| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 5000, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 3.1430612111542, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.124, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.9096499041651624, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.971, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 1.963357152408043, | |
| "learning_rate": 9.987820251299121e-06, | |
| "loss": 1.8813, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.931497009564988, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 1.8264, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.014420552850295, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 1.7815, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.7693673411468296, | |
| "learning_rate": 9.414737964294636e-06, | |
| "loss": 1.7795, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 1.5985741500266653, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 1.7885, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.5468022654000388, | |
| "learning_rate": 8.596699001693257e-06, | |
| "loss": 1.771, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 1.6447937843717773, | |
| "learning_rate": 8.078307376628292e-06, | |
| "loss": 1.7706, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.566629345204418, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.7634, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 1.6089870593659625, | |
| "learning_rate": 6.873032967079562e-06, | |
| "loss": 1.7241, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.5484779186475413, | |
| "learning_rate": 6.209609477998339e-06, | |
| "loss": 1.7287, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 1.5850310588338916, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 1.6224, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 1.7746427733728092, | |
| "learning_rate": 4.825502516487497e-06, | |
| "loss": 1.4283, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 1.7232081953947909, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 1.4763, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 1.7024573641927823, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 1.4036, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 1.681053350335325, | |
| "learning_rate": 2.8081442660546126e-06, | |
| "loss": 1.4223, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 1.5805323673193001, | |
| "learning_rate": 2.204035482646267e-06, | |
| "loss": 1.416, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 1.8952832093764047, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 1.4118, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.7448747247813432, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 1.4386, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 1.6558543089408067, | |
| "learning_rate": 7.597595192178702e-07, | |
| "loss": 1.4189, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 1.9939504796568306, | |
| "learning_rate": 4.322727117869951e-07, | |
| "loss": 1.4129, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 1.7587188318416578, | |
| "learning_rate": 1.9369152030840553e-07, | |
| "loss": 1.388, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 1.9110466730907998, | |
| "learning_rate": 4.865965629214819e-08, | |
| "loss": 1.3457, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.7323350066509577, | |
| "learning_rate": 0.0, | |
| "loss": 1.4088, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 250, | |
| "total_flos": 4745305128960.0, | |
| "train_loss": 1.6201500358581542, | |
| "train_runtime": 510.1426, | |
| "train_samples_per_second": 3.917, | |
| "train_steps_per_second": 0.49 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4745305128960.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |