| { | |
| "best_metric": 10.364180564880371, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.023276790130640986, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004655358026128197, | |
| "grad_norm": 0.08034619688987732, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004655358026128197, | |
| "eval_loss": 10.37507438659668, | |
| "eval_runtime": 0.1056, | |
| "eval_samples_per_second": 473.46, | |
| "eval_steps_per_second": 123.1, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009310716052256394, | |
| "grad_norm": 0.0749102234840393, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3809, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001396607407838459, | |
| "grad_norm": 0.06931249797344208, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3767, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018621432104512787, | |
| "grad_norm": 0.06932879984378815, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3765, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0023276790130640984, | |
| "grad_norm": 0.06687504798173904, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.374, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002793214815676918, | |
| "grad_norm": 0.06729339063167572, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3737, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003258750618289738, | |
| "grad_norm": 0.06792795658111572, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3732, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0037242864209025574, | |
| "grad_norm": 0.06860123574733734, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3749, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004189822223515377, | |
| "grad_norm": 0.07388696074485779, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3734, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004655358026128197, | |
| "grad_norm": 0.0747343897819519, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3742, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005120893828741016, | |
| "grad_norm": 0.07938987761735916, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3728, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005586429631353836, | |
| "grad_norm": 0.07385125011205673, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3744, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006051965433966656, | |
| "grad_norm": 0.08533329516649246, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3741, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006517501236579476, | |
| "grad_norm": 0.08624856919050217, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3741, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006983037039192295, | |
| "grad_norm": 0.08045453578233719, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3729, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007448572841805115, | |
| "grad_norm": 0.07829487323760986, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.373, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007914108644417935, | |
| "grad_norm": 0.08200827240943909, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3736, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008379644447030755, | |
| "grad_norm": 0.0861327275633812, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3708, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008845180249643574, | |
| "grad_norm": 0.08856945484876633, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3701, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009310716052256394, | |
| "grad_norm": 0.08527480810880661, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3688, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009776251854869213, | |
| "grad_norm": 0.09549330174922943, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3692, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010241787657482033, | |
| "grad_norm": 0.09057743847370148, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3644, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010707323460094852, | |
| "grad_norm": 0.09438870847225189, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3678, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011172859262707672, | |
| "grad_norm": 0.10676027089357376, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3717, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011638395065320493, | |
| "grad_norm": 0.12098844349384308, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3726, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011638395065320493, | |
| "eval_loss": 10.368098258972168, | |
| "eval_runtime": 0.1133, | |
| "eval_samples_per_second": 441.427, | |
| "eval_steps_per_second": 114.771, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012103930867933313, | |
| "grad_norm": 0.10627330094575882, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3702, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012569466670546132, | |
| "grad_norm": 0.10381853580474854, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.3708, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013035002473158952, | |
| "grad_norm": 0.10166678577661514, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.3696, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013500538275771771, | |
| "grad_norm": 0.0987962856888771, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3697, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01396607407838459, | |
| "grad_norm": 0.1027960553765297, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.3657, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01443160988099741, | |
| "grad_norm": 0.1086529791355133, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.3673, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01489714568361023, | |
| "grad_norm": 0.10278735309839249, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3675, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01536268148622305, | |
| "grad_norm": 0.11028151959180832, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3646, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01582821728883587, | |
| "grad_norm": 0.10963913053274155, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.367, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01629375309144869, | |
| "grad_norm": 0.1109132319688797, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.3666, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01675928889406151, | |
| "grad_norm": 0.12010210752487183, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.365, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01722482469667433, | |
| "grad_norm": 0.10872060805559158, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3677, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01769036049928715, | |
| "grad_norm": 0.11967775970697403, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3694, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.018155896301899968, | |
| "grad_norm": 0.12095995992422104, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.3682, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018621432104512788, | |
| "grad_norm": 0.1160871833562851, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3678, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019086967907125607, | |
| "grad_norm": 0.11703995615243912, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.3691, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.019552503709738427, | |
| "grad_norm": 0.1204780787229538, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.3658, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.020018039512351246, | |
| "grad_norm": 0.1138206347823143, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.3638, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.020483575314964066, | |
| "grad_norm": 0.11795376986265182, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3662, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.020949111117576885, | |
| "grad_norm": 0.12404084205627441, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3632, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021414646920189705, | |
| "grad_norm": 0.1252797544002533, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.3641, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.021880182722802524, | |
| "grad_norm": 0.13455331325531006, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.3666, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.022345718525415344, | |
| "grad_norm": 0.12587407231330872, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.3644, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.022811254328028163, | |
| "grad_norm": 0.13471944630146027, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.3673, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.023276790130640986, | |
| "grad_norm": 0.16384567320346832, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3668, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.023276790130640986, | |
| "eval_loss": 10.364180564880371, | |
| "eval_runtime": 0.1038, | |
| "eval_samples_per_second": 481.811, | |
| "eval_steps_per_second": 125.271, | |
| "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": 42768059596800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |