File size: 5,878 Bytes
69801c1 8c6f012 69801c1 8c6f012 69801c1 2c9ab39 d63ca6d fe5bf30 04080ca 52ee620 43567c0 8b257e3 86a321a d7d7a48 d75e8c5 5ba93e9 e7c6037 bc2d9e2 84ea0c9 71b4269 b922b3c 46e28db 4436634 95b4624 aecb01b 9c4b570 31183b0 a467fa0 8b94d72 7f8e908 8c6f012 69801c1 8c6f012 69801c1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.8054862842892767,
"eval_steps": 500,
"global_step": 13500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.10390689941812137,
"grad_norm": 1.8855979442596436,
"learning_rate": 1.9310058187863676e-05,
"loss": 0.8022,
"step": 500
},
{
"epoch": 0.20781379883624274,
"grad_norm": 0.8622527122497559,
"learning_rate": 1.86173455250762e-05,
"loss": 0.5316,
"step": 1000
},
{
"epoch": 0.3117206982543641,
"grad_norm": 1.404678225517273,
"learning_rate": 1.7924632862288724e-05,
"loss": 0.4832,
"step": 1500
},
{
"epoch": 0.41562759767248547,
"grad_norm": 1.3559819459915161,
"learning_rate": 1.7233305624826823e-05,
"loss": 0.4518,
"step": 2000
},
{
"epoch": 0.5195344970906068,
"grad_norm": 0.8163271546363831,
"learning_rate": 1.6540592962039347e-05,
"loss": 0.4389,
"step": 2500
},
{
"epoch": 0.6234413965087282,
"grad_norm": 0.8109046816825867,
"learning_rate": 1.584788029925187e-05,
"loss": 0.4193,
"step": 3000
},
{
"epoch": 0.7273482959268496,
"grad_norm": 1.0217444896697998,
"learning_rate": 1.5155167636464397e-05,
"loss": 0.4215,
"step": 3500
},
{
"epoch": 0.8312551953449709,
"grad_norm": 1.6476292610168457,
"learning_rate": 1.446245497367692e-05,
"loss": 0.4062,
"step": 4000
},
{
"epoch": 0.9351620947630923,
"grad_norm": 1.4694277048110962,
"learning_rate": 1.3769742310889445e-05,
"loss": 0.4029,
"step": 4500
},
{
"epoch": 1.0,
"eval_loss": 0.3212089240550995,
"eval_runtime": 31.4577,
"eval_samples_per_second": 15.704,
"eval_steps_per_second": 7.852,
"step": 4812
},
{
"epoch": 1.0390689941812137,
"grad_norm": 0.6561925411224365,
"learning_rate": 1.3077029648101969e-05,
"loss": 0.4059,
"step": 5000
},
{
"epoch": 1.142975893599335,
"grad_norm": 0.6741281747817993,
"learning_rate": 1.2384316985314493e-05,
"loss": 0.3594,
"step": 5500
},
{
"epoch": 1.2468827930174564,
"grad_norm": 0.48619207739830017,
"learning_rate": 1.1691604322527017e-05,
"loss": 0.3736,
"step": 6000
},
{
"epoch": 1.3507896924355778,
"grad_norm": 1.1009119749069214,
"learning_rate": 1.099889165973954e-05,
"loss": 0.3624,
"step": 6500
},
{
"epoch": 1.4546965918536992,
"grad_norm": 0.3497615456581116,
"learning_rate": 1.0306178996952066e-05,
"loss": 0.3516,
"step": 7000
},
{
"epoch": 1.5586034912718203,
"grad_norm": 1.4209001064300537,
"learning_rate": 9.61346633416459e-06,
"loss": 0.3565,
"step": 7500
},
{
"epoch": 1.6625103906899419,
"grad_norm": 0.8116744160652161,
"learning_rate": 8.920753671377114e-06,
"loss": 0.3635,
"step": 8000
},
{
"epoch": 1.766417290108063,
"grad_norm": 0.8015578985214233,
"learning_rate": 8.228041008589638e-06,
"loss": 0.3549,
"step": 8500
},
{
"epoch": 1.8703241895261846,
"grad_norm": 0.7980790734291077,
"learning_rate": 7.536713771127737e-06,
"loss": 0.3495,
"step": 9000
},
{
"epoch": 1.9742310889443058,
"grad_norm": 1.4501579999923706,
"learning_rate": 6.845386533665836e-06,
"loss": 0.3385,
"step": 9500
},
{
"epoch": 2.0,
"eval_loss": 0.29613471031188965,
"eval_runtime": 31.4504,
"eval_samples_per_second": 15.707,
"eval_steps_per_second": 7.854,
"step": 9624
},
{
"epoch": 2.0781379883624274,
"grad_norm": 0.6130263209342957,
"learning_rate": 6.15267387087836e-06,
"loss": 0.3293,
"step": 10000
},
{
"epoch": 2.1820448877805485,
"grad_norm": 1.2724053859710693,
"learning_rate": 5.459961208090885e-06,
"loss": 0.3369,
"step": 10500
},
{
"epoch": 2.28595178719867,
"grad_norm": 0.7700533270835876,
"learning_rate": 4.767248545303408e-06,
"loss": 0.3387,
"step": 11000
},
{
"epoch": 2.3898586866167912,
"grad_norm": 1.4450799226760864,
"learning_rate": 4.0759213078415074e-06,
"loss": 0.3411,
"step": 11500
},
{
"epoch": 2.493765586034913,
"grad_norm": 0.8265316486358643,
"learning_rate": 3.3832086450540318e-06,
"loss": 0.317,
"step": 12000
},
{
"epoch": 2.597672485453034,
"grad_norm": 1.4168757200241089,
"learning_rate": 2.690495982266556e-06,
"loss": 0.3176,
"step": 12500
},
{
"epoch": 2.7015793848711556,
"grad_norm": 1.0274338722229004,
"learning_rate": 1.99778331947908e-06,
"loss": 0.3389,
"step": 13000
},
{
"epoch": 2.8054862842892767,
"grad_norm": 1.6529736518859863,
"learning_rate": 1.3050706566916044e-06,
"loss": 0.3163,
"step": 13500
}
],
"logging_steps": 500,
"max_steps": 14436,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.644064512933888e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|