| { | |
| "best_metric": 10.3728666305542, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01464611328768628, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002929222657537256, | |
| "grad_norm": 0.025340523570775986, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 10.3728, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002929222657537256, | |
| "eval_loss": 10.373064994812012, | |
| "eval_runtime": 14.2255, | |
| "eval_samples_per_second": 404.203, | |
| "eval_steps_per_second": 101.086, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005858445315074512, | |
| "grad_norm": 0.02154785953462124, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 10.3758, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008787667972611768, | |
| "grad_norm": 0.02488698996603489, | |
| "learning_rate": 1.5e-06, | |
| "loss": 10.3737, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011716890630149024, | |
| "grad_norm": 0.02246084250509739, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 10.3739, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001464611328768628, | |
| "grad_norm": 0.024568594992160797, | |
| "learning_rate": 2.5e-06, | |
| "loss": 10.3741, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017575335945223536, | |
| "grad_norm": 0.02053692936897278, | |
| "learning_rate": 3e-06, | |
| "loss": 10.3734, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002050455860276079, | |
| "grad_norm": 0.02354443445801735, | |
| "learning_rate": 3.5e-06, | |
| "loss": 10.3743, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0023433781260298048, | |
| "grad_norm": 0.02450806088745594, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 10.3753, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0026363003917835304, | |
| "grad_norm": 0.024845441803336143, | |
| "learning_rate": 4.5e-06, | |
| "loss": 10.3759, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002929222657537256, | |
| "grad_norm": 0.0253719724714756, | |
| "learning_rate": 5e-06, | |
| "loss": 10.3731, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0032221449232909816, | |
| "grad_norm": 0.02256913110613823, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 10.3737, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003515067189044707, | |
| "grad_norm": 0.0258257444947958, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 10.3741, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0038079894547984328, | |
| "grad_norm": 0.03032153844833374, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 10.3725, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004100911720552158, | |
| "grad_norm": 0.026030762121081352, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 10.3745, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004393833986305884, | |
| "grad_norm": 0.02117944322526455, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 10.3723, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0046867562520596096, | |
| "grad_norm": 0.029438018798828125, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 10.3753, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004979678517813335, | |
| "grad_norm": 0.026865482330322266, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 10.376, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005272600783567061, | |
| "grad_norm": 0.026240473613142967, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 10.3722, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005565523049320786, | |
| "grad_norm": 0.02773893065750599, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 10.3746, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005858445315074512, | |
| "grad_norm": 0.024244513362646103, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 10.3727, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0061513675808282375, | |
| "grad_norm": 0.028417950496077538, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 10.3738, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006444289846581963, | |
| "grad_norm": 0.028397424146533012, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 10.371, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006737212112335689, | |
| "grad_norm": 0.026659617200493813, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 10.3725, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007030134378089414, | |
| "grad_norm": 0.029838740825653076, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 10.3733, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00732305664384314, | |
| "grad_norm": 0.03084457293152809, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 10.3728, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0076159789095968655, | |
| "grad_norm": 0.028473639860749245, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 10.3729, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007908901175350591, | |
| "grad_norm": 0.028158007189631462, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 10.3724, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008201823441104317, | |
| "grad_norm": 0.028451206162571907, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 10.3726, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008494745706858042, | |
| "grad_norm": 0.026855139061808586, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 10.3725, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008787667972611768, | |
| "grad_norm": 0.028105178847908974, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 10.3753, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009080590238365494, | |
| "grad_norm": 0.02491852454841137, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 10.3756, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009373512504119219, | |
| "grad_norm": 0.02876235358417034, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 10.3714, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009666434769872945, | |
| "grad_norm": 0.033276189118623734, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 10.3722, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00995935703562667, | |
| "grad_norm": 0.030624445527791977, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 10.3726, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.010252279301380396, | |
| "grad_norm": 0.0296514630317688, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 10.3737, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010545201567134121, | |
| "grad_norm": 0.029347486793994904, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 10.3741, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010838123832887847, | |
| "grad_norm": 0.03406284749507904, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 10.3732, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.011131046098641573, | |
| "grad_norm": 0.03096814826130867, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 10.3737, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.011423968364395298, | |
| "grad_norm": 0.03231000900268555, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 10.3728, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011716890630149024, | |
| "grad_norm": 0.03423743322491646, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 10.3727, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01200981289590275, | |
| "grad_norm": 0.03633436933159828, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 10.371, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.012302735161656475, | |
| "grad_norm": 0.03613651916384697, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 10.3698, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0125956574274102, | |
| "grad_norm": 0.03508604317903519, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 10.3709, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012888579693163926, | |
| "grad_norm": 0.03531428426504135, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 10.3693, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.013181501958917652, | |
| "grad_norm": 0.0372382253408432, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 10.3731, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013474424224671377, | |
| "grad_norm": 0.037255220115184784, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 10.3696, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013767346490425103, | |
| "grad_norm": 0.03376002609729767, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 10.3722, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.014060268756178829, | |
| "grad_norm": 0.03821876645088196, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 10.3675, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.014353191021932554, | |
| "grad_norm": 0.04366350546479225, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 10.3713, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01464611328768628, | |
| "grad_norm": 0.04582428187131882, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 10.3714, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01464611328768628, | |
| "eval_loss": 10.3728666305542, | |
| "eval_runtime": 13.841, | |
| "eval_samples_per_second": 415.431, | |
| "eval_steps_per_second": 103.894, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5491756892160.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |