Upload trainer_state.json
Browse files- trainer_state.json +169 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 12111,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.12,
|
| 12 |
+
"learning_rate": 4.793576087854017e-05,
|
| 13 |
+
"loss": 2.3279,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.25,
|
| 18 |
+
"learning_rate": 4.5871521757080346e-05,
|
| 19 |
+
"loss": 1.6773,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.37,
|
| 24 |
+
"learning_rate": 4.380728263562051e-05,
|
| 25 |
+
"loss": 1.4905,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.5,
|
| 30 |
+
"learning_rate": 4.174304351416068e-05,
|
| 31 |
+
"loss": 1.3552,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.62,
|
| 36 |
+
"learning_rate": 3.9678804392700854e-05,
|
| 37 |
+
"loss": 1.2864,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.74,
|
| 42 |
+
"learning_rate": 3.761456527124102e-05,
|
| 43 |
+
"loss": 1.2008,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.87,
|
| 48 |
+
"learning_rate": 3.555032614978119e-05,
|
| 49 |
+
"loss": 1.1758,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.99,
|
| 54 |
+
"learning_rate": 3.348608702832136e-05,
|
| 55 |
+
"loss": 1.122,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.11,
|
| 60 |
+
"learning_rate": 3.1421847906861534e-05,
|
| 61 |
+
"loss": 1.0693,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.24,
|
| 66 |
+
"learning_rate": 2.9357608785401702e-05,
|
| 67 |
+
"loss": 1.037,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.36,
|
| 72 |
+
"learning_rate": 2.729336966394187e-05,
|
| 73 |
+
"loss": 1.0164,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.49,
|
| 78 |
+
"learning_rate": 2.5229130542482042e-05,
|
| 79 |
+
"loss": 0.99,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.61,
|
| 84 |
+
"learning_rate": 2.316489142102221e-05,
|
| 85 |
+
"loss": 0.9796,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.73,
|
| 90 |
+
"learning_rate": 2.1100652299562382e-05,
|
| 91 |
+
"loss": 0.9223,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.86,
|
| 96 |
+
"learning_rate": 1.9036413178102553e-05,
|
| 97 |
+
"loss": 0.9296,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.98,
|
| 102 |
+
"learning_rate": 1.697217405664272e-05,
|
| 103 |
+
"loss": 0.8937,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.11,
|
| 108 |
+
"learning_rate": 1.4907934935182893e-05,
|
| 109 |
+
"loss": 0.876,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.23,
|
| 114 |
+
"learning_rate": 1.2843695813723062e-05,
|
| 115 |
+
"loss": 0.8717,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.35,
|
| 120 |
+
"learning_rate": 1.0779456692263231e-05,
|
| 121 |
+
"loss": 0.8513,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.48,
|
| 126 |
+
"learning_rate": 8.715217570803403e-06,
|
| 127 |
+
"loss": 0.8391,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.6,
|
| 132 |
+
"learning_rate": 6.650978449343573e-06,
|
| 133 |
+
"loss": 0.8317,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.72,
|
| 138 |
+
"learning_rate": 4.586739327883742e-06,
|
| 139 |
+
"loss": 0.8231,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.85,
|
| 144 |
+
"learning_rate": 2.522500206423912e-06,
|
| 145 |
+
"loss": 0.8137,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.97,
|
| 150 |
+
"learning_rate": 4.5826108496408225e-07,
|
| 151 |
+
"loss": 0.8145,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.0,
|
| 156 |
+
"step": 12111,
|
| 157 |
+
"total_flos": 1.1295642461038182e+17,
|
| 158 |
+
"train_loss": 1.0889082555776386,
|
| 159 |
+
"train_runtime": 7447.3904,
|
| 160 |
+
"train_samples_per_second": 16.262,
|
| 161 |
+
"train_steps_per_second": 1.626
|
| 162 |
+
}
|
| 163 |
+
],
|
| 164 |
+
"max_steps": 12111,
|
| 165 |
+
"num_train_epochs": 3,
|
| 166 |
+
"total_flos": 1.1295642461038182e+17,
|
| 167 |
+
"trial_name": null,
|
| 168 |
+
"trial_params": null
|
| 169 |
+
}
|