| { | |
| "best_metric": 11.751538276672363, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2206287920573635, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00441257584114727, | |
| "grad_norm": 0.03916708379983902, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00441257584114727, | |
| "eval_loss": 11.75829792022705, | |
| "eval_runtime": 0.1152, | |
| "eval_samples_per_second": 433.976, | |
| "eval_steps_per_second": 112.834, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00882515168229454, | |
| "grad_norm": 0.04253336414694786, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7627, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013237727523441808, | |
| "grad_norm": 0.042270563542842865, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.7635, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01765030336458908, | |
| "grad_norm": 0.0455668568611145, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.7626, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02206287920573635, | |
| "grad_norm": 0.04789022356271744, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.7608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.026475455046883617, | |
| "grad_norm": 0.053647249937057495, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.762, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03088803088803089, | |
| "grad_norm": 0.056196682155132294, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.7602, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03530060672917816, | |
| "grad_norm": 0.062173619866371155, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.763, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.039713182570325425, | |
| "grad_norm": 0.058516975492239, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.7619, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0441257584114727, | |
| "grad_norm": 0.059458985924720764, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.7615, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04853833425261997, | |
| "grad_norm": 0.06595244258642197, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.7588, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.052950910093767234, | |
| "grad_norm": 0.08006404340267181, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.7586, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.057363485934914506, | |
| "grad_norm": 0.056580327451229095, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.7608, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06177606177606178, | |
| "grad_norm": 0.05059433355927467, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.7602, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06618863761720904, | |
| "grad_norm": 0.05608620494604111, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.7602, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07060121345835632, | |
| "grad_norm": 0.05768270418047905, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.7597, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07501378929950359, | |
| "grad_norm": 0.058973509818315506, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.7601, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07942636514065085, | |
| "grad_norm": 0.06731297075748444, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.7583, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08383894098179813, | |
| "grad_norm": 0.06289275735616684, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.759, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0882515168229454, | |
| "grad_norm": 0.0705365464091301, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.7586, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09266409266409266, | |
| "grad_norm": 0.07340474426746368, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.7604, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09707666850523994, | |
| "grad_norm": 0.07441547513008118, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.7541, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1014892443463872, | |
| "grad_norm": 0.09309042990207672, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.7575, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10590182018753447, | |
| "grad_norm": 0.09298382699489594, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.7559, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11031439602868175, | |
| "grad_norm": 0.11296705901622772, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.7559, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11031439602868175, | |
| "eval_loss": 11.754063606262207, | |
| "eval_runtime": 0.1144, | |
| "eval_samples_per_second": 437.174, | |
| "eval_steps_per_second": 113.665, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11472697186982901, | |
| "grad_norm": 0.08237963169813156, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.7582, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11913954771097628, | |
| "grad_norm": 0.0781407356262207, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.7578, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12355212355212356, | |
| "grad_norm": 0.08831605315208435, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.7569, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12796469939327082, | |
| "grad_norm": 0.0830259621143341, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.7563, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13237727523441808, | |
| "grad_norm": 0.08338623493909836, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.7598, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13678985107556535, | |
| "grad_norm": 0.09287534654140472, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.7559, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14120242691671264, | |
| "grad_norm": 0.08480775356292725, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.7557, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1456150027578599, | |
| "grad_norm": 0.10712478309869766, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.7569, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15002757859900717, | |
| "grad_norm": 0.1056855097413063, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.7546, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15444015444015444, | |
| "grad_norm": 0.11568643897771835, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.7539, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1588527302813017, | |
| "grad_norm": 0.12338628619909286, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.7537, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.1299927532672882, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.7543, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16767788196359626, | |
| "grad_norm": 0.09283430874347687, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.7571, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17209045780474352, | |
| "grad_norm": 0.0892544612288475, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.7577, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1765030336458908, | |
| "grad_norm": 0.08588219434022903, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.7591, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18091560948703805, | |
| "grad_norm": 0.10914891213178635, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.7575, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18532818532818532, | |
| "grad_norm": 0.10082217305898666, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.7547, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1897407611693326, | |
| "grad_norm": 0.10159717500209808, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.7576, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.19415333701047988, | |
| "grad_norm": 0.10012318938970566, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.754, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.19856591285162714, | |
| "grad_norm": 0.11955250799655914, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.7546, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2029784886927744, | |
| "grad_norm": 0.10700767487287521, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.7574, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.20739106453392167, | |
| "grad_norm": 0.10580254346132278, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.7561, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.21180364037506894, | |
| "grad_norm": 0.10959888994693756, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.7556, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 0.12163785099983215, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.7515, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2206287920573635, | |
| "grad_norm": 0.1607298105955124, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7545, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2206287920573635, | |
| "eval_loss": 11.751538276672363, | |
| "eval_runtime": 0.1129, | |
| "eval_samples_per_second": 442.842, | |
| "eval_steps_per_second": 115.139, | |
| "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": 163886137344000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |