| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005534493732185848, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011068987464371696, | |
| "eval_loss": 15.692317962646484, | |
| "eval_runtime": 2279.2004, | |
| "eval_samples_per_second": 6.676, | |
| "eval_steps_per_second": 0.835, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003320696239311509, | |
| "grad_norm": 32.227516174316406, | |
| "learning_rate": 3e-05, | |
| "loss": 62.3027, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005534493732185849, | |
| "eval_loss": 13.698588371276855, | |
| "eval_runtime": 2287.6869, | |
| "eval_samples_per_second": 6.651, | |
| "eval_steps_per_second": 0.831, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006641392478623018, | |
| "grad_norm": 38.565956115722656, | |
| "learning_rate": 6e-05, | |
| "loss": 58.5863, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009962088717934527, | |
| "grad_norm": 52.073787689208984, | |
| "learning_rate": 9e-05, | |
| "loss": 40.3884, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011068987464371697, | |
| "eval_loss": 3.4627695083618164, | |
| "eval_runtime": 2290.4417, | |
| "eval_samples_per_second": 6.643, | |
| "eval_steps_per_second": 0.83, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013282784957246035, | |
| "grad_norm": 38.57117462158203, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 13.3548, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0016603481196557546, | |
| "grad_norm": 30.507431030273438, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1808, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016603481196557546, | |
| "eval_loss": 1.3598648309707642, | |
| "eval_runtime": 2290.1174, | |
| "eval_samples_per_second": 6.644, | |
| "eval_steps_per_second": 0.831, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0019924177435869054, | |
| "grad_norm": 18.248498916625977, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.9639, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0022137974928743394, | |
| "eval_loss": 0.33800774812698364, | |
| "eval_runtime": 2289.3613, | |
| "eval_samples_per_second": 6.646, | |
| "eval_steps_per_second": 0.831, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0023244873675180564, | |
| "grad_norm": 5.235165119171143, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 1.4472, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002656556991449207, | |
| "grad_norm": 10.688201904296875, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 1.467, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002767246866092924, | |
| "eval_loss": 0.4081224501132965, | |
| "eval_runtime": 2288.0412, | |
| "eval_samples_per_second": 6.65, | |
| "eval_steps_per_second": 0.831, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002988626615380358, | |
| "grad_norm": 2.59802508354187, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 1.4075, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003320696239311509, | |
| "grad_norm": 4.958655834197998, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1573, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003320696239311509, | |
| "eval_loss": 0.2955036461353302, | |
| "eval_runtime": 2288.277, | |
| "eval_samples_per_second": 6.65, | |
| "eval_steps_per_second": 0.831, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0036527658632426597, | |
| "grad_norm": 6.128028392791748, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 1.0715, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0038741456125300938, | |
| "eval_loss": 0.2891024947166443, | |
| "eval_runtime": 2288.3848, | |
| "eval_samples_per_second": 6.649, | |
| "eval_steps_per_second": 0.831, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.003984835487173811, | |
| "grad_norm": 2.5431346893310547, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 1.0104, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004316905111104961, | |
| "grad_norm": 1.9325594902038574, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.9858, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.004427594985748679, | |
| "eval_loss": 0.3066931962966919, | |
| "eval_runtime": 2292.1204, | |
| "eval_samples_per_second": 6.638, | |
| "eval_steps_per_second": 0.83, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004648974735036113, | |
| "grad_norm": 3.1589062213897705, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.3215, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0049810443589672635, | |
| "grad_norm": 7.741284370422363, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2969, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0049810443589672635, | |
| "eval_loss": 0.3100440800189972, | |
| "eval_runtime": 2289.1555, | |
| "eval_samples_per_second": 6.647, | |
| "eval_steps_per_second": 0.831, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005313113982898414, | |
| "grad_norm": 4.175896644592285, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 1.3884, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.005534493732185848, | |
| "eval_loss": 0.3020959794521332, | |
| "eval_runtime": 2290.7826, | |
| "eval_samples_per_second": 6.642, | |
| "eval_steps_per_second": 0.83, | |
| "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": 1.3781132378112e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |