| { | |
| "best_metric": 11.688956260681152, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.019794630706420884, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00039589261412841767, | |
| "grad_norm": 0.660332202911377, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7831, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039589261412841767, | |
| "eval_loss": 11.771588325500488, | |
| "eval_runtime": 0.1661, | |
| "eval_samples_per_second": 301.019, | |
| "eval_steps_per_second": 78.265, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007917852282568353, | |
| "grad_norm": 0.8166902661323547, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7861, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001187677842385253, | |
| "grad_norm": 0.7606441378593445, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.7854, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015835704565136707, | |
| "grad_norm": 0.795393168926239, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.778, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0019794630706420884, | |
| "grad_norm": 0.705385684967041, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.7718, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002375355684770506, | |
| "grad_norm": 0.6611534357070923, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.7576, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002771248298898924, | |
| "grad_norm": 0.6945996880531311, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.7553, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0031671409130273414, | |
| "grad_norm": 0.6706441640853882, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.7538, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003563033527155759, | |
| "grad_norm": 0.6835849285125732, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.7428, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003958926141284177, | |
| "grad_norm": 0.6822184324264526, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.7323, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004354818755412594, | |
| "grad_norm": 0.6467664241790771, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.7443, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004750711369541012, | |
| "grad_norm": 0.8287248611450195, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.6987, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005146603983669429, | |
| "grad_norm": 0.8050388693809509, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.7223, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005542496597797848, | |
| "grad_norm": 0.8280295729637146, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.7638, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005938389211926265, | |
| "grad_norm": 0.8300166726112366, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.752, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006334281826054683, | |
| "grad_norm": 0.8016781210899353, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.7529, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0067301744401831, | |
| "grad_norm": 0.8565889000892639, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.7516, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007126067054311518, | |
| "grad_norm": 0.759502649307251, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.736, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007521959668439935, | |
| "grad_norm": 0.7802271842956543, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.7279, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007917852282568354, | |
| "grad_norm": 0.8107627034187317, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.7233, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00831374489669677, | |
| "grad_norm": 0.8617903590202332, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.7283, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008709637510825189, | |
| "grad_norm": 0.7742336392402649, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.7023, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009105530124953607, | |
| "grad_norm": 0.8047570586204529, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.7137, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009501422739082024, | |
| "grad_norm": 0.8058279752731323, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.6884, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009897315353210442, | |
| "grad_norm": 1.0013773441314697, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.6581, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009897315353210442, | |
| "eval_loss": 11.716475486755371, | |
| "eval_runtime": 0.1593, | |
| "eval_samples_per_second": 313.955, | |
| "eval_steps_per_second": 81.628, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010293207967338859, | |
| "grad_norm": 0.9336376786231995, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.7377, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.010689100581467277, | |
| "grad_norm": 0.9597164988517761, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.7309, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011084993195595695, | |
| "grad_norm": 0.9862052798271179, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.7275, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.011480885809724112, | |
| "grad_norm": 0.9398750066757202, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.7179, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01187677842385253, | |
| "grad_norm": 0.9106470346450806, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.7238, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012272671037980947, | |
| "grad_norm": 0.9347615242004395, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.7057, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.012668563652109366, | |
| "grad_norm": 0.8774538636207581, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.6895, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.013064456266237782, | |
| "grad_norm": 0.9370536208152771, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.6945, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0134603488803662, | |
| "grad_norm": 0.9235231876373291, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.6921, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.013856241494494619, | |
| "grad_norm": 0.9303660988807678, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.6912, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014252134108623036, | |
| "grad_norm": 0.8900956511497498, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.6827, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.014648026722751454, | |
| "grad_norm": 1.000619649887085, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.6509, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01504391933687987, | |
| "grad_norm": 0.9968812465667725, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.6788, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.015439811951008289, | |
| "grad_norm": 0.9819913506507874, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.7155, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.015835704565136707, | |
| "grad_norm": 1.0137593746185303, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.7058, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.016231597179265124, | |
| "grad_norm": 0.9970508813858032, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.6978, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01662748979339354, | |
| "grad_norm": 1.027045726776123, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.7046, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01702338240752196, | |
| "grad_norm": 0.8774479627609253, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.6764, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.017419275021650377, | |
| "grad_norm": 0.9244899153709412, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.6821, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.017815167635778794, | |
| "grad_norm": 0.9668672680854797, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.6844, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.018211060249907214, | |
| "grad_norm": 0.9782124161720276, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.6838, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01860695286403563, | |
| "grad_norm": 0.9850881099700928, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.6841, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.019002845478164047, | |
| "grad_norm": 0.9748925566673279, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.6842, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.019398738092292464, | |
| "grad_norm": 0.9819056987762451, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.6558, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.019794630706420884, | |
| "grad_norm": 1.0381964445114136, | |
| "learning_rate": 1e-05, | |
| "loss": 11.6251, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.019794630706420884, | |
| "eval_loss": 11.688956260681152, | |
| "eval_runtime": 0.1594, | |
| "eval_samples_per_second": 313.714, | |
| "eval_steps_per_second": 81.566, | |
| "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": 163886137344000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |