| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006198667286533395, | |
| "eval_steps": 3, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.479466914613358e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.479466914613358e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1449.1424, | |
| "eval_samples_per_second": 23.437, | |
| "eval_steps_per_second": 11.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.958933829226716e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.438400743840075e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.438400743840075e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1449.9698, | |
| "eval_samples_per_second": 23.424, | |
| "eval_steps_per_second": 11.712, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.917867658453432e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001239733457306679, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001487680148768015, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001487680148768015, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1451.6845, | |
| "eval_samples_per_second": 23.396, | |
| "eval_steps_per_second": 11.698, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00017356268402293507, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00019835735316906864, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00022315202231520224, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00022315202231520224, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1451.3675, | |
| "eval_samples_per_second": 23.401, | |
| "eval_steps_per_second": 11.701, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002479466914613358, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0002727413606074694, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.000297536029753603, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.000297536029753603, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1449.1471, | |
| "eval_samples_per_second": 23.437, | |
| "eval_steps_per_second": 11.719, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00032233069889973654, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00034712536804587014, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00037192003719200374, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00037192003719200374, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1449.1097, | |
| "eval_samples_per_second": 23.438, | |
| "eval_steps_per_second": 11.719, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003967147063381373, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0004215093754842709, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0004463040446304045, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0004463040446304045, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1449.581, | |
| "eval_samples_per_second": 23.43, | |
| "eval_steps_per_second": 11.715, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.000471098713776538, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0004958933829226716, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005206880520688052, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0005206880520688052, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1451.8773, | |
| "eval_samples_per_second": 23.393, | |
| "eval_steps_per_second": 11.697, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0005454827212149388, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0005702773903610724, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.000595072059507206, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000595072059507206, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1449.6919, | |
| "eval_samples_per_second": 23.428, | |
| "eval_steps_per_second": 11.714, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0006198667286533395, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": 6531344184115200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |