| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08650519031141868, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017301038062283738, | |
| "eval_loss": 2.302046537399292, | |
| "eval_runtime": 15.5992, | |
| "eval_samples_per_second": 15.642, | |
| "eval_steps_per_second": 7.821, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00865051903114187, | |
| "grad_norm": 24.06183433532715, | |
| "learning_rate": 5e-05, | |
| "loss": 9.0626, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01730103806228374, | |
| "grad_norm": 27.19295883178711, | |
| "learning_rate": 0.0001, | |
| "loss": 8.5014, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01730103806228374, | |
| "eval_loss": 2.070117473602295, | |
| "eval_runtime": 15.6921, | |
| "eval_samples_per_second": 15.549, | |
| "eval_steps_per_second": 7.775, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025951557093425604, | |
| "grad_norm": 21.27532386779785, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 8.0084, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03460207612456748, | |
| "grad_norm": 19.899616241455078, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.9735, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03460207612456748, | |
| "eval_loss": 1.817107915878296, | |
| "eval_runtime": 16.0994, | |
| "eval_samples_per_second": 15.156, | |
| "eval_steps_per_second": 7.578, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04325259515570934, | |
| "grad_norm": 21.587718963623047, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 7.4689, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05190311418685121, | |
| "grad_norm": 39.68190002441406, | |
| "learning_rate": 5e-05, | |
| "loss": 7.2719, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05190311418685121, | |
| "eval_loss": 1.784308910369873, | |
| "eval_runtime": 15.9451, | |
| "eval_samples_per_second": 15.303, | |
| "eval_steps_per_second": 7.651, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06055363321799308, | |
| "grad_norm": 25.20235824584961, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 7.7887, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06920415224913495, | |
| "grad_norm": 15.550032615661621, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.1321, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06920415224913495, | |
| "eval_loss": 1.7673637866973877, | |
| "eval_runtime": 16.0282, | |
| "eval_samples_per_second": 15.223, | |
| "eval_steps_per_second": 7.612, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07785467128027682, | |
| "grad_norm": 18.17325210571289, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 7.0574, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08650519031141868, | |
| "grad_norm": 17.976709365844727, | |
| "learning_rate": 0.0, | |
| "loss": 7.3887, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08650519031141868, | |
| "eval_loss": 1.7634177207946777, | |
| "eval_runtime": 15.8295, | |
| "eval_samples_per_second": 15.414, | |
| "eval_steps_per_second": 7.707, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8763358996070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |