| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017520805957074025, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003504161191414805, | |
| "eval_loss": NaN, | |
| "eval_runtime": 518.3461, | |
| "eval_samples_per_second": 9.272, | |
| "eval_steps_per_second": 1.159, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010512483574244415, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017520805957074025, | |
| "eval_loss": NaN, | |
| "eval_runtime": 518.7288, | |
| "eval_samples_per_second": 9.265, | |
| "eval_steps_per_second": 1.159, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002102496714848883, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0031537450722733244, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003504161191414805, | |
| "eval_loss": NaN, | |
| "eval_runtime": 518.5802, | |
| "eval_samples_per_second": 9.268, | |
| "eval_steps_per_second": 1.159, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004204993429697766, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005256241787122208, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005256241787122208, | |
| "eval_loss": NaN, | |
| "eval_runtime": 518.8609, | |
| "eval_samples_per_second": 9.263, | |
| "eval_steps_per_second": 1.158, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006307490144546649, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00700832238282961, | |
| "eval_loss": NaN, | |
| "eval_runtime": 518.8327, | |
| "eval_samples_per_second": 9.263, | |
| "eval_steps_per_second": 1.158, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007358738501971091, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008409986859395532, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008760402978537012, | |
| "eval_loss": NaN, | |
| "eval_runtime": 518.7316, | |
| "eval_samples_per_second": 9.265, | |
| "eval_steps_per_second": 1.159, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009461235216819974, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010512483574244415, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010512483574244415, | |
| "eval_loss": NaN, | |
| "eval_runtime": 518.7787, | |
| "eval_samples_per_second": 9.264, | |
| "eval_steps_per_second": 1.158, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011563731931668857, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.012264564169951819, | |
| "eval_loss": NaN, | |
| "eval_runtime": 518.5102, | |
| "eval_samples_per_second": 9.269, | |
| "eval_steps_per_second": 1.159, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.012614980289093298, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01366622864651774, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01401664476565922, | |
| "eval_loss": NaN, | |
| "eval_runtime": 518.5471, | |
| "eval_samples_per_second": 9.268, | |
| "eval_steps_per_second": 1.159, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014717477003942181, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01576872536136662, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01576872536136662, | |
| "eval_loss": NaN, | |
| "eval_runtime": 518.5655, | |
| "eval_samples_per_second": 9.268, | |
| "eval_steps_per_second": 1.159, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.016819973718791063, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.017520805957074025, | |
| "eval_loss": NaN, | |
| "eval_runtime": 518.601, | |
| "eval_samples_per_second": 9.267, | |
| "eval_steps_per_second": 1.159, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "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": 1.0517835366059213e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |