| { | |
| "best_metric": 0.186006560921669, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.02464875523786049, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004929751047572097, | |
| "grad_norm": 16.109819412231445, | |
| "learning_rate": 5e-05, | |
| "loss": 29.4533, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004929751047572097, | |
| "eval_loss": 0.9603370428085327, | |
| "eval_runtime": 3.0611, | |
| "eval_samples_per_second": 16.334, | |
| "eval_steps_per_second": 4.247, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009859502095144195, | |
| "grad_norm": 20.44527816772461, | |
| "learning_rate": 0.0001, | |
| "loss": 27.02, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014789253142716292, | |
| "grad_norm": 27.137901306152344, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 28.5982, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001971900419028839, | |
| "grad_norm": 31.249736785888672, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 27.7378, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002464875523786049, | |
| "grad_norm": 33.9106330871582, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 19.9321, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029578506285432584, | |
| "grad_norm": 29.641433715820312, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 14.4626, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034508257333004683, | |
| "grad_norm": 18.87112045288086, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.2571, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003943800838057678, | |
| "grad_norm": 12.238442420959473, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 8.5361, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004436775942814888, | |
| "grad_norm": 11.49522590637207, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 7.6979, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004929751047572098, | |
| "grad_norm": 16.27753257751465, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 8.7148, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005422726152329307, | |
| "grad_norm": 16.755895614624023, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 8.6156, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005915701257086517, | |
| "grad_norm": 15.086666107177734, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 8.4236, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006408676361843727, | |
| "grad_norm": 24.53133773803711, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 21.0469, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006901651466600937, | |
| "grad_norm": 23.84539031982422, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 17.6924, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007394626571358146, | |
| "grad_norm": 19.023969650268555, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 14.8849, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007887601676115356, | |
| "grad_norm": 15.09223461151123, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 9.2037, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008380576780872565, | |
| "grad_norm": 13.912789344787598, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 9.4201, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008873551885629776, | |
| "grad_norm": 18.199228286743164, | |
| "learning_rate": 7.75e-05, | |
| "loss": 9.6571, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009366526990386986, | |
| "grad_norm": 17.265899658203125, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 8.2732, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009859502095144195, | |
| "grad_norm": 12.391765594482422, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.3309, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010352477199901405, | |
| "grad_norm": 8.548321723937988, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 5.1052, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010845452304658615, | |
| "grad_norm": 6.970586776733398, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 5.9035, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011338427409415824, | |
| "grad_norm": 8.961589813232422, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 6.3156, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011831402514173034, | |
| "grad_norm": 13.788490295410156, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 6.0985, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012324377618930245, | |
| "grad_norm": 14.768447875976562, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 6.0537, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012324377618930245, | |
| "eval_loss": 0.2265699952840805, | |
| "eval_runtime": 3.1388, | |
| "eval_samples_per_second": 15.93, | |
| "eval_steps_per_second": 4.142, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012817352723687454, | |
| "grad_norm": 10.468292236328125, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 20.6504, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013310327828444664, | |
| "grad_norm": 11.983538627624512, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 14.0288, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013803302933201873, | |
| "grad_norm": 11.06685733795166, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 8.5962, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014296278037959083, | |
| "grad_norm": 8.283320426940918, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 7.9514, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014789253142716292, | |
| "grad_norm": 6.831525802612305, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 6.8261, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015282228247473502, | |
| "grad_norm": 6.675940036773682, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 5.9154, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01577520335223071, | |
| "grad_norm": 5.194748878479004, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 5.2149, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01626817845698792, | |
| "grad_norm": 4.787224292755127, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 4.336, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01676115356174513, | |
| "grad_norm": 4.844122886657715, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.0652, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01725412866650234, | |
| "grad_norm": 4.37100887298584, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 4.0931, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.017747103771259553, | |
| "grad_norm": 6.856547832489014, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 5.6895, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.018240078876016762, | |
| "grad_norm": 7.979983806610107, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.8833, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.018733053980773972, | |
| "grad_norm": 8.421024322509766, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 15.118, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01922602908553118, | |
| "grad_norm": 9.07979965209961, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 14.3319, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01971900419028839, | |
| "grad_norm": 6.959233283996582, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 8.4428, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0202119792950456, | |
| "grad_norm": 11.418706893920898, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 7.1254, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02070495439980281, | |
| "grad_norm": 6.823760509490967, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 6.6503, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02119792950456002, | |
| "grad_norm": 5.575032711029053, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 6.2792, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02169090460931723, | |
| "grad_norm": 5.068197250366211, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 4.4281, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02218387971407444, | |
| "grad_norm": 5.049072742462158, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 4.1483, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.022676854818831648, | |
| "grad_norm": 4.566128253936768, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 4.1247, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.023169829923588858, | |
| "grad_norm": 4.03365421295166, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.581, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.023662805028346067, | |
| "grad_norm": 5.189533233642578, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.5164, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.024155780133103277, | |
| "grad_norm": 6.00453519821167, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.8618, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02464875523786049, | |
| "grad_norm": 8.213972091674805, | |
| "learning_rate": 1e-05, | |
| "loss": 3.8589, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02464875523786049, | |
| "eval_loss": 0.186006560921669, | |
| "eval_runtime": 3.1298, | |
| "eval_samples_per_second": 15.976, | |
| "eval_steps_per_second": 4.154, | |
| "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": 2.972701001200435e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |