| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03303303303303303, | |
| "eval_steps": 14, | |
| "global_step": 55, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006006006006006006, | |
| "eval_loss": 0.6866704821586609, | |
| "eval_runtime": 23.0889, | |
| "eval_samples_per_second": 30.361, | |
| "eval_steps_per_second": 15.202, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006006006006006006, | |
| "grad_norm": 2.2922801971435547, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.6831, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008408408408408409, | |
| "eval_loss": 0.3266207277774811, | |
| "eval_runtime": 22.9886, | |
| "eval_samples_per_second": 30.493, | |
| "eval_steps_per_second": 15.268, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012012012012012012, | |
| "grad_norm": 2.6258339881896973, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 1.3072, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016816816816816817, | |
| "eval_loss": 0.19282115995883942, | |
| "eval_runtime": 23.0157, | |
| "eval_samples_per_second": 30.457, | |
| "eval_steps_per_second": 15.25, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.018018018018018018, | |
| "grad_norm": 2.959623336791992, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0187, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.024024024024024024, | |
| "grad_norm": 4.844839096069336, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.7602, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025225225225225224, | |
| "eval_loss": 0.1556524932384491, | |
| "eval_runtime": 22.9916, | |
| "eval_samples_per_second": 30.489, | |
| "eval_steps_per_second": 15.266, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03003003003003003, | |
| "grad_norm": 1.8236432075500488, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 0.6399, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 55, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 14, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8958120831221760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |