| { |
| "best_metric": 0.7864583333333334, |
| "best_model_checkpoint": "Output_llama3_80-20_New/checkpoint-192", |
| "epoch": 12.0, |
| "eval_steps": 500, |
| "global_step": 1152, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5, |
| "eval_balanced_accuracy": 0.5509253870329415, |
| "eval_loss": 0.6700918078422546, |
| "eval_runtime": 63.4356, |
| "eval_samples_per_second": 3.027, |
| "eval_steps_per_second": 0.378, |
| "step": 96 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7864583333333334, |
| "eval_balanced_accuracy": 0.7730263157894737, |
| "eval_loss": 0.5816970467567444, |
| "eval_runtime": 81.877, |
| "eval_samples_per_second": 2.345, |
| "eval_steps_per_second": 0.293, |
| "step": 192 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.671875, |
| "eval_balanced_accuracy": 0.6611111111111111, |
| "eval_loss": 0.5816349983215332, |
| "eval_runtime": 79.9417, |
| "eval_samples_per_second": 2.402, |
| "eval_steps_per_second": 0.3, |
| "step": 288 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.734375, |
| "eval_balanced_accuracy": 0.6917016806722689, |
| "eval_loss": 0.5791379809379578, |
| "eval_runtime": 80.5316, |
| "eval_samples_per_second": 2.384, |
| "eval_steps_per_second": 0.298, |
| "step": 384 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7604166666666666, |
| "eval_balanced_accuracy": 0.727891156462585, |
| "eval_loss": 0.6088356971740723, |
| "eval_runtime": 80.2275, |
| "eval_samples_per_second": 2.393, |
| "eval_steps_per_second": 0.299, |
| "step": 480 |
| }, |
| { |
| "epoch": 5.208333333333333, |
| "grad_norm": 6.6746439933776855, |
| "learning_rate": 7.395833333333335e-06, |
| "loss": 0.6212, |
| "step": 500 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.6770833333333334, |
| "eval_balanced_accuracy": 0.6646667393912948, |
| "eval_loss": 0.5876281261444092, |
| "eval_runtime": 80.9461, |
| "eval_samples_per_second": 2.372, |
| "eval_steps_per_second": 0.296, |
| "step": 576 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.59375, |
| "eval_balanced_accuracy": 0.6351214003387916, |
| "eval_loss": 0.6212968826293945, |
| "eval_runtime": 80.028, |
| "eval_samples_per_second": 2.399, |
| "eval_steps_per_second": 0.3, |
| "step": 672 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.7395833333333334, |
| "eval_balanced_accuracy": 0.6975702456902402, |
| "eval_loss": 0.5972201228141785, |
| "eval_runtime": 70.9941, |
| "eval_samples_per_second": 2.704, |
| "eval_steps_per_second": 0.338, |
| "step": 768 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.7291666666666666, |
| "eval_balanced_accuracy": 0.6857699805068227, |
| "eval_loss": 0.6078045964241028, |
| "eval_runtime": 81.911, |
| "eval_samples_per_second": 2.344, |
| "eval_steps_per_second": 0.293, |
| "step": 864 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.6770833333333334, |
| "eval_balanced_accuracy": 0.6552448325411738, |
| "eval_loss": 0.61850506067276, |
| "eval_runtime": 82.3418, |
| "eval_samples_per_second": 2.332, |
| "eval_steps_per_second": 0.291, |
| "step": 960 |
| }, |
| { |
| "epoch": 10.416666666666666, |
| "grad_norm": 80.89810943603516, |
| "learning_rate": 4.791666666666668e-06, |
| "loss": 0.5248, |
| "step": 1000 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.6875, |
| "eval_balanced_accuracy": 0.6525843213997928, |
| "eval_loss": 0.6357616782188416, |
| "eval_runtime": 80.6861, |
| "eval_samples_per_second": 2.38, |
| "eval_steps_per_second": 0.297, |
| "step": 1056 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.71875, |
| "eval_balanced_accuracy": 0.6770025839793281, |
| "eval_loss": 0.6519039869308472, |
| "eval_runtime": 84.7662, |
| "eval_samples_per_second": 2.265, |
| "eval_steps_per_second": 0.283, |
| "step": 1152 |
| }, |
| { |
| "epoch": 12.0, |
| "step": 1152, |
| "total_flos": 1.4576163971176858e+17, |
| "train_loss": 0.561662839518653, |
| "train_runtime": 12634.972, |
| "train_samples_per_second": 1.216, |
| "train_steps_per_second": 0.152 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1920, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 10, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 10 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.4576163971176858e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
