| { | |
| "best_metric": 11.926774978637695, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.18854584020740042, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002513944536098672, | |
| "grad_norm": 0.01306601706892252, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 11.9327, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002513944536098672, | |
| "eval_loss": 11.931513786315918, | |
| "eval_runtime": 0.2553, | |
| "eval_samples_per_second": 195.821, | |
| "eval_steps_per_second": 50.913, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005027889072197344, | |
| "grad_norm": 0.013035156764090061, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.9322, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007541833608296017, | |
| "grad_norm": 0.013919487595558167, | |
| "learning_rate": 0.0001, | |
| "loss": 11.932, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010055778144394689, | |
| "grad_norm": 0.012912580743432045, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 11.9316, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012569722680493361, | |
| "grad_norm": 0.01366867870092392, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 11.932, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015083667216592034, | |
| "grad_norm": 0.018193839117884636, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9317, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017597611752690707, | |
| "grad_norm": 0.019369425252079964, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 11.931, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020111556288789377, | |
| "grad_norm": 0.019250450655817986, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 11.9308, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02262550082488805, | |
| "grad_norm": 0.027681566774845123, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9314, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025139445360986723, | |
| "grad_norm": 0.028774602338671684, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 11.9326, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027653389897085396, | |
| "grad_norm": 0.03369531035423279, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 11.9304, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03016733443318407, | |
| "grad_norm": 0.038345273584127426, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.928, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03268127896928274, | |
| "grad_norm": 0.01788642816245556, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 11.9323, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.035195223505381415, | |
| "grad_norm": 0.01733534224331379, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 11.9322, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.037709168041480084, | |
| "grad_norm": 0.017722493037581444, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9322, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.040223112577578754, | |
| "grad_norm": 0.018521340563893318, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 11.9315, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04273705711367743, | |
| "grad_norm": 0.022729676216840744, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 11.9313, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0452510016497761, | |
| "grad_norm": 0.024669429287314415, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9309, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.047764946185874776, | |
| "grad_norm": 0.025852613151073456, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 11.9314, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.050278890721973446, | |
| "grad_norm": 0.03324759006500244, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 11.9309, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.052792835258072116, | |
| "grad_norm": 0.032473403960466385, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9301, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05530677979417079, | |
| "grad_norm": 0.04105048254132271, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 11.9316, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05782072433026946, | |
| "grad_norm": 0.039779629558324814, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 11.9302, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06033466886636814, | |
| "grad_norm": 0.057441096752882004, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9324, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06284861340246681, | |
| "grad_norm": 0.07438816875219345, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 11.9318, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06284861340246681, | |
| "eval_loss": 11.930198669433594, | |
| "eval_runtime": 0.2524, | |
| "eval_samples_per_second": 198.062, | |
| "eval_steps_per_second": 51.496, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06536255793856548, | |
| "grad_norm": 0.02685977704823017, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 11.9309, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06787650247466415, | |
| "grad_norm": 0.03275511413812637, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9311, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07039044701076283, | |
| "grad_norm": 0.02926531247794628, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 11.9315, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0729043915468615, | |
| "grad_norm": 0.028518393635749817, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 11.9315, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07541833608296017, | |
| "grad_norm": 0.03880656510591507, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9307, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07793228061905884, | |
| "grad_norm": 0.03654514625668526, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 11.9317, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08044622515515751, | |
| "grad_norm": 0.044491469860076904, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 11.9293, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08296016969125619, | |
| "grad_norm": 0.048509083688259125, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9298, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08547411422735486, | |
| "grad_norm": 0.048801239579916, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 11.9294, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08798805876345353, | |
| "grad_norm": 0.056390538811683655, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 11.9279, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0905020032995522, | |
| "grad_norm": 0.08711764216423035, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9253, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09301594783565087, | |
| "grad_norm": 0.10037648677825928, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 11.9241, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09552989237174955, | |
| "grad_norm": 0.049203407019376755, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 11.9305, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09804383690784822, | |
| "grad_norm": 0.04130005091428757, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9299, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10055778144394689, | |
| "grad_norm": 0.03922172635793686, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 11.9311, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10307172598004556, | |
| "grad_norm": 0.05184343457221985, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 11.9305, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10558567051614423, | |
| "grad_norm": 0.051686421036720276, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9302, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10809961505224291, | |
| "grad_norm": 0.05162731558084488, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 11.9288, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11061355958834158, | |
| "grad_norm": 0.05084317922592163, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 11.9282, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11312750412444025, | |
| "grad_norm": 0.058874111622571945, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9284, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11564144866053892, | |
| "grad_norm": 0.07015693932771683, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 11.9275, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11815539319663759, | |
| "grad_norm": 0.07656406611204147, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 11.9277, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12066933773273628, | |
| "grad_norm": 0.10160171240568161, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9253, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12318328226883495, | |
| "grad_norm": 0.09546644985675812, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 11.9254, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12569722680493361, | |
| "grad_norm": 0.11191833764314651, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 11.9233, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12569722680493361, | |
| "eval_loss": 11.927906036376953, | |
| "eval_runtime": 0.2529, | |
| "eval_samples_per_second": 197.706, | |
| "eval_steps_per_second": 51.404, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1282111713410323, | |
| "grad_norm": 0.05173062905669212, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.93, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.13072511587713095, | |
| "grad_norm": 0.05328970402479172, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 11.9296, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13323906041322964, | |
| "grad_norm": 0.056689877063035965, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 11.9302, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1357530049493283, | |
| "grad_norm": 0.06390019506216049, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9286, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.13826694948542698, | |
| "grad_norm": 0.06817812472581863, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 11.9289, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14078089402152566, | |
| "grad_norm": 0.05301738157868385, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 11.9298, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.14329483855762432, | |
| "grad_norm": 0.059947434812784195, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.9289, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.145808783093723, | |
| "grad_norm": 0.07889833301305771, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 11.9266, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.14832272762982165, | |
| "grad_norm": 0.06598637998104095, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 11.9268, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.15083667216592034, | |
| "grad_norm": 0.08608434349298477, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.9247, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15335061670201902, | |
| "grad_norm": 0.10251203924417496, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 11.9256, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.15586456123811768, | |
| "grad_norm": 0.0993577390909195, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 11.9241, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.15837850577421636, | |
| "grad_norm": 0.07237444818019867, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9288, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.16089245031031502, | |
| "grad_norm": 0.05976445600390434, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 11.9289, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1634063948464137, | |
| "grad_norm": 0.06411750614643097, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 11.9291, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.16592033938251238, | |
| "grad_norm": 0.0686773806810379, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.9287, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.16843428391861104, | |
| "grad_norm": 0.06071595102548599, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 11.9295, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.17094822845470972, | |
| "grad_norm": 0.06004241108894348, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 11.9284, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.17346217299080838, | |
| "grad_norm": 0.07173370569944382, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.9266, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.17597611752690706, | |
| "grad_norm": 0.06722280383110046, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 11.9268, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17849006206300574, | |
| "grad_norm": 0.07276538014411926, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 11.9266, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.1810040065991044, | |
| "grad_norm": 0.08135631680488586, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9252, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.18351795113520308, | |
| "grad_norm": 0.11169477552175522, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 11.9248, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.18603189567130174, | |
| "grad_norm": 0.12029822915792465, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 11.9263, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.18854584020740042, | |
| "grad_norm": 0.15942874550819397, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9266, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.18854584020740042, | |
| "eval_loss": 11.926774978637695, | |
| "eval_runtime": 0.2466, | |
| "eval_samples_per_second": 202.779, | |
| "eval_steps_per_second": 52.723, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 1563741388800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |