{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.9992985737666586, "eval_steps": 500, "global_step": 6414, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04676174888940846, "grad_norm": 0.414691299200058, "learning_rate": 9.923004399748587e-06, "loss": 1.3939, "step": 100 }, { "epoch": 0.09352349777881692, "grad_norm": 0.373704195022583, "learning_rate": 9.765870521684476e-06, "loss": 1.2045, "step": 200 }, { "epoch": 0.1402852466682254, "grad_norm": 0.4187537431716919, "learning_rate": 9.608736643620365e-06, "loss": 1.2093, "step": 300 }, { "epoch": 0.18704699555763385, "grad_norm": 0.49985188245773315, "learning_rate": 9.451602765556255e-06, "loss": 1.1465, "step": 400 }, { "epoch": 0.23380874444704233, "grad_norm": 0.547389805316925, "learning_rate": 9.294468887492145e-06, "loss": 1.1502, "step": 500 }, { "epoch": 0.2805704933364508, "grad_norm": 0.521124541759491, "learning_rate": 9.137335009428033e-06, "loss": 1.1455, "step": 600 }, { "epoch": 0.32733224222585927, "grad_norm": 0.5321390628814697, "learning_rate": 8.980201131363923e-06, "loss": 1.1196, "step": 700 }, { "epoch": 0.3740939911152677, "grad_norm": 0.5767441987991333, "learning_rate": 8.823067253299812e-06, "loss": 1.115, "step": 800 }, { "epoch": 0.4208557400046762, "grad_norm": 0.6053145527839661, "learning_rate": 8.6659333752357e-06, "loss": 1.1419, "step": 900 }, { "epoch": 0.46761748889408467, "grad_norm": 0.6067389249801636, "learning_rate": 8.50879949717159e-06, "loss": 1.1077, "step": 1000 }, { "epoch": 0.5143792377834931, "grad_norm": 0.6225459575653076, "learning_rate": 8.35166561910748e-06, "loss": 1.1181, "step": 1100 }, { "epoch": 0.5611409866729016, "grad_norm": 0.6895543932914734, "learning_rate": 8.19453174104337e-06, "loss": 1.1015, "step": 1200 }, { "epoch": 0.60790273556231, "grad_norm": 0.6458436846733093, "learning_rate": 8.03739786297926e-06, "loss": 1.1198, "step": 1300 }, { "epoch": 0.6546644844517185, "grad_norm": 0.663877010345459, "learning_rate": 7.88026398491515e-06, "loss": 1.0982, "step": 1400 }, { "epoch": 0.701426233341127, "grad_norm": 0.6076435446739197, "learning_rate": 7.723130106851037e-06, "loss": 1.0911, "step": 1500 }, { "epoch": 0.7481879822305354, "grad_norm": 1.181686282157898, "learning_rate": 7.565996228786927e-06, "loss": 1.0917, "step": 1600 }, { "epoch": 0.7949497311199439, "grad_norm": 0.8685171008110046, "learning_rate": 7.408862350722817e-06, "loss": 1.0836, "step": 1700 }, { "epoch": 0.8417114800093524, "grad_norm": 0.7595590949058533, "learning_rate": 7.251728472658706e-06, "loss": 1.0937, "step": 1800 }, { "epoch": 0.8884732288987608, "grad_norm": 1.043165683746338, "learning_rate": 7.0945945945945946e-06, "loss": 1.0681, "step": 1900 }, { "epoch": 0.9352349777881693, "grad_norm": 0.7252351641654968, "learning_rate": 6.937460716530484e-06, "loss": 1.0753, "step": 2000 }, { "epoch": 0.9819967266775778, "grad_norm": 16.970993041992188, "learning_rate": 6.780326838466373e-06, "loss": 1.068, "step": 2100 }, { "epoch": 1.0287584755669863, "grad_norm": 0.7194657921791077, "learning_rate": 6.623192960402264e-06, "loss": 1.0816, "step": 2200 }, { "epoch": 1.0755202244563946, "grad_norm": 0.8986325860023499, "learning_rate": 6.467630421118794e-06, "loss": 1.0516, "step": 2300 }, { "epoch": 1.1222819733458032, "grad_norm": 0.8846977353096008, "learning_rate": 6.3104965430546826e-06, "loss": 1.0775, "step": 2400 }, { "epoch": 1.1690437222352117, "grad_norm": 0.8062325119972229, "learning_rate": 6.153362664990572e-06, "loss": 1.0796, "step": 2500 }, { "epoch": 1.21580547112462, "grad_norm": 9.224539756774902, "learning_rate": 5.996228786926462e-06, "loss": 1.0646, "step": 2600 }, { "epoch": 1.2625672200140285, "grad_norm": 0.7716740369796753, "learning_rate": 5.839094908862352e-06, "loss": 1.0699, "step": 2700 }, { "epoch": 1.3093289689034369, "grad_norm": 1.1291840076446533, "learning_rate": 5.681961030798241e-06, "loss": 1.0679, "step": 2800 }, { "epoch": 1.3560907177928454, "grad_norm": 1.0691558122634888, "learning_rate": 5.5248271527341305e-06, "loss": 1.0871, "step": 2900 }, { "epoch": 1.402852466682254, "grad_norm": 1.0153058767318726, "learning_rate": 5.367693274670019e-06, "loss": 1.0418, "step": 3000 }, { "epoch": 1.4496142155716623, "grad_norm": 0.8397168517112732, "learning_rate": 5.210559396605908e-06, "loss": 1.0751, "step": 3100 }, { "epoch": 1.4963759644610708, "grad_norm": 0.9355253577232361, "learning_rate": 5.053425518541798e-06, "loss": 1.0588, "step": 3200 }, { "epoch": 1.5431377133504793, "grad_norm": 0.9902454614639282, "learning_rate": 4.896291640477687e-06, "loss": 1.0847, "step": 3300 }, { "epoch": 1.5898994622398877, "grad_norm": 0.9210862517356873, "learning_rate": 4.739157762413577e-06, "loss": 1.076, "step": 3400 }, { "epoch": 1.6366612111292962, "grad_norm": 0.9090029001235962, "learning_rate": 4.5820238843494665e-06, "loss": 1.0579, "step": 3500 }, { "epoch": 1.6834229600187047, "grad_norm": 0.9450795650482178, "learning_rate": 4.424890006285355e-06, "loss": 1.079, "step": 3600 }, { "epoch": 1.730184708908113, "grad_norm": 0.8659577965736389, "learning_rate": 4.267756128221245e-06, "loss": 1.0583, "step": 3700 }, { "epoch": 1.7769464577975216, "grad_norm": 0.9201979041099548, "learning_rate": 4.110622250157134e-06, "loss": 1.0263, "step": 3800 }, { "epoch": 1.8237082066869301, "grad_norm": 1.2461769580841064, "learning_rate": 3.953488372093024e-06, "loss": 1.0579, "step": 3900 }, { "epoch": 1.8704699555763384, "grad_norm": 0.8340646028518677, "learning_rate": 3.796354494028913e-06, "loss": 1.0781, "step": 4000 }, { "epoch": 1.917231704465747, "grad_norm": 1.7858061790466309, "learning_rate": 3.6392206159648025e-06, "loss": 1.0701, "step": 4100 }, { "epoch": 1.9639934533551555, "grad_norm": 1.354982614517212, "learning_rate": 3.4820867379006918e-06, "loss": 1.0613, "step": 4200 }, { "epoch": 2.010755202244564, "grad_norm": 0.9671053886413574, "learning_rate": 3.324952859836581e-06, "loss": 1.0741, "step": 4300 }, { "epoch": 2.0575169511339726, "grad_norm": 0.8994483351707458, "learning_rate": 3.1678189817724704e-06, "loss": 1.0347, "step": 4400 }, { "epoch": 2.104278700023381, "grad_norm": 1.036387324333191, "learning_rate": 3.0106851037083594e-06, "loss": 1.054, "step": 4500 }, { "epoch": 2.1510404489127892, "grad_norm": 1.0670599937438965, "learning_rate": 2.8535512256442495e-06, "loss": 1.0315, "step": 4600 }, { "epoch": 2.197802197802198, "grad_norm": 1.0409014225006104, "learning_rate": 2.6964173475801384e-06, "loss": 1.0626, "step": 4700 }, { "epoch": 2.2445639466916063, "grad_norm": 1.0264023542404175, "learning_rate": 2.5392834695160278e-06, "loss": 1.0352, "step": 4800 }, { "epoch": 2.2913256955810146, "grad_norm": 3.9457595348358154, "learning_rate": 2.382149591451917e-06, "loss": 1.0428, "step": 4900 }, { "epoch": 2.3380874444704234, "grad_norm": 0.966581404209137, "learning_rate": 2.225015713387807e-06, "loss": 1.0487, "step": 5000 }, { "epoch": 2.3848491933598317, "grad_norm": 1.0433825254440308, "learning_rate": 2.0678818353236958e-06, "loss": 1.0679, "step": 5100 }, { "epoch": 2.43161094224924, "grad_norm": 1.005495548248291, "learning_rate": 1.910747957259585e-06, "loss": 1.0497, "step": 5200 }, { "epoch": 2.4783726911386488, "grad_norm": 1.0041530132293701, "learning_rate": 1.7536140791954748e-06, "loss": 1.05, "step": 5300 }, { "epoch": 2.525134440028057, "grad_norm": 1.108376383781433, "learning_rate": 1.596480201131364e-06, "loss": 1.0618, "step": 5400 }, { "epoch": 2.5718961889174654, "grad_norm": 1.0034010410308838, "learning_rate": 1.4393463230672533e-06, "loss": 1.0486, "step": 5500 }, { "epoch": 2.6186579378068737, "grad_norm": 0.9590221047401428, "learning_rate": 1.2822124450031428e-06, "loss": 1.0514, "step": 5600 }, { "epoch": 2.6654196866962825, "grad_norm": 1.027959942817688, "learning_rate": 1.1250785669390322e-06, "loss": 1.0578, "step": 5700 }, { "epoch": 2.712181435585691, "grad_norm": 0.9596933722496033, "learning_rate": 9.679446888749215e-07, "loss": 1.0659, "step": 5800 }, { "epoch": 2.7589431844750996, "grad_norm": 1.142251968383789, "learning_rate": 8.108108108108109e-07, "loss": 1.0714, "step": 5900 }, { "epoch": 2.805704933364508, "grad_norm": 1.2584409713745117, "learning_rate": 6.536769327467001e-07, "loss": 1.0485, "step": 6000 }, { "epoch": 2.852466682253916, "grad_norm": 1.3494170904159546, "learning_rate": 4.965430546825896e-07, "loss": 1.0321, "step": 6100 }, { "epoch": 2.8992284311433245, "grad_norm": 0.9571290612220764, "learning_rate": 3.39409176618479e-07, "loss": 1.0181, "step": 6200 }, { "epoch": 2.9459901800327333, "grad_norm": 1.231972575187683, "learning_rate": 1.8227529855436833e-07, "loss": 1.0409, "step": 6300 }, { "epoch": 2.9927519289221416, "grad_norm": 2.6358070373535156, "learning_rate": 2.6712759270898807e-08, "loss": 1.048, "step": 6400 } ], "logging_steps": 100, "max_steps": 6414, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 2138, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4.481950171724329e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }