| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.026663111585121985, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005332622317024396, | |
| "eval_loss": 1.0614696741104126, | |
| "eval_runtime": 82.4311, | |
| "eval_samples_per_second": 9.584, | |
| "eval_steps_per_second": 4.792, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026663111585121984, | |
| "grad_norm": 1.0974019765853882, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0424, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005332622317024397, | |
| "grad_norm": 1.134436011314392, | |
| "learning_rate": 0.0001, | |
| "loss": 0.727, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005332622317024397, | |
| "eval_loss": 0.39596226811408997, | |
| "eval_runtime": 82.9564, | |
| "eval_samples_per_second": 9.523, | |
| "eval_steps_per_second": 4.762, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007998933475536596, | |
| "grad_norm": 0.968150794506073, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.2826, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010665244634048793, | |
| "grad_norm": 0.5643301010131836, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.093, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010665244634048793, | |
| "eval_loss": 0.043653760105371475, | |
| "eval_runtime": 83.127, | |
| "eval_samples_per_second": 9.504, | |
| "eval_steps_per_second": 4.752, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013331555792560993, | |
| "grad_norm": 0.2168484926223755, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0351, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015997866951073192, | |
| "grad_norm": 0.33927980065345764, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0159, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015997866951073192, | |
| "eval_loss": 0.011334585957229137, | |
| "eval_runtime": 83.5481, | |
| "eval_samples_per_second": 9.456, | |
| "eval_steps_per_second": 4.728, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01866417810958539, | |
| "grad_norm": 0.2027255892753601, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0098, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.021330489268097587, | |
| "grad_norm": 0.025620242580771446, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0064, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.021330489268097587, | |
| "eval_loss": 0.011297364719212055, | |
| "eval_runtime": 83.5257, | |
| "eval_samples_per_second": 9.458, | |
| "eval_steps_per_second": 4.729, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023996800426609784, | |
| "grad_norm": 0.018756398931145668, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0026, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026663111585121985, | |
| "grad_norm": 0.4856107831001282, | |
| "learning_rate": 0.0, | |
| "loss": 0.0082, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.026663111585121985, | |
| "eval_loss": 0.010740067809820175, | |
| "eval_runtime": 83.5173, | |
| "eval_samples_per_second": 9.459, | |
| "eval_steps_per_second": 4.73, | |
| "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": 1.586645434368e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |