| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02829121086382497, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003772161448509996, | |
| "grad_norm": 4.458075523376465, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.5843, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003772161448509996, | |
| "eval_loss": 2.658385992050171, | |
| "eval_runtime": 249.7715, | |
| "eval_samples_per_second": 8.94, | |
| "eval_steps_per_second": 4.472, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "grad_norm": 4.317282676696777, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.5154, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001131648434552999, | |
| "grad_norm": 3.815100908279419, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3005, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015088645794039985, | |
| "grad_norm": 3.509941577911377, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 2.35, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001886080724254998, | |
| "grad_norm": 3.3900184631347656, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 2.0218, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002263296869105998, | |
| "grad_norm": 2.7318315505981445, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.0075, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002640513013956997, | |
| "grad_norm": 2.1249992847442627, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.9131, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003017729158807997, | |
| "grad_norm": 1.878459095954895, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 1.8521, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033949453036589967, | |
| "grad_norm": 1.9627385139465332, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.9097, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003772161448509996, | |
| "grad_norm": 1.7230076789855957, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 1.9486, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004149377593360996, | |
| "grad_norm": 2.0652852058410645, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.7748, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004526593738211996, | |
| "grad_norm": 1.8609416484832764, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.725, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004903809883062995, | |
| "grad_norm": 2.0955309867858887, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 1.9241, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005281026027913994, | |
| "grad_norm": 2.041574239730835, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 1.6188, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005658242172764994, | |
| "grad_norm": 2.067662000656128, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.9323, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006035458317615994, | |
| "grad_norm": 2.0383667945861816, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 1.7904, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006412674462466994, | |
| "grad_norm": 1.8715559244155884, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 1.8773, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0067898906073179935, | |
| "grad_norm": 1.7730380296707153, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.735, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007167106752168993, | |
| "grad_norm": 1.8929604291915894, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.7652, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007544322897019992, | |
| "grad_norm": 1.9013259410858154, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 1.9643, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007921539041870993, | |
| "grad_norm": 1.7703946828842163, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7194, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008298755186721992, | |
| "grad_norm": 1.600402593612671, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 1.6232, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00867597133157299, | |
| "grad_norm": 2.0844128131866455, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.8605, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009053187476423991, | |
| "grad_norm": 1.8568676710128784, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.8041, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00943040362127499, | |
| "grad_norm": 1.8989644050598145, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 1.8471, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00943040362127499, | |
| "eval_loss": 1.688022494316101, | |
| "eval_runtime": 250.0347, | |
| "eval_samples_per_second": 8.931, | |
| "eval_steps_per_second": 4.467, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00980761976612599, | |
| "grad_norm": 1.910681128501892, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 1.592, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01018483591097699, | |
| "grad_norm": 1.9144117832183838, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5902, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010562052055827989, | |
| "grad_norm": 1.9871450662612915, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 1.8691, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01093926820067899, | |
| "grad_norm": 1.9655017852783203, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 1.6454, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011316484345529988, | |
| "grad_norm": 1.7076811790466309, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6844, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011693700490380989, | |
| "grad_norm": 2.0288169384002686, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.6277, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.012070916635231988, | |
| "grad_norm": 1.8550974130630493, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 1.4866, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012448132780082987, | |
| "grad_norm": 2.0670886039733887, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.7357, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.012825348924933987, | |
| "grad_norm": 1.8562512397766113, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 1.6598, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.013202565069784986, | |
| "grad_norm": 1.8503985404968262, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.5857, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013579781214635987, | |
| "grad_norm": 1.8370240926742554, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.6454, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013956997359486986, | |
| "grad_norm": 2.2695977687835693, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 1.3565, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014334213504337986, | |
| "grad_norm": 1.9079887866973877, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 1.442, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.014711429649188985, | |
| "grad_norm": 2.0044844150543213, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6545, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.015088645794039984, | |
| "grad_norm": 1.9024779796600342, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 1.5019, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015465861938890985, | |
| "grad_norm": 5.068066596984863, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 1.3254, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.015843078083741986, | |
| "grad_norm": 4.698451995849609, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.7416, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.016220294228592985, | |
| "grad_norm": 2.670969247817993, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.5371, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 2.174680233001709, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 1.4181, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.016974726518294982, | |
| "grad_norm": 2.4585800170898438, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.4326, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01735194266314598, | |
| "grad_norm": 2.4140963554382324, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 1.3759, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.017729158807996984, | |
| "grad_norm": 2.5143070220947266, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.8091, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.018106374952847983, | |
| "grad_norm": 2.9653544425964355, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9618, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01848359109769898, | |
| "grad_norm": 2.469782829284668, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.6423, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "grad_norm": 2.3597214221954346, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.5789, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "eval_loss": 1.6308754682540894, | |
| "eval_runtime": 249.9813, | |
| "eval_samples_per_second": 8.933, | |
| "eval_steps_per_second": 4.468, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01923802338740098, | |
| "grad_norm": 1.7687246799468994, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.8913, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.01961523953225198, | |
| "grad_norm": 1.832263708114624, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 1.7582, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.01999245567710298, | |
| "grad_norm": 2.0533218383789062, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 1.8514, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.02036967182195398, | |
| "grad_norm": 1.902577519416809, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.9063, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.02074688796680498, | |
| "grad_norm": 2.0547704696655273, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 1.9272, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.021124104111655977, | |
| "grad_norm": 1.9024983644485474, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 1.7496, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.02150132025650698, | |
| "grad_norm": 1.7016141414642334, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.905, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.02187853640135798, | |
| "grad_norm": 1.8714863061904907, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 1.7749, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.022255752546208978, | |
| "grad_norm": 1.7974597215652466, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.7632, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.022632968691059976, | |
| "grad_norm": 1.6825218200683594, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.8978, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.023010184835910975, | |
| "grad_norm": 1.8190650939941406, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 1.7671, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.023387400980761978, | |
| "grad_norm": 1.753597617149353, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 1.6744, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.023764617125612977, | |
| "grad_norm": 1.6556949615478516, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.8486, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.024141833270463976, | |
| "grad_norm": 1.8840663433074951, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 1.7873, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.024519049415314974, | |
| "grad_norm": 1.7227132320404053, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 1.8526, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.024896265560165973, | |
| "grad_norm": 1.8766735792160034, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9803, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.025273481705016976, | |
| "grad_norm": 1.913208246231079, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.7791, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.025650697849867975, | |
| "grad_norm": 1.606818675994873, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 1.6366, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.026027913994718974, | |
| "grad_norm": 1.7870965003967285, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.794, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.026405130139569973, | |
| "grad_norm": 1.6979774236679077, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 1.5391, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.026782346284420975, | |
| "grad_norm": 1.9064507484436035, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 1.7034, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.027159562429271974, | |
| "grad_norm": 1.8551948070526123, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.6344, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.027536778574122973, | |
| "grad_norm": 1.7518131732940674, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 1.5952, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.02791399471897397, | |
| "grad_norm": 1.8491065502166748, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 1.5739, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.02829121086382497, | |
| "grad_norm": 1.7698376178741455, | |
| "learning_rate": 0.0, | |
| "loss": 1.6641, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02829121086382497, | |
| "eval_loss": 1.5686583518981934, | |
| "eval_runtime": 250.0886, | |
| "eval_samples_per_second": 8.929, | |
| "eval_steps_per_second": 4.466, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.04651664621568e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |