Evaluation on the test set completed on 2024_10_31.
Browse files- README.md +46 -66
- all_results.json +15 -15
- config.json +90 -106
- logs/events.out.tfevents.1730353344.datavisu3 +2 -2
- logs/events.out.tfevents.1730354208.datavisu4 +3 -0
- logs/events.out.tfevents.1730354489.datavisu4 +3 -0
- model.safetensors +1 -1
- runs/events.out.tfevents.1730352882.datavisu3 +3 -0
- runs/events.out.tfevents.1730354197.datavisu4 +0 -0
- test_results.json +12 -1
- threshold.json +1 -0
- train_results.json +7 -7
- trainer_state.json +336 -596
README.md
CHANGED
|
@@ -16,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- Rmse: 0.
|
| 21 |
-
- Mae: 0.
|
| 22 |
-
- R2: -1.
|
| 23 |
-
- Explained Variance: 0.
|
| 24 |
-
- Learning Rate:
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -53,66 +53,46 @@ The following hyperparameters were used during training:
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss | Rmse | Mae | R2 | Explained Variance | Rate |
|
| 55 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:--------:|:------------------:|:------:|
|
| 56 |
-
| No log | 1.0 | 2 | 0.
|
| 57 |
-
| No log | 2.0 | 4 | 0.
|
| 58 |
-
| No log | 3.0 | 6 | 0.
|
| 59 |
-
| No log | 4.0 | 8 | 0.
|
| 60 |
-
| No log | 5.0 | 10 | 0.
|
| 61 |
-
| No log | 6.0 | 12 | 0.
|
| 62 |
-
| No log | 7.0 | 14 | 0.
|
| 63 |
-
| No log | 8.0 | 16 | 0.
|
| 64 |
-
| No log | 9.0 | 18 | 0.
|
| 65 |
-
| No log | 10.0 | 20 | 0.
|
| 66 |
-
| No log | 11.0 | 22 | 0.
|
| 67 |
-
| No log | 12.0 | 24 | 0.
|
| 68 |
-
| No log | 13.0 | 26 | 0.
|
| 69 |
-
| No log | 14.0 | 28 | 0.
|
| 70 |
-
| No log | 15.0 | 30 | 0.
|
| 71 |
-
| No log | 16.0 | 32 | 0.
|
| 72 |
-
| No log | 17.0 | 34 | 0.
|
| 73 |
-
| No log | 18.0 | 36 | 0.
|
| 74 |
-
| No log | 19.0 | 38 | 0.
|
| 75 |
-
| No log | 20.0 | 40 | 0.
|
| 76 |
-
| No log | 21.0 | 42 | 0.
|
| 77 |
-
| No log | 22.0 | 44 | 0.
|
| 78 |
-
| No log | 23.0 | 46 | 0.
|
| 79 |
-
| No log | 24.0 | 48 | 0.
|
| 80 |
-
| No log | 25.0 | 50 | 0.
|
| 81 |
-
| No log | 26.0 | 52 | 0.
|
| 82 |
-
| No log | 27.0 | 54 | 0.
|
| 83 |
-
| No log | 28.0 | 56 | 0.
|
| 84 |
-
| No log | 29.0 | 58 | 0.
|
| 85 |
-
| No log | 30.0 | 60 | 0.
|
| 86 |
-
| No log | 31.0 | 62 | 0.
|
| 87 |
-
| No log | 32.0 | 64 | 0.
|
| 88 |
-
| No log | 33.0 | 66 | 0.
|
| 89 |
-
| No log | 34.0 | 68 | 0.
|
| 90 |
-
| No log | 35.0 | 70 | 0.
|
| 91 |
-
| No log | 36.0 | 72 | 0.
|
| 92 |
-
| No log | 37.0 | 74 | 0.
|
| 93 |
-
| No log | 38.0 | 76 | 0.
|
| 94 |
-
| No log | 39.0 | 78 | 0.
|
| 95 |
-
| No log | 40.0 | 80 | 0.
|
| 96 |
-
| No log | 41.0 | 82 | 0.6196 | 0.3456 | 0.3095 | -11.4656 | 0.1154 | 0.0001 |
|
| 97 |
-
| No log | 42.0 | 84 | 0.6185 | 0.3453 | 0.3096 | -11.4190 | 0.1220 | 1e-05 |
|
| 98 |
-
| No log | 43.0 | 86 | 0.6196 | 0.3457 | 0.3099 | -11.4211 | 0.1224 | 1e-05 |
|
| 99 |
-
| No log | 44.0 | 88 | 0.6175 | 0.3448 | 0.3091 | -11.3422 | 0.1252 | 1e-05 |
|
| 100 |
-
| No log | 45.0 | 90 | 0.6148 | 0.3435 | 0.3079 | -11.2377 | 0.1267 | 1e-05 |
|
| 101 |
-
| No log | 46.0 | 92 | 0.6156 | 0.3439 | 0.3081 | -11.2161 | 0.1232 | 1e-05 |
|
| 102 |
-
| No log | 47.0 | 94 | 0.6162 | 0.3442 | 0.3084 | -11.2359 | 0.1219 | 1e-05 |
|
| 103 |
-
| No log | 48.0 | 96 | 0.6153 | 0.3438 | 0.3079 | -11.1407 | 0.1218 | 1e-05 |
|
| 104 |
-
| No log | 49.0 | 98 | 0.6142 | 0.3434 | 0.3075 | -11.0878 | 0.1259 | 1e-05 |
|
| 105 |
-
| No log | 50.0 | 100 | 0.6125 | 0.3427 | 0.3071 | -11.1648 | 0.1241 | 1e-05 |
|
| 106 |
-
| No log | 51.0 | 102 | 0.6131 | 0.3430 | 0.3072 | -11.2371 | 0.1274 | 1e-05 |
|
| 107 |
-
| No log | 52.0 | 104 | 0.6137 | 0.3434 | 0.3077 | -11.3909 | 0.1274 | 1e-05 |
|
| 108 |
-
| No log | 53.0 | 106 | 0.6139 | 0.3434 | 0.3077 | -11.5018 | 0.1224 | 1e-05 |
|
| 109 |
-
| No log | 54.0 | 108 | 0.6157 | 0.3445 | 0.3089 | -11.6674 | 0.1222 | 1e-05 |
|
| 110 |
-
| No log | 55.0 | 110 | 0.6168 | 0.3448 | 0.3090 | -11.6467 | 0.1222 | 1e-05 |
|
| 111 |
-
| No log | 56.0 | 112 | 0.6140 | 0.3434 | 0.3077 | -11.4968 | 0.1250 | 1e-05 |
|
| 112 |
-
| No log | 57.0 | 114 | 0.6133 | 0.3430 | 0.3071 | -11.5002 | 0.1216 | 0.0000 |
|
| 113 |
-
| No log | 58.0 | 116 | 0.6130 | 0.3428 | 0.3070 | -11.4475 | 0.1210 | 0.0000 |
|
| 114 |
-
| No log | 59.0 | 118 | 0.6150 | 0.3441 | 0.3083 | -11.5562 | 0.1178 | 0.0000 |
|
| 115 |
-
| No log | 60.0 | 120 | 0.6167 | 0.3450 | 0.3092 | -11.4676 | 0.1243 | 0.0000 |
|
| 116 |
|
| 117 |
|
| 118 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6195
|
| 20 |
+
- Rmse: 0.3419
|
| 21 |
+
- Mae: 0.3068
|
| 22 |
+
- R2: -1.6131
|
| 23 |
+
- Explained Variance: 0.2071
|
| 24 |
+
- Learning Rate: 1e-05
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss | Rmse | Mae | R2 | Explained Variance | Rate |
|
| 55 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:--------:|:------------------:|:------:|
|
| 56 |
+
| No log | 1.0 | 2 | 0.7150 | 0.4100 | 0.3849 | -20.2909 | 0.0364 | 0.001 |
|
| 57 |
+
| No log | 2.0 | 4 | 0.7314 | 0.4163 | 0.3895 | -21.2182 | 0.0241 | 0.001 |
|
| 58 |
+
| No log | 3.0 | 6 | 0.7726 | 0.4321 | 0.4041 | -24.8224 | -0.0469 | 0.001 |
|
| 59 |
+
| No log | 4.0 | 8 | 0.7917 | 0.4380 | 0.4095 | -26.5816 | -0.0667 | 0.001 |
|
| 60 |
+
| No log | 5.0 | 10 | 0.7853 | 0.4318 | 0.4021 | -26.9559 | -0.1362 | 0.001 |
|
| 61 |
+
| No log | 6.0 | 12 | 0.7648 | 0.4224 | 0.3905 | -24.4015 | -0.1297 | 0.001 |
|
| 62 |
+
| No log | 7.0 | 14 | 0.7392 | 0.4103 | 0.3760 | -22.5579 | -0.1098 | 0.001 |
|
| 63 |
+
| No log | 8.0 | 16 | 0.7115 | 0.3983 | 0.3639 | -20.0674 | -0.1054 | 0.0001 |
|
| 64 |
+
| No log | 9.0 | 18 | 0.6897 | 0.3879 | 0.3535 | -18.1665 | -0.0925 | 0.0001 |
|
| 65 |
+
| No log | 10.0 | 20 | 0.6777 | 0.3818 | 0.3468 | -16.9447 | -0.1029 | 0.0001 |
|
| 66 |
+
| No log | 11.0 | 22 | 0.6702 | 0.3780 | 0.3424 | -16.0375 | -0.1169 | 0.0001 |
|
| 67 |
+
| No log | 12.0 | 24 | 0.6639 | 0.3744 | 0.3389 | -15.6052 | -0.1121 | 0.0001 |
|
| 68 |
+
| No log | 13.0 | 26 | 0.6565 | 0.3703 | 0.3346 | -14.8051 | -0.1065 | 0.0001 |
|
| 69 |
+
| No log | 14.0 | 28 | 0.6501 | 0.3668 | 0.3310 | -14.2312 | -0.0958 | 0.0001 |
|
| 70 |
+
| No log | 15.0 | 30 | 0.6468 | 0.3648 | 0.3289 | -14.0799 | -0.0855 | 0.0001 |
|
| 71 |
+
| No log | 16.0 | 32 | 0.6471 | 0.3650 | 0.3289 | -14.2557 | -0.0823 | 0.0001 |
|
| 72 |
+
| No log | 17.0 | 34 | 0.6435 | 0.3631 | 0.3268 | -14.0598 | -0.0810 | 0.0001 |
|
| 73 |
+
| No log | 18.0 | 36 | 0.6438 | 0.3634 | 0.3270 | -14.0369 | -0.0799 | 0.0001 |
|
| 74 |
+
| No log | 19.0 | 38 | 0.6400 | 0.3614 | 0.3250 | -13.8152 | -0.0888 | 0.0001 |
|
| 75 |
+
| No log | 20.0 | 40 | 0.6392 | 0.3609 | 0.3246 | -13.7104 | -0.0935 | 0.0001 |
|
| 76 |
+
| No log | 21.0 | 42 | 0.6387 | 0.3606 | 0.3246 | -13.8099 | -0.0993 | 0.0001 |
|
| 77 |
+
| No log | 22.0 | 44 | 0.6388 | 0.3606 | 0.3243 | -13.8497 | -0.1056 | 0.0001 |
|
| 78 |
+
| No log | 23.0 | 46 | 0.6362 | 0.3590 | 0.3228 | -13.5622 | -0.1035 | 0.0001 |
|
| 79 |
+
| No log | 24.0 | 48 | 0.6354 | 0.3585 | 0.3223 | -13.6453 | -0.1058 | 0.0001 |
|
| 80 |
+
| No log | 25.0 | 50 | 0.6345 | 0.3578 | 0.3214 | -13.6023 | -0.1036 | 0.0001 |
|
| 81 |
+
| No log | 26.0 | 52 | 0.6349 | 0.3581 | 0.3212 | -13.6304 | -0.1173 | 0.0001 |
|
| 82 |
+
| No log | 27.0 | 54 | 0.6333 | 0.3571 | 0.3201 | -13.5613 | -0.1148 | 0.0001 |
|
| 83 |
+
| No log | 28.0 | 56 | 0.6295 | 0.3548 | 0.3177 | -13.2331 | -0.1083 | 0.0001 |
|
| 84 |
+
| No log | 29.0 | 58 | 0.6285 | 0.3543 | 0.3173 | -13.1623 | -0.1047 | 0.0001 |
|
| 85 |
+
| No log | 30.0 | 60 | 0.6263 | 0.3532 | 0.3163 | -12.7132 | -0.0926 | 0.0001 |
|
| 86 |
+
| No log | 31.0 | 62 | 0.6273 | 0.3538 | 0.3167 | -12.8739 | -0.0893 | 0.0001 |
|
| 87 |
+
| No log | 32.0 | 64 | 0.6294 | 0.3550 | 0.3181 | -12.9355 | -0.0790 | 0.0001 |
|
| 88 |
+
| No log | 33.0 | 66 | 0.6299 | 0.3554 | 0.3185 | -12.9352 | -0.0752 | 0.0001 |
|
| 89 |
+
| No log | 34.0 | 68 | 0.6321 | 0.3564 | 0.3193 | -13.2672 | -0.0702 | 0.0001 |
|
| 90 |
+
| No log | 35.0 | 70 | 0.6279 | 0.3541 | 0.3175 | -12.9995 | -0.0487 | 0.0001 |
|
| 91 |
+
| No log | 36.0 | 72 | 0.6280 | 0.3541 | 0.3174 | -13.0074 | -0.0466 | 0.0001 |
|
| 92 |
+
| No log | 37.0 | 74 | 0.6304 | 0.3554 | 0.3187 | -13.2310 | -0.0494 | 1e-05 |
|
| 93 |
+
| No log | 38.0 | 76 | 0.6297 | 0.3551 | 0.3183 | -12.9830 | -0.0439 | 1e-05 |
|
| 94 |
+
| No log | 39.0 | 78 | 0.6308 | 0.3558 | 0.3193 | -13.1598 | -0.0430 | 1e-05 |
|
| 95 |
+
| No log | 40.0 | 80 | 0.6292 | 0.3548 | 0.3183 | -13.0698 | -0.0435 | 1e-05 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
|
| 97 |
|
| 98 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,17 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_explained_variance": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_mae": 0.
|
| 6 |
-
"eval_r2": -1.
|
| 7 |
-
"eval_rmse": 0.
|
| 8 |
-
"eval_runtime": 1.
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second": 1.
|
| 11 |
-
"learning_rate":
|
| 12 |
-
"total_flos":
|
| 13 |
-
"train_loss": 0.
|
| 14 |
-
"train_runtime":
|
| 15 |
-
"train_samples_per_second":
|
| 16 |
-
"train_steps_per_second":
|
| 17 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_explained_variance": 0.20714369416236877,
|
| 4 |
+
"eval_loss": 0.6195399761199951,
|
| 5 |
+
"eval_mae": 0.3067561388015747,
|
| 6 |
+
"eval_r2": -1.6130945682525635,
|
| 7 |
+
"eval_rmse": 0.34193673729896545,
|
| 8 |
+
"eval_runtime": 1.099,
|
| 9 |
+
"eval_samples_per_second": 45.496,
|
| 10 |
+
"eval_steps_per_second": 1.82,
|
| 11 |
+
"learning_rate": 1e-05,
|
| 12 |
+
"total_flos": 2.9601852123168e+17,
|
| 13 |
+
"train_loss": 0.64580397605896,
|
| 14 |
+
"train_runtime": 275.9938,
|
| 15 |
+
"train_samples_per_second": 27.175,
|
| 16 |
+
"train_steps_per_second": 1.087
|
| 17 |
}
|
config.json
CHANGED
|
@@ -1,107 +1,91 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
"train_batch_size": 32,
|
| 93 |
-
"eval_batch_size": 32,
|
| 94 |
-
"optimizer": {
|
| 95 |
-
"type": "Adam"
|
| 96 |
-
},
|
| 97 |
-
"lr_scheduler_type": {
|
| 98 |
-
"type": "ReduceLROnPlateau"
|
| 99 |
-
},
|
| 100 |
-
"patience_lr_scheduler": 5,
|
| 101 |
-
"factor_lr_scheduler": 0.1,
|
| 102 |
-
"weight_decay": 0.0001,
|
| 103 |
-
"early_stopping_patience": 10,
|
| 104 |
-
"freeze_encoder": true,
|
| 105 |
-
"data_augmentation": true,
|
| 106 |
-
"num_epochs": 150
|
| 107 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/dinov2-large",
|
| 3 |
+
"apply_layernorm": true,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Dinov2ForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"drop_path_rate": 0.0,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Acropore_branched",
|
| 14 |
+
"1": "Acropore_digitised",
|
| 15 |
+
"2": "Acropore_tabular",
|
| 16 |
+
"3": "Algae",
|
| 17 |
+
"4": "Dead_coral",
|
| 18 |
+
"5": "Fish",
|
| 19 |
+
"6": "Millepore",
|
| 20 |
+
"7": "No_acropore_encrusting",
|
| 21 |
+
"8": "No_acropore_massive",
|
| 22 |
+
"9": "No_acropore_sub_massive",
|
| 23 |
+
"10": "Rock",
|
| 24 |
+
"11": "Rubble",
|
| 25 |
+
"12": "Sand"
|
| 26 |
+
},
|
| 27 |
+
"image_size": 164,
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"label2id": {
|
| 30 |
+
"Acropore_branched": 0,
|
| 31 |
+
"Acropore_digitised": 1,
|
| 32 |
+
"Acropore_tabular": 2,
|
| 33 |
+
"Algae": 3,
|
| 34 |
+
"Dead_coral": 4,
|
| 35 |
+
"Fish": 5,
|
| 36 |
+
"Millepore": 6,
|
| 37 |
+
"No_acropore_encrusting": 7,
|
| 38 |
+
"No_acropore_massive": 8,
|
| 39 |
+
"No_acropore_sub_massive": 9,
|
| 40 |
+
"Rock": 10,
|
| 41 |
+
"Rubble": 11,
|
| 42 |
+
"Sand": 12
|
| 43 |
+
},
|
| 44 |
+
"layer_norm_eps": 1e-06,
|
| 45 |
+
"layerscale_value": 1.0,
|
| 46 |
+
"mlp_ratio": 4,
|
| 47 |
+
"model_type": "dinov2",
|
| 48 |
+
"num_attention_heads": 16,
|
| 49 |
+
"num_channels": 3,
|
| 50 |
+
"num_hidden_layers": 24,
|
| 51 |
+
"out_features": [
|
| 52 |
+
"stage24"
|
| 53 |
+
],
|
| 54 |
+
"out_indices": [
|
| 55 |
+
24
|
| 56 |
+
],
|
| 57 |
+
"patch_size": 14,
|
| 58 |
+
"problem_type": "multi_label_classification",
|
| 59 |
+
"qkv_bias": true,
|
| 60 |
+
"reshape_hidden_states": true,
|
| 61 |
+
"stage_names": [
|
| 62 |
+
"stem",
|
| 63 |
+
"stage1",
|
| 64 |
+
"stage2",
|
| 65 |
+
"stage3",
|
| 66 |
+
"stage4",
|
| 67 |
+
"stage5",
|
| 68 |
+
"stage6",
|
| 69 |
+
"stage7",
|
| 70 |
+
"stage8",
|
| 71 |
+
"stage9",
|
| 72 |
+
"stage10",
|
| 73 |
+
"stage11",
|
| 74 |
+
"stage12",
|
| 75 |
+
"stage13",
|
| 76 |
+
"stage14",
|
| 77 |
+
"stage15",
|
| 78 |
+
"stage16",
|
| 79 |
+
"stage17",
|
| 80 |
+
"stage18",
|
| 81 |
+
"stage19",
|
| 82 |
+
"stage20",
|
| 83 |
+
"stage21",
|
| 84 |
+
"stage22",
|
| 85 |
+
"stage23",
|
| 86 |
+
"stage24"
|
| 87 |
+
],
|
| 88 |
+
"torch_dtype": "float32",
|
| 89 |
+
"transformers_version": "4.44.2",
|
| 90 |
+
"use_swiglu_ffn": false
|
| 91 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/events.out.tfevents.1730353344.datavisu3
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da2ac5ad39216a587fed6417c22c3f0c9fbe120eb5f2fda537c771f1c00547eb
|
| 3 |
+
size 562
|
logs/events.out.tfevents.1730354208.datavisu4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f09a86ceb3ba5902bb455494bc444ad34068b80a03b84a1af738deee197d3aa9
|
| 3 |
+
size 27578
|
logs/events.out.tfevents.1730354489.datavisu4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d595ee38637c40e64c90e923415ce5643091f9cce108836d577f42de7b55d900
|
| 3 |
+
size 40
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1222958756
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bb8018d733bef1a8345ef794b9f74c454fe90a64f664c4f475de6f2ce48c64d
|
| 3 |
size 1222958756
|
runs/events.out.tfevents.1730352882.datavisu3
CHANGED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f4f2c5da543c6ae5472319e39eb74aed35ce6a0508f4bfe799213764e16657e
|
| 3 |
+
size 40
|
runs/events.out.tfevents.1730354197.datavisu4
ADDED
|
File without changes
|
test_results.json
CHANGED
|
@@ -1 +1,12 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_explained_variance": 0.20714369416236877,
|
| 4 |
+
"eval_loss": 0.6195399761199951,
|
| 5 |
+
"eval_mae": 0.3067561388015747,
|
| 6 |
+
"eval_r2": -1.6130945682525635,
|
| 7 |
+
"eval_rmse": 0.34193673729896545,
|
| 8 |
+
"eval_runtime": 1.099,
|
| 9 |
+
"eval_samples_per_second": 45.496,
|
| 10 |
+
"eval_steps_per_second": 1.82,
|
| 11 |
+
"learning_rate": 1e-05
|
| 12 |
+
}
|
threshold.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"Acropore_branched": 0.085, "Acropore_digitised": 0.431, "Acropore_tabular": 0.0, "Algae": 0.0, "Dead_coral": 0.17, "Fish": 0.009, "Millepore": 0.0, "No_acropore_encrusting": 0.0, "No_acropore_massive": 0.0, "No_acropore_sub_massive": 0.077, "Rock": 0.0, "Rubble": 0.0, "Sand": 0.0}
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"learning_rate":
|
| 4 |
-
"total_flos":
|
| 5 |
-
"train_loss": 0.
|
| 6 |
-
"train_runtime":
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"learning_rate": 1e-05,
|
| 4 |
+
"total_flos": 2.9601852123168e+17,
|
| 5 |
+
"train_loss": 0.64580397605896,
|
| 6 |
+
"train_runtime": 275.9938,
|
| 7 |
+
"train_samples_per_second": 27.175,
|
| 8 |
+
"train_steps_per_second": 1.087
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,802 +1,542 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "/home1/datahome/villien/project_hub/DinoVdeau/models/Ziboiai-large-2024_10_31-prova_batch-size32_freeze_probs/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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 |
-
"eval_explained_variance": 0.
|
| 14 |
-
"eval_loss": 0.
|
| 15 |
-
"eval_mae": 0.
|
| 16 |
-
"eval_r2": -
|
| 17 |
-
"eval_rmse": 0.
|
| 18 |
-
"eval_runtime": 1.
|
| 19 |
-
"eval_samples_per_second":
|
| 20 |
-
"eval_steps_per_second": 1.
|
| 21 |
"learning_rate": 0.001,
|
| 22 |
"step": 2
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"epoch": 2.0,
|
| 26 |
-
"eval_explained_variance": 0.
|
| 27 |
-
"eval_loss": 0.
|
| 28 |
-
"eval_mae": 0.
|
| 29 |
-
"eval_r2": -
|
| 30 |
-
"eval_rmse": 0.
|
| 31 |
-
"eval_runtime": 0.
|
| 32 |
-
"eval_samples_per_second":
|
| 33 |
-
"eval_steps_per_second": 6.
|
| 34 |
"learning_rate": 0.001,
|
| 35 |
"step": 4
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 3.0,
|
| 39 |
-
"eval_explained_variance": 0.
|
| 40 |
-
"eval_loss": 0.
|
| 41 |
-
"eval_mae": 0.
|
| 42 |
-
"eval_r2": -
|
| 43 |
-
"eval_rmse": 0.
|
| 44 |
-
"eval_runtime": 0.
|
| 45 |
-
"eval_samples_per_second":
|
| 46 |
-
"eval_steps_per_second": 6.
|
| 47 |
"learning_rate": 0.001,
|
| 48 |
"step": 6
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
-
"eval_explained_variance": 0.
|
| 53 |
-
"eval_loss": 0.
|
| 54 |
-
"eval_mae": 0.
|
| 55 |
-
"eval_r2": -
|
| 56 |
-
"eval_rmse": 0.
|
| 57 |
-
"eval_runtime": 0.
|
| 58 |
-
"eval_samples_per_second":
|
| 59 |
-
"eval_steps_per_second": 6.
|
| 60 |
"learning_rate": 0.001,
|
| 61 |
"step": 8
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 5.0,
|
| 65 |
-
"eval_explained_variance": 0.
|
| 66 |
-
"eval_loss": 0.
|
| 67 |
-
"eval_mae": 0.
|
| 68 |
-
"eval_r2": -26.
|
| 69 |
-
"eval_rmse": 0.
|
| 70 |
-
"eval_runtime": 0.
|
| 71 |
-
"eval_samples_per_second":
|
| 72 |
-
"eval_steps_per_second": 6.
|
| 73 |
"learning_rate": 0.001,
|
| 74 |
"step": 10
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 6.0,
|
| 78 |
-
"eval_explained_variance": -0.
|
| 79 |
-
"eval_loss": 0.
|
| 80 |
-
"eval_mae": 0.
|
| 81 |
-
"eval_r2": -24.
|
| 82 |
-
"eval_rmse": 0.
|
| 83 |
-
"eval_runtime": 0.
|
| 84 |
-
"eval_samples_per_second":
|
| 85 |
-
"eval_steps_per_second": 6.
|
| 86 |
"learning_rate": 0.001,
|
| 87 |
"step": 12
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 7.0,
|
| 91 |
-
"eval_explained_variance": -0.
|
| 92 |
-
"eval_loss": 0.
|
| 93 |
-
"eval_mae": 0.
|
| 94 |
-
"eval_r2": -22.
|
| 95 |
-
"eval_rmse": 0.
|
| 96 |
-
"eval_runtime": 0.
|
| 97 |
-
"eval_samples_per_second":
|
| 98 |
-
"eval_steps_per_second": 6.
|
| 99 |
"learning_rate": 0.001,
|
| 100 |
"step": 14
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 8.0,
|
| 104 |
-
"eval_explained_variance": -0.
|
| 105 |
-
"eval_loss": 0.
|
| 106 |
-
"eval_mae": 0.
|
| 107 |
-
"eval_r2": -20.
|
| 108 |
-
"eval_rmse": 0.
|
| 109 |
-
"eval_runtime": 0.
|
| 110 |
-
"eval_samples_per_second":
|
| 111 |
-
"eval_steps_per_second": 6.
|
| 112 |
"learning_rate": 0.0001,
|
| 113 |
"step": 16
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 9.0,
|
| 117 |
-
"eval_explained_variance": -0.
|
| 118 |
-
"eval_loss": 0.
|
| 119 |
-
"eval_mae": 0.
|
| 120 |
-
"eval_r2": -18.
|
| 121 |
-
"eval_rmse": 0.
|
| 122 |
-
"eval_runtime": 0.
|
| 123 |
-
"eval_samples_per_second":
|
| 124 |
-
"eval_steps_per_second": 6.
|
| 125 |
"learning_rate": 0.0001,
|
| 126 |
"step": 18
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 10.0,
|
| 130 |
-
"eval_explained_variance": -0.
|
| 131 |
-
"eval_loss": 0.
|
| 132 |
-
"eval_mae": 0.
|
| 133 |
-
"eval_r2": -
|
| 134 |
-
"eval_rmse": 0.
|
| 135 |
-
"eval_runtime": 0.
|
| 136 |
-
"eval_samples_per_second":
|
| 137 |
-
"eval_steps_per_second": 6.
|
| 138 |
"learning_rate": 0.0001,
|
| 139 |
"step": 20
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 11.0,
|
| 143 |
-
"eval_explained_variance": -0.
|
| 144 |
-
"eval_loss": 0.
|
| 145 |
-
"eval_mae": 0.
|
| 146 |
-
"eval_r2": -16.
|
| 147 |
-
"eval_rmse": 0.
|
| 148 |
-
"eval_runtime": 0.
|
| 149 |
-
"eval_samples_per_second":
|
| 150 |
-
"eval_steps_per_second": 6.
|
| 151 |
"learning_rate": 0.0001,
|
| 152 |
"step": 22
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 12.0,
|
| 156 |
-
"eval_explained_variance": -0.
|
| 157 |
-
"eval_loss": 0.
|
| 158 |
-
"eval_mae": 0.
|
| 159 |
-
"eval_r2": -
|
| 160 |
-
"eval_rmse": 0.
|
| 161 |
-
"eval_runtime": 0.
|
| 162 |
-
"eval_samples_per_second": 151.
|
| 163 |
-
"eval_steps_per_second": 6.
|
| 164 |
"learning_rate": 0.0001,
|
| 165 |
"step": 24
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 13.0,
|
| 169 |
-
"eval_explained_variance": -0.
|
| 170 |
-
"eval_loss": 0.
|
| 171 |
-
"eval_mae": 0.
|
| 172 |
-
"eval_r2": -
|
| 173 |
-
"eval_rmse": 0.
|
| 174 |
-
"eval_runtime": 0.
|
| 175 |
-
"eval_samples_per_second":
|
| 176 |
-
"eval_steps_per_second": 6.
|
| 177 |
"learning_rate": 0.0001,
|
| 178 |
"step": 26
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 14.0,
|
| 182 |
-
"eval_explained_variance": -0.
|
| 183 |
-
"eval_loss": 0.
|
| 184 |
-
"eval_mae": 0.
|
| 185 |
-
"eval_r2": -14.
|
| 186 |
-
"eval_rmse": 0.
|
| 187 |
-
"eval_runtime": 0.
|
| 188 |
-
"eval_samples_per_second":
|
| 189 |
-
"eval_steps_per_second": 6.
|
| 190 |
"learning_rate": 0.0001,
|
| 191 |
"step": 28
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 15.0,
|
| 195 |
-
"eval_explained_variance": -0.
|
| 196 |
-
"eval_loss": 0.
|
| 197 |
-
"eval_mae": 0.
|
| 198 |
-
"eval_r2": -14.
|
| 199 |
-
"eval_rmse": 0.
|
| 200 |
-
"eval_runtime": 0.
|
| 201 |
-
"eval_samples_per_second":
|
| 202 |
-
"eval_steps_per_second": 6.
|
| 203 |
"learning_rate": 0.0001,
|
| 204 |
"step": 30
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 16.0,
|
| 208 |
-
"eval_explained_variance": 0.
|
| 209 |
-
"eval_loss": 0.
|
| 210 |
-
"eval_mae": 0.
|
| 211 |
-
"eval_r2": -14.
|
| 212 |
-
"eval_rmse": 0.
|
| 213 |
-
"eval_runtime": 0.
|
| 214 |
-
"eval_samples_per_second":
|
| 215 |
-
"eval_steps_per_second": 6.
|
| 216 |
"learning_rate": 0.0001,
|
| 217 |
"step": 32
|
| 218 |
},
|
| 219 |
{
|
| 220 |
"epoch": 17.0,
|
| 221 |
-
"eval_explained_variance": 0.
|
| 222 |
-
"eval_loss": 0.
|
| 223 |
-
"eval_mae": 0.
|
| 224 |
-
"eval_r2": -14.
|
| 225 |
-
"eval_rmse": 0.
|
| 226 |
-
"eval_runtime": 0.
|
| 227 |
-
"eval_samples_per_second":
|
| 228 |
-
"eval_steps_per_second": 6.
|
| 229 |
"learning_rate": 0.0001,
|
| 230 |
"step": 34
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 18.0,
|
| 234 |
-
"eval_explained_variance": 0.
|
| 235 |
-
"eval_loss": 0.
|
| 236 |
-
"eval_mae": 0.
|
| 237 |
-
"eval_r2": -
|
| 238 |
-
"eval_rmse": 0.
|
| 239 |
-
"eval_runtime": 0.
|
| 240 |
-
"eval_samples_per_second":
|
| 241 |
-
"eval_steps_per_second": 6.
|
| 242 |
"learning_rate": 0.0001,
|
| 243 |
"step": 36
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 19.0,
|
| 247 |
-
"eval_explained_variance": 0.
|
| 248 |
-
"eval_loss": 0.
|
| 249 |
-
"eval_mae": 0.
|
| 250 |
-
"eval_r2": -13.
|
| 251 |
-
"eval_rmse": 0.
|
| 252 |
-
"eval_runtime": 0.
|
| 253 |
-
"eval_samples_per_second":
|
| 254 |
-
"eval_steps_per_second": 6.
|
| 255 |
"learning_rate": 0.0001,
|
| 256 |
"step": 38
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 20.0,
|
| 260 |
-
"eval_explained_variance": 0.
|
| 261 |
-
"eval_loss": 0.
|
| 262 |
-
"eval_mae": 0.
|
| 263 |
-
"eval_r2": -13.
|
| 264 |
-
"eval_rmse": 0.
|
| 265 |
-
"eval_runtime": 0.
|
| 266 |
-
"eval_samples_per_second":
|
| 267 |
-
"eval_steps_per_second": 6.
|
| 268 |
"learning_rate": 0.0001,
|
| 269 |
"step": 40
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 21.0,
|
| 273 |
-
"eval_explained_variance": 0.
|
| 274 |
-
"eval_loss": 0.
|
| 275 |
-
"eval_mae": 0.
|
| 276 |
-
"eval_r2": -13.
|
| 277 |
-
"eval_rmse": 0.
|
| 278 |
-
"eval_runtime": 0.
|
| 279 |
-
"eval_samples_per_second":
|
| 280 |
-
"eval_steps_per_second": 6.
|
| 281 |
"learning_rate": 0.0001,
|
| 282 |
"step": 42
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 22.0,
|
| 286 |
-
"eval_explained_variance": 0.
|
| 287 |
-
"eval_loss": 0.
|
| 288 |
-
"eval_mae": 0.
|
| 289 |
-
"eval_r2": -13.
|
| 290 |
-
"eval_rmse": 0.
|
| 291 |
-
"eval_runtime": 0.
|
| 292 |
-
"eval_samples_per_second":
|
| 293 |
-
"eval_steps_per_second": 6.
|
| 294 |
"learning_rate": 0.0001,
|
| 295 |
"step": 44
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 23.0,
|
| 299 |
-
"eval_explained_variance": 0.
|
| 300 |
-
"eval_loss": 0.
|
| 301 |
-
"eval_mae": 0.
|
| 302 |
-
"eval_r2": -13.
|
| 303 |
-
"eval_rmse": 0.
|
| 304 |
-
"eval_runtime": 0.
|
| 305 |
-
"eval_samples_per_second":
|
| 306 |
-
"eval_steps_per_second": 6.
|
| 307 |
"learning_rate": 0.0001,
|
| 308 |
"step": 46
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 24.0,
|
| 312 |
-
"eval_explained_variance": 0.
|
| 313 |
-
"eval_loss": 0.
|
| 314 |
-
"eval_mae": 0.
|
| 315 |
-
"eval_r2": -13.
|
| 316 |
-
"eval_rmse": 0.
|
| 317 |
-
"eval_runtime": 0.
|
| 318 |
-
"eval_samples_per_second":
|
| 319 |
-
"eval_steps_per_second": 6.
|
| 320 |
"learning_rate": 0.0001,
|
| 321 |
"step": 48
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 25.0,
|
| 325 |
-
"eval_explained_variance": 0.
|
| 326 |
-
"eval_loss": 0.
|
| 327 |
-
"eval_mae": 0.
|
| 328 |
-
"eval_r2": -
|
| 329 |
-
"eval_rmse": 0.
|
| 330 |
-
"eval_runtime": 0.
|
| 331 |
-
"eval_samples_per_second":
|
| 332 |
-
"eval_steps_per_second": 6.
|
| 333 |
"learning_rate": 0.0001,
|
| 334 |
"step": 50
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 26.0,
|
| 338 |
-
"eval_explained_variance": 0.
|
| 339 |
-
"eval_loss": 0.
|
| 340 |
-
"eval_mae": 0.
|
| 341 |
-
"eval_r2": -
|
| 342 |
-
"eval_rmse": 0.
|
| 343 |
-
"eval_runtime": 0.
|
| 344 |
-
"eval_samples_per_second":
|
| 345 |
-
"eval_steps_per_second": 6.
|
| 346 |
"learning_rate": 0.0001,
|
| 347 |
"step": 52
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 27.0,
|
| 351 |
-
"eval_explained_variance": 0.
|
| 352 |
-
"eval_loss": 0.
|
| 353 |
-
"eval_mae": 0.
|
| 354 |
-
"eval_r2": -
|
| 355 |
-
"eval_rmse": 0.
|
| 356 |
-
"eval_runtime": 0.
|
| 357 |
-
"eval_samples_per_second":
|
| 358 |
-
"eval_steps_per_second": 6.
|
| 359 |
"learning_rate": 0.0001,
|
| 360 |
"step": 54
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 28.0,
|
| 364 |
-
"eval_explained_variance": 0.
|
| 365 |
-
"eval_loss": 0.
|
| 366 |
-
"eval_mae": 0.
|
| 367 |
-
"eval_r2": -
|
| 368 |
-
"eval_rmse": 0.
|
| 369 |
-
"eval_runtime": 0.
|
| 370 |
-
"eval_samples_per_second":
|
| 371 |
-
"eval_steps_per_second": 6.
|
| 372 |
"learning_rate": 0.0001,
|
| 373 |
"step": 56
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"epoch": 29.0,
|
| 377 |
-
"eval_explained_variance": 0.
|
| 378 |
-
"eval_loss": 0.
|
| 379 |
-
"eval_mae": 0.
|
| 380 |
-
"eval_r2": -
|
| 381 |
-
"eval_rmse": 0.
|
| 382 |
-
"eval_runtime": 0.
|
| 383 |
-
"eval_samples_per_second":
|
| 384 |
-
"eval_steps_per_second": 6.
|
| 385 |
"learning_rate": 0.0001,
|
| 386 |
"step": 58
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 30.0,
|
| 390 |
-
"eval_explained_variance": 0.
|
| 391 |
-
"eval_loss": 0.
|
| 392 |
-
"eval_mae": 0.
|
| 393 |
-
"eval_r2": -12.
|
| 394 |
-
"eval_rmse": 0.
|
| 395 |
-
"eval_runtime": 0.
|
| 396 |
-
"eval_samples_per_second":
|
| 397 |
-
"eval_steps_per_second":
|
| 398 |
"learning_rate": 0.0001,
|
| 399 |
"step": 60
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 31.0,
|
| 403 |
-
"eval_explained_variance": 0.
|
| 404 |
-
"eval_loss": 0.
|
| 405 |
-
"eval_mae": 0.
|
| 406 |
-
"eval_r2": -12.
|
| 407 |
-
"eval_rmse": 0.
|
| 408 |
-
"eval_runtime": 0.
|
| 409 |
-
"eval_samples_per_second":
|
| 410 |
-
"eval_steps_per_second": 6.
|
| 411 |
"learning_rate": 0.0001,
|
| 412 |
"step": 62
|
| 413 |
},
|
| 414 |
{
|
| 415 |
"epoch": 32.0,
|
| 416 |
-
"eval_explained_variance": 0.
|
| 417 |
-
"eval_loss": 0.
|
| 418 |
-
"eval_mae": 0.
|
| 419 |
-
"eval_r2": -
|
| 420 |
-
"eval_rmse": 0.
|
| 421 |
-
"eval_runtime": 0.
|
| 422 |
-
"eval_samples_per_second":
|
| 423 |
-
"eval_steps_per_second": 6.
|
| 424 |
"learning_rate": 0.0001,
|
| 425 |
"step": 64
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 33.0,
|
| 429 |
-
"eval_explained_variance": 0.
|
| 430 |
-
"eval_loss": 0.
|
| 431 |
-
"eval_mae": 0.
|
| 432 |
-
"eval_r2": -
|
| 433 |
-
"eval_rmse": 0.
|
| 434 |
-
"eval_runtime": 0.
|
| 435 |
-
"eval_samples_per_second":
|
| 436 |
-
"eval_steps_per_second": 6.
|
| 437 |
"learning_rate": 0.0001,
|
| 438 |
"step": 66
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 34.0,
|
| 442 |
-
"eval_explained_variance": 0.
|
| 443 |
-
"eval_loss": 0.
|
| 444 |
-
"eval_mae": 0.
|
| 445 |
-
"eval_r2": -
|
| 446 |
-
"eval_rmse": 0.
|
| 447 |
-
"eval_runtime": 0.
|
| 448 |
-
"eval_samples_per_second":
|
| 449 |
-
"eval_steps_per_second": 6.
|
| 450 |
"learning_rate": 0.0001,
|
| 451 |
"step": 68
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 35.0,
|
| 455 |
-
"eval_explained_variance": 0.
|
| 456 |
-
"eval_loss": 0.
|
| 457 |
-
"eval_mae": 0.
|
| 458 |
-
"eval_r2": -
|
| 459 |
-
"eval_rmse": 0.
|
| 460 |
-
"eval_runtime": 0.
|
| 461 |
-
"eval_samples_per_second":
|
| 462 |
-
"eval_steps_per_second": 6.
|
| 463 |
"learning_rate": 0.0001,
|
| 464 |
"step": 70
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 36.0,
|
| 468 |
-
"eval_explained_variance": 0.
|
| 469 |
-
"eval_loss": 0.
|
| 470 |
-
"eval_mae": 0.
|
| 471 |
-
"eval_r2": -
|
| 472 |
-
"eval_rmse": 0.
|
| 473 |
-
"eval_runtime": 0.
|
| 474 |
-
"eval_samples_per_second":
|
| 475 |
-
"eval_steps_per_second": 6.
|
| 476 |
"learning_rate": 0.0001,
|
| 477 |
"step": 72
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 37.0,
|
| 481 |
-
"eval_explained_variance": 0.
|
| 482 |
-
"eval_loss": 0.
|
| 483 |
-
"eval_mae": 0.
|
| 484 |
-
"eval_r2": -
|
| 485 |
-
"eval_rmse": 0.
|
| 486 |
-
"eval_runtime": 0.
|
| 487 |
-
"eval_samples_per_second":
|
| 488 |
-
"eval_steps_per_second": 6.
|
| 489 |
-
"learning_rate":
|
| 490 |
"step": 74
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 38.0,
|
| 494 |
-
"eval_explained_variance": 0.
|
| 495 |
-
"eval_loss": 0.
|
| 496 |
-
"eval_mae": 0.
|
| 497 |
-
"eval_r2": -
|
| 498 |
-
"eval_rmse": 0.
|
| 499 |
-
"eval_runtime": 0.
|
| 500 |
-
"eval_samples_per_second":
|
| 501 |
-
"eval_steps_per_second": 6.
|
| 502 |
-
"learning_rate":
|
| 503 |
"step": 76
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 39.0,
|
| 507 |
-
"eval_explained_variance": 0.
|
| 508 |
-
"eval_loss": 0.
|
| 509 |
-
"eval_mae": 0.
|
| 510 |
-
"eval_r2": -
|
| 511 |
-
"eval_rmse": 0.
|
| 512 |
-
"eval_runtime": 0.
|
| 513 |
-
"eval_samples_per_second":
|
| 514 |
-
"eval_steps_per_second": 6.
|
| 515 |
-
"learning_rate":
|
| 516 |
"step": 78
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 40.0,
|
| 520 |
-
"eval_explained_variance": 0.
|
| 521 |
-
"eval_loss": 0.
|
| 522 |
-
"eval_mae": 0.
|
| 523 |
-
"eval_r2": -
|
| 524 |
-
"eval_rmse": 0.
|
| 525 |
-
"eval_runtime": 0.
|
| 526 |
-
"eval_samples_per_second":
|
| 527 |
-
"eval_steps_per_second": 6.
|
| 528 |
-
"learning_rate": 0.0001,
|
| 529 |
-
"step": 80
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 41.0,
|
| 533 |
-
"eval_explained_variance": 0.11544161289930344,
|
| 534 |
-
"eval_loss": 0.6195899844169617,
|
| 535 |
-
"eval_mae": 0.30954211950302124,
|
| 536 |
-
"eval_r2": -11.46561050415039,
|
| 537 |
-
"eval_rmse": 0.34560662508010864,
|
| 538 |
-
"eval_runtime": 0.3049,
|
| 539 |
-
"eval_samples_per_second": 163.969,
|
| 540 |
-
"eval_steps_per_second": 6.559,
|
| 541 |
-
"learning_rate": 0.0001,
|
| 542 |
-
"step": 82
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 42.0,
|
| 546 |
-
"eval_explained_variance": 0.12202569097280502,
|
| 547 |
-
"eval_loss": 0.6184768676757812,
|
| 548 |
-
"eval_mae": 0.3095985949039459,
|
| 549 |
-
"eval_r2": -11.41903305053711,
|
| 550 |
-
"eval_rmse": 0.3453018367290497,
|
| 551 |
-
"eval_runtime": 0.3052,
|
| 552 |
-
"eval_samples_per_second": 163.826,
|
| 553 |
-
"eval_steps_per_second": 6.553,
|
| 554 |
-
"learning_rate": 1e-05,
|
| 555 |
-
"step": 84
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 43.0,
|
| 559 |
-
"eval_explained_variance": 0.12239150702953339,
|
| 560 |
-
"eval_loss": 0.619608998298645,
|
| 561 |
-
"eval_mae": 0.3099028468132019,
|
| 562 |
-
"eval_r2": -11.421133995056152,
|
| 563 |
-
"eval_rmse": 0.3457002341747284,
|
| 564 |
-
"eval_runtime": 0.2987,
|
| 565 |
-
"eval_samples_per_second": 167.405,
|
| 566 |
-
"eval_steps_per_second": 6.696,
|
| 567 |
-
"learning_rate": 1e-05,
|
| 568 |
-
"step": 86
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 44.0,
|
| 572 |
-
"eval_explained_variance": 0.12524205446243286,
|
| 573 |
-
"eval_loss": 0.6175010204315186,
|
| 574 |
-
"eval_mae": 0.3090519905090332,
|
| 575 |
-
"eval_r2": -11.342177391052246,
|
| 576 |
-
"eval_rmse": 0.34480178356170654,
|
| 577 |
-
"eval_runtime": 0.3287,
|
| 578 |
-
"eval_samples_per_second": 152.124,
|
| 579 |
-
"eval_steps_per_second": 6.085,
|
| 580 |
-
"learning_rate": 1e-05,
|
| 581 |
-
"step": 88
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"epoch": 45.0,
|
| 585 |
-
"eval_explained_variance": 0.12674368917942047,
|
| 586 |
-
"eval_loss": 0.6147510409355164,
|
| 587 |
-
"eval_mae": 0.307899534702301,
|
| 588 |
-
"eval_r2": -11.237728118896484,
|
| 589 |
-
"eval_rmse": 0.3434869647026062,
|
| 590 |
-
"eval_runtime": 0.3235,
|
| 591 |
-
"eval_samples_per_second": 154.557,
|
| 592 |
-
"eval_steps_per_second": 6.182,
|
| 593 |
-
"learning_rate": 1e-05,
|
| 594 |
-
"step": 90
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 46.0,
|
| 598 |
-
"eval_explained_variance": 0.12321905046701431,
|
| 599 |
-
"eval_loss": 0.6155768036842346,
|
| 600 |
-
"eval_mae": 0.3080970048904419,
|
| 601 |
-
"eval_r2": -11.216095924377441,
|
| 602 |
-
"eval_rmse": 0.3438577651977539,
|
| 603 |
-
"eval_runtime": 0.299,
|
| 604 |
-
"eval_samples_per_second": 167.246,
|
| 605 |
-
"eval_steps_per_second": 6.69,
|
| 606 |
-
"learning_rate": 1e-05,
|
| 607 |
-
"step": 92
|
| 608 |
-
},
|
| 609 |
-
{
|
| 610 |
-
"epoch": 47.0,
|
| 611 |
-
"eval_explained_variance": 0.12190257012844086,
|
| 612 |
-
"eval_loss": 0.616154670715332,
|
| 613 |
-
"eval_mae": 0.30844491720199585,
|
| 614 |
-
"eval_r2": -11.23585319519043,
|
| 615 |
-
"eval_rmse": 0.3442190885543823,
|
| 616 |
-
"eval_runtime": 0.299,
|
| 617 |
-
"eval_samples_per_second": 167.245,
|
| 618 |
-
"eval_steps_per_second": 6.69,
|
| 619 |
-
"learning_rate": 1e-05,
|
| 620 |
-
"step": 94
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 48.0,
|
| 624 |
-
"eval_explained_variance": 0.12182028591632843,
|
| 625 |
-
"eval_loss": 0.6153092980384827,
|
| 626 |
-
"eval_mae": 0.3079487085342407,
|
| 627 |
-
"eval_r2": -11.14069652557373,
|
| 628 |
-
"eval_rmse": 0.34381839632987976,
|
| 629 |
-
"eval_runtime": 0.3282,
|
| 630 |
-
"eval_samples_per_second": 152.339,
|
| 631 |
-
"eval_steps_per_second": 6.094,
|
| 632 |
-
"learning_rate": 1e-05,
|
| 633 |
-
"step": 96
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 49.0,
|
| 637 |
-
"eval_explained_variance": 0.12591353058815002,
|
| 638 |
-
"eval_loss": 0.6142339110374451,
|
| 639 |
-
"eval_mae": 0.3075259327888489,
|
| 640 |
-
"eval_r2": -11.087849617004395,
|
| 641 |
-
"eval_rmse": 0.3433670699596405,
|
| 642 |
-
"eval_runtime": 0.3232,
|
| 643 |
-
"eval_samples_per_second": 154.7,
|
| 644 |
-
"eval_steps_per_second": 6.188,
|
| 645 |
"learning_rate": 1e-05,
|
| 646 |
-
"step":
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"epoch": 50.0,
|
| 650 |
-
"eval_explained_variance": 0.12409819662570953,
|
| 651 |
-
"eval_loss": 0.6125256419181824,
|
| 652 |
-
"eval_mae": 0.3070906400680542,
|
| 653 |
-
"eval_r2": -11.164841651916504,
|
| 654 |
-
"eval_rmse": 0.34268108010292053,
|
| 655 |
-
"eval_runtime": 0.323,
|
| 656 |
-
"eval_samples_per_second": 154.8,
|
| 657 |
-
"eval_steps_per_second": 6.192,
|
| 658 |
-
"learning_rate": 1e-05,
|
| 659 |
-
"step": 100
|
| 660 |
},
|
| 661 |
{
|
| 662 |
-
"epoch":
|
| 663 |
-
"eval_explained_variance": 0.12737669050693512,
|
| 664 |
-
"eval_loss": 0.6131001114845276,
|
| 665 |
-
"eval_mae": 0.3071759045124054,
|
| 666 |
-
"eval_r2": -11.23709487915039,
|
| 667 |
-
"eval_rmse": 0.34303510189056396,
|
| 668 |
-
"eval_runtime": 0.3251,
|
| 669 |
-
"eval_samples_per_second": 153.791,
|
| 670 |
-
"eval_steps_per_second": 6.152,
|
| 671 |
-
"learning_rate": 1e-05,
|
| 672 |
-
"step": 102
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 52.0,
|
| 676 |
-
"eval_explained_variance": 0.12739494442939758,
|
| 677 |
-
"eval_loss": 0.6136941313743591,
|
| 678 |
-
"eval_mae": 0.30773404240608215,
|
| 679 |
-
"eval_r2": -11.390901565551758,
|
| 680 |
-
"eval_rmse": 0.34343937039375305,
|
| 681 |
-
"eval_runtime": 0.3154,
|
| 682 |
-
"eval_samples_per_second": 158.551,
|
| 683 |
-
"eval_steps_per_second": 6.342,
|
| 684 |
-
"learning_rate": 1e-05,
|
| 685 |
-
"step": 104
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"epoch": 53.0,
|
| 689 |
-
"eval_explained_variance": 0.12241682410240173,
|
| 690 |
-
"eval_loss": 0.613895058631897,
|
| 691 |
-
"eval_mae": 0.3076512813568115,
|
| 692 |
-
"eval_r2": -11.501760482788086,
|
| 693 |
-
"eval_rmse": 0.3434452712535858,
|
| 694 |
-
"eval_runtime": 0.3001,
|
| 695 |
-
"eval_samples_per_second": 166.603,
|
| 696 |
-
"eval_steps_per_second": 6.664,
|
| 697 |
-
"learning_rate": 1e-05,
|
| 698 |
-
"step": 106
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 54.0,
|
| 702 |
-
"eval_explained_variance": 0.1222328469157219,
|
| 703 |
-
"eval_loss": 0.6156599521636963,
|
| 704 |
-
"eval_mae": 0.30890733003616333,
|
| 705 |
-
"eval_r2": -11.667372703552246,
|
| 706 |
-
"eval_rmse": 0.3445097804069519,
|
| 707 |
-
"eval_runtime": 0.3773,
|
| 708 |
-
"eval_samples_per_second": 132.51,
|
| 709 |
-
"eval_steps_per_second": 5.3,
|
| 710 |
-
"learning_rate": 1e-05,
|
| 711 |
-
"step": 108
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 55.0,
|
| 715 |
-
"eval_explained_variance": 0.12218669801950455,
|
| 716 |
-
"eval_loss": 0.6167553067207336,
|
| 717 |
-
"eval_mae": 0.30896657705307007,
|
| 718 |
-
"eval_r2": -11.646692276000977,
|
| 719 |
-
"eval_rmse": 0.34482434391975403,
|
| 720 |
-
"eval_runtime": 0.3779,
|
| 721 |
-
"eval_samples_per_second": 132.317,
|
| 722 |
-
"eval_steps_per_second": 5.293,
|
| 723 |
-
"learning_rate": 1e-05,
|
| 724 |
-
"step": 110
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 56.0,
|
| 728 |
-
"eval_explained_variance": 0.12501628696918488,
|
| 729 |
-
"eval_loss": 0.6139956116676331,
|
| 730 |
-
"eval_mae": 0.3077108561992645,
|
| 731 |
-
"eval_r2": -11.49679946899414,
|
| 732 |
-
"eval_rmse": 0.3434431850910187,
|
| 733 |
-
"eval_runtime": 0.2984,
|
| 734 |
-
"eval_samples_per_second": 167.575,
|
| 735 |
-
"eval_steps_per_second": 6.703,
|
| 736 |
"learning_rate": 1e-05,
|
| 737 |
-
"step":
|
| 738 |
-
|
| 739 |
-
|
| 740 |
-
"
|
| 741 |
-
"
|
| 742 |
-
"
|
| 743 |
-
"eval_mae": 0.3070979416370392,
|
| 744 |
-
"eval_r2": -11.500228881835938,
|
| 745 |
-
"eval_rmse": 0.342957466840744,
|
| 746 |
-
"eval_runtime": 0.3776,
|
| 747 |
-
"eval_samples_per_second": 132.398,
|
| 748 |
-
"eval_steps_per_second": 5.296,
|
| 749 |
-
"learning_rate": 1.0000000000000002e-06,
|
| 750 |
-
"step": 114
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"epoch": 58.0,
|
| 754 |
-
"eval_explained_variance": 0.12097452580928802,
|
| 755 |
-
"eval_loss": 0.6130067706108093,
|
| 756 |
-
"eval_mae": 0.30698391795158386,
|
| 757 |
-
"eval_r2": -11.447521209716797,
|
| 758 |
-
"eval_rmse": 0.3428483307361603,
|
| 759 |
-
"eval_runtime": 0.3786,
|
| 760 |
-
"eval_samples_per_second": 132.082,
|
| 761 |
-
"eval_steps_per_second": 5.283,
|
| 762 |
-
"learning_rate": 1.0000000000000002e-06,
|
| 763 |
-
"step": 116
|
| 764 |
-
},
|
| 765 |
-
{
|
| 766 |
-
"epoch": 59.0,
|
| 767 |
-
"eval_explained_variance": 0.11784002184867859,
|
| 768 |
-
"eval_loss": 0.61500084400177,
|
| 769 |
-
"eval_mae": 0.30830222368240356,
|
| 770 |
-
"eval_r2": -11.556161880493164,
|
| 771 |
-
"eval_rmse": 0.34413495659828186,
|
| 772 |
-
"eval_runtime": 0.3056,
|
| 773 |
-
"eval_samples_per_second": 163.604,
|
| 774 |
-
"eval_steps_per_second": 6.544,
|
| 775 |
-
"learning_rate": 1.0000000000000002e-06,
|
| 776 |
-
"step": 118
|
| 777 |
-
},
|
| 778 |
-
{
|
| 779 |
-
"epoch": 60.0,
|
| 780 |
-
"eval_explained_variance": 0.12427856028079987,
|
| 781 |
-
"eval_loss": 0.6166698336601257,
|
| 782 |
-
"eval_mae": 0.30922549962997437,
|
| 783 |
-
"eval_r2": -11.467646598815918,
|
| 784 |
-
"eval_rmse": 0.34501928091049194,
|
| 785 |
-
"eval_runtime": 0.3778,
|
| 786 |
-
"eval_samples_per_second": 132.332,
|
| 787 |
-
"eval_steps_per_second": 5.293,
|
| 788 |
-
"learning_rate": 1.0000000000000002e-06,
|
| 789 |
-
"step": 120
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"epoch": 60.0,
|
| 793 |
-
"learning_rate": 1.0000000000000002e-06,
|
| 794 |
-
"step": 120,
|
| 795 |
-
"total_flos": 4.4402778184752e+17,
|
| 796 |
-
"train_loss": 0.6329069137573242,
|
| 797 |
-
"train_runtime": 375.0945,
|
| 798 |
-
"train_samples_per_second": 19.995,
|
| 799 |
-
"train_steps_per_second": 0.8
|
| 800 |
}
|
| 801 |
],
|
| 802 |
"logging_steps": 500,
|
|
@@ -825,7 +565,7 @@
|
|
| 825 |
"attributes": {}
|
| 826 |
}
|
| 827 |
},
|
| 828 |
-
"total_flos":
|
| 829 |
"train_batch_size": 32,
|
| 830 |
"trial_name": null,
|
| 831 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6263097524642944,
|
| 3 |
+
"best_model_checkpoint": "/home1/datahome/villien/project_hub/DinoVdeau/models/Ziboiai-large-2024_10_31-prova_batch-size32_freeze_probs/checkpoint-60",
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 80,
|
| 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 |
+
"eval_explained_variance": 0.03638218343257904,
|
| 14 |
+
"eval_loss": 0.7150455713272095,
|
| 15 |
+
"eval_mae": 0.3848940134048462,
|
| 16 |
+
"eval_r2": -20.29086685180664,
|
| 17 |
+
"eval_rmse": 0.40997111797332764,
|
| 18 |
+
"eval_runtime": 1.32,
|
| 19 |
+
"eval_samples_per_second": 37.88,
|
| 20 |
+
"eval_steps_per_second": 1.515,
|
| 21 |
"learning_rate": 0.001,
|
| 22 |
"step": 2
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"epoch": 2.0,
|
| 26 |
+
"eval_explained_variance": 0.0240942370146513,
|
| 27 |
+
"eval_loss": 0.7314126491546631,
|
| 28 |
+
"eval_mae": 0.3895121216773987,
|
| 29 |
+
"eval_r2": -21.218204498291016,
|
| 30 |
+
"eval_rmse": 0.4163060486316681,
|
| 31 |
+
"eval_runtime": 0.3125,
|
| 32 |
+
"eval_samples_per_second": 160.002,
|
| 33 |
+
"eval_steps_per_second": 6.4,
|
| 34 |
"learning_rate": 0.001,
|
| 35 |
"step": 4
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 3.0,
|
| 39 |
+
"eval_explained_variance": -0.04694412648677826,
|
| 40 |
+
"eval_loss": 0.7726277112960815,
|
| 41 |
+
"eval_mae": 0.40413352847099304,
|
| 42 |
+
"eval_r2": -24.822391510009766,
|
| 43 |
+
"eval_rmse": 0.4320966601371765,
|
| 44 |
+
"eval_runtime": 0.3275,
|
| 45 |
+
"eval_samples_per_second": 152.667,
|
| 46 |
+
"eval_steps_per_second": 6.107,
|
| 47 |
"learning_rate": 0.001,
|
| 48 |
"step": 6
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
+
"eval_explained_variance": -0.06671242415904999,
|
| 53 |
+
"eval_loss": 0.7917326092720032,
|
| 54 |
+
"eval_mae": 0.4094983637332916,
|
| 55 |
+
"eval_r2": -26.581586837768555,
|
| 56 |
+
"eval_rmse": 0.4379725754261017,
|
| 57 |
+
"eval_runtime": 0.3153,
|
| 58 |
+
"eval_samples_per_second": 158.574,
|
| 59 |
+
"eval_steps_per_second": 6.343,
|
| 60 |
"learning_rate": 0.001,
|
| 61 |
"step": 8
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 5.0,
|
| 65 |
+
"eval_explained_variance": -0.13621382415294647,
|
| 66 |
+
"eval_loss": 0.7852649092674255,
|
| 67 |
+
"eval_mae": 0.402120441198349,
|
| 68 |
+
"eval_r2": -26.95589256286621,
|
| 69 |
+
"eval_rmse": 0.43184274435043335,
|
| 70 |
+
"eval_runtime": 0.3123,
|
| 71 |
+
"eval_samples_per_second": 160.086,
|
| 72 |
+
"eval_steps_per_second": 6.403,
|
| 73 |
"learning_rate": 0.001,
|
| 74 |
"step": 10
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 6.0,
|
| 78 |
+
"eval_explained_variance": -0.12974193692207336,
|
| 79 |
+
"eval_loss": 0.7647674679756165,
|
| 80 |
+
"eval_mae": 0.3905399441719055,
|
| 81 |
+
"eval_r2": -24.40153694152832,
|
| 82 |
+
"eval_rmse": 0.42244094610214233,
|
| 83 |
+
"eval_runtime": 0.3317,
|
| 84 |
+
"eval_samples_per_second": 150.759,
|
| 85 |
+
"eval_steps_per_second": 6.03,
|
| 86 |
"learning_rate": 0.001,
|
| 87 |
"step": 12
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 7.0,
|
| 91 |
+
"eval_explained_variance": -0.10977767407894135,
|
| 92 |
+
"eval_loss": 0.7391812205314636,
|
| 93 |
+
"eval_mae": 0.376028835773468,
|
| 94 |
+
"eval_r2": -22.557889938354492,
|
| 95 |
+
"eval_rmse": 0.41028541326522827,
|
| 96 |
+
"eval_runtime": 0.3205,
|
| 97 |
+
"eval_samples_per_second": 155.989,
|
| 98 |
+
"eval_steps_per_second": 6.24,
|
| 99 |
"learning_rate": 0.001,
|
| 100 |
"step": 14
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 8.0,
|
| 104 |
+
"eval_explained_variance": -0.10544480383396149,
|
| 105 |
+
"eval_loss": 0.7115270495414734,
|
| 106 |
+
"eval_mae": 0.36385056376457214,
|
| 107 |
+
"eval_r2": -20.067392349243164,
|
| 108 |
+
"eval_rmse": 0.39825379848480225,
|
| 109 |
+
"eval_runtime": 0.3104,
|
| 110 |
+
"eval_samples_per_second": 161.103,
|
| 111 |
+
"eval_steps_per_second": 6.444,
|
| 112 |
"learning_rate": 0.0001,
|
| 113 |
"step": 16
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 9.0,
|
| 117 |
+
"eval_explained_variance": -0.09249210357666016,
|
| 118 |
+
"eval_loss": 0.6896975040435791,
|
| 119 |
+
"eval_mae": 0.35347798466682434,
|
| 120 |
+
"eval_r2": -18.16646385192871,
|
| 121 |
+
"eval_rmse": 0.3878582715988159,
|
| 122 |
+
"eval_runtime": 0.3226,
|
| 123 |
+
"eval_samples_per_second": 155.006,
|
| 124 |
+
"eval_steps_per_second": 6.2,
|
| 125 |
"learning_rate": 0.0001,
|
| 126 |
"step": 18
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 10.0,
|
| 130 |
+
"eval_explained_variance": -0.10285507887601852,
|
| 131 |
+
"eval_loss": 0.6777035593986511,
|
| 132 |
+
"eval_mae": 0.34683120250701904,
|
| 133 |
+
"eval_r2": -16.94469451904297,
|
| 134 |
+
"eval_rmse": 0.3818005323410034,
|
| 135 |
+
"eval_runtime": 0.3016,
|
| 136 |
+
"eval_samples_per_second": 165.76,
|
| 137 |
+
"eval_steps_per_second": 6.63,
|
| 138 |
"learning_rate": 0.0001,
|
| 139 |
"step": 20
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 11.0,
|
| 143 |
+
"eval_explained_variance": -0.11687294393777847,
|
| 144 |
+
"eval_loss": 0.6701759099960327,
|
| 145 |
+
"eval_mae": 0.3423532247543335,
|
| 146 |
+
"eval_r2": -16.037521362304688,
|
| 147 |
+
"eval_rmse": 0.3779585659503937,
|
| 148 |
+
"eval_runtime": 0.3107,
|
| 149 |
+
"eval_samples_per_second": 160.916,
|
| 150 |
+
"eval_steps_per_second": 6.437,
|
| 151 |
"learning_rate": 0.0001,
|
| 152 |
"step": 22
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 12.0,
|
| 156 |
+
"eval_explained_variance": -0.11208173632621765,
|
| 157 |
+
"eval_loss": 0.663905918598175,
|
| 158 |
+
"eval_mae": 0.3388546407222748,
|
| 159 |
+
"eval_r2": -15.605177879333496,
|
| 160 |
+
"eval_rmse": 0.37438222765922546,
|
| 161 |
+
"eval_runtime": 0.3308,
|
| 162 |
+
"eval_samples_per_second": 151.17,
|
| 163 |
+
"eval_steps_per_second": 6.047,
|
| 164 |
"learning_rate": 0.0001,
|
| 165 |
"step": 24
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 13.0,
|
| 169 |
+
"eval_explained_variance": -0.10647904872894287,
|
| 170 |
+
"eval_loss": 0.656491219997406,
|
| 171 |
+
"eval_mae": 0.3345881700515747,
|
| 172 |
+
"eval_r2": -14.805088996887207,
|
| 173 |
+
"eval_rmse": 0.3702985942363739,
|
| 174 |
+
"eval_runtime": 0.3222,
|
| 175 |
+
"eval_samples_per_second": 155.166,
|
| 176 |
+
"eval_steps_per_second": 6.207,
|
| 177 |
"learning_rate": 0.0001,
|
| 178 |
"step": 26
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 14.0,
|
| 182 |
+
"eval_explained_variance": -0.0958017110824585,
|
| 183 |
+
"eval_loss": 0.6501385569572449,
|
| 184 |
+
"eval_mae": 0.33100754022598267,
|
| 185 |
+
"eval_r2": -14.231175422668457,
|
| 186 |
+
"eval_rmse": 0.3668138384819031,
|
| 187 |
+
"eval_runtime": 0.3293,
|
| 188 |
+
"eval_samples_per_second": 151.853,
|
| 189 |
+
"eval_steps_per_second": 6.074,
|
| 190 |
"learning_rate": 0.0001,
|
| 191 |
"step": 28
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 15.0,
|
| 195 |
+
"eval_explained_variance": -0.08547426015138626,
|
| 196 |
+
"eval_loss": 0.6467865705490112,
|
| 197 |
+
"eval_mae": 0.32885220646858215,
|
| 198 |
+
"eval_r2": -14.07986831665039,
|
| 199 |
+
"eval_rmse": 0.36475783586502075,
|
| 200 |
+
"eval_runtime": 0.3253,
|
| 201 |
+
"eval_samples_per_second": 153.717,
|
| 202 |
+
"eval_steps_per_second": 6.149,
|
| 203 |
"learning_rate": 0.0001,
|
| 204 |
"step": 30
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 16.0,
|
| 208 |
+
"eval_explained_variance": -0.08231981098651886,
|
| 209 |
+
"eval_loss": 0.6471170783042908,
|
| 210 |
+
"eval_mae": 0.3288896679878235,
|
| 211 |
+
"eval_r2": -14.255745887756348,
|
| 212 |
+
"eval_rmse": 0.3650059998035431,
|
| 213 |
+
"eval_runtime": 0.305,
|
| 214 |
+
"eval_samples_per_second": 163.945,
|
| 215 |
+
"eval_steps_per_second": 6.558,
|
| 216 |
"learning_rate": 0.0001,
|
| 217 |
"step": 32
|
| 218 |
},
|
| 219 |
{
|
| 220 |
"epoch": 17.0,
|
| 221 |
+
"eval_explained_variance": -0.08097466081380844,
|
| 222 |
+
"eval_loss": 0.6435126662254333,
|
| 223 |
+
"eval_mae": 0.3268200755119324,
|
| 224 |
+
"eval_r2": -14.059813499450684,
|
| 225 |
+
"eval_rmse": 0.36310678720474243,
|
| 226 |
+
"eval_runtime": 0.3322,
|
| 227 |
+
"eval_samples_per_second": 150.492,
|
| 228 |
+
"eval_steps_per_second": 6.02,
|
| 229 |
"learning_rate": 0.0001,
|
| 230 |
"step": 34
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 18.0,
|
| 234 |
+
"eval_explained_variance": -0.07994352281093597,
|
| 235 |
+
"eval_loss": 0.6437923908233643,
|
| 236 |
+
"eval_mae": 0.3269612491130829,
|
| 237 |
+
"eval_r2": -14.036934852600098,
|
| 238 |
+
"eval_rmse": 0.36342939734458923,
|
| 239 |
+
"eval_runtime": 0.3107,
|
| 240 |
+
"eval_samples_per_second": 160.922,
|
| 241 |
+
"eval_steps_per_second": 6.437,
|
| 242 |
"learning_rate": 0.0001,
|
| 243 |
"step": 36
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 19.0,
|
| 247 |
+
"eval_explained_variance": -0.08883289247751236,
|
| 248 |
+
"eval_loss": 0.6399621367454529,
|
| 249 |
+
"eval_mae": 0.3249860107898712,
|
| 250 |
+
"eval_r2": -13.81522274017334,
|
| 251 |
+
"eval_rmse": 0.36136963963508606,
|
| 252 |
+
"eval_runtime": 0.3104,
|
| 253 |
+
"eval_samples_per_second": 161.092,
|
| 254 |
+
"eval_steps_per_second": 6.444,
|
| 255 |
"learning_rate": 0.0001,
|
| 256 |
"step": 38
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 20.0,
|
| 260 |
+
"eval_explained_variance": -0.09353505074977875,
|
| 261 |
+
"eval_loss": 0.6391971707344055,
|
| 262 |
+
"eval_mae": 0.3246455192565918,
|
| 263 |
+
"eval_r2": -13.710391998291016,
|
| 264 |
+
"eval_rmse": 0.3608955144882202,
|
| 265 |
+
"eval_runtime": 0.3119,
|
| 266 |
+
"eval_samples_per_second": 160.306,
|
| 267 |
+
"eval_steps_per_second": 6.412,
|
| 268 |
"learning_rate": 0.0001,
|
| 269 |
"step": 40
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 21.0,
|
| 273 |
+
"eval_explained_variance": -0.09930111467838287,
|
| 274 |
+
"eval_loss": 0.6386714577674866,
|
| 275 |
+
"eval_mae": 0.32462170720100403,
|
| 276 |
+
"eval_r2": -13.809860229492188,
|
| 277 |
+
"eval_rmse": 0.3606450855731964,
|
| 278 |
+
"eval_runtime": 0.3149,
|
| 279 |
+
"eval_samples_per_second": 158.8,
|
| 280 |
+
"eval_steps_per_second": 6.352,
|
| 281 |
"learning_rate": 0.0001,
|
| 282 |
"step": 42
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 22.0,
|
| 286 |
+
"eval_explained_variance": -0.10561199486255646,
|
| 287 |
+
"eval_loss": 0.6388444304466248,
|
| 288 |
+
"eval_mae": 0.3243348002433777,
|
| 289 |
+
"eval_r2": -13.849721908569336,
|
| 290 |
+
"eval_rmse": 0.36056435108184814,
|
| 291 |
+
"eval_runtime": 0.3094,
|
| 292 |
+
"eval_samples_per_second": 161.607,
|
| 293 |
+
"eval_steps_per_second": 6.464,
|
| 294 |
"learning_rate": 0.0001,
|
| 295 |
"step": 44
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 23.0,
|
| 299 |
+
"eval_explained_variance": -0.1035044863820076,
|
| 300 |
+
"eval_loss": 0.6361631155014038,
|
| 301 |
+
"eval_mae": 0.3227779269218445,
|
| 302 |
+
"eval_r2": -13.562189102172852,
|
| 303 |
+
"eval_rmse": 0.35895633697509766,
|
| 304 |
+
"eval_runtime": 0.3094,
|
| 305 |
+
"eval_samples_per_second": 161.581,
|
| 306 |
+
"eval_steps_per_second": 6.463,
|
| 307 |
"learning_rate": 0.0001,
|
| 308 |
"step": 46
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 24.0,
|
| 312 |
+
"eval_explained_variance": -0.10584529489278793,
|
| 313 |
+
"eval_loss": 0.635435163974762,
|
| 314 |
+
"eval_mae": 0.3223152160644531,
|
| 315 |
+
"eval_r2": -13.645319938659668,
|
| 316 |
+
"eval_rmse": 0.35847193002700806,
|
| 317 |
+
"eval_runtime": 0.3094,
|
| 318 |
+
"eval_samples_per_second": 161.602,
|
| 319 |
+
"eval_steps_per_second": 6.464,
|
| 320 |
"learning_rate": 0.0001,
|
| 321 |
"step": 48
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 25.0,
|
| 325 |
+
"eval_explained_variance": -0.1035505086183548,
|
| 326 |
+
"eval_loss": 0.6344550848007202,
|
| 327 |
+
"eval_mae": 0.32144099473953247,
|
| 328 |
+
"eval_r2": -13.602314949035645,
|
| 329 |
+
"eval_rmse": 0.35783687233924866,
|
| 330 |
+
"eval_runtime": 0.3092,
|
| 331 |
+
"eval_samples_per_second": 161.704,
|
| 332 |
+
"eval_steps_per_second": 6.468,
|
| 333 |
"learning_rate": 0.0001,
|
| 334 |
"step": 50
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 26.0,
|
| 338 |
+
"eval_explained_variance": -0.11728200316429138,
|
| 339 |
+
"eval_loss": 0.6348865628242493,
|
| 340 |
+
"eval_mae": 0.3211889863014221,
|
| 341 |
+
"eval_r2": -13.630416870117188,
|
| 342 |
+
"eval_rmse": 0.3580625355243683,
|
| 343 |
+
"eval_runtime": 0.331,
|
| 344 |
+
"eval_samples_per_second": 151.064,
|
| 345 |
+
"eval_steps_per_second": 6.043,
|
| 346 |
"learning_rate": 0.0001,
|
| 347 |
"step": 52
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 27.0,
|
| 351 |
+
"eval_explained_variance": -0.11483900249004364,
|
| 352 |
+
"eval_loss": 0.6332749724388123,
|
| 353 |
+
"eval_mae": 0.32009246945381165,
|
| 354 |
+
"eval_r2": -13.561347007751465,
|
| 355 |
+
"eval_rmse": 0.3570806384086609,
|
| 356 |
+
"eval_runtime": 0.3173,
|
| 357 |
+
"eval_samples_per_second": 157.565,
|
| 358 |
+
"eval_steps_per_second": 6.303,
|
| 359 |
"learning_rate": 0.0001,
|
| 360 |
"step": 54
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 28.0,
|
| 364 |
+
"eval_explained_variance": -0.10828801989555359,
|
| 365 |
+
"eval_loss": 0.6295092701911926,
|
| 366 |
+
"eval_mae": 0.31767499446868896,
|
| 367 |
+
"eval_r2": -13.23308277130127,
|
| 368 |
+
"eval_rmse": 0.35479238629341125,
|
| 369 |
+
"eval_runtime": 0.3087,
|
| 370 |
+
"eval_samples_per_second": 161.989,
|
| 371 |
+
"eval_steps_per_second": 6.48,
|
| 372 |
"learning_rate": 0.0001,
|
| 373 |
"step": 56
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"epoch": 29.0,
|
| 377 |
+
"eval_explained_variance": -0.1047045886516571,
|
| 378 |
+
"eval_loss": 0.6285346746444702,
|
| 379 |
+
"eval_mae": 0.3173280954360962,
|
| 380 |
+
"eval_r2": -13.162256240844727,
|
| 381 |
+
"eval_rmse": 0.35434553027153015,
|
| 382 |
+
"eval_runtime": 0.3277,
|
| 383 |
+
"eval_samples_per_second": 152.596,
|
| 384 |
+
"eval_steps_per_second": 6.104,
|
| 385 |
"learning_rate": 0.0001,
|
| 386 |
"step": 58
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 30.0,
|
| 390 |
+
"eval_explained_variance": -0.09264782071113586,
|
| 391 |
+
"eval_loss": 0.6263097524642944,
|
| 392 |
+
"eval_mae": 0.31627562642097473,
|
| 393 |
+
"eval_r2": -12.713174819946289,
|
| 394 |
+
"eval_rmse": 0.3532228171825409,
|
| 395 |
+
"eval_runtime": 0.3523,
|
| 396 |
+
"eval_samples_per_second": 141.931,
|
| 397 |
+
"eval_steps_per_second": 5.677,
|
| 398 |
"learning_rate": 0.0001,
|
| 399 |
"step": 60
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 31.0,
|
| 403 |
+
"eval_explained_variance": -0.08934260159730911,
|
| 404 |
+
"eval_loss": 0.6272528767585754,
|
| 405 |
+
"eval_mae": 0.316723495721817,
|
| 406 |
+
"eval_r2": -12.873921394348145,
|
| 407 |
+
"eval_rmse": 0.35376670956611633,
|
| 408 |
+
"eval_runtime": 0.3073,
|
| 409 |
+
"eval_samples_per_second": 162.723,
|
| 410 |
+
"eval_steps_per_second": 6.509,
|
| 411 |
"learning_rate": 0.0001,
|
| 412 |
"step": 62
|
| 413 |
},
|
| 414 |
{
|
| 415 |
"epoch": 32.0,
|
| 416 |
+
"eval_explained_variance": -0.07898036390542984,
|
| 417 |
+
"eval_loss": 0.6294133067131042,
|
| 418 |
+
"eval_mae": 0.31807586550712585,
|
| 419 |
+
"eval_r2": -12.935453414916992,
|
| 420 |
+
"eval_rmse": 0.3550169765949249,
|
| 421 |
+
"eval_runtime": 0.3094,
|
| 422 |
+
"eval_samples_per_second": 161.626,
|
| 423 |
+
"eval_steps_per_second": 6.465,
|
| 424 |
"learning_rate": 0.0001,
|
| 425 |
"step": 64
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 33.0,
|
| 429 |
+
"eval_explained_variance": -0.07519607990980148,
|
| 430 |
+
"eval_loss": 0.6299176216125488,
|
| 431 |
+
"eval_mae": 0.3185364603996277,
|
| 432 |
+
"eval_r2": -12.93520736694336,
|
| 433 |
+
"eval_rmse": 0.35538923740386963,
|
| 434 |
+
"eval_runtime": 0.3097,
|
| 435 |
+
"eval_samples_per_second": 161.472,
|
| 436 |
+
"eval_steps_per_second": 6.459,
|
| 437 |
"learning_rate": 0.0001,
|
| 438 |
"step": 66
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 34.0,
|
| 442 |
+
"eval_explained_variance": -0.07019602507352829,
|
| 443 |
+
"eval_loss": 0.6320692300796509,
|
| 444 |
+
"eval_mae": 0.3193182349205017,
|
| 445 |
+
"eval_r2": -13.267191886901855,
|
| 446 |
+
"eval_rmse": 0.35644862055778503,
|
| 447 |
+
"eval_runtime": 0.3161,
|
| 448 |
+
"eval_samples_per_second": 158.177,
|
| 449 |
+
"eval_steps_per_second": 6.327,
|
| 450 |
"learning_rate": 0.0001,
|
| 451 |
"step": 68
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 35.0,
|
| 455 |
+
"eval_explained_variance": -0.04873532056808472,
|
| 456 |
+
"eval_loss": 0.6279481649398804,
|
| 457 |
+
"eval_mae": 0.31752488017082214,
|
| 458 |
+
"eval_r2": -12.99951171875,
|
| 459 |
+
"eval_rmse": 0.3541102707386017,
|
| 460 |
+
"eval_runtime": 0.3124,
|
| 461 |
+
"eval_samples_per_second": 160.036,
|
| 462 |
+
"eval_steps_per_second": 6.401,
|
| 463 |
"learning_rate": 0.0001,
|
| 464 |
"step": 70
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 36.0,
|
| 468 |
+
"eval_explained_variance": -0.04663123935461044,
|
| 469 |
+
"eval_loss": 0.6280075907707214,
|
| 470 |
+
"eval_mae": 0.31736499071121216,
|
| 471 |
+
"eval_r2": -13.00741195678711,
|
| 472 |
+
"eval_rmse": 0.35407301783561707,
|
| 473 |
+
"eval_runtime": 0.3095,
|
| 474 |
+
"eval_samples_per_second": 161.554,
|
| 475 |
+
"eval_steps_per_second": 6.462,
|
| 476 |
"learning_rate": 0.0001,
|
| 477 |
"step": 72
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 37.0,
|
| 481 |
+
"eval_explained_variance": -0.04936327785253525,
|
| 482 |
+
"eval_loss": 0.6303659081459045,
|
| 483 |
+
"eval_mae": 0.3187006115913391,
|
| 484 |
+
"eval_r2": -13.230977058410645,
|
| 485 |
+
"eval_rmse": 0.35543760657310486,
|
| 486 |
+
"eval_runtime": 0.3251,
|
| 487 |
+
"eval_samples_per_second": 153.806,
|
| 488 |
+
"eval_steps_per_second": 6.152,
|
| 489 |
+
"learning_rate": 1e-05,
|
| 490 |
"step": 74
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 38.0,
|
| 494 |
+
"eval_explained_variance": -0.04394898936152458,
|
| 495 |
+
"eval_loss": 0.6297122836112976,
|
| 496 |
+
"eval_mae": 0.31833118200302124,
|
| 497 |
+
"eval_r2": -12.983016967773438,
|
| 498 |
+
"eval_rmse": 0.3550592064857483,
|
| 499 |
+
"eval_runtime": 0.3087,
|
| 500 |
+
"eval_samples_per_second": 161.995,
|
| 501 |
+
"eval_steps_per_second": 6.48,
|
| 502 |
+
"learning_rate": 1e-05,
|
| 503 |
"step": 76
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 39.0,
|
| 507 |
+
"eval_explained_variance": -0.04296223446726799,
|
| 508 |
+
"eval_loss": 0.630845308303833,
|
| 509 |
+
"eval_mae": 0.3193325996398926,
|
| 510 |
+
"eval_r2": -13.159842491149902,
|
| 511 |
+
"eval_rmse": 0.35580796003341675,
|
| 512 |
+
"eval_runtime": 0.3097,
|
| 513 |
+
"eval_samples_per_second": 161.465,
|
| 514 |
+
"eval_steps_per_second": 6.459,
|
| 515 |
+
"learning_rate": 1e-05,
|
| 516 |
"step": 78
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 40.0,
|
| 520 |
+
"eval_explained_variance": -0.04348618537187576,
|
| 521 |
+
"eval_loss": 0.6291573643684387,
|
| 522 |
+
"eval_mae": 0.3182610869407654,
|
| 523 |
+
"eval_r2": -13.069788932800293,
|
| 524 |
+
"eval_rmse": 0.3547934889793396,
|
| 525 |
+
"eval_runtime": 0.3206,
|
| 526 |
+
"eval_samples_per_second": 155.938,
|
| 527 |
+
"eval_steps_per_second": 6.238,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 528 |
"learning_rate": 1e-05,
|
| 529 |
+
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 530 |
},
|
| 531 |
{
|
| 532 |
+
"epoch": 40.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 533 |
"learning_rate": 1e-05,
|
| 534 |
+
"step": 80,
|
| 535 |
+
"total_flos": 2.9601852123168e+17,
|
| 536 |
+
"train_loss": 0.64580397605896,
|
| 537 |
+
"train_runtime": 275.9938,
|
| 538 |
+
"train_samples_per_second": 27.175,
|
| 539 |
+
"train_steps_per_second": 1.087
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 540 |
}
|
| 541 |
],
|
| 542 |
"logging_steps": 500,
|
|
|
|
| 565 |
"attributes": {}
|
| 566 |
}
|
| 567 |
},
|
| 568 |
+
"total_flos": 2.9601852123168e+17,
|
| 569 |
"train_batch_size": 32,
|
| 570 |
"trial_name": null,
|
| 571 |
"trial_params": null
|