| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0491228070175438, |
| "eval_steps": 30, |
| "global_step": 150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07017543859649122, |
| "grad_norm": 0.4250744879245758, |
| "learning_rate": 0.00019962469712828614, |
| "loss": 0.6094220161437989, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.14035087719298245, |
| "grad_norm": 0.30426689982414246, |
| "learning_rate": 0.00019543482507085482, |
| "loss": 0.5189157009124756, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.21052631578947367, |
| "grad_norm": 0.3195377588272095, |
| "learning_rate": 0.00018678252666130013, |
| "loss": 0.4654271602630615, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.21052631578947367, |
| "eval_loss": 0.4821685254573822, |
| "eval_runtime": 26.1957, |
| "eval_samples_per_second": 9.162, |
| "eval_steps_per_second": 2.29, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2807017543859649, |
| "grad_norm": 0.2729398012161255, |
| "learning_rate": 0.00017407237375691392, |
| "loss": 0.5165626049041748, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.3508771929824561, |
| "grad_norm": 0.34597083926200867, |
| "learning_rate": 0.0001578986789811849, |
| "loss": 0.5297622203826904, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.42105263157894735, |
| "grad_norm": 0.3952707350254059, |
| "learning_rate": 0.00013901770632605547, |
| "loss": 0.5074038982391358, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.42105263157894735, |
| "eval_loss": 0.47542476654052734, |
| "eval_runtime": 25.7324, |
| "eval_samples_per_second": 9.327, |
| "eval_steps_per_second": 2.332, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.49122807017543857, |
| "grad_norm": 0.2613320052623749, |
| "learning_rate": 0.00011831230908818563, |
| "loss": 0.5146247386932373, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.5614035087719298, |
| "grad_norm": 0.2839556932449341, |
| "learning_rate": 9.675064863002196e-05, |
| "loss": 0.44298686981201174, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.631578947368421, |
| "grad_norm": 0.3424423635005951, |
| "learning_rate": 7.534092423052381e-05, |
| "loss": 0.44837327003479005, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.631578947368421, |
| "eval_loss": 0.472128301858902, |
| "eval_runtime": 25.8951, |
| "eval_samples_per_second": 9.268, |
| "eval_steps_per_second": 2.317, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.7017543859649122, |
| "grad_norm": 0.2950887680053711, |
| "learning_rate": 5.5084230807412126e-05, |
| "loss": 0.4572721481323242, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.7719298245614035, |
| "grad_norm": 0.3997437059879303, |
| "learning_rate": 3.6927748831453836e-05, |
| "loss": 0.4888507843017578, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.8421052631578947, |
| "grad_norm": 0.30841732025146484, |
| "learning_rate": 2.1720455220364444e-05, |
| "loss": 0.4997568130493164, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.8421052631578947, |
| "eval_loss": 0.46787339448928833, |
| "eval_runtime": 25.8471, |
| "eval_samples_per_second": 9.285, |
| "eval_steps_per_second": 2.321, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.9122807017543859, |
| "grad_norm": 0.31729358434677124, |
| "learning_rate": 1.0173426121705576e-05, |
| "loss": 0.45314512252807615, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.9824561403508771, |
| "grad_norm": 0.3034511208534241, |
| "learning_rate": 2.826587782529444e-06, |
| "loss": 0.41479806900024413, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.0491228070175438, |
| "grad_norm": 0.3052826523780823, |
| "learning_rate": 2.347019815158724e-08, |
| "loss": 0.45969629287719727, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.0491228070175438, |
| "eval_loss": 0.46667739748954773, |
| "eval_runtime": 25.8488, |
| "eval_samples_per_second": 9.285, |
| "eval_steps_per_second": 2.321, |
| "step": 150 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 150, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 30, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9766840338321408.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
