| { | |
| "best_metric": 0.9463087248322147, | |
| "best_model_checkpoint": "finetuned-for-YogaPoses/checkpoint-200", | |
| "epoch": 4.0, | |
| "eval_steps": 100, | |
| "global_step": 212, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18867924528301888, | |
| "grad_norm": 4.57135009765625, | |
| "learning_rate": 0.00019056603773584906, | |
| "loss": 0.2108, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.37735849056603776, | |
| "grad_norm": 2.5890703201293945, | |
| "learning_rate": 0.00018113207547169812, | |
| "loss": 0.2414, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5660377358490566, | |
| "grad_norm": 8.661531448364258, | |
| "learning_rate": 0.00017169811320754717, | |
| "loss": 0.2201, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7547169811320755, | |
| "grad_norm": 10.479974746704102, | |
| "learning_rate": 0.00016226415094339625, | |
| "loss": 0.3454, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9433962264150944, | |
| "grad_norm": 11.653122901916504, | |
| "learning_rate": 0.0001528301886792453, | |
| "loss": 0.1532, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1320754716981132, | |
| "grad_norm": 14.78357982635498, | |
| "learning_rate": 0.00014339622641509434, | |
| "loss": 0.4086, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.320754716981132, | |
| "grad_norm": 4.90693473815918, | |
| "learning_rate": 0.0001339622641509434, | |
| "loss": 0.2329, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.509433962264151, | |
| "grad_norm": 9.73343563079834, | |
| "learning_rate": 0.00012452830188679244, | |
| "loss": 0.2904, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.6981132075471699, | |
| "grad_norm": 10.988191604614258, | |
| "learning_rate": 0.00011509433962264151, | |
| "loss": 0.162, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.8867924528301887, | |
| "grad_norm": 8.248613357543945, | |
| "learning_rate": 0.00010566037735849057, | |
| "loss": 0.2812, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.8867924528301887, | |
| "eval_accuracy": 0.9328859060402684, | |
| "eval_loss": 0.18304018676280975, | |
| "eval_runtime": 19.9096, | |
| "eval_samples_per_second": 7.484, | |
| "eval_steps_per_second": 0.954, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0754716981132075, | |
| "grad_norm": 0.6969878673553467, | |
| "learning_rate": 9.622641509433963e-05, | |
| "loss": 0.1697, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.2641509433962264, | |
| "grad_norm": 13.04124927520752, | |
| "learning_rate": 8.679245283018869e-05, | |
| "loss": 0.2429, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.452830188679245, | |
| "grad_norm": 0.741187334060669, | |
| "learning_rate": 7.735849056603774e-05, | |
| "loss": 0.2734, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.641509433962264, | |
| "grad_norm": 2.852130889892578, | |
| "learning_rate": 6.79245283018868e-05, | |
| "loss": 0.1988, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.830188679245283, | |
| "grad_norm": 3.7858972549438477, | |
| "learning_rate": 5.849056603773585e-05, | |
| "loss": 0.2767, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.018867924528302, | |
| "grad_norm": 15.999140739440918, | |
| "learning_rate": 4.9056603773584906e-05, | |
| "loss": 0.233, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.207547169811321, | |
| "grad_norm": 8.683842658996582, | |
| "learning_rate": 3.962264150943397e-05, | |
| "loss": 0.1651, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.3962264150943398, | |
| "grad_norm": 13.785407066345215, | |
| "learning_rate": 3.018867924528302e-05, | |
| "loss": 0.139, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.5849056603773586, | |
| "grad_norm": 10.78865909576416, | |
| "learning_rate": 2.0754716981132076e-05, | |
| "loss": 0.2001, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.7735849056603774, | |
| "grad_norm": 7.327868461608887, | |
| "learning_rate": 1.1320754716981132e-05, | |
| "loss": 0.1828, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.7735849056603774, | |
| "eval_accuracy": 0.9463087248322147, | |
| "eval_loss": 0.22337837517261505, | |
| "eval_runtime": 19.9353, | |
| "eval_samples_per_second": 7.474, | |
| "eval_steps_per_second": 0.953, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.9622641509433962, | |
| "grad_norm": 16.639904022216797, | |
| "learning_rate": 1.8867924528301887e-06, | |
| "loss": 0.2423, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 212, | |
| "total_flos": 6760040527650816.0, | |
| "train_loss": 0.23189341304999478, | |
| "train_runtime": 970.6721, | |
| "train_samples_per_second": 3.457, | |
| "train_steps_per_second": 0.218 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 212, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6760040527650816.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |