Commit
•
090403e
1
Parent(s):
3babf51
Upload trainer_state.json
Browse files- trainer_state.json +716 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,716 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9998000399920016,
|
| 5 |
+
"global_step": 5000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 4.9000199960008e-05,
|
| 13 |
+
"loss": 2.3432,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"eval_loss": 1.4642062187194824,
|
| 19 |
+
"eval_runtime": 608.6446,
|
| 20 |
+
"eval_samples_per_second": 16.428,
|
| 21 |
+
"eval_steps_per_second": 2.054,
|
| 22 |
+
"step": 100
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.04,
|
| 26 |
+
"learning_rate": 4.8000399920015995e-05,
|
| 27 |
+
"loss": 1.4307,
|
| 28 |
+
"step": 200
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.04,
|
| 32 |
+
"eval_loss": 1.2907178401947021,
|
| 33 |
+
"eval_runtime": 609.8275,
|
| 34 |
+
"eval_samples_per_second": 16.396,
|
| 35 |
+
"eval_steps_per_second": 2.05,
|
| 36 |
+
"step": 200
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.06,
|
| 40 |
+
"learning_rate": 4.7000599880024e-05,
|
| 41 |
+
"loss": 1.3923,
|
| 42 |
+
"step": 300
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.06,
|
| 46 |
+
"eval_loss": 1.2444946765899658,
|
| 47 |
+
"eval_runtime": 609.21,
|
| 48 |
+
"eval_samples_per_second": 16.413,
|
| 49 |
+
"eval_steps_per_second": 2.052,
|
| 50 |
+
"step": 300
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.08,
|
| 54 |
+
"learning_rate": 4.6000799840031995e-05,
|
| 55 |
+
"loss": 1.2719,
|
| 56 |
+
"step": 400
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.08,
|
| 60 |
+
"eval_loss": 1.1913342475891113,
|
| 61 |
+
"eval_runtime": 609.6719,
|
| 62 |
+
"eval_samples_per_second": 16.401,
|
| 63 |
+
"eval_steps_per_second": 2.05,
|
| 64 |
+
"step": 400
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.1,
|
| 68 |
+
"learning_rate": 4.5000999800039995e-05,
|
| 69 |
+
"loss": 1.1292,
|
| 70 |
+
"step": 500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.1,
|
| 74 |
+
"eval_loss": 0.996195912361145,
|
| 75 |
+
"eval_runtime": 609.7968,
|
| 76 |
+
"eval_samples_per_second": 16.397,
|
| 77 |
+
"eval_steps_per_second": 2.05,
|
| 78 |
+
"step": 500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.12,
|
| 82 |
+
"learning_rate": 4.4001199760047995e-05,
|
| 83 |
+
"loss": 0.9344,
|
| 84 |
+
"step": 600
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.12,
|
| 88 |
+
"eval_loss": 0.7351303696632385,
|
| 89 |
+
"eval_runtime": 609.8878,
|
| 90 |
+
"eval_samples_per_second": 16.395,
|
| 91 |
+
"eval_steps_per_second": 2.05,
|
| 92 |
+
"step": 600
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.14,
|
| 96 |
+
"learning_rate": 4.300139972005599e-05,
|
| 97 |
+
"loss": 0.7481,
|
| 98 |
+
"step": 700
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.14,
|
| 102 |
+
"eval_loss": 0.6376619338989258,
|
| 103 |
+
"eval_runtime": 609.9126,
|
| 104 |
+
"eval_samples_per_second": 16.394,
|
| 105 |
+
"eval_steps_per_second": 2.049,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.16,
|
| 110 |
+
"learning_rate": 4.200159968006399e-05,
|
| 111 |
+
"loss": 0.6194,
|
| 112 |
+
"step": 800
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.16,
|
| 116 |
+
"eval_loss": 0.48432987928390503,
|
| 117 |
+
"eval_runtime": 609.6991,
|
| 118 |
+
"eval_samples_per_second": 16.4,
|
| 119 |
+
"eval_steps_per_second": 2.05,
|
| 120 |
+
"step": 800
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.18,
|
| 124 |
+
"learning_rate": 4.100179964007199e-05,
|
| 125 |
+
"loss": 0.4363,
|
| 126 |
+
"step": 900
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.18,
|
| 130 |
+
"eval_loss": 0.4042782783508301,
|
| 131 |
+
"eval_runtime": 609.9266,
|
| 132 |
+
"eval_samples_per_second": 16.394,
|
| 133 |
+
"eval_steps_per_second": 2.049,
|
| 134 |
+
"step": 900
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.2,
|
| 138 |
+
"learning_rate": 4.000199960007999e-05,
|
| 139 |
+
"loss": 0.416,
|
| 140 |
+
"step": 1000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.2,
|
| 144 |
+
"eval_loss": 0.36932361125946045,
|
| 145 |
+
"eval_runtime": 609.5733,
|
| 146 |
+
"eval_samples_per_second": 16.403,
|
| 147 |
+
"eval_steps_per_second": 2.051,
|
| 148 |
+
"step": 1000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.22,
|
| 152 |
+
"learning_rate": 3.900219956008798e-05,
|
| 153 |
+
"loss": 0.3295,
|
| 154 |
+
"step": 1100
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.22,
|
| 158 |
+
"eval_loss": 0.351975679397583,
|
| 159 |
+
"eval_runtime": 609.6621,
|
| 160 |
+
"eval_samples_per_second": 16.401,
|
| 161 |
+
"eval_steps_per_second": 2.05,
|
| 162 |
+
"step": 1100
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.24,
|
| 166 |
+
"learning_rate": 3.800239952009598e-05,
|
| 167 |
+
"loss": 0.3416,
|
| 168 |
+
"step": 1200
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.24,
|
| 172 |
+
"eval_loss": 0.33431148529052734,
|
| 173 |
+
"eval_runtime": 609.7514,
|
| 174 |
+
"eval_samples_per_second": 16.398,
|
| 175 |
+
"eval_steps_per_second": 2.05,
|
| 176 |
+
"step": 1200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.26,
|
| 180 |
+
"learning_rate": 3.700259948010398e-05,
|
| 181 |
+
"loss": 0.3755,
|
| 182 |
+
"step": 1300
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.26,
|
| 186 |
+
"eval_loss": 0.3273898661136627,
|
| 187 |
+
"eval_runtime": 609.2386,
|
| 188 |
+
"eval_samples_per_second": 16.412,
|
| 189 |
+
"eval_steps_per_second": 2.052,
|
| 190 |
+
"step": 1300
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.28,
|
| 194 |
+
"learning_rate": 3.600279944011198e-05,
|
| 195 |
+
"loss": 0.3064,
|
| 196 |
+
"step": 1400
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.28,
|
| 200 |
+
"eval_loss": 0.3126789629459381,
|
| 201 |
+
"eval_runtime": 609.5068,
|
| 202 |
+
"eval_samples_per_second": 16.405,
|
| 203 |
+
"eval_steps_per_second": 2.051,
|
| 204 |
+
"step": 1400
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.3,
|
| 208 |
+
"learning_rate": 3.500299940011998e-05,
|
| 209 |
+
"loss": 0.3295,
|
| 210 |
+
"step": 1500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.3,
|
| 214 |
+
"eval_loss": 0.2998415529727936,
|
| 215 |
+
"eval_runtime": 609.5568,
|
| 216 |
+
"eval_samples_per_second": 16.404,
|
| 217 |
+
"eval_steps_per_second": 2.051,
|
| 218 |
+
"step": 1500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.32,
|
| 222 |
+
"learning_rate": 3.4003199360127974e-05,
|
| 223 |
+
"loss": 0.2928,
|
| 224 |
+
"step": 1600
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.32,
|
| 228 |
+
"eval_loss": 0.2964608073234558,
|
| 229 |
+
"eval_runtime": 609.9976,
|
| 230 |
+
"eval_samples_per_second": 16.392,
|
| 231 |
+
"eval_steps_per_second": 2.049,
|
| 232 |
+
"step": 1600
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.34,
|
| 236 |
+
"learning_rate": 3.3003399320135974e-05,
|
| 237 |
+
"loss": 0.3069,
|
| 238 |
+
"step": 1700
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.34,
|
| 242 |
+
"eval_loss": 0.2876538336277008,
|
| 243 |
+
"eval_runtime": 609.9834,
|
| 244 |
+
"eval_samples_per_second": 16.392,
|
| 245 |
+
"eval_steps_per_second": 2.049,
|
| 246 |
+
"step": 1700
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.36,
|
| 250 |
+
"learning_rate": 3.2003599280143974e-05,
|
| 251 |
+
"loss": 0.3048,
|
| 252 |
+
"step": 1800
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.36,
|
| 256 |
+
"eval_loss": 0.28498831391334534,
|
| 257 |
+
"eval_runtime": 609.9303,
|
| 258 |
+
"eval_samples_per_second": 16.394,
|
| 259 |
+
"eval_steps_per_second": 2.049,
|
| 260 |
+
"step": 1800
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.38,
|
| 264 |
+
"learning_rate": 3.1003799240151974e-05,
|
| 265 |
+
"loss": 0.2916,
|
| 266 |
+
"step": 1900
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.38,
|
| 270 |
+
"eval_loss": 0.2817072570323944,
|
| 271 |
+
"eval_runtime": 609.733,
|
| 272 |
+
"eval_samples_per_second": 16.399,
|
| 273 |
+
"eval_steps_per_second": 2.05,
|
| 274 |
+
"step": 1900
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.4,
|
| 278 |
+
"learning_rate": 3.000399920015997e-05,
|
| 279 |
+
"loss": 0.2979,
|
| 280 |
+
"step": 2000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.4,
|
| 284 |
+
"eval_loss": 0.2590666711330414,
|
| 285 |
+
"eval_runtime": 609.3809,
|
| 286 |
+
"eval_samples_per_second": 16.408,
|
| 287 |
+
"eval_steps_per_second": 2.051,
|
| 288 |
+
"step": 2000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.42,
|
| 292 |
+
"learning_rate": 2.9004199160167967e-05,
|
| 293 |
+
"loss": 0.2846,
|
| 294 |
+
"step": 2100
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.42,
|
| 298 |
+
"eval_loss": 0.2540070712566376,
|
| 299 |
+
"eval_runtime": 609.9231,
|
| 300 |
+
"eval_samples_per_second": 16.394,
|
| 301 |
+
"eval_steps_per_second": 2.049,
|
| 302 |
+
"step": 2100
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.44,
|
| 306 |
+
"learning_rate": 2.8004399120175967e-05,
|
| 307 |
+
"loss": 0.2568,
|
| 308 |
+
"step": 2200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.44,
|
| 312 |
+
"eval_loss": 0.3389109969139099,
|
| 313 |
+
"eval_runtime": 610.1831,
|
| 314 |
+
"eval_samples_per_second": 16.387,
|
| 315 |
+
"eval_steps_per_second": 2.049,
|
| 316 |
+
"step": 2200
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.46,
|
| 320 |
+
"learning_rate": 2.7004599080183964e-05,
|
| 321 |
+
"loss": 0.277,
|
| 322 |
+
"step": 2300
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.46,
|
| 326 |
+
"eval_loss": 0.23687200248241425,
|
| 327 |
+
"eval_runtime": 609.7591,
|
| 328 |
+
"eval_samples_per_second": 16.398,
|
| 329 |
+
"eval_steps_per_second": 2.05,
|
| 330 |
+
"step": 2300
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.48,
|
| 334 |
+
"learning_rate": 2.6004799040191963e-05,
|
| 335 |
+
"loss": 0.2385,
|
| 336 |
+
"step": 2400
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.48,
|
| 340 |
+
"eval_loss": 0.22378966212272644,
|
| 341 |
+
"eval_runtime": 609.717,
|
| 342 |
+
"eval_samples_per_second": 16.399,
|
| 343 |
+
"eval_steps_per_second": 2.05,
|
| 344 |
+
"step": 2400
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.5,
|
| 348 |
+
"learning_rate": 2.5004999000199963e-05,
|
| 349 |
+
"loss": 0.2477,
|
| 350 |
+
"step": 2500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.5,
|
| 354 |
+
"eval_loss": 0.21604961156845093,
|
| 355 |
+
"eval_runtime": 609.6145,
|
| 356 |
+
"eval_samples_per_second": 16.402,
|
| 357 |
+
"eval_steps_per_second": 2.05,
|
| 358 |
+
"step": 2500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.52,
|
| 362 |
+
"learning_rate": 2.400519896020796e-05,
|
| 363 |
+
"loss": 0.2271,
|
| 364 |
+
"step": 2600
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.52,
|
| 368 |
+
"eval_loss": 0.21389839053153992,
|
| 369 |
+
"eval_runtime": 609.791,
|
| 370 |
+
"eval_samples_per_second": 16.397,
|
| 371 |
+
"eval_steps_per_second": 2.05,
|
| 372 |
+
"step": 2600
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.54,
|
| 376 |
+
"learning_rate": 2.300539892021596e-05,
|
| 377 |
+
"loss": 0.2457,
|
| 378 |
+
"step": 2700
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.54,
|
| 382 |
+
"eval_loss": 0.2024470716714859,
|
| 383 |
+
"eval_runtime": 610.0348,
|
| 384 |
+
"eval_samples_per_second": 16.391,
|
| 385 |
+
"eval_steps_per_second": 2.049,
|
| 386 |
+
"step": 2700
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.56,
|
| 390 |
+
"learning_rate": 2.2005598880223956e-05,
|
| 391 |
+
"loss": 0.2037,
|
| 392 |
+
"step": 2800
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.56,
|
| 396 |
+
"eval_loss": 0.2085147500038147,
|
| 397 |
+
"eval_runtime": 609.8962,
|
| 398 |
+
"eval_samples_per_second": 16.395,
|
| 399 |
+
"eval_steps_per_second": 2.05,
|
| 400 |
+
"step": 2800
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.58,
|
| 404 |
+
"learning_rate": 2.1005798840231956e-05,
|
| 405 |
+
"loss": 0.1865,
|
| 406 |
+
"step": 2900
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.58,
|
| 410 |
+
"eval_loss": 0.19782070815563202,
|
| 411 |
+
"eval_runtime": 610.0823,
|
| 412 |
+
"eval_samples_per_second": 16.39,
|
| 413 |
+
"eval_steps_per_second": 2.049,
|
| 414 |
+
"step": 2900
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.6,
|
| 418 |
+
"learning_rate": 2.0005998800239953e-05,
|
| 419 |
+
"loss": 0.2354,
|
| 420 |
+
"step": 3000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.6,
|
| 424 |
+
"eval_loss": 0.19286589324474335,
|
| 425 |
+
"eval_runtime": 609.7041,
|
| 426 |
+
"eval_samples_per_second": 16.4,
|
| 427 |
+
"eval_steps_per_second": 2.05,
|
| 428 |
+
"step": 3000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.62,
|
| 432 |
+
"learning_rate": 1.900619876024795e-05,
|
| 433 |
+
"loss": 0.2001,
|
| 434 |
+
"step": 3100
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.62,
|
| 438 |
+
"eval_loss": 0.1864747703075409,
|
| 439 |
+
"eval_runtime": 609.9124,
|
| 440 |
+
"eval_samples_per_second": 16.394,
|
| 441 |
+
"eval_steps_per_second": 2.049,
|
| 442 |
+
"step": 3100
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.64,
|
| 446 |
+
"learning_rate": 1.800639872025595e-05,
|
| 447 |
+
"loss": 0.2396,
|
| 448 |
+
"step": 3200
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.64,
|
| 452 |
+
"eval_loss": 0.18323543667793274,
|
| 453 |
+
"eval_runtime": 609.6847,
|
| 454 |
+
"eval_samples_per_second": 16.4,
|
| 455 |
+
"eval_steps_per_second": 2.05,
|
| 456 |
+
"step": 3200
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.66,
|
| 460 |
+
"learning_rate": 1.700659868026395e-05,
|
| 461 |
+
"loss": 0.2197,
|
| 462 |
+
"step": 3300
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.66,
|
| 466 |
+
"eval_loss": 0.17903800308704376,
|
| 467 |
+
"eval_runtime": 609.9785,
|
| 468 |
+
"eval_samples_per_second": 16.392,
|
| 469 |
+
"eval_steps_per_second": 2.049,
|
| 470 |
+
"step": 3300
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.68,
|
| 474 |
+
"learning_rate": 1.6006798640271946e-05,
|
| 475 |
+
"loss": 0.1813,
|
| 476 |
+
"step": 3400
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.68,
|
| 480 |
+
"eval_loss": 0.1766795963048935,
|
| 481 |
+
"eval_runtime": 610.2222,
|
| 482 |
+
"eval_samples_per_second": 16.386,
|
| 483 |
+
"eval_steps_per_second": 2.048,
|
| 484 |
+
"step": 3400
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.7,
|
| 488 |
+
"learning_rate": 1.5006998600279946e-05,
|
| 489 |
+
"loss": 0.2109,
|
| 490 |
+
"step": 3500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.7,
|
| 494 |
+
"eval_loss": 0.19698815047740936,
|
| 495 |
+
"eval_runtime": 609.8891,
|
| 496 |
+
"eval_samples_per_second": 16.395,
|
| 497 |
+
"eval_steps_per_second": 2.05,
|
| 498 |
+
"step": 3500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.72,
|
| 502 |
+
"learning_rate": 1.4007198560287942e-05,
|
| 503 |
+
"loss": 0.1956,
|
| 504 |
+
"step": 3600
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.72,
|
| 508 |
+
"eval_loss": 0.16582651436328888,
|
| 509 |
+
"eval_runtime": 609.6936,
|
| 510 |
+
"eval_samples_per_second": 16.4,
|
| 511 |
+
"eval_steps_per_second": 2.05,
|
| 512 |
+
"step": 3600
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.74,
|
| 516 |
+
"learning_rate": 1.300739852029594e-05,
|
| 517 |
+
"loss": 0.182,
|
| 518 |
+
"step": 3700
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.74,
|
| 522 |
+
"eval_loss": 0.16288767755031586,
|
| 523 |
+
"eval_runtime": 609.0863,
|
| 524 |
+
"eval_samples_per_second": 16.416,
|
| 525 |
+
"eval_steps_per_second": 2.052,
|
| 526 |
+
"step": 3700
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.76,
|
| 530 |
+
"learning_rate": 1.200759848030394e-05,
|
| 531 |
+
"loss": 0.1916,
|
| 532 |
+
"step": 3800
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.76,
|
| 536 |
+
"eval_loss": 0.16099461913108826,
|
| 537 |
+
"eval_runtime": 609.8321,
|
| 538 |
+
"eval_samples_per_second": 16.396,
|
| 539 |
+
"eval_steps_per_second": 2.05,
|
| 540 |
+
"step": 3800
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.78,
|
| 544 |
+
"learning_rate": 1.1007798440311939e-05,
|
| 545 |
+
"loss": 0.1777,
|
| 546 |
+
"step": 3900
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.78,
|
| 550 |
+
"eval_loss": 0.15565015375614166,
|
| 551 |
+
"eval_runtime": 609.8635,
|
| 552 |
+
"eval_samples_per_second": 16.395,
|
| 553 |
+
"eval_steps_per_second": 2.05,
|
| 554 |
+
"step": 3900
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.8,
|
| 558 |
+
"learning_rate": 1.0007998400319935e-05,
|
| 559 |
+
"loss": 0.2005,
|
| 560 |
+
"step": 4000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.8,
|
| 564 |
+
"eval_loss": 0.14921262860298157,
|
| 565 |
+
"eval_runtime": 610.1879,
|
| 566 |
+
"eval_samples_per_second": 16.387,
|
| 567 |
+
"eval_steps_per_second": 2.049,
|
| 568 |
+
"step": 4000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.82,
|
| 572 |
+
"learning_rate": 9.008198360327935e-06,
|
| 573 |
+
"loss": 0.1553,
|
| 574 |
+
"step": 4100
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.82,
|
| 578 |
+
"eval_loss": 0.1529964804649353,
|
| 579 |
+
"eval_runtime": 610.1046,
|
| 580 |
+
"eval_samples_per_second": 16.389,
|
| 581 |
+
"eval_steps_per_second": 2.049,
|
| 582 |
+
"step": 4100
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.84,
|
| 586 |
+
"learning_rate": 8.008398320335933e-06,
|
| 587 |
+
"loss": 0.1631,
|
| 588 |
+
"step": 4200
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.84,
|
| 592 |
+
"eval_loss": 0.14477799832820892,
|
| 593 |
+
"eval_runtime": 610.0122,
|
| 594 |
+
"eval_samples_per_second": 16.391,
|
| 595 |
+
"eval_steps_per_second": 2.049,
|
| 596 |
+
"step": 4200
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.86,
|
| 600 |
+
"learning_rate": 7.008598280343931e-06,
|
| 601 |
+
"loss": 0.1591,
|
| 602 |
+
"step": 4300
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.86,
|
| 606 |
+
"eval_loss": 0.1444890797138214,
|
| 607 |
+
"eval_runtime": 609.9783,
|
| 608 |
+
"eval_samples_per_second": 16.392,
|
| 609 |
+
"eval_steps_per_second": 2.049,
|
| 610 |
+
"step": 4300
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.88,
|
| 614 |
+
"learning_rate": 6.00879824035193e-06,
|
| 615 |
+
"loss": 0.1499,
|
| 616 |
+
"step": 4400
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.88,
|
| 620 |
+
"eval_loss": 0.14274311065673828,
|
| 621 |
+
"eval_runtime": 610.0602,
|
| 622 |
+
"eval_samples_per_second": 16.39,
|
| 623 |
+
"eval_steps_per_second": 2.049,
|
| 624 |
+
"step": 4400
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.9,
|
| 628 |
+
"learning_rate": 5.008998200359928e-06,
|
| 629 |
+
"loss": 0.1487,
|
| 630 |
+
"step": 4500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.9,
|
| 634 |
+
"eval_loss": 0.14181652665138245,
|
| 635 |
+
"eval_runtime": 610.1238,
|
| 636 |
+
"eval_samples_per_second": 16.388,
|
| 637 |
+
"eval_steps_per_second": 2.049,
|
| 638 |
+
"step": 4500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.92,
|
| 642 |
+
"learning_rate": 4.009198160367926e-06,
|
| 643 |
+
"loss": 0.1638,
|
| 644 |
+
"step": 4600
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.92,
|
| 648 |
+
"eval_loss": 0.13808925449848175,
|
| 649 |
+
"eval_runtime": 610.1852,
|
| 650 |
+
"eval_samples_per_second": 16.387,
|
| 651 |
+
"eval_steps_per_second": 2.049,
|
| 652 |
+
"step": 4600
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 0.94,
|
| 656 |
+
"learning_rate": 3.009398120375925e-06,
|
| 657 |
+
"loss": 0.1745,
|
| 658 |
+
"step": 4700
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.94,
|
| 662 |
+
"eval_loss": 0.13902875781059265,
|
| 663 |
+
"eval_runtime": 610.079,
|
| 664 |
+
"eval_samples_per_second": 16.39,
|
| 665 |
+
"eval_steps_per_second": 2.049,
|
| 666 |
+
"step": 4700
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.96,
|
| 670 |
+
"learning_rate": 2.009598080383923e-06,
|
| 671 |
+
"loss": 0.1551,
|
| 672 |
+
"step": 4800
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.96,
|
| 676 |
+
"eval_loss": 0.1366284191608429,
|
| 677 |
+
"eval_runtime": 610.06,
|
| 678 |
+
"eval_samples_per_second": 16.39,
|
| 679 |
+
"eval_steps_per_second": 2.049,
|
| 680 |
+
"step": 4800
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.98,
|
| 684 |
+
"learning_rate": 1.0097980403919217e-06,
|
| 685 |
+
"loss": 0.1408,
|
| 686 |
+
"step": 4900
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.98,
|
| 690 |
+
"eval_loss": 0.1324094831943512,
|
| 691 |
+
"eval_runtime": 610.0607,
|
| 692 |
+
"eval_samples_per_second": 16.39,
|
| 693 |
+
"eval_steps_per_second": 2.049,
|
| 694 |
+
"step": 4900
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.0,
|
| 698 |
+
"learning_rate": 9.998000399920016e-09,
|
| 699 |
+
"loss": 0.1254,
|
| 700 |
+
"step": 5000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.0,
|
| 704 |
+
"eval_loss": 0.13563768565654755,
|
| 705 |
+
"eval_runtime": 610.0968,
|
| 706 |
+
"eval_samples_per_second": 16.389,
|
| 707 |
+
"eval_steps_per_second": 2.049,
|
| 708 |
+
"step": 5000
|
| 709 |
+
}
|
| 710 |
+
],
|
| 711 |
+
"max_steps": 5001,
|
| 712 |
+
"num_train_epochs": 1,
|
| 713 |
+
"total_flos": 1.3204083949028208e+16,
|
| 714 |
+
"trial_name": null,
|
| 715 |
+
"trial_params": null
|
| 716 |
+
}
|