| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.662921348314606, | |
| "eval_steps": 500, | |
| "global_step": 593, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11235955056179775, | |
| "grad_norm": 3.5541882514953613, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.9261, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2247191011235955, | |
| "grad_norm": 1.3109055757522583, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.3754, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33707865168539325, | |
| "grad_norm": 1.4723390340805054, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2649, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.449438202247191, | |
| "grad_norm": 0.7010077238082886, | |
| "learning_rate": 0.000199844353174683, | |
| "loss": 0.2166, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5617977528089888, | |
| "grad_norm": 1.1943029165267944, | |
| "learning_rate": 0.00019937789721741653, | |
| "loss": 0.1767, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6741573033707865, | |
| "grad_norm": 0.5831332206726074, | |
| "learning_rate": 0.00019860208417597864, | |
| "loss": 0.1481, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7865168539325843, | |
| "grad_norm": 1.139088749885559, | |
| "learning_rate": 0.00019751932910710805, | |
| "loss": 0.1318, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.898876404494382, | |
| "grad_norm": 1.130523681640625, | |
| "learning_rate": 0.00019613300255858616, | |
| "loss": 0.1277, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0112359550561798, | |
| "grad_norm": 0.8881850242614746, | |
| "learning_rate": 0.0001944474200769355, | |
| "loss": 0.1202, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1235955056179776, | |
| "grad_norm": 0.6445964574813843, | |
| "learning_rate": 0.00019246782877339766, | |
| "loss": 0.101, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2359550561797752, | |
| "grad_norm": 0.45679864287376404, | |
| "learning_rate": 0.00019020039099000907, | |
| "loss": 0.1078, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.348314606741573, | |
| "grad_norm": 0.5455164909362793, | |
| "learning_rate": 0.0001876521651166215, | |
| "loss": 0.0931, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.4606741573033708, | |
| "grad_norm": 0.5435442924499512, | |
| "learning_rate": 0.00018483108361858262, | |
| "loss": 0.0866, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.5730337078651684, | |
| "grad_norm": 0.4356015622615814, | |
| "learning_rate": 0.00018174592834347504, | |
| "loss": 0.0899, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.6853932584269664, | |
| "grad_norm": 0.6584963798522949, | |
| "learning_rate": 0.00017840630318378232, | |
| "loss": 0.0905, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.797752808988764, | |
| "grad_norm": 0.500027060508728, | |
| "learning_rate": 0.00017482260418058164, | |
| "loss": 0.091, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.9101123595505618, | |
| "grad_norm": 0.720208466053009, | |
| "learning_rate": 0.00017100598716132773, | |
| "loss": 0.0805, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.0224719101123596, | |
| "grad_norm": 0.7830264568328857, | |
| "learning_rate": 0.0001669683330124706, | |
| "loss": 0.0779, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.134831460674157, | |
| "grad_norm": 0.6720086932182312, | |
| "learning_rate": 0.0001627222106950102, | |
| "loss": 0.0731, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.247191011235955, | |
| "grad_norm": 0.4705169200897217, | |
| "learning_rate": 0.0001582808381181189, | |
| "loss": 0.0705, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.359550561797753, | |
| "grad_norm": 0.40476611256599426, | |
| "learning_rate": 0.0001536580409926296, | |
| "loss": 0.0715, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.4719101123595504, | |
| "grad_norm": 0.5198217034339905, | |
| "learning_rate": 0.0001488682097924756, | |
| "loss": 0.0658, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.5842696629213484, | |
| "grad_norm": 0.3450973331928253, | |
| "learning_rate": 0.00014392625495805912, | |
| "loss": 0.0613, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.696629213483146, | |
| "grad_norm": 0.4224022626876831, | |
| "learning_rate": 0.00013884756048099687, | |
| "loss": 0.0663, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.808988764044944, | |
| "grad_norm": 0.3117457926273346, | |
| "learning_rate": 0.00013364793601473106, | |
| "loss": 0.0577, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.9213483146067416, | |
| "grad_norm": 0.2872294783592224, | |
| "learning_rate": 0.00012834356766008197, | |
| "loss": 0.0626, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.033707865168539, | |
| "grad_norm": 0.4661742150783539, | |
| "learning_rate": 0.0001229509675789439, | |
| "loss": 0.0619, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.146067415730337, | |
| "grad_norm": 0.3543541729450226, | |
| "learning_rate": 0.00011748692259297347, | |
| "loss": 0.0494, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.258426966292135, | |
| "grad_norm": 0.3537474572658539, | |
| "learning_rate": 0.00011196844192727984, | |
| "loss": 0.052, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.370786516853933, | |
| "grad_norm": 0.3915044367313385, | |
| "learning_rate": 0.00010641270426178676, | |
| "loss": 0.0547, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.4831460674157304, | |
| "grad_norm": 0.3162959814071655, | |
| "learning_rate": 0.00010083700425509279, | |
| "loss": 0.0524, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.595505617977528, | |
| "grad_norm": 0.38653671741485596, | |
| "learning_rate": 9.52586987072972e-05, | |
| "loss": 0.0465, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.7078651685393256, | |
| "grad_norm": 0.3417101800441742, | |
| "learning_rate": 8.969515252938322e-05, | |
| "loss": 0.0482, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.8202247191011236, | |
| "grad_norm": 0.28841620683670044, | |
| "learning_rate": 8.41636846873528e-05, | |
| "loss": 0.0564, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.932584269662921, | |
| "grad_norm": 0.3317897915840149, | |
| "learning_rate": 7.868151428938502e-05, | |
| "loss": 0.0458, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.044943820224719, | |
| "grad_norm": 0.1963573545217514, | |
| "learning_rate": 7.326570698384568e-05, | |
| "loss": 0.0498, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.157303370786517, | |
| "grad_norm": 0.2925940454006195, | |
| "learning_rate": 6.793312183500759e-05, | |
| "loss": 0.0411, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.269662921348314, | |
| "grad_norm": 0.2857739329338074, | |
| "learning_rate": 6.270035884185367e-05, | |
| "loss": 0.0391, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.382022471910112, | |
| "grad_norm": 0.3383257985115051, | |
| "learning_rate": 5.758370726333434e-05, | |
| "loss": 0.0448, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.49438202247191, | |
| "grad_norm": 0.2550479471683502, | |
| "learning_rate": 5.2599094910938594e-05, | |
| "loss": 0.0382, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.606741573033708, | |
| "grad_norm": 0.21575377881526947, | |
| "learning_rate": 4.7762038566428155e-05, | |
| "loss": 0.043, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.719101123595506, | |
| "grad_norm": 0.24605822563171387, | |
| "learning_rate": 4.3087595679081096e-05, | |
| "loss": 0.0417, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.831460674157303, | |
| "grad_norm": 0.2827017903327942, | |
| "learning_rate": 3.8590317492808236e-05, | |
| "loss": 0.0421, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.943820224719101, | |
| "grad_norm": 0.2163945734500885, | |
| "learning_rate": 3.428420374905483e-05, | |
| "loss": 0.0412, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.056179775280899, | |
| "grad_norm": 0.22983698546886444, | |
| "learning_rate": 3.0182659106494192e-05, | |
| "loss": 0.0393, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.168539325842697, | |
| "grad_norm": 0.25033506751060486, | |
| "learning_rate": 2.629845141317656e-05, | |
| "loss": 0.0358, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.280898876404494, | |
| "grad_norm": 0.21685783565044403, | |
| "learning_rate": 2.264367196102869e-05, | |
| "loss": 0.0332, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.393258426966292, | |
| "grad_norm": 0.2170724868774414, | |
| "learning_rate": 1.9229697846429773e-05, | |
| "loss": 0.0379, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.50561797752809, | |
| "grad_norm": 0.17588071525096893, | |
| "learning_rate": 1.606715655403289e-05, | |
| "loss": 0.033, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.617977528089888, | |
| "grad_norm": 0.3224557936191559, | |
| "learning_rate": 1.3165892874079899e-05, | |
| "loss": 0.0379, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.730337078651686, | |
| "grad_norm": 0.443591445684433, | |
| "learning_rate": 1.0534938256194671e-05, | |
| "loss": 0.0352, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.842696629213483, | |
| "grad_norm": 0.23971615731716156, | |
| "learning_rate": 8.182482695053728e-06, | |
| "loss": 0.0343, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.955056179775281, | |
| "grad_norm": 0.33371302485466003, | |
| "learning_rate": 6.1158492354529195e-06, | |
| "loss": 0.0346, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 6.067415730337078, | |
| "grad_norm": 0.2301403433084488, | |
| "learning_rate": 4.3414711761338375e-06, | |
| "loss": 0.0343, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.179775280898877, | |
| "grad_norm": 0.16674034297466278, | |
| "learning_rate": 2.8648720433333996e-06, | |
| "loss": 0.03, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.292134831460674, | |
| "grad_norm": 0.2350272834300995, | |
| "learning_rate": 1.6906483963973207e-06, | |
| "loss": 0.0344, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.404494382022472, | |
| "grad_norm": 0.1408814638853073, | |
| "learning_rate": 8.224555189827565e-07, | |
| "loss": 0.0387, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.51685393258427, | |
| "grad_norm": 0.2586834132671356, | |
| "learning_rate": 2.629960403923715e-07, | |
| "loss": 0.0329, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.629213483146067, | |
| "grad_norm": 0.21313035488128662, | |
| "learning_rate": 1.4011522460866122e-08, | |
| "loss": 0.0324, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.662921348314606, | |
| "step": 593, | |
| "total_flos": 8.40154581763943e+16, | |
| "train_loss": 0.0879759074865666, | |
| "train_runtime": 704.4365, | |
| "train_samples_per_second": 53.876, | |
| "train_steps_per_second": 0.842 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 593, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.40154581763943e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |