Commit
•
66faedd
1
Parent(s):
d4e5f69
End of training
Browse files- README.md +82 -0
- trainer_state.json +378 -0
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/detr-resnet-50
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: detr-r50-mist1-bg-8ah-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-mist1-bg-8ah-6l
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.1031
|
| 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: 25
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 3.6794 | 1.0 | 115 | 2.8222 |
|
| 51 |
+
| 3.0269 | 2.0 | 230 | 2.8120 |
|
| 52 |
+
| 2.8681 | 3.0 | 345 | 2.7980 |
|
| 53 |
+
| 2.752 | 4.0 | 460 | 2.4853 |
|
| 54 |
+
| 2.7715 | 5.0 | 575 | 2.4140 |
|
| 55 |
+
| 2.6846 | 6.0 | 690 | 2.4715 |
|
| 56 |
+
| 2.6236 | 7.0 | 805 | 2.4614 |
|
| 57 |
+
| 2.5318 | 8.0 | 920 | 2.3441 |
|
| 58 |
+
| 2.5224 | 9.0 | 1035 | 2.2837 |
|
| 59 |
+
| 2.4661 | 10.0 | 1150 | 2.2510 |
|
| 60 |
+
| 2.4313 | 11.0 | 1265 | 2.3339 |
|
| 61 |
+
| 2.4125 | 12.0 | 1380 | 2.2957 |
|
| 62 |
+
| 2.4113 | 13.0 | 1495 | 2.2358 |
|
| 63 |
+
| 2.3784 | 14.0 | 1610 | 2.2635 |
|
| 64 |
+
| 2.3199 | 15.0 | 1725 | 2.2320 |
|
| 65 |
+
| 2.3321 | 16.0 | 1840 | 2.2250 |
|
| 66 |
+
| 2.3305 | 17.0 | 1955 | 2.2020 |
|
| 67 |
+
| 2.2932 | 18.0 | 2070 | 2.1826 |
|
| 68 |
+
| 2.2952 | 19.0 | 2185 | 2.1626 |
|
| 69 |
+
| 2.2663 | 20.0 | 2300 | 2.1573 |
|
| 70 |
+
| 2.2916 | 21.0 | 2415 | 2.1653 |
|
| 71 |
+
| 2.2703 | 22.0 | 2530 | 2.1444 |
|
| 72 |
+
| 2.2431 | 23.0 | 2645 | 2.1374 |
|
| 73 |
+
| 2.2243 | 24.0 | 2760 | 2.1276 |
|
| 74 |
+
| 2.2413 | 25.0 | 2875 | 2.1031 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.35.0
|
| 80 |
+
- Pytorch 2.0.0
|
| 81 |
+
- Datasets 2.1.0
|
| 82 |
+
- Tokenizers 0.14.1
|
trainer_state.json
ADDED
|
@@ -0,0 +1,378 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.1030609607696533,
|
| 3 |
+
"best_model_checkpoint": "detr-r50-mist1-bg-8ah-6l/checkpoint-2875",
|
| 4 |
+
"epoch": 25.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2875,
|
| 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": 9.620869565217393e-06,
|
| 14 |
+
"loss": 3.6794,
|
| 15 |
+
"step": 115
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_loss": 2.8221545219421387,
|
| 20 |
+
"eval_runtime": 6.0762,
|
| 21 |
+
"eval_samples_per_second": 6.583,
|
| 22 |
+
"eval_steps_per_second": 0.823,
|
| 23 |
+
"step": 115
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 9.224347826086957e-06,
|
| 28 |
+
"loss": 3.0269,
|
| 29 |
+
"step": 230
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_loss": 2.8120057582855225,
|
| 34 |
+
"eval_runtime": 5.8393,
|
| 35 |
+
"eval_samples_per_second": 6.85,
|
| 36 |
+
"eval_steps_per_second": 0.856,
|
| 37 |
+
"step": 230
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 3.0,
|
| 41 |
+
"learning_rate": 8.824347826086957e-06,
|
| 42 |
+
"loss": 2.8681,
|
| 43 |
+
"step": 345
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 3.0,
|
| 47 |
+
"eval_loss": 2.7979869842529297,
|
| 48 |
+
"eval_runtime": 5.8717,
|
| 49 |
+
"eval_samples_per_second": 6.812,
|
| 50 |
+
"eval_steps_per_second": 0.852,
|
| 51 |
+
"step": 345
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.0,
|
| 55 |
+
"learning_rate": 8.424347826086958e-06,
|
| 56 |
+
"loss": 2.752,
|
| 57 |
+
"step": 460
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"eval_loss": 2.485291004180908,
|
| 62 |
+
"eval_runtime": 5.9082,
|
| 63 |
+
"eval_samples_per_second": 6.77,
|
| 64 |
+
"eval_steps_per_second": 0.846,
|
| 65 |
+
"step": 460
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 5.0,
|
| 69 |
+
"learning_rate": 8.027826086956523e-06,
|
| 70 |
+
"loss": 2.7715,
|
| 71 |
+
"step": 575
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 5.0,
|
| 75 |
+
"eval_loss": 2.413987159729004,
|
| 76 |
+
"eval_runtime": 5.8023,
|
| 77 |
+
"eval_samples_per_second": 6.894,
|
| 78 |
+
"eval_steps_per_second": 0.862,
|
| 79 |
+
"step": 575
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 6.0,
|
| 83 |
+
"learning_rate": 7.627826086956522e-06,
|
| 84 |
+
"loss": 2.6846,
|
| 85 |
+
"step": 690
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 6.0,
|
| 89 |
+
"eval_loss": 2.4714808464050293,
|
| 90 |
+
"eval_runtime": 5.8424,
|
| 91 |
+
"eval_samples_per_second": 6.847,
|
| 92 |
+
"eval_steps_per_second": 0.856,
|
| 93 |
+
"step": 690
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.0,
|
| 97 |
+
"learning_rate": 7.231304347826088e-06,
|
| 98 |
+
"loss": 2.6236,
|
| 99 |
+
"step": 805
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.0,
|
| 103 |
+
"eval_loss": 2.461406946182251,
|
| 104 |
+
"eval_runtime": 5.862,
|
| 105 |
+
"eval_samples_per_second": 6.824,
|
| 106 |
+
"eval_steps_per_second": 0.853,
|
| 107 |
+
"step": 805
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"learning_rate": 6.8313043478260874e-06,
|
| 112 |
+
"loss": 2.5318,
|
| 113 |
+
"step": 920
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 8.0,
|
| 117 |
+
"eval_loss": 2.3440959453582764,
|
| 118 |
+
"eval_runtime": 5.9348,
|
| 119 |
+
"eval_samples_per_second": 6.74,
|
| 120 |
+
"eval_steps_per_second": 0.842,
|
| 121 |
+
"step": 920
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 9.0,
|
| 125 |
+
"learning_rate": 6.431304347826087e-06,
|
| 126 |
+
"loss": 2.5224,
|
| 127 |
+
"step": 1035
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 9.0,
|
| 131 |
+
"eval_loss": 2.283745765686035,
|
| 132 |
+
"eval_runtime": 5.872,
|
| 133 |
+
"eval_samples_per_second": 6.812,
|
| 134 |
+
"eval_steps_per_second": 0.851,
|
| 135 |
+
"step": 1035
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.0,
|
| 139 |
+
"learning_rate": 6.031304347826088e-06,
|
| 140 |
+
"loss": 2.4661,
|
| 141 |
+
"step": 1150
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.0,
|
| 145 |
+
"eval_loss": 2.250960111618042,
|
| 146 |
+
"eval_runtime": 5.9135,
|
| 147 |
+
"eval_samples_per_second": 6.764,
|
| 148 |
+
"eval_steps_per_second": 0.846,
|
| 149 |
+
"step": 1150
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 11.0,
|
| 153 |
+
"learning_rate": 5.631304347826088e-06,
|
| 154 |
+
"loss": 2.4313,
|
| 155 |
+
"step": 1265
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 11.0,
|
| 159 |
+
"eval_loss": 2.333876132965088,
|
| 160 |
+
"eval_runtime": 5.8831,
|
| 161 |
+
"eval_samples_per_second": 6.799,
|
| 162 |
+
"eval_steps_per_second": 0.85,
|
| 163 |
+
"step": 1265
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 12.0,
|
| 167 |
+
"learning_rate": 5.2313043478260875e-06,
|
| 168 |
+
"loss": 2.4125,
|
| 169 |
+
"step": 1380
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 12.0,
|
| 173 |
+
"eval_loss": 2.2956740856170654,
|
| 174 |
+
"eval_runtime": 5.9965,
|
| 175 |
+
"eval_samples_per_second": 6.671,
|
| 176 |
+
"eval_steps_per_second": 0.834,
|
| 177 |
+
"step": 1380
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"learning_rate": 4.831304347826087e-06,
|
| 182 |
+
"loss": 2.4113,
|
| 183 |
+
"step": 1495
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 13.0,
|
| 187 |
+
"eval_loss": 2.235807180404663,
|
| 188 |
+
"eval_runtime": 5.8572,
|
| 189 |
+
"eval_samples_per_second": 6.829,
|
| 190 |
+
"eval_steps_per_second": 0.854,
|
| 191 |
+
"step": 1495
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.0,
|
| 195 |
+
"learning_rate": 4.4313043478260875e-06,
|
| 196 |
+
"loss": 2.3784,
|
| 197 |
+
"step": 1610
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 14.0,
|
| 201 |
+
"eval_loss": 2.263479232788086,
|
| 202 |
+
"eval_runtime": 5.9302,
|
| 203 |
+
"eval_samples_per_second": 6.745,
|
| 204 |
+
"eval_steps_per_second": 0.843,
|
| 205 |
+
"step": 1610
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 15.0,
|
| 209 |
+
"learning_rate": 4.031304347826087e-06,
|
| 210 |
+
"loss": 2.3199,
|
| 211 |
+
"step": 1725
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 15.0,
|
| 215 |
+
"eval_loss": 2.232009172439575,
|
| 216 |
+
"eval_runtime": 5.8956,
|
| 217 |
+
"eval_samples_per_second": 6.785,
|
| 218 |
+
"eval_steps_per_second": 0.848,
|
| 219 |
+
"step": 1725
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.0,
|
| 223 |
+
"learning_rate": 3.631304347826087e-06,
|
| 224 |
+
"loss": 2.3321,
|
| 225 |
+
"step": 1840
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 16.0,
|
| 229 |
+
"eval_loss": 2.2249927520751953,
|
| 230 |
+
"eval_runtime": 5.9501,
|
| 231 |
+
"eval_samples_per_second": 6.723,
|
| 232 |
+
"eval_steps_per_second": 0.84,
|
| 233 |
+
"step": 1840
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 17.0,
|
| 237 |
+
"learning_rate": 3.2313043478260876e-06,
|
| 238 |
+
"loss": 2.3305,
|
| 239 |
+
"step": 1955
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.0,
|
| 243 |
+
"eval_loss": 2.202038288116455,
|
| 244 |
+
"eval_runtime": 5.8864,
|
| 245 |
+
"eval_samples_per_second": 6.795,
|
| 246 |
+
"eval_steps_per_second": 0.849,
|
| 247 |
+
"step": 1955
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 18.0,
|
| 251 |
+
"learning_rate": 2.831304347826087e-06,
|
| 252 |
+
"loss": 2.2932,
|
| 253 |
+
"step": 2070
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 18.0,
|
| 257 |
+
"eval_loss": 2.1825520992279053,
|
| 258 |
+
"eval_runtime": 5.8462,
|
| 259 |
+
"eval_samples_per_second": 6.842,
|
| 260 |
+
"eval_steps_per_second": 0.855,
|
| 261 |
+
"step": 2070
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 19.0,
|
| 265 |
+
"learning_rate": 2.431304347826087e-06,
|
| 266 |
+
"loss": 2.2952,
|
| 267 |
+
"step": 2185
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 19.0,
|
| 271 |
+
"eval_loss": 2.1626458168029785,
|
| 272 |
+
"eval_runtime": 5.963,
|
| 273 |
+
"eval_samples_per_second": 6.708,
|
| 274 |
+
"eval_steps_per_second": 0.839,
|
| 275 |
+
"step": 2185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 20.0,
|
| 279 |
+
"learning_rate": 2.0313043478260872e-06,
|
| 280 |
+
"loss": 2.2663,
|
| 281 |
+
"step": 2300
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 20.0,
|
| 285 |
+
"eval_loss": 2.157285213470459,
|
| 286 |
+
"eval_runtime": 5.9246,
|
| 287 |
+
"eval_samples_per_second": 6.751,
|
| 288 |
+
"eval_steps_per_second": 0.844,
|
| 289 |
+
"step": 2300
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 21.0,
|
| 293 |
+
"learning_rate": 1.631304347826087e-06,
|
| 294 |
+
"loss": 2.2916,
|
| 295 |
+
"step": 2415
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 21.0,
|
| 299 |
+
"eval_loss": 2.1653225421905518,
|
| 300 |
+
"eval_runtime": 5.8815,
|
| 301 |
+
"eval_samples_per_second": 6.801,
|
| 302 |
+
"eval_steps_per_second": 0.85,
|
| 303 |
+
"step": 2415
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 22.0,
|
| 307 |
+
"learning_rate": 1.231304347826087e-06,
|
| 308 |
+
"loss": 2.2703,
|
| 309 |
+
"step": 2530
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 22.0,
|
| 313 |
+
"eval_loss": 2.1443889141082764,
|
| 314 |
+
"eval_runtime": 5.8599,
|
| 315 |
+
"eval_samples_per_second": 6.826,
|
| 316 |
+
"eval_steps_per_second": 0.853,
|
| 317 |
+
"step": 2530
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 23.0,
|
| 321 |
+
"learning_rate": 8.347826086956523e-07,
|
| 322 |
+
"loss": 2.2431,
|
| 323 |
+
"step": 2645
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 23.0,
|
| 327 |
+
"eval_loss": 2.1373696327209473,
|
| 328 |
+
"eval_runtime": 5.8436,
|
| 329 |
+
"eval_samples_per_second": 6.845,
|
| 330 |
+
"eval_steps_per_second": 0.856,
|
| 331 |
+
"step": 2645
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 24.0,
|
| 335 |
+
"learning_rate": 4.347826086956522e-07,
|
| 336 |
+
"loss": 2.2243,
|
| 337 |
+
"step": 2760
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 24.0,
|
| 341 |
+
"eval_loss": 2.1275973320007324,
|
| 342 |
+
"eval_runtime": 5.9461,
|
| 343 |
+
"eval_samples_per_second": 6.727,
|
| 344 |
+
"eval_steps_per_second": 0.841,
|
| 345 |
+
"step": 2760
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 25.0,
|
| 349 |
+
"learning_rate": 3.478260869565218e-08,
|
| 350 |
+
"loss": 2.2413,
|
| 351 |
+
"step": 2875
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 25.0,
|
| 355 |
+
"eval_loss": 2.1030609607696533,
|
| 356 |
+
"eval_runtime": 5.9121,
|
| 357 |
+
"eval_samples_per_second": 6.766,
|
| 358 |
+
"eval_steps_per_second": 0.846,
|
| 359 |
+
"step": 2875
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 25.0,
|
| 363 |
+
"step": 2875,
|
| 364 |
+
"total_flos": 5.49474551424e+18,
|
| 365 |
+
"train_loss": 2.50671312945822,
|
| 366 |
+
"train_runtime": 2370.7956,
|
| 367 |
+
"train_samples_per_second": 4.851,
|
| 368 |
+
"train_steps_per_second": 1.213
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"logging_steps": 500,
|
| 372 |
+
"max_steps": 2875,
|
| 373 |
+
"num_train_epochs": 25,
|
| 374 |
+
"save_steps": 500,
|
| 375 |
+
"total_flos": 5.49474551424e+18,
|
| 376 |
+
"trial_name": null,
|
| 377 |
+
"trial_params": null
|
| 378 |
+
}
|