| { | |
| "best_metric": 0.03248881921172142, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.40160642570281124, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008032128514056224, | |
| "grad_norm": 1.2944245338439941, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1673, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008032128514056224, | |
| "eval_loss": 0.24973352253437042, | |
| "eval_runtime": 5.3355, | |
| "eval_samples_per_second": 9.371, | |
| "eval_steps_per_second": 2.436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01606425702811245, | |
| "grad_norm": 1.5140950679779053, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2614, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024096385542168676, | |
| "grad_norm": 1.3528778553009033, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.5811, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0321285140562249, | |
| "grad_norm": 1.0362355709075928, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.6793, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.040160642570281124, | |
| "grad_norm": 4.546697616577148, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.7611, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04819277108433735, | |
| "grad_norm": 0.8056478500366211, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.481, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05622489959839357, | |
| "grad_norm": 0.8942221999168396, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.1482, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0642570281124498, | |
| "grad_norm": 1.588688611984253, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.3126, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07228915662650602, | |
| "grad_norm": 5.0189056396484375, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 3.8842, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08032128514056225, | |
| "grad_norm": 4.0612921714782715, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.5376, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08835341365461848, | |
| "grad_norm": 2.6428403854370117, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6561, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0963855421686747, | |
| "grad_norm": 3.2785227298736572, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.6203, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10441767068273092, | |
| "grad_norm": 2.314138174057007, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.1542, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11244979919678715, | |
| "grad_norm": 1.5888618230819702, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.3159, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12048192771084337, | |
| "grad_norm": 1.0906137228012085, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5244, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1285140562248996, | |
| "grad_norm": 0.6349501609802246, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.498, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13654618473895583, | |
| "grad_norm": 2.2518177032470703, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.662, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14457831325301204, | |
| "grad_norm": 0.9098783135414124, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.9979, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15261044176706828, | |
| "grad_norm": 1.2482787370681763, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.6041, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1606425702811245, | |
| "grad_norm": 5.019254207611084, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.2294, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1686746987951807, | |
| "grad_norm": 4.074834823608398, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.0263, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17670682730923695, | |
| "grad_norm": 4.873847484588623, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.3144, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18473895582329317, | |
| "grad_norm": 0.9878688454627991, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1086, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1927710843373494, | |
| "grad_norm": 1.0189340114593506, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1161, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20080321285140562, | |
| "grad_norm": 0.7090588212013245, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0693, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20080321285140562, | |
| "eval_loss": 0.03601743280887604, | |
| "eval_runtime": 5.4403, | |
| "eval_samples_per_second": 9.191, | |
| "eval_steps_per_second": 2.39, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20883534136546184, | |
| "grad_norm": 0.546523928642273, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.1084, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.21686746987951808, | |
| "grad_norm": 0.4799603223800659, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.9756, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2248995983935743, | |
| "grad_norm": 0.5448339581489563, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.2519, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23293172690763053, | |
| "grad_norm": 0.4197559952735901, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.6386, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24096385542168675, | |
| "grad_norm": 0.5254598259925842, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.1602, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24899598393574296, | |
| "grad_norm": 0.5117546319961548, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.896, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2570281124497992, | |
| "grad_norm": 0.7296671271324158, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.3107, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.26506024096385544, | |
| "grad_norm": 1.1409062147140503, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.4452, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.27309236947791166, | |
| "grad_norm": 2.794985055923462, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.6358, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.28112449799196787, | |
| "grad_norm": 14.123102188110352, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.8044, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": 0.567223310470581, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0429, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2971887550200803, | |
| "grad_norm": 0.49257692694664, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0362, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.30522088353413657, | |
| "grad_norm": 1.7930783033370972, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.5118, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3132530120481928, | |
| "grad_norm": 0.8841942548751831, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4644, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.321285140562249, | |
| "grad_norm": 0.30380862951278687, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.3108, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3293172690763052, | |
| "grad_norm": 0.4109308421611786, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.8338, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3373493975903614, | |
| "grad_norm": 0.37386301159858704, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.1962, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3453815261044177, | |
| "grad_norm": 0.5806508660316467, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.1743, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3534136546184739, | |
| "grad_norm": 0.7219189405441284, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.6337, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3614457831325301, | |
| "grad_norm": 0.889197826385498, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.6495, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.36947791164658633, | |
| "grad_norm": 2.914224863052368, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.9181, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.37751004016064255, | |
| "grad_norm": 3.432201862335205, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.3767, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3855421686746988, | |
| "grad_norm": 0.26241597533226013, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.028, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.39357429718875503, | |
| "grad_norm": 0.29001384973526, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0255, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.40160642570281124, | |
| "grad_norm": 0.43991392850875854, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0338, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.40160642570281124, | |
| "eval_loss": 0.03248881921172142, | |
| "eval_runtime": 5.4412, | |
| "eval_samples_per_second": 9.189, | |
| "eval_steps_per_second": 2.389, | |
| "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": 5.0840048862285005e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |