| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.029102814787867765, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00029102814787867765, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3536.3621, | |
| "eval_samples_per_second": 3.273, | |
| "eval_steps_per_second": 1.637, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000873084443636033, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001746168887272066, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002619253330908099, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002619253330908099, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3470.931, | |
| "eval_samples_per_second": 3.335, | |
| "eval_steps_per_second": 1.668, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003492337774544132, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004365422218180165, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005238506661816198, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005238506661816198, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3616.2795, | |
| "eval_samples_per_second": 3.201, | |
| "eval_steps_per_second": 1.601, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006111591105452231, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999229036240723, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006984675549088264, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007857759992724296, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019624552364536473, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007857759992724296, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4416.1483, | |
| "eval_samples_per_second": 2.621, | |
| "eval_steps_per_second": 1.311, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00873084443636033, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009603928879996362, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018724960070727972, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.010477013323632395, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010477013323632395, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4415.3141, | |
| "eval_samples_per_second": 2.622, | |
| "eval_steps_per_second": 1.311, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.011350097767268428, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017343225094356855, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.012223182210904461, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016494480483301836, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.013096266654540493, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013096266654540493, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4414.3267, | |
| "eval_samples_per_second": 2.622, | |
| "eval_steps_per_second": 1.311, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013969351098176527, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01484243554181256, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001346117057077493, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.01571551998544859, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012334453638559057, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.01571551998544859, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4417.0007, | |
| "eval_samples_per_second": 2.621, | |
| "eval_steps_per_second": 1.31, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.016588604429084625, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011175373974578378, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.01746168887272066, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.018334773316356693, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.824626025421626e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.018334773316356693, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4414.1348, | |
| "eval_samples_per_second": 2.622, | |
| "eval_steps_per_second": 1.311, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.019207857759992723, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.66554636144095e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.020080942203628757, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.538829429225069e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.02095402664726479, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.02095402664726479, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4414.6203, | |
| "eval_samples_per_second": 2.622, | |
| "eval_steps_per_second": 1.311, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.021827111090900825, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.022700195534536855, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5055195166981645e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.02357327997817289, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6567749056431467e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.02357327997817289, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4413.3957, | |
| "eval_samples_per_second": 2.623, | |
| "eval_steps_per_second": 1.311, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.024446364421808923, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.025319448865444953, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2750399292720283e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.026192533309080987, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.026192533309080987, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4409.9116, | |
| "eval_samples_per_second": 2.625, | |
| "eval_steps_per_second": 1.312, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02706561775271702, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7544763546352834e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.027938702196353055, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.028811786639989085, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.709637592770991e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.028811786639989085, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4413.4607, | |
| "eval_samples_per_second": 2.623, | |
| "eval_steps_per_second": 1.311, | |
| "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 | |
| } | |