| { |
| "best_metric": 2.4178671836853027, |
| "best_model_checkpoint": "clip-mixer-300k/checkpoint-18750", |
| "epoch": 3.0, |
| "global_step": 28125, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "learning_rate": 4.9111111111111114e-05, |
| "loss": 2.1259, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 4.8222222222222225e-05, |
| "loss": 1.8445, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 4.7333333333333336e-05, |
| "loss": 1.7594, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 4.644444444444445e-05, |
| "loss": 1.7145, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 4.555555555555556e-05, |
| "loss": 1.6367, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 4.466666666666667e-05, |
| "loss": 1.6162, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 4.377777777777778e-05, |
| "loss": 1.5544, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 4.2888888888888886e-05, |
| "loss": 1.5502, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 4.2e-05, |
| "loss": 1.5128, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 4.111111111111111e-05, |
| "loss": 1.473, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 4.022222222222222e-05, |
| "loss": 1.4328, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 3.933333333333333e-05, |
| "loss": 1.4208, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 3.844444444444444e-05, |
| "loss": 1.4009, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 3.7555555555555554e-05, |
| "loss": 1.3752, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 3.6666666666666666e-05, |
| "loss": 1.3387, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 3.577777777777778e-05, |
| "loss": 1.3141, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 3.4888888888888895e-05, |
| "loss": 1.3023, |
| "step": 8500 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 3.4000000000000007e-05, |
| "loss": 1.2811, |
| "step": 9000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.599307060241699, |
| "eval_runtime": 359.2177, |
| "eval_samples_per_second": 83.515, |
| "eval_steps_per_second": 2.611, |
| "step": 9375 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 3.311111111111112e-05, |
| "loss": 1.1965, |
| "step": 9500 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 3.222222222222223e-05, |
| "loss": 0.9531, |
| "step": 10000 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 3.1333333333333334e-05, |
| "loss": 0.9502, |
| "step": 10500 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 3.044444444444445e-05, |
| "loss": 0.9351, |
| "step": 11000 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 2.955555555555556e-05, |
| "loss": 0.9377, |
| "step": 11500 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 2.8666666666666668e-05, |
| "loss": 0.9437, |
| "step": 12000 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.9403, |
| "step": 12500 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 2.688888888888889e-05, |
| "loss": 0.9138, |
| "step": 13000 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 2.6000000000000002e-05, |
| "loss": 0.9201, |
| "step": 13500 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 2.5111111111111113e-05, |
| "loss": 0.8969, |
| "step": 14000 |
| }, |
| { |
| "epoch": 1.55, |
| "learning_rate": 2.4222222222222224e-05, |
| "loss": 0.9031, |
| "step": 14500 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 2.3333333333333336e-05, |
| "loss": 0.8836, |
| "step": 15000 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 2.2444444444444447e-05, |
| "loss": 0.8711, |
| "step": 15500 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 2.1555555555555555e-05, |
| "loss": 0.8671, |
| "step": 16000 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 2.0666666666666666e-05, |
| "loss": 0.8494, |
| "step": 16500 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 1.9777777777777778e-05, |
| "loss": 0.8346, |
| "step": 17000 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 1.888888888888889e-05, |
| "loss": 0.8396, |
| "step": 17500 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 1.8e-05, |
| "loss": 0.802, |
| "step": 18000 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 1.7111111111111112e-05, |
| "loss": 0.8159, |
| "step": 18500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.4178671836853027, |
| "eval_runtime": 360.9468, |
| "eval_samples_per_second": 83.115, |
| "eval_steps_per_second": 2.599, |
| "step": 18750 |
| }, |
| { |
| "epoch": 2.03, |
| "learning_rate": 1.6222222222222223e-05, |
| "loss": 0.637, |
| "step": 19000 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 1.5333333333333334e-05, |
| "loss": 0.4617, |
| "step": 19500 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 1.4444444444444444e-05, |
| "loss": 0.4634, |
| "step": 20000 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 1.3555555555555557e-05, |
| "loss": 0.4644, |
| "step": 20500 |
| }, |
| { |
| "epoch": 2.24, |
| "learning_rate": 1.2666666666666668e-05, |
| "loss": 0.4426, |
| "step": 21000 |
| }, |
| { |
| "epoch": 2.29, |
| "learning_rate": 1.1777777777777778e-05, |
| "loss": 0.4559, |
| "step": 21500 |
| }, |
| { |
| "epoch": 2.35, |
| "learning_rate": 1.088888888888889e-05, |
| "loss": 0.443, |
| "step": 22000 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 1e-05, |
| "loss": 0.4359, |
| "step": 22500 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 9.111111111111112e-06, |
| "loss": 0.4303, |
| "step": 23000 |
| }, |
| { |
| "epoch": 2.51, |
| "learning_rate": 8.222222222222223e-06, |
| "loss": 0.4228, |
| "step": 23500 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 7.333333333333334e-06, |
| "loss": 0.4125, |
| "step": 24000 |
| }, |
| { |
| "epoch": 2.61, |
| "learning_rate": 6.4444444444444445e-06, |
| "loss": 0.4139, |
| "step": 24500 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 5.555555555555556e-06, |
| "loss": 0.4146, |
| "step": 25000 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 4.666666666666667e-06, |
| "loss": 0.3986, |
| "step": 25500 |
| }, |
| { |
| "epoch": 2.77, |
| "learning_rate": 3.777777777777778e-06, |
| "loss": 0.4017, |
| "step": 26000 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 2.888888888888889e-06, |
| "loss": 0.3922, |
| "step": 26500 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.3917, |
| "step": 27000 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 1.1111111111111112e-06, |
| "loss": 0.385, |
| "step": 27500 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 2.2222222222222224e-07, |
| "loss": 0.374, |
| "step": 28000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 2.4597387313842773, |
| "eval_runtime": 361.6503, |
| "eval_samples_per_second": 82.953, |
| "eval_steps_per_second": 2.594, |
| "step": 28125 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 28125, |
| "total_flos": 9.03625120512e+16, |
| "train_loss": 0.9465052639431424, |
| "train_runtime": 18848.6969, |
| "train_samples_per_second": 47.749, |
| "train_steps_per_second": 1.492 |
| } |
| ], |
| "max_steps": 28125, |
| "num_train_epochs": 3, |
| "total_flos": 9.03625120512e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
