| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07635336336565626, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015270672673131252, | |
| "grad_norm": 1.7919381856918335, | |
| "learning_rate": 0.00019980267284282717, | |
| "loss": 2.5081, | |
| "mean_token_accuracy": 0.5467605337500572, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0030541345346262504, | |
| "grad_norm": 2.8579838275909424, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 1.7298, | |
| "mean_token_accuracy": 0.6468371748924255, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004581201801939375, | |
| "grad_norm": 1.7089707851409912, | |
| "learning_rate": 0.0001982287250728689, | |
| "loss": 1.1637, | |
| "mean_token_accuracy": 0.7540688991546631, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006108269069252501, | |
| "grad_norm": 0.9711195826530457, | |
| "learning_rate": 0.0001968583161128631, | |
| "loss": 0.8899, | |
| "mean_token_accuracy": 0.8186888545751572, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007635336336565626, | |
| "grad_norm": 0.8973957896232605, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.8256, | |
| "mean_token_accuracy": 0.8281645506620408, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00916240360387875, | |
| "grad_norm": 0.9836689829826355, | |
| "learning_rate": 0.00019297764858882514, | |
| "loss": 0.754, | |
| "mean_token_accuracy": 0.8368939191102982, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.010689470871191877, | |
| "grad_norm": 1.0244220495224, | |
| "learning_rate": 0.00019048270524660196, | |
| "loss": 0.7019, | |
| "mean_token_accuracy": 0.8408633172512054, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.012216538138505002, | |
| "grad_norm": 1.1119804382324219, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 0.6498, | |
| "mean_token_accuracy": 0.8521306127309799, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.013743605405818126, | |
| "grad_norm": 0.7104642987251282, | |
| "learning_rate": 0.00018443279255020152, | |
| "loss": 0.6679, | |
| "mean_token_accuracy": 0.8470089048147201, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.015270672673131251, | |
| "grad_norm": 0.7890557646751404, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.6581, | |
| "mean_token_accuracy": 0.8512038260698318, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.016797739940444378, | |
| "grad_norm": 0.6953688859939575, | |
| "learning_rate": 0.00017705132427757895, | |
| "loss": 0.6358, | |
| "mean_token_accuracy": 0.8534704208374023, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0183248072077575, | |
| "grad_norm": 0.8764053583145142, | |
| "learning_rate": 0.00017289686274214118, | |
| "loss": 0.6124, | |
| "mean_token_accuracy": 0.857587480545044, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.019851874475070627, | |
| "grad_norm": 0.8632748126983643, | |
| "learning_rate": 0.00016845471059286887, | |
| "loss": 0.6382, | |
| "mean_token_accuracy": 0.8533297270536423, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.021378941742383754, | |
| "grad_norm": 0.9536803960800171, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 0.6252, | |
| "mean_token_accuracy": 0.8563201695680618, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.022906009009696877, | |
| "grad_norm": 0.7280343174934387, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 0.6105, | |
| "mean_token_accuracy": 0.8567106693983078, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.024433076277010003, | |
| "grad_norm": 0.6883084177970886, | |
| "learning_rate": 0.00015358267949789966, | |
| "loss": 0.6134, | |
| "mean_token_accuracy": 0.8576973646879196, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.025960143544323126, | |
| "grad_norm": 0.7537200450897217, | |
| "learning_rate": 0.00014817536741017152, | |
| "loss": 0.6182, | |
| "mean_token_accuracy": 0.8572364389896393, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.027487210811636253, | |
| "grad_norm": 0.8564761877059937, | |
| "learning_rate": 0.00014257792915650728, | |
| "loss": 0.604, | |
| "mean_token_accuracy": 0.8564972043037414, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02901427807894938, | |
| "grad_norm": 0.9395449757575989, | |
| "learning_rate": 0.00013681245526846783, | |
| "loss": 0.6082, | |
| "mean_token_accuracy": 0.8573319047689438, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.030541345346262502, | |
| "grad_norm": 1.4290846586227417, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.5852, | |
| "mean_token_accuracy": 0.859686890244484, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.032068412613575625, | |
| "grad_norm": 0.8474317789077759, | |
| "learning_rate": 0.0001248689887164855, | |
| "loss": 0.5912, | |
| "mean_token_accuracy": 0.863548994064331, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.033595479880888755, | |
| "grad_norm": 0.8646250367164612, | |
| "learning_rate": 0.00011873813145857249, | |
| "loss": 0.5862, | |
| "mean_token_accuracy": 0.861778911948204, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.03512254714820188, | |
| "grad_norm": 0.9591971635818481, | |
| "learning_rate": 0.00011253332335643043, | |
| "loss": 0.5656, | |
| "mean_token_accuracy": 0.8678788006305694, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.036649614415515, | |
| "grad_norm": 0.7952109575271606, | |
| "learning_rate": 0.00010627905195293135, | |
| "loss": 0.581, | |
| "mean_token_accuracy": 0.8648124188184738, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.03817668168282813, | |
| "grad_norm": 0.7618094086647034, | |
| "learning_rate": 0.0001, | |
| "loss": 0.576, | |
| "mean_token_accuracy": 0.8639664649963379, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.039703748950141254, | |
| "grad_norm": 0.730375349521637, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 0.5915, | |
| "mean_token_accuracy": 0.8597521275281906, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.04123081621745438, | |
| "grad_norm": 0.8533547520637512, | |
| "learning_rate": 8.746667664356956e-05, | |
| "loss": 0.5891, | |
| "mean_token_accuracy": 0.859322988986969, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.04275788348476751, | |
| "grad_norm": 0.7875514626502991, | |
| "learning_rate": 8.126186854142752e-05, | |
| "loss": 0.5957, | |
| "mean_token_accuracy": 0.8590130746364594, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.04428495075208063, | |
| "grad_norm": 0.8987193703651428, | |
| "learning_rate": 7.513101128351454e-05, | |
| "loss": 0.5997, | |
| "mean_token_accuracy": 0.8575950294733048, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.04581201801939375, | |
| "grad_norm": 0.7341880202293396, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.5614, | |
| "mean_token_accuracy": 0.8668889582157135, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.047339085286706876, | |
| "grad_norm": 0.7949256300926208, | |
| "learning_rate": 6.318754473153221e-05, | |
| "loss": 0.5936, | |
| "mean_token_accuracy": 0.8569323867559433, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.048866152554020006, | |
| "grad_norm": 0.840946614742279, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 0.5901, | |
| "mean_token_accuracy": 0.863608232140541, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.05039321982133313, | |
| "grad_norm": 0.9876859188079834, | |
| "learning_rate": 5.182463258982846e-05, | |
| "loss": 0.5787, | |
| "mean_token_accuracy": 0.8655537277460098, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.05192028708864625, | |
| "grad_norm": 0.7635581493377686, | |
| "learning_rate": 4.6417320502100316e-05, | |
| "loss": 0.6074, | |
| "mean_token_accuracy": 0.8565149992704392, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.05344735435595938, | |
| "grad_norm": 0.7946358919143677, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.6015, | |
| "mean_token_accuracy": 0.8584772288799286, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.054974421623272506, | |
| "grad_norm": 0.8052517771720886, | |
| "learning_rate": 3.6257601025131026e-05, | |
| "loss": 0.5552, | |
| "mean_token_accuracy": 0.8673796206712723, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.05650148889058563, | |
| "grad_norm": 0.7466617226600647, | |
| "learning_rate": 3.154528940713113e-05, | |
| "loss": 0.5954, | |
| "mean_token_accuracy": 0.8603360831737519, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.05802855615789876, | |
| "grad_norm": 0.7672128081321716, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 0.5764, | |
| "mean_token_accuracy": 0.8672617733478546, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.05955562342521188, | |
| "grad_norm": 0.7813590168952942, | |
| "learning_rate": 2.2948675722421086e-05, | |
| "loss": 0.5812, | |
| "mean_token_accuracy": 0.8635528743267059, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.061082690692525005, | |
| "grad_norm": 0.7313287854194641, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.5563, | |
| "mean_token_accuracy": 0.8667043030261994, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06260975795983813, | |
| "grad_norm": 0.9430689215660095, | |
| "learning_rate": 1.5567207449798515e-05, | |
| "loss": 0.5452, | |
| "mean_token_accuracy": 0.871171161532402, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.06413682522715125, | |
| "grad_norm": 0.8281370401382446, | |
| "learning_rate": 1.2369331995613665e-05, | |
| "loss": 0.5809, | |
| "mean_token_accuracy": 0.8636080652475357, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.06566389249446439, | |
| "grad_norm": 0.704873263835907, | |
| "learning_rate": 9.517294753398064e-06, | |
| "loss": 0.5975, | |
| "mean_token_accuracy": 0.859060087800026, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.06719095976177751, | |
| "grad_norm": 0.8515197038650513, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 0.5867, | |
| "mean_token_accuracy": 0.8638981640338897, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.06871802702909063, | |
| "grad_norm": 0.7860581874847412, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 0.5802, | |
| "mean_token_accuracy": 0.8683864206075669, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07024509429640376, | |
| "grad_norm": 0.8138625621795654, | |
| "learning_rate": 3.1416838871368924e-06, | |
| "loss": 0.5918, | |
| "mean_token_accuracy": 0.8596341729164123, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.07177216156371688, | |
| "grad_norm": 0.8401088714599609, | |
| "learning_rate": 1.771274927131139e-06, | |
| "loss": 0.6209, | |
| "mean_token_accuracy": 0.8542895227670669, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.07329922883103, | |
| "grad_norm": 0.993623673915863, | |
| "learning_rate": 7.885298685522235e-07, | |
| "loss": 0.5791, | |
| "mean_token_accuracy": 0.865888985991478, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.07482629609834313, | |
| "grad_norm": 0.8312510848045349, | |
| "learning_rate": 1.973271571728441e-07, | |
| "loss": 0.5615, | |
| "mean_token_accuracy": 0.8679140955209732, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.07635336336565626, | |
| "grad_norm": 0.9254234433174133, | |
| "learning_rate": 0.0, | |
| "loss": 0.5822, | |
| "mean_token_accuracy": 0.8632416158914566, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "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": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5806155567955968.0, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |