| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015455950540958269, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015455950540958269, | |
| "grad_norm": 0.26332780718803406, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1237, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015455950540958269, | |
| "eval_loss": 1.321516513824463, | |
| "eval_runtime": 6.0393, | |
| "eval_samples_per_second": 45.204, | |
| "eval_steps_per_second": 22.685, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0030911901081916537, | |
| "grad_norm": 0.2900320589542389, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2338, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00463678516228748, | |
| "grad_norm": 0.3545430600643158, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4773, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00463678516228748, | |
| "eval_loss": 1.3202024698257446, | |
| "eval_runtime": 4.7852, | |
| "eval_samples_per_second": 57.051, | |
| "eval_steps_per_second": 28.63, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0061823802163833074, | |
| "grad_norm": 0.32492122054100037, | |
| "learning_rate": 8e-05, | |
| "loss": 1.317, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0077279752704791345, | |
| "grad_norm": 0.2560977041721344, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9961, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00927357032457496, | |
| "grad_norm": 0.3331815004348755, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2011, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00927357032457496, | |
| "eval_loss": 1.3012441396713257, | |
| "eval_runtime": 4.8825, | |
| "eval_samples_per_second": 55.914, | |
| "eval_steps_per_second": 28.06, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010819165378670788, | |
| "grad_norm": 0.3901693820953369, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2942, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012364760432766615, | |
| "grad_norm": 0.3264555335044861, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0978, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013910355486862442, | |
| "grad_norm": 0.6461142897605896, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6565, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013910355486862442, | |
| "eval_loss": 1.2162935733795166, | |
| "eval_runtime": 4.8177, | |
| "eval_samples_per_second": 56.666, | |
| "eval_steps_per_second": 28.437, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015455950540958269, | |
| "grad_norm": 0.37601980566978455, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0025, | |
| "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": 287765975531520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |