| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9986431478968792, | |
| "eval_steps": 500, | |
| "global_step": 368, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.027137042062415198, | |
| "grad_norm": 1.4497582912445068, | |
| "learning_rate": 0.0001998659482680456, | |
| "loss": 3.4336, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.054274084124830396, | |
| "grad_norm": 1.846526861190796, | |
| "learning_rate": 0.00019904804439875633, | |
| "loss": 1.9601, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0814111261872456, | |
| "grad_norm": 0.9556183815002441, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 1.202, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10854816824966079, | |
| "grad_norm": 1.0818341970443726, | |
| "learning_rate": 0.00019521176659107142, | |
| "loss": 1.1366, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13568521031207598, | |
| "grad_norm": 0.9879324436187744, | |
| "learning_rate": 0.00019222195128618106, | |
| "loss": 1.0269, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1628222523744912, | |
| "grad_norm": 1.1216270923614502, | |
| "learning_rate": 0.000188545602565321, | |
| "loss": 1.0766, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18995929443690637, | |
| "grad_norm": 1.1110620498657227, | |
| "learning_rate": 0.00018421008849228118, | |
| "loss": 0.9947, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21709633649932158, | |
| "grad_norm": 0.8764580488204956, | |
| "learning_rate": 0.00017924768419510904, | |
| "loss": 1.0024, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24423337856173677, | |
| "grad_norm": 1.2004687786102295, | |
| "learning_rate": 0.00017369533159843369, | |
| "loss": 1.04, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.27137042062415195, | |
| "grad_norm": 0.9665369391441345, | |
| "learning_rate": 0.00016759436441447545, | |
| "loss": 0.9809, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 1.5474181175231934, | |
| "learning_rate": 0.00016099020044000727, | |
| "loss": 0.9405, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3256445047489824, | |
| "grad_norm": 1.014674186706543, | |
| "learning_rate": 0.00015393200344991995, | |
| "loss": 0.9054, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.35278154681139756, | |
| "grad_norm": 1.013979434967041, | |
| "learning_rate": 0.00014647231720437686, | |
| "loss": 0.9754, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.37991858887381275, | |
| "grad_norm": 1.0418416261672974, | |
| "learning_rate": 0.0001386666742941419, | |
| "loss": 0.8711, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.40705563093622793, | |
| "grad_norm": 0.9280593395233154, | |
| "learning_rate": 0.0001305731827359753, | |
| "loss": 0.8358, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.43419267299864317, | |
| "grad_norm": 1.0268974304199219, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 0.8568, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.46132971506105835, | |
| "grad_norm": 0.9812881350517273, | |
| "learning_rate": 0.00011376535145871684, | |
| "loss": 0.888, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.48846675712347354, | |
| "grad_norm": 1.2109171152114868, | |
| "learning_rate": 0.00010517613528842097, | |
| "loss": 0.9166, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5156037991858887, | |
| "grad_norm": 0.9860134124755859, | |
| "learning_rate": 9.654838610302923e-05, | |
| "loss": 0.8357, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5427408412483039, | |
| "grad_norm": 1.1094295978546143, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.928, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5698778833107191, | |
| "grad_norm": 0.9386014342308044, | |
| "learning_rate": 7.943400969140635e-05, | |
| "loss": 0.9522, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 1.0436668395996094, | |
| "learning_rate": 7.107478804634325e-05, | |
| "loss": 0.8619, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6241519674355496, | |
| "grad_norm": 1.0143946409225464, | |
| "learning_rate": 6.293089609549325e-05, | |
| "loss": 0.8046, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6512890094979648, | |
| "grad_norm": 1.107064127922058, | |
| "learning_rate": 5.506295990328385e-05, | |
| "loss": 0.8532, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6784260515603799, | |
| "grad_norm": 0.8748170137405396, | |
| "learning_rate": 4.75295512200992e-05, | |
| "loss": 0.8276, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7055630936227951, | |
| "grad_norm": 1.0721319913864136, | |
| "learning_rate": 4.038675145307747e-05, | |
| "loss": 0.7517, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7327001356852103, | |
| "grad_norm": 1.1542731523513794, | |
| "learning_rate": 3.36877341759205e-05, | |
| "loss": 0.8542, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7598371777476255, | |
| "grad_norm": 0.89125657081604, | |
| "learning_rate": 2.7482369285662378e-05, | |
| "loss": 0.8601, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7869742198100407, | |
| "grad_norm": 0.9904446601867676, | |
| "learning_rate": 2.181685175319702e-05, | |
| "loss": 0.8787, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8141112618724559, | |
| "grad_norm": 0.9311710596084595, | |
| "learning_rate": 1.6733357731279377e-05, | |
| "loss": 0.7493, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.841248303934871, | |
| "grad_norm": 1.0216141939163208, | |
| "learning_rate": 1.2269730580055805e-05, | |
| "loss": 0.7497, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.8683853459972863, | |
| "grad_norm": 0.9951556324958801, | |
| "learning_rate": 8.45919914746337e-06, | |
| "loss": 0.8324, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 1.0728198289871216, | |
| "learning_rate": 5.3301304017194135e-06, | |
| "loss": 0.7964, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9226594301221167, | |
| "grad_norm": 1.1030397415161133, | |
| "learning_rate": 2.905818257394799e-06, | |
| "loss": 0.8166, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.9497964721845319, | |
| "grad_norm": 0.974777102470398, | |
| "learning_rate": 1.2043101671253554e-06, | |
| "loss": 0.7952, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9769335142469471, | |
| "grad_norm": 1.078715443611145, | |
| "learning_rate": 2.382727698752474e-07, | |
| "loss": 0.8726, | |
| "step": 360 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 368, | |
| "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": 1620605933346816.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |