| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 260, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0038461538461538464, | |
| "grad_norm": 0.09405899047851562, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 2.0595, | |
| "mean_token_accuracy": 0.5536306202411652, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019230769230769232, | |
| "grad_norm": 0.08910957723855972, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 1.8585, | |
| "mean_token_accuracy": 0.5810351483523846, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.038461538461538464, | |
| "grad_norm": 0.08904706686735153, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 1.9022, | |
| "mean_token_accuracy": 0.5676299393177032, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.057692307692307696, | |
| "grad_norm": 0.08470770716667175, | |
| "learning_rate": 0.00011538461538461538, | |
| "loss": 1.7707, | |
| "mean_token_accuracy": 0.5904860138893128, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 0.08369024842977524, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 1.8988, | |
| "mean_token_accuracy": 0.5750770568847656, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09615384615384616, | |
| "grad_norm": 0.09705021977424622, | |
| "learning_rate": 0.00019230769230769233, | |
| "loss": 1.7922, | |
| "mean_token_accuracy": 0.5889591336250305, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11538461538461539, | |
| "grad_norm": 0.09560074657201767, | |
| "learning_rate": 0.00019985583705641418, | |
| "loss": 1.8499, | |
| "mean_token_accuracy": 0.580015218257904, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1346153846153846, | |
| "grad_norm": 0.10197644680738449, | |
| "learning_rate": 0.0001992708874098054, | |
| "loss": 1.7104, | |
| "mean_token_accuracy": 0.6041951894760131, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 0.13560408353805542, | |
| "learning_rate": 0.00019823877374156647, | |
| "loss": 1.6712, | |
| "mean_token_accuracy": 0.6099030375480652, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17307692307692307, | |
| "grad_norm": 0.08910802006721497, | |
| "learning_rate": 0.00019676414519013781, | |
| "loss": 1.7598, | |
| "mean_token_accuracy": 0.6009629964828491, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19230769230769232, | |
| "grad_norm": 0.07992758601903915, | |
| "learning_rate": 0.00019485364419471454, | |
| "loss": 1.7385, | |
| "mean_token_accuracy": 0.6025008857250214, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21153846153846154, | |
| "grad_norm": 0.10774888843297958, | |
| "learning_rate": 0.00019251587657449236, | |
| "loss": 1.7556, | |
| "mean_token_accuracy": 0.5930293738842011, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 0.09247864037752151, | |
| "learning_rate": 0.0001897613727639014, | |
| "loss": 1.8556, | |
| "mean_token_accuracy": 0.5815793335437774, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.09036409109830856, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.7937, | |
| "mean_token_accuracy": 0.5908996999263764, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2692307692307692, | |
| "grad_norm": 0.08717014640569687, | |
| "learning_rate": 0.00018305360832480117, | |
| "loss": 1.7211, | |
| "mean_token_accuracy": 0.5962238609790802, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28846153846153844, | |
| "grad_norm": 0.0832277238368988, | |
| "learning_rate": 0.0001791305627069662, | |
| "loss": 1.7616, | |
| "mean_token_accuracy": 0.5980025470256806, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 0.09641429781913757, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 1.9454, | |
| "mean_token_accuracy": 0.5685357481241227, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3269230769230769, | |
| "grad_norm": 0.0839536264538765, | |
| "learning_rate": 0.00017023442153554777, | |
| "loss": 1.7512, | |
| "mean_token_accuracy": 0.601141732931137, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.34615384615384615, | |
| "grad_norm": 0.09633956849575043, | |
| "learning_rate": 0.0001653013984983585, | |
| "loss": 1.7946, | |
| "mean_token_accuracy": 0.5880300402641296, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.36538461538461536, | |
| "grad_norm": 0.1043943241238594, | |
| "learning_rate": 0.0001600742264237979, | |
| "loss": 1.8304, | |
| "mean_token_accuracy": 0.5875581204891205, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 0.0865144208073616, | |
| "learning_rate": 0.00015457645101945046, | |
| "loss": 1.6875, | |
| "mean_token_accuracy": 0.6015634536743164, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.40384615384615385, | |
| "grad_norm": 0.09035369008779526, | |
| "learning_rate": 0.00014883283692099112, | |
| "loss": 1.8378, | |
| "mean_token_accuracy": 0.5831819474697113, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4230769230769231, | |
| "grad_norm": 0.08860991895198822, | |
| "learning_rate": 0.00014286925614030542, | |
| "loss": 1.798, | |
| "mean_token_accuracy": 0.5853480577468873, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4423076923076923, | |
| "grad_norm": 0.08836635202169418, | |
| "learning_rate": 0.00013671257152545277, | |
| "loss": 1.801, | |
| "mean_token_accuracy": 0.5812891662120819, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 0.09542136639356613, | |
| "learning_rate": 0.0001303905157574247, | |
| "loss": 1.69, | |
| "mean_token_accuracy": 0.6061259090900422, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4807692307692308, | |
| "grad_norm": 0.08438368141651154, | |
| "learning_rate": 0.0001239315664287558, | |
| "loss": 1.7784, | |
| "mean_token_accuracy": 0.5900569677352905, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.10227668285369873, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 1.7175, | |
| "mean_token_accuracy": 0.5924076437950134, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5192307692307693, | |
| "grad_norm": 0.0860576331615448, | |
| "learning_rate": 0.00011071984957874479, | |
| "loss": 1.6981, | |
| "mean_token_accuracy": 0.6106000781059265, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 0.09762172400951385, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 1.762, | |
| "mean_token_accuracy": 0.5936734616756439, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5576923076923077, | |
| "grad_norm": 0.08866383880376816, | |
| "learning_rate": 9.73152007189939e-05, | |
| "loss": 1.6937, | |
| "mean_token_accuracy": 0.6022425711154937, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 0.09346310794353485, | |
| "learning_rate": 9.061590105968208e-05, | |
| "loss": 1.7799, | |
| "mean_token_accuracy": 0.5884160101413727, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5961538461538461, | |
| "grad_norm": 0.10388106107711792, | |
| "learning_rate": 8.395887191422397e-05, | |
| "loss": 1.7951, | |
| "mean_token_accuracy": 0.5963736653327942, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.09293079376220703, | |
| "learning_rate": 7.73740997570278e-05, | |
| "loss": 1.9635, | |
| "mean_token_accuracy": 0.5650549530982971, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6346153846153846, | |
| "grad_norm": 0.09150257706642151, | |
| "learning_rate": 7.089124558212871e-05, | |
| "loss": 1.7436, | |
| "mean_token_accuracy": 0.5971101462841034, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6538461538461539, | |
| "grad_norm": 0.09019029885530472, | |
| "learning_rate": 6.453951129574644e-05, | |
| "loss": 1.7784, | |
| "mean_token_accuracy": 0.5899733185768128, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6730769230769231, | |
| "grad_norm": 0.09248427301645279, | |
| "learning_rate": 5.834750817679606e-05, | |
| "loss": 1.6719, | |
| "mean_token_accuracy": 0.6091178715229034, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 0.11273639649152756, | |
| "learning_rate": 5.234312799786921e-05, | |
| "loss": 1.7856, | |
| "mean_token_accuracy": 0.5923596352338791, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7115384615384616, | |
| "grad_norm": 0.09874605387449265, | |
| "learning_rate": 4.6553417387219886e-05, | |
| "loss": 1.7215, | |
| "mean_token_accuracy": 0.6017483115196228, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7307692307692307, | |
| "grad_norm": 0.09074950963258743, | |
| "learning_rate": 4.100445599768774e-05, | |
| "loss": 1.9318, | |
| "mean_token_accuracy": 0.5736395329236984, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.12326296418905258, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 1.7836, | |
| "mean_token_accuracy": 0.5871184587478637, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.10748053342103958, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 1.6282, | |
| "mean_token_accuracy": 0.6153640151023865, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7884615384615384, | |
| "grad_norm": 0.093140609562397, | |
| "learning_rate": 2.6045926771976303e-05, | |
| "loss": 1.6998, | |
| "mean_token_accuracy": 0.5974012076854706, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.8076923076923077, | |
| "grad_norm": 0.10797327011823654, | |
| "learning_rate": 2.1697413758237784e-05, | |
| "loss": 1.6651, | |
| "mean_token_accuracy": 0.6072666823863984, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8269230769230769, | |
| "grad_norm": 0.0944468230009079, | |
| "learning_rate": 1.7701613410634365e-05, | |
| "loss": 1.6446, | |
| "mean_token_accuracy": 0.6169975221157074, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 0.1349770575761795, | |
| "learning_rate": 1.4076524743778319e-05, | |
| "loss": 1.6874, | |
| "mean_token_accuracy": 0.610532957315445, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8653846153846154, | |
| "grad_norm": 0.09194570034742355, | |
| "learning_rate": 1.083847690782972e-05, | |
| "loss": 1.8036, | |
| "mean_token_accuracy": 0.5944990277290344, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8846153846153846, | |
| "grad_norm": 0.09132257848978043, | |
| "learning_rate": 8.002055634117578e-06, | |
| "loss": 1.6791, | |
| "mean_token_accuracy": 0.6079061985015869, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9038461538461539, | |
| "grad_norm": 0.08958450704813004, | |
| "learning_rate": 5.580037533961546e-06, | |
| "loss": 1.7627, | |
| "mean_token_accuracy": 0.6024388492107391, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.08657591044902802, | |
| "learning_rate": 3.5833325466437694e-06, | |
| "loss": 1.6514, | |
| "mean_token_accuracy": 0.6082013726234436, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9423076923076923, | |
| "grad_norm": 0.09413374960422516, | |
| "learning_rate": 2.0209347957732328e-06, | |
| "loss": 1.6913, | |
| "mean_token_accuracy": 0.6105992496013641, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.9615384615384616, | |
| "grad_norm": 0.09713339805603027, | |
| "learning_rate": 8.998820754091531e-07, | |
| "loss": 1.7552, | |
| "mean_token_accuracy": 0.5954502403736115, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9807692307692307, | |
| "grad_norm": 0.10334648191928864, | |
| "learning_rate": 2.2522414843748618e-07, | |
| "loss": 1.6602, | |
| "mean_token_accuracy": 0.6200077295303345, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.1041092649102211, | |
| "learning_rate": 0.0, | |
| "loss": 1.7604, | |
| "mean_token_accuracy": 0.5999625205993653, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 260, | |
| "total_flos": 2381129238708224.0, | |
| "train_loss": 0.0, | |
| "train_runtime": 0.6875, | |
| "train_samples_per_second": 3024.065, | |
| "train_steps_per_second": 378.19 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 260, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2381129238708224.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |