| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00210737052842316, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.21474105684632e-05, | |
| "eval_loss": 0.6331943273544312, | |
| "eval_runtime": 1127.3109, | |
| "eval_samples_per_second": 8.862, | |
| "eval_steps_per_second": 4.431, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000210737052842316, | |
| "grad_norm": 4.398820400238037, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8283, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000421474105684632, | |
| "grad_norm": 3.8103866577148438, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2524, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000421474105684632, | |
| "eval_loss": 0.5776350498199463, | |
| "eval_runtime": 1131.3004, | |
| "eval_samples_per_second": 8.831, | |
| "eval_steps_per_second": 4.415, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000632211158526948, | |
| "grad_norm": 3.405839204788208, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2289, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000842948211369264, | |
| "grad_norm": 2.9374308586120605, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1579, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000842948211369264, | |
| "eval_loss": 0.5359046459197998, | |
| "eval_runtime": 1133.2705, | |
| "eval_samples_per_second": 8.815, | |
| "eval_steps_per_second": 4.408, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00105368526421158, | |
| "grad_norm": 3.117830276489258, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9743, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001264422317053896, | |
| "grad_norm": 3.5818986892700195, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0424, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001264422317053896, | |
| "eval_loss": 0.5147128701210022, | |
| "eval_runtime": 1132.2037, | |
| "eval_samples_per_second": 8.824, | |
| "eval_steps_per_second": 4.412, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001475159369896212, | |
| "grad_norm": 3.088940382003784, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.0867, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.001685896422738528, | |
| "grad_norm": 2.9631552696228027, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.8087, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001685896422738528, | |
| "eval_loss": 0.5086004734039307, | |
| "eval_runtime": 1133.9336, | |
| "eval_samples_per_second": 8.81, | |
| "eval_steps_per_second": 4.405, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001896633475580844, | |
| "grad_norm": 3.090548038482666, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.2553, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00210737052842316, | |
| "grad_norm": 3.1793596744537354, | |
| "learning_rate": 0.0, | |
| "loss": 1.9481, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00210737052842316, | |
| "eval_loss": 0.5075772404670715, | |
| "eval_runtime": 1131.3867, | |
| "eval_samples_per_second": 8.83, | |
| "eval_steps_per_second": 4.415, | |
| "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": 1.708853041299456e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |