| { | |
| "best_metric": 1.6780412197113037, | |
| "best_model_checkpoint": "autotrain-dpdvy-2fgj4/checkpoint-125", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 14.090579986572266, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 3.0673, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 12.678583145141602, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 3.1665, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 13.062363624572754, | |
| "learning_rate": 1.153846153846154e-05, | |
| "loss": 3.0745, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 12.005086898803711, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 2.9223, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 12.953086853027344, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 3.1513, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 13.483661651611328, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 3.1013, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 13.102580070495605, | |
| "learning_rate": 2.6923076923076923e-05, | |
| "loss": 2.9917, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.6923076923076923e-05, | |
| "loss": 3.0553, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 12.6341552734375, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 3.1777, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 10.707420349121094, | |
| "learning_rate": 3.461538461538462e-05, | |
| "loss": 2.9388, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 10.78902530670166, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 3.0375, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 12.372330665588379, | |
| "learning_rate": 4.230769230769231e-05, | |
| "loss": 2.9353, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 11.65170955657959, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 2.8238, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 10.07817268371582, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1418, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 11.010019302368164, | |
| "learning_rate": 4.955357142857143e-05, | |
| "loss": 2.7185, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 11.038318634033203, | |
| "learning_rate": 4.910714285714286e-05, | |
| "loss": 2.9647, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 10.025190353393555, | |
| "learning_rate": 4.866071428571429e-05, | |
| "loss": 2.7857, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 10.354557991027832, | |
| "learning_rate": 4.8214285714285716e-05, | |
| "loss": 2.726, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 9.022831916809082, | |
| "learning_rate": 4.7767857142857144e-05, | |
| "loss": 2.7734, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 8.233414649963379, | |
| "learning_rate": 4.732142857142857e-05, | |
| "loss": 2.8013, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 9.093657493591309, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 2.7761, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 9.356589317321777, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 2.7867, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 7.915736198425293, | |
| "learning_rate": 4.598214285714286e-05, | |
| "loss": 2.5973, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 9.075019836425781, | |
| "learning_rate": 4.5535714285714286e-05, | |
| "loss": 2.7835, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 15.833548545837402, | |
| "learning_rate": 4.5089285714285714e-05, | |
| "loss": 2.8758, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.1326530612244898, | |
| "eval_f1_macro": 0.057275273745861985, | |
| "eval_f1_micro": 0.1326530612244898, | |
| "eval_f1_weighted": 0.08088347027122537, | |
| "eval_loss": 2.653775930404663, | |
| "eval_precision_macro": 0.044651835093011565, | |
| "eval_precision_micro": 0.1326530612244898, | |
| "eval_precision_weighted": 0.06580869527298099, | |
| "eval_recall_macro": 0.09901960784313725, | |
| "eval_recall_micro": 0.1326530612244898, | |
| "eval_recall_weighted": 0.1326530612244898, | |
| "eval_runtime": 0.1203, | |
| "eval_samples_per_second": 814.945, | |
| "eval_steps_per_second": 33.263, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 7.568680763244629, | |
| "learning_rate": 4.464285714285715e-05, | |
| "loss": 2.5985, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 9.416265487670898, | |
| "learning_rate": 4.419642857142857e-05, | |
| "loss": 2.3711, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 8.699418067932129, | |
| "learning_rate": 4.375e-05, | |
| "loss": 2.5099, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 9.023210525512695, | |
| "learning_rate": 4.3303571428571435e-05, | |
| "loss": 2.4655, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 9.81415843963623, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 2.4712, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 9.26953411102295, | |
| "learning_rate": 4.2410714285714285e-05, | |
| "loss": 2.432, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 9.773411750793457, | |
| "learning_rate": 4.196428571428572e-05, | |
| "loss": 2.38, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 8.679231643676758, | |
| "learning_rate": 4.151785714285715e-05, | |
| "loss": 2.3639, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 9.794059753417969, | |
| "learning_rate": 4.107142857142857e-05, | |
| "loss": 2.3523, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 10.422601699829102, | |
| "learning_rate": 4.0625000000000005e-05, | |
| "loss": 2.3657, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 8.450103759765625, | |
| "learning_rate": 4.017857142857143e-05, | |
| "loss": 2.3282, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 9.94312858581543, | |
| "learning_rate": 3.9732142857142855e-05, | |
| "loss": 2.36, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 10.141396522521973, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 2.4293, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 9.665178298950195, | |
| "learning_rate": 3.883928571428572e-05, | |
| "loss": 2.2062, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 11.53431510925293, | |
| "learning_rate": 3.839285714285715e-05, | |
| "loss": 2.4555, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 10.239005088806152, | |
| "learning_rate": 3.794642857142857e-05, | |
| "loss": 2.2474, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 11.729203224182129, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 2.4625, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 13.804224014282227, | |
| "learning_rate": 3.705357142857143e-05, | |
| "loss": 2.4599, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 10.596861839294434, | |
| "learning_rate": 3.6607142857142853e-05, | |
| "loss": 2.3025, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 10.572052955627441, | |
| "learning_rate": 3.616071428571429e-05, | |
| "loss": 2.3181, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 11.940258026123047, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 2.2404, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 11.33704662322998, | |
| "learning_rate": 3.5267857142857145e-05, | |
| "loss": 2.5559, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 12.002726554870605, | |
| "learning_rate": 3.4821428571428574e-05, | |
| "loss": 2.0579, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 11.418220520019531, | |
| "learning_rate": 3.4375e-05, | |
| "loss": 2.1282, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 17.700702667236328, | |
| "learning_rate": 3.392857142857143e-05, | |
| "loss": 2.4874, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.2857142857142857, | |
| "eval_f1_macro": 0.19056662291956414, | |
| "eval_f1_micro": 0.2857142857142857, | |
| "eval_f1_weighted": 0.22140982600166276, | |
| "eval_loss": 2.349097967147827, | |
| "eval_precision_macro": 0.21696943483275663, | |
| "eval_precision_micro": 0.2857142857142857, | |
| "eval_precision_weighted": 0.23142757102841136, | |
| "eval_recall_macro": 0.2230392156862745, | |
| "eval_recall_micro": 0.2857142857142857, | |
| "eval_recall_weighted": 0.2857142857142857, | |
| "eval_runtime": 0.116, | |
| "eval_samples_per_second": 845.135, | |
| "eval_steps_per_second": 34.495, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 10.884347915649414, | |
| "learning_rate": 3.348214285714286e-05, | |
| "loss": 2.0613, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 10.920637130737305, | |
| "learning_rate": 3.303571428571429e-05, | |
| "loss": 1.9789, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 10.85609245300293, | |
| "learning_rate": 3.2589285714285716e-05, | |
| "loss": 1.8808, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 10.412084579467773, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 1.9346, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 9.992473602294922, | |
| "learning_rate": 3.169642857142857e-05, | |
| "loss": 1.5298, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 12.011486053466797, | |
| "learning_rate": 3.125e-05, | |
| "loss": 2.1032, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.2800000000000002, | |
| "grad_norm": 12.152674674987793, | |
| "learning_rate": 3.080357142857143e-05, | |
| "loss": 2.0241, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 11.63778305053711, | |
| "learning_rate": 3.0357142857142857e-05, | |
| "loss": 2.1084, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 10.898219108581543, | |
| "learning_rate": 2.9910714285714286e-05, | |
| "loss": 1.8422, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 10.050783157348633, | |
| "learning_rate": 2.9464285714285718e-05, | |
| "loss": 1.6849, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 11.283549308776855, | |
| "learning_rate": 2.9017857142857146e-05, | |
| "loss": 1.6371, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 10.182291030883789, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.8368, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 10.567183494567871, | |
| "learning_rate": 2.8125000000000003e-05, | |
| "loss": 1.7345, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 13.132766723632812, | |
| "learning_rate": 2.767857142857143e-05, | |
| "loss": 1.9293, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 11.20378589630127, | |
| "learning_rate": 2.7232142857142856e-05, | |
| "loss": 1.9088, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 9.244080543518066, | |
| "learning_rate": 2.6785714285714288e-05, | |
| "loss": 1.8632, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "grad_norm": 14.100431442260742, | |
| "learning_rate": 2.6339285714285716e-05, | |
| "loss": 2.0808, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 10.50901985168457, | |
| "learning_rate": 2.5892857142857148e-05, | |
| "loss": 1.7468, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 10.505558013916016, | |
| "learning_rate": 2.544642857142857e-05, | |
| "loss": 1.7015, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 10.95505428314209, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.5555, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 12.247352600097656, | |
| "learning_rate": 2.455357142857143e-05, | |
| "loss": 1.8414, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 14.747278213500977, | |
| "learning_rate": 2.4107142857142858e-05, | |
| "loss": 1.7425, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "grad_norm": 12.440173149108887, | |
| "learning_rate": 2.3660714285714286e-05, | |
| "loss": 1.8499, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 9.904756546020508, | |
| "learning_rate": 2.3214285714285715e-05, | |
| "loss": 1.523, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 17.330537796020508, | |
| "learning_rate": 2.2767857142857143e-05, | |
| "loss": 1.8983, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.46938775510204084, | |
| "eval_f1_macro": 0.39296402771634975, | |
| "eval_f1_micro": 0.46938775510204084, | |
| "eval_f1_weighted": 0.42382422893969623, | |
| "eval_loss": 1.962062120437622, | |
| "eval_precision_macro": 0.4379509379509379, | |
| "eval_precision_micro": 0.46938775510204084, | |
| "eval_precision_weighted": 0.4513148982536737, | |
| "eval_recall_macro": 0.4205882352941176, | |
| "eval_recall_micro": 0.46938775510204084, | |
| "eval_recall_weighted": 0.46938775510204084, | |
| "eval_runtime": 0.1162, | |
| "eval_samples_per_second": 843.061, | |
| "eval_steps_per_second": 34.411, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "grad_norm": 11.348670959472656, | |
| "learning_rate": 2.2321428571428575e-05, | |
| "loss": 1.4333, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "grad_norm": 10.445756912231445, | |
| "learning_rate": 2.1875e-05, | |
| "loss": 1.6537, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "grad_norm": 10.392913818359375, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 1.383, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "grad_norm": 9.649495124816895, | |
| "learning_rate": 2.098214285714286e-05, | |
| "loss": 1.4573, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 9.06779670715332, | |
| "learning_rate": 2.0535714285714285e-05, | |
| "loss": 1.3847, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "grad_norm": 11.916837692260742, | |
| "learning_rate": 2.0089285714285717e-05, | |
| "loss": 1.4877, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2800000000000002, | |
| "grad_norm": 10.652131080627441, | |
| "learning_rate": 1.9642857142857145e-05, | |
| "loss": 1.614, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "grad_norm": 9.547950744628906, | |
| "learning_rate": 1.9196428571428573e-05, | |
| "loss": 1.4662, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "grad_norm": 11.057686805725098, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 1.3756, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "grad_norm": 11.566869735717773, | |
| "learning_rate": 1.8303571428571427e-05, | |
| "loss": 1.5774, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "grad_norm": 13.334156036376953, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 1.5652, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "grad_norm": 12.016660690307617, | |
| "learning_rate": 1.7410714285714287e-05, | |
| "loss": 1.5098, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "grad_norm": 9.972099304199219, | |
| "learning_rate": 1.6964285714285715e-05, | |
| "loss": 1.3357, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "grad_norm": 10.04750919342041, | |
| "learning_rate": 1.6517857142857144e-05, | |
| "loss": 1.2745, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "grad_norm": 10.588435173034668, | |
| "learning_rate": 1.6071428571428572e-05, | |
| "loss": 1.0839, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "grad_norm": 10.37175178527832, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 1.1205, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "grad_norm": 10.8080415725708, | |
| "learning_rate": 1.5178571428571429e-05, | |
| "loss": 1.4232, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.7199999999999998, | |
| "grad_norm": 9.315281867980957, | |
| "learning_rate": 1.4732142857142859e-05, | |
| "loss": 1.175, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "grad_norm": 10.718316078186035, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.3465, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "grad_norm": 10.400609970092773, | |
| "learning_rate": 1.3839285714285715e-05, | |
| "loss": 1.3037, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "grad_norm": 10.373046875, | |
| "learning_rate": 1.3392857142857144e-05, | |
| "loss": 1.3794, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "grad_norm": 12.27895736694336, | |
| "learning_rate": 1.2946428571428574e-05, | |
| "loss": 1.5354, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "grad_norm": 9.416078567504883, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.1127, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "grad_norm": 10.97613525390625, | |
| "learning_rate": 1.2053571428571429e-05, | |
| "loss": 1.208, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 19.747652053833008, | |
| "learning_rate": 1.1607142857142857e-05, | |
| "loss": 1.3328, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5612244897959183, | |
| "eval_f1_macro": 0.4927701383583736, | |
| "eval_f1_micro": 0.5612244897959183, | |
| "eval_f1_weighted": 0.5213652560591336, | |
| "eval_loss": 1.7371511459350586, | |
| "eval_precision_macro": 0.5056022408963585, | |
| "eval_precision_micro": 0.5612244897959183, | |
| "eval_precision_weighted": 0.5240767735665695, | |
| "eval_recall_macro": 0.5225490196078431, | |
| "eval_recall_micro": 0.5612244897959183, | |
| "eval_recall_weighted": 0.5612244897959183, | |
| "eval_runtime": 0.1152, | |
| "eval_samples_per_second": 850.765, | |
| "eval_steps_per_second": 34.725, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "grad_norm": 9.819528579711914, | |
| "learning_rate": 1.1160714285714287e-05, | |
| "loss": 1.2081, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "grad_norm": 9.64730453491211, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 1.1187, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "grad_norm": 10.466198921203613, | |
| "learning_rate": 1.0267857142857142e-05, | |
| "loss": 1.3042, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "grad_norm": 10.586526870727539, | |
| "learning_rate": 9.821428571428573e-06, | |
| "loss": 1.2627, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "grad_norm": 11.021370887756348, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 1.369, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "grad_norm": 9.286604881286621, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 1.0915, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "grad_norm": 10.715047836303711, | |
| "learning_rate": 8.482142857142858e-06, | |
| "loss": 1.28, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "grad_norm": 9.866848945617676, | |
| "learning_rate": 8.035714285714286e-06, | |
| "loss": 1.0737, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "grad_norm": 10.503690719604492, | |
| "learning_rate": 7.589285714285714e-06, | |
| "loss": 1.1515, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "grad_norm": 9.61823844909668, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 1.0827, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "grad_norm": 10.555536270141602, | |
| "learning_rate": 6.696428571428572e-06, | |
| "loss": 1.1674, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "grad_norm": 9.302597999572754, | |
| "learning_rate": 6.25e-06, | |
| "loss": 1.0401, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "grad_norm": 11.41283130645752, | |
| "learning_rate": 5.803571428571429e-06, | |
| "loss": 1.0568, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.5600000000000005, | |
| "grad_norm": 8.852797508239746, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 1.043, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "grad_norm": 10.713024139404297, | |
| "learning_rate": 4.910714285714286e-06, | |
| "loss": 1.2006, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "grad_norm": 11.334012031555176, | |
| "learning_rate": 4.464285714285715e-06, | |
| "loss": 1.0098, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "grad_norm": 9.988310813903809, | |
| "learning_rate": 4.017857142857143e-06, | |
| "loss": 1.1678, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "grad_norm": 11.369806289672852, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 1.1006, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "grad_norm": 8.683494567871094, | |
| "learning_rate": 3.125e-06, | |
| "loss": 0.9208, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 11.041170120239258, | |
| "learning_rate": 2.6785714285714285e-06, | |
| "loss": 1.1191, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "grad_norm": 11.118208885192871, | |
| "learning_rate": 2.2321428571428573e-06, | |
| "loss": 1.2661, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "grad_norm": 9.99183177947998, | |
| "learning_rate": 1.7857142857142857e-06, | |
| "loss": 1.0169, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "grad_norm": 8.416065216064453, | |
| "learning_rate": 1.3392857142857143e-06, | |
| "loss": 0.9999, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "grad_norm": 10.9324312210083, | |
| "learning_rate": 8.928571428571428e-07, | |
| "loss": 1.1752, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 17.929676055908203, | |
| "learning_rate": 4.464285714285714e-07, | |
| "loss": 1.3872, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5510204081632653, | |
| "eval_f1_macro": 0.48698637963343844, | |
| "eval_f1_micro": 0.5510204081632653, | |
| "eval_f1_weighted": 0.5140266479552194, | |
| "eval_loss": 1.6780412197113037, | |
| "eval_precision_macro": 0.49788642729819194, | |
| "eval_precision_micro": 0.5510204081632653, | |
| "eval_precision_weighted": 0.5202149041434755, | |
| "eval_recall_macro": 0.5220588235294118, | |
| "eval_recall_micro": 0.5510204081632653, | |
| "eval_recall_weighted": 0.5510204081632653, | |
| "eval_runtime": 0.1179, | |
| "eval_samples_per_second": 831.21, | |
| "eval_steps_per_second": 33.927, | |
| "step": 125 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 64763066415360.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |