| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013008130081300813, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00026016260162601624, | |
| "eval_loss": 1.6751753091812134, | |
| "eval_runtime": 141.0385, | |
| "eval_samples_per_second": 11.479, | |
| "eval_steps_per_second": 5.743, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013008130081300813, | |
| "grad_norm": 1.0476776361465454, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4272, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0026016260162601626, | |
| "grad_norm": 0.8934007287025452, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5275, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0026016260162601626, | |
| "eval_loss": 1.3305332660675049, | |
| "eval_runtime": 140.9501, | |
| "eval_samples_per_second": 11.486, | |
| "eval_steps_per_second": 5.747, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003902439024390244, | |
| "grad_norm": 1.2252614498138428, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1904, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005203252032520325, | |
| "grad_norm": 1.2517619132995605, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.695, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005203252032520325, | |
| "eval_loss": 0.596894383430481, | |
| "eval_runtime": 140.9354, | |
| "eval_samples_per_second": 11.488, | |
| "eval_steps_per_second": 5.747, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0065040650406504065, | |
| "grad_norm": 1.1258476972579956, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5775, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007804878048780488, | |
| "grad_norm": 1.4381378889083862, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5968, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007804878048780488, | |
| "eval_loss": 0.49518758058547974, | |
| "eval_runtime": 140.8574, | |
| "eval_samples_per_second": 11.494, | |
| "eval_steps_per_second": 5.75, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009105691056910569, | |
| "grad_norm": 0.9850269556045532, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4895, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01040650406504065, | |
| "grad_norm": 0.9892436265945435, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5728, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01040650406504065, | |
| "eval_loss": 0.4556264877319336, | |
| "eval_runtime": 140.766, | |
| "eval_samples_per_second": 11.501, | |
| "eval_steps_per_second": 5.754, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011707317073170732, | |
| "grad_norm": 1.071173906326294, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.527, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013008130081300813, | |
| "grad_norm": 1.2692747116088867, | |
| "learning_rate": 0.0, | |
| "loss": 0.4899, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013008130081300813, | |
| "eval_loss": 0.4491496980190277, | |
| "eval_runtime": 141.0117, | |
| "eval_samples_per_second": 11.481, | |
| "eval_steps_per_second": 5.744, | |
| "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": 1.241628182839296e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |