| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.5441640378548893, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.025236593059936908, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.3794, | |
| "eval_samples_per_second": 8.713, | |
| "eval_steps_per_second": 4.356, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07570977917981073, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15141955835962145, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22712933753943218, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22712933753943218, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.3829, | |
| "eval_samples_per_second": 8.711, | |
| "eval_steps_per_second": 4.355, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3028391167192429, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3785488958990536, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.45425867507886436, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.45425867507886436, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.4146, | |
| "eval_samples_per_second": 8.693, | |
| "eval_steps_per_second": 4.347, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5299684542586751, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999229036240723, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6056782334384858, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6813880126182965, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019624552364536473, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6813880126182965, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.4093, | |
| "eval_samples_per_second": 8.696, | |
| "eval_steps_per_second": 4.348, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7570977917981072, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.832807570977918, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018724960070727972, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9085173501577287, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9085173501577287, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.4068, | |
| "eval_samples_per_second": 8.697, | |
| "eval_steps_per_second": 4.349, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9842271293375394, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017343225094356855, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.0701892744479495, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016494480483301836, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.1458990536277602, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1458990536277602, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.3909, | |
| "eval_samples_per_second": 8.706, | |
| "eval_steps_per_second": 4.353, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.221608832807571, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.2973186119873816, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001346117057077493, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.3730283911671926, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012334453638559057, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.3730283911671926, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.3879, | |
| "eval_samples_per_second": 8.708, | |
| "eval_steps_per_second": 4.354, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.4487381703470033, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011175373974578378, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.524447949526814, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.6001577287066246, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.824626025421626e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.6001577287066246, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.3973, | |
| "eval_samples_per_second": 8.703, | |
| "eval_steps_per_second": 4.351, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.6758675078864353, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.66554636144095e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.751577287066246, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.538829429225069e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.8272870662460567, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.8272870662460567, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.3913, | |
| "eval_samples_per_second": 8.706, | |
| "eval_steps_per_second": 4.353, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.9029968454258674, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.9787066246056781, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5055195166981645e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.0646687697160884, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6567749056431467e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.0646687697160884, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.3893, | |
| "eval_samples_per_second": 8.707, | |
| "eval_steps_per_second": 4.354, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.140378548895899, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.2160883280757098, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2750399292720283e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 2.2917981072555205, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.2917981072555205, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.41, | |
| "eval_samples_per_second": 8.696, | |
| "eval_steps_per_second": 4.348, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.367507886435331, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7544763546352834e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 2.443217665615142, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.5189274447949526, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.709637592770991e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.5189274447949526, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.4262, | |
| "eval_samples_per_second": 8.687, | |
| "eval_steps_per_second": 4.343, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 5.531924224404357e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |