| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 433, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02313475997686524, |
| "grad_norm": 3.5443220138549805, |
| "learning_rate": 0.00013846153846153847, |
| "loss": 2.4906261444091795, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.04626951995373048, |
| "grad_norm": 0.4789237976074219, |
| "learning_rate": 0.00019714285714285716, |
| "loss": 0.13569670915603638, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06940427993059572, |
| "grad_norm": 0.0071147712878882885, |
| "learning_rate": 0.0001923809523809524, |
| "loss": 0.023090672492980958, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.09253903990746096, |
| "grad_norm": 0.031249770894646645, |
| "learning_rate": 0.00018761904761904763, |
| "loss": 0.07923950552940369, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1156737998843262, |
| "grad_norm": 0.23233748972415924, |
| "learning_rate": 0.00018285714285714286, |
| "loss": 0.01179821714758873, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.13880855986119145, |
| "grad_norm": 1.0764169692993164, |
| "learning_rate": 0.0001780952380952381, |
| "loss": 0.04595586061477661, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.16194331983805668, |
| "grad_norm": 0.4203377366065979, |
| "learning_rate": 0.00017333333333333334, |
| "loss": 0.020573070645332335, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.18507807981492191, |
| "grad_norm": 0.06960943341255188, |
| "learning_rate": 0.00016857142857142857, |
| "loss": 0.02428939938545227, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.20821283979178715, |
| "grad_norm": 0.761617124080658, |
| "learning_rate": 0.0001638095238095238, |
| "loss": 0.03832740783691406, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2313475997686524, |
| "grad_norm": 0.024328596889972687, |
| "learning_rate": 0.00015904761904761904, |
| "loss": 0.010582192242145539, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.25448235974551764, |
| "grad_norm": 0.03712387755513191, |
| "learning_rate": 0.0001542857142857143, |
| "loss": 0.014394421875476838, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.2776171197223829, |
| "grad_norm": 0.35509419441223145, |
| "learning_rate": 0.00014952380952380954, |
| "loss": 0.03347426652908325, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.3007518796992481, |
| "grad_norm": 0.11692740023136139, |
| "learning_rate": 0.00014476190476190475, |
| "loss": 0.06869672536849976, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.32388663967611336, |
| "grad_norm": 0.025060011073946953, |
| "learning_rate": 0.00014, |
| "loss": 0.002869569510221481, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.3470213996529786, |
| "grad_norm": 0.04316815361380577, |
| "learning_rate": 0.00013523809523809525, |
| "loss": 0.017471878230571745, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.37015615962984383, |
| "grad_norm": 0.24662676453590393, |
| "learning_rate": 0.0001304761904761905, |
| "loss": 0.04017368853092194, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.3932909196067091, |
| "grad_norm": 0.013658199459314346, |
| "learning_rate": 0.00012571428571428572, |
| "loss": 0.011992159485816955, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.4164256795835743, |
| "grad_norm": 0.011875756084918976, |
| "learning_rate": 0.00012095238095238095, |
| "loss": 0.003486642986536026, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.43956043956043955, |
| "grad_norm": 0.008698398247361183, |
| "learning_rate": 0.00011619047619047621, |
| "loss": 0.009918726235628127, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.4626951995373048, |
| "grad_norm": 0.012751366011798382, |
| "learning_rate": 0.00011142857142857144, |
| "loss": 0.0135767862200737, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.48582995951417, |
| "grad_norm": 0.013968385756015778, |
| "learning_rate": 0.00010666666666666667, |
| "loss": 0.0009812915697693825, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.5089647194910353, |
| "grad_norm": 0.38197270035743713, |
| "learning_rate": 0.0001019047619047619, |
| "loss": 0.010036008059978485, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.5320994794679005, |
| "grad_norm": 0.008353643119335175, |
| "learning_rate": 9.714285714285715e-05, |
| "loss": 0.0008777316659688949, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.5552342394447658, |
| "grad_norm": 0.03482387587428093, |
| "learning_rate": 9.238095238095239e-05, |
| "loss": 0.06720049977302552, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.578368999421631, |
| "grad_norm": 0.017207808792591095, |
| "learning_rate": 8.761904761904762e-05, |
| "loss": 0.009993697702884673, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.6015037593984962, |
| "grad_norm": 0.04262904077768326, |
| "learning_rate": 8.285714285714287e-05, |
| "loss": 0.005409357324242592, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.6246385193753615, |
| "grad_norm": 0.010086641646921635, |
| "learning_rate": 7.80952380952381e-05, |
| "loss": 0.0022824501618742945, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.6477732793522267, |
| "grad_norm": 0.019428474828600883, |
| "learning_rate": 7.333333333333333e-05, |
| "loss": 0.009420862048864364, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.6709080393290919, |
| "grad_norm": 0.010999761521816254, |
| "learning_rate": 6.857142857142858e-05, |
| "loss": 0.017436870932579042, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.6940427993059572, |
| "grad_norm": 0.03521187976002693, |
| "learning_rate": 6.38095238095238e-05, |
| "loss": 0.007618572562932968, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7171775592828225, |
| "grad_norm": 0.02904939278960228, |
| "learning_rate": 5.904761904761905e-05, |
| "loss": 0.009538635611534119, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.7403123192596877, |
| "grad_norm": 0.28503215312957764, |
| "learning_rate": 5.428571428571428e-05, |
| "loss": 0.003535139188170433, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.763447079236553, |
| "grad_norm": 0.1933276355266571, |
| "learning_rate": 4.9523809523809525e-05, |
| "loss": 0.00619364008307457, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.7865818392134182, |
| "grad_norm": 0.007664988283067942, |
| "learning_rate": 4.476190476190477e-05, |
| "loss": 0.0007373106665909291, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.8097165991902834, |
| "grad_norm": 0.5651599764823914, |
| "learning_rate": 4e-05, |
| "loss": 0.07755469083786011, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.8328513591671486, |
| "grad_norm": 0.05437934026122093, |
| "learning_rate": 3.523809523809524e-05, |
| "loss": 0.015709011256694792, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.8559861191440139, |
| "grad_norm": 0.061594076454639435, |
| "learning_rate": 3.0476190476190482e-05, |
| "loss": 0.04147002398967743, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.8791208791208791, |
| "grad_norm": 0.03086649812757969, |
| "learning_rate": 2.5714285714285714e-05, |
| "loss": 0.0031579844653606415, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.9022556390977443, |
| "grad_norm": 0.3715185523033142, |
| "learning_rate": 2.0952380952380954e-05, |
| "loss": 0.01193058043718338, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.9253903990746096, |
| "grad_norm": 0.017640365287661552, |
| "learning_rate": 1.6190476190476193e-05, |
| "loss": 0.00927691012620926, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.9485251590514748, |
| "grad_norm": 0.02302401326596737, |
| "learning_rate": 1.1428571428571429e-05, |
| "loss": 0.07495037913322448, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.97165991902834, |
| "grad_norm": 0.013834159821271896, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.015109787881374358, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.9947946790052054, |
| "grad_norm": 0.023592131212353706, |
| "learning_rate": 1.9047619047619051e-06, |
| "loss": 0.012308744341135025, |
| "step": 430 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 433, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3979819485155328.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
