| { | |
| "best_metric": 0.8354740061162079, | |
| "best_model_checkpoint": "checkpoints/boolq-roberta/checkpoint-15930", | |
| "epoch": 54.0, | |
| "global_step": 15930, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5525993883792049, | |
| "eval_loss": 0.6860924959182739, | |
| "eval_runtime": 9.8191, | |
| "eval_samples_per_second": 333.024, | |
| "eval_steps_per_second": 41.654, | |
| "step": 295 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5525993883792049, | |
| "epoch": 1.0, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0068813559322033905, | |
| "loss": 0.768, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6259938837920489, | |
| "eval_loss": 0.6413273811340332, | |
| "eval_runtime": 9.8093, | |
| "eval_samples_per_second": 333.357, | |
| "eval_steps_per_second": 41.695, | |
| "step": 590 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.6259938837920489, | |
| "epoch": 2.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7058103975535168, | |
| "eval_loss": 0.7142531871795654, | |
| "eval_runtime": 9.821, | |
| "eval_samples_per_second": 332.961, | |
| "eval_steps_per_second": 41.646, | |
| "step": 885 | |
| }, | |
| { | |
| "best_epoch": 2, | |
| "best_eval_accuracy": 0.7058103975535168, | |
| "epoch": 3.0, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.00676271186440678, | |
| "loss": 0.7341, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7798165137614679, | |
| "eval_loss": 0.4908980429172516, | |
| "eval_runtime": 9.8251, | |
| "eval_samples_per_second": 332.822, | |
| "eval_steps_per_second": 41.628, | |
| "step": 1180 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.7798165137614679, | |
| "epoch": 4.0, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7865443425076453, | |
| "eval_loss": 0.4921702444553375, | |
| "eval_runtime": 9.8323, | |
| "eval_samples_per_second": 332.579, | |
| "eval_steps_per_second": 41.598, | |
| "step": 1475 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.7865443425076453, | |
| "epoch": 5.0, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 0.00664406779661017, | |
| "loss": 0.6102, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.791743119266055, | |
| "eval_loss": 0.5190699696540833, | |
| "eval_runtime": 9.8121, | |
| "eval_samples_per_second": 333.263, | |
| "eval_steps_per_second": 41.683, | |
| "step": 1770 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.791743119266055, | |
| "epoch": 6.0, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 0.006525423728813559, | |
| "loss": 0.5638, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7602446483180428, | |
| "eval_loss": 0.5134357810020447, | |
| "eval_runtime": 9.8046, | |
| "eval_samples_per_second": 333.516, | |
| "eval_steps_per_second": 41.715, | |
| "step": 2065 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.791743119266055, | |
| "epoch": 7.0, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8048929663608563, | |
| "eval_loss": 0.4786987006664276, | |
| "eval_runtime": 9.8048, | |
| "eval_samples_per_second": 333.508, | |
| "eval_steps_per_second": 41.714, | |
| "step": 2360 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.8048929663608563, | |
| "epoch": 8.0, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 0.006406779661016949, | |
| "loss": 0.5123, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8036697247706422, | |
| "eval_loss": 0.4702308177947998, | |
| "eval_runtime": 9.8236, | |
| "eval_samples_per_second": 332.873, | |
| "eval_steps_per_second": 41.635, | |
| "step": 2655 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.8048929663608563, | |
| "epoch": 9.0, | |
| "step": 2655 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.791743119266055, | |
| "eval_loss": 0.5443930625915527, | |
| "eval_runtime": 9.8027, | |
| "eval_samples_per_second": 333.58, | |
| "eval_steps_per_second": 41.723, | |
| "step": 2950 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.8048929663608563, | |
| "epoch": 10.0, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 0.006288135593220339, | |
| "loss": 0.5045, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7871559633027523, | |
| "eval_loss": 0.5409664511680603, | |
| "eval_runtime": 9.8211, | |
| "eval_samples_per_second": 332.955, | |
| "eval_steps_per_second": 41.645, | |
| "step": 3245 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.8048929663608563, | |
| "epoch": 11.0, | |
| "step": 3245 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 0.006169491525423729, | |
| "loss": 0.4583, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8162079510703364, | |
| "eval_loss": 0.460715115070343, | |
| "eval_runtime": 9.8053, | |
| "eval_samples_per_second": 333.493, | |
| "eval_steps_per_second": 41.712, | |
| "step": 3540 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.8162079510703364, | |
| "epoch": 12.0, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8079510703363915, | |
| "eval_loss": 0.5161741375923157, | |
| "eval_runtime": 9.8021, | |
| "eval_samples_per_second": 333.603, | |
| "eval_steps_per_second": 41.726, | |
| "step": 3835 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.8162079510703364, | |
| "epoch": 13.0, | |
| "step": 3835 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "learning_rate": 0.006050847457627119, | |
| "loss": 0.4401, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.826605504587156, | |
| "eval_loss": 0.5039022564888, | |
| "eval_runtime": 9.7965, | |
| "eval_samples_per_second": 333.792, | |
| "eval_steps_per_second": 41.75, | |
| "step": 4130 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.826605504587156, | |
| "epoch": 14.0, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.807645259938838, | |
| "eval_loss": 0.4858939051628113, | |
| "eval_runtime": 9.8364, | |
| "eval_samples_per_second": 332.437, | |
| "eval_steps_per_second": 41.58, | |
| "step": 4425 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.826605504587156, | |
| "epoch": 15.0, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "learning_rate": 0.005932203389830509, | |
| "loss": 0.4317, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8006116207951071, | |
| "eval_loss": 0.5990845561027527, | |
| "eval_runtime": 9.8097, | |
| "eval_samples_per_second": 333.344, | |
| "eval_steps_per_second": 41.694, | |
| "step": 4720 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.826605504587156, | |
| "epoch": 16.0, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 0.005813559322033898, | |
| "loss": 0.3821, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8214067278287461, | |
| "eval_loss": 0.6158734560012817, | |
| "eval_runtime": 9.8135, | |
| "eval_samples_per_second": 333.213, | |
| "eval_steps_per_second": 41.677, | |
| "step": 5015 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.826605504587156, | |
| "epoch": 17.0, | |
| "step": 5015 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8024464831804281, | |
| "eval_loss": 0.6013011336326599, | |
| "eval_runtime": 9.8051, | |
| "eval_samples_per_second": 333.5, | |
| "eval_steps_per_second": 41.713, | |
| "step": 5310 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.826605504587156, | |
| "epoch": 18.0, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "learning_rate": 0.005694915254237288, | |
| "loss": 0.3534, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8226299694189603, | |
| "eval_loss": 0.5256037712097168, | |
| "eval_runtime": 9.8062, | |
| "eval_samples_per_second": 333.464, | |
| "eval_steps_per_second": 41.708, | |
| "step": 5605 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.826605504587156, | |
| "epoch": 19.0, | |
| "step": 5605 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8256880733944955, | |
| "eval_loss": 0.6150120496749878, | |
| "eval_runtime": 9.8251, | |
| "eval_samples_per_second": 332.821, | |
| "eval_steps_per_second": 41.628, | |
| "step": 5900 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.826605504587156, | |
| "epoch": 20.0, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 20.34, | |
| "learning_rate": 0.005576271186440678, | |
| "loss": 0.337, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.828440366972477, | |
| "eval_loss": 0.5820947885513306, | |
| "eval_runtime": 9.8077, | |
| "eval_samples_per_second": 333.413, | |
| "eval_steps_per_second": 41.702, | |
| "step": 6195 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.828440366972477, | |
| "epoch": 21.0, | |
| "step": 6195 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.82782874617737, | |
| "eval_loss": 0.5438685417175293, | |
| "eval_runtime": 9.8107, | |
| "eval_samples_per_second": 333.309, | |
| "eval_steps_per_second": 41.689, | |
| "step": 6490 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.828440366972477, | |
| "epoch": 22.0, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 22.03, | |
| "learning_rate": 0.005457627118644068, | |
| "loss": 0.3002, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8302752293577982, | |
| "eval_loss": 0.568505048751831, | |
| "eval_runtime": 9.8907, | |
| "eval_samples_per_second": 330.614, | |
| "eval_steps_per_second": 41.352, | |
| "step": 6785 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 23.0, | |
| "step": 6785 | |
| }, | |
| { | |
| "epoch": 23.73, | |
| "learning_rate": 0.005338983050847458, | |
| "loss": 0.2875, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8125382262996942, | |
| "eval_loss": 0.6513988375663757, | |
| "eval_runtime": 9.8218, | |
| "eval_samples_per_second": 332.932, | |
| "eval_steps_per_second": 41.642, | |
| "step": 7080 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 24.0, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8223241590214068, | |
| "eval_loss": 0.6830200552940369, | |
| "eval_runtime": 9.8098, | |
| "eval_samples_per_second": 333.34, | |
| "eval_steps_per_second": 41.693, | |
| "step": 7375 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 25.0, | |
| "step": 7375 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 0.005220338983050848, | |
| "loss": 0.2724, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8207951070336391, | |
| "eval_loss": 0.6568824052810669, | |
| "eval_runtime": 9.8777, | |
| "eval_samples_per_second": 331.049, | |
| "eval_steps_per_second": 41.406, | |
| "step": 7670 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 26.0, | |
| "step": 7670 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8275229357798165, | |
| "eval_loss": 0.6946196556091309, | |
| "eval_runtime": 9.7866, | |
| "eval_samples_per_second": 334.131, | |
| "eval_steps_per_second": 41.792, | |
| "step": 7965 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 27.0, | |
| "step": 7965 | |
| }, | |
| { | |
| "epoch": 27.12, | |
| "learning_rate": 0.005101694915254237, | |
| "loss": 0.2599, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8229357798165138, | |
| "eval_loss": 0.7936107516288757, | |
| "eval_runtime": 9.8279, | |
| "eval_samples_per_second": 332.727, | |
| "eval_steps_per_second": 41.616, | |
| "step": 8260 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 28.0, | |
| "step": 8260 | |
| }, | |
| { | |
| "epoch": 28.81, | |
| "learning_rate": 0.004983050847457627, | |
| "loss": 0.2504, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.8287461773700305, | |
| "eval_loss": 0.6681709885597229, | |
| "eval_runtime": 9.8102, | |
| "eval_samples_per_second": 333.327, | |
| "eval_steps_per_second": 41.691, | |
| "step": 8555 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 29.0, | |
| "step": 8555 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8226299694189603, | |
| "eval_loss": 0.7363224029541016, | |
| "eval_runtime": 9.8095, | |
| "eval_samples_per_second": 333.349, | |
| "eval_steps_per_second": 41.694, | |
| "step": 8850 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 30.0, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 30.51, | |
| "learning_rate": 0.004864406779661017, | |
| "loss": 0.2333, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.8287461773700305, | |
| "eval_loss": 0.6868186593055725, | |
| "eval_runtime": 9.835, | |
| "eval_samples_per_second": 332.487, | |
| "eval_steps_per_second": 41.586, | |
| "step": 9145 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 31.0, | |
| "step": 9145 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8299694189602447, | |
| "eval_loss": 0.7315894365310669, | |
| "eval_runtime": 9.8164, | |
| "eval_samples_per_second": 333.117, | |
| "eval_steps_per_second": 41.665, | |
| "step": 9440 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 32.0, | |
| "step": 9440 | |
| }, | |
| { | |
| "epoch": 32.2, | |
| "learning_rate": 0.0047457627118644066, | |
| "loss": 0.2116, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.8235474006116208, | |
| "eval_loss": 0.7920485734939575, | |
| "eval_runtime": 9.8087, | |
| "eval_samples_per_second": 333.379, | |
| "eval_steps_per_second": 41.698, | |
| "step": 9735 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 33.0, | |
| "step": 9735 | |
| }, | |
| { | |
| "epoch": 33.9, | |
| "learning_rate": 0.004627118644067797, | |
| "loss": 0.2016, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.8302752293577982, | |
| "eval_loss": 0.8122466802597046, | |
| "eval_runtime": 9.8089, | |
| "eval_samples_per_second": 333.371, | |
| "eval_steps_per_second": 41.697, | |
| "step": 10030 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 34.0, | |
| "step": 10030 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.8235474006116208, | |
| "eval_loss": 0.8033488988876343, | |
| "eval_runtime": 9.8046, | |
| "eval_samples_per_second": 333.516, | |
| "eval_steps_per_second": 41.715, | |
| "step": 10325 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 35.0, | |
| "step": 10325 | |
| }, | |
| { | |
| "epoch": 35.59, | |
| "learning_rate": 0.004508474576271186, | |
| "loss": 0.2053, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8275229357798165, | |
| "eval_loss": 0.8479099273681641, | |
| "eval_runtime": 9.8042, | |
| "eval_samples_per_second": 333.529, | |
| "eval_steps_per_second": 41.717, | |
| "step": 10620 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 36.0, | |
| "step": 10620 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.826605504587156, | |
| "eval_loss": 0.7674300074577332, | |
| "eval_runtime": 9.8042, | |
| "eval_samples_per_second": 333.532, | |
| "eval_steps_per_second": 41.717, | |
| "step": 10915 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 37.0, | |
| "step": 10915 | |
| }, | |
| { | |
| "epoch": 37.29, | |
| "learning_rate": 0.004389830508474577, | |
| "loss": 0.1784, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.8302752293577982, | |
| "eval_loss": 0.7334691882133484, | |
| "eval_runtime": 9.8101, | |
| "eval_samples_per_second": 333.331, | |
| "eval_steps_per_second": 41.692, | |
| "step": 11210 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 38.0, | |
| "step": 11210 | |
| }, | |
| { | |
| "epoch": 38.98, | |
| "learning_rate": 0.004271186440677966, | |
| "loss": 0.1742, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.8244648318042813, | |
| "eval_loss": 0.8439134955406189, | |
| "eval_runtime": 9.8448, | |
| "eval_samples_per_second": 332.155, | |
| "eval_steps_per_second": 41.545, | |
| "step": 11505 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 39.0, | |
| "step": 11505 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8269113149847095, | |
| "eval_loss": 0.7226125597953796, | |
| "eval_runtime": 9.7971, | |
| "eval_samples_per_second": 333.772, | |
| "eval_steps_per_second": 41.747, | |
| "step": 11800 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 40.0, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 40.68, | |
| "learning_rate": 0.0041525423728813555, | |
| "loss": 0.1607, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.8262996941896025, | |
| "eval_loss": 0.783122181892395, | |
| "eval_runtime": 9.8034, | |
| "eval_samples_per_second": 333.559, | |
| "eval_steps_per_second": 41.72, | |
| "step": 12095 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 41.0, | |
| "step": 12095 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.8204892966360856, | |
| "eval_loss": 0.8774231672286987, | |
| "eval_runtime": 9.8122, | |
| "eval_samples_per_second": 333.26, | |
| "eval_steps_per_second": 41.683, | |
| "step": 12390 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 42.0, | |
| "step": 12390 | |
| }, | |
| { | |
| "epoch": 42.37, | |
| "learning_rate": 0.004033898305084746, | |
| "loss": 0.1482, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.8201834862385321, | |
| "eval_loss": 0.9140273928642273, | |
| "eval_runtime": 9.8202, | |
| "eval_samples_per_second": 332.988, | |
| "eval_steps_per_second": 41.649, | |
| "step": 12685 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 43.0, | |
| "step": 12685 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8293577981651377, | |
| "eval_loss": 1.0441981554031372, | |
| "eval_runtime": 9.8317, | |
| "eval_samples_per_second": 332.596, | |
| "eval_steps_per_second": 41.6, | |
| "step": 12980 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 44.0, | |
| "step": 12980 | |
| }, | |
| { | |
| "epoch": 44.07, | |
| "learning_rate": 0.003915254237288135, | |
| "loss": 0.1353, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.8204892966360856, | |
| "eval_loss": 0.9284624457359314, | |
| "eval_runtime": 9.8086, | |
| "eval_samples_per_second": 333.381, | |
| "eval_steps_per_second": 41.698, | |
| "step": 13275 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 45.0, | |
| "step": 13275 | |
| }, | |
| { | |
| "epoch": 45.76, | |
| "learning_rate": 0.0037966101694915256, | |
| "loss": 0.1442, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.8296636085626912, | |
| "eval_loss": 0.9967836141586304, | |
| "eval_runtime": 9.7985, | |
| "eval_samples_per_second": 333.726, | |
| "eval_steps_per_second": 41.741, | |
| "step": 13570 | |
| }, | |
| { | |
| "best_epoch": 22, | |
| "best_eval_accuracy": 0.8302752293577982, | |
| "epoch": 46.0, | |
| "step": 13570 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.969611406326294, | |
| "eval_runtime": 9.8112, | |
| "eval_samples_per_second": 333.294, | |
| "eval_steps_per_second": 41.687, | |
| "step": 13865 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.8333333333333334, | |
| "epoch": 47.0, | |
| "step": 13865 | |
| }, | |
| { | |
| "epoch": 47.46, | |
| "learning_rate": 0.0036779661016949155, | |
| "loss": 0.1308, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.9742096662521362, | |
| "eval_runtime": 9.8104, | |
| "eval_samples_per_second": 333.319, | |
| "eval_steps_per_second": 41.69, | |
| "step": 14160 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.8333333333333334, | |
| "epoch": 48.0, | |
| "step": 14160 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.8324159021406727, | |
| "eval_loss": 0.9350805282592773, | |
| "eval_runtime": 9.8421, | |
| "eval_samples_per_second": 332.247, | |
| "eval_steps_per_second": 41.556, | |
| "step": 14455 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.8333333333333334, | |
| "epoch": 49.0, | |
| "step": 14455 | |
| }, | |
| { | |
| "epoch": 49.15, | |
| "learning_rate": 0.003559322033898305, | |
| "loss": 0.12, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.8232415902140673, | |
| "eval_loss": 1.0194205045700073, | |
| "eval_runtime": 9.8031, | |
| "eval_samples_per_second": 333.567, | |
| "eval_steps_per_second": 41.721, | |
| "step": 14750 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.8333333333333334, | |
| "epoch": 50.0, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 50.85, | |
| "learning_rate": 0.0034406779661016952, | |
| "loss": 0.1151, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 1.0169928073883057, | |
| "eval_runtime": 9.8124, | |
| "eval_samples_per_second": 333.252, | |
| "eval_steps_per_second": 41.682, | |
| "step": 15045 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.8333333333333334, | |
| "epoch": 51.0, | |
| "step": 15045 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.8324159021406727, | |
| "eval_loss": 0.9195823073387146, | |
| "eval_runtime": 9.8284, | |
| "eval_samples_per_second": 332.708, | |
| "eval_steps_per_second": 41.614, | |
| "step": 15340 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.8333333333333334, | |
| "epoch": 52.0, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 52.54, | |
| "learning_rate": 0.003322033898305085, | |
| "loss": 0.1081, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.8290519877675842, | |
| "eval_loss": 0.9286013245582581, | |
| "eval_runtime": 9.8253, | |
| "eval_samples_per_second": 332.815, | |
| "eval_steps_per_second": 41.627, | |
| "step": 15635 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.8333333333333334, | |
| "epoch": 53.0, | |
| "step": 15635 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.8354740061162079, | |
| "eval_loss": 0.9297749400138855, | |
| "eval_runtime": 9.8216, | |
| "eval_samples_per_second": 332.938, | |
| "eval_steps_per_second": 41.643, | |
| "step": 15930 | |
| }, | |
| { | |
| "best_epoch": 53, | |
| "best_eval_accuracy": 0.8354740061162079, | |
| "epoch": 54.0, | |
| "step": 15930 | |
| } | |
| ], | |
| "max_steps": 29500, | |
| "num_train_epochs": 100, | |
| "total_flos": 1.1860177898825626e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |