| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08553100498930863, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002851033499643621, | |
| "eval_loss": 10.161999702453613, | |
| "eval_runtime": 1.9355, | |
| "eval_samples_per_second": 76.465, | |
| "eval_steps_per_second": 38.233, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008553100498930863, | |
| "grad_norm": 9.774493217468262, | |
| "learning_rate": 6e-05, | |
| "loss": 10.488, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017106200997861726, | |
| "grad_norm": 11.545764923095703, | |
| "learning_rate": 0.00012, | |
| "loss": 10.096, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022808267997148968, | |
| "eval_loss": 9.838736534118652, | |
| "eval_runtime": 1.9191, | |
| "eval_samples_per_second": 77.121, | |
| "eval_steps_per_second": 38.561, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02565930149679259, | |
| "grad_norm": 10.72104263305664, | |
| "learning_rate": 0.00018, | |
| "loss": 9.9893, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03421240199572345, | |
| "grad_norm": 9.705013275146484, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 9.9066, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.042765502494654314, | |
| "grad_norm": 10.249577522277832, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 9.0912, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.045616535994297935, | |
| "eval_loss": 8.672515869140625, | |
| "eval_runtime": 1.9292, | |
| "eval_samples_per_second": 76.717, | |
| "eval_steps_per_second": 38.359, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05131860299358518, | |
| "grad_norm": 9.849855422973633, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 8.873, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05987170349251604, | |
| "grad_norm": 9.548686027526855, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 8.3583, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0684248039914469, | |
| "grad_norm": 9.711939811706543, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 8.0473, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0684248039914469, | |
| "eval_loss": 7.907596111297607, | |
| "eval_runtime": 1.9255, | |
| "eval_samples_per_second": 76.862, | |
| "eval_steps_per_second": 38.431, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07697790449037777, | |
| "grad_norm": 12.171854019165039, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 7.895, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08553100498930863, | |
| "grad_norm": 9.699213981628418, | |
| "learning_rate": 0.0, | |
| "loss": 8.0159, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4294084657152.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |