| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9999191919191919, | |
| "global_step": 6187, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7705, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1e-06, | |
| "loss": 2.9903, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 2.6103124618530273, | |
| "eval_runtime": 21.555, | |
| "eval_samples_per_second": 46.393, | |
| "eval_steps_per_second": 1.485, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1e-06, | |
| "loss": 2.7311, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 2.303687572479248, | |
| "eval_runtime": 21.5668, | |
| "eval_samples_per_second": 46.368, | |
| "eval_steps_per_second": 1.484, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1e-06, | |
| "loss": 2.3175, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 2.1831250190734863, | |
| "eval_runtime": 21.6264, | |
| "eval_samples_per_second": 46.24, | |
| "eval_steps_per_second": 1.48, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-06, | |
| "loss": 2.2645, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.130187511444092, | |
| "eval_runtime": 21.5721, | |
| "eval_samples_per_second": 46.356, | |
| "eval_steps_per_second": 1.483, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-06, | |
| "loss": 2.1012, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.102562427520752, | |
| "eval_runtime": 21.5886, | |
| "eval_samples_per_second": 46.321, | |
| "eval_steps_per_second": 1.482, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-06, | |
| "loss": 2.2054, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.0776875019073486, | |
| "eval_runtime": 21.5931, | |
| "eval_samples_per_second": 46.311, | |
| "eval_steps_per_second": 1.482, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-06, | |
| "loss": 2.1123, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.058500051498413, | |
| "eval_runtime": 21.5702, | |
| "eval_samples_per_second": 46.36, | |
| "eval_steps_per_second": 1.484, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0723, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.0454375743865967, | |
| "eval_runtime": 21.601, | |
| "eval_samples_per_second": 46.294, | |
| "eval_steps_per_second": 1.481, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0369, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.036062479019165, | |
| "eval_runtime": 21.5801, | |
| "eval_samples_per_second": 46.339, | |
| "eval_steps_per_second": 1.483, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-06, | |
| "loss": 2.1556, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.0283124446868896, | |
| "eval_runtime": 21.578, | |
| "eval_samples_per_second": 46.343, | |
| "eval_steps_per_second": 1.483, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0969, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.0223751068115234, | |
| "eval_runtime": 21.5462, | |
| "eval_samples_per_second": 46.412, | |
| "eval_steps_per_second": 1.485, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0542, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.017312526702881, | |
| "eval_runtime": 21.7681, | |
| "eval_samples_per_second": 45.939, | |
| "eval_steps_per_second": 1.47, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9574, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.012624979019165, | |
| "eval_runtime": 21.6595, | |
| "eval_samples_per_second": 46.169, | |
| "eval_steps_per_second": 1.477, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0246, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.009000062942505, | |
| "eval_runtime": 21.635, | |
| "eval_samples_per_second": 46.221, | |
| "eval_steps_per_second": 1.479, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0172, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.0059375762939453, | |
| "eval_runtime": 21.5668, | |
| "eval_samples_per_second": 46.368, | |
| "eval_steps_per_second": 1.484, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9788, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.002187490463257, | |
| "eval_runtime": 21.5772, | |
| "eval_samples_per_second": 46.345, | |
| "eval_steps_per_second": 1.483, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1e-06, | |
| "loss": 2.001, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.9981249570846558, | |
| "eval_runtime": 21.6059, | |
| "eval_samples_per_second": 46.284, | |
| "eval_steps_per_second": 1.481, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9815, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.995437502861023, | |
| "eval_runtime": 21.583, | |
| "eval_samples_per_second": 46.333, | |
| "eval_steps_per_second": 1.483, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0833, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.9923125505447388, | |
| "eval_runtime": 21.5969, | |
| "eval_samples_per_second": 46.303, | |
| "eval_steps_per_second": 1.482, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0181, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.9904375076293945, | |
| "eval_runtime": 21.5756, | |
| "eval_samples_per_second": 46.349, | |
| "eval_steps_per_second": 1.483, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0131, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.9896249771118164, | |
| "eval_runtime": 21.5918, | |
| "eval_samples_per_second": 46.314, | |
| "eval_steps_per_second": 1.482, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9979, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.9875625371932983, | |
| "eval_runtime": 21.565, | |
| "eval_samples_per_second": 46.372, | |
| "eval_steps_per_second": 1.484, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0325, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.9860625267028809, | |
| "eval_runtime": 21.5888, | |
| "eval_samples_per_second": 46.32, | |
| "eval_steps_per_second": 1.482, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1e-06, | |
| "loss": 2.105, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.984375, | |
| "eval_runtime": 21.5906, | |
| "eval_samples_per_second": 46.316, | |
| "eval_steps_per_second": 1.482, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0709, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.9822499752044678, | |
| "eval_runtime": 21.6129, | |
| "eval_samples_per_second": 46.269, | |
| "eval_steps_per_second": 1.481, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0523, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.9815000295639038, | |
| "eval_runtime": 21.5779, | |
| "eval_samples_per_second": 46.344, | |
| "eval_steps_per_second": 1.483, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9995, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.9774999618530273, | |
| "eval_runtime": 21.5937, | |
| "eval_samples_per_second": 46.31, | |
| "eval_steps_per_second": 1.482, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8896, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.9772499799728394, | |
| "eval_runtime": 21.6433, | |
| "eval_samples_per_second": 46.204, | |
| "eval_steps_per_second": 1.479, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-06, | |
| "loss": 2.088, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.9761874675750732, | |
| "eval_runtime": 21.6127, | |
| "eval_samples_per_second": 46.269, | |
| "eval_steps_per_second": 1.481, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9491, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.9765000343322754, | |
| "eval_runtime": 21.5915, | |
| "eval_samples_per_second": 46.315, | |
| "eval_steps_per_second": 1.482, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0771, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.973562479019165, | |
| "eval_runtime": 21.6552, | |
| "eval_samples_per_second": 46.178, | |
| "eval_steps_per_second": 1.478, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0921, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.9715625047683716, | |
| "eval_runtime": 21.6072, | |
| "eval_samples_per_second": 46.281, | |
| "eval_steps_per_second": 1.481, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-06, | |
| "loss": 1.967, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.9698749780654907, | |
| "eval_runtime": 21.5859, | |
| "eval_samples_per_second": 46.326, | |
| "eval_steps_per_second": 1.482, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9998, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.9673750400543213, | |
| "eval_runtime": 21.5761, | |
| "eval_samples_per_second": 46.348, | |
| "eval_steps_per_second": 1.483, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0577, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.9666249752044678, | |
| "eval_runtime": 21.5981, | |
| "eval_samples_per_second": 46.3, | |
| "eval_steps_per_second": 1.482, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0249, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.965000033378601, | |
| "eval_runtime": 21.5716, | |
| "eval_samples_per_second": 46.357, | |
| "eval_steps_per_second": 1.483, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9365, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.9635624885559082, | |
| "eval_runtime": 21.5755, | |
| "eval_samples_per_second": 46.349, | |
| "eval_steps_per_second": 1.483, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0111, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.9628750085830688, | |
| "eval_runtime": 21.5574, | |
| "eval_samples_per_second": 46.388, | |
| "eval_steps_per_second": 1.484, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0041, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.9611250162124634, | |
| "eval_runtime": 21.6082, | |
| "eval_samples_per_second": 46.279, | |
| "eval_steps_per_second": 1.481, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0181, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.9593125581741333, | |
| "eval_runtime": 21.7618, | |
| "eval_samples_per_second": 45.952, | |
| "eval_steps_per_second": 1.47, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0277, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.9578125476837158, | |
| "eval_runtime": 21.5803, | |
| "eval_samples_per_second": 46.339, | |
| "eval_steps_per_second": 1.483, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-06, | |
| "loss": 1.973, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.957124948501587, | |
| "eval_runtime": 21.6031, | |
| "eval_samples_per_second": 46.29, | |
| "eval_steps_per_second": 1.481, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9841, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.9556875228881836, | |
| "eval_runtime": 21.74, | |
| "eval_samples_per_second": 45.998, | |
| "eval_steps_per_second": 1.472, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0041, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.9543124437332153, | |
| "eval_runtime": 21.5907, | |
| "eval_samples_per_second": 46.316, | |
| "eval_steps_per_second": 1.482, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8736, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.9544999599456787, | |
| "eval_runtime": 21.6106, | |
| "eval_samples_per_second": 46.274, | |
| "eval_steps_per_second": 1.481, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0252, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.954687476158142, | |
| "eval_runtime": 21.6061, | |
| "eval_samples_per_second": 46.283, | |
| "eval_steps_per_second": 1.481, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0165, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.9551249742507935, | |
| "eval_runtime": 21.6096, | |
| "eval_samples_per_second": 46.276, | |
| "eval_steps_per_second": 1.481, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0753, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.9535000324249268, | |
| "eval_runtime": 21.5781, | |
| "eval_samples_per_second": 46.343, | |
| "eval_steps_per_second": 1.483, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0401, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.9523124694824219, | |
| "eval_runtime": 21.5923, | |
| "eval_samples_per_second": 46.313, | |
| "eval_steps_per_second": 1.482, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9997, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.9514374732971191, | |
| "eval_runtime": 21.5788, | |
| "eval_samples_per_second": 46.342, | |
| "eval_steps_per_second": 1.483, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9983, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.9509999752044678, | |
| "eval_runtime": 21.5723, | |
| "eval_samples_per_second": 46.356, | |
| "eval_steps_per_second": 1.483, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0708, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.9498125314712524, | |
| "eval_runtime": 21.6676, | |
| "eval_samples_per_second": 46.152, | |
| "eval_steps_per_second": 1.477, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0041, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.949375033378601, | |
| "eval_runtime": 21.5738, | |
| "eval_samples_per_second": 46.353, | |
| "eval_steps_per_second": 1.483, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9361, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.9479999542236328, | |
| "eval_runtime": 21.6244, | |
| "eval_samples_per_second": 46.244, | |
| "eval_steps_per_second": 1.48, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1e-06, | |
| "loss": 1.996, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.9463125467300415, | |
| "eval_runtime": 21.5711, | |
| "eval_samples_per_second": 46.358, | |
| "eval_steps_per_second": 1.483, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9434, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.946062445640564, | |
| "eval_runtime": 21.6589, | |
| "eval_samples_per_second": 46.17, | |
| "eval_steps_per_second": 1.477, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9713, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.9454375505447388, | |
| "eval_runtime": 21.5799, | |
| "eval_samples_per_second": 46.339, | |
| "eval_steps_per_second": 1.483, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0267, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.9446874856948853, | |
| "eval_runtime": 21.6125, | |
| "eval_samples_per_second": 46.269, | |
| "eval_steps_per_second": 1.481, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9422, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.9424999952316284, | |
| "eval_runtime": 21.5951, | |
| "eval_samples_per_second": 46.307, | |
| "eval_steps_per_second": 1.482, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9464, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.9424375295639038, | |
| "eval_runtime": 21.5707, | |
| "eval_samples_per_second": 46.359, | |
| "eval_steps_per_second": 1.483, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-06, | |
| "loss": 2.028, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.9411250352859497, | |
| "eval_runtime": 21.5905, | |
| "eval_samples_per_second": 46.317, | |
| "eval_steps_per_second": 1.482, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0127, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.941562533378601, | |
| "eval_runtime": 21.5988, | |
| "eval_samples_per_second": 46.299, | |
| "eval_steps_per_second": 1.482, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9577, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.9395625591278076, | |
| "eval_runtime": 21.5636, | |
| "eval_samples_per_second": 46.375, | |
| "eval_steps_per_second": 1.484, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9023, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.9394375085830688, | |
| "eval_runtime": 21.5844, | |
| "eval_samples_per_second": 46.33, | |
| "eval_steps_per_second": 1.483, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0571, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.9391249418258667, | |
| "eval_runtime": 21.6088, | |
| "eval_samples_per_second": 46.277, | |
| "eval_steps_per_second": 1.481, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1e-06, | |
| "loss": 2.023, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.9401874542236328, | |
| "eval_runtime": 21.5901, | |
| "eval_samples_per_second": 46.318, | |
| "eval_steps_per_second": 1.482, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9559, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.939062476158142, | |
| "eval_runtime": 21.5898, | |
| "eval_samples_per_second": 46.318, | |
| "eval_steps_per_second": 1.482, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9522, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.9381250143051147, | |
| "eval_runtime": 21.6135, | |
| "eval_samples_per_second": 46.267, | |
| "eval_steps_per_second": 1.481, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9785, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.9374375343322754, | |
| "eval_runtime": 21.5705, | |
| "eval_samples_per_second": 46.36, | |
| "eval_steps_per_second": 1.484, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0394, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.9369374513626099, | |
| "eval_runtime": 21.5881, | |
| "eval_samples_per_second": 46.322, | |
| "eval_steps_per_second": 1.482, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0392, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.9351249933242798, | |
| "eval_runtime": 21.5738, | |
| "eval_samples_per_second": 46.353, | |
| "eval_steps_per_second": 1.483, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9352, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.9348125457763672, | |
| "eval_runtime": 21.5633, | |
| "eval_samples_per_second": 46.375, | |
| "eval_steps_per_second": 1.484, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9418, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.9336249828338623, | |
| "eval_runtime": 21.66, | |
| "eval_samples_per_second": 46.168, | |
| "eval_steps_per_second": 1.477, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0288, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.9332499504089355, | |
| "eval_runtime": 21.5801, | |
| "eval_samples_per_second": 46.339, | |
| "eval_steps_per_second": 1.483, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0209, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.9328750371932983, | |
| "eval_runtime": 21.714, | |
| "eval_samples_per_second": 46.053, | |
| "eval_steps_per_second": 1.474, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0951, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.9322500228881836, | |
| "eval_runtime": 21.5724, | |
| "eval_samples_per_second": 46.356, | |
| "eval_steps_per_second": 1.483, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9686, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.9313124418258667, | |
| "eval_runtime": 21.5878, | |
| "eval_samples_per_second": 46.323, | |
| "eval_steps_per_second": 1.482, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1e-06, | |
| "loss": 2.008, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.9303125143051147, | |
| "eval_runtime": 21.5821, | |
| "eval_samples_per_second": 46.335, | |
| "eval_steps_per_second": 1.483, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1e-06, | |
| "loss": 1.998, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.9296875, | |
| "eval_runtime": 21.643, | |
| "eval_samples_per_second": 46.204, | |
| "eval_steps_per_second": 1.479, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9939, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.928125023841858, | |
| "eval_runtime": 21.6015, | |
| "eval_samples_per_second": 46.293, | |
| "eval_steps_per_second": 1.481, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0758, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.9277499914169312, | |
| "eval_runtime": 21.6035, | |
| "eval_samples_per_second": 46.289, | |
| "eval_steps_per_second": 1.481, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0049, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.928375005722046, | |
| "eval_runtime": 21.774, | |
| "eval_samples_per_second": 45.926, | |
| "eval_steps_per_second": 1.47, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9863, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.9279375076293945, | |
| "eval_runtime": 21.6241, | |
| "eval_samples_per_second": 46.245, | |
| "eval_steps_per_second": 1.48, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9947, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.9278124570846558, | |
| "eval_runtime": 21.5978, | |
| "eval_samples_per_second": 46.301, | |
| "eval_steps_per_second": 1.482, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9341, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.9268125295639038, | |
| "eval_runtime": 21.5635, | |
| "eval_samples_per_second": 46.375, | |
| "eval_steps_per_second": 1.484, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9241, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.9255625009536743, | |
| "eval_runtime": 21.5833, | |
| "eval_samples_per_second": 46.332, | |
| "eval_steps_per_second": 1.483, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9837, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.925374984741211, | |
| "eval_runtime": 21.745, | |
| "eval_samples_per_second": 45.988, | |
| "eval_steps_per_second": 1.472, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1e-06, | |
| "loss": 1.973, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.9242500066757202, | |
| "eval_runtime": 21.5975, | |
| "eval_samples_per_second": 46.302, | |
| "eval_steps_per_second": 1.482, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9233, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.9240624904632568, | |
| "eval_runtime": 21.6099, | |
| "eval_samples_per_second": 46.275, | |
| "eval_steps_per_second": 1.481, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9619, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.92368745803833, | |
| "eval_runtime": 21.5993, | |
| "eval_samples_per_second": 46.298, | |
| "eval_steps_per_second": 1.482, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9975, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.9224375486373901, | |
| "eval_runtime": 21.5918, | |
| "eval_samples_per_second": 46.314, | |
| "eval_steps_per_second": 1.482, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9807, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.9214999675750732, | |
| "eval_runtime": 21.5688, | |
| "eval_samples_per_second": 46.363, | |
| "eval_steps_per_second": 1.484, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8974, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.924375057220459, | |
| "eval_runtime": 21.5825, | |
| "eval_samples_per_second": 46.334, | |
| "eval_steps_per_second": 1.483, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0246, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.9245624542236328, | |
| "eval_runtime": 21.6472, | |
| "eval_samples_per_second": 46.195, | |
| "eval_steps_per_second": 1.478, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9318, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.9228750467300415, | |
| "eval_runtime": 21.6026, | |
| "eval_samples_per_second": 46.291, | |
| "eval_steps_per_second": 1.481, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9721, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.9230624437332153, | |
| "eval_runtime": 21.5765, | |
| "eval_samples_per_second": 46.347, | |
| "eval_steps_per_second": 1.483, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9978, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.9227499961853027, | |
| "eval_runtime": 21.6602, | |
| "eval_samples_per_second": 46.168, | |
| "eval_steps_per_second": 1.477, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8698, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.9231250286102295, | |
| "eval_runtime": 21.684, | |
| "eval_samples_per_second": 46.117, | |
| "eval_steps_per_second": 1.476, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9715, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.9209375381469727, | |
| "eval_runtime": 21.5945, | |
| "eval_samples_per_second": 46.308, | |
| "eval_steps_per_second": 1.482, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9874, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.9190624952316284, | |
| "eval_runtime": 21.5978, | |
| "eval_samples_per_second": 46.301, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0096, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.919374942779541, | |
| "eval_runtime": 21.5737, | |
| "eval_samples_per_second": 46.353, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9226, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.919124960899353, | |
| "eval_runtime": 21.5786, | |
| "eval_samples_per_second": 46.342, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9934, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.919124960899353, | |
| "eval_runtime": 21.5567, | |
| "eval_samples_per_second": 46.389, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9778, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.9184374809265137, | |
| "eval_runtime": 21.5886, | |
| "eval_samples_per_second": 46.321, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9206, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.9199374914169312, | |
| "eval_runtime": 21.684, | |
| "eval_samples_per_second": 46.117, | |
| "eval_steps_per_second": 1.476, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8988, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.919374942779541, | |
| "eval_runtime": 21.5854, | |
| "eval_samples_per_second": 46.328, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0907, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.9197499752044678, | |
| "eval_runtime": 21.5829, | |
| "eval_samples_per_second": 46.333, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0045, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.9206875562667847, | |
| "eval_runtime": 21.5983, | |
| "eval_samples_per_second": 46.3, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1e-06, | |
| "loss": 1.938, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.9186874628067017, | |
| "eval_runtime": 21.6418, | |
| "eval_samples_per_second": 46.207, | |
| "eval_steps_per_second": 1.479, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9877, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.918624997138977, | |
| "eval_runtime": 21.5764, | |
| "eval_samples_per_second": 46.347, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1e-06, | |
| "loss": 1.884, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.9181874990463257, | |
| "eval_runtime": 21.6142, | |
| "eval_samples_per_second": 46.266, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0029, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.9176249504089355, | |
| "eval_runtime": 21.6204, | |
| "eval_samples_per_second": 46.253, | |
| "eval_steps_per_second": 1.48, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9871, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.9174375534057617, | |
| "eval_runtime": 21.5968, | |
| "eval_samples_per_second": 46.303, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9415, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.917562484741211, | |
| "eval_runtime": 21.5748, | |
| "eval_samples_per_second": 46.35, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0646, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.9170000553131104, | |
| "eval_runtime": 21.6665, | |
| "eval_samples_per_second": 46.154, | |
| "eval_steps_per_second": 1.477, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9221, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.9166874885559082, | |
| "eval_runtime": 21.6037, | |
| "eval_samples_per_second": 46.288, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8499, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.9155625104904175, | |
| "eval_runtime": 21.5624, | |
| "eval_samples_per_second": 46.377, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0678, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.9151250123977661, | |
| "eval_runtime": 21.5683, | |
| "eval_samples_per_second": 46.364, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9067, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.9144999980926514, | |
| "eval_runtime": 21.5675, | |
| "eval_samples_per_second": 46.366, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0528, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.914562463760376, | |
| "eval_runtime": 21.5545, | |
| "eval_samples_per_second": 46.394, | |
| "eval_steps_per_second": 1.485, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0069, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.9144375324249268, | |
| "eval_runtime": 21.5614, | |
| "eval_samples_per_second": 46.379, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0498, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.9149999618530273, | |
| "eval_runtime": 21.5646, | |
| "eval_samples_per_second": 46.372, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0296, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.9141875505447388, | |
| "eval_runtime": 21.5633, | |
| "eval_samples_per_second": 46.375, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9634, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.9131875038146973, | |
| "eval_runtime": 21.5505, | |
| "eval_samples_per_second": 46.403, | |
| "eval_steps_per_second": 1.485, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0171, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.913562536239624, | |
| "eval_runtime": 21.5632, | |
| "eval_samples_per_second": 46.375, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9484, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.9150625467300415, | |
| "eval_runtime": 21.5801, | |
| "eval_samples_per_second": 46.339, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0042, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.9144375324249268, | |
| "eval_runtime": 21.5746, | |
| "eval_samples_per_second": 46.351, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9661, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.9140000343322754, | |
| "eval_runtime": 21.6459, | |
| "eval_samples_per_second": 46.198, | |
| "eval_steps_per_second": 1.478, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8565, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.9128750562667847, | |
| "eval_runtime": 21.57, | |
| "eval_samples_per_second": 46.361, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1e-06, | |
| "loss": 1.972, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.9139374494552612, | |
| "eval_runtime": 21.5805, | |
| "eval_samples_per_second": 46.338, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8855, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.9141249656677246, | |
| "eval_runtime": 21.6158, | |
| "eval_samples_per_second": 46.262, | |
| "eval_steps_per_second": 1.48, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1e-06, | |
| "loss": 1.913, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.9146875143051147, | |
| "eval_runtime": 21.5474, | |
| "eval_samples_per_second": 46.409, | |
| "eval_steps_per_second": 1.485, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0252, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.9136874675750732, | |
| "eval_runtime": 21.555, | |
| "eval_samples_per_second": 46.393, | |
| "eval_steps_per_second": 1.485, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0193, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.9125624895095825, | |
| "eval_runtime": 21.5626, | |
| "eval_samples_per_second": 46.377, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8765, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.9117499589920044, | |
| "eval_runtime": 21.5826, | |
| "eval_samples_per_second": 46.334, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9179, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.9114999771118164, | |
| "eval_runtime": 21.5598, | |
| "eval_samples_per_second": 46.383, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9387, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.9118125438690186, | |
| "eval_runtime": 21.6259, | |
| "eval_samples_per_second": 46.241, | |
| "eval_steps_per_second": 1.48, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9386, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.9107500314712524, | |
| "eval_runtime": 21.5698, | |
| "eval_samples_per_second": 46.361, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9395, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.9112499952316284, | |
| "eval_runtime": 21.6242, | |
| "eval_samples_per_second": 46.245, | |
| "eval_steps_per_second": 1.48, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-06, | |
| "loss": 1.883, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.9111875295639038, | |
| "eval_runtime": 21.5742, | |
| "eval_samples_per_second": 46.352, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9956, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.9107500314712524, | |
| "eval_runtime": 21.5887, | |
| "eval_samples_per_second": 46.321, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9536, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.9124375581741333, | |
| "eval_runtime": 21.5963, | |
| "eval_samples_per_second": 46.304, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9391, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.9121249914169312, | |
| "eval_runtime": 21.5911, | |
| "eval_samples_per_second": 46.315, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8853, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.9098750352859497, | |
| "eval_runtime": 21.5981, | |
| "eval_samples_per_second": 46.3, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8877, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.9091875553131104, | |
| "eval_runtime": 21.5725, | |
| "eval_samples_per_second": 46.355, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9746, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.909000039100647, | |
| "eval_runtime": 21.6032, | |
| "eval_samples_per_second": 46.29, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0241, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.9088125228881836, | |
| "eval_runtime": 21.6136, | |
| "eval_samples_per_second": 46.267, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9257, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.9088749885559082, | |
| "eval_runtime": 21.572, | |
| "eval_samples_per_second": 46.356, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0036, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.9089374542236328, | |
| "eval_runtime": 21.5831, | |
| "eval_samples_per_second": 46.333, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9253, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.909500002861023, | |
| "eval_runtime": 21.6823, | |
| "eval_samples_per_second": 46.121, | |
| "eval_steps_per_second": 1.476, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0153, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.9086250066757202, | |
| "eval_runtime": 21.5458, | |
| "eval_samples_per_second": 46.413, | |
| "eval_steps_per_second": 1.485, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0366, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.9090625047683716, | |
| "eval_runtime": 21.6111, | |
| "eval_samples_per_second": 46.273, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9283, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.9079999923706055, | |
| "eval_runtime": 21.6291, | |
| "eval_samples_per_second": 46.234, | |
| "eval_steps_per_second": 1.479, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-06, | |
| "loss": 2.023, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.9077500104904175, | |
| "eval_runtime": 21.6052, | |
| "eval_samples_per_second": 46.285, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0456, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.9064375162124634, | |
| "eval_runtime": 21.5712, | |
| "eval_samples_per_second": 46.358, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0027, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.9082499742507935, | |
| "eval_runtime": 21.5748, | |
| "eval_samples_per_second": 46.35, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9597, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.909000039100647, | |
| "eval_runtime": 21.6055, | |
| "eval_samples_per_second": 46.285, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9969, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.9086250066757202, | |
| "eval_runtime": 21.5805, | |
| "eval_samples_per_second": 46.338, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9597, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.907562494277954, | |
| "eval_runtime": 21.6041, | |
| "eval_samples_per_second": 46.288, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9571, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.907812476158142, | |
| "eval_runtime": 21.593, | |
| "eval_samples_per_second": 46.311, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0231, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.9071249961853027, | |
| "eval_runtime": 21.588, | |
| "eval_samples_per_second": 46.322, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9554, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.9047499895095825, | |
| "eval_runtime": 21.5963, | |
| "eval_samples_per_second": 46.304, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9042, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.9048750400543213, | |
| "eval_runtime": 21.601, | |
| "eval_samples_per_second": 46.294, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8837, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.9047499895095825, | |
| "eval_runtime": 21.5744, | |
| "eval_samples_per_second": 46.351, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1e-06, | |
| "loss": 1.931, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.9033750295639038, | |
| "eval_runtime": 21.5833, | |
| "eval_samples_per_second": 46.332, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1e-06, | |
| "loss": 1.891, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.9033124446868896, | |
| "eval_runtime": 21.5683, | |
| "eval_samples_per_second": 46.364, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9157, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.9033750295639038, | |
| "eval_runtime": 21.6387, | |
| "eval_samples_per_second": 46.213, | |
| "eval_steps_per_second": 1.479, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9626, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.9030624628067017, | |
| "eval_runtime": 21.6073, | |
| "eval_samples_per_second": 46.281, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0237, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.90443754196167, | |
| "eval_runtime": 21.5689, | |
| "eval_samples_per_second": 46.363, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9002, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.9045624732971191, | |
| "eval_runtime": 21.5902, | |
| "eval_samples_per_second": 46.317, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9676, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.9063124656677246, | |
| "eval_runtime": 21.6165, | |
| "eval_samples_per_second": 46.261, | |
| "eval_steps_per_second": 1.48, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0352, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.9059375524520874, | |
| "eval_runtime": 21.575, | |
| "eval_samples_per_second": 46.35, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-06, | |
| "loss": 1.996, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.9054374694824219, | |
| "eval_runtime": 21.5922, | |
| "eval_samples_per_second": 46.313, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9681, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.9049999713897705, | |
| "eval_runtime": 21.5631, | |
| "eval_samples_per_second": 46.376, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9749, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.90443754196167, | |
| "eval_runtime": 21.59, | |
| "eval_samples_per_second": 46.318, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9298, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.9034374952316284, | |
| "eval_runtime": 21.6076, | |
| "eval_samples_per_second": 46.28, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9732, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.9023749828338623, | |
| "eval_runtime": 21.5985, | |
| "eval_samples_per_second": 46.3, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9114, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.9015624523162842, | |
| "eval_runtime": 21.5773, | |
| "eval_samples_per_second": 46.345, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9449, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.9018125534057617, | |
| "eval_runtime": 21.5622, | |
| "eval_samples_per_second": 46.377, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9619, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.9030624628067017, | |
| "eval_runtime": 21.6519, | |
| "eval_samples_per_second": 46.185, | |
| "eval_steps_per_second": 1.478, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9091, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.9013124704360962, | |
| "eval_runtime": 21.5954, | |
| "eval_samples_per_second": 46.306, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9262, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.9016250371932983, | |
| "eval_runtime": 21.5732, | |
| "eval_samples_per_second": 46.354, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0112, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.902187466621399, | |
| "eval_runtime": 21.5764, | |
| "eval_samples_per_second": 46.347, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9816, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.9011249542236328, | |
| "eval_runtime": 21.5714, | |
| "eval_samples_per_second": 46.358, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-06, | |
| "loss": 1.861, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.8998124599456787, | |
| "eval_runtime": 21.567, | |
| "eval_samples_per_second": 46.367, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9451, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.8995000123977661, | |
| "eval_runtime": 21.588, | |
| "eval_samples_per_second": 46.322, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0126, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.9004374742507935, | |
| "eval_runtime": 21.5695, | |
| "eval_samples_per_second": 46.362, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8937, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.9018750190734863, | |
| "eval_runtime": 21.5846, | |
| "eval_samples_per_second": 46.329, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9457, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.8994375467300415, | |
| "eval_runtime": 21.5822, | |
| "eval_samples_per_second": 46.335, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1e-06, | |
| "loss": 2.062, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.899749994277954, | |
| "eval_runtime": 21.5866, | |
| "eval_samples_per_second": 46.325, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9497, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.9012500047683716, | |
| "eval_runtime": 21.6617, | |
| "eval_samples_per_second": 46.164, | |
| "eval_steps_per_second": 1.477, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0455, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.9005000591278076, | |
| "eval_runtime": 21.6313, | |
| "eval_samples_per_second": 46.229, | |
| "eval_steps_per_second": 1.479, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9166, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.8993124961853027, | |
| "eval_runtime": 21.6028, | |
| "eval_samples_per_second": 46.29, | |
| "eval_steps_per_second": 1.481, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9117, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.899749994277954, | |
| "eval_runtime": 21.5853, | |
| "eval_samples_per_second": 46.328, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0035, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.8984375, | |
| "eval_runtime": 21.5723, | |
| "eval_samples_per_second": 46.356, | |
| "eval_steps_per_second": 1.483, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9852, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.8980000019073486, | |
| "eval_runtime": 21.6353, | |
| "eval_samples_per_second": 46.221, | |
| "eval_steps_per_second": 1.479, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1e-06, | |
| "loss": 2.034, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.8988125324249268, | |
| "eval_runtime": 21.5587, | |
| "eval_samples_per_second": 46.385, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8832, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.8982499837875366, | |
| "eval_runtime": 21.5628, | |
| "eval_samples_per_second": 46.376, | |
| "eval_steps_per_second": 1.484, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1e-06, | |
| "loss": 1.956, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.8980624675750732, | |
| "eval_runtime": 21.5868, | |
| "eval_samples_per_second": 46.325, | |
| "eval_steps_per_second": 1.482, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8746, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.8969374895095825, | |
| "eval_runtime": 21.5821, | |
| "eval_samples_per_second": 46.335, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8892, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.8958749771118164, | |
| "eval_runtime": 21.6083, | |
| "eval_samples_per_second": 46.278, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0095, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.8948750495910645, | |
| "eval_runtime": 21.6201, | |
| "eval_samples_per_second": 46.253, | |
| "eval_steps_per_second": 1.48, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9422, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.897125005722046, | |
| "eval_runtime": 21.5595, | |
| "eval_samples_per_second": 46.383, | |
| "eval_steps_per_second": 1.484, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8938, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.8969999551773071, | |
| "eval_runtime": 21.5569, | |
| "eval_samples_per_second": 46.389, | |
| "eval_steps_per_second": 1.484, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-06, | |
| "loss": 1.874, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.8964999914169312, | |
| "eval_runtime": 21.5507, | |
| "eval_samples_per_second": 46.402, | |
| "eval_steps_per_second": 1.485, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8995, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.8951250314712524, | |
| "eval_runtime": 21.6188, | |
| "eval_samples_per_second": 46.256, | |
| "eval_steps_per_second": 1.48, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8192, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.895937442779541, | |
| "eval_runtime": 21.5982, | |
| "eval_samples_per_second": 46.3, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9252, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.8956249952316284, | |
| "eval_runtime": 21.6523, | |
| "eval_samples_per_second": 46.185, | |
| "eval_steps_per_second": 1.478, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8958, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.896875023841858, | |
| "eval_runtime": 21.6098, | |
| "eval_samples_per_second": 46.275, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9043, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.8940000534057617, | |
| "eval_runtime": 21.5718, | |
| "eval_samples_per_second": 46.357, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9596, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.8939374685287476, | |
| "eval_runtime": 21.6391, | |
| "eval_samples_per_second": 46.213, | |
| "eval_steps_per_second": 1.479, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9218, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.8934375047683716, | |
| "eval_runtime": 21.5925, | |
| "eval_samples_per_second": 46.312, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9027, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.8935625553131104, | |
| "eval_runtime": 21.5668, | |
| "eval_samples_per_second": 46.368, | |
| "eval_steps_per_second": 1.484, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0138, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.8940000534057617, | |
| "eval_runtime": 21.5794, | |
| "eval_samples_per_second": 46.341, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9878, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.894124984741211, | |
| "eval_runtime": 21.7429, | |
| "eval_samples_per_second": 45.992, | |
| "eval_steps_per_second": 1.472, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0328, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.8918750286102295, | |
| "eval_runtime": 21.5689, | |
| "eval_samples_per_second": 46.363, | |
| "eval_steps_per_second": 1.484, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-06, | |
| "loss": 1.894, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.8916250467300415, | |
| "eval_runtime": 21.6262, | |
| "eval_samples_per_second": 46.24, | |
| "eval_steps_per_second": 1.48, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-06, | |
| "loss": 1.952, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.8934999704360962, | |
| "eval_runtime": 21.5943, | |
| "eval_samples_per_second": 46.309, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9383, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.894124984741211, | |
| "eval_runtime": 21.5954, | |
| "eval_samples_per_second": 46.306, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9761, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.8935625553131104, | |
| "eval_runtime": 21.5892, | |
| "eval_samples_per_second": 46.32, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8925, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.8925625085830688, | |
| "eval_runtime": 21.6011, | |
| "eval_samples_per_second": 46.294, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8558, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.8917499780654907, | |
| "eval_runtime": 21.652, | |
| "eval_samples_per_second": 46.185, | |
| "eval_steps_per_second": 1.478, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9386, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.8930624723434448, | |
| "eval_runtime": 21.608, | |
| "eval_samples_per_second": 46.279, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9294, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.8916875123977661, | |
| "eval_runtime": 21.5916, | |
| "eval_samples_per_second": 46.314, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1e-06, | |
| "loss": 1.92, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.8911875486373901, | |
| "eval_runtime": 21.5961, | |
| "eval_samples_per_second": 46.305, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9115, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.8904999494552612, | |
| "eval_runtime": 21.5851, | |
| "eval_samples_per_second": 46.328, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1e-06, | |
| "loss": 1.7885, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.8905625343322754, | |
| "eval_runtime": 21.5921, | |
| "eval_samples_per_second": 46.313, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9907, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.890125036239624, | |
| "eval_runtime": 21.5976, | |
| "eval_samples_per_second": 46.301, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8993, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.8910000324249268, | |
| "eval_runtime": 21.6337, | |
| "eval_samples_per_second": 46.224, | |
| "eval_steps_per_second": 1.479, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9179, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.8908125162124634, | |
| "eval_runtime": 21.5991, | |
| "eval_samples_per_second": 46.298, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8432, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.891124963760376, | |
| "eval_runtime": 21.5977, | |
| "eval_samples_per_second": 46.301, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9284, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.8915624618530273, | |
| "eval_runtime": 21.5848, | |
| "eval_samples_per_second": 46.329, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9587, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.8913124799728394, | |
| "eval_runtime": 21.587, | |
| "eval_samples_per_second": 46.324, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9536, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.8917499780654907, | |
| "eval_runtime": 21.5919, | |
| "eval_samples_per_second": 46.314, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8101, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.8914999961853027, | |
| "eval_runtime": 21.5804, | |
| "eval_samples_per_second": 46.338, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9749, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.8907500505447388, | |
| "eval_runtime": 21.59, | |
| "eval_samples_per_second": 46.318, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9275, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.8913124799728394, | |
| "eval_runtime": 21.6004, | |
| "eval_samples_per_second": 46.295, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9226, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.8911875486373901, | |
| "eval_runtime": 21.5995, | |
| "eval_samples_per_second": 46.297, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9028, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.8923125267028809, | |
| "eval_runtime": 21.656, | |
| "eval_samples_per_second": 46.177, | |
| "eval_steps_per_second": 1.478, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9238, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.8915624618530273, | |
| "eval_runtime": 21.574, | |
| "eval_samples_per_second": 46.352, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9168, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.8916875123977661, | |
| "eval_runtime": 21.5773, | |
| "eval_samples_per_second": 46.345, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9032, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.8912500143051147, | |
| "eval_runtime": 21.5933, | |
| "eval_samples_per_second": 46.311, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9834, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.890625, | |
| "eval_runtime": 21.6052, | |
| "eval_samples_per_second": 46.285, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9134, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.8895000219345093, | |
| "eval_runtime": 21.586, | |
| "eval_samples_per_second": 46.326, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9176, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.8895000219345093, | |
| "eval_runtime": 21.7961, | |
| "eval_samples_per_second": 45.88, | |
| "eval_steps_per_second": 1.468, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-06, | |
| "loss": 1.972, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.8908125162124634, | |
| "eval_runtime": 21.7651, | |
| "eval_samples_per_second": 45.945, | |
| "eval_steps_per_second": 1.47, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9347, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.889312505722046, | |
| "eval_runtime": 21.6078, | |
| "eval_samples_per_second": 46.28, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8683, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.8899375200271606, | |
| "eval_runtime": 21.5933, | |
| "eval_samples_per_second": 46.311, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8978, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.8900624513626099, | |
| "eval_runtime": 21.7246, | |
| "eval_samples_per_second": 46.031, | |
| "eval_steps_per_second": 1.473, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9114, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.8910624980926514, | |
| "eval_runtime": 21.5984, | |
| "eval_samples_per_second": 46.3, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8513, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.8907500505447388, | |
| "eval_runtime": 21.5892, | |
| "eval_samples_per_second": 46.32, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9279, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.8891874551773071, | |
| "eval_runtime": 21.5992, | |
| "eval_samples_per_second": 46.298, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1e-06, | |
| "loss": 1.963, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.8878124952316284, | |
| "eval_runtime": 21.746, | |
| "eval_samples_per_second": 45.986, | |
| "eval_steps_per_second": 1.472, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9512, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.8887499570846558, | |
| "eval_runtime": 21.6357, | |
| "eval_samples_per_second": 46.22, | |
| "eval_steps_per_second": 1.479, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8867, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.8880624771118164, | |
| "eval_runtime": 21.5957, | |
| "eval_samples_per_second": 46.305, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9328, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.886812448501587, | |
| "eval_runtime": 21.6158, | |
| "eval_samples_per_second": 46.263, | |
| "eval_steps_per_second": 1.48, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8483, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.8883124589920044, | |
| "eval_runtime": 21.596, | |
| "eval_samples_per_second": 46.305, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9146, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.8877500295639038, | |
| "eval_runtime": 21.5948, | |
| "eval_samples_per_second": 46.307, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0254, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.8882499933242798, | |
| "eval_runtime": 21.5935, | |
| "eval_samples_per_second": 46.31, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8772, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.8884375095367432, | |
| "eval_runtime": 21.581, | |
| "eval_samples_per_second": 46.337, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9283, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.8867499828338623, | |
| "eval_runtime": 21.6018, | |
| "eval_samples_per_second": 46.292, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-06, | |
| "loss": 2.014, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.8861249685287476, | |
| "eval_runtime": 21.5908, | |
| "eval_samples_per_second": 46.316, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8434, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.8859374523162842, | |
| "eval_runtime": 21.6442, | |
| "eval_samples_per_second": 46.202, | |
| "eval_steps_per_second": 1.478, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9982, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.8853750228881836, | |
| "eval_runtime": 21.6247, | |
| "eval_samples_per_second": 46.243, | |
| "eval_steps_per_second": 1.48, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9145, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.885812520980835, | |
| "eval_runtime": 21.6265, | |
| "eval_samples_per_second": 46.24, | |
| "eval_steps_per_second": 1.48, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8797, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.8846875429153442, | |
| "eval_runtime": 21.5985, | |
| "eval_samples_per_second": 46.299, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9019, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.8836250305175781, | |
| "eval_runtime": 21.6199, | |
| "eval_samples_per_second": 46.254, | |
| "eval_steps_per_second": 1.48, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9676, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.8840625286102295, | |
| "eval_runtime": 21.6856, | |
| "eval_samples_per_second": 46.113, | |
| "eval_steps_per_second": 1.476, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0023, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.8842500448226929, | |
| "eval_runtime": 21.5877, | |
| "eval_samples_per_second": 46.323, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9213, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.885312557220459, | |
| "eval_runtime": 21.6471, | |
| "eval_samples_per_second": 46.196, | |
| "eval_steps_per_second": 1.478, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9546, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.8870625495910645, | |
| "eval_runtime": 21.6008, | |
| "eval_samples_per_second": 46.295, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9272, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.8875625133514404, | |
| "eval_runtime": 21.5928, | |
| "eval_samples_per_second": 46.312, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9035, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.8865000009536743, | |
| "eval_runtime": 21.6432, | |
| "eval_samples_per_second": 46.204, | |
| "eval_steps_per_second": 1.479, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8836, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.88462495803833, | |
| "eval_runtime": 21.5992, | |
| "eval_samples_per_second": 46.298, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9743, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.8844374418258667, | |
| "eval_runtime": 21.5787, | |
| "eval_samples_per_second": 46.342, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9226, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.8844374418258667, | |
| "eval_runtime": 21.5815, | |
| "eval_samples_per_second": 46.336, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9141, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.8848750591278076, | |
| "eval_runtime": 21.5897, | |
| "eval_samples_per_second": 46.318, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9228, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.8845624923706055, | |
| "eval_runtime": 21.5792, | |
| "eval_samples_per_second": 46.341, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0065, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.8842500448226929, | |
| "eval_runtime": 21.6043, | |
| "eval_samples_per_second": 46.287, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8786, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.884374976158142, | |
| "eval_runtime": 21.6133, | |
| "eval_samples_per_second": 46.268, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-06, | |
| "loss": 1.893, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.8838750123977661, | |
| "eval_runtime": 21.5693, | |
| "eval_samples_per_second": 46.362, | |
| "eval_steps_per_second": 1.484, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8662, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.8825000524520874, | |
| "eval_runtime": 21.5912, | |
| "eval_samples_per_second": 46.315, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9182, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.8834375143051147, | |
| "eval_runtime": 21.6098, | |
| "eval_samples_per_second": 46.275, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9631, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.8834375143051147, | |
| "eval_runtime": 21.7457, | |
| "eval_samples_per_second": 45.986, | |
| "eval_steps_per_second": 1.472, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1e-06, | |
| "loss": 1.7758, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.8830000162124634, | |
| "eval_runtime": 21.5915, | |
| "eval_samples_per_second": 46.315, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9728, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.885312557220459, | |
| "eval_runtime": 21.6235, | |
| "eval_samples_per_second": 46.246, | |
| "eval_steps_per_second": 1.48, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8779, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.885312557220459, | |
| "eval_runtime": 21.6072, | |
| "eval_samples_per_second": 46.281, | |
| "eval_steps_per_second": 1.481, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8991, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.8837499618530273, | |
| "eval_runtime": 21.5731, | |
| "eval_samples_per_second": 46.354, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9968, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.8833750486373901, | |
| "eval_runtime": 21.5715, | |
| "eval_samples_per_second": 46.357, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9012, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.8824374675750732, | |
| "eval_runtime": 21.5769, | |
| "eval_samples_per_second": 46.346, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8975, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.8840625286102295, | |
| "eval_runtime": 21.5778, | |
| "eval_samples_per_second": 46.344, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0213, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.8850624561309814, | |
| "eval_runtime": 21.7712, | |
| "eval_samples_per_second": 45.932, | |
| "eval_steps_per_second": 1.47, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9718, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.883562445640564, | |
| "eval_runtime": 21.5678, | |
| "eval_samples_per_second": 46.365, | |
| "eval_steps_per_second": 1.484, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9855, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.8822499513626099, | |
| "eval_runtime": 21.5723, | |
| "eval_samples_per_second": 46.356, | |
| "eval_steps_per_second": 1.483, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1e-06, | |
| "loss": 1.952, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.8823750019073486, | |
| "eval_runtime": 21.5631, | |
| "eval_samples_per_second": 46.376, | |
| "eval_steps_per_second": 1.484, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8926, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.8806250095367432, | |
| "eval_runtime": 21.624, | |
| "eval_samples_per_second": 46.245, | |
| "eval_steps_per_second": 1.48, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9346, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.8816250562667847, | |
| "eval_runtime": 21.5878, | |
| "eval_samples_per_second": 46.322, | |
| "eval_steps_per_second": 1.482, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8823, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.881250023841858, | |
| "eval_runtime": 21.5569, | |
| "eval_samples_per_second": 46.389, | |
| "eval_steps_per_second": 1.484, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9383, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.8806250095367432, | |
| "eval_runtime": 21.6839, | |
| "eval_samples_per_second": 46.117, | |
| "eval_steps_per_second": 1.476, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1e-06, | |
| "loss": 1.7947, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.8808749914169312, | |
| "eval_runtime": 21.5728, | |
| "eval_samples_per_second": 46.355, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9227, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.882312536239624, | |
| "eval_runtime": 21.5671, | |
| "eval_samples_per_second": 46.367, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8955, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.8823750019073486, | |
| "eval_runtime": 21.5831, | |
| "eval_samples_per_second": 46.333, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9989, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.881250023841858, | |
| "eval_runtime": 21.5628, | |
| "eval_samples_per_second": 46.376, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9677, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.8819375038146973, | |
| "eval_runtime": 21.5581, | |
| "eval_samples_per_second": 46.386, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8583, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.8811875581741333, | |
| "eval_runtime": 21.5968, | |
| "eval_samples_per_second": 46.303, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9972, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.8818124532699585, | |
| "eval_runtime": 21.6261, | |
| "eval_samples_per_second": 46.24, | |
| "eval_steps_per_second": 1.48, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8436, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.8809374570846558, | |
| "eval_runtime": 21.6385, | |
| "eval_samples_per_second": 46.214, | |
| "eval_steps_per_second": 1.479, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9464, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.8806250095367432, | |
| "eval_runtime": 21.5985, | |
| "eval_samples_per_second": 46.299, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9133, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.8808125257492065, | |
| "eval_runtime": 21.6055, | |
| "eval_samples_per_second": 46.284, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9932, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.8813749551773071, | |
| "eval_runtime": 21.5789, | |
| "eval_samples_per_second": 46.342, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8855, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.8813124895095825, | |
| "eval_runtime": 21.549, | |
| "eval_samples_per_second": 46.406, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9001, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.8811875581741333, | |
| "eval_runtime": 21.5415, | |
| "eval_samples_per_second": 46.422, | |
| "eval_steps_per_second": 1.486, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8811, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.8804999589920044, | |
| "eval_runtime": 21.5596, | |
| "eval_samples_per_second": 46.383, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0566, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.8810625076293945, | |
| "eval_runtime": 21.5594, | |
| "eval_samples_per_second": 46.384, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9561, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.881250023841858, | |
| "eval_runtime": 21.5398, | |
| "eval_samples_per_second": 46.426, | |
| "eval_steps_per_second": 1.486, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9045, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.8804999589920044, | |
| "eval_runtime": 21.5702, | |
| "eval_samples_per_second": 46.36, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9714, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.8798749446868896, | |
| "eval_runtime": 21.5811, | |
| "eval_samples_per_second": 46.337, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9288, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.879812479019165, | |
| "eval_runtime": 21.55, | |
| "eval_samples_per_second": 46.404, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8237, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.8797500133514404, | |
| "eval_runtime": 21.5524, | |
| "eval_samples_per_second": 46.398, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9617, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.8813124895095825, | |
| "eval_runtime": 21.5313, | |
| "eval_samples_per_second": 46.444, | |
| "eval_steps_per_second": 1.486, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9844, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.8817499876022339, | |
| "eval_runtime": 21.5808, | |
| "eval_samples_per_second": 46.338, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9525, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.8786875009536743, | |
| "eval_runtime": 21.5448, | |
| "eval_samples_per_second": 46.415, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8189, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.8784375190734863, | |
| "eval_runtime": 21.5565, | |
| "eval_samples_per_second": 46.39, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8924, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.878812551498413, | |
| "eval_runtime": 21.6129, | |
| "eval_samples_per_second": 46.269, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8579, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.8789374828338623, | |
| "eval_runtime": 21.6098, | |
| "eval_samples_per_second": 46.275, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8618, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.8783124685287476, | |
| "eval_runtime": 21.5917, | |
| "eval_samples_per_second": 46.314, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9999, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.8779375553131104, | |
| "eval_runtime": 21.6272, | |
| "eval_samples_per_second": 46.238, | |
| "eval_steps_per_second": 1.48, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8795, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.8776874542236328, | |
| "eval_runtime": 21.5765, | |
| "eval_samples_per_second": 46.347, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8766, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.878749966621399, | |
| "eval_runtime": 21.6054, | |
| "eval_samples_per_second": 46.285, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8596, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.8778125047683716, | |
| "eval_runtime": 21.6178, | |
| "eval_samples_per_second": 46.258, | |
| "eval_steps_per_second": 1.48, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9722, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.8778749704360962, | |
| "eval_runtime": 21.6267, | |
| "eval_samples_per_second": 46.239, | |
| "eval_steps_per_second": 1.48, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9459, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.878749966621399, | |
| "eval_runtime": 21.5929, | |
| "eval_samples_per_second": 46.312, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9772, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.8791249990463257, | |
| "eval_runtime": 21.6453, | |
| "eval_samples_per_second": 46.199, | |
| "eval_steps_per_second": 1.478, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9241, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.877750039100647, | |
| "eval_runtime": 21.5578, | |
| "eval_samples_per_second": 46.387, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9391, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.8766249418258667, | |
| "eval_runtime": 21.5657, | |
| "eval_samples_per_second": 46.37, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9602, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.8764375448226929, | |
| "eval_runtime": 21.5619, | |
| "eval_samples_per_second": 46.378, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0581, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.8766875267028809, | |
| "eval_runtime": 21.5636, | |
| "eval_samples_per_second": 46.375, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9303, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.8773750066757202, | |
| "eval_runtime": 21.5664, | |
| "eval_samples_per_second": 46.368, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-06, | |
| "loss": 1.837, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.8773125410079956, | |
| "eval_runtime": 21.561, | |
| "eval_samples_per_second": 46.38, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9485, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.8799375295639038, | |
| "eval_runtime": 21.5621, | |
| "eval_samples_per_second": 46.378, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9599, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.8831249475479126, | |
| "eval_runtime": 21.5818, | |
| "eval_samples_per_second": 46.335, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9171, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.8783750534057617, | |
| "eval_runtime": 21.6332, | |
| "eval_samples_per_second": 46.225, | |
| "eval_steps_per_second": 1.479, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8861, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.8766875267028809, | |
| "eval_runtime": 21.5533, | |
| "eval_samples_per_second": 46.397, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9208, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.8760625123977661, | |
| "eval_runtime": 21.5483, | |
| "eval_samples_per_second": 46.407, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8775, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.8756250143051147, | |
| "eval_runtime": 21.5365, | |
| "eval_samples_per_second": 46.433, | |
| "eval_steps_per_second": 1.486, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1e-06, | |
| "loss": 1.962, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.875499963760376, | |
| "eval_runtime": 21.5519, | |
| "eval_samples_per_second": 46.4, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1e-06, | |
| "loss": 1.92, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.8764375448226929, | |
| "eval_runtime": 21.5524, | |
| "eval_samples_per_second": 46.399, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8704, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.875749945640564, | |
| "eval_runtime": 21.5397, | |
| "eval_samples_per_second": 46.426, | |
| "eval_steps_per_second": 1.486, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1e-06, | |
| "loss": 1.896, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.874750018119812, | |
| "eval_runtime": 21.5328, | |
| "eval_samples_per_second": 46.441, | |
| "eval_steps_per_second": 1.486, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8639, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.8745625019073486, | |
| "eval_runtime": 21.541, | |
| "eval_samples_per_second": 46.423, | |
| "eval_steps_per_second": 1.486, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8501, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.8751250505447388, | |
| "eval_runtime": 21.5841, | |
| "eval_samples_per_second": 46.33, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-06, | |
| "loss": 1.958, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.8756250143051147, | |
| "eval_runtime": 21.7332, | |
| "eval_samples_per_second": 46.012, | |
| "eval_steps_per_second": 1.472, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9339, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.8751875162124634, | |
| "eval_runtime": 21.5783, | |
| "eval_samples_per_second": 46.343, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8906, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.8748749494552612, | |
| "eval_runtime": 21.5897, | |
| "eval_samples_per_second": 46.318, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-06, | |
| "loss": 1.953, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.8763749599456787, | |
| "eval_runtime": 21.6102, | |
| "eval_samples_per_second": 46.274, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9304, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.8776249885559082, | |
| "eval_runtime": 21.5663, | |
| "eval_samples_per_second": 46.369, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9081, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.876562476158142, | |
| "eval_runtime": 21.5451, | |
| "eval_samples_per_second": 46.414, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1e-06, | |
| "loss": 1.966, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.8761249780654907, | |
| "eval_runtime": 21.5413, | |
| "eval_samples_per_second": 46.422, | |
| "eval_steps_per_second": 1.486, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9819, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.8755625486373901, | |
| "eval_runtime": 21.5524, | |
| "eval_samples_per_second": 46.399, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9206, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.8758125305175781, | |
| "eval_runtime": 21.7021, | |
| "eval_samples_per_second": 46.079, | |
| "eval_steps_per_second": 1.475, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9011, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.8749375343322754, | |
| "eval_runtime": 21.5651, | |
| "eval_samples_per_second": 46.371, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0006, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.8758749961853027, | |
| "eval_runtime": 21.5599, | |
| "eval_samples_per_second": 46.382, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8774, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.8758125305175781, | |
| "eval_runtime": 21.5817, | |
| "eval_samples_per_second": 46.336, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9009, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.875249981880188, | |
| "eval_runtime": 21.5655, | |
| "eval_samples_per_second": 46.37, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1e-06, | |
| "loss": 1.93, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.8749375343322754, | |
| "eval_runtime": 21.5523, | |
| "eval_samples_per_second": 46.399, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9684, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.8741874694824219, | |
| "eval_runtime": 21.5577, | |
| "eval_samples_per_second": 46.387, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9726, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.8737499713897705, | |
| "eval_runtime": 21.7399, | |
| "eval_samples_per_second": 45.998, | |
| "eval_steps_per_second": 1.472, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8864, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.8734999895095825, | |
| "eval_runtime": 21.7297, | |
| "eval_samples_per_second": 46.02, | |
| "eval_steps_per_second": 1.473, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8647, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.8739374876022339, | |
| "eval_runtime": 21.5773, | |
| "eval_samples_per_second": 46.345, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9116, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.8738750219345093, | |
| "eval_runtime": 21.5785, | |
| "eval_samples_per_second": 46.342, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8138, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.8732500076293945, | |
| "eval_runtime": 21.5722, | |
| "eval_samples_per_second": 46.356, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8506, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.8730000257492065, | |
| "eval_runtime": 21.5369, | |
| "eval_samples_per_second": 46.432, | |
| "eval_steps_per_second": 1.486, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9682, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.8727500438690186, | |
| "eval_runtime": 21.5444, | |
| "eval_samples_per_second": 46.416, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9206, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.871749997138977, | |
| "eval_runtime": 21.6398, | |
| "eval_samples_per_second": 46.211, | |
| "eval_steps_per_second": 1.479, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9281, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.8723125457763672, | |
| "eval_runtime": 21.5661, | |
| "eval_samples_per_second": 46.369, | |
| "eval_steps_per_second": 1.484, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1e-06, | |
| "loss": 1.7545, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.872499942779541, | |
| "eval_runtime": 21.587, | |
| "eval_samples_per_second": 46.324, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9969, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.8730624914169312, | |
| "eval_runtime": 21.6092, | |
| "eval_samples_per_second": 46.276, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8196, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.8728125095367432, | |
| "eval_runtime": 21.6084, | |
| "eval_samples_per_second": 46.278, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8404, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.8725625276565552, | |
| "eval_runtime": 21.58, | |
| "eval_samples_per_second": 46.339, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8799, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.8741250038146973, | |
| "eval_runtime": 21.5927, | |
| "eval_samples_per_second": 46.312, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-06, | |
| "loss": 1.993, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.8760625123977661, | |
| "eval_runtime": 21.5913, | |
| "eval_samples_per_second": 46.315, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9346, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.8756874799728394, | |
| "eval_runtime": 21.601, | |
| "eval_samples_per_second": 46.294, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9037, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.8730624914169312, | |
| "eval_runtime": 21.6017, | |
| "eval_samples_per_second": 46.293, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8902, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.8721250295639038, | |
| "eval_runtime": 21.579, | |
| "eval_samples_per_second": 46.341, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-06, | |
| "loss": 2.019, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.8739999532699585, | |
| "eval_runtime": 21.5802, | |
| "eval_samples_per_second": 46.339, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8906, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.8728749752044678, | |
| "eval_runtime": 21.5856, | |
| "eval_samples_per_second": 46.327, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9652, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.871000051498413, | |
| "eval_runtime": 21.6176, | |
| "eval_samples_per_second": 46.258, | |
| "eval_steps_per_second": 1.48, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9899, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.870937466621399, | |
| "eval_runtime": 21.5907, | |
| "eval_samples_per_second": 46.316, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9037, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.8716249465942383, | |
| "eval_runtime": 21.5777, | |
| "eval_samples_per_second": 46.344, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8631, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.8726874589920044, | |
| "eval_runtime": 21.6244, | |
| "eval_samples_per_second": 46.244, | |
| "eval_steps_per_second": 1.48, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1e-06, | |
| "loss": 1.7984, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.8730624914169312, | |
| "eval_runtime": 21.6044, | |
| "eval_samples_per_second": 46.287, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9407, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.8730624914169312, | |
| "eval_runtime": 21.6177, | |
| "eval_samples_per_second": 46.258, | |
| "eval_steps_per_second": 1.48, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8164, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.873437523841858, | |
| "eval_runtime": 21.6277, | |
| "eval_samples_per_second": 46.237, | |
| "eval_steps_per_second": 1.48, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8932, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.871999979019165, | |
| "eval_runtime": 21.6169, | |
| "eval_samples_per_second": 46.26, | |
| "eval_steps_per_second": 1.48, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9844, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.8725625276565552, | |
| "eval_runtime": 21.5819, | |
| "eval_samples_per_second": 46.335, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9424, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.8738750219345093, | |
| "eval_runtime": 21.5932, | |
| "eval_samples_per_second": 46.311, | |
| "eval_steps_per_second": 1.482, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9486, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.8728125095367432, | |
| "eval_runtime": 21.5827, | |
| "eval_samples_per_second": 46.333, | |
| "eval_steps_per_second": 1.483, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9749, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.8716249465942383, | |
| "eval_runtime": 21.6181, | |
| "eval_samples_per_second": 46.258, | |
| "eval_steps_per_second": 1.48, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8682, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.8724374771118164, | |
| "eval_runtime": 21.6027, | |
| "eval_samples_per_second": 46.291, | |
| "eval_steps_per_second": 1.481, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9345, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.8714375495910645, | |
| "eval_runtime": 21.6133, | |
| "eval_samples_per_second": 46.268, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8661, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.8723125457763672, | |
| "eval_runtime": 21.6661, | |
| "eval_samples_per_second": 46.155, | |
| "eval_steps_per_second": 1.477, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9508, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.871999979019165, | |
| "eval_runtime": 21.5876, | |
| "eval_samples_per_second": 46.323, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9146, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.8727500438690186, | |
| "eval_runtime": 21.5919, | |
| "eval_samples_per_second": 46.314, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-06, | |
| "loss": 1.7965, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.871500015258789, | |
| "eval_runtime": 21.6483, | |
| "eval_samples_per_second": 46.193, | |
| "eval_steps_per_second": 1.478, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9109, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.8706250190734863, | |
| "eval_runtime": 21.6261, | |
| "eval_samples_per_second": 46.24, | |
| "eval_steps_per_second": 1.48, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9373, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.8695000410079956, | |
| "eval_runtime": 21.6392, | |
| "eval_samples_per_second": 46.213, | |
| "eval_steps_per_second": 1.479, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8915, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.8704999685287476, | |
| "eval_runtime": 21.6056, | |
| "eval_samples_per_second": 46.284, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9567, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.8711249828338623, | |
| "eval_runtime": 21.6009, | |
| "eval_samples_per_second": 46.294, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9928, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.8720624446868896, | |
| "eval_runtime": 21.6088, | |
| "eval_samples_per_second": 46.277, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9007, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.8716875314712524, | |
| "eval_runtime": 21.5836, | |
| "eval_samples_per_second": 46.331, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0197, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.8726249933242798, | |
| "eval_runtime": 21.6035, | |
| "eval_samples_per_second": 46.289, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8577, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.8723125457763672, | |
| "eval_runtime": 21.5721, | |
| "eval_samples_per_second": 46.356, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9027, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.871500015258789, | |
| "eval_runtime": 21.6009, | |
| "eval_samples_per_second": 46.294, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9688, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.870687484741211, | |
| "eval_runtime": 21.6082, | |
| "eval_samples_per_second": 46.279, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8481, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.871000051498413, | |
| "eval_runtime": 21.5824, | |
| "eval_samples_per_second": 46.334, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0055, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.8702499866485596, | |
| "eval_runtime": 21.5896, | |
| "eval_samples_per_second": 46.319, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8399, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.8694374561309814, | |
| "eval_runtime": 21.5874, | |
| "eval_samples_per_second": 46.323, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9194, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.870687484741211, | |
| "eval_runtime": 21.5716, | |
| "eval_samples_per_second": 46.357, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1e-06, | |
| "loss": 1.88, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.8708125352859497, | |
| "eval_runtime": 21.6211, | |
| "eval_samples_per_second": 46.251, | |
| "eval_steps_per_second": 1.48, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9445, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.8707499504089355, | |
| "eval_runtime": 21.5768, | |
| "eval_samples_per_second": 46.346, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8887, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.8695625066757202, | |
| "eval_runtime": 21.6318, | |
| "eval_samples_per_second": 46.228, | |
| "eval_steps_per_second": 1.479, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1e-06, | |
| "loss": 1.888, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.86899995803833, | |
| "eval_runtime": 21.6021, | |
| "eval_samples_per_second": 46.292, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1e-06, | |
| "loss": 1.933, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.869687557220459, | |
| "eval_runtime": 21.5965, | |
| "eval_samples_per_second": 46.304, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9369, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.870437502861023, | |
| "eval_runtime": 21.6057, | |
| "eval_samples_per_second": 46.284, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8328, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.8711249828338623, | |
| "eval_runtime": 21.5785, | |
| "eval_samples_per_second": 46.343, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9838, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.871000051498413, | |
| "eval_runtime": 21.6054, | |
| "eval_samples_per_second": 46.285, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8654, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.869687557220459, | |
| "eval_runtime": 21.5808, | |
| "eval_samples_per_second": 46.338, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8876, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.8686250448226929, | |
| "eval_runtime": 21.5951, | |
| "eval_samples_per_second": 46.307, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8914, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.8711249828338623, | |
| "eval_runtime": 21.5778, | |
| "eval_samples_per_second": 46.344, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1e-06, | |
| "loss": 1.967, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.8733124732971191, | |
| "eval_runtime": 21.6111, | |
| "eval_samples_per_second": 46.272, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9661, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.872249960899353, | |
| "eval_runtime": 21.5819, | |
| "eval_samples_per_second": 46.335, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8294, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.8703750371932983, | |
| "eval_runtime": 21.6271, | |
| "eval_samples_per_second": 46.238, | |
| "eval_steps_per_second": 1.48, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1e-06, | |
| "loss": 1.856, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.869937539100647, | |
| "eval_runtime": 21.5927, | |
| "eval_samples_per_second": 46.312, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9569, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.8698749542236328, | |
| "eval_runtime": 21.618, | |
| "eval_samples_per_second": 46.258, | |
| "eval_steps_per_second": 1.48, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9006, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.8704999685287476, | |
| "eval_runtime": 21.5544, | |
| "eval_samples_per_second": 46.394, | |
| "eval_steps_per_second": 1.485, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8635, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.869687557220459, | |
| "eval_runtime": 21.5869, | |
| "eval_samples_per_second": 46.324, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9302, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.8683124780654907, | |
| "eval_runtime": 21.6281, | |
| "eval_samples_per_second": 46.236, | |
| "eval_steps_per_second": 1.48, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1e-06, | |
| "loss": 1.939, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.8693749904632568, | |
| "eval_runtime": 21.6034, | |
| "eval_samples_per_second": 46.289, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0063, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.8693125247955322, | |
| "eval_runtime": 21.614, | |
| "eval_samples_per_second": 46.266, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9715, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.86899995803833, | |
| "eval_runtime": 21.6058, | |
| "eval_samples_per_second": 46.284, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8157, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.868749976158142, | |
| "eval_runtime": 21.6026, | |
| "eval_samples_per_second": 46.291, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8611, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.8670624494552612, | |
| "eval_runtime": 21.5635, | |
| "eval_samples_per_second": 46.375, | |
| "eval_steps_per_second": 1.484, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8827, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.8689374923706055, | |
| "eval_runtime": 21.59, | |
| "eval_samples_per_second": 46.318, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9646, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.868749976158142, | |
| "eval_runtime": 21.5851, | |
| "eval_samples_per_second": 46.328, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9296, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.8684375286102295, | |
| "eval_runtime": 21.591, | |
| "eval_samples_per_second": 46.315, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9716, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.867687463760376, | |
| "eval_runtime": 21.5971, | |
| "eval_samples_per_second": 46.303, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9831, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.8676249980926514, | |
| "eval_runtime": 21.6382, | |
| "eval_samples_per_second": 46.215, | |
| "eval_steps_per_second": 1.479, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9715, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.8678125143051147, | |
| "eval_runtime": 21.6005, | |
| "eval_samples_per_second": 46.295, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9537, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.8674999475479126, | |
| "eval_runtime": 21.6161, | |
| "eval_samples_per_second": 46.262, | |
| "eval_steps_per_second": 1.48, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8924, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.8671875, | |
| "eval_runtime": 21.5707, | |
| "eval_samples_per_second": 46.359, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8183, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.8671250343322754, | |
| "eval_runtime": 21.5773, | |
| "eval_samples_per_second": 46.345, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1e-06, | |
| "loss": 1.969, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.8673750162124634, | |
| "eval_runtime": 21.5742, | |
| "eval_samples_per_second": 46.352, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8521, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.8665624856948853, | |
| "eval_runtime": 21.6165, | |
| "eval_samples_per_second": 46.261, | |
| "eval_steps_per_second": 1.48, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8958, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.8663749694824219, | |
| "eval_runtime": 21.5664, | |
| "eval_samples_per_second": 46.368, | |
| "eval_steps_per_second": 1.484, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9078, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.8668124675750732, | |
| "eval_runtime": 21.5521, | |
| "eval_samples_per_second": 46.399, | |
| "eval_steps_per_second": 1.485, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0287, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.8656874895095825, | |
| "eval_runtime": 21.6113, | |
| "eval_samples_per_second": 46.272, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8675, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.866437554359436, | |
| "eval_runtime": 21.5543, | |
| "eval_samples_per_second": 46.394, | |
| "eval_steps_per_second": 1.485, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9092, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.8676249980926514, | |
| "eval_runtime": 21.5876, | |
| "eval_samples_per_second": 46.323, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9228, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.8668750524520874, | |
| "eval_runtime": 21.5838, | |
| "eval_samples_per_second": 46.331, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8323, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.8671250343322754, | |
| "eval_runtime": 21.5909, | |
| "eval_samples_per_second": 46.316, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8681, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.8672499656677246, | |
| "eval_runtime": 21.6347, | |
| "eval_samples_per_second": 46.222, | |
| "eval_steps_per_second": 1.479, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8857, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.866937518119812, | |
| "eval_runtime": 21.5667, | |
| "eval_samples_per_second": 46.368, | |
| "eval_steps_per_second": 1.484, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8886, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.8674999475479126, | |
| "eval_runtime": 21.5708, | |
| "eval_samples_per_second": 46.359, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8823, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.8668750524520874, | |
| "eval_runtime": 21.5567, | |
| "eval_samples_per_second": 46.389, | |
| "eval_steps_per_second": 1.484, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8864, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.8669999837875366, | |
| "eval_runtime": 21.5934, | |
| "eval_samples_per_second": 46.311, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8154, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.8663125038146973, | |
| "eval_runtime": 21.5778, | |
| "eval_samples_per_second": 46.344, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0137, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.8665624856948853, | |
| "eval_runtime": 21.607, | |
| "eval_samples_per_second": 46.281, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9625, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.8675625324249268, | |
| "eval_runtime": 21.5865, | |
| "eval_samples_per_second": 46.325, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8932, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.8663749694824219, | |
| "eval_runtime": 21.5997, | |
| "eval_samples_per_second": 46.297, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8908, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.8663749694824219, | |
| "eval_runtime": 21.5689, | |
| "eval_samples_per_second": 46.363, | |
| "eval_steps_per_second": 1.484, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8462, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.8659374713897705, | |
| "eval_runtime": 21.6266, | |
| "eval_samples_per_second": 46.239, | |
| "eval_steps_per_second": 1.48, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1e-06, | |
| "loss": 1.931, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.8665000200271606, | |
| "eval_runtime": 21.5565, | |
| "eval_samples_per_second": 46.39, | |
| "eval_steps_per_second": 1.484, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8934, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.8661249876022339, | |
| "eval_runtime": 21.5483, | |
| "eval_samples_per_second": 46.407, | |
| "eval_steps_per_second": 1.485, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9062, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.864687442779541, | |
| "eval_runtime": 21.5553, | |
| "eval_samples_per_second": 46.392, | |
| "eval_steps_per_second": 1.485, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9488, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.865625023841858, | |
| "eval_runtime": 21.6493, | |
| "eval_samples_per_second": 46.191, | |
| "eval_steps_per_second": 1.478, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8542, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.8663749694824219, | |
| "eval_runtime": 21.5708, | |
| "eval_samples_per_second": 46.359, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8613, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.865625023841858, | |
| "eval_runtime": 21.5531, | |
| "eval_samples_per_second": 46.397, | |
| "eval_steps_per_second": 1.485, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9469, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.864437460899353, | |
| "eval_runtime": 21.6086, | |
| "eval_samples_per_second": 46.278, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9361, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.8630625009536743, | |
| "eval_runtime": 21.5955, | |
| "eval_samples_per_second": 46.306, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8308, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.8620624542236328, | |
| "eval_runtime": 21.6009, | |
| "eval_samples_per_second": 46.294, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1e-06, | |
| "loss": 2.009, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.862874984741211, | |
| "eval_runtime": 21.5914, | |
| "eval_samples_per_second": 46.315, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1e-06, | |
| "loss": 1.904, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.8635624647140503, | |
| "eval_runtime": 21.5927, | |
| "eval_samples_per_second": 46.312, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9847, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.8627500534057617, | |
| "eval_runtime": 21.5734, | |
| "eval_samples_per_second": 46.353, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9402, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.8653124570846558, | |
| "eval_runtime": 21.6183, | |
| "eval_samples_per_second": 46.257, | |
| "eval_steps_per_second": 1.48, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9575, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.8649375438690186, | |
| "eval_runtime": 21.5847, | |
| "eval_samples_per_second": 46.329, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9414, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.8635624647140503, | |
| "eval_runtime": 21.5693, | |
| "eval_samples_per_second": 46.362, | |
| "eval_steps_per_second": 1.484, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8488, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.863124966621399, | |
| "eval_runtime": 21.7767, | |
| "eval_samples_per_second": 45.921, | |
| "eval_steps_per_second": 1.469, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8756, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.8624999523162842, | |
| "eval_runtime": 21.5671, | |
| "eval_samples_per_second": 46.367, | |
| "eval_steps_per_second": 1.484, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9141, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.8633124828338623, | |
| "eval_runtime": 21.5606, | |
| "eval_samples_per_second": 46.381, | |
| "eval_steps_per_second": 1.484, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8407, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.8626874685287476, | |
| "eval_runtime": 21.5655, | |
| "eval_samples_per_second": 46.37, | |
| "eval_steps_per_second": 1.484, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8517, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.8627500534057617, | |
| "eval_runtime": 21.5756, | |
| "eval_samples_per_second": 46.349, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-06, | |
| "loss": 1.856, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.8637499809265137, | |
| "eval_runtime": 21.5785, | |
| "eval_samples_per_second": 46.342, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8582, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.863437533378601, | |
| "eval_runtime": 21.5986, | |
| "eval_samples_per_second": 46.299, | |
| "eval_steps_per_second": 1.482, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8528, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.8622499704360962, | |
| "eval_runtime": 21.6191, | |
| "eval_samples_per_second": 46.255, | |
| "eval_steps_per_second": 1.48, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-06, | |
| "loss": 1.896, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.8615000247955322, | |
| "eval_runtime": 21.5689, | |
| "eval_samples_per_second": 46.363, | |
| "eval_steps_per_second": 1.484, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9112, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.86118745803833, | |
| "eval_runtime": 21.577, | |
| "eval_samples_per_second": 46.346, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9361, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.8620624542236328, | |
| "eval_runtime": 21.6002, | |
| "eval_samples_per_second": 46.296, | |
| "eval_steps_per_second": 1.481, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9024, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.8619375228881836, | |
| "eval_runtime": 21.6227, | |
| "eval_samples_per_second": 46.248, | |
| "eval_steps_per_second": 1.48, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9028, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.8627500534057617, | |
| "eval_runtime": 21.5823, | |
| "eval_samples_per_second": 46.334, | |
| "eval_steps_per_second": 1.483, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8198, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.8626874685287476, | |
| "eval_runtime": 21.5914, | |
| "eval_samples_per_second": 46.315, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1e-06, | |
| "loss": 1.967, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.8630625009536743, | |
| "eval_runtime": 21.5946, | |
| "eval_samples_per_second": 46.308, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8466, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.8624374866485596, | |
| "eval_runtime": 21.5514, | |
| "eval_samples_per_second": 46.401, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8635, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.8626874685287476, | |
| "eval_runtime": 21.5938, | |
| "eval_samples_per_second": 46.31, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9223, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.8628125190734863, | |
| "eval_runtime": 21.5984, | |
| "eval_samples_per_second": 46.3, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9931, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.8619999885559082, | |
| "eval_runtime": 21.8827, | |
| "eval_samples_per_second": 45.698, | |
| "eval_steps_per_second": 1.462, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9137, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.8615000247955322, | |
| "eval_runtime": 21.5734, | |
| "eval_samples_per_second": 46.353, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9683, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.863124966621399, | |
| "eval_runtime": 21.5788, | |
| "eval_samples_per_second": 46.342, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9427, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.8628125190734863, | |
| "eval_runtime": 21.5727, | |
| "eval_samples_per_second": 46.355, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8678, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.8617500066757202, | |
| "eval_runtime": 21.5841, | |
| "eval_samples_per_second": 46.33, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9757, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.8612500429153442, | |
| "eval_runtime": 21.5639, | |
| "eval_samples_per_second": 46.374, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9448, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 1.860687494277954, | |
| "eval_runtime": 21.5528, | |
| "eval_samples_per_second": 46.398, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9297, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 1.8616249561309814, | |
| "eval_runtime": 21.5684, | |
| "eval_samples_per_second": 46.364, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9876, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 1.8630000352859497, | |
| "eval_runtime": 21.5722, | |
| "eval_samples_per_second": 46.356, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9954, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 1.8636250495910645, | |
| "eval_runtime": 21.5747, | |
| "eval_samples_per_second": 46.35, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8693, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 1.8613749742507935, | |
| "eval_runtime": 21.6006, | |
| "eval_samples_per_second": 46.295, | |
| "eval_steps_per_second": 1.481, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9001, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 1.859874963760376, | |
| "eval_runtime": 21.6053, | |
| "eval_samples_per_second": 46.285, | |
| "eval_steps_per_second": 1.481, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9062, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.8604375123977661, | |
| "eval_runtime": 21.6077, | |
| "eval_samples_per_second": 46.28, | |
| "eval_steps_per_second": 1.481, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8388, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.860937476158142, | |
| "eval_runtime": 21.5983, | |
| "eval_samples_per_second": 46.3, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8595, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.8619375228881836, | |
| "eval_runtime": 21.5823, | |
| "eval_samples_per_second": 46.334, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1e-06, | |
| "loss": 1.839, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.8622499704360962, | |
| "eval_runtime": 21.5981, | |
| "eval_samples_per_second": 46.3, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8295, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.8627500534057617, | |
| "eval_runtime": 21.5809, | |
| "eval_samples_per_second": 46.337, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8441, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.8630625009536743, | |
| "eval_runtime": 21.6036, | |
| "eval_samples_per_second": 46.289, | |
| "eval_steps_per_second": 1.481, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8115, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.862625002861023, | |
| "eval_runtime": 21.5853, | |
| "eval_samples_per_second": 46.328, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9005, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.862874984741211, | |
| "eval_runtime": 21.591, | |
| "eval_samples_per_second": 46.316, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0089, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.863124966621399, | |
| "eval_runtime": 21.5772, | |
| "eval_samples_per_second": 46.345, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8844, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.8622499704360962, | |
| "eval_runtime": 21.5763, | |
| "eval_samples_per_second": 46.347, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9881, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.8629374504089355, | |
| "eval_runtime": 21.6029, | |
| "eval_samples_per_second": 46.29, | |
| "eval_steps_per_second": 1.481, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9513, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.8619999885559082, | |
| "eval_runtime": 21.5844, | |
| "eval_samples_per_second": 46.33, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9402, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.8602499961853027, | |
| "eval_runtime": 21.5782, | |
| "eval_samples_per_second": 46.343, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8831, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.8602499961853027, | |
| "eval_runtime": 21.5914, | |
| "eval_samples_per_second": 46.315, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8559, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.860124945640564, | |
| "eval_runtime": 21.621, | |
| "eval_samples_per_second": 46.251, | |
| "eval_steps_per_second": 1.48, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9143, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.859125018119812, | |
| "eval_runtime": 21.635, | |
| "eval_samples_per_second": 46.221, | |
| "eval_steps_per_second": 1.479, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9208, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.8601875305175781, | |
| "eval_runtime": 21.5808, | |
| "eval_samples_per_second": 46.338, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9305, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.8603750467300415, | |
| "eval_runtime": 21.5694, | |
| "eval_samples_per_second": 46.362, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8194, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.8591874837875366, | |
| "eval_runtime": 21.5705, | |
| "eval_samples_per_second": 46.36, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9233, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 1.8585000038146973, | |
| "eval_runtime": 21.5597, | |
| "eval_samples_per_second": 46.383, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8612, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 1.8569999933242798, | |
| "eval_runtime": 21.5726, | |
| "eval_samples_per_second": 46.355, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8693, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 1.8571875095367432, | |
| "eval_runtime": 21.5497, | |
| "eval_samples_per_second": 46.404, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1e-06, | |
| "loss": 1.907, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 1.8586875200271606, | |
| "eval_runtime": 21.5621, | |
| "eval_samples_per_second": 46.378, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8938, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 1.8597500324249268, | |
| "eval_runtime": 21.573, | |
| "eval_samples_per_second": 46.354, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9379, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 1.8589375019073486, | |
| "eval_runtime": 21.6039, | |
| "eval_samples_per_second": 46.288, | |
| "eval_steps_per_second": 1.481, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9152, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.8595625162124634, | |
| "eval_runtime": 21.5632, | |
| "eval_samples_per_second": 46.375, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8737, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.8599375486373901, | |
| "eval_runtime": 21.5502, | |
| "eval_samples_per_second": 46.403, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9452, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.859624981880188, | |
| "eval_runtime": 21.555, | |
| "eval_samples_per_second": 46.393, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1e-06, | |
| "loss": 1.7954, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.858875036239624, | |
| "eval_runtime": 21.5874, | |
| "eval_samples_per_second": 46.323, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1e-06, | |
| "loss": 1.867, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.8594374656677246, | |
| "eval_runtime": 21.5688, | |
| "eval_samples_per_second": 46.363, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9465, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.859375, | |
| "eval_runtime": 21.5683, | |
| "eval_samples_per_second": 46.364, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8563, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.8601875305175781, | |
| "eval_runtime": 21.5556, | |
| "eval_samples_per_second": 46.392, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9413, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.8608125448226929, | |
| "eval_runtime": 21.554, | |
| "eval_samples_per_second": 46.395, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8672, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.8600624799728394, | |
| "eval_runtime": 21.561, | |
| "eval_samples_per_second": 46.38, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9427, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.8600000143051147, | |
| "eval_runtime": 21.5522, | |
| "eval_samples_per_second": 46.399, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8576, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.8570624589920044, | |
| "eval_runtime": 21.5628, | |
| "eval_samples_per_second": 46.376, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9259, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.8559999465942383, | |
| "eval_runtime": 21.5485, | |
| "eval_samples_per_second": 46.407, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9291, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.856124997138977, | |
| "eval_runtime": 21.5528, | |
| "eval_samples_per_second": 46.398, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8441, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.8566875457763672, | |
| "eval_runtime": 21.5783, | |
| "eval_samples_per_second": 46.343, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1e-06, | |
| "loss": 1.905, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.8570624589920044, | |
| "eval_runtime": 21.5547, | |
| "eval_samples_per_second": 46.394, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9797, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.8564374446868896, | |
| "eval_runtime": 21.5456, | |
| "eval_samples_per_second": 46.413, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8988, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.8571875095367432, | |
| "eval_runtime": 21.5553, | |
| "eval_samples_per_second": 46.392, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9099, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.8568124771118164, | |
| "eval_runtime": 21.5449, | |
| "eval_samples_per_second": 46.415, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9458, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.8576250076293945, | |
| "eval_runtime": 21.5523, | |
| "eval_samples_per_second": 46.399, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9416, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.8564374446868896, | |
| "eval_runtime": 21.561, | |
| "eval_samples_per_second": 46.38, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8823, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.8567500114440918, | |
| "eval_runtime": 21.5589, | |
| "eval_samples_per_second": 46.385, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8919, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.8569375276565552, | |
| "eval_runtime": 21.5546, | |
| "eval_samples_per_second": 46.394, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9271, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.8585624694824219, | |
| "eval_runtime": 21.5722, | |
| "eval_samples_per_second": 46.356, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9337, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.8586875200271606, | |
| "eval_runtime": 21.5528, | |
| "eval_samples_per_second": 46.398, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9362, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.8581249713897705, | |
| "eval_runtime": 21.5364, | |
| "eval_samples_per_second": 46.433, | |
| "eval_steps_per_second": 1.486, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8491, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 1.8567500114440918, | |
| "eval_runtime": 21.6083, | |
| "eval_samples_per_second": 46.279, | |
| "eval_steps_per_second": 1.481, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8954, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 1.8565624952316284, | |
| "eval_runtime": 21.576, | |
| "eval_samples_per_second": 46.348, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8662, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 1.856624960899353, | |
| "eval_runtime": 21.567, | |
| "eval_samples_per_second": 46.367, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9247, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 1.856124997138977, | |
| "eval_runtime": 21.5695, | |
| "eval_samples_per_second": 46.362, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9457, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 1.8573124408721924, | |
| "eval_runtime": 21.5802, | |
| "eval_samples_per_second": 46.339, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8775, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 1.855562448501587, | |
| "eval_runtime": 21.5795, | |
| "eval_samples_per_second": 46.34, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9068, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.855875015258789, | |
| "eval_runtime": 21.5796, | |
| "eval_samples_per_second": 46.34, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-06, | |
| "loss": 1.946, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.8560625314712524, | |
| "eval_runtime": 21.5655, | |
| "eval_samples_per_second": 46.37, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9571, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.8551249504089355, | |
| "eval_runtime": 21.5888, | |
| "eval_samples_per_second": 46.32, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8821, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.8554999828338623, | |
| "eval_runtime": 21.6112, | |
| "eval_samples_per_second": 46.272, | |
| "eval_steps_per_second": 1.481, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8955, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.8547500371932983, | |
| "eval_runtime": 21.5724, | |
| "eval_samples_per_second": 46.355, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9742, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.8536875247955322, | |
| "eval_runtime": 21.5718, | |
| "eval_samples_per_second": 46.357, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9093, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.8535000085830688, | |
| "eval_runtime": 21.5691, | |
| "eval_samples_per_second": 46.363, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9554, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.8543750047683716, | |
| "eval_runtime": 21.5774, | |
| "eval_samples_per_second": 46.345, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8263, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.8541874885559082, | |
| "eval_runtime": 21.5724, | |
| "eval_samples_per_second": 46.356, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9127, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.8545000553131104, | |
| "eval_runtime": 21.5547, | |
| "eval_samples_per_second": 46.394, | |
| "eval_steps_per_second": 1.485, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8252, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.8549375534057617, | |
| "eval_runtime": 21.5655, | |
| "eval_samples_per_second": 46.37, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8472, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.8551249504089355, | |
| "eval_runtime": 21.5877, | |
| "eval_samples_per_second": 46.323, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9126, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.8554999828338623, | |
| "eval_runtime": 21.5809, | |
| "eval_samples_per_second": 46.337, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8399, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.8544374704360962, | |
| "eval_runtime": 21.5745, | |
| "eval_samples_per_second": 46.351, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8661, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.8534375429153442, | |
| "eval_runtime": 21.5844, | |
| "eval_samples_per_second": 46.33, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8978, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.853124976158142, | |
| "eval_runtime": 21.5729, | |
| "eval_samples_per_second": 46.354, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8909, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.85337495803833, | |
| "eval_runtime": 21.5575, | |
| "eval_samples_per_second": 46.388, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9605, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.85337495803833, | |
| "eval_runtime": 21.6309, | |
| "eval_samples_per_second": 46.23, | |
| "eval_steps_per_second": 1.479, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9278, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.8543750047683716, | |
| "eval_runtime": 21.5801, | |
| "eval_samples_per_second": 46.339, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8411, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.8535000085830688, | |
| "eval_runtime": 21.5905, | |
| "eval_samples_per_second": 46.317, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9211, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.8535000085830688, | |
| "eval_runtime": 21.5883, | |
| "eval_samples_per_second": 46.321, | |
| "eval_steps_per_second": 1.482, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8927, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.8531874418258667, | |
| "eval_runtime": 21.561, | |
| "eval_samples_per_second": 46.38, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8337, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.8536250591278076, | |
| "eval_runtime": 21.562, | |
| "eval_samples_per_second": 46.378, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8951, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.8544374704360962, | |
| "eval_runtime": 21.5582, | |
| "eval_samples_per_second": 46.386, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9056, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.855062484741211, | |
| "eval_runtime": 21.5666, | |
| "eval_samples_per_second": 46.368, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8787, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.8537499904632568, | |
| "eval_runtime": 21.5601, | |
| "eval_samples_per_second": 46.382, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9587, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.8549375534057617, | |
| "eval_runtime": 21.5652, | |
| "eval_samples_per_second": 46.371, | |
| "eval_steps_per_second": 1.484, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1e-06, | |
| "loss": 2.048, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.8557499647140503, | |
| "eval_runtime": 21.5611, | |
| "eval_samples_per_second": 46.38, | |
| "eval_steps_per_second": 1.484, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8774, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.8544374704360962, | |
| "eval_runtime": 21.5818, | |
| "eval_samples_per_second": 46.335, | |
| "eval_steps_per_second": 1.483, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8685, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.8531874418258667, | |
| "eval_runtime": 21.541, | |
| "eval_samples_per_second": 46.423, | |
| "eval_steps_per_second": 1.486, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9003, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.8539999723434448, | |
| "eval_runtime": 21.5656, | |
| "eval_samples_per_second": 46.37, | |
| "eval_steps_per_second": 1.484, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8741, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.854812502861023, | |
| "eval_runtime": 21.5498, | |
| "eval_samples_per_second": 46.404, | |
| "eval_steps_per_second": 1.485, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9455, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.854312539100647, | |
| "eval_runtime": 21.548, | |
| "eval_samples_per_second": 46.408, | |
| "eval_steps_per_second": 1.485, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8652, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.8546874523162842, | |
| "eval_runtime": 21.6256, | |
| "eval_samples_per_second": 46.241, | |
| "eval_steps_per_second": 1.48, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8865, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.8538124561309814, | |
| "eval_runtime": 21.5739, | |
| "eval_samples_per_second": 46.352, | |
| "eval_steps_per_second": 1.483, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8254, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.8561874628067017, | |
| "eval_runtime": 21.5774, | |
| "eval_samples_per_second": 46.345, | |
| "eval_steps_per_second": 1.483, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1e-06, | |
| "loss": 1.931, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.8570624589920044, | |
| "eval_runtime": 21.5741, | |
| "eval_samples_per_second": 46.352, | |
| "eval_steps_per_second": 1.483, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9049, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.8558125495910645, | |
| "eval_runtime": 21.5808, | |
| "eval_samples_per_second": 46.337, | |
| "eval_steps_per_second": 1.483, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9455, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.8558125495910645, | |
| "eval_runtime": 21.5517, | |
| "eval_samples_per_second": 46.4, | |
| "eval_steps_per_second": 1.485, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8257, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.8536250591278076, | |
| "eval_runtime": 21.5808, | |
| "eval_samples_per_second": 46.337, | |
| "eval_steps_per_second": 1.483, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8485, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.8534375429153442, | |
| "eval_runtime": 21.5622, | |
| "eval_samples_per_second": 46.377, | |
| "eval_steps_per_second": 1.484, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8769, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.8535624742507935, | |
| "eval_runtime": 21.5883, | |
| "eval_samples_per_second": 46.321, | |
| "eval_steps_per_second": 1.482, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9807, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.8546249866485596, | |
| "eval_runtime": 21.5658, | |
| "eval_samples_per_second": 46.37, | |
| "eval_steps_per_second": 1.484, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9611, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8552500009536743, | |
| "eval_runtime": 21.5706, | |
| "eval_samples_per_second": 46.359, | |
| "eval_steps_per_second": 1.484, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8893, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.854312539100647, | |
| "eval_runtime": 21.5674, | |
| "eval_samples_per_second": 46.366, | |
| "eval_steps_per_second": 1.484, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1e-06, | |
| "loss": 1.9574, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.854562520980835, | |
| "eval_runtime": 21.5527, | |
| "eval_samples_per_second": 46.398, | |
| "eval_steps_per_second": 1.485, | |
| "step": 6180 | |
| } | |
| ], | |
| "max_steps": 6187, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.777315501421101e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |