| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 8.012820512820513, |
| "eval_steps": 500, |
| "global_step": 15000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2670940170940171, |
| "grad_norm": 0.11774194240570068, |
| "learning_rate": 4.9809218559218565e-05, |
| "loss": 0.246, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2670940170940171, |
| "eval_f1": 0.5214187643020595, |
| "eval_loss": 0.03276558592915535, |
| "eval_precision": 0.5067158868528732, |
| "eval_recall": 0.5370003770739065, |
| "eval_runtime": 119.6438, |
| "eval_samples_per_second": 123.349, |
| "eval_steps_per_second": 3.861, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5341880341880342, |
| "grad_norm": 0.042453471571207047, |
| "learning_rate": 4.961843711843712e-05, |
| "loss": 0.0238, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5341880341880342, |
| "eval_f1": 0.6635963067112459, |
| "eval_loss": 0.01632688380777836, |
| "eval_precision": 0.6257568797761723, |
| "eval_recall": 0.7063065610859729, |
| "eval_runtime": 125.2059, |
| "eval_samples_per_second": 117.87, |
| "eval_steps_per_second": 3.69, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8012820512820513, |
| "grad_norm": 0.024465590715408325, |
| "learning_rate": 4.9427655677655683e-05, |
| "loss": 0.0127, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.8012820512820513, |
| "eval_f1": 0.9185966204705558, |
| "eval_loss": 0.007961403578519821, |
| "eval_precision": 0.8978039780397804, |
| "eval_recall": 0.9403751885369532, |
| "eval_runtime": 214.5953, |
| "eval_samples_per_second": 68.771, |
| "eval_steps_per_second": 2.153, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0683760683760684, |
| "grad_norm": 0.06622592359781265, |
| "learning_rate": 4.923687423687424e-05, |
| "loss": 0.0063, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0683760683760684, |
| "eval_f1": 0.9344357210681118, |
| "eval_loss": 0.005176798906177282, |
| "eval_precision": 0.9185448253881529, |
| "eval_recall": 0.9508861236802413, |
| "eval_runtime": 215.2423, |
| "eval_samples_per_second": 68.565, |
| "eval_steps_per_second": 2.146, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.3354700854700854, |
| "grad_norm": 0.048759885132312775, |
| "learning_rate": 4.9046092796092795e-05, |
| "loss": 0.0041, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.3354700854700854, |
| "eval_f1": 0.9516508609641868, |
| "eval_loss": 0.0035495704505592585, |
| "eval_precision": 0.9410165430164509, |
| "eval_recall": 0.9625282805429864, |
| "eval_runtime": 215.3598, |
| "eval_samples_per_second": 68.527, |
| "eval_steps_per_second": 2.145, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.6025641025641026, |
| "grad_norm": 0.04741215705871582, |
| "learning_rate": 4.885531135531136e-05, |
| "loss": 0.003, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.6025641025641026, |
| "eval_f1": 0.9602090789225843, |
| "eval_loss": 0.002707522828131914, |
| "eval_precision": 0.9593056078283778, |
| "eval_recall": 0.9611142533936652, |
| "eval_runtime": 215.7177, |
| "eval_samples_per_second": 68.413, |
| "eval_steps_per_second": 2.142, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.8696581196581197, |
| "grad_norm": 0.022911719977855682, |
| "learning_rate": 4.8664529914529914e-05, |
| "loss": 0.0024, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.8696581196581197, |
| "eval_f1": 0.9571561338289963, |
| "eval_loss": 0.0023886554408818483, |
| "eval_precision": 0.9438233137829912, |
| "eval_recall": 0.9708710407239819, |
| "eval_runtime": 205.5029, |
| "eval_samples_per_second": 71.814, |
| "eval_steps_per_second": 2.248, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.1367521367521367, |
| "grad_norm": 0.05229872837662697, |
| "learning_rate": 4.8473748473748476e-05, |
| "loss": 0.0018, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.1367521367521367, |
| "eval_f1": 0.9639815719670529, |
| "eval_loss": 0.0022004263009876013, |
| "eval_precision": 0.9518886131789358, |
| "eval_recall": 0.9763857466063348, |
| "eval_runtime": 217.5053, |
| "eval_samples_per_second": 67.851, |
| "eval_steps_per_second": 2.124, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.4038461538461537, |
| "grad_norm": 0.04928997904062271, |
| "learning_rate": 4.828296703296704e-05, |
| "loss": 0.0013, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.4038461538461537, |
| "eval_f1": 0.9693363629974934, |
| "eval_loss": 0.0017703943885862827, |
| "eval_precision": 0.9635356028500908, |
| "eval_recall": 0.9752073906485671, |
| "eval_runtime": 205.3479, |
| "eval_samples_per_second": 71.868, |
| "eval_steps_per_second": 2.25, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.6709401709401708, |
| "grad_norm": 0.03343936800956726, |
| "learning_rate": 4.8092185592185595e-05, |
| "loss": 0.0014, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.6709401709401708, |
| "eval_f1": 0.9706270005648653, |
| "eval_loss": 0.001739403698593378, |
| "eval_precision": 0.9693493794659647, |
| "eval_recall": 0.9719079939668175, |
| "eval_runtime": 204.7418, |
| "eval_samples_per_second": 72.081, |
| "eval_steps_per_second": 2.257, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.9380341880341883, |
| "grad_norm": 0.07879549264907837, |
| "learning_rate": 4.790140415140416e-05, |
| "loss": 0.0013, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.9380341880341883, |
| "eval_f1": 0.9702524596250233, |
| "eval_loss": 0.0016117716440930963, |
| "eval_precision": 0.9555301645338209, |
| "eval_recall": 0.985435520361991, |
| "eval_runtime": 216.8331, |
| "eval_samples_per_second": 68.062, |
| "eval_steps_per_second": 2.131, |
| "step": 5500 |
| }, |
| { |
| "epoch": 3.2051282051282053, |
| "grad_norm": 0.14366598427295685, |
| "learning_rate": 4.771062271062271e-05, |
| "loss": 0.0008, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.2051282051282053, |
| "eval_f1": 0.977527028941032, |
| "eval_loss": 0.001418485539034009, |
| "eval_precision": 0.9791449919606545, |
| "eval_recall": 0.9759144042232277, |
| "eval_runtime": 217.6653, |
| "eval_samples_per_second": 67.801, |
| "eval_steps_per_second": 2.123, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.4722222222222223, |
| "grad_norm": 0.01724930852651596, |
| "learning_rate": 4.751984126984127e-05, |
| "loss": 0.0009, |
| "step": 6500 |
| }, |
| { |
| "epoch": 3.4722222222222223, |
| "eval_f1": 0.9748389220712035, |
| "eval_loss": 0.0014127923641353846, |
| "eval_precision": 0.9726888784608165, |
| "eval_recall": 0.976998491704374, |
| "eval_runtime": 120.5351, |
| "eval_samples_per_second": 122.437, |
| "eval_steps_per_second": 3.833, |
| "step": 6500 |
| }, |
| { |
| "epoch": 3.7393162393162394, |
| "grad_norm": 0.0373033843934536, |
| "learning_rate": 4.732905982905983e-05, |
| "loss": 0.0008, |
| "step": 7000 |
| }, |
| { |
| "epoch": 3.7393162393162394, |
| "eval_f1": 0.9767944381811348, |
| "eval_loss": 0.001502642291598022, |
| "eval_precision": 0.973501872659176, |
| "eval_recall": 0.9801093514328808, |
| "eval_runtime": 119.8163, |
| "eval_samples_per_second": 123.172, |
| "eval_steps_per_second": 3.856, |
| "step": 7000 |
| }, |
| { |
| "epoch": 4.006410256410256, |
| "grad_norm": 0.004327626433223486, |
| "learning_rate": 4.713827838827839e-05, |
| "loss": 0.0007, |
| "step": 7500 |
| }, |
| { |
| "epoch": 4.006410256410256, |
| "eval_f1": 0.9779735682819383, |
| "eval_loss": 0.001390722580254078, |
| "eval_precision": 0.9724137931034482, |
| "eval_recall": 0.9835972850678733, |
| "eval_runtime": 119.5661, |
| "eval_samples_per_second": 123.43, |
| "eval_steps_per_second": 3.864, |
| "step": 7500 |
| }, |
| { |
| "epoch": 4.273504273504273, |
| "grad_norm": 0.0008369502611458302, |
| "learning_rate": 4.694749694749695e-05, |
| "loss": 0.0006, |
| "step": 8000 |
| }, |
| { |
| "epoch": 4.273504273504273, |
| "eval_f1": 0.9788639365918097, |
| "eval_loss": 0.0014948239549994469, |
| "eval_precision": 0.9797884397431054, |
| "eval_recall": 0.9779411764705882, |
| "eval_runtime": 121.1034, |
| "eval_samples_per_second": 121.863, |
| "eval_steps_per_second": 3.815, |
| "step": 8000 |
| }, |
| { |
| "epoch": 4.5405982905982905, |
| "grad_norm": 0.034645263105630875, |
| "learning_rate": 4.675671550671551e-05, |
| "loss": 0.0005, |
| "step": 8500 |
| }, |
| { |
| "epoch": 4.5405982905982905, |
| "eval_f1": 0.9742678851052889, |
| "eval_loss": 0.0017295886063948274, |
| "eval_precision": 0.9662509851189096, |
| "eval_recall": 0.9824189291101055, |
| "eval_runtime": 214.7422, |
| "eval_samples_per_second": 68.724, |
| "eval_steps_per_second": 2.151, |
| "step": 8500 |
| }, |
| { |
| "epoch": 4.8076923076923075, |
| "grad_norm": 0.010439756326377392, |
| "learning_rate": 4.656593406593407e-05, |
| "loss": 0.0006, |
| "step": 9000 |
| }, |
| { |
| "epoch": 4.8076923076923075, |
| "eval_f1": 0.9778079816277271, |
| "eval_loss": 0.0013649952597916126, |
| "eval_precision": 0.9723167264762083, |
| "eval_recall": 0.9833616138763197, |
| "eval_runtime": 215.7325, |
| "eval_samples_per_second": 68.409, |
| "eval_steps_per_second": 2.142, |
| "step": 9000 |
| }, |
| { |
| "epoch": 5.0747863247863245, |
| "grad_norm": 0.022446786984801292, |
| "learning_rate": 4.637515262515263e-05, |
| "loss": 0.0005, |
| "step": 9500 |
| }, |
| { |
| "epoch": 5.0747863247863245, |
| "eval_f1": 0.9819268602626252, |
| "eval_loss": 0.0013456182787194848, |
| "eval_precision": 0.9804962872450418, |
| "eval_recall": 0.9833616138763197, |
| "eval_runtime": 145.9782, |
| "eval_samples_per_second": 101.097, |
| "eval_steps_per_second": 3.165, |
| "step": 9500 |
| }, |
| { |
| "epoch": 5.3418803418803416, |
| "grad_norm": 0.0010687178000807762, |
| "learning_rate": 4.618437118437119e-05, |
| "loss": 0.0004, |
| "step": 10000 |
| }, |
| { |
| "epoch": 5.3418803418803416, |
| "eval_f1": 0.9747765825886088, |
| "eval_loss": 0.0019718140829354525, |
| "eval_precision": 0.9652049350769373, |
| "eval_recall": 0.9845399698340875, |
| "eval_runtime": 218.776, |
| "eval_samples_per_second": 67.457, |
| "eval_steps_per_second": 2.112, |
| "step": 10000 |
| }, |
| { |
| "epoch": 5.608974358974359, |
| "grad_norm": 0.010968877002596855, |
| "learning_rate": 4.599358974358974e-05, |
| "loss": 0.0005, |
| "step": 10500 |
| }, |
| { |
| "epoch": 5.608974358974359, |
| "eval_f1": 0.9817333301906805, |
| "eval_loss": 0.0013046471867710352, |
| "eval_precision": 0.9818490405921456, |
| "eval_recall": 0.9816176470588235, |
| "eval_runtime": 205.7951, |
| "eval_samples_per_second": 71.712, |
| "eval_steps_per_second": 2.245, |
| "step": 10500 |
| }, |
| { |
| "epoch": 5.8760683760683765, |
| "grad_norm": 0.0015924246981739998, |
| "learning_rate": 4.5802808302808305e-05, |
| "loss": 0.0004, |
| "step": 11000 |
| }, |
| { |
| "epoch": 5.8760683760683765, |
| "eval_f1": 0.9823409981585532, |
| "eval_loss": 0.0014677270082756877, |
| "eval_precision": 0.9840601646012677, |
| "eval_recall": 0.9806278280542986, |
| "eval_runtime": 203.592, |
| "eval_samples_per_second": 72.488, |
| "eval_steps_per_second": 2.269, |
| "step": 11000 |
| }, |
| { |
| "epoch": 6.1431623931623935, |
| "grad_norm": 0.004735188093036413, |
| "learning_rate": 4.561202686202686e-05, |
| "loss": 0.0004, |
| "step": 11500 |
| }, |
| { |
| "epoch": 6.1431623931623935, |
| "eval_f1": 0.9827679432023886, |
| "eval_loss": 0.0012729066656902432, |
| "eval_precision": 0.9803480136954177, |
| "eval_recall": 0.9851998491704375, |
| "eval_runtime": 119.9744, |
| "eval_samples_per_second": 123.01, |
| "eval_steps_per_second": 3.851, |
| "step": 11500 |
| }, |
| { |
| "epoch": 6.410256410256411, |
| "grad_norm": 0.008303467184305191, |
| "learning_rate": 4.5421245421245424e-05, |
| "loss": 0.0003, |
| "step": 12000 |
| }, |
| { |
| "epoch": 6.410256410256411, |
| "eval_f1": 0.9750854909623841, |
| "eval_loss": 0.0016973286401480436, |
| "eval_precision": 0.9626567452115199, |
| "eval_recall": 0.9878393665158371, |
| "eval_runtime": 219.3026, |
| "eval_samples_per_second": 67.295, |
| "eval_steps_per_second": 2.107, |
| "step": 12000 |
| }, |
| { |
| "epoch": 6.677350427350428, |
| "grad_norm": 0.007308937143534422, |
| "learning_rate": 4.5230463980463986e-05, |
| "loss": 0.0003, |
| "step": 12500 |
| }, |
| { |
| "epoch": 6.677350427350428, |
| "eval_f1": 0.9813210991994756, |
| "eval_loss": 0.0012571236584335566, |
| "eval_precision": 0.9747047335627267, |
| "eval_recall": 0.98802790346908, |
| "eval_runtime": 219.2644, |
| "eval_samples_per_second": 67.307, |
| "eval_steps_per_second": 2.107, |
| "step": 12500 |
| }, |
| { |
| "epoch": 6.944444444444445, |
| "grad_norm": 0.05341866984963417, |
| "learning_rate": 4.503968253968254e-05, |
| "loss": 0.0004, |
| "step": 13000 |
| }, |
| { |
| "epoch": 6.944444444444445, |
| "eval_f1": 0.9821235357764502, |
| "eval_loss": 0.0013370579108595848, |
| "eval_precision": 0.9802328857169688, |
| "eval_recall": 0.9840214932126696, |
| "eval_runtime": 219.0265, |
| "eval_samples_per_second": 67.38, |
| "eval_steps_per_second": 2.109, |
| "step": 13000 |
| }, |
| { |
| "epoch": 7.211538461538462, |
| "grad_norm": 0.0043980698101222515, |
| "learning_rate": 4.4848901098901105e-05, |
| "loss": 0.0003, |
| "step": 13500 |
| }, |
| { |
| "epoch": 7.211538461538462, |
| "eval_f1": 0.9812013269651554, |
| "eval_loss": 0.00139136821962893, |
| "eval_precision": 0.9795649927185607, |
| "eval_recall": 0.9828431372549019, |
| "eval_runtime": 205.0799, |
| "eval_samples_per_second": 71.962, |
| "eval_steps_per_second": 2.253, |
| "step": 13500 |
| }, |
| { |
| "epoch": 7.478632478632479, |
| "grad_norm": 0.012946384958922863, |
| "learning_rate": 4.465811965811966e-05, |
| "loss": 0.0003, |
| "step": 14000 |
| }, |
| { |
| "epoch": 7.478632478632479, |
| "eval_f1": 0.9811170275151885, |
| "eval_loss": 0.0012917759595438838, |
| "eval_precision": 0.9765584870417932, |
| "eval_recall": 0.9857183257918553, |
| "eval_runtime": 205.9645, |
| "eval_samples_per_second": 71.653, |
| "eval_steps_per_second": 2.243, |
| "step": 14000 |
| }, |
| { |
| "epoch": 7.745726495726496, |
| "grad_norm": 0.0030930449720472097, |
| "learning_rate": 4.4467338217338216e-05, |
| "loss": 0.0003, |
| "step": 14500 |
| }, |
| { |
| "epoch": 7.745726495726496, |
| "eval_f1": 0.9808375067597752, |
| "eval_loss": 0.0013525269459933043, |
| "eval_precision": 0.9785596997419658, |
| "eval_recall": 0.9831259426847662, |
| "eval_runtime": 122.7721, |
| "eval_samples_per_second": 120.206, |
| "eval_steps_per_second": 3.763, |
| "step": 14500 |
| }, |
| { |
| "epoch": 8.012820512820513, |
| "grad_norm": 0.00297636934556067, |
| "learning_rate": 4.427655677655678e-05, |
| "loss": 0.0002, |
| "step": 15000 |
| }, |
| { |
| "epoch": 8.012820512820513, |
| "eval_f1": 0.9820384687912502, |
| "eval_loss": 0.0015595377190038562, |
| "eval_precision": 0.9822236891738967, |
| "eval_recall": 0.981853318250377, |
| "eval_runtime": 208.3474, |
| "eval_samples_per_second": 70.834, |
| "eval_steps_per_second": 2.217, |
| "step": 15000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 131040, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 70, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.2536694351387706e+17, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
