| { |
| "best_metric": 0.5204638472032742, |
| "best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-229", |
| "epoch": 9.822646657571623, |
| "eval_steps": 500, |
| "global_step": 450, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9822646657571623, |
| "eval_accuracy": 0.4631650750341064, |
| "eval_loss": 1.5760536193847656, |
| "eval_runtime": 39.2455, |
| "eval_samples_per_second": 37.355, |
| "eval_steps_per_second": 4.688, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.9863574351978173, |
| "eval_accuracy": 0.48090040927694405, |
| "eval_loss": 1.4805983304977417, |
| "eval_runtime": 39.2635, |
| "eval_samples_per_second": 37.338, |
| "eval_steps_per_second": 4.686, |
| "step": 91 |
| }, |
| { |
| "epoch": 2.990450204638472, |
| "eval_accuracy": 0.5102319236016372, |
| "eval_loss": 1.3860737085342407, |
| "eval_runtime": 39.1657, |
| "eval_samples_per_second": 37.431, |
| "eval_steps_per_second": 4.698, |
| "step": 137 |
| }, |
| { |
| "epoch": 3.9945429740791267, |
| "eval_accuracy": 0.5129604365620737, |
| "eval_loss": 1.3546371459960938, |
| "eval_runtime": 39.3014, |
| "eval_samples_per_second": 37.301, |
| "eval_steps_per_second": 4.682, |
| "step": 183 |
| }, |
| { |
| "epoch": 4.998635743519782, |
| "eval_accuracy": 0.5204638472032742, |
| "eval_loss": 1.3680198192596436, |
| "eval_runtime": 39.2818, |
| "eval_samples_per_second": 37.32, |
| "eval_steps_per_second": 4.684, |
| "step": 229 |
| }, |
| { |
| "epoch": 5.980900409276944, |
| "eval_accuracy": 0.5068212824010914, |
| "eval_loss": 1.3954683542251587, |
| "eval_runtime": 39.3425, |
| "eval_samples_per_second": 37.262, |
| "eval_steps_per_second": 4.677, |
| "step": 274 |
| }, |
| { |
| "epoch": 6.984993178717599, |
| "eval_accuracy": 0.5088676671214188, |
| "eval_loss": 1.4225218296051025, |
| "eval_runtime": 39.3807, |
| "eval_samples_per_second": 37.226, |
| "eval_steps_per_second": 4.672, |
| "step": 320 |
| }, |
| { |
| "epoch": 7.9890859481582535, |
| "eval_accuracy": 0.5054570259208732, |
| "eval_loss": 1.441685676574707, |
| "eval_runtime": 39.4269, |
| "eval_samples_per_second": 37.183, |
| "eval_steps_per_second": 4.667, |
| "step": 366 |
| }, |
| { |
| "epoch": 8.993178717598909, |
| "eval_accuracy": 0.5075034106412005, |
| "eval_loss": 1.4451576471328735, |
| "eval_runtime": 39.3805, |
| "eval_samples_per_second": 37.227, |
| "eval_steps_per_second": 4.672, |
| "step": 412 |
| }, |
| { |
| "epoch": 9.822646657571623, |
| "eval_accuracy": 0.5122783083219645, |
| "eval_loss": 1.4489926099777222, |
| "eval_runtime": 39.4874, |
| "eval_samples_per_second": 37.126, |
| "eval_steps_per_second": 4.66, |
| "step": 450 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 450, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.671870367055708e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
