End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +627 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.97,
|
| 3 |
+
"eval_loss": 0.00046362177818082273,
|
| 4 |
+
"eval_mse": 0.00046362175269109836,
|
| 5 |
+
"eval_runtime": 8.3552,
|
| 6 |
+
"eval_samples": 313,
|
| 7 |
+
"eval_samples_per_second": 37.462,
|
| 8 |
+
"eval_steps_per_second": 9.455,
|
| 9 |
+
"train_loss": 0.0036955964937131257,
|
| 10 |
+
"train_runtime": 2019.4918,
|
| 11 |
+
"train_samples": 5945,
|
| 12 |
+
"train_samples_per_second": 8.831,
|
| 13 |
+
"train_steps_per_second": 0.137
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.97,
|
| 3 |
+
"eval_loss": 0.00046362177818082273,
|
| 4 |
+
"eval_mse": 0.00046362175269109836,
|
| 5 |
+
"eval_runtime": 8.3552,
|
| 6 |
+
"eval_samples": 313,
|
| 7 |
+
"eval_samples_per_second": 37.462,
|
| 8 |
+
"eval_steps_per_second": 9.455
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.97,
|
| 3 |
+
"train_loss": 0.0036955964937131257,
|
| 4 |
+
"train_runtime": 2019.4918,
|
| 5 |
+
"train_samples": 5945,
|
| 6 |
+
"train_samples_per_second": 8.831,
|
| 7 |
+
"train_steps_per_second": 0.137
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,627 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9697377269670477,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 276,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 14 |
+
"loss": 0.01,
|
| 15 |
+
"step": 3
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"learning_rate": 8.571428571428571e-06,
|
| 20 |
+
"loss": 0.0093,
|
| 21 |
+
"step": 6
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 1.2857142857142859e-05,
|
| 26 |
+
"loss": 0.0089,
|
| 27 |
+
"step": 9
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.13,
|
| 31 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 32 |
+
"loss": 0.0091,
|
| 33 |
+
"step": 12
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.16,
|
| 37 |
+
"learning_rate": 1.9923664122137406e-05,
|
| 38 |
+
"loss": 0.0095,
|
| 39 |
+
"step": 15
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.19,
|
| 43 |
+
"learning_rate": 1.969465648854962e-05,
|
| 44 |
+
"loss": 0.0081,
|
| 45 |
+
"step": 18
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.23,
|
| 49 |
+
"learning_rate": 1.9465648854961833e-05,
|
| 50 |
+
"loss": 0.0073,
|
| 51 |
+
"step": 21
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.26,
|
| 55 |
+
"learning_rate": 1.923664122137405e-05,
|
| 56 |
+
"loss": 0.0082,
|
| 57 |
+
"step": 24
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.29,
|
| 61 |
+
"learning_rate": 1.900763358778626e-05,
|
| 62 |
+
"loss": 0.0063,
|
| 63 |
+
"step": 27
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.32,
|
| 67 |
+
"learning_rate": 1.8778625954198473e-05,
|
| 68 |
+
"loss": 0.0077,
|
| 69 |
+
"step": 30
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.36,
|
| 73 |
+
"learning_rate": 1.854961832061069e-05,
|
| 74 |
+
"loss": 0.006,
|
| 75 |
+
"step": 33
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.39,
|
| 79 |
+
"learning_rate": 1.83206106870229e-05,
|
| 80 |
+
"loss": 0.0064,
|
| 81 |
+
"step": 36
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.42,
|
| 85 |
+
"learning_rate": 1.8091603053435117e-05,
|
| 86 |
+
"loss": 0.0056,
|
| 87 |
+
"step": 39
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.45,
|
| 91 |
+
"learning_rate": 1.786259541984733e-05,
|
| 92 |
+
"loss": 0.0055,
|
| 93 |
+
"step": 42
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.48,
|
| 97 |
+
"learning_rate": 1.7633587786259544e-05,
|
| 98 |
+
"loss": 0.0052,
|
| 99 |
+
"step": 45
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.52,
|
| 103 |
+
"learning_rate": 1.7404580152671757e-05,
|
| 104 |
+
"loss": 0.0064,
|
| 105 |
+
"step": 48
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.54,
|
| 109 |
+
"eval_loss": 0.000551095581613481,
|
| 110 |
+
"eval_mse": 0.0005510955593948523,
|
| 111 |
+
"eval_runtime": 8.5427,
|
| 112 |
+
"eval_samples_per_second": 36.64,
|
| 113 |
+
"eval_steps_per_second": 9.248,
|
| 114 |
+
"step": 50
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.55,
|
| 118 |
+
"learning_rate": 1.717557251908397e-05,
|
| 119 |
+
"loss": 0.0061,
|
| 120 |
+
"step": 51
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.58,
|
| 124 |
+
"learning_rate": 1.6946564885496184e-05,
|
| 125 |
+
"loss": 0.0052,
|
| 126 |
+
"step": 54
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.61,
|
| 130 |
+
"learning_rate": 1.6717557251908398e-05,
|
| 131 |
+
"loss": 0.0053,
|
| 132 |
+
"step": 57
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.65,
|
| 136 |
+
"learning_rate": 1.648854961832061e-05,
|
| 137 |
+
"loss": 0.0043,
|
| 138 |
+
"step": 60
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.68,
|
| 142 |
+
"learning_rate": 1.6259541984732825e-05,
|
| 143 |
+
"loss": 0.0035,
|
| 144 |
+
"step": 63
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.71,
|
| 148 |
+
"learning_rate": 1.6030534351145038e-05,
|
| 149 |
+
"loss": 0.0041,
|
| 150 |
+
"step": 66
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.74,
|
| 154 |
+
"learning_rate": 1.5801526717557255e-05,
|
| 155 |
+
"loss": 0.0046,
|
| 156 |
+
"step": 69
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.77,
|
| 160 |
+
"learning_rate": 1.5572519083969465e-05,
|
| 161 |
+
"loss": 0.0036,
|
| 162 |
+
"step": 72
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.81,
|
| 166 |
+
"learning_rate": 1.5343511450381682e-05,
|
| 167 |
+
"loss": 0.0042,
|
| 168 |
+
"step": 75
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.84,
|
| 172 |
+
"learning_rate": 1.5114503816793895e-05,
|
| 173 |
+
"loss": 0.0037,
|
| 174 |
+
"step": 78
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.87,
|
| 178 |
+
"learning_rate": 1.4885496183206107e-05,
|
| 179 |
+
"loss": 0.0039,
|
| 180 |
+
"step": 81
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.9,
|
| 184 |
+
"learning_rate": 1.4656488549618322e-05,
|
| 185 |
+
"loss": 0.0027,
|
| 186 |
+
"step": 84
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.94,
|
| 190 |
+
"learning_rate": 1.4427480916030536e-05,
|
| 191 |
+
"loss": 0.003,
|
| 192 |
+
"step": 87
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.97,
|
| 196 |
+
"learning_rate": 1.4198473282442749e-05,
|
| 197 |
+
"loss": 0.0031,
|
| 198 |
+
"step": 90
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.0,
|
| 202 |
+
"learning_rate": 1.3969465648854963e-05,
|
| 203 |
+
"loss": 0.0032,
|
| 204 |
+
"step": 93
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.03,
|
| 208 |
+
"learning_rate": 1.3740458015267178e-05,
|
| 209 |
+
"loss": 0.0031,
|
| 210 |
+
"step": 96
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.07,
|
| 214 |
+
"learning_rate": 1.351145038167939e-05,
|
| 215 |
+
"loss": 0.0043,
|
| 216 |
+
"step": 99
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.08,
|
| 220 |
+
"eval_loss": 0.0004679011180996895,
|
| 221 |
+
"eval_mse": 0.00046790109512442456,
|
| 222 |
+
"eval_runtime": 8.5901,
|
| 223 |
+
"eval_samples_per_second": 36.437,
|
| 224 |
+
"eval_steps_per_second": 9.197,
|
| 225 |
+
"step": 100
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.1,
|
| 229 |
+
"learning_rate": 1.3282442748091605e-05,
|
| 230 |
+
"loss": 0.0032,
|
| 231 |
+
"step": 102
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.13,
|
| 235 |
+
"learning_rate": 1.3053435114503818e-05,
|
| 236 |
+
"loss": 0.0037,
|
| 237 |
+
"step": 105
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.16,
|
| 241 |
+
"learning_rate": 1.2824427480916032e-05,
|
| 242 |
+
"loss": 0.0026,
|
| 243 |
+
"step": 108
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.19,
|
| 247 |
+
"learning_rate": 1.2595419847328245e-05,
|
| 248 |
+
"loss": 0.003,
|
| 249 |
+
"step": 111
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.23,
|
| 253 |
+
"learning_rate": 1.236641221374046e-05,
|
| 254 |
+
"loss": 0.0027,
|
| 255 |
+
"step": 114
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.26,
|
| 259 |
+
"learning_rate": 1.2137404580152672e-05,
|
| 260 |
+
"loss": 0.0034,
|
| 261 |
+
"step": 117
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.29,
|
| 265 |
+
"learning_rate": 1.1908396946564887e-05,
|
| 266 |
+
"loss": 0.0031,
|
| 267 |
+
"step": 120
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.32,
|
| 271 |
+
"learning_rate": 1.16793893129771e-05,
|
| 272 |
+
"loss": 0.0038,
|
| 273 |
+
"step": 123
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.36,
|
| 277 |
+
"learning_rate": 1.1450381679389312e-05,
|
| 278 |
+
"loss": 0.003,
|
| 279 |
+
"step": 126
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.39,
|
| 283 |
+
"learning_rate": 1.1221374045801527e-05,
|
| 284 |
+
"loss": 0.003,
|
| 285 |
+
"step": 129
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.42,
|
| 289 |
+
"learning_rate": 1.0992366412213743e-05,
|
| 290 |
+
"loss": 0.0032,
|
| 291 |
+
"step": 132
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.45,
|
| 295 |
+
"learning_rate": 1.0763358778625954e-05,
|
| 296 |
+
"loss": 0.0028,
|
| 297 |
+
"step": 135
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.48,
|
| 301 |
+
"learning_rate": 1.0534351145038168e-05,
|
| 302 |
+
"loss": 0.003,
|
| 303 |
+
"step": 138
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.52,
|
| 307 |
+
"learning_rate": 1.0305343511450383e-05,
|
| 308 |
+
"loss": 0.0025,
|
| 309 |
+
"step": 141
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.55,
|
| 313 |
+
"learning_rate": 1.0076335877862595e-05,
|
| 314 |
+
"loss": 0.0033,
|
| 315 |
+
"step": 144
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.58,
|
| 319 |
+
"learning_rate": 9.84732824427481e-06,
|
| 320 |
+
"loss": 0.0031,
|
| 321 |
+
"step": 147
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.61,
|
| 325 |
+
"learning_rate": 9.618320610687025e-06,
|
| 326 |
+
"loss": 0.0028,
|
| 327 |
+
"step": 150
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.61,
|
| 331 |
+
"eval_loss": 0.0006046506459824741,
|
| 332 |
+
"eval_mse": 0.0006046506115009975,
|
| 333 |
+
"eval_runtime": 8.4067,
|
| 334 |
+
"eval_samples_per_second": 37.232,
|
| 335 |
+
"eval_steps_per_second": 9.397,
|
| 336 |
+
"step": 150
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.65,
|
| 340 |
+
"learning_rate": 9.389312977099237e-06,
|
| 341 |
+
"loss": 0.0029,
|
| 342 |
+
"step": 153
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.68,
|
| 346 |
+
"learning_rate": 9.16030534351145e-06,
|
| 347 |
+
"loss": 0.0029,
|
| 348 |
+
"step": 156
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.71,
|
| 352 |
+
"learning_rate": 8.931297709923665e-06,
|
| 353 |
+
"loss": 0.0021,
|
| 354 |
+
"step": 159
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.74,
|
| 358 |
+
"learning_rate": 8.702290076335879e-06,
|
| 359 |
+
"loss": 0.0029,
|
| 360 |
+
"step": 162
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.78,
|
| 364 |
+
"learning_rate": 8.473282442748092e-06,
|
| 365 |
+
"loss": 0.0026,
|
| 366 |
+
"step": 165
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.81,
|
| 370 |
+
"learning_rate": 8.244274809160306e-06,
|
| 371 |
+
"loss": 0.0028,
|
| 372 |
+
"step": 168
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.84,
|
| 376 |
+
"learning_rate": 8.015267175572519e-06,
|
| 377 |
+
"loss": 0.0031,
|
| 378 |
+
"step": 171
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.87,
|
| 382 |
+
"learning_rate": 7.786259541984733e-06,
|
| 383 |
+
"loss": 0.0024,
|
| 384 |
+
"step": 174
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.9,
|
| 388 |
+
"learning_rate": 7.557251908396948e-06,
|
| 389 |
+
"loss": 0.0021,
|
| 390 |
+
"step": 177
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.94,
|
| 394 |
+
"learning_rate": 7.328244274809161e-06,
|
| 395 |
+
"loss": 0.0024,
|
| 396 |
+
"step": 180
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.97,
|
| 400 |
+
"learning_rate": 7.0992366412213746e-06,
|
| 401 |
+
"loss": 0.0024,
|
| 402 |
+
"step": 183
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.0,
|
| 406 |
+
"learning_rate": 6.870229007633589e-06,
|
| 407 |
+
"loss": 0.0025,
|
| 408 |
+
"step": 186
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.03,
|
| 412 |
+
"learning_rate": 6.641221374045802e-06,
|
| 413 |
+
"loss": 0.0024,
|
| 414 |
+
"step": 189
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.07,
|
| 418 |
+
"learning_rate": 6.412213740458016e-06,
|
| 419 |
+
"loss": 0.0027,
|
| 420 |
+
"step": 192
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.1,
|
| 424 |
+
"learning_rate": 6.18320610687023e-06,
|
| 425 |
+
"loss": 0.0029,
|
| 426 |
+
"step": 195
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.13,
|
| 430 |
+
"learning_rate": 5.9541984732824435e-06,
|
| 431 |
+
"loss": 0.0025,
|
| 432 |
+
"step": 198
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.15,
|
| 436 |
+
"eval_loss": 0.0004669851914513856,
|
| 437 |
+
"eval_mse": 0.0004669852106191058,
|
| 438 |
+
"eval_runtime": 8.5435,
|
| 439 |
+
"eval_samples_per_second": 36.636,
|
| 440 |
+
"eval_steps_per_second": 9.247,
|
| 441 |
+
"step": 200
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.16,
|
| 445 |
+
"learning_rate": 5.725190839694656e-06,
|
| 446 |
+
"loss": 0.002,
|
| 447 |
+
"step": 201
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.2,
|
| 451 |
+
"learning_rate": 5.496183206106871e-06,
|
| 452 |
+
"loss": 0.0026,
|
| 453 |
+
"step": 204
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.23,
|
| 457 |
+
"learning_rate": 5.267175572519084e-06,
|
| 458 |
+
"loss": 0.0024,
|
| 459 |
+
"step": 207
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.26,
|
| 463 |
+
"learning_rate": 5.038167938931297e-06,
|
| 464 |
+
"loss": 0.0025,
|
| 465 |
+
"step": 210
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.29,
|
| 469 |
+
"learning_rate": 4.8091603053435125e-06,
|
| 470 |
+
"loss": 0.0022,
|
| 471 |
+
"step": 213
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.32,
|
| 475 |
+
"learning_rate": 4.580152671755725e-06,
|
| 476 |
+
"loss": 0.002,
|
| 477 |
+
"step": 216
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.36,
|
| 481 |
+
"learning_rate": 4.351145038167939e-06,
|
| 482 |
+
"loss": 0.0024,
|
| 483 |
+
"step": 219
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.39,
|
| 487 |
+
"learning_rate": 4.122137404580153e-06,
|
| 488 |
+
"loss": 0.0021,
|
| 489 |
+
"step": 222
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.42,
|
| 493 |
+
"learning_rate": 3.893129770992366e-06,
|
| 494 |
+
"loss": 0.0019,
|
| 495 |
+
"step": 225
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.45,
|
| 499 |
+
"learning_rate": 3.6641221374045806e-06,
|
| 500 |
+
"loss": 0.0021,
|
| 501 |
+
"step": 228
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.49,
|
| 505 |
+
"learning_rate": 3.4351145038167944e-06,
|
| 506 |
+
"loss": 0.0027,
|
| 507 |
+
"step": 231
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.52,
|
| 511 |
+
"learning_rate": 3.206106870229008e-06,
|
| 512 |
+
"loss": 0.0024,
|
| 513 |
+
"step": 234
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.55,
|
| 517 |
+
"learning_rate": 2.9770992366412218e-06,
|
| 518 |
+
"loss": 0.0024,
|
| 519 |
+
"step": 237
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.58,
|
| 523 |
+
"learning_rate": 2.7480916030534356e-06,
|
| 524 |
+
"loss": 0.0021,
|
| 525 |
+
"step": 240
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.61,
|
| 529 |
+
"learning_rate": 2.5190839694656487e-06,
|
| 530 |
+
"loss": 0.0019,
|
| 531 |
+
"step": 243
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.65,
|
| 535 |
+
"learning_rate": 2.2900763358778625e-06,
|
| 536 |
+
"loss": 0.0019,
|
| 537 |
+
"step": 246
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.68,
|
| 541 |
+
"learning_rate": 2.0610687022900764e-06,
|
| 542 |
+
"loss": 0.0025,
|
| 543 |
+
"step": 249
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.69,
|
| 547 |
+
"eval_loss": 0.00047420692862942815,
|
| 548 |
+
"eval_mse": 0.00047420695769180793,
|
| 549 |
+
"eval_runtime": 8.5496,
|
| 550 |
+
"eval_samples_per_second": 36.61,
|
| 551 |
+
"eval_steps_per_second": 9.24,
|
| 552 |
+
"step": 250
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.71,
|
| 556 |
+
"learning_rate": 1.8320610687022903e-06,
|
| 557 |
+
"loss": 0.0021,
|
| 558 |
+
"step": 252
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 2.74,
|
| 562 |
+
"learning_rate": 1.603053435114504e-06,
|
| 563 |
+
"loss": 0.0024,
|
| 564 |
+
"step": 255
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.78,
|
| 568 |
+
"learning_rate": 1.3740458015267178e-06,
|
| 569 |
+
"loss": 0.0024,
|
| 570 |
+
"step": 258
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.81,
|
| 574 |
+
"learning_rate": 1.1450381679389313e-06,
|
| 575 |
+
"loss": 0.0021,
|
| 576 |
+
"step": 261
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.84,
|
| 580 |
+
"learning_rate": 9.160305343511451e-07,
|
| 581 |
+
"loss": 0.0026,
|
| 582 |
+
"step": 264
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 2.87,
|
| 586 |
+
"learning_rate": 6.870229007633589e-07,
|
| 587 |
+
"loss": 0.0023,
|
| 588 |
+
"step": 267
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.91,
|
| 592 |
+
"learning_rate": 4.5801526717557257e-07,
|
| 593 |
+
"loss": 0.0021,
|
| 594 |
+
"step": 270
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.94,
|
| 598 |
+
"learning_rate": 2.2900763358778629e-07,
|
| 599 |
+
"loss": 0.0026,
|
| 600 |
+
"step": 273
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 2.97,
|
| 604 |
+
"learning_rate": 0.0,
|
| 605 |
+
"loss": 0.0024,
|
| 606 |
+
"step": 276
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.97,
|
| 610 |
+
"step": 276,
|
| 611 |
+
"total_flos": 4678301863342080.0,
|
| 612 |
+
"train_loss": 0.0036955964937131257,
|
| 613 |
+
"train_runtime": 2019.4918,
|
| 614 |
+
"train_samples_per_second": 8.831,
|
| 615 |
+
"train_steps_per_second": 0.137
|
| 616 |
+
}
|
| 617 |
+
],
|
| 618 |
+
"logging_steps": 3,
|
| 619 |
+
"max_steps": 276,
|
| 620 |
+
"num_input_tokens_seen": 0,
|
| 621 |
+
"num_train_epochs": 3,
|
| 622 |
+
"save_steps": 100,
|
| 623 |
+
"total_flos": 4678301863342080.0,
|
| 624 |
+
"train_batch_size": 4,
|
| 625 |
+
"trial_name": null,
|
| 626 |
+
"trial_params": null
|
| 627 |
+
}
|