| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05480953685941354, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010961907371882709, | |
| "eval_loss": 0.9682910442352295, | |
| "eval_runtime": 34.1538, | |
| "eval_samples_per_second": 11.273, | |
| "eval_steps_per_second": 5.651, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005480953685941353, | |
| "grad_norm": 0.957384467124939, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8217, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010961907371882707, | |
| "grad_norm": 0.9359698295593262, | |
| "learning_rate": 0.0001, | |
| "loss": 0.666, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010961907371882707, | |
| "eval_loss": 0.5619043707847595, | |
| "eval_runtime": 34.6323, | |
| "eval_samples_per_second": 11.117, | |
| "eval_steps_per_second": 5.573, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01644286105782406, | |
| "grad_norm": 1.0605751276016235, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.2908, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021923814743765414, | |
| "grad_norm": 1.456253170967102, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3967, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021923814743765414, | |
| "eval_loss": 0.20093432068824768, | |
| "eval_runtime": 34.7914, | |
| "eval_samples_per_second": 11.066, | |
| "eval_steps_per_second": 5.547, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02740476842970677, | |
| "grad_norm": 1.1946262121200562, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1072, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03288572211564812, | |
| "grad_norm": 0.5105569958686829, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0743, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03288572211564812, | |
| "eval_loss": 0.17875532805919647, | |
| "eval_runtime": 34.7125, | |
| "eval_samples_per_second": 11.091, | |
| "eval_steps_per_second": 5.56, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03836667580158948, | |
| "grad_norm": 0.7014047503471375, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2792, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04384762948753083, | |
| "grad_norm": 0.4467286169528961, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3702, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04384762948753083, | |
| "eval_loss": 0.16739042103290558, | |
| "eval_runtime": 34.89, | |
| "eval_samples_per_second": 11.035, | |
| "eval_steps_per_second": 5.532, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04932858317347218, | |
| "grad_norm": 0.5335176587104797, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2862, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05480953685941354, | |
| "grad_norm": 0.4365200698375702, | |
| "learning_rate": 0.0, | |
| "loss": 0.0772, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05480953685941354, | |
| "eval_loss": 0.16572637856006622, | |
| "eval_runtime": 34.9, | |
| "eval_samples_per_second": 11.032, | |
| "eval_steps_per_second": 5.53, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.294694973702144e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |