End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +483 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.24,
|
| 3 |
+
"eval_accuracy": 0.3428783934548159,
|
| 4 |
+
"eval_loss": 1.694771409034729,
|
| 5 |
+
"eval_runtime": 695.3156,
|
| 6 |
+
"eval_samples_per_second": 3.867,
|
| 7 |
+
"eval_steps_per_second": 0.485
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.24,
|
| 3 |
+
"eval_accuracy": 0.3428783934548159,
|
| 4 |
+
"eval_loss": 1.694771409034729,
|
| 5 |
+
"eval_runtime": 695.3156,
|
| 6 |
+
"eval_samples_per_second": 3.867,
|
| 7 |
+
"eval_steps_per_second": 0.485
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3429557577659241,
|
| 3 |
+
"best_model_checkpoint": "timesformer-base-finetuned-k400-finetuned-elder/checkpoint-145",
|
| 4 |
+
"epoch": 3.2447916666666665,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 576,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"grad_norm": 11.353941917419434,
|
| 14 |
+
"learning_rate": 8.620689655172414e-06,
|
| 15 |
+
"loss": 1.8739,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"grad_norm": 11.876654624938965,
|
| 21 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 22 |
+
"loss": 1.7689,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05,
|
| 27 |
+
"grad_norm": 9.898606300354004,
|
| 28 |
+
"learning_rate": 2.5862068965517244e-05,
|
| 29 |
+
"loss": 1.6938,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07,
|
| 34 |
+
"grad_norm": 11.877754211425781,
|
| 35 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 36 |
+
"loss": 1.6831,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.09,
|
| 41 |
+
"grad_norm": 11.96393871307373,
|
| 42 |
+
"learning_rate": 4.3103448275862066e-05,
|
| 43 |
+
"loss": 1.8106,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1,
|
| 48 |
+
"grad_norm": 11.26883316040039,
|
| 49 |
+
"learning_rate": 4.980694980694981e-05,
|
| 50 |
+
"loss": 1.7056,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.12,
|
| 55 |
+
"grad_norm": 10.789453506469727,
|
| 56 |
+
"learning_rate": 4.884169884169885e-05,
|
| 57 |
+
"loss": 1.8426,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.14,
|
| 62 |
+
"grad_norm": 11.942329406738281,
|
| 63 |
+
"learning_rate": 4.787644787644788e-05,
|
| 64 |
+
"loss": 1.8344,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.16,
|
| 69 |
+
"grad_norm": 9.601066589355469,
|
| 70 |
+
"learning_rate": 4.6911196911196914e-05,
|
| 71 |
+
"loss": 1.6152,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.17,
|
| 76 |
+
"grad_norm": 7.940020561218262,
|
| 77 |
+
"learning_rate": 4.594594594594595e-05,
|
| 78 |
+
"loss": 1.661,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.19,
|
| 83 |
+
"grad_norm": 8.261001586914062,
|
| 84 |
+
"learning_rate": 4.498069498069498e-05,
|
| 85 |
+
"loss": 1.7736,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.21,
|
| 90 |
+
"grad_norm": 10.65363883972168,
|
| 91 |
+
"learning_rate": 4.401544401544402e-05,
|
| 92 |
+
"loss": 1.6354,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.23,
|
| 97 |
+
"grad_norm": 7.867549896240234,
|
| 98 |
+
"learning_rate": 4.305019305019305e-05,
|
| 99 |
+
"loss": 1.7635,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.24,
|
| 104 |
+
"grad_norm": 5.6440958976745605,
|
| 105 |
+
"learning_rate": 4.2084942084942086e-05,
|
| 106 |
+
"loss": 1.5696,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.25,
|
| 111 |
+
"eval_accuracy": 0.3429557577659241,
|
| 112 |
+
"eval_loss": 1.6705849170684814,
|
| 113 |
+
"eval_runtime": 1154.9511,
|
| 114 |
+
"eval_samples_per_second": 2.759,
|
| 115 |
+
"eval_steps_per_second": 0.345,
|
| 116 |
+
"step": 145
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.01,
|
| 120 |
+
"grad_norm": 10.702627182006836,
|
| 121 |
+
"learning_rate": 4.111969111969112e-05,
|
| 122 |
+
"loss": 1.622,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.03,
|
| 127 |
+
"grad_norm": 8.490106582641602,
|
| 128 |
+
"learning_rate": 4.015444015444015e-05,
|
| 129 |
+
"loss": 1.6023,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.04,
|
| 134 |
+
"grad_norm": 8.917444229125977,
|
| 135 |
+
"learning_rate": 3.918918918918919e-05,
|
| 136 |
+
"loss": 1.553,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.06,
|
| 141 |
+
"grad_norm": 7.563806533813477,
|
| 142 |
+
"learning_rate": 3.822393822393823e-05,
|
| 143 |
+
"loss": 1.7744,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.08,
|
| 148 |
+
"grad_norm": 12.07093334197998,
|
| 149 |
+
"learning_rate": 3.725868725868726e-05,
|
| 150 |
+
"loss": 1.6268,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.1,
|
| 155 |
+
"grad_norm": 10.829654693603516,
|
| 156 |
+
"learning_rate": 3.6293436293436295e-05,
|
| 157 |
+
"loss": 1.7149,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.11,
|
| 162 |
+
"grad_norm": 7.444002628326416,
|
| 163 |
+
"learning_rate": 3.532818532818533e-05,
|
| 164 |
+
"loss": 1.6117,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.13,
|
| 169 |
+
"grad_norm": 8.430509567260742,
|
| 170 |
+
"learning_rate": 3.436293436293436e-05,
|
| 171 |
+
"loss": 1.5871,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.15,
|
| 176 |
+
"grad_norm": 7.962520122528076,
|
| 177 |
+
"learning_rate": 3.33976833976834e-05,
|
| 178 |
+
"loss": 1.6071,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.16,
|
| 183 |
+
"grad_norm": 6.775651454925537,
|
| 184 |
+
"learning_rate": 3.2432432432432436e-05,
|
| 185 |
+
"loss": 1.5901,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.18,
|
| 190 |
+
"grad_norm": 8.024240493774414,
|
| 191 |
+
"learning_rate": 3.1467181467181466e-05,
|
| 192 |
+
"loss": 1.5367,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.2,
|
| 197 |
+
"grad_norm": 6.758663177490234,
|
| 198 |
+
"learning_rate": 3.0501930501930504e-05,
|
| 199 |
+
"loss": 1.5108,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.22,
|
| 204 |
+
"grad_norm": 4.902159690856934,
|
| 205 |
+
"learning_rate": 2.953667953667954e-05,
|
| 206 |
+
"loss": 1.6178,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.23,
|
| 211 |
+
"grad_norm": 8.776327133178711,
|
| 212 |
+
"learning_rate": 2.857142857142857e-05,
|
| 213 |
+
"loss": 1.5294,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.25,
|
| 218 |
+
"grad_norm": 7.898609638214111,
|
| 219 |
+
"learning_rate": 2.7606177606177608e-05,
|
| 220 |
+
"loss": 1.5394,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.25,
|
| 225 |
+
"eval_accuracy": 0.3250705993096956,
|
| 226 |
+
"eval_loss": 1.6106971502304077,
|
| 227 |
+
"eval_runtime": 810.1945,
|
| 228 |
+
"eval_samples_per_second": 3.934,
|
| 229 |
+
"eval_steps_per_second": 0.492,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.02,
|
| 234 |
+
"grad_norm": 8.846714973449707,
|
| 235 |
+
"learning_rate": 2.6640926640926645e-05,
|
| 236 |
+
"loss": 1.4717,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.03,
|
| 241 |
+
"grad_norm": 6.829111099243164,
|
| 242 |
+
"learning_rate": 2.5675675675675675e-05,
|
| 243 |
+
"loss": 1.6512,
|
| 244 |
+
"step": 310
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.05,
|
| 248 |
+
"grad_norm": 7.631171226501465,
|
| 249 |
+
"learning_rate": 2.4710424710424712e-05,
|
| 250 |
+
"loss": 1.5668,
|
| 251 |
+
"step": 320
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.07,
|
| 255 |
+
"grad_norm": 8.5497465133667,
|
| 256 |
+
"learning_rate": 2.3745173745173746e-05,
|
| 257 |
+
"loss": 1.4588,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.09,
|
| 262 |
+
"grad_norm": 11.353889465332031,
|
| 263 |
+
"learning_rate": 2.277992277992278e-05,
|
| 264 |
+
"loss": 1.531,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.1,
|
| 269 |
+
"grad_norm": 11.622316360473633,
|
| 270 |
+
"learning_rate": 2.1814671814671817e-05,
|
| 271 |
+
"loss": 1.4747,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.12,
|
| 276 |
+
"grad_norm": 5.152277946472168,
|
| 277 |
+
"learning_rate": 2.084942084942085e-05,
|
| 278 |
+
"loss": 1.6246,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.14,
|
| 283 |
+
"grad_norm": 8.466754913330078,
|
| 284 |
+
"learning_rate": 1.9884169884169884e-05,
|
| 285 |
+
"loss": 1.6078,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.16,
|
| 290 |
+
"grad_norm": 9.230478286743164,
|
| 291 |
+
"learning_rate": 1.891891891891892e-05,
|
| 292 |
+
"loss": 1.4345,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.17,
|
| 297 |
+
"grad_norm": 6.181694507598877,
|
| 298 |
+
"learning_rate": 1.7953667953667955e-05,
|
| 299 |
+
"loss": 1.4972,
|
| 300 |
+
"step": 390
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.19,
|
| 304 |
+
"grad_norm": 5.838415622711182,
|
| 305 |
+
"learning_rate": 1.698841698841699e-05,
|
| 306 |
+
"loss": 1.5436,
|
| 307 |
+
"step": 400
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.21,
|
| 311 |
+
"grad_norm": 5.769914627075195,
|
| 312 |
+
"learning_rate": 1.6023166023166026e-05,
|
| 313 |
+
"loss": 1.4575,
|
| 314 |
+
"step": 410
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.23,
|
| 318 |
+
"grad_norm": 13.202679634094238,
|
| 319 |
+
"learning_rate": 1.505791505791506e-05,
|
| 320 |
+
"loss": 1.6595,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.24,
|
| 325 |
+
"grad_norm": 6.772584438323975,
|
| 326 |
+
"learning_rate": 1.4092664092664093e-05,
|
| 327 |
+
"loss": 1.3926,
|
| 328 |
+
"step": 430
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.25,
|
| 332 |
+
"eval_accuracy": 0.3115782867900847,
|
| 333 |
+
"eval_loss": 1.6140949726104736,
|
| 334 |
+
"eval_runtime": 852.1564,
|
| 335 |
+
"eval_samples_per_second": 3.74,
|
| 336 |
+
"eval_steps_per_second": 0.468,
|
| 337 |
+
"step": 435
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.01,
|
| 341 |
+
"grad_norm": 14.996703147888184,
|
| 342 |
+
"learning_rate": 1.3127413127413127e-05,
|
| 343 |
+
"loss": 1.4789,
|
| 344 |
+
"step": 440
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.03,
|
| 348 |
+
"grad_norm": 11.151080131530762,
|
| 349 |
+
"learning_rate": 1.2162162162162164e-05,
|
| 350 |
+
"loss": 1.3946,
|
| 351 |
+
"step": 450
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.04,
|
| 355 |
+
"grad_norm": 18.826932907104492,
|
| 356 |
+
"learning_rate": 1.1196911196911197e-05,
|
| 357 |
+
"loss": 1.4647,
|
| 358 |
+
"step": 460
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 3.06,
|
| 362 |
+
"grad_norm": 7.545161247253418,
|
| 363 |
+
"learning_rate": 1.0231660231660233e-05,
|
| 364 |
+
"loss": 1.4306,
|
| 365 |
+
"step": 470
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.08,
|
| 369 |
+
"grad_norm": 6.167401313781738,
|
| 370 |
+
"learning_rate": 9.266409266409266e-06,
|
| 371 |
+
"loss": 1.4875,
|
| 372 |
+
"step": 480
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.1,
|
| 376 |
+
"grad_norm": 6.006252288818359,
|
| 377 |
+
"learning_rate": 8.301158301158302e-06,
|
| 378 |
+
"loss": 1.3679,
|
| 379 |
+
"step": 490
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.11,
|
| 383 |
+
"grad_norm": 11.11434555053711,
|
| 384 |
+
"learning_rate": 7.335907335907337e-06,
|
| 385 |
+
"loss": 1.3347,
|
| 386 |
+
"step": 500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.13,
|
| 390 |
+
"grad_norm": 14.269789695739746,
|
| 391 |
+
"learning_rate": 6.370656370656371e-06,
|
| 392 |
+
"loss": 1.5499,
|
| 393 |
+
"step": 510
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.15,
|
| 397 |
+
"grad_norm": 10.421883583068848,
|
| 398 |
+
"learning_rate": 5.405405405405406e-06,
|
| 399 |
+
"loss": 1.3448,
|
| 400 |
+
"step": 520
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.16,
|
| 404 |
+
"grad_norm": 7.902385234832764,
|
| 405 |
+
"learning_rate": 4.4401544401544405e-06,
|
| 406 |
+
"loss": 1.588,
|
| 407 |
+
"step": 530
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.18,
|
| 411 |
+
"grad_norm": 7.623480796813965,
|
| 412 |
+
"learning_rate": 3.474903474903475e-06,
|
| 413 |
+
"loss": 1.3432,
|
| 414 |
+
"step": 540
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.2,
|
| 418 |
+
"grad_norm": 8.848978996276855,
|
| 419 |
+
"learning_rate": 2.5096525096525096e-06,
|
| 420 |
+
"loss": 1.5031,
|
| 421 |
+
"step": 550
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.22,
|
| 425 |
+
"grad_norm": 6.524665355682373,
|
| 426 |
+
"learning_rate": 1.5444015444015445e-06,
|
| 427 |
+
"loss": 1.4014,
|
| 428 |
+
"step": 560
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.23,
|
| 432 |
+
"grad_norm": 11.393948554992676,
|
| 433 |
+
"learning_rate": 5.791505791505791e-07,
|
| 434 |
+
"loss": 1.5686,
|
| 435 |
+
"step": 570
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.24,
|
| 439 |
+
"eval_accuracy": 0.30059617194854094,
|
| 440 |
+
"eval_loss": 1.634132981300354,
|
| 441 |
+
"eval_runtime": 934.7118,
|
| 442 |
+
"eval_samples_per_second": 3.41,
|
| 443 |
+
"eval_steps_per_second": 0.427,
|
| 444 |
+
"step": 576
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 3.24,
|
| 448 |
+
"step": 576,
|
| 449 |
+
"total_flos": 4.0295036866264105e+18,
|
| 450 |
+
"train_loss": 1.5763822098573048,
|
| 451 |
+
"train_runtime": 8421.9334,
|
| 452 |
+
"train_samples_per_second": 0.547,
|
| 453 |
+
"train_steps_per_second": 0.068
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.24,
|
| 457 |
+
"eval_accuracy": 0.3428783934548159,
|
| 458 |
+
"eval_loss": 1.694771409034729,
|
| 459 |
+
"eval_runtime": 743.9046,
|
| 460 |
+
"eval_samples_per_second": 3.615,
|
| 461 |
+
"eval_steps_per_second": 0.453,
|
| 462 |
+
"step": 576
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 3.24,
|
| 466 |
+
"eval_accuracy": 0.3428783934548159,
|
| 467 |
+
"eval_loss": 1.694771409034729,
|
| 468 |
+
"eval_runtime": 695.3156,
|
| 469 |
+
"eval_samples_per_second": 3.867,
|
| 470 |
+
"eval_steps_per_second": 0.485,
|
| 471 |
+
"step": 576
|
| 472 |
+
}
|
| 473 |
+
],
|
| 474 |
+
"logging_steps": 10,
|
| 475 |
+
"max_steps": 576,
|
| 476 |
+
"num_input_tokens_seen": 0,
|
| 477 |
+
"num_train_epochs": 9223372036854775807,
|
| 478 |
+
"save_steps": 500,
|
| 479 |
+
"total_flos": 4.0295036866264105e+18,
|
| 480 |
+
"train_batch_size": 8,
|
| 481 |
+
"trial_name": null,
|
| 482 |
+
"trial_params": null
|
| 483 |
+
}
|