| { | |
| "best_metric": 2.1456618309020996, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01063264221158958, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "grad_norm": 4.344120979309082, | |
| "learning_rate": 2e-05, | |
| "loss": 8.7225, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 2.2007393836975098, | |
| "eval_runtime": 309.1751, | |
| "eval_samples_per_second": 3.202, | |
| "eval_steps_per_second": 1.601, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008506113769271664, | |
| "grad_norm": 4.502124309539795, | |
| "learning_rate": 4e-05, | |
| "loss": 8.7309, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "grad_norm": 4.4900641441345215, | |
| "learning_rate": 6e-05, | |
| "loss": 8.8287, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017012227538543328, | |
| "grad_norm": 5.5868144035339355, | |
| "learning_rate": 8e-05, | |
| "loss": 9.0612, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "grad_norm": 5.150924205780029, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0809, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "eval_loss": 2.1832621097564697, | |
| "eval_runtime": 308.8333, | |
| "eval_samples_per_second": 3.206, | |
| "eval_steps_per_second": 1.603, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "grad_norm": 4.976151943206787, | |
| "learning_rate": 0.00012, | |
| "loss": 8.8457, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029771398192450825, | |
| "grad_norm": 5.121574401855469, | |
| "learning_rate": 0.00014, | |
| "loss": 9.051, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0034024455077086655, | |
| "grad_norm": 4.654540538787842, | |
| "learning_rate": 0.00016, | |
| "loss": 8.783, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "grad_norm": 4.982942581176758, | |
| "learning_rate": 0.00018, | |
| "loss": 8.2208, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "grad_norm": 4.907604217529297, | |
| "learning_rate": 0.0002, | |
| "loss": 8.124, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "eval_loss": 2.158656358718872, | |
| "eval_runtime": 310.6757, | |
| "eval_samples_per_second": 3.187, | |
| "eval_steps_per_second": 1.593, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "grad_norm": 4.688698768615723, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 8.5195, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005103668261562998, | |
| "grad_norm": 4.8131794929504395, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 9.5152, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005528973950026581, | |
| "grad_norm": 4.646464824676514, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 7.5373, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005954279638490165, | |
| "grad_norm": 5.341791152954102, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 9.2033, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "grad_norm": 4.57265567779541, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 8.2836, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "eval_loss": 2.1536974906921387, | |
| "eval_runtime": 312.2097, | |
| "eval_samples_per_second": 3.171, | |
| "eval_steps_per_second": 1.585, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006804891015417331, | |
| "grad_norm": 4.516714572906494, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 8.0979, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007230196703880914, | |
| "grad_norm": 4.64660120010376, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 8.7766, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007655502392344498, | |
| "grad_norm": 4.283811569213867, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 8.0383, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00808080808080808, | |
| "grad_norm": 5.0667643547058105, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 8.5667, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "grad_norm": 4.93750524520874, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 7.8461, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "eval_loss": 2.1466376781463623, | |
| "eval_runtime": 308.6858, | |
| "eval_samples_per_second": 3.207, | |
| "eval_steps_per_second": 1.604, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008931419457735247, | |
| "grad_norm": 4.635622978210449, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 8.4835, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "grad_norm": 5.024051189422607, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 8.4714, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009782030834662414, | |
| "grad_norm": 4.305144786834717, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 8.1257, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "grad_norm": 3.969085693359375, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 7.8921, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01063264221158958, | |
| "grad_norm": 4.106435298919678, | |
| "learning_rate": 0.0, | |
| "loss": 8.6033, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01063264221158958, | |
| "eval_loss": 2.1456618309020996, | |
| "eval_runtime": 309.1335, | |
| "eval_samples_per_second": 3.203, | |
| "eval_steps_per_second": 1.601, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 8544265206497280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |