| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.875, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 2.9394371509552, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.4418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 3.083791494369507, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.5045, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.28125, | |
| "grad_norm": 2.887883186340332, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4981, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 1.4925549030303955, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 0.4423, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.46875, | |
| "grad_norm": 1.9005215167999268, | |
| "learning_rate": 9.86522435289912e-06, | |
| "loss": 0.4336, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 1.7973142862319946, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.4162, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.65625, | |
| "grad_norm": 1.3991189002990723, | |
| "learning_rate": 9.468163201617063e-06, | |
| "loss": 0.3872, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 1.0571672916412354, | |
| "learning_rate": 9.177439057064684e-06, | |
| "loss": 0.3715, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.84375, | |
| "grad_norm": 0.9835160970687866, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 0.3734, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 0.7332506775856018, | |
| "learning_rate": 8.43120818934367e-06, | |
| "loss": 0.3755, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0625, | |
| "grad_norm": 1.1038920879364014, | |
| "learning_rate": 7.985792958513932e-06, | |
| "loss": 0.578, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.15625, | |
| "grad_norm": 0.5584242343902588, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.3221, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.6514401435852051, | |
| "learning_rate": 6.980398830195785e-06, | |
| "loss": 0.3391, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.34375, | |
| "grad_norm": 0.5581364631652832, | |
| "learning_rate": 6.434016163555452e-06, | |
| "loss": 0.3351, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4375, | |
| "grad_norm": 0.5454242825508118, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 0.3254, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.53125, | |
| "grad_norm": 0.49989643692970276, | |
| "learning_rate": 5.290724144552379e-06, | |
| "loss": 0.3213, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.625, | |
| "grad_norm": 0.4163621664047241, | |
| "learning_rate": 4.7092758554476215e-06, | |
| "loss": 0.28, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.71875, | |
| "grad_norm": 0.421804279088974, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.3087, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8125, | |
| "grad_norm": 0.4409330189228058, | |
| "learning_rate": 3.5659838364445505e-06, | |
| "loss": 0.3169, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.90625, | |
| "grad_norm": 0.44110220670700073, | |
| "learning_rate": 3.019601169804216e-06, | |
| "loss": 0.2951, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.03125, | |
| "grad_norm": 0.7339137196540833, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.5593, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.125, | |
| "grad_norm": 0.341443806886673, | |
| "learning_rate": 2.0142070414860704e-06, | |
| "loss": 0.2949, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.21875, | |
| "grad_norm": 0.3330724239349365, | |
| "learning_rate": 1.5687918106563326e-06, | |
| "loss": 0.3198, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.3125, | |
| "grad_norm": 0.3333916962146759, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.2861, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.40625, | |
| "grad_norm": 0.3423750102519989, | |
| "learning_rate": 8.225609429353187e-07, | |
| "loss": 0.2944, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.31113386154174805, | |
| "learning_rate": 5.318367983829393e-07, | |
| "loss": 0.3017, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.59375, | |
| "grad_norm": 0.2907048463821411, | |
| "learning_rate": 3.015368960704584e-07, | |
| "loss": 0.2762, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6875, | |
| "grad_norm": 0.3126791715621948, | |
| "learning_rate": 1.3477564710088097e-07, | |
| "loss": 0.2966, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.78125, | |
| "grad_norm": 0.34525594115257263, | |
| "learning_rate": 3.3808211290284886e-08, | |
| "loss": 0.2969, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.875, | |
| "grad_norm": 0.2925986349582672, | |
| "learning_rate": 0.0, | |
| "loss": 0.2782, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.875, | |
| "step": 30, | |
| "total_flos": 32226785263616.0, | |
| "train_loss": 0.3623232106367747, | |
| "train_runtime": 446.9713, | |
| "train_samples_per_second": 6.712, | |
| "train_steps_per_second": 0.067 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 32226785263616.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |