| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005362692286035282, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0725384572070562e-05, | |
| "eval_loss": 4.963016510009766, | |
| "eval_runtime": 1684.1872, | |
| "eval_samples_per_second": 23.31, | |
| "eval_steps_per_second": 11.655, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.362692286035281e-05, | |
| "grad_norm": 4.095840930938721, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2077, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00010725384572070562, | |
| "grad_norm": 3.8304200172424316, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3148, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00010725384572070562, | |
| "eval_loss": 4.481961250305176, | |
| "eval_runtime": 1676.1458, | |
| "eval_samples_per_second": 23.422, | |
| "eval_steps_per_second": 11.711, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00016088076858105843, | |
| "grad_norm": 6.369905948638916, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.3419, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00021450769144141125, | |
| "grad_norm": 4.40816593170166, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1923, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00021450769144141125, | |
| "eval_loss": 2.036909580230713, | |
| "eval_runtime": 1676.791, | |
| "eval_samples_per_second": 23.413, | |
| "eval_steps_per_second": 11.706, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0002681346143017641, | |
| "grad_norm": 5.617472171783447, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5147, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00032176153716211687, | |
| "grad_norm": 4.534087657928467, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0213, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00032176153716211687, | |
| "eval_loss": 1.0484462976455688, | |
| "eval_runtime": 1683.903, | |
| "eval_samples_per_second": 23.314, | |
| "eval_steps_per_second": 11.657, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0003753884600224697, | |
| "grad_norm": 5.003360271453857, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8204, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0004290153828828225, | |
| "grad_norm": 10.329523086547852, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7724, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0004290153828828225, | |
| "eval_loss": 0.965052604675293, | |
| "eval_runtime": 1695.5597, | |
| "eval_samples_per_second": 23.153, | |
| "eval_steps_per_second": 11.577, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00048264230574317533, | |
| "grad_norm": 5.659180641174316, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.922, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0005362692286035282, | |
| "grad_norm": 5.8149213790893555, | |
| "learning_rate": 0.0, | |
| "loss": 0.9943, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0005362692286035282, | |
| "eval_loss": 0.9484821557998657, | |
| "eval_runtime": 1666.1755, | |
| "eval_samples_per_second": 23.562, | |
| "eval_steps_per_second": 11.781, | |
| "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": 3496008304558080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |