| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 130, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 1.3998, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 1.203125, | |
| "learning_rate": 4.993398052663416e-05, | |
| "loss": 1.2457, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 4.953193036870676e-05, | |
| "loss": 1.0969, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 4.877104772313846e-05, | |
| "loss": 1.0383, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 4.766372503162375e-05, | |
| "loss": 0.9794, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 4.622799718031961e-05, | |
| "loss": 0.9258, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.6923076923076925, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 4.448724776693342e-05, | |
| "loss": 0.9013, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 4.246982825372522e-05, | |
| "loss": 0.8851, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.4615384615384617, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 4.020859620925235e-05, | |
| "loss": 0.8483, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 3.77403801594802e-05, | |
| "loss": 0.8315, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.230769230769231, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 3.510537976419131e-05, | |
| "loss": 0.8181, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 3.234651108797708e-05, | |
| "loss": 0.7815, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 2.9508707629336874e-05, | |
| "loss": 0.8063, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 5.384615384615385, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 2.6638188491974207e-05, | |
| "loss": 0.7603, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 5.769230769230769, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 2.378170561753209e-05, | |
| "loss": 0.7657, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 2.098578234003466e-05, | |
| "loss": 0.749, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 6.538461538461538, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 1.8295955663644855e-05, | |
| "loss": 0.7504, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 6.923076923076923, | |
| "grad_norm": 0.447265625, | |
| "learning_rate": 1.575603460470665e-05, | |
| "loss": 0.7376, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 7.3076923076923075, | |
| "grad_norm": 0.474609375, | |
| "learning_rate": 1.3407386677402312e-05, | |
| "loss": 0.7354, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "grad_norm": 0.447265625, | |
| "learning_rate": 1.1288264143982296e-05, | |
| "loss": 0.7365, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.076923076923077, | |
| "grad_norm": 0.4609375, | |
| "learning_rate": 9.433181002882383e-06, | |
| "loss": 0.731, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 8.461538461538462, | |
| "grad_norm": 0.443359375, | |
| "learning_rate": 7.872350861678565e-06, | |
| "loss": 0.7102, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 8.846153846153847, | |
| "grad_norm": 0.443359375, | |
| "learning_rate": 6.631194850202872e-06, | |
| "loss": 0.7296, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 0.416015625, | |
| "learning_rate": 5.729927588404395e-06, | |
| "loss": 0.7268, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 9.615384615384615, | |
| "grad_norm": 0.41796875, | |
| "learning_rate": 5.1832279522675925e-06, | |
| "loss": 0.7262, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.77734375, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7346, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 130, | |
| "total_flos": 2.5375909456379904e+17, | |
| "train_loss": 0.0, | |
| "train_runtime": 2.0428, | |
| "train_samples_per_second": 964.355, | |
| "train_steps_per_second": 63.638 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 2.5375909456379904e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |