| { |
| "best_global_step": 6000, |
| "best_metric": 0.9012365963906207, |
| "best_model_checkpoint": "/home/rupak/Desktop/Topic-Modeling /topic modeling 25k/checkpoint/muril(l)-25k-2e5-256-16-10/checkpoint-6000", |
| "epoch": 4.7964814074370254, |
| "eval_steps": 1000, |
| "global_step": 6000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0007996801279488205, |
| "grad_norm": 25.879539489746094, |
| "learning_rate": 0.0, |
| "loss": 1.5698, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07996801279488205, |
| "grad_norm": 53.82084655761719, |
| "learning_rate": 1.5840000000000002e-06, |
| "loss": 1.6265, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1599360255897641, |
| "grad_norm": 7.198434352874756, |
| "learning_rate": 3.1840000000000003e-06, |
| "loss": 1.4956, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.23990403838464613, |
| "grad_norm": 8.492032051086426, |
| "learning_rate": 4.784e-06, |
| "loss": 1.0364, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.3198720511795282, |
| "grad_norm": 20.075029373168945, |
| "learning_rate": 6.384e-06, |
| "loss": 0.5206, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.39984006397441024, |
| "grad_norm": 21.228702545166016, |
| "learning_rate": 7.984e-06, |
| "loss": 0.4196, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.47980807676929227, |
| "grad_norm": 9.807292938232422, |
| "learning_rate": 9.584000000000002e-06, |
| "loss": 0.364, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.5597760895641744, |
| "grad_norm": 5.047133445739746, |
| "learning_rate": 1.1184000000000002e-05, |
| "loss": 0.3409, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.6397441023590564, |
| "grad_norm": 14.136054039001465, |
| "learning_rate": 1.2784000000000002e-05, |
| "loss": 0.3574, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.7197121151539384, |
| "grad_norm": 4.156088829040527, |
| "learning_rate": 1.4384e-05, |
| "loss": 0.3665, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.7996801279488205, |
| "grad_norm": 12.220858573913574, |
| "learning_rate": 1.5984e-05, |
| "loss": 0.3201, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7996801279488205, |
| "eval_accuracy": 0.8868452618952419, |
| "eval_auroc_macro": 0.9821551565989282, |
| "eval_auroc_weighted": 0.9818783632588722, |
| "eval_f1_macro": 0.8873579116114954, |
| "eval_f1_weighted": 0.8863768689638406, |
| "eval_loss": 0.3724072277545929, |
| "eval_precision_macro": 0.8883690638640166, |
| "eval_precision_weighted": 0.8877963273366011, |
| "eval_recall_macro": 0.8881765917966007, |
| "eval_recall_weighted": 0.8868452618952419, |
| "eval_runtime": 6.278, |
| "eval_samples_per_second": 398.375, |
| "eval_steps_per_second": 49.857, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8796481407437026, |
| "grad_norm": 17.05066680908203, |
| "learning_rate": 1.7584e-05, |
| "loss": 0.3364, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.9596161535385845, |
| "grad_norm": 7.545499801635742, |
| "learning_rate": 1.9184e-05, |
| "loss": 0.3163, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.0391843262694922, |
| "grad_norm": 6.938131332397461, |
| "learning_rate": 1.991296625222025e-05, |
| "loss": 0.33, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.1191523390643743, |
| "grad_norm": 11.203085899353027, |
| "learning_rate": 1.9735346358792185e-05, |
| "loss": 0.2745, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.1991203518592564, |
| "grad_norm": 4.243178844451904, |
| "learning_rate": 1.955772646536412e-05, |
| "loss": 0.2759, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.2790883646541382, |
| "grad_norm": 0.7625662088394165, |
| "learning_rate": 1.938010657193606e-05, |
| "loss": 0.302, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.3590563774490203, |
| "grad_norm": 52.485660552978516, |
| "learning_rate": 1.9202486678507993e-05, |
| "loss": 0.2567, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.4390243902439024, |
| "grad_norm": 8.310826301574707, |
| "learning_rate": 1.902486678507993e-05, |
| "loss": 0.2925, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.5189924030387845, |
| "grad_norm": 7.896425247192383, |
| "learning_rate": 1.884724689165187e-05, |
| "loss": 0.3101, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.5989604158336665, |
| "grad_norm": 11.918813705444336, |
| "learning_rate": 1.86696269982238e-05, |
| "loss": 0.2644, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.5989604158336665, |
| "eval_accuracy": 0.899640143942423, |
| "eval_auroc_macro": 0.9858436759681066, |
| "eval_auroc_weighted": 0.9856690564940799, |
| "eval_f1_macro": 0.8999952784325647, |
| "eval_f1_weighted": 0.899271866196283, |
| "eval_loss": 0.36566194891929626, |
| "eval_precision_macro": 0.9002435933046236, |
| "eval_precision_weighted": 0.9000507081560623, |
| "eval_recall_macro": 0.9008670037402549, |
| "eval_recall_weighted": 0.899640143942423, |
| "eval_runtime": 6.2102, |
| "eval_samples_per_second": 402.728, |
| "eval_steps_per_second": 50.401, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.6789284286285486, |
| "grad_norm": 4.957444667816162, |
| "learning_rate": 1.849200710479574e-05, |
| "loss": 0.2629, |
| "step": 2100 |
| }, |
| { |
| "epoch": 1.7588964414234307, |
| "grad_norm": 68.0340805053711, |
| "learning_rate": 1.8314387211367673e-05, |
| "loss": 0.2467, |
| "step": 2200 |
| }, |
| { |
| "epoch": 1.8388644542183128, |
| "grad_norm": 6.16074275970459, |
| "learning_rate": 1.813676731793961e-05, |
| "loss": 0.3059, |
| "step": 2300 |
| }, |
| { |
| "epoch": 1.9188324670131949, |
| "grad_norm": 25.60173988342285, |
| "learning_rate": 1.795914742451155e-05, |
| "loss": 0.2247, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1.9988004798080767, |
| "grad_norm": 14.7791748046875, |
| "learning_rate": 1.778152753108348e-05, |
| "loss": 0.3139, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.0783686525389844, |
| "grad_norm": 1.2503273487091064, |
| "learning_rate": 1.760390763765542e-05, |
| "loss": 0.2017, |
| "step": 2600 |
| }, |
| { |
| "epoch": 2.1583366653338665, |
| "grad_norm": 0.10312394797801971, |
| "learning_rate": 1.7426287744227356e-05, |
| "loss": 0.1336, |
| "step": 2700 |
| }, |
| { |
| "epoch": 2.2383046781287486, |
| "grad_norm": 17.44778060913086, |
| "learning_rate": 1.724866785079929e-05, |
| "loss": 0.1682, |
| "step": 2800 |
| }, |
| { |
| "epoch": 2.3182726909236306, |
| "grad_norm": 16.813922882080078, |
| "learning_rate": 1.7071047957371228e-05, |
| "loss": 0.2017, |
| "step": 2900 |
| }, |
| { |
| "epoch": 2.3982407037185127, |
| "grad_norm": 1.6435425281524658, |
| "learning_rate": 1.6893428063943164e-05, |
| "loss": 0.1731, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.3982407037185127, |
| "eval_accuracy": 0.899640143942423, |
| "eval_auroc_macro": 0.9826539122109719, |
| "eval_auroc_weighted": 0.9823944467087085, |
| "eval_f1_macro": 0.9003900298720995, |
| "eval_f1_weighted": 0.899400488889071, |
| "eval_loss": 0.4533480405807495, |
| "eval_precision_macro": 0.900771380467704, |
| "eval_precision_weighted": 0.8998950761798218, |
| "eval_recall_macro": 0.9007412354178097, |
| "eval_recall_weighted": 0.899640143942423, |
| "eval_runtime": 12.9804, |
| "eval_samples_per_second": 192.676, |
| "eval_steps_per_second": 24.113, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.478208716513395, |
| "grad_norm": 5.001162052154541, |
| "learning_rate": 1.67158081705151e-05, |
| "loss": 0.1865, |
| "step": 3100 |
| }, |
| { |
| "epoch": 2.5581767293082764, |
| "grad_norm": 2.225888252258301, |
| "learning_rate": 1.6538188277087036e-05, |
| "loss": 0.1825, |
| "step": 3200 |
| }, |
| { |
| "epoch": 2.638144742103159, |
| "grad_norm": 10.553831100463867, |
| "learning_rate": 1.636056838365897e-05, |
| "loss": 0.1961, |
| "step": 3300 |
| }, |
| { |
| "epoch": 2.7181127548980406, |
| "grad_norm": 78.96723937988281, |
| "learning_rate": 1.6182948490230908e-05, |
| "loss": 0.1688, |
| "step": 3400 |
| }, |
| { |
| "epoch": 2.7980807676929227, |
| "grad_norm": 25.426177978515625, |
| "learning_rate": 1.6005328596802844e-05, |
| "loss": 0.2036, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.8780487804878048, |
| "grad_norm": 9.436786651611328, |
| "learning_rate": 1.582770870337478e-05, |
| "loss": 0.1639, |
| "step": 3600 |
| }, |
| { |
| "epoch": 2.958016793282687, |
| "grad_norm": 4.328421592712402, |
| "learning_rate": 1.5650088809946716e-05, |
| "loss": 0.1589, |
| "step": 3700 |
| }, |
| { |
| "epoch": 3.0375849660135947, |
| "grad_norm": 11.474821090698242, |
| "learning_rate": 1.5472468916518652e-05, |
| "loss": 0.1461, |
| "step": 3800 |
| }, |
| { |
| "epoch": 3.117552978808477, |
| "grad_norm": 0.47800692915916443, |
| "learning_rate": 1.5294849023090588e-05, |
| "loss": 0.1074, |
| "step": 3900 |
| }, |
| { |
| "epoch": 3.1975209916033585, |
| "grad_norm": 0.019819365814328194, |
| "learning_rate": 1.5117229129662522e-05, |
| "loss": 0.0909, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.1975209916033585, |
| "eval_accuracy": 0.8980407836865254, |
| "eval_auroc_macro": 0.9845075523589977, |
| "eval_auroc_weighted": 0.984352097055703, |
| "eval_f1_macro": 0.8985314967385932, |
| "eval_f1_weighted": 0.8976563352060407, |
| "eval_loss": 0.5361937284469604, |
| "eval_precision_macro": 0.8986211757374079, |
| "eval_precision_weighted": 0.8983529768629782, |
| "eval_recall_macro": 0.8995002852715424, |
| "eval_recall_weighted": 0.8980407836865254, |
| "eval_runtime": 13.2069, |
| "eval_samples_per_second": 189.371, |
| "eval_steps_per_second": 23.7, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.2774890043982405, |
| "grad_norm": 20506.994140625, |
| "learning_rate": 1.493960923623446e-05, |
| "loss": 0.1061, |
| "step": 4100 |
| }, |
| { |
| "epoch": 3.3574570171931226, |
| "grad_norm": 0.2834841012954712, |
| "learning_rate": 1.4761989342806396e-05, |
| "loss": 0.0893, |
| "step": 4200 |
| }, |
| { |
| "epoch": 3.4374250299880047, |
| "grad_norm": 40.21791458129883, |
| "learning_rate": 1.458436944937833e-05, |
| "loss": 0.1219, |
| "step": 4300 |
| }, |
| { |
| "epoch": 3.517393042782887, |
| "grad_norm": 0.042944587767124176, |
| "learning_rate": 1.4406749555950268e-05, |
| "loss": 0.0995, |
| "step": 4400 |
| }, |
| { |
| "epoch": 3.597361055577769, |
| "grad_norm": 0.014542081393301487, |
| "learning_rate": 1.4229129662522204e-05, |
| "loss": 0.1027, |
| "step": 4500 |
| }, |
| { |
| "epoch": 3.677329068372651, |
| "grad_norm": 0.0956217423081398, |
| "learning_rate": 1.4051509769094141e-05, |
| "loss": 0.0975, |
| "step": 4600 |
| }, |
| { |
| "epoch": 3.757297081167533, |
| "grad_norm": 0.380467027425766, |
| "learning_rate": 1.3873889875666075e-05, |
| "loss": 0.0994, |
| "step": 4700 |
| }, |
| { |
| "epoch": 3.837265093962415, |
| "grad_norm": 21.856365203857422, |
| "learning_rate": 1.3696269982238011e-05, |
| "loss": 0.0898, |
| "step": 4800 |
| }, |
| { |
| "epoch": 3.917233106757297, |
| "grad_norm": 3.2071404457092285, |
| "learning_rate": 1.3518650088809947e-05, |
| "loss": 0.098, |
| "step": 4900 |
| }, |
| { |
| "epoch": 3.9972011195521793, |
| "grad_norm": 44.20155334472656, |
| "learning_rate": 1.3341030195381883e-05, |
| "loss": 0.1379, |
| "step": 5000 |
| }, |
| { |
| "epoch": 3.9972011195521793, |
| "eval_accuracy": 0.8960415833666533, |
| "eval_auroc_macro": 0.9785502533271109, |
| "eval_auroc_weighted": 0.9782031369287175, |
| "eval_f1_macro": 0.8962655065969253, |
| "eval_f1_weighted": 0.8953294988740432, |
| "eval_loss": 0.585455596446991, |
| "eval_precision_macro": 0.8973276067711584, |
| "eval_precision_weighted": 0.8974988867668197, |
| "eval_recall_macro": 0.8980216106981015, |
| "eval_recall_weighted": 0.8960415833666533, |
| "eval_runtime": 13.1175, |
| "eval_samples_per_second": 190.661, |
| "eval_steps_per_second": 23.861, |
| "step": 5000 |
| }, |
| { |
| "epoch": 4.076769292283087, |
| "grad_norm": 11.875359535217285, |
| "learning_rate": 1.3163410301953821e-05, |
| "loss": 0.0458, |
| "step": 5100 |
| }, |
| { |
| "epoch": 4.156737305077969, |
| "grad_norm": 0.037335313856601715, |
| "learning_rate": 1.2985790408525755e-05, |
| "loss": 0.0487, |
| "step": 5200 |
| }, |
| { |
| "epoch": 4.23670531787285, |
| "grad_norm": 0.013043818064033985, |
| "learning_rate": 1.2808170515097691e-05, |
| "loss": 0.061, |
| "step": 5300 |
| }, |
| { |
| "epoch": 4.316673330667733, |
| "grad_norm": 0.2669573426246643, |
| "learning_rate": 1.2630550621669629e-05, |
| "loss": 0.0446, |
| "step": 5400 |
| }, |
| { |
| "epoch": 4.396641343462615, |
| "grad_norm": 0.34643861651420593, |
| "learning_rate": 1.2452930728241563e-05, |
| "loss": 0.0542, |
| "step": 5500 |
| }, |
| { |
| "epoch": 4.476609356257497, |
| "grad_norm": 10.271299362182617, |
| "learning_rate": 1.22753108348135e-05, |
| "loss": 0.0698, |
| "step": 5600 |
| }, |
| { |
| "epoch": 4.556577369052379, |
| "grad_norm": 0.09664414823055267, |
| "learning_rate": 1.2097690941385437e-05, |
| "loss": 0.0445, |
| "step": 5700 |
| }, |
| { |
| "epoch": 4.636545381847261, |
| "grad_norm": 0.016957182437181473, |
| "learning_rate": 1.1920071047957371e-05, |
| "loss": 0.0672, |
| "step": 5800 |
| }, |
| { |
| "epoch": 4.716513394642143, |
| "grad_norm": 0.010930199176073074, |
| "learning_rate": 1.1742451154529309e-05, |
| "loss": 0.0897, |
| "step": 5900 |
| }, |
| { |
| "epoch": 4.7964814074370254, |
| "grad_norm": 0.045626524835824966, |
| "learning_rate": 1.1564831261101243e-05, |
| "loss": 0.0757, |
| "step": 6000 |
| }, |
| { |
| "epoch": 4.7964814074370254, |
| "eval_accuracy": 0.9012395041983207, |
| "eval_auroc_macro": 0.9808400598732152, |
| "eval_auroc_weighted": 0.9806547591394953, |
| "eval_f1_macro": 0.9019706436600858, |
| "eval_f1_weighted": 0.9012365963906207, |
| "eval_loss": 0.6127548813819885, |
| "eval_precision_macro": 0.9021413467891518, |
| "eval_precision_weighted": 0.9016118161501111, |
| "eval_recall_macro": 0.9021814325163104, |
| "eval_recall_weighted": 0.9012395041983207, |
| "eval_runtime": 13.1731, |
| "eval_samples_per_second": 189.856, |
| "eval_steps_per_second": 23.761, |
| "step": 6000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 12510, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 30, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5720958926505336.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
