End of training
Browse files- all_results.json +8 -0
- runs/Apr22_14-48-26_c22c5fe5ea7f/events.out.tfevents.1682185324.c22c5fe5ea7f.11410.2 +3 -0
- test_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +796 -0
- val_results.json +8 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.89,
|
| 3 |
+
"eval_accuracy": 0.9292161520190024,
|
| 4 |
+
"eval_loss": 0.2668735980987549,
|
| 5 |
+
"eval_runtime": 60.4298,
|
| 6 |
+
"eval_samples_per_second": 34.834,
|
| 7 |
+
"eval_steps_per_second": 0.546
|
| 8 |
+
}
|
runs/Apr22_14-48-26_c22c5fe5ea7f/events.out.tfevents.1682185324.c22c5fe5ea7f.11410.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6180207a4e39a37461f98fee105eb29e0c658fd63020d75baace87ea92b9a92e
|
| 3 |
+
size 1057
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.89,
|
| 3 |
+
"eval_accuracy": 0.9292161520190024,
|
| 4 |
+
"eval_loss": 0.2668735980987549,
|
| 5 |
+
"eval_runtime": 60.4298,
|
| 6 |
+
"eval_samples_per_second": 34.834,
|
| 7 |
+
"eval_steps_per_second": 0.546
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.89,
|
| 3 |
+
"eval_accuracy": 0.9557397430584335,
|
| 4 |
+
"eval_loss": 0.16691383719444275,
|
| 5 |
+
"eval_runtime": 327.4304,
|
| 6 |
+
"eval_samples_per_second": 36.848,
|
| 7 |
+
"eval_steps_per_second": 0.577
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,796 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.934375,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finetuned-THFOOD-50/checkpoint-940",
|
| 4 |
+
"epoch": 19.894179894179896,
|
| 5 |
+
"global_step": 940,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.21,
|
| 12 |
+
"learning_rate": 5.319148936170213e-06,
|
| 13 |
+
"loss": 3.9199,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.42,
|
| 18 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 19 |
+
"loss": 3.8792,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.63,
|
| 24 |
+
"learning_rate": 1.595744680851064e-05,
|
| 25 |
+
"loss": 3.7844,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.85,
|
| 30 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 31 |
+
"loss": 3.6558,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.99,
|
| 36 |
+
"eval_accuracy": 0.28,
|
| 37 |
+
"eval_loss": 3.195585012435913,
|
| 38 |
+
"eval_runtime": 43.9765,
|
| 39 |
+
"eval_samples_per_second": 36.383,
|
| 40 |
+
"eval_steps_per_second": 0.568,
|
| 41 |
+
"step": 47
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.06,
|
| 45 |
+
"learning_rate": 2.6595744680851064e-05,
|
| 46 |
+
"loss": 3.4006,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.27,
|
| 51 |
+
"learning_rate": 3.191489361702128e-05,
|
| 52 |
+
"loss": 2.9259,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.48,
|
| 57 |
+
"learning_rate": 3.723404255319149e-05,
|
| 58 |
+
"loss": 2.4813,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.69,
|
| 63 |
+
"learning_rate": 4.2553191489361704e-05,
|
| 64 |
+
"loss": 2.0113,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.9,
|
| 69 |
+
"learning_rate": 4.787234042553192e-05,
|
| 70 |
+
"loss": 1.705,
|
| 71 |
+
"step": 90
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.99,
|
| 75 |
+
"eval_accuracy": 0.67875,
|
| 76 |
+
"eval_loss": 1.1700831651687622,
|
| 77 |
+
"eval_runtime": 42.7514,
|
| 78 |
+
"eval_samples_per_second": 37.426,
|
| 79 |
+
"eval_steps_per_second": 0.585,
|
| 80 |
+
"step": 94
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.12,
|
| 84 |
+
"learning_rate": 4.964539007092199e-05,
|
| 85 |
+
"loss": 1.4876,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.33,
|
| 90 |
+
"learning_rate": 4.905437352245863e-05,
|
| 91 |
+
"loss": 1.3025,
|
| 92 |
+
"step": 110
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.54,
|
| 96 |
+
"learning_rate": 4.846335697399527e-05,
|
| 97 |
+
"loss": 1.1542,
|
| 98 |
+
"step": 120
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.75,
|
| 102 |
+
"learning_rate": 4.787234042553192e-05,
|
| 103 |
+
"loss": 1.0516,
|
| 104 |
+
"step": 130
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.96,
|
| 108 |
+
"learning_rate": 4.728132387706856e-05,
|
| 109 |
+
"loss": 0.9805,
|
| 110 |
+
"step": 140
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.98,
|
| 114 |
+
"eval_accuracy": 0.8125,
|
| 115 |
+
"eval_loss": 0.6491796374320984,
|
| 116 |
+
"eval_runtime": 42.6164,
|
| 117 |
+
"eval_samples_per_second": 37.544,
|
| 118 |
+
"eval_steps_per_second": 0.587,
|
| 119 |
+
"step": 141
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.17,
|
| 123 |
+
"learning_rate": 4.669030732860521e-05,
|
| 124 |
+
"loss": 0.9217,
|
| 125 |
+
"step": 150
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.39,
|
| 129 |
+
"learning_rate": 4.609929078014185e-05,
|
| 130 |
+
"loss": 0.8574,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.6,
|
| 135 |
+
"learning_rate": 4.550827423167849e-05,
|
| 136 |
+
"loss": 0.7836,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.81,
|
| 141 |
+
"learning_rate": 4.491725768321513e-05,
|
| 142 |
+
"loss": 0.7925,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 4.0,
|
| 147 |
+
"eval_accuracy": 0.864375,
|
| 148 |
+
"eval_loss": 0.47244203090667725,
|
| 149 |
+
"eval_runtime": 42.4933,
|
| 150 |
+
"eval_samples_per_second": 37.653,
|
| 151 |
+
"eval_steps_per_second": 0.588,
|
| 152 |
+
"step": 189
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.02,
|
| 156 |
+
"learning_rate": 4.432624113475177e-05,
|
| 157 |
+
"loss": 0.769,
|
| 158 |
+
"step": 190
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.23,
|
| 162 |
+
"learning_rate": 4.373522458628842e-05,
|
| 163 |
+
"loss": 0.6721,
|
| 164 |
+
"step": 200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.44,
|
| 168 |
+
"learning_rate": 4.3144208037825064e-05,
|
| 169 |
+
"loss": 0.6727,
|
| 170 |
+
"step": 210
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.66,
|
| 174 |
+
"learning_rate": 4.2553191489361704e-05,
|
| 175 |
+
"loss": 0.6304,
|
| 176 |
+
"step": 220
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.87,
|
| 180 |
+
"learning_rate": 4.1962174940898345e-05,
|
| 181 |
+
"loss": 0.6169,
|
| 182 |
+
"step": 230
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.99,
|
| 186 |
+
"eval_accuracy": 0.87375,
|
| 187 |
+
"eval_loss": 0.41286996006965637,
|
| 188 |
+
"eval_runtime": 42.6335,
|
| 189 |
+
"eval_samples_per_second": 37.529,
|
| 190 |
+
"eval_steps_per_second": 0.586,
|
| 191 |
+
"step": 236
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 5.08,
|
| 195 |
+
"learning_rate": 4.1371158392434986e-05,
|
| 196 |
+
"loss": 0.5997,
|
| 197 |
+
"step": 240
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 5.29,
|
| 201 |
+
"learning_rate": 4.078014184397163e-05,
|
| 202 |
+
"loss": 0.5769,
|
| 203 |
+
"step": 250
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 5.5,
|
| 207 |
+
"learning_rate": 4.018912529550828e-05,
|
| 208 |
+
"loss": 0.5889,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.71,
|
| 213 |
+
"learning_rate": 3.959810874704492e-05,
|
| 214 |
+
"loss": 0.5698,
|
| 215 |
+
"step": 270
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 5.93,
|
| 219 |
+
"learning_rate": 3.900709219858156e-05,
|
| 220 |
+
"loss": 0.5343,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 5.99,
|
| 225 |
+
"eval_accuracy": 0.8825,
|
| 226 |
+
"eval_loss": 0.371685266494751,
|
| 227 |
+
"eval_runtime": 42.6664,
|
| 228 |
+
"eval_samples_per_second": 37.5,
|
| 229 |
+
"eval_steps_per_second": 0.586,
|
| 230 |
+
"step": 283
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 6.14,
|
| 234 |
+
"learning_rate": 3.84160756501182e-05,
|
| 235 |
+
"loss": 0.5222,
|
| 236 |
+
"step": 290
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 6.35,
|
| 240 |
+
"learning_rate": 3.782505910165485e-05,
|
| 241 |
+
"loss": 0.565,
|
| 242 |
+
"step": 300
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 6.56,
|
| 246 |
+
"learning_rate": 3.723404255319149e-05,
|
| 247 |
+
"loss": 0.5147,
|
| 248 |
+
"step": 310
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 6.77,
|
| 252 |
+
"learning_rate": 3.664302600472813e-05,
|
| 253 |
+
"loss": 0.5166,
|
| 254 |
+
"step": 320
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 6.98,
|
| 258 |
+
"learning_rate": 3.605200945626478e-05,
|
| 259 |
+
"loss": 0.5196,
|
| 260 |
+
"step": 330
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 6.98,
|
| 264 |
+
"eval_accuracy": 0.890625,
|
| 265 |
+
"eval_loss": 0.3654029965400696,
|
| 266 |
+
"eval_runtime": 41.9867,
|
| 267 |
+
"eval_samples_per_second": 38.107,
|
| 268 |
+
"eval_steps_per_second": 0.595,
|
| 269 |
+
"step": 330
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 7.2,
|
| 273 |
+
"learning_rate": 3.546099290780142e-05,
|
| 274 |
+
"loss": 0.4794,
|
| 275 |
+
"step": 340
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 7.41,
|
| 279 |
+
"learning_rate": 3.4869976359338065e-05,
|
| 280 |
+
"loss": 0.4747,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 7.62,
|
| 285 |
+
"learning_rate": 3.4278959810874706e-05,
|
| 286 |
+
"loss": 0.4549,
|
| 287 |
+
"step": 360
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 7.83,
|
| 291 |
+
"learning_rate": 3.3687943262411347e-05,
|
| 292 |
+
"loss": 0.5059,
|
| 293 |
+
"step": 370
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 8.0,
|
| 297 |
+
"eval_accuracy": 0.896875,
|
| 298 |
+
"eval_loss": 0.3267361521720886,
|
| 299 |
+
"eval_runtime": 42.9793,
|
| 300 |
+
"eval_samples_per_second": 37.227,
|
| 301 |
+
"eval_steps_per_second": 0.582,
|
| 302 |
+
"step": 378
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 8.04,
|
| 306 |
+
"learning_rate": 3.309692671394799e-05,
|
| 307 |
+
"loss": 0.4381,
|
| 308 |
+
"step": 380
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 8.25,
|
| 312 |
+
"learning_rate": 3.2505910165484634e-05,
|
| 313 |
+
"loss": 0.4277,
|
| 314 |
+
"step": 390
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 8.47,
|
| 318 |
+
"learning_rate": 3.191489361702128e-05,
|
| 319 |
+
"loss": 0.4362,
|
| 320 |
+
"step": 400
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 8.68,
|
| 324 |
+
"learning_rate": 3.132387706855792e-05,
|
| 325 |
+
"loss": 0.4095,
|
| 326 |
+
"step": 410
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 8.89,
|
| 330 |
+
"learning_rate": 3.073286052009456e-05,
|
| 331 |
+
"loss": 0.4432,
|
| 332 |
+
"step": 420
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 8.99,
|
| 336 |
+
"eval_accuracy": 0.908125,
|
| 337 |
+
"eval_loss": 0.2996412217617035,
|
| 338 |
+
"eval_runtime": 42.09,
|
| 339 |
+
"eval_samples_per_second": 38.014,
|
| 340 |
+
"eval_steps_per_second": 0.594,
|
| 341 |
+
"step": 425
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 9.1,
|
| 345 |
+
"learning_rate": 3.0141843971631207e-05,
|
| 346 |
+
"loss": 0.4369,
|
| 347 |
+
"step": 430
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 9.31,
|
| 351 |
+
"learning_rate": 2.9550827423167847e-05,
|
| 352 |
+
"loss": 0.4071,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 9.52,
|
| 357 |
+
"learning_rate": 2.895981087470449e-05,
|
| 358 |
+
"loss": 0.3956,
|
| 359 |
+
"step": 450
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 9.74,
|
| 363 |
+
"learning_rate": 2.836879432624114e-05,
|
| 364 |
+
"loss": 0.3971,
|
| 365 |
+
"step": 460
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 9.95,
|
| 369 |
+
"learning_rate": 2.777777777777778e-05,
|
| 370 |
+
"loss": 0.3819,
|
| 371 |
+
"step": 470
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 9.99,
|
| 375 |
+
"eval_accuracy": 0.90875,
|
| 376 |
+
"eval_loss": 0.30557677149772644,
|
| 377 |
+
"eval_runtime": 42.6034,
|
| 378 |
+
"eval_samples_per_second": 37.556,
|
| 379 |
+
"eval_steps_per_second": 0.587,
|
| 380 |
+
"step": 472
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 10.16,
|
| 384 |
+
"learning_rate": 2.7186761229314423e-05,
|
| 385 |
+
"loss": 0.4018,
|
| 386 |
+
"step": 480
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 10.37,
|
| 390 |
+
"learning_rate": 2.6595744680851064e-05,
|
| 391 |
+
"loss": 0.3847,
|
| 392 |
+
"step": 490
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 10.58,
|
| 396 |
+
"learning_rate": 2.6004728132387708e-05,
|
| 397 |
+
"loss": 0.3719,
|
| 398 |
+
"step": 500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 10.79,
|
| 402 |
+
"learning_rate": 2.5413711583924348e-05,
|
| 403 |
+
"loss": 0.3627,
|
| 404 |
+
"step": 510
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 10.98,
|
| 408 |
+
"eval_accuracy": 0.92125,
|
| 409 |
+
"eval_loss": 0.2795552909374237,
|
| 410 |
+
"eval_runtime": 42.2776,
|
| 411 |
+
"eval_samples_per_second": 37.845,
|
| 412 |
+
"eval_steps_per_second": 0.591,
|
| 413 |
+
"step": 519
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 11.01,
|
| 417 |
+
"learning_rate": 2.4822695035460995e-05,
|
| 418 |
+
"loss": 0.3823,
|
| 419 |
+
"step": 520
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 11.22,
|
| 423 |
+
"learning_rate": 2.4231678486997636e-05,
|
| 424 |
+
"loss": 0.3417,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 11.43,
|
| 429 |
+
"learning_rate": 2.364066193853428e-05,
|
| 430 |
+
"loss": 0.3663,
|
| 431 |
+
"step": 540
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 11.64,
|
| 435 |
+
"learning_rate": 2.3049645390070924e-05,
|
| 436 |
+
"loss": 0.3518,
|
| 437 |
+
"step": 550
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 11.85,
|
| 441 |
+
"learning_rate": 2.2458628841607564e-05,
|
| 442 |
+
"loss": 0.3505,
|
| 443 |
+
"step": 560
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 12.0,
|
| 447 |
+
"eval_accuracy": 0.915,
|
| 448 |
+
"eval_loss": 0.2753271758556366,
|
| 449 |
+
"eval_runtime": 43.0104,
|
| 450 |
+
"eval_samples_per_second": 37.2,
|
| 451 |
+
"eval_steps_per_second": 0.581,
|
| 452 |
+
"step": 567
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 12.06,
|
| 456 |
+
"learning_rate": 2.186761229314421e-05,
|
| 457 |
+
"loss": 0.3182,
|
| 458 |
+
"step": 570
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 12.28,
|
| 462 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 463 |
+
"loss": 0.3526,
|
| 464 |
+
"step": 580
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 12.49,
|
| 468 |
+
"learning_rate": 2.0685579196217493e-05,
|
| 469 |
+
"loss": 0.3441,
|
| 470 |
+
"step": 590
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 12.7,
|
| 474 |
+
"learning_rate": 2.009456264775414e-05,
|
| 475 |
+
"loss": 0.3178,
|
| 476 |
+
"step": 600
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 12.91,
|
| 480 |
+
"learning_rate": 1.950354609929078e-05,
|
| 481 |
+
"loss": 0.3224,
|
| 482 |
+
"step": 610
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 12.99,
|
| 486 |
+
"eval_accuracy": 0.920625,
|
| 487 |
+
"eval_loss": 0.28300976753234863,
|
| 488 |
+
"eval_runtime": 42.2858,
|
| 489 |
+
"eval_samples_per_second": 37.838,
|
| 490 |
+
"eval_steps_per_second": 0.591,
|
| 491 |
+
"step": 614
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 13.12,
|
| 495 |
+
"learning_rate": 1.8912529550827425e-05,
|
| 496 |
+
"loss": 0.3412,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 13.33,
|
| 501 |
+
"learning_rate": 1.8321513002364065e-05,
|
| 502 |
+
"loss": 0.3155,
|
| 503 |
+
"step": 630
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 13.54,
|
| 507 |
+
"learning_rate": 1.773049645390071e-05,
|
| 508 |
+
"loss": 0.327,
|
| 509 |
+
"step": 640
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 13.76,
|
| 513 |
+
"learning_rate": 1.7139479905437353e-05,
|
| 514 |
+
"loss": 0.3049,
|
| 515 |
+
"step": 650
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 13.97,
|
| 519 |
+
"learning_rate": 1.6548463356973994e-05,
|
| 520 |
+
"loss": 0.3206,
|
| 521 |
+
"step": 660
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 13.99,
|
| 525 |
+
"eval_accuracy": 0.923125,
|
| 526 |
+
"eval_loss": 0.2796793282032013,
|
| 527 |
+
"eval_runtime": 42.1391,
|
| 528 |
+
"eval_samples_per_second": 37.97,
|
| 529 |
+
"eval_steps_per_second": 0.593,
|
| 530 |
+
"step": 661
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 14.18,
|
| 534 |
+
"learning_rate": 1.595744680851064e-05,
|
| 535 |
+
"loss": 0.2965,
|
| 536 |
+
"step": 670
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 14.39,
|
| 540 |
+
"learning_rate": 1.536643026004728e-05,
|
| 541 |
+
"loss": 0.294,
|
| 542 |
+
"step": 680
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 14.6,
|
| 546 |
+
"learning_rate": 1.4775413711583924e-05,
|
| 547 |
+
"loss": 0.3325,
|
| 548 |
+
"step": 690
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 14.81,
|
| 552 |
+
"learning_rate": 1.418439716312057e-05,
|
| 553 |
+
"loss": 0.3141,
|
| 554 |
+
"step": 700
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 14.98,
|
| 558 |
+
"eval_accuracy": 0.92875,
|
| 559 |
+
"eval_loss": 0.2568666338920593,
|
| 560 |
+
"eval_runtime": 42.5767,
|
| 561 |
+
"eval_samples_per_second": 37.579,
|
| 562 |
+
"eval_steps_per_second": 0.587,
|
| 563 |
+
"step": 708
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 15.03,
|
| 567 |
+
"learning_rate": 1.3593380614657212e-05,
|
| 568 |
+
"loss": 0.3035,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 15.24,
|
| 573 |
+
"learning_rate": 1.3002364066193854e-05,
|
| 574 |
+
"loss": 0.2836,
|
| 575 |
+
"step": 720
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 15.45,
|
| 579 |
+
"learning_rate": 1.2411347517730498e-05,
|
| 580 |
+
"loss": 0.2892,
|
| 581 |
+
"step": 730
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 15.66,
|
| 585 |
+
"learning_rate": 1.182033096926714e-05,
|
| 586 |
+
"loss": 0.3382,
|
| 587 |
+
"step": 740
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 15.87,
|
| 591 |
+
"learning_rate": 1.1229314420803782e-05,
|
| 592 |
+
"loss": 0.2946,
|
| 593 |
+
"step": 750
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 16.0,
|
| 597 |
+
"eval_accuracy": 0.931875,
|
| 598 |
+
"eval_loss": 0.25816333293914795,
|
| 599 |
+
"eval_runtime": 42.6426,
|
| 600 |
+
"eval_samples_per_second": 37.521,
|
| 601 |
+
"eval_steps_per_second": 0.586,
|
| 602 |
+
"step": 756
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 16.08,
|
| 606 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 607 |
+
"loss": 0.279,
|
| 608 |
+
"step": 760
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 16.3,
|
| 612 |
+
"learning_rate": 1.004728132387707e-05,
|
| 613 |
+
"loss": 0.2867,
|
| 614 |
+
"step": 770
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 16.51,
|
| 618 |
+
"learning_rate": 9.456264775413712e-06,
|
| 619 |
+
"loss": 0.2787,
|
| 620 |
+
"step": 780
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 16.72,
|
| 624 |
+
"learning_rate": 8.865248226950355e-06,
|
| 625 |
+
"loss": 0.3116,
|
| 626 |
+
"step": 790
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 16.93,
|
| 630 |
+
"learning_rate": 8.274231678486997e-06,
|
| 631 |
+
"loss": 0.3008,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 16.99,
|
| 636 |
+
"eval_accuracy": 0.93375,
|
| 637 |
+
"eval_loss": 0.2583409249782562,
|
| 638 |
+
"eval_runtime": 44.0351,
|
| 639 |
+
"eval_samples_per_second": 36.335,
|
| 640 |
+
"eval_steps_per_second": 0.568,
|
| 641 |
+
"step": 803
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 17.14,
|
| 645 |
+
"learning_rate": 7.68321513002364e-06,
|
| 646 |
+
"loss": 0.2553,
|
| 647 |
+
"step": 810
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 17.35,
|
| 651 |
+
"learning_rate": 7.092198581560285e-06,
|
| 652 |
+
"loss": 0.2857,
|
| 653 |
+
"step": 820
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 17.57,
|
| 657 |
+
"learning_rate": 6.501182033096927e-06,
|
| 658 |
+
"loss": 0.2584,
|
| 659 |
+
"step": 830
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 17.78,
|
| 663 |
+
"learning_rate": 5.91016548463357e-06,
|
| 664 |
+
"loss": 0.3162,
|
| 665 |
+
"step": 840
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 17.99,
|
| 669 |
+
"learning_rate": 5.319148936170213e-06,
|
| 670 |
+
"loss": 0.2356,
|
| 671 |
+
"step": 850
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 17.99,
|
| 675 |
+
"eval_accuracy": 0.928125,
|
| 676 |
+
"eval_loss": 0.2566778063774109,
|
| 677 |
+
"eval_runtime": 43.8016,
|
| 678 |
+
"eval_samples_per_second": 36.528,
|
| 679 |
+
"eval_steps_per_second": 0.571,
|
| 680 |
+
"step": 850
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 18.2,
|
| 684 |
+
"learning_rate": 4.728132387706856e-06,
|
| 685 |
+
"loss": 0.2426,
|
| 686 |
+
"step": 860
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 18.41,
|
| 690 |
+
"learning_rate": 4.137115839243498e-06,
|
| 691 |
+
"loss": 0.2754,
|
| 692 |
+
"step": 870
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 18.62,
|
| 696 |
+
"learning_rate": 3.5460992907801423e-06,
|
| 697 |
+
"loss": 0.2581,
|
| 698 |
+
"step": 880
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 18.84,
|
| 702 |
+
"learning_rate": 2.955082742316785e-06,
|
| 703 |
+
"loss": 0.2954,
|
| 704 |
+
"step": 890
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 18.98,
|
| 708 |
+
"eval_accuracy": 0.931875,
|
| 709 |
+
"eval_loss": 0.25814077258110046,
|
| 710 |
+
"eval_runtime": 42.9843,
|
| 711 |
+
"eval_samples_per_second": 37.223,
|
| 712 |
+
"eval_steps_per_second": 0.582,
|
| 713 |
+
"step": 897
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 19.05,
|
| 717 |
+
"learning_rate": 2.364066193853428e-06,
|
| 718 |
+
"loss": 0.2766,
|
| 719 |
+
"step": 900
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 19.26,
|
| 723 |
+
"learning_rate": 1.7730496453900712e-06,
|
| 724 |
+
"loss": 0.289,
|
| 725 |
+
"step": 910
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 19.47,
|
| 729 |
+
"learning_rate": 1.182033096926714e-06,
|
| 730 |
+
"loss": 0.2598,
|
| 731 |
+
"step": 920
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 19.68,
|
| 735 |
+
"learning_rate": 5.91016548463357e-07,
|
| 736 |
+
"loss": 0.2659,
|
| 737 |
+
"step": 930
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 19.89,
|
| 741 |
+
"learning_rate": 0.0,
|
| 742 |
+
"loss": 0.2628,
|
| 743 |
+
"step": 940
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 19.89,
|
| 747 |
+
"eval_accuracy": 0.934375,
|
| 748 |
+
"eval_loss": 0.25352808833122253,
|
| 749 |
+
"eval_runtime": 43.2178,
|
| 750 |
+
"eval_samples_per_second": 37.022,
|
| 751 |
+
"eval_steps_per_second": 0.578,
|
| 752 |
+
"step": 940
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 19.89,
|
| 756 |
+
"step": 940,
|
| 757 |
+
"total_flos": 7.820350673549525e+18,
|
| 758 |
+
"train_loss": 0.7086160603989946,
|
| 759 |
+
"train_runtime": 9826.2518,
|
| 760 |
+
"train_samples_per_second": 24.557,
|
| 761 |
+
"train_steps_per_second": 0.096
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 19.89,
|
| 765 |
+
"eval_accuracy": 0.9557397430584335,
|
| 766 |
+
"eval_loss": 0.16691383719444275,
|
| 767 |
+
"eval_runtime": 327.4304,
|
| 768 |
+
"eval_samples_per_second": 36.848,
|
| 769 |
+
"eval_steps_per_second": 0.577,
|
| 770 |
+
"step": 940
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 19.89,
|
| 774 |
+
"eval_accuracy": 0.934375,
|
| 775 |
+
"eval_loss": 0.25352808833122253,
|
| 776 |
+
"eval_runtime": 44.4189,
|
| 777 |
+
"eval_samples_per_second": 36.021,
|
| 778 |
+
"eval_steps_per_second": 0.563,
|
| 779 |
+
"step": 940
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 19.89,
|
| 783 |
+
"eval_accuracy": 0.9292161520190024,
|
| 784 |
+
"eval_loss": 0.2668735980987549,
|
| 785 |
+
"eval_runtime": 60.4298,
|
| 786 |
+
"eval_samples_per_second": 34.834,
|
| 787 |
+
"eval_steps_per_second": 0.546,
|
| 788 |
+
"step": 940
|
| 789 |
+
}
|
| 790 |
+
],
|
| 791 |
+
"max_steps": 940,
|
| 792 |
+
"num_train_epochs": 20,
|
| 793 |
+
"total_flos": 7.820350673549525e+18,
|
| 794 |
+
"trial_name": null,
|
| 795 |
+
"trial_params": null
|
| 796 |
+
}
|
val_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.89,
|
| 3 |
+
"eval_accuracy": 0.934375,
|
| 4 |
+
"eval_loss": 0.25352808833122253,
|
| 5 |
+
"eval_runtime": 44.4189,
|
| 6 |
+
"eval_samples_per_second": 36.021,
|
| 7 |
+
"eval_steps_per_second": 0.563
|
| 8 |
+
}
|