| { | |
| "best_metric": 0.3074355721473694, | |
| "best_model_checkpoint": "finetuned-breast_cancer_images/checkpoint-100", | |
| "epoch": 4.0, | |
| "global_step": 336, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0, | |
| "loss": 0.4362, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0, | |
| "loss": 0.4081, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0, | |
| "loss": 0.5069, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0, | |
| "loss": 0.4546, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0, | |
| "loss": 0.4799, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0, | |
| "loss": 0.5819, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0, | |
| "loss": 0.4704, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0, | |
| "loss": 0.5476, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0, | |
| "loss": 0.5506, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0, | |
| "loss": 0.4716, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_accuracy": 0.8987341772151899, | |
| "eval_loss": 0.3074355721473694, | |
| "eval_runtime": 2.4007, | |
| "eval_samples_per_second": 98.722, | |
| "eval_steps_per_second": 12.496, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0, | |
| "loss": 0.4972, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0, | |
| "loss": 0.5508, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0, | |
| "loss": 0.3687, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0, | |
| "loss": 0.5155, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0, | |
| "loss": 0.4511, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0, | |
| "loss": 0.4943, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0, | |
| "loss": 0.4756, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0, | |
| "loss": 0.4893, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0, | |
| "loss": 0.553, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.0, | |
| "loss": 0.5523, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_accuracy": 0.8987341772151899, | |
| "eval_loss": 0.3074355721473694, | |
| "eval_runtime": 2.4171, | |
| "eval_samples_per_second": 98.05, | |
| "eval_steps_per_second": 12.411, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.0, | |
| "loss": 0.5049, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0, | |
| "loss": 0.4306, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0, | |
| "loss": 0.4699, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.0, | |
| "loss": 0.5013, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0, | |
| "loss": 0.509, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.0, | |
| "loss": 0.4949, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0, | |
| "loss": 0.5185, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.0, | |
| "loss": 0.469, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 0.0, | |
| "loss": 0.5256, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 0.0, | |
| "loss": 0.4472, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_accuracy": 0.8987341772151899, | |
| "eval_loss": 0.3074355721473694, | |
| "eval_runtime": 2.4655, | |
| "eval_samples_per_second": 96.127, | |
| "eval_steps_per_second": 12.168, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 0.0, | |
| "loss": 0.4371, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.0, | |
| "loss": 0.5614, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.0, | |
| "loss": 0.4989, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 336, | |
| "total_flos": 4.156707577848054e+17, | |
| "train_loss": 0.4933107083752042, | |
| "train_runtime": 131.5099, | |
| "train_samples_per_second": 40.788, | |
| "train_steps_per_second": 2.555 | |
| } | |
| ], | |
| "max_steps": 336, | |
| "num_train_epochs": 4, | |
| "total_flos": 4.156707577848054e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |