| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.45662100456621, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0091324200913242, | |
| "eval_loss": 1.9843593835830688, | |
| "eval_runtime": 3.2855, | |
| "eval_samples_per_second": 14.305, | |
| "eval_steps_per_second": 7.305, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.045662100456621, | |
| "grad_norm": 1.4866653680801392, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9161, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.091324200913242, | |
| "grad_norm": 1.9973965883255005, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9062, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.091324200913242, | |
| "eval_loss": 1.8147876262664795, | |
| "eval_runtime": 3.3405, | |
| "eval_samples_per_second": 14.07, | |
| "eval_steps_per_second": 7.185, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 1.9531378746032715, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6399, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.182648401826484, | |
| "grad_norm": 2.1125802993774414, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3004, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.182648401826484, | |
| "eval_loss": 1.2232025861740112, | |
| "eval_runtime": 3.309, | |
| "eval_samples_per_second": 14.204, | |
| "eval_steps_per_second": 7.253, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.228310502283105, | |
| "grad_norm": 1.892870545387268, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1939, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 2.2009050846099854, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1432, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "eval_loss": 1.1795270442962646, | |
| "eval_runtime": 3.4173, | |
| "eval_samples_per_second": 13.753, | |
| "eval_steps_per_second": 7.023, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.319634703196347, | |
| "grad_norm": 2.0374162197113037, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.131, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 2.147594690322876, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1629, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "eval_loss": 1.1687428951263428, | |
| "eval_runtime": 3.3917, | |
| "eval_samples_per_second": 13.858, | |
| "eval_steps_per_second": 7.076, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 1.7530230283737183, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.06, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "grad_norm": 1.960148811340332, | |
| "learning_rate": 0.0, | |
| "loss": 1.1337, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "eval_loss": 1.1660501956939697, | |
| "eval_runtime": 3.3268, | |
| "eval_samples_per_second": 14.128, | |
| "eval_steps_per_second": 7.214, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |