| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022006235099944985, | |
| "eval_steps": 34, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004890274466654441, | |
| "grad_norm": 0.42223185300827026, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.2369, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004890274466654441, | |
| "eval_loss": 1.3036277294158936, | |
| "eval_runtime": 1355.2246, | |
| "eval_samples_per_second": 1.906, | |
| "eval_steps_per_second": 0.635, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009780548933308881, | |
| "grad_norm": 0.49382174015045166, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.3544, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014670823399963323, | |
| "grad_norm": 0.43727555871009827, | |
| "learning_rate": 2e-05, | |
| "loss": 1.403, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019561097866617762, | |
| "grad_norm": 0.3653078079223633, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 1.189, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024451372333272204, | |
| "grad_norm": 0.3689245283603668, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.1686, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029341646799926646, | |
| "grad_norm": 0.44767728447914124, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2578, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034231921266581087, | |
| "grad_norm": 0.4529785215854645, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 1.2452, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0039122195733235525, | |
| "grad_norm": 0.6146576404571533, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 1.5423, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004401247019988997, | |
| "grad_norm": 0.42456191778182983, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1323, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004890274466654441, | |
| "grad_norm": 0.4658707082271576, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.2595, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005379301913319885, | |
| "grad_norm": 0.6462928652763367, | |
| "learning_rate": 7.333333333333333e-05, | |
| "loss": 1.3136, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005868329359985329, | |
| "grad_norm": 0.514143168926239, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1999, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006357356806650773, | |
| "grad_norm": 0.43792784214019775, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 1.0675, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0068463842533162175, | |
| "grad_norm": 0.6212848424911499, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 1.3066, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007335411699981661, | |
| "grad_norm": 0.6186118125915527, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2355, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007824439146647105, | |
| "grad_norm": 0.6825079917907715, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 1.2258, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00831346659331255, | |
| "grad_norm": 0.3936300575733185, | |
| "learning_rate": 0.00011333333333333334, | |
| "loss": 1.1337, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008802494039977994, | |
| "grad_norm": 0.5038918852806091, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1278, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009291521486643438, | |
| "grad_norm": 0.5894134640693665, | |
| "learning_rate": 0.00012666666666666666, | |
| "loss": 1.1902, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009780548933308882, | |
| "grad_norm": 1.1452070474624634, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.1023, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010269576379974325, | |
| "grad_norm": 0.4289817214012146, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0195, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01075860382663977, | |
| "grad_norm": 1.290226936340332, | |
| "learning_rate": 0.00014666666666666666, | |
| "loss": 0.9534, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011247631273305215, | |
| "grad_norm": 0.5022335648536682, | |
| "learning_rate": 0.00015333333333333334, | |
| "loss": 0.8952, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011736658719970658, | |
| "grad_norm": 0.5421992540359497, | |
| "learning_rate": 0.00016, | |
| "loss": 0.8553, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012225686166636102, | |
| "grad_norm": 1.568458080291748, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.9764, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012714713613301546, | |
| "grad_norm": 0.6190416812896729, | |
| "learning_rate": 0.00017333333333333334, | |
| "loss": 0.9819, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013203741059966991, | |
| "grad_norm": 0.4747830927371979, | |
| "learning_rate": 0.00018, | |
| "loss": 0.9395, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013692768506632435, | |
| "grad_norm": 0.9486120343208313, | |
| "learning_rate": 0.0001866666666666667, | |
| "loss": 0.9669, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014181795953297879, | |
| "grad_norm": 0.4615766108036041, | |
| "learning_rate": 0.00019333333333333333, | |
| "loss": 0.9341, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014670823399963322, | |
| "grad_norm": 0.46146905422210693, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0082, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015159850846628768, | |
| "grad_norm": 0.47625860571861267, | |
| "learning_rate": 0.00019998292504580528, | |
| "loss": 0.9419, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01564887829329421, | |
| "grad_norm": 0.5290003418922424, | |
| "learning_rate": 0.0001999317060143023, | |
| "loss": 1.1635, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.016137905739959654, | |
| "grad_norm": 0.5592769980430603, | |
| "learning_rate": 0.0001998463603967434, | |
| "loss": 0.9437, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0166269331866251, | |
| "grad_norm": 0.3583241403102875, | |
| "learning_rate": 0.00019972691733857883, | |
| "loss": 1.1428, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0166269331866251, | |
| "eval_loss": 1.0231887102127075, | |
| "eval_runtime": 1359.3297, | |
| "eval_samples_per_second": 1.9, | |
| "eval_steps_per_second": 0.633, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017115960633290545, | |
| "grad_norm": 0.41851457953453064, | |
| "learning_rate": 0.00019957341762950344, | |
| "loss": 1.0976, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.017604988079955988, | |
| "grad_norm": 0.46739837527275085, | |
| "learning_rate": 0.0001993859136895274, | |
| "loss": 1.0089, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.018094015526621432, | |
| "grad_norm": 0.3970998227596283, | |
| "learning_rate": 0.00019916446955107428, | |
| "loss": 1.1005, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.018583042973286876, | |
| "grad_norm": 0.5996494293212891, | |
| "learning_rate": 0.0001989091608371146, | |
| "loss": 0.9741, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01907207041995232, | |
| "grad_norm": 0.27929016947746277, | |
| "learning_rate": 0.00019862007473534025, | |
| "loss": 0.9607, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019561097866617763, | |
| "grad_norm": 0.33169642090797424, | |
| "learning_rate": 0.0001982973099683902, | |
| "loss": 1.1173, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020050125313283207, | |
| "grad_norm": 0.3042043149471283, | |
| "learning_rate": 0.0001979409767601366, | |
| "loss": 1.1178, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02053915275994865, | |
| "grad_norm": 0.3394615650177002, | |
| "learning_rate": 0.00019755119679804367, | |
| "loss": 1.0167, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.021028180206614098, | |
| "grad_norm": 0.3241017758846283, | |
| "learning_rate": 0.0001971281031916114, | |
| "loss": 1.0089, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02151720765327954, | |
| "grad_norm": 0.6870384812355042, | |
| "learning_rate": 0.00019667184042691875, | |
| "loss": 1.0362, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.022006235099944985, | |
| "grad_norm": 0.31295979022979736, | |
| "learning_rate": 0.00019618256431728194, | |
| "loss": 1.0032, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9975293879975936e+17, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |