| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009437386569872959, | |
| "eval_steps": 13, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024198427102238354, | |
| "eval_loss": 1.701516032218933, | |
| "eval_runtime": 34.007, | |
| "eval_samples_per_second": 51.166, | |
| "eval_steps_per_second": 25.583, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024198427102238356, | |
| "grad_norm": 4.161612510681152, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 6.4132, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003145795523290986, | |
| "eval_loss": 1.5509511232376099, | |
| "eval_runtime": 33.7517, | |
| "eval_samples_per_second": 51.553, | |
| "eval_steps_per_second": 25.777, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004839685420447671, | |
| "grad_norm": 3.3003146648406982, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.2296, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006291591046581972, | |
| "eval_loss": 1.4776992797851562, | |
| "eval_runtime": 33.7454, | |
| "eval_samples_per_second": 51.563, | |
| "eval_steps_per_second": 25.781, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007259528130671506, | |
| "grad_norm": 3.2282333374023438, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 5.6494, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009437386569872959, | |
| "eval_loss": 1.4494463205337524, | |
| "eval_runtime": 33.7435, | |
| "eval_samples_per_second": 51.565, | |
| "eval_steps_per_second": 25.783, | |
| "step": 39 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1492861845504000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |