| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03402445507708666, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017012227538543328, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017012227538543328, | |
| "eval_loss": NaN, | |
| "eval_runtime": 118.1515, | |
| "eval_samples_per_second": 8.379, | |
| "eval_steps_per_second": 4.19, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034024455077086655, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005103668261562998, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006804891015417331, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "eval_loss": NaN, | |
| "eval_runtime": 61.2185, | |
| "eval_samples_per_second": 16.172, | |
| "eval_steps_per_second": 8.086, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01190855927698033, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 790.2877, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013609782030834662, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015311004784688996, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01701222753854333, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01701222753854333, | |
| "eval_loss": NaN, | |
| "eval_runtime": 74.9176, | |
| "eval_samples_per_second": 13.215, | |
| "eval_steps_per_second": 6.607, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020414673046251993, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.1183, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022115895800106325, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02381711855396066, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025518341307814992, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025518341307814992, | |
| "eval_loss": NaN, | |
| "eval_runtime": 74.9253, | |
| "eval_samples_per_second": 13.213, | |
| "eval_steps_per_second": 6.607, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027219564061669324, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.028920786815523656, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03062200956937799, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 883.2592, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03232323232323232, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03402445507708666, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03402445507708666, | |
| "eval_loss": NaN, | |
| "eval_runtime": 74.9591, | |
| "eval_samples_per_second": 13.207, | |
| "eval_steps_per_second": 6.604, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.6183106592505856e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |