| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.384, |
| "eval_steps": 100, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.032, |
| "grad_norm": 25.09992027282715, |
| "learning_rate": 4.3999999999999997e-07, |
| "loss": 1.0546456146240235, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.064, |
| "grad_norm": 44.00643539428711, |
| "learning_rate": 9.399999999999999e-07, |
| "loss": 1.2045201873779297, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.064, |
| "eval_loss": 0.15259136259555817, |
| "eval_runtime": 320.8429, |
| "eval_samples_per_second": 6.234, |
| "eval_steps_per_second": 1.558, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.096, |
| "grad_norm": 409.5372314453125, |
| "learning_rate": 9.511111111111111e-07, |
| "loss": 0.8091524505615234, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.128, |
| "grad_norm": 4.935479640960693, |
| "learning_rate": 8.955555555555555e-07, |
| "loss": 0.9019821166992188, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.128, |
| "eval_loss": 0.1397811472415924, |
| "eval_runtime": 320.5384, |
| "eval_samples_per_second": 6.24, |
| "eval_steps_per_second": 1.56, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 2.68009877204895, |
| "learning_rate": 8.399999999999999e-07, |
| "loss": 0.8488493347167969, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.192, |
| "grad_norm": 250.0933380126953, |
| "learning_rate": 7.844444444444445e-07, |
| "loss": 0.8013427734375, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.192, |
| "eval_loss": 0.13730598986148834, |
| "eval_runtime": 320.7296, |
| "eval_samples_per_second": 6.236, |
| "eval_steps_per_second": 1.559, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.224, |
| "grad_norm": 3.164937973022461, |
| "learning_rate": 7.288888888888889e-07, |
| "loss": 0.6347025299072265, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.256, |
| "grad_norm": 120.01831817626953, |
| "learning_rate": 6.733333333333333e-07, |
| "loss": 0.960202407836914, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.256, |
| "eval_loss": 0.12297496199607849, |
| "eval_runtime": 320.4414, |
| "eval_samples_per_second": 6.241, |
| "eval_steps_per_second": 1.56, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.288, |
| "grad_norm": 25.20623779296875, |
| "learning_rate": 6.177777777777777e-07, |
| "loss": 0.7631096649169922, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 124.12076568603516, |
| "learning_rate": 5.622222222222222e-07, |
| "loss": 0.9197311401367188, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_loss": 0.13506844639778137, |
| "eval_runtime": 320.4909, |
| "eval_samples_per_second": 6.24, |
| "eval_steps_per_second": 1.56, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.352, |
| "grad_norm": 24.420225143432617, |
| "learning_rate": 5.066666666666667e-07, |
| "loss": 0.7606878662109375, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.384, |
| "grad_norm": 354.97039794921875, |
| "learning_rate": 4.511111111111111e-07, |
| "loss": 0.7917160034179688, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.384, |
| "eval_loss": 0.14342211186885834, |
| "eval_runtime": 313.4668, |
| "eval_samples_per_second": 6.38, |
| "eval_steps_per_second": 1.595, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 3.570791931934176e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
