Commit ·
3c6dfce
1
Parent(s): 1f59655
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +151 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9392201834862385,
|
| 4 |
+
"eval_loss": 0.2945544421672821,
|
| 5 |
+
"eval_runtime": 4.2562,
|
| 6 |
+
"eval_samples": 872,
|
| 7 |
+
"eval_samples_per_second": 204.88,
|
| 8 |
+
"eval_steps_per_second": 25.61,
|
| 9 |
+
"train_loss": 0.1284604350518161,
|
| 10 |
+
"train_runtime": 4731.3564,
|
| 11 |
+
"train_samples": 67349,
|
| 12 |
+
"train_samples_per_second": 71.173,
|
| 13 |
+
"train_steps_per_second": 2.225
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9392201834862385,
|
| 4 |
+
"eval_loss": 0.2945544421672821,
|
| 5 |
+
"eval_runtime": 4.2562,
|
| 6 |
+
"eval_samples": 872,
|
| 7 |
+
"eval_samples_per_second": 204.88,
|
| 8 |
+
"eval_steps_per_second": 25.61
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.1284604350518161,
|
| 4 |
+
"train_runtime": 4731.3564,
|
| 5 |
+
"train_samples": 67349,
|
| 6 |
+
"train_samples_per_second": 71.173,
|
| 7 |
+
"train_steps_per_second": 2.225
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 10525,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.24,
|
| 12 |
+
"learning_rate": 1.9049881235154395e-05,
|
| 13 |
+
"loss": 0.3246,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.48,
|
| 18 |
+
"learning_rate": 1.809976247030879e-05,
|
| 19 |
+
"loss": 0.2362,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.71,
|
| 24 |
+
"learning_rate": 1.7149643705463184e-05,
|
| 25 |
+
"loss": 0.2107,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.95,
|
| 30 |
+
"learning_rate": 1.6199524940617578e-05,
|
| 31 |
+
"loss": 0.1928,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.19,
|
| 36 |
+
"learning_rate": 1.5249406175771972e-05,
|
| 37 |
+
"loss": 0.1586,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.43,
|
| 42 |
+
"learning_rate": 1.4299287410926367e-05,
|
| 43 |
+
"loss": 0.1425,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.66,
|
| 48 |
+
"learning_rate": 1.3349168646080762e-05,
|
| 49 |
+
"loss": 0.1467,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.9,
|
| 54 |
+
"learning_rate": 1.2399049881235155e-05,
|
| 55 |
+
"loss": 0.1468,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.14,
|
| 60 |
+
"learning_rate": 1.144893111638955e-05,
|
| 61 |
+
"loss": 0.1224,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.38,
|
| 66 |
+
"learning_rate": 1.0498812351543943e-05,
|
| 67 |
+
"loss": 0.1058,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.61,
|
| 72 |
+
"learning_rate": 9.548693586698338e-06,
|
| 73 |
+
"loss": 0.1106,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.85,
|
| 78 |
+
"learning_rate": 8.598574821852733e-06,
|
| 79 |
+
"loss": 0.1007,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.09,
|
| 84 |
+
"learning_rate": 7.648456057007126e-06,
|
| 85 |
+
"loss": 0.0981,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 3.33,
|
| 90 |
+
"learning_rate": 6.698337292161521e-06,
|
| 91 |
+
"loss": 0.0875,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.56,
|
| 96 |
+
"learning_rate": 5.748218527315916e-06,
|
| 97 |
+
"loss": 0.0851,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.8,
|
| 102 |
+
"learning_rate": 4.798099762470309e-06,
|
| 103 |
+
"loss": 0.0841,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.04,
|
| 108 |
+
"learning_rate": 3.8479809976247036e-06,
|
| 109 |
+
"loss": 0.0825,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.28,
|
| 114 |
+
"learning_rate": 2.897862232779098e-06,
|
| 115 |
+
"loss": 0.0685,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 4.51,
|
| 120 |
+
"learning_rate": 1.947743467933492e-06,
|
| 121 |
+
"loss": 0.0642,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.75,
|
| 126 |
+
"learning_rate": 9.976247030878861e-07,
|
| 127 |
+
"loss": 0.0693,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.99,
|
| 132 |
+
"learning_rate": 4.750593824228029e-08,
|
| 133 |
+
"loss": 0.0631,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 5.0,
|
| 138 |
+
"step": 10525,
|
| 139 |
+
"total_flos": 0.0,
|
| 140 |
+
"train_loss": 0.1284604350518161,
|
| 141 |
+
"train_runtime": 4731.3564,
|
| 142 |
+
"train_samples_per_second": 71.173,
|
| 143 |
+
"train_steps_per_second": 2.225
|
| 144 |
+
}
|
| 145 |
+
],
|
| 146 |
+
"max_steps": 10525,
|
| 147 |
+
"num_train_epochs": 5,
|
| 148 |
+
"total_flos": 0.0,
|
| 149 |
+
"trial_name": null,
|
| 150 |
+
"trial_params": null
|
| 151 |
+
}
|