Upload trainer_state.json
Browse files- trainer_state.json +898 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,898 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 49.01960784313726,
|
| 5 |
+
"global_step": 12500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 4.9e-05,
|
| 13 |
+
"loss": 2.0116,
|
| 14 |
+
"step": 255
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.4553,
|
| 19 |
+
"eval_f1_macro": 0.1796,
|
| 20 |
+
"eval_gen_len": 2.3716,
|
| 21 |
+
"eval_loss": 0.7925581336021423,
|
| 22 |
+
"eval_precision": 0.2144,
|
| 23 |
+
"eval_recall": 0.2023,
|
| 24 |
+
"eval_runtime": 18.41,
|
| 25 |
+
"eval_samples_per_second": 264.584,
|
| 26 |
+
"step": 255
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0,
|
| 30 |
+
"learning_rate": 4.8e-05,
|
| 31 |
+
"loss": 0.779,
|
| 32 |
+
"step": 510
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.4911,
|
| 37 |
+
"eval_f1_macro": 0.2749,
|
| 38 |
+
"eval_gen_len": 2.2535,
|
| 39 |
+
"eval_loss": 0.752581775188446,
|
| 40 |
+
"eval_precision": 0.4243,
|
| 41 |
+
"eval_recall": 0.2719,
|
| 42 |
+
"eval_runtime": 18.4504,
|
| 43 |
+
"eval_samples_per_second": 264.005,
|
| 44 |
+
"step": 510
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"learning_rate": 4.7e-05,
|
| 49 |
+
"loss": 0.6777,
|
| 50 |
+
"step": 765
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.0,
|
| 54 |
+
"eval_accuracy": 0.503,
|
| 55 |
+
"eval_f1_macro": 0.2851,
|
| 56 |
+
"eval_gen_len": 2.3207,
|
| 57 |
+
"eval_loss": 0.7490188479423523,
|
| 58 |
+
"eval_precision": 0.3735,
|
| 59 |
+
"eval_recall": 0.288,
|
| 60 |
+
"eval_runtime": 18.569,
|
| 61 |
+
"eval_samples_per_second": 262.318,
|
| 62 |
+
"step": 765
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"learning_rate": 4.600000000000001e-05,
|
| 67 |
+
"loss": 0.5968,
|
| 68 |
+
"step": 1020
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.0,
|
| 72 |
+
"eval_accuracy": 0.5013,
|
| 73 |
+
"eval_f1_macro": 0.2994,
|
| 74 |
+
"eval_gen_len": 2.2948,
|
| 75 |
+
"eval_loss": 0.7779901027679443,
|
| 76 |
+
"eval_precision": 0.3833,
|
| 77 |
+
"eval_recall": 0.2971,
|
| 78 |
+
"eval_runtime": 18.5932,
|
| 79 |
+
"eval_samples_per_second": 261.978,
|
| 80 |
+
"step": 1020
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"learning_rate": 4.5e-05,
|
| 85 |
+
"loss": 0.5367,
|
| 86 |
+
"step": 1275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.0,
|
| 90 |
+
"eval_accuracy": 0.5044,
|
| 91 |
+
"eval_f1_macro": 0.3052,
|
| 92 |
+
"eval_gen_len": 2.3751,
|
| 93 |
+
"eval_loss": 0.8049420118331909,
|
| 94 |
+
"eval_precision": 0.3699,
|
| 95 |
+
"eval_recall": 0.3016,
|
| 96 |
+
"eval_runtime": 18.6267,
|
| 97 |
+
"eval_samples_per_second": 261.506,
|
| 98 |
+
"step": 1275
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.0,
|
| 102 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 103 |
+
"loss": 0.475,
|
| 104 |
+
"step": 1530
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"eval_accuracy": 0.5005,
|
| 109 |
+
"eval_f1_macro": 0.3111,
|
| 110 |
+
"eval_gen_len": 2.3361,
|
| 111 |
+
"eval_loss": 0.8648290038108826,
|
| 112 |
+
"eval_precision": 0.3545,
|
| 113 |
+
"eval_recall": 0.3096,
|
| 114 |
+
"eval_runtime": 18.6251,
|
| 115 |
+
"eval_samples_per_second": 261.529,
|
| 116 |
+
"step": 1530
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.0,
|
| 120 |
+
"learning_rate": 4.3e-05,
|
| 121 |
+
"loss": 0.4194,
|
| 122 |
+
"step": 1785
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.0,
|
| 126 |
+
"eval_accuracy": 0.4868,
|
| 127 |
+
"eval_f1_macro": 0.2957,
|
| 128 |
+
"eval_gen_len": 2.3318,
|
| 129 |
+
"eval_loss": 0.9633024334907532,
|
| 130 |
+
"eval_precision": 0.3316,
|
| 131 |
+
"eval_recall": 0.2895,
|
| 132 |
+
"eval_runtime": 18.3899,
|
| 133 |
+
"eval_samples_per_second": 264.873,
|
| 134 |
+
"step": 1785
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 8.0,
|
| 138 |
+
"learning_rate": 4.2e-05,
|
| 139 |
+
"loss": 0.3619,
|
| 140 |
+
"step": 2040
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 8.0,
|
| 144 |
+
"eval_accuracy": 0.4925,
|
| 145 |
+
"eval_f1_macro": 0.2992,
|
| 146 |
+
"eval_gen_len": 2.3545,
|
| 147 |
+
"eval_loss": 0.9422969818115234,
|
| 148 |
+
"eval_precision": 0.3316,
|
| 149 |
+
"eval_recall": 0.2964,
|
| 150 |
+
"eval_runtime": 18.6364,
|
| 151 |
+
"eval_samples_per_second": 261.37,
|
| 152 |
+
"step": 2040
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 9.0,
|
| 156 |
+
"learning_rate": 4.1e-05,
|
| 157 |
+
"loss": 0.3126,
|
| 158 |
+
"step": 2295
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 9.0,
|
| 162 |
+
"eval_accuracy": 0.4718,
|
| 163 |
+
"eval_f1_macro": 0.2899,
|
| 164 |
+
"eval_gen_len": 2.4246,
|
| 165 |
+
"eval_loss": 1.086911678314209,
|
| 166 |
+
"eval_precision": 0.3039,
|
| 167 |
+
"eval_recall": 0.2956,
|
| 168 |
+
"eval_runtime": 18.6675,
|
| 169 |
+
"eval_samples_per_second": 260.935,
|
| 170 |
+
"step": 2295
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 10.0,
|
| 174 |
+
"learning_rate": 4e-05,
|
| 175 |
+
"loss": 0.2714,
|
| 176 |
+
"step": 2550
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 10.0,
|
| 180 |
+
"eval_accuracy": 0.4757,
|
| 181 |
+
"eval_f1_macro": 0.2959,
|
| 182 |
+
"eval_gen_len": 2.3593,
|
| 183 |
+
"eval_loss": 1.1425822973251343,
|
| 184 |
+
"eval_precision": 0.3162,
|
| 185 |
+
"eval_recall": 0.2919,
|
| 186 |
+
"eval_runtime": 18.4062,
|
| 187 |
+
"eval_samples_per_second": 264.64,
|
| 188 |
+
"step": 2550
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 11.0,
|
| 192 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 193 |
+
"loss": 0.2295,
|
| 194 |
+
"step": 2805
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 11.0,
|
| 198 |
+
"eval_accuracy": 0.4691,
|
| 199 |
+
"eval_f1_macro": 0.289,
|
| 200 |
+
"eval_gen_len": 2.4087,
|
| 201 |
+
"eval_loss": 1.189605951309204,
|
| 202 |
+
"eval_precision": 0.304,
|
| 203 |
+
"eval_recall": 0.2901,
|
| 204 |
+
"eval_runtime": 18.6533,
|
| 205 |
+
"eval_samples_per_second": 261.133,
|
| 206 |
+
"step": 2805
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 12.0,
|
| 210 |
+
"learning_rate": 3.8e-05,
|
| 211 |
+
"loss": 0.1945,
|
| 212 |
+
"step": 3060
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 12.0,
|
| 216 |
+
"eval_accuracy": 0.4703,
|
| 217 |
+
"eval_f1_macro": 0.3098,
|
| 218 |
+
"eval_gen_len": 2.38,
|
| 219 |
+
"eval_loss": 1.2930792570114136,
|
| 220 |
+
"eval_precision": 0.3263,
|
| 221 |
+
"eval_recall": 0.3061,
|
| 222 |
+
"eval_runtime": 18.3552,
|
| 223 |
+
"eval_samples_per_second": 265.375,
|
| 224 |
+
"step": 3060
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 13.0,
|
| 228 |
+
"learning_rate": 3.7e-05,
|
| 229 |
+
"loss": 0.1622,
|
| 230 |
+
"step": 3315
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 13.0,
|
| 234 |
+
"eval_accuracy": 0.4648,
|
| 235 |
+
"eval_f1_macro": 0.3084,
|
| 236 |
+
"eval_gen_len": 2.4237,
|
| 237 |
+
"eval_loss": 1.3369712829589844,
|
| 238 |
+
"eval_precision": 0.3194,
|
| 239 |
+
"eval_recall": 0.3082,
|
| 240 |
+
"eval_runtime": 18.3904,
|
| 241 |
+
"eval_samples_per_second": 264.867,
|
| 242 |
+
"step": 3315
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 14.0,
|
| 246 |
+
"learning_rate": 3.6e-05,
|
| 247 |
+
"loss": 0.1339,
|
| 248 |
+
"step": 3570
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 14.0,
|
| 252 |
+
"eval_accuracy": 0.4757,
|
| 253 |
+
"eval_f1_macro": 0.3098,
|
| 254 |
+
"eval_gen_len": 2.3874,
|
| 255 |
+
"eval_loss": 1.5157912969589233,
|
| 256 |
+
"eval_precision": 0.3258,
|
| 257 |
+
"eval_recall": 0.3087,
|
| 258 |
+
"eval_runtime": 18.3743,
|
| 259 |
+
"eval_samples_per_second": 265.099,
|
| 260 |
+
"step": 3570
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 15.0,
|
| 264 |
+
"learning_rate": 3.5e-05,
|
| 265 |
+
"loss": 0.1195,
|
| 266 |
+
"step": 3825
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 15.0,
|
| 270 |
+
"eval_accuracy": 0.4683,
|
| 271 |
+
"eval_f1_macro": 0.3044,
|
| 272 |
+
"eval_gen_len": 2.403,
|
| 273 |
+
"eval_loss": 1.5008689165115356,
|
| 274 |
+
"eval_precision": 0.3135,
|
| 275 |
+
"eval_recall": 0.3059,
|
| 276 |
+
"eval_runtime": 18.3877,
|
| 277 |
+
"eval_samples_per_second": 264.905,
|
| 278 |
+
"step": 3825
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 16.0,
|
| 282 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 283 |
+
"loss": 0.1019,
|
| 284 |
+
"step": 4080
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 16.0,
|
| 288 |
+
"eval_accuracy": 0.4738,
|
| 289 |
+
"eval_f1_macro": 0.3054,
|
| 290 |
+
"eval_gen_len": 2.3734,
|
| 291 |
+
"eval_loss": 1.5503424406051636,
|
| 292 |
+
"eval_precision": 0.3235,
|
| 293 |
+
"eval_recall": 0.3035,
|
| 294 |
+
"eval_runtime": 18.347,
|
| 295 |
+
"eval_samples_per_second": 265.493,
|
| 296 |
+
"step": 4080
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 17.0,
|
| 300 |
+
"learning_rate": 3.3e-05,
|
| 301 |
+
"loss": 0.0853,
|
| 302 |
+
"step": 4335
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 17.0,
|
| 306 |
+
"eval_accuracy": 0.4759,
|
| 307 |
+
"eval_f1_macro": 0.305,
|
| 308 |
+
"eval_gen_len": 2.3954,
|
| 309 |
+
"eval_loss": 1.7289695739746094,
|
| 310 |
+
"eval_precision": 0.3219,
|
| 311 |
+
"eval_recall": 0.3014,
|
| 312 |
+
"eval_runtime": 18.3899,
|
| 313 |
+
"eval_samples_per_second": 264.873,
|
| 314 |
+
"step": 4335
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 18.0,
|
| 318 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 319 |
+
"loss": 0.0773,
|
| 320 |
+
"step": 4590
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 18.0,
|
| 324 |
+
"eval_accuracy": 0.473,
|
| 325 |
+
"eval_f1_macro": 0.3045,
|
| 326 |
+
"eval_gen_len": 2.4233,
|
| 327 |
+
"eval_loss": 1.7796562910079956,
|
| 328 |
+
"eval_precision": 0.321,
|
| 329 |
+
"eval_recall": 0.2996,
|
| 330 |
+
"eval_runtime": 18.3356,
|
| 331 |
+
"eval_samples_per_second": 265.658,
|
| 332 |
+
"step": 4590
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 19.0,
|
| 336 |
+
"learning_rate": 3.1e-05,
|
| 337 |
+
"loss": 0.0681,
|
| 338 |
+
"step": 4845
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 19.0,
|
| 342 |
+
"eval_accuracy": 0.4638,
|
| 343 |
+
"eval_f1_macro": 0.2984,
|
| 344 |
+
"eval_gen_len": 2.3843,
|
| 345 |
+
"eval_loss": 1.753821611404419,
|
| 346 |
+
"eval_precision": 0.3106,
|
| 347 |
+
"eval_recall": 0.2996,
|
| 348 |
+
"eval_runtime": 18.3825,
|
| 349 |
+
"eval_samples_per_second": 264.98,
|
| 350 |
+
"step": 4845
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 20.0,
|
| 354 |
+
"learning_rate": 3e-05,
|
| 355 |
+
"loss": 0.0617,
|
| 356 |
+
"step": 5100
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 20.0,
|
| 360 |
+
"eval_accuracy": 0.4638,
|
| 361 |
+
"eval_f1_macro": 0.3047,
|
| 362 |
+
"eval_gen_len": 2.4092,
|
| 363 |
+
"eval_loss": 1.868014931678772,
|
| 364 |
+
"eval_precision": 0.3154,
|
| 365 |
+
"eval_recall": 0.3036,
|
| 366 |
+
"eval_runtime": 18.3921,
|
| 367 |
+
"eval_samples_per_second": 264.841,
|
| 368 |
+
"step": 5100
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 21.0,
|
| 372 |
+
"learning_rate": 2.9e-05,
|
| 373 |
+
"loss": 0.0537,
|
| 374 |
+
"step": 5355
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 21.0,
|
| 378 |
+
"eval_accuracy": 0.4642,
|
| 379 |
+
"eval_f1_macro": 0.3035,
|
| 380 |
+
"eval_gen_len": 2.3738,
|
| 381 |
+
"eval_loss": 1.9632675647735596,
|
| 382 |
+
"eval_precision": 0.3201,
|
| 383 |
+
"eval_recall": 0.2996,
|
| 384 |
+
"eval_runtime": 18.4289,
|
| 385 |
+
"eval_samples_per_second": 264.314,
|
| 386 |
+
"step": 5355
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 22.0,
|
| 390 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 391 |
+
"loss": 0.0473,
|
| 392 |
+
"step": 5610
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 22.0,
|
| 396 |
+
"eval_accuracy": 0.4726,
|
| 397 |
+
"eval_f1_macro": 0.303,
|
| 398 |
+
"eval_gen_len": 2.3862,
|
| 399 |
+
"eval_loss": 1.8952040672302246,
|
| 400 |
+
"eval_precision": 0.3214,
|
| 401 |
+
"eval_recall": 0.2998,
|
| 402 |
+
"eval_runtime": 18.3834,
|
| 403 |
+
"eval_samples_per_second": 264.967,
|
| 404 |
+
"step": 5610
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 23.0,
|
| 408 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 409 |
+
"loss": 0.0465,
|
| 410 |
+
"step": 5865
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 23.0,
|
| 414 |
+
"eval_accuracy": 0.466,
|
| 415 |
+
"eval_f1_macro": 0.3035,
|
| 416 |
+
"eval_gen_len": 2.4024,
|
| 417 |
+
"eval_loss": 1.9048091173171997,
|
| 418 |
+
"eval_precision": 0.3173,
|
| 419 |
+
"eval_recall": 0.3012,
|
| 420 |
+
"eval_runtime": 18.3842,
|
| 421 |
+
"eval_samples_per_second": 264.956,
|
| 422 |
+
"step": 5865
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 24.0,
|
| 426 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 427 |
+
"loss": 0.0406,
|
| 428 |
+
"step": 6120
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 24.0,
|
| 432 |
+
"eval_accuracy": 0.4634,
|
| 433 |
+
"eval_f1_macro": 0.3068,
|
| 434 |
+
"eval_gen_len": 2.426,
|
| 435 |
+
"eval_loss": 2.021580696105957,
|
| 436 |
+
"eval_precision": 0.3153,
|
| 437 |
+
"eval_recall": 0.3044,
|
| 438 |
+
"eval_runtime": 18.3498,
|
| 439 |
+
"eval_samples_per_second": 265.452,
|
| 440 |
+
"step": 6120
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 25.0,
|
| 444 |
+
"learning_rate": 2.5e-05,
|
| 445 |
+
"loss": 0.0358,
|
| 446 |
+
"step": 6375
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 25.0,
|
| 450 |
+
"eval_accuracy": 0.4742,
|
| 451 |
+
"eval_f1_macro": 0.3003,
|
| 452 |
+
"eval_gen_len": 2.3597,
|
| 453 |
+
"eval_loss": 2.116412401199341,
|
| 454 |
+
"eval_precision": 0.3236,
|
| 455 |
+
"eval_recall": 0.2931,
|
| 456 |
+
"eval_runtime": 18.3974,
|
| 457 |
+
"eval_samples_per_second": 264.766,
|
| 458 |
+
"step": 6375
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 26.0,
|
| 462 |
+
"learning_rate": 2.4e-05,
|
| 463 |
+
"loss": 0.0353,
|
| 464 |
+
"step": 6630
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 26.0,
|
| 468 |
+
"eval_accuracy": 0.4668,
|
| 469 |
+
"eval_f1_macro": 0.3004,
|
| 470 |
+
"eval_gen_len": 2.4484,
|
| 471 |
+
"eval_loss": 2.0235698223114014,
|
| 472 |
+
"eval_precision": 0.3084,
|
| 473 |
+
"eval_recall": 0.2995,
|
| 474 |
+
"eval_runtime": 18.3702,
|
| 475 |
+
"eval_samples_per_second": 265.158,
|
| 476 |
+
"step": 6630
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 27.0,
|
| 480 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 481 |
+
"loss": 0.0314,
|
| 482 |
+
"step": 6885
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 27.0,
|
| 486 |
+
"eval_accuracy": 0.464,
|
| 487 |
+
"eval_f1_macro": 0.3013,
|
| 488 |
+
"eval_gen_len": 2.4204,
|
| 489 |
+
"eval_loss": 2.124769926071167,
|
| 490 |
+
"eval_precision": 0.3066,
|
| 491 |
+
"eval_recall": 0.3019,
|
| 492 |
+
"eval_runtime": 18.4132,
|
| 493 |
+
"eval_samples_per_second": 264.538,
|
| 494 |
+
"step": 6885
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 28.0,
|
| 498 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 499 |
+
"loss": 0.0296,
|
| 500 |
+
"step": 7140
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 28.0,
|
| 504 |
+
"eval_accuracy": 0.4722,
|
| 505 |
+
"eval_f1_macro": 0.2997,
|
| 506 |
+
"eval_gen_len": 2.3732,
|
| 507 |
+
"eval_loss": 2.124000072479248,
|
| 508 |
+
"eval_precision": 0.3261,
|
| 509 |
+
"eval_recall": 0.294,
|
| 510 |
+
"eval_runtime": 18.3663,
|
| 511 |
+
"eval_samples_per_second": 265.213,
|
| 512 |
+
"step": 7140
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 29.0,
|
| 516 |
+
"learning_rate": 2.1e-05,
|
| 517 |
+
"loss": 0.0274,
|
| 518 |
+
"step": 7395
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 29.0,
|
| 522 |
+
"eval_accuracy": 0.467,
|
| 523 |
+
"eval_f1_macro": 0.3011,
|
| 524 |
+
"eval_gen_len": 2.3636,
|
| 525 |
+
"eval_loss": 2.1549148559570312,
|
| 526 |
+
"eval_precision": 0.3197,
|
| 527 |
+
"eval_recall": 0.2963,
|
| 528 |
+
"eval_runtime": 18.4004,
|
| 529 |
+
"eval_samples_per_second": 264.722,
|
| 530 |
+
"step": 7395
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 30.0,
|
| 534 |
+
"learning_rate": 2e-05,
|
| 535 |
+
"loss": 0.0248,
|
| 536 |
+
"step": 7650
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 30.0,
|
| 540 |
+
"eval_accuracy": 0.4697,
|
| 541 |
+
"eval_f1_macro": 0.2982,
|
| 542 |
+
"eval_gen_len": 2.3798,
|
| 543 |
+
"eval_loss": 2.2189269065856934,
|
| 544 |
+
"eval_precision": 0.3152,
|
| 545 |
+
"eval_recall": 0.2951,
|
| 546 |
+
"eval_runtime": 18.3622,
|
| 547 |
+
"eval_samples_per_second": 265.273,
|
| 548 |
+
"step": 7650
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 31.0,
|
| 552 |
+
"learning_rate": 1.9e-05,
|
| 553 |
+
"loss": 0.0219,
|
| 554 |
+
"step": 7905
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 31.0,
|
| 558 |
+
"eval_accuracy": 0.4736,
|
| 559 |
+
"eval_f1_macro": 0.3048,
|
| 560 |
+
"eval_gen_len": 2.3942,
|
| 561 |
+
"eval_loss": 2.3595752716064453,
|
| 562 |
+
"eval_precision": 0.3157,
|
| 563 |
+
"eval_recall": 0.3049,
|
| 564 |
+
"eval_runtime": 18.3521,
|
| 565 |
+
"eval_samples_per_second": 265.419,
|
| 566 |
+
"step": 7905
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 32.0,
|
| 570 |
+
"learning_rate": 1.8e-05,
|
| 571 |
+
"loss": 0.0205,
|
| 572 |
+
"step": 8160
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 32.0,
|
| 576 |
+
"eval_accuracy": 0.4705,
|
| 577 |
+
"eval_f1_macro": 0.3013,
|
| 578 |
+
"eval_gen_len": 2.3909,
|
| 579 |
+
"eval_loss": 2.4317517280578613,
|
| 580 |
+
"eval_precision": 0.3151,
|
| 581 |
+
"eval_recall": 0.3001,
|
| 582 |
+
"eval_runtime": 18.3589,
|
| 583 |
+
"eval_samples_per_second": 265.321,
|
| 584 |
+
"step": 8160
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 33.0,
|
| 588 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 589 |
+
"loss": 0.0189,
|
| 590 |
+
"step": 8415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 33.0,
|
| 594 |
+
"eval_accuracy": 0.4767,
|
| 595 |
+
"eval_f1_macro": 0.3084,
|
| 596 |
+
"eval_gen_len": 2.3751,
|
| 597 |
+
"eval_loss": 2.4803547859191895,
|
| 598 |
+
"eval_precision": 0.3242,
|
| 599 |
+
"eval_recall": 0.3045,
|
| 600 |
+
"eval_runtime": 18.4166,
|
| 601 |
+
"eval_samples_per_second": 264.489,
|
| 602 |
+
"step": 8415
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 34.0,
|
| 606 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 607 |
+
"loss": 0.0211,
|
| 608 |
+
"step": 8670
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 34.0,
|
| 612 |
+
"eval_accuracy": 0.4699,
|
| 613 |
+
"eval_f1_macro": 0.304,
|
| 614 |
+
"eval_gen_len": 2.4102,
|
| 615 |
+
"eval_loss": 2.371544361114502,
|
| 616 |
+
"eval_precision": 0.3223,
|
| 617 |
+
"eval_recall": 0.2999,
|
| 618 |
+
"eval_runtime": 18.4037,
|
| 619 |
+
"eval_samples_per_second": 264.675,
|
| 620 |
+
"step": 8670
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 35.0,
|
| 624 |
+
"learning_rate": 1.5e-05,
|
| 625 |
+
"loss": 0.0156,
|
| 626 |
+
"step": 8925
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 35.0,
|
| 630 |
+
"eval_accuracy": 0.4753,
|
| 631 |
+
"eval_f1_macro": 0.3014,
|
| 632 |
+
"eval_gen_len": 2.395,
|
| 633 |
+
"eval_loss": 2.55307674407959,
|
| 634 |
+
"eval_precision": 0.3136,
|
| 635 |
+
"eval_recall": 0.2973,
|
| 636 |
+
"eval_runtime": 18.4323,
|
| 637 |
+
"eval_samples_per_second": 264.264,
|
| 638 |
+
"step": 8925
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 36.0,
|
| 642 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 643 |
+
"loss": 0.0179,
|
| 644 |
+
"step": 9180
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 36.0,
|
| 648 |
+
"eval_accuracy": 0.4829,
|
| 649 |
+
"eval_f1_macro": 0.3055,
|
| 650 |
+
"eval_gen_len": 2.3621,
|
| 651 |
+
"eval_loss": 2.49765682220459,
|
| 652 |
+
"eval_precision": 0.3308,
|
| 653 |
+
"eval_recall": 0.2991,
|
| 654 |
+
"eval_runtime": 18.4231,
|
| 655 |
+
"eval_samples_per_second": 264.396,
|
| 656 |
+
"step": 9180
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 37.0,
|
| 660 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 661 |
+
"loss": 0.0155,
|
| 662 |
+
"step": 9435
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 37.0,
|
| 666 |
+
"eval_accuracy": 0.4808,
|
| 667 |
+
"eval_f1_macro": 0.3086,
|
| 668 |
+
"eval_gen_len": 2.3775,
|
| 669 |
+
"eval_loss": 2.4960439205169678,
|
| 670 |
+
"eval_precision": 0.3245,
|
| 671 |
+
"eval_recall": 0.3039,
|
| 672 |
+
"eval_runtime": 18.4083,
|
| 673 |
+
"eval_samples_per_second": 264.609,
|
| 674 |
+
"step": 9435
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 38.0,
|
| 678 |
+
"learning_rate": 1.2e-05,
|
| 679 |
+
"loss": 0.0154,
|
| 680 |
+
"step": 9690
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 38.0,
|
| 684 |
+
"eval_accuracy": 0.4652,
|
| 685 |
+
"eval_f1_macro": 0.3047,
|
| 686 |
+
"eval_gen_len": 2.3983,
|
| 687 |
+
"eval_loss": 2.59112811088562,
|
| 688 |
+
"eval_precision": 0.3196,
|
| 689 |
+
"eval_recall": 0.2998,
|
| 690 |
+
"eval_runtime": 18.406,
|
| 691 |
+
"eval_samples_per_second": 264.642,
|
| 692 |
+
"step": 9690
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 39.0,
|
| 696 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 697 |
+
"loss": 0.0144,
|
| 698 |
+
"step": 9945
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 39.0,
|
| 702 |
+
"eval_accuracy": 0.473,
|
| 703 |
+
"eval_f1_macro": 0.3097,
|
| 704 |
+
"eval_gen_len": 2.3634,
|
| 705 |
+
"eval_loss": 2.646393299102783,
|
| 706 |
+
"eval_precision": 0.3283,
|
| 707 |
+
"eval_recall": 0.3046,
|
| 708 |
+
"eval_runtime": 18.3793,
|
| 709 |
+
"eval_samples_per_second": 265.027,
|
| 710 |
+
"step": 9945
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 40.0,
|
| 714 |
+
"learning_rate": 1e-05,
|
| 715 |
+
"loss": 0.0135,
|
| 716 |
+
"step": 10200
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 40.0,
|
| 720 |
+
"eval_accuracy": 0.4695,
|
| 721 |
+
"eval_f1_macro": 0.3035,
|
| 722 |
+
"eval_gen_len": 2.3812,
|
| 723 |
+
"eval_loss": 2.711395740509033,
|
| 724 |
+
"eval_precision": 0.3185,
|
| 725 |
+
"eval_recall": 0.2989,
|
| 726 |
+
"eval_runtime": 18.3802,
|
| 727 |
+
"eval_samples_per_second": 265.013,
|
| 728 |
+
"step": 10200
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 41.0,
|
| 732 |
+
"learning_rate": 9e-06,
|
| 733 |
+
"loss": 0.0132,
|
| 734 |
+
"step": 10455
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 41.0,
|
| 738 |
+
"eval_accuracy": 0.4707,
|
| 739 |
+
"eval_f1_macro": 0.307,
|
| 740 |
+
"eval_gen_len": 2.4055,
|
| 741 |
+
"eval_loss": 2.706991672515869,
|
| 742 |
+
"eval_precision": 0.3218,
|
| 743 |
+
"eval_recall": 0.3029,
|
| 744 |
+
"eval_runtime": 18.4175,
|
| 745 |
+
"eval_samples_per_second": 264.476,
|
| 746 |
+
"step": 10455
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 42.0,
|
| 750 |
+
"learning_rate": 8.000000000000001e-06,
|
| 751 |
+
"loss": 0.0113,
|
| 752 |
+
"step": 10710
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 42.0,
|
| 756 |
+
"eval_accuracy": 0.4705,
|
| 757 |
+
"eval_f1_macro": 0.3041,
|
| 758 |
+
"eval_gen_len": 2.3833,
|
| 759 |
+
"eval_loss": 2.7490220069885254,
|
| 760 |
+
"eval_precision": 0.3226,
|
| 761 |
+
"eval_recall": 0.3009,
|
| 762 |
+
"eval_runtime": 18.3891,
|
| 763 |
+
"eval_samples_per_second": 264.885,
|
| 764 |
+
"step": 10710
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 43.0,
|
| 768 |
+
"learning_rate": 7.000000000000001e-06,
|
| 769 |
+
"loss": 0.0104,
|
| 770 |
+
"step": 10965
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 43.0,
|
| 774 |
+
"eval_accuracy": 0.4707,
|
| 775 |
+
"eval_f1_macro": 0.3094,
|
| 776 |
+
"eval_gen_len": 2.3868,
|
| 777 |
+
"eval_loss": 2.8594679832458496,
|
| 778 |
+
"eval_precision": 0.3257,
|
| 779 |
+
"eval_recall": 0.304,
|
| 780 |
+
"eval_runtime": 18.4068,
|
| 781 |
+
"eval_samples_per_second": 264.631,
|
| 782 |
+
"step": 10965
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 44.0,
|
| 786 |
+
"learning_rate": 6e-06,
|
| 787 |
+
"loss": 0.0125,
|
| 788 |
+
"step": 11220
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 44.0,
|
| 792 |
+
"eval_accuracy": 0.4705,
|
| 793 |
+
"eval_f1_macro": 0.3068,
|
| 794 |
+
"eval_gen_len": 2.3921,
|
| 795 |
+
"eval_loss": 2.777812957763672,
|
| 796 |
+
"eval_precision": 0.3207,
|
| 797 |
+
"eval_recall": 0.3034,
|
| 798 |
+
"eval_runtime": 18.3628,
|
| 799 |
+
"eval_samples_per_second": 265.264,
|
| 800 |
+
"step": 11220
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 45.0,
|
| 804 |
+
"learning_rate": 5e-06,
|
| 805 |
+
"loss": 0.0094,
|
| 806 |
+
"step": 11475
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 45.0,
|
| 810 |
+
"eval_accuracy": 0.4753,
|
| 811 |
+
"eval_f1_macro": 0.3102,
|
| 812 |
+
"eval_gen_len": 2.4036,
|
| 813 |
+
"eval_loss": 2.7739901542663574,
|
| 814 |
+
"eval_precision": 0.3301,
|
| 815 |
+
"eval_recall": 0.3028,
|
| 816 |
+
"eval_runtime": 18.4413,
|
| 817 |
+
"eval_samples_per_second": 264.135,
|
| 818 |
+
"step": 11475
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 46.0,
|
| 822 |
+
"learning_rate": 4.000000000000001e-06,
|
| 823 |
+
"loss": 0.0094,
|
| 824 |
+
"step": 11730
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 46.0,
|
| 828 |
+
"eval_accuracy": 0.4755,
|
| 829 |
+
"eval_f1_macro": 0.3122,
|
| 830 |
+
"eval_gen_len": 2.3979,
|
| 831 |
+
"eval_loss": 2.759046792984009,
|
| 832 |
+
"eval_precision": 0.3284,
|
| 833 |
+
"eval_recall": 0.3064,
|
| 834 |
+
"eval_runtime": 18.4399,
|
| 835 |
+
"eval_samples_per_second": 264.155,
|
| 836 |
+
"step": 11730
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 47.0,
|
| 840 |
+
"learning_rate": 3e-06,
|
| 841 |
+
"loss": 0.0085,
|
| 842 |
+
"step": 11985
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 47.0,
|
| 846 |
+
"eval_accuracy": 0.4759,
|
| 847 |
+
"eval_f1_macro": 0.3092,
|
| 848 |
+
"eval_gen_len": 2.3903,
|
| 849 |
+
"eval_loss": 2.8234634399414062,
|
| 850 |
+
"eval_precision": 0.3248,
|
| 851 |
+
"eval_recall": 0.304,
|
| 852 |
+
"eval_runtime": 18.4435,
|
| 853 |
+
"eval_samples_per_second": 264.104,
|
| 854 |
+
"step": 11985
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 48.0,
|
| 858 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 859 |
+
"loss": 0.0087,
|
| 860 |
+
"step": 12240
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 48.0,
|
| 864 |
+
"eval_accuracy": 0.474,
|
| 865 |
+
"eval_f1_macro": 0.3097,
|
| 866 |
+
"eval_gen_len": 2.3977,
|
| 867 |
+
"eval_loss": 2.834430694580078,
|
| 868 |
+
"eval_precision": 0.3247,
|
| 869 |
+
"eval_recall": 0.3045,
|
| 870 |
+
"eval_runtime": 18.4163,
|
| 871 |
+
"eval_samples_per_second": 264.494,
|
| 872 |
+
"step": 12240
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 49.0,
|
| 876 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 877 |
+
"loss": 0.009,
|
| 878 |
+
"step": 12495
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 49.0,
|
| 882 |
+
"eval_accuracy": 0.4732,
|
| 883 |
+
"eval_f1_macro": 0.3081,
|
| 884 |
+
"eval_gen_len": 2.3868,
|
| 885 |
+
"eval_loss": 2.841893196105957,
|
| 886 |
+
"eval_precision": 0.3256,
|
| 887 |
+
"eval_recall": 0.3018,
|
| 888 |
+
"eval_runtime": 18.4481,
|
| 889 |
+
"eval_samples_per_second": 264.037,
|
| 890 |
+
"step": 12495
|
| 891 |
+
}
|
| 892 |
+
],
|
| 893 |
+
"max_steps": 12750,
|
| 894 |
+
"num_train_epochs": 50,
|
| 895 |
+
"total_flos": 1.14107158131029e+17,
|
| 896 |
+
"trial_name": null,
|
| 897 |
+
"trial_params": null
|
| 898 |
+
}
|