| { | |
| "best_metric": 0.17765101790428162, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6010518407212622, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012021036814425245, | |
| "grad_norm": 2.3797473907470703, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0836, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012021036814425245, | |
| "eval_loss": 3.279723882675171, | |
| "eval_runtime": 3.5916, | |
| "eval_samples_per_second": 13.921, | |
| "eval_steps_per_second": 3.62, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02404207362885049, | |
| "grad_norm": 2.795534372329712, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5328, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03606311044327573, | |
| "grad_norm": 2.296565055847168, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.0337, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04808414725770098, | |
| "grad_norm": 1.519423246383667, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.2429, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06010518407212622, | |
| "grad_norm": 1.6455806493759155, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.1802, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07212622088655146, | |
| "grad_norm": 1.7605764865875244, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.9603, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08414725770097671, | |
| "grad_norm": 1.3515708446502686, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.7666, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09616829451540196, | |
| "grad_norm": 1.8652924299240112, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.647, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10818933132982719, | |
| "grad_norm": 2.0083870887756348, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.6241, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12021036814425244, | |
| "grad_norm": 1.7070515155792236, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.6184, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1322314049586777, | |
| "grad_norm": 1.4008787870407104, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.5239, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14425244177310292, | |
| "grad_norm": 1.700635313987732, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.543, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1562734785875282, | |
| "grad_norm": 2.88712215423584, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.3132, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.16829451540195342, | |
| "grad_norm": 3.047614336013794, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.657, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.18031555221637866, | |
| "grad_norm": 1.6900277137756348, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.521, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19233658903080392, | |
| "grad_norm": 1.0074207782745361, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.3502, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.20435762584522915, | |
| "grad_norm": 0.9452375173568726, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.2876, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.21637866265965439, | |
| "grad_norm": 1.2094521522521973, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.3112, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.22839969947407965, | |
| "grad_norm": 1.0654776096343994, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.2754, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.24042073628850488, | |
| "grad_norm": 0.916575014591217, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.2157, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25244177310293014, | |
| "grad_norm": 0.9523929953575134, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.1841, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2644628099173554, | |
| "grad_norm": 0.8460620641708374, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.1881, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2764838467317806, | |
| "grad_norm": 0.96810382604599, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.153, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.28850488354620585, | |
| "grad_norm": 0.9148619771003723, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1122, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3005259203606311, | |
| "grad_norm": 1.086602807044983, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1507, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3005259203606311, | |
| "eval_loss": 0.3329227864742279, | |
| "eval_runtime": 3.2198, | |
| "eval_samples_per_second": 15.529, | |
| "eval_steps_per_second": 4.038, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3125469571750564, | |
| "grad_norm": 1.4042689800262451, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.858, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3245679939894816, | |
| "grad_norm": 0.9543754458427429, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.2523, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.33658903080390684, | |
| "grad_norm": 0.7887716293334961, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.183, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3486100676183321, | |
| "grad_norm": 0.5809823274612427, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.1227, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3606311044327573, | |
| "grad_norm": 0.5213009715080261, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.1021, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.37265214124718254, | |
| "grad_norm": 0.7495287656784058, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.1105, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.38467317806160783, | |
| "grad_norm": 0.7786484956741333, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.1269, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.39669421487603307, | |
| "grad_norm": 0.9299702644348145, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.1516, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4087152516904583, | |
| "grad_norm": 0.7013904452323914, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0962, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.42073628850488354, | |
| "grad_norm": 0.7207347750663757, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.1143, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.43275732531930877, | |
| "grad_norm": 1.1033786535263062, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.1311, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.44477836213373406, | |
| "grad_norm": 1.0275310277938843, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.11, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4567993989481593, | |
| "grad_norm": 1.1997830867767334, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.747, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.46882043576258453, | |
| "grad_norm": 1.128527045249939, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.1777, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.48084147257700977, | |
| "grad_norm": 1.0002365112304688, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.167, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.492862509391435, | |
| "grad_norm": 0.6199818253517151, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.088, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5048835462058603, | |
| "grad_norm": 0.7970647215843201, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.1077, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5169045830202855, | |
| "grad_norm": 1.1322096586227417, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.1165, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5289256198347108, | |
| "grad_norm": 0.6188007593154907, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0835, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.540946656649136, | |
| "grad_norm": 0.9790140986442566, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0758, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5529676934635612, | |
| "grad_norm": 0.5559037923812866, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0812, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5649887302779865, | |
| "grad_norm": 0.7460304498672485, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0698, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5770097670924117, | |
| "grad_norm": 0.6634911894798279, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0954, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5890308039068369, | |
| "grad_norm": 0.8137192726135254, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0842, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6010518407212622, | |
| "grad_norm": 0.7482524514198303, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1316, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6010518407212622, | |
| "eval_loss": 0.17765101790428162, | |
| "eval_runtime": 3.227, | |
| "eval_samples_per_second": 15.494, | |
| "eval_steps_per_second": 4.028, | |
| "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": 5.776961889086996e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |