| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.119047619047619, | |
| "eval_steps": 50, | |
| "global_step": 32, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 46.61829376220703, | |
| "learning_rate": 1e-05, | |
| "loss": 4.6774, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "eval_loss": 1.471437931060791, | |
| "eval_runtime": 1.9182, | |
| "eval_samples_per_second": 9.384, | |
| "eval_steps_per_second": 2.607, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 63.79775619506836, | |
| "learning_rate": 2e-05, | |
| "loss": 6.5028, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 46.904991149902344, | |
| "learning_rate": 3e-05, | |
| "loss": 4.2509, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 45.17517852783203, | |
| "learning_rate": 4e-05, | |
| "loss": 3.119, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 21.702096939086914, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5286, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 4.377859592437744, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0881, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.7174571752548218, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0147, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 0.34401047229766846, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0034, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.39977094531059265, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0057, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.1112188920378685, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0714285714285714, | |
| "grad_norm": 0.043372031301259995, | |
| "learning_rate": 9.949107209404665e-05, | |
| "loss": 0.0022, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1666666666666667, | |
| "grad_norm": 0.06652797013521194, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.0019, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2619047619047619, | |
| "grad_norm": 0.023348161950707436, | |
| "learning_rate": 9.548159976772592e-05, | |
| "loss": 0.0011, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3571428571428572, | |
| "grad_norm": 0.03964816406369209, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.0011, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4523809523809523, | |
| "grad_norm": 0.01563054323196411, | |
| "learning_rate": 8.778747871771292e-05, | |
| "loss": 0.0008, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5476190476190477, | |
| "grad_norm": 0.016337910667061806, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.0006, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.6428571428571428, | |
| "grad_norm": 0.11815639585256577, | |
| "learning_rate": 7.703204087277988e-05, | |
| "loss": 0.0011, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7380952380952381, | |
| "grad_norm": 0.016254905611276627, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0005, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8333333333333335, | |
| "grad_norm": 0.018024485558271408, | |
| "learning_rate": 6.408662784207149e-05, | |
| "loss": 0.0005, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9285714285714286, | |
| "grad_norm": 0.006660263519734144, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0476190476190474, | |
| "grad_norm": 0.010882961563766003, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0004, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 0.01785612478852272, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.0004, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.238095238095238, | |
| "grad_norm": 7.871150016784668, | |
| "learning_rate": 3.591337215792852e-05, | |
| "loss": 0.0022, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.3333333333333335, | |
| "grad_norm": 0.0037954822182655334, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0002, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.4285714285714284, | |
| "grad_norm": 0.005396911408752203, | |
| "learning_rate": 2.296795912722014e-05, | |
| "loss": 0.0002, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.5238095238095237, | |
| "grad_norm": 0.0063310302793979645, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0003, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.619047619047619, | |
| "grad_norm": 0.00621925899758935, | |
| "learning_rate": 1.2212521282287092e-05, | |
| "loss": 0.0003, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.7142857142857144, | |
| "grad_norm": 0.007356972433626652, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0003, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.8095238095238093, | |
| "grad_norm": 0.008695575408637524, | |
| "learning_rate": 4.5184002322740785e-06, | |
| "loss": 0.0003, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.9047619047619047, | |
| "grad_norm": 0.006082715000957251, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.0003, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.0238095238095237, | |
| "grad_norm": 0.007619617972522974, | |
| "learning_rate": 5.089279059533658e-07, | |
| "loss": 0.0003, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.119047619047619, | |
| "grad_norm": 0.007134860381484032, | |
| "learning_rate": 0.0, | |
| "loss": 0.0003, | |
| "step": 32 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 32, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.426912209076224e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |