| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011574743908791018, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00023149487817582037, | |
| "eval_loss": 1.8957964181900024, | |
| "eval_runtime": 213.5939, | |
| "eval_samples_per_second": 8.516, | |
| "eval_steps_per_second": 4.26, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011574743908791018, | |
| "grad_norm": 56.71136474609375, | |
| "learning_rate": 5e-05, | |
| "loss": 7.2579, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0023149487817582036, | |
| "grad_norm": 65.8984603881836, | |
| "learning_rate": 0.0001, | |
| "loss": 6.12, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0023149487817582036, | |
| "eval_loss": 1.417953610420227, | |
| "eval_runtime": 215.2865, | |
| "eval_samples_per_second": 8.449, | |
| "eval_steps_per_second": 4.227, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0034724231726373056, | |
| "grad_norm": 28.132305145263672, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.8545, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004629897563516407, | |
| "grad_norm": 25.49907684326172, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.7388, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004629897563516407, | |
| "eval_loss": 0.9980469346046448, | |
| "eval_runtime": 215.4792, | |
| "eval_samples_per_second": 8.442, | |
| "eval_steps_per_second": 4.223, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005787371954395509, | |
| "grad_norm": 25.179100036621094, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.1546, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006944846345274611, | |
| "grad_norm": 32.69419860839844, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2057, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006944846345274611, | |
| "eval_loss": 0.926070511341095, | |
| "eval_runtime": 215.3339, | |
| "eval_samples_per_second": 8.447, | |
| "eval_steps_per_second": 4.226, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008102320736153712, | |
| "grad_norm": 17.25409698486328, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.1471, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009259795127032814, | |
| "grad_norm": 34.82718276977539, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.9987, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009259795127032814, | |
| "eval_loss": 0.9166962504386902, | |
| "eval_runtime": 215.3726, | |
| "eval_samples_per_second": 8.446, | |
| "eval_steps_per_second": 4.225, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010417269517911916, | |
| "grad_norm": 28.590742111206055, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.2002, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011574743908791018, | |
| "grad_norm": 25.067100524902344, | |
| "learning_rate": 0.0, | |
| "loss": 3.8477, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011574743908791018, | |
| "eval_loss": 0.9125587344169617, | |
| "eval_runtime": 215.4423, | |
| "eval_samples_per_second": 8.443, | |
| "eval_steps_per_second": 4.224, | |
| "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": 8763509991014400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |