| { | |
| "best_metric": 1.084580659866333, | |
| "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": 8.859833717346191, | |
| "learning_rate": 8.599564959462131e-07, | |
| "loss": 1.0519, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39354584809130266, | |
| "grad_norm": 10.870162010192871, | |
| "learning_rate": 8.154637136642278e-07, | |
| "loss": 1.0529, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5903187721369539, | |
| "grad_norm": 11.251194953918457, | |
| "learning_rate": 7.709709313822424e-07, | |
| "loss": 1.0397, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7870916961826053, | |
| "grad_norm": 12.0984468460083, | |
| "learning_rate": 7.26478149100257e-07, | |
| "loss": 1.0515, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9838646202282566, | |
| "grad_norm": 7.28156042098999, | |
| "learning_rate": 6.819853668182716e-07, | |
| "loss": 1.0337, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7004354886330085, | |
| "eval_loss": 1.1068506240844727, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 1190.7929, | |
| "eval_samples_per_second": 91.018, | |
| "eval_steps_per_second": 2.844, | |
| "step": 2541 | |
| }, | |
| { | |
| "epoch": 1.1806375442739079, | |
| "grad_norm": 8.778160095214844, | |
| "learning_rate": 6.374925845362863e-07, | |
| "loss": 1.0223, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.3774104683195592, | |
| "grad_norm": 8.823763847351074, | |
| "learning_rate": 5.929998022543009e-07, | |
| "loss": 1.0247, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.5741833923652107, | |
| "grad_norm": 9.15168285369873, | |
| "learning_rate": 5.485070199723155e-07, | |
| "loss": 1.024, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.770956316410862, | |
| "grad_norm": 10.23277473449707, | |
| "learning_rate": 5.040142376903302e-07, | |
| "loss": 1.0362, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.9677292404565132, | |
| "grad_norm": 8.250983238220215, | |
| "learning_rate": 4.5952145540834485e-07, | |
| "loss": 1.0253, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7026590640684972, | |
| "eval_loss": 1.09512197971344, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 1206.999, | |
| "eval_samples_per_second": 89.796, | |
| "eval_steps_per_second": 2.806, | |
| "step": 5082 | |
| }, | |
| { | |
| "epoch": 2.1645021645021645, | |
| "grad_norm": 11.255722045898438, | |
| "learning_rate": 4.150286731263595e-07, | |
| "loss": 1.0128, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.3612750885478158, | |
| "grad_norm": 11.691879272460938, | |
| "learning_rate": 3.705358908443741e-07, | |
| "loss": 1.0168, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.558048012593467, | |
| "grad_norm": 10.441214561462402, | |
| "learning_rate": 3.2604310856238877e-07, | |
| "loss": 1.0093, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.7548209366391183, | |
| "grad_norm": 7.868481159210205, | |
| "learning_rate": 2.815503262804034e-07, | |
| "loss": 1.0133, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.9515938606847696, | |
| "grad_norm": 10.433448791503906, | |
| "learning_rate": 2.37057543998418e-07, | |
| "loss": 1.0152, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7059898139946855, | |
| "eval_loss": 1.0874797105789185, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 1227.8405, | |
| "eval_samples_per_second": 88.272, | |
| "eval_steps_per_second": 2.759, | |
| "step": 7623 | |
| }, | |
| { | |
| "epoch": 3.1483667847304213, | |
| "grad_norm": 8.449857711791992, | |
| "learning_rate": 1.9256476171643265e-07, | |
| "loss": 1.0039, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.3451397087760726, | |
| "grad_norm": 13.326553344726562, | |
| "learning_rate": 1.4807197943444728e-07, | |
| "loss": 1.0143, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.541912632821724, | |
| "grad_norm": 8.523683547973633, | |
| "learning_rate": 1.0357919715246192e-07, | |
| "loss": 1.0021, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.738685556867375, | |
| "grad_norm": 10.767390251159668, | |
| "learning_rate": 5.9086414870476566e-08, | |
| "loss": 1.0003, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.9354584809130264, | |
| "grad_norm": 8.742927551269531, | |
| "learning_rate": 1.4593632588491198e-08, | |
| "loss": 1.0086, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7055469441984057, | |
| "eval_loss": 1.084580659866333, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 1210.0183, | |
| "eval_samples_per_second": 89.572, | |
| "eval_steps_per_second": 2.799, | |
| "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 | |
| } | |