| { | |
| "best_metric": 0.0006509709637612104, | |
| "best_model_checkpoint": "humza-sami/prompt-classifier/checkpoint-247", | |
| "epoch": 19.0, | |
| "eval_steps": 500, | |
| "global_step": 247, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.1265, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.111129641532898, | |
| "eval_runtime": 0.0855, | |
| "eval_samples_per_second": 292.39, | |
| "eval_steps_per_second": 46.782, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.1033, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.108482837677002, | |
| "eval_runtime": 0.0857, | |
| "eval_samples_per_second": 291.796, | |
| "eval_steps_per_second": 46.687, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 3e-06, | |
| "loss": 1.0507, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.1056454181671143, | |
| "eval_runtime": 0.0827, | |
| "eval_samples_per_second": 302.186, | |
| "eval_steps_per_second": 48.35, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.0898, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0706, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.0947411060333252, | |
| "eval_runtime": 0.0864, | |
| "eval_samples_per_second": 289.336, | |
| "eval_steps_per_second": 46.294, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 6e-06, | |
| "loss": 1.0614, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.051918387413025, | |
| "eval_runtime": 0.0973, | |
| "eval_samples_per_second": 256.927, | |
| "eval_steps_per_second": 41.108, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 1.0133, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.8626992702484131, | |
| "eval_runtime": 0.0947, | |
| "eval_samples_per_second": 264.056, | |
| "eval_steps_per_second": 42.249, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.892, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 9e-06, | |
| "loss": 0.7292, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.5572385787963867, | |
| "eval_runtime": 0.0833, | |
| "eval_samples_per_second": 299.954, | |
| "eval_steps_per_second": 47.993, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4992, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.19228488206863403, | |
| "eval_runtime": 0.0864, | |
| "eval_samples_per_second": 289.389, | |
| "eval_steps_per_second": 46.302, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 0.3048, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.05422622710466385, | |
| "eval_runtime": 0.0847, | |
| "eval_samples_per_second": 295.026, | |
| "eval_steps_per_second": 47.204, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.1196, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.0357, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.02210908569395542, | |
| "eval_runtime": 0.0776, | |
| "eval_samples_per_second": 321.978, | |
| "eval_steps_per_second": 51.516, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.0143, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.008073830977082253, | |
| "eval_runtime": 0.0889, | |
| "eval_samples_per_second": 281.316, | |
| "eval_steps_per_second": 45.011, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0071, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.01958407461643219, | |
| "eval_runtime": 0.0969, | |
| "eval_samples_per_second": 257.94, | |
| "eval_steps_per_second": 41.27, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0041, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.00249945605173707, | |
| "eval_runtime": 0.0789, | |
| "eval_samples_per_second": 316.996, | |
| "eval_steps_per_second": 50.719, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 13.08, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 0.003, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0024, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.0013755728723481297, | |
| "eval_runtime": 0.0872, | |
| "eval_samples_per_second": 286.818, | |
| "eval_steps_per_second": 45.891, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.002, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.0011439197696745396, | |
| "eval_runtime": 0.0872, | |
| "eval_samples_per_second": 286.641, | |
| "eval_steps_per_second": 45.863, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0017, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.0010419671889394522, | |
| "eval_runtime": 0.0861, | |
| "eval_samples_per_second": 290.515, | |
| "eval_steps_per_second": 46.482, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 16.15, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0016, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.0014, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.0008559968555346131, | |
| "eval_runtime": 0.0864, | |
| "eval_samples_per_second": 289.468, | |
| "eval_steps_per_second": 46.315, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.0012, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.000737538211978972, | |
| "eval_runtime": 0.0854, | |
| "eval_samples_per_second": 292.593, | |
| "eval_steps_per_second": 46.815, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0011, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.0006509709637612104, | |
| "eval_runtime": 0.0863, | |
| "eval_samples_per_second": 289.626, | |
| "eval_steps_per_second": 46.34, | |
| "step": 247 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 260, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 181727093133432.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |