| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.983050847457627, | |
| "eval_steps": 500, | |
| "global_step": 396, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0009996066923030483, | |
| "loss": 2.8429, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0009984273879759713, | |
| "loss": 1.7586, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0009964639423366442, | |
| "loss": 1.7084, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0009937194443381972, | |
| "loss": 1.7022, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0009901982117093786, | |
| "loss": 1.436, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000985905784161771, | |
| "loss": 1.5345, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0009808489146745465, | |
| "loss": 1.5542, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0009750355588704727, | |
| "loss": 1.5173, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.000968474862499881, | |
| "loss": 1.4094, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0009611771470522907, | |
| "loss": 1.6779, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0009531538935183251, | |
| "loss": 1.593, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0009444177243274617, | |
| "loss": 1.8026, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0009349823834900395, | |
| "loss": 1.1646, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0009248627149747573, | |
| "loss": 1.4566, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0009140746393556853, | |
| "loss": 1.3848, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0009026351287655293, | |
| "loss": 1.6641, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0008905621801945467, | |
| "loss": 1.2664, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0008778747871771292, | |
| "loss": 1.4103, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0008645929099105886, | |
| "loss": 1.3391, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0008507374438531607, | |
| "loss": 1.3329, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0008363301868506264, | |
| "loss": 1.4708, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0008213938048432696, | |
| "loss": 1.5326, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0008059517962071233, | |
| "loss": 1.5317, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0007900284547855992, | |
| "loss": 1.2481, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0007736488316696662, | |
| "loss": 1.4773, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0007568386957867032, | |
| "loss": 1.2638, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0007396244933600284, | |
| "loss": 1.2867, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0007220333063028871, | |
| "loss": 1.0248, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0007040928096123516, | |
| "loss": 1.0408, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0006858312278301637, | |
| "loss": 1.1847, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0006672772906390176, | |
| "loss": 0.9884, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0006484601876641375, | |
| "loss": 1.0086, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0006294095225512603, | |
| "loss": 1.0438, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0006101552663932703, | |
| "loss": 0.9305, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0005907277105787513, | |
| "loss": 1.0619, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0005711574191366427, | |
| "loss": 1.5694, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0005514751806519673, | |
| "loss": 1.0704, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0005317119598282822, | |
| "loss": 1.1666, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0005118988487730537, | |
| "loss": 0.9914, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.000492067018082596, | |
| "loss": 1.0523, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00047224766780353, | |
| "loss": 0.9491, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0004524719783479088, | |
| "loss": 1.041, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0004327710614392341, | |
| "loss": 1.237, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00041317591116653486, | |
| "loss": 1.0301, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00039371735522351166, | |
| "loss": 1.0687, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00037442600640946044, | |
| "loss": 0.9959, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0003553322144682737, | |
| "loss": 0.9951, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0003364660183412892, | |
| "loss": 1.1158, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0003178570989091028, | |
| "loss": 1.2224, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00029953473229669324, | |
| "loss": 1.0617, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002815277438153203, | |
| "loss": 0.9955, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0002638644626136587, | |
| "loss": 0.9129, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00024657267710950857, | |
| "loss": 1.0105, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0002296795912722014, | |
| "loss": 0.7617, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.00021321178182447708, | |
| "loss": 0.629, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00019719515643116677, | |
| "loss": 0.7202, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00018165491294045593, | |
| "loss": 0.7211, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.00016661549974185424, | |
| "loss": 0.6464, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00015210057730323618, | |
| "loss": 0.6799, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0001381329809474649, | |
| "loss": 0.6218, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.00012473468492715895, | |
| "loss": 0.7277, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.00011192676785412154, | |
| "loss": 0.6244, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 9.972937953781985e-05, | |
| "loss": 0.6352, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 8.816170928508365e-05, | |
| "loss": 0.6462, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 7.724195571089787e-05, | |
| "loss": 0.6377, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 6.698729810778065e-05, | |
| "loss": 0.7165, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 5.741386941879179e-05, | |
| "loss": 0.6948, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.853673085668947e-05, | |
| "loss": 0.6849, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.036984820916722e-05, | |
| "loss": 0.6742, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.292606986744667e-05, | |
| "loss": 0.7078, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2.6217106612792528e-05, | |
| "loss": 0.6499, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.025351319275137e-05, | |
| "loss": 0.6878, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.5044671716097413e-05, | |
| "loss": 0.5469, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.0598776892610684e-05, | |
| "loss": 0.7233, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 6.9228231409067535e-06, | |
| "loss": 0.7482, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 4.02259358460233e-06, | |
| "loss": 0.6865, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.9026509541272275e-06, | |
| "loss": 0.6953, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 5.663304084960185e-07, | |
| "loss": 0.671, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.573428833345769e-08, | |
| "loss": 0.6152, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "step": 396, | |
| "total_flos": 1.0914041201688576e+17, | |
| "train_loss": 1.0966757915236733, | |
| "train_runtime": 4531.1008, | |
| "train_samples_per_second": 0.703, | |
| "train_steps_per_second": 0.087 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 396, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1.0914041201688576e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |