| { | |
| "best_metric": 0.34419700503349304, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.059417706476530004, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011883541295306002, | |
| "grad_norm": 3.8583266735076904, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0588, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011883541295306002, | |
| "eval_loss": 7.116491794586182, | |
| "eval_runtime": 4.2971, | |
| "eval_samples_per_second": 11.636, | |
| "eval_steps_per_second": 3.025, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023767082590612004, | |
| "grad_norm": 3.7670252323150635, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0283, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0035650623885918, | |
| "grad_norm": 4.636148929595947, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.5078, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004753416518122401, | |
| "grad_norm": 4.651632308959961, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.5027, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0059417706476530005, | |
| "grad_norm": 5.130126953125, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.8078, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0071301247771836, | |
| "grad_norm": 5.748180389404297, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.9374, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008318478906714201, | |
| "grad_norm": 4.101024627685547, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.2732, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009506833036244802, | |
| "grad_norm": 4.253706932067871, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.1, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0106951871657754, | |
| "grad_norm": 2.773369312286377, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.114, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011883541295306001, | |
| "grad_norm": 2.6358070373535156, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.0818, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013071895424836602, | |
| "grad_norm": 2.299405813217163, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.9123, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0142602495543672, | |
| "grad_norm": 3.731668710708618, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.2773, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015448603683897801, | |
| "grad_norm": 2.423055648803711, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.0221, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.016636957813428402, | |
| "grad_norm": 2.326035976409912, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.7976, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017825311942959002, | |
| "grad_norm": 2.6155567169189453, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.8461, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019013666072489603, | |
| "grad_norm": 1.5926434993743896, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.6395, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020202020202020204, | |
| "grad_norm": 1.8488845825195312, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.6839, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0213903743315508, | |
| "grad_norm": 1.5457555055618286, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.5364, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0225787284610814, | |
| "grad_norm": 1.8210150003433228, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.6909, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023767082590612002, | |
| "grad_norm": 1.565142273902893, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.5963, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024955436720142603, | |
| "grad_norm": 1.2754619121551514, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.5801, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.026143790849673203, | |
| "grad_norm": 1.2012678384780884, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.5503, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.027332144979203804, | |
| "grad_norm": 1.0641955137252808, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4726, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0285204991087344, | |
| "grad_norm": 1.842871904373169, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.7947, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.029708853238265002, | |
| "grad_norm": 1.9366096258163452, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.8874, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029708853238265002, | |
| "eval_loss": 0.5146859884262085, | |
| "eval_runtime": 2.3469, | |
| "eval_samples_per_second": 21.305, | |
| "eval_steps_per_second": 5.539, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.030897207367795602, | |
| "grad_norm": 1.3286805152893066, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7485, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03208556149732621, | |
| "grad_norm": 1.5405412912368774, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.5451, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.033273915626856804, | |
| "grad_norm": 1.233147382736206, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.5002, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0344622697563874, | |
| "grad_norm": 1.0292119979858398, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4288, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.035650623885918005, | |
| "grad_norm": 1.3014405965805054, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.4733, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0368389780154486, | |
| "grad_norm": 1.4494003057479858, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.494, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.038027332144979206, | |
| "grad_norm": 1.3643971681594849, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.5351, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 1.1455105543136597, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.525, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04040404040404041, | |
| "grad_norm": 1.1091620922088623, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.447, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.041592394533571005, | |
| "grad_norm": 1.2071998119354248, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.6096, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 1.4972431659698486, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.5981, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.043969102792632206, | |
| "grad_norm": 1.3450655937194824, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.6781, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0451574569221628, | |
| "grad_norm": 1.5478042364120483, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.8215, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04634581105169341, | |
| "grad_norm": 1.301225185394287, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4669, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.047534165181224004, | |
| "grad_norm": 1.215628743171692, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4811, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0487225193107546, | |
| "grad_norm": 1.021491289138794, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.37, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.049910873440285206, | |
| "grad_norm": 1.1163012981414795, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.3745, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0510992275698158, | |
| "grad_norm": 1.2882263660430908, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.4898, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05228758169934641, | |
| "grad_norm": 1.1887884140014648, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.4594, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.053475935828877004, | |
| "grad_norm": 1.2757731676101685, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.3928, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05466428995840761, | |
| "grad_norm": 1.0226280689239502, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.4737, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.055852644087938205, | |
| "grad_norm": 1.1754165887832642, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.5274, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0570409982174688, | |
| "grad_norm": 1.3346490859985352, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.5732, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.058229352346999406, | |
| "grad_norm": 1.156563401222229, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.5148, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.059417706476530004, | |
| "grad_norm": 1.2868088483810425, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6007, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.059417706476530004, | |
| "eval_loss": 0.34419700503349304, | |
| "eval_runtime": 2.344, | |
| "eval_samples_per_second": 21.331, | |
| "eval_steps_per_second": 5.546, | |
| "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": 6.037089589846344e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |