{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.9921259842519685, "eval_steps": 500, "global_step": 570, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.05249343832020997, "grad_norm": 5.856240742467741, "learning_rate": 5e-06, "loss": 0.9788, "step": 10 }, { "epoch": 0.10498687664041995, "grad_norm": 1.504758475031017, "learning_rate": 5e-06, "loss": 0.8672, "step": 20 }, { "epoch": 0.15748031496062992, "grad_norm": 0.9699579752356402, "learning_rate": 5e-06, "loss": 0.8312, "step": 30 }, { "epoch": 0.2099737532808399, "grad_norm": 2.3401202479822167, "learning_rate": 5e-06, "loss": 0.8176, "step": 40 }, { "epoch": 0.26246719160104987, "grad_norm": 1.4328785905158876, "learning_rate": 5e-06, "loss": 0.8021, "step": 50 }, { "epoch": 0.31496062992125984, "grad_norm": 1.776027549071983, "learning_rate": 5e-06, "loss": 0.7924, "step": 60 }, { "epoch": 0.3674540682414698, "grad_norm": 1.6731596205975654, "learning_rate": 5e-06, "loss": 0.7862, "step": 70 }, { "epoch": 0.4199475065616798, "grad_norm": 0.7241122381033481, "learning_rate": 5e-06, "loss": 0.7745, "step": 80 }, { "epoch": 0.47244094488188976, "grad_norm": 0.667641025148353, "learning_rate": 5e-06, "loss": 0.7684, "step": 90 }, { "epoch": 0.5249343832020997, "grad_norm": 0.5504196367515327, "learning_rate": 5e-06, "loss": 0.7659, "step": 100 }, { "epoch": 0.5774278215223098, "grad_norm": 0.5097698406084038, "learning_rate": 5e-06, "loss": 0.7644, "step": 110 }, { "epoch": 0.6299212598425197, "grad_norm": 0.7982727448245113, "learning_rate": 5e-06, "loss": 0.7621, "step": 120 }, { "epoch": 0.6824146981627297, "grad_norm": 0.7024212096277765, "learning_rate": 5e-06, "loss": 0.7587, "step": 130 }, { "epoch": 0.7349081364829396, "grad_norm": 0.6368075359040738, "learning_rate": 5e-06, "loss": 0.7528, "step": 140 }, { "epoch": 0.7874015748031497, "grad_norm": 0.5954968543585505, "learning_rate": 5e-06, "loss": 0.7523, "step": 150 }, { "epoch": 0.8398950131233596, "grad_norm": 0.670163545471037, "learning_rate": 5e-06, "loss": 0.7534, "step": 160 }, { "epoch": 0.8923884514435696, "grad_norm": 0.5996022754065202, "learning_rate": 5e-06, "loss": 0.7517, "step": 170 }, { "epoch": 0.9448818897637795, "grad_norm": 0.8415836628541776, "learning_rate": 5e-06, "loss": 0.7459, "step": 180 }, { "epoch": 0.9973753280839895, "grad_norm": 0.690137189983478, "learning_rate": 5e-06, "loss": 0.7488, "step": 190 }, { "epoch": 1.0498687664041995, "grad_norm": 0.5870306499065036, "learning_rate": 5e-06, "loss": 0.7462, "step": 200 }, { "epoch": 1.1023622047244095, "grad_norm": 0.6711935804641513, "learning_rate": 5e-06, "loss": 0.7045, "step": 210 }, { "epoch": 1.1548556430446195, "grad_norm": 0.6793309667692513, "learning_rate": 5e-06, "loss": 0.7054, "step": 220 }, { "epoch": 1.2073490813648293, "grad_norm": 0.4945921653765713, "learning_rate": 5e-06, "loss": 0.7007, "step": 230 }, { "epoch": 1.2598425196850394, "grad_norm": 0.7994708362053626, "learning_rate": 5e-06, "loss": 0.7035, "step": 240 }, { "epoch": 1.3123359580052494, "grad_norm": 0.6645996514564108, "learning_rate": 5e-06, "loss": 0.7029, "step": 250 }, { "epoch": 1.3648293963254594, "grad_norm": 0.6524179166081678, "learning_rate": 5e-06, "loss": 0.7069, "step": 260 }, { "epoch": 1.4173228346456692, "grad_norm": 0.8192112613994083, "learning_rate": 5e-06, "loss": 0.7058, "step": 270 }, { "epoch": 1.4698162729658792, "grad_norm": 0.7359384256295017, "learning_rate": 5e-06, "loss": 0.7096, "step": 280 }, { "epoch": 1.5223097112860893, "grad_norm": 0.8479895809019217, "learning_rate": 5e-06, "loss": 0.7014, "step": 290 }, { "epoch": 1.574803149606299, "grad_norm": 0.5643654766970888, "learning_rate": 5e-06, "loss": 0.7027, "step": 300 }, { "epoch": 1.627296587926509, "grad_norm": 0.5431958308145564, "learning_rate": 5e-06, "loss": 0.7014, "step": 310 }, { "epoch": 1.6797900262467191, "grad_norm": 0.520988761182218, "learning_rate": 5e-06, "loss": 0.7004, "step": 320 }, { "epoch": 1.7322834645669292, "grad_norm": 0.5293919501601649, "learning_rate": 5e-06, "loss": 0.7014, "step": 330 }, { "epoch": 1.7847769028871392, "grad_norm": 0.5558746861224813, "learning_rate": 5e-06, "loss": 0.7051, "step": 340 }, { "epoch": 1.8372703412073492, "grad_norm": 0.5864088226331533, "learning_rate": 5e-06, "loss": 0.7028, "step": 350 }, { "epoch": 1.889763779527559, "grad_norm": 0.5203657185554663, "learning_rate": 5e-06, "loss": 0.7029, "step": 360 }, { "epoch": 1.942257217847769, "grad_norm": 0.5249283309342107, "learning_rate": 5e-06, "loss": 0.6985, "step": 370 }, { "epoch": 1.9947506561679789, "grad_norm": 0.5014731402840785, "learning_rate": 5e-06, "loss": 0.698, "step": 380 }, { "epoch": 2.047244094488189, "grad_norm": 0.6606881961316096, "learning_rate": 5e-06, "loss": 0.701, "step": 390 }, { "epoch": 2.099737532808399, "grad_norm": 0.7956310597917616, "learning_rate": 5e-06, "loss": 0.6552, "step": 400 }, { "epoch": 2.152230971128609, "grad_norm": 0.7409823582769325, "learning_rate": 5e-06, "loss": 0.6529, "step": 410 }, { "epoch": 2.204724409448819, "grad_norm": 0.5301522848133626, "learning_rate": 5e-06, "loss": 0.6583, "step": 420 }, { "epoch": 2.257217847769029, "grad_norm": 0.5707394351699061, "learning_rate": 5e-06, "loss": 0.6567, "step": 430 }, { "epoch": 2.309711286089239, "grad_norm": 0.8305197146184463, "learning_rate": 5e-06, "loss": 0.6591, "step": 440 }, { "epoch": 2.362204724409449, "grad_norm": 0.6345171704808862, "learning_rate": 5e-06, "loss": 0.6586, "step": 450 }, { "epoch": 2.4146981627296586, "grad_norm": 0.540143075416848, "learning_rate": 5e-06, "loss": 0.6577, "step": 460 }, { "epoch": 2.4671916010498687, "grad_norm": 0.6047688082843984, "learning_rate": 5e-06, "loss": 0.6583, "step": 470 }, { "epoch": 2.5196850393700787, "grad_norm": 0.5089956964635003, "learning_rate": 5e-06, "loss": 0.6597, "step": 480 }, { "epoch": 2.5721784776902887, "grad_norm": 0.6189665519218218, "learning_rate": 5e-06, "loss": 0.6593, "step": 490 }, { "epoch": 2.6246719160104988, "grad_norm": 0.6080333484551841, "learning_rate": 5e-06, "loss": 0.6586, "step": 500 }, { "epoch": 2.677165354330709, "grad_norm": 0.6796282219494648, "learning_rate": 5e-06, "loss": 0.6613, "step": 510 }, { "epoch": 2.729658792650919, "grad_norm": 0.6734905288037869, "learning_rate": 5e-06, "loss": 0.6593, "step": 520 }, { "epoch": 2.7821522309711284, "grad_norm": 0.7251898875558835, "learning_rate": 5e-06, "loss": 0.6579, "step": 530 }, { "epoch": 2.8346456692913384, "grad_norm": 0.5903651504718952, "learning_rate": 5e-06, "loss": 0.6613, "step": 540 }, { "epoch": 2.8871391076115485, "grad_norm": 0.6998542288142676, "learning_rate": 5e-06, "loss": 0.6589, "step": 550 }, { "epoch": 2.9396325459317585, "grad_norm": 0.6240795370124482, "learning_rate": 5e-06, "loss": 0.6594, "step": 560 }, { "epoch": 2.9921259842519685, "grad_norm": 0.5469561259952066, "learning_rate": 5e-06, "loss": 0.6579, "step": 570 }, { "epoch": 2.9921259842519685, "step": 570, "total_flos": 954352470589440.0, "train_loss": 0.718004734474316, "train_runtime": 8541.7768, "train_samples_per_second": 34.252, "train_steps_per_second": 0.067 } ], "logging_steps": 10, "max_steps": 570, "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": true }, "attributes": {} } }, "total_flos": 954352470589440.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }