| { |
| "best_global_step": 1000, |
| "best_metric": 3.8735694885253906, |
| "best_model_checkpoint": "/tmp/colab_artifacts_v2/pretrain_checkpoints/checkpoint-1000", |
| "epoch": 0.21003990758244068, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.010501995379122032, |
| "grad_norm": 16.108776092529297, |
| "learning_rate": 4.716981132075472e-06, |
| "loss": 7.048248901367187, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.021003990758244065, |
| "grad_norm": 7.494509220123291, |
| "learning_rate": 9.958071278825997e-06, |
| "loss": 5.635718994140625, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0315059861373661, |
| "grad_norm": 3.1452040672302246, |
| "learning_rate": 1.5199161425576522e-05, |
| "loss": 4.769013366699219, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.04200798151648813, |
| "grad_norm": 6.104097843170166, |
| "learning_rate": 2.0440251572327044e-05, |
| "loss": 4.167159423828125, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.05250997689561017, |
| "grad_norm": 2.9789626598358154, |
| "learning_rate": 2.5681341719077568e-05, |
| "loss": 4.021661987304688, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.0630119722747322, |
| "grad_norm": 3.7343900203704834, |
| "learning_rate": 3.092243186582809e-05, |
| "loss": 3.8835012817382815, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.07351396765385423, |
| "grad_norm": 3.598313808441162, |
| "learning_rate": 3.6163522012578616e-05, |
| "loss": 3.719826354980469, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.08401596303297626, |
| "grad_norm": 2.9602694511413574, |
| "learning_rate": 4.140461215932914e-05, |
| "loss": 3.6351690673828125, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.0945179584120983, |
| "grad_norm": 2.4005064964294434, |
| "learning_rate": 4.664570230607967e-05, |
| "loss": 3.552754211425781, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.10501995379122034, |
| "grad_norm": 3.6799378395080566, |
| "learning_rate": 4.978991596638656e-05, |
| "loss": 3.5413519287109376, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.10501995379122034, |
| "eval_loss": 4.811308860778809, |
| "eval_runtime": 24.7312, |
| "eval_samples_per_second": 10.958, |
| "eval_steps_per_second": 2.75, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.11552194917034236, |
| "grad_norm": 2.4428603649139404, |
| "learning_rate": 4.9206349206349204e-05, |
| "loss": 3.434654541015625, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.1260239445494644, |
| "grad_norm": 2.2486448287963867, |
| "learning_rate": 4.862278244631186e-05, |
| "loss": 3.5255862426757814, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.13652593992858644, |
| "grad_norm": 2.5440492630004883, |
| "learning_rate": 4.803921568627452e-05, |
| "loss": 3.265621337890625, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.14702793530770847, |
| "grad_norm": 5.0713605880737305, |
| "learning_rate": 4.745564892623716e-05, |
| "loss": 3.3151104736328123, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.1575299306868305, |
| "grad_norm": 3.032827615737915, |
| "learning_rate": 4.6872082166199816e-05, |
| "loss": 3.3802804565429687, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.16803192606595252, |
| "grad_norm": 2.8556971549987793, |
| "learning_rate": 4.6288515406162466e-05, |
| "loss": 3.175123596191406, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.17853392144507457, |
| "grad_norm": 2.813127279281616, |
| "learning_rate": 4.5704948646125116e-05, |
| "loss": 3.1402743530273436, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.1890359168241966, |
| "grad_norm": 3.5564844608306885, |
| "learning_rate": 4.512138188608777e-05, |
| "loss": 3.1378076171875, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.19953791220331862, |
| "grad_norm": 4.420061111450195, |
| "learning_rate": 4.453781512605042e-05, |
| "loss": 3.09103271484375, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.21003990758244068, |
| "grad_norm": 3.6192879676818848, |
| "learning_rate": 4.395424836601307e-05, |
| "loss": 3.145036315917969, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.21003990758244068, |
| "eval_loss": 3.8735694885253906, |
| "eval_runtime": 24.3553, |
| "eval_samples_per_second": 11.127, |
| "eval_steps_per_second": 2.792, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 4761, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.01 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.426615270428672e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
