Commit
·
efa59b4
1
Parent(s):
2123747
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +895 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 2.1741048878636855,
|
| 4 |
+
"train_runtime": 774.6069,
|
| 5 |
+
"train_samples": 459,
|
| 6 |
+
"train_samples_per_second": 1.185,
|
| 7 |
+
"train_steps_per_second": 0.075
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 2.1741048878636855,
|
| 4 |
+
"train_runtime": 774.6069,
|
| 5 |
+
"train_samples": 459,
|
| 6 |
+
"train_samples_per_second": 1.185,
|
| 7 |
+
"train_steps_per_second": 0.075
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,895 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 58,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 3e-05,
|
| 13 |
+
"loss": 2.6543,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"eval_accuracy": 0.05133992343294669,
|
| 19 |
+
"eval_loss": 2.611328125,
|
| 20 |
+
"eval_runtime": 4.6158,
|
| 21 |
+
"eval_samples_per_second": 18.632,
|
| 22 |
+
"eval_steps_per_second": 1.3,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07,
|
| 27 |
+
"learning_rate": 3e-05,
|
| 28 |
+
"loss": 2.6077,
|
| 29 |
+
"step": 2
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.07,
|
| 33 |
+
"eval_accuracy": 0.05133992343294669,
|
| 34 |
+
"eval_loss": 2.611328125,
|
| 35 |
+
"eval_runtime": 4.3958,
|
| 36 |
+
"eval_samples_per_second": 19.564,
|
| 37 |
+
"eval_steps_per_second": 1.365,
|
| 38 |
+
"step": 2
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"learning_rate": 2.9978001207766858e-05,
|
| 43 |
+
"loss": 2.5964,
|
| 44 |
+
"step": 3
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1,
|
| 48 |
+
"eval_accuracy": 0.05192560425118565,
|
| 49 |
+
"eval_loss": 2.560546875,
|
| 50 |
+
"eval_runtime": 4.3633,
|
| 51 |
+
"eval_samples_per_second": 19.71,
|
| 52 |
+
"eval_steps_per_second": 1.375,
|
| 53 |
+
"step": 3
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.14,
|
| 57 |
+
"learning_rate": 2.9912069357315394e-05,
|
| 58 |
+
"loss": 2.7302,
|
| 59 |
+
"step": 4
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14,
|
| 63 |
+
"eval_accuracy": 0.052668418947488714,
|
| 64 |
+
"eval_loss": 2.5234375,
|
| 65 |
+
"eval_runtime": 3.6387,
|
| 66 |
+
"eval_samples_per_second": 23.635,
|
| 67 |
+
"eval_steps_per_second": 1.649,
|
| 68 |
+
"step": 4
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.17,
|
| 72 |
+
"learning_rate": 2.9802397838122895e-05,
|
| 73 |
+
"loss": 2.7002,
|
| 74 |
+
"step": 5
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.17,
|
| 78 |
+
"eval_accuracy": 0.05286840751957031,
|
| 79 |
+
"eval_loss": 2.5078125,
|
| 80 |
+
"eval_runtime": 4.3812,
|
| 81 |
+
"eval_samples_per_second": 19.629,
|
| 82 |
+
"eval_steps_per_second": 1.369,
|
| 83 |
+
"step": 5
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.21,
|
| 87 |
+
"learning_rate": 2.96493083356513e-05,
|
| 88 |
+
"loss": 2.5674,
|
| 89 |
+
"step": 6
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.21,
|
| 93 |
+
"eval_accuracy": 0.0532683846637335,
|
| 94 |
+
"eval_loss": 2.494140625,
|
| 95 |
+
"eval_runtime": 4.3925,
|
| 96 |
+
"eval_samples_per_second": 19.579,
|
| 97 |
+
"eval_steps_per_second": 1.366,
|
| 98 |
+
"step": 6
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.24,
|
| 102 |
+
"learning_rate": 2.9453249887788343e-05,
|
| 103 |
+
"loss": 2.6399,
|
| 104 |
+
"step": 7
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.24,
|
| 108 |
+
"eval_accuracy": 0.05339694874578595,
|
| 109 |
+
"eval_loss": 2.48828125,
|
| 110 |
+
"eval_runtime": 4.3565,
|
| 111 |
+
"eval_samples_per_second": 19.741,
|
| 112 |
+
"eval_steps_per_second": 1.377,
|
| 113 |
+
"step": 7
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.28,
|
| 117 |
+
"learning_rate": 2.9214797567742036e-05,
|
| 118 |
+
"loss": 2.533,
|
| 119 |
+
"step": 8
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.28,
|
| 123 |
+
"eval_accuracy": 0.05362550711387921,
|
| 124 |
+
"eval_loss": 2.48046875,
|
| 125 |
+
"eval_runtime": 4.3451,
|
| 126 |
+
"eval_samples_per_second": 19.792,
|
| 127 |
+
"eval_steps_per_second": 1.381,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.31,
|
| 132 |
+
"learning_rate": 2.8934650797251875e-05,
|
| 133 |
+
"loss": 2.7202,
|
| 134 |
+
"step": 9
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.31,
|
| 138 |
+
"eval_accuracy": 0.05358265241986172,
|
| 139 |
+
"eval_loss": 2.474609375,
|
| 140 |
+
"eval_runtime": 4.3538,
|
| 141 |
+
"eval_samples_per_second": 19.753,
|
| 142 |
+
"eval_steps_per_second": 1.378,
|
| 143 |
+
"step": 9
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.34,
|
| 147 |
+
"learning_rate": 2.861363129506436e-05,
|
| 148 |
+
"loss": 2.5137,
|
| 149 |
+
"step": 10
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.34,
|
| 153 |
+
"eval_accuracy": 0.0533683789497743,
|
| 154 |
+
"eval_loss": 2.46484375,
|
| 155 |
+
"eval_runtime": 4.2706,
|
| 156 |
+
"eval_samples_per_second": 20.138,
|
| 157 |
+
"eval_steps_per_second": 1.405,
|
| 158 |
+
"step": 10
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.38,
|
| 162 |
+
"learning_rate": 2.8252680666690346e-05,
|
| 163 |
+
"loss": 2.499,
|
| 164 |
+
"step": 11
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.38,
|
| 168 |
+
"eval_accuracy": 0.053554082623850065,
|
| 169 |
+
"eval_loss": 2.451171875,
|
| 170 |
+
"eval_runtime": 3.643,
|
| 171 |
+
"eval_samples_per_second": 23.607,
|
| 172 |
+
"eval_steps_per_second": 1.647,
|
| 173 |
+
"step": 11
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.41,
|
| 177 |
+
"learning_rate": 2.7852857642513838e-05,
|
| 178 |
+
"loss": 2.7026,
|
| 179 |
+
"step": 12
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.41,
|
| 183 |
+
"eval_accuracy": 0.05393977487000743,
|
| 184 |
+
"eval_loss": 2.44140625,
|
| 185 |
+
"eval_runtime": 4.3592,
|
| 186 |
+
"eval_samples_per_second": 19.729,
|
| 187 |
+
"eval_steps_per_second": 1.376,
|
| 188 |
+
"step": 12
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.45,
|
| 192 |
+
"learning_rate": 2.741533497235336e-05,
|
| 193 |
+
"loss": 2.5254,
|
| 194 |
+
"step": 13
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.45,
|
| 198 |
+
"eval_accuracy": 0.05431118221815896,
|
| 199 |
+
"eval_loss": 2.43359375,
|
| 200 |
+
"eval_runtime": 4.3496,
|
| 201 |
+
"eval_samples_per_second": 19.772,
|
| 202 |
+
"eval_steps_per_second": 1.379,
|
| 203 |
+
"step": 13
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.48,
|
| 207 |
+
"learning_rate": 2.6941395985584656e-05,
|
| 208 |
+
"loss": 2.5667,
|
| 209 |
+
"step": 14
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.48,
|
| 213 |
+
"eval_accuracy": 0.05453974058625222,
|
| 214 |
+
"eval_loss": 2.423828125,
|
| 215 |
+
"eval_runtime": 3.9428,
|
| 216 |
+
"eval_samples_per_second": 21.812,
|
| 217 |
+
"eval_steps_per_second": 1.522,
|
| 218 |
+
"step": 14
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.52,
|
| 222 |
+
"learning_rate": 2.643243082691455e-05,
|
| 223 |
+
"loss": 2.5715,
|
| 224 |
+
"step": 15
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.52,
|
| 228 |
+
"eval_accuracy": 0.054768298954345464,
|
| 229 |
+
"eval_loss": 2.416015625,
|
| 230 |
+
"eval_runtime": 4.3566,
|
| 231 |
+
"eval_samples_per_second": 19.74,
|
| 232 |
+
"eval_steps_per_second": 1.377,
|
| 233 |
+
"step": 15
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.55,
|
| 237 |
+
"learning_rate": 2.5889932378846963e-05,
|
| 238 |
+
"loss": 2.3739,
|
| 239 |
+
"step": 16
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.55,
|
| 243 |
+
"eval_accuracy": 0.05499685732243872,
|
| 244 |
+
"eval_loss": 2.41015625,
|
| 245 |
+
"eval_runtime": 3.9638,
|
| 246 |
+
"eval_samples_per_second": 21.696,
|
| 247 |
+
"eval_steps_per_second": 1.514,
|
| 248 |
+
"step": 16
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.59,
|
| 252 |
+
"learning_rate": 2.531549188280135e-05,
|
| 253 |
+
"loss": 2.4756,
|
| 254 |
+
"step": 17
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.59,
|
| 258 |
+
"eval_accuracy": 0.054896863036397923,
|
| 259 |
+
"eval_loss": 2.404296875,
|
| 260 |
+
"eval_runtime": 3.6572,
|
| 261 |
+
"eval_samples_per_second": 23.515,
|
| 262 |
+
"eval_steps_per_second": 1.641,
|
| 263 |
+
"step": 17
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.62,
|
| 267 |
+
"learning_rate": 2.4710794271727415e-05,
|
| 268 |
+
"loss": 2.4783,
|
| 269 |
+
"step": 18
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.62,
|
| 273 |
+
"eval_accuracy": 0.05496828752642706,
|
| 274 |
+
"eval_loss": 2.3984375,
|
| 275 |
+
"eval_runtime": 4.3549,
|
| 276 |
+
"eval_samples_per_second": 19.748,
|
| 277 |
+
"eval_steps_per_second": 1.378,
|
| 278 |
+
"step": 18
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.66,
|
| 282 |
+
"learning_rate": 2.407761322790648e-05,
|
| 283 |
+
"loss": 2.5665,
|
| 284 |
+
"step": 19
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.66,
|
| 288 |
+
"eval_accuracy": 0.05488257813839209,
|
| 289 |
+
"eval_loss": 2.390625,
|
| 290 |
+
"eval_runtime": 4.3461,
|
| 291 |
+
"eval_samples_per_second": 19.788,
|
| 292 |
+
"eval_steps_per_second": 1.381,
|
| 293 |
+
"step": 19
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.69,
|
| 297 |
+
"learning_rate": 2.407761322790648e-05,
|
| 298 |
+
"loss": 2.4888,
|
| 299 |
+
"step": 20
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.69,
|
| 303 |
+
"eval_accuracy": 0.05488257813839209,
|
| 304 |
+
"eval_loss": 2.390625,
|
| 305 |
+
"eval_runtime": 4.3835,
|
| 306 |
+
"eval_samples_per_second": 19.619,
|
| 307 |
+
"eval_steps_per_second": 1.369,
|
| 308 |
+
"step": 20
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.72,
|
| 312 |
+
"learning_rate": 2.341780598043574e-05,
|
| 313 |
+
"loss": 2.4476,
|
| 314 |
+
"step": 21
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.72,
|
| 318 |
+
"eval_accuracy": 0.05499685732243872,
|
| 319 |
+
"eval_loss": 2.3828125,
|
| 320 |
+
"eval_runtime": 4.2591,
|
| 321 |
+
"eval_samples_per_second": 20.192,
|
| 322 |
+
"eval_steps_per_second": 1.409,
|
| 323 |
+
"step": 21
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.76,
|
| 327 |
+
"learning_rate": 2.2733307857655327e-05,
|
| 328 |
+
"loss": 2.604,
|
| 329 |
+
"step": 22
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.76,
|
| 333 |
+
"eval_accuracy": 0.05521113079252614,
|
| 334 |
+
"eval_loss": 2.375,
|
| 335 |
+
"eval_runtime": 4.354,
|
| 336 |
+
"eval_samples_per_second": 19.752,
|
| 337 |
+
"eval_steps_per_second": 1.378,
|
| 338 |
+
"step": 22
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.79,
|
| 342 |
+
"learning_rate": 2.2026126610496852e-05,
|
| 343 |
+
"loss": 2.3416,
|
| 344 |
+
"step": 23
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.79,
|
| 348 |
+
"eval_accuracy": 0.05539683446660191,
|
| 349 |
+
"eval_loss": 2.365234375,
|
| 350 |
+
"eval_runtime": 4.3608,
|
| 351 |
+
"eval_samples_per_second": 19.721,
|
| 352 |
+
"eval_steps_per_second": 1.376,
|
| 353 |
+
"step": 23
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.83,
|
| 357 |
+
"learning_rate": 2.129833652340397e-05,
|
| 358 |
+
"loss": 2.6028,
|
| 359 |
+
"step": 24
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.83,
|
| 363 |
+
"eval_accuracy": 0.05546825895663105,
|
| 364 |
+
"eval_loss": 2.35546875,
|
| 365 |
+
"eval_runtime": 4.354,
|
| 366 |
+
"eval_samples_per_second": 19.752,
|
| 367 |
+
"eval_steps_per_second": 1.378,
|
| 368 |
+
"step": 24
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.86,
|
| 372 |
+
"learning_rate": 2.055207233009872e-05,
|
| 373 |
+
"loss": 2.3425,
|
| 374 |
+
"step": 25
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.86,
|
| 378 |
+
"eval_accuracy": 0.055753956916747616,
|
| 379 |
+
"eval_loss": 2.34765625,
|
| 380 |
+
"eval_runtime": 3.9522,
|
| 381 |
+
"eval_samples_per_second": 21.76,
|
| 382 |
+
"eval_steps_per_second": 1.518,
|
| 383 |
+
"step": 25
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.9,
|
| 387 |
+
"learning_rate": 1.9789522952039697e-05,
|
| 388 |
+
"loss": 2.4142,
|
| 389 |
+
"step": 26
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.9,
|
| 393 |
+
"eval_accuracy": 0.055811096508770926,
|
| 394 |
+
"eval_loss": 2.33984375,
|
| 395 |
+
"eval_runtime": 4.3577,
|
| 396 |
+
"eval_samples_per_second": 19.735,
|
| 397 |
+
"eval_steps_per_second": 1.377,
|
| 398 |
+
"step": 26
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.93,
|
| 402 |
+
"learning_rate": 1.9012925077938318e-05,
|
| 403 |
+
"loss": 2.5317,
|
| 404 |
+
"step": 27
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.93,
|
| 408 |
+
"eval_accuracy": 0.05592537569281755,
|
| 409 |
+
"eval_loss": 2.333984375,
|
| 410 |
+
"eval_runtime": 3.95,
|
| 411 |
+
"eval_samples_per_second": 21.772,
|
| 412 |
+
"eval_steps_per_second": 1.519,
|
| 413 |
+
"step": 27
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.97,
|
| 417 |
+
"learning_rate": 1.8224556603165363e-05,
|
| 418 |
+
"loss": 2.4119,
|
| 419 |
+
"step": 28
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.97,
|
| 423 |
+
"eval_accuracy": 0.05612536426489915,
|
| 424 |
+
"eval_loss": 2.330078125,
|
| 425 |
+
"eval_runtime": 3.959,
|
| 426 |
+
"eval_samples_per_second": 21.723,
|
| 427 |
+
"eval_steps_per_second": 1.516,
|
| 428 |
+
"step": 28
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.0,
|
| 432 |
+
"learning_rate": 1.7426729948291474e-05,
|
| 433 |
+
"loss": 2.4048,
|
| 434 |
+
"step": 29
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.0,
|
| 438 |
+
"eval_accuracy": 0.0562539283469516,
|
| 439 |
+
"eval_loss": 2.326171875,
|
| 440 |
+
"eval_runtime": 4.3642,
|
| 441 |
+
"eval_samples_per_second": 19.706,
|
| 442 |
+
"eval_steps_per_second": 1.375,
|
| 443 |
+
"step": 29
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.03,
|
| 447 |
+
"learning_rate": 1.662178527635913e-05,
|
| 448 |
+
"loss": 1.9646,
|
| 449 |
+
"step": 30
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.03,
|
| 453 |
+
"eval_accuracy": 0.0563539226329924,
|
| 454 |
+
"eval_loss": 2.32421875,
|
| 455 |
+
"eval_runtime": 4.3686,
|
| 456 |
+
"eval_samples_per_second": 19.686,
|
| 457 |
+
"eval_steps_per_second": 1.373,
|
| 458 |
+
"step": 30
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.07,
|
| 462 |
+
"learning_rate": 1.5812083628781265e-05,
|
| 463 |
+
"loss": 1.9233,
|
| 464 |
+
"step": 31
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.07,
|
| 468 |
+
"eval_accuracy": 0.056296783040969085,
|
| 469 |
+
"eval_loss": 2.3203125,
|
| 470 |
+
"eval_runtime": 4.3634,
|
| 471 |
+
"eval_samples_per_second": 19.709,
|
| 472 |
+
"eval_steps_per_second": 1.375,
|
| 473 |
+
"step": 31
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.1,
|
| 477 |
+
"learning_rate": 1.5e-05,
|
| 478 |
+
"loss": 1.9276,
|
| 479 |
+
"step": 32
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.1,
|
| 483 |
+
"eval_accuracy": 0.0563539226329924,
|
| 484 |
+
"eval_loss": 2.3203125,
|
| 485 |
+
"eval_runtime": 3.6556,
|
| 486 |
+
"eval_samples_per_second": 23.526,
|
| 487 |
+
"eval_steps_per_second": 1.641,
|
| 488 |
+
"step": 32
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.14,
|
| 492 |
+
"learning_rate": 1.4187916371218739e-05,
|
| 493 |
+
"loss": 1.8702,
|
| 494 |
+
"step": 33
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.14,
|
| 498 |
+
"eval_accuracy": 0.05649677161305068,
|
| 499 |
+
"eval_loss": 2.328125,
|
| 500 |
+
"eval_runtime": 3.6562,
|
| 501 |
+
"eval_samples_per_second": 23.522,
|
| 502 |
+
"eval_steps_per_second": 1.641,
|
| 503 |
+
"step": 33
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.17,
|
| 507 |
+
"learning_rate": 1.3378214723640877e-05,
|
| 508 |
+
"loss": 2.0997,
|
| 509 |
+
"step": 34
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.17,
|
| 513 |
+
"eval_accuracy": 0.05649677161305068,
|
| 514 |
+
"eval_loss": 2.333984375,
|
| 515 |
+
"eval_runtime": 3.9689,
|
| 516 |
+
"eval_samples_per_second": 21.668,
|
| 517 |
+
"eval_steps_per_second": 1.512,
|
| 518 |
+
"step": 34
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.21,
|
| 522 |
+
"learning_rate": 1.2573270051708529e-05,
|
| 523 |
+
"loss": 1.7943,
|
| 524 |
+
"step": 35
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.21,
|
| 528 |
+
"eval_accuracy": 0.05676818467516142,
|
| 529 |
+
"eval_loss": 2.33203125,
|
| 530 |
+
"eval_runtime": 4.3641,
|
| 531 |
+
"eval_samples_per_second": 19.706,
|
| 532 |
+
"eval_steps_per_second": 1.375,
|
| 533 |
+
"step": 35
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.24,
|
| 537 |
+
"learning_rate": 1.177544339683464e-05,
|
| 538 |
+
"loss": 1.8579,
|
| 539 |
+
"step": 36
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.24,
|
| 543 |
+
"eval_accuracy": 0.056668190389120625,
|
| 544 |
+
"eval_loss": 2.32421875,
|
| 545 |
+
"eval_runtime": 3.3714,
|
| 546 |
+
"eval_samples_per_second": 25.509,
|
| 547 |
+
"eval_steps_per_second": 1.78,
|
| 548 |
+
"step": 36
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.28,
|
| 552 |
+
"learning_rate": 1.098707492206169e-05,
|
| 553 |
+
"loss": 1.8844,
|
| 554 |
+
"step": 37
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.28,
|
| 558 |
+
"eval_accuracy": 0.05676818467516142,
|
| 559 |
+
"eval_loss": 2.314453125,
|
| 560 |
+
"eval_runtime": 4.3578,
|
| 561 |
+
"eval_samples_per_second": 19.735,
|
| 562 |
+
"eval_steps_per_second": 1.377,
|
| 563 |
+
"step": 37
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.31,
|
| 567 |
+
"learning_rate": 1.0210477047960303e-05,
|
| 568 |
+
"loss": 1.9288,
|
| 569 |
+
"step": 38
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.31,
|
| 573 |
+
"eval_accuracy": 0.05689674875721387,
|
| 574 |
+
"eval_loss": 2.30859375,
|
| 575 |
+
"eval_runtime": 3.3527,
|
| 576 |
+
"eval_samples_per_second": 25.651,
|
| 577 |
+
"eval_steps_per_second": 1.79,
|
| 578 |
+
"step": 38
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.34,
|
| 582 |
+
"learning_rate": 9.447927669901284e-06,
|
| 583 |
+
"loss": 1.6616,
|
| 584 |
+
"step": 39
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.34,
|
| 588 |
+
"eval_accuracy": 0.057025312839266325,
|
| 589 |
+
"eval_loss": 2.3046875,
|
| 590 |
+
"eval_runtime": 4.3576,
|
| 591 |
+
"eval_samples_per_second": 19.736,
|
| 592 |
+
"eval_steps_per_second": 1.377,
|
| 593 |
+
"step": 39
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.38,
|
| 597 |
+
"learning_rate": 8.701663476596031e-06,
|
| 598 |
+
"loss": 1.6443,
|
| 599 |
+
"step": 40
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.38,
|
| 603 |
+
"eval_accuracy": 0.05705388263527798,
|
| 604 |
+
"eval_loss": 2.3046875,
|
| 605 |
+
"eval_runtime": 4.3425,
|
| 606 |
+
"eval_samples_per_second": 19.804,
|
| 607 |
+
"eval_steps_per_second": 1.382,
|
| 608 |
+
"step": 40
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.41,
|
| 612 |
+
"learning_rate": 7.97387338950315e-06,
|
| 613 |
+
"loss": 1.7616,
|
| 614 |
+
"step": 41
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.41,
|
| 618 |
+
"eval_accuracy": 0.057182446717330436,
|
| 619 |
+
"eval_loss": 2.302734375,
|
| 620 |
+
"eval_runtime": 4.3701,
|
| 621 |
+
"eval_samples_per_second": 19.679,
|
| 622 |
+
"eval_steps_per_second": 1.373,
|
| 623 |
+
"step": 41
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.45,
|
| 627 |
+
"learning_rate": 7.266692142344673e-06,
|
| 628 |
+
"loss": 1.7904,
|
| 629 |
+
"step": 42
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.45,
|
| 633 |
+
"eval_accuracy": 0.0571110222273013,
|
| 634 |
+
"eval_loss": 2.302734375,
|
| 635 |
+
"eval_runtime": 3.9729,
|
| 636 |
+
"eval_samples_per_second": 21.647,
|
| 637 |
+
"eval_steps_per_second": 1.51,
|
| 638 |
+
"step": 42
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.48,
|
| 642 |
+
"learning_rate": 6.582194019564266e-06,
|
| 643 |
+
"loss": 1.8762,
|
| 644 |
+
"step": 43
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.48,
|
| 648 |
+
"eval_accuracy": 0.05729672590137706,
|
| 649 |
+
"eval_loss": 2.302734375,
|
| 650 |
+
"eval_runtime": 4.3645,
|
| 651 |
+
"eval_samples_per_second": 19.704,
|
| 652 |
+
"eval_steps_per_second": 1.375,
|
| 653 |
+
"step": 43
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.52,
|
| 657 |
+
"learning_rate": 5.922386772093526e-06,
|
| 658 |
+
"loss": 1.6569,
|
| 659 |
+
"step": 44
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.52,
|
| 663 |
+
"eval_accuracy": 0.05725387120735958,
|
| 664 |
+
"eval_loss": 2.302734375,
|
| 665 |
+
"eval_runtime": 4.4596,
|
| 666 |
+
"eval_samples_per_second": 19.284,
|
| 667 |
+
"eval_steps_per_second": 1.345,
|
| 668 |
+
"step": 44
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.55,
|
| 672 |
+
"learning_rate": 5.289205728272587e-06,
|
| 673 |
+
"loss": 1.647,
|
| 674 |
+
"step": 45
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.55,
|
| 678 |
+
"eval_accuracy": 0.05733958059539455,
|
| 679 |
+
"eval_loss": 2.302734375,
|
| 680 |
+
"eval_runtime": 4.3534,
|
| 681 |
+
"eval_samples_per_second": 19.755,
|
| 682 |
+
"eval_steps_per_second": 1.378,
|
| 683 |
+
"step": 45
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.59,
|
| 687 |
+
"learning_rate": 4.684508117198649e-06,
|
| 688 |
+
"loss": 1.8168,
|
| 689 |
+
"step": 46
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.59,
|
| 693 |
+
"eval_accuracy": 0.057425289983429516,
|
| 694 |
+
"eval_loss": 2.302734375,
|
| 695 |
+
"eval_runtime": 3.9668,
|
| 696 |
+
"eval_samples_per_second": 21.68,
|
| 697 |
+
"eval_steps_per_second": 1.513,
|
| 698 |
+
"step": 46
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.62,
|
| 702 |
+
"learning_rate": 4.110067621153041e-06,
|
| 703 |
+
"loss": 1.7194,
|
| 704 |
+
"step": 47
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.62,
|
| 708 |
+
"eval_accuracy": 0.057311010799382896,
|
| 709 |
+
"eval_loss": 2.302734375,
|
| 710 |
+
"eval_runtime": 4.3648,
|
| 711 |
+
"eval_samples_per_second": 19.703,
|
| 712 |
+
"eval_steps_per_second": 1.375,
|
| 713 |
+
"step": 47
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.66,
|
| 717 |
+
"learning_rate": 3.567569173085455e-06,
|
| 718 |
+
"loss": 1.7667,
|
| 719 |
+
"step": 48
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.66,
|
| 723 |
+
"eval_accuracy": 0.05722530141134792,
|
| 724 |
+
"eval_loss": 2.302734375,
|
| 725 |
+
"eval_runtime": 4.3629,
|
| 726 |
+
"eval_samples_per_second": 19.712,
|
| 727 |
+
"eval_steps_per_second": 1.375,
|
| 728 |
+
"step": 48
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.69,
|
| 732 |
+
"learning_rate": 3.0586040144153436e-06,
|
| 733 |
+
"loss": 1.7621,
|
| 734 |
+
"step": 49
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.69,
|
| 738 |
+
"eval_accuracy": 0.05729672590137706,
|
| 739 |
+
"eval_loss": 2.302734375,
|
| 740 |
+
"eval_runtime": 4.3603,
|
| 741 |
+
"eval_samples_per_second": 19.723,
|
| 742 |
+
"eval_steps_per_second": 1.376,
|
| 743 |
+
"step": 49
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.72,
|
| 747 |
+
"learning_rate": 2.5846650276466435e-06,
|
| 748 |
+
"loss": 1.7269,
|
| 749 |
+
"step": 50
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.72,
|
| 753 |
+
"eval_accuracy": 0.05733958059539455,
|
| 754 |
+
"eval_loss": 2.30078125,
|
| 755 |
+
"eval_runtime": 3.6679,
|
| 756 |
+
"eval_samples_per_second": 23.447,
|
| 757 |
+
"eval_steps_per_second": 1.636,
|
| 758 |
+
"step": 50
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.76,
|
| 762 |
+
"learning_rate": 2.1471423574861643e-06,
|
| 763 |
+
"loss": 1.7815,
|
| 764 |
+
"step": 51
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.76,
|
| 768 |
+
"eval_accuracy": 0.057396720187417864,
|
| 769 |
+
"eval_loss": 2.30078125,
|
| 770 |
+
"eval_runtime": 4.3528,
|
| 771 |
+
"eval_samples_per_second": 19.757,
|
| 772 |
+
"eval_steps_per_second": 1.378,
|
| 773 |
+
"step": 51
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.79,
|
| 777 |
+
"learning_rate": 1.7473193333096576e-06,
|
| 778 |
+
"loss": 1.8318,
|
| 779 |
+
"step": 52
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.79,
|
| 783 |
+
"eval_accuracy": 0.057396720187417864,
|
| 784 |
+
"eval_loss": 2.298828125,
|
| 785 |
+
"eval_runtime": 4.3561,
|
| 786 |
+
"eval_samples_per_second": 19.743,
|
| 787 |
+
"eval_steps_per_second": 1.377,
|
| 788 |
+
"step": 52
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.83,
|
| 792 |
+
"learning_rate": 1.3863687049356465e-06,
|
| 793 |
+
"loss": 1.9366,
|
| 794 |
+
"step": 53
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.83,
|
| 798 |
+
"eval_accuracy": 0.057468144677447,
|
| 799 |
+
"eval_loss": 2.298828125,
|
| 800 |
+
"eval_runtime": 4.3614,
|
| 801 |
+
"eval_samples_per_second": 19.719,
|
| 802 |
+
"eval_steps_per_second": 1.376,
|
| 803 |
+
"step": 53
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.86,
|
| 807 |
+
"learning_rate": 1.0653492027481287e-06,
|
| 808 |
+
"loss": 1.736,
|
| 809 |
+
"step": 54
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.86,
|
| 813 |
+
"eval_accuracy": 0.057553854065481976,
|
| 814 |
+
"eval_loss": 2.296875,
|
| 815 |
+
"eval_runtime": 4.3622,
|
| 816 |
+
"eval_samples_per_second": 19.715,
|
| 817 |
+
"eval_steps_per_second": 1.375,
|
| 818 |
+
"step": 54
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.9,
|
| 822 |
+
"learning_rate": 7.852024322579649e-07,
|
| 823 |
+
"loss": 1.9984,
|
| 824 |
+
"step": 55
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.9,
|
| 828 |
+
"eval_accuracy": 0.05753956916747614,
|
| 829 |
+
"eval_loss": 2.296875,
|
| 830 |
+
"eval_runtime": 4.3417,
|
| 831 |
+
"eval_samples_per_second": 19.808,
|
| 832 |
+
"eval_steps_per_second": 1.382,
|
| 833 |
+
"step": 55
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.93,
|
| 837 |
+
"learning_rate": 5.467501122116564e-07,
|
| 838 |
+
"loss": 1.7203,
|
| 839 |
+
"step": 56
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.93,
|
| 843 |
+
"eval_accuracy": 0.05753956916747614,
|
| 844 |
+
"eval_loss": 2.294921875,
|
| 845 |
+
"eval_runtime": 3.6633,
|
| 846 |
+
"eval_samples_per_second": 23.476,
|
| 847 |
+
"eval_steps_per_second": 1.638,
|
| 848 |
+
"step": 56
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 1.97,
|
| 852 |
+
"learning_rate": 3.5069166434870014e-07,
|
| 853 |
+
"loss": 1.7391,
|
| 854 |
+
"step": 57
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.97,
|
| 858 |
+
"eval_accuracy": 0.0575681389634878,
|
| 859 |
+
"eval_loss": 2.294921875,
|
| 860 |
+
"eval_runtime": 4.3729,
|
| 861 |
+
"eval_samples_per_second": 19.667,
|
| 862 |
+
"eval_steps_per_second": 1.372,
|
| 863 |
+
"step": 57
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.0,
|
| 867 |
+
"learning_rate": 1.9760216187710788e-07,
|
| 868 |
+
"loss": 1.6611,
|
| 869 |
+
"step": 58
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 2.0,
|
| 873 |
+
"eval_accuracy": 0.057553854065481976,
|
| 874 |
+
"eval_loss": 2.294921875,
|
| 875 |
+
"eval_runtime": 3.3519,
|
| 876 |
+
"eval_samples_per_second": 25.657,
|
| 877 |
+
"eval_steps_per_second": 1.79,
|
| 878 |
+
"step": 58
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.0,
|
| 882 |
+
"step": 58,
|
| 883 |
+
"total_flos": 3170519875584.0,
|
| 884 |
+
"train_loss": 2.1741048878636855,
|
| 885 |
+
"train_runtime": 774.6069,
|
| 886 |
+
"train_samples_per_second": 1.185,
|
| 887 |
+
"train_steps_per_second": 0.075
|
| 888 |
+
}
|
| 889 |
+
],
|
| 890 |
+
"max_steps": 58,
|
| 891 |
+
"num_train_epochs": 2,
|
| 892 |
+
"total_flos": 3170519875584.0,
|
| 893 |
+
"trial_name": null,
|
| 894 |
+
"trial_params": null
|
| 895 |
+
}
|