| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1306602425380752, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013066024253807521, | |
| "eval_loss": NaN, | |
| "eval_runtime": 439.2747, | |
| "eval_samples_per_second": 5.869, | |
| "eval_steps_per_second": 2.934, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003919807276142257, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007839614552284513, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011759421828426769, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011759421828426769, | |
| "eval_loss": NaN, | |
| "eval_runtime": 439.3706, | |
| "eval_samples_per_second": 5.867, | |
| "eval_steps_per_second": 2.934, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015679229104569026, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.019599036380711282, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023518843656853538, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.023518843656853538, | |
| "eval_loss": NaN, | |
| "eval_runtime": 439.3537, | |
| "eval_samples_per_second": 5.868, | |
| "eval_steps_per_second": 2.934, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.027438650932995794, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999229036240723, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03135845820913805, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.035278265485280305, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019624552364536473, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.035278265485280305, | |
| "eval_loss": NaN, | |
| "eval_runtime": 439.4105, | |
| "eval_samples_per_second": 5.867, | |
| "eval_steps_per_second": 2.933, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.039198072761422564, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04311788003756482, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018724960070727972, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.047037687313707076, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.047037687313707076, | |
| "eval_loss": NaN, | |
| "eval_runtime": 439.315, | |
| "eval_samples_per_second": 5.868, | |
| "eval_steps_per_second": 2.934, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.050957494589849335, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017343225094356855, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05487730186599159, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016494480483301836, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05879710914213385, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05879710914213385, | |
| "eval_loss": NaN, | |
| "eval_runtime": 439.436, | |
| "eval_samples_per_second": 5.867, | |
| "eval_steps_per_second": 2.933, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0627169164182761, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06663672369441835, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001346117057077493, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.07055653097056061, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012334453638559057, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.07055653097056061, | |
| "eval_loss": NaN, | |
| "eval_runtime": 439.2892, | |
| "eval_samples_per_second": 5.869, | |
| "eval_steps_per_second": 2.934, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.07447633824670287, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011175373974578378, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.07839614552284513, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08231595279898739, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.824626025421626e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.08231595279898739, | |
| "eval_loss": NaN, | |
| "eval_runtime": 639.1005, | |
| "eval_samples_per_second": 4.034, | |
| "eval_steps_per_second": 2.017, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.08623576007512963, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.66554636144095e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.09015556735127189, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.538829429225069e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.09407537462741415, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.09407537462741415, | |
| "eval_loss": NaN, | |
| "eval_runtime": 927.4346, | |
| "eval_samples_per_second": 2.78, | |
| "eval_steps_per_second": 1.39, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.09799518190355641, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.10191498917969867, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5055195166981645e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.10583479645584092, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6567749056431467e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.10583479645584092, | |
| "eval_loss": NaN, | |
| "eval_runtime": 926.5094, | |
| "eval_samples_per_second": 2.782, | |
| "eval_steps_per_second": 1.391, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.10975460373198317, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.11367441100812543, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2750399292720283e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.1175942182842677, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1175942182842677, | |
| "eval_loss": NaN, | |
| "eval_runtime": 926.1549, | |
| "eval_samples_per_second": 2.784, | |
| "eval_steps_per_second": 1.392, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.12151402556040995, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7544763546352834e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.1254338328365522, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.12935364011269446, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.709637592770991e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.12935364011269446, | |
| "eval_loss": NaN, | |
| "eval_runtime": 926.3077, | |
| "eval_samples_per_second": 2.783, | |
| "eval_steps_per_second": 1.392, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.022836126777344e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |