| { | |
| "best_metric": 2.4751908779144287, | |
| "best_model_checkpoint": "output/6ix9ine/checkpoint-205", | |
| "epoch": 5.0, | |
| "global_step": 205, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.742060843007589e-06, | |
| "loss": 3.316, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.8312641592473922e-05, | |
| "loss": 3.5414, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.88355754965355e-05, | |
| "loss": 3.3994, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.347351557997133e-05, | |
| "loss": 3.2221, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.882020496458803e-05, | |
| "loss": 3.2784, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00011137140040750911, | |
| "loss": 3.376, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00012800934269961248, | |
| "loss": 3.0065, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0001364337946790438, | |
| "loss": 3.118, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.159865617752075, | |
| "eval_runtime": 2.6213, | |
| "eval_samples_per_second": 20.982, | |
| "eval_steps_per_second": 2.67, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001354800547756731, | |
| "loss": 3.1208, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00012527997991807724, | |
| "loss": 2.8559, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00010724375598316453, | |
| "loss": 2.9927, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.386493606940326e-05, | |
| "loss": 2.9799, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 5.8375700540314535e-05, | |
| "loss": 2.9474, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.4300000000000054e-05, | |
| "loss": 2.8929, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.496636030269317e-05, | |
| "loss": 2.821, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.04770552307078e-06, | |
| "loss": 2.7814, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.0470073223114014, | |
| "eval_runtime": 2.6251, | |
| "eval_samples_per_second": 20.952, | |
| "eval_steps_per_second": 2.667, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.9181951337103552e-07, | |
| "loss": 2.7319, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 6.793535661894039e-06, | |
| "loss": 2.7967, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 2.194015018891494e-05, | |
| "loss": 2.9303, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.3537605728465236e-05, | |
| "loss": 2.6571, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.859999999999997e-05, | |
| "loss": 2.816, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 9.36623942715347e-05, | |
| "loss": 2.8496, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.00011525984981108502, | |
| "loss": 2.9189, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00013040646433810595, | |
| "loss": 2.8699, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.00013700818048662894, | |
| "loss": 2.5821, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.900149345397949, | |
| "eval_runtime": 2.5511, | |
| "eval_samples_per_second": 20.775, | |
| "eval_steps_per_second": 2.744, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.00013415229447692926, | |
| "loss": 2.6428, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.00012223363969730686, | |
| "loss": 2.6782, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00010290000000000009, | |
| "loss": 2.6065, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 7.882429945968553e-05, | |
| "loss": 2.5807, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 5.333506393059687e-05, | |
| "loss": 2.5988, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 2.9956244016835525e-05, | |
| "loss": 2.5281, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.1920020081922795e-05, | |
| "loss": 2.6676, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 1.7199452243269073e-06, | |
| "loss": 2.6813, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.566208600997925, | |
| "eval_runtime": 2.6398, | |
| "eval_samples_per_second": 20.835, | |
| "eval_steps_per_second": 2.652, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 9.63352496067802e-06, | |
| "loss": 2.2438, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 2.7012936807688713e-05, | |
| "loss": 2.4722, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 5.042226894930893e-05, | |
| "loss": 2.5159, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 7.646728298233023e-05, | |
| "loss": 2.2916, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.00010137157954994105, | |
| "loss": 2.3591, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 0.00012152415773578518, | |
| "loss": 2.7456, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 0.0001340029924949682, | |
| "loss": 2.4208, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0001369987139612046, | |
| "loss": 2.3052, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.4751908779144287, | |
| "eval_runtime": 3.015, | |
| "eval_samples_per_second": 21.227, | |
| "eval_steps_per_second": 2.653, | |
| "step": 205 | |
| } | |
| ], | |
| "max_steps": 205, | |
| "num_train_epochs": 5, | |
| "total_flos": 210470731776000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |