| { | |
| "best_metric": 11.915068626403809, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.061609549480169425, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012321909896033886, | |
| "grad_norm": 0.07178230583667755, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9363, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012321909896033886, | |
| "eval_loss": 11.935738563537598, | |
| "eval_runtime": 0.7485, | |
| "eval_samples_per_second": 66.799, | |
| "eval_steps_per_second": 17.368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002464381979206777, | |
| "grad_norm": 0.08658259361982346, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9365, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0036965729688101657, | |
| "grad_norm": 0.07627413421869278, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.936, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004928763958413554, | |
| "grad_norm": 0.06695223599672318, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9371, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0061609549480169425, | |
| "grad_norm": 0.07730023562908173, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9373, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0073931459376203315, | |
| "grad_norm": 0.08005542308092117, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9352, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00862533692722372, | |
| "grad_norm": 0.08071882277727127, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9335, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009857527916827109, | |
| "grad_norm": 0.09804913401603699, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9324, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011089718906430497, | |
| "grad_norm": 0.0916438177227974, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9314, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012321909896033885, | |
| "grad_norm": 0.11245589703321457, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9334, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013554100885637273, | |
| "grad_norm": 0.15651749074459076, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.931, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014786291875240663, | |
| "grad_norm": 0.165276437997818, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.929, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01601848286484405, | |
| "grad_norm": 0.10776877403259277, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9321, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01725067385444744, | |
| "grad_norm": 0.08762101083993912, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9322, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.018482864844050827, | |
| "grad_norm": 0.1009363904595375, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9318, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019715055833654217, | |
| "grad_norm": 0.10808451473712921, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9334, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020947246823257604, | |
| "grad_norm": 0.10856714844703674, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9314, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.022179437812860994, | |
| "grad_norm": 0.1188795268535614, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.931, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.023411628802464383, | |
| "grad_norm": 0.1201574057340622, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9307, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02464381979206777, | |
| "grad_norm": 0.13258428871631622, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9308, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02587601078167116, | |
| "grad_norm": 0.14269478619098663, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9279, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.027108201771274546, | |
| "grad_norm": 0.16528292000293732, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9243, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.028340392760877936, | |
| "grad_norm": 0.1886805295944214, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9237, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.029572583750481326, | |
| "grad_norm": 0.19681161642074585, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9207, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.030804774740084712, | |
| "grad_norm": 0.23278166353702545, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9213, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.030804774740084712, | |
| "eval_loss": 11.922410011291504, | |
| "eval_runtime": 0.4466, | |
| "eval_samples_per_second": 111.969, | |
| "eval_steps_per_second": 29.112, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0320369657296881, | |
| "grad_norm": 0.14079074561595917, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9271, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03326915671929149, | |
| "grad_norm": 0.1567951738834381, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.9258, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03450134770889488, | |
| "grad_norm": 0.16366036236286163, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9249, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03573353869849827, | |
| "grad_norm": 0.1638365387916565, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.926, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.036965729688101655, | |
| "grad_norm": 0.17652325332164764, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9231, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03819792067770504, | |
| "grad_norm": 0.15289749205112457, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9256, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.039430111667308435, | |
| "grad_norm": 0.21502667665481567, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.918, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04066230265691182, | |
| "grad_norm": 0.16959460079669952, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9229, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04189449364651521, | |
| "grad_norm": 0.18960808217525482, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.921, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0431266846361186, | |
| "grad_norm": 0.20932435989379883, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.9176, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04435887562572199, | |
| "grad_norm": 0.2247883677482605, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9166, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.045591066615325374, | |
| "grad_norm": 0.2090682089328766, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.9216, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04682325760492877, | |
| "grad_norm": 0.19237466156482697, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.9209, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04805544859453215, | |
| "grad_norm": 0.15888743102550507, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.9218, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04928763958413554, | |
| "grad_norm": 0.1693039834499359, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.9215, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.050519830573738926, | |
| "grad_norm": 0.18711499869823456, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9198, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05175202156334232, | |
| "grad_norm": 0.1777219921350479, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9196, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.052984212552945706, | |
| "grad_norm": 0.17029505968093872, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.9212, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05421640354254909, | |
| "grad_norm": 0.1959444284439087, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.92, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.055448594532152486, | |
| "grad_norm": 0.19401198625564575, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.9157, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05668078552175587, | |
| "grad_norm": 0.18555186688899994, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.9181, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05791297651135926, | |
| "grad_norm": 0.207061767578125, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.9177, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05914516750096265, | |
| "grad_norm": 0.19741538166999817, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9168, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06037735849056604, | |
| "grad_norm": 0.2410183548927307, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.9102, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.061609549480169425, | |
| "grad_norm": 0.27445363998413086, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9102, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.061609549480169425, | |
| "eval_loss": 11.915068626403809, | |
| "eval_runtime": 0.4086, | |
| "eval_samples_per_second": 122.365, | |
| "eval_steps_per_second": 31.815, | |
| "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": 417735062323200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |