| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005266165152205338, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0532330304410676e-05, | |
| "eval_loss": 1.6582940816879272, | |
| "eval_runtime": 2628.7906, | |
| "eval_samples_per_second": 15.208, | |
| "eval_steps_per_second": 7.604, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010532330304410677, | |
| "grad_norm": 0.7095797657966614, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 6.5103, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001369202939573388, | |
| "eval_loss": 1.5630433559417725, | |
| "eval_runtime": 2628.2538, | |
| "eval_samples_per_second": 15.211, | |
| "eval_steps_per_second": 7.605, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00021064660608821354, | |
| "grad_norm": 1.1872904300689697, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.1906, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0002738405879146776, | |
| "eval_loss": 1.5086828470230103, | |
| "eval_runtime": 2628.3211, | |
| "eval_samples_per_second": 15.21, | |
| "eval_steps_per_second": 7.605, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0003159699091323203, | |
| "grad_norm": 1.3008513450622559, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 6.0153, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0004107608818720164, | |
| "eval_loss": 1.4872322082519531, | |
| "eval_runtime": 2628.7191, | |
| "eval_samples_per_second": 15.208, | |
| "eval_steps_per_second": 7.604, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0004212932121764271, | |
| "grad_norm": 1.2373629808425903, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 5.9399, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0005266165152205338, | |
| "grad_norm": 1.7535955905914307, | |
| "learning_rate": 0.0, | |
| "loss": 6.1511, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 1.963059069321216e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |