| { | |
| "best_metric": 0.69132841, | |
| "best_model_checkpoint": "/home/aiscuser/Swift-Scripts/output/solar-10-7b-instruct-v1/v13-20240202-072530/checkpoint-1600", | |
| "epoch": 1.9144144144144144, | |
| "eval_steps": 100, | |
| "global_step": 1700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "acc": 0.74863632, | |
| "epoch": 0.11, | |
| "learning_rate": 9.158878504672898e-05, | |
| "loss": 0.96384094, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_acc": 0.7936049620361458, | |
| "eval_loss": 0.7536066770553589, | |
| "eval_runtime": 42.7757, | |
| "eval_samples_per_second": 3.366, | |
| "eval_steps_per_second": 1.683, | |
| "step": 100 | |
| }, | |
| { | |
| "acc": 0.78036346, | |
| "epoch": 0.23, | |
| "learning_rate": 9.738751814223513e-05, | |
| "loss": 0.77767517, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_acc": 0.7983638113570741, | |
| "eval_loss": 0.7331455945968628, | |
| "eval_runtime": 42.7344, | |
| "eval_samples_per_second": 3.37, | |
| "eval_steps_per_second": 1.685, | |
| "step": 200 | |
| }, | |
| { | |
| "acc": 0.78766861, | |
| "epoch": 0.34, | |
| "learning_rate": 9.448476052249638e-05, | |
| "loss": 0.74959351, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_acc": 0.8007432360175383, | |
| "eval_loss": 0.721094012260437, | |
| "eval_runtime": 42.8657, | |
| "eval_samples_per_second": 3.359, | |
| "eval_steps_per_second": 1.68, | |
| "step": 300 | |
| }, | |
| { | |
| "acc": 0.79140198, | |
| "epoch": 0.45, | |
| "learning_rate": 9.158200290275763e-05, | |
| "loss": 0.73811386, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_acc": 0.8014650839482408, | |
| "eval_loss": 0.7137336730957031, | |
| "eval_runtime": 42.7833, | |
| "eval_samples_per_second": 3.366, | |
| "eval_steps_per_second": 1.683, | |
| "step": 400 | |
| }, | |
| { | |
| "acc": 0.79137726, | |
| "epoch": 0.56, | |
| "learning_rate": 8.867924528301888e-05, | |
| "loss": 0.73802383, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_acc": 0.8026948989412896, | |
| "eval_loss": 0.7035187482833862, | |
| "eval_runtime": 42.8037, | |
| "eval_samples_per_second": 3.364, | |
| "eval_steps_per_second": 1.682, | |
| "step": 500 | |
| }, | |
| { | |
| "acc": 0.79086266, | |
| "epoch": 0.68, | |
| "learning_rate": 8.577648766328012e-05, | |
| "loss": 0.73371964, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_acc": 0.8036573628488932, | |
| "eval_loss": 0.7004870772361755, | |
| "eval_runtime": 42.738, | |
| "eval_samples_per_second": 3.369, | |
| "eval_steps_per_second": 1.685, | |
| "step": 600 | |
| }, | |
| { | |
| "acc": 0.79403992, | |
| "epoch": 0.79, | |
| "learning_rate": 8.290275761973875e-05, | |
| "loss": 0.72441986, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_acc": 0.8039781841514276, | |
| "eval_loss": 0.6986453533172607, | |
| "eval_runtime": 42.7916, | |
| "eval_samples_per_second": 3.365, | |
| "eval_steps_per_second": 1.683, | |
| "step": 700 | |
| }, | |
| { | |
| "acc": 0.79215607, | |
| "epoch": 0.9, | |
| "learning_rate": 8e-05, | |
| "loss": 0.72639374, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_acc": 0.8061437279435355, | |
| "eval_loss": 0.6950626373291016, | |
| "eval_runtime": 42.7835, | |
| "eval_samples_per_second": 3.366, | |
| "eval_steps_per_second": 1.683, | |
| "step": 800 | |
| }, | |
| { | |
| "acc": 0.79285507, | |
| "epoch": 1.01, | |
| "learning_rate": 7.709724238026124e-05, | |
| "loss": 0.72425797, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_acc": 0.8062774034862582, | |
| "eval_loss": 0.7004315257072449, | |
| "eval_runtime": 42.8077, | |
| "eval_samples_per_second": 3.364, | |
| "eval_steps_per_second": 1.682, | |
| "step": 900 | |
| }, | |
| { | |
| "acc": 0.81319962, | |
| "epoch": 1.13, | |
| "learning_rate": 7.41944847605225e-05, | |
| "loss": 0.63495399, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_acc": 0.804539621430863, | |
| "eval_loss": 0.6987484693527222, | |
| "eval_runtime": 42.8689, | |
| "eval_samples_per_second": 3.359, | |
| "eval_steps_per_second": 1.68, | |
| "step": 1000 | |
| }, | |
| { | |
| "acc": 0.81136383, | |
| "epoch": 1.24, | |
| "learning_rate": 7.129172714078375e-05, | |
| "loss": 0.63906494, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_acc": 0.8052614693615656, | |
| "eval_loss": 0.6985421776771545, | |
| "eval_runtime": 42.8262, | |
| "eval_samples_per_second": 3.362, | |
| "eval_steps_per_second": 1.681, | |
| "step": 1100 | |
| }, | |
| { | |
| "acc": 0.81388062, | |
| "epoch": 1.35, | |
| "learning_rate": 6.8388969521045e-05, | |
| "loss": 0.63106087, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_acc": 0.8074002780451288, | |
| "eval_loss": 0.6972200274467468, | |
| "eval_runtime": 42.7351, | |
| "eval_samples_per_second": 3.37, | |
| "eval_steps_per_second": 1.685, | |
| "step": 1200 | |
| }, | |
| { | |
| "acc": 0.81398033, | |
| "epoch": 1.46, | |
| "learning_rate": 6.548621190130625e-05, | |
| "loss": 0.63091103, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_acc": 0.807854774890386, | |
| "eval_loss": 0.6948702931404114, | |
| "eval_runtime": 42.8184, | |
| "eval_samples_per_second": 3.363, | |
| "eval_steps_per_second": 1.682, | |
| "step": 1300 | |
| }, | |
| { | |
| "acc": 0.81455872, | |
| "epoch": 1.58, | |
| "learning_rate": 6.258345428156749e-05, | |
| "loss": 0.62791916, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_acc": 0.8081755961929206, | |
| "eval_loss": 0.6945727467536926, | |
| "eval_runtime": 42.7416, | |
| "eval_samples_per_second": 3.369, | |
| "eval_steps_per_second": 1.685, | |
| "step": 1400 | |
| }, | |
| { | |
| "acc": 0.81421364, | |
| "epoch": 1.69, | |
| "learning_rate": 5.968069666182874e-05, | |
| "loss": 0.62950912, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_acc": 0.8069992514169607, | |
| "eval_loss": 0.692737340927124, | |
| "eval_runtime": 42.8216, | |
| "eval_samples_per_second": 3.363, | |
| "eval_steps_per_second": 1.681, | |
| "step": 1500 | |
| }, | |
| { | |
| "acc": 0.81544525, | |
| "epoch": 1.8, | |
| "learning_rate": 5.6777939042089986e-05, | |
| "loss": 0.63058929, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_acc": 0.8083894770612768, | |
| "eval_loss": 0.6913284063339233, | |
| "eval_runtime": 42.8047, | |
| "eval_samples_per_second": 3.364, | |
| "eval_steps_per_second": 1.682, | |
| "step": 1600 | |
| }, | |
| { | |
| "acc": 0.81801094, | |
| "epoch": 1.91, | |
| "learning_rate": 5.387518142235124e-05, | |
| "loss": 0.61622761, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_acc": 0.8079349802160197, | |
| "eval_loss": 0.6917322874069214, | |
| "eval_runtime": 42.7927, | |
| "eval_samples_per_second": 3.365, | |
| "eval_steps_per_second": 1.683, | |
| "step": 1700 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3552, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "total_flos": 2.357686760579793e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |