| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 78, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.3164514303207397, |
| "epoch": 0.012861736334405145, |
| "grad_norm": 1.3205718994140625, |
| "learning_rate": 0.0, |
| "loss": 2.108562469482422, |
| "mean_token_accuracy": 0.5302465185523033, |
| "num_tokens": 125343.0, |
| "step": 1 |
| }, |
| { |
| "entropy": 1.3486243188381195, |
| "epoch": 0.02572347266881029, |
| "grad_norm": 1.291916847229004, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": 2.126715898513794, |
| "mean_token_accuracy": 0.5257277637720108, |
| "num_tokens": 254461.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 1.3619738817214966, |
| "epoch": 0.03858520900321544, |
| "grad_norm": 1.2188917398452759, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 2.027977705001831, |
| "mean_token_accuracy": 0.53680220246315, |
| "num_tokens": 384058.0, |
| "step": 3 |
| }, |
| { |
| "entropy": 1.4663979560136795, |
| "epoch": 0.05144694533762058, |
| "grad_norm": 0.9349287152290344, |
| "learning_rate": 1.25e-05, |
| "loss": 1.9901375770568848, |
| "mean_token_accuracy": 0.5396364852786064, |
| "num_tokens": 512679.0, |
| "step": 4 |
| }, |
| { |
| "entropy": 1.6146472543478012, |
| "epoch": 0.06430868167202572, |
| "grad_norm": 0.6370308995246887, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 1.9074194431304932, |
| "mean_token_accuracy": 0.5429708510637283, |
| "num_tokens": 642851.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 1.7623443454504013, |
| "epoch": 0.07717041800643087, |
| "grad_norm": 0.41252008080482483, |
| "learning_rate": 2.0833333333333336e-05, |
| "loss": 1.815047264099121, |
| "mean_token_accuracy": 0.557150200009346, |
| "num_tokens": 771427.0, |
| "step": 6 |
| }, |
| { |
| "entropy": 1.9809899777173996, |
| "epoch": 0.09003215434083602, |
| "grad_norm": 0.5013964772224426, |
| "learning_rate": 2.5e-05, |
| "loss": 1.824620246887207, |
| "mean_token_accuracy": 0.5521566867828369, |
| "num_tokens": 900229.0, |
| "step": 7 |
| }, |
| { |
| "entropy": 2.035237669944763, |
| "epoch": 0.10289389067524116, |
| "grad_norm": 0.5846648812294006, |
| "learning_rate": 2.916666666666667e-05, |
| "loss": 1.767448902130127, |
| "mean_token_accuracy": 0.5620294511318207, |
| "num_tokens": 1028916.0, |
| "step": 8 |
| }, |
| { |
| "entropy": 1.9594171047210693, |
| "epoch": 0.1157556270096463, |
| "grad_norm": 0.5288171172142029, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.7006888389587402, |
| "mean_token_accuracy": 0.5697884187102318, |
| "num_tokens": 1157441.0, |
| "step": 9 |
| }, |
| { |
| "entropy": 1.7999890595674515, |
| "epoch": 0.12861736334405144, |
| "grad_norm": 0.4071674346923828, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 1.625780701637268, |
| "mean_token_accuracy": 0.5814985409379005, |
| "num_tokens": 1285378.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.658578023314476, |
| "epoch": 0.1414790996784566, |
| "grad_norm": 0.3109852075576782, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 1.5975825786590576, |
| "mean_token_accuracy": 0.5808091089129448, |
| "num_tokens": 1413453.0, |
| "step": 11 |
| }, |
| { |
| "entropy": 1.4805417656898499, |
| "epoch": 0.15434083601286175, |
| "grad_norm": 0.2870834469795227, |
| "learning_rate": 4.5833333333333334e-05, |
| "loss": 1.518122673034668, |
| "mean_token_accuracy": 0.5996171087026596, |
| "num_tokens": 1542982.0, |
| "step": 12 |
| }, |
| { |
| "entropy": 1.3833045214414597, |
| "epoch": 0.16720257234726688, |
| "grad_norm": 0.27810704708099365, |
| "learning_rate": 5e-05, |
| "loss": 1.4639174938201904, |
| "mean_token_accuracy": 0.6109028086066246, |
| "num_tokens": 1672219.0, |
| "step": 13 |
| }, |
| { |
| "entropy": 1.3444313406944275, |
| "epoch": 0.18006430868167203, |
| "grad_norm": 0.2850067615509033, |
| "learning_rate": 4.9997496794168726e-05, |
| "loss": 1.4495856761932373, |
| "mean_token_accuracy": 0.6085417345166206, |
| "num_tokens": 1801169.0, |
| "step": 14 |
| }, |
| { |
| "entropy": 1.3875805139541626, |
| "epoch": 0.19292604501607716, |
| "grad_norm": 0.22854836285114288, |
| "learning_rate": 4.998998767795805e-05, |
| "loss": 1.4494396448135376, |
| "mean_token_accuracy": 0.6096145436167717, |
| "num_tokens": 1929597.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 1.4042701870203018, |
| "epoch": 0.2057877813504823, |
| "grad_norm": 0.25544342398643494, |
| "learning_rate": 4.9977474155117045e-05, |
| "loss": 1.4276520013809204, |
| "mean_token_accuracy": 0.6092700362205505, |
| "num_tokens": 2058901.0, |
| "step": 16 |
| }, |
| { |
| "entropy": 1.3920131623744965, |
| "epoch": 0.21864951768488747, |
| "grad_norm": 0.2532227039337158, |
| "learning_rate": 4.995995873155958e-05, |
| "loss": 1.372622013092041, |
| "mean_token_accuracy": 0.6218594387173653, |
| "num_tokens": 2188340.0, |
| "step": 17 |
| }, |
| { |
| "entropy": 1.4117262363433838, |
| "epoch": 0.2315112540192926, |
| "grad_norm": 0.23465679585933685, |
| "learning_rate": 4.99374449148625e-05, |
| "loss": 1.3505568504333496, |
| "mean_token_accuracy": 0.6291927620768547, |
| "num_tokens": 2317737.0, |
| "step": 18 |
| }, |
| { |
| "entropy": 1.39142644405365, |
| "epoch": 0.24437299035369775, |
| "grad_norm": 0.1970938742160797, |
| "learning_rate": 4.9909937213563165e-05, |
| "loss": 1.3315509557724, |
| "mean_token_accuracy": 0.6313857734203339, |
| "num_tokens": 2447871.0, |
| "step": 19 |
| }, |
| { |
| "entropy": 1.396314412355423, |
| "epoch": 0.2572347266881029, |
| "grad_norm": 0.19241943955421448, |
| "learning_rate": 4.987744113625665e-05, |
| "loss": 1.3494808673858643, |
| "mean_token_accuracy": 0.6292985901236534, |
| "num_tokens": 2575540.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.332438975572586, |
| "epoch": 0.27009646302250806, |
| "grad_norm": 0.19267837703227997, |
| "learning_rate": 4.9839963190492576e-05, |
| "loss": 1.293985366821289, |
| "mean_token_accuracy": 0.640266053378582, |
| "num_tokens": 2701365.0, |
| "step": 21 |
| }, |
| { |
| "entropy": 1.3236675560474396, |
| "epoch": 0.2829581993569132, |
| "grad_norm": 0.18189704418182373, |
| "learning_rate": 4.979751088147192e-05, |
| "loss": 1.2964701652526855, |
| "mean_token_accuracy": 0.6390737816691399, |
| "num_tokens": 2830897.0, |
| "step": 22 |
| }, |
| { |
| "entropy": 1.3403686434030533, |
| "epoch": 0.2958199356913183, |
| "grad_norm": 0.16925957798957825, |
| "learning_rate": 4.975009271054409e-05, |
| "loss": 1.313760757446289, |
| "mean_token_accuracy": 0.6331784650683403, |
| "num_tokens": 2960144.0, |
| "step": 23 |
| }, |
| { |
| "entropy": 1.3093593418598175, |
| "epoch": 0.3086816720257235, |
| "grad_norm": 0.17534375190734863, |
| "learning_rate": 4.969771817350445e-05, |
| "loss": 1.2865062952041626, |
| "mean_token_accuracy": 0.6429941952228546, |
| "num_tokens": 3089440.0, |
| "step": 24 |
| }, |
| { |
| "entropy": 1.2958146631717682, |
| "epoch": 0.3215434083601286, |
| "grad_norm": 0.18624980747699738, |
| "learning_rate": 4.9640397758692715e-05, |
| "loss": 1.2817679643630981, |
| "mean_token_accuracy": 0.6394432112574577, |
| "num_tokens": 3217927.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.252070963382721, |
| "epoch": 0.33440514469453375, |
| "grad_norm": 0.16373585164546967, |
| "learning_rate": 4.957814294489261e-05, |
| "loss": 1.2472319602966309, |
| "mean_token_accuracy": 0.6489637866616249, |
| "num_tokens": 3347968.0, |
| "step": 26 |
| }, |
| { |
| "entropy": 1.239806517958641, |
| "epoch": 0.34726688102893893, |
| "grad_norm": 0.15866123139858246, |
| "learning_rate": 4.9510966199033174e-05, |
| "loss": 1.2464823722839355, |
| "mean_token_accuracy": 0.6469453647732735, |
| "num_tokens": 3476400.0, |
| "step": 27 |
| }, |
| { |
| "entropy": 1.2075979709625244, |
| "epoch": 0.36012861736334406, |
| "grad_norm": 0.15684208273887634, |
| "learning_rate": 4.943888097369216e-05, |
| "loss": 1.2147959470748901, |
| "mean_token_accuracy": 0.6535271480679512, |
| "num_tokens": 3606524.0, |
| "step": 28 |
| }, |
| { |
| "entropy": 1.2250622063875198, |
| "epoch": 0.3729903536977492, |
| "grad_norm": 0.16190986335277557, |
| "learning_rate": 4.936190170440208e-05, |
| "loss": 1.2240623235702515, |
| "mean_token_accuracy": 0.652711808681488, |
| "num_tokens": 3735020.0, |
| "step": 29 |
| }, |
| { |
| "entropy": 1.2123340517282486, |
| "epoch": 0.3858520900321543, |
| "grad_norm": 0.16800783574581146, |
| "learning_rate": 4.928004380675941e-05, |
| "loss": 1.204244613647461, |
| "mean_token_accuracy": 0.6567093506455421, |
| "num_tokens": 3865295.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.2247880101203918, |
| "epoch": 0.3987138263665595, |
| "grad_norm": 0.14405229687690735, |
| "learning_rate": 4.9193323673337476e-05, |
| "loss": 1.1991829872131348, |
| "mean_token_accuracy": 0.6602997556328773, |
| "num_tokens": 3994821.0, |
| "step": 31 |
| }, |
| { |
| "entropy": 1.2614206820726395, |
| "epoch": 0.4115755627009646, |
| "grad_norm": 0.15460604429244995, |
| "learning_rate": 4.910175867040377e-05, |
| "loss": 1.216886043548584, |
| "mean_token_accuracy": 0.6516416072845459, |
| "num_tokens": 4124589.0, |
| "step": 32 |
| }, |
| { |
| "entropy": 1.227910652756691, |
| "epoch": 0.42443729903536975, |
| "grad_norm": 0.16159985959529877, |
| "learning_rate": 4.9005367134442235e-05, |
| "loss": 1.2033252716064453, |
| "mean_token_accuracy": 0.6573327481746674, |
| "num_tokens": 4251091.0, |
| "step": 33 |
| }, |
| { |
| "entropy": 1.2353373318910599, |
| "epoch": 0.43729903536977494, |
| "grad_norm": 0.14645665884017944, |
| "learning_rate": 4.890416836848127e-05, |
| "loss": 1.2113966941833496, |
| "mean_token_accuracy": 0.6547944620251656, |
| "num_tokens": 4381459.0, |
| "step": 34 |
| }, |
| { |
| "entropy": 1.224476620554924, |
| "epoch": 0.45016077170418006, |
| "grad_norm": 0.14515644311904907, |
| "learning_rate": 4.8798182638228166e-05, |
| "loss": 1.2142887115478516, |
| "mean_token_accuracy": 0.6527992635965347, |
| "num_tokens": 4510718.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 1.1847395598888397, |
| "epoch": 0.4630225080385852, |
| "grad_norm": 0.14294442534446716, |
| "learning_rate": 4.868743116801074e-05, |
| "loss": 1.1840288639068604, |
| "mean_token_accuracy": 0.661017507314682, |
| "num_tokens": 4638887.0, |
| "step": 36 |
| }, |
| { |
| "entropy": 1.1811462491750717, |
| "epoch": 0.4758842443729904, |
| "grad_norm": 0.14014433324337006, |
| "learning_rate": 4.857193613652711e-05, |
| "loss": 1.1855542659759521, |
| "mean_token_accuracy": 0.6628495678305626, |
| "num_tokens": 4768654.0, |
| "step": 37 |
| }, |
| { |
| "entropy": 1.1724539399147034, |
| "epoch": 0.4887459807073955, |
| "grad_norm": 0.13748519122600555, |
| "learning_rate": 4.845172067240415e-05, |
| "loss": 1.1737499237060547, |
| "mean_token_accuracy": 0.6616369336843491, |
| "num_tokens": 4897218.0, |
| "step": 38 |
| }, |
| { |
| "entropy": 1.1392606794834137, |
| "epoch": 0.5016077170418006, |
| "grad_norm": 0.13618677854537964, |
| "learning_rate": 4.8326808849565936e-05, |
| "loss": 1.1376512050628662, |
| "mean_token_accuracy": 0.6733426377177238, |
| "num_tokens": 5025378.0, |
| "step": 39 |
| }, |
| { |
| "entropy": 1.1519914269447327, |
| "epoch": 0.5144694533762058, |
| "grad_norm": 0.3906066119670868, |
| "learning_rate": 4.819722568241274e-05, |
| "loss": 1.143772840499878, |
| "mean_token_accuracy": 0.6695929691195488, |
| "num_tokens": 5155612.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.1371284574270248, |
| "epoch": 0.5273311897106109, |
| "grad_norm": 0.13867925107479095, |
| "learning_rate": 4.806299712081172e-05, |
| "loss": 1.1251044273376465, |
| "mean_token_accuracy": 0.6758962124586105, |
| "num_tokens": 5284700.0, |
| "step": 41 |
| }, |
| { |
| "entropy": 1.137900173664093, |
| "epoch": 0.5401929260450161, |
| "grad_norm": 0.1261901706457138, |
| "learning_rate": 4.792415004490034e-05, |
| "loss": 1.1260221004486084, |
| "mean_token_accuracy": 0.6749331429600716, |
| "num_tokens": 5414507.0, |
| "step": 42 |
| }, |
| { |
| "entropy": 1.1564348489046097, |
| "epoch": 0.5530546623794212, |
| "grad_norm": 0.13415029644966125, |
| "learning_rate": 4.77807122597034e-05, |
| "loss": 1.1496460437774658, |
| "mean_token_accuracy": 0.6670970395207405, |
| "num_tokens": 5542542.0, |
| "step": 43 |
| }, |
| { |
| "entropy": 1.1538237184286118, |
| "epoch": 0.5659163987138264, |
| "grad_norm": 0.13376805186271667, |
| "learning_rate": 4.7632712489564926e-05, |
| "loss": 1.142371416091919, |
| "mean_token_accuracy": 0.6690651848912239, |
| "num_tokens": 5672067.0, |
| "step": 44 |
| }, |
| { |
| "entropy": 1.1469541490077972, |
| "epoch": 0.5787781350482315, |
| "grad_norm": 0.1293802261352539, |
| "learning_rate": 4.748018037239592e-05, |
| "loss": 1.1333601474761963, |
| "mean_token_accuracy": 0.6723547354340553, |
| "num_tokens": 5800609.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 1.1472823396325111, |
| "epoch": 0.5916398713826366, |
| "grad_norm": 0.13228115439414978, |
| "learning_rate": 4.732314645373921e-05, |
| "loss": 1.1329843997955322, |
| "mean_token_accuracy": 0.6703030541539192, |
| "num_tokens": 5930479.0, |
| "step": 46 |
| }, |
| { |
| "entropy": 1.1718984246253967, |
| "epoch": 0.6045016077170418, |
| "grad_norm": 0.13948604464530945, |
| "learning_rate": 4.7161642180652464e-05, |
| "loss": 1.1499552726745605, |
| "mean_token_accuracy": 0.6675512716174126, |
| "num_tokens": 6059629.0, |
| "step": 47 |
| }, |
| { |
| "entropy": 1.1396477073431015, |
| "epoch": 0.617363344051447, |
| "grad_norm": 0.1955496221780777, |
| "learning_rate": 4.699569989541074e-05, |
| "loss": 1.1260184049606323, |
| "mean_token_accuracy": 0.6692441701889038, |
| "num_tokens": 6188823.0, |
| "step": 48 |
| }, |
| { |
| "entropy": 1.1151351928710938, |
| "epoch": 0.6302250803858521, |
| "grad_norm": 0.12929458916187286, |
| "learning_rate": 4.6825352829029705e-05, |
| "loss": 1.113462209701538, |
| "mean_token_accuracy": 0.6757279857993126, |
| "num_tokens": 6318206.0, |
| "step": 49 |
| }, |
| { |
| "entropy": 1.1347133666276932, |
| "epoch": 0.6430868167202572, |
| "grad_norm": 0.13723939657211304, |
| "learning_rate": 4.665063509461097e-05, |
| "loss": 1.1344139575958252, |
| "mean_token_accuracy": 0.6683605685830116, |
| "num_tokens": 6447361.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.1195298731327057, |
| "epoch": 0.6559485530546624, |
| "grad_norm": 0.13720719516277313, |
| "learning_rate": 4.647158168051066e-05, |
| "loss": 1.1230884790420532, |
| "mean_token_accuracy": 0.6711617782711983, |
| "num_tokens": 6575145.0, |
| "step": 51 |
| }, |
| { |
| "entropy": 1.1320514380931854, |
| "epoch": 0.6688102893890675, |
| "grad_norm": 0.13503903150558472, |
| "learning_rate": 4.628822844333278e-05, |
| "loss": 1.1332721710205078, |
| "mean_token_accuracy": 0.6704861670732498, |
| "num_tokens": 6704707.0, |
| "step": 52 |
| }, |
| { |
| "entropy": 1.089632272720337, |
| "epoch": 0.6816720257234726, |
| "grad_norm": 0.13158641755580902, |
| "learning_rate": 4.6100612100748765e-05, |
| "loss": 1.0860098600387573, |
| "mean_token_accuracy": 0.6809655949473381, |
| "num_tokens": 6833251.0, |
| "step": 53 |
| }, |
| { |
| "entropy": 1.0989741384983063, |
| "epoch": 0.6945337620578779, |
| "grad_norm": 0.1341676563024521, |
| "learning_rate": 4.59087702241444e-05, |
| "loss": 1.0967470407485962, |
| "mean_token_accuracy": 0.6795956119894981, |
| "num_tokens": 6962347.0, |
| "step": 54 |
| }, |
| { |
| "entropy": 1.1306142508983612, |
| "epoch": 0.707395498392283, |
| "grad_norm": 0.13467787206172943, |
| "learning_rate": 4.571274123109606e-05, |
| "loss": 1.1218006610870361, |
| "mean_token_accuracy": 0.671770267188549, |
| "num_tokens": 7092228.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 1.1027807146310806, |
| "epoch": 0.7202572347266881, |
| "grad_norm": 0.13593968749046326, |
| "learning_rate": 4.551256437767719e-05, |
| "loss": 1.095794439315796, |
| "mean_token_accuracy": 0.6783477663993835, |
| "num_tokens": 7221530.0, |
| "step": 56 |
| }, |
| { |
| "entropy": 1.107944592833519, |
| "epoch": 0.7331189710610932, |
| "grad_norm": 0.1346762329339981, |
| "learning_rate": 4.530827975059715e-05, |
| "loss": 1.1026043891906738, |
| "mean_token_accuracy": 0.678081251680851, |
| "num_tokens": 7351093.0, |
| "step": 57 |
| }, |
| { |
| "entropy": 1.0734399557113647, |
| "epoch": 0.7459807073954984, |
| "grad_norm": 0.13501109182834625, |
| "learning_rate": 4.5099928259173516e-05, |
| "loss": 1.0623465776443481, |
| "mean_token_accuracy": 0.6868591457605362, |
| "num_tokens": 7480072.0, |
| "step": 58 |
| }, |
| { |
| "entropy": 1.1313968002796173, |
| "epoch": 0.7588424437299035, |
| "grad_norm": 0.13890723884105682, |
| "learning_rate": 4.488755162713975e-05, |
| "loss": 1.1160048246383667, |
| "mean_token_accuracy": 0.6727871224284172, |
| "num_tokens": 7609332.0, |
| "step": 59 |
| }, |
| { |
| "entropy": 1.095849946141243, |
| "epoch": 0.7717041800643086, |
| "grad_norm": 0.13449780642986298, |
| "learning_rate": 4.467119238428975e-05, |
| "loss": 1.0761332511901855, |
| "mean_token_accuracy": 0.6832353696227074, |
| "num_tokens": 7738055.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.1199684739112854, |
| "epoch": 0.7845659163987139, |
| "grad_norm": 0.1393275260925293, |
| "learning_rate": 4.445089385796099e-05, |
| "loss": 1.103759527206421, |
| "mean_token_accuracy": 0.6751135662198067, |
| "num_tokens": 7866931.0, |
| "step": 61 |
| }, |
| { |
| "entropy": 1.1070469170808792, |
| "epoch": 0.797427652733119, |
| "grad_norm": 0.1381961554288864, |
| "learning_rate": 4.422670016435792e-05, |
| "loss": 1.0982931852340698, |
| "mean_token_accuracy": 0.6770086959004402, |
| "num_tokens": 7996176.0, |
| "step": 62 |
| }, |
| { |
| "entropy": 1.094884604215622, |
| "epoch": 0.8102893890675241, |
| "grad_norm": 0.13925445079803467, |
| "learning_rate": 4.3998656199717435e-05, |
| "loss": 1.0968135595321655, |
| "mean_token_accuracy": 0.6778521537780762, |
| "num_tokens": 8122564.0, |
| "step": 63 |
| }, |
| { |
| "entropy": 1.1247451156377792, |
| "epoch": 0.8231511254019293, |
| "grad_norm": 0.1368095874786377, |
| "learning_rate": 4.3766807631318106e-05, |
| "loss": 1.1230825185775757, |
| "mean_token_accuracy": 0.6699690893292427, |
| "num_tokens": 8248931.0, |
| "step": 64 |
| }, |
| { |
| "entropy": 1.1110749542713165, |
| "epoch": 0.8360128617363344, |
| "grad_norm": 0.1357615739107132, |
| "learning_rate": 4.353120088833501e-05, |
| "loss": 1.1095378398895264, |
| "mean_token_accuracy": 0.674089215695858, |
| "num_tokens": 8377505.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 1.0629576370120049, |
| "epoch": 0.8488745980707395, |
| "grad_norm": 0.13470520079135895, |
| "learning_rate": 4.329188315254196e-05, |
| "loss": 1.0582916736602783, |
| "mean_token_accuracy": 0.6866432577371597, |
| "num_tokens": 8506057.0, |
| "step": 66 |
| }, |
| { |
| "entropy": 1.093516543507576, |
| "epoch": 0.8617363344051447, |
| "grad_norm": 0.13414740562438965, |
| "learning_rate": 4.3048902348863116e-05, |
| "loss": 1.0902202129364014, |
| "mean_token_accuracy": 0.6787593588232994, |
| "num_tokens": 8634840.0, |
| "step": 67 |
| }, |
| { |
| "entropy": 1.1101883202791214, |
| "epoch": 0.8745980707395499, |
| "grad_norm": 0.15326927602291107, |
| "learning_rate": 4.280230713577564e-05, |
| "loss": 1.1111077070236206, |
| "mean_token_accuracy": 0.6747671589255333, |
| "num_tokens": 8764641.0, |
| "step": 68 |
| }, |
| { |
| "entropy": 1.1037775576114655, |
| "epoch": 0.887459807073955, |
| "grad_norm": 0.13019205629825592, |
| "learning_rate": 4.255214689556557e-05, |
| "loss": 1.0991560220718384, |
| "mean_token_accuracy": 0.6750917881727219, |
| "num_tokens": 8894121.0, |
| "step": 69 |
| }, |
| { |
| "entropy": 1.0799639970064163, |
| "epoch": 0.9003215434083601, |
| "grad_norm": 0.13600145280361176, |
| "learning_rate": 4.229847172443866e-05, |
| "loss": 1.0659914016723633, |
| "mean_token_accuracy": 0.6862578168511391, |
| "num_tokens": 9021109.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.0842745453119278, |
| "epoch": 0.9131832797427653, |
| "grad_norm": 0.13035736978054047, |
| "learning_rate": 4.204133242248832e-05, |
| "loss": 1.0697667598724365, |
| "mean_token_accuracy": 0.6838485077023506, |
| "num_tokens": 9150645.0, |
| "step": 71 |
| }, |
| { |
| "entropy": 1.0927303433418274, |
| "epoch": 0.9260450160771704, |
| "grad_norm": 0.12931469082832336, |
| "learning_rate": 4.1780780483522575e-05, |
| "loss": 1.0853153467178345, |
| "mean_token_accuracy": 0.6794879287481308, |
| "num_tokens": 9279241.0, |
| "step": 72 |
| }, |
| { |
| "entropy": 1.0969749689102173, |
| "epoch": 0.9389067524115756, |
| "grad_norm": 0.14029595255851746, |
| "learning_rate": 4.151686808475204e-05, |
| "loss": 1.0877366065979004, |
| "mean_token_accuracy": 0.6796814650297165, |
| "num_tokens": 9409900.0, |
| "step": 73 |
| }, |
| { |
| "entropy": 1.0737035870552063, |
| "epoch": 0.9517684887459807, |
| "grad_norm": 0.13181892037391663, |
| "learning_rate": 4.1249648076341165e-05, |
| "loss": 1.0674468278884888, |
| "mean_token_accuracy": 0.6823575049638748, |
| "num_tokens": 9539355.0, |
| "step": 74 |
| }, |
| { |
| "entropy": 1.077784962952137, |
| "epoch": 0.9646302250803859, |
| "grad_norm": 0.13357527554035187, |
| "learning_rate": 4.0979173970824626e-05, |
| "loss": 1.0709781646728516, |
| "mean_token_accuracy": 0.6832851618528366, |
| "num_tokens": 9669661.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 1.0898889154195786, |
| "epoch": 0.977491961414791, |
| "grad_norm": 0.1380884051322937, |
| "learning_rate": 4.070549993239106e-05, |
| "loss": 1.079447627067566, |
| "mean_token_accuracy": 0.6803383082151413, |
| "num_tokens": 9799265.0, |
| "step": 76 |
| }, |
| { |
| "entropy": 1.1030114442110062, |
| "epoch": 0.9903536977491961, |
| "grad_norm": 0.14150051772594452, |
| "learning_rate": 4.0428680766036384e-05, |
| "loss": 1.0985944271087646, |
| "mean_token_accuracy": 0.6765774413943291, |
| "num_tokens": 9928475.0, |
| "step": 77 |
| }, |
| { |
| "entropy": 1.1045236786206563, |
| "epoch": 1.0, |
| "grad_norm": 0.15571743249893188, |
| "learning_rate": 4.0148771906588706e-05, |
| "loss": 1.078245759010315, |
| "mean_token_accuracy": 0.6769482294718424, |
| "num_tokens": 9977189.0, |
| "step": 78 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 234, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.0577206156596347e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
