| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 7815, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06397952655150352, | |
| "grad_norm": 1.344713568687439, | |
| "learning_rate": 0.00029616122840690973, | |
| "loss": 2.6677, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12795905310300704, | |
| "grad_norm": 1.3358043432235718, | |
| "learning_rate": 0.00029232245681381954, | |
| "loss": 2.2932, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19193857965451055, | |
| "grad_norm": 1.3450862169265747, | |
| "learning_rate": 0.0002885220729366602, | |
| "loss": 2.2158, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2559181062060141, | |
| "grad_norm": 1.1904783248901367, | |
| "learning_rate": 0.00028468330134357004, | |
| "loss": 2.1907, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3198976327575176, | |
| "grad_norm": 1.3194555044174194, | |
| "learning_rate": 0.00028084452975047985, | |
| "loss": 2.1725, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3838771593090211, | |
| "grad_norm": 1.3454678058624268, | |
| "learning_rate": 0.0002770057581573896, | |
| "loss": 2.1586, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44785668586052463, | |
| "grad_norm": 1.318642497062683, | |
| "learning_rate": 0.0002731669865642994, | |
| "loss": 2.1429, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5118362124120281, | |
| "grad_norm": 1.1936390399932861, | |
| "learning_rate": 0.0002693282149712092, | |
| "loss": 2.0988, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5758157389635317, | |
| "grad_norm": 1.1406426429748535, | |
| "learning_rate": 0.000265489443378119, | |
| "loss": 2.0834, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6397952655150352, | |
| "grad_norm": 1.2195415496826172, | |
| "learning_rate": 0.0002616506717850288, | |
| "loss": 2.1004, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7037747920665387, | |
| "grad_norm": 1.2042839527130127, | |
| "learning_rate": 0.00025781190019193856, | |
| "loss": 2.0883, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.7677543186180422, | |
| "grad_norm": 1.159279465675354, | |
| "learning_rate": 0.0002539731285988483, | |
| "loss": 2.0852, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8317338451695457, | |
| "grad_norm": 1.2210711240768433, | |
| "learning_rate": 0.00025013435700575813, | |
| "loss": 2.0449, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.8957133717210493, | |
| "grad_norm": 1.2941797971725464, | |
| "learning_rate": 0.00024629558541266794, | |
| "loss": 2.0455, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9596928982725528, | |
| "grad_norm": 1.1550540924072266, | |
| "learning_rate": 0.00024245681381957772, | |
| "loss": 2.0293, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0236724248240563, | |
| "grad_norm": 1.3520652055740356, | |
| "learning_rate": 0.0002386564299424184, | |
| "loss": 1.9799, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.0876519513755598, | |
| "grad_norm": 1.375148892402649, | |
| "learning_rate": 0.0002348176583493282, | |
| "loss": 1.9032, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.1516314779270633, | |
| "grad_norm": 1.4116652011871338, | |
| "learning_rate": 0.00023097888675623797, | |
| "loss": 1.9398, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.2156110044785668, | |
| "grad_norm": 1.2254273891448975, | |
| "learning_rate": 0.00022714011516314776, | |
| "loss": 1.9097, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.2795905310300704, | |
| "grad_norm": 1.3888587951660156, | |
| "learning_rate": 0.00022330134357005757, | |
| "loss": 1.9039, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.3435700575815739, | |
| "grad_norm": 1.4431171417236328, | |
| "learning_rate": 0.00021946257197696736, | |
| "loss": 1.9095, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.4075495841330774, | |
| "grad_norm": 1.2467221021652222, | |
| "learning_rate": 0.00021562380038387714, | |
| "loss": 1.9103, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.471529110684581, | |
| "grad_norm": 1.41363525390625, | |
| "learning_rate": 0.00021178502879078693, | |
| "loss": 1.9132, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.5355086372360844, | |
| "grad_norm": 1.4501458406448364, | |
| "learning_rate": 0.0002079462571976967, | |
| "loss": 1.9095, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.599488163787588, | |
| "grad_norm": 1.2889657020568848, | |
| "learning_rate": 0.00020410748560460652, | |
| "loss": 1.9308, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.6634676903390915, | |
| "grad_norm": 1.4488581418991089, | |
| "learning_rate": 0.0002002687140115163, | |
| "loss": 1.9161, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.727447216890595, | |
| "grad_norm": 1.3905428647994995, | |
| "learning_rate": 0.0001964299424184261, | |
| "loss": 1.8958, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.7914267434420985, | |
| "grad_norm": 1.3509632349014282, | |
| "learning_rate": 0.00019259117082533588, | |
| "loss": 1.8933, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.855406269993602, | |
| "grad_norm": 1.3293097019195557, | |
| "learning_rate": 0.00018875239923224566, | |
| "loss": 1.8902, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.9193857965451055, | |
| "grad_norm": 1.3575371503829956, | |
| "learning_rate": 0.00018491362763915547, | |
| "loss": 1.9107, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.983365323096609, | |
| "grad_norm": 1.4029614925384521, | |
| "learning_rate": 0.00018107485604606526, | |
| "loss": 1.9122, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.0473448496481126, | |
| "grad_norm": 1.6483345031738281, | |
| "learning_rate": 0.00017723608445297504, | |
| "loss": 1.7797, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.111324376199616, | |
| "grad_norm": 1.7276026010513306, | |
| "learning_rate": 0.00017339731285988483, | |
| "loss": 1.7411, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.1753039027511196, | |
| "grad_norm": 1.6449826955795288, | |
| "learning_rate": 0.00016955854126679461, | |
| "loss": 1.7355, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.239283429302623, | |
| "grad_norm": 1.606766939163208, | |
| "learning_rate": 0.00016571976967370443, | |
| "loss": 1.7479, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.3032629558541267, | |
| "grad_norm": 1.6743805408477783, | |
| "learning_rate": 0.0001618809980806142, | |
| "loss": 1.7376, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.36724248240563, | |
| "grad_norm": 1.58048415184021, | |
| "learning_rate": 0.00015804222648752397, | |
| "loss": 1.7499, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.4312220089571337, | |
| "grad_norm": 1.7509996891021729, | |
| "learning_rate": 0.00015420345489443375, | |
| "loss": 1.741, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.495201535508637, | |
| "grad_norm": 1.6279881000518799, | |
| "learning_rate": 0.00015036468330134354, | |
| "loss": 1.7584, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.5591810620601407, | |
| "grad_norm": 1.6708228588104248, | |
| "learning_rate": 0.00014652591170825335, | |
| "loss": 1.7505, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.6231605886116443, | |
| "grad_norm": 1.628318428993225, | |
| "learning_rate": 0.00014268714011516314, | |
| "loss": 1.7535, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.6871401151631478, | |
| "grad_norm": 1.66116464138031, | |
| "learning_rate": 0.00013884836852207292, | |
| "loss": 1.7534, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.7511196417146513, | |
| "grad_norm": 1.7303767204284668, | |
| "learning_rate": 0.0001350095969289827, | |
| "loss": 1.7605, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.815099168266155, | |
| "grad_norm": 1.6892797946929932, | |
| "learning_rate": 0.00013117082533589252, | |
| "loss": 1.7343, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.8790786948176583, | |
| "grad_norm": 1.700649380683899, | |
| "learning_rate": 0.0001273320537428023, | |
| "loss": 1.7545, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.943058221369162, | |
| "grad_norm": 1.7158896923065186, | |
| "learning_rate": 0.0001234932821497121, | |
| "loss": 1.7472, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.0070377479206654, | |
| "grad_norm": 1.5952404737472534, | |
| "learning_rate": 0.00011965451055662187, | |
| "loss": 1.709, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.071017274472169, | |
| "grad_norm": 1.8965271711349487, | |
| "learning_rate": 0.00011581573896353166, | |
| "loss": 1.5308, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.1349968010236724, | |
| "grad_norm": 1.9957573413848877, | |
| "learning_rate": 0.00011197696737044146, | |
| "loss": 1.564, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.198976327575176, | |
| "grad_norm": 2.0544333457946777, | |
| "learning_rate": 0.00010813819577735124, | |
| "loss": 1.5668, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.2629558541266794, | |
| "grad_norm": 2.041703462600708, | |
| "learning_rate": 0.00010429942418426103, | |
| "loss": 1.5766, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.326935380678183, | |
| "grad_norm": 2.300631284713745, | |
| "learning_rate": 0.00010046065259117082, | |
| "loss": 1.5701, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.3909149072296865, | |
| "grad_norm": 1.9454134702682495, | |
| "learning_rate": 9.662188099808061e-05, | |
| "loss": 1.5701, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 3.45489443378119, | |
| "grad_norm": 2.113377571105957, | |
| "learning_rate": 9.278310940499041e-05, | |
| "loss": 1.5882, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.5188739603326935, | |
| "grad_norm": 2.2492353916168213, | |
| "learning_rate": 8.894433781190018e-05, | |
| "loss": 1.5778, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.582853486884197, | |
| "grad_norm": 2.1024489402770996, | |
| "learning_rate": 8.510556621880996e-05, | |
| "loss": 1.5926, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.6468330134357005, | |
| "grad_norm": 2.1116743087768555, | |
| "learning_rate": 8.126679462571976e-05, | |
| "loss": 1.5937, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 3.710812539987204, | |
| "grad_norm": 2.013080596923828, | |
| "learning_rate": 7.742802303262955e-05, | |
| "loss": 1.5913, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.7747920665387076, | |
| "grad_norm": 2.1557400226593018, | |
| "learning_rate": 7.358925143953934e-05, | |
| "loss": 1.6041, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 3.838771593090211, | |
| "grad_norm": 2.10186767578125, | |
| "learning_rate": 6.975047984644913e-05, | |
| "loss": 1.5799, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.9027511196417146, | |
| "grad_norm": 2.129519462585449, | |
| "learning_rate": 6.591170825335893e-05, | |
| "loss": 1.5946, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 3.966730646193218, | |
| "grad_norm": 2.045646905899048, | |
| "learning_rate": 6.20729366602687e-05, | |
| "loss": 1.5882, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 4.030710172744722, | |
| "grad_norm": 2.2427146434783936, | |
| "learning_rate": 5.82341650671785e-05, | |
| "loss": 1.5005, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 4.094689699296225, | |
| "grad_norm": 2.2632296085357666, | |
| "learning_rate": 5.439539347408829e-05, | |
| "loss": 1.3888, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 4.158669225847729, | |
| "grad_norm": 2.541220188140869, | |
| "learning_rate": 5.0556621880998075e-05, | |
| "loss": 1.4124, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.222648752399232, | |
| "grad_norm": 2.566311836242676, | |
| "learning_rate": 4.6717850287907866e-05, | |
| "loss": 1.409, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 4.286628278950736, | |
| "grad_norm": 2.425945281982422, | |
| "learning_rate": 4.287907869481765e-05, | |
| "loss": 1.4134, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 4.350607805502239, | |
| "grad_norm": 2.4377615451812744, | |
| "learning_rate": 3.904030710172744e-05, | |
| "loss": 1.4257, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 4.414587332053743, | |
| "grad_norm": 2.6660194396972656, | |
| "learning_rate": 3.5201535508637234e-05, | |
| "loss": 1.4288, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 4.478566858605246, | |
| "grad_norm": 2.393036365509033, | |
| "learning_rate": 3.1362763915547026e-05, | |
| "loss": 1.4182, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.54254638515675, | |
| "grad_norm": 2.6361422538757324, | |
| "learning_rate": 2.752399232245681e-05, | |
| "loss": 1.4149, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 4.606525911708253, | |
| "grad_norm": 2.6104772090911865, | |
| "learning_rate": 2.3685220729366603e-05, | |
| "loss": 1.407, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 4.670505438259757, | |
| "grad_norm": 2.4266579151153564, | |
| "learning_rate": 1.9846449136276387e-05, | |
| "loss": 1.4113, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 4.73448496481126, | |
| "grad_norm": 2.5348973274230957, | |
| "learning_rate": 1.600767754318618e-05, | |
| "loss": 1.3936, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 4.798464491362764, | |
| "grad_norm": 2.3764045238494873, | |
| "learning_rate": 1.2168905950095967e-05, | |
| "loss": 1.4097, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.862444017914267, | |
| "grad_norm": 2.4267590045928955, | |
| "learning_rate": 8.330134357005757e-06, | |
| "loss": 1.4209, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 4.926423544465771, | |
| "grad_norm": 2.7150962352752686, | |
| "learning_rate": 4.4913627639155465e-06, | |
| "loss": 1.4148, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 4.990403071017274, | |
| "grad_norm": 2.550471067428589, | |
| "learning_rate": 6.525911708253358e-07, | |
| "loss": 1.4254, | |
| "step": 7800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 7815, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 2500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2180160877992346e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |