| { |
| "best_global_step": 220, |
| "best_metric": 0.9673469387755103, |
| "best_model_checkpoint": "openscene-vit-dinov3/checkpoint-220", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 220, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5681818181818182, |
| "grad_norm": 4.421525478363037, |
| "learning_rate": 4.94949494949495e-05, |
| "loss": 1.4400157165527343, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9428571428571428, |
| "eval_loss": 0.26997923851013184, |
| "eval_runtime": 1.1805, |
| "eval_samples_per_second": 207.544, |
| "eval_steps_per_second": 6.777, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.1363636363636362, |
| "grad_norm": 4.229369640350342, |
| "learning_rate": 4.318181818181819e-05, |
| "loss": 0.4380963134765625, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.7045454545454546, |
| "grad_norm": 3.172253131866455, |
| "learning_rate": 3.686868686868687e-05, |
| "loss": 0.37906173706054686, |
| "step": 75 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9510204081632653, |
| "eval_loss": 0.16226090490818024, |
| "eval_runtime": 1.1782, |
| "eval_samples_per_second": 207.937, |
| "eval_steps_per_second": 6.79, |
| "step": 88 |
| }, |
| { |
| "epoch": 2.2727272727272725, |
| "grad_norm": 1.5214864015579224, |
| "learning_rate": 3.055555555555556e-05, |
| "loss": 0.20603399276733397, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.840909090909091, |
| "grad_norm": 5.112223148345947, |
| "learning_rate": 2.4242424242424244e-05, |
| "loss": 0.20943599700927734, |
| "step": 125 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9551020408163265, |
| "eval_loss": 0.13978086411952972, |
| "eval_runtime": 1.2117, |
| "eval_samples_per_second": 202.193, |
| "eval_steps_per_second": 6.602, |
| "step": 132 |
| }, |
| { |
| "epoch": 3.409090909090909, |
| "grad_norm": 6.524664878845215, |
| "learning_rate": 1.7929292929292927e-05, |
| "loss": 0.18524658203125, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.9772727272727275, |
| "grad_norm": 4.473592281341553, |
| "learning_rate": 1.1616161616161616e-05, |
| "loss": 0.163247013092041, |
| "step": 175 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9510204081632653, |
| "eval_loss": 0.14097806811332703, |
| "eval_runtime": 1.1694, |
| "eval_samples_per_second": 209.507, |
| "eval_steps_per_second": 6.841, |
| "step": 176 |
| }, |
| { |
| "epoch": 4.545454545454545, |
| "grad_norm": 4.454753875732422, |
| "learning_rate": 5.303030303030304e-06, |
| "loss": 0.1688283348083496, |
| "step": 200 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9673469387755103, |
| "eval_loss": 0.11901210993528366, |
| "eval_runtime": 1.2093, |
| "eval_samples_per_second": 202.6, |
| "eval_steps_per_second": 6.616, |
| "step": 220 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 220, |
| "total_flos": 5.372136194116608e+17, |
| "train_loss": 0.37391618165102875, |
| "train_runtime": 105.9399, |
| "train_samples_per_second": 65.556, |
| "train_steps_per_second": 2.077 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 220, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 5.372136194116608e+17, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
