| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07207207207207207, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014414414414414415, | |
| "eval_loss": 1.645052194595337, | |
| "eval_runtime": 22.5295, | |
| "eval_samples_per_second": 13.005, | |
| "eval_steps_per_second": 6.525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007207207207207207, | |
| "grad_norm": 9.337347030639648, | |
| "learning_rate": 5e-05, | |
| "loss": 6.6234, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014414414414414415, | |
| "grad_norm": 10.592222213745117, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3621, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014414414414414415, | |
| "eval_loss": 1.458554983139038, | |
| "eval_runtime": 23.5258, | |
| "eval_samples_per_second": 12.454, | |
| "eval_steps_per_second": 6.248, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021621621621621623, | |
| "grad_norm": 16.050689697265625, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.2438, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02882882882882883, | |
| "grad_norm": 9.789994239807129, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.7815, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02882882882882883, | |
| "eval_loss": 1.4146848917007446, | |
| "eval_runtime": 24.267, | |
| "eval_samples_per_second": 12.074, | |
| "eval_steps_per_second": 6.058, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.036036036036036036, | |
| "grad_norm": 6.070463180541992, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.7176, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.043243243243243246, | |
| "grad_norm": 8.626254081726074, | |
| "learning_rate": 5e-05, | |
| "loss": 5.8359, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.043243243243243246, | |
| "eval_loss": 1.398380160331726, | |
| "eval_runtime": 24.3726, | |
| "eval_samples_per_second": 12.022, | |
| "eval_steps_per_second": 6.031, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05045045045045045, | |
| "grad_norm": 7.817641258239746, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.3514, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05765765765765766, | |
| "grad_norm": 8.90640926361084, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.224, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05765765765765766, | |
| "eval_loss": 1.3918262720108032, | |
| "eval_runtime": 24.6816, | |
| "eval_samples_per_second": 11.871, | |
| "eval_steps_per_second": 5.956, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06486486486486487, | |
| "grad_norm": 10.465152740478516, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.6809, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07207207207207207, | |
| "grad_norm": 11.144843101501465, | |
| "learning_rate": 0.0, | |
| "loss": 6.1119, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07207207207207207, | |
| "eval_loss": 1.3903932571411133, | |
| "eval_runtime": 24.5969, | |
| "eval_samples_per_second": 11.912, | |
| "eval_steps_per_second": 5.976, | |
| "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": 8938615908335616.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |