| [ |
| { |
| "loss": 1.0146, |
| "grad_norm": 8.066655158996582, |
| "learning_rate": 1.88259587020649e-05, |
| "epoch": 0.5908419497784343, |
| "step": 200 |
| }, |
| { |
| "eval_loss": 0.6535171866416931, |
| "eval_accuracy": 0.7455686853766618, |
| "eval_precision": 0.7438951273666146, |
| "eval_recall": 0.7635212365766714, |
| "eval_f1": 0.7480569004890223, |
| "eval_runtime": 4.1402, |
| "eval_samples_per_second": 654.079, |
| "eval_steps_per_second": 10.386, |
| "epoch": 1.0, |
| "step": 339 |
| }, |
| { |
| "loss": 0.7183, |
| "grad_norm": 8.033791542053223, |
| "learning_rate": 1.7646017699115045e-05, |
| "epoch": 1.1802067946824224, |
| "step": 400 |
| }, |
| { |
| "loss": 0.5841, |
| "grad_norm": 7.553318500518799, |
| "learning_rate": 1.6466076696165194e-05, |
| "epoch": 1.7710487444608567, |
| "step": 600 |
| }, |
| { |
| "eval_loss": 0.5103763341903687, |
| "eval_accuracy": 0.7961595273264401, |
| "eval_precision": 0.7954926941267795, |
| "eval_recall": 0.8145635466866111, |
| "eval_f1": 0.8004633351993021, |
| "eval_runtime": 4.2164, |
| "eval_samples_per_second": 642.252, |
| "eval_steps_per_second": 10.198, |
| "epoch": 2.0, |
| "step": 678 |
| }, |
| { |
| "loss": 0.4924, |
| "grad_norm": 11.982539176940918, |
| "learning_rate": 1.528613569321534e-05, |
| "epoch": 2.360413589364845, |
| "step": 800 |
| }, |
| { |
| "loss": 0.4396, |
| "grad_norm": 10.420658111572266, |
| "learning_rate": 1.410619469026549e-05, |
| "epoch": 2.951255539143279, |
| "step": 1000 |
| }, |
| { |
| "eval_loss": 0.43686869740486145, |
| "eval_accuracy": 0.8319793205317577, |
| "eval_precision": 0.8322550154197035, |
| "eval_recall": 0.8486163782995474, |
| "eval_f1": 0.839237623407653, |
| "eval_runtime": 4.2136, |
| "eval_samples_per_second": 642.679, |
| "eval_steps_per_second": 10.205, |
| "epoch": 3.0, |
| "step": 1017 |
| }, |
| { |
| "loss": 0.3559, |
| "grad_norm": 13.99537181854248, |
| "learning_rate": 1.2926253687315635e-05, |
| "epoch": 3.5406203840472674, |
| "step": 1200 |
| }, |
| { |
| "eval_loss": 0.40422186255455017, |
| "eval_accuracy": 0.8545051698670606, |
| "eval_precision": 0.8628044809228071, |
| "eval_recall": 0.8634142412515072, |
| "eval_f1": 0.8630242724646225, |
| "eval_runtime": 4.206, |
| "eval_samples_per_second": 643.836, |
| "eval_steps_per_second": 10.223, |
| "epoch": 4.0, |
| "step": 1356 |
| }, |
| { |
| "loss": 0.3394, |
| "grad_norm": 14.122424125671387, |
| "learning_rate": 1.1746312684365783e-05, |
| "epoch": 4.129985228951256, |
| "step": 1400 |
| }, |
| { |
| "loss": 0.2889, |
| "grad_norm": 10.866605758666992, |
| "learning_rate": 1.056637168141593e-05, |
| "epoch": 4.72082717872969, |
| "step": 1600 |
| }, |
| { |
| "eval_loss": 0.4265260100364685, |
| "eval_accuracy": 0.8441654357459379, |
| "eval_precision": 0.8441186724361562, |
| "eval_recall": 0.8647582579749038, |
| "eval_f1": 0.8517152790349632, |
| "eval_runtime": 4.1986, |
| "eval_samples_per_second": 644.981, |
| "eval_steps_per_second": 10.242, |
| "epoch": 5.0, |
| "step": 1695 |
| }, |
| { |
| "loss": 0.2514, |
| "grad_norm": 5.72359561920166, |
| "learning_rate": 9.386430678466077e-06, |
| "epoch": 5.310192023633678, |
| "step": 1800 |
| }, |
| { |
| "loss": 0.2464, |
| "grad_norm": 9.600533485412598, |
| "learning_rate": 8.206489675516224e-06, |
| "epoch": 5.901033973412112, |
| "step": 2000 |
| }, |
| { |
| "eval_loss": 0.389065682888031, |
| "eval_accuracy": 0.8626292466765141, |
| "eval_precision": 0.8652231358736173, |
| "eval_recall": 0.8783380417030334, |
| "eval_f1": 0.8702889928876043, |
| "eval_runtime": 4.2127, |
| "eval_samples_per_second": 642.817, |
| "eval_steps_per_second": 10.207, |
| "epoch": 6.0, |
| "step": 2034 |
| }, |
| { |
| "loss": 0.211, |
| "grad_norm": 17.138826370239258, |
| "learning_rate": 7.026548672566372e-06, |
| "epoch": 6.4903988183161, |
| "step": 2200 |
| }, |
| { |
| "eval_loss": 0.39963972568511963, |
| "eval_accuracy": 0.8674298375184638, |
| "eval_precision": 0.8702205064128979, |
| "eval_recall": 0.8830179653015887, |
| "eval_f1": 0.8754706796586051, |
| "eval_runtime": 4.256, |
| "eval_samples_per_second": 636.271, |
| "eval_steps_per_second": 10.103, |
| "epoch": 7.0, |
| "step": 2373 |
| }, |
| { |
| "loss": 0.1979, |
| "grad_norm": 6.464990615844727, |
| "learning_rate": 5.8466076696165195e-06, |
| "epoch": 7.079763663220088, |
| "step": 2400 |
| }, |
| { |
| "loss": 0.1781, |
| "grad_norm": 9.935137748718262, |
| "learning_rate": 4.666666666666667e-06, |
| "epoch": 7.670605612998523, |
| "step": 2600 |
| }, |
| { |
| "eval_loss": 0.4202274978160858, |
| "eval_accuracy": 0.8707533234859675, |
| "eval_precision": 0.8721032179023319, |
| "eval_recall": 0.8847283016982879, |
| "eval_f1": 0.8775633088032715, |
| "eval_runtime": 4.21, |
| "eval_samples_per_second": 643.232, |
| "eval_steps_per_second": 10.214, |
| "epoch": 8.0, |
| "step": 2712 |
| }, |
| { |
| "loss": 0.1651, |
| "grad_norm": 9.050063133239746, |
| "learning_rate": 3.4867256637168144e-06, |
| "epoch": 8.259970457902511, |
| "step": 2800 |
| }, |
| { |
| "loss": 0.1541, |
| "grad_norm": 11.100234985351562, |
| "learning_rate": 2.306784660766962e-06, |
| "epoch": 8.850812407680944, |
| "step": 3000 |
| }, |
| { |
| "eval_loss": 0.4208575487136841, |
| "eval_accuracy": 0.869645494830133, |
| "eval_precision": 0.8718772232277948, |
| "eval_recall": 0.8837444901736863, |
| "eval_f1": 0.877165841562759, |
| "eval_runtime": 4.2122, |
| "eval_samples_per_second": 642.888, |
| "eval_steps_per_second": 10.208, |
| "epoch": 9.0, |
| "step": 3051 |
| }, |
| { |
| "loss": 0.1452, |
| "grad_norm": 9.718356132507324, |
| "learning_rate": 1.1268436578171092e-06, |
| "epoch": 9.440177252584933, |
| "step": 3200 |
| }, |
| { |
| "eval_loss": 0.4245568513870239, |
| "eval_accuracy": 0.8670605612998523, |
| "eval_precision": 0.8694463928962631, |
| "eval_recall": 0.8819628066777028, |
| "eval_f1": 0.8750774553354714, |
| "eval_runtime": 4.2399, |
| "eval_samples_per_second": 638.697, |
| "eval_steps_per_second": 10.142, |
| "epoch": 10.0, |
| "step": 3390 |
| }, |
| { |
| "train_runtime": 1402.4702, |
| "train_samples_per_second": 154.442, |
| "train_steps_per_second": 2.417, |
| "total_flos": 1.42477194921984e+16, |
| "train_loss": 0.34887106960150344, |
| "epoch": 10.0, |
| "step": 3390 |
| } |
| ] |
