| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004085384536819528, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.170769073639057e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 463.268, | |
| "eval_samples_per_second": 44.495, | |
| "eval_steps_per_second": 5.563, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00024512307220917167, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004085384536819528, | |
| "eval_loss": NaN, | |
| "eval_runtime": 462.98, | |
| "eval_samples_per_second": 44.522, | |
| "eval_steps_per_second": 5.566, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004902461444183433, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000735369216627515, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008170769073639056, | |
| "eval_loss": NaN, | |
| "eval_runtime": 462.9011, | |
| "eval_samples_per_second": 44.53, | |
| "eval_steps_per_second": 5.567, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009804922888366867, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0012256153610458584, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012256153610458584, | |
| "eval_loss": NaN, | |
| "eval_runtime": 462.8819, | |
| "eval_samples_per_second": 44.532, | |
| "eval_steps_per_second": 5.567, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00147073843325503, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016341538147278112, | |
| "eval_loss": NaN, | |
| "eval_runtime": 462.983, | |
| "eval_samples_per_second": 44.522, | |
| "eval_steps_per_second": 5.566, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001715861505464202, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0019609845776733734, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002042692268409764, | |
| "eval_loss": NaN, | |
| "eval_runtime": 462.9228, | |
| "eval_samples_per_second": 44.528, | |
| "eval_steps_per_second": 5.567, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002206107649882545, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0024512307220917167, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0024512307220917167, | |
| "eval_loss": NaN, | |
| "eval_runtime": 463.0065, | |
| "eval_samples_per_second": 44.52, | |
| "eval_steps_per_second": 5.566, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0026963537943008884, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0028597691757736698, | |
| "eval_loss": NaN, | |
| "eval_runtime": 463.0989, | |
| "eval_samples_per_second": 44.511, | |
| "eval_steps_per_second": 5.565, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00294147686651006, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.003186599938719232, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0032683076294556224, | |
| "eval_loss": NaN, | |
| "eval_runtime": 462.8888, | |
| "eval_samples_per_second": 44.531, | |
| "eval_steps_per_second": 5.567, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003431723010928404, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0036768460831375755, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0036768460831375755, | |
| "eval_loss": NaN, | |
| "eval_runtime": 463.0744, | |
| "eval_samples_per_second": 44.513, | |
| "eval_steps_per_second": 5.565, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003921969155346747, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.004085384536819528, | |
| "eval_loss": NaN, | |
| "eval_runtime": 463.074, | |
| "eval_samples_per_second": 44.513, | |
| "eval_steps_per_second": 5.565, | |
| "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": 1.317128896512e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |