Commit
•
2b5835a
1
Parent(s):
ebac23b
End of training
Browse files- README.md +1 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Apr24_22-53-17_91f3f55b97b0/events.out.tfevents.1714000131.91f3f55b97b0.1605.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +575 -0
README.md
CHANGED
|
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
- Accuracy: 0.7667
|
| 22 |
|
| 23 |
## Model description
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.7073
|
| 21 |
- Accuracy: 0.7667
|
| 22 |
|
| 23 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 37.935483870967744,
|
| 3 |
+
"eval_accuracy": 0.7666666666666667,
|
| 4 |
+
"eval_loss": 0.7072709798812866,
|
| 5 |
+
"eval_runtime": 1.4511,
|
| 6 |
+
"eval_samples_per_second": 41.349,
|
| 7 |
+
"eval_steps_per_second": 1.378,
|
| 8 |
+
"total_flos": 1.2027310550050406e+18,
|
| 9 |
+
"train_loss": 0.8700437156521544,
|
| 10 |
+
"train_runtime": 913.4545,
|
| 11 |
+
"train_samples_per_second": 44.784,
|
| 12 |
+
"train_steps_per_second": 0.322
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 37.935483870967744,
|
| 3 |
+
"eval_accuracy": 0.7666666666666667,
|
| 4 |
+
"eval_loss": 0.7072709798812866,
|
| 5 |
+
"eval_runtime": 1.4511,
|
| 6 |
+
"eval_samples_per_second": 41.349,
|
| 7 |
+
"eval_steps_per_second": 1.378
|
| 8 |
+
}
|
runs/Apr24_22-53-17_91f3f55b97b0/events.out.tfevents.1714000131.91f3f55b97b0.1605.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c4c29e904718ebc8f7f17de632044a94685c65f16285954c5a1755c9f7e7b9e
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 37.935483870967744,
|
| 3 |
+
"total_flos": 1.2027310550050406e+18,
|
| 4 |
+
"train_loss": 0.8700437156521544,
|
| 5 |
+
"train_runtime": 913.4545,
|
| 6 |
+
"train_samples_per_second": 44.784,
|
| 7 |
+
"train_steps_per_second": 0.322
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,575 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7666666666666667,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-dmae-va-U5-42C/checkpoint-232",
|
| 4 |
+
"epoch": 37.935483870967744,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 294,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.9032258064516129,
|
| 13 |
+
"eval_accuracy": 0.35,
|
| 14 |
+
"eval_loss": 1.3925895690917969,
|
| 15 |
+
"eval_runtime": 1.9549,
|
| 16 |
+
"eval_samples_per_second": 30.693,
|
| 17 |
+
"eval_steps_per_second": 1.023,
|
| 18 |
+
"step": 7
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.2903225806451613,
|
| 22 |
+
"grad_norm": 3.2569632530212402,
|
| 23 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 24 |
+
"loss": 1.4087,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.935483870967742,
|
| 29 |
+
"eval_accuracy": 0.4166666666666667,
|
| 30 |
+
"eval_loss": 1.3364887237548828,
|
| 31 |
+
"eval_runtime": 1.315,
|
| 32 |
+
"eval_samples_per_second": 45.628,
|
| 33 |
+
"eval_steps_per_second": 1.521,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.5806451612903225,
|
| 38 |
+
"grad_norm": 2.8684847354888916,
|
| 39 |
+
"learning_rate": 6.666666666666667e-06,
|
| 40 |
+
"loss": 1.3807,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.967741935483871,
|
| 45 |
+
"eval_accuracy": 0.4166666666666667,
|
| 46 |
+
"eval_loss": 1.2813018560409546,
|
| 47 |
+
"eval_runtime": 1.3067,
|
| 48 |
+
"eval_samples_per_second": 45.917,
|
| 49 |
+
"eval_steps_per_second": 1.531,
|
| 50 |
+
"step": 23
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.870967741935484,
|
| 54 |
+
"grad_norm": 3.6313109397888184,
|
| 55 |
+
"learning_rate": 1e-05,
|
| 56 |
+
"loss": 1.35,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"eval_accuracy": 0.4,
|
| 62 |
+
"eval_loss": 1.2406634092330933,
|
| 63 |
+
"eval_runtime": 1.3069,
|
| 64 |
+
"eval_samples_per_second": 45.909,
|
| 65 |
+
"eval_steps_per_second": 1.53,
|
| 66 |
+
"step": 31
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.903225806451613,
|
| 70 |
+
"eval_accuracy": 0.48333333333333334,
|
| 71 |
+
"eval_loss": 1.2116148471832275,
|
| 72 |
+
"eval_runtime": 1.3014,
|
| 73 |
+
"eval_samples_per_second": 46.103,
|
| 74 |
+
"eval_steps_per_second": 1.537,
|
| 75 |
+
"step": 38
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.161290322580645,
|
| 79 |
+
"grad_norm": 3.7117483615875244,
|
| 80 |
+
"learning_rate": 9.621212121212122e-06,
|
| 81 |
+
"loss": 1.2933,
|
| 82 |
+
"step": 40
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 5.935483870967742,
|
| 86 |
+
"eval_accuracy": 0.48333333333333334,
|
| 87 |
+
"eval_loss": 1.165272831916809,
|
| 88 |
+
"eval_runtime": 1.3337,
|
| 89 |
+
"eval_samples_per_second": 44.987,
|
| 90 |
+
"eval_steps_per_second": 1.5,
|
| 91 |
+
"step": 46
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.451612903225806,
|
| 95 |
+
"grad_norm": 4.500431060791016,
|
| 96 |
+
"learning_rate": 9.242424242424244e-06,
|
| 97 |
+
"loss": 1.2426,
|
| 98 |
+
"step": 50
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.967741935483871,
|
| 102 |
+
"eval_accuracy": 0.5166666666666667,
|
| 103 |
+
"eval_loss": 1.115120768547058,
|
| 104 |
+
"eval_runtime": 1.3716,
|
| 105 |
+
"eval_samples_per_second": 43.745,
|
| 106 |
+
"eval_steps_per_second": 1.458,
|
| 107 |
+
"step": 54
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 7.741935483870968,
|
| 111 |
+
"grad_norm": 4.069227695465088,
|
| 112 |
+
"learning_rate": 8.863636363636365e-06,
|
| 113 |
+
"loss": 1.1771,
|
| 114 |
+
"step": 60
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 8.0,
|
| 118 |
+
"eval_accuracy": 0.6,
|
| 119 |
+
"eval_loss": 1.0440610647201538,
|
| 120 |
+
"eval_runtime": 1.9614,
|
| 121 |
+
"eval_samples_per_second": 30.59,
|
| 122 |
+
"eval_steps_per_second": 1.02,
|
| 123 |
+
"step": 62
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 8.903225806451612,
|
| 127 |
+
"eval_accuracy": 0.5666666666666667,
|
| 128 |
+
"eval_loss": 0.9990090727806091,
|
| 129 |
+
"eval_runtime": 1.6529,
|
| 130 |
+
"eval_samples_per_second": 36.299,
|
| 131 |
+
"eval_steps_per_second": 1.21,
|
| 132 |
+
"step": 69
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 9.03225806451613,
|
| 136 |
+
"grad_norm": 6.175364971160889,
|
| 137 |
+
"learning_rate": 8.484848484848486e-06,
|
| 138 |
+
"loss": 1.0983,
|
| 139 |
+
"step": 70
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 9.935483870967742,
|
| 143 |
+
"eval_accuracy": 0.6333333333333333,
|
| 144 |
+
"eval_loss": 0.9455800652503967,
|
| 145 |
+
"eval_runtime": 1.336,
|
| 146 |
+
"eval_samples_per_second": 44.911,
|
| 147 |
+
"eval_steps_per_second": 1.497,
|
| 148 |
+
"step": 77
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 10.32258064516129,
|
| 152 |
+
"grad_norm": 5.833083152770996,
|
| 153 |
+
"learning_rate": 8.106060606060606e-06,
|
| 154 |
+
"loss": 1.0338,
|
| 155 |
+
"step": 80
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 10.967741935483872,
|
| 159 |
+
"eval_accuracy": 0.6833333333333333,
|
| 160 |
+
"eval_loss": 0.9160192012786865,
|
| 161 |
+
"eval_runtime": 1.3605,
|
| 162 |
+
"eval_samples_per_second": 44.101,
|
| 163 |
+
"eval_steps_per_second": 1.47,
|
| 164 |
+
"step": 85
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 11.612903225806452,
|
| 168 |
+
"grad_norm": 7.081052303314209,
|
| 169 |
+
"learning_rate": 7.727272727272727e-06,
|
| 170 |
+
"loss": 0.9665,
|
| 171 |
+
"step": 90
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.0,
|
| 175 |
+
"eval_accuracy": 0.6833333333333333,
|
| 176 |
+
"eval_loss": 0.8940223455429077,
|
| 177 |
+
"eval_runtime": 1.6293,
|
| 178 |
+
"eval_samples_per_second": 36.825,
|
| 179 |
+
"eval_steps_per_second": 1.228,
|
| 180 |
+
"step": 93
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 12.903225806451612,
|
| 184 |
+
"grad_norm": 10.133336067199707,
|
| 185 |
+
"learning_rate": 7.348484848484849e-06,
|
| 186 |
+
"loss": 0.9133,
|
| 187 |
+
"step": 100
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 12.903225806451612,
|
| 191 |
+
"eval_accuracy": 0.6,
|
| 192 |
+
"eval_loss": 0.8753000497817993,
|
| 193 |
+
"eval_runtime": 1.851,
|
| 194 |
+
"eval_samples_per_second": 32.415,
|
| 195 |
+
"eval_steps_per_second": 1.081,
|
| 196 |
+
"step": 100
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 13.935483870967742,
|
| 200 |
+
"eval_accuracy": 0.6666666666666666,
|
| 201 |
+
"eval_loss": 0.8517557978630066,
|
| 202 |
+
"eval_runtime": 1.7325,
|
| 203 |
+
"eval_samples_per_second": 34.633,
|
| 204 |
+
"eval_steps_per_second": 1.154,
|
| 205 |
+
"step": 108
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 14.193548387096774,
|
| 209 |
+
"grad_norm": 7.324928283691406,
|
| 210 |
+
"learning_rate": 6.969696969696971e-06,
|
| 211 |
+
"loss": 0.8521,
|
| 212 |
+
"step": 110
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 14.967741935483872,
|
| 216 |
+
"eval_accuracy": 0.65,
|
| 217 |
+
"eval_loss": 0.8514594435691833,
|
| 218 |
+
"eval_runtime": 1.3473,
|
| 219 |
+
"eval_samples_per_second": 44.535,
|
| 220 |
+
"eval_steps_per_second": 1.484,
|
| 221 |
+
"step": 116
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 15.483870967741936,
|
| 225 |
+
"grad_norm": 8.610685348510742,
|
| 226 |
+
"learning_rate": 6.590909090909091e-06,
|
| 227 |
+
"loss": 0.8461,
|
| 228 |
+
"step": 120
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 16.0,
|
| 232 |
+
"eval_accuracy": 0.65,
|
| 233 |
+
"eval_loss": 0.8406927585601807,
|
| 234 |
+
"eval_runtime": 1.3128,
|
| 235 |
+
"eval_samples_per_second": 45.703,
|
| 236 |
+
"eval_steps_per_second": 1.523,
|
| 237 |
+
"step": 124
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 16.774193548387096,
|
| 241 |
+
"grad_norm": 8.986543655395508,
|
| 242 |
+
"learning_rate": 6.212121212121213e-06,
|
| 243 |
+
"loss": 0.808,
|
| 244 |
+
"step": 130
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 16.903225806451612,
|
| 248 |
+
"eval_accuracy": 0.65,
|
| 249 |
+
"eval_loss": 0.8217867016792297,
|
| 250 |
+
"eval_runtime": 1.3566,
|
| 251 |
+
"eval_samples_per_second": 44.227,
|
| 252 |
+
"eval_steps_per_second": 1.474,
|
| 253 |
+
"step": 131
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 17.93548387096774,
|
| 257 |
+
"eval_accuracy": 0.6833333333333333,
|
| 258 |
+
"eval_loss": 0.817019522190094,
|
| 259 |
+
"eval_runtime": 1.3417,
|
| 260 |
+
"eval_samples_per_second": 44.72,
|
| 261 |
+
"eval_steps_per_second": 1.491,
|
| 262 |
+
"step": 139
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 18.06451612903226,
|
| 266 |
+
"grad_norm": 14.52387523651123,
|
| 267 |
+
"learning_rate": 5.833333333333334e-06,
|
| 268 |
+
"loss": 0.7779,
|
| 269 |
+
"step": 140
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 18.967741935483872,
|
| 273 |
+
"eval_accuracy": 0.7166666666666667,
|
| 274 |
+
"eval_loss": 0.7972093224525452,
|
| 275 |
+
"eval_runtime": 1.333,
|
| 276 |
+
"eval_samples_per_second": 45.011,
|
| 277 |
+
"eval_steps_per_second": 1.5,
|
| 278 |
+
"step": 147
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 19.35483870967742,
|
| 282 |
+
"grad_norm": 9.242515563964844,
|
| 283 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 284 |
+
"loss": 0.758,
|
| 285 |
+
"step": 150
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 20.0,
|
| 289 |
+
"eval_accuracy": 0.7333333333333333,
|
| 290 |
+
"eval_loss": 0.7816523313522339,
|
| 291 |
+
"eval_runtime": 1.3563,
|
| 292 |
+
"eval_samples_per_second": 44.24,
|
| 293 |
+
"eval_steps_per_second": 1.475,
|
| 294 |
+
"step": 155
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 20.64516129032258,
|
| 298 |
+
"grad_norm": 10.172256469726562,
|
| 299 |
+
"learning_rate": 5.075757575757576e-06,
|
| 300 |
+
"loss": 0.7416,
|
| 301 |
+
"step": 160
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 20.903225806451612,
|
| 305 |
+
"eval_accuracy": 0.7166666666666667,
|
| 306 |
+
"eval_loss": 0.7677698135375977,
|
| 307 |
+
"eval_runtime": 1.3666,
|
| 308 |
+
"eval_samples_per_second": 43.906,
|
| 309 |
+
"eval_steps_per_second": 1.464,
|
| 310 |
+
"step": 162
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 21.93548387096774,
|
| 314 |
+
"grad_norm": 9.232048988342285,
|
| 315 |
+
"learning_rate": 4.696969696969698e-06,
|
| 316 |
+
"loss": 0.7344,
|
| 317 |
+
"step": 170
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 21.93548387096774,
|
| 321 |
+
"eval_accuracy": 0.7166666666666667,
|
| 322 |
+
"eval_loss": 0.7650207281112671,
|
| 323 |
+
"eval_runtime": 1.3874,
|
| 324 |
+
"eval_samples_per_second": 43.248,
|
| 325 |
+
"eval_steps_per_second": 1.442,
|
| 326 |
+
"step": 170
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 22.967741935483872,
|
| 330 |
+
"eval_accuracy": 0.7333333333333333,
|
| 331 |
+
"eval_loss": 0.7427585124969482,
|
| 332 |
+
"eval_runtime": 1.3402,
|
| 333 |
+
"eval_samples_per_second": 44.768,
|
| 334 |
+
"eval_steps_per_second": 1.492,
|
| 335 |
+
"step": 178
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 23.225806451612904,
|
| 339 |
+
"grad_norm": 8.738112449645996,
|
| 340 |
+
"learning_rate": 4.3181818181818185e-06,
|
| 341 |
+
"loss": 0.7091,
|
| 342 |
+
"step": 180
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 24.0,
|
| 346 |
+
"eval_accuracy": 0.75,
|
| 347 |
+
"eval_loss": 0.7280309200286865,
|
| 348 |
+
"eval_runtime": 1.3549,
|
| 349 |
+
"eval_samples_per_second": 44.284,
|
| 350 |
+
"eval_steps_per_second": 1.476,
|
| 351 |
+
"step": 186
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 24.516129032258064,
|
| 355 |
+
"grad_norm": 9.839088439941406,
|
| 356 |
+
"learning_rate": 3.93939393939394e-06,
|
| 357 |
+
"loss": 0.6876,
|
| 358 |
+
"step": 190
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 24.903225806451612,
|
| 362 |
+
"eval_accuracy": 0.75,
|
| 363 |
+
"eval_loss": 0.7235161066055298,
|
| 364 |
+
"eval_runtime": 1.346,
|
| 365 |
+
"eval_samples_per_second": 44.577,
|
| 366 |
+
"eval_steps_per_second": 1.486,
|
| 367 |
+
"step": 193
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 25.806451612903224,
|
| 371 |
+
"grad_norm": 9.253539085388184,
|
| 372 |
+
"learning_rate": 3.560606060606061e-06,
|
| 373 |
+
"loss": 0.6887,
|
| 374 |
+
"step": 200
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 25.93548387096774,
|
| 378 |
+
"eval_accuracy": 0.75,
|
| 379 |
+
"eval_loss": 0.7277832627296448,
|
| 380 |
+
"eval_runtime": 1.4422,
|
| 381 |
+
"eval_samples_per_second": 41.604,
|
| 382 |
+
"eval_steps_per_second": 1.387,
|
| 383 |
+
"step": 201
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 26.967741935483872,
|
| 387 |
+
"eval_accuracy": 0.75,
|
| 388 |
+
"eval_loss": 0.7264487147331238,
|
| 389 |
+
"eval_runtime": 1.3795,
|
| 390 |
+
"eval_samples_per_second": 43.494,
|
| 391 |
+
"eval_steps_per_second": 1.45,
|
| 392 |
+
"step": 209
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 27.096774193548388,
|
| 396 |
+
"grad_norm": 9.031746864318848,
|
| 397 |
+
"learning_rate": 3.181818181818182e-06,
|
| 398 |
+
"loss": 0.6897,
|
| 399 |
+
"step": 210
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 28.0,
|
| 403 |
+
"eval_accuracy": 0.75,
|
| 404 |
+
"eval_loss": 0.7228216528892517,
|
| 405 |
+
"eval_runtime": 1.5018,
|
| 406 |
+
"eval_samples_per_second": 39.952,
|
| 407 |
+
"eval_steps_per_second": 1.332,
|
| 408 |
+
"step": 217
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 28.387096774193548,
|
| 412 |
+
"grad_norm": 9.238479614257812,
|
| 413 |
+
"learning_rate": 2.803030303030303e-06,
|
| 414 |
+
"loss": 0.6637,
|
| 415 |
+
"step": 220
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 28.903225806451612,
|
| 419 |
+
"eval_accuracy": 0.75,
|
| 420 |
+
"eval_loss": 0.7162961363792419,
|
| 421 |
+
"eval_runtime": 1.8314,
|
| 422 |
+
"eval_samples_per_second": 32.762,
|
| 423 |
+
"eval_steps_per_second": 1.092,
|
| 424 |
+
"step": 224
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 29.677419354838708,
|
| 428 |
+
"grad_norm": 11.410670280456543,
|
| 429 |
+
"learning_rate": 2.4242424242424244e-06,
|
| 430 |
+
"loss": 0.6924,
|
| 431 |
+
"step": 230
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 29.93548387096774,
|
| 435 |
+
"eval_accuracy": 0.7666666666666667,
|
| 436 |
+
"eval_loss": 0.7072709798812866,
|
| 437 |
+
"eval_runtime": 1.7495,
|
| 438 |
+
"eval_samples_per_second": 34.295,
|
| 439 |
+
"eval_steps_per_second": 1.143,
|
| 440 |
+
"step": 232
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 30.967741935483872,
|
| 444 |
+
"grad_norm": 9.04150676727295,
|
| 445 |
+
"learning_rate": 2.0454545454545457e-06,
|
| 446 |
+
"loss": 0.6234,
|
| 447 |
+
"step": 240
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 30.967741935483872,
|
| 451 |
+
"eval_accuracy": 0.7666666666666667,
|
| 452 |
+
"eval_loss": 0.7057181596755981,
|
| 453 |
+
"eval_runtime": 1.7336,
|
| 454 |
+
"eval_samples_per_second": 34.609,
|
| 455 |
+
"eval_steps_per_second": 1.154,
|
| 456 |
+
"step": 240
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 32.0,
|
| 460 |
+
"eval_accuracy": 0.7666666666666667,
|
| 461 |
+
"eval_loss": 0.7090018391609192,
|
| 462 |
+
"eval_runtime": 1.9304,
|
| 463 |
+
"eval_samples_per_second": 31.081,
|
| 464 |
+
"eval_steps_per_second": 1.036,
|
| 465 |
+
"step": 248
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 32.25806451612903,
|
| 469 |
+
"grad_norm": 10.956854820251465,
|
| 470 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 471 |
+
"loss": 0.6652,
|
| 472 |
+
"step": 250
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 32.903225806451616,
|
| 476 |
+
"eval_accuracy": 0.7666666666666667,
|
| 477 |
+
"eval_loss": 0.7051603198051453,
|
| 478 |
+
"eval_runtime": 2.0298,
|
| 479 |
+
"eval_samples_per_second": 29.559,
|
| 480 |
+
"eval_steps_per_second": 0.985,
|
| 481 |
+
"step": 255
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 33.54838709677419,
|
| 485 |
+
"grad_norm": 11.52700424194336,
|
| 486 |
+
"learning_rate": 1.287878787878788e-06,
|
| 487 |
+
"loss": 0.6343,
|
| 488 |
+
"step": 260
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 33.935483870967744,
|
| 492 |
+
"eval_accuracy": 0.7666666666666667,
|
| 493 |
+
"eval_loss": 0.7009490132331848,
|
| 494 |
+
"eval_runtime": 1.5868,
|
| 495 |
+
"eval_samples_per_second": 37.811,
|
| 496 |
+
"eval_steps_per_second": 1.26,
|
| 497 |
+
"step": 263
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 34.83870967741935,
|
| 501 |
+
"grad_norm": 10.979878425598145,
|
| 502 |
+
"learning_rate": 9.090909090909091e-07,
|
| 503 |
+
"loss": 0.6327,
|
| 504 |
+
"step": 270
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 34.96774193548387,
|
| 508 |
+
"eval_accuracy": 0.7666666666666667,
|
| 509 |
+
"eval_loss": 0.7016925811767578,
|
| 510 |
+
"eval_runtime": 1.3715,
|
| 511 |
+
"eval_samples_per_second": 43.748,
|
| 512 |
+
"eval_steps_per_second": 1.458,
|
| 513 |
+
"step": 271
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 36.0,
|
| 517 |
+
"eval_accuracy": 0.7666666666666667,
|
| 518 |
+
"eval_loss": 0.7023322582244873,
|
| 519 |
+
"eval_runtime": 1.3676,
|
| 520 |
+
"eval_samples_per_second": 43.872,
|
| 521 |
+
"eval_steps_per_second": 1.462,
|
| 522 |
+
"step": 279
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 36.12903225806452,
|
| 526 |
+
"grad_norm": 8.543764114379883,
|
| 527 |
+
"learning_rate": 5.303030303030304e-07,
|
| 528 |
+
"loss": 0.6339,
|
| 529 |
+
"step": 280
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 36.903225806451616,
|
| 533 |
+
"eval_accuracy": 0.7666666666666667,
|
| 534 |
+
"eval_loss": 0.7027052044868469,
|
| 535 |
+
"eval_runtime": 1.3882,
|
| 536 |
+
"eval_samples_per_second": 43.221,
|
| 537 |
+
"eval_steps_per_second": 1.441,
|
| 538 |
+
"step": 286
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 37.41935483870968,
|
| 542 |
+
"grad_norm": 10.100813865661621,
|
| 543 |
+
"learning_rate": 1.5151515151515152e-07,
|
| 544 |
+
"loss": 0.6275,
|
| 545 |
+
"step": 290
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 37.935483870967744,
|
| 549 |
+
"eval_accuracy": 0.7666666666666667,
|
| 550 |
+
"eval_loss": 0.7030532956123352,
|
| 551 |
+
"eval_runtime": 1.3783,
|
| 552 |
+
"eval_samples_per_second": 43.53,
|
| 553 |
+
"eval_steps_per_second": 1.451,
|
| 554 |
+
"step": 294
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 37.935483870967744,
|
| 558 |
+
"step": 294,
|
| 559 |
+
"total_flos": 1.2027310550050406e+18,
|
| 560 |
+
"train_loss": 0.8700437156521544,
|
| 561 |
+
"train_runtime": 913.4545,
|
| 562 |
+
"train_samples_per_second": 44.784,
|
| 563 |
+
"train_steps_per_second": 0.322
|
| 564 |
+
}
|
| 565 |
+
],
|
| 566 |
+
"logging_steps": 10,
|
| 567 |
+
"max_steps": 294,
|
| 568 |
+
"num_input_tokens_seen": 0,
|
| 569 |
+
"num_train_epochs": 42,
|
| 570 |
+
"save_steps": 500,
|
| 571 |
+
"total_flos": 1.2027310550050406e+18,
|
| 572 |
+
"train_batch_size": 32,
|
| 573 |
+
"trial_name": null,
|
| 574 |
+
"trial_params": null
|
| 575 |
+
}
|