| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.049714143673875215, |
| "eval_steps": 13, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0009942828734775043, |
| "grad_norm": 1.0767807960510254, |
| "learning_rate": 5e-06, |
| "loss": 1.4767, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0009942828734775043, |
| "eval_loss": 1.4993078708648682, |
| "eval_runtime": 34.2272, |
| "eval_samples_per_second": 12.388, |
| "eval_steps_per_second": 6.194, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0019885657469550086, |
| "grad_norm": 1.241318702697754, |
| "learning_rate": 1e-05, |
| "loss": 1.2547, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.002982848620432513, |
| "grad_norm": 1.0247488021850586, |
| "learning_rate": 1.5e-05, |
| "loss": 1.2667, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.003977131493910017, |
| "grad_norm": 1.1591644287109375, |
| "learning_rate": 2e-05, |
| "loss": 1.4027, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.004971414367387522, |
| "grad_norm": 1.1431999206542969, |
| "learning_rate": 2.5e-05, |
| "loss": 1.5309, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.005965697240865026, |
| "grad_norm": 1.1215442419052124, |
| "learning_rate": 3e-05, |
| "loss": 1.2735, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.00695998011434253, |
| "grad_norm": 1.185957908630371, |
| "learning_rate": 3.5e-05, |
| "loss": 1.3907, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.007954262987820034, |
| "grad_norm": 0.9886231422424316, |
| "learning_rate": 4e-05, |
| "loss": 1.2722, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.008948545861297539, |
| "grad_norm": 1.3221428394317627, |
| "learning_rate": 4.5e-05, |
| "loss": 1.5192, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.009942828734775044, |
| "grad_norm": 1.54436457157135, |
| "learning_rate": 5e-05, |
| "loss": 1.8312, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.010937111608252548, |
| "grad_norm": 1.059188723564148, |
| "learning_rate": 4.99229333433282e-05, |
| "loss": 1.3039, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.011931394481730051, |
| "grad_norm": 1.1226993799209595, |
| "learning_rate": 4.9692208514878444e-05, |
| "loss": 1.1677, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.012925677355207556, |
| "grad_norm": 1.0901505947113037, |
| "learning_rate": 4.9309248009941914e-05, |
| "loss": 1.2394, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.012925677355207556, |
| "eval_loss": 1.2392393350601196, |
| "eval_runtime": 34.2682, |
| "eval_samples_per_second": 12.373, |
| "eval_steps_per_second": 6.186, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.01391996022868506, |
| "grad_norm": 0.9254087209701538, |
| "learning_rate": 4.877641290737884e-05, |
| "loss": 1.7542, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.014914243102162566, |
| "grad_norm": 0.6952210068702698, |
| "learning_rate": 4.8096988312782174e-05, |
| "loss": 1.19, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.01590852597564007, |
| "grad_norm": 0.6884624361991882, |
| "learning_rate": 4.72751631047092e-05, |
| "loss": 1.2885, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.016902808849117573, |
| "grad_norm": 0.6651028990745544, |
| "learning_rate": 4.6316004108852305e-05, |
| "loss": 1.1477, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.017897091722595078, |
| "grad_norm": 0.7259565591812134, |
| "learning_rate": 4.522542485937369e-05, |
| "loss": 1.3021, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.018891374596072583, |
| "grad_norm": 0.8364481329917908, |
| "learning_rate": 4.401014914000078e-05, |
| "loss": 1.3226, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.019885657469550087, |
| "grad_norm": 0.6525047421455383, |
| "learning_rate": 4.267766952966369e-05, |
| "loss": 1.0674, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.020879940343027592, |
| "grad_norm": 0.6612785458564758, |
| "learning_rate": 4.123620120825459e-05, |
| "loss": 1.1099, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.021874223216505097, |
| "grad_norm": 0.6104527115821838, |
| "learning_rate": 3.969463130731183e-05, |
| "loss": 1.1705, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.0228685060899826, |
| "grad_norm": 0.6610237956047058, |
| "learning_rate": 3.8062464117898724e-05, |
| "loss": 1.0519, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.023862788963460103, |
| "grad_norm": 0.6938290596008301, |
| "learning_rate": 3.634976249348867e-05, |
| "loss": 0.9388, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.024857071836937607, |
| "grad_norm": 0.6120235919952393, |
| "learning_rate": 3.456708580912725e-05, |
| "loss": 1.0911, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.025851354710415112, |
| "grad_norm": 0.6890453100204468, |
| "learning_rate": 3.272542485937369e-05, |
| "loss": 0.9741, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.025851354710415112, |
| "eval_loss": 1.1278754472732544, |
| "eval_runtime": 34.2794, |
| "eval_samples_per_second": 12.369, |
| "eval_steps_per_second": 6.184, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.026845637583892617, |
| "grad_norm": 0.6195194125175476, |
| "learning_rate": 3.083613409639764e-05, |
| "loss": 1.3244, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.02783992045737012, |
| "grad_norm": 0.5792179107666016, |
| "learning_rate": 2.8910861626005776e-05, |
| "loss": 1.0774, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.028834203330847626, |
| "grad_norm": 0.6153373718261719, |
| "learning_rate": 2.6961477393196126e-05, |
| "loss": 1.4603, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.02982848620432513, |
| "grad_norm": 0.5552039742469788, |
| "learning_rate": 2.5e-05, |
| "loss": 0.9616, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.030822769077802636, |
| "grad_norm": 0.6039525270462036, |
| "learning_rate": 2.303852260680388e-05, |
| "loss": 1.1378, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.03181705195128014, |
| "grad_norm": 0.5297777652740479, |
| "learning_rate": 2.1089138373994223e-05, |
| "loss": 0.9908, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.03281133482475764, |
| "grad_norm": 0.6318143606185913, |
| "learning_rate": 1.9163865903602374e-05, |
| "loss": 1.0829, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.033805617698235146, |
| "grad_norm": 0.5691390037536621, |
| "learning_rate": 1.7274575140626318e-05, |
| "loss": 1.2315, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.03479990057171265, |
| "grad_norm": 0.5200899243354797, |
| "learning_rate": 1.5432914190872757e-05, |
| "loss": 1.0599, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.035794183445190156, |
| "grad_norm": 0.4896901249885559, |
| "learning_rate": 1.3650237506511331e-05, |
| "loss": 1.2254, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.03678846631866766, |
| "grad_norm": 0.5189372897148132, |
| "learning_rate": 1.1937535882101281e-05, |
| "loss": 1.0241, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.037782749192145165, |
| "grad_norm": 0.5271244645118713, |
| "learning_rate": 1.0305368692688174e-05, |
| "loss": 0.9474, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.03877703206562267, |
| "grad_norm": 0.5122260451316833, |
| "learning_rate": 8.763798791745411e-06, |
| "loss": 1.1279, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.03877703206562267, |
| "eval_loss": 1.0933287143707275, |
| "eval_runtime": 34.2822, |
| "eval_samples_per_second": 12.368, |
| "eval_steps_per_second": 6.184, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.039771314939100175, |
| "grad_norm": 0.5207390785217285, |
| "learning_rate": 7.3223304703363135e-06, |
| "loss": 0.85, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.04076559781257768, |
| "grad_norm": 0.49141305685043335, |
| "learning_rate": 5.989850859999227e-06, |
| "loss": 0.8256, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.041759880686055184, |
| "grad_norm": 0.49803686141967773, |
| "learning_rate": 4.7745751406263165e-06, |
| "loss": 1.0561, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.04275416355953269, |
| "grad_norm": 0.5928795337677002, |
| "learning_rate": 3.6839958911476957e-06, |
| "loss": 1.0151, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.043748446433010194, |
| "grad_norm": 0.4802905023097992, |
| "learning_rate": 2.7248368952908053e-06, |
| "loss": 0.9441, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.0447427293064877, |
| "grad_norm": 0.45927828550338745, |
| "learning_rate": 1.9030116872178316e-06, |
| "loss": 0.9223, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.0457370121799652, |
| "grad_norm": 0.5768618583679199, |
| "learning_rate": 1.2235870926211619e-06, |
| "loss": 1.1136, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.04673129505344271, |
| "grad_norm": 0.6009936332702637, |
| "learning_rate": 6.907519900580861e-07, |
| "loss": 1.1245, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.047725577926920205, |
| "grad_norm": 0.9392962455749512, |
| "learning_rate": 3.077914851215585e-07, |
| "loss": 1.2505, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.04871986080039771, |
| "grad_norm": 0.5324287414550781, |
| "learning_rate": 7.706665667180091e-08, |
| "loss": 0.8628, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.049714143673875215, |
| "grad_norm": 0.4643092751502991, |
| "learning_rate": 0.0, |
| "loss": 0.9188, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.7547965428137984e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
