| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.32, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.008, |
| "grad_norm": 0.11767578125, |
| "learning_rate": 0.00016, |
| "loss": 0.6554988384246826, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.016, |
| "grad_norm": 0.126953125, |
| "learning_rate": 0.00019870967741935483, |
| "loss": 0.6316752910614014, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.024, |
| "grad_norm": 0.05908203125, |
| "learning_rate": 0.0001970967741935484, |
| "loss": 0.6129528522491455, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.032, |
| "grad_norm": 0.062255859375, |
| "learning_rate": 0.00019548387096774195, |
| "loss": 0.60089111328125, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.0546875, |
| "learning_rate": 0.00019387096774193548, |
| "loss": 0.6051591873168946, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.048, |
| "grad_norm": 0.053955078125, |
| "learning_rate": 0.00019225806451612904, |
| "loss": 0.5910581588745117, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.056, |
| "grad_norm": 0.04931640625, |
| "learning_rate": 0.0001906451612903226, |
| "loss": 0.5913372993469238, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.064, |
| "grad_norm": 0.05078125, |
| "learning_rate": 0.00018903225806451616, |
| "loss": 0.5835432052612305, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.072, |
| "grad_norm": 0.047119140625, |
| "learning_rate": 0.0001874193548387097, |
| "loss": 0.5777533054351807, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.04833984375, |
| "learning_rate": 0.00018580645161290325, |
| "loss": 0.5595584392547608, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.088, |
| "grad_norm": 0.1103515625, |
| "learning_rate": 0.0001841935483870968, |
| "loss": 0.5782830715179443, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.096, |
| "grad_norm": 0.052001953125, |
| "learning_rate": 0.00018258064516129033, |
| "loss": 0.561436939239502, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.104, |
| "grad_norm": 0.0537109375, |
| "learning_rate": 0.00018096774193548387, |
| "loss": 0.5930795192718505, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.112, |
| "grad_norm": 0.051513671875, |
| "learning_rate": 0.00017935483870967742, |
| "loss": 0.5740991592407226, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.053955078125, |
| "learning_rate": 0.00017774193548387098, |
| "loss": 0.5711933135986328, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.128, |
| "grad_norm": 0.054443359375, |
| "learning_rate": 0.0001761290322580645, |
| "loss": 0.5878489494323731, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.136, |
| "grad_norm": 0.083984375, |
| "learning_rate": 0.00017451612903225807, |
| "loss": 0.5775240421295166, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.144, |
| "grad_norm": 0.06298828125, |
| "learning_rate": 0.00017290322580645163, |
| "loss": 0.5785224914550782, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.152, |
| "grad_norm": 0.058837890625, |
| "learning_rate": 0.00017129032258064516, |
| "loss": 0.5774213314056397, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.0556640625, |
| "learning_rate": 0.00016967741935483872, |
| "loss": 0.5569428443908692, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.168, |
| "grad_norm": 0.057373046875, |
| "learning_rate": 0.00016806451612903228, |
| "loss": 0.5698188304901123, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.176, |
| "grad_norm": 0.057861328125, |
| "learning_rate": 0.0001664516129032258, |
| "loss": 0.574033784866333, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.184, |
| "grad_norm": 0.057373046875, |
| "learning_rate": 0.00016483870967741937, |
| "loss": 0.5798182010650634, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.192, |
| "grad_norm": 0.06884765625, |
| "learning_rate": 0.00016322580645161292, |
| "loss": 0.5746054172515869, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.37109375, |
| "learning_rate": 0.00016161290322580645, |
| "loss": 0.5746851921081543, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.208, |
| "grad_norm": 0.059326171875, |
| "learning_rate": 0.00016, |
| "loss": 0.5720233917236328, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.216, |
| "grad_norm": 0.058349609375, |
| "learning_rate": 0.00015838709677419357, |
| "loss": 0.5694709777832031, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.224, |
| "grad_norm": 0.06005859375, |
| "learning_rate": 0.0001567741935483871, |
| "loss": 0.56185941696167, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.232, |
| "grad_norm": 0.06005859375, |
| "learning_rate": 0.00015516129032258063, |
| "loss": 0.5761864662170411, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.059814453125, |
| "learning_rate": 0.0001535483870967742, |
| "loss": 0.5672729969024658, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.248, |
| "grad_norm": 0.05859375, |
| "learning_rate": 0.00015193548387096775, |
| "loss": 0.5709065437316895, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.256, |
| "grad_norm": 0.06298828125, |
| "learning_rate": 0.00015032258064516128, |
| "loss": 0.5686789989471436, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.264, |
| "grad_norm": 0.0595703125, |
| "learning_rate": 0.00014870967741935484, |
| "loss": 0.5607232570648193, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.272, |
| "grad_norm": 0.06298828125, |
| "learning_rate": 0.0001470967741935484, |
| "loss": 0.5666838645935058, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.062255859375, |
| "learning_rate": 0.00014548387096774196, |
| "loss": 0.5663557052612305, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.288, |
| "grad_norm": 0.06103515625, |
| "learning_rate": 0.00014387096774193549, |
| "loss": 0.5619307518005371, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.296, |
| "grad_norm": 0.06494140625, |
| "learning_rate": 0.00014225806451612904, |
| "loss": 0.5675935268402099, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.304, |
| "grad_norm": 0.09375, |
| "learning_rate": 0.0001406451612903226, |
| "loss": 0.558326530456543, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.312, |
| "grad_norm": 0.068359375, |
| "learning_rate": 0.00013903225806451613, |
| "loss": 0.5571943759918213, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.06787109375, |
| "learning_rate": 0.0001374193548387097, |
| "loss": 0.5767090797424317, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 625, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.881105397909977e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
