| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.020618556701031, | |
| "eval_steps": 25, | |
| "global_step": 49, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": 21.207786560058594, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 13.4151, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "eval_loss": 10.289013862609863, | |
| "eval_runtime": 6.8593, | |
| "eval_samples_per_second": 7.289, | |
| "eval_steps_per_second": 1.021, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 20.19322967529297, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 9.5074, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "grad_norm": 18.897502899169922, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 8.6476, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 17.77202033996582, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 7.1991, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.20618556701030927, | |
| "grad_norm": 19.367111206054688, | |
| "learning_rate": 0.00015, | |
| "loss": 5.3903, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.24742268041237114, | |
| "grad_norm": 18.797807693481445, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 3.3717, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.28865979381443296, | |
| "grad_norm": 29.97896957397461, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 8.1725, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.32989690721649484, | |
| "grad_norm": 13.854898452758789, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.4758, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3711340206185567, | |
| "grad_norm": 7.236441612243652, | |
| "learning_rate": 0.00027, | |
| "loss": 0.7477, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 10.648214340209961, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9083, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4536082474226804, | |
| "grad_norm": 4.636464595794678, | |
| "learning_rate": 0.0002995135962201315, | |
| "loss": 0.8218, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4948453608247423, | |
| "grad_norm": 13.175925254821777, | |
| "learning_rate": 0.00029805753939568687, | |
| "loss": 0.6549, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5360824742268041, | |
| "grad_norm": 7.059333324432373, | |
| "learning_rate": 0.00029564127261390776, | |
| "loss": 1.3904, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5773195876288659, | |
| "grad_norm": 2.427844762802124, | |
| "learning_rate": 0.00029228046629207175, | |
| "loss": 0.5766, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6185567010309279, | |
| "grad_norm": 2.2444586753845215, | |
| "learning_rate": 0.0002879969165488236, | |
| "loss": 0.4453, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6597938144329897, | |
| "grad_norm": 4.176374435424805, | |
| "learning_rate": 0.0002828184038479814, | |
| "loss": 0.4982, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7010309278350515, | |
| "grad_norm": 4.361511707305908, | |
| "learning_rate": 0.0002767785128315692, | |
| "loss": 0.5536, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7422680412371134, | |
| "grad_norm": 2.4813404083251953, | |
| "learning_rate": 0.00026991641451052517, | |
| "loss": 0.3833, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7835051546391752, | |
| "grad_norm": 3.9218337535858154, | |
| "learning_rate": 0.00026227661222566516, | |
| "loss": 0.884, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8247422680412371, | |
| "grad_norm": 4.639664649963379, | |
| "learning_rate": 0.0002539086530264399, | |
| "loss": 0.6114, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.865979381443299, | |
| "grad_norm": 1.8246965408325195, | |
| "learning_rate": 0.0002448668063393066, | |
| "loss": 0.3129, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9072164948453608, | |
| "grad_norm": 1.7663586139678955, | |
| "learning_rate": 0.00023520971200967334, | |
| "loss": 0.3082, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.9484536082474226, | |
| "grad_norm": 1.5523817539215088, | |
| "learning_rate": 0.000225, | |
| "loss": 0.2148, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9896907216494846, | |
| "grad_norm": 2.3061859607696533, | |
| "learning_rate": 0.0002143038842104581, | |
| "loss": 0.3259, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.0309278350515463, | |
| "grad_norm": 6.233306407928467, | |
| "learning_rate": 0.0002031907330563803, | |
| "loss": 1.2769, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0309278350515463, | |
| "eval_loss": 0.38126152753829956, | |
| "eval_runtime": 7.0093, | |
| "eval_samples_per_second": 7.133, | |
| "eval_steps_per_second": 0.999, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0721649484536082, | |
| "grad_norm": 1.989977240562439, | |
| "learning_rate": 0.0001917326195874679, | |
| "loss": 0.343, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.1134020618556701, | |
| "grad_norm": 2.740975856781006, | |
| "learning_rate": 0.00018000385406640666, | |
| "loss": 0.3353, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.1546391752577319, | |
| "grad_norm": 1.8761099576950073, | |
| "learning_rate": 0.00016808050203829842, | |
| "loss": 0.2779, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1958762886597938, | |
| "grad_norm": 2.2417774200439453, | |
| "learning_rate": 0.00015603989101641228, | |
| "loss": 0.1635, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.2371134020618557, | |
| "grad_norm": 1.4561247825622559, | |
| "learning_rate": 0.00014396010898358775, | |
| "loss": 0.1073, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2783505154639174, | |
| "grad_norm": 3.3076512813568115, | |
| "learning_rate": 0.00013191949796170156, | |
| "loss": 0.5154, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.3195876288659794, | |
| "grad_norm": 14.383665084838867, | |
| "learning_rate": 0.00011999614593359334, | |
| "loss": 0.6328, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3608247422680413, | |
| "grad_norm": 5.465051651000977, | |
| "learning_rate": 0.0001082673804125321, | |
| "loss": 0.4116, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.402061855670103, | |
| "grad_norm": 3.239784002304077, | |
| "learning_rate": 9.680926694361964e-05, | |
| "loss": 0.3851, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.443298969072165, | |
| "grad_norm": 3.6306114196777344, | |
| "learning_rate": 8.569611578954184e-05, | |
| "loss": 0.259, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4845360824742269, | |
| "grad_norm": 1.7656078338623047, | |
| "learning_rate": 7.500000000000002e-05, | |
| "loss": 0.1385, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.5257731958762886, | |
| "grad_norm": 1.992281436920166, | |
| "learning_rate": 6.479028799032664e-05, | |
| "loss": 0.3655, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5670103092783505, | |
| "grad_norm": 1.3977735042572021, | |
| "learning_rate": 5.513319366069342e-05, | |
| "loss": 0.1773, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.6082474226804124, | |
| "grad_norm": 1.901423692703247, | |
| "learning_rate": 4.609134697356009e-05, | |
| "loss": 0.2494, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.6494845360824741, | |
| "grad_norm": 1.1777201890945435, | |
| "learning_rate": 3.7723387774334816e-05, | |
| "loss": 0.1005, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.690721649484536, | |
| "grad_norm": 1.6862914562225342, | |
| "learning_rate": 3.0083585489474855e-05, | |
| "loss": 0.1787, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.731958762886598, | |
| "grad_norm": 1.3741050958633423, | |
| "learning_rate": 2.3221487168430806e-05, | |
| "loss": 0.1702, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.7731958762886597, | |
| "grad_norm": 2.1378395557403564, | |
| "learning_rate": 1.718159615201853e-05, | |
| "loss": 0.331, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.8144329896907216, | |
| "grad_norm": 2.2513341903686523, | |
| "learning_rate": 1.2003083451176366e-05, | |
| "loss": 0.3772, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.8556701030927836, | |
| "grad_norm": 2.2573084831237793, | |
| "learning_rate": 7.719533707928177e-06, | |
| "loss": 0.2378, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.8969072164948453, | |
| "grad_norm": 1.544053316116333, | |
| "learning_rate": 4.358727386092198e-06, | |
| "loss": 0.1291, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.9381443298969072, | |
| "grad_norm": 1.1243300437927246, | |
| "learning_rate": 1.942460604313073e-06, | |
| "loss": 0.0924, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.9793814432989691, | |
| "grad_norm": 0.9546339511871338, | |
| "learning_rate": 4.864037798685105e-07, | |
| "loss": 0.1468, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.020618556701031, | |
| "grad_norm": 4.817622184753418, | |
| "learning_rate": 0.0, | |
| "loss": 0.465, | |
| "step": 49 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 49, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.553988385695334e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |