Commit
•
3e8b986
1
Parent(s):
93f1e69
Model save
Browse files- README.md +96 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +930 -0
README.md
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-1_120-samples_config-4
|
| 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-1_120-samples_config-4
|
| 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: 1.3447
|
| 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: 16
|
| 46 |
+
- total_train_batch_size: 16
|
| 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 |
+
| 2.121 | 0.9091 | 5 | 2.1020 |
|
| 57 |
+
| 2.0709 | 2.0 | 11 | 2.0931 |
|
| 58 |
+
| 2.0454 | 2.9091 | 16 | 2.0755 |
|
| 59 |
+
| 2.0502 | 4.0 | 22 | 2.0472 |
|
| 60 |
+
| 2.0511 | 4.9091 | 27 | 2.0100 |
|
| 61 |
+
| 1.9554 | 6.0 | 33 | 1.9472 |
|
| 62 |
+
| 1.8921 | 6.9091 | 38 | 1.8795 |
|
| 63 |
+
| 1.8104 | 8.0 | 44 | 1.7813 |
|
| 64 |
+
| 1.7636 | 8.9091 | 49 | 1.6937 |
|
| 65 |
+
| 1.6011 | 10.0 | 55 | 1.6142 |
|
| 66 |
+
| 1.5128 | 10.9091 | 60 | 1.5751 |
|
| 67 |
+
| 1.4277 | 12.0 | 66 | 1.5353 |
|
| 68 |
+
| 1.4998 | 12.9091 | 71 | 1.5001 |
|
| 69 |
+
| 1.4154 | 14.0 | 77 | 1.4583 |
|
| 70 |
+
| 1.4201 | 14.9091 | 82 | 1.4252 |
|
| 71 |
+
| 1.3364 | 16.0 | 88 | 1.3921 |
|
| 72 |
+
| 1.2762 | 16.9091 | 93 | 1.3691 |
|
| 73 |
+
| 1.2851 | 18.0 | 99 | 1.3437 |
|
| 74 |
+
| 1.2239 | 18.9091 | 104 | 1.3261 |
|
| 75 |
+
| 1.221 | 20.0 | 110 | 1.3084 |
|
| 76 |
+
| 1.2011 | 20.9091 | 115 | 1.2951 |
|
| 77 |
+
| 1.1433 | 22.0 | 121 | 1.2824 |
|
| 78 |
+
| 1.1579 | 22.9091 | 126 | 1.2746 |
|
| 79 |
+
| 1.0871 | 24.0 | 132 | 1.2680 |
|
| 80 |
+
| 1.0745 | 24.9091 | 137 | 1.2635 |
|
| 81 |
+
| 1.0006 | 26.0 | 143 | 1.2674 |
|
| 82 |
+
| 0.9628 | 26.9091 | 148 | 1.2689 |
|
| 83 |
+
| 0.9237 | 28.0 | 154 | 1.2717 |
|
| 84 |
+
| 0.8824 | 28.9091 | 159 | 1.2880 |
|
| 85 |
+
| 0.8706 | 30.0 | 165 | 1.2961 |
|
| 86 |
+
| 0.8328 | 30.9091 | 170 | 1.3266 |
|
| 87 |
+
| 0.7667 | 32.0 | 176 | 1.3447 |
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
### Framework versions
|
| 91 |
+
|
| 92 |
+
- PEFT 0.12.0
|
| 93 |
+
- Transformers 4.44.0
|
| 94 |
+
- Pytorch 2.1.2+cu121
|
| 95 |
+
- Datasets 2.20.0
|
| 96 |
+
- 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 sha256:2813b9da52ce43b51ba2878f47ace0bdd4068f9f91b035ade30c14db8cde6430
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 32.0,
|
| 3 |
+
"total_flos": 4.322507713465549e+16,
|
| 4 |
+
"train_loss": 1.4077397015961735,
|
| 5 |
+
"train_runtime": 3298.1261,
|
| 6 |
+
"train_samples": 88,
|
| 7 |
+
"train_samples_per_second": 4.002,
|
| 8 |
+
"train_steps_per_second": 0.227
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 32.0,
|
| 3 |
+
"total_flos": 4.322507713465549e+16,
|
| 4 |
+
"train_loss": 1.4077397015961735,
|
| 5 |
+
"train_runtime": 3298.1261,
|
| 6 |
+
"train_samples": 88,
|
| 7 |
+
"train_samples_per_second": 4.002,
|
| 8 |
+
"train_steps_per_second": 0.227
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,930 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.2635489702224731,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-1_120-samples_config-4/checkpoint-137",
|
| 4 |
+
"epoch": 32.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 176,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18181818181818182,
|
| 13 |
+
"grad_norm": 1.874562382698059,
|
| 14 |
+
"learning_rate": 1.3333333333333336e-07,
|
| 15 |
+
"loss": 2.2898,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.36363636363636365,
|
| 20 |
+
"grad_norm": 1.8042479753494263,
|
| 21 |
+
"learning_rate": 2.666666666666667e-07,
|
| 22 |
+
"loss": 2.0811,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.7272727272727273,
|
| 27 |
+
"grad_norm": 1.760155200958252,
|
| 28 |
+
"learning_rate": 5.333333333333335e-07,
|
| 29 |
+
"loss": 2.121,
|
| 30 |
+
"step": 4
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.9090909090909091,
|
| 34 |
+
"eval_loss": 2.101999044418335,
|
| 35 |
+
"eval_runtime": 9.6381,
|
| 36 |
+
"eval_samples_per_second": 2.49,
|
| 37 |
+
"eval_steps_per_second": 2.49,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0909090909090908,
|
| 42 |
+
"grad_norm": 1.5958633422851562,
|
| 43 |
+
"learning_rate": 8.000000000000001e-07,
|
| 44 |
+
"loss": 1.9468,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.4545454545454546,
|
| 49 |
+
"grad_norm": 1.8069952726364136,
|
| 50 |
+
"learning_rate": 1.066666666666667e-06,
|
| 51 |
+
"loss": 2.1471,
|
| 52 |
+
"step": 8
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.8181818181818183,
|
| 56 |
+
"grad_norm": 1.736191749572754,
|
| 57 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 58 |
+
"loss": 2.0709,
|
| 59 |
+
"step": 10
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"eval_loss": 2.0930726528167725,
|
| 64 |
+
"eval_runtime": 9.6259,
|
| 65 |
+
"eval_samples_per_second": 2.493,
|
| 66 |
+
"eval_steps_per_second": 2.493,
|
| 67 |
+
"step": 11
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.1818181818181817,
|
| 71 |
+
"grad_norm": 1.6809439659118652,
|
| 72 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 73 |
+
"loss": 2.1306,
|
| 74 |
+
"step": 12
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.5454545454545454,
|
| 78 |
+
"grad_norm": 1.747848391532898,
|
| 79 |
+
"learning_rate": 1.8666666666666669e-06,
|
| 80 |
+
"loss": 2.0776,
|
| 81 |
+
"step": 14
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.909090909090909,
|
| 85 |
+
"grad_norm": 1.8399686813354492,
|
| 86 |
+
"learning_rate": 2.133333333333334e-06,
|
| 87 |
+
"loss": 2.0454,
|
| 88 |
+
"step": 16
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.909090909090909,
|
| 92 |
+
"eval_loss": 2.075482130050659,
|
| 93 |
+
"eval_runtime": 9.6366,
|
| 94 |
+
"eval_samples_per_second": 2.491,
|
| 95 |
+
"eval_steps_per_second": 2.491,
|
| 96 |
+
"step": 16
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.2727272727272725,
|
| 100 |
+
"grad_norm": 1.8816026449203491,
|
| 101 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 102 |
+
"loss": 2.1284,
|
| 103 |
+
"step": 18
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.6363636363636362,
|
| 107 |
+
"grad_norm": 1.5757534503936768,
|
| 108 |
+
"learning_rate": 2.666666666666667e-06,
|
| 109 |
+
"loss": 2.03,
|
| 110 |
+
"step": 20
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.0,
|
| 114 |
+
"grad_norm": 1.9466415643692017,
|
| 115 |
+
"learning_rate": 2.9333333333333338e-06,
|
| 116 |
+
"loss": 2.0502,
|
| 117 |
+
"step": 22
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"eval_loss": 2.0472075939178467,
|
| 122 |
+
"eval_runtime": 9.6277,
|
| 123 |
+
"eval_samples_per_second": 2.493,
|
| 124 |
+
"eval_steps_per_second": 2.493,
|
| 125 |
+
"step": 22
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.363636363636363,
|
| 129 |
+
"grad_norm": 1.6615264415740967,
|
| 130 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 131 |
+
"loss": 2.0197,
|
| 132 |
+
"step": 24
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.7272727272727275,
|
| 136 |
+
"grad_norm": 1.7619231939315796,
|
| 137 |
+
"learning_rate": 3.4666666666666672e-06,
|
| 138 |
+
"loss": 2.0511,
|
| 139 |
+
"step": 26
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 4.909090909090909,
|
| 143 |
+
"eval_loss": 2.0100386142730713,
|
| 144 |
+
"eval_runtime": 9.6313,
|
| 145 |
+
"eval_samples_per_second": 2.492,
|
| 146 |
+
"eval_steps_per_second": 2.492,
|
| 147 |
+
"step": 27
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 5.090909090909091,
|
| 151 |
+
"grad_norm": 1.8135912418365479,
|
| 152 |
+
"learning_rate": 3.7333333333333337e-06,
|
| 153 |
+
"loss": 1.9759,
|
| 154 |
+
"step": 28
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.454545454545454,
|
| 158 |
+
"grad_norm": 1.8354995250701904,
|
| 159 |
+
"learning_rate": 4.000000000000001e-06,
|
| 160 |
+
"loss": 2.0128,
|
| 161 |
+
"step": 30
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.818181818181818,
|
| 165 |
+
"grad_norm": 1.8015000820159912,
|
| 166 |
+
"learning_rate": 4.266666666666668e-06,
|
| 167 |
+
"loss": 1.9554,
|
| 168 |
+
"step": 32
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 6.0,
|
| 172 |
+
"eval_loss": 1.9471648931503296,
|
| 173 |
+
"eval_runtime": 9.6325,
|
| 174 |
+
"eval_samples_per_second": 2.492,
|
| 175 |
+
"eval_steps_per_second": 2.492,
|
| 176 |
+
"step": 33
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 6.181818181818182,
|
| 180 |
+
"grad_norm": 1.7802411317825317,
|
| 181 |
+
"learning_rate": 4.533333333333334e-06,
|
| 182 |
+
"loss": 1.9607,
|
| 183 |
+
"step": 34
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.545454545454545,
|
| 187 |
+
"grad_norm": 1.5615451335906982,
|
| 188 |
+
"learning_rate": 4.800000000000001e-06,
|
| 189 |
+
"loss": 1.9032,
|
| 190 |
+
"step": 36
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 6.909090909090909,
|
| 194 |
+
"grad_norm": 1.8741137981414795,
|
| 195 |
+
"learning_rate": 5.0666666666666676e-06,
|
| 196 |
+
"loss": 1.8921,
|
| 197 |
+
"step": 38
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 6.909090909090909,
|
| 201 |
+
"eval_loss": 1.8795281648635864,
|
| 202 |
+
"eval_runtime": 9.6403,
|
| 203 |
+
"eval_samples_per_second": 2.49,
|
| 204 |
+
"eval_steps_per_second": 2.49,
|
| 205 |
+
"step": 38
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 7.2727272727272725,
|
| 209 |
+
"grad_norm": 1.7604111433029175,
|
| 210 |
+
"learning_rate": 5.333333333333334e-06,
|
| 211 |
+
"loss": 1.8681,
|
| 212 |
+
"step": 40
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.636363636363637,
|
| 216 |
+
"grad_norm": 1.6821084022521973,
|
| 217 |
+
"learning_rate": 5.600000000000001e-06,
|
| 218 |
+
"loss": 1.769,
|
| 219 |
+
"step": 42
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 8.0,
|
| 223 |
+
"grad_norm": 1.665964126586914,
|
| 224 |
+
"learning_rate": 5.8666666666666675e-06,
|
| 225 |
+
"loss": 1.8104,
|
| 226 |
+
"step": 44
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 8.0,
|
| 230 |
+
"eval_loss": 1.7812843322753906,
|
| 231 |
+
"eval_runtime": 9.6236,
|
| 232 |
+
"eval_samples_per_second": 2.494,
|
| 233 |
+
"eval_steps_per_second": 2.494,
|
| 234 |
+
"step": 44
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 8.363636363636363,
|
| 238 |
+
"grad_norm": 1.5216890573501587,
|
| 239 |
+
"learning_rate": 6.133333333333334e-06,
|
| 240 |
+
"loss": 1.7145,
|
| 241 |
+
"step": 46
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.727272727272727,
|
| 245 |
+
"grad_norm": 1.4722410440444946,
|
| 246 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 247 |
+
"loss": 1.7636,
|
| 248 |
+
"step": 48
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.909090909090908,
|
| 252 |
+
"eval_loss": 1.6937414407730103,
|
| 253 |
+
"eval_runtime": 9.6259,
|
| 254 |
+
"eval_samples_per_second": 2.493,
|
| 255 |
+
"eval_steps_per_second": 2.493,
|
| 256 |
+
"step": 49
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 9.090909090909092,
|
| 260 |
+
"grad_norm": 1.2136281728744507,
|
| 261 |
+
"learning_rate": 6.666666666666667e-06,
|
| 262 |
+
"loss": 1.659,
|
| 263 |
+
"step": 50
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 9.454545454545455,
|
| 267 |
+
"grad_norm": 1.0023685693740845,
|
| 268 |
+
"learning_rate": 6.9333333333333344e-06,
|
| 269 |
+
"loss": 1.6509,
|
| 270 |
+
"step": 52
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 9.818181818181818,
|
| 274 |
+
"grad_norm": 1.0440162420272827,
|
| 275 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 276 |
+
"loss": 1.6011,
|
| 277 |
+
"step": 54
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 10.0,
|
| 281 |
+
"eval_loss": 1.6141911745071411,
|
| 282 |
+
"eval_runtime": 9.6302,
|
| 283 |
+
"eval_samples_per_second": 2.492,
|
| 284 |
+
"eval_steps_per_second": 2.492,
|
| 285 |
+
"step": 55
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 10.181818181818182,
|
| 289 |
+
"grad_norm": 0.7877157926559448,
|
| 290 |
+
"learning_rate": 7.4666666666666675e-06,
|
| 291 |
+
"loss": 1.5814,
|
| 292 |
+
"step": 56
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 10.545454545454545,
|
| 296 |
+
"grad_norm": 0.6534942984580994,
|
| 297 |
+
"learning_rate": 7.733333333333334e-06,
|
| 298 |
+
"loss": 1.5824,
|
| 299 |
+
"step": 58
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 10.909090909090908,
|
| 303 |
+
"grad_norm": 0.6240991950035095,
|
| 304 |
+
"learning_rate": 8.000000000000001e-06,
|
| 305 |
+
"loss": 1.5128,
|
| 306 |
+
"step": 60
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 10.909090909090908,
|
| 310 |
+
"eval_loss": 1.5751093626022339,
|
| 311 |
+
"eval_runtime": 9.6475,
|
| 312 |
+
"eval_samples_per_second": 2.488,
|
| 313 |
+
"eval_steps_per_second": 2.488,
|
| 314 |
+
"step": 60
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 11.272727272727273,
|
| 318 |
+
"grad_norm": 0.6224139928817749,
|
| 319 |
+
"learning_rate": 8.266666666666667e-06,
|
| 320 |
+
"loss": 1.5444,
|
| 321 |
+
"step": 62
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 11.636363636363637,
|
| 325 |
+
"grad_norm": 0.6345284581184387,
|
| 326 |
+
"learning_rate": 8.533333333333335e-06,
|
| 327 |
+
"loss": 1.5682,
|
| 328 |
+
"step": 64
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 12.0,
|
| 332 |
+
"grad_norm": 0.5680299997329712,
|
| 333 |
+
"learning_rate": 8.8e-06,
|
| 334 |
+
"loss": 1.4277,
|
| 335 |
+
"step": 66
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 12.0,
|
| 339 |
+
"eval_loss": 1.5352739095687866,
|
| 340 |
+
"eval_runtime": 9.6312,
|
| 341 |
+
"eval_samples_per_second": 2.492,
|
| 342 |
+
"eval_steps_per_second": 2.492,
|
| 343 |
+
"step": 66
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 12.363636363636363,
|
| 347 |
+
"grad_norm": 0.5991209745407104,
|
| 348 |
+
"learning_rate": 9.066666666666667e-06,
|
| 349 |
+
"loss": 1.4703,
|
| 350 |
+
"step": 68
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 12.727272727272727,
|
| 354 |
+
"grad_norm": 0.5993205308914185,
|
| 355 |
+
"learning_rate": 9.333333333333334e-06,
|
| 356 |
+
"loss": 1.4998,
|
| 357 |
+
"step": 70
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 12.909090909090908,
|
| 361 |
+
"eval_loss": 1.5001062154769897,
|
| 362 |
+
"eval_runtime": 9.6248,
|
| 363 |
+
"eval_samples_per_second": 2.494,
|
| 364 |
+
"eval_steps_per_second": 2.494,
|
| 365 |
+
"step": 71
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 13.090909090909092,
|
| 369 |
+
"grad_norm": 0.5633314251899719,
|
| 370 |
+
"learning_rate": 9.600000000000001e-06,
|
| 371 |
+
"loss": 1.445,
|
| 372 |
+
"step": 72
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 13.454545454545455,
|
| 376 |
+
"grad_norm": 0.5419648885726929,
|
| 377 |
+
"learning_rate": 9.866666666666668e-06,
|
| 378 |
+
"loss": 1.4256,
|
| 379 |
+
"step": 74
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 13.818181818181818,
|
| 383 |
+
"grad_norm": 0.5384172201156616,
|
| 384 |
+
"learning_rate": 9.999945845889795e-06,
|
| 385 |
+
"loss": 1.4154,
|
| 386 |
+
"step": 76
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 14.0,
|
| 390 |
+
"eval_loss": 1.4582971334457397,
|
| 391 |
+
"eval_runtime": 9.6218,
|
| 392 |
+
"eval_samples_per_second": 2.494,
|
| 393 |
+
"eval_steps_per_second": 2.494,
|
| 394 |
+
"step": 77
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 14.181818181818182,
|
| 398 |
+
"grad_norm": 0.6161755323410034,
|
| 399 |
+
"learning_rate": 9.999512620046523e-06,
|
| 400 |
+
"loss": 1.4459,
|
| 401 |
+
"step": 78
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 14.545454545454545,
|
| 405 |
+
"grad_norm": 0.5570430159568787,
|
| 406 |
+
"learning_rate": 9.99864620589731e-06,
|
| 407 |
+
"loss": 1.3661,
|
| 408 |
+
"step": 80
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 14.909090909090908,
|
| 412 |
+
"grad_norm": 0.5637471675872803,
|
| 413 |
+
"learning_rate": 9.99734667851357e-06,
|
| 414 |
+
"loss": 1.4201,
|
| 415 |
+
"step": 82
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 14.909090909090908,
|
| 419 |
+
"eval_loss": 1.4252301454544067,
|
| 420 |
+
"eval_runtime": 9.6319,
|
| 421 |
+
"eval_samples_per_second": 2.492,
|
| 422 |
+
"eval_steps_per_second": 2.492,
|
| 423 |
+
"step": 82
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 15.272727272727273,
|
| 427 |
+
"grad_norm": 0.5539014935493469,
|
| 428 |
+
"learning_rate": 9.995614150494293e-06,
|
| 429 |
+
"loss": 1.3497,
|
| 430 |
+
"step": 84
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 15.636363636363637,
|
| 434 |
+
"grad_norm": 0.5583813786506653,
|
| 435 |
+
"learning_rate": 9.993448771956285e-06,
|
| 436 |
+
"loss": 1.3512,
|
| 437 |
+
"step": 86
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 16.0,
|
| 441 |
+
"grad_norm": 0.5377728939056396,
|
| 442 |
+
"learning_rate": 9.99085073052117e-06,
|
| 443 |
+
"loss": 1.3364,
|
| 444 |
+
"step": 88
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 16.0,
|
| 448 |
+
"eval_loss": 1.3921159505844116,
|
| 449 |
+
"eval_runtime": 9.635,
|
| 450 |
+
"eval_samples_per_second": 2.491,
|
| 451 |
+
"eval_steps_per_second": 2.491,
|
| 452 |
+
"step": 88
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 16.363636363636363,
|
| 456 |
+
"grad_norm": 0.5390649437904358,
|
| 457 |
+
"learning_rate": 9.987820251299121e-06,
|
| 458 |
+
"loss": 1.3614,
|
| 459 |
+
"step": 90
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 16.727272727272727,
|
| 463 |
+
"grad_norm": 0.5126790404319763,
|
| 464 |
+
"learning_rate": 9.984357596869369e-06,
|
| 465 |
+
"loss": 1.2762,
|
| 466 |
+
"step": 92
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 16.90909090909091,
|
| 470 |
+
"eval_loss": 1.3691315650939941,
|
| 471 |
+
"eval_runtime": 9.6319,
|
| 472 |
+
"eval_samples_per_second": 2.492,
|
| 473 |
+
"eval_steps_per_second": 2.492,
|
| 474 |
+
"step": 93
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 17.09090909090909,
|
| 478 |
+
"grad_norm": 0.5642189383506775,
|
| 479 |
+
"learning_rate": 9.980463067257437e-06,
|
| 480 |
+
"loss": 1.2961,
|
| 481 |
+
"step": 94
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 17.454545454545453,
|
| 485 |
+
"grad_norm": 0.5290245413780212,
|
| 486 |
+
"learning_rate": 9.976136999909156e-06,
|
| 487 |
+
"loss": 1.1987,
|
| 488 |
+
"step": 96
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 17.818181818181817,
|
| 492 |
+
"grad_norm": 0.5963008403778076,
|
| 493 |
+
"learning_rate": 9.971379769661422e-06,
|
| 494 |
+
"loss": 1.2851,
|
| 495 |
+
"step": 98
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 18.0,
|
| 499 |
+
"eval_loss": 1.3436861038208008,
|
| 500 |
+
"eval_runtime": 9.6214,
|
| 501 |
+
"eval_samples_per_second": 2.494,
|
| 502 |
+
"eval_steps_per_second": 2.494,
|
| 503 |
+
"step": 99
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 18.181818181818183,
|
| 507 |
+
"grad_norm": 0.5820615291595459,
|
| 508 |
+
"learning_rate": 9.966191788709716e-06,
|
| 509 |
+
"loss": 1.329,
|
| 510 |
+
"step": 100
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 18.545454545454547,
|
| 514 |
+
"grad_norm": 0.5619508624076843,
|
| 515 |
+
"learning_rate": 9.960573506572391e-06,
|
| 516 |
+
"loss": 1.2428,
|
| 517 |
+
"step": 102
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 18.90909090909091,
|
| 521 |
+
"grad_norm": 0.5272645950317383,
|
| 522 |
+
"learning_rate": 9.95452541005172e-06,
|
| 523 |
+
"loss": 1.2239,
|
| 524 |
+
"step": 104
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 18.90909090909091,
|
| 528 |
+
"eval_loss": 1.3261139392852783,
|
| 529 |
+
"eval_runtime": 9.6475,
|
| 530 |
+
"eval_samples_per_second": 2.488,
|
| 531 |
+
"eval_steps_per_second": 2.488,
|
| 532 |
+
"step": 104
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 19.272727272727273,
|
| 536 |
+
"grad_norm": 0.5720901489257812,
|
| 537 |
+
"learning_rate": 9.948048023191728e-06,
|
| 538 |
+
"loss": 1.1753,
|
| 539 |
+
"step": 106
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 19.636363636363637,
|
| 543 |
+
"grad_norm": 0.5877869725227356,
|
| 544 |
+
"learning_rate": 9.941141907232766e-06,
|
| 545 |
+
"loss": 1.2334,
|
| 546 |
+
"step": 108
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 20.0,
|
| 550 |
+
"grad_norm": 0.5674625039100647,
|
| 551 |
+
"learning_rate": 9.933807660562898e-06,
|
| 552 |
+
"loss": 1.221,
|
| 553 |
+
"step": 110
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 20.0,
|
| 557 |
+
"eval_loss": 1.308407187461853,
|
| 558 |
+
"eval_runtime": 9.6226,
|
| 559 |
+
"eval_samples_per_second": 2.494,
|
| 560 |
+
"eval_steps_per_second": 2.494,
|
| 561 |
+
"step": 110
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 20.363636363636363,
|
| 565 |
+
"grad_norm": 0.5934170484542847,
|
| 566 |
+
"learning_rate": 9.926045918666045e-06,
|
| 567 |
+
"loss": 1.1685,
|
| 568 |
+
"step": 112
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 20.727272727272727,
|
| 572 |
+
"grad_norm": 0.6199212670326233,
|
| 573 |
+
"learning_rate": 9.91785735406693e-06,
|
| 574 |
+
"loss": 1.2011,
|
| 575 |
+
"step": 114
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 20.90909090909091,
|
| 579 |
+
"eval_loss": 1.2950953245162964,
|
| 580 |
+
"eval_runtime": 9.6285,
|
| 581 |
+
"eval_samples_per_second": 2.493,
|
| 582 |
+
"eval_steps_per_second": 2.493,
|
| 583 |
+
"step": 115
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 21.09090909090909,
|
| 587 |
+
"grad_norm": 0.5995011329650879,
|
| 588 |
+
"learning_rate": 9.909242676272797e-06,
|
| 589 |
+
"loss": 1.1717,
|
| 590 |
+
"step": 116
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 21.454545454545453,
|
| 594 |
+
"grad_norm": 0.6024748682975769,
|
| 595 |
+
"learning_rate": 9.90020263171194e-06,
|
| 596 |
+
"loss": 1.1654,
|
| 597 |
+
"step": 118
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 21.818181818181817,
|
| 601 |
+
"grad_norm": 0.6147428750991821,
|
| 602 |
+
"learning_rate": 9.890738003669029e-06,
|
| 603 |
+
"loss": 1.1433,
|
| 604 |
+
"step": 120
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 22.0,
|
| 608 |
+
"eval_loss": 1.2823587656021118,
|
| 609 |
+
"eval_runtime": 9.6228,
|
| 610 |
+
"eval_samples_per_second": 2.494,
|
| 611 |
+
"eval_steps_per_second": 2.494,
|
| 612 |
+
"step": 121
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 22.181818181818183,
|
| 616 |
+
"grad_norm": 0.612140953540802,
|
| 617 |
+
"learning_rate": 9.880849612217238e-06,
|
| 618 |
+
"loss": 1.0765,
|
| 619 |
+
"step": 122
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 22.545454545454547,
|
| 623 |
+
"grad_norm": 0.647298276424408,
|
| 624 |
+
"learning_rate": 9.870538314147194e-06,
|
| 625 |
+
"loss": 1.1183,
|
| 626 |
+
"step": 124
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 22.90909090909091,
|
| 630 |
+
"grad_norm": 0.6705971360206604,
|
| 631 |
+
"learning_rate": 9.859805002892733e-06,
|
| 632 |
+
"loss": 1.1579,
|
| 633 |
+
"step": 126
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 22.90909090909091,
|
| 637 |
+
"eval_loss": 1.2746213674545288,
|
| 638 |
+
"eval_runtime": 9.6328,
|
| 639 |
+
"eval_samples_per_second": 2.491,
|
| 640 |
+
"eval_steps_per_second": 2.491,
|
| 641 |
+
"step": 126
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 23.272727272727273,
|
| 645 |
+
"grad_norm": 0.670023500919342,
|
| 646 |
+
"learning_rate": 9.84865060845349e-06,
|
| 647 |
+
"loss": 1.0965,
|
| 648 |
+
"step": 128
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 23.636363636363637,
|
| 652 |
+
"grad_norm": 0.6824691891670227,
|
| 653 |
+
"learning_rate": 9.83707609731432e-06,
|
| 654 |
+
"loss": 1.061,
|
| 655 |
+
"step": 130
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 24.0,
|
| 659 |
+
"grad_norm": 0.6598721146583557,
|
| 660 |
+
"learning_rate": 9.825082472361558e-06,
|
| 661 |
+
"loss": 1.0871,
|
| 662 |
+
"step": 132
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 24.0,
|
| 666 |
+
"eval_loss": 1.268039345741272,
|
| 667 |
+
"eval_runtime": 9.6219,
|
| 668 |
+
"eval_samples_per_second": 2.494,
|
| 669 |
+
"eval_steps_per_second": 2.494,
|
| 670 |
+
"step": 132
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 24.363636363636363,
|
| 674 |
+
"grad_norm": 0.6824683547019958,
|
| 675 |
+
"learning_rate": 9.812670772796113e-06,
|
| 676 |
+
"loss": 1.0733,
|
| 677 |
+
"step": 134
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 24.727272727272727,
|
| 681 |
+
"grad_norm": 0.7309969663619995,
|
| 682 |
+
"learning_rate": 9.799842074043438e-06,
|
| 683 |
+
"loss": 1.0745,
|
| 684 |
+
"step": 136
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 24.90909090909091,
|
| 688 |
+
"eval_loss": 1.2635489702224731,
|
| 689 |
+
"eval_runtime": 9.6334,
|
| 690 |
+
"eval_samples_per_second": 2.491,
|
| 691 |
+
"eval_steps_per_second": 2.491,
|
| 692 |
+
"step": 137
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 25.09090909090909,
|
| 696 |
+
"grad_norm": 0.8717047572135925,
|
| 697 |
+
"learning_rate": 9.786597487660336e-06,
|
| 698 |
+
"loss": 1.0049,
|
| 699 |
+
"step": 138
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 25.454545454545453,
|
| 703 |
+
"grad_norm": 0.7290262579917908,
|
| 704 |
+
"learning_rate": 9.77293816123866e-06,
|
| 705 |
+
"loss": 1.0355,
|
| 706 |
+
"step": 140
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 25.818181818181817,
|
| 710 |
+
"grad_norm": 0.8125291466712952,
|
| 711 |
+
"learning_rate": 9.75886527830587e-06,
|
| 712 |
+
"loss": 1.0006,
|
| 713 |
+
"step": 142
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 26.0,
|
| 717 |
+
"eval_loss": 1.2674241065979004,
|
| 718 |
+
"eval_runtime": 9.6242,
|
| 719 |
+
"eval_samples_per_second": 2.494,
|
| 720 |
+
"eval_steps_per_second": 2.494,
|
| 721 |
+
"step": 143
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 26.181818181818183,
|
| 725 |
+
"grad_norm": 0.777037501335144,
|
| 726 |
+
"learning_rate": 9.744380058222483e-06,
|
| 727 |
+
"loss": 1.0235,
|
| 728 |
+
"step": 144
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 26.545454545454547,
|
| 732 |
+
"grad_norm": 0.7910988330841064,
|
| 733 |
+
"learning_rate": 9.729483756076436e-06,
|
| 734 |
+
"loss": 1.0119,
|
| 735 |
+
"step": 146
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 26.90909090909091,
|
| 739 |
+
"grad_norm": 0.8250744342803955,
|
| 740 |
+
"learning_rate": 9.714177662574316e-06,
|
| 741 |
+
"loss": 0.9628,
|
| 742 |
+
"step": 148
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 26.90909090909091,
|
| 746 |
+
"eval_loss": 1.2688733339309692,
|
| 747 |
+
"eval_runtime": 9.6388,
|
| 748 |
+
"eval_samples_per_second": 2.49,
|
| 749 |
+
"eval_steps_per_second": 2.49,
|
| 750 |
+
"step": 148
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 27.272727272727273,
|
| 754 |
+
"grad_norm": 0.9542063474655151,
|
| 755 |
+
"learning_rate": 9.698463103929542e-06,
|
| 756 |
+
"loss": 0.9176,
|
| 757 |
+
"step": 150
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 27.636363636363637,
|
| 761 |
+
"grad_norm": 0.8577086925506592,
|
| 762 |
+
"learning_rate": 9.682341441747446e-06,
|
| 763 |
+
"loss": 0.9908,
|
| 764 |
+
"step": 152
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 28.0,
|
| 768 |
+
"grad_norm": 0.8569504022598267,
|
| 769 |
+
"learning_rate": 9.665814072907293e-06,
|
| 770 |
+
"loss": 0.9237,
|
| 771 |
+
"step": 154
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 28.0,
|
| 775 |
+
"eval_loss": 1.2716994285583496,
|
| 776 |
+
"eval_runtime": 9.6271,
|
| 777 |
+
"eval_samples_per_second": 2.493,
|
| 778 |
+
"eval_steps_per_second": 2.493,
|
| 779 |
+
"step": 154
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 28.363636363636363,
|
| 783 |
+
"grad_norm": 0.933702826499939,
|
| 784 |
+
"learning_rate": 9.648882429441258e-06,
|
| 785 |
+
"loss": 0.9053,
|
| 786 |
+
"step": 156
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 28.727272727272727,
|
| 790 |
+
"grad_norm": 1.002100944519043,
|
| 791 |
+
"learning_rate": 9.63154797841033e-06,
|
| 792 |
+
"loss": 0.8824,
|
| 793 |
+
"step": 158
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 28.90909090909091,
|
| 797 |
+
"eval_loss": 1.2879880666732788,
|
| 798 |
+
"eval_runtime": 9.6501,
|
| 799 |
+
"eval_samples_per_second": 2.487,
|
| 800 |
+
"eval_steps_per_second": 2.487,
|
| 801 |
+
"step": 159
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 29.09090909090909,
|
| 805 |
+
"grad_norm": 0.9883065819740295,
|
| 806 |
+
"learning_rate": 9.613812221777212e-06,
|
| 807 |
+
"loss": 0.9089,
|
| 808 |
+
"step": 160
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 29.454545454545453,
|
| 812 |
+
"grad_norm": 1.0561895370483398,
|
| 813 |
+
"learning_rate": 9.595676696276173e-06,
|
| 814 |
+
"loss": 0.9285,
|
| 815 |
+
"step": 162
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 29.818181818181817,
|
| 819 |
+
"grad_norm": 1.1776067018508911,
|
| 820 |
+
"learning_rate": 9.577142973279896e-06,
|
| 821 |
+
"loss": 0.8706,
|
| 822 |
+
"step": 164
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 30.0,
|
| 826 |
+
"eval_loss": 1.296054482460022,
|
| 827 |
+
"eval_runtime": 9.6279,
|
| 828 |
+
"eval_samples_per_second": 2.493,
|
| 829 |
+
"eval_steps_per_second": 2.493,
|
| 830 |
+
"step": 165
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 30.181818181818183,
|
| 834 |
+
"grad_norm": 1.0879513025283813,
|
| 835 |
+
"learning_rate": 9.55821265866333e-06,
|
| 836 |
+
"loss": 0.7961,
|
| 837 |
+
"step": 166
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 30.545454545454547,
|
| 841 |
+
"grad_norm": 1.1668307781219482,
|
| 842 |
+
"learning_rate": 9.538887392664544e-06,
|
| 843 |
+
"loss": 0.7865,
|
| 844 |
+
"step": 168
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 30.90909090909091,
|
| 848 |
+
"grad_norm": 1.065364956855774,
|
| 849 |
+
"learning_rate": 9.519168849742603e-06,
|
| 850 |
+
"loss": 0.8328,
|
| 851 |
+
"step": 170
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 30.90909090909091,
|
| 855 |
+
"eval_loss": 1.326621174812317,
|
| 856 |
+
"eval_runtime": 9.6286,
|
| 857 |
+
"eval_samples_per_second": 2.493,
|
| 858 |
+
"eval_steps_per_second": 2.493,
|
| 859 |
+
"step": 170
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 31.272727272727273,
|
| 863 |
+
"grad_norm": 1.143373727798462,
|
| 864 |
+
"learning_rate": 9.499058738432492e-06,
|
| 865 |
+
"loss": 0.8381,
|
| 866 |
+
"step": 172
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 31.636363636363637,
|
| 870 |
+
"grad_norm": 1.1452257633209229,
|
| 871 |
+
"learning_rate": 9.478558801197065e-06,
|
| 872 |
+
"loss": 0.7725,
|
| 873 |
+
"step": 174
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 32.0,
|
| 877 |
+
"grad_norm": 1.2163513898849487,
|
| 878 |
+
"learning_rate": 9.457670814276083e-06,
|
| 879 |
+
"loss": 0.7667,
|
| 880 |
+
"step": 176
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 32.0,
|
| 884 |
+
"eval_loss": 1.344734787940979,
|
| 885 |
+
"eval_runtime": 9.6252,
|
| 886 |
+
"eval_samples_per_second": 2.493,
|
| 887 |
+
"eval_steps_per_second": 2.493,
|
| 888 |
+
"step": 176
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 32.0,
|
| 892 |
+
"step": 176,
|
| 893 |
+
"total_flos": 4.322507713465549e+16,
|
| 894 |
+
"train_loss": 1.4077397015961735,
|
| 895 |
+
"train_runtime": 3298.1261,
|
| 896 |
+
"train_samples_per_second": 4.002,
|
| 897 |
+
"train_steps_per_second": 0.227
|
| 898 |
+
}
|
| 899 |
+
],
|
| 900 |
+
"logging_steps": 2,
|
| 901 |
+
"max_steps": 750,
|
| 902 |
+
"num_input_tokens_seen": 0,
|
| 903 |
+
"num_train_epochs": 150,
|
| 904 |
+
"save_steps": 25,
|
| 905 |
+
"stateful_callbacks": {
|
| 906 |
+
"EarlyStoppingCallback": {
|
| 907 |
+
"args": {
|
| 908 |
+
"early_stopping_patience": 7,
|
| 909 |
+
"early_stopping_threshold": 0.0
|
| 910 |
+
},
|
| 911 |
+
"attributes": {
|
| 912 |
+
"early_stopping_patience_counter": 0
|
| 913 |
+
}
|
| 914 |
+
},
|
| 915 |
+
"TrainerControl": {
|
| 916 |
+
"args": {
|
| 917 |
+
"should_epoch_stop": false,
|
| 918 |
+
"should_evaluate": false,
|
| 919 |
+
"should_log": false,
|
| 920 |
+
"should_save": true,
|
| 921 |
+
"should_training_stop": true
|
| 922 |
+
},
|
| 923 |
+
"attributes": {}
|
| 924 |
+
}
|
| 925 |
+
},
|
| 926 |
+
"total_flos": 4.322507713465549e+16,
|
| 927 |
+
"train_batch_size": 1,
|
| 928 |
+
"trial_name": null,
|
| 929 |
+
"trial_params": null
|
| 930 |
+
}
|