69 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1380 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: meta-llama/Meta-Llama-3-8B
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: downstream-7b
|
| 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 |
+
# downstream-7b
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.0792
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 1
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 4
|
| 48 |
+
- gradient_accumulation_steps: 4
|
| 49 |
+
- total_train_batch_size: 64
|
| 50 |
+
- total_eval_batch_size: 4
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 1
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 60 |
+
| 1.0709 | 0.9992 | 949 | 1.0792 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.11.1
|
| 66 |
+
- Transformers 4.43.4
|
| 67 |
+
- Pytorch 2.3.1+cu121
|
| 68 |
+
- Datasets 2.19.1
|
| 69 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9992103185048697,
|
| 3 |
+
"total_flos": 1959448100732928.0,
|
| 4 |
+
"train_loss": 1.0930153100081064,
|
| 5 |
+
"train_runtime": 22340.3866,
|
| 6 |
+
"train_samples": 103932,
|
| 7 |
+
"train_samples_per_second": 2.72,
|
| 8 |
+
"train_steps_per_second": 0.042
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9992103185048697,
|
| 3 |
+
"total_flos": 1959448100732928.0,
|
| 4 |
+
"train_loss": 1.0930153100081064,
|
| 5 |
+
"train_runtime": 22340.3866,
|
| 6 |
+
"train_samples": 103932,
|
| 7 |
+
"train_samples_per_second": 2.72,
|
| 8 |
+
"train_steps_per_second": 0.042
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1380 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9992103185048697,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 949,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0010529086601737299,
|
| 13 |
+
"grad_norm": 4.026114469450001,
|
| 14 |
+
"learning_rate": 2.105263157894737e-06,
|
| 15 |
+
"loss": 1.3755,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0052645433008686494,
|
| 20 |
+
"grad_norm": 1.1251945428540173,
|
| 21 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 22 |
+
"loss": 1.3102,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.010529086601737299,
|
| 27 |
+
"grad_norm": 0.563945023031292,
|
| 28 |
+
"learning_rate": 2.105263157894737e-05,
|
| 29 |
+
"loss": 1.2626,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01579362990260595,
|
| 34 |
+
"grad_norm": 0.4336837922055097,
|
| 35 |
+
"learning_rate": 3.157894736842105e-05,
|
| 36 |
+
"loss": 1.2133,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.021058173203474598,
|
| 41 |
+
"grad_norm": 0.33707427690007363,
|
| 42 |
+
"learning_rate": 4.210526315789474e-05,
|
| 43 |
+
"loss": 1.1636,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.026322716504343247,
|
| 48 |
+
"grad_norm": 0.2412443925117212,
|
| 49 |
+
"learning_rate": 5.2631578947368424e-05,
|
| 50 |
+
"loss": 1.1845,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0315872598052119,
|
| 55 |
+
"grad_norm": 0.2414606698915264,
|
| 56 |
+
"learning_rate": 6.31578947368421e-05,
|
| 57 |
+
"loss": 1.1401,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03685180310608055,
|
| 62 |
+
"grad_norm": 0.22628642837844729,
|
| 63 |
+
"learning_rate": 7.368421052631579e-05,
|
| 64 |
+
"loss": 1.1591,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.042116346406949196,
|
| 69 |
+
"grad_norm": 0.2208133931977146,
|
| 70 |
+
"learning_rate": 8.421052631578948e-05,
|
| 71 |
+
"loss": 1.1397,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04738088970781785,
|
| 76 |
+
"grad_norm": 0.21905054641153135,
|
| 77 |
+
"learning_rate": 9.473684210526316e-05,
|
| 78 |
+
"loss": 1.1295,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.052645433008686494,
|
| 83 |
+
"grad_norm": 0.1951061692287286,
|
| 84 |
+
"learning_rate": 0.00010526315789473685,
|
| 85 |
+
"loss": 1.141,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05790997630955515,
|
| 90 |
+
"grad_norm": 0.18792729468212402,
|
| 91 |
+
"learning_rate": 0.00011578947368421053,
|
| 92 |
+
"loss": 1.121,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0631745196104238,
|
| 97 |
+
"grad_norm": 0.189919407852987,
|
| 98 |
+
"learning_rate": 0.0001263157894736842,
|
| 99 |
+
"loss": 1.1347,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06843906291129244,
|
| 104 |
+
"grad_norm": 0.18793881851552416,
|
| 105 |
+
"learning_rate": 0.0001368421052631579,
|
| 106 |
+
"loss": 1.0961,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0737036062121611,
|
| 111 |
+
"grad_norm": 0.18263188517758086,
|
| 112 |
+
"learning_rate": 0.00014736842105263158,
|
| 113 |
+
"loss": 1.0937,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07896814951302975,
|
| 118 |
+
"grad_norm": 0.18520098125405152,
|
| 119 |
+
"learning_rate": 0.00015789473684210527,
|
| 120 |
+
"loss": 1.1419,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.08423269281389839,
|
| 125 |
+
"grad_norm": 0.18675524775004465,
|
| 126 |
+
"learning_rate": 0.00016842105263157895,
|
| 127 |
+
"loss": 1.1094,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08949723611476705,
|
| 132 |
+
"grad_norm": 0.18469057661828525,
|
| 133 |
+
"learning_rate": 0.00017894736842105264,
|
| 134 |
+
"loss": 1.0952,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0947617794156357,
|
| 139 |
+
"grad_norm": 0.17860571701450936,
|
| 140 |
+
"learning_rate": 0.00018947368421052632,
|
| 141 |
+
"loss": 1.1035,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.10002632271650434,
|
| 146 |
+
"grad_norm": 0.2032976356381528,
|
| 147 |
+
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 1.1329,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.10529086601737299,
|
| 153 |
+
"grad_norm": 0.18932762375677964,
|
| 154 |
+
"learning_rate": 0.0001999830846194422,
|
| 155 |
+
"loss": 1.0902,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.11055540931824165,
|
| 160 |
+
"grad_norm": 0.17823414518835126,
|
| 161 |
+
"learning_rate": 0.00019993234420037073,
|
| 162 |
+
"loss": 1.0951,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1158199526191103,
|
| 167 |
+
"grad_norm": 0.19033211796864122,
|
| 168 |
+
"learning_rate": 0.00019984779590865556,
|
| 169 |
+
"loss": 1.11,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.12108449591997894,
|
| 174 |
+
"grad_norm": 0.1781090004150184,
|
| 175 |
+
"learning_rate": 0.0001997294683476273,
|
| 176 |
+
"loss": 1.1216,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1263490392208476,
|
| 181 |
+
"grad_norm": 0.20142566240295628,
|
| 182 |
+
"learning_rate": 0.0001995774015484005,
|
| 183 |
+
"loss": 1.088,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.13161358252171623,
|
| 188 |
+
"grad_norm": 0.16738672746077932,
|
| 189 |
+
"learning_rate": 0.00019939164695633067,
|
| 190 |
+
"loss": 1.1069,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.13687812582258488,
|
| 195 |
+
"grad_norm": 0.17141306079033702,
|
| 196 |
+
"learning_rate": 0.00019917226741361015,
|
| 197 |
+
"loss": 1.1178,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.14214266912345355,
|
| 202 |
+
"grad_norm": 0.18242919862111662,
|
| 203 |
+
"learning_rate": 0.00019891933713800798,
|
| 204 |
+
"loss": 1.115,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1474072124243222,
|
| 209 |
+
"grad_norm": 0.18858703761293544,
|
| 210 |
+
"learning_rate": 0.00019863294169776148,
|
| 211 |
+
"loss": 1.092,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.15267175572519084,
|
| 216 |
+
"grad_norm": 0.1851910906506613,
|
| 217 |
+
"learning_rate": 0.00019831317798262786,
|
| 218 |
+
"loss": 1.1015,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1579362990260595,
|
| 223 |
+
"grad_norm": 0.17061718616532065,
|
| 224 |
+
"learning_rate": 0.00019796015417110577,
|
| 225 |
+
"loss": 1.0834,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.16320084232692814,
|
| 230 |
+
"grad_norm": 0.19083175263550564,
|
| 231 |
+
"learning_rate": 0.0001975739896938375,
|
| 232 |
+
"loss": 1.0915,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.16846538562779678,
|
| 237 |
+
"grad_norm": 0.17041981222039004,
|
| 238 |
+
"learning_rate": 0.00019715481519320496,
|
| 239 |
+
"loss": 1.1045,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.17372992892866543,
|
| 244 |
+
"grad_norm": 0.17539080495334333,
|
| 245 |
+
"learning_rate": 0.00019670277247913205,
|
| 246 |
+
"loss": 1.0822,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.1789944722295341,
|
| 251 |
+
"grad_norm": 0.16847918243353582,
|
| 252 |
+
"learning_rate": 0.00019621801448110952,
|
| 253 |
+
"loss": 1.1113,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.18425901553040275,
|
| 258 |
+
"grad_norm": 0.16577520965121645,
|
| 259 |
+
"learning_rate": 0.00019570070519645767,
|
| 260 |
+
"loss": 1.0726,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1895235588312714,
|
| 265 |
+
"grad_norm": 0.17216940817918563,
|
| 266 |
+
"learning_rate": 0.00019515101963484485,
|
| 267 |
+
"loss": 1.1214,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.19478810213214004,
|
| 272 |
+
"grad_norm": 0.16717603329959776,
|
| 273 |
+
"learning_rate": 0.00019456914375908023,
|
| 274 |
+
"loss": 1.0749,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.20005264543300869,
|
| 279 |
+
"grad_norm": 0.16743311436795275,
|
| 280 |
+
"learning_rate": 0.0001939552744222014,
|
| 281 |
+
"loss": 1.0856,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.20531718873387733,
|
| 286 |
+
"grad_norm": 0.16628473925396028,
|
| 287 |
+
"learning_rate": 0.00019330961930087725,
|
| 288 |
+
"loss": 1.1088,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21058173203474598,
|
| 293 |
+
"grad_norm": 0.1735673710306468,
|
| 294 |
+
"learning_rate": 0.00019263239682514952,
|
| 295 |
+
"loss": 1.094,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.21584627533561462,
|
| 300 |
+
"grad_norm": 0.16463208491106188,
|
| 301 |
+
"learning_rate": 0.00019192383610453618,
|
| 302 |
+
"loss": 1.1191,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.2211108186364833,
|
| 307 |
+
"grad_norm": 0.1697201646634803,
|
| 308 |
+
"learning_rate": 0.00019118417685052194,
|
| 309 |
+
"loss": 1.1188,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.22637536193735194,
|
| 314 |
+
"grad_norm": 0.15930348674889006,
|
| 315 |
+
"learning_rate": 0.00019041366929546219,
|
| 316 |
+
"loss": 1.1132,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.2316399052382206,
|
| 321 |
+
"grad_norm": 0.16154587528605638,
|
| 322 |
+
"learning_rate": 0.0001896125741079272,
|
| 323 |
+
"loss": 1.1029,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.23690444853908924,
|
| 328 |
+
"grad_norm": 0.1689593754891321,
|
| 329 |
+
"learning_rate": 0.00018878116230451613,
|
| 330 |
+
"loss": 1.1196,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.24216899183995788,
|
| 335 |
+
"grad_norm": 0.158620581331537,
|
| 336 |
+
"learning_rate": 0.0001879197151581702,
|
| 337 |
+
"loss": 1.0786,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.24743353514082653,
|
| 342 |
+
"grad_norm": 0.1591976970503649,
|
| 343 |
+
"learning_rate": 0.00018702852410301554,
|
| 344 |
+
"loss": 1.0861,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.2526980784416952,
|
| 349 |
+
"grad_norm": 0.16271741933565712,
|
| 350 |
+
"learning_rate": 0.00018610789063576913,
|
| 351 |
+
"loss": 1.077,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.25796262174256385,
|
| 356 |
+
"grad_norm": 0.16691583214883504,
|
| 357 |
+
"learning_rate": 0.00018515812621373997,
|
| 358 |
+
"loss": 1.0931,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.26322716504343247,
|
| 363 |
+
"grad_norm": 0.15795453416798677,
|
| 364 |
+
"learning_rate": 0.00018417955214946092,
|
| 365 |
+
"loss": 1.0929,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.26849170834430114,
|
| 370 |
+
"grad_norm": 0.15734119895920037,
|
| 371 |
+
"learning_rate": 0.00018317249950198597,
|
| 372 |
+
"loss": 1.086,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.27375625164516976,
|
| 377 |
+
"grad_norm": 0.15815121783491273,
|
| 378 |
+
"learning_rate": 0.0001821373089648906,
|
| 379 |
+
"loss": 1.1142,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.27902079494603843,
|
| 384 |
+
"grad_norm": 0.15790684873329372,
|
| 385 |
+
"learning_rate": 0.00018107433075101252,
|
| 386 |
+
"loss": 1.0907,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2842853382469071,
|
| 391 |
+
"grad_norm": 0.1603612919235376,
|
| 392 |
+
"learning_rate": 0.00017998392447397197,
|
| 393 |
+
"loss": 1.103,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.2895498815477757,
|
| 398 |
+
"grad_norm": 0.1935643212000403,
|
| 399 |
+
"learning_rate": 0.00017886645902651167,
|
| 400 |
+
"loss": 1.1207,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.2948144248486444,
|
| 405 |
+
"grad_norm": 0.16197395404790052,
|
| 406 |
+
"learning_rate": 0.0001777223124556978,
|
| 407 |
+
"loss": 1.1036,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.300078968149513,
|
| 412 |
+
"grad_norm": 0.16503760296000086,
|
| 413 |
+
"learning_rate": 0.00017655187183502344,
|
| 414 |
+
"loss": 1.0647,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.3053435114503817,
|
| 419 |
+
"grad_norm": 0.1772283442967409,
|
| 420 |
+
"learning_rate": 0.00017535553313345904,
|
| 421 |
+
"loss": 1.1075,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.3106080547512503,
|
| 426 |
+
"grad_norm": 0.16282645295325013,
|
| 427 |
+
"learning_rate": 0.00017413370108149286,
|
| 428 |
+
"loss": 1.1094,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.315872598052119,
|
| 433 |
+
"grad_norm": 0.15561402718068354,
|
| 434 |
+
"learning_rate": 0.00017288678903420762,
|
| 435 |
+
"loss": 1.0776,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.32113714135298765,
|
| 440 |
+
"grad_norm": 0.15594031474920508,
|
| 441 |
+
"learning_rate": 0.00017161521883143934,
|
| 442 |
+
"loss": 1.1078,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.32640168465385627,
|
| 447 |
+
"grad_norm": 0.1570395383591175,
|
| 448 |
+
"learning_rate": 0.00017031942065506576,
|
| 449 |
+
"loss": 1.1124,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.33166622795472495,
|
| 454 |
+
"grad_norm": 0.15773152315944608,
|
| 455 |
+
"learning_rate": 0.00016899983288347248,
|
| 456 |
+
"loss": 1.0913,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.33693077125559356,
|
| 461 |
+
"grad_norm": 0.15310806808595664,
|
| 462 |
+
"learning_rate": 0.00016765690194324616,
|
| 463 |
+
"loss": 1.0845,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.34219531455646224,
|
| 468 |
+
"grad_norm": 0.16384678369715433,
|
| 469 |
+
"learning_rate": 0.00016629108215814525,
|
| 470 |
+
"loss": 1.1173,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.34745985785733086,
|
| 475 |
+
"grad_norm": 0.165818325184464,
|
| 476 |
+
"learning_rate": 0.00016490283559539838,
|
| 477 |
+
"loss": 1.1014,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.35272440115819953,
|
| 482 |
+
"grad_norm": 0.15456003221800826,
|
| 483 |
+
"learning_rate": 0.000163492631909384,
|
| 484 |
+
"loss": 1.0915,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.3579889444590682,
|
| 489 |
+
"grad_norm": 0.16059867173233644,
|
| 490 |
+
"learning_rate": 0.00016206094818274229,
|
| 491 |
+
"loss": 1.0969,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3632534877599368,
|
| 496 |
+
"grad_norm": 0.17415674474557066,
|
| 497 |
+
"learning_rate": 0.00016060826876497478,
|
| 498 |
+
"loss": 1.1145,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.3685180310608055,
|
| 503 |
+
"grad_norm": 0.16440403677512835,
|
| 504 |
+
"learning_rate": 0.0001591350851085851,
|
| 505 |
+
"loss": 1.0683,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.3737825743616741,
|
| 510 |
+
"grad_norm": 0.15901493438320982,
|
| 511 |
+
"learning_rate": 0.00015764189560281677,
|
| 512 |
+
"loss": 1.1199,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.3790471176625428,
|
| 517 |
+
"grad_norm": 0.15988293404570103,
|
| 518 |
+
"learning_rate": 0.00015612920540504453,
|
| 519 |
+
"loss": 1.0709,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3843116609634114,
|
| 524 |
+
"grad_norm": 0.1616109424204681,
|
| 525 |
+
"learning_rate": 0.00015459752626987563,
|
| 526 |
+
"loss": 1.1027,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3895762042642801,
|
| 531 |
+
"grad_norm": 0.1513607201651111,
|
| 532 |
+
"learning_rate": 0.00015304737637601926,
|
| 533 |
+
"loss": 1.0956,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3948407475651487,
|
| 538 |
+
"grad_norm": 0.15452619863423803,
|
| 539 |
+
"learning_rate": 0.0001514792801509831,
|
| 540 |
+
"loss": 1.0952,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.40010529086601737,
|
| 545 |
+
"grad_norm": 0.15418975657555584,
|
| 546 |
+
"learning_rate": 0.00014989376809365493,
|
| 547 |
+
"loss": 1.0934,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.40536983416688604,
|
| 552 |
+
"grad_norm": 0.15158447263390024,
|
| 553 |
+
"learning_rate": 0.00014829137659483143,
|
| 554 |
+
"loss": 1.0981,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.41063437746775466,
|
| 559 |
+
"grad_norm": 0.15420702474431047,
|
| 560 |
+
"learning_rate": 0.0001466726477557527,
|
| 561 |
+
"loss": 1.1013,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.41589892076862334,
|
| 566 |
+
"grad_norm": 0.1513401762569788,
|
| 567 |
+
"learning_rate": 0.00014503812920470534,
|
| 568 |
+
"loss": 1.1128,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.42116346406949196,
|
| 573 |
+
"grad_norm": 0.1759021276212348,
|
| 574 |
+
"learning_rate": 0.00014338837391175582,
|
| 575 |
+
"loss": 1.0793,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.42642800737036063,
|
| 580 |
+
"grad_norm": 0.15639002655528358,
|
| 581 |
+
"learning_rate": 0.00014172394000167623,
|
| 582 |
+
"loss": 1.1126,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.43169255067122925,
|
| 587 |
+
"grad_norm": 0.1558922751326013,
|
| 588 |
+
"learning_rate": 0.00014004539056512667,
|
| 589 |
+
"loss": 1.0864,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.4369570939720979,
|
| 594 |
+
"grad_norm": 0.15449223519766864,
|
| 595 |
+
"learning_rate": 0.00013835329346815716,
|
| 596 |
+
"loss": 1.1161,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.4422216372729666,
|
| 601 |
+
"grad_norm": 0.15398779214531882,
|
| 602 |
+
"learning_rate": 0.0001366482211600945,
|
| 603 |
+
"loss": 1.113,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.4474861805738352,
|
| 608 |
+
"grad_norm": 0.15902962443654645,
|
| 609 |
+
"learning_rate": 0.000134930750479878,
|
| 610 |
+
"loss": 1.0783,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4527507238747039,
|
| 615 |
+
"grad_norm": 0.15614703146804315,
|
| 616 |
+
"learning_rate": 0.00013320146246091074,
|
| 617 |
+
"loss": 1.0891,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4580152671755725,
|
| 622 |
+
"grad_norm": 0.151735228198923,
|
| 623 |
+
"learning_rate": 0.00013146094213449148,
|
| 624 |
+
"loss": 1.1006,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.4632798104764412,
|
| 629 |
+
"grad_norm": 0.1633743946888902,
|
| 630 |
+
"learning_rate": 0.00012970977833189393,
|
| 631 |
+
"loss": 1.0717,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.4685443537773098,
|
| 636 |
+
"grad_norm": 0.16534257355481496,
|
| 637 |
+
"learning_rate": 0.00012794856348516095,
|
| 638 |
+
"loss": 1.0778,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.47380889707817847,
|
| 643 |
+
"grad_norm": 0.1856142828881669,
|
| 644 |
+
"learning_rate": 0.00012617789342668004,
|
| 645 |
+
"loss": 1.0859,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.47907344037904714,
|
| 650 |
+
"grad_norm": 0.15229515578033356,
|
| 651 |
+
"learning_rate": 0.00012439836718760886,
|
| 652 |
+
"loss": 1.0761,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.48433798367991576,
|
| 657 |
+
"grad_norm": 0.15984985984562605,
|
| 658 |
+
"learning_rate": 0.00012261058679521834,
|
| 659 |
+
"loss": 1.0926,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.48960252698078444,
|
| 664 |
+
"grad_norm": 0.14896040772758903,
|
| 665 |
+
"learning_rate": 0.00012081515706922227,
|
| 666 |
+
"loss": 1.0834,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.49486707028165305,
|
| 671 |
+
"grad_norm": 0.1514924492192347,
|
| 672 |
+
"learning_rate": 0.00011901268541716224,
|
| 673 |
+
"loss": 1.0885,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5001316135825217,
|
| 678 |
+
"grad_norm": 0.1513889418015892,
|
| 679 |
+
"learning_rate": 0.00011720378162891708,
|
| 680 |
+
"loss": 1.1001,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.5053961568833903,
|
| 685 |
+
"grad_norm": 0.15159825336613816,
|
| 686 |
+
"learning_rate": 0.0001153890576704062,
|
| 687 |
+
"loss": 1.1082,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.510660700184259,
|
| 692 |
+
"grad_norm": 0.15427722774659086,
|
| 693 |
+
"learning_rate": 0.00011356912747655685,
|
| 694 |
+
"loss": 1.0843,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.5159252434851277,
|
| 699 |
+
"grad_norm": 0.14639500931900093,
|
| 700 |
+
"learning_rate": 0.00011174460674360549,
|
| 701 |
+
"loss": 1.1058,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.5211897867859964,
|
| 706 |
+
"grad_norm": 0.15320269723203808,
|
| 707 |
+
"learning_rate": 0.00010991611272080269,
|
| 708 |
+
"loss": 1.1125,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.5264543300868649,
|
| 713 |
+
"grad_norm": 0.15092814943890553,
|
| 714 |
+
"learning_rate": 0.00010808426400159338,
|
| 715 |
+
"loss": 1.0898,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.5317188733877336,
|
| 720 |
+
"grad_norm": 0.14712598563479434,
|
| 721 |
+
"learning_rate": 0.00010624968031434173,
|
| 722 |
+
"loss": 1.0975,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.5369834166886023,
|
| 727 |
+
"grad_norm": 0.1506174008648404,
|
| 728 |
+
"learning_rate": 0.00010441298231267242,
|
| 729 |
+
"loss": 1.0789,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.542247959989471,
|
| 734 |
+
"grad_norm": 0.14915164476738402,
|
| 735 |
+
"learning_rate": 0.00010257479136549889,
|
| 736 |
+
"loss": 1.088,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.5475125032903395,
|
| 741 |
+
"grad_norm": 0.14933216158522156,
|
| 742 |
+
"learning_rate": 0.00010073572934680919,
|
| 743 |
+
"loss": 1.1012,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.5527770465912082,
|
| 748 |
+
"grad_norm": 0.1623395783916047,
|
| 749 |
+
"learning_rate": 9.889641842528178e-05,
|
| 750 |
+
"loss": 1.0992,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5580415898920769,
|
| 755 |
+
"grad_norm": 0.15524883773019818,
|
| 756 |
+
"learning_rate": 9.70574808538006e-05,
|
| 757 |
+
"loss": 1.0558,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.5633061331929455,
|
| 762 |
+
"grad_norm": 0.14879516385003932,
|
| 763 |
+
"learning_rate": 9.521953875894257e-05,
|
| 764 |
+
"loss": 1.0634,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5685706764938142,
|
| 769 |
+
"grad_norm": 0.14856407933911947,
|
| 770 |
+
"learning_rate": 9.338321393050719e-05,
|
| 771 |
+
"loss": 1.0513,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5738352197946828,
|
| 776 |
+
"grad_norm": 0.1514919636398635,
|
| 777 |
+
"learning_rate": 9.154912761116056e-05,
|
| 778 |
+
"loss": 1.0899,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5790997630955514,
|
| 783 |
+
"grad_norm": 0.15005939408454377,
|
| 784 |
+
"learning_rate": 8.971790028626395e-05,
|
| 785 |
+
"loss": 1.09,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5843643063964201,
|
| 790 |
+
"grad_norm": 0.1541140355049706,
|
| 791 |
+
"learning_rate": 8.789015147395919e-05,
|
| 792 |
+
"loss": 1.072,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5896288496972888,
|
| 797 |
+
"grad_norm": 0.14756189100480177,
|
| 798 |
+
"learning_rate": 8.606649951558073e-05,
|
| 799 |
+
"loss": 1.0548,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5948933929981574,
|
| 804 |
+
"grad_norm": 0.14468591274130843,
|
| 805 |
+
"learning_rate": 8.424756136646623e-05,
|
| 806 |
+
"loss": 1.056,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.600157936299026,
|
| 811 |
+
"grad_norm": 0.1510683202100121,
|
| 812 |
+
"learning_rate": 8.243395238723571e-05,
|
| 813 |
+
"loss": 1.0999,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.6054224795998947,
|
| 818 |
+
"grad_norm": 0.14942489035639112,
|
| 819 |
+
"learning_rate": 8.062628613561051e-05,
|
| 820 |
+
"loss": 1.08,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.6106870229007634,
|
| 825 |
+
"grad_norm": 0.14792710995590722,
|
| 826 |
+
"learning_rate": 7.8825174158842e-05,
|
| 827 |
+
"loss": 1.0916,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.615951566201632,
|
| 832 |
+
"grad_norm": 0.14543568608581728,
|
| 833 |
+
"learning_rate": 7.703122578682046e-05,
|
| 834 |
+
"loss": 1.061,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.6212161095025006,
|
| 839 |
+
"grad_norm": 0.14792849899325772,
|
| 840 |
+
"learning_rate": 7.524504792593419e-05,
|
| 841 |
+
"loss": 1.1101,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.6264806528033693,
|
| 846 |
+
"grad_norm": 0.14574924924348462,
|
| 847 |
+
"learning_rate": 7.346724485374837e-05,
|
| 848 |
+
"loss": 1.0687,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.631745196104238,
|
| 853 |
+
"grad_norm": 0.1434166906369258,
|
| 854 |
+
"learning_rate": 7.169841801457347e-05,
|
| 855 |
+
"loss": 1.0825,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.6370097394051066,
|
| 860 |
+
"grad_norm": 0.14254720323207454,
|
| 861 |
+
"learning_rate": 6.993916581599202e-05,
|
| 862 |
+
"loss": 1.0896,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.6422742827059753,
|
| 867 |
+
"grad_norm": 0.14534591022474969,
|
| 868 |
+
"learning_rate": 6.819008342641273e-05,
|
| 869 |
+
"loss": 1.0805,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.6475388260068439,
|
| 874 |
+
"grad_norm": 0.1471482502229213,
|
| 875 |
+
"learning_rate": 6.645176257372055e-05,
|
| 876 |
+
"loss": 1.0933,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.6528033693077125,
|
| 881 |
+
"grad_norm": 0.14967562406928056,
|
| 882 |
+
"learning_rate": 6.472479134509052e-05,
|
| 883 |
+
"loss": 1.0987,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.6580679126085812,
|
| 888 |
+
"grad_norm": 0.14756218985788289,
|
| 889 |
+
"learning_rate": 6.300975398803362e-05,
|
| 890 |
+
"loss": 1.0862,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.6633324559094499,
|
| 895 |
+
"grad_norm": 0.14358810278632364,
|
| 896 |
+
"learning_rate": 6.130723071274107e-05,
|
| 897 |
+
"loss": 1.0736,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.6685969992103185,
|
| 902 |
+
"grad_norm": 0.14508119820046267,
|
| 903 |
+
"learning_rate": 5.961779749579516e-05,
|
| 904 |
+
"loss": 1.077,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6738615425111871,
|
| 909 |
+
"grad_norm": 0.14868475648668983,
|
| 910 |
+
"learning_rate": 5.794202588531166e-05,
|
| 911 |
+
"loss": 1.0921,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6791260858120558,
|
| 916 |
+
"grad_norm": 0.14136660751737096,
|
| 917 |
+
"learning_rate": 5.628048280758096e-05,
|
| 918 |
+
"loss": 1.0967,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6843906291129245,
|
| 923 |
+
"grad_norm": 0.14429824406995242,
|
| 924 |
+
"learning_rate": 5.4633730375272594e-05,
|
| 925 |
+
"loss": 1.094,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.6896551724137931,
|
| 930 |
+
"grad_norm": 0.1435583500936634,
|
| 931 |
+
"learning_rate": 5.300232569726804e-05,
|
| 932 |
+
"loss": 1.0796,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.6949197157146617,
|
| 937 |
+
"grad_norm": 0.14917594264214823,
|
| 938 |
+
"learning_rate": 5.13868206901867e-05,
|
| 939 |
+
"loss": 1.0813,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.7001842590155304,
|
| 944 |
+
"grad_norm": 0.14484547003342338,
|
| 945 |
+
"learning_rate": 4.9787761891668397e-05,
|
| 946 |
+
"loss": 1.0833,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.7054488023163991,
|
| 951 |
+
"grad_norm": 0.14125281408090304,
|
| 952 |
+
"learning_rate": 4.820569027547533e-05,
|
| 953 |
+
"loss": 1.0813,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.7107133456172677,
|
| 958 |
+
"grad_norm": 0.1408995053360923,
|
| 959 |
+
"learning_rate": 4.6641141068476666e-05,
|
| 960 |
+
"loss": 1.0752,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.7159778889181364,
|
| 965 |
+
"grad_norm": 0.1414179653044325,
|
| 966 |
+
"learning_rate": 4.5094643569577186e-05,
|
| 967 |
+
"loss": 1.054,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.721242432219005,
|
| 972 |
+
"grad_norm": 0.14582058548503438,
|
| 973 |
+
"learning_rate": 4.356672097065134e-05,
|
| 974 |
+
"loss": 1.1048,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.7265069755198736,
|
| 979 |
+
"grad_norm": 0.14009606861616825,
|
| 980 |
+
"learning_rate": 4.205789017954364e-05,
|
| 981 |
+
"loss": 1.0683,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.7317715188207423,
|
| 986 |
+
"grad_norm": 0.14586506040118713,
|
| 987 |
+
"learning_rate": 4.056866164519465e-05,
|
| 988 |
+
"loss": 1.0728,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.737036062121611,
|
| 993 |
+
"grad_norm": 0.14168474565307407,
|
| 994 |
+
"learning_rate": 3.909953918495234e-05,
|
| 995 |
+
"loss": 1.0476,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.7423006054224796,
|
| 1000 |
+
"grad_norm": 0.14476382479542646,
|
| 1001 |
+
"learning_rate": 3.7651019814126654e-05,
|
| 1002 |
+
"loss": 1.05,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.7475651487233482,
|
| 1007 |
+
"grad_norm": 0.14528550784733454,
|
| 1008 |
+
"learning_rate": 3.622359357784569e-05,
|
| 1009 |
+
"loss": 1.0611,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.7528296920242169,
|
| 1014 |
+
"grad_norm": 0.14781069746763306,
|
| 1015 |
+
"learning_rate": 3.481774338526954e-05,
|
| 1016 |
+
"loss": 1.0952,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.7580942353250856,
|
| 1021 |
+
"grad_norm": 0.15618197530507127,
|
| 1022 |
+
"learning_rate": 3.343394484621855e-05,
|
| 1023 |
+
"loss": 1.0836,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.7633587786259542,
|
| 1028 |
+
"grad_norm": 0.22087793925041818,
|
| 1029 |
+
"learning_rate": 3.207266611027069e-05,
|
| 1030 |
+
"loss": 1.0727,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.7686233219268228,
|
| 1035 |
+
"grad_norm": 0.14674869869141435,
|
| 1036 |
+
"learning_rate": 3.0734367708383294e-05,
|
| 1037 |
+
"loss": 1.0712,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.7738878652276915,
|
| 1042 |
+
"grad_norm": 0.14673826341334423,
|
| 1043 |
+
"learning_rate": 2.9419502397091713e-05,
|
| 1044 |
+
"loss": 1.0852,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.7791524085285602,
|
| 1049 |
+
"grad_norm": 0.1426087824509766,
|
| 1050 |
+
"learning_rate": 2.812851500533843e-05,
|
| 1051 |
+
"loss": 1.0604,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.7844169518294288,
|
| 1056 |
+
"grad_norm": 0.1446320144127932,
|
| 1057 |
+
"learning_rate": 2.6861842283983953e-05,
|
| 1058 |
+
"loss": 1.0537,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7896814951302974,
|
| 1063 |
+
"grad_norm": 0.14326111319394175,
|
| 1064 |
+
"learning_rate": 2.5619912758050725e-05,
|
| 1065 |
+
"loss": 1.0942,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7949460384311661,
|
| 1070 |
+
"grad_norm": 0.14149919988871043,
|
| 1071 |
+
"learning_rate": 2.4403146581749925e-05,
|
| 1072 |
+
"loss": 1.0578,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.8002105817320347,
|
| 1077 |
+
"grad_norm": 0.14034086298796508,
|
| 1078 |
+
"learning_rate": 2.3211955396340002e-05,
|
| 1079 |
+
"loss": 1.0808,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.8054751250329034,
|
| 1084 |
+
"grad_norm": 0.1433790314655123,
|
| 1085 |
+
"learning_rate": 2.204674219086531e-05,
|
| 1086 |
+
"loss": 1.0906,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.8107396683337721,
|
| 1091 |
+
"grad_norm": 0.138618618401559,
|
| 1092 |
+
"learning_rate": 2.090790116582191e-05,
|
| 1093 |
+
"loss": 1.0559,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.8160042116346407,
|
| 1098 |
+
"grad_norm": 0.1429827381187093,
|
| 1099 |
+
"learning_rate": 1.9795817599796418e-05,
|
| 1100 |
+
"loss": 1.0792,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.8212687549355093,
|
| 1105 |
+
"grad_norm": 0.14200271718072968,
|
| 1106 |
+
"learning_rate": 1.871086771912348e-05,
|
| 1107 |
+
"loss": 1.0702,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.826533298236378,
|
| 1112 |
+
"grad_norm": 0.1429932480295589,
|
| 1113 |
+
"learning_rate": 1.7653418570605475e-05,
|
| 1114 |
+
"loss": 1.0715,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.8317978415372467,
|
| 1119 |
+
"grad_norm": 0.14431467515210814,
|
| 1120 |
+
"learning_rate": 1.6623827897337762e-05,
|
| 1121 |
+
"loss": 1.0713,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.8370623848381153,
|
| 1126 |
+
"grad_norm": 0.15238820455432608,
|
| 1127 |
+
"learning_rate": 1.562244401768144e-05,
|
| 1128 |
+
"loss": 1.0824,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.8423269281389839,
|
| 1133 |
+
"grad_norm": 0.14830242766673976,
|
| 1134 |
+
"learning_rate": 1.4649605707424707e-05,
|
| 1135 |
+
"loss": 1.0787,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.8475914714398526,
|
| 1140 |
+
"grad_norm": 0.14468170557092047,
|
| 1141 |
+
"learning_rate": 1.3705642085172366e-05,
|
| 1142 |
+
"loss": 1.0737,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.8528560147407213,
|
| 1147 |
+
"grad_norm": 0.14674968769736463,
|
| 1148 |
+
"learning_rate": 1.2790872501002472e-05,
|
| 1149 |
+
"loss": 1.0577,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.8581205580415899,
|
| 1154 |
+
"grad_norm": 0.14311627432536864,
|
| 1155 |
+
"learning_rate": 1.1905606428427774e-05,
|
| 1156 |
+
"loss": 1.0692,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.8633851013424585,
|
| 1161 |
+
"grad_norm": 0.14558376197107287,
|
| 1162 |
+
"learning_rate": 1.105014335969855e-05,
|
| 1163 |
+
"loss": 1.0934,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.8686496446433272,
|
| 1168 |
+
"grad_norm": 0.14414555681497093,
|
| 1169 |
+
"learning_rate": 1.0224772704482033e-05,
|
| 1170 |
+
"loss": 1.0875,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.8739141879441958,
|
| 1175 |
+
"grad_norm": 0.1399627142514978,
|
| 1176 |
+
"learning_rate": 9.429773691952858e-06,
|
| 1177 |
+
"loss": 1.082,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.8791787312450645,
|
| 1182 |
+
"grad_norm": 0.1392001373823857,
|
| 1183 |
+
"learning_rate": 8.665415276327871e-06,
|
| 1184 |
+
"loss": 1.0573,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.8844432745459332,
|
| 1189 |
+
"grad_norm": 0.13993969105859186,
|
| 1190 |
+
"learning_rate": 7.931956045876688e-06,
|
| 1191 |
+
"loss": 1.0448,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.8897078178468018,
|
| 1196 |
+
"grad_norm": 0.16741517197447736,
|
| 1197 |
+
"learning_rate": 7.229644135439473e-06,
|
| 1198 |
+
"loss": 1.104,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.8949723611476704,
|
| 1203 |
+
"grad_norm": 0.14123729142229655,
|
| 1204 |
+
"learning_rate": 6.558717142480919e-06,
|
| 1205 |
+
"loss": 1.0808,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.9002369044485391,
|
| 1210 |
+
"grad_norm": 0.1424278055064695,
|
| 1211 |
+
"learning_rate": 5.919402046709288e-06,
|
| 1212 |
+
"loss": 1.0709,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9055014477494078,
|
| 1217 |
+
"grad_norm": 0.13993993967003346,
|
| 1218 |
+
"learning_rate": 5.311915133287415e-06,
|
| 1219 |
+
"loss": 1.0941,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.9107659910502763,
|
| 1224 |
+
"grad_norm": 0.14557850289664284,
|
| 1225 |
+
"learning_rate": 4.7364619196617495e-06,
|
| 1226 |
+
"loss": 1.0492,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.916030534351145,
|
| 1231 |
+
"grad_norm": 0.1450177459066908,
|
| 1232 |
+
"learning_rate": 4.193237086034351e-06,
|
| 1233 |
+
"loss": 1.0972,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.9212950776520137,
|
| 1238 |
+
"grad_norm": 0.1570091074884799,
|
| 1239 |
+
"learning_rate": 3.6824244095010065e-06,
|
| 1240 |
+
"loss": 1.0695,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.9265596209528824,
|
| 1245 |
+
"grad_norm": 0.14097561405495265,
|
| 1246 |
+
"learning_rate": 3.2041967018780707e-06,
|
| 1247 |
+
"loss": 1.0948,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.931824164253751,
|
| 1252 |
+
"grad_norm": 0.1420984285291773,
|
| 1253 |
+
"learning_rate": 2.7587157512388718e-06,
|
| 1254 |
+
"loss": 1.0573,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.9370887075546196,
|
| 1259 |
+
"grad_norm": 0.1545471738706476,
|
| 1260 |
+
"learning_rate": 2.346132267179646e-06,
|
| 1261 |
+
"loss": 1.0786,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.9423532508554883,
|
| 1266 |
+
"grad_norm": 0.14481364480205125,
|
| 1267 |
+
"learning_rate": 1.9665858298333005e-06,
|
| 1268 |
+
"loss": 1.0939,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.9476177941563569,
|
| 1273 |
+
"grad_norm": 0.1446556897144525,
|
| 1274 |
+
"learning_rate": 1.6202048426483651e-06,
|
| 1275 |
+
"loss": 1.0752,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.9528823374572256,
|
| 1280 |
+
"grad_norm": 0.13840641658264988,
|
| 1281 |
+
"learning_rate": 1.3071064889491724e-06,
|
| 1282 |
+
"loss": 1.0757,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.9581468807580943,
|
| 1287 |
+
"grad_norm": 0.1405867091258211,
|
| 1288 |
+
"learning_rate": 1.0273966922918155e-06,
|
| 1289 |
+
"loss": 1.0886,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.9634114240589629,
|
| 1294 |
+
"grad_norm": 0.15143973079201015,
|
| 1295 |
+
"learning_rate": 7.81170080629412e-07,
|
| 1296 |
+
"loss": 1.0337,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.9686759673598315,
|
| 1301 |
+
"grad_norm": 0.15113893856195346,
|
| 1302 |
+
"learning_rate": 5.68509954298757e-07,
|
| 1303 |
+
"loss": 1.099,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.9739405106607002,
|
| 1308 |
+
"grad_norm": 0.1436446854214333,
|
| 1309 |
+
"learning_rate": 3.8948825783918784e-07,
|
| 1310 |
+
"loss": 1.0595,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.9792050539615689,
|
| 1315 |
+
"grad_norm": 0.14373165990559605,
|
| 1316 |
+
"learning_rate": 2.4416555565318635e-07,
|
| 1317 |
+
"loss": 1.0815,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.9844695972624374,
|
| 1322 |
+
"grad_norm": 0.14233020784379563,
|
| 1323 |
+
"learning_rate": 1.3259101151694708e-07,
|
| 1324 |
+
"loss": 1.0569,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.9897341405633061,
|
| 1329 |
+
"grad_norm": 0.13823967108377017,
|
| 1330 |
+
"learning_rate": 5.480237194799287e-08,
|
| 1331 |
+
"loss": 1.0689,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.9949986838641748,
|
| 1336 |
+
"grad_norm": 0.1431568671824589,
|
| 1337 |
+
"learning_rate": 1.0825953435122938e-08,
|
| 1338 |
+
"loss": 1.0709,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.9992103185048697,
|
| 1343 |
+
"eval_loss": 1.07915198802948,
|
| 1344 |
+
"eval_runtime": 3821.2872,
|
| 1345 |
+
"eval_samples_per_second": 3.522,
|
| 1346 |
+
"eval_steps_per_second": 0.881,
|
| 1347 |
+
"step": 949
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.9992103185048697,
|
| 1351 |
+
"step": 949,
|
| 1352 |
+
"total_flos": 1959448100732928.0,
|
| 1353 |
+
"train_loss": 1.0930153100081064,
|
| 1354 |
+
"train_runtime": 22340.3866,
|
| 1355 |
+
"train_samples_per_second": 2.72,
|
| 1356 |
+
"train_steps_per_second": 0.042
|
| 1357 |
+
}
|
| 1358 |
+
],
|
| 1359 |
+
"logging_steps": 5,
|
| 1360 |
+
"max_steps": 949,
|
| 1361 |
+
"num_input_tokens_seen": 0,
|
| 1362 |
+
"num_train_epochs": 1,
|
| 1363 |
+
"save_steps": 100,
|
| 1364 |
+
"stateful_callbacks": {
|
| 1365 |
+
"TrainerControl": {
|
| 1366 |
+
"args": {
|
| 1367 |
+
"should_epoch_stop": false,
|
| 1368 |
+
"should_evaluate": false,
|
| 1369 |
+
"should_log": false,
|
| 1370 |
+
"should_save": true,
|
| 1371 |
+
"should_training_stop": true
|
| 1372 |
+
},
|
| 1373 |
+
"attributes": {}
|
| 1374 |
+
}
|
| 1375 |
+
},
|
| 1376 |
+
"total_flos": 1959448100732928.0,
|
| 1377 |
+
"train_batch_size": 4,
|
| 1378 |
+
"trial_name": null,
|
| 1379 |
+
"trial_params": null
|
| 1380 |
+
}
|