| { | |
| "best_metric": 4.2027716636657715, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.002471699045924168, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.886796183696674e-05, | |
| "grad_norm": 11.413167953491211, | |
| "learning_rate": 2e-05, | |
| "loss": 7.2123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.886796183696674e-05, | |
| "eval_loss": 7.52592658996582, | |
| "eval_runtime": 1135.6075, | |
| "eval_samples_per_second": 3.75, | |
| "eval_steps_per_second": 1.876, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019773592367393347, | |
| "grad_norm": 8.532044410705566, | |
| "learning_rate": 4e-05, | |
| "loss": 6.2251, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00029660388551090017, | |
| "grad_norm": 11.336974143981934, | |
| "learning_rate": 6e-05, | |
| "loss": 7.5963, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00039547184734786694, | |
| "grad_norm": 11.541173934936523, | |
| "learning_rate": 8e-05, | |
| "loss": 7.196, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004943398091848336, | |
| "grad_norm": 13.50476360321045, | |
| "learning_rate": 0.0001, | |
| "loss": 6.456, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004943398091848336, | |
| "eval_loss": 6.623749732971191, | |
| "eval_runtime": 1148.4533, | |
| "eval_samples_per_second": 3.708, | |
| "eval_steps_per_second": 1.855, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005932077710218003, | |
| "grad_norm": 11.225502967834473, | |
| "learning_rate": 0.00012, | |
| "loss": 6.1921, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006920757328587672, | |
| "grad_norm": 11.57914924621582, | |
| "learning_rate": 0.00014, | |
| "loss": 5.5553, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007909436946957339, | |
| "grad_norm": 10.31067943572998, | |
| "learning_rate": 0.00016, | |
| "loss": 5.242, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008898116565327006, | |
| "grad_norm": 11.511025428771973, | |
| "learning_rate": 0.00018, | |
| "loss": 4.6341, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009886796183696672, | |
| "grad_norm": 9.778360366821289, | |
| "learning_rate": 0.0002, | |
| "loss": 4.4974, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009886796183696672, | |
| "eval_loss": 4.582190990447998, | |
| "eval_runtime": 1129.0691, | |
| "eval_samples_per_second": 3.772, | |
| "eval_steps_per_second": 1.887, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001087547580206634, | |
| "grad_norm": 8.830248832702637, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 4.7394, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0011864155420436007, | |
| "grad_norm": 9.814061164855957, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 4.3392, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0012852835038805676, | |
| "grad_norm": 9.087082862854004, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 4.4741, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0013841514657175343, | |
| "grad_norm": 8.418217658996582, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 4.065, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.001483019427554501, | |
| "grad_norm": 9.908651351928711, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.3679, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001483019427554501, | |
| "eval_loss": 4.397404193878174, | |
| "eval_runtime": 1118.2098, | |
| "eval_samples_per_second": 3.809, | |
| "eval_steps_per_second": 1.905, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015818873893914678, | |
| "grad_norm": 9.443998336791992, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.4487, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0016807553512284345, | |
| "grad_norm": 12.183076858520508, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 4.3741, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0017796233130654012, | |
| "grad_norm": 12.255166053771973, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 3.8147, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001878491274902368, | |
| "grad_norm": 8.746517181396484, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.8452, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0019773592367393344, | |
| "grad_norm": 7.476744174957275, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.9029, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0019773592367393344, | |
| "eval_loss": 4.2419514656066895, | |
| "eval_runtime": 1136.2772, | |
| "eval_samples_per_second": 3.748, | |
| "eval_steps_per_second": 1.875, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002076227198576301, | |
| "grad_norm": 10.04932689666748, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 4.6902, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002175095160413268, | |
| "grad_norm": 7.8697919845581055, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 3.581, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0022739631222502346, | |
| "grad_norm": 9.06474781036377, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 4.3666, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0023728310840872013, | |
| "grad_norm": 9.24133586883545, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 4.4222, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002471699045924168, | |
| "grad_norm": 9.29888916015625, | |
| "learning_rate": 0.0, | |
| "loss": 4.5624, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002471699045924168, | |
| "eval_loss": 4.2027716636657715, | |
| "eval_runtime": 1136.0717, | |
| "eval_samples_per_second": 3.749, | |
| "eval_steps_per_second": 1.875, | |
| "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": 4777728540672000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |