| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 24.0, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.6789208650588989, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4645, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.8403657674789429, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7164, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.49805760383605957, | |
| "learning_rate": 0.00019285714285714286, | |
| "loss": 1.3102, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.41022056341171265, | |
| "learning_rate": 0.00018571428571428572, | |
| "loss": 1.2661, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.3694780766963959, | |
| "learning_rate": 0.0001785714285714286, | |
| "loss": 1.4341, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 0.3030174672603607, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 1.1851, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "grad_norm": 0.2777923345565796, | |
| "learning_rate": 0.00016428571428571428, | |
| "loss": 1.0019, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 0.3465845584869385, | |
| "learning_rate": 0.00015714285714285716, | |
| "loss": 1.1571, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "grad_norm": 0.18477143347263336, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.6604, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.33299827575683594, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 0.9984, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "grad_norm": 0.29114991426467896, | |
| "learning_rate": 0.00013571428571428572, | |
| "loss": 0.7564, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "grad_norm": 0.41081565618515015, | |
| "learning_rate": 0.00012857142857142858, | |
| "loss": 0.9316, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "grad_norm": 0.2087474763393402, | |
| "learning_rate": 0.00012142857142857143, | |
| "loss": 0.519, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "grad_norm": 0.3250860869884491, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 0.6471, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.2854531407356262, | |
| "learning_rate": 0.00010714285714285715, | |
| "loss": 0.6497, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "grad_norm": 0.22819894552230835, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5187, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "grad_norm": 0.2653699517250061, | |
| "learning_rate": 9.285714285714286e-05, | |
| "loss": 0.5952, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "grad_norm": 0.19908660650253296, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.4334, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "grad_norm": 0.18152070045471191, | |
| "learning_rate": 7.857142857142858e-05, | |
| "loss": 0.4109, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 0.21493348479270935, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 0.4921, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "grad_norm": 0.17556029558181763, | |
| "learning_rate": 6.428571428571429e-05, | |
| "loss": 0.4047, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "grad_norm": 0.2304663360118866, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.455, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "grad_norm": 0.1766856610774994, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3617, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "grad_norm": 0.21619734168052673, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.4267, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.18261326849460602, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.3513, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "grad_norm": 0.1662844866514206, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.3451, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "grad_norm": 0.17096859216690063, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.3272, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "grad_norm": 0.18789789080619812, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.3846, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "grad_norm": 0.20240667462348938, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 0.3596, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 0.17768487334251404, | |
| "learning_rate": 0.0, | |
| "loss": 0.3359, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "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": 3973144527212544.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |