| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012099213551119177, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024198427102238354, | |
| "grad_norm": 2.4724628925323486, | |
| "learning_rate": 2e-05, | |
| "loss": 6.8564, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00024198427102238354, | |
| "eval_loss": 1.701516032218933, | |
| "eval_runtime": 34.7817, | |
| "eval_samples_per_second": 50.026, | |
| "eval_steps_per_second": 25.013, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004839685420447671, | |
| "grad_norm": 1.9025840759277344, | |
| "learning_rate": 4e-05, | |
| "loss": 6.6296, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007259528130671506, | |
| "grad_norm": 2.4124374389648438, | |
| "learning_rate": 6e-05, | |
| "loss": 6.2767, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009679370840895341, | |
| "grad_norm": 1.8183839321136475, | |
| "learning_rate": 8e-05, | |
| "loss": 6.3779, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012099213551119178, | |
| "grad_norm": 1.4838781356811523, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3467, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014519056261343012, | |
| "grad_norm": 2.388962984085083, | |
| "learning_rate": 0.00012, | |
| "loss": 6.9645, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016938898971566847, | |
| "grad_norm": 2.148257255554199, | |
| "learning_rate": 0.00014, | |
| "loss": 6.1611, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0019358741681790683, | |
| "grad_norm": 2.916733980178833, | |
| "learning_rate": 0.00016, | |
| "loss": 7.0594, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002177858439201452, | |
| "grad_norm": 2.6664950847625732, | |
| "learning_rate": 0.00018, | |
| "loss": 6.5461, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0024198427102238356, | |
| "grad_norm": 2.471181631088257, | |
| "learning_rate": 0.0002, | |
| "loss": 5.6375, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002661826981246219, | |
| "grad_norm": 3.933795690536499, | |
| "learning_rate": 0.0001996917333733128, | |
| "loss": 5.941, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0029038112522686023, | |
| "grad_norm": 4.380200386047363, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 5.5236, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003145795523290986, | |
| "grad_norm": 4.660627365112305, | |
| "learning_rate": 0.00019723699203976766, | |
| "loss": 6.6635, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003145795523290986, | |
| "eval_loss": 1.5675233602523804, | |
| "eval_runtime": 34.6237, | |
| "eval_samples_per_second": 50.255, | |
| "eval_steps_per_second": 25.127, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0033877797943133695, | |
| "grad_norm": 4.443027973175049, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 6.2077, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003629764065335753, | |
| "grad_norm": 3.561443567276001, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 6.7655, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0038717483363581366, | |
| "grad_norm": 4.5063886642456055, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 6.4769, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00411373260738052, | |
| "grad_norm": 4.318703651428223, | |
| "learning_rate": 0.00018526401643540922, | |
| "loss": 6.5227, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004355716878402904, | |
| "grad_norm": 3.5019469261169434, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 6.579, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004597701149425287, | |
| "grad_norm": 3.5339195728302, | |
| "learning_rate": 0.0001760405965600031, | |
| "loss": 6.0713, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004839685420447671, | |
| "grad_norm": 3.601715564727783, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.1731, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005081669691470054, | |
| "grad_norm": 3.8356359004974365, | |
| "learning_rate": 0.00016494480483301836, | |
| "loss": 5.7358, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005323653962492438, | |
| "grad_norm": 3.1003851890563965, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 5.5531, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0055656382335148216, | |
| "grad_norm": 2.5003840923309326, | |
| "learning_rate": 0.0001522498564715949, | |
| "loss": 4.4929, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005807622504537205, | |
| "grad_norm": 3.624629259109497, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 5.5564, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006049606775559589, | |
| "grad_norm": 3.041182041168213, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 5.2167, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006291591046581972, | |
| "grad_norm": 3.689633846282959, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.2159, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006291591046581972, | |
| "eval_loss": 1.4802727699279785, | |
| "eval_runtime": 34.6152, | |
| "eval_samples_per_second": 50.267, | |
| "eval_steps_per_second": 25.133, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006533575317604356, | |
| "grad_norm": 3.0940749645233154, | |
| "learning_rate": 0.00012334453638559057, | |
| "loss": 6.2322, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006775559588626739, | |
| "grad_norm": 2.8410699367523193, | |
| "learning_rate": 0.0001156434465040231, | |
| "loss": 5.9674, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007017543859649123, | |
| "grad_norm": 3.7612247467041016, | |
| "learning_rate": 0.0001078459095727845, | |
| "loss": 6.2043, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007259528130671506, | |
| "grad_norm": 2.866365671157837, | |
| "learning_rate": 0.0001, | |
| "loss": 5.4941, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00750151240169389, | |
| "grad_norm": 3.132918119430542, | |
| "learning_rate": 9.215409042721552e-05, | |
| "loss": 5.7106, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.007743496672716273, | |
| "grad_norm": 3.546154499053955, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 6.2481, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.007985480943738656, | |
| "grad_norm": 3.2497243881225586, | |
| "learning_rate": 7.66554636144095e-05, | |
| "loss": 5.8963, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00822746521476104, | |
| "grad_norm": 2.7139110565185547, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 5.1744, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008469449485783424, | |
| "grad_norm": 3.148625373840332, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 5.7334, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008711433756805808, | |
| "grad_norm": 3.692917823791504, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 5.1302, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00895341802782819, | |
| "grad_norm": 3.0616631507873535, | |
| "learning_rate": 4.7750143528405126e-05, | |
| "loss": 5.4077, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009195402298850575, | |
| "grad_norm": 2.9874343872070312, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 5.458, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.009437386569872959, | |
| "grad_norm": 3.2835030555725098, | |
| "learning_rate": 3.5055195166981645e-05, | |
| "loss": 6.9377, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009437386569872959, | |
| "eval_loss": 1.4466110467910767, | |
| "eval_runtime": 34.6976, | |
| "eval_samples_per_second": 50.148, | |
| "eval_steps_per_second": 25.074, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009679370840895343, | |
| "grad_norm": 4.230708599090576, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 6.783, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009921355111917725, | |
| "grad_norm": 2.771728754043579, | |
| "learning_rate": 2.3959403439996907e-05, | |
| "loss": 5.4397, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010163339382940109, | |
| "grad_norm": 2.9131264686584473, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 5.1459, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.010405323653962493, | |
| "grad_norm": 3.516796350479126, | |
| "learning_rate": 1.4735983564590783e-05, | |
| "loss": 4.8108, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.010647307924984877, | |
| "grad_norm": 2.349928379058838, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 5.0233, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.010889292196007259, | |
| "grad_norm": 3.442686080932617, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 5.8234, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011131276467029643, | |
| "grad_norm": 4.57712459564209, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 5.9854, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.011373260738052027, | |
| "grad_norm": 2.746769666671753, | |
| "learning_rate": 2.7630079602323442e-06, | |
| "loss": 6.1983, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01161524500907441, | |
| "grad_norm": 3.05855655670166, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 4.7803, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.011857229280096793, | |
| "grad_norm": 2.8926703929901123, | |
| "learning_rate": 3.0826662668720364e-07, | |
| "loss": 5.5748, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.012099213551119177, | |
| "grad_norm": 3.569244861602783, | |
| "learning_rate": 0.0, | |
| "loss": 5.9647, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1910863162245120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |