| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08741258741258741, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017482517482517483, | |
| "eval_loss": 4.200336933135986, | |
| "eval_runtime": 17.1547, | |
| "eval_samples_per_second": 14.049, | |
| "eval_steps_per_second": 7.053, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008741258741258742, | |
| "grad_norm": 1.021557092666626, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0302, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017482517482517484, | |
| "grad_norm": 1.0658315420150757, | |
| "learning_rate": 0.0001, | |
| "loss": 3.9812, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017482517482517484, | |
| "eval_loss": 3.920738935470581, | |
| "eval_runtime": 17.4386, | |
| "eval_samples_per_second": 13.82, | |
| "eval_steps_per_second": 6.939, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026223776223776224, | |
| "grad_norm": 1.1982165575027466, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.7456, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03496503496503497, | |
| "grad_norm": 1.2464399337768555, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.5651, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03496503496503497, | |
| "eval_loss": 3.5671958923339844, | |
| "eval_runtime": 17.4762, | |
| "eval_samples_per_second": 13.79, | |
| "eval_steps_per_second": 6.924, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.043706293706293704, | |
| "grad_norm": 1.3184598684310913, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.3777, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05244755244755245, | |
| "grad_norm": 1.3302963972091675, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3628, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05244755244755245, | |
| "eval_loss": 3.413740873336792, | |
| "eval_runtime": 17.7307, | |
| "eval_samples_per_second": 13.592, | |
| "eval_steps_per_second": 6.824, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06118881118881119, | |
| "grad_norm": 1.3246403932571411, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.3863, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06993006993006994, | |
| "grad_norm": 2.0674448013305664, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.5705, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06993006993006994, | |
| "eval_loss": 3.375098705291748, | |
| "eval_runtime": 17.6331, | |
| "eval_samples_per_second": 13.667, | |
| "eval_steps_per_second": 6.862, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07867132867132867, | |
| "grad_norm": 1.7660764455795288, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.384, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08741258741258741, | |
| "grad_norm": 1.2882437705993652, | |
| "learning_rate": 0.0, | |
| "loss": 3.2939, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08741258741258741, | |
| "eval_loss": 3.3708629608154297, | |
| "eval_runtime": 17.5176, | |
| "eval_samples_per_second": 13.758, | |
| "eval_steps_per_second": 6.907, | |
| "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": 1.0598409257877504e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |