| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013628620102214651, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00045428733674048835, | |
| "eval_loss": 3.4793825149536133, | |
| "eval_runtime": 35.5762, | |
| "eval_samples_per_second": 26.057, | |
| "eval_steps_per_second": 13.042, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001362862010221465, | |
| "grad_norm": 5.091403484344482, | |
| "learning_rate": 6e-05, | |
| "loss": 3.3166, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00272572402044293, | |
| "grad_norm": 3.2241737842559814, | |
| "learning_rate": 0.00012, | |
| "loss": 2.6477, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003634298693923907, | |
| "eval_loss": 1.3390246629714966, | |
| "eval_runtime": 35.6116, | |
| "eval_samples_per_second": 26.031, | |
| "eval_steps_per_second": 13.029, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0040885860306643955, | |
| "grad_norm": 2.9629907608032227, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7023, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00545144804088586, | |
| "grad_norm": 5.996878147125244, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.0172, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0068143100511073255, | |
| "grad_norm": 1.9135724306106567, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.5242, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007268597387847814, | |
| "eval_loss": 0.4879297614097595, | |
| "eval_runtime": 35.612, | |
| "eval_samples_per_second": 26.031, | |
| "eval_steps_per_second": 13.029, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008177172061328791, | |
| "grad_norm": 1.7589951753616333, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.3898, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009540034071550256, | |
| "grad_norm": 2.2107276916503906, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.4252, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01090289608177172, | |
| "grad_norm": 1.2082346677780151, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.3324, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01090289608177172, | |
| "eval_loss": 0.33602961897850037, | |
| "eval_runtime": 35.692, | |
| "eval_samples_per_second": 25.972, | |
| "eval_steps_per_second": 13.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012265758091993186, | |
| "grad_norm": 1.107161283493042, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.325, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013628620102214651, | |
| "grad_norm": 0.9933003783226013, | |
| "learning_rate": 0.0, | |
| "loss": 0.2946, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3015894871572480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |