Upload 3 files
Browse files- all_results.json +7 -0
- eval_results.json +7 -0
- trainer_state.json +445 -0
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_loss": 0.10511729121208191,
|
| 4 |
+
"eval_runtime": 182.4801,
|
| 5 |
+
"eval_samples_per_second": 8.253,
|
| 6 |
+
"eval_steps_per_second": 1.036
|
| 7 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_loss": 0.10511729121208191,
|
| 4 |
+
"eval_runtime": 182.4801,
|
| 5 |
+
"eval_samples_per_second": 8.253,
|
| 6 |
+
"eval_steps_per_second": 1.036
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,445 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 3104,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 0.00019677835051546392,
|
| 13 |
+
"loss": 0.9382,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.13,
|
| 18 |
+
"learning_rate": 0.00019355670103092784,
|
| 19 |
+
"loss": 0.4059,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.19,
|
| 24 |
+
"learning_rate": 0.00019033505154639175,
|
| 25 |
+
"loss": 0.3835,
|
| 26 |
+
"step": 150
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.26,
|
| 30 |
+
"learning_rate": 0.0001871134020618557,
|
| 31 |
+
"loss": 0.3911,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.32,
|
| 36 |
+
"learning_rate": 0.0001838917525773196,
|
| 37 |
+
"loss": 0.3482,
|
| 38 |
+
"step": 250
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.39,
|
| 42 |
+
"learning_rate": 0.0001806701030927835,
|
| 43 |
+
"loss": 0.3409,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.45,
|
| 48 |
+
"learning_rate": 0.00017744845360824743,
|
| 49 |
+
"loss": 0.362,
|
| 50 |
+
"step": 350
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.52,
|
| 54 |
+
"learning_rate": 0.00017422680412371134,
|
| 55 |
+
"loss": 0.2979,
|
| 56 |
+
"step": 400
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.58,
|
| 60 |
+
"learning_rate": 0.00017100515463917525,
|
| 61 |
+
"loss": 0.2824,
|
| 62 |
+
"step": 450
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.64,
|
| 66 |
+
"learning_rate": 0.0001677835051546392,
|
| 67 |
+
"loss": 0.2422,
|
| 68 |
+
"step": 500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.64,
|
| 72 |
+
"eval_loss": 0.260538786649704,
|
| 73 |
+
"eval_runtime": 181.4734,
|
| 74 |
+
"eval_samples_per_second": 8.299,
|
| 75 |
+
"eval_steps_per_second": 1.041,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.71,
|
| 80 |
+
"learning_rate": 0.0001645618556701031,
|
| 81 |
+
"loss": 0.2609,
|
| 82 |
+
"step": 550
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.77,
|
| 86 |
+
"learning_rate": 0.00016134020618556702,
|
| 87 |
+
"loss": 0.2699,
|
| 88 |
+
"step": 600
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.84,
|
| 92 |
+
"learning_rate": 0.00015811855670103093,
|
| 93 |
+
"loss": 0.2714,
|
| 94 |
+
"step": 650
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.9,
|
| 98 |
+
"learning_rate": 0.00015489690721649487,
|
| 99 |
+
"loss": 0.3153,
|
| 100 |
+
"step": 700
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.97,
|
| 104 |
+
"learning_rate": 0.00015167525773195875,
|
| 105 |
+
"loss": 0.2316,
|
| 106 |
+
"step": 750
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.03,
|
| 110 |
+
"learning_rate": 0.0001484536082474227,
|
| 111 |
+
"loss": 0.1855,
|
| 112 |
+
"step": 800
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.1,
|
| 116 |
+
"learning_rate": 0.0001452319587628866,
|
| 117 |
+
"loss": 0.1853,
|
| 118 |
+
"step": 850
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.16,
|
| 122 |
+
"learning_rate": 0.00014201030927835052,
|
| 123 |
+
"loss": 0.194,
|
| 124 |
+
"step": 900
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.22,
|
| 128 |
+
"learning_rate": 0.00013878865979381443,
|
| 129 |
+
"loss": 0.2174,
|
| 130 |
+
"step": 950
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.29,
|
| 134 |
+
"learning_rate": 0.00013556701030927837,
|
| 135 |
+
"loss": 0.2246,
|
| 136 |
+
"step": 1000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.29,
|
| 140 |
+
"eval_loss": 0.1958554983139038,
|
| 141 |
+
"eval_runtime": 180.3002,
|
| 142 |
+
"eval_samples_per_second": 8.353,
|
| 143 |
+
"eval_steps_per_second": 1.048,
|
| 144 |
+
"step": 1000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.35,
|
| 148 |
+
"learning_rate": 0.00013234536082474226,
|
| 149 |
+
"loss": 0.1895,
|
| 150 |
+
"step": 1050
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.42,
|
| 154 |
+
"learning_rate": 0.0001291237113402062,
|
| 155 |
+
"loss": 0.1964,
|
| 156 |
+
"step": 1100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.48,
|
| 160 |
+
"learning_rate": 0.0001259020618556701,
|
| 161 |
+
"loss": 0.1666,
|
| 162 |
+
"step": 1150
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.55,
|
| 166 |
+
"learning_rate": 0.00012268041237113402,
|
| 167 |
+
"loss": 0.2008,
|
| 168 |
+
"step": 1200
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.61,
|
| 172 |
+
"learning_rate": 0.00011945876288659794,
|
| 173 |
+
"loss": 0.1952,
|
| 174 |
+
"step": 1250
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.68,
|
| 178 |
+
"learning_rate": 0.00011623711340206188,
|
| 179 |
+
"loss": 0.2173,
|
| 180 |
+
"step": 1300
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.74,
|
| 184 |
+
"learning_rate": 0.00011301546391752577,
|
| 185 |
+
"loss": 0.1722,
|
| 186 |
+
"step": 1350
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.8,
|
| 190 |
+
"learning_rate": 0.0001097938144329897,
|
| 191 |
+
"loss": 0.1882,
|
| 192 |
+
"step": 1400
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.87,
|
| 196 |
+
"learning_rate": 0.00010657216494845361,
|
| 197 |
+
"loss": 0.2224,
|
| 198 |
+
"step": 1450
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.93,
|
| 202 |
+
"learning_rate": 0.00010335051546391754,
|
| 203 |
+
"loss": 0.1697,
|
| 204 |
+
"step": 1500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.93,
|
| 208 |
+
"eval_loss": 0.28020888566970825,
|
| 209 |
+
"eval_runtime": 182.4392,
|
| 210 |
+
"eval_samples_per_second": 8.255,
|
| 211 |
+
"eval_steps_per_second": 1.036,
|
| 212 |
+
"step": 1500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.0,
|
| 216 |
+
"learning_rate": 0.00010012886597938145,
|
| 217 |
+
"loss": 0.1388,
|
| 218 |
+
"step": 1550
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.06,
|
| 222 |
+
"learning_rate": 9.690721649484537e-05,
|
| 223 |
+
"loss": 0.1353,
|
| 224 |
+
"step": 1600
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.13,
|
| 228 |
+
"learning_rate": 9.368556701030928e-05,
|
| 229 |
+
"loss": 0.0905,
|
| 230 |
+
"step": 1650
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.19,
|
| 234 |
+
"learning_rate": 9.04639175257732e-05,
|
| 235 |
+
"loss": 0.1694,
|
| 236 |
+
"step": 1700
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.26,
|
| 240 |
+
"learning_rate": 8.724226804123712e-05,
|
| 241 |
+
"loss": 0.1674,
|
| 242 |
+
"step": 1750
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.32,
|
| 246 |
+
"learning_rate": 8.402061855670103e-05,
|
| 247 |
+
"loss": 0.1464,
|
| 248 |
+
"step": 1800
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.38,
|
| 252 |
+
"learning_rate": 8.079896907216496e-05,
|
| 253 |
+
"loss": 0.1125,
|
| 254 |
+
"step": 1850
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.45,
|
| 258 |
+
"learning_rate": 7.757731958762887e-05,
|
| 259 |
+
"loss": 0.1548,
|
| 260 |
+
"step": 1900
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.51,
|
| 264 |
+
"learning_rate": 7.43556701030928e-05,
|
| 265 |
+
"loss": 0.0984,
|
| 266 |
+
"step": 1950
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.58,
|
| 270 |
+
"learning_rate": 7.113402061855671e-05,
|
| 271 |
+
"loss": 0.1224,
|
| 272 |
+
"step": 2000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.58,
|
| 276 |
+
"eval_loss": 0.1549469381570816,
|
| 277 |
+
"eval_runtime": 183.076,
|
| 278 |
+
"eval_samples_per_second": 8.226,
|
| 279 |
+
"eval_steps_per_second": 1.032,
|
| 280 |
+
"step": 2000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.64,
|
| 284 |
+
"learning_rate": 6.791237113402062e-05,
|
| 285 |
+
"loss": 0.0856,
|
| 286 |
+
"step": 2050
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.71,
|
| 290 |
+
"learning_rate": 6.469072164948455e-05,
|
| 291 |
+
"loss": 0.1656,
|
| 292 |
+
"step": 2100
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.77,
|
| 296 |
+
"learning_rate": 6.146907216494846e-05,
|
| 297 |
+
"loss": 0.1391,
|
| 298 |
+
"step": 2150
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.84,
|
| 302 |
+
"learning_rate": 5.824742268041238e-05,
|
| 303 |
+
"loss": 0.1165,
|
| 304 |
+
"step": 2200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.9,
|
| 308 |
+
"learning_rate": 5.50257731958763e-05,
|
| 309 |
+
"loss": 0.1023,
|
| 310 |
+
"step": 2250
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.96,
|
| 314 |
+
"learning_rate": 5.180412371134021e-05,
|
| 315 |
+
"loss": 0.1263,
|
| 316 |
+
"step": 2300
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.03,
|
| 320 |
+
"learning_rate": 4.8582474226804124e-05,
|
| 321 |
+
"loss": 0.0729,
|
| 322 |
+
"step": 2350
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 3.09,
|
| 326 |
+
"learning_rate": 4.536082474226804e-05,
|
| 327 |
+
"loss": 0.1125,
|
| 328 |
+
"step": 2400
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.16,
|
| 332 |
+
"learning_rate": 4.213917525773196e-05,
|
| 333 |
+
"loss": 0.13,
|
| 334 |
+
"step": 2450
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 3.22,
|
| 338 |
+
"learning_rate": 3.8917525773195875e-05,
|
| 339 |
+
"loss": 0.1385,
|
| 340 |
+
"step": 2500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.22,
|
| 344 |
+
"eval_loss": 0.14271119236946106,
|
| 345 |
+
"eval_runtime": 181.9727,
|
| 346 |
+
"eval_samples_per_second": 8.276,
|
| 347 |
+
"eval_steps_per_second": 1.039,
|
| 348 |
+
"step": 2500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 3.29,
|
| 352 |
+
"learning_rate": 3.5695876288659795e-05,
|
| 353 |
+
"loss": 0.0899,
|
| 354 |
+
"step": 2550
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 3.35,
|
| 358 |
+
"learning_rate": 3.2474226804123714e-05,
|
| 359 |
+
"loss": 0.0811,
|
| 360 |
+
"step": 2600
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.41,
|
| 364 |
+
"learning_rate": 2.925257731958763e-05,
|
| 365 |
+
"loss": 0.0897,
|
| 366 |
+
"step": 2650
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 3.48,
|
| 370 |
+
"learning_rate": 2.603092783505155e-05,
|
| 371 |
+
"loss": 0.0789,
|
| 372 |
+
"step": 2700
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.54,
|
| 376 |
+
"learning_rate": 2.2809278350515466e-05,
|
| 377 |
+
"loss": 0.0745,
|
| 378 |
+
"step": 2750
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 3.61,
|
| 382 |
+
"learning_rate": 1.9587628865979382e-05,
|
| 383 |
+
"loss": 0.0523,
|
| 384 |
+
"step": 2800
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.67,
|
| 388 |
+
"learning_rate": 1.6365979381443298e-05,
|
| 389 |
+
"loss": 0.0735,
|
| 390 |
+
"step": 2850
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 3.74,
|
| 394 |
+
"learning_rate": 1.3144329896907218e-05,
|
| 395 |
+
"loss": 0.0909,
|
| 396 |
+
"step": 2900
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.8,
|
| 400 |
+
"learning_rate": 9.922680412371134e-06,
|
| 401 |
+
"loss": 0.064,
|
| 402 |
+
"step": 2950
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 3.87,
|
| 406 |
+
"learning_rate": 6.701030927835052e-06,
|
| 407 |
+
"loss": 0.0589,
|
| 408 |
+
"step": 3000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.87,
|
| 412 |
+
"eval_loss": 0.13845542073249817,
|
| 413 |
+
"eval_runtime": 183.5137,
|
| 414 |
+
"eval_samples_per_second": 8.206,
|
| 415 |
+
"eval_steps_per_second": 1.03,
|
| 416 |
+
"step": 3000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.93,
|
| 420 |
+
"learning_rate": 3.4793814432989694e-06,
|
| 421 |
+
"loss": 0.0887,
|
| 422 |
+
"step": 3050
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.99,
|
| 426 |
+
"learning_rate": 2.577319587628866e-07,
|
| 427 |
+
"loss": 0.0577,
|
| 428 |
+
"step": 3100
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.0,
|
| 432 |
+
"step": 3104,
|
| 433 |
+
"total_flos": 3.845910334361518e+18,
|
| 434 |
+
"train_loss": 0.188343092505148,
|
| 435 |
+
"train_runtime": 9039.9113,
|
| 436 |
+
"train_samples_per_second": 5.49,
|
| 437 |
+
"train_steps_per_second": 0.343
|
| 438 |
+
}
|
| 439 |
+
],
|
| 440 |
+
"max_steps": 3104,
|
| 441 |
+
"num_train_epochs": 4,
|
| 442 |
+
"total_flos": 3.845910334361518e+18,
|
| 443 |
+
"trial_name": null,
|
| 444 |
+
"trial_params": null
|
| 445 |
+
}
|