| { |
| "best_metric": 1.6555372476577759, |
| "best_model_checkpoint": "./nix2_7_checkpoints/checkpoint-100", |
| "epoch": 0.005781808983485708, |
| "eval_steps": 50, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0005781808983485708, |
| "grad_norm": 0.42287012934684753, |
| "learning_rate": 0.00018181818181818183, |
| "loss": 2.6194, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0011563617966971417, |
| "grad_norm": 0.440746545791626, |
| "learning_rate": 0.00019971129134476473, |
| "loss": 2.219, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0017345426950457123, |
| "grad_norm": 0.5202638506889343, |
| "learning_rate": 0.00019871542617383743, |
| "loss": 1.9173, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0023127235933942834, |
| "grad_norm": 0.33755865693092346, |
| "learning_rate": 0.000197015936819118, |
| "loss": 1.8698, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.002890904491742854, |
| "grad_norm": 0.30062955617904663, |
| "learning_rate": 0.0001946249369071837, |
| "loss": 1.7915, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.002890904491742854, |
| "eval_loss": 1.7323133945465088, |
| "eval_runtime": 48829.3841, |
| "eval_samples_per_second": 0.296, |
| "eval_steps_per_second": 0.296, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0034690853900914247, |
| "grad_norm": 0.3231092691421509, |
| "learning_rate": 0.00019155946901614702, |
| "loss": 1.6959, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.004047266288439996, |
| "grad_norm": 0.30537882447242737, |
| "learning_rate": 0.00018784138319950398, |
| "loss": 1.7047, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.004625447186788567, |
| "grad_norm": 0.26564449071884155, |
| "learning_rate": 0.00018349718124324076, |
| "loss": 1.7114, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.005203628085137137, |
| "grad_norm": 0.369289368391037, |
| "learning_rate": 0.00017855782776630483, |
| "loss": 1.5732, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.005781808983485708, |
| "grad_norm": 0.2947627902030945, |
| "learning_rate": 0.00017305852951087798, |
| "loss": 1.7628, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.005781808983485708, |
| "eval_loss": 1.6555372476577759, |
| "eval_runtime": 44170.1173, |
| "eval_samples_per_second": 0.327, |
| "eval_steps_per_second": 0.327, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 383, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "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": 6531344184115200.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
