| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.27010406241333157, |
| "eval_steps": 150, |
| "global_step": 700, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.003858629463047594, |
| "grad_norm": 0.9612510204315186, |
| "learning_rate": 1.8e-05, |
| "loss": 1.0067429542541504, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.007717258926095188, |
| "grad_norm": 0.6660895347595215, |
| "learning_rate": 3.8e-05, |
| "loss": 0.8466403007507324, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.011575888389142782, |
| "grad_norm": 0.5681023001670837, |
| "learning_rate": 5.8e-05, |
| "loss": 0.7557645797729492, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.015434517852190376, |
| "grad_norm": 0.7179134488105774, |
| "learning_rate": 7.800000000000001e-05, |
| "loss": 0.7409078121185303, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.019293147315237968, |
| "grad_norm": 0.5565946102142334, |
| "learning_rate": 9.8e-05, |
| "loss": 0.7274651050567627, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.023151776778285563, |
| "grad_norm": 0.5450749397277832, |
| "learning_rate": 0.000118, |
| "loss": 0.741389274597168, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.027010406241333156, |
| "grad_norm": 0.4871410131454468, |
| "learning_rate": 0.000138, |
| "loss": 0.725303316116333, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.03086903570438075, |
| "grad_norm": 0.5452415347099304, |
| "learning_rate": 0.00015800000000000002, |
| "loss": 0.724397611618042, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.03472766516742835, |
| "grad_norm": 0.438076376914978, |
| "learning_rate": 0.00017800000000000002, |
| "loss": 0.7216084480285645, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.038586294630475935, |
| "grad_norm": 0.3792989253997803, |
| "learning_rate": 0.00019800000000000002, |
| "loss": 0.7241204738616943, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04244492409352353, |
| "grad_norm": 0.31958940625190735, |
| "learning_rate": 0.0001999935634368633, |
| "loss": 0.7156620502471924, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.04630355355657113, |
| "grad_norm": 0.3532995283603668, |
| "learning_rate": 0.00019997131465276176, |
| "loss": 0.716402530670166, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.05016218301961872, |
| "grad_norm": 0.3720763921737671, |
| "learning_rate": 0.0001999331777190454, |
| "loss": 0.725121021270752, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.05402081248266631, |
| "grad_norm": 0.327168345451355, |
| "learning_rate": 0.0001998791586967059, |
| "loss": 0.711461877822876, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.05787944194571391, |
| "grad_norm": 0.31293419003486633, |
| "learning_rate": 0.00019980926617082901, |
| "loss": 0.7175386905670166, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.05787944194571391, |
| "eval_loss": 0.7297696471214294, |
| "eval_runtime": 244.1933, |
| "eval_samples_per_second": 3.419, |
| "eval_steps_per_second": 1.712, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.0617380714087615, |
| "grad_norm": 0.3199326694011688, |
| "learning_rate": 0.0001997235112492302, |
| "loss": 0.7084239006042481, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.06559670087180909, |
| "grad_norm": 0.3334254026412964, |
| "learning_rate": 0.00019962190756068907, |
| "loss": 0.7120396614074707, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.0694553303348567, |
| "grad_norm": 0.32970502972602844, |
| "learning_rate": 0.00019950447125278376, |
| "loss": 0.7141448974609375, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.07331395979790428, |
| "grad_norm": 0.3339720368385315, |
| "learning_rate": 0.00019937122098932428, |
| "loss": 0.7231975555419922, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.07717258926095187, |
| "grad_norm": 0.302263081073761, |
| "learning_rate": 0.00019922217794738657, |
| "loss": 0.7377682685852051, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.08103121872399947, |
| "grad_norm": 0.3148849904537201, |
| "learning_rate": 0.00019905736581394689, |
| "loss": 0.7064791202545166, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.08488984818704706, |
| "grad_norm": 0.3036375641822815, |
| "learning_rate": 0.00019887681078211707, |
| "loss": 0.7082621097564697, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.08874847765009465, |
| "grad_norm": 0.353236585855484, |
| "learning_rate": 0.00019868054154698202, |
| "loss": 0.7202902793884277, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.09260710711314225, |
| "grad_norm": 0.2983817458152771, |
| "learning_rate": 0.0001984685893010392, |
| "loss": 0.6949288845062256, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.09646573657618984, |
| "grad_norm": 0.3325659930706024, |
| "learning_rate": 0.00019824098772924114, |
| "loss": 0.7241635799407959, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.10032436603923744, |
| "grad_norm": 0.29093560576438904, |
| "learning_rate": 0.00019799777300364218, |
| "loss": 0.7079925060272216, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.10418299550228503, |
| "grad_norm": 0.3151165246963501, |
| "learning_rate": 0.0001977389837776497, |
| "loss": 0.7299640655517579, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.10804162496533262, |
| "grad_norm": 0.30055317282676697, |
| "learning_rate": 0.000197464661179881, |
| "loss": 0.7072536468505859, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.11190025442838022, |
| "grad_norm": 0.28629517555236816, |
| "learning_rate": 0.00019717484880762685, |
| "loss": 0.7206380844116211, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.1196175133544754, |
| "grad_norm": 0.31153738498687744, |
| "learning_rate": 0.0001965489414302289, |
| "loss": 0.722527265548706, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.123476142817523, |
| "grad_norm": 0.2931964695453644, |
| "learning_rate": 0.00019621294589872003, |
| "loss": 0.7037133693695068, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.1273347722805706, |
| "grad_norm": 0.33466067910194397, |
| "learning_rate": 0.0001958616595241865, |
| "loss": 0.727421760559082, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.13119340174361818, |
| "grad_norm": 0.28575319051742554, |
| "learning_rate": 0.00019549513813554785, |
| "loss": 0.6994576930999756, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.13505203120666578, |
| "grad_norm": 0.31457364559173584, |
| "learning_rate": 0.0001951134399829799, |
| "loss": 0.734303331375122, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.1389106606697134, |
| "grad_norm": 0.30264604091644287, |
| "learning_rate": 0.00019471662572865736, |
| "loss": 0.7409284591674805, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.14276929013276096, |
| "grad_norm": 0.28342851996421814, |
| "learning_rate": 0.00019430475843711293, |
| "loss": 0.7335753440856934, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.14662791959580856, |
| "grad_norm": 0.30577903985977173, |
| "learning_rate": 0.00019387790356521463, |
| "loss": 0.7155701637268066, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.15048654905885617, |
| "grad_norm": 0.28058379888534546, |
| "learning_rate": 0.000193436128951763, |
| "loss": 0.6958878993988037, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.15434517852190374, |
| "grad_norm": 0.30901074409484863, |
| "learning_rate": 0.0001929795048067095, |
| "loss": 0.7224118709564209, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.15820380798495134, |
| "grad_norm": 0.28316858410835266, |
| "learning_rate": 0.0001925081036999984, |
| "loss": 0.7156408786773681, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.16206243744799895, |
| "grad_norm": 0.29417017102241516, |
| "learning_rate": 0.00019202200055003346, |
| "loss": 0.7048601150512696, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.16592106691104652, |
| "grad_norm": 0.29546213150024414, |
| "learning_rate": 0.00019152127261177126, |
| "loss": 0.7047354698181152, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.16977969637409412, |
| "grad_norm": 0.2986455261707306, |
| "learning_rate": 0.0001910059994644434, |
| "loss": 0.6936575889587402, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.17363832583714173, |
| "grad_norm": 0.35280054807662964, |
| "learning_rate": 0.0001904762629989091, |
| "loss": 0.6981217384338378, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.17363832583714173, |
| "eval_loss": 0.7733834385871887, |
| "eval_runtime": 241.1126, |
| "eval_samples_per_second": 3.463, |
| "eval_steps_per_second": 1.734, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.1774969553001893, |
| "grad_norm": 0.28504979610443115, |
| "learning_rate": 0.00018993214740464063, |
| "loss": 0.7187217235565185, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.1813555847632369, |
| "grad_norm": 0.294179230928421, |
| "learning_rate": 0.00018937373915634323, |
| "loss": 0.723856258392334, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.1852142142262845, |
| "grad_norm": 0.3039489984512329, |
| "learning_rate": 0.00018880112700021205, |
| "loss": 0.7158075332641601, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.18907284368933208, |
| "grad_norm": 0.3352907598018646, |
| "learning_rate": 0.0001882144019398278, |
| "loss": 0.7123313903808594, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.19293147315237968, |
| "grad_norm": 0.31155890226364136, |
| "learning_rate": 0.00018761365722169403, |
| "loss": 0.7325988292694092, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.1967901026154273, |
| "grad_norm": 0.3036295175552368, |
| "learning_rate": 0.00018699898832041757, |
| "loss": 0.7070968627929688, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.2006487320784749, |
| "grad_norm": 0.2792280316352844, |
| "learning_rate": 0.00018637049292353513, |
| "loss": 0.7023006916046143, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.20450736154152246, |
| "grad_norm": 0.30598390102386475, |
| "learning_rate": 0.00018572827091598793, |
| "loss": 0.708428144454956, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.20836599100457007, |
| "grad_norm": 0.28768792748451233, |
| "learning_rate": 0.00018507242436424765, |
| "loss": 0.708616304397583, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.21222462046761767, |
| "grad_norm": 0.32237133383750916, |
| "learning_rate": 0.00018440305750009483, |
| "loss": 0.7210727214813233, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.21608324993066524, |
| "grad_norm": 0.2892608940601349, |
| "learning_rate": 0.000183720276704054, |
| "loss": 0.6931821823120117, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.21994187939371285, |
| "grad_norm": 0.3152562081813812, |
| "learning_rate": 0.00018302419048848667, |
| "loss": 0.7213119506835938, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.22380050885676045, |
| "grad_norm": 0.31499791145324707, |
| "learning_rate": 0.00018231490948034592, |
| "loss": 0.6939045906066894, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.22765913831980802, |
| "grad_norm": 0.2861924469470978, |
| "learning_rate": 0.00018159254640359487, |
| "loss": 0.7252971649169921, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.23537639724590323, |
| "grad_norm": 0.2836938500404358, |
| "learning_rate": 0.00018010903531734363, |
| "loss": 0.6902801513671875, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.2392350267089508, |
| "grad_norm": 0.3197932243347168, |
| "learning_rate": 0.00017934812307793583, |
| "loss": 0.6933451175689698, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.2430936561719984, |
| "grad_norm": 0.29024383425712585, |
| "learning_rate": 0.00017857460027263225, |
| "loss": 0.6954158306121826, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.246952285635046, |
| "grad_norm": 0.29053837060928345, |
| "learning_rate": 0.00017778858983515743, |
| "loss": 0.7062996864318848, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.2508109150980936, |
| "grad_norm": 0.2862823009490967, |
| "learning_rate": 0.00017699021668385895, |
| "loss": 0.726755428314209, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.2546695445611412, |
| "grad_norm": 0.31322675943374634, |
| "learning_rate": 0.00017617960770185444, |
| "loss": 0.7403687953948974, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.25852817402418876, |
| "grad_norm": 0.2916722595691681, |
| "learning_rate": 0.00017535689171686644, |
| "loss": 0.6931378364562988, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.26238680348723636, |
| "grad_norm": 0.3099428117275238, |
| "learning_rate": 0.00017452219948074814, |
| "loss": 0.7085556983947754, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.26624543295028397, |
| "grad_norm": 0.30417969822883606, |
| "learning_rate": 0.0001736756636487035, |
| "loss": 0.7230380058288575, |
| "step": 690 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2592, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.261857846271484e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
