Commit
·
943c725
1
Parent(s):
912a8d6
End of training
Browse files- README.md +107 -0
- model.safetensors +1 -1
- trainer_state.json +728 -0
README.md
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: polejowska/detr-r50-cd45rb-8ah-6l
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: detr-r50-finetuned-mist1-gb-4ah-6l
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# detr-r50-finetuned-mist1-gb-4ah-6l
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [polejowska/detr-r50-cd45rb-8ah-6l](https://huggingface.co/polejowska/detr-r50-cd45rb-8ah-6l) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.2166
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-05
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 50
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 3.4044 | 1.0 | 115 | 3.0048 |
|
| 51 |
+
| 3.1708 | 2.0 | 230 | 2.9028 |
|
| 52 |
+
| 3.0756 | 3.0 | 345 | 2.8538 |
|
| 53 |
+
| 2.9769 | 4.0 | 460 | 2.8149 |
|
| 54 |
+
| 2.8999 | 5.0 | 575 | 2.7332 |
|
| 55 |
+
| 2.8609 | 6.0 | 690 | 2.7212 |
|
| 56 |
+
| 2.8338 | 7.0 | 805 | 2.6894 |
|
| 57 |
+
| 2.8103 | 8.0 | 920 | 2.7045 |
|
| 58 |
+
| 2.8036 | 9.0 | 1035 | 2.7786 |
|
| 59 |
+
| 2.7486 | 10.0 | 1150 | 2.6881 |
|
| 60 |
+
| 2.7076 | 11.0 | 1265 | 2.6059 |
|
| 61 |
+
| 2.7156 | 12.0 | 1380 | 2.6483 |
|
| 62 |
+
| 2.6655 | 13.0 | 1495 | 2.5438 |
|
| 63 |
+
| 2.6368 | 14.0 | 1610 | 2.5342 |
|
| 64 |
+
| 2.5982 | 15.0 | 1725 | 2.5287 |
|
| 65 |
+
| 2.6116 | 16.0 | 1840 | 2.4446 |
|
| 66 |
+
| 2.5592 | 17.0 | 1955 | 2.4365 |
|
| 67 |
+
| 2.5528 | 18.0 | 2070 | 2.4844 |
|
| 68 |
+
| 2.5248 | 19.0 | 2185 | 2.4195 |
|
| 69 |
+
| 2.4853 | 20.0 | 2300 | 2.4538 |
|
| 70 |
+
| 2.5295 | 21.0 | 2415 | 2.5696 |
|
| 71 |
+
| 2.5069 | 22.0 | 2530 | 2.4537 |
|
| 72 |
+
| 2.4504 | 23.0 | 2645 | 2.5152 |
|
| 73 |
+
| 2.4447 | 24.0 | 2760 | 2.4432 |
|
| 74 |
+
| 2.4303 | 25.0 | 2875 | 2.4033 |
|
| 75 |
+
| 2.4137 | 26.0 | 2990 | 2.3796 |
|
| 76 |
+
| 2.41 | 27.0 | 3105 | 2.3599 |
|
| 77 |
+
| 2.3816 | 28.0 | 3220 | 2.4018 |
|
| 78 |
+
| 2.3752 | 29.0 | 3335 | 2.3116 |
|
| 79 |
+
| 2.3929 | 30.0 | 3450 | 2.3105 |
|
| 80 |
+
| 2.3791 | 31.0 | 3565 | 2.3677 |
|
| 81 |
+
| 2.3639 | 32.0 | 3680 | 2.4312 |
|
| 82 |
+
| 2.3475 | 33.0 | 3795 | 2.3052 |
|
| 83 |
+
| 2.3429 | 34.0 | 3910 | 2.3222 |
|
| 84 |
+
| 2.3115 | 35.0 | 4025 | 2.3126 |
|
| 85 |
+
| 2.3276 | 36.0 | 4140 | 2.3154 |
|
| 86 |
+
| 2.3126 | 37.0 | 4255 | 2.3534 |
|
| 87 |
+
| 2.2934 | 38.0 | 4370 | 2.2566 |
|
| 88 |
+
| 2.2901 | 39.0 | 4485 | 2.2748 |
|
| 89 |
+
| 2.2622 | 40.0 | 4600 | 2.2620 |
|
| 90 |
+
| 2.2707 | 41.0 | 4715 | 2.2336 |
|
| 91 |
+
| 2.2338 | 42.0 | 4830 | 2.2242 |
|
| 92 |
+
| 2.2457 | 43.0 | 4945 | 2.2192 |
|
| 93 |
+
| 2.227 | 44.0 | 5060 | 2.2067 |
|
| 94 |
+
| 2.2215 | 45.0 | 5175 | 2.2183 |
|
| 95 |
+
| 2.2075 | 46.0 | 5290 | 2.2188 |
|
| 96 |
+
| 2.2286 | 47.0 | 5405 | 2.2306 |
|
| 97 |
+
| 2.2292 | 48.0 | 5520 | 2.2160 |
|
| 98 |
+
| 2.219 | 49.0 | 5635 | 2.2208 |
|
| 99 |
+
| 2.2125 | 50.0 | 5750 | 2.2166 |
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
### Framework versions
|
| 103 |
+
|
| 104 |
+
- Transformers 4.35.0
|
| 105 |
+
- Pytorch 2.0.0
|
| 106 |
+
- Datasets 2.1.0
|
| 107 |
+
- Tokenizers 0.14.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 166494824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03a13c67ec7bcd25ca536198d4cc57900ecebbaac67ad5332b4775a08051119b
|
| 3 |
size 166494824
|
trainer_state.json
ADDED
|
@@ -0,0 +1,728 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.206695079803467,
|
| 3 |
+
"best_model_checkpoint": "detr-r50-finetuned-mist1-gb-4ah-6l/checkpoint-5060",
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5750,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"learning_rate": 9.812173913043479e-06,
|
| 14 |
+
"loss": 3.4044,
|
| 15 |
+
"step": 115
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_loss": 3.004835844039917,
|
| 20 |
+
"eval_runtime": 5.8385,
|
| 21 |
+
"eval_samples_per_second": 6.851,
|
| 22 |
+
"eval_steps_per_second": 0.856,
|
| 23 |
+
"step": 115
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 9.612173913043479e-06,
|
| 28 |
+
"loss": 3.1708,
|
| 29 |
+
"step": 230
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_loss": 2.902806520462036,
|
| 34 |
+
"eval_runtime": 5.7867,
|
| 35 |
+
"eval_samples_per_second": 6.912,
|
| 36 |
+
"eval_steps_per_second": 0.864,
|
| 37 |
+
"step": 230
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 3.0,
|
| 41 |
+
"learning_rate": 9.412173913043479e-06,
|
| 42 |
+
"loss": 3.0756,
|
| 43 |
+
"step": 345
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 3.0,
|
| 47 |
+
"eval_loss": 2.853818416595459,
|
| 48 |
+
"eval_runtime": 5.8759,
|
| 49 |
+
"eval_samples_per_second": 6.808,
|
| 50 |
+
"eval_steps_per_second": 0.851,
|
| 51 |
+
"step": 345
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.0,
|
| 55 |
+
"learning_rate": 9.21217391304348e-06,
|
| 56 |
+
"loss": 2.9769,
|
| 57 |
+
"step": 460
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"eval_loss": 2.814894914627075,
|
| 62 |
+
"eval_runtime": 5.8445,
|
| 63 |
+
"eval_samples_per_second": 6.844,
|
| 64 |
+
"eval_steps_per_second": 0.855,
|
| 65 |
+
"step": 460
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 5.0,
|
| 69 |
+
"learning_rate": 9.01217391304348e-06,
|
| 70 |
+
"loss": 2.8999,
|
| 71 |
+
"step": 575
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 5.0,
|
| 75 |
+
"eval_loss": 2.7331762313842773,
|
| 76 |
+
"eval_runtime": 5.9217,
|
| 77 |
+
"eval_samples_per_second": 6.755,
|
| 78 |
+
"eval_steps_per_second": 0.844,
|
| 79 |
+
"step": 575
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 6.0,
|
| 83 |
+
"learning_rate": 8.81217391304348e-06,
|
| 84 |
+
"loss": 2.8609,
|
| 85 |
+
"step": 690
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 6.0,
|
| 89 |
+
"eval_loss": 2.7212414741516113,
|
| 90 |
+
"eval_runtime": 5.879,
|
| 91 |
+
"eval_samples_per_second": 6.804,
|
| 92 |
+
"eval_steps_per_second": 0.85,
|
| 93 |
+
"step": 690
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.0,
|
| 97 |
+
"learning_rate": 8.613913043478262e-06,
|
| 98 |
+
"loss": 2.8338,
|
| 99 |
+
"step": 805
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.0,
|
| 103 |
+
"eval_loss": 2.689382553100586,
|
| 104 |
+
"eval_runtime": 5.8299,
|
| 105 |
+
"eval_samples_per_second": 6.861,
|
| 106 |
+
"eval_steps_per_second": 0.858,
|
| 107 |
+
"step": 805
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"learning_rate": 8.413913043478262e-06,
|
| 112 |
+
"loss": 2.8103,
|
| 113 |
+
"step": 920
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 8.0,
|
| 117 |
+
"eval_loss": 2.704505681991577,
|
| 118 |
+
"eval_runtime": 5.7873,
|
| 119 |
+
"eval_samples_per_second": 6.912,
|
| 120 |
+
"eval_steps_per_second": 0.864,
|
| 121 |
+
"step": 920
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 9.0,
|
| 125 |
+
"learning_rate": 8.21391304347826e-06,
|
| 126 |
+
"loss": 2.8036,
|
| 127 |
+
"step": 1035
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 9.0,
|
| 131 |
+
"eval_loss": 2.778614044189453,
|
| 132 |
+
"eval_runtime": 5.7444,
|
| 133 |
+
"eval_samples_per_second": 6.963,
|
| 134 |
+
"eval_steps_per_second": 0.87,
|
| 135 |
+
"step": 1035
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.0,
|
| 139 |
+
"learning_rate": 8.013913043478262e-06,
|
| 140 |
+
"loss": 2.7486,
|
| 141 |
+
"step": 1150
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.0,
|
| 145 |
+
"eval_loss": 2.688080310821533,
|
| 146 |
+
"eval_runtime": 5.7616,
|
| 147 |
+
"eval_samples_per_second": 6.943,
|
| 148 |
+
"eval_steps_per_second": 0.868,
|
| 149 |
+
"step": 1150
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 11.0,
|
| 153 |
+
"learning_rate": 7.813913043478263e-06,
|
| 154 |
+
"loss": 2.7076,
|
| 155 |
+
"step": 1265
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 11.0,
|
| 159 |
+
"eval_loss": 2.605870485305786,
|
| 160 |
+
"eval_runtime": 5.8415,
|
| 161 |
+
"eval_samples_per_second": 6.848,
|
| 162 |
+
"eval_steps_per_second": 0.856,
|
| 163 |
+
"step": 1265
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 12.0,
|
| 167 |
+
"learning_rate": 7.615652173913044e-06,
|
| 168 |
+
"loss": 2.7156,
|
| 169 |
+
"step": 1380
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 12.0,
|
| 173 |
+
"eval_loss": 2.648322343826294,
|
| 174 |
+
"eval_runtime": 5.8314,
|
| 175 |
+
"eval_samples_per_second": 6.859,
|
| 176 |
+
"eval_steps_per_second": 0.857,
|
| 177 |
+
"step": 1380
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"learning_rate": 7.415652173913044e-06,
|
| 182 |
+
"loss": 2.6655,
|
| 183 |
+
"step": 1495
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 13.0,
|
| 187 |
+
"eval_loss": 2.5438005924224854,
|
| 188 |
+
"eval_runtime": 5.7667,
|
| 189 |
+
"eval_samples_per_second": 6.936,
|
| 190 |
+
"eval_steps_per_second": 0.867,
|
| 191 |
+
"step": 1495
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.0,
|
| 195 |
+
"learning_rate": 7.215652173913043e-06,
|
| 196 |
+
"loss": 2.6368,
|
| 197 |
+
"step": 1610
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 14.0,
|
| 201 |
+
"eval_loss": 2.5342297554016113,
|
| 202 |
+
"eval_runtime": 5.7673,
|
| 203 |
+
"eval_samples_per_second": 6.936,
|
| 204 |
+
"eval_steps_per_second": 0.867,
|
| 205 |
+
"step": 1610
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 15.0,
|
| 209 |
+
"learning_rate": 7.015652173913044e-06,
|
| 210 |
+
"loss": 2.5982,
|
| 211 |
+
"step": 1725
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 15.0,
|
| 215 |
+
"eval_loss": 2.5287182331085205,
|
| 216 |
+
"eval_runtime": 5.8321,
|
| 217 |
+
"eval_samples_per_second": 6.859,
|
| 218 |
+
"eval_steps_per_second": 0.857,
|
| 219 |
+
"step": 1725
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.0,
|
| 223 |
+
"learning_rate": 6.815652173913045e-06,
|
| 224 |
+
"loss": 2.6116,
|
| 225 |
+
"step": 1840
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 16.0,
|
| 229 |
+
"eval_loss": 2.4446094036102295,
|
| 230 |
+
"eval_runtime": 5.7529,
|
| 231 |
+
"eval_samples_per_second": 6.953,
|
| 232 |
+
"eval_steps_per_second": 0.869,
|
| 233 |
+
"step": 1840
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 17.0,
|
| 237 |
+
"learning_rate": 6.615652173913044e-06,
|
| 238 |
+
"loss": 2.5592,
|
| 239 |
+
"step": 1955
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.0,
|
| 243 |
+
"eval_loss": 2.4365103244781494,
|
| 244 |
+
"eval_runtime": 5.7499,
|
| 245 |
+
"eval_samples_per_second": 6.957,
|
| 246 |
+
"eval_steps_per_second": 0.87,
|
| 247 |
+
"step": 1955
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 18.0,
|
| 251 |
+
"learning_rate": 6.415652173913044e-06,
|
| 252 |
+
"loss": 2.5528,
|
| 253 |
+
"step": 2070
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 18.0,
|
| 257 |
+
"eval_loss": 2.484395980834961,
|
| 258 |
+
"eval_runtime": 5.7801,
|
| 259 |
+
"eval_samples_per_second": 6.92,
|
| 260 |
+
"eval_steps_per_second": 0.865,
|
| 261 |
+
"step": 2070
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 19.0,
|
| 265 |
+
"learning_rate": 6.215652173913044e-06,
|
| 266 |
+
"loss": 2.5248,
|
| 267 |
+
"step": 2185
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 19.0,
|
| 271 |
+
"eval_loss": 2.4194891452789307,
|
| 272 |
+
"eval_runtime": 5.7656,
|
| 273 |
+
"eval_samples_per_second": 6.938,
|
| 274 |
+
"eval_steps_per_second": 0.867,
|
| 275 |
+
"step": 2185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 20.0,
|
| 279 |
+
"learning_rate": 6.015652173913044e-06,
|
| 280 |
+
"loss": 2.4853,
|
| 281 |
+
"step": 2300
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 20.0,
|
| 285 |
+
"eval_loss": 2.453843832015991,
|
| 286 |
+
"eval_runtime": 5.8034,
|
| 287 |
+
"eval_samples_per_second": 6.893,
|
| 288 |
+
"eval_steps_per_second": 0.862,
|
| 289 |
+
"step": 2300
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 21.0,
|
| 293 |
+
"learning_rate": 5.815652173913045e-06,
|
| 294 |
+
"loss": 2.5295,
|
| 295 |
+
"step": 2415
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 21.0,
|
| 299 |
+
"eval_loss": 2.569608211517334,
|
| 300 |
+
"eval_runtime": 5.8097,
|
| 301 |
+
"eval_samples_per_second": 6.885,
|
| 302 |
+
"eval_steps_per_second": 0.861,
|
| 303 |
+
"step": 2415
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 22.0,
|
| 307 |
+
"learning_rate": 5.615652173913044e-06,
|
| 308 |
+
"loss": 2.5069,
|
| 309 |
+
"step": 2530
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 22.0,
|
| 313 |
+
"eval_loss": 2.4536538124084473,
|
| 314 |
+
"eval_runtime": 5.7892,
|
| 315 |
+
"eval_samples_per_second": 6.909,
|
| 316 |
+
"eval_steps_per_second": 0.864,
|
| 317 |
+
"step": 2530
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 23.0,
|
| 321 |
+
"learning_rate": 5.4156521739130445e-06,
|
| 322 |
+
"loss": 2.4504,
|
| 323 |
+
"step": 2645
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 23.0,
|
| 327 |
+
"eval_loss": 2.515150547027588,
|
| 328 |
+
"eval_runtime": 5.8674,
|
| 329 |
+
"eval_samples_per_second": 6.817,
|
| 330 |
+
"eval_steps_per_second": 0.852,
|
| 331 |
+
"step": 2645
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 24.0,
|
| 335 |
+
"learning_rate": 5.215652173913044e-06,
|
| 336 |
+
"loss": 2.4447,
|
| 337 |
+
"step": 2760
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 24.0,
|
| 341 |
+
"eval_loss": 2.4431958198547363,
|
| 342 |
+
"eval_runtime": 5.9181,
|
| 343 |
+
"eval_samples_per_second": 6.759,
|
| 344 |
+
"eval_steps_per_second": 0.845,
|
| 345 |
+
"step": 2760
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 25.0,
|
| 349 |
+
"learning_rate": 5.015652173913044e-06,
|
| 350 |
+
"loss": 2.4303,
|
| 351 |
+
"step": 2875
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 25.0,
|
| 355 |
+
"eval_loss": 2.4032533168792725,
|
| 356 |
+
"eval_runtime": 5.9198,
|
| 357 |
+
"eval_samples_per_second": 6.757,
|
| 358 |
+
"eval_steps_per_second": 0.845,
|
| 359 |
+
"step": 2875
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 26.0,
|
| 363 |
+
"learning_rate": 4.815652173913044e-06,
|
| 364 |
+
"loss": 2.4137,
|
| 365 |
+
"step": 2990
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 26.0,
|
| 369 |
+
"eval_loss": 2.3795552253723145,
|
| 370 |
+
"eval_runtime": 5.8418,
|
| 371 |
+
"eval_samples_per_second": 6.847,
|
| 372 |
+
"eval_steps_per_second": 0.856,
|
| 373 |
+
"step": 2990
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 27.0,
|
| 377 |
+
"learning_rate": 4.615652173913044e-06,
|
| 378 |
+
"loss": 2.41,
|
| 379 |
+
"step": 3105
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 27.0,
|
| 383 |
+
"eval_loss": 2.3598742485046387,
|
| 384 |
+
"eval_runtime": 5.8868,
|
| 385 |
+
"eval_samples_per_second": 6.795,
|
| 386 |
+
"eval_steps_per_second": 0.849,
|
| 387 |
+
"step": 3105
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 28.0,
|
| 391 |
+
"learning_rate": 4.415652173913044e-06,
|
| 392 |
+
"loss": 2.3816,
|
| 393 |
+
"step": 3220
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 28.0,
|
| 397 |
+
"eval_loss": 2.401759386062622,
|
| 398 |
+
"eval_runtime": 5.8373,
|
| 399 |
+
"eval_samples_per_second": 6.852,
|
| 400 |
+
"eval_steps_per_second": 0.857,
|
| 401 |
+
"step": 3220
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 29.0,
|
| 405 |
+
"learning_rate": 4.215652173913044e-06,
|
| 406 |
+
"loss": 2.3752,
|
| 407 |
+
"step": 3335
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 29.0,
|
| 411 |
+
"eval_loss": 2.3115689754486084,
|
| 412 |
+
"eval_runtime": 5.8962,
|
| 413 |
+
"eval_samples_per_second": 6.784,
|
| 414 |
+
"eval_steps_per_second": 0.848,
|
| 415 |
+
"step": 3335
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 30.0,
|
| 419 |
+
"learning_rate": 4.0156521739130435e-06,
|
| 420 |
+
"loss": 2.3929,
|
| 421 |
+
"step": 3450
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 30.0,
|
| 425 |
+
"eval_loss": 2.310469150543213,
|
| 426 |
+
"eval_runtime": 5.8122,
|
| 427 |
+
"eval_samples_per_second": 6.882,
|
| 428 |
+
"eval_steps_per_second": 0.86,
|
| 429 |
+
"step": 3450
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 31.0,
|
| 433 |
+
"learning_rate": 3.815652173913044e-06,
|
| 434 |
+
"loss": 2.3791,
|
| 435 |
+
"step": 3565
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 31.0,
|
| 439 |
+
"eval_loss": 2.367689371109009,
|
| 440 |
+
"eval_runtime": 5.837,
|
| 441 |
+
"eval_samples_per_second": 6.853,
|
| 442 |
+
"eval_steps_per_second": 0.857,
|
| 443 |
+
"step": 3565
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 32.0,
|
| 447 |
+
"learning_rate": 3.615652173913044e-06,
|
| 448 |
+
"loss": 2.3639,
|
| 449 |
+
"step": 3680
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 32.0,
|
| 453 |
+
"eval_loss": 2.431199550628662,
|
| 454 |
+
"eval_runtime": 5.8179,
|
| 455 |
+
"eval_samples_per_second": 6.875,
|
| 456 |
+
"eval_steps_per_second": 0.859,
|
| 457 |
+
"step": 3680
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 33.0,
|
| 461 |
+
"learning_rate": 3.4156521739130437e-06,
|
| 462 |
+
"loss": 2.3475,
|
| 463 |
+
"step": 3795
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 33.0,
|
| 467 |
+
"eval_loss": 2.3051953315734863,
|
| 468 |
+
"eval_runtime": 5.7888,
|
| 469 |
+
"eval_samples_per_second": 6.91,
|
| 470 |
+
"eval_steps_per_second": 0.864,
|
| 471 |
+
"step": 3795
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 34.0,
|
| 475 |
+
"learning_rate": 3.2156521739130435e-06,
|
| 476 |
+
"loss": 2.3429,
|
| 477 |
+
"step": 3910
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 34.0,
|
| 481 |
+
"eval_loss": 2.322197675704956,
|
| 482 |
+
"eval_runtime": 5.7936,
|
| 483 |
+
"eval_samples_per_second": 6.904,
|
| 484 |
+
"eval_steps_per_second": 0.863,
|
| 485 |
+
"step": 3910
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 35.0,
|
| 489 |
+
"learning_rate": 3.015652173913044e-06,
|
| 490 |
+
"loss": 2.3115,
|
| 491 |
+
"step": 4025
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 35.0,
|
| 495 |
+
"eval_loss": 2.3126182556152344,
|
| 496 |
+
"eval_runtime": 5.8416,
|
| 497 |
+
"eval_samples_per_second": 6.847,
|
| 498 |
+
"eval_steps_per_second": 0.856,
|
| 499 |
+
"step": 4025
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 36.0,
|
| 503 |
+
"learning_rate": 2.815652173913044e-06,
|
| 504 |
+
"loss": 2.3276,
|
| 505 |
+
"step": 4140
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 36.0,
|
| 509 |
+
"eval_loss": 2.3154168128967285,
|
| 510 |
+
"eval_runtime": 5.7988,
|
| 511 |
+
"eval_samples_per_second": 6.898,
|
| 512 |
+
"eval_steps_per_second": 0.862,
|
| 513 |
+
"step": 4140
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 37.0,
|
| 517 |
+
"learning_rate": 2.6156521739130438e-06,
|
| 518 |
+
"loss": 2.3126,
|
| 519 |
+
"step": 4255
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 37.0,
|
| 523 |
+
"eval_loss": 2.353442430496216,
|
| 524 |
+
"eval_runtime": 5.7487,
|
| 525 |
+
"eval_samples_per_second": 6.958,
|
| 526 |
+
"eval_steps_per_second": 0.87,
|
| 527 |
+
"step": 4255
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 38.0,
|
| 531 |
+
"learning_rate": 2.417391304347826e-06,
|
| 532 |
+
"loss": 2.2934,
|
| 533 |
+
"step": 4370
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 38.0,
|
| 537 |
+
"eval_loss": 2.2566468715667725,
|
| 538 |
+
"eval_runtime": 5.902,
|
| 539 |
+
"eval_samples_per_second": 6.777,
|
| 540 |
+
"eval_steps_per_second": 0.847,
|
| 541 |
+
"step": 4370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 39.0,
|
| 545 |
+
"learning_rate": 2.2173913043478264e-06,
|
| 546 |
+
"loss": 2.2901,
|
| 547 |
+
"step": 4485
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 39.0,
|
| 551 |
+
"eval_loss": 2.274752140045166,
|
| 552 |
+
"eval_runtime": 5.8191,
|
| 553 |
+
"eval_samples_per_second": 6.874,
|
| 554 |
+
"eval_steps_per_second": 0.859,
|
| 555 |
+
"step": 4485
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 40.0,
|
| 559 |
+
"learning_rate": 2.017391304347826e-06,
|
| 560 |
+
"loss": 2.2622,
|
| 561 |
+
"step": 4600
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 40.0,
|
| 565 |
+
"eval_loss": 2.2620463371276855,
|
| 566 |
+
"eval_runtime": 5.7456,
|
| 567 |
+
"eval_samples_per_second": 6.962,
|
| 568 |
+
"eval_steps_per_second": 0.87,
|
| 569 |
+
"step": 4600
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 41.0,
|
| 573 |
+
"learning_rate": 1.8173913043478262e-06,
|
| 574 |
+
"loss": 2.2707,
|
| 575 |
+
"step": 4715
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 41.0,
|
| 579 |
+
"eval_loss": 2.2336184978485107,
|
| 580 |
+
"eval_runtime": 5.8344,
|
| 581 |
+
"eval_samples_per_second": 6.856,
|
| 582 |
+
"eval_steps_per_second": 0.857,
|
| 583 |
+
"step": 4715
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 42.0,
|
| 587 |
+
"learning_rate": 1.6173913043478262e-06,
|
| 588 |
+
"loss": 2.2338,
|
| 589 |
+
"step": 4830
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 42.0,
|
| 593 |
+
"eval_loss": 2.224193811416626,
|
| 594 |
+
"eval_runtime": 5.7896,
|
| 595 |
+
"eval_samples_per_second": 6.909,
|
| 596 |
+
"eval_steps_per_second": 0.864,
|
| 597 |
+
"step": 4830
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 43.0,
|
| 601 |
+
"learning_rate": 1.4173913043478262e-06,
|
| 602 |
+
"loss": 2.2457,
|
| 603 |
+
"step": 4945
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 43.0,
|
| 607 |
+
"eval_loss": 2.219238758087158,
|
| 608 |
+
"eval_runtime": 5.8096,
|
| 609 |
+
"eval_samples_per_second": 6.885,
|
| 610 |
+
"eval_steps_per_second": 0.861,
|
| 611 |
+
"step": 4945
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 44.0,
|
| 615 |
+
"learning_rate": 1.2173913043478262e-06,
|
| 616 |
+
"loss": 2.227,
|
| 617 |
+
"step": 5060
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 44.0,
|
| 621 |
+
"eval_loss": 2.206695079803467,
|
| 622 |
+
"eval_runtime": 5.7447,
|
| 623 |
+
"eval_samples_per_second": 6.963,
|
| 624 |
+
"eval_steps_per_second": 0.87,
|
| 625 |
+
"step": 5060
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 45.0,
|
| 629 |
+
"learning_rate": 1.0173913043478262e-06,
|
| 630 |
+
"loss": 2.2215,
|
| 631 |
+
"step": 5175
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 45.0,
|
| 635 |
+
"eval_loss": 2.2183449268341064,
|
| 636 |
+
"eval_runtime": 5.7702,
|
| 637 |
+
"eval_samples_per_second": 6.932,
|
| 638 |
+
"eval_steps_per_second": 0.867,
|
| 639 |
+
"step": 5175
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 46.0,
|
| 643 |
+
"learning_rate": 8.173913043478261e-07,
|
| 644 |
+
"loss": 2.2075,
|
| 645 |
+
"step": 5290
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 46.0,
|
| 649 |
+
"eval_loss": 2.2187769412994385,
|
| 650 |
+
"eval_runtime": 5.7737,
|
| 651 |
+
"eval_samples_per_second": 6.928,
|
| 652 |
+
"eval_steps_per_second": 0.866,
|
| 653 |
+
"step": 5290
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 47.0,
|
| 657 |
+
"learning_rate": 6.173913043478262e-07,
|
| 658 |
+
"loss": 2.2286,
|
| 659 |
+
"step": 5405
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 47.0,
|
| 663 |
+
"eval_loss": 2.2306272983551025,
|
| 664 |
+
"eval_runtime": 5.7527,
|
| 665 |
+
"eval_samples_per_second": 6.953,
|
| 666 |
+
"eval_steps_per_second": 0.869,
|
| 667 |
+
"step": 5405
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 48.0,
|
| 671 |
+
"learning_rate": 4.1739130434782616e-07,
|
| 672 |
+
"loss": 2.2292,
|
| 673 |
+
"step": 5520
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 48.0,
|
| 677 |
+
"eval_loss": 2.2159781455993652,
|
| 678 |
+
"eval_runtime": 5.8705,
|
| 679 |
+
"eval_samples_per_second": 6.814,
|
| 680 |
+
"eval_steps_per_second": 0.852,
|
| 681 |
+
"step": 5520
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 49.0,
|
| 685 |
+
"learning_rate": 2.173913043478261e-07,
|
| 686 |
+
"loss": 2.219,
|
| 687 |
+
"step": 5635
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 49.0,
|
| 691 |
+
"eval_loss": 2.2207822799682617,
|
| 692 |
+
"eval_runtime": 5.7679,
|
| 693 |
+
"eval_samples_per_second": 6.935,
|
| 694 |
+
"eval_steps_per_second": 0.867,
|
| 695 |
+
"step": 5635
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 50.0,
|
| 699 |
+
"learning_rate": 1.739130434782609e-08,
|
| 700 |
+
"loss": 2.2125,
|
| 701 |
+
"step": 5750
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 50.0,
|
| 705 |
+
"eval_loss": 2.216578722000122,
|
| 706 |
+
"eval_runtime": 5.8453,
|
| 707 |
+
"eval_samples_per_second": 6.843,
|
| 708 |
+
"eval_steps_per_second": 0.855,
|
| 709 |
+
"step": 5750
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 50.0,
|
| 713 |
+
"step": 5750,
|
| 714 |
+
"total_flos": 1.098949102848e+19,
|
| 715 |
+
"train_loss": 2.5100708697775134,
|
| 716 |
+
"train_runtime": 4619.9285,
|
| 717 |
+
"train_samples_per_second": 4.978,
|
| 718 |
+
"train_steps_per_second": 1.245
|
| 719 |
+
}
|
| 720 |
+
],
|
| 721 |
+
"logging_steps": 500,
|
| 722 |
+
"max_steps": 5750,
|
| 723 |
+
"num_train_epochs": 50,
|
| 724 |
+
"save_steps": 500,
|
| 725 |
+
"total_flos": 1.098949102848e+19,
|
| 726 |
+
"trial_name": null,
|
| 727 |
+
"trial_params": null
|
| 728 |
+
}
|