| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008531149359097404, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.531149359097404e-05, | |
| "grad_norm": 0.8922680616378784, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7629, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.531149359097404e-05, | |
| "eval_loss": 3.126101493835449, | |
| "eval_runtime": 187.7436, | |
| "eval_samples_per_second": 26.291, | |
| "eval_steps_per_second": 13.146, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017062298718194808, | |
| "grad_norm": 0.9431661367416382, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0406, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00025593448077292216, | |
| "grad_norm": 0.8109967708587646, | |
| "learning_rate": 6e-05, | |
| "loss": 3.1476, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025593448077292216, | |
| "eval_loss": 3.1226754188537598, | |
| "eval_runtime": 186.4918, | |
| "eval_samples_per_second": 26.468, | |
| "eval_steps_per_second": 13.234, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00034124597436389616, | |
| "grad_norm": 0.8224407434463501, | |
| "learning_rate": 8e-05, | |
| "loss": 2.9903, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004265574679548702, | |
| "grad_norm": 0.9300077557563782, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1351, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005118689615458443, | |
| "grad_norm": 0.9735047817230225, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9901, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005118689615458443, | |
| "eval_loss": 3.0837738513946533, | |
| "eval_runtime": 186.7424, | |
| "eval_samples_per_second": 26.432, | |
| "eval_steps_per_second": 13.216, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005971804551368183, | |
| "grad_norm": 1.1074120998382568, | |
| "learning_rate": 0.00014, | |
| "loss": 2.7724, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006824919487277923, | |
| "grad_norm": 1.1702643632888794, | |
| "learning_rate": 0.00016, | |
| "loss": 2.5928, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007678034423187664, | |
| "grad_norm": 2.0787010192871094, | |
| "learning_rate": 0.00018, | |
| "loss": 3.2394, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007678034423187664, | |
| "eval_loss": 2.8718318939208984, | |
| "eval_runtime": 186.8191, | |
| "eval_samples_per_second": 26.421, | |
| "eval_steps_per_second": 13.211, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008531149359097404, | |
| "grad_norm": 1.5365502834320068, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7958, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2059778654208000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |