| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06940251375904835, | |
| "eval_steps": 500, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001388050275180967, | |
| "grad_norm": 1.386236310005188, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 2.432, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.002776100550361934, | |
| "grad_norm": 1.2055169343948364, | |
| "learning_rate": 0.00019793814432989693, | |
| "loss": 1.8849, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0041641508255429015, | |
| "grad_norm": 1.1103655099868774, | |
| "learning_rate": 0.00019381443298969073, | |
| "loss": 1.7944, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.005552201100723868, | |
| "grad_norm": 1.1928976774215698, | |
| "learning_rate": 0.00018969072164948454, | |
| "loss": 1.7832, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.006940251375904836, | |
| "grad_norm": 1.2889844179153442, | |
| "learning_rate": 0.00018556701030927837, | |
| "loss": 1.811, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.008328301651085803, | |
| "grad_norm": 1.304612159729004, | |
| "learning_rate": 0.00018144329896907217, | |
| "loss": 1.7718, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.00971635192626677, | |
| "grad_norm": 1.2339240312576294, | |
| "learning_rate": 0.00017731958762886598, | |
| "loss": 1.7757, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.011104402201447736, | |
| "grad_norm": 1.196730136871338, | |
| "learning_rate": 0.0001731958762886598, | |
| "loss": 1.7639, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.012492452476628703, | |
| "grad_norm": 1.1369080543518066, | |
| "learning_rate": 0.00016907216494845361, | |
| "loss": 1.7508, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.013880502751809671, | |
| "grad_norm": 1.1714072227478027, | |
| "learning_rate": 0.00016494845360824742, | |
| "loss": 1.7451, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.015268553026990638, | |
| "grad_norm": 2.0464041233062744, | |
| "learning_rate": 0.00016082474226804125, | |
| "loss": 1.7266, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.016656603302171606, | |
| "grad_norm": 1.2468883991241455, | |
| "learning_rate": 0.00015670103092783506, | |
| "loss": 1.7476, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.018044653577352573, | |
| "grad_norm": 1.3278380632400513, | |
| "learning_rate": 0.00015257731958762886, | |
| "loss": 1.713, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.01943270385253354, | |
| "grad_norm": 1.83975088596344, | |
| "learning_rate": 0.0001484536082474227, | |
| "loss": 1.712, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.020820754127714506, | |
| "grad_norm": 1.1055878400802612, | |
| "learning_rate": 0.0001443298969072165, | |
| "loss": 1.7305, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.022208804402895473, | |
| "grad_norm": 1.2078220844268799, | |
| "learning_rate": 0.0001402061855670103, | |
| "loss": 1.7094, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.02359685467807644, | |
| "grad_norm": 1.9538626670837402, | |
| "learning_rate": 0.00013608247422680414, | |
| "loss": 1.7252, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.024984904953257406, | |
| "grad_norm": 1.149594783782959, | |
| "learning_rate": 0.00013195876288659794, | |
| "loss": 1.7108, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.026372955228438372, | |
| "grad_norm": 1.2434228658676147, | |
| "learning_rate": 0.00012783505154639175, | |
| "loss": 1.7106, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.027761005503619342, | |
| "grad_norm": 1.0074732303619385, | |
| "learning_rate": 0.00012371134020618558, | |
| "loss": 1.7222, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.02914905577880031, | |
| "grad_norm": 1.2611148357391357, | |
| "learning_rate": 0.00011958762886597938, | |
| "loss": 1.6937, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.030537106053981276, | |
| "grad_norm": 1.0606039762496948, | |
| "learning_rate": 0.00011546391752577319, | |
| "loss": 1.6904, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.03192515632916224, | |
| "grad_norm": 1.202054500579834, | |
| "learning_rate": 0.00011134020618556702, | |
| "loss": 1.7305, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.03331320660434321, | |
| "grad_norm": 0.9994720220565796, | |
| "learning_rate": 0.00010721649484536083, | |
| "loss": 1.7045, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.034701256879524175, | |
| "grad_norm": 1.222708821296692, | |
| "learning_rate": 0.00010309278350515463, | |
| "loss": 1.6707, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.036089307154705146, | |
| "grad_norm": 1.170048475265503, | |
| "learning_rate": 9.896907216494846e-05, | |
| "loss": 1.6999, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.03747735742988611, | |
| "grad_norm": 1.3302826881408691, | |
| "learning_rate": 9.484536082474227e-05, | |
| "loss": 1.6899, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.03886540770506708, | |
| "grad_norm": 1.1185508966445923, | |
| "learning_rate": 9.072164948453609e-05, | |
| "loss": 1.6899, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.04025345798024804, | |
| "grad_norm": 1.6227563619613647, | |
| "learning_rate": 8.65979381443299e-05, | |
| "loss": 1.6844, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.04164150825542901, | |
| "grad_norm": 1.4536927938461304, | |
| "learning_rate": 8.247422680412371e-05, | |
| "loss": 1.6873, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.04302955853060998, | |
| "grad_norm": 1.2233431339263916, | |
| "learning_rate": 7.835051546391753e-05, | |
| "loss": 1.656, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.044417608805790945, | |
| "grad_norm": 1.3101099729537964, | |
| "learning_rate": 7.422680412371135e-05, | |
| "loss": 1.6722, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.045805659080971915, | |
| "grad_norm": 1.224885106086731, | |
| "learning_rate": 7.010309278350515e-05, | |
| "loss": 1.6536, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.04719370935615288, | |
| "grad_norm": 1.1796605587005615, | |
| "learning_rate": 6.597938144329897e-05, | |
| "loss": 1.6783, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.04858175963133385, | |
| "grad_norm": 1.2505239248275757, | |
| "learning_rate": 6.185567010309279e-05, | |
| "loss": 1.676, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.04996980990651481, | |
| "grad_norm": 0.9648654460906982, | |
| "learning_rate": 5.7731958762886594e-05, | |
| "loss": 1.6617, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.05135786018169578, | |
| "grad_norm": 1.0220248699188232, | |
| "learning_rate": 5.360824742268041e-05, | |
| "loss": 1.6611, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.052745910456876745, | |
| "grad_norm": 1.0856778621673584, | |
| "learning_rate": 4.948453608247423e-05, | |
| "loss": 1.6608, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.054133960732057715, | |
| "grad_norm": 1.439794659614563, | |
| "learning_rate": 4.536082474226804e-05, | |
| "loss": 1.6693, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.055522011007238685, | |
| "grad_norm": 1.1624224185943604, | |
| "learning_rate": 4.1237113402061855e-05, | |
| "loss": 1.6447, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.05691006128241965, | |
| "grad_norm": 1.0445908308029175, | |
| "learning_rate": 3.7113402061855674e-05, | |
| "loss": 1.6458, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.05829811155760062, | |
| "grad_norm": 1.2009379863739014, | |
| "learning_rate": 3.2989690721649485e-05, | |
| "loss": 1.6362, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.05968616183278158, | |
| "grad_norm": 1.1339406967163086, | |
| "learning_rate": 2.8865979381443297e-05, | |
| "loss": 1.6605, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.06107421210796255, | |
| "grad_norm": 1.1409072875976562, | |
| "learning_rate": 2.4742268041237116e-05, | |
| "loss": 1.6582, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.062462262383143514, | |
| "grad_norm": 1.0138684511184692, | |
| "learning_rate": 2.0618556701030927e-05, | |
| "loss": 1.6539, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.06385031265832448, | |
| "grad_norm": 1.0418405532836914, | |
| "learning_rate": 1.6494845360824743e-05, | |
| "loss": 1.6676, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.06523836293350545, | |
| "grad_norm": 1.0475600957870483, | |
| "learning_rate": 1.2371134020618558e-05, | |
| "loss": 1.6416, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.06662641320868642, | |
| "grad_norm": 1.334047555923462, | |
| "learning_rate": 8.247422680412371e-06, | |
| "loss": 1.6297, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.06801446348386739, | |
| "grad_norm": 1.0327249765396118, | |
| "learning_rate": 4.123711340206186e-06, | |
| "loss": 1.6329, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.06940251375904835, | |
| "grad_norm": 1.007521390914917, | |
| "learning_rate": 0.0, | |
| "loss": 1.6405, | |
| "step": 5000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1538290661520589e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |