|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 8.366013071895425, |
|
"eval_steps": 10.0, |
|
"global_step": 80, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.10457516339869281, |
|
"grad_norm": 6.079821586608887, |
|
"learning_rate": 5.000000000000001e-07, |
|
"loss": 0.5536, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.20915032679738563, |
|
"grad_norm": 6.397408485412598, |
|
"learning_rate": 1.0000000000000002e-06, |
|
"loss": 0.5528, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.3137254901960784, |
|
"grad_norm": 5.950789451599121, |
|
"learning_rate": 1.5e-06, |
|
"loss": 0.5438, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.41830065359477125, |
|
"grad_norm": 5.743692874908447, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 0.5351, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.5228758169934641, |
|
"grad_norm": 3.9552488327026367, |
|
"learning_rate": 2.5e-06, |
|
"loss": 0.5425, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.6274509803921569, |
|
"grad_norm": 5.907255172729492, |
|
"learning_rate": 3e-06, |
|
"loss": 0.5432, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.7320261437908496, |
|
"grad_norm": 6.004484176635742, |
|
"learning_rate": 3.5e-06, |
|
"loss": 0.544, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.8366013071895425, |
|
"grad_norm": 5.635789394378662, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 0.5056, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.9411764705882353, |
|
"grad_norm": 2.8101253509521484, |
|
"learning_rate": 4.5e-06, |
|
"loss": 0.4968, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 1.0457516339869282, |
|
"grad_norm": 2.6935434341430664, |
|
"learning_rate": 5e-06, |
|
"loss": 0.4755, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 1.1503267973856208, |
|
"grad_norm": 3.1984055042266846, |
|
"learning_rate": 4.99847706754774e-06, |
|
"loss": 0.4559, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 1.2549019607843137, |
|
"grad_norm": 3.488842248916626, |
|
"learning_rate": 4.993910125649561e-06, |
|
"loss": 0.4511, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 1.3594771241830066, |
|
"grad_norm": 2.507657051086426, |
|
"learning_rate": 4.986304738420684e-06, |
|
"loss": 0.4032, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 1.4640522875816995, |
|
"grad_norm": 2.3815805912017822, |
|
"learning_rate": 4.975670171853926e-06, |
|
"loss": 0.3984, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 1.5686274509803921, |
|
"grad_norm": 3.52946138381958, |
|
"learning_rate": 4.962019382530521e-06, |
|
"loss": 0.394, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 1.673202614379085, |
|
"grad_norm": 2.6642520427703857, |
|
"learning_rate": 4.9453690018345144e-06, |
|
"loss": 0.3778, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 1.7777777777777777, |
|
"grad_norm": 0.9417625665664673, |
|
"learning_rate": 4.925739315689991e-06, |
|
"loss": 0.3839, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 1.8823529411764706, |
|
"grad_norm": 0.8939223289489746, |
|
"learning_rate": 4.903154239845798e-06, |
|
"loss": 0.3599, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 1.9869281045751634, |
|
"grad_norm": 0.9599626064300537, |
|
"learning_rate": 4.8776412907378845e-06, |
|
"loss": 0.3494, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 2.0915032679738563, |
|
"grad_norm": 1.0300042629241943, |
|
"learning_rate": 4.849231551964771e-06, |
|
"loss": 0.3329, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 2.196078431372549, |
|
"grad_norm": 1.173368215560913, |
|
"learning_rate": 4.817959636416969e-06, |
|
"loss": 0.324, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 2.3006535947712417, |
|
"grad_norm": 0.5053654313087463, |
|
"learning_rate": 4.783863644106502e-06, |
|
"loss": 0.3192, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 2.4052287581699345, |
|
"grad_norm": 0.7185565233230591, |
|
"learning_rate": 4.746985115747918e-06, |
|
"loss": 0.3214, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 2.5098039215686274, |
|
"grad_norm": 0.5996802449226379, |
|
"learning_rate": 4.707368982147318e-06, |
|
"loss": 0.3074, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 2.6143790849673203, |
|
"grad_norm": 0.5362175703048706, |
|
"learning_rate": 4.665063509461098e-06, |
|
"loss": 0.3108, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 2.718954248366013, |
|
"grad_norm": 1.5828744173049927, |
|
"learning_rate": 4.620120240391065e-06, |
|
"loss": 0.303, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 2.8235294117647056, |
|
"grad_norm": 1.048822045326233, |
|
"learning_rate": 4.572593931387604e-06, |
|
"loss": 0.2971, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 2.928104575163399, |
|
"grad_norm": 0.37474843859672546, |
|
"learning_rate": 4.522542485937369e-06, |
|
"loss": 0.3041, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 3.0326797385620914, |
|
"grad_norm": 0.37631165981292725, |
|
"learning_rate": 4.470026884016805e-06, |
|
"loss": 0.2925, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 3.1372549019607843, |
|
"grad_norm": 0.5196499824523926, |
|
"learning_rate": 4.415111107797445e-06, |
|
"loss": 0.2967, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 3.241830065359477, |
|
"grad_norm": 2.151287794113159, |
|
"learning_rate": 4.357862063693486e-06, |
|
"loss": 0.2867, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 3.34640522875817, |
|
"grad_norm": 0.7420333027839661, |
|
"learning_rate": 4.2983495008466285e-06, |
|
"loss": 0.2867, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 3.450980392156863, |
|
"grad_norm": 0.9488831162452698, |
|
"learning_rate": 4.236645926147493e-06, |
|
"loss": 0.2812, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 3.5555555555555554, |
|
"grad_norm": 0.4171179533004761, |
|
"learning_rate": 4.172826515897146e-06, |
|
"loss": 0.2813, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 3.6601307189542482, |
|
"grad_norm": 0.3109152317047119, |
|
"learning_rate": 4.106969024216348e-06, |
|
"loss": 0.2856, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 3.764705882352941, |
|
"grad_norm": 1.511412501335144, |
|
"learning_rate": 4.039153688314146e-06, |
|
"loss": 0.2762, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 3.869281045751634, |
|
"grad_norm": 0.2636289894580841, |
|
"learning_rate": 3.969463130731183e-06, |
|
"loss": 0.2661, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 3.973856209150327, |
|
"grad_norm": 0.36717239022254944, |
|
"learning_rate": 3.897982258676867e-06, |
|
"loss": 0.2697, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 4.078431372549019, |
|
"grad_norm": 0.31323152780532837, |
|
"learning_rate": 3.824798160583012e-06, |
|
"loss": 0.2681, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 4.183006535947713, |
|
"grad_norm": 0.28556039929389954, |
|
"learning_rate": 3.7500000000000005e-06, |
|
"loss": 0.2688, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 4.287581699346405, |
|
"grad_norm": 0.25580766797065735, |
|
"learning_rate": 3.6736789069647273e-06, |
|
"loss": 0.2587, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 4.392156862745098, |
|
"grad_norm": 0.28098028898239136, |
|
"learning_rate": 3.595927866972694e-06, |
|
"loss": 0.2619, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 4.496732026143791, |
|
"grad_norm": 0.3076843023300171, |
|
"learning_rate": 3.516841607689501e-06, |
|
"loss": 0.2632, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 4.601307189542483, |
|
"grad_norm": 0.37901487946510315, |
|
"learning_rate": 3.436516483539781e-06, |
|
"loss": 0.2705, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 4.705882352941177, |
|
"grad_norm": 0.3699696362018585, |
|
"learning_rate": 3.3550503583141726e-06, |
|
"loss": 0.2573, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 4.810457516339869, |
|
"grad_norm": 0.21686607599258423, |
|
"learning_rate": 3.272542485937369e-06, |
|
"loss": 0.2597, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 4.915032679738562, |
|
"grad_norm": 0.253548800945282, |
|
"learning_rate": 3.189093389542498e-06, |
|
"loss": 0.2579, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 5.019607843137255, |
|
"grad_norm": 0.2619287073612213, |
|
"learning_rate": 3.1048047389991693e-06, |
|
"loss": 0.2557, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 5.124183006535947, |
|
"grad_norm": 0.22800114750862122, |
|
"learning_rate": 3.019779227044398e-06, |
|
"loss": 0.2499, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 5.228758169934641, |
|
"grad_norm": 0.2334267795085907, |
|
"learning_rate": 2.9341204441673267e-06, |
|
"loss": 0.257, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 5.333333333333333, |
|
"grad_norm": 0.21543391048908234, |
|
"learning_rate": 2.847932752400164e-06, |
|
"loss": 0.2587, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 5.437908496732026, |
|
"grad_norm": 0.23680457472801208, |
|
"learning_rate": 2.761321158169134e-06, |
|
"loss": 0.244, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 5.542483660130719, |
|
"grad_norm": 0.23751680552959442, |
|
"learning_rate": 2.6743911843603134e-06, |
|
"loss": 0.2516, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 5.647058823529412, |
|
"grad_norm": 0.22354498505592346, |
|
"learning_rate": 2.587248741756253e-06, |
|
"loss": 0.251, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 5.751633986928105, |
|
"grad_norm": 0.2219904214143753, |
|
"learning_rate": 2.5e-06, |
|
"loss": 0.2513, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 5.856209150326797, |
|
"grad_norm": 0.24870158731937408, |
|
"learning_rate": 2.4127512582437486e-06, |
|
"loss": 0.2478, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 5.96078431372549, |
|
"grad_norm": 0.2249930202960968, |
|
"learning_rate": 2.325608815639687e-06, |
|
"loss": 0.2448, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 6.065359477124183, |
|
"grad_norm": 0.2350921630859375, |
|
"learning_rate": 2.238678841830867e-06, |
|
"loss": 0.2436, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 6.169934640522876, |
|
"grad_norm": 0.2143002599477768, |
|
"learning_rate": 2.1520672475998374e-06, |
|
"loss": 0.2447, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 6.2745098039215685, |
|
"grad_norm": 0.23206955194473267, |
|
"learning_rate": 2.0658795558326745e-06, |
|
"loss": 0.2472, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 6.379084967320262, |
|
"grad_norm": 0.2509792447090149, |
|
"learning_rate": 1.9802207729556023e-06, |
|
"loss": 0.2444, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 6.483660130718954, |
|
"grad_norm": 0.21777762472629547, |
|
"learning_rate": 1.895195261000831e-06, |
|
"loss": 0.2406, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 6.588235294117647, |
|
"grad_norm": 0.214972585439682, |
|
"learning_rate": 1.8109066104575023e-06, |
|
"loss": 0.2403, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 6.69281045751634, |
|
"grad_norm": 0.2152736335992813, |
|
"learning_rate": 1.7274575140626318e-06, |
|
"loss": 0.2407, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 6.7973856209150325, |
|
"grad_norm": 0.21374449133872986, |
|
"learning_rate": 1.6449496416858285e-06, |
|
"loss": 0.2354, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 6.901960784313726, |
|
"grad_norm": 0.23214764893054962, |
|
"learning_rate": 1.56348351646022e-06, |
|
"loss": 0.2441, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 7.006535947712418, |
|
"grad_norm": 0.21843403577804565, |
|
"learning_rate": 1.4831583923105e-06, |
|
"loss": 0.242, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 7.111111111111111, |
|
"grad_norm": 0.22605258226394653, |
|
"learning_rate": 1.4040721330273063e-06, |
|
"loss": 0.2439, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 7.215686274509804, |
|
"grad_norm": 0.21626867353916168, |
|
"learning_rate": 1.3263210930352737e-06, |
|
"loss": 0.2413, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 7.3202614379084965, |
|
"grad_norm": 0.21916088461875916, |
|
"learning_rate": 1.2500000000000007e-06, |
|
"loss": 0.2361, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 7.42483660130719, |
|
"grad_norm": 0.212180495262146, |
|
"learning_rate": 1.1752018394169882e-06, |
|
"loss": 0.2329, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 7.529411764705882, |
|
"grad_norm": 0.25572070479393005, |
|
"learning_rate": 1.1020177413231334e-06, |
|
"loss": 0.2365, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 7.633986928104575, |
|
"grad_norm": 0.24046508967876434, |
|
"learning_rate": 1.0305368692688175e-06, |
|
"loss": 0.2372, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 7.738562091503268, |
|
"grad_norm": 0.21979837119579315, |
|
"learning_rate": 9.608463116858544e-07, |
|
"loss": 0.238, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 7.8431372549019605, |
|
"grad_norm": 0.2575077712535858, |
|
"learning_rate": 8.930309757836517e-07, |
|
"loss": 0.2382, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 7.947712418300654, |
|
"grad_norm": 0.2223196178674698, |
|
"learning_rate": 8.271734841028553e-07, |
|
"loss": 0.2352, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 8.052287581699346, |
|
"grad_norm": 0.23885323107242584, |
|
"learning_rate": 7.633540738525066e-07, |
|
"loss": 0.2347, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 8.156862745098039, |
|
"grad_norm": 0.22449229657649994, |
|
"learning_rate": 7.016504991533727e-07, |
|
"loss": 0.241, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 8.261437908496733, |
|
"grad_norm": 0.21523602306842804, |
|
"learning_rate": 6.421379363065142e-07, |
|
"loss": 0.2344, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 8.366013071895425, |
|
"grad_norm": 0.22689399123191833, |
|
"learning_rate": 5.848888922025553e-07, |
|
"loss": 0.24, |
|
"step": 80 |
|
} |
|
], |
|
"logging_steps": 1.0, |
|
"max_steps": 100, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 12, |
|
"save_steps": 10, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": false, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 7.116079112262779e+18, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|