| { | |
| "best_metric": 0.9092560719066743, | |
| "best_model_checkpoint": "./output_1/checkpoint-1408", | |
| "epoch": 29.53846153846154, | |
| "eval_steps": 64, | |
| "global_step": 1920, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.753846153846154e-06, | |
| "loss": 0.5876, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_f1": 0.8264750469953308, | |
| "eval_loss": 0.426924467086792, | |
| "eval_precision": 0.8384115884115884, | |
| "eval_recall": 0.8222047843249156, | |
| "eval_runtime": 1.7863, | |
| "eval_samples_per_second": 163.47, | |
| "eval_steps_per_second": 5.598, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 9.50769230769231e-06, | |
| "loss": 0.331, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_f1": 0.8797480620155038, | |
| "eval_loss": 0.3329169452190399, | |
| "eval_precision": 0.8921407595440745, | |
| "eval_recall": 0.8746849289009369, | |
| "eval_runtime": 1.7913, | |
| "eval_samples_per_second": 163.008, | |
| "eval_steps_per_second": 5.582, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 9.261538461538461e-06, | |
| "loss": 0.2585, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_f1": 0.8914823472996463, | |
| "eval_loss": 0.31825584173202515, | |
| "eval_precision": 0.8960271317829458, | |
| "eval_recall": 0.8887382888666951, | |
| "eval_runtime": 1.7885, | |
| "eval_samples_per_second": 163.262, | |
| "eval_steps_per_second": 5.591, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 9.015384615384616e-06, | |
| "loss": 0.2016, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_f1": 0.8988811005098933, | |
| "eval_loss": 0.3036338686943054, | |
| "eval_precision": 0.9010176651305684, | |
| "eval_recall": 0.8972987111808627, | |
| "eval_runtime": 1.7803, | |
| "eval_samples_per_second": 164.015, | |
| "eval_steps_per_second": 5.617, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 8.76923076923077e-06, | |
| "loss": 0.1733, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_f1": 0.8919073833036791, | |
| "eval_loss": 0.31887006759643555, | |
| "eval_precision": 0.8940092165898618, | |
| "eval_recall": 0.890355257526038, | |
| "eval_runtime": 1.7908, | |
| "eval_samples_per_second": 163.059, | |
| "eval_steps_per_second": 5.584, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 8.523076923076923e-06, | |
| "loss": 0.1627, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_f1": 0.8975599724181316, | |
| "eval_loss": 0.3417821526527405, | |
| "eval_precision": 0.9093253968253968, | |
| "eval_recall": 0.8924478052028344, | |
| "eval_runtime": 1.7807, | |
| "eval_samples_per_second": 163.98, | |
| "eval_steps_per_second": 5.616, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 8.276923076923078e-06, | |
| "loss": 0.1268, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "eval_f1": 0.8907594463150018, | |
| "eval_loss": 0.33714038133621216, | |
| "eval_precision": 0.9003055391287207, | |
| "eval_recall": 0.8863128358776811, | |
| "eval_runtime": 1.7763, | |
| "eval_samples_per_second": 164.386, | |
| "eval_steps_per_second": 5.63, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 8.03076923076923e-06, | |
| "loss": 0.1059, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "eval_f1": 0.8910119800132443, | |
| "eval_loss": 0.36000651121139526, | |
| "eval_precision": 0.8987068965517242, | |
| "eval_recall": 0.8871213202073525, | |
| "eval_runtime": 1.809, | |
| "eval_samples_per_second": 161.417, | |
| "eval_steps_per_second": 5.528, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 7.784615384615385e-06, | |
| "loss": 0.1036, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_f1": 0.9018817204301075, | |
| "eval_loss": 0.3717869520187378, | |
| "eval_precision": 0.9072715791518919, | |
| "eval_recall": 0.8987492271840967, | |
| "eval_runtime": 1.7837, | |
| "eval_samples_per_second": 163.704, | |
| "eval_steps_per_second": 5.606, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 7.538461538461539e-06, | |
| "loss": 0.0901, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "eval_f1": 0.8978072239720984, | |
| "eval_loss": 0.3917124569416046, | |
| "eval_precision": 0.9075004928050463, | |
| "eval_recall": 0.8932562895325058, | |
| "eval_runtime": 1.816, | |
| "eval_samples_per_second": 160.796, | |
| "eval_steps_per_second": 5.507, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 7.292307692307693e-06, | |
| "loss": 0.0859, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "eval_f1": 0.8944069431051109, | |
| "eval_loss": 0.3997272551059723, | |
| "eval_precision": 0.9030704986489806, | |
| "eval_recall": 0.8901888048699291, | |
| "eval_runtime": 1.7905, | |
| "eval_samples_per_second": 163.086, | |
| "eval_steps_per_second": 5.585, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 7.046153846153847e-06, | |
| "loss": 0.0559, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "eval_f1": 0.9027916488324536, | |
| "eval_loss": 0.4531518518924713, | |
| "eval_precision": 0.9027916488324536, | |
| "eval_recall": 0.9027916488324536, | |
| "eval_runtime": 1.7898, | |
| "eval_samples_per_second": 163.144, | |
| "eval_steps_per_second": 5.587, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 0.0593, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "eval_f1": 0.8808563748079878, | |
| "eval_loss": 0.47470441460609436, | |
| "eval_precision": 0.8859960169038714, | |
| "eval_recall": 0.8779188662196225, | |
| "eval_runtime": 1.7809, | |
| "eval_samples_per_second": 163.966, | |
| "eval_steps_per_second": 5.615, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "learning_rate": 6.553846153846154e-06, | |
| "loss": 0.0448, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "eval_f1": 0.8958481951776287, | |
| "eval_loss": 0.4653804302215576, | |
| "eval_precision": 0.8958481951776287, | |
| "eval_recall": 0.8958481951776287, | |
| "eval_runtime": 1.7817, | |
| "eval_samples_per_second": 163.887, | |
| "eval_steps_per_second": 5.613, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 14.77, | |
| "learning_rate": 6.307692307692308e-06, | |
| "loss": 0.035, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 14.77, | |
| "eval_f1": 0.9024576473395372, | |
| "eval_loss": 0.4710945188999176, | |
| "eval_precision": 0.9040958083832336, | |
| "eval_recall": 0.9011746801731108, | |
| "eval_runtime": 1.8119, | |
| "eval_samples_per_second": 161.155, | |
| "eval_steps_per_second": 5.519, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 6.061538461538462e-06, | |
| "loss": 0.0372, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "eval_f1": 0.8839804948528084, | |
| "eval_loss": 0.5761662125587463, | |
| "eval_precision": 0.8915556426332288, | |
| "eval_recall": 0.8801778665525277, | |
| "eval_runtime": 1.7874, | |
| "eval_samples_per_second": 163.369, | |
| "eval_steps_per_second": 5.595, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 16.74, | |
| "learning_rate": 5.815384615384616e-06, | |
| "loss": 0.0341, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 16.74, | |
| "eval_f1": 0.9020838323353293, | |
| "eval_loss": 0.5446054339408875, | |
| "eval_precision": 0.9060461070030448, | |
| "eval_recall": 0.8995577115137681, | |
| "eval_runtime": 1.7858, | |
| "eval_samples_per_second": 163.512, | |
| "eval_steps_per_second": 5.6, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 5.56923076923077e-06, | |
| "loss": 0.0321, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "eval_f1": 0.9058548177161077, | |
| "eval_loss": 0.5152109265327454, | |
| "eval_precision": 0.908026113671275, | |
| "eval_recall": 0.9042421648356874, | |
| "eval_runtime": 1.7852, | |
| "eval_samples_per_second": 163.569, | |
| "eval_steps_per_second": 5.602, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 5.323076923076923e-06, | |
| "loss": 0.0171, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "eval_f1": 0.887100671789667, | |
| "eval_loss": 0.6121218204498291, | |
| "eval_precision": 0.897562663766253, | |
| "eval_recall": 0.882436866885433, | |
| "eval_runtime": 1.7977, | |
| "eval_samples_per_second": 162.431, | |
| "eval_steps_per_second": 5.563, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 19.69, | |
| "learning_rate": 5.076923076923077e-06, | |
| "loss": 0.0261, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 19.69, | |
| "eval_f1": 0.9024576473395372, | |
| "eval_loss": 0.5516932010650635, | |
| "eval_precision": 0.9040958083832336, | |
| "eval_recall": 0.9011746801731108, | |
| "eval_runtime": 1.7934, | |
| "eval_samples_per_second": 162.821, | |
| "eval_steps_per_second": 5.576, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 20.68, | |
| "learning_rate": 4.830769230769231e-06, | |
| "loss": 0.0153, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 20.68, | |
| "eval_f1": 0.89848348618354, | |
| "eval_loss": 0.5832306146621704, | |
| "eval_precision": 0.9031007751937985, | |
| "eval_recall": 0.89568174252152, | |
| "eval_runtime": 1.7807, | |
| "eval_samples_per_second": 163.978, | |
| "eval_steps_per_second": 5.616, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 21.66, | |
| "learning_rate": 4.5846153846153855e-06, | |
| "loss": 0.0183, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 21.66, | |
| "eval_f1": 0.9092560719066743, | |
| "eval_loss": 0.5685573220252991, | |
| "eval_precision": 0.9120123153894261, | |
| "eval_recall": 0.9073096494982642, | |
| "eval_runtime": 1.8067, | |
| "eval_samples_per_second": 161.617, | |
| "eval_steps_per_second": 5.535, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 22.65, | |
| "learning_rate": 4.338461538461539e-06, | |
| "loss": 0.0098, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 22.65, | |
| "eval_f1": 0.9058548177161077, | |
| "eval_loss": 0.5791997909545898, | |
| "eval_precision": 0.908026113671275, | |
| "eval_recall": 0.9042421648356874, | |
| "eval_runtime": 1.7948, | |
| "eval_samples_per_second": 162.694, | |
| "eval_steps_per_second": 5.572, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 23.63, | |
| "learning_rate": 4.0923076923076925e-06, | |
| "loss": 0.0216, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 23.63, | |
| "eval_f1": 0.8948732718894008, | |
| "eval_loss": 0.6078387498855591, | |
| "eval_precision": 0.9001797250692184, | |
| "eval_recall": 0.8918057735292719, | |
| "eval_runtime": 1.7897, | |
| "eval_samples_per_second": 163.158, | |
| "eval_steps_per_second": 5.588, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.0076, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "eval_f1": 0.8950898203592814, | |
| "eval_loss": 0.6126357913017273, | |
| "eval_precision": 0.898989898989899, | |
| "eval_recall": 0.8926142578589432, | |
| "eval_runtime": 1.7831, | |
| "eval_samples_per_second": 163.755, | |
| "eval_steps_per_second": 5.608, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 0.0073, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "eval_f1": 0.9058548177161077, | |
| "eval_loss": 0.6077719926834106, | |
| "eval_precision": 0.908026113671275, | |
| "eval_recall": 0.9042421648356874, | |
| "eval_runtime": 1.7913, | |
| "eval_samples_per_second": 163.011, | |
| "eval_steps_per_second": 5.583, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 26.58, | |
| "learning_rate": 3.353846153846154e-06, | |
| "loss": 0.0257, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 26.58, | |
| "eval_f1": 0.9020838323353293, | |
| "eval_loss": 0.6265017986297607, | |
| "eval_precision": 0.9060461070030448, | |
| "eval_recall": 0.8995577115137681, | |
| "eval_runtime": 1.8318, | |
| "eval_samples_per_second": 159.409, | |
| "eval_steps_per_second": 5.459, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 27.57, | |
| "learning_rate": 3.1076923076923076e-06, | |
| "loss": 0.0047, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 27.57, | |
| "eval_f1": 0.891252898280854, | |
| "eval_loss": 0.6706699728965759, | |
| "eval_precision": 0.8972822910578608, | |
| "eval_recall": 0.8879298045370239, | |
| "eval_runtime": 1.7836, | |
| "eval_samples_per_second": 163.716, | |
| "eval_steps_per_second": 5.607, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 28.55, | |
| "learning_rate": 2.8615384615384615e-06, | |
| "loss": 0.0063, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 28.55, | |
| "eval_f1": 0.89848348618354, | |
| "eval_loss": 0.6434349417686462, | |
| "eval_precision": 0.9031007751937985, | |
| "eval_recall": 0.89568174252152, | |
| "eval_runtime": 1.8097, | |
| "eval_samples_per_second": 161.353, | |
| "eval_steps_per_second": 5.526, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 29.54, | |
| "learning_rate": 2.615384615384616e-06, | |
| "loss": 0.0045, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 29.54, | |
| "eval_f1": 0.9092560719066743, | |
| "eval_loss": 0.6284749507904053, | |
| "eval_precision": 0.9120123153894261, | |
| "eval_recall": 0.9073096494982642, | |
| "eval_runtime": 1.7895, | |
| "eval_samples_per_second": 163.173, | |
| "eval_steps_per_second": 5.588, | |
| "step": 1920 | |
| } | |
| ], | |
| "logging_steps": 64, | |
| "max_steps": 2600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 40, | |
| "save_steps": 64, | |
| "total_flos": 2249673523312320.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |