| { | |
| "best_metric": 1.475806474685669, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.13151405556468848, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026302811112937697, | |
| "grad_norm": 7.6924729347229, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9139, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026302811112937697, | |
| "eval_loss": 6.583785533905029, | |
| "eval_runtime": 2.2573, | |
| "eval_samples_per_second": 22.151, | |
| "eval_steps_per_second": 5.759, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005260562222587539, | |
| "grad_norm": 8.963078498840332, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2095, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007890843333881308, | |
| "grad_norm": 7.708944797515869, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.1646, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010521124445175079, | |
| "grad_norm": 5.140854835510254, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.3043, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013151405556468848, | |
| "grad_norm": 5.477720260620117, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.8263, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015781686667762616, | |
| "grad_norm": 6.843749523162842, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.6723, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018411967779056387, | |
| "grad_norm": 7.493031978607178, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.812, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.021042248890350158, | |
| "grad_norm": 6.828537940979004, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.5599, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023672530001643925, | |
| "grad_norm": 4.211589813232422, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.6797, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026302811112937696, | |
| "grad_norm": 5.306011199951172, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.4685, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028933092224231464, | |
| "grad_norm": 4.892298221588135, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.0411, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03156337333552523, | |
| "grad_norm": 5.788684368133545, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.8765, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034193654446819, | |
| "grad_norm": 7.938673496246338, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.1427, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03682393555811277, | |
| "grad_norm": 4.239195823669434, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.9294, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.039454216669406544, | |
| "grad_norm": 3.0556766986846924, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.9143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.042084497780700315, | |
| "grad_norm": 3.01393461227417, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.7901, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04471477889199408, | |
| "grad_norm": 2.964114189147949, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.8135, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04734506000328785, | |
| "grad_norm": 2.678053379058838, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.8461, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04997534111458162, | |
| "grad_norm": 2.649806022644043, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.959, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05260562222587539, | |
| "grad_norm": 2.9589452743530273, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.7594, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05523590333716916, | |
| "grad_norm": 3.0157201290130615, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.7822, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05786618444846293, | |
| "grad_norm": 3.3775577545166016, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.5996, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0604964655597567, | |
| "grad_norm": 4.172215461730957, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.5145, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06312674667105046, | |
| "grad_norm": 4.449634075164795, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.3848, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06575702778234424, | |
| "grad_norm": 5.117303371429443, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.4496, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06575702778234424, | |
| "eval_loss": 1.613996982574463, | |
| "eval_runtime": 2.3308, | |
| "eval_samples_per_second": 21.452, | |
| "eval_steps_per_second": 5.577, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.068387308893638, | |
| "grad_norm": 2.0202596187591553, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.5667, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07101759000493178, | |
| "grad_norm": 2.1556060314178467, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.5961, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07364787111622555, | |
| "grad_norm": 1.9927035570144653, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.5073, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07627815222751931, | |
| "grad_norm": 1.8589670658111572, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.5465, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07890843333881309, | |
| "grad_norm": 2.149338483810425, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.616, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08153871445010685, | |
| "grad_norm": 2.1401331424713135, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.511, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08416899556140063, | |
| "grad_norm": 3.1085312366485596, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.5366, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0867992766726944, | |
| "grad_norm": 3.0993728637695312, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.53, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08942955778398816, | |
| "grad_norm": 3.186367988586426, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.6375, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09205983889528194, | |
| "grad_norm": 3.874236583709717, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.5334, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0946901200065757, | |
| "grad_norm": 4.275596618652344, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.3862, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09732040111786948, | |
| "grad_norm": 3.7926650047302246, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.2366, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09995068222916324, | |
| "grad_norm": 3.127962827682495, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.454, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10258096334045701, | |
| "grad_norm": 2.497931957244873, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.3641, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10521124445175078, | |
| "grad_norm": 2.0440142154693604, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.4007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10784152556304455, | |
| "grad_norm": 2.033963680267334, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.5559, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11047180667433831, | |
| "grad_norm": 2.140683889389038, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.5221, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11310208778563209, | |
| "grad_norm": 2.208739757537842, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.5577, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11573236889692586, | |
| "grad_norm": 2.212786912918091, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.5415, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11836265000821963, | |
| "grad_norm": 2.4894113540649414, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.5774, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1209929311195134, | |
| "grad_norm": 2.980783224105835, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.6721, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12362321223080716, | |
| "grad_norm": 3.151621103286743, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.5915, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12625349334210093, | |
| "grad_norm": 3.5633890628814697, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.5143, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12888377445339472, | |
| "grad_norm": 3.7043654918670654, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.242, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13151405556468848, | |
| "grad_norm": 4.95023775100708, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3159, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13151405556468848, | |
| "eval_loss": 1.475806474685669, | |
| "eval_runtime": 2.3073, | |
| "eval_samples_per_second": 21.671, | |
| "eval_steps_per_second": 5.634, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |