| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 52560, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9809741248097414e-05, | |
| "loss": 0.6459, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9619482496194826e-05, | |
| "loss": 0.4121, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9429223744292238e-05, | |
| "loss": 0.3439, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.923896499238965e-05, | |
| "loss": 0.3113, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9048706240487066e-05, | |
| "loss": 0.2776, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.8858447488584478e-05, | |
| "loss": 0.2665, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.866818873668189e-05, | |
| "loss": 0.2538, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.8477929984779303e-05, | |
| "loss": 0.2583, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.8287671232876715e-05, | |
| "loss": 0.2515, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.8097412480974127e-05, | |
| "loss": 0.218, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.790715372907154e-05, | |
| "loss": 0.2041, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.771689497716895e-05, | |
| "loss": 0.1916, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.7526636225266364e-05, | |
| "loss": 0.1879, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.7336377473363776e-05, | |
| "loss": 0.2072, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.7146118721461188e-05, | |
| "loss": 0.2066, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.69558599695586e-05, | |
| "loss": 0.2069, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.6765601217656012e-05, | |
| "loss": 0.1913, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.6575342465753425e-05, | |
| "loss": 0.1942, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.6385083713850837e-05, | |
| "loss": 0.171, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.619482496194825e-05, | |
| "loss": 0.1609, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.6004566210045664e-05, | |
| "loss": 0.1736, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.5814307458143077e-05, | |
| "loss": 0.1696, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.562404870624049e-05, | |
| "loss": 0.1559, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.54337899543379e-05, | |
| "loss": 0.1577, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.5243531202435313e-05, | |
| "loss": 0.151, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.5053272450532725e-05, | |
| "loss": 0.147, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.4863013698630138e-05, | |
| "loss": 0.145, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.467275494672755e-05, | |
| "loss": 0.163, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.4482496194824962e-05, | |
| "loss": 0.162, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4292237442922376e-05, | |
| "loss": 0.1484, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.4101978691019788e-05, | |
| "loss": 0.1385, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.39117199391172e-05, | |
| "loss": 0.1436, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3721461187214612e-05, | |
| "loss": 0.1292, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.3531202435312025e-05, | |
| "loss": 0.1482, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3340943683409437e-05, | |
| "loss": 0.1274, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9567564969397891, | |
| "eval_f1": 0.8423064061529643, | |
| "eval_loss": 0.14508096873760223, | |
| "eval_precision": 0.8260095568256348, | |
| "eval_recall": 0.8592592592592593, | |
| "eval_runtime": 35.0181, | |
| "eval_samples_per_second": 250.156, | |
| "eval_steps_per_second": 62.539, | |
| "step": 17520 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.3150684931506849e-05, | |
| "loss": 0.1016, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.2960426179604261e-05, | |
| "loss": 0.0952, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.2770167427701677e-05, | |
| "loss": 0.0896, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.2579908675799089e-05, | |
| "loss": 0.1053, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.2389649923896501e-05, | |
| "loss": 0.0977, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.2199391171993913e-05, | |
| "loss": 0.0992, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.2009132420091326e-05, | |
| "loss": 0.0977, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.1818873668188738e-05, | |
| "loss": 0.0809, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.162861491628615e-05, | |
| "loss": 0.09, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.1438356164383562e-05, | |
| "loss": 0.0993, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.1248097412480976e-05, | |
| "loss": 0.0991, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.1057838660578388e-05, | |
| "loss": 0.0964, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.08675799086758e-05, | |
| "loss": 0.0836, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.0677321156773213e-05, | |
| "loss": 0.0969, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.0487062404870625e-05, | |
| "loss": 0.0819, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.0296803652968037e-05, | |
| "loss": 0.1056, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.010654490106545e-05, | |
| "loss": 0.0796, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 9.916286149162863e-06, | |
| "loss": 0.077, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 9.726027397260275e-06, | |
| "loss": 0.0737, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.535768645357688e-06, | |
| "loss": 0.0968, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.3455098934551e-06, | |
| "loss": 0.0774, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.155251141552512e-06, | |
| "loss": 0.0734, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.964992389649924e-06, | |
| "loss": 0.0792, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.774733637747336e-06, | |
| "loss": 0.0771, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.584474885844748e-06, | |
| "loss": 0.076, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.394216133942162e-06, | |
| "loss": 0.0794, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.203957382039575e-06, | |
| "loss": 0.0842, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.013698630136987e-06, | |
| "loss": 0.0831, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.823439878234399e-06, | |
| "loss": 0.0804, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 7.633181126331813e-06, | |
| "loss": 0.081, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 7.442922374429224e-06, | |
| "loss": 0.0731, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 7.252663622526636e-06, | |
| "loss": 0.0615, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.0624048706240486e-06, | |
| "loss": 0.0823, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.8721461187214625e-06, | |
| "loss": 0.0613, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.681887366818875e-06, | |
| "loss": 0.0777, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9699693444846775, | |
| "eval_f1": 0.8876556316957822, | |
| "eval_loss": 0.11980047076940536, | |
| "eval_precision": 0.8790862167845537, | |
| "eval_recall": 0.8963937621832359, | |
| "eval_runtime": 35.3315, | |
| "eval_samples_per_second": 247.938, | |
| "eval_steps_per_second": 61.984, | |
| "step": 35040 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 6.491628614916287e-06, | |
| "loss": 0.0397, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 6.301369863013699e-06, | |
| "loss": 0.0581, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.111111111111112e-06, | |
| "loss": 0.0481, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 5.920852359208524e-06, | |
| "loss": 0.042, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 5.7305936073059365e-06, | |
| "loss": 0.0472, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 5.540334855403349e-06, | |
| "loss": 0.046, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 5.350076103500762e-06, | |
| "loss": 0.042, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 5.159817351598174e-06, | |
| "loss": 0.0428, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 4.969558599695586e-06, | |
| "loss": 0.0458, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 4.779299847792998e-06, | |
| "loss": 0.0371, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.589041095890411e-06, | |
| "loss": 0.0582, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.3987823439878235e-06, | |
| "loss": 0.04, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 4.2085235920852366e-06, | |
| "loss": 0.0559, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.018264840182649e-06, | |
| "loss": 0.0442, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.828006088280061e-06, | |
| "loss": 0.0482, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 3.6377473363774736e-06, | |
| "loss": 0.0434, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.447488584474886e-06, | |
| "loss": 0.0457, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.2572298325722984e-06, | |
| "loss": 0.0404, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 3.066971080669711e-06, | |
| "loss": 0.0521, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.876712328767123e-06, | |
| "loss": 0.0605, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2.6864535768645362e-06, | |
| "loss": 0.05, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2.4961948249619484e-06, | |
| "loss": 0.0471, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 2.3059360730593606e-06, | |
| "loss": 0.0403, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.1156773211567732e-06, | |
| "loss": 0.0533, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.925418569254186e-06, | |
| "loss": 0.04, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.7351598173515982e-06, | |
| "loss": 0.0435, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.5449010654490107e-06, | |
| "loss": 0.0417, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.3546423135464233e-06, | |
| "loss": 0.036, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.1643835616438357e-06, | |
| "loss": 0.0364, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 9.74124809741248e-07, | |
| "loss": 0.0339, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 7.838660578386606e-07, | |
| "loss": 0.0291, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 5.936073059360731e-07, | |
| "loss": 0.0351, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 4.0334855403348556e-07, | |
| "loss": 0.0393, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.1308980213089802e-07, | |
| "loss": 0.0342, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.2831050228310502e-08, | |
| "loss": 0.0438, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9766719005351363, | |
| "eval_f1": 0.9076281864883202, | |
| "eval_loss": 0.10344000160694122, | |
| "eval_precision": 0.9026412184306921, | |
| "eval_recall": 0.9126705653021443, | |
| "eval_runtime": 35.4439, | |
| "eval_samples_per_second": 247.151, | |
| "eval_steps_per_second": 61.788, | |
| "step": 52560 | |
| } | |
| ], | |
| "max_steps": 52560, | |
| "num_train_epochs": 3, | |
| "total_flos": 4848998991932040.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |