| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.029476787030213707, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005895357406042742, | |
| "eval_loss": 11.93494987487793, | |
| "eval_runtime": 22.1509, | |
| "eval_samples_per_second": 128.979, | |
| "eval_steps_per_second": 16.162, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017686072218128224, | |
| "grad_norm": 0.40249624848365784, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9355, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029476787030213707, | |
| "eval_loss": 11.932616233825684, | |
| "eval_runtime": 21.2141, | |
| "eval_samples_per_second": 134.675, | |
| "eval_steps_per_second": 16.876, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003537214443625645, | |
| "grad_norm": 0.31879347562789917, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9335, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005305821665438467, | |
| "grad_norm": 0.3556462526321411, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9286, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0058953574060427415, | |
| "eval_loss": 11.923737525939941, | |
| "eval_runtime": 21.1557, | |
| "eval_samples_per_second": 135.047, | |
| "eval_steps_per_second": 16.922, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00707442888725129, | |
| "grad_norm": 0.4747415781021118, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 11.9255, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008843036109064112, | |
| "grad_norm": 0.5072726607322693, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9161, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008843036109064112, | |
| "eval_loss": 11.908404350280762, | |
| "eval_runtime": 21.5643, | |
| "eval_samples_per_second": 132.488, | |
| "eval_steps_per_second": 16.602, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010611643330876934, | |
| "grad_norm": 0.509223222732544, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 11.9059, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011790714812085483, | |
| "eval_loss": 11.8934907913208, | |
| "eval_runtime": 21.3386, | |
| "eval_samples_per_second": 133.889, | |
| "eval_steps_per_second": 16.777, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012380250552689757, | |
| "grad_norm": 0.49812066555023193, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 11.8962, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01414885777450258, | |
| "grad_norm": 0.4185691475868225, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 11.8831, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014738393515106854, | |
| "eval_loss": 11.88258171081543, | |
| "eval_runtime": 21.3695, | |
| "eval_samples_per_second": 133.695, | |
| "eval_steps_per_second": 16.753, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0159174649963154, | |
| "grad_norm": 0.444751113653183, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 11.8809, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.017686072218128224, | |
| "grad_norm": 0.4151949882507324, | |
| "learning_rate": 5e-05, | |
| "loss": 11.8796, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017686072218128224, | |
| "eval_loss": 11.876304626464844, | |
| "eval_runtime": 21.2507, | |
| "eval_samples_per_second": 134.442, | |
| "eval_steps_per_second": 16.846, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019454679439941048, | |
| "grad_norm": 0.3371483385562897, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 11.8769, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.020633750921149593, | |
| "eval_loss": 11.87283706665039, | |
| "eval_runtime": 21.1617, | |
| "eval_samples_per_second": 135.008, | |
| "eval_steps_per_second": 16.917, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.021223286661753868, | |
| "grad_norm": 0.3654229938983917, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 11.8738, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02299189388356669, | |
| "grad_norm": 0.3954028785228729, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 11.8702, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.023581429624170966, | |
| "eval_loss": 11.871051788330078, | |
| "eval_runtime": 21.0709, | |
| "eval_samples_per_second": 135.59, | |
| "eval_steps_per_second": 16.99, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.024760501105379515, | |
| "grad_norm": 0.34736475348472595, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 11.8696, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.026529108327192335, | |
| "grad_norm": 0.4360477030277252, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.8703, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026529108327192335, | |
| "eval_loss": 11.870366096496582, | |
| "eval_runtime": 21.2945, | |
| "eval_samples_per_second": 134.166, | |
| "eval_steps_per_second": 16.812, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02829771554900516, | |
| "grad_norm": 0.27372610569000244, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 11.8696, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.029476787030213707, | |
| "eval_loss": 11.87025260925293, | |
| "eval_runtime": 21.3042, | |
| "eval_samples_per_second": 134.105, | |
| "eval_steps_per_second": 16.804, | |
| "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": 55089561600000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |