| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 4, |
| "global_step": 21, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.047619047619047616, |
| "grad_norm": 19.672672271728516, |
| "learning_rate": 0.0, |
| "loss": 3.0009765625, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09523809523809523, |
| "grad_norm": 3.495249032974243, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 2.94921875, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 0.785777747631073, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 2.62127685546875, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 1.4822601079940796, |
| "learning_rate": 5e-05, |
| "loss": 3.09619140625, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 1.172309160232544, |
| "learning_rate": 4.965817444277468e-05, |
| "loss": 2.478271484375, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "eval_loss": 2.8265380859375, |
| "eval_runtime": 6.3944, |
| "eval_samples_per_second": 0.626, |
| "eval_steps_per_second": 0.156, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 1.0528908967971802, |
| "learning_rate": 4.864308396768294e-05, |
| "loss": 2.6767578125, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 2.0651323795318604, |
| "learning_rate": 4.6985571585149876e-05, |
| "loss": 2.90771484375, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 1.249152421951294, |
| "learning_rate": 4.473599997017701e-05, |
| "loss": 2.60498046875, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.9470052123069763, |
| "learning_rate": 4.1962721217947135e-05, |
| "loss": 1.57421875, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "eval_loss": 2.736328125, |
| "eval_runtime": 5.9877, |
| "eval_samples_per_second": 0.668, |
| "eval_steps_per_second": 0.167, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 1.259230136871338, |
| "learning_rate": 3.875e-05, |
| "loss": 2.66015625, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5238095238095238, |
| "grad_norm": 10.03598690032959, |
| "learning_rate": 3.519545322482755e-05, |
| "loss": 2.697021484375, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 4.0796403884887695, |
| "learning_rate": 3.140708399750594e-05, |
| "loss": 2.570068359375, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "grad_norm": 0.9835389256477356, |
| "learning_rate": 2.7500000000000004e-05, |
| "loss": 2.524658203125, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "eval_loss": 2.6021728515625, |
| "eval_runtime": 6.0027, |
| "eval_samples_per_second": 0.666, |
| "eval_steps_per_second": 0.167, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 56.96556091308594, |
| "learning_rate": 2.359291600249407e-05, |
| "loss": 2.89990234375, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 5.033456325531006, |
| "learning_rate": 1.9804546775172457e-05, |
| "loss": 2.611328125, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 2.694977045059204, |
| "learning_rate": 1.6250000000000005e-05, |
| "loss": 2.3192138671875, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "grad_norm": 3.9417147636413574, |
| "learning_rate": 1.3037278782052863e-05, |
| "loss": 2.55517578125, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "eval_loss": 2.5360107421875, |
| "eval_runtime": 6.1985, |
| "eval_samples_per_second": 0.645, |
| "eval_steps_per_second": 0.161, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 4.908124923706055, |
| "learning_rate": 1.0264000029822999e-05, |
| "loss": 2.6435546875, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.9047619047619048, |
| "grad_norm": 6.779687881469727, |
| "learning_rate": 8.01442841485013e-06, |
| "loss": 2.009033203125, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 1.1810510158538818, |
| "learning_rate": 6.356916032317063e-06, |
| "loss": 2.4130859375, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.2115916013717651, |
| "learning_rate": 5.341825557225321e-06, |
| "loss": 2.400390625, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.504150390625, |
| "eval_runtime": 5.9924, |
| "eval_samples_per_second": 0.668, |
| "eval_steps_per_second": 0.167, |
| "step": 21 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 21, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1485673054168678e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
