| { | |
| "best_metric": 0.20911003649234772, | |
| "best_model_checkpoint": "/data/jcanete/all_results/mldoc/albeto_xlarge/epochs_3_bs_16_lr_5e-6/checkpoint-1500", | |
| "epoch": 2.9991546914623837, | |
| "global_step": 1773, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.2770000100135803, | |
| "eval_loss": 1.3528416156768799, | |
| "eval_runtime": 24.2204, | |
| "eval_samples_per_second": 41.287, | |
| "eval_steps_per_second": 5.161, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.47999998927116394, | |
| "eval_loss": 1.0430142879486084, | |
| "eval_runtime": 23.7736, | |
| "eval_samples_per_second": 42.063, | |
| "eval_steps_per_second": 5.258, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.5640000104904175, | |
| "eval_loss": 1.0979323387145996, | |
| "eval_runtime": 23.5496, | |
| "eval_samples_per_second": 42.464, | |
| "eval_steps_per_second": 5.308, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.5720000267028809, | |
| "eval_loss": 0.9388349652290344, | |
| "eval_runtime": 25.4729, | |
| "eval_samples_per_second": 39.257, | |
| "eval_steps_per_second": 4.907, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.601240834743373e-06, | |
| "loss": 0.2676, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.7160000205039978, | |
| "eval_loss": 0.6925698518753052, | |
| "eval_runtime": 24.8675, | |
| "eval_samples_per_second": 40.213, | |
| "eval_steps_per_second": 5.027, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.8560000061988831, | |
| "eval_loss": 0.673073947429657, | |
| "eval_runtime": 25.8013, | |
| "eval_samples_per_second": 38.758, | |
| "eval_steps_per_second": 4.845, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_accuracy": 0.9369999766349792, | |
| "eval_loss": 0.3746216893196106, | |
| "eval_runtime": 25.6232, | |
| "eval_samples_per_second": 39.027, | |
| "eval_steps_per_second": 4.878, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_accuracy": 0.9350000023841858, | |
| "eval_loss": 0.35705798864364624, | |
| "eval_runtime": 25.7852, | |
| "eval_samples_per_second": 38.782, | |
| "eval_steps_per_second": 4.848, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_accuracy": 0.9409999847412109, | |
| "eval_loss": 0.27689608931541443, | |
| "eval_runtime": 24.8438, | |
| "eval_samples_per_second": 40.252, | |
| "eval_steps_per_second": 5.031, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.1912013536379022e-06, | |
| "loss": 0.1019, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_accuracy": 0.9350000023841858, | |
| "eval_loss": 0.291538268327713, | |
| "eval_runtime": 26.3153, | |
| "eval_samples_per_second": 38.001, | |
| "eval_steps_per_second": 4.75, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_accuracy": 0.9509999752044678, | |
| "eval_loss": 0.21956732869148254, | |
| "eval_runtime": 24.9343, | |
| "eval_samples_per_second": 40.105, | |
| "eval_steps_per_second": 5.013, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_accuracy": 0.9520000219345093, | |
| "eval_loss": 0.2259828746318817, | |
| "eval_runtime": 25.7253, | |
| "eval_samples_per_second": 38.872, | |
| "eval_steps_per_second": 4.859, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_accuracy": 0.9509999752044678, | |
| "eval_loss": 0.256782591342926, | |
| "eval_runtime": 25.7431, | |
| "eval_samples_per_second": 38.845, | |
| "eval_steps_per_second": 4.856, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_accuracy": 0.9549999833106995, | |
| "eval_loss": 0.2290709912776947, | |
| "eval_runtime": 24.8624, | |
| "eval_samples_per_second": 40.221, | |
| "eval_steps_per_second": 5.028, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.81161872532431e-07, | |
| "loss": 0.0593, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_accuracy": 0.9589999914169312, | |
| "eval_loss": 0.20911003649234772, | |
| "eval_runtime": 25.438, | |
| "eval_samples_per_second": 39.311, | |
| "eval_steps_per_second": 4.914, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_accuracy": 0.9490000009536743, | |
| "eval_loss": 0.2575547695159912, | |
| "eval_runtime": 25.2822, | |
| "eval_samples_per_second": 39.554, | |
| "eval_steps_per_second": 4.944, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_accuracy": 0.9509999752044678, | |
| "eval_loss": 0.23298123478889465, | |
| "eval_runtime": 25.3064, | |
| "eval_samples_per_second": 39.516, | |
| "eval_steps_per_second": 4.939, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1773, | |
| "total_flos": 3375408735295488.0, | |
| "train_loss": 0.1292072490857808, | |
| "train_runtime": 3156.6951, | |
| "train_samples_per_second": 8.989, | |
| "train_steps_per_second": 0.562 | |
| } | |
| ], | |
| "max_steps": 1773, | |
| "num_train_epochs": 3, | |
| "total_flos": 3375408735295488.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |