End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"eval_accuracy": 0.894109396914446,
|
| 4 |
+
"eval_loss": 0.303189218044281,
|
| 5 |
+
"eval_runtime": 41.2026,
|
| 6 |
+
"eval_samples_per_second": 69.219,
|
| 7 |
+
"eval_steps_per_second": 1.092,
|
| 8 |
+
"total_flos": 6.364199987970048e+18,
|
| 9 |
+
"train_loss": 0.48602974390983583,
|
| 10 |
+
"train_runtime": 5351.8475,
|
| 11 |
+
"train_samples_per_second": 47.954,
|
| 12 |
+
"train_steps_per_second": 0.187
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"eval_accuracy": 0.894109396914446,
|
| 4 |
+
"eval_loss": 0.303189218044281,
|
| 5 |
+
"eval_runtime": 41.2026,
|
| 6 |
+
"eval_samples_per_second": 69.219,
|
| 7 |
+
"eval_steps_per_second": 1.092
|
| 8 |
+
}
|
runs/May10_13-56-27_5ef4b5b162fa/events.out.tfevents.1715354789.5ef4b5b162fa.34.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12752e032aaa9a99d8a0b69c2a4934529f883af9a29f384c13e3121609eb791d
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"total_flos": 6.364199987970048e+18,
|
| 4 |
+
"train_loss": 0.48602974390983583,
|
| 5 |
+
"train_runtime": 5351.8475,
|
| 6 |
+
"train_samples_per_second": 47.954,
|
| 7 |
+
"train_steps_per_second": 0.187
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,820 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.894109396914446,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-classification/checkpoint-1000",
|
| 4 |
+
"epoch": 9.975062344139651,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"grad_norm": 5.313328742980957,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 2.0631,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2,
|
| 20 |
+
"grad_norm": 5.775210857391357,
|
| 21 |
+
"learning_rate": 2e-05,
|
| 22 |
+
"loss": 1.7746,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3,
|
| 27 |
+
"grad_norm": 4.816771984100342,
|
| 28 |
+
"learning_rate": 3e-05,
|
| 29 |
+
"loss": 1.5563,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4,
|
| 34 |
+
"grad_norm": 6.007688999176025,
|
| 35 |
+
"learning_rate": 4e-05,
|
| 36 |
+
"loss": 1.2361,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5,
|
| 41 |
+
"grad_norm": 7.807107925415039,
|
| 42 |
+
"learning_rate": 5e-05,
|
| 43 |
+
"loss": 1.0685,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6,
|
| 48 |
+
"grad_norm": 6.920202732086182,
|
| 49 |
+
"learning_rate": 6e-05,
|
| 50 |
+
"loss": 0.9716,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7,
|
| 55 |
+
"grad_norm": 5.678104877471924,
|
| 56 |
+
"learning_rate": 7e-05,
|
| 57 |
+
"loss": 0.9274,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.8,
|
| 62 |
+
"grad_norm": 7.1128010749816895,
|
| 63 |
+
"learning_rate": 8e-05,
|
| 64 |
+
"loss": 0.8962,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.9,
|
| 69 |
+
"grad_norm": 8.700326919555664,
|
| 70 |
+
"learning_rate": 9e-05,
|
| 71 |
+
"loss": 0.8924,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.0,
|
| 76 |
+
"grad_norm": 7.496997833251953,
|
| 77 |
+
"learning_rate": 0.0001,
|
| 78 |
+
"loss": 0.8514,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0,
|
| 83 |
+
"eval_accuracy": 0.705820476858345,
|
| 84 |
+
"eval_loss": 0.7862311005592346,
|
| 85 |
+
"eval_runtime": 38.0587,
|
| 86 |
+
"eval_samples_per_second": 74.937,
|
| 87 |
+
"eval_steps_per_second": 1.182,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.1,
|
| 92 |
+
"grad_norm": 5.842683792114258,
|
| 93 |
+
"learning_rate": 9.888888888888889e-05,
|
| 94 |
+
"loss": 0.7961,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.2,
|
| 99 |
+
"grad_norm": 7.082647323608398,
|
| 100 |
+
"learning_rate": 9.777777777777778e-05,
|
| 101 |
+
"loss": 0.8179,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.3,
|
| 106 |
+
"grad_norm": 6.531412601470947,
|
| 107 |
+
"learning_rate": 9.666666666666667e-05,
|
| 108 |
+
"loss": 0.772,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.4,
|
| 113 |
+
"grad_norm": 4.981847763061523,
|
| 114 |
+
"learning_rate": 9.555555555555557e-05,
|
| 115 |
+
"loss": 0.7298,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.5,
|
| 120 |
+
"grad_norm": 6.9995198249816895,
|
| 121 |
+
"learning_rate": 9.444444444444444e-05,
|
| 122 |
+
"loss": 0.6882,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.6,
|
| 127 |
+
"grad_norm": 4.9766693115234375,
|
| 128 |
+
"learning_rate": 9.333333333333334e-05,
|
| 129 |
+
"loss": 0.7048,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.7,
|
| 134 |
+
"grad_norm": 5.899988174438477,
|
| 135 |
+
"learning_rate": 9.222222222222223e-05,
|
| 136 |
+
"loss": 0.7254,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.8,
|
| 141 |
+
"grad_norm": 4.040374755859375,
|
| 142 |
+
"learning_rate": 9.111111111111112e-05,
|
| 143 |
+
"loss": 0.6543,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.9,
|
| 148 |
+
"grad_norm": 6.156548023223877,
|
| 149 |
+
"learning_rate": 9e-05,
|
| 150 |
+
"loss": 0.6329,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 2.0,
|
| 155 |
+
"grad_norm": 6.268504619598389,
|
| 156 |
+
"learning_rate": 8.888888888888889e-05,
|
| 157 |
+
"loss": 0.631,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.0,
|
| 162 |
+
"eval_accuracy": 0.7885694249649369,
|
| 163 |
+
"eval_loss": 0.5491923093795776,
|
| 164 |
+
"eval_runtime": 38.032,
|
| 165 |
+
"eval_samples_per_second": 74.989,
|
| 166 |
+
"eval_steps_per_second": 1.183,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.09,
|
| 171 |
+
"grad_norm": 6.425785541534424,
|
| 172 |
+
"learning_rate": 8.777777777777778e-05,
|
| 173 |
+
"loss": 0.612,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.19,
|
| 178 |
+
"grad_norm": 5.754735469818115,
|
| 179 |
+
"learning_rate": 8.666666666666667e-05,
|
| 180 |
+
"loss": 0.6117,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.29,
|
| 185 |
+
"grad_norm": 5.51466703414917,
|
| 186 |
+
"learning_rate": 8.555555555555556e-05,
|
| 187 |
+
"loss": 0.6041,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.39,
|
| 192 |
+
"grad_norm": 5.170792102813721,
|
| 193 |
+
"learning_rate": 8.444444444444444e-05,
|
| 194 |
+
"loss": 0.6057,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.49,
|
| 199 |
+
"grad_norm": 5.319341659545898,
|
| 200 |
+
"learning_rate": 8.333333333333334e-05,
|
| 201 |
+
"loss": 0.556,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.59,
|
| 206 |
+
"grad_norm": 7.033453941345215,
|
| 207 |
+
"learning_rate": 8.222222222222222e-05,
|
| 208 |
+
"loss": 0.5918,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.69,
|
| 213 |
+
"grad_norm": 6.37441349029541,
|
| 214 |
+
"learning_rate": 8.111111111111112e-05,
|
| 215 |
+
"loss": 0.5603,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.79,
|
| 220 |
+
"grad_norm": 4.926444053649902,
|
| 221 |
+
"learning_rate": 8e-05,
|
| 222 |
+
"loss": 0.5827,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.89,
|
| 227 |
+
"grad_norm": 4.273934841156006,
|
| 228 |
+
"learning_rate": 7.88888888888889e-05,
|
| 229 |
+
"loss": 0.5406,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.99,
|
| 234 |
+
"grad_norm": 5.528937816619873,
|
| 235 |
+
"learning_rate": 7.777777777777778e-05,
|
| 236 |
+
"loss": 0.5516,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.99,
|
| 241 |
+
"eval_accuracy": 0.8078541374474053,
|
| 242 |
+
"eval_loss": 0.5194684863090515,
|
| 243 |
+
"eval_runtime": 38.7637,
|
| 244 |
+
"eval_samples_per_second": 73.574,
|
| 245 |
+
"eval_steps_per_second": 1.161,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.09,
|
| 250 |
+
"grad_norm": 9.39556884765625,
|
| 251 |
+
"learning_rate": 7.666666666666667e-05,
|
| 252 |
+
"loss": 0.5039,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 3.19,
|
| 257 |
+
"grad_norm": 5.658567428588867,
|
| 258 |
+
"learning_rate": 7.555555555555556e-05,
|
| 259 |
+
"loss": 0.497,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.29,
|
| 264 |
+
"grad_norm": 5.974184513092041,
|
| 265 |
+
"learning_rate": 7.444444444444444e-05,
|
| 266 |
+
"loss": 0.5041,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.39,
|
| 271 |
+
"grad_norm": 5.876557350158691,
|
| 272 |
+
"learning_rate": 7.333333333333333e-05,
|
| 273 |
+
"loss": 0.4978,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.49,
|
| 278 |
+
"grad_norm": 7.005821704864502,
|
| 279 |
+
"learning_rate": 7.222222222222222e-05,
|
| 280 |
+
"loss": 0.5145,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.59,
|
| 285 |
+
"grad_norm": 4.967439651489258,
|
| 286 |
+
"learning_rate": 7.111111111111112e-05,
|
| 287 |
+
"loss": 0.4803,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.69,
|
| 292 |
+
"grad_norm": 4.976831436157227,
|
| 293 |
+
"learning_rate": 7e-05,
|
| 294 |
+
"loss": 0.4816,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.79,
|
| 299 |
+
"grad_norm": 6.872544288635254,
|
| 300 |
+
"learning_rate": 6.88888888888889e-05,
|
| 301 |
+
"loss": 0.4811,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.89,
|
| 306 |
+
"grad_norm": 5.97269868850708,
|
| 307 |
+
"learning_rate": 6.777777777777778e-05,
|
| 308 |
+
"loss": 0.4978,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.99,
|
| 313 |
+
"grad_norm": 5.982359886169434,
|
| 314 |
+
"learning_rate": 6.666666666666667e-05,
|
| 315 |
+
"loss": 0.4597,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 4.0,
|
| 320 |
+
"eval_accuracy": 0.8229312762973352,
|
| 321 |
+
"eval_loss": 0.48398053646087646,
|
| 322 |
+
"eval_runtime": 38.5586,
|
| 323 |
+
"eval_samples_per_second": 73.965,
|
| 324 |
+
"eval_steps_per_second": 1.167,
|
| 325 |
+
"step": 401
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 4.09,
|
| 329 |
+
"grad_norm": 4.751348972320557,
|
| 330 |
+
"learning_rate": 6.555555555555556e-05,
|
| 331 |
+
"loss": 0.4443,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.19,
|
| 336 |
+
"grad_norm": 4.549768447875977,
|
| 337 |
+
"learning_rate": 6.444444444444446e-05,
|
| 338 |
+
"loss": 0.423,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.29,
|
| 343 |
+
"grad_norm": 6.269441604614258,
|
| 344 |
+
"learning_rate": 6.333333333333333e-05,
|
| 345 |
+
"loss": 0.449,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.39,
|
| 350 |
+
"grad_norm": 4.581325531005859,
|
| 351 |
+
"learning_rate": 6.222222222222222e-05,
|
| 352 |
+
"loss": 0.4099,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.49,
|
| 357 |
+
"grad_norm": 5.31665563583374,
|
| 358 |
+
"learning_rate": 6.111111111111112e-05,
|
| 359 |
+
"loss": 0.4075,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.59,
|
| 364 |
+
"grad_norm": 5.4510416984558105,
|
| 365 |
+
"learning_rate": 6e-05,
|
| 366 |
+
"loss": 0.4195,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.69,
|
| 371 |
+
"grad_norm": 5.312283515930176,
|
| 372 |
+
"learning_rate": 5.8888888888888896e-05,
|
| 373 |
+
"loss": 0.3829,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.79,
|
| 378 |
+
"grad_norm": 5.865201950073242,
|
| 379 |
+
"learning_rate": 5.7777777777777776e-05,
|
| 380 |
+
"loss": 0.4209,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.89,
|
| 385 |
+
"grad_norm": 5.123416423797607,
|
| 386 |
+
"learning_rate": 5.666666666666667e-05,
|
| 387 |
+
"loss": 0.4094,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4.99,
|
| 392 |
+
"grad_norm": 4.805253982543945,
|
| 393 |
+
"learning_rate": 5.555555555555556e-05,
|
| 394 |
+
"loss": 0.4094,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 5.0,
|
| 399 |
+
"eval_accuracy": 0.8597475455820477,
|
| 400 |
+
"eval_loss": 0.3945947587490082,
|
| 401 |
+
"eval_runtime": 38.9464,
|
| 402 |
+
"eval_samples_per_second": 73.229,
|
| 403 |
+
"eval_steps_per_second": 1.155,
|
| 404 |
+
"step": 501
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 5.09,
|
| 408 |
+
"grad_norm": 4.796308517456055,
|
| 409 |
+
"learning_rate": 5.4444444444444446e-05,
|
| 410 |
+
"loss": 0.3555,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 5.19,
|
| 415 |
+
"grad_norm": 4.460272789001465,
|
| 416 |
+
"learning_rate": 5.333333333333333e-05,
|
| 417 |
+
"loss": 0.3719,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 5.29,
|
| 422 |
+
"grad_norm": 5.035310745239258,
|
| 423 |
+
"learning_rate": 5.222222222222223e-05,
|
| 424 |
+
"loss": 0.3785,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 5.39,
|
| 429 |
+
"grad_norm": 5.145148754119873,
|
| 430 |
+
"learning_rate": 5.111111111111111e-05,
|
| 431 |
+
"loss": 0.3881,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 5.49,
|
| 436 |
+
"grad_norm": 6.646022319793701,
|
| 437 |
+
"learning_rate": 5e-05,
|
| 438 |
+
"loss": 0.3776,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 5.59,
|
| 443 |
+
"grad_norm": 6.039920330047607,
|
| 444 |
+
"learning_rate": 4.888888888888889e-05,
|
| 445 |
+
"loss": 0.3891,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.69,
|
| 450 |
+
"grad_norm": 4.1056623458862305,
|
| 451 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 452 |
+
"loss": 0.3369,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.79,
|
| 457 |
+
"grad_norm": 5.633683204650879,
|
| 458 |
+
"learning_rate": 4.666666666666667e-05,
|
| 459 |
+
"loss": 0.3606,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 5.89,
|
| 464 |
+
"grad_norm": 5.873307704925537,
|
| 465 |
+
"learning_rate": 4.555555555555556e-05,
|
| 466 |
+
"loss": 0.3386,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.99,
|
| 471 |
+
"grad_norm": 5.3684983253479,
|
| 472 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 473 |
+
"loss": 0.3289,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 6.0,
|
| 478 |
+
"eval_accuracy": 0.8572931276297335,
|
| 479 |
+
"eval_loss": 0.3786664605140686,
|
| 480 |
+
"eval_runtime": 40.3623,
|
| 481 |
+
"eval_samples_per_second": 70.66,
|
| 482 |
+
"eval_steps_per_second": 1.115,
|
| 483 |
+
"step": 601
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 6.08,
|
| 487 |
+
"grad_norm": 4.093196392059326,
|
| 488 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 489 |
+
"loss": 0.3251,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 6.18,
|
| 494 |
+
"grad_norm": 4.739712715148926,
|
| 495 |
+
"learning_rate": 4.222222222222222e-05,
|
| 496 |
+
"loss": 0.3029,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 6.28,
|
| 501 |
+
"grad_norm": 3.9042539596557617,
|
| 502 |
+
"learning_rate": 4.111111111111111e-05,
|
| 503 |
+
"loss": 0.3269,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 6.38,
|
| 508 |
+
"grad_norm": 5.695065498352051,
|
| 509 |
+
"learning_rate": 4e-05,
|
| 510 |
+
"loss": 0.3318,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 6.48,
|
| 515 |
+
"grad_norm": 4.814879894256592,
|
| 516 |
+
"learning_rate": 3.888888888888889e-05,
|
| 517 |
+
"loss": 0.3087,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.58,
|
| 522 |
+
"grad_norm": 4.633285999298096,
|
| 523 |
+
"learning_rate": 3.777777777777778e-05,
|
| 524 |
+
"loss": 0.3416,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.68,
|
| 529 |
+
"grad_norm": 4.862430095672607,
|
| 530 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 531 |
+
"loss": 0.3063,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 6.78,
|
| 536 |
+
"grad_norm": 4.930345058441162,
|
| 537 |
+
"learning_rate": 3.555555555555556e-05,
|
| 538 |
+
"loss": 0.3225,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 6.88,
|
| 543 |
+
"grad_norm": 4.587200164794922,
|
| 544 |
+
"learning_rate": 3.444444444444445e-05,
|
| 545 |
+
"loss": 0.3139,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 6.98,
|
| 550 |
+
"grad_norm": 5.570033550262451,
|
| 551 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 552 |
+
"loss": 0.3145,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.99,
|
| 557 |
+
"eval_accuracy": 0.8772791023842917,
|
| 558 |
+
"eval_loss": 0.3536257743835449,
|
| 559 |
+
"eval_runtime": 42.7073,
|
| 560 |
+
"eval_samples_per_second": 66.78,
|
| 561 |
+
"eval_steps_per_second": 1.054,
|
| 562 |
+
"step": 701
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 7.08,
|
| 566 |
+
"grad_norm": 5.562831401824951,
|
| 567 |
+
"learning_rate": 3.222222222222223e-05,
|
| 568 |
+
"loss": 0.2998,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 7.18,
|
| 573 |
+
"grad_norm": 5.306057453155518,
|
| 574 |
+
"learning_rate": 3.111111111111111e-05,
|
| 575 |
+
"loss": 0.2807,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 7.28,
|
| 580 |
+
"grad_norm": 5.671096324920654,
|
| 581 |
+
"learning_rate": 3e-05,
|
| 582 |
+
"loss": 0.2794,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 7.38,
|
| 587 |
+
"grad_norm": 5.412108421325684,
|
| 588 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 589 |
+
"loss": 0.2814,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 7.48,
|
| 594 |
+
"grad_norm": 4.249139308929443,
|
| 595 |
+
"learning_rate": 2.777777777777778e-05,
|
| 596 |
+
"loss": 0.2531,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 7.58,
|
| 601 |
+
"grad_norm": 5.714820861816406,
|
| 602 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 603 |
+
"loss": 0.2712,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 7.68,
|
| 608 |
+
"grad_norm": 5.9426469802856445,
|
| 609 |
+
"learning_rate": 2.5555555555555554e-05,
|
| 610 |
+
"loss": 0.2589,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 7.78,
|
| 615 |
+
"grad_norm": 4.787610054016113,
|
| 616 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 617 |
+
"loss": 0.2745,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 7.88,
|
| 622 |
+
"grad_norm": 3.9021761417388916,
|
| 623 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 624 |
+
"loss": 0.2728,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.98,
|
| 629 |
+
"grad_norm": 5.153603553771973,
|
| 630 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 631 |
+
"loss": 0.2911,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 8.0,
|
| 636 |
+
"eval_accuracy": 0.885343618513324,
|
| 637 |
+
"eval_loss": 0.32486388087272644,
|
| 638 |
+
"eval_runtime": 42.9219,
|
| 639 |
+
"eval_samples_per_second": 66.446,
|
| 640 |
+
"eval_steps_per_second": 1.048,
|
| 641 |
+
"step": 802
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 8.08,
|
| 645 |
+
"grad_norm": 5.644151210784912,
|
| 646 |
+
"learning_rate": 2.111111111111111e-05,
|
| 647 |
+
"loss": 0.2559,
|
| 648 |
+
"step": 810
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 8.18,
|
| 652 |
+
"grad_norm": 4.023806095123291,
|
| 653 |
+
"learning_rate": 2e-05,
|
| 654 |
+
"loss": 0.2415,
|
| 655 |
+
"step": 820
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 8.28,
|
| 659 |
+
"grad_norm": 6.214153289794922,
|
| 660 |
+
"learning_rate": 1.888888888888889e-05,
|
| 661 |
+
"loss": 0.2447,
|
| 662 |
+
"step": 830
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 8.38,
|
| 666 |
+
"grad_norm": 3.903085231781006,
|
| 667 |
+
"learning_rate": 1.777777777777778e-05,
|
| 668 |
+
"loss": 0.2602,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 8.48,
|
| 673 |
+
"grad_norm": 5.1828131675720215,
|
| 674 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 675 |
+
"loss": 0.2529,
|
| 676 |
+
"step": 850
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 8.58,
|
| 680 |
+
"grad_norm": 4.840915203094482,
|
| 681 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 682 |
+
"loss": 0.2302,
|
| 683 |
+
"step": 860
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 8.68,
|
| 687 |
+
"grad_norm": 5.424919128417969,
|
| 688 |
+
"learning_rate": 1.4444444444444444e-05,
|
| 689 |
+
"loss": 0.246,
|
| 690 |
+
"step": 870
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 8.78,
|
| 694 |
+
"grad_norm": 6.8232316970825195,
|
| 695 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 696 |
+
"loss": 0.2435,
|
| 697 |
+
"step": 880
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 8.88,
|
| 701 |
+
"grad_norm": 4.856207847595215,
|
| 702 |
+
"learning_rate": 1.2222222222222222e-05,
|
| 703 |
+
"loss": 0.2376,
|
| 704 |
+
"step": 890
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 8.98,
|
| 708 |
+
"grad_norm": 5.239475250244141,
|
| 709 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 710 |
+
"loss": 0.2487,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 9.0,
|
| 715 |
+
"eval_accuracy": 0.8937587657784011,
|
| 716 |
+
"eval_loss": 0.30939263105392456,
|
| 717 |
+
"eval_runtime": 39.5102,
|
| 718 |
+
"eval_samples_per_second": 72.184,
|
| 719 |
+
"eval_steps_per_second": 1.139,
|
| 720 |
+
"step": 902
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 9.08,
|
| 724 |
+
"grad_norm": 5.607595443725586,
|
| 725 |
+
"learning_rate": 1e-05,
|
| 726 |
+
"loss": 0.2253,
|
| 727 |
+
"step": 910
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 9.18,
|
| 731 |
+
"grad_norm": 3.9586544036865234,
|
| 732 |
+
"learning_rate": 8.88888888888889e-06,
|
| 733 |
+
"loss": 0.2478,
|
| 734 |
+
"step": 920
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 9.28,
|
| 738 |
+
"grad_norm": 3.8814537525177,
|
| 739 |
+
"learning_rate": 7.777777777777777e-06,
|
| 740 |
+
"loss": 0.2173,
|
| 741 |
+
"step": 930
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 9.38,
|
| 745 |
+
"grad_norm": 7.456895351409912,
|
| 746 |
+
"learning_rate": 6.666666666666667e-06,
|
| 747 |
+
"loss": 0.2315,
|
| 748 |
+
"step": 940
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 9.48,
|
| 752 |
+
"grad_norm": 4.543576717376709,
|
| 753 |
+
"learning_rate": 5.555555555555556e-06,
|
| 754 |
+
"loss": 0.2281,
|
| 755 |
+
"step": 950
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 9.58,
|
| 759 |
+
"grad_norm": 4.659777641296387,
|
| 760 |
+
"learning_rate": 4.444444444444445e-06,
|
| 761 |
+
"loss": 0.2324,
|
| 762 |
+
"step": 960
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 9.68,
|
| 766 |
+
"grad_norm": 4.048426151275635,
|
| 767 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 768 |
+
"loss": 0.2132,
|
| 769 |
+
"step": 970
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 9.78,
|
| 773 |
+
"grad_norm": 3.969958543777466,
|
| 774 |
+
"learning_rate": 2.2222222222222225e-06,
|
| 775 |
+
"loss": 0.2076,
|
| 776 |
+
"step": 980
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 9.88,
|
| 780 |
+
"grad_norm": 5.621995449066162,
|
| 781 |
+
"learning_rate": 1.1111111111111112e-06,
|
| 782 |
+
"loss": 0.2262,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 9.98,
|
| 787 |
+
"grad_norm": 4.668450355529785,
|
| 788 |
+
"learning_rate": 0.0,
|
| 789 |
+
"loss": 0.2291,
|
| 790 |
+
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 9.98,
|
| 794 |
+
"eval_accuracy": 0.894109396914446,
|
| 795 |
+
"eval_loss": 0.303189218044281,
|
| 796 |
+
"eval_runtime": 39.0907,
|
| 797 |
+
"eval_samples_per_second": 72.958,
|
| 798 |
+
"eval_steps_per_second": 1.151,
|
| 799 |
+
"step": 1000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 9.98,
|
| 803 |
+
"step": 1000,
|
| 804 |
+
"total_flos": 6.364199987970048e+18,
|
| 805 |
+
"train_loss": 0.48602974390983583,
|
| 806 |
+
"train_runtime": 5351.8475,
|
| 807 |
+
"train_samples_per_second": 47.954,
|
| 808 |
+
"train_steps_per_second": 0.187
|
| 809 |
+
}
|
| 810 |
+
],
|
| 811 |
+
"logging_steps": 10,
|
| 812 |
+
"max_steps": 1000,
|
| 813 |
+
"num_input_tokens_seen": 0,
|
| 814 |
+
"num_train_epochs": 10,
|
| 815 |
+
"save_steps": 500,
|
| 816 |
+
"total_flos": 6.364199987970048e+18,
|
| 817 |
+
"train_batch_size": 64,
|
| 818 |
+
"trial_name": null,
|
| 819 |
+
"trial_params": null
|
| 820 |
+
}
|