| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.941747572815534, | |
| "eval_steps": 500, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.032362459546925564, | |
| "grad_norm": 0.19843709468841553, | |
| "learning_rate": 4.999994725208513e-06, | |
| "loss": 1.6354, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06472491909385113, | |
| "grad_norm": 0.19520695507526398, | |
| "learning_rate": 4.998353859072719e-06, | |
| "loss": 1.5795, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0970873786407767, | |
| "grad_norm": 0.15560713410377502, | |
| "learning_rate": 4.9937847678082505e-06, | |
| "loss": 1.4644, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12944983818770225, | |
| "grad_norm": 0.113382488489151, | |
| "learning_rate": 4.986292806672453e-06, | |
| "loss": 1.3852, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16181229773462782, | |
| "grad_norm": 0.1354118436574936, | |
| "learning_rate": 4.975886756706802e-06, | |
| "loss": 1.3513, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1941747572815534, | |
| "grad_norm": 0.13614092767238617, | |
| "learning_rate": 4.962578814444986e-06, | |
| "loss": 1.3174, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22653721682847897, | |
| "grad_norm": 0.11831384897232056, | |
| "learning_rate": 4.946384577617804e-06, | |
| "loss": 1.2983, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2588996763754045, | |
| "grad_norm": 0.11915043741464615, | |
| "learning_rate": 4.927323026871671e-06, | |
| "loss": 1.3172, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2912621359223301, | |
| "grad_norm": 0.12973643839359283, | |
| "learning_rate": 4.905416503522124e-06, | |
| "loss": 1.2763, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.32362459546925565, | |
| "grad_norm": 0.15487492084503174, | |
| "learning_rate": 4.880690683368418e-06, | |
| "loss": 1.2858, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3559870550161812, | |
| "grad_norm": 0.1625741720199585, | |
| "learning_rate": 4.853174546599903e-06, | |
| "loss": 1.3051, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3883495145631068, | |
| "grad_norm": 0.15691585838794708, | |
| "learning_rate": 4.822900343829452e-06, | |
| "loss": 1.2487, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.42071197411003236, | |
| "grad_norm": 0.15258367359638214, | |
| "learning_rate": 4.78990355829375e-06, | |
| "loss": 1.2935, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.45307443365695793, | |
| "grad_norm": 0.149098739027977, | |
| "learning_rate": 4.754222864264748e-06, | |
| "loss": 1.2484, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4854368932038835, | |
| "grad_norm": 0.13359490036964417, | |
| "learning_rate": 4.715900081721021e-06, | |
| "loss": 1.2698, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.517799352750809, | |
| "grad_norm": 0.1649194359779358, | |
| "learning_rate": 4.674980127332175e-06, | |
| "loss": 1.2839, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5501618122977346, | |
| "grad_norm": 0.17222905158996582, | |
| "learning_rate": 4.631510961813731e-06, | |
| "loss": 1.2659, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.5825242718446602, | |
| "grad_norm": 0.17811669409275055, | |
| "learning_rate": 4.585543533714202e-06, | |
| "loss": 1.282, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6148867313915858, | |
| "grad_norm": 0.18572162091732025, | |
| "learning_rate": 4.537131719700248e-06, | |
| "loss": 1.2637, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.6472491909385113, | |
| "grad_norm": 0.18194597959518433, | |
| "learning_rate": 4.48633226140989e-06, | |
| "loss": 1.2783, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6796116504854369, | |
| "grad_norm": 0.18696360290050507, | |
| "learning_rate": 4.433204698947805e-06, | |
| "loss": 1.2744, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.7119741100323624, | |
| "grad_norm": 0.1837579309940338, | |
| "learning_rate": 4.377811301100642e-06, | |
| "loss": 1.273, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.7443365695792881, | |
| "grad_norm": 0.1855243444442749, | |
| "learning_rate": 4.320216992354158e-06, | |
| "loss": 1.2584, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.7766990291262136, | |
| "grad_norm": 0.29544222354888916, | |
| "learning_rate": 4.260489276797709e-06, | |
| "loss": 1.287, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8090614886731392, | |
| "grad_norm": 0.1854172646999359, | |
| "learning_rate": 4.198698159005278e-06, | |
| "loss": 1.2711, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.8414239482200647, | |
| "grad_norm": 0.1921299248933792, | |
| "learning_rate": 4.134916061985798e-06, | |
| "loss": 1.2735, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.8737864077669902, | |
| "grad_norm": 0.19444109499454498, | |
| "learning_rate": 4.069217742298901e-06, | |
| "loss": 1.2659, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.9061488673139159, | |
| "grad_norm": 0.1953461915254593, | |
| "learning_rate": 4.001680202435617e-06, | |
| "loss": 1.2917, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9385113268608414, | |
| "grad_norm": 0.17386198043823242, | |
| "learning_rate": 3.932382600566691e-06, | |
| "loss": 1.2704, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.970873786407767, | |
| "grad_norm": 0.18356619775295258, | |
| "learning_rate": 3.861406157764314e-06, | |
| "loss": 1.2775, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0032362459546926, | |
| "grad_norm": 0.21802374720573425, | |
| "learning_rate": 3.7888340628060083e-06, | |
| "loss": 1.3152, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.035598705501618, | |
| "grad_norm": 0.205328568816185, | |
| "learning_rate": 3.714751374672243e-06, | |
| "loss": 1.2973, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.0679611650485437, | |
| "grad_norm": 0.19713380932807922, | |
| "learning_rate": 3.6392449228520456e-06, | |
| "loss": 1.28, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.1003236245954693, | |
| "grad_norm": 0.20696976780891418, | |
| "learning_rate": 3.562403205573474e-06, | |
| "loss": 1.2812, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.132686084142395, | |
| "grad_norm": 0.1874680519104004, | |
| "learning_rate": 3.484316286078233e-06, | |
| "loss": 1.2657, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.1650485436893203, | |
| "grad_norm": 0.17423813045024872, | |
| "learning_rate": 3.4050756870619785e-06, | |
| "loss": 1.2336, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.197411003236246, | |
| "grad_norm": 0.2038557380437851, | |
| "learning_rate": 3.324774283404065e-06, | |
| "loss": 1.2637, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.2297734627831716, | |
| "grad_norm": 0.22192490100860596, | |
| "learning_rate": 3.243506193312452e-06, | |
| "loss": 1.2474, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.262135922330097, | |
| "grad_norm": 0.21069851517677307, | |
| "learning_rate": 3.1613666680113398e-06, | |
| "loss": 1.2604, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.2944983818770226, | |
| "grad_norm": 0.20909801125526428, | |
| "learning_rate": 3.0784519801008546e-06, | |
| "loss": 1.2867, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.3268608414239482, | |
| "grad_norm": 0.20224529504776, | |
| "learning_rate": 2.9948593107196044e-06, | |
| "loss": 1.2946, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.3592233009708738, | |
| "grad_norm": 0.2082245945930481, | |
| "learning_rate": 2.9106866356423845e-06, | |
| "loss": 1.3071, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.3915857605177995, | |
| "grad_norm": 0.1968870759010315, | |
| "learning_rate": 2.8260326104465147e-06, | |
| "loss": 1.2709, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.4239482200647249, | |
| "grad_norm": 0.20573362708091736, | |
| "learning_rate": 2.740996454881397e-06, | |
| "loss": 1.245, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.4563106796116505, | |
| "grad_norm": 0.2424907386302948, | |
| "learning_rate": 2.6556778365768467e-06, | |
| "loss": 1.2665, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.4886731391585761, | |
| "grad_norm": 0.2233143001794815, | |
| "learning_rate": 2.5701767542264663e-06, | |
| "loss": 1.2871, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.5210355987055015, | |
| "grad_norm": 0.3519347012042999, | |
| "learning_rate": 2.4845934203829954e-06, | |
| "loss": 1.2889, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.5533980582524272, | |
| "grad_norm": 0.22095517814159393, | |
| "learning_rate": 2.3990281440030106e-06, | |
| "loss": 1.2895, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.5857605177993528, | |
| "grad_norm": 0.22900894284248352, | |
| "learning_rate": 2.3135812128786207e-06, | |
| "loss": 1.2986, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.6181229773462782, | |
| "grad_norm": 0.22317421436309814, | |
| "learning_rate": 2.228352776093982e-06, | |
| "loss": 1.2647, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.650485436893204, | |
| "grad_norm": 0.21420355141162872, | |
| "learning_rate": 2.143442726644385e-06, | |
| "loss": 1.2726, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.6828478964401294, | |
| "grad_norm": 0.23652972280979156, | |
| "learning_rate": 2.05895058435548e-06, | |
| "loss": 1.3003, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.715210355987055, | |
| "grad_norm": 0.21717728674411774, | |
| "learning_rate": 1.9749753792399e-06, | |
| "loss": 1.2808, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.7475728155339807, | |
| "grad_norm": 0.22195585072040558, | |
| "learning_rate": 1.8916155354279652e-06, | |
| "loss": 1.2856, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.779935275080906, | |
| "grad_norm": 0.25054916739463806, | |
| "learning_rate": 1.8089687558085122e-06, | |
| "loss": 1.2958, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.8122977346278317, | |
| "grad_norm": 0.2313874512910843, | |
| "learning_rate": 1.7271319075150786e-06, | |
| "loss": 1.2985, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.8446601941747574, | |
| "grad_norm": 0.2183278501033783, | |
| "learning_rate": 1.6462009083916275e-06, | |
| "loss": 1.288, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.8770226537216828, | |
| "grad_norm": 0.2164868861436844, | |
| "learning_rate": 1.5662706145709128e-06, | |
| "loss": 1.2852, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.9093851132686084, | |
| "grad_norm": 0.2470543533563614, | |
| "learning_rate": 1.4874347092972285e-06, | |
| "loss": 1.2768, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.941747572815534, | |
| "grad_norm": 0.21252723038196564, | |
| "learning_rate": 1.4097855931238516e-06, | |
| "loss": 1.2506, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 4635, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.453766865339023e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |