| { | |
| "best_metric": 1.303216814994812, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.03406187908032927, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011353959693443088, | |
| "eval_loss": 1.7595603466033936, | |
| "eval_runtime": 15.1794, | |
| "eval_samples_per_second": 24.441, | |
| "eval_steps_per_second": 12.253, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034061879080329264, | |
| "grad_norm": 0.6357326507568359, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6886, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005676979846721544, | |
| "eval_loss": 1.6256749629974365, | |
| "eval_runtime": 14.3668, | |
| "eval_samples_per_second": 25.823, | |
| "eval_steps_per_second": 12.946, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006812375816065853, | |
| "grad_norm": 0.7150976061820984, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 1.6512, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01021856372409878, | |
| "grad_norm": 1.0526561737060547, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 1.5439, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011353959693443088, | |
| "eval_loss": 1.4340248107910156, | |
| "eval_runtime": 14.5386, | |
| "eval_samples_per_second": 25.518, | |
| "eval_steps_per_second": 12.793, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013624751632131706, | |
| "grad_norm": 0.5291152000427246, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.4267, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017030939540164634, | |
| "grad_norm": 0.6879667043685913, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.4713, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017030939540164634, | |
| "eval_loss": 1.3600554466247559, | |
| "eval_runtime": 15.3162, | |
| "eval_samples_per_second": 24.223, | |
| "eval_steps_per_second": 12.144, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02043712744819756, | |
| "grad_norm": 0.4458349347114563, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 1.1997, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.022707919386886176, | |
| "eval_loss": 1.3166388273239136, | |
| "eval_runtime": 14.737, | |
| "eval_samples_per_second": 25.175, | |
| "eval_steps_per_second": 12.621, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023843315356230486, | |
| "grad_norm": 0.42704302072525024, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 1.2463, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02724950326426341, | |
| "grad_norm": 0.5720973014831543, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 1.2871, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02838489923360772, | |
| "eval_loss": 1.3052393198013306, | |
| "eval_runtime": 15.1912, | |
| "eval_samples_per_second": 24.422, | |
| "eval_steps_per_second": 12.244, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03065569117229634, | |
| "grad_norm": 0.5630245804786682, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 1.2883, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03406187908032927, | |
| "grad_norm": 0.47691431641578674, | |
| "learning_rate": 0.0, | |
| "loss": 1.3533, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03406187908032927, | |
| "eval_loss": 1.303216814994812, | |
| "eval_runtime": 14.7075, | |
| "eval_samples_per_second": 25.225, | |
| "eval_steps_per_second": 12.647, | |
| "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": 4135709237575680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |