[ { "loss": 1.9340267944335938, "grad_norm": 2.087617874145508, "learning_rate": 2.7272727272727273e-05, "epoch": 0.06793478260869565, "step": 25 }, { "loss": 1.434371337890625, "grad_norm": 9.7031831741333, "learning_rate": 4.963872832369942e-05, "epoch": 0.1358695652173913, "step": 50 }, { "loss": 0.7280014038085938, "grad_norm": 6.587019443511963, "learning_rate": 4.783236994219654e-05, "epoch": 0.20380434782608695, "step": 75 }, { "loss": 0.3517536926269531, "grad_norm": 8.999853134155273, "learning_rate": 4.602601156069364e-05, "epoch": 0.2717391304347826, "step": 100 }, { "loss": 0.21358098983764648, "grad_norm": 5.7537641525268555, "learning_rate": 4.421965317919075e-05, "epoch": 0.33967391304347827, "step": 125 }, { "loss": 0.13838543891906738, "grad_norm": 7.918935775756836, "learning_rate": 4.2413294797687863e-05, "epoch": 0.4076086956521739, "step": 150 }, { "loss": 0.13867578506469727, "grad_norm": 3.042539596557617, "learning_rate": 4.0606936416184974e-05, "epoch": 0.47554347826086957, "step": 175 }, { "loss": 0.09853402137756348, "grad_norm": 5.201169967651367, "learning_rate": 3.8800578034682085e-05, "epoch": 0.5434782608695652, "step": 200 }, { "loss": 0.08022554397583008, "grad_norm": 0.3783286213874817, "learning_rate": 3.699421965317919e-05, "epoch": 0.6114130434782609, "step": 225 }, { "loss": 0.07914683818817139, "grad_norm": 8.319209098815918, "learning_rate": 3.5187861271676306e-05, "epoch": 0.6793478260869565, "step": 250 }, { "loss": 0.053278565406799316, "grad_norm": 13.588916778564453, "learning_rate": 3.338150289017341e-05, "epoch": 0.7472826086956522, "step": 275 }, { "loss": 0.048708949089050296, "grad_norm": 1.73992121219635, "learning_rate": 3.157514450867052e-05, "epoch": 0.8152173913043478, "step": 300 }, { "loss": 0.0432391357421875, "grad_norm": 0.679373562335968, "learning_rate": 2.9768786127167632e-05, "epoch": 0.8831521739130435, "step": 325 }, { "loss": 0.04947152614593506, "grad_norm": 3.5385937690734863, "learning_rate": 2.7962427745664742e-05, "epoch": 0.9510869565217391, "step": 350 }, { "eval_loss": 1.042189598083496, "eval_accuracy": 0.8136904761904762, "eval_f1_macro": 0.7957429289704423, "eval_runtime": 27.9971, "eval_samples_per_second": 60.006, "eval_steps_per_second": 0.964, "epoch": 1.0, "step": 368 }, { "loss": 0.02682175636291504, "grad_norm": 0.1977403163909912, "learning_rate": 2.615606936416185e-05, "epoch": 1.0190217391304348, "step": 375 }, { "loss": 0.03454513549804687, "grad_norm": 14.26342487335205, "learning_rate": 2.434971098265896e-05, "epoch": 1.0869565217391304, "step": 400 }, { "loss": 0.018174402713775635, "grad_norm": 0.07522018998861313, "learning_rate": 2.254335260115607e-05, "epoch": 1.1548913043478262, "step": 425 }, { "loss": 0.015198019742965698, "grad_norm": 0.25197938084602356, "learning_rate": 2.073699421965318e-05, "epoch": 1.2228260869565217, "step": 450 }, { "loss": 0.010181854963302612, "grad_norm": 4.96293830871582, "learning_rate": 1.893063583815029e-05, "epoch": 1.2907608695652173, "step": 475 }, { "loss": 0.009627439975738526, "grad_norm": 15.551200866699219, "learning_rate": 1.71242774566474e-05, "epoch": 1.358695652173913, "step": 500 }, { "loss": 0.002052832543849945, "grad_norm": 0.02654379792511463, "learning_rate": 1.531791907514451e-05, "epoch": 1.4266304347826086, "step": 525 }, { "loss": 0.0028450772166252135, "grad_norm": 0.020132457837462425, "learning_rate": 1.351156069364162e-05, "epoch": 1.4945652173913042, "step": 550 }, { "loss": 0.012542355060577392, "grad_norm": 0.10431922972202301, "learning_rate": 1.1705202312138729e-05, "epoch": 1.5625, "step": 575 }, { "loss": 0.016759835481643677, "grad_norm": 0.017946448177099228, "learning_rate": 9.898843930635838e-06, "epoch": 1.6304347826086958, "step": 600 }, { "loss": 0.005359081029891968, "grad_norm": 0.37056228518486023, "learning_rate": 8.092485549132949e-06, "epoch": 1.6983695652173914, "step": 625 }, { "loss": 0.0013646985590457916, "grad_norm": 0.06766042113304138, "learning_rate": 6.2861271676300585e-06, "epoch": 1.766304347826087, "step": 650 }, { "loss": 0.004821262657642365, "grad_norm": 0.011222124099731445, "learning_rate": 4.4797687861271675e-06, "epoch": 1.8342391304347827, "step": 675 }, { "loss": 0.00359181672334671, "grad_norm": 0.3214636445045471, "learning_rate": 2.673410404624278e-06, "epoch": 1.9021739130434783, "step": 700 }, { "loss": 0.0043311807513237, "grad_norm": 0.028017066419124603, "learning_rate": 8.670520231213873e-07, "epoch": 1.9701086956521738, "step": 725 }, { "eval_loss": 0.85707688331604, "eval_accuracy": 0.8410714285714286, "eval_f1_macro": 0.8302318375441802, "eval_runtime": 28.7565, "eval_samples_per_second": 58.422, "eval_steps_per_second": 0.939, "epoch": 2.0, "step": 736 }, { "train_runtime": 2162.5059, "train_samples_per_second": 10.876, "train_steps_per_second": 0.34, "total_flos": 641075179540800.0, "train_loss": 0.18888104255007498, "epoch": 2.0, "step": 736 } ]