| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009028733945782453, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.5143669728912266e-05, | |
| "eval_loss": 2.5635130405426025, | |
| "eval_runtime": 298.4496, | |
| "eval_samples_per_second": 31.252, | |
| "eval_steps_per_second": 7.814, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00045143669728912265, | |
| "grad_norm": 0.6829887628555298, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3672, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009028733945782453, | |
| "grad_norm": 0.6255219578742981, | |
| "learning_rate": 0.0002, | |
| "loss": 2.174, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001354310091867368, | |
| "grad_norm": 0.6357229948043823, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1169, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0018057467891564906, | |
| "grad_norm": 0.6617687940597534, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2879, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0022571834864456132, | |
| "grad_norm": 0.6272353529930115, | |
| "learning_rate": 0.0002, | |
| "loss": 2.219, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0022571834864456132, | |
| "eval_loss": 2.1563453674316406, | |
| "eval_runtime": 297.2114, | |
| "eval_samples_per_second": 31.382, | |
| "eval_steps_per_second": 7.846, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002708620183734736, | |
| "grad_norm": 0.6150534749031067, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0668, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0031600568810238585, | |
| "grad_norm": 0.629759669303894, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1185, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.003611493578312981, | |
| "grad_norm": 0.5716665983200073, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1695, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.004062930275602104, | |
| "grad_norm": 0.8046770691871643, | |
| "learning_rate": 0.0002, | |
| "loss": 2.002, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0045143669728912265, | |
| "grad_norm": 0.5744296312332153, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1034, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0045143669728912265, | |
| "eval_loss": 2.102687120437622, | |
| "eval_runtime": 296.9029, | |
| "eval_samples_per_second": 31.414, | |
| "eval_steps_per_second": 7.854, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004965803670180349, | |
| "grad_norm": 0.6123510599136353, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0783, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.005417240367469472, | |
| "grad_norm": 0.6725351214408875, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0282, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.005868677064758594, | |
| "grad_norm": 0.6317930221557617, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1056, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.006320113762047717, | |
| "grad_norm": 0.6830048561096191, | |
| "learning_rate": 0.0002, | |
| "loss": 2.063, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.00677155045933684, | |
| "grad_norm": 0.6954776644706726, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9812, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.00677155045933684, | |
| "eval_loss": 2.0730745792388916, | |
| "eval_runtime": 296.9969, | |
| "eval_samples_per_second": 31.404, | |
| "eval_steps_per_second": 7.852, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.007222987156625962, | |
| "grad_norm": 0.6882342100143433, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0299, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.007674423853915085, | |
| "grad_norm": 0.6809920072555542, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1699, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.008125860551204208, | |
| "grad_norm": 0.6971638798713684, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9678, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.00857729724849333, | |
| "grad_norm": 0.6451826691627502, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0033, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.009028733945782453, | |
| "grad_norm": 0.739595890045166, | |
| "learning_rate": 0.0002, | |
| "loss": 2.037, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.009028733945782453, | |
| "eval_loss": 2.0487308502197266, | |
| "eval_runtime": 297.0738, | |
| "eval_samples_per_second": 31.396, | |
| "eval_steps_per_second": 7.85, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.890390469967872e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |