| { | |
| "best_global_step": 222, | |
| "best_metric": 0.8706896551724138, | |
| "best_model_checkpoint": "regnet_y_400mf-mlxim-finetuned-chest_xray-pneumonia\\checkpoint-222", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 222, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 28.7855167388916, | |
| "learning_rate": 1.956521739130435e-05, | |
| "loss": 0.6087, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "grad_norm": 43.801177978515625, | |
| "learning_rate": 4.130434782608696e-05, | |
| "loss": 0.5084, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 25.356504440307617, | |
| "learning_rate": 4.849246231155779e-05, | |
| "loss": 0.4925, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.54421768707483, | |
| "grad_norm": 26.614465713500977, | |
| "learning_rate": 4.597989949748744e-05, | |
| "loss": 0.4521, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6802721088435374, | |
| "grad_norm": 19.9810848236084, | |
| "learning_rate": 4.346733668341709e-05, | |
| "loss": 0.4434, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 25.83266258239746, | |
| "learning_rate": 4.095477386934674e-05, | |
| "loss": 0.381, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 39.32706069946289, | |
| "learning_rate": 3.844221105527639e-05, | |
| "loss": 0.4107, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6829501915708812, | |
| "eval_loss": 0.6099166870117188, | |
| "eval_runtime": 112.6101, | |
| "eval_samples_per_second": 9.271, | |
| "eval_steps_per_second": 0.293, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.0816326530612246, | |
| "grad_norm": 26.652603149414062, | |
| "learning_rate": 3.592964824120603e-05, | |
| "loss": 0.3729, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.217687074829932, | |
| "grad_norm": 30.554269790649414, | |
| "learning_rate": 3.341708542713568e-05, | |
| "loss": 0.3731, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3537414965986394, | |
| "grad_norm": 20.16573143005371, | |
| "learning_rate": 3.0904522613065326e-05, | |
| "loss": 0.3633, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.489795918367347, | |
| "grad_norm": 38.18863296508789, | |
| "learning_rate": 2.8391959798994978e-05, | |
| "loss": 0.3606, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.6258503401360545, | |
| "grad_norm": 32.72572326660156, | |
| "learning_rate": 2.5879396984924626e-05, | |
| "loss": 0.3292, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.7619047619047619, | |
| "grad_norm": 30.875274658203125, | |
| "learning_rate": 2.3366834170854275e-05, | |
| "loss": 0.3345, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.8979591836734695, | |
| "grad_norm": 36.543487548828125, | |
| "learning_rate": 2.085427135678392e-05, | |
| "loss": 0.3186, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7452107279693486, | |
| "eval_loss": 0.5401968955993652, | |
| "eval_runtime": 118.9784, | |
| "eval_samples_per_second": 8.775, | |
| "eval_steps_per_second": 0.277, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.0272108843537415, | |
| "grad_norm": 34.06245040893555, | |
| "learning_rate": 1.834170854271357e-05, | |
| "loss": 0.3627, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.163265306122449, | |
| "grad_norm": 28.00713539123535, | |
| "learning_rate": 1.5829145728643217e-05, | |
| "loss": 0.3284, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.2993197278911564, | |
| "grad_norm": 41.861385345458984, | |
| "learning_rate": 1.3316582914572864e-05, | |
| "loss": 0.3309, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.435374149659864, | |
| "grad_norm": 23.51487922668457, | |
| "learning_rate": 1.0804020100502512e-05, | |
| "loss": 0.3197, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 34.21602249145508, | |
| "learning_rate": 8.291457286432161e-06, | |
| "loss": 0.3373, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.707482993197279, | |
| "grad_norm": 28.09819221496582, | |
| "learning_rate": 5.778894472361809e-06, | |
| "loss": 0.3174, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.8435374149659864, | |
| "grad_norm": 31.80492401123047, | |
| "learning_rate": 3.2663316582914575e-06, | |
| "loss": 0.3282, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.979591836734694, | |
| "grad_norm": 59.607566833496094, | |
| "learning_rate": 7.537688442211055e-07, | |
| "loss": 0.3731, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8706896551724138, | |
| "eval_loss": 0.33842238783836365, | |
| "eval_runtime": 110.0941, | |
| "eval_samples_per_second": 9.483, | |
| "eval_steps_per_second": 0.3, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 222, | |
| "total_flos": 4.975400461644104e+17, | |
| "train_loss": 0.3838548327351476, | |
| "train_runtime": 9417.8372, | |
| "train_samples_per_second": 2.99, | |
| "train_steps_per_second": 0.024 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 222, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 4.975400461644104e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |