| { | |
| "best_metric": 3.5291860103607178, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.0256045519203414, | |
| "eval_steps": 25, | |
| "global_step": 66, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04551920341394026, | |
| "grad_norm": 1.5629485845565796, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7004, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04551920341394026, | |
| "eval_loss": 4.0469136238098145, | |
| "eval_runtime": 4.6058, | |
| "eval_samples_per_second": 10.856, | |
| "eval_steps_per_second": 2.823, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09103840682788052, | |
| "grad_norm": 1.6075812578201294, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7173, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13655761024182078, | |
| "grad_norm": 1.4795007705688477, | |
| "learning_rate": 9.994579552923277e-05, | |
| "loss": 3.7871, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.18207681365576103, | |
| "grad_norm": 0.668359100818634, | |
| "learning_rate": 9.978331270024886e-05, | |
| "loss": 3.8203, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22759601706970128, | |
| "grad_norm": 1.8153729438781738, | |
| "learning_rate": 9.951294294841516e-05, | |
| "loss": 3.8883, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.27311522048364156, | |
| "grad_norm": 2.145763635635376, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.6344, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3186344238975818, | |
| "grad_norm": 1.1244003772735596, | |
| "learning_rate": 9.865140639375449e-05, | |
| "loss": 3.4501, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.36415362731152207, | |
| "grad_norm": 0.4040810465812683, | |
| "learning_rate": 9.80623151079494e-05, | |
| "loss": 3.4181, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4096728307254623, | |
| "grad_norm": 0.498119592666626, | |
| "learning_rate": 9.736948293323593e-05, | |
| "loss": 3.5928, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.45519203413940257, | |
| "grad_norm": 0.8037330508232117, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.6543, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5007112375533428, | |
| "grad_norm": 0.6568593978881836, | |
| "learning_rate": 9.567951819055496e-05, | |
| "loss": 3.4914, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5462304409672831, | |
| "grad_norm": 0.5638713836669922, | |
| "learning_rate": 9.468645689567598e-05, | |
| "loss": 3.3873, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5917496443812233, | |
| "grad_norm": 0.4466124475002289, | |
| "learning_rate": 9.359778745001225e-05, | |
| "loss": 3.4433, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6372688477951636, | |
| "grad_norm": 0.42094528675079346, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.4876, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6827880512091038, | |
| "grad_norm": 0.5585120916366577, | |
| "learning_rate": 9.114433891662902e-05, | |
| "loss": 3.5733, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7283072546230441, | |
| "grad_norm": 0.6824477910995483, | |
| "learning_rate": 8.978547040132317e-05, | |
| "loss": 3.3876, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7738264580369844, | |
| "grad_norm": 0.7325260639190674, | |
| "learning_rate": 8.834280064097317e-05, | |
| "loss": 3.4021, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8193456614509246, | |
| "grad_norm": 0.6445585489273071, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.4157, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.4666988253593445, | |
| "learning_rate": 8.522015296811584e-05, | |
| "loss": 3.4133, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9103840682788051, | |
| "grad_norm": 0.4899771213531494, | |
| "learning_rate": 8.354769778736406e-05, | |
| "loss": 3.5271, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9559032716927454, | |
| "grad_norm": 0.661791980266571, | |
| "learning_rate": 8.180646870215952e-05, | |
| "loss": 3.6405, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0085348506401137, | |
| "grad_norm": 0.4138284921646118, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.0918, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.054054054054054, | |
| "grad_norm": 0.3383225202560425, | |
| "learning_rate": 7.813462348869497e-05, | |
| "loss": 3.4534, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0995732574679944, | |
| "grad_norm": 0.3657989501953125, | |
| "learning_rate": 7.62128531571699e-05, | |
| "loss": 3.2994, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1450924608819346, | |
| "grad_norm": 0.36880072951316833, | |
| "learning_rate": 7.42399792043627e-05, | |
| "loss": 3.2221, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1450924608819346, | |
| "eval_loss": 3.59340238571167, | |
| "eval_runtime": 4.8896, | |
| "eval_samples_per_second": 10.226, | |
| "eval_steps_per_second": 2.659, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1906116642958748, | |
| "grad_norm": 0.48038947582244873, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.6039, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.236130867709815, | |
| "grad_norm": 0.41462457180023193, | |
| "learning_rate": 7.01600434026499e-05, | |
| "loss": 2.6349, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2816500711237553, | |
| "grad_norm": 0.5014923214912415, | |
| "learning_rate": 6.80628104764508e-05, | |
| "loss": 3.9871, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3271692745376955, | |
| "grad_norm": 0.42576462030410767, | |
| "learning_rate": 6.593410809564689e-05, | |
| "loss": 3.366, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3726884779516357, | |
| "grad_norm": 0.3873802721500397, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.2166, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4182076813655762, | |
| "grad_norm": 0.47148817777633667, | |
| "learning_rate": 6.160287135049127e-05, | |
| "loss": 3.3829, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4637268847795164, | |
| "grad_norm": 0.4588596820831299, | |
| "learning_rate": 5.941077131483025e-05, | |
| "loss": 2.8047, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5092460881934566, | |
| "grad_norm": 0.3620421290397644, | |
| "learning_rate": 5.720804534473382e-05, | |
| "loss": 3.88, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.5547652916073968, | |
| "grad_norm": 0.29916054010391235, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.2053, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.600284495021337, | |
| "grad_norm": 0.38498491048812866, | |
| "learning_rate": 5.27919546552662e-05, | |
| "loss": 3.4077, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6458036984352775, | |
| "grad_norm": 0.3801584541797638, | |
| "learning_rate": 5.058922868516978e-05, | |
| "loss": 3.4857, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6913229018492175, | |
| "grad_norm": 0.3769657015800476, | |
| "learning_rate": 4.839712864950873e-05, | |
| "loss": 2.7502, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 0.4362291097640991, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.6884, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7823613086770982, | |
| "grad_norm": 0.2888215184211731, | |
| "learning_rate": 4.406589190435313e-05, | |
| "loss": 3.2926, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.8278805120910384, | |
| "grad_norm": 0.34629708528518677, | |
| "learning_rate": 4.19371895235492e-05, | |
| "loss": 3.2089, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8733997155049786, | |
| "grad_norm": 0.382393479347229, | |
| "learning_rate": 3.98399565973501e-05, | |
| "loss": 3.2629, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.9189189189189189, | |
| "grad_norm": 0.5005021691322327, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.756, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.9644381223328593, | |
| "grad_norm": 0.6277827620506287, | |
| "learning_rate": 3.576002079563732e-05, | |
| "loss": 3.6943, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0170697012802274, | |
| "grad_norm": 0.3988167643547058, | |
| "learning_rate": 3.378714684283011e-05, | |
| "loss": 3.3128, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.062588904694168, | |
| "grad_norm": 0.38560742139816284, | |
| "learning_rate": 3.186537651130503e-05, | |
| "loss": 3.331, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.108108108108108, | |
| "grad_norm": 0.32665321230888367, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.0789, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.1536273115220483, | |
| "grad_norm": 0.4147993326187134, | |
| "learning_rate": 2.8193531297840503e-05, | |
| "loss": 3.1504, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.199146514935989, | |
| "grad_norm": 0.515488862991333, | |
| "learning_rate": 2.645230221263596e-05, | |
| "loss": 3.508, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.244665718349929, | |
| "grad_norm": 0.41275349259376526, | |
| "learning_rate": 2.4779847031884175e-05, | |
| "loss": 2.3739, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.2901849217638692, | |
| "grad_norm": 0.35043126344680786, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.9068, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2901849217638692, | |
| "eval_loss": 3.5291860103607178, | |
| "eval_runtime": 4.8939, | |
| "eval_samples_per_second": 10.217, | |
| "eval_steps_per_second": 2.656, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.3357041251778092, | |
| "grad_norm": 0.3074302077293396, | |
| "learning_rate": 2.165719935902685e-05, | |
| "loss": 3.0223, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.3812233285917497, | |
| "grad_norm": 0.43086740374565125, | |
| "learning_rate": 2.0214529598676836e-05, | |
| "loss": 3.2073, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.42674253200569, | |
| "grad_norm": 0.5334138870239258, | |
| "learning_rate": 1.8855661083370986e-05, | |
| "loss": 3.475, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.47226173541963, | |
| "grad_norm": 0.35528457164764404, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.0396, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.5177809388335706, | |
| "grad_norm": 0.3946029543876648, | |
| "learning_rate": 1.6402212549987762e-05, | |
| "loss": 4.2628, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.5633001422475106, | |
| "grad_norm": 0.3490312397480011, | |
| "learning_rate": 1.531354310432403e-05, | |
| "loss": 3.2317, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.608819345661451, | |
| "grad_norm": 0.3952423334121704, | |
| "learning_rate": 1.4320481809445051e-05, | |
| "loss": 3.2827, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.654338549075391, | |
| "grad_norm": 0.4798361361026764, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.2247, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.6998577524893315, | |
| "grad_norm": 0.4341035783290863, | |
| "learning_rate": 1.2630517066764069e-05, | |
| "loss": 2.4414, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.7453769559032715, | |
| "grad_norm": 0.44139501452445984, | |
| "learning_rate": 1.1937684892050604e-05, | |
| "loss": 4.1782, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.790896159317212, | |
| "grad_norm": 0.3148343861103058, | |
| "learning_rate": 1.1348593606245522e-05, | |
| "loss": 3.0881, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.8364153627311524, | |
| "grad_norm": 0.403652161359787, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.3378, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.8819345661450924, | |
| "grad_norm": 0.44468310475349426, | |
| "learning_rate": 1.0487057051584856e-05, | |
| "loss": 3.375, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.927453769559033, | |
| "grad_norm": 0.5985783934593201, | |
| "learning_rate": 1.0216687299751144e-05, | |
| "loss": 3.8349, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.972972972972973, | |
| "grad_norm": 0.5112795829772949, | |
| "learning_rate": 1.0054204470767243e-05, | |
| "loss": 3.4318, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.0256045519203414, | |
| "grad_norm": 0.2921772003173828, | |
| "learning_rate": 1e-05, | |
| "loss": 3.1404, | |
| "step": 66 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 66, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 9.108787643746877e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |