| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0025556710340245005, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.407561378699334e-05, | |
| "grad_norm": 2.5001614093780518, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.825, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.407561378699334e-05, | |
| "eval_loss": 5.655045509338379, | |
| "eval_runtime": 5197.3091, | |
| "eval_samples_per_second": 2.378, | |
| "eval_steps_per_second": 1.189, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.815122757398668e-05, | |
| "grad_norm": 2.1226208209991455, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.6844, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010222684136098001, | |
| "grad_norm": 2.5686793327331543, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1539, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013630245514797336, | |
| "grad_norm": 4.603909015655518, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 4.0091, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001703780689349667, | |
| "grad_norm": 2.2434098720550537, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 1.482, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020445368272196002, | |
| "grad_norm": 2.6793839931488037, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.8997, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00023852929650895337, | |
| "grad_norm": 3.525517463684082, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 1.328, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002726049102959467, | |
| "grad_norm": 4.246636867523193, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 1.3833, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00030668052408294006, | |
| "grad_norm": 5.746326923370361, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.1267, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003407561378699334, | |
| "grad_norm": 5.541106700897217, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 0.8371, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003748317516569267, | |
| "grad_norm": 4.492342472076416, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.8644, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00040890736544392005, | |
| "grad_norm": 5.070585250854492, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.5652, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004429829792309134, | |
| "grad_norm": 3.305798292160034, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 0.5209, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00047705859301790674, | |
| "grad_norm": 1.7791708707809448, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 0.1586, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005111342068049, | |
| "grad_norm": 4.680875301361084, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5646, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005452098205918934, | |
| "grad_norm": 3.8708016872406006, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 0.431, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005792854343788867, | |
| "grad_norm": 4.305510520935059, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 0.4888, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0006133610481658801, | |
| "grad_norm": 4.049569606781006, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.2277, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006474366619528734, | |
| "grad_norm": 3.324610948562622, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.2978, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006815122757398668, | |
| "grad_norm": 3.7074697017669678, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 0.3028, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007155878895268601, | |
| "grad_norm": 1.7295836210250854, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0916, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007496635033138534, | |
| "grad_norm": 2.569653272628784, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 0.3138, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0007837391171008468, | |
| "grad_norm": 2.379580020904541, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.2004, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0008178147308878401, | |
| "grad_norm": 2.292313814163208, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1673, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0008518903446748335, | |
| "grad_norm": 2.342252731323242, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.2094, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0008518903446748335, | |
| "eval_loss": 0.17272759974002838, | |
| "eval_runtime": 5196.4661, | |
| "eval_samples_per_second": 2.378, | |
| "eval_steps_per_second": 1.189, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0008859659584618268, | |
| "grad_norm": 3.6202399730682373, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 0.127, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0009200415722488202, | |
| "grad_norm": 1.361546516418457, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0881, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0009541171860358135, | |
| "grad_norm": 3.2597994804382324, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 0.209, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0009881927998228069, | |
| "grad_norm": 2.3739514350891113, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 0.0655, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0010222684136098, | |
| "grad_norm": 0.39956721663475037, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.013, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0010563440273967935, | |
| "grad_norm": 2.310549736022949, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 0.0997, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0010904196411837869, | |
| "grad_norm": 3.8629372119903564, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 0.1503, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0011244952549707803, | |
| "grad_norm": 1.4826256036758423, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0285, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0011585708687577734, | |
| "grad_norm": 1.613270878791809, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 0.0595, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0011926464825447668, | |
| "grad_norm": 0.6385797262191772, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 0.0196, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0012267220963317602, | |
| "grad_norm": 1.283711552619934, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0276, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0012607977101187534, | |
| "grad_norm": 5.805143356323242, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 0.1078, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0012948733239057468, | |
| "grad_norm": 0.6078380346298218, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 0.0143, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0013289489376927402, | |
| "grad_norm": 1.3938196897506714, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0196, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0013630245514797336, | |
| "grad_norm": 4.788840293884277, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 0.1522, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0013971001652667268, | |
| "grad_norm": 7.833195686340332, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 0.0832, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0014311757790537202, | |
| "grad_norm": 6.889073371887207, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.1242, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0014652513928407136, | |
| "grad_norm": 6.13986349105835, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 0.0414, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0014993270066277068, | |
| "grad_norm": 7.624245643615723, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 0.1478, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0015334026204147002, | |
| "grad_norm": 0.07408539205789566, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0022, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0015674782342016936, | |
| "grad_norm": 1.7765361070632935, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 0.1055, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.001601553847988687, | |
| "grad_norm": 1.6538923978805542, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 0.0226, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0016356294617756802, | |
| "grad_norm": 13.931591987609863, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.2841, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0016697050755626736, | |
| "grad_norm": 11.1533203125, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 0.1394, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.001703780689349667, | |
| "grad_norm": 4.493430137634277, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 0.0744, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.001703780689349667, | |
| "eval_loss": 0.0442812517285347, | |
| "eval_runtime": 5199.0583, | |
| "eval_samples_per_second": 2.377, | |
| "eval_steps_per_second": 1.188, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0017378563031366602, | |
| "grad_norm": 4.004736423492432, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.4785, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0017719319169236536, | |
| "grad_norm": 0.8578753471374512, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 0.0086, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.001806007530710647, | |
| "grad_norm": 1.8137702941894531, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 0.0333, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0018400831444976404, | |
| "grad_norm": 0.4614853262901306, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0078, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0018741587582846336, | |
| "grad_norm": 0.09576446563005447, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 0.0015, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.001908234372071627, | |
| "grad_norm": 0.09370886534452438, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 0.0019, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0019423099858586204, | |
| "grad_norm": 0.4553550183773041, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0037, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0019763855996456138, | |
| "grad_norm": 0.11098048835992813, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 0.0025, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.002010461213432607, | |
| "grad_norm": 0.11278193444013596, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 0.0022, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0020445368272196, | |
| "grad_norm": 1.5145128965377808, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.042, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0020786124410065937, | |
| "grad_norm": 0.15734955668449402, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 0.0031, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.002112688054793587, | |
| "grad_norm": 0.16131563484668732, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 0.0041, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.00214676366858058, | |
| "grad_norm": 1.3162636756896973, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.017, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0021808392823675737, | |
| "grad_norm": 0.5748438239097595, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 0.0109, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.002214914896154567, | |
| "grad_norm": 1.6675885915756226, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 0.0192, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0022489905099415605, | |
| "grad_norm": 0.22785191237926483, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0039, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0022830661237285537, | |
| "grad_norm": 0.2156006395816803, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 0.0043, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.002317141737515547, | |
| "grad_norm": 1.7005534172058105, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 0.0998, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0023512173513025405, | |
| "grad_norm": 0.23563118278980255, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0034, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0023852929650895337, | |
| "grad_norm": 0.18278473615646362, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 0.0037, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.002419368578876527, | |
| "grad_norm": 2.191817045211792, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 0.0575, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0024534441926635205, | |
| "grad_norm": 0.29528528451919556, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0046, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0024875198064505137, | |
| "grad_norm": 0.05887974426150322, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 0.0012, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.002521595420237507, | |
| "grad_norm": 0.8336066603660583, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 0.0193, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.0025556710340245005, | |
| "grad_norm": 0.5219399333000183, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0082, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0025556710340245005, | |
| "eval_loss": 0.019740475341677666, | |
| "eval_runtime": 5200.5985, | |
| "eval_samples_per_second": 2.376, | |
| "eval_steps_per_second": 1.188, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1111982529917747e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |