| { | |
| "best_metric": 2.237405776977539, | |
| "best_model_checkpoint": "output/rihanna/checkpoint-262", | |
| "epoch": 2.0, | |
| "global_step": 262, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00013670742670262692, | |
| "loss": 3.4044, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00013523678052634687, | |
| "loss": 2.8194, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00013280918103490095, | |
| "loss": 2.7475, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00012945949034742042, | |
| "loss": 2.9331, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012523581249268407, | |
| "loss": 2.8944, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00012019880259978666, | |
| "loss": 2.6589, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00011442079584574986, | |
| "loss": 2.7123, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010798476866903087, | |
| "loss": 2.5847, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00010098314716666811, | |
| "loss": 2.391, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.351647978736063e-05, | |
| "loss": 2.5899, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.5691993381587e-05, | |
| "loss": 2.3867, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 7.762205334494898e-05, | |
| "loss": 2.4515, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.942254996821776e-05, | |
| "loss": 2.7458, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.121123416728538e-05, | |
| "loss": 2.4949, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.310602649316754e-05, | |
| "loss": 2.5412, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.5223323705920566e-05, | |
| "loss": 2.5738, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.7676327231320786e-05, | |
| "loss": 2.2778, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.0573417504900444e-05, | |
| "loss": 2.0957, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.401659754895943e-05, | |
| "loss": 2.3988, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.8100028133934438e-05, | |
| "loss": 2.3799, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2908675560288951e-05, | |
| "loss": 2.5075, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.517091479772992e-06, | |
| "loss": 2.1984, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.988342278719811e-06, | |
| "loss": 2.4497, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.3731033982246404e-06, | |
| "loss": 2.3199, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.089315974356758e-07, | |
| "loss": 2.3814, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.9725610793441152e-08, | |
| "loss": 2.1807, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.336484432220459, | |
| "eval_runtime": 8.0556, | |
| "eval_samples_per_second": 22.593, | |
| "eval_steps_per_second": 2.855, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.153829445781081e-07, | |
| "loss": 2.3816, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.5916577414195624e-06, | |
| "loss": 2.1418, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.8302217539407e-06, | |
| "loss": 2.1866, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 6.998927551907465e-06, | |
| "loss": 2.3514, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.1052270183036815e-05, | |
| "loss": 2.3302, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.5932040657672757e-05, | |
| "loss": 2.0237, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.1568161872809022e-05, | |
| "loss": 2.1338, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.7879694970972374e-05, | |
| "loss": 2.1066, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.477600168191081e-05, | |
| "loss": 2.1939, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.215804595500327e-05, | |
| "loss": 2.1481, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 4.991981618998877e-05, | |
| "loss": 2.4364, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.794984764173325e-05, | |
| "loss": 2.1677, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 6.613282313617852e-05, | |
| "loss": 2.3095, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.435122911001204e-05, | |
| "loss": 2.4404, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.248704319210595e-05, | |
| "loss": 2.0718, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.042342909181217e-05, | |
| "loss": 2.2015, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.804641445426643e-05, | |
| "loss": 2.1899, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00010524652758746261, | |
| "loss": 2.1465, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00011192036955648884, | |
| "loss": 2.3478, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00011797209906849287, | |
| "loss": 2.3704, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0001233148088243337, | |
| "loss": 2.2886, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00012787177357149405, | |
| "loss": 2.1345, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00013157755193529395, | |
| "loss": 2.0747, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00013437892620529645, | |
| "loss": 2.2118, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.000136235666580879, | |
| "loss": 2.1172, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00013712110890084145, | |
| "loss": 2.2353, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.237405776977539, | |
| "eval_runtime": 8.3034, | |
| "eval_samples_per_second": 22.521, | |
| "eval_steps_per_second": 2.89, | |
| "step": 262 | |
| } | |
| ], | |
| "max_steps": 262, | |
| "num_train_epochs": 2, | |
| "total_flos": 272919527424000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |