| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006553575479545283, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.680403969114175e-05, | |
| "eval_loss": 11.085497856140137, | |
| "eval_runtime": 174.8054, | |
| "eval_samples_per_second": 143.342, | |
| "eval_steps_per_second": 71.674, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.402019845570875e-05, | |
| "grad_norm": 0.8793793320655823, | |
| "learning_rate": 5e-05, | |
| "loss": 44.3397, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001680403969114175, | |
| "grad_norm": 0.8667848110198975, | |
| "learning_rate": 0.0001, | |
| "loss": 44.3344, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001680403969114175, | |
| "eval_loss": 11.081645011901855, | |
| "eval_runtime": 173.6105, | |
| "eval_samples_per_second": 144.329, | |
| "eval_steps_per_second": 72.167, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0002520605953671263, | |
| "grad_norm": 0.8332545161247253, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 44.3081, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000336080793822835, | |
| "grad_norm": 0.876369833946228, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 44.2913, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000336080793822835, | |
| "eval_loss": 11.07130241394043, | |
| "eval_runtime": 180.501, | |
| "eval_samples_per_second": 138.819, | |
| "eval_steps_per_second": 69.412, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00042010099227854375, | |
| "grad_norm": 0.9054920673370361, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 44.2714, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005041211907342526, | |
| "grad_norm": 0.9127441048622131, | |
| "learning_rate": 5e-05, | |
| "loss": 44.2555, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005041211907342526, | |
| "eval_loss": 11.063674926757812, | |
| "eval_runtime": 180.8119, | |
| "eval_samples_per_second": 138.58, | |
| "eval_steps_per_second": 69.293, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005881413891899612, | |
| "grad_norm": 0.9231416583061218, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 44.2482, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 58274611200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |