Bespoke-Stratos-17k / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
17c0a34 verified
raw
history blame
7.06 kB
{"current_steps": 10, "total_steps": 363, "loss": 0.8018, "lr": 5e-06, "epoch": 0.0823045267489712, "percentage": 2.75, "elapsed_time": "0:02:16", "remaining_time": "1:20:13"}
{"current_steps": 20, "total_steps": 363, "loss": 0.6615, "lr": 5e-06, "epoch": 0.1646090534979424, "percentage": 5.51, "elapsed_time": "0:04:28", "remaining_time": "1:16:41"}
{"current_steps": 30, "total_steps": 363, "loss": 0.6226, "lr": 5e-06, "epoch": 0.24691358024691357, "percentage": 8.26, "elapsed_time": "0:06:39", "remaining_time": "1:13:58"}
{"current_steps": 40, "total_steps": 363, "loss": 0.5947, "lr": 5e-06, "epoch": 0.3292181069958848, "percentage": 11.02, "elapsed_time": "0:08:51", "remaining_time": "1:11:32"}
{"current_steps": 50, "total_steps": 363, "loss": 0.5731, "lr": 5e-06, "epoch": 0.411522633744856, "percentage": 13.77, "elapsed_time": "0:11:03", "remaining_time": "1:09:12"}
{"current_steps": 60, "total_steps": 363, "loss": 0.5748, "lr": 5e-06, "epoch": 0.49382716049382713, "percentage": 16.53, "elapsed_time": "0:13:14", "remaining_time": "1:06:53"}
{"current_steps": 70, "total_steps": 363, "loss": 0.5696, "lr": 5e-06, "epoch": 0.5761316872427984, "percentage": 19.28, "elapsed_time": "0:15:26", "remaining_time": "1:04:37"}
{"current_steps": 80, "total_steps": 363, "loss": 0.5579, "lr": 5e-06, "epoch": 0.6584362139917695, "percentage": 22.04, "elapsed_time": "0:17:38", "remaining_time": "1:02:23"}
{"current_steps": 90, "total_steps": 363, "loss": 0.563, "lr": 5e-06, "epoch": 0.7407407407407407, "percentage": 24.79, "elapsed_time": "0:19:50", "remaining_time": "1:00:10"}
{"current_steps": 100, "total_steps": 363, "loss": 0.5506, "lr": 5e-06, "epoch": 0.823045267489712, "percentage": 27.55, "elapsed_time": "0:22:02", "remaining_time": "0:57:57"}
{"current_steps": 110, "total_steps": 363, "loss": 0.5526, "lr": 5e-06, "epoch": 0.9053497942386831, "percentage": 30.3, "elapsed_time": "0:24:13", "remaining_time": "0:55:43"}
{"current_steps": 120, "total_steps": 363, "loss": 0.5415, "lr": 5e-06, "epoch": 0.9876543209876543, "percentage": 33.06, "elapsed_time": "0:26:25", "remaining_time": "0:53:30"}
{"current_steps": 121, "total_steps": 363, "eval_loss": 0.5658594369888306, "epoch": 0.9958847736625515, "percentage": 33.33, "elapsed_time": "0:27:15", "remaining_time": "0:54:30"}
{"current_steps": 130, "total_steps": 363, "loss": 0.5334, "lr": 5e-06, "epoch": 1.0699588477366255, "percentage": 35.81, "elapsed_time": "0:30:12", "remaining_time": "0:54:09"}
{"current_steps": 140, "total_steps": 363, "loss": 0.5067, "lr": 5e-06, "epoch": 1.1522633744855968, "percentage": 38.57, "elapsed_time": "0:32:25", "remaining_time": "0:51:38"}
{"current_steps": 150, "total_steps": 363, "loss": 0.4975, "lr": 5e-06, "epoch": 1.2345679012345678, "percentage": 41.32, "elapsed_time": "0:34:37", "remaining_time": "0:49:09"}
{"current_steps": 160, "total_steps": 363, "loss": 0.4907, "lr": 5e-06, "epoch": 1.316872427983539, "percentage": 44.08, "elapsed_time": "0:36:49", "remaining_time": "0:46:42"}
{"current_steps": 170, "total_steps": 363, "loss": 0.4846, "lr": 5e-06, "epoch": 1.3991769547325104, "percentage": 46.83, "elapsed_time": "0:39:01", "remaining_time": "0:44:18"}
{"current_steps": 180, "total_steps": 363, "loss": 0.4857, "lr": 5e-06, "epoch": 1.4814814814814814, "percentage": 49.59, "elapsed_time": "0:41:13", "remaining_time": "0:41:54"}
{"current_steps": 190, "total_steps": 363, "loss": 0.4922, "lr": 5e-06, "epoch": 1.5637860082304527, "percentage": 52.34, "elapsed_time": "0:43:25", "remaining_time": "0:39:32"}
{"current_steps": 200, "total_steps": 363, "loss": 0.485, "lr": 5e-06, "epoch": 1.646090534979424, "percentage": 55.1, "elapsed_time": "0:45:37", "remaining_time": "0:37:11"}
{"current_steps": 210, "total_steps": 363, "loss": 0.4899, "lr": 5e-06, "epoch": 1.7283950617283952, "percentage": 57.85, "elapsed_time": "0:47:49", "remaining_time": "0:34:50"}
{"current_steps": 220, "total_steps": 363, "loss": 0.4794, "lr": 5e-06, "epoch": 1.8106995884773662, "percentage": 60.61, "elapsed_time": "0:50:01", "remaining_time": "0:32:31"}
{"current_steps": 230, "total_steps": 363, "loss": 0.4925, "lr": 5e-06, "epoch": 1.8930041152263375, "percentage": 63.36, "elapsed_time": "0:52:13", "remaining_time": "0:30:11"}
{"current_steps": 240, "total_steps": 363, "loss": 0.486, "lr": 5e-06, "epoch": 1.9753086419753085, "percentage": 66.12, "elapsed_time": "0:54:25", "remaining_time": "0:27:53"}
{"current_steps": 243, "total_steps": 363, "eval_loss": 0.552381157875061, "epoch": 2.0, "percentage": 66.94, "elapsed_time": "0:55:34", "remaining_time": "0:27:26"}
{"current_steps": 250, "total_steps": 363, "loss": 0.4643, "lr": 5e-06, "epoch": 2.05761316872428, "percentage": 68.87, "elapsed_time": "0:58:15", "remaining_time": "0:26:19"}
{"current_steps": 260, "total_steps": 363, "loss": 0.4264, "lr": 5e-06, "epoch": 2.139917695473251, "percentage": 71.63, "elapsed_time": "1:00:27", "remaining_time": "0:23:56"}
{"current_steps": 270, "total_steps": 363, "loss": 0.427, "lr": 5e-06, "epoch": 2.2222222222222223, "percentage": 74.38, "elapsed_time": "1:02:39", "remaining_time": "0:21:34"}
{"current_steps": 280, "total_steps": 363, "loss": 0.4284, "lr": 5e-06, "epoch": 2.3045267489711936, "percentage": 77.13, "elapsed_time": "1:04:51", "remaining_time": "0:19:13"}
{"current_steps": 290, "total_steps": 363, "loss": 0.4298, "lr": 5e-06, "epoch": 2.386831275720165, "percentage": 79.89, "elapsed_time": "1:07:03", "remaining_time": "0:16:52"}
{"current_steps": 300, "total_steps": 363, "loss": 0.4332, "lr": 5e-06, "epoch": 2.4691358024691357, "percentage": 82.64, "elapsed_time": "1:09:15", "remaining_time": "0:14:32"}
{"current_steps": 310, "total_steps": 363, "loss": 0.432, "lr": 5e-06, "epoch": 2.551440329218107, "percentage": 85.4, "elapsed_time": "1:11:27", "remaining_time": "0:12:13"}
{"current_steps": 320, "total_steps": 363, "loss": 0.4297, "lr": 5e-06, "epoch": 2.633744855967078, "percentage": 88.15, "elapsed_time": "1:13:39", "remaining_time": "0:09:53"}
{"current_steps": 330, "total_steps": 363, "loss": 0.4301, "lr": 5e-06, "epoch": 2.7160493827160495, "percentage": 90.91, "elapsed_time": "1:15:51", "remaining_time": "0:07:35"}
{"current_steps": 340, "total_steps": 363, "loss": 0.4256, "lr": 5e-06, "epoch": 2.7983539094650207, "percentage": 93.66, "elapsed_time": "1:18:03", "remaining_time": "0:05:16"}
{"current_steps": 350, "total_steps": 363, "loss": 0.4252, "lr": 5e-06, "epoch": 2.8806584362139915, "percentage": 96.42, "elapsed_time": "1:20:15", "remaining_time": "0:02:58"}
{"current_steps": 360, "total_steps": 363, "loss": 0.4216, "lr": 5e-06, "epoch": 2.962962962962963, "percentage": 99.17, "elapsed_time": "1:22:27", "remaining_time": "0:00:41"}
{"current_steps": 363, "total_steps": 363, "eval_loss": 0.55907142162323, "epoch": 2.9876543209876543, "percentage": 100.0, "elapsed_time": "1:24:44", "remaining_time": "0:00:00"}
{"current_steps": 363, "total_steps": 363, "epoch": 2.9876543209876543, "percentage": 100.0, "elapsed_time": "1:25:55", "remaining_time": "0:00:00"}