Commit
•
8e20324
1
Parent(s):
1fc15ad
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +151 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"train_loss": 0.0387608133931748,
|
| 4 |
+
"train_runtime": 15676.2621,
|
| 5 |
+
"train_samples": 10763,
|
| 6 |
+
"train_samples_per_second": 5.493,
|
| 7 |
+
"train_steps_per_second": 0.687
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"train_loss": 0.0387608133931748,
|
| 4 |
+
"train_runtime": 15676.2621,
|
| 5 |
+
"train_samples": 10763,
|
| 6 |
+
"train_samples_per_second": 5.493,
|
| 7 |
+
"train_steps_per_second": 0.687
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"global_step": 10768,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.37,
|
| 12 |
+
"learning_rate": 2.8620913818722143e-05,
|
| 13 |
+
"loss": 0.0869,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.74,
|
| 18 |
+
"learning_rate": 2.7227897473997028e-05,
|
| 19 |
+
"loss": 0.071,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.11,
|
| 24 |
+
"learning_rate": 2.583488112927192e-05,
|
| 25 |
+
"loss": 0.0672,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.49,
|
| 30 |
+
"learning_rate": 2.4441864784546807e-05,
|
| 31 |
+
"loss": 0.0553,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.86,
|
| 36 |
+
"learning_rate": 2.3051634472511147e-05,
|
| 37 |
+
"loss": 0.0634,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.23,
|
| 42 |
+
"learning_rate": 2.1658618127786032e-05,
|
| 43 |
+
"loss": 0.0578,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.6,
|
| 48 |
+
"learning_rate": 2.0265601783060923e-05,
|
| 49 |
+
"loss": 0.0567,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.97,
|
| 54 |
+
"learning_rate": 1.8872585438335808e-05,
|
| 55 |
+
"loss": 0.0485,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.34,
|
| 60 |
+
"learning_rate": 1.74795690936107e-05,
|
| 61 |
+
"loss": 0.0376,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.71,
|
| 66 |
+
"learning_rate": 1.6086552748885588e-05,
|
| 67 |
+
"loss": 0.0392,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.09,
|
| 72 |
+
"learning_rate": 1.4693536404160476e-05,
|
| 73 |
+
"loss": 0.0388,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.46,
|
| 78 |
+
"learning_rate": 1.3300520059435364e-05,
|
| 79 |
+
"loss": 0.0289,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.83,
|
| 84 |
+
"learning_rate": 1.1910289747399702e-05,
|
| 85 |
+
"loss": 0.0329,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.2,
|
| 90 |
+
"learning_rate": 1.051727340267459e-05,
|
| 91 |
+
"loss": 0.0275,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.57,
|
| 96 |
+
"learning_rate": 9.124257057949479e-06,
|
| 97 |
+
"loss": 0.0222,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 5.94,
|
| 102 |
+
"learning_rate": 7.734026745913819e-06,
|
| 103 |
+
"loss": 0.0238,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.32,
|
| 108 |
+
"learning_rate": 6.341010401188708e-06,
|
| 109 |
+
"loss": 0.0173,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 6.69,
|
| 114 |
+
"learning_rate": 4.947994056463596e-06,
|
| 115 |
+
"loss": 0.0172,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.06,
|
| 120 |
+
"learning_rate": 3.5549777117384844e-06,
|
| 121 |
+
"loss": 0.0137,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.43,
|
| 126 |
+
"learning_rate": 2.161961367013373e-06,
|
| 127 |
+
"loss": 0.0123,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.8,
|
| 132 |
+
"learning_rate": 7.717310549777118e-07,
|
| 133 |
+
"loss": 0.0121,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 8.0,
|
| 138 |
+
"step": 10768,
|
| 139 |
+
"total_flos": 1.8659637466025165e+17,
|
| 140 |
+
"train_loss": 0.0387608133931748,
|
| 141 |
+
"train_runtime": 15676.2621,
|
| 142 |
+
"train_samples_per_second": 5.493,
|
| 143 |
+
"train_steps_per_second": 0.687
|
| 144 |
+
}
|
| 145 |
+
],
|
| 146 |
+
"max_steps": 10768,
|
| 147 |
+
"num_train_epochs": 8,
|
| 148 |
+
"total_flos": 1.8659637466025165e+17,
|
| 149 |
+
"trial_name": null,
|
| 150 |
+
"trial_params": null
|
| 151 |
+
}
|