| { | |
| "best_metric": 10.375311851501465, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.03411028993746447, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011370096645821489, | |
| "eval_loss": 10.37795639038086, | |
| "eval_runtime": 4.5144, | |
| "eval_samples_per_second": 164.14, | |
| "eval_steps_per_second": 41.201, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034110289937464467, | |
| "grad_norm": 0.022033361718058586, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3806, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005685048322910745, | |
| "eval_loss": 10.377598762512207, | |
| "eval_runtime": 4.4571, | |
| "eval_samples_per_second": 166.253, | |
| "eval_steps_per_second": 41.731, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006822057987492893, | |
| "grad_norm": 0.02438768371939659, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 10.3789, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01023308698123934, | |
| "grad_norm": 0.037406694144010544, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 10.3787, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01137009664582149, | |
| "eval_loss": 10.376873970031738, | |
| "eval_runtime": 4.5982, | |
| "eval_samples_per_second": 161.149, | |
| "eval_steps_per_second": 40.45, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013644115974985787, | |
| "grad_norm": 0.03667740151286125, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 10.377, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017055144968732235, | |
| "grad_norm": 0.03651963546872139, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.376, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017055144968732235, | |
| "eval_loss": 10.376157760620117, | |
| "eval_runtime": 4.6278, | |
| "eval_samples_per_second": 160.119, | |
| "eval_steps_per_second": 40.192, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02046617396247868, | |
| "grad_norm": 0.03485073149204254, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 10.3759, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02274019329164298, | |
| "eval_loss": 10.375664710998535, | |
| "eval_runtime": 4.537, | |
| "eval_samples_per_second": 163.323, | |
| "eval_steps_per_second": 40.996, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023877202956225127, | |
| "grad_norm": 0.049262672662734985, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 10.3759, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.027288231949971573, | |
| "grad_norm": 0.04128611460328102, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 10.3746, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.028425241614553724, | |
| "eval_loss": 10.375368118286133, | |
| "eval_runtime": 4.6223, | |
| "eval_samples_per_second": 160.311, | |
| "eval_steps_per_second": 40.24, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.030699260943718023, | |
| "grad_norm": 0.04697146639227867, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 10.375, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03411028993746447, | |
| "grad_norm": 0.050780996680259705, | |
| "learning_rate": 0.0, | |
| "loss": 10.3761, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03411028993746447, | |
| "eval_loss": 10.375311851501465, | |
| "eval_runtime": 4.5568, | |
| "eval_samples_per_second": 162.614, | |
| "eval_steps_per_second": 40.818, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1582149009408.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |