| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.27932960893854747, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00558659217877095, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.7411, | |
| "eval_samples_per_second": 34.549, | |
| "eval_steps_per_second": 4.347, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01675977653631285, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027932960893854747, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.1897, | |
| "eval_samples_per_second": 36.876, | |
| "eval_steps_per_second": 4.64, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0335195530726257, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05027932960893855, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.055865921787709494, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.2028, | |
| "eval_samples_per_second": 36.817, | |
| "eval_steps_per_second": 4.633, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0670391061452514, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08379888268156424, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08379888268156424, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.2185, | |
| "eval_samples_per_second": 36.746, | |
| "eval_steps_per_second": 4.624, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1005586592178771, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11173184357541899, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.2114, | |
| "eval_samples_per_second": 36.778, | |
| "eval_steps_per_second": 4.628, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11731843575418995, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1340782122905028, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13966480446927373, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.2183, | |
| "eval_samples_per_second": 36.747, | |
| "eval_steps_per_second": 4.624, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15083798882681565, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16759776536312848, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16759776536312848, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.2227, | |
| "eval_samples_per_second": 36.728, | |
| "eval_steps_per_second": 4.621, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18435754189944134, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19553072625698323, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.2053, | |
| "eval_samples_per_second": 36.806, | |
| "eval_steps_per_second": 4.631, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2011173184357542, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.21787709497206703, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.22346368715083798, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.2123, | |
| "eval_samples_per_second": 36.774, | |
| "eval_steps_per_second": 4.627, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2346368715083799, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.25139664804469275, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.25139664804469275, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.2149, | |
| "eval_samples_per_second": 36.763, | |
| "eval_steps_per_second": 4.626, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2681564245810056, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.27932960893854747, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.2081, | |
| "eval_samples_per_second": 36.793, | |
| "eval_steps_per_second": 4.63, | |
| "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": 1.3607236534272e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |