| { | |
| "best_metric": 0.8307692307692308, | |
| "best_model_checkpoint": "omarmomen/tf_babylm_1/finetune/sst2/checkpoint-1600", | |
| "epoch": 4.556962025316456, | |
| "global_step": 3600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.7657480239868164, | |
| "eval_f1": 0.7733333333333333, | |
| "eval_loss": 0.48952749371528625, | |
| "eval_mcc": 0.533119535626159, | |
| "eval_runtime": 0.6794, | |
| "eval_samples_per_second": 747.755, | |
| "eval_steps_per_second": 94.205, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.7834645509719849, | |
| "eval_f1": 0.8007246376811594, | |
| "eval_loss": 0.4489835798740387, | |
| "eval_mcc": 0.576754658800836, | |
| "eval_runtime": 0.6711, | |
| "eval_samples_per_second": 756.956, | |
| "eval_steps_per_second": 95.364, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.683544303797468e-05, | |
| "loss": 0.4517, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.8129921555519104, | |
| "eval_f1": 0.8183556405353728, | |
| "eval_loss": 0.4774584472179413, | |
| "eval_mcc": 0.6274832725618316, | |
| "eval_runtime": 0.6731, | |
| "eval_samples_per_second": 754.687, | |
| "eval_steps_per_second": 95.079, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_accuracy": 0.8228346705436707, | |
| "eval_f1": 0.8170731707317073, | |
| "eval_loss": 0.4105101227760315, | |
| "eval_mcc": 0.6465702369056265, | |
| "eval_runtime": 0.6717, | |
| "eval_samples_per_second": 756.27, | |
| "eval_steps_per_second": 95.278, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.367088607594937e-05, | |
| "loss": 0.2923, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_accuracy": 0.8149606585502625, | |
| "eval_f1": 0.8239700374531835, | |
| "eval_loss": 0.4857898950576782, | |
| "eval_mcc": 0.6339364104084189, | |
| "eval_runtime": 0.6723, | |
| "eval_samples_per_second": 755.671, | |
| "eval_steps_per_second": 95.203, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_accuracy": 0.8169291615486145, | |
| "eval_f1": 0.8228571428571428, | |
| "eval_loss": 0.5239109992980957, | |
| "eval_mcc": 0.6357405398605986, | |
| "eval_runtime": 0.6727, | |
| "eval_samples_per_second": 755.204, | |
| "eval_steps_per_second": 95.144, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_accuracy": 0.7637795209884644, | |
| "eval_f1": 0.7902097902097902, | |
| "eval_loss": 0.6100760698318481, | |
| "eval_mcc": 0.5467773556337732, | |
| "eval_runtime": 0.6727, | |
| "eval_samples_per_second": 755.151, | |
| "eval_steps_per_second": 95.137, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.050632911392405e-05, | |
| "loss": 0.2322, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_accuracy": 0.8267716765403748, | |
| "eval_f1": 0.8307692307692308, | |
| "eval_loss": 0.6272916197776794, | |
| "eval_mcc": 0.6546078105862819, | |
| "eval_runtime": 0.6722, | |
| "eval_samples_per_second": 755.698, | |
| "eval_steps_per_second": 95.206, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_accuracy": 0.7992125749588013, | |
| "eval_f1": 0.8068181818181818, | |
| "eval_loss": 0.6427187919616699, | |
| "eval_mcc": 0.6008122892984797, | |
| "eval_runtime": 0.6732, | |
| "eval_samples_per_second": 754.579, | |
| "eval_steps_per_second": 95.065, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 3.7341772151898736e-05, | |
| "loss": 0.1644, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_accuracy": 0.8169291615486145, | |
| "eval_f1": 0.8180039138943248, | |
| "eval_loss": 0.5454850196838379, | |
| "eval_mcc": 0.6340038022931133, | |
| "eval_runtime": 0.6736, | |
| "eval_samples_per_second": 754.184, | |
| "eval_steps_per_second": 95.015, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_accuracy": 0.8149606585502625, | |
| "eval_f1": 0.8104838709677419, | |
| "eval_loss": 0.5786112546920776, | |
| "eval_mcc": 0.6303470266599184, | |
| "eval_runtime": 0.6734, | |
| "eval_samples_per_second": 754.357, | |
| "eval_steps_per_second": 95.037, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_accuracy": 0.8188976645469666, | |
| "eval_f1": 0.8250950570342205, | |
| "eval_loss": 0.7192121148109436, | |
| "eval_mcc": 0.6398874815952302, | |
| "eval_runtime": 0.6726, | |
| "eval_samples_per_second": 755.237, | |
| "eval_steps_per_second": 95.148, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 3.4177215189873416e-05, | |
| "loss": 0.1477, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "eval_accuracy": 0.8051180839538574, | |
| "eval_f1": 0.8107074569789675, | |
| "eval_loss": 0.7842402458190918, | |
| "eval_mcc": 0.6117037813256844, | |
| "eval_runtime": 0.6735, | |
| "eval_samples_per_second": 754.282, | |
| "eval_steps_per_second": 95.028, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "eval_accuracy": 0.7854330539703369, | |
| "eval_f1": 0.7970204841713222, | |
| "eval_loss": 0.7084320783615112, | |
| "eval_mcc": 0.575362828713563, | |
| "eval_runtime": 0.6735, | |
| "eval_samples_per_second": 754.266, | |
| "eval_steps_per_second": 95.026, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 3.10126582278481e-05, | |
| "loss": 0.1101, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_accuracy": 0.7775590419769287, | |
| "eval_f1": 0.7941712204007286, | |
| "eval_loss": 0.8787282109260559, | |
| "eval_mcc": 0.5635308581623699, | |
| "eval_runtime": 0.6726, | |
| "eval_samples_per_second": 755.3, | |
| "eval_steps_per_second": 95.156, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_accuracy": 0.7775590419769287, | |
| "eval_f1": 0.7911275415896488, | |
| "eval_loss": 0.9535109996795654, | |
| "eval_mcc": 0.5606954034738957, | |
| "eval_runtime": 0.674, | |
| "eval_samples_per_second": 753.699, | |
| "eval_steps_per_second": 94.954, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "eval_accuracy": 0.789370059967041, | |
| "eval_f1": 0.7914230019493177, | |
| "eval_loss": 0.9281810522079468, | |
| "eval_mcc": 0.5789992073276542, | |
| "eval_runtime": 0.6733, | |
| "eval_samples_per_second": 754.472, | |
| "eval_steps_per_second": 95.052, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 2.7848101265822786e-05, | |
| "loss": 0.0878, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "eval_accuracy": 0.7992125749588013, | |
| "eval_f1": 0.7992125984251969, | |
| "eval_loss": 0.8580671548843384, | |
| "eval_mcc": 0.5984499728745253, | |
| "eval_runtime": 0.6728, | |
| "eval_samples_per_second": 755.083, | |
| "eval_steps_per_second": 95.129, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "step": 3600, | |
| "total_flos": 6318390507405312.0, | |
| "train_loss": 0.2085385314623515, | |
| "train_runtime": 617.8306, | |
| "train_samples_per_second": 817.829, | |
| "train_steps_per_second": 12.787 | |
| } | |
| ], | |
| "max_steps": 7900, | |
| "num_train_epochs": 10, | |
| "total_flos": 6318390507405312.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |