| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01123882503192848, | |
| "eval_steps": 5, | |
| "global_step": 33, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00034057045551298427, | |
| "eval_loss": NaN, | |
| "eval_runtime": 56.6798, | |
| "eval_samples_per_second": 21.824, | |
| "eval_steps_per_second": 10.921, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010217113665389529, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017028522775649213, | |
| "eval_loss": NaN, | |
| "eval_runtime": 56.1446, | |
| "eval_samples_per_second": 22.032, | |
| "eval_steps_per_second": 11.025, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0020434227330779057, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0030651340996168583, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010588235294117647, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0034057045551298426, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.9301, | |
| "eval_samples_per_second": 22.117, | |
| "eval_steps_per_second": 11.067, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004086845466155811, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001411764705882353, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005108556832694764, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017647058823529413, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005108556832694764, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.9685, | |
| "eval_samples_per_second": 22.102, | |
| "eval_steps_per_second": 11.06, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006130268199233717, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006811409110259685, | |
| "eval_loss": NaN, | |
| "eval_runtime": 56.0375, | |
| "eval_samples_per_second": 22.075, | |
| "eval_steps_per_second": 11.046, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007151979565772669, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008173690932311623, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008514261387824606, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.9379, | |
| "eval_samples_per_second": 22.114, | |
| "eval_steps_per_second": 11.066, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009195402298850575, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010217113665389528, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010217113665389528, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.6874, | |
| "eval_samples_per_second": 22.213, | |
| "eval_steps_per_second": 11.116, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01123882503192848, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 33 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 33, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 17, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2269642103980032.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |