Model save
Browse files- README.md +69 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1683 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3.1
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: induction-10k-50seeds-gpt4omini-llama3.1-8b-instruct-lora64_lr2e-4_epoch3
|
| 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 |
+
# induction-10k-50seeds-gpt4omini-llama3.1-8b-instruct-lora64_lr2e-4_epoch3
|
| 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: 0.3508
|
| 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: 0.0002
|
| 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: 3
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 0.3733 | 0.9935 | 77 | 0.3744 |
|
| 59 |
+
| 0.33 | 2.0 | 155 | 0.3544 |
|
| 60 |
+
| 0.3079 | 2.9806 | 231 | 0.3508 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.13.0
|
| 66 |
+
- Transformers 4.45.0.dev0
|
| 67 |
+
- Pytorch 2.4.0+cu121
|
| 68 |
+
- Datasets 3.0.1
|
| 69 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9806451612903224,
|
| 3 |
+
"total_flos": 9.324729662937498e+16,
|
| 4 |
+
"train_loss": 0.3951803825118325,
|
| 5 |
+
"train_runtime": 2997.4381,
|
| 6 |
+
"train_samples": 9863,
|
| 7 |
+
"train_samples_per_second": 9.871,
|
| 8 |
+
"train_steps_per_second": 0.077
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9806451612903224,
|
| 3 |
+
"total_flos": 9.324729662937498e+16,
|
| 4 |
+
"train_loss": 0.3951803825118325,
|
| 5 |
+
"train_runtime": 2997.4381,
|
| 6 |
+
"train_samples": 9863,
|
| 7 |
+
"train_samples_per_second": 9.871,
|
| 8 |
+
"train_steps_per_second": 0.077
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1683 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9806451612903224,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 231,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.012903225806451613,
|
| 13 |
+
"grad_norm": 0.882150089808769,
|
| 14 |
+
"learning_rate": 8.333333333333334e-06,
|
| 15 |
+
"loss": 1.3191,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.025806451612903226,
|
| 20 |
+
"grad_norm": 0.8369153094823952,
|
| 21 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 22 |
+
"loss": 1.249,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03870967741935484,
|
| 27 |
+
"grad_norm": 0.8525103918091212,
|
| 28 |
+
"learning_rate": 2.5e-05,
|
| 29 |
+
"loss": 1.2775,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05161290322580645,
|
| 34 |
+
"grad_norm": 0.8113130093304075,
|
| 35 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 36 |
+
"loss": 1.2577,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06451612903225806,
|
| 41 |
+
"grad_norm": 0.7691226782403744,
|
| 42 |
+
"learning_rate": 4.166666666666667e-05,
|
| 43 |
+
"loss": 1.2275,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07741935483870968,
|
| 48 |
+
"grad_norm": 0.5954210054804412,
|
| 49 |
+
"learning_rate": 5e-05,
|
| 50 |
+
"loss": 1.1159,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09032258064516129,
|
| 55 |
+
"grad_norm": 0.48189256930049384,
|
| 56 |
+
"learning_rate": 5.833333333333334e-05,
|
| 57 |
+
"loss": 1.0593,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1032258064516129,
|
| 62 |
+
"grad_norm": 0.5241879927945232,
|
| 63 |
+
"learning_rate": 6.666666666666667e-05,
|
| 64 |
+
"loss": 1.0031,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.11612903225806452,
|
| 69 |
+
"grad_norm": 0.5751865259411146,
|
| 70 |
+
"learning_rate": 7.500000000000001e-05,
|
| 71 |
+
"loss": 0.9263,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.12903225806451613,
|
| 76 |
+
"grad_norm": 0.5686526755807603,
|
| 77 |
+
"learning_rate": 8.333333333333334e-05,
|
| 78 |
+
"loss": 0.8146,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.14193548387096774,
|
| 83 |
+
"grad_norm": 0.5156906474251192,
|
| 84 |
+
"learning_rate": 9.166666666666667e-05,
|
| 85 |
+
"loss": 0.7583,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.15483870967741936,
|
| 90 |
+
"grad_norm": 0.4901634328534619,
|
| 91 |
+
"learning_rate": 0.0001,
|
| 92 |
+
"loss": 0.6686,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.16774193548387098,
|
| 97 |
+
"grad_norm": 0.376084270046461,
|
| 98 |
+
"learning_rate": 0.00010833333333333333,
|
| 99 |
+
"loss": 0.6005,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.18064516129032257,
|
| 104 |
+
"grad_norm": 0.2761318809240614,
|
| 105 |
+
"learning_rate": 0.00011666666666666668,
|
| 106 |
+
"loss": 0.5741,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1935483870967742,
|
| 111 |
+
"grad_norm": 0.25038763704461725,
|
| 112 |
+
"learning_rate": 0.000125,
|
| 113 |
+
"loss": 0.5465,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2064516129032258,
|
| 118 |
+
"grad_norm": 0.2214903977106201,
|
| 119 |
+
"learning_rate": 0.00013333333333333334,
|
| 120 |
+
"loss": 0.5138,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.21935483870967742,
|
| 125 |
+
"grad_norm": 0.28905541505099525,
|
| 126 |
+
"learning_rate": 0.00014166666666666668,
|
| 127 |
+
"loss": 0.5247,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.23225806451612904,
|
| 132 |
+
"grad_norm": 0.20699066633757193,
|
| 133 |
+
"learning_rate": 0.00015000000000000001,
|
| 134 |
+
"loss": 0.4978,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.24516129032258063,
|
| 139 |
+
"grad_norm": 0.219457528851344,
|
| 140 |
+
"learning_rate": 0.00015833333333333332,
|
| 141 |
+
"loss": 0.4924,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.25806451612903225,
|
| 146 |
+
"grad_norm": 0.16596853789220767,
|
| 147 |
+
"learning_rate": 0.0001666666666666667,
|
| 148 |
+
"loss": 0.4759,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2709677419354839,
|
| 153 |
+
"grad_norm": 0.13228412371333673,
|
| 154 |
+
"learning_rate": 0.000175,
|
| 155 |
+
"loss": 0.4613,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2838709677419355,
|
| 160 |
+
"grad_norm": 0.1421107856190867,
|
| 161 |
+
"learning_rate": 0.00018333333333333334,
|
| 162 |
+
"loss": 0.4852,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2967741935483871,
|
| 167 |
+
"grad_norm": 0.12552928984887968,
|
| 168 |
+
"learning_rate": 0.00019166666666666667,
|
| 169 |
+
"loss": 0.4786,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3096774193548387,
|
| 174 |
+
"grad_norm": 0.11489463060846784,
|
| 175 |
+
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 0.4532,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3225806451612903,
|
| 181 |
+
"grad_norm": 0.11476879539402507,
|
| 182 |
+
"learning_rate": 0.00019998848349441062,
|
| 183 |
+
"loss": 0.4454,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.33548387096774196,
|
| 188 |
+
"grad_norm": 0.1256602270101812,
|
| 189 |
+
"learning_rate": 0.00019995393663024054,
|
| 190 |
+
"loss": 0.4513,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.34838709677419355,
|
| 195 |
+
"grad_norm": 0.11833482485698336,
|
| 196 |
+
"learning_rate": 0.00019989636736467278,
|
| 197 |
+
"loss": 0.44,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.36129032258064514,
|
| 202 |
+
"grad_norm": 0.11124019681377781,
|
| 203 |
+
"learning_rate": 0.00019981578895764273,
|
| 204 |
+
"loss": 0.4439,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3741935483870968,
|
| 209 |
+
"grad_norm": 0.10954971384477814,
|
| 210 |
+
"learning_rate": 0.00019971221996878394,
|
| 211 |
+
"loss": 0.4274,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3870967741935484,
|
| 216 |
+
"grad_norm": 0.11422715129880294,
|
| 217 |
+
"learning_rate": 0.00019958568425315314,
|
| 218 |
+
"loss": 0.4254,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4,
|
| 223 |
+
"grad_norm": 0.11262310014016527,
|
| 224 |
+
"learning_rate": 0.00019943621095573586,
|
| 225 |
+
"loss": 0.4204,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4129032258064516,
|
| 230 |
+
"grad_norm": 0.11143099554463408,
|
| 231 |
+
"learning_rate": 0.00019926383450473344,
|
| 232 |
+
"loss": 0.4105,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4258064516129032,
|
| 237 |
+
"grad_norm": 0.1088260973247734,
|
| 238 |
+
"learning_rate": 0.00019906859460363307,
|
| 239 |
+
"loss": 0.4136,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.43870967741935485,
|
| 244 |
+
"grad_norm": 0.10400753996611788,
|
| 245 |
+
"learning_rate": 0.00019885053622206304,
|
| 246 |
+
"loss": 0.4213,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.45161290322580644,
|
| 251 |
+
"grad_norm": 0.09587900896302251,
|
| 252 |
+
"learning_rate": 0.0001986097095854347,
|
| 253 |
+
"loss": 0.4085,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4645161290322581,
|
| 258 |
+
"grad_norm": 0.10119603747308556,
|
| 259 |
+
"learning_rate": 0.0001983461701633742,
|
| 260 |
+
"loss": 0.4181,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.4774193548387097,
|
| 265 |
+
"grad_norm": 0.10062413136253176,
|
| 266 |
+
"learning_rate": 0.00019805997865694614,
|
| 267 |
+
"loss": 0.4098,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.49032258064516127,
|
| 272 |
+
"grad_norm": 0.09162394941720846,
|
| 273 |
+
"learning_rate": 0.0001977512009846721,
|
| 274 |
+
"loss": 0.4085,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5032258064516129,
|
| 279 |
+
"grad_norm": 0.09269316443279575,
|
| 280 |
+
"learning_rate": 0.00019741990826734794,
|
| 281 |
+
"loss": 0.3994,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5161290322580645,
|
| 286 |
+
"grad_norm": 0.08782581803238095,
|
| 287 |
+
"learning_rate": 0.00019706617681166218,
|
| 288 |
+
"loss": 0.3983,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5290322580645161,
|
| 293 |
+
"grad_norm": 0.08665646987756218,
|
| 294 |
+
"learning_rate": 0.00019669008809262062,
|
| 295 |
+
"loss": 0.3938,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5419354838709678,
|
| 300 |
+
"grad_norm": 0.09289388957990503,
|
| 301 |
+
"learning_rate": 0.00019629172873477995,
|
| 302 |
+
"loss": 0.396,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5548387096774193,
|
| 307 |
+
"grad_norm": 0.09203344649472522,
|
| 308 |
+
"learning_rate": 0.00019587119049229557,
|
| 309 |
+
"loss": 0.4052,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.567741935483871,
|
| 314 |
+
"grad_norm": 0.08209774194723368,
|
| 315 |
+
"learning_rate": 0.0001954285702277879,
|
| 316 |
+
"loss": 0.3959,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5806451612903226,
|
| 321 |
+
"grad_norm": 0.08595872863630391,
|
| 322 |
+
"learning_rate": 0.00019496396989003193,
|
| 323 |
+
"loss": 0.397,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5935483870967742,
|
| 328 |
+
"grad_norm": 0.09041908237644536,
|
| 329 |
+
"learning_rate": 0.00019447749649047542,
|
| 330 |
+
"loss": 0.3992,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6064516129032258,
|
| 335 |
+
"grad_norm": 0.08321976348844515,
|
| 336 |
+
"learning_rate": 0.00019396926207859084,
|
| 337 |
+
"loss": 0.4095,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6193548387096774,
|
| 342 |
+
"grad_norm": 0.07887604040253807,
|
| 343 |
+
"learning_rate": 0.00019343938371606712,
|
| 344 |
+
"loss": 0.3866,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.632258064516129,
|
| 349 |
+
"grad_norm": 0.08329265943906447,
|
| 350 |
+
"learning_rate": 0.00019288798344984672,
|
| 351 |
+
"loss": 0.3985,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6451612903225806,
|
| 356 |
+
"grad_norm": 0.08661703211305888,
|
| 357 |
+
"learning_rate": 0.00019231518828401458,
|
| 358 |
+
"loss": 0.3925,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6580645161290323,
|
| 363 |
+
"grad_norm": 0.08382217550700771,
|
| 364 |
+
"learning_rate": 0.00019172113015054532,
|
| 365 |
+
"loss": 0.3862,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6709677419354839,
|
| 370 |
+
"grad_norm": 0.08245124856491458,
|
| 371 |
+
"learning_rate": 0.00019110594587891519,
|
| 372 |
+
"loss": 0.3847,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6838709677419355,
|
| 377 |
+
"grad_norm": 0.08319716279149986,
|
| 378 |
+
"learning_rate": 0.00019046977716458626,
|
| 379 |
+
"loss": 0.3775,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6967741935483871,
|
| 384 |
+
"grad_norm": 0.08074648144423298,
|
| 385 |
+
"learning_rate": 0.0001898127705363696,
|
| 386 |
+
"loss": 0.3786,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7096774193548387,
|
| 391 |
+
"grad_norm": 0.08472762376284584,
|
| 392 |
+
"learning_rate": 0.0001891350773226754,
|
| 393 |
+
"loss": 0.3923,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7225806451612903,
|
| 398 |
+
"grad_norm": 0.08398076059437376,
|
| 399 |
+
"learning_rate": 0.00018843685361665723,
|
| 400 |
+
"loss": 0.3709,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7354838709677419,
|
| 405 |
+
"grad_norm": 0.08465216102770419,
|
| 406 |
+
"learning_rate": 0.00018771826024025946,
|
| 407 |
+
"loss": 0.3818,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7483870967741936,
|
| 412 |
+
"grad_norm": 0.09145572810056589,
|
| 413 |
+
"learning_rate": 0.00018697946270717467,
|
| 414 |
+
"loss": 0.39,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7612903225806451,
|
| 419 |
+
"grad_norm": 0.08415188367023674,
|
| 420 |
+
"learning_rate": 0.00018622063118472134,
|
| 421 |
+
"loss": 0.3733,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7741935483870968,
|
| 426 |
+
"grad_norm": 0.08576290382509591,
|
| 427 |
+
"learning_rate": 0.00018544194045464886,
|
| 428 |
+
"loss": 0.3878,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7870967741935484,
|
| 433 |
+
"grad_norm": 0.0844142047859298,
|
| 434 |
+
"learning_rate": 0.00018464356987288013,
|
| 435 |
+
"loss": 0.3637,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.8,
|
| 440 |
+
"grad_norm": 0.08918487261557899,
|
| 441 |
+
"learning_rate": 0.00018382570332820043,
|
| 442 |
+
"loss": 0.3775,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.8129032258064516,
|
| 447 |
+
"grad_norm": 0.0795181880669878,
|
| 448 |
+
"learning_rate": 0.00018298852919990252,
|
| 449 |
+
"loss": 0.3853,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.8258064516129032,
|
| 454 |
+
"grad_norm": 0.08173055996583302,
|
| 455 |
+
"learning_rate": 0.0001821322403143969,
|
| 456 |
+
"loss": 0.38,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.8387096774193549,
|
| 461 |
+
"grad_norm": 0.08525070031165603,
|
| 462 |
+
"learning_rate": 0.0001812570339007983,
|
| 463 |
+
"loss": 0.3778,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8516129032258064,
|
| 468 |
+
"grad_norm": 0.08531235204546653,
|
| 469 |
+
"learning_rate": 0.00018036311154549784,
|
| 470 |
+
"loss": 0.3727,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.864516129032258,
|
| 475 |
+
"grad_norm": 0.08169851479895494,
|
| 476 |
+
"learning_rate": 0.00017945067914573146,
|
| 477 |
+
"loss": 0.365,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8774193548387097,
|
| 482 |
+
"grad_norm": 0.08463789046916101,
|
| 483 |
+
"learning_rate": 0.0001785199468621559,
|
| 484 |
+
"loss": 0.3752,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.8903225806451613,
|
| 489 |
+
"grad_norm": 0.09441843624235378,
|
| 490 |
+
"learning_rate": 0.000177571129070442,
|
| 491 |
+
"loss": 0.3665,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.9032258064516129,
|
| 496 |
+
"grad_norm": 0.08530939476149231,
|
| 497 |
+
"learning_rate": 0.0001766044443118978,
|
| 498 |
+
"loss": 0.3926,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.9161290322580645,
|
| 503 |
+
"grad_norm": 0.0836606457284625,
|
| 504 |
+
"learning_rate": 0.00017562011524313185,
|
| 505 |
+
"loss": 0.3844,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.9290322580645162,
|
| 510 |
+
"grad_norm": 0.09868625782773943,
|
| 511 |
+
"learning_rate": 0.00017461836858476856,
|
| 512 |
+
"loss": 0.3835,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.9419354838709677,
|
| 517 |
+
"grad_norm": 0.082132336261239,
|
| 518 |
+
"learning_rate": 0.00017359943506922774,
|
| 519 |
+
"loss": 0.3792,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.9548387096774194,
|
| 524 |
+
"grad_norm": 0.08948965393301354,
|
| 525 |
+
"learning_rate": 0.0001725635493875799,
|
| 526 |
+
"loss": 0.3813,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.967741935483871,
|
| 531 |
+
"grad_norm": 0.08539410389371488,
|
| 532 |
+
"learning_rate": 0.00017151095013548994,
|
| 533 |
+
"loss": 0.3774,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9806451612903225,
|
| 538 |
+
"grad_norm": 0.08690404790165682,
|
| 539 |
+
"learning_rate": 0.00017044187975826124,
|
| 540 |
+
"loss": 0.3762,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.9935483870967742,
|
| 545 |
+
"grad_norm": 0.09039522496805455,
|
| 546 |
+
"learning_rate": 0.0001693565844949933,
|
| 547 |
+
"loss": 0.3733,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9935483870967742,
|
| 552 |
+
"eval_loss": 0.3743511736392975,
|
| 553 |
+
"eval_runtime": 42.1339,
|
| 554 |
+
"eval_samples_per_second": 24.66,
|
| 555 |
+
"eval_steps_per_second": 0.783,
|
| 556 |
+
"step": 77
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.0064516129032257,
|
| 560 |
+
"grad_norm": 0.09165665911792642,
|
| 561 |
+
"learning_rate": 0.00016825531432186543,
|
| 562 |
+
"loss": 0.3532,
|
| 563 |
+
"step": 78
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.0193548387096774,
|
| 567 |
+
"grad_norm": 0.0801922544260219,
|
| 568 |
+
"learning_rate": 0.0001671383228945597,
|
| 569 |
+
"loss": 0.347,
|
| 570 |
+
"step": 79
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.032258064516129,
|
| 574 |
+
"grad_norm": 0.08352186065175837,
|
| 575 |
+
"learning_rate": 0.00016600586748983641,
|
| 576 |
+
"loss": 0.3566,
|
| 577 |
+
"step": 80
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0451612903225806,
|
| 581 |
+
"grad_norm": 0.08793176795367076,
|
| 582 |
+
"learning_rate": 0.0001648582089462756,
|
| 583 |
+
"loss": 0.3473,
|
| 584 |
+
"step": 81
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.0580645161290323,
|
| 588 |
+
"grad_norm": 0.08913951531063671,
|
| 589 |
+
"learning_rate": 0.00016369561160419784,
|
| 590 |
+
"loss": 0.342,
|
| 591 |
+
"step": 82
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.070967741935484,
|
| 595 |
+
"grad_norm": 0.08309712335786672,
|
| 596 |
+
"learning_rate": 0.0001625183432447789,
|
| 597 |
+
"loss": 0.345,
|
| 598 |
+
"step": 83
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.0838709677419356,
|
| 602 |
+
"grad_norm": 0.08725330804483407,
|
| 603 |
+
"learning_rate": 0.00016132667502837165,
|
| 604 |
+
"loss": 0.3523,
|
| 605 |
+
"step": 84
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.096774193548387,
|
| 609 |
+
"grad_norm": 0.08680862762413778,
|
| 610 |
+
"learning_rate": 0.00016012088143204953,
|
| 611 |
+
"loss": 0.3554,
|
| 612 |
+
"step": 85
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.1096774193548387,
|
| 616 |
+
"grad_norm": 0.0863782848559528,
|
| 617 |
+
"learning_rate": 0.00015890124018638638,
|
| 618 |
+
"loss": 0.364,
|
| 619 |
+
"step": 86
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.1225806451612903,
|
| 623 |
+
"grad_norm": 0.08388848992116194,
|
| 624 |
+
"learning_rate": 0.00015766803221148673,
|
| 625 |
+
"loss": 0.3568,
|
| 626 |
+
"step": 87
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.135483870967742,
|
| 630 |
+
"grad_norm": 0.08226994751114965,
|
| 631 |
+
"learning_rate": 0.00015642154155228122,
|
| 632 |
+
"loss": 0.3489,
|
| 633 |
+
"step": 88
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.1483870967741936,
|
| 637 |
+
"grad_norm": 0.08575965994905438,
|
| 638 |
+
"learning_rate": 0.00015516205531310273,
|
| 639 |
+
"loss": 0.3466,
|
| 640 |
+
"step": 89
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.1612903225806452,
|
| 644 |
+
"grad_norm": 0.0895747440427046,
|
| 645 |
+
"learning_rate": 0.00015388986359155758,
|
| 646 |
+
"loss": 0.3488,
|
| 647 |
+
"step": 90
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.1741935483870969,
|
| 651 |
+
"grad_norm": 0.08403222320010312,
|
| 652 |
+
"learning_rate": 0.00015260525941170712,
|
| 653 |
+
"loss": 0.356,
|
| 654 |
+
"step": 91
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1870967741935483,
|
| 658 |
+
"grad_norm": 0.08627434364043794,
|
| 659 |
+
"learning_rate": 0.0001513085386565758,
|
| 660 |
+
"loss": 0.3519,
|
| 661 |
+
"step": 92
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.2,
|
| 665 |
+
"grad_norm": 0.08925414655300028,
|
| 666 |
+
"learning_rate": 0.00015000000000000001,
|
| 667 |
+
"loss": 0.3523,
|
| 668 |
+
"step": 93
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.2129032258064516,
|
| 672 |
+
"grad_norm": 0.09120079741968923,
|
| 673 |
+
"learning_rate": 0.00014867994483783485,
|
| 674 |
+
"loss": 0.3555,
|
| 675 |
+
"step": 94
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.2258064516129032,
|
| 679 |
+
"grad_norm": 0.08519037826685563,
|
| 680 |
+
"learning_rate": 0.0001473486772185334,
|
| 681 |
+
"loss": 0.3551,
|
| 682 |
+
"step": 95
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.238709677419355,
|
| 686 |
+
"grad_norm": 0.08814591743170447,
|
| 687 |
+
"learning_rate": 0.00014600650377311522,
|
| 688 |
+
"loss": 0.3535,
|
| 689 |
+
"step": 96
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2516129032258063,
|
| 693 |
+
"grad_norm": 0.08812877093082108,
|
| 694 |
+
"learning_rate": 0.00014465373364454001,
|
| 695 |
+
"loss": 0.3498,
|
| 696 |
+
"step": 97
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.2645161290322582,
|
| 700 |
+
"grad_norm": 0.08596197743921638,
|
| 701 |
+
"learning_rate": 0.00014329067841650274,
|
| 702 |
+
"loss": 0.3484,
|
| 703 |
+
"step": 98
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.2774193548387096,
|
| 707 |
+
"grad_norm": 0.09025513346881896,
|
| 708 |
+
"learning_rate": 0.00014191765204166643,
|
| 709 |
+
"loss": 0.3465,
|
| 710 |
+
"step": 99
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.2903225806451613,
|
| 714 |
+
"grad_norm": 0.08665409616008209,
|
| 715 |
+
"learning_rate": 0.00014053497076934948,
|
| 716 |
+
"loss": 0.35,
|
| 717 |
+
"step": 100
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.303225806451613,
|
| 721 |
+
"grad_norm": 0.09012608398761074,
|
| 722 |
+
"learning_rate": 0.00013914295307268396,
|
| 723 |
+
"loss": 0.3516,
|
| 724 |
+
"step": 101
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.3161290322580645,
|
| 728 |
+
"grad_norm": 0.09456407877563842,
|
| 729 |
+
"learning_rate": 0.00013774191957526143,
|
| 730 |
+
"loss": 0.3639,
|
| 731 |
+
"step": 102
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.3290322580645162,
|
| 735 |
+
"grad_norm": 0.0888376260234129,
|
| 736 |
+
"learning_rate": 0.00013633219297728416,
|
| 737 |
+
"loss": 0.3396,
|
| 738 |
+
"step": 103
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.3419354838709676,
|
| 742 |
+
"grad_norm": 0.08652600639054038,
|
| 743 |
+
"learning_rate": 0.00013491409798123687,
|
| 744 |
+
"loss": 0.3445,
|
| 745 |
+
"step": 104
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.3548387096774195,
|
| 749 |
+
"grad_norm": 0.09269194410505097,
|
| 750 |
+
"learning_rate": 0.00013348796121709862,
|
| 751 |
+
"loss": 0.3555,
|
| 752 |
+
"step": 105
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.367741935483871,
|
| 756 |
+
"grad_norm": 0.09421096011594207,
|
| 757 |
+
"learning_rate": 0.00013205411116710972,
|
| 758 |
+
"loss": 0.3508,
|
| 759 |
+
"step": 106
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.3806451612903226,
|
| 763 |
+
"grad_norm": 0.09286783444235318,
|
| 764 |
+
"learning_rate": 0.00013061287809011242,
|
| 765 |
+
"loss": 0.3571,
|
| 766 |
+
"step": 107
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.3935483870967742,
|
| 770 |
+
"grad_norm": 0.08172852976047028,
|
| 771 |
+
"learning_rate": 0.0001291645939454825,
|
| 772 |
+
"loss": 0.3488,
|
| 773 |
+
"step": 108
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.4064516129032258,
|
| 777 |
+
"grad_norm": 0.09033973727962885,
|
| 778 |
+
"learning_rate": 0.0001277095923166689,
|
| 779 |
+
"loss": 0.3498,
|
| 780 |
+
"step": 109
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.4193548387096775,
|
| 784 |
+
"grad_norm": 0.09628933362833343,
|
| 785 |
+
"learning_rate": 0.00012624820833435937,
|
| 786 |
+
"loss": 0.3472,
|
| 787 |
+
"step": 110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.432258064516129,
|
| 791 |
+
"grad_norm": 0.08471497514674803,
|
| 792 |
+
"learning_rate": 0.00012478077859929,
|
| 793 |
+
"loss": 0.3353,
|
| 794 |
+
"step": 111
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.4451612903225808,
|
| 798 |
+
"grad_norm": 0.08976133324522119,
|
| 799 |
+
"learning_rate": 0.00012330764110471566,
|
| 800 |
+
"loss": 0.3468,
|
| 801 |
+
"step": 112
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.4580645161290322,
|
| 805 |
+
"grad_norm": 0.09634877556737409,
|
| 806 |
+
"learning_rate": 0.00012182913515856015,
|
| 807 |
+
"loss": 0.3541,
|
| 808 |
+
"step": 113
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.4709677419354839,
|
| 812 |
+
"grad_norm": 0.09348923296138459,
|
| 813 |
+
"learning_rate": 0.0001203456013052634,
|
| 814 |
+
"loss": 0.3521,
|
| 815 |
+
"step": 114
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.4838709677419355,
|
| 819 |
+
"grad_norm": 0.09437711091684706,
|
| 820 |
+
"learning_rate": 0.00011885738124734358,
|
| 821 |
+
"loss": 0.3566,
|
| 822 |
+
"step": 115
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.4967741935483871,
|
| 826 |
+
"grad_norm": 0.08916702937111011,
|
| 827 |
+
"learning_rate": 0.00011736481776669306,
|
| 828 |
+
"loss": 0.3458,
|
| 829 |
+
"step": 116
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.5096774193548388,
|
| 833 |
+
"grad_norm": 0.09100601467580355,
|
| 834 |
+
"learning_rate": 0.00011586825464562514,
|
| 835 |
+
"loss": 0.3593,
|
| 836 |
+
"step": 117
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.5225806451612902,
|
| 840 |
+
"grad_norm": 0.08990470683690902,
|
| 841 |
+
"learning_rate": 0.00011436803658769082,
|
| 842 |
+
"loss": 0.3434,
|
| 843 |
+
"step": 118
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.535483870967742,
|
| 847 |
+
"grad_norm": 0.0932653393737011,
|
| 848 |
+
"learning_rate": 0.00011286450913828312,
|
| 849 |
+
"loss": 0.342,
|
| 850 |
+
"step": 119
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.5483870967741935,
|
| 854 |
+
"grad_norm": 0.08960531773257623,
|
| 855 |
+
"learning_rate": 0.00011135801860504749,
|
| 856 |
+
"loss": 0.3628,
|
| 857 |
+
"step": 120
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.5612903225806452,
|
| 861 |
+
"grad_norm": 0.09275069273094473,
|
| 862 |
+
"learning_rate": 0.00010984891197811687,
|
| 863 |
+
"loss": 0.3513,
|
| 864 |
+
"step": 121
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.5741935483870968,
|
| 868 |
+
"grad_norm": 0.09527469311088294,
|
| 869 |
+
"learning_rate": 0.00010833753685018935,
|
| 870 |
+
"loss": 0.3556,
|
| 871 |
+
"step": 122
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.5870967741935482,
|
| 875 |
+
"grad_norm": 0.09323849659154124,
|
| 876 |
+
"learning_rate": 0.0001068242413364671,
|
| 877 |
+
"loss": 0.3448,
|
| 878 |
+
"step": 123
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.6,
|
| 882 |
+
"grad_norm": 0.08474554028292876,
|
| 883 |
+
"learning_rate": 0.00010530937399447496,
|
| 884 |
+
"loss": 0.3499,
|
| 885 |
+
"step": 124
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.6129032258064515,
|
| 889 |
+
"grad_norm": 0.09382059811382143,
|
| 890 |
+
"learning_rate": 0.00010379328374377715,
|
| 891 |
+
"loss": 0.3384,
|
| 892 |
+
"step": 125
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.6258064516129034,
|
| 896 |
+
"grad_norm": 0.09276702527842776,
|
| 897 |
+
"learning_rate": 0.00010227631978561056,
|
| 898 |
+
"loss": 0.3444,
|
| 899 |
+
"step": 126
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.6387096774193548,
|
| 903 |
+
"grad_norm": 0.08750152088472078,
|
| 904 |
+
"learning_rate": 0.00010075883152245334,
|
| 905 |
+
"loss": 0.3569,
|
| 906 |
+
"step": 127
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.6516129032258065,
|
| 910 |
+
"grad_norm": 0.08714445180642569,
|
| 911 |
+
"learning_rate": 9.92411684775467e-05,
|
| 912 |
+
"loss": 0.342,
|
| 913 |
+
"step": 128
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.664516129032258,
|
| 917 |
+
"grad_norm": 0.08469902272466831,
|
| 918 |
+
"learning_rate": 9.772368021438943e-05,
|
| 919 |
+
"loss": 0.3342,
|
| 920 |
+
"step": 129
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.6774193548387095,
|
| 924 |
+
"grad_norm": 0.08724585745005611,
|
| 925 |
+
"learning_rate": 9.620671625622288e-05,
|
| 926 |
+
"loss": 0.3335,
|
| 927 |
+
"step": 130
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.6903225806451614,
|
| 931 |
+
"grad_norm": 0.09087336723016343,
|
| 932 |
+
"learning_rate": 9.469062600552509e-05,
|
| 933 |
+
"loss": 0.3447,
|
| 934 |
+
"step": 131
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.7032258064516128,
|
| 938 |
+
"grad_norm": 0.08863278083042062,
|
| 939 |
+
"learning_rate": 9.317575866353292e-05,
|
| 940 |
+
"loss": 0.3487,
|
| 941 |
+
"step": 132
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.7161290322580647,
|
| 945 |
+
"grad_norm": 0.08343459715762,
|
| 946 |
+
"learning_rate": 9.166246314981066e-05,
|
| 947 |
+
"loss": 0.3454,
|
| 948 |
+
"step": 133
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.729032258064516,
|
| 952 |
+
"grad_norm": 0.08837483796029806,
|
| 953 |
+
"learning_rate": 9.015108802188313e-05,
|
| 954 |
+
"loss": 0.3484,
|
| 955 |
+
"step": 134
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.7419354838709677,
|
| 959 |
+
"grad_norm": 0.08762249376974672,
|
| 960 |
+
"learning_rate": 8.86419813949525e-05,
|
| 961 |
+
"loss": 0.3447,
|
| 962 |
+
"step": 135
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7548387096774194,
|
| 966 |
+
"grad_norm": 0.08446853010895118,
|
| 967 |
+
"learning_rate": 8.713549086171691e-05,
|
| 968 |
+
"loss": 0.3466,
|
| 969 |
+
"step": 136
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7677419354838708,
|
| 973 |
+
"grad_norm": 0.08897676787603495,
|
| 974 |
+
"learning_rate": 8.563196341230919e-05,
|
| 975 |
+
"loss": 0.3434,
|
| 976 |
+
"step": 137
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.7806451612903227,
|
| 980 |
+
"grad_norm": 0.09210810174866911,
|
| 981 |
+
"learning_rate": 8.413174535437487e-05,
|
| 982 |
+
"loss": 0.355,
|
| 983 |
+
"step": 138
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.793548387096774,
|
| 987 |
+
"grad_norm": 0.0877098792555575,
|
| 988 |
+
"learning_rate": 8.263518223330697e-05,
|
| 989 |
+
"loss": 0.3392,
|
| 990 |
+
"step": 139
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.8064516129032258,
|
| 994 |
+
"grad_norm": 0.09059259587839792,
|
| 995 |
+
"learning_rate": 8.114261875265643e-05,
|
| 996 |
+
"loss": 0.3465,
|
| 997 |
+
"step": 140
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.8193548387096774,
|
| 1001 |
+
"grad_norm": 0.09043152099082513,
|
| 1002 |
+
"learning_rate": 7.965439869473664e-05,
|
| 1003 |
+
"loss": 0.3409,
|
| 1004 |
+
"step": 141
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.832258064516129,
|
| 1008 |
+
"grad_norm": 0.08863483273837267,
|
| 1009 |
+
"learning_rate": 7.817086484143986e-05,
|
| 1010 |
+
"loss": 0.3497,
|
| 1011 |
+
"step": 142
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.8451612903225807,
|
| 1015 |
+
"grad_norm": 0.08351509862847174,
|
| 1016 |
+
"learning_rate": 7.669235889528436e-05,
|
| 1017 |
+
"loss": 0.3484,
|
| 1018 |
+
"step": 143
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.8580645161290321,
|
| 1022 |
+
"grad_norm": 0.08881689002413959,
|
| 1023 |
+
"learning_rate": 7.521922140071002e-05,
|
| 1024 |
+
"loss": 0.3428,
|
| 1025 |
+
"step": 144
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.870967741935484,
|
| 1029 |
+
"grad_norm": 0.08962413300366581,
|
| 1030 |
+
"learning_rate": 7.375179166564063e-05,
|
| 1031 |
+
"loss": 0.3353,
|
| 1032 |
+
"step": 145
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.8838709677419354,
|
| 1036 |
+
"grad_norm": 0.08991947191225944,
|
| 1037 |
+
"learning_rate": 7.229040768333115e-05,
|
| 1038 |
+
"loss": 0.3366,
|
| 1039 |
+
"step": 146
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.896774193548387,
|
| 1043 |
+
"grad_norm": 0.0890545628104281,
|
| 1044 |
+
"learning_rate": 7.08354060545175e-05,
|
| 1045 |
+
"loss": 0.3381,
|
| 1046 |
+
"step": 147
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.9096774193548387,
|
| 1050 |
+
"grad_norm": 0.09306016588414409,
|
| 1051 |
+
"learning_rate": 6.93871219098876e-05,
|
| 1052 |
+
"loss": 0.3356,
|
| 1053 |
+
"step": 148
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.9225806451612903,
|
| 1057 |
+
"grad_norm": 0.08816048934545212,
|
| 1058 |
+
"learning_rate": 6.79458888328903e-05,
|
| 1059 |
+
"loss": 0.3412,
|
| 1060 |
+
"step": 149
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.935483870967742,
|
| 1064 |
+
"grad_norm": 0.09006593042575502,
|
| 1065 |
+
"learning_rate": 6.651203878290139e-05,
|
| 1066 |
+
"loss": 0.3471,
|
| 1067 |
+
"step": 150
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.9483870967741934,
|
| 1071 |
+
"grad_norm": 0.08499237638300171,
|
| 1072 |
+
"learning_rate": 6.508590201876317e-05,
|
| 1073 |
+
"loss": 0.335,
|
| 1074 |
+
"step": 151
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.9612903225806453,
|
| 1078 |
+
"grad_norm": 0.09566747308379261,
|
| 1079 |
+
"learning_rate": 6.366780702271589e-05,
|
| 1080 |
+
"loss": 0.3395,
|
| 1081 |
+
"step": 152
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.9741935483870967,
|
| 1085 |
+
"grad_norm": 0.0915253754596643,
|
| 1086 |
+
"learning_rate": 6.225808042473858e-05,
|
| 1087 |
+
"loss": 0.3488,
|
| 1088 |
+
"step": 153
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.9870967741935484,
|
| 1092 |
+
"grad_norm": 0.08657357278603872,
|
| 1093 |
+
"learning_rate": 6.085704692731609e-05,
|
| 1094 |
+
"loss": 0.3344,
|
| 1095 |
+
"step": 154
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.0,
|
| 1099 |
+
"grad_norm": 0.08950726731743963,
|
| 1100 |
+
"learning_rate": 5.9465029230650534e-05,
|
| 1101 |
+
"loss": 0.33,
|
| 1102 |
+
"step": 155
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.0,
|
| 1106 |
+
"eval_loss": 0.35439133644104004,
|
| 1107 |
+
"eval_runtime": 36.1469,
|
| 1108 |
+
"eval_samples_per_second": 28.744,
|
| 1109 |
+
"eval_steps_per_second": 0.913,
|
| 1110 |
+
"step": 155
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.0129032258064514,
|
| 1114 |
+
"grad_norm": 0.08961232668946545,
|
| 1115 |
+
"learning_rate": 5.8082347958333625e-05,
|
| 1116 |
+
"loss": 0.3273,
|
| 1117 |
+
"step": 156
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.0258064516129033,
|
| 1121 |
+
"grad_norm": 0.09402916213349197,
|
| 1122 |
+
"learning_rate": 5.670932158349731e-05,
|
| 1123 |
+
"loss": 0.3218,
|
| 1124 |
+
"step": 157
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.0387096774193547,
|
| 1128 |
+
"grad_norm": 0.08520247695821515,
|
| 1129 |
+
"learning_rate": 5.5346266355459995e-05,
|
| 1130 |
+
"loss": 0.3089,
|
| 1131 |
+
"step": 158
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.0516129032258066,
|
| 1135 |
+
"grad_norm": 0.08637288183919145,
|
| 1136 |
+
"learning_rate": 5.399349622688479e-05,
|
| 1137 |
+
"loss": 0.3266,
|
| 1138 |
+
"step": 159
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.064516129032258,
|
| 1142 |
+
"grad_norm": 0.08823864345930746,
|
| 1143 |
+
"learning_rate": 5.26513227814666e-05,
|
| 1144 |
+
"loss": 0.329,
|
| 1145 |
+
"step": 160
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 2.07741935483871,
|
| 1149 |
+
"grad_norm": 0.09384371931382793,
|
| 1150 |
+
"learning_rate": 5.1320055162165115e-05,
|
| 1151 |
+
"loss": 0.3275,
|
| 1152 |
+
"step": 161
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 2.0903225806451613,
|
| 1156 |
+
"grad_norm": 0.09516405744887674,
|
| 1157 |
+
"learning_rate": 5.000000000000002e-05,
|
| 1158 |
+
"loss": 0.332,
|
| 1159 |
+
"step": 162
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 2.1032258064516127,
|
| 1163 |
+
"grad_norm": 0.08966279182804247,
|
| 1164 |
+
"learning_rate": 4.869146134342426e-05,
|
| 1165 |
+
"loss": 0.3247,
|
| 1166 |
+
"step": 163
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 2.1161290322580646,
|
| 1170 |
+
"grad_norm": 0.08700940402163973,
|
| 1171 |
+
"learning_rate": 4.739474058829289e-05,
|
| 1172 |
+
"loss": 0.3221,
|
| 1173 |
+
"step": 164
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.129032258064516,
|
| 1177 |
+
"grad_norm": 0.08984677102800173,
|
| 1178 |
+
"learning_rate": 4.611013640844245e-05,
|
| 1179 |
+
"loss": 0.3272,
|
| 1180 |
+
"step": 165
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 2.141935483870968,
|
| 1184 |
+
"grad_norm": 0.08964202186304891,
|
| 1185 |
+
"learning_rate": 4.483794468689728e-05,
|
| 1186 |
+
"loss": 0.3188,
|
| 1187 |
+
"step": 166
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 2.1548387096774193,
|
| 1191 |
+
"grad_norm": 0.09997697429798251,
|
| 1192 |
+
"learning_rate": 4.357845844771881e-05,
|
| 1193 |
+
"loss": 0.3383,
|
| 1194 |
+
"step": 167
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.167741935483871,
|
| 1198 |
+
"grad_norm": 0.09510073376177604,
|
| 1199 |
+
"learning_rate": 4.2331967788513295e-05,
|
| 1200 |
+
"loss": 0.3252,
|
| 1201 |
+
"step": 168
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.1806451612903226,
|
| 1205 |
+
"grad_norm": 0.09107612709336496,
|
| 1206 |
+
"learning_rate": 4.109875981361363e-05,
|
| 1207 |
+
"loss": 0.3217,
|
| 1208 |
+
"step": 169
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 2.193548387096774,
|
| 1212 |
+
"grad_norm": 0.08804927379783276,
|
| 1213 |
+
"learning_rate": 3.987911856795047e-05,
|
| 1214 |
+
"loss": 0.3173,
|
| 1215 |
+
"step": 170
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.206451612903226,
|
| 1219 |
+
"grad_norm": 0.0916081059987062,
|
| 1220 |
+
"learning_rate": 3.8673324971628357e-05,
|
| 1221 |
+
"loss": 0.3285,
|
| 1222 |
+
"step": 171
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 2.2193548387096773,
|
| 1226 |
+
"grad_norm": 0.09226628432750343,
|
| 1227 |
+
"learning_rate": 3.7481656755221125e-05,
|
| 1228 |
+
"loss": 0.3154,
|
| 1229 |
+
"step": 172
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 2.232258064516129,
|
| 1233 |
+
"grad_norm": 0.09145015878266409,
|
| 1234 |
+
"learning_rate": 3.630438839580217e-05,
|
| 1235 |
+
"loss": 0.3087,
|
| 1236 |
+
"step": 173
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 2.2451612903225806,
|
| 1240 |
+
"grad_norm": 0.08786201399591659,
|
| 1241 |
+
"learning_rate": 3.5141791053724405e-05,
|
| 1242 |
+
"loss": 0.3151,
|
| 1243 |
+
"step": 174
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 2.258064516129032,
|
| 1247 |
+
"grad_norm": 0.09259402512083086,
|
| 1248 |
+
"learning_rate": 3.399413251016359e-05,
|
| 1249 |
+
"loss": 0.3369,
|
| 1250 |
+
"step": 175
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 2.270967741935484,
|
| 1254 |
+
"grad_norm": 0.09311260751337232,
|
| 1255 |
+
"learning_rate": 3.2861677105440336e-05,
|
| 1256 |
+
"loss": 0.3051,
|
| 1257 |
+
"step": 176
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.2838709677419353,
|
| 1261 |
+
"grad_norm": 0.09217712904693832,
|
| 1262 |
+
"learning_rate": 3.174468567813461e-05,
|
| 1263 |
+
"loss": 0.3199,
|
| 1264 |
+
"step": 177
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.296774193548387,
|
| 1268 |
+
"grad_norm": 0.09141877592974519,
|
| 1269 |
+
"learning_rate": 3.0643415505006735e-05,
|
| 1270 |
+
"loss": 0.3229,
|
| 1271 |
+
"step": 178
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 2.3096774193548386,
|
| 1275 |
+
"grad_norm": 0.09528833689903496,
|
| 1276 |
+
"learning_rate": 2.9558120241738784e-05,
|
| 1277 |
+
"loss": 0.3286,
|
| 1278 |
+
"step": 179
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 2.3225806451612905,
|
| 1282 |
+
"grad_norm": 0.09070636787107308,
|
| 1283 |
+
"learning_rate": 2.8489049864510054e-05,
|
| 1284 |
+
"loss": 0.3348,
|
| 1285 |
+
"step": 180
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 2.335483870967742,
|
| 1289 |
+
"grad_norm": 0.09307512327341362,
|
| 1290 |
+
"learning_rate": 2.7436450612420095e-05,
|
| 1291 |
+
"loss": 0.3256,
|
| 1292 |
+
"step": 181
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 2.3483870967741938,
|
| 1296 |
+
"grad_norm": 0.09127823479306682,
|
| 1297 |
+
"learning_rate": 2.640056493077231e-05,
|
| 1298 |
+
"loss": 0.3181,
|
| 1299 |
+
"step": 182
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.361290322580645,
|
| 1303 |
+
"grad_norm": 0.09246009256113925,
|
| 1304 |
+
"learning_rate": 2.5381631415231454e-05,
|
| 1305 |
+
"loss": 0.3391,
|
| 1306 |
+
"step": 183
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.3741935483870966,
|
| 1310 |
+
"grad_norm": 0.09095352379758655,
|
| 1311 |
+
"learning_rate": 2.4379884756868167e-05,
|
| 1312 |
+
"loss": 0.3172,
|
| 1313 |
+
"step": 184
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.3870967741935485,
|
| 1317 |
+
"grad_norm": 0.0926880163626768,
|
| 1318 |
+
"learning_rate": 2.339555568810221e-05,
|
| 1319 |
+
"loss": 0.3177,
|
| 1320 |
+
"step": 185
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.4,
|
| 1324 |
+
"grad_norm": 0.09094474131194094,
|
| 1325 |
+
"learning_rate": 2.242887092955801e-05,
|
| 1326 |
+
"loss": 0.3199,
|
| 1327 |
+
"step": 186
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.412903225806452,
|
| 1331 |
+
"grad_norm": 0.09106546035353981,
|
| 1332 |
+
"learning_rate": 2.1480053137844115e-05,
|
| 1333 |
+
"loss": 0.3222,
|
| 1334 |
+
"step": 187
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.425806451612903,
|
| 1338 |
+
"grad_norm": 0.08873018715134598,
|
| 1339 |
+
"learning_rate": 2.054932085426856e-05,
|
| 1340 |
+
"loss": 0.3118,
|
| 1341 |
+
"step": 188
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 2.4387096774193546,
|
| 1345 |
+
"grad_norm": 0.0932765377498955,
|
| 1346 |
+
"learning_rate": 1.9636888454502178e-05,
|
| 1347 |
+
"loss": 0.3358,
|
| 1348 |
+
"step": 189
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 2.4516129032258065,
|
| 1352 |
+
"grad_norm": 0.09181586534157822,
|
| 1353 |
+
"learning_rate": 1.8742966099201697e-05,
|
| 1354 |
+
"loss": 0.3157,
|
| 1355 |
+
"step": 190
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 2.464516129032258,
|
| 1359 |
+
"grad_norm": 0.0929486436457203,
|
| 1360 |
+
"learning_rate": 1.7867759685603114e-05,
|
| 1361 |
+
"loss": 0.3154,
|
| 1362 |
+
"step": 191
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.47741935483871,
|
| 1366 |
+
"grad_norm": 0.09188630220285351,
|
| 1367 |
+
"learning_rate": 1.7011470800097496e-05,
|
| 1368 |
+
"loss": 0.3181,
|
| 1369 |
+
"step": 192
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 2.490322580645161,
|
| 1373 |
+
"grad_norm": 0.09574286894431329,
|
| 1374 |
+
"learning_rate": 1.6174296671799572e-05,
|
| 1375 |
+
"loss": 0.3222,
|
| 1376 |
+
"step": 193
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 2.5032258064516126,
|
| 1380 |
+
"grad_norm": 0.09145354457132104,
|
| 1381 |
+
"learning_rate": 1.5356430127119913e-05,
|
| 1382 |
+
"loss": 0.3222,
|
| 1383 |
+
"step": 194
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 2.5161290322580645,
|
| 1387 |
+
"grad_norm": 0.09039580690260736,
|
| 1388 |
+
"learning_rate": 1.4558059545351143e-05,
|
| 1389 |
+
"loss": 0.324,
|
| 1390 |
+
"step": 195
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 2.5290322580645164,
|
| 1394 |
+
"grad_norm": 0.08979381831653434,
|
| 1395 |
+
"learning_rate": 1.3779368815278647e-05,
|
| 1396 |
+
"loss": 0.3107,
|
| 1397 |
+
"step": 196
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 2.541935483870968,
|
| 1401 |
+
"grad_norm": 0.09526292697431937,
|
| 1402 |
+
"learning_rate": 1.302053729282533e-05,
|
| 1403 |
+
"loss": 0.3219,
|
| 1404 |
+
"step": 197
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.554838709677419,
|
| 1408 |
+
"grad_norm": 0.09310358146453943,
|
| 1409 |
+
"learning_rate": 1.2281739759740574e-05,
|
| 1410 |
+
"loss": 0.3214,
|
| 1411 |
+
"step": 198
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 2.567741935483871,
|
| 1415 |
+
"grad_norm": 0.09212645063531479,
|
| 1416 |
+
"learning_rate": 1.1563146383342772e-05,
|
| 1417 |
+
"loss": 0.3154,
|
| 1418 |
+
"step": 199
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 2.5806451612903225,
|
| 1422 |
+
"grad_norm": 0.09533681862557382,
|
| 1423 |
+
"learning_rate": 1.0864922677324618e-05,
|
| 1424 |
+
"loss": 0.319,
|
| 1425 |
+
"step": 200
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.5935483870967744,
|
| 1429 |
+
"grad_norm": 0.09551418366783314,
|
| 1430 |
+
"learning_rate": 1.01872294636304e-05,
|
| 1431 |
+
"loss": 0.3333,
|
| 1432 |
+
"step": 201
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 2.606451612903226,
|
| 1436 |
+
"grad_norm": 0.08930212325894361,
|
| 1437 |
+
"learning_rate": 9.530222835413738e-06,
|
| 1438 |
+
"loss": 0.3048,
|
| 1439 |
+
"step": 202
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 2.6193548387096772,
|
| 1443 |
+
"grad_norm": 0.09220378121771236,
|
| 1444 |
+
"learning_rate": 8.894054121084838e-06,
|
| 1445 |
+
"loss": 0.3146,
|
| 1446 |
+
"step": 203
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 2.632258064516129,
|
| 1450 |
+
"grad_norm": 0.09150774720724307,
|
| 1451 |
+
"learning_rate": 8.278869849454718e-06,
|
| 1452 |
+
"loss": 0.3311,
|
| 1453 |
+
"step": 204
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 2.6451612903225805,
|
| 1457 |
+
"grad_norm": 0.09261513270619316,
|
| 1458 |
+
"learning_rate": 7.684811715985429e-06,
|
| 1459 |
+
"loss": 0.3172,
|
| 1460 |
+
"step": 205
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 2.6580645161290324,
|
| 1464 |
+
"grad_norm": 0.0941004102909483,
|
| 1465 |
+
"learning_rate": 7.1120165501533e-06,
|
| 1466 |
+
"loss": 0.3347,
|
| 1467 |
+
"step": 206
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 2.670967741935484,
|
| 1471 |
+
"grad_norm": 0.08707518610128166,
|
| 1472 |
+
"learning_rate": 6.560616283932897e-06,
|
| 1473 |
+
"loss": 0.3116,
|
| 1474 |
+
"step": 207
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 2.6838709677419352,
|
| 1478 |
+
"grad_norm": 0.08648707636296159,
|
| 1479 |
+
"learning_rate": 6.030737921409169e-06,
|
| 1480 |
+
"loss": 0.3144,
|
| 1481 |
+
"step": 208
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 2.696774193548387,
|
| 1485 |
+
"grad_norm": 0.09169150101119816,
|
| 1486 |
+
"learning_rate": 5.52250350952459e-06,
|
| 1487 |
+
"loss": 0.3255,
|
| 1488 |
+
"step": 209
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 2.709677419354839,
|
| 1492 |
+
"grad_norm": 0.09060072523264334,
|
| 1493 |
+
"learning_rate": 5.036030109968082e-06,
|
| 1494 |
+
"loss": 0.3183,
|
| 1495 |
+
"step": 210
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 2.7225806451612904,
|
| 1499 |
+
"grad_norm": 0.09077216490604942,
|
| 1500 |
+
"learning_rate": 4.5714297722121106e-06,
|
| 1501 |
+
"loss": 0.321,
|
| 1502 |
+
"step": 211
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 2.735483870967742,
|
| 1506 |
+
"grad_norm": 0.09088968433443333,
|
| 1507 |
+
"learning_rate": 4.128809507704445e-06,
|
| 1508 |
+
"loss": 0.3172,
|
| 1509 |
+
"step": 212
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 2.7483870967741937,
|
| 1513 |
+
"grad_norm": 0.09191902683388614,
|
| 1514 |
+
"learning_rate": 3.7082712652200867e-06,
|
| 1515 |
+
"loss": 0.3261,
|
| 1516 |
+
"step": 213
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 2.761290322580645,
|
| 1520 |
+
"grad_norm": 0.08843215800144302,
|
| 1521 |
+
"learning_rate": 3.3099119073793928e-06,
|
| 1522 |
+
"loss": 0.3158,
|
| 1523 |
+
"step": 214
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 2.774193548387097,
|
| 1527 |
+
"grad_norm": 0.09079938334868655,
|
| 1528 |
+
"learning_rate": 2.9338231883378366e-06,
|
| 1529 |
+
"loss": 0.3178,
|
| 1530 |
+
"step": 215
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 2.7870967741935484,
|
| 1534 |
+
"grad_norm": 0.09122789808454786,
|
| 1535 |
+
"learning_rate": 2.580091732652101e-06,
|
| 1536 |
+
"loss": 0.3282,
|
| 1537 |
+
"step": 216
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 2.8,
|
| 1541 |
+
"grad_norm": 0.09380292374109117,
|
| 1542 |
+
"learning_rate": 2.248799015327907e-06,
|
| 1543 |
+
"loss": 0.3359,
|
| 1544 |
+
"step": 217
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 2.8129032258064517,
|
| 1548 |
+
"grad_norm": 0.09035917420929797,
|
| 1549 |
+
"learning_rate": 1.9400213430538773e-06,
|
| 1550 |
+
"loss": 0.3169,
|
| 1551 |
+
"step": 218
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 2.825806451612903,
|
| 1555 |
+
"grad_norm": 0.09195121657817087,
|
| 1556 |
+
"learning_rate": 1.6538298366257976e-06,
|
| 1557 |
+
"loss": 0.3314,
|
| 1558 |
+
"step": 219
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 2.838709677419355,
|
| 1562 |
+
"grad_norm": 0.09166102367139951,
|
| 1563 |
+
"learning_rate": 1.3902904145653096e-06,
|
| 1564 |
+
"loss": 0.3258,
|
| 1565 |
+
"step": 220
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 2.8516129032258064,
|
| 1569 |
+
"grad_norm": 0.0921992572010057,
|
| 1570 |
+
"learning_rate": 1.1494637779369766e-06,
|
| 1571 |
+
"loss": 0.3298,
|
| 1572 |
+
"step": 221
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 2.864516129032258,
|
| 1576 |
+
"grad_norm": 0.09068261067988724,
|
| 1577 |
+
"learning_rate": 9.314053963669245e-07,
|
| 1578 |
+
"loss": 0.3214,
|
| 1579 |
+
"step": 222
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 2.8774193548387097,
|
| 1583 |
+
"grad_norm": 0.09417924199778298,
|
| 1584 |
+
"learning_rate": 7.361654952665609e-07,
|
| 1585 |
+
"loss": 0.3134,
|
| 1586 |
+
"step": 223
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 2.8903225806451616,
|
| 1590 |
+
"grad_norm": 0.0901765977296441,
|
| 1591 |
+
"learning_rate": 5.637890442641402e-07,
|
| 1592 |
+
"loss": 0.3221,
|
| 1593 |
+
"step": 224
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 2.903225806451613,
|
| 1597 |
+
"grad_norm": 0.09094506589085496,
|
| 1598 |
+
"learning_rate": 4.143157468468717e-07,
|
| 1599 |
+
"loss": 0.3128,
|
| 1600 |
+
"step": 225
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.9161290322580644,
|
| 1604 |
+
"grad_norm": 0.08772549933058231,
|
| 1605 |
+
"learning_rate": 2.877800312160783e-07,
|
| 1606 |
+
"loss": 0.3248,
|
| 1607 |
+
"step": 226
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.9290322580645163,
|
| 1611 |
+
"grad_norm": 0.09191883931659987,
|
| 1612 |
+
"learning_rate": 1.8421104235727405e-07,
|
| 1613 |
+
"loss": 0.3114,
|
| 1614 |
+
"step": 227
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.9419354838709677,
|
| 1618 |
+
"grad_norm": 0.08876137430429,
|
| 1619 |
+
"learning_rate": 1.0363263532724432e-07,
|
| 1620 |
+
"loss": 0.3127,
|
| 1621 |
+
"step": 228
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.9548387096774196,
|
| 1625 |
+
"grad_norm": 0.09157045134043748,
|
| 1626 |
+
"learning_rate": 4.606336975948589e-08,
|
| 1627 |
+
"loss": 0.3275,
|
| 1628 |
+
"step": 229
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.967741935483871,
|
| 1632 |
+
"grad_norm": 0.08940213355520302,
|
| 1633 |
+
"learning_rate": 1.1516505589381776e-08,
|
| 1634 |
+
"loss": 0.3246,
|
| 1635 |
+
"step": 230
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.9806451612903224,
|
| 1639 |
+
"grad_norm": 0.0895898052255747,
|
| 1640 |
+
"learning_rate": 0.0,
|
| 1641 |
+
"loss": 0.3079,
|
| 1642 |
+
"step": 231
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 2.9806451612903224,
|
| 1646 |
+
"eval_loss": 0.3507891595363617,
|
| 1647 |
+
"eval_runtime": 36.0777,
|
| 1648 |
+
"eval_samples_per_second": 28.799,
|
| 1649 |
+
"eval_steps_per_second": 0.915,
|
| 1650 |
+
"step": 231
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.9806451612903224,
|
| 1654 |
+
"step": 231,
|
| 1655 |
+
"total_flos": 9.324729662937498e+16,
|
| 1656 |
+
"train_loss": 0.3951803825118325,
|
| 1657 |
+
"train_runtime": 2997.4381,
|
| 1658 |
+
"train_samples_per_second": 9.871,
|
| 1659 |
+
"train_steps_per_second": 0.077
|
| 1660 |
+
}
|
| 1661 |
+
],
|
| 1662 |
+
"logging_steps": 1,
|
| 1663 |
+
"max_steps": 231,
|
| 1664 |
+
"num_input_tokens_seen": 0,
|
| 1665 |
+
"num_train_epochs": 3,
|
| 1666 |
+
"save_steps": 500,
|
| 1667 |
+
"stateful_callbacks": {
|
| 1668 |
+
"TrainerControl": {
|
| 1669 |
+
"args": {
|
| 1670 |
+
"should_epoch_stop": false,
|
| 1671 |
+
"should_evaluate": false,
|
| 1672 |
+
"should_log": false,
|
| 1673 |
+
"should_save": true,
|
| 1674 |
+
"should_training_stop": true
|
| 1675 |
+
},
|
| 1676 |
+
"attributes": {}
|
| 1677 |
+
}
|
| 1678 |
+
},
|
| 1679 |
+
"total_flos": 9.324729662937498e+16,
|
| 1680 |
+
"train_batch_size": 8,
|
| 1681 |
+
"trial_name": null,
|
| 1682 |
+
"trial_params": null
|
| 1683 |
+
}
|