| { | |
| "best_metric": 1.265008568763733, | |
| "best_model_checkpoint": "cat_breed_image_detection/checkpoint-10164", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 10164, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19677292404565133, | |
| "grad_norm": 9.472394943237305, | |
| "learning_rate": 8.599564959462131e-07, | |
| "loss": 1.2504, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39354584809130266, | |
| "grad_norm": 13.004825592041016, | |
| "learning_rate": 8.154637136642278e-07, | |
| "loss": 1.2416, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5903187721369539, | |
| "grad_norm": 7.997884273529053, | |
| "learning_rate": 7.709709313822424e-07, | |
| "loss": 1.2367, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7870916961826053, | |
| "grad_norm": 8.67659854888916, | |
| "learning_rate": 7.26478149100257e-07, | |
| "loss": 1.2441, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9838646202282566, | |
| "grad_norm": 10.490302085876465, | |
| "learning_rate": 6.819853668182716e-07, | |
| "loss": 1.2106, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6619519486271036, | |
| "eval_loss": 1.2953426837921143, | |
| "eval_model_preparation_time": 0.0055, | |
| "eval_runtime": 1207.1956, | |
| "eval_samples_per_second": 89.782, | |
| "eval_steps_per_second": 2.806, | |
| "step": 2541 | |
| }, | |
| { | |
| "epoch": 1.1806375442739079, | |
| "grad_norm": 9.106962203979492, | |
| "learning_rate": 6.374925845362863e-07, | |
| "loss": 1.2229, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.3774104683195592, | |
| "grad_norm": 6.981090068817139, | |
| "learning_rate": 5.929998022543009e-07, | |
| "loss": 1.2177, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.5741833923652107, | |
| "grad_norm": 13.470215797424316, | |
| "learning_rate": 5.485070199723155e-07, | |
| "loss": 1.1995, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.770956316410862, | |
| "grad_norm": 8.636761665344238, | |
| "learning_rate": 5.040142376903302e-07, | |
| "loss": 1.2087, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.9677292404565132, | |
| "grad_norm": 9.918224334716797, | |
| "learning_rate": 4.5952145540834485e-07, | |
| "loss": 1.2103, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6657993799822852, | |
| "eval_loss": 1.2781411409378052, | |
| "eval_model_preparation_time": 0.0055, | |
| "eval_runtime": 1214.5435, | |
| "eval_samples_per_second": 89.238, | |
| "eval_steps_per_second": 2.789, | |
| "step": 5082 | |
| }, | |
| { | |
| "epoch": 2.1645021645021645, | |
| "grad_norm": 9.103760719299316, | |
| "learning_rate": 4.150286731263595e-07, | |
| "loss": 1.2016, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.3612750885478158, | |
| "grad_norm": 9.183661460876465, | |
| "learning_rate": 3.705358908443741e-07, | |
| "loss": 1.1993, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.558048012593467, | |
| "grad_norm": 7.494422912597656, | |
| "learning_rate": 3.2604310856238877e-07, | |
| "loss": 1.2033, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.7548209366391183, | |
| "grad_norm": 9.207113265991211, | |
| "learning_rate": 2.815503262804034e-07, | |
| "loss": 1.1868, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.9515938606847696, | |
| "grad_norm": 8.814680099487305, | |
| "learning_rate": 2.37057543998418e-07, | |
| "loss": 1.1994, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6672848390906407, | |
| "eval_loss": 1.2696255445480347, | |
| "eval_model_preparation_time": 0.0055, | |
| "eval_runtime": 1228.8502, | |
| "eval_samples_per_second": 88.2, | |
| "eval_steps_per_second": 2.756, | |
| "step": 7623 | |
| }, | |
| { | |
| "epoch": 3.1483667847304213, | |
| "grad_norm": 10.587736129760742, | |
| "learning_rate": 1.9256476171643265e-07, | |
| "loss": 1.1888, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.3451397087760726, | |
| "grad_norm": 7.582997798919678, | |
| "learning_rate": 1.4807197943444728e-07, | |
| "loss": 1.1889, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.541912632821724, | |
| "grad_norm": 12.2061128616333, | |
| "learning_rate": 1.0357919715246192e-07, | |
| "loss": 1.1898, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.738685556867375, | |
| "grad_norm": 8.521767616271973, | |
| "learning_rate": 5.9086414870476566e-08, | |
| "loss": 1.1845, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.9354584809130264, | |
| "grad_norm": 11.329971313476562, | |
| "learning_rate": 1.4593632588491198e-08, | |
| "loss": 1.1925, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6685027310304104, | |
| "eval_loss": 1.265008568763733, | |
| "eval_model_preparation_time": 0.0055, | |
| "eval_runtime": 1388.927, | |
| "eval_samples_per_second": 78.034, | |
| "eval_steps_per_second": 2.439, | |
| "step": 10164 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 10164, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.0414127158862545e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |