| { |
| "best_global_step": 700, |
| "best_metric": 0.5273797512054443, |
| "best_model_checkpoint": "/dgx2/pawangcs/Trained_Models/Phi4-3shot/checkpoint-700", |
| "epoch": 1.9190672153635115, |
| "eval_steps": 100, |
| "global_step": 700, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.27434842249657065, |
| "grad_norm": 0.6248233914375305, |
| "learning_rate": 0.0002179699417406859, |
| "loss": 0.832540283203125, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.27434842249657065, |
| "eval_loss": 0.6426836252212524, |
| "eval_runtime": 1160.1148, |
| "eval_samples_per_second": 2.515, |
| "eval_steps_per_second": 0.629, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5486968449931413, |
| "grad_norm": 0.6830066442489624, |
| "learning_rate": 0.0002157366837530479, |
| "loss": 0.6157448196411133, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5486968449931413, |
| "eval_loss": 0.6033561825752258, |
| "eval_runtime": 405.4127, |
| "eval_samples_per_second": 7.198, |
| "eval_steps_per_second": 1.801, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.823045267489712, |
| "grad_norm": 0.6402314901351929, |
| "learning_rate": 0.00021002940172700765, |
| "loss": 0.5921715927124024, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.823045267489712, |
| "eval_loss": 0.5785361528396606, |
| "eval_runtime": 405.9414, |
| "eval_samples_per_second": 7.188, |
| "eval_steps_per_second": 1.798, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.0960219478737998, |
| "grad_norm": 0.8042563796043396, |
| "learning_rate": 0.00020103385405654221, |
| "loss": 0.5310408401489258, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.0960219478737998, |
| "eval_loss": 0.5722617506980896, |
| "eval_runtime": 406.5022, |
| "eval_samples_per_second": 7.178, |
| "eval_steps_per_second": 1.796, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.3703703703703702, |
| "grad_norm": 0.6911748051643372, |
| "learning_rate": 0.0001890428243259542, |
| "loss": 0.45402183532714846, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.3703703703703702, |
| "eval_loss": 0.5583283305168152, |
| "eval_runtime": 404.6307, |
| "eval_samples_per_second": 7.212, |
| "eval_steps_per_second": 1.804, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.6447187928669411, |
| "grad_norm": 0.6612902283668518, |
| "learning_rate": 0.00017444659190372805, |
| "loss": 0.4490911865234375, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.6447187928669411, |
| "eval_loss": 0.5405105948448181, |
| "eval_runtime": 464.3862, |
| "eval_samples_per_second": 6.284, |
| "eval_steps_per_second": 1.572, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.9190672153635115, |
| "grad_norm": 0.6907134652137756, |
| "learning_rate": 0.00015772022928155024, |
| "loss": 0.446926155090332, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.9190672153635115, |
| "eval_loss": 0.5273797512054443, |
| "eval_runtime": 407.3892, |
| "eval_samples_per_second": 7.163, |
| "eval_steps_per_second": 1.792, |
| "step": 700 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 1825, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.187699724261908e+18, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
