Commit
•
bd7c687
1
Parent(s):
8f1dc49
Model save
Browse files- README.md +95 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1496 -0
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: Llama-31-8B_task-3_120-samples_config-3
|
| 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 |
+
# Llama-31-8B_task-3_120-samples_config-3
|
| 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 the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.5313
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 150
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
+
| 2.3729 | 1.0 | 11 | 2.4972 |
|
| 57 |
+
| 2.6938 | 2.0 | 22 | 2.4571 |
|
| 58 |
+
| 2.6474 | 3.0 | 33 | 2.3881 |
|
| 59 |
+
| 2.2763 | 4.0 | 44 | 2.2642 |
|
| 60 |
+
| 2.0268 | 5.0 | 55 | 2.0694 |
|
| 61 |
+
| 1.7309 | 6.0 | 66 | 1.7871 |
|
| 62 |
+
| 1.4481 | 7.0 | 77 | 1.4330 |
|
| 63 |
+
| 1.0554 | 8.0 | 88 | 1.0675 |
|
| 64 |
+
| 0.8392 | 9.0 | 99 | 0.7563 |
|
| 65 |
+
| 0.4685 | 10.0 | 110 | 0.6437 |
|
| 66 |
+
| 0.3588 | 11.0 | 121 | 0.5851 |
|
| 67 |
+
| 0.6319 | 12.0 | 132 | 0.5407 |
|
| 68 |
+
| 0.4211 | 13.0 | 143 | 0.5248 |
|
| 69 |
+
| 0.495 | 14.0 | 154 | 0.5127 |
|
| 70 |
+
| 0.4232 | 15.0 | 165 | 0.5019 |
|
| 71 |
+
| 0.496 | 16.0 | 176 | 0.5103 |
|
| 72 |
+
| 0.3903 | 17.0 | 187 | 0.4814 |
|
| 73 |
+
| 0.331 | 18.0 | 198 | 0.4913 |
|
| 74 |
+
| 0.2403 | 19.0 | 209 | 0.4869 |
|
| 75 |
+
| 0.3563 | 20.0 | 220 | 0.4718 |
|
| 76 |
+
| 0.4107 | 21.0 | 231 | 0.4596 |
|
| 77 |
+
| 0.2631 | 22.0 | 242 | 0.4478 |
|
| 78 |
+
| 0.4212 | 23.0 | 253 | 0.4496 |
|
| 79 |
+
| 0.3304 | 24.0 | 264 | 0.4408 |
|
| 80 |
+
| 0.3296 | 25.0 | 275 | 0.4437 |
|
| 81 |
+
| 0.3266 | 26.0 | 286 | 0.4441 |
|
| 82 |
+
| 0.1403 | 27.0 | 297 | 0.4496 |
|
| 83 |
+
| 0.1732 | 28.0 | 308 | 0.4574 |
|
| 84 |
+
| 0.1797 | 29.0 | 319 | 0.4809 |
|
| 85 |
+
| 0.1355 | 30.0 | 330 | 0.4990 |
|
| 86 |
+
| 0.1346 | 31.0 | 341 | 0.5313 |
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
### Framework versions
|
| 90 |
+
|
| 91 |
+
- PEFT 0.12.0
|
| 92 |
+
- Transformers 4.44.0
|
| 93 |
+
- Pytorch 2.1.2+cu121
|
| 94 |
+
- Datasets 2.20.0
|
| 95 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf6624e2e473dedd57eed1ac9f52903eed1ed135e8b8230a63afbb3ad6748e9b
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 31.0,
|
| 3 |
+
"total_flos": 2.1292989192077312e+17,
|
| 4 |
+
"train_loss": 0.8120344140050698,
|
| 5 |
+
"train_runtime": 7851.2602,
|
| 6 |
+
"train_samples": 88,
|
| 7 |
+
"train_samples_per_second": 1.681,
|
| 8 |
+
"train_steps_per_second": 0.21
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 31.0,
|
| 3 |
+
"total_flos": 2.1292989192077312e+17,
|
| 4 |
+
"train_loss": 0.8120344140050698,
|
| 5 |
+
"train_runtime": 7851.2602,
|
| 6 |
+
"train_samples": 88,
|
| 7 |
+
"train_samples_per_second": 1.681,
|
| 8 |
+
"train_steps_per_second": 0.21
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1496 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.44082728028297424,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-3_120-samples_config-3/checkpoint-264",
|
| 4 |
+
"epoch": 31.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 341,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09090909090909091,
|
| 13 |
+
"grad_norm": 3.931244373321533,
|
| 14 |
+
"learning_rate": 6.060606060606061e-08,
|
| 15 |
+
"loss": 3.095,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18181818181818182,
|
| 20 |
+
"grad_norm": 2.530280828475952,
|
| 21 |
+
"learning_rate": 1.2121212121212122e-07,
|
| 22 |
+
"loss": 2.5399,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.36363636363636365,
|
| 27 |
+
"grad_norm": 2.5952248573303223,
|
| 28 |
+
"learning_rate": 2.4242424242424244e-07,
|
| 29 |
+
"loss": 2.5861,
|
| 30 |
+
"step": 4
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5454545454545454,
|
| 34 |
+
"grad_norm": 2.0955796241760254,
|
| 35 |
+
"learning_rate": 3.6363636363636366e-07,
|
| 36 |
+
"loss": 2.4442,
|
| 37 |
+
"step": 6
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.7272727272727273,
|
| 41 |
+
"grad_norm": 3.4685494899749756,
|
| 42 |
+
"learning_rate": 4.848484848484849e-07,
|
| 43 |
+
"loss": 2.4938,
|
| 44 |
+
"step": 8
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.9090909090909091,
|
| 48 |
+
"grad_norm": 3.055572509765625,
|
| 49 |
+
"learning_rate": 6.060606060606061e-07,
|
| 50 |
+
"loss": 2.3729,
|
| 51 |
+
"step": 10
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0,
|
| 55 |
+
"eval_loss": 2.4972100257873535,
|
| 56 |
+
"eval_runtime": 21.0088,
|
| 57 |
+
"eval_samples_per_second": 1.142,
|
| 58 |
+
"eval_steps_per_second": 1.142,
|
| 59 |
+
"step": 11
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.0909090909090908,
|
| 63 |
+
"grad_norm": 2.5200321674346924,
|
| 64 |
+
"learning_rate": 7.272727272727273e-07,
|
| 65 |
+
"loss": 2.4004,
|
| 66 |
+
"step": 12
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.2727272727272727,
|
| 70 |
+
"grad_norm": 2.5053160190582275,
|
| 71 |
+
"learning_rate": 8.484848484848486e-07,
|
| 72 |
+
"loss": 2.3639,
|
| 73 |
+
"step": 14
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.4545454545454546,
|
| 77 |
+
"grad_norm": 2.5543558597564697,
|
| 78 |
+
"learning_rate": 9.696969696969698e-07,
|
| 79 |
+
"loss": 2.7736,
|
| 80 |
+
"step": 16
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.6363636363636362,
|
| 84 |
+
"grad_norm": 2.6235134601593018,
|
| 85 |
+
"learning_rate": 1.090909090909091e-06,
|
| 86 |
+
"loss": 2.3351,
|
| 87 |
+
"step": 18
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.8181818181818183,
|
| 91 |
+
"grad_norm": 2.2782557010650635,
|
| 92 |
+
"learning_rate": 1.2121212121212122e-06,
|
| 93 |
+
"loss": 2.4073,
|
| 94 |
+
"step": 20
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 2.0,
|
| 98 |
+
"grad_norm": 3.364241123199463,
|
| 99 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 100 |
+
"loss": 2.6938,
|
| 101 |
+
"step": 22
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.0,
|
| 105 |
+
"eval_loss": 2.457120180130005,
|
| 106 |
+
"eval_runtime": 20.9973,
|
| 107 |
+
"eval_samples_per_second": 1.143,
|
| 108 |
+
"eval_steps_per_second": 1.143,
|
| 109 |
+
"step": 22
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.1818181818181817,
|
| 113 |
+
"grad_norm": 2.8939199447631836,
|
| 114 |
+
"learning_rate": 1.4545454545454546e-06,
|
| 115 |
+
"loss": 2.6378,
|
| 116 |
+
"step": 24
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.3636363636363638,
|
| 120 |
+
"grad_norm": 1.724478006362915,
|
| 121 |
+
"learning_rate": 1.5757575757575759e-06,
|
| 122 |
+
"loss": 2.3463,
|
| 123 |
+
"step": 26
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.5454545454545454,
|
| 127 |
+
"grad_norm": 3.102917194366455,
|
| 128 |
+
"learning_rate": 1.6969696969696973e-06,
|
| 129 |
+
"loss": 2.3407,
|
| 130 |
+
"step": 28
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.7272727272727275,
|
| 134 |
+
"grad_norm": 2.207613945007324,
|
| 135 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 136 |
+
"loss": 2.4054,
|
| 137 |
+
"step": 30
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 2.909090909090909,
|
| 141 |
+
"grad_norm": 3.5173332691192627,
|
| 142 |
+
"learning_rate": 1.9393939393939395e-06,
|
| 143 |
+
"loss": 2.6474,
|
| 144 |
+
"step": 32
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.0,
|
| 148 |
+
"eval_loss": 2.3881404399871826,
|
| 149 |
+
"eval_runtime": 20.9969,
|
| 150 |
+
"eval_samples_per_second": 1.143,
|
| 151 |
+
"eval_steps_per_second": 1.143,
|
| 152 |
+
"step": 33
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.090909090909091,
|
| 156 |
+
"grad_norm": 2.588070869445801,
|
| 157 |
+
"learning_rate": 2.0606060606060607e-06,
|
| 158 |
+
"loss": 2.2888,
|
| 159 |
+
"step": 34
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.2727272727272725,
|
| 163 |
+
"grad_norm": 3.921119451522827,
|
| 164 |
+
"learning_rate": 2.181818181818182e-06,
|
| 165 |
+
"loss": 2.858,
|
| 166 |
+
"step": 36
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.4545454545454546,
|
| 170 |
+
"grad_norm": 3.1361024379730225,
|
| 171 |
+
"learning_rate": 2.303030303030303e-06,
|
| 172 |
+
"loss": 2.292,
|
| 173 |
+
"step": 38
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.6363636363636362,
|
| 177 |
+
"grad_norm": 2.6496403217315674,
|
| 178 |
+
"learning_rate": 2.4242424242424244e-06,
|
| 179 |
+
"loss": 2.2874,
|
| 180 |
+
"step": 40
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.8181818181818183,
|
| 184 |
+
"grad_norm": 1.7044334411621094,
|
| 185 |
+
"learning_rate": 2.5454545454545456e-06,
|
| 186 |
+
"loss": 2.0497,
|
| 187 |
+
"step": 42
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 4.0,
|
| 191 |
+
"grad_norm": 2.6162171363830566,
|
| 192 |
+
"learning_rate": 2.666666666666667e-06,
|
| 193 |
+
"loss": 2.2763,
|
| 194 |
+
"step": 44
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.0,
|
| 198 |
+
"eval_loss": 2.264249801635742,
|
| 199 |
+
"eval_runtime": 21.0004,
|
| 200 |
+
"eval_samples_per_second": 1.143,
|
| 201 |
+
"eval_steps_per_second": 1.143,
|
| 202 |
+
"step": 44
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.181818181818182,
|
| 206 |
+
"grad_norm": 3.5348732471466064,
|
| 207 |
+
"learning_rate": 2.7878787878787885e-06,
|
| 208 |
+
"loss": 2.486,
|
| 209 |
+
"step": 46
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.363636363636363,
|
| 213 |
+
"grad_norm": 1.8792097568511963,
|
| 214 |
+
"learning_rate": 2.9090909090909093e-06,
|
| 215 |
+
"loss": 2.0279,
|
| 216 |
+
"step": 48
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 4.545454545454545,
|
| 220 |
+
"grad_norm": 3.1981241703033447,
|
| 221 |
+
"learning_rate": 3.0303030303030305e-06,
|
| 222 |
+
"loss": 2.279,
|
| 223 |
+
"step": 50
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 4.7272727272727275,
|
| 227 |
+
"grad_norm": 2.5685250759124756,
|
| 228 |
+
"learning_rate": 3.1515151515151517e-06,
|
| 229 |
+
"loss": 2.1978,
|
| 230 |
+
"step": 52
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.909090909090909,
|
| 234 |
+
"grad_norm": 2.161813497543335,
|
| 235 |
+
"learning_rate": 3.272727272727273e-06,
|
| 236 |
+
"loss": 2.0268,
|
| 237 |
+
"step": 54
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 5.0,
|
| 241 |
+
"eval_loss": 2.069439649581909,
|
| 242 |
+
"eval_runtime": 20.9965,
|
| 243 |
+
"eval_samples_per_second": 1.143,
|
| 244 |
+
"eval_steps_per_second": 1.143,
|
| 245 |
+
"step": 55
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.090909090909091,
|
| 249 |
+
"grad_norm": 2.084135055541992,
|
| 250 |
+
"learning_rate": 3.3939393939393946e-06,
|
| 251 |
+
"loss": 1.9478,
|
| 252 |
+
"step": 56
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.2727272727272725,
|
| 256 |
+
"grad_norm": 2.176788806915283,
|
| 257 |
+
"learning_rate": 3.5151515151515154e-06,
|
| 258 |
+
"loss": 1.9753,
|
| 259 |
+
"step": 58
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.454545454545454,
|
| 263 |
+
"grad_norm": 4.001251220703125,
|
| 264 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 265 |
+
"loss": 2.1318,
|
| 266 |
+
"step": 60
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.636363636363637,
|
| 270 |
+
"grad_norm": 3.4586737155914307,
|
| 271 |
+
"learning_rate": 3.757575757575758e-06,
|
| 272 |
+
"loss": 1.9426,
|
| 273 |
+
"step": 62
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 5.818181818181818,
|
| 277 |
+
"grad_norm": 3.11710786819458,
|
| 278 |
+
"learning_rate": 3.878787878787879e-06,
|
| 279 |
+
"loss": 1.9089,
|
| 280 |
+
"step": 64
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 6.0,
|
| 284 |
+
"grad_norm": 2.0227549076080322,
|
| 285 |
+
"learning_rate": 4.000000000000001e-06,
|
| 286 |
+
"loss": 1.7309,
|
| 287 |
+
"step": 66
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 6.0,
|
| 291 |
+
"eval_loss": 1.7871297597885132,
|
| 292 |
+
"eval_runtime": 20.9996,
|
| 293 |
+
"eval_samples_per_second": 1.143,
|
| 294 |
+
"eval_steps_per_second": 1.143,
|
| 295 |
+
"step": 66
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 6.181818181818182,
|
| 299 |
+
"grad_norm": 3.2912845611572266,
|
| 300 |
+
"learning_rate": 4.1212121212121215e-06,
|
| 301 |
+
"loss": 1.8532,
|
| 302 |
+
"step": 68
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.363636363636363,
|
| 306 |
+
"grad_norm": 2.7779335975646973,
|
| 307 |
+
"learning_rate": 4.242424242424243e-06,
|
| 308 |
+
"loss": 1.7371,
|
| 309 |
+
"step": 70
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.545454545454545,
|
| 313 |
+
"grad_norm": 1.3037850856781006,
|
| 314 |
+
"learning_rate": 4.363636363636364e-06,
|
| 315 |
+
"loss": 1.4541,
|
| 316 |
+
"step": 72
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 6.7272727272727275,
|
| 320 |
+
"grad_norm": 2.257749557495117,
|
| 321 |
+
"learning_rate": 4.4848484848484855e-06,
|
| 322 |
+
"loss": 1.5641,
|
| 323 |
+
"step": 74
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 6.909090909090909,
|
| 327 |
+
"grad_norm": 2.7067761421203613,
|
| 328 |
+
"learning_rate": 4.606060606060606e-06,
|
| 329 |
+
"loss": 1.4481,
|
| 330 |
+
"step": 76
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 7.0,
|
| 334 |
+
"eval_loss": 1.4330077171325684,
|
| 335 |
+
"eval_runtime": 21.0001,
|
| 336 |
+
"eval_samples_per_second": 1.143,
|
| 337 |
+
"eval_steps_per_second": 1.143,
|
| 338 |
+
"step": 77
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.090909090909091,
|
| 342 |
+
"grad_norm": 1.7599331140518188,
|
| 343 |
+
"learning_rate": 4.727272727272728e-06,
|
| 344 |
+
"loss": 1.3604,
|
| 345 |
+
"step": 78
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.2727272727272725,
|
| 349 |
+
"grad_norm": 1.4922908544540405,
|
| 350 |
+
"learning_rate": 4.848484848484849e-06,
|
| 351 |
+
"loss": 1.3767,
|
| 352 |
+
"step": 80
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.454545454545454,
|
| 356 |
+
"grad_norm": 2.4537432193756104,
|
| 357 |
+
"learning_rate": 4.9696969696969696e-06,
|
| 358 |
+
"loss": 1.2013,
|
| 359 |
+
"step": 82
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.636363636363637,
|
| 363 |
+
"grad_norm": 2.7686843872070312,
|
| 364 |
+
"learning_rate": 5.090909090909091e-06,
|
| 365 |
+
"loss": 1.1578,
|
| 366 |
+
"step": 84
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 7.818181818181818,
|
| 370 |
+
"grad_norm": 2.3368959426879883,
|
| 371 |
+
"learning_rate": 5.212121212121213e-06,
|
| 372 |
+
"loss": 1.1423,
|
| 373 |
+
"step": 86
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 8.0,
|
| 377 |
+
"grad_norm": 1.5859788656234741,
|
| 378 |
+
"learning_rate": 5.333333333333334e-06,
|
| 379 |
+
"loss": 1.0554,
|
| 380 |
+
"step": 88
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.0,
|
| 384 |
+
"eval_loss": 1.0675058364868164,
|
| 385 |
+
"eval_runtime": 21.0113,
|
| 386 |
+
"eval_samples_per_second": 1.142,
|
| 387 |
+
"eval_steps_per_second": 1.142,
|
| 388 |
+
"step": 88
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 8.181818181818182,
|
| 392 |
+
"grad_norm": 1.8273411989212036,
|
| 393 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 394 |
+
"loss": 0.9927,
|
| 395 |
+
"step": 90
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 8.363636363636363,
|
| 399 |
+
"grad_norm": 1.7687430381774902,
|
| 400 |
+
"learning_rate": 5.575757575757577e-06,
|
| 401 |
+
"loss": 0.8886,
|
| 402 |
+
"step": 92
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 8.545454545454545,
|
| 406 |
+
"grad_norm": 1.9781934022903442,
|
| 407 |
+
"learning_rate": 5.696969696969698e-06,
|
| 408 |
+
"loss": 0.7076,
|
| 409 |
+
"step": 94
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 8.727272727272727,
|
| 413 |
+
"grad_norm": 1.8124470710754395,
|
| 414 |
+
"learning_rate": 5.8181818181818185e-06,
|
| 415 |
+
"loss": 0.8414,
|
| 416 |
+
"step": 96
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 8.909090909090908,
|
| 420 |
+
"grad_norm": 1.2052216529846191,
|
| 421 |
+
"learning_rate": 5.93939393939394e-06,
|
| 422 |
+
"loss": 0.8392,
|
| 423 |
+
"step": 98
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 9.0,
|
| 427 |
+
"eval_loss": 0.756293773651123,
|
| 428 |
+
"eval_runtime": 21.002,
|
| 429 |
+
"eval_samples_per_second": 1.143,
|
| 430 |
+
"eval_steps_per_second": 1.143,
|
| 431 |
+
"step": 99
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 9.090909090909092,
|
| 435 |
+
"grad_norm": 1.1055922508239746,
|
| 436 |
+
"learning_rate": 6.060606060606061e-06,
|
| 437 |
+
"loss": 0.7587,
|
| 438 |
+
"step": 100
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 9.272727272727273,
|
| 442 |
+
"grad_norm": 1.4254761934280396,
|
| 443 |
+
"learning_rate": 6.181818181818182e-06,
|
| 444 |
+
"loss": 0.333,
|
| 445 |
+
"step": 102
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 9.454545454545455,
|
| 449 |
+
"grad_norm": 1.636863350868225,
|
| 450 |
+
"learning_rate": 6.303030303030303e-06,
|
| 451 |
+
"loss": 1.0304,
|
| 452 |
+
"step": 104
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 9.636363636363637,
|
| 456 |
+
"grad_norm": 1.3520318269729614,
|
| 457 |
+
"learning_rate": 6.424242424242425e-06,
|
| 458 |
+
"loss": 0.5626,
|
| 459 |
+
"step": 106
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 9.818181818181818,
|
| 463 |
+
"grad_norm": 0.739101231098175,
|
| 464 |
+
"learning_rate": 6.545454545454546e-06,
|
| 465 |
+
"loss": 0.4562,
|
| 466 |
+
"step": 108
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 10.0,
|
| 470 |
+
"grad_norm": 0.719274640083313,
|
| 471 |
+
"learning_rate": 6.666666666666667e-06,
|
| 472 |
+
"loss": 0.4685,
|
| 473 |
+
"step": 110
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 10.0,
|
| 477 |
+
"eval_loss": 0.6436794400215149,
|
| 478 |
+
"eval_runtime": 20.9986,
|
| 479 |
+
"eval_samples_per_second": 1.143,
|
| 480 |
+
"eval_steps_per_second": 1.143,
|
| 481 |
+
"step": 110
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 10.181818181818182,
|
| 485 |
+
"grad_norm": 0.5967914462089539,
|
| 486 |
+
"learning_rate": 6.787878787878789e-06,
|
| 487 |
+
"loss": 0.4207,
|
| 488 |
+
"step": 112
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 10.363636363636363,
|
| 492 |
+
"grad_norm": 0.7981317639350891,
|
| 493 |
+
"learning_rate": 6.90909090909091e-06,
|
| 494 |
+
"loss": 0.7027,
|
| 495 |
+
"step": 114
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 10.545454545454545,
|
| 499 |
+
"grad_norm": 0.648346483707428,
|
| 500 |
+
"learning_rate": 7.030303030303031e-06,
|
| 501 |
+
"loss": 0.48,
|
| 502 |
+
"step": 116
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 10.727272727272727,
|
| 506 |
+
"grad_norm": 1.0265989303588867,
|
| 507 |
+
"learning_rate": 7.151515151515152e-06,
|
| 508 |
+
"loss": 0.6033,
|
| 509 |
+
"step": 118
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 10.909090909090908,
|
| 513 |
+
"grad_norm": 0.6349014639854431,
|
| 514 |
+
"learning_rate": 7.272727272727273e-06,
|
| 515 |
+
"loss": 0.3588,
|
| 516 |
+
"step": 120
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 11.0,
|
| 520 |
+
"eval_loss": 0.5850974321365356,
|
| 521 |
+
"eval_runtime": 21.004,
|
| 522 |
+
"eval_samples_per_second": 1.143,
|
| 523 |
+
"eval_steps_per_second": 1.143,
|
| 524 |
+
"step": 121
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 11.090909090909092,
|
| 528 |
+
"grad_norm": 0.530517041683197,
|
| 529 |
+
"learning_rate": 7.393939393939395e-06,
|
| 530 |
+
"loss": 0.4937,
|
| 531 |
+
"step": 122
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 11.272727272727273,
|
| 535 |
+
"grad_norm": 0.9633344411849976,
|
| 536 |
+
"learning_rate": 7.515151515151516e-06,
|
| 537 |
+
"loss": 0.542,
|
| 538 |
+
"step": 124
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 11.454545454545455,
|
| 542 |
+
"grad_norm": 0.6681090593338013,
|
| 543 |
+
"learning_rate": 7.636363636363638e-06,
|
| 544 |
+
"loss": 0.4627,
|
| 545 |
+
"step": 126
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 11.636363636363637,
|
| 549 |
+
"grad_norm": 0.4449699819087982,
|
| 550 |
+
"learning_rate": 7.757575757575758e-06,
|
| 551 |
+
"loss": 0.4319,
|
| 552 |
+
"step": 128
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 11.818181818181818,
|
| 556 |
+
"grad_norm": 0.5469127297401428,
|
| 557 |
+
"learning_rate": 7.87878787878788e-06,
|
| 558 |
+
"loss": 0.3578,
|
| 559 |
+
"step": 130
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 12.0,
|
| 563 |
+
"grad_norm": 0.9779024720191956,
|
| 564 |
+
"learning_rate": 8.000000000000001e-06,
|
| 565 |
+
"loss": 0.6319,
|
| 566 |
+
"step": 132
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 12.0,
|
| 570 |
+
"eval_loss": 0.5406798720359802,
|
| 571 |
+
"eval_runtime": 20.9992,
|
| 572 |
+
"eval_samples_per_second": 1.143,
|
| 573 |
+
"eval_steps_per_second": 1.143,
|
| 574 |
+
"step": 132
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 12.181818181818182,
|
| 578 |
+
"grad_norm": 0.5859923958778381,
|
| 579 |
+
"learning_rate": 8.121212121212121e-06,
|
| 580 |
+
"loss": 0.3894,
|
| 581 |
+
"step": 134
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 12.363636363636363,
|
| 585 |
+
"grad_norm": 0.1749761551618576,
|
| 586 |
+
"learning_rate": 8.242424242424243e-06,
|
| 587 |
+
"loss": 0.2537,
|
| 588 |
+
"step": 136
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 12.545454545454545,
|
| 592 |
+
"grad_norm": 1.400254487991333,
|
| 593 |
+
"learning_rate": 8.363636363636365e-06,
|
| 594 |
+
"loss": 0.6108,
|
| 595 |
+
"step": 138
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 12.727272727272727,
|
| 599 |
+
"grad_norm": 0.556860089302063,
|
| 600 |
+
"learning_rate": 8.484848484848486e-06,
|
| 601 |
+
"loss": 0.5365,
|
| 602 |
+
"step": 140
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 12.909090909090908,
|
| 606 |
+
"grad_norm": 0.4626636207103729,
|
| 607 |
+
"learning_rate": 8.606060606060606e-06,
|
| 608 |
+
"loss": 0.4211,
|
| 609 |
+
"step": 142
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.0,
|
| 613 |
+
"eval_loss": 0.5247967839241028,
|
| 614 |
+
"eval_runtime": 21.0033,
|
| 615 |
+
"eval_samples_per_second": 1.143,
|
| 616 |
+
"eval_steps_per_second": 1.143,
|
| 617 |
+
"step": 143
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 13.090909090909092,
|
| 621 |
+
"grad_norm": 0.42664870619773865,
|
| 622 |
+
"learning_rate": 8.727272727272728e-06,
|
| 623 |
+
"loss": 0.4939,
|
| 624 |
+
"step": 144
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 13.272727272727273,
|
| 628 |
+
"grad_norm": 0.38396334648132324,
|
| 629 |
+
"learning_rate": 8.84848484848485e-06,
|
| 630 |
+
"loss": 0.3484,
|
| 631 |
+
"step": 146
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 13.454545454545455,
|
| 635 |
+
"grad_norm": 0.43991151452064514,
|
| 636 |
+
"learning_rate": 8.969696969696971e-06,
|
| 637 |
+
"loss": 0.4156,
|
| 638 |
+
"step": 148
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 13.636363636363637,
|
| 642 |
+
"grad_norm": 0.4237063229084015,
|
| 643 |
+
"learning_rate": 9.090909090909091e-06,
|
| 644 |
+
"loss": 0.3955,
|
| 645 |
+
"step": 150
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 13.818181818181818,
|
| 649 |
+
"grad_norm": 0.34925854206085205,
|
| 650 |
+
"learning_rate": 9.212121212121213e-06,
|
| 651 |
+
"loss": 0.446,
|
| 652 |
+
"step": 152
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 14.0,
|
| 656 |
+
"grad_norm": 0.8939254879951477,
|
| 657 |
+
"learning_rate": 9.333333333333334e-06,
|
| 658 |
+
"loss": 0.495,
|
| 659 |
+
"step": 154
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 14.0,
|
| 663 |
+
"eval_loss": 0.5127188563346863,
|
| 664 |
+
"eval_runtime": 20.9989,
|
| 665 |
+
"eval_samples_per_second": 1.143,
|
| 666 |
+
"eval_steps_per_second": 1.143,
|
| 667 |
+
"step": 154
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 14.181818181818182,
|
| 671 |
+
"grad_norm": 0.4808824062347412,
|
| 672 |
+
"learning_rate": 9.454545454545456e-06,
|
| 673 |
+
"loss": 0.4217,
|
| 674 |
+
"step": 156
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 14.363636363636363,
|
| 678 |
+
"grad_norm": 0.3635479807853699,
|
| 679 |
+
"learning_rate": 9.575757575757576e-06,
|
| 680 |
+
"loss": 0.4738,
|
| 681 |
+
"step": 158
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 14.545454545454545,
|
| 685 |
+
"grad_norm": 0.2080135941505432,
|
| 686 |
+
"learning_rate": 9.696969696969698e-06,
|
| 687 |
+
"loss": 0.3693,
|
| 688 |
+
"step": 160
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 14.727272727272727,
|
| 692 |
+
"grad_norm": 2.0220720767974854,
|
| 693 |
+
"learning_rate": 9.81818181818182e-06,
|
| 694 |
+
"loss": 0.3737,
|
| 695 |
+
"step": 162
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 14.909090909090908,
|
| 699 |
+
"grad_norm": 0.3454424738883972,
|
| 700 |
+
"learning_rate": 9.939393939393939e-06,
|
| 701 |
+
"loss": 0.4232,
|
| 702 |
+
"step": 164
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 15.0,
|
| 706 |
+
"eval_loss": 0.5019441246986389,
|
| 707 |
+
"eval_runtime": 21.0036,
|
| 708 |
+
"eval_samples_per_second": 1.143,
|
| 709 |
+
"eval_steps_per_second": 1.143,
|
| 710 |
+
"step": 165
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 15.090909090909092,
|
| 714 |
+
"grad_norm": 0.4212585389614105,
|
| 715 |
+
"learning_rate": 9.999988811118232e-06,
|
| 716 |
+
"loss": 0.4735,
|
| 717 |
+
"step": 166
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 15.272727272727273,
|
| 721 |
+
"grad_norm": 0.22414664924144745,
|
| 722 |
+
"learning_rate": 9.999899300364534e-06,
|
| 723 |
+
"loss": 0.2503,
|
| 724 |
+
"step": 168
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 15.454545454545455,
|
| 728 |
+
"grad_norm": 1.3229994773864746,
|
| 729 |
+
"learning_rate": 9.999720280459576e-06,
|
| 730 |
+
"loss": 0.4071,
|
| 731 |
+
"step": 170
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 15.636363636363637,
|
| 735 |
+
"grad_norm": 0.29747679829597473,
|
| 736 |
+
"learning_rate": 9.999451754608208e-06,
|
| 737 |
+
"loss": 0.3427,
|
| 738 |
+
"step": 172
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 15.818181818181818,
|
| 742 |
+
"grad_norm": 0.3459671437740326,
|
| 743 |
+
"learning_rate": 9.99909372761763e-06,
|
| 744 |
+
"loss": 0.4779,
|
| 745 |
+
"step": 174
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 16.0,
|
| 749 |
+
"grad_norm": 0.31325361132621765,
|
| 750 |
+
"learning_rate": 9.99864620589731e-06,
|
| 751 |
+
"loss": 0.496,
|
| 752 |
+
"step": 176
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 16.0,
|
| 756 |
+
"eval_loss": 0.5102820992469788,
|
| 757 |
+
"eval_runtime": 21.0039,
|
| 758 |
+
"eval_samples_per_second": 1.143,
|
| 759 |
+
"eval_steps_per_second": 1.143,
|
| 760 |
+
"step": 176
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 16.181818181818183,
|
| 764 |
+
"grad_norm": 0.35442739725112915,
|
| 765 |
+
"learning_rate": 9.998109197458865e-06,
|
| 766 |
+
"loss": 0.2946,
|
| 767 |
+
"step": 178
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 16.363636363636363,
|
| 771 |
+
"grad_norm": 1.0050742626190186,
|
| 772 |
+
"learning_rate": 9.997482711915926e-06,
|
| 773 |
+
"loss": 0.5689,
|
| 774 |
+
"step": 180
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 16.545454545454547,
|
| 778 |
+
"grad_norm": 0.3000654876232147,
|
| 779 |
+
"learning_rate": 9.996766760483955e-06,
|
| 780 |
+
"loss": 0.3062,
|
| 781 |
+
"step": 182
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 16.727272727272727,
|
| 785 |
+
"grad_norm": 0.33660659193992615,
|
| 786 |
+
"learning_rate": 9.995961355980052e-06,
|
| 787 |
+
"loss": 0.3404,
|
| 788 |
+
"step": 184
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 16.90909090909091,
|
| 792 |
+
"grad_norm": 0.32371142506599426,
|
| 793 |
+
"learning_rate": 9.99506651282272e-06,
|
| 794 |
+
"loss": 0.3903,
|
| 795 |
+
"step": 186
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 17.0,
|
| 799 |
+
"eval_loss": 0.4814320504665375,
|
| 800 |
+
"eval_runtime": 21.0016,
|
| 801 |
+
"eval_samples_per_second": 1.143,
|
| 802 |
+
"eval_steps_per_second": 1.143,
|
| 803 |
+
"step": 187
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 17.09090909090909,
|
| 807 |
+
"grad_norm": 0.7857639193534851,
|
| 808 |
+
"learning_rate": 9.994082247031613e-06,
|
| 809 |
+
"loss": 0.5145,
|
| 810 |
+
"step": 188
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 17.272727272727273,
|
| 814 |
+
"grad_norm": 0.007223070599138737,
|
| 815 |
+
"learning_rate": 9.993008576227248e-06,
|
| 816 |
+
"loss": 0.2366,
|
| 817 |
+
"step": 190
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 17.454545454545453,
|
| 821 |
+
"grad_norm": 0.5182167887687683,
|
| 822 |
+
"learning_rate": 9.991845519630679e-06,
|
| 823 |
+
"loss": 0.4549,
|
| 824 |
+
"step": 192
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 17.636363636363637,
|
| 828 |
+
"grad_norm": 0.2884611487388611,
|
| 829 |
+
"learning_rate": 9.99059309806317e-06,
|
| 830 |
+
"loss": 0.3861,
|
| 831 |
+
"step": 194
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 17.818181818181817,
|
| 835 |
+
"grad_norm": 0.49307528138160706,
|
| 836 |
+
"learning_rate": 9.989251333945813e-06,
|
| 837 |
+
"loss": 0.4248,
|
| 838 |
+
"step": 196
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 18.0,
|
| 842 |
+
"grad_norm": 0.48076504468917847,
|
| 843 |
+
"learning_rate": 9.987820251299121e-06,
|
| 844 |
+
"loss": 0.331,
|
| 845 |
+
"step": 198
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 18.0,
|
| 849 |
+
"eval_loss": 0.49132904410362244,
|
| 850 |
+
"eval_runtime": 21.0024,
|
| 851 |
+
"eval_samples_per_second": 1.143,
|
| 852 |
+
"eval_steps_per_second": 1.143,
|
| 853 |
+
"step": 198
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 18.181818181818183,
|
| 857 |
+
"grad_norm": 0.5222908854484558,
|
| 858 |
+
"learning_rate": 9.986299875742612e-06,
|
| 859 |
+
"loss": 0.4817,
|
| 860 |
+
"step": 200
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 18.363636363636363,
|
| 864 |
+
"grad_norm": 0.3346542418003082,
|
| 865 |
+
"learning_rate": 9.984690234494338e-06,
|
| 866 |
+
"loss": 0.2685,
|
| 867 |
+
"step": 202
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 18.545454545454547,
|
| 871 |
+
"grad_norm": 0.48757171630859375,
|
| 872 |
+
"learning_rate": 9.982991356370404e-06,
|
| 873 |
+
"loss": 0.4127,
|
| 874 |
+
"step": 204
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 18.727272727272727,
|
| 878 |
+
"grad_norm": 0.5337949991226196,
|
| 879 |
+
"learning_rate": 9.98120327178445e-06,
|
| 880 |
+
"loss": 0.4215,
|
| 881 |
+
"step": 206
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 18.90909090909091,
|
| 885 |
+
"grad_norm": 0.26037395000457764,
|
| 886 |
+
"learning_rate": 9.979326012747106e-06,
|
| 887 |
+
"loss": 0.2403,
|
| 888 |
+
"step": 208
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 19.0,
|
| 892 |
+
"eval_loss": 0.4869350492954254,
|
| 893 |
+
"eval_runtime": 21.0006,
|
| 894 |
+
"eval_samples_per_second": 1.143,
|
| 895 |
+
"eval_steps_per_second": 1.143,
|
| 896 |
+
"step": 209
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 19.09090909090909,
|
| 900 |
+
"grad_norm": 0.31072062253952026,
|
| 901 |
+
"learning_rate": 9.977359612865424e-06,
|
| 902 |
+
"loss": 0.2671,
|
| 903 |
+
"step": 210
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 19.272727272727273,
|
| 907 |
+
"grad_norm": 0.5128066539764404,
|
| 908 |
+
"learning_rate": 9.975304107342268e-06,
|
| 909 |
+
"loss": 0.3695,
|
| 910 |
+
"step": 212
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 19.454545454545453,
|
| 914 |
+
"grad_norm": 0.585717499256134,
|
| 915 |
+
"learning_rate": 9.973159532975691e-06,
|
| 916 |
+
"loss": 0.5722,
|
| 917 |
+
"step": 214
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 19.636363636363637,
|
| 921 |
+
"grad_norm": 0.4827703833580017,
|
| 922 |
+
"learning_rate": 9.970925928158275e-06,
|
| 923 |
+
"loss": 0.3577,
|
| 924 |
+
"step": 216
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 19.818181818181817,
|
| 928 |
+
"grad_norm": 0.3153725266456604,
|
| 929 |
+
"learning_rate": 9.968603332876435e-06,
|
| 930 |
+
"loss": 0.2262,
|
| 931 |
+
"step": 218
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 20.0,
|
| 935 |
+
"grad_norm": 0.4635719954967499,
|
| 936 |
+
"learning_rate": 9.966191788709716e-06,
|
| 937 |
+
"loss": 0.3563,
|
| 938 |
+
"step": 220
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 20.0,
|
| 942 |
+
"eval_loss": 0.471805602312088,
|
| 943 |
+
"eval_runtime": 21.0011,
|
| 944 |
+
"eval_samples_per_second": 1.143,
|
| 945 |
+
"eval_steps_per_second": 1.143,
|
| 946 |
+
"step": 220
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 20.181818181818183,
|
| 950 |
+
"grad_norm": 0.4292517304420471,
|
| 951 |
+
"learning_rate": 9.963691338830045e-06,
|
| 952 |
+
"loss": 0.2494,
|
| 953 |
+
"step": 222
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 20.363636363636363,
|
| 957 |
+
"grad_norm": 0.2989480495452881,
|
| 958 |
+
"learning_rate": 9.961102028000948e-06,
|
| 959 |
+
"loss": 0.2761,
|
| 960 |
+
"step": 224
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 20.545454545454547,
|
| 964 |
+
"grad_norm": 0.4395551383495331,
|
| 965 |
+
"learning_rate": 9.958423902576764e-06,
|
| 966 |
+
"loss": 0.5072,
|
| 967 |
+
"step": 226
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 20.727272727272727,
|
| 971 |
+
"grad_norm": 0.47977691888809204,
|
| 972 |
+
"learning_rate": 9.955657010501807e-06,
|
| 973 |
+
"loss": 0.2494,
|
| 974 |
+
"step": 228
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 20.90909090909091,
|
| 978 |
+
"grad_norm": 0.4911171793937683,
|
| 979 |
+
"learning_rate": 9.952801401309504e-06,
|
| 980 |
+
"loss": 0.4107,
|
| 981 |
+
"step": 230
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 21.0,
|
| 985 |
+
"eval_loss": 0.4596048593521118,
|
| 986 |
+
"eval_runtime": 20.9979,
|
| 987 |
+
"eval_samples_per_second": 1.143,
|
| 988 |
+
"eval_steps_per_second": 1.143,
|
| 989 |
+
"step": 231
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 21.09090909090909,
|
| 993 |
+
"grad_norm": 0.5808133482933044,
|
| 994 |
+
"learning_rate": 9.949857126121519e-06,
|
| 995 |
+
"loss": 0.4717,
|
| 996 |
+
"step": 232
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 21.272727272727273,
|
| 1000 |
+
"grad_norm": 0.19762107729911804,
|
| 1001 |
+
"learning_rate": 9.946824237646823e-06,
|
| 1002 |
+
"loss": 0.165,
|
| 1003 |
+
"step": 234
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 21.454545454545453,
|
| 1007 |
+
"grad_norm": 0.5478127598762512,
|
| 1008 |
+
"learning_rate": 9.94370279018077e-06,
|
| 1009 |
+
"loss": 0.383,
|
| 1010 |
+
"step": 236
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 21.636363636363637,
|
| 1014 |
+
"grad_norm": 0.3956260085105896,
|
| 1015 |
+
"learning_rate": 9.940492839604103e-06,
|
| 1016 |
+
"loss": 0.3194,
|
| 1017 |
+
"step": 238
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 21.818181818181817,
|
| 1021 |
+
"grad_norm": 0.608517050743103,
|
| 1022 |
+
"learning_rate": 9.937194443381972e-06,
|
| 1023 |
+
"loss": 0.3811,
|
| 1024 |
+
"step": 240
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 22.0,
|
| 1028 |
+
"grad_norm": 0.35069647431373596,
|
| 1029 |
+
"learning_rate": 9.933807660562898e-06,
|
| 1030 |
+
"loss": 0.2631,
|
| 1031 |
+
"step": 242
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 22.0,
|
| 1035 |
+
"eval_loss": 0.4477730691432953,
|
| 1036 |
+
"eval_runtime": 20.9988,
|
| 1037 |
+
"eval_samples_per_second": 1.143,
|
| 1038 |
+
"eval_steps_per_second": 1.143,
|
| 1039 |
+
"step": 242
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 22.181818181818183,
|
| 1043 |
+
"grad_norm": 0.5358024835586548,
|
| 1044 |
+
"learning_rate": 9.930332551777709e-06,
|
| 1045 |
+
"loss": 0.24,
|
| 1046 |
+
"step": 244
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 22.363636363636363,
|
| 1050 |
+
"grad_norm": 0.5837539434432983,
|
| 1051 |
+
"learning_rate": 9.926769179238467e-06,
|
| 1052 |
+
"loss": 0.312,
|
| 1053 |
+
"step": 246
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 22.545454545454547,
|
| 1057 |
+
"grad_norm": 0.4202631711959839,
|
| 1058 |
+
"learning_rate": 9.923117606737347e-06,
|
| 1059 |
+
"loss": 0.1839,
|
| 1060 |
+
"step": 248
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 22.727272727272727,
|
| 1064 |
+
"grad_norm": 0.7312754988670349,
|
| 1065 |
+
"learning_rate": 9.919377899645497e-06,
|
| 1066 |
+
"loss": 0.3982,
|
| 1067 |
+
"step": 250
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 22.90909090909091,
|
| 1071 |
+
"grad_norm": 0.6649301648139954,
|
| 1072 |
+
"learning_rate": 9.915550124911866e-06,
|
| 1073 |
+
"loss": 0.4212,
|
| 1074 |
+
"step": 252
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 23.0,
|
| 1078 |
+
"eval_loss": 0.4496145248413086,
|
| 1079 |
+
"eval_runtime": 21.002,
|
| 1080 |
+
"eval_samples_per_second": 1.143,
|
| 1081 |
+
"eval_steps_per_second": 1.143,
|
| 1082 |
+
"step": 253
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 23.09090909090909,
|
| 1086 |
+
"grad_norm": 0.4475117027759552,
|
| 1087 |
+
"learning_rate": 9.91163435106201e-06,
|
| 1088 |
+
"loss": 0.2837,
|
| 1089 |
+
"step": 254
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 23.272727272727273,
|
| 1093 |
+
"grad_norm": 0.7331680059432983,
|
| 1094 |
+
"learning_rate": 9.907630648196857e-06,
|
| 1095 |
+
"loss": 0.4256,
|
| 1096 |
+
"step": 256
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 23.454545454545453,
|
| 1100 |
+
"grad_norm": 0.5951094627380371,
|
| 1101 |
+
"learning_rate": 9.903539087991462e-06,
|
| 1102 |
+
"loss": 0.2876,
|
| 1103 |
+
"step": 258
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 23.636363636363637,
|
| 1107 |
+
"grad_norm": 0.5116230845451355,
|
| 1108 |
+
"learning_rate": 9.899359743693715e-06,
|
| 1109 |
+
"loss": 0.2226,
|
| 1110 |
+
"step": 260
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 23.818181818181817,
|
| 1114 |
+
"grad_norm": 0.4971112310886383,
|
| 1115 |
+
"learning_rate": 9.895092690123036e-06,
|
| 1116 |
+
"loss": 0.2511,
|
| 1117 |
+
"step": 262
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 24.0,
|
| 1121 |
+
"grad_norm": 0.0066973976790905,
|
| 1122 |
+
"learning_rate": 9.890738003669029e-06,
|
| 1123 |
+
"loss": 0.3304,
|
| 1124 |
+
"step": 264
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 24.0,
|
| 1128 |
+
"eval_loss": 0.44082728028297424,
|
| 1129 |
+
"eval_runtime": 20.9935,
|
| 1130 |
+
"eval_samples_per_second": 1.143,
|
| 1131 |
+
"eval_steps_per_second": 1.143,
|
| 1132 |
+
"step": 264
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 24.181818181818183,
|
| 1136 |
+
"grad_norm": 0.5074991583824158,
|
| 1137 |
+
"learning_rate": 9.886295762290125e-06,
|
| 1138 |
+
"loss": 0.1619,
|
| 1139 |
+
"step": 266
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 24.363636363636363,
|
| 1143 |
+
"grad_norm": 0.803401529788971,
|
| 1144 |
+
"learning_rate": 9.881766045512176e-06,
|
| 1145 |
+
"loss": 0.3071,
|
| 1146 |
+
"step": 268
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 24.545454545454547,
|
| 1150 |
+
"grad_norm": 0.7890399694442749,
|
| 1151 |
+
"learning_rate": 9.877148934427037e-06,
|
| 1152 |
+
"loss": 0.2939,
|
| 1153 |
+
"step": 270
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 24.727272727272727,
|
| 1157 |
+
"grad_norm": 0.5034437775611877,
|
| 1158 |
+
"learning_rate": 9.872444511691108e-06,
|
| 1159 |
+
"loss": 0.2662,
|
| 1160 |
+
"step": 272
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 24.90909090909091,
|
| 1164 |
+
"grad_norm": 0.7107832431793213,
|
| 1165 |
+
"learning_rate": 9.867652861523866e-06,
|
| 1166 |
+
"loss": 0.3296,
|
| 1167 |
+
"step": 274
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 25.0,
|
| 1171 |
+
"eval_loss": 0.4437350928783417,
|
| 1172 |
+
"eval_runtime": 21.0123,
|
| 1173 |
+
"eval_samples_per_second": 1.142,
|
| 1174 |
+
"eval_steps_per_second": 1.142,
|
| 1175 |
+
"step": 275
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 25.09090909090909,
|
| 1179 |
+
"grad_norm": 0.8815945386886597,
|
| 1180 |
+
"learning_rate": 9.862774069706346e-06,
|
| 1181 |
+
"loss": 0.3628,
|
| 1182 |
+
"step": 276
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 25.272727272727273,
|
| 1186 |
+
"grad_norm": 0.6133561134338379,
|
| 1187 |
+
"learning_rate": 9.85780822357961e-06,
|
| 1188 |
+
"loss": 0.2528,
|
| 1189 |
+
"step": 278
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 25.454545454545453,
|
| 1193 |
+
"grad_norm": 0.7392721772193909,
|
| 1194 |
+
"learning_rate": 9.85275541204318e-06,
|
| 1195 |
+
"loss": 0.166,
|
| 1196 |
+
"step": 280
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 25.636363636363637,
|
| 1200 |
+
"grad_norm": 0.7326251268386841,
|
| 1201 |
+
"learning_rate": 9.847615725553457e-06,
|
| 1202 |
+
"loss": 0.1924,
|
| 1203 |
+
"step": 282
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 25.818181818181817,
|
| 1207 |
+
"grad_norm": 0.9658777117729187,
|
| 1208 |
+
"learning_rate": 9.842389256122086e-06,
|
| 1209 |
+
"loss": 0.3393,
|
| 1210 |
+
"step": 284
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 26.0,
|
| 1214 |
+
"grad_norm": 0.9744178056716919,
|
| 1215 |
+
"learning_rate": 9.83707609731432e-06,
|
| 1216 |
+
"loss": 0.3266,
|
| 1217 |
+
"step": 286
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 26.0,
|
| 1221 |
+
"eval_loss": 0.44414618611335754,
|
| 1222 |
+
"eval_runtime": 20.9954,
|
| 1223 |
+
"eval_samples_per_second": 1.143,
|
| 1224 |
+
"eval_steps_per_second": 1.143,
|
| 1225 |
+
"step": 286
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 26.181818181818183,
|
| 1229 |
+
"grad_norm": 1.009691834449768,
|
| 1230 |
+
"learning_rate": 9.831676344247343e-06,
|
| 1231 |
+
"loss": 0.2983,
|
| 1232 |
+
"step": 288
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 26.363636363636363,
|
| 1236 |
+
"grad_norm": 0.9881241917610168,
|
| 1237 |
+
"learning_rate": 9.826190093588564e-06,
|
| 1238 |
+
"loss": 0.3114,
|
| 1239 |
+
"step": 290
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 26.545454545454547,
|
| 1243 |
+
"grad_norm": 0.6508401036262512,
|
| 1244 |
+
"learning_rate": 9.820617443553889e-06,
|
| 1245 |
+
"loss": 0.1722,
|
| 1246 |
+
"step": 292
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 26.727272727272727,
|
| 1250 |
+
"grad_norm": 1.0022698640823364,
|
| 1251 |
+
"learning_rate": 9.814958493905962e-06,
|
| 1252 |
+
"loss": 0.2775,
|
| 1253 |
+
"step": 294
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 26.90909090909091,
|
| 1257 |
+
"grad_norm": 0.8220618963241577,
|
| 1258 |
+
"learning_rate": 9.80921334595238e-06,
|
| 1259 |
+
"loss": 0.1403,
|
| 1260 |
+
"step": 296
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 27.0,
|
| 1264 |
+
"eval_loss": 0.4495992660522461,
|
| 1265 |
+
"eval_runtime": 21.0004,
|
| 1266 |
+
"eval_samples_per_second": 1.143,
|
| 1267 |
+
"eval_steps_per_second": 1.143,
|
| 1268 |
+
"step": 297
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 27.09090909090909,
|
| 1272 |
+
"grad_norm": 0.6972556114196777,
|
| 1273 |
+
"learning_rate": 9.80338210254388e-06,
|
| 1274 |
+
"loss": 0.2361,
|
| 1275 |
+
"step": 298
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 27.272727272727273,
|
| 1279 |
+
"grad_norm": 1.3660632371902466,
|
| 1280 |
+
"learning_rate": 9.797464868072489e-06,
|
| 1281 |
+
"loss": 0.1793,
|
| 1282 |
+
"step": 300
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 27.454545454545453,
|
| 1286 |
+
"grad_norm": 0.9514533281326294,
|
| 1287 |
+
"learning_rate": 9.791461748469669e-06,
|
| 1288 |
+
"loss": 0.346,
|
| 1289 |
+
"step": 302
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 27.636363636363637,
|
| 1293 |
+
"grad_norm": 1.0539543628692627,
|
| 1294 |
+
"learning_rate": 9.785372851204415e-06,
|
| 1295 |
+
"loss": 0.201,
|
| 1296 |
+
"step": 304
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 27.818181818181817,
|
| 1300 |
+
"grad_norm": 1.111655592918396,
|
| 1301 |
+
"learning_rate": 9.779198285281326e-06,
|
| 1302 |
+
"loss": 0.2216,
|
| 1303 |
+
"step": 306
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 28.0,
|
| 1307 |
+
"grad_norm": 0.7238084077835083,
|
| 1308 |
+
"learning_rate": 9.77293816123866e-06,
|
| 1309 |
+
"loss": 0.1732,
|
| 1310 |
+
"step": 308
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 28.0,
|
| 1314 |
+
"eval_loss": 0.45740625262260437,
|
| 1315 |
+
"eval_runtime": 21.0057,
|
| 1316 |
+
"eval_samples_per_second": 1.143,
|
| 1317 |
+
"eval_steps_per_second": 1.143,
|
| 1318 |
+
"step": 308
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 28.181818181818183,
|
| 1322 |
+
"grad_norm": 1.3565870523452759,
|
| 1323 |
+
"learning_rate": 9.766592591146353e-06,
|
| 1324 |
+
"loss": 0.3174,
|
| 1325 |
+
"step": 310
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 28.363636363636363,
|
| 1329 |
+
"grad_norm": 1.3067699670791626,
|
| 1330 |
+
"learning_rate": 9.760161688604008e-06,
|
| 1331 |
+
"loss": 0.2076,
|
| 1332 |
+
"step": 312
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 28.545454545454547,
|
| 1336 |
+
"grad_norm": 0.9948272705078125,
|
| 1337 |
+
"learning_rate": 9.753645568738872e-06,
|
| 1338 |
+
"loss": 0.1527,
|
| 1339 |
+
"step": 314
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 28.727272727272727,
|
| 1343 |
+
"grad_norm": 1.3128433227539062,
|
| 1344 |
+
"learning_rate": 9.747044348203766e-06,
|
| 1345 |
+
"loss": 0.1789,
|
| 1346 |
+
"step": 316
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 28.90909090909091,
|
| 1350 |
+
"grad_norm": 0.9066749215126038,
|
| 1351 |
+
"learning_rate": 9.740358145174999e-06,
|
| 1352 |
+
"loss": 0.1797,
|
| 1353 |
+
"step": 318
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 29.0,
|
| 1357 |
+
"eval_loss": 0.4808818995952606,
|
| 1358 |
+
"eval_runtime": 20.9997,
|
| 1359 |
+
"eval_samples_per_second": 1.143,
|
| 1360 |
+
"eval_steps_per_second": 1.143,
|
| 1361 |
+
"step": 319
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 29.09090909090909,
|
| 1365 |
+
"grad_norm": 1.0640830993652344,
|
| 1366 |
+
"learning_rate": 9.733587079350254e-06,
|
| 1367 |
+
"loss": 0.1481,
|
| 1368 |
+
"step": 320
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 29.272727272727273,
|
| 1372 |
+
"grad_norm": 1.490294337272644,
|
| 1373 |
+
"learning_rate": 9.72673127194644e-06,
|
| 1374 |
+
"loss": 0.355,
|
| 1375 |
+
"step": 322
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 29.454545454545453,
|
| 1379 |
+
"grad_norm": 0.6777256727218628,
|
| 1380 |
+
"learning_rate": 9.719790845697534e-06,
|
| 1381 |
+
"loss": 0.1048,
|
| 1382 |
+
"step": 324
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 29.636363636363637,
|
| 1386 |
+
"grad_norm": 1.5173866748809814,
|
| 1387 |
+
"learning_rate": 9.71276592485237e-06,
|
| 1388 |
+
"loss": 0.1738,
|
| 1389 |
+
"step": 326
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 29.818181818181817,
|
| 1393 |
+
"grad_norm": 1.211938500404358,
|
| 1394 |
+
"learning_rate": 9.705656635172418e-06,
|
| 1395 |
+
"loss": 0.0788,
|
| 1396 |
+
"step": 328
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 30.0,
|
| 1400 |
+
"grad_norm": 1.4657930135726929,
|
| 1401 |
+
"learning_rate": 9.698463103929542e-06,
|
| 1402 |
+
"loss": 0.1355,
|
| 1403 |
+
"step": 330
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 30.0,
|
| 1407 |
+
"eval_loss": 0.49904152750968933,
|
| 1408 |
+
"eval_runtime": 21.0013,
|
| 1409 |
+
"eval_samples_per_second": 1.143,
|
| 1410 |
+
"eval_steps_per_second": 1.143,
|
| 1411 |
+
"step": 330
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 30.181818181818183,
|
| 1415 |
+
"grad_norm": 1.3539866209030151,
|
| 1416 |
+
"learning_rate": 9.69118545990371e-06,
|
| 1417 |
+
"loss": 0.1336,
|
| 1418 |
+
"step": 332
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 30.363636363636363,
|
| 1422 |
+
"grad_norm": 1.1103911399841309,
|
| 1423 |
+
"learning_rate": 9.683823833380692e-06,
|
| 1424 |
+
"loss": 0.1738,
|
| 1425 |
+
"step": 334
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 30.545454545454547,
|
| 1429 |
+
"grad_norm": 1.4360435009002686,
|
| 1430 |
+
"learning_rate": 9.676378356149733e-06,
|
| 1431 |
+
"loss": 0.0891,
|
| 1432 |
+
"step": 336
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 30.727272727272727,
|
| 1436 |
+
"grad_norm": 1.7939261198043823,
|
| 1437 |
+
"learning_rate": 9.668849161501186e-06,
|
| 1438 |
+
"loss": 0.2107,
|
| 1439 |
+
"step": 338
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 30.90909090909091,
|
| 1443 |
+
"grad_norm": 1.3665426969528198,
|
| 1444 |
+
"learning_rate": 9.66123638422413e-06,
|
| 1445 |
+
"loss": 0.1346,
|
| 1446 |
+
"step": 340
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 31.0,
|
| 1450 |
+
"eval_loss": 0.5312966704368591,
|
| 1451 |
+
"eval_runtime": 21.0009,
|
| 1452 |
+
"eval_samples_per_second": 1.143,
|
| 1453 |
+
"eval_steps_per_second": 1.143,
|
| 1454 |
+
"step": 341
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 31.0,
|
| 1458 |
+
"step": 341,
|
| 1459 |
+
"total_flos": 2.1292989192077312e+17,
|
| 1460 |
+
"train_loss": 0.8120344140050698,
|
| 1461 |
+
"train_runtime": 7851.2602,
|
| 1462 |
+
"train_samples_per_second": 1.681,
|
| 1463 |
+
"train_steps_per_second": 0.21
|
| 1464 |
+
}
|
| 1465 |
+
],
|
| 1466 |
+
"logging_steps": 2,
|
| 1467 |
+
"max_steps": 1650,
|
| 1468 |
+
"num_input_tokens_seen": 0,
|
| 1469 |
+
"num_train_epochs": 150,
|
| 1470 |
+
"save_steps": 25,
|
| 1471 |
+
"stateful_callbacks": {
|
| 1472 |
+
"EarlyStoppingCallback": {
|
| 1473 |
+
"args": {
|
| 1474 |
+
"early_stopping_patience": 7,
|
| 1475 |
+
"early_stopping_threshold": 0.0
|
| 1476 |
+
},
|
| 1477 |
+
"attributes": {
|
| 1478 |
+
"early_stopping_patience_counter": 0
|
| 1479 |
+
}
|
| 1480 |
+
},
|
| 1481 |
+
"TrainerControl": {
|
| 1482 |
+
"args": {
|
| 1483 |
+
"should_epoch_stop": false,
|
| 1484 |
+
"should_evaluate": false,
|
| 1485 |
+
"should_log": false,
|
| 1486 |
+
"should_save": true,
|
| 1487 |
+
"should_training_stop": true
|
| 1488 |
+
},
|
| 1489 |
+
"attributes": {}
|
| 1490 |
+
}
|
| 1491 |
+
},
|
| 1492 |
+
"total_flos": 2.1292989192077312e+17,
|
| 1493 |
+
"train_batch_size": 1,
|
| 1494 |
+
"trial_name": null,
|
| 1495 |
+
"trial_params": null
|
| 1496 |
+
}
|