| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022006235099944985, | |
| "eval_steps": 34, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004890274466654441, | |
| "grad_norm": 1.4216102361679077, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 3.258, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004890274466654441, | |
| "eval_loss": 3.5600969791412354, | |
| "eval_runtime": 1313.2977, | |
| "eval_samples_per_second": 1.967, | |
| "eval_steps_per_second": 0.656, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009780548933308881, | |
| "grad_norm": 1.504632830619812, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 3.8029, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014670823399963323, | |
| "grad_norm": 1.6489232778549194, | |
| "learning_rate": 2e-05, | |
| "loss": 3.6594, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019561097866617762, | |
| "grad_norm": 1.274643063545227, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 3.1495, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024451372333272204, | |
| "grad_norm": 1.4067387580871582, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.6677, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029341646799926646, | |
| "grad_norm": 1.7147626876831055, | |
| "learning_rate": 4e-05, | |
| "loss": 3.8075, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034231921266581087, | |
| "grad_norm": 1.672584891319275, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 3.3499, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0039122195733235525, | |
| "grad_norm": 2.0120997428894043, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 4.2653, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004401247019988997, | |
| "grad_norm": 2.0601062774658203, | |
| "learning_rate": 6e-05, | |
| "loss": 3.3055, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004890274466654441, | |
| "grad_norm": 2.0153276920318604, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.1547, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005379301913319885, | |
| "grad_norm": 2.443328857421875, | |
| "learning_rate": 7.333333333333333e-05, | |
| "loss": 3.4654, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005868329359985329, | |
| "grad_norm": 2.801769971847534, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8224, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006357356806650773, | |
| "grad_norm": 2.6738572120666504, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 2.8465, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0068463842533162175, | |
| "grad_norm": 2.8812367916107178, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 2.622, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007335411699981661, | |
| "grad_norm": 2.9697248935699463, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9623, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007824439146647105, | |
| "grad_norm": 2.5231637954711914, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 2.2665, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00831346659331255, | |
| "grad_norm": 2.341275691986084, | |
| "learning_rate": 0.00011333333333333334, | |
| "loss": 2.2247, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008802494039977994, | |
| "grad_norm": 2.683793306350708, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9371, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009291521486643438, | |
| "grad_norm": 2.972334384918213, | |
| "learning_rate": 0.00012666666666666666, | |
| "loss": 1.8682, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009780548933308882, | |
| "grad_norm": 3.541074275970459, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.912, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010269576379974325, | |
| "grad_norm": 2.9546866416931152, | |
| "learning_rate": 0.00014, | |
| "loss": 1.6904, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01075860382663977, | |
| "grad_norm": 2.5912656784057617, | |
| "learning_rate": 0.00014666666666666666, | |
| "loss": 1.5096, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011247631273305215, | |
| "grad_norm": 2.258963108062744, | |
| "learning_rate": 0.00015333333333333334, | |
| "loss": 1.3978, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011736658719970658, | |
| "grad_norm": 2.275815725326538, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1538, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012225686166636102, | |
| "grad_norm": 2.224825382232666, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 1.471, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012714713613301546, | |
| "grad_norm": 1.876035451889038, | |
| "learning_rate": 0.00017333333333333334, | |
| "loss": 1.4368, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013203741059966991, | |
| "grad_norm": 1.6051979064941406, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3951, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013692768506632435, | |
| "grad_norm": 1.7268619537353516, | |
| "learning_rate": 0.0001866666666666667, | |
| "loss": 1.1915, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014181795953297879, | |
| "grad_norm": 1.888218879699707, | |
| "learning_rate": 0.00019333333333333333, | |
| "loss": 1.1358, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014670823399963322, | |
| "grad_norm": 1.7404896020889282, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2051, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015159850846628768, | |
| "grad_norm": 1.560935139656067, | |
| "learning_rate": 0.00019998292504580528, | |
| "loss": 1.1611, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01564887829329421, | |
| "grad_norm": 2.000502824783325, | |
| "learning_rate": 0.0001999317060143023, | |
| "loss": 1.4315, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.016137905739959654, | |
| "grad_norm": 1.7972925901412964, | |
| "learning_rate": 0.0001998463603967434, | |
| "loss": 1.1507, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0166269331866251, | |
| "grad_norm": 1.4039409160614014, | |
| "learning_rate": 0.00019972691733857883, | |
| "loss": 1.1626, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0166269331866251, | |
| "eval_loss": 1.1705251932144165, | |
| "eval_runtime": 1316.0492, | |
| "eval_samples_per_second": 1.963, | |
| "eval_steps_per_second": 0.654, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017115960633290545, | |
| "grad_norm": 1.5077097415924072, | |
| "learning_rate": 0.00019957341762950344, | |
| "loss": 1.0223, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.017604988079955988, | |
| "grad_norm": 1.4470211267471313, | |
| "learning_rate": 0.0001993859136895274, | |
| "loss": 1.0228, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.018094015526621432, | |
| "grad_norm": 1.7781013250350952, | |
| "learning_rate": 0.00019916446955107428, | |
| "loss": 1.0388, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.018583042973286876, | |
| "grad_norm": 1.8719812631607056, | |
| "learning_rate": 0.0001989091608371146, | |
| "loss": 1.0568, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01907207041995232, | |
| "grad_norm": 1.389418363571167, | |
| "learning_rate": 0.00019862007473534025, | |
| "loss": 1.2011, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019561097866617763, | |
| "grad_norm": 1.561482310295105, | |
| "learning_rate": 0.0001982973099683902, | |
| "loss": 1.2364, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020050125313283207, | |
| "grad_norm": 1.3894869089126587, | |
| "learning_rate": 0.0001979409767601366, | |
| "loss": 1.0156, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02053915275994865, | |
| "grad_norm": 1.2144147157669067, | |
| "learning_rate": 0.00019755119679804367, | |
| "loss": 0.9838, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.021028180206614098, | |
| "grad_norm": 1.2613141536712646, | |
| "learning_rate": 0.0001971281031916114, | |
| "loss": 0.9763, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02151720765327954, | |
| "grad_norm": 1.316279649734497, | |
| "learning_rate": 0.00019667184042691875, | |
| "loss": 1.0909, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.022006235099944985, | |
| "grad_norm": 1.4056583642959595, | |
| "learning_rate": 0.00019618256431728194, | |
| "loss": 1.2575, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9975293879975936e+17, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |