Commit
•
58cfb64
1
Parent(s):
c32b21b
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +880 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.9830793414199561,
|
| 4 |
+
"train_runtime": 617.3135,
|
| 5 |
+
"train_samples": 303,
|
| 6 |
+
"train_samples_per_second": 1.473,
|
| 7 |
+
"train_steps_per_second": 0.092
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.9830793414199561,
|
| 4 |
+
"train_runtime": 617.3135,
|
| 5 |
+
"train_samples": 303,
|
| 6 |
+
"train_samples_per_second": 1.473,
|
| 7 |
+
"train_steps_per_second": 0.092
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,880 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 57,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 3e-05,
|
| 13 |
+
"loss": 2.6941,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"eval_accuracy": 0.062219502243982046,
|
| 19 |
+
"eval_loss": 2.654296875,
|
| 20 |
+
"eval_runtime": 3.1639,
|
| 21 |
+
"eval_samples_per_second": 18.016,
|
| 22 |
+
"eval_steps_per_second": 1.264,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.11,
|
| 27 |
+
"learning_rate": 3e-05,
|
| 28 |
+
"loss": 2.6914,
|
| 29 |
+
"step": 2
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.11,
|
| 33 |
+
"eval_accuracy": 0.062219502243982046,
|
| 34 |
+
"eval_loss": 2.654296875,
|
| 35 |
+
"eval_runtime": 3.1507,
|
| 36 |
+
"eval_samples_per_second": 18.091,
|
| 37 |
+
"eval_steps_per_second": 1.27,
|
| 38 |
+
"step": 2
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.16,
|
| 42 |
+
"learning_rate": 2.997722274649974e-05,
|
| 43 |
+
"loss": 2.6003,
|
| 44 |
+
"step": 3
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.16,
|
| 48 |
+
"eval_accuracy": 0.06265016546534294,
|
| 49 |
+
"eval_loss": 2.6015625,
|
| 50 |
+
"eval_runtime": 3.124,
|
| 51 |
+
"eval_samples_per_second": 18.246,
|
| 52 |
+
"eval_steps_per_second": 1.28,
|
| 53 |
+
"step": 3
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.21,
|
| 57 |
+
"learning_rate": 2.9908960159769243e-05,
|
| 58 |
+
"loss": 2.5603,
|
| 59 |
+
"step": 4
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.21,
|
| 63 |
+
"eval_accuracy": 0.06265016546534294,
|
| 64 |
+
"eval_loss": 2.5703125,
|
| 65 |
+
"eval_runtime": 3.1396,
|
| 66 |
+
"eval_samples_per_second": 18.155,
|
| 67 |
+
"eval_steps_per_second": 1.274,
|
| 68 |
+
"step": 4
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.26,
|
| 72 |
+
"learning_rate": 2.9795419551040836e-05,
|
| 73 |
+
"loss": 2.6072,
|
| 74 |
+
"step": 5
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.26,
|
| 78 |
+
"eval_accuracy": 0.06296749626002993,
|
| 79 |
+
"eval_loss": 2.55078125,
|
| 80 |
+
"eval_runtime": 2.3207,
|
| 81 |
+
"eval_samples_per_second": 24.561,
|
| 82 |
+
"eval_steps_per_second": 1.724,
|
| 83 |
+
"step": 5
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.32,
|
| 87 |
+
"learning_rate": 2.9636945739411533e-05,
|
| 88 |
+
"loss": 2.5444,
|
| 89 |
+
"step": 6
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.32,
|
| 93 |
+
"eval_accuracy": 0.06283149734802121,
|
| 94 |
+
"eval_loss": 2.546875,
|
| 95 |
+
"eval_runtime": 3.1226,
|
| 96 |
+
"eval_samples_per_second": 18.254,
|
| 97 |
+
"eval_steps_per_second": 1.281,
|
| 98 |
+
"step": 6
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.37,
|
| 102 |
+
"learning_rate": 2.9434020004638757e-05,
|
| 103 |
+
"loss": 2.4467,
|
| 104 |
+
"step": 7
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.37,
|
| 108 |
+
"eval_accuracy": 0.06292216328936036,
|
| 109 |
+
"eval_loss": 2.55078125,
|
| 110 |
+
"eval_runtime": 2.1195,
|
| 111 |
+
"eval_samples_per_second": 26.894,
|
| 112 |
+
"eval_steps_per_second": 1.887,
|
| 113 |
+
"step": 7
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.42,
|
| 117 |
+
"learning_rate": 2.9187258625509518e-05,
|
| 118 |
+
"loss": 2.5452,
|
| 119 |
+
"step": 8
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.42,
|
| 123 |
+
"eval_accuracy": 0.06287683031869079,
|
| 124 |
+
"eval_loss": 2.55078125,
|
| 125 |
+
"eval_runtime": 2.717,
|
| 126 |
+
"eval_samples_per_second": 20.979,
|
| 127 |
+
"eval_steps_per_second": 1.472,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.47,
|
| 132 |
+
"learning_rate": 2.8897411008222026e-05,
|
| 133 |
+
"loss": 2.6128,
|
| 134 |
+
"step": 9
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.47,
|
| 138 |
+
"eval_accuracy": 0.06308082868670384,
|
| 139 |
+
"eval_loss": 2.544921875,
|
| 140 |
+
"eval_runtime": 2.9144,
|
| 141 |
+
"eval_samples_per_second": 19.558,
|
| 142 |
+
"eval_steps_per_second": 1.372,
|
| 143 |
+
"step": 9
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.53,
|
| 147 |
+
"learning_rate": 2.8565357410463664e-05,
|
| 148 |
+
"loss": 2.4568,
|
| 149 |
+
"step": 10
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.53,
|
| 153 |
+
"eval_accuracy": 0.06265016546534294,
|
| 154 |
+
"eval_loss": 2.5390625,
|
| 155 |
+
"eval_runtime": 3.1199,
|
| 156 |
+
"eval_samples_per_second": 18.27,
|
| 157 |
+
"eval_steps_per_second": 1.282,
|
| 158 |
+
"step": 10
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.58,
|
| 162 |
+
"learning_rate": 2.8192106268097336e-05,
|
| 163 |
+
"loss": 2.5098,
|
| 164 |
+
"step": 11
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.58,
|
| 168 |
+
"eval_accuracy": 0.06278616437735164,
|
| 169 |
+
"eval_loss": 2.53515625,
|
| 170 |
+
"eval_runtime": 3.1268,
|
| 171 |
+
"eval_samples_per_second": 18.23,
|
| 172 |
+
"eval_steps_per_second": 1.279,
|
| 173 |
+
"step": 11
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.63,
|
| 177 |
+
"learning_rate": 2.7778791132574908e-05,
|
| 178 |
+
"loss": 2.6047,
|
| 179 |
+
"step": 12
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.63,
|
| 183 |
+
"eval_accuracy": 0.0631261616573734,
|
| 184 |
+
"eval_loss": 2.5234375,
|
| 185 |
+
"eval_runtime": 3.1183,
|
| 186 |
+
"eval_samples_per_second": 18.279,
|
| 187 |
+
"eval_steps_per_second": 1.283,
|
| 188 |
+
"step": 12
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.68,
|
| 192 |
+
"learning_rate": 2.7326667228378677e-05,
|
| 193 |
+
"loss": 2.5022,
|
| 194 |
+
"step": 13
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.68,
|
| 198 |
+
"eval_accuracy": 0.0630128292306995,
|
| 199 |
+
"eval_loss": 2.515625,
|
| 200 |
+
"eval_runtime": 2.5192,
|
| 201 |
+
"eval_samples_per_second": 22.626,
|
| 202 |
+
"eval_steps_per_second": 1.588,
|
| 203 |
+
"step": 13
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.74,
|
| 207 |
+
"learning_rate": 2.6837107640945904e-05,
|
| 208 |
+
"loss": 2.605,
|
| 209 |
+
"step": 14
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.74,
|
| 213 |
+
"eval_accuracy": 0.06326216056938211,
|
| 214 |
+
"eval_loss": 2.5078125,
|
| 215 |
+
"eval_runtime": 3.1482,
|
| 216 |
+
"eval_samples_per_second": 18.105,
|
| 217 |
+
"eval_steps_per_second": 1.271,
|
| 218 |
+
"step": 14
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.79,
|
| 222 |
+
"learning_rate": 2.6311599146653446e-05,
|
| 223 |
+
"loss": 2.6055,
|
| 224 |
+
"step": 15
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.79,
|
| 228 |
+
"eval_accuracy": 0.06335282651072124,
|
| 229 |
+
"eval_loss": 2.501953125,
|
| 230 |
+
"eval_runtime": 3.116,
|
| 231 |
+
"eval_samples_per_second": 18.293,
|
| 232 |
+
"eval_steps_per_second": 1.284,
|
| 233 |
+
"step": 15
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.84,
|
| 237 |
+
"learning_rate": 2.575173769752677e-05,
|
| 238 |
+
"loss": 2.5061,
|
| 239 |
+
"step": 16
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.84,
|
| 243 |
+
"eval_accuracy": 0.06323949408404733,
|
| 244 |
+
"eval_loss": 2.49609375,
|
| 245 |
+
"eval_runtime": 2.7142,
|
| 246 |
+
"eval_samples_per_second": 21.001,
|
| 247 |
+
"eval_steps_per_second": 1.474,
|
| 248 |
+
"step": 16
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.89,
|
| 252 |
+
"learning_rate": 2.5159223574386117e-05,
|
| 253 |
+
"loss": 2.4348,
|
| 254 |
+
"step": 17
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.89,
|
| 258 |
+
"eval_accuracy": 0.06310349517203863,
|
| 259 |
+
"eval_loss": 2.490234375,
|
| 260 |
+
"eval_runtime": 3.1245,
|
| 261 |
+
"eval_samples_per_second": 18.243,
|
| 262 |
+
"eval_steps_per_second": 1.28,
|
| 263 |
+
"step": 17
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.95,
|
| 267 |
+
"learning_rate": 2.4535856223149525e-05,
|
| 268 |
+
"loss": 2.6284,
|
| 269 |
+
"step": 18
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.95,
|
| 273 |
+
"eval_accuracy": 0.06319416111337776,
|
| 274 |
+
"eval_loss": 2.48828125,
|
| 275 |
+
"eval_runtime": 3.1284,
|
| 276 |
+
"eval_samples_per_second": 18.22,
|
| 277 |
+
"eval_steps_per_second": 1.279,
|
| 278 |
+
"step": 18
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.0,
|
| 282 |
+
"learning_rate": 2.3883528789974703e-05,
|
| 283 |
+
"loss": 2.5574,
|
| 284 |
+
"step": 19
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.0,
|
| 288 |
+
"eval_accuracy": 0.06308082868670384,
|
| 289 |
+
"eval_loss": 2.486328125,
|
| 290 |
+
"eval_runtime": 2.5211,
|
| 291 |
+
"eval_samples_per_second": 22.61,
|
| 292 |
+
"eval_steps_per_second": 1.587,
|
| 293 |
+
"step": 19
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.05,
|
| 297 |
+
"learning_rate": 2.320422237183641e-05,
|
| 298 |
+
"loss": 2.0814,
|
| 299 |
+
"step": 20
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.05,
|
| 303 |
+
"eval_accuracy": 0.0632848270547169,
|
| 304 |
+
"eval_loss": 2.484375,
|
| 305 |
+
"eval_runtime": 3.128,
|
| 306 |
+
"eval_samples_per_second": 18.222,
|
| 307 |
+
"eval_steps_per_second": 1.279,
|
| 308 |
+
"step": 20
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.11,
|
| 312 |
+
"learning_rate": 2.25e-05,
|
| 313 |
+
"loss": 2.0636,
|
| 314 |
+
"step": 21
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.11,
|
| 318 |
+
"eval_accuracy": 0.06351149190806474,
|
| 319 |
+
"eval_loss": 2.484375,
|
| 320 |
+
"eval_runtime": 3.1237,
|
| 321 |
+
"eval_samples_per_second": 18.248,
|
| 322 |
+
"eval_steps_per_second": 1.281,
|
| 323 |
+
"step": 21
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.16,
|
| 327 |
+
"learning_rate": 2.25e-05,
|
| 328 |
+
"loss": 1.9459,
|
| 329 |
+
"step": 22
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.16,
|
| 333 |
+
"eval_accuracy": 0.06351149190806474,
|
| 334 |
+
"eval_loss": 2.484375,
|
| 335 |
+
"eval_runtime": 2.9479,
|
| 336 |
+
"eval_samples_per_second": 19.336,
|
| 337 |
+
"eval_steps_per_second": 1.357,
|
| 338 |
+
"step": 22
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.21,
|
| 342 |
+
"learning_rate": 2.177300037466334e-05,
|
| 343 |
+
"loss": 2.0527,
|
| 344 |
+
"step": 23
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.21,
|
| 348 |
+
"eval_accuracy": 0.06344349245206038,
|
| 349 |
+
"eval_loss": 2.48828125,
|
| 350 |
+
"eval_runtime": 2.921,
|
| 351 |
+
"eval_samples_per_second": 19.514,
|
| 352 |
+
"eval_steps_per_second": 1.369,
|
| 353 |
+
"step": 23
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.26,
|
| 357 |
+
"learning_rate": 2.1025431369794546e-05,
|
| 358 |
+
"loss": 1.8881,
|
| 359 |
+
"step": 24
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.26,
|
| 363 |
+
"eval_accuracy": 0.06348882542272995,
|
| 364 |
+
"eval_loss": 2.49609375,
|
| 365 |
+
"eval_runtime": 3.1227,
|
| 366 |
+
"eval_samples_per_second": 18.253,
|
| 367 |
+
"eval_steps_per_second": 1.281,
|
| 368 |
+
"step": 24
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.32,
|
| 372 |
+
"learning_rate": 2.025956332789132e-05,
|
| 373 |
+
"loss": 1.8668,
|
| 374 |
+
"step": 25
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.32,
|
| 378 |
+
"eval_accuracy": 0.06362482433473865,
|
| 379 |
+
"eval_loss": 2.51171875,
|
| 380 |
+
"eval_runtime": 3.1172,
|
| 381 |
+
"eval_samples_per_second": 18.286,
|
| 382 |
+
"eval_steps_per_second": 1.283,
|
| 383 |
+
"step": 25
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.37,
|
| 387 |
+
"learning_rate": 1.9477722165025422e-05,
|
| 388 |
+
"loss": 2.0375,
|
| 389 |
+
"step": 26
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.37,
|
| 393 |
+
"eval_accuracy": 0.06357949136406908,
|
| 394 |
+
"eval_loss": 2.529296875,
|
| 395 |
+
"eval_runtime": 2.719,
|
| 396 |
+
"eval_samples_per_second": 20.963,
|
| 397 |
+
"eval_steps_per_second": 1.471,
|
| 398 |
+
"step": 26
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.42,
|
| 402 |
+
"learning_rate": 1.8682282307111988e-05,
|
| 403 |
+
"loss": 1.9402,
|
| 404 |
+
"step": 27
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.42,
|
| 408 |
+
"eval_accuracy": 0.06319416111337776,
|
| 409 |
+
"eval_loss": 2.544921875,
|
| 410 |
+
"eval_runtime": 3.1228,
|
| 411 |
+
"eval_samples_per_second": 18.253,
|
| 412 |
+
"eval_steps_per_second": 1.281,
|
| 413 |
+
"step": 27
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.47,
|
| 417 |
+
"learning_rate": 1.7875659478856077e-05,
|
| 418 |
+
"loss": 1.6086,
|
| 419 |
+
"step": 28
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.47,
|
| 423 |
+
"eval_accuracy": 0.06333016002538647,
|
| 424 |
+
"eval_loss": 2.55859375,
|
| 425 |
+
"eval_runtime": 2.917,
|
| 426 |
+
"eval_samples_per_second": 19.541,
|
| 427 |
+
"eval_steps_per_second": 1.371,
|
| 428 |
+
"step": 28
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.53,
|
| 432 |
+
"learning_rate": 1.7060303367276123e-05,
|
| 433 |
+
"loss": 1.8185,
|
| 434 |
+
"step": 29
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.53,
|
| 438 |
+
"eval_accuracy": 0.06319416111337776,
|
| 439 |
+
"eval_loss": 2.564453125,
|
| 440 |
+
"eval_runtime": 2.7052,
|
| 441 |
+
"eval_samples_per_second": 21.07,
|
| 442 |
+
"eval_steps_per_second": 1.479,
|
| 443 |
+
"step": 29
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.58,
|
| 447 |
+
"learning_rate": 1.623869018208499e-05,
|
| 448 |
+
"loss": 1.7324,
|
| 449 |
+
"step": 30
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.58,
|
| 453 |
+
"eval_accuracy": 0.0630128292306995,
|
| 454 |
+
"eval_loss": 2.560546875,
|
| 455 |
+
"eval_runtime": 3.1208,
|
| 456 |
+
"eval_samples_per_second": 18.264,
|
| 457 |
+
"eval_steps_per_second": 1.282,
|
| 458 |
+
"step": 30
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.63,
|
| 462 |
+
"learning_rate": 1.5413315135522434e-05,
|
| 463 |
+
"loss": 1.9285,
|
| 464 |
+
"step": 31
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.63,
|
| 468 |
+
"eval_accuracy": 0.06283149734802121,
|
| 469 |
+
"eval_loss": 2.552734375,
|
| 470 |
+
"eval_runtime": 3.1183,
|
| 471 |
+
"eval_samples_per_second": 18.279,
|
| 472 |
+
"eval_steps_per_second": 1.283,
|
| 473 |
+
"step": 31
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.68,
|
| 477 |
+
"learning_rate": 1.4586684864477572e-05,
|
| 478 |
+
"loss": 1.8031,
|
| 479 |
+
"step": 32
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.68,
|
| 483 |
+
"eval_accuracy": 0.06305816220136906,
|
| 484 |
+
"eval_loss": 2.544921875,
|
| 485 |
+
"eval_runtime": 2.9132,
|
| 486 |
+
"eval_samples_per_second": 19.566,
|
| 487 |
+
"eval_steps_per_second": 1.373,
|
| 488 |
+
"step": 32
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.74,
|
| 492 |
+
"learning_rate": 1.3761309817915017e-05,
|
| 493 |
+
"loss": 1.7321,
|
| 494 |
+
"step": 33
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.74,
|
| 498 |
+
"eval_accuracy": 0.0630128292306995,
|
| 499 |
+
"eval_loss": 2.53515625,
|
| 500 |
+
"eval_runtime": 2.7189,
|
| 501 |
+
"eval_samples_per_second": 20.964,
|
| 502 |
+
"eval_steps_per_second": 1.471,
|
| 503 |
+
"step": 33
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.79,
|
| 507 |
+
"learning_rate": 1.2939696632723877e-05,
|
| 508 |
+
"loss": 1.7802,
|
| 509 |
+
"step": 34
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.79,
|
| 513 |
+
"eval_accuracy": 0.0631488281427082,
|
| 514 |
+
"eval_loss": 2.525390625,
|
| 515 |
+
"eval_runtime": 3.1376,
|
| 516 |
+
"eval_samples_per_second": 18.167,
|
| 517 |
+
"eval_steps_per_second": 1.275,
|
| 518 |
+
"step": 34
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.84,
|
| 522 |
+
"learning_rate": 1.2124340521143929e-05,
|
| 523 |
+
"loss": 2.0637,
|
| 524 |
+
"step": 35
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.84,
|
| 528 |
+
"eval_accuracy": 0.06321682759871254,
|
| 529 |
+
"eval_loss": 2.515625,
|
| 530 |
+
"eval_runtime": 3.126,
|
| 531 |
+
"eval_samples_per_second": 18.234,
|
| 532 |
+
"eval_steps_per_second": 1.28,
|
| 533 |
+
"step": 35
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.89,
|
| 537 |
+
"learning_rate": 1.1317717692888014e-05,
|
| 538 |
+
"loss": 1.8159,
|
| 539 |
+
"step": 36
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.89,
|
| 543 |
+
"eval_accuracy": 0.0632848270547169,
|
| 544 |
+
"eval_loss": 2.5078125,
|
| 545 |
+
"eval_runtime": 2.5304,
|
| 546 |
+
"eval_samples_per_second": 22.526,
|
| 547 |
+
"eval_steps_per_second": 1.581,
|
| 548 |
+
"step": 36
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.95,
|
| 552 |
+
"learning_rate": 1.0522277834974586e-05,
|
| 553 |
+
"loss": 1.7142,
|
| 554 |
+
"step": 37
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.95,
|
| 558 |
+
"eval_accuracy": 0.06344349245206038,
|
| 559 |
+
"eval_loss": 2.50390625,
|
| 560 |
+
"eval_runtime": 2.9235,
|
| 561 |
+
"eval_samples_per_second": 19.497,
|
| 562 |
+
"eval_steps_per_second": 1.368,
|
| 563 |
+
"step": 37
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.0,
|
| 567 |
+
"learning_rate": 9.740436672108686e-06,
|
| 568 |
+
"loss": 1.8793,
|
| 569 |
+
"step": 38
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.0,
|
| 573 |
+
"eval_accuracy": 0.06337549299605603,
|
| 574 |
+
"eval_loss": 2.5,
|
| 575 |
+
"eval_runtime": 3.1269,
|
| 576 |
+
"eval_samples_per_second": 18.229,
|
| 577 |
+
"eval_steps_per_second": 1.279,
|
| 578 |
+
"step": 38
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.05,
|
| 582 |
+
"learning_rate": 8.974568630205462e-06,
|
| 583 |
+
"loss": 1.6914,
|
| 584 |
+
"step": 39
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.05,
|
| 588 |
+
"eval_accuracy": 0.06357949136406908,
|
| 589 |
+
"eval_loss": 2.501953125,
|
| 590 |
+
"eval_runtime": 2.3189,
|
| 591 |
+
"eval_samples_per_second": 24.581,
|
| 592 |
+
"eval_steps_per_second": 1.725,
|
| 593 |
+
"step": 39
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.11,
|
| 597 |
+
"learning_rate": 8.226999625336663e-06,
|
| 598 |
+
"loss": 1.411,
|
| 599 |
+
"step": 40
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.11,
|
| 603 |
+
"eval_accuracy": 0.06389682215875607,
|
| 604 |
+
"eval_loss": 2.50390625,
|
| 605 |
+
"eval_runtime": 3.1258,
|
| 606 |
+
"eval_samples_per_second": 18.235,
|
| 607 |
+
"eval_steps_per_second": 1.28,
|
| 608 |
+
"step": 40
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.16,
|
| 612 |
+
"learning_rate": 7.500000000000004e-06,
|
| 613 |
+
"loss": 1.4182,
|
| 614 |
+
"step": 41
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.16,
|
| 618 |
+
"eval_accuracy": 0.0638514891880865,
|
| 619 |
+
"eval_loss": 2.509765625,
|
| 620 |
+
"eval_runtime": 3.1169,
|
| 621 |
+
"eval_samples_per_second": 18.287,
|
| 622 |
+
"eval_steps_per_second": 1.283,
|
| 623 |
+
"step": 41
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 2.21,
|
| 627 |
+
"learning_rate": 6.795777628163599e-06,
|
| 628 |
+
"loss": 1.6223,
|
| 629 |
+
"step": 42
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.21,
|
| 633 |
+
"eval_accuracy": 0.06378348973208214,
|
| 634 |
+
"eval_loss": 2.517578125,
|
| 635 |
+
"eval_runtime": 2.7171,
|
| 636 |
+
"eval_samples_per_second": 20.978,
|
| 637 |
+
"eval_steps_per_second": 1.472,
|
| 638 |
+
"step": 42
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.26,
|
| 642 |
+
"learning_rate": 6.116471210025302e-06,
|
| 643 |
+
"loss": 1.623,
|
| 644 |
+
"step": 43
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.26,
|
| 648 |
+
"eval_accuracy": 0.06344349245206038,
|
| 649 |
+
"eval_loss": 2.52734375,
|
| 650 |
+
"eval_runtime": 2.7121,
|
| 651 |
+
"eval_samples_per_second": 21.017,
|
| 652 |
+
"eval_steps_per_second": 1.475,
|
| 653 |
+
"step": 43
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.32,
|
| 657 |
+
"learning_rate": 5.464143776850483e-06,
|
| 658 |
+
"loss": 1.5748,
|
| 659 |
+
"step": 44
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.32,
|
| 663 |
+
"eval_accuracy": 0.06344349245206038,
|
| 664 |
+
"eval_loss": 2.537109375,
|
| 665 |
+
"eval_runtime": 2.9216,
|
| 666 |
+
"eval_samples_per_second": 19.51,
|
| 667 |
+
"eval_steps_per_second": 1.369,
|
| 668 |
+
"step": 44
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.37,
|
| 672 |
+
"learning_rate": 4.840776425613887e-06,
|
| 673 |
+
"loss": 1.7166,
|
| 674 |
+
"step": 45
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.37,
|
| 678 |
+
"eval_accuracy": 0.0631488281427082,
|
| 679 |
+
"eval_loss": 2.546875,
|
| 680 |
+
"eval_runtime": 3.1159,
|
| 681 |
+
"eval_samples_per_second": 18.293,
|
| 682 |
+
"eval_steps_per_second": 1.284,
|
| 683 |
+
"step": 45
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.42,
|
| 687 |
+
"learning_rate": 4.248262302473233e-06,
|
| 688 |
+
"loss": 1.3432,
|
| 689 |
+
"step": 46
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.42,
|
| 693 |
+
"eval_accuracy": 0.0629901627453647,
|
| 694 |
+
"eval_loss": 2.556640625,
|
| 695 |
+
"eval_runtime": 2.9081,
|
| 696 |
+
"eval_samples_per_second": 19.6,
|
| 697 |
+
"eval_steps_per_second": 1.375,
|
| 698 |
+
"step": 46
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 2.47,
|
| 702 |
+
"learning_rate": 3.688400853346558e-06,
|
| 703 |
+
"loss": 1.5325,
|
| 704 |
+
"step": 47
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.47,
|
| 708 |
+
"eval_accuracy": 0.06305816220136906,
|
| 709 |
+
"eval_loss": 2.564453125,
|
| 710 |
+
"eval_runtime": 2.9197,
|
| 711 |
+
"eval_samples_per_second": 19.522,
|
| 712 |
+
"eval_steps_per_second": 1.37,
|
| 713 |
+
"step": 47
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.53,
|
| 717 |
+
"learning_rate": 3.162892359054098e-06,
|
| 718 |
+
"loss": 1.5076,
|
| 719 |
+
"step": 48
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 2.53,
|
| 723 |
+
"eval_accuracy": 0.062854163833356,
|
| 724 |
+
"eval_loss": 2.572265625,
|
| 725 |
+
"eval_runtime": 3.1077,
|
| 726 |
+
"eval_samples_per_second": 18.341,
|
| 727 |
+
"eval_steps_per_second": 1.287,
|
| 728 |
+
"step": 48
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.58,
|
| 732 |
+
"learning_rate": 2.673332771621324e-06,
|
| 733 |
+
"loss": 1.6636,
|
| 734 |
+
"step": 49
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.58,
|
| 738 |
+
"eval_accuracy": 0.06274083140668207,
|
| 739 |
+
"eval_loss": 2.578125,
|
| 740 |
+
"eval_runtime": 2.5045,
|
| 741 |
+
"eval_samples_per_second": 22.759,
|
| 742 |
+
"eval_steps_per_second": 1.597,
|
| 743 |
+
"step": 49
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 2.63,
|
| 747 |
+
"learning_rate": 2.221208867425096e-06,
|
| 748 |
+
"loss": 1.2897,
|
| 749 |
+
"step": 50
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 2.63,
|
| 753 |
+
"eval_accuracy": 0.06267283195067773,
|
| 754 |
+
"eval_loss": 2.583984375,
|
| 755 |
+
"eval_runtime": 3.1236,
|
| 756 |
+
"eval_samples_per_second": 18.248,
|
| 757 |
+
"eval_steps_per_second": 1.281,
|
| 758 |
+
"step": 50
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.68,
|
| 762 |
+
"learning_rate": 1.8078937319026655e-06,
|
| 763 |
+
"loss": 1.4559,
|
| 764 |
+
"step": 51
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.68,
|
| 768 |
+
"eval_accuracy": 0.06265016546534294,
|
| 769 |
+
"eval_loss": 2.587890625,
|
| 770 |
+
"eval_runtime": 2.523,
|
| 771 |
+
"eval_samples_per_second": 22.592,
|
| 772 |
+
"eval_steps_per_second": 1.585,
|
| 773 |
+
"step": 51
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.74,
|
| 777 |
+
"learning_rate": 1.4346425895363385e-06,
|
| 778 |
+
"loss": 1.3904,
|
| 779 |
+
"step": 52
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.74,
|
| 783 |
+
"eval_accuracy": 0.06267283195067773,
|
| 784 |
+
"eval_loss": 2.58984375,
|
| 785 |
+
"eval_runtime": 3.1182,
|
| 786 |
+
"eval_samples_per_second": 18.28,
|
| 787 |
+
"eval_steps_per_second": 1.283,
|
| 788 |
+
"step": 52
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.79,
|
| 792 |
+
"learning_rate": 1.1025889917779735e-06,
|
| 793 |
+
"loss": 1.4961,
|
| 794 |
+
"step": 53
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.79,
|
| 798 |
+
"eval_accuracy": 0.0625594995240038,
|
| 799 |
+
"eval_loss": 2.591796875,
|
| 800 |
+
"eval_runtime": 2.3139,
|
| 801 |
+
"eval_samples_per_second": 24.633,
|
| 802 |
+
"eval_steps_per_second": 1.729,
|
| 803 |
+
"step": 53
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.84,
|
| 807 |
+
"learning_rate": 8.127413744904805e-07,
|
| 808 |
+
"loss": 1.5276,
|
| 809 |
+
"step": 54
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.84,
|
| 813 |
+
"eval_accuracy": 0.06253683303866903,
|
| 814 |
+
"eval_loss": 2.59375,
|
| 815 |
+
"eval_runtime": 2.5424,
|
| 816 |
+
"eval_samples_per_second": 22.42,
|
| 817 |
+
"eval_steps_per_second": 1.573,
|
| 818 |
+
"step": 54
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.89,
|
| 822 |
+
"learning_rate": 5.659799953612438e-07,
|
| 823 |
+
"loss": 1.3479,
|
| 824 |
+
"step": 55
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.89,
|
| 828 |
+
"eval_accuracy": 0.062468833582664675,
|
| 829 |
+
"eval_loss": 2.595703125,
|
| 830 |
+
"eval_runtime": 3.124,
|
| 831 |
+
"eval_samples_per_second": 18.246,
|
| 832 |
+
"eval_steps_per_second": 1.28,
|
| 833 |
+
"step": 55
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 2.95,
|
| 837 |
+
"learning_rate": 3.630542605884657e-07,
|
| 838 |
+
"loss": 1.4094,
|
| 839 |
+
"step": 56
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 2.95,
|
| 843 |
+
"eval_accuracy": 0.06242350061199511,
|
| 844 |
+
"eval_loss": 2.595703125,
|
| 845 |
+
"eval_runtime": 2.3282,
|
| 846 |
+
"eval_samples_per_second": 24.482,
|
| 847 |
+
"eval_steps_per_second": 1.718,
|
| 848 |
+
"step": 56
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.0,
|
| 852 |
+
"learning_rate": 2.0458044895916516e-07,
|
| 853 |
+
"loss": 1.5486,
|
| 854 |
+
"step": 57
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 3.0,
|
| 858 |
+
"eval_accuracy": 0.06235550115599075,
|
| 859 |
+
"eval_loss": 2.595703125,
|
| 860 |
+
"eval_runtime": 2.9026,
|
| 861 |
+
"eval_samples_per_second": 19.637,
|
| 862 |
+
"eval_steps_per_second": 1.378,
|
| 863 |
+
"step": 57
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 3.0,
|
| 867 |
+
"step": 57,
|
| 868 |
+
"total_flos": 3114896719872.0,
|
| 869 |
+
"train_loss": 1.9830793414199561,
|
| 870 |
+
"train_runtime": 617.3135,
|
| 871 |
+
"train_samples_per_second": 1.473,
|
| 872 |
+
"train_steps_per_second": 0.092
|
| 873 |
+
}
|
| 874 |
+
],
|
| 875 |
+
"max_steps": 57,
|
| 876 |
+
"num_train_epochs": 3,
|
| 877 |
+
"total_flos": 3114896719872.0,
|
| 878 |
+
"trial_name": null,
|
| 879 |
+
"trial_params": null
|
| 880 |
+
}
|