| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3415137231349945, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.4337, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.33824849128723145, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.4472, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3517794609069824, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4119, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.49278953671455383, | |
| "learning_rate": 0.00019977668786231534, | |
| "loss": 0.4045, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.5396780967712402, | |
| "learning_rate": 0.000199107748815478, | |
| "loss": 0.4354, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.5213820934295654, | |
| "learning_rate": 0.0001979961705036587, | |
| "loss": 0.4435, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.42753931879997253, | |
| "learning_rate": 0.00019644691750543767, | |
| "loss": 0.4306, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.46985888481140137, | |
| "learning_rate": 0.0001944669091607919, | |
| "loss": 0.4558, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.44640442728996277, | |
| "learning_rate": 0.00019206498866764288, | |
| "loss": 0.4777, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.4198346734046936, | |
| "learning_rate": 0.00018925188358598813, | |
| "loss": 0.4845, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.43529659509658813, | |
| "learning_rate": 0.00018604015792601396, | |
| "loss": 0.4327, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.4187154471874237, | |
| "learning_rate": 0.00018244415603417603, | |
| "loss": 0.4682, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.4378308057785034, | |
| "learning_rate": 0.0001784799385278661, | |
| "loss": 0.5107, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.40074899792671204, | |
| "learning_rate": 0.00017416521056479577, | |
| "loss": 0.4809, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.4163818955421448, | |
| "learning_rate": 0.00016951924276746425, | |
| "loss": 0.4956, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.39697593450546265, | |
| "learning_rate": 0.00016456278515588024, | |
| "loss": 0.4907, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.4083729088306427, | |
| "learning_rate": 0.00015931797447293552, | |
| "loss": 0.4838, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.38315674662590027, | |
| "learning_rate": 0.00015380823531633729, | |
| "loss": 0.4958, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.37201324105262756, | |
| "learning_rate": 0.00014805817551866838, | |
| "loss": 0.4897, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.37709081172943115, | |
| "learning_rate": 0.0001420934762428335, | |
| "loss": 0.4692, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.37321537733078003, | |
| "learning_rate": 0.00013594077728375128, | |
| "loss": 0.5103, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.38839632272720337, | |
| "learning_rate": 0.00012962755808856342, | |
| "loss": 0.5218, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.37921735644340515, | |
| "learning_rate": 0.00012318201502675285, | |
| "loss": 0.5324, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.4005667567253113, | |
| "learning_rate": 0.00011663293545831302, | |
| "loss": 0.5168, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.37409457564353943, | |
| "learning_rate": 0.00011000956916240985, | |
| "loss": 0.4907, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.3958514630794525, | |
| "learning_rate": 0.00010334149770076747, | |
| "loss": 0.5186, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.38589972257614136, | |
| "learning_rate": 9.665850229923258e-05, | |
| "loss": 0.5282, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.3830341100692749, | |
| "learning_rate": 8.999043083759017e-05, | |
| "loss": 0.4814, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.37159013748168945, | |
| "learning_rate": 8.336706454168701e-05, | |
| "loss": 0.5096, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.3702056109905243, | |
| "learning_rate": 7.681798497324716e-05, | |
| "loss": 0.4727, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.3684118688106537, | |
| "learning_rate": 7.037244191143661e-05, | |
| "loss": 0.4695, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.3787296712398529, | |
| "learning_rate": 6.405922271624874e-05, | |
| "loss": 0.5261, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.39863407611846924, | |
| "learning_rate": 5.790652375716652e-05, | |
| "loss": 0.5312, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.35908952355384827, | |
| "learning_rate": 5.1941824481331626e-05, | |
| "loss": 0.507, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.37030553817749023, | |
| "learning_rate": 4.6191764683662744e-05, | |
| "loss": 0.4799, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.3842332661151886, | |
| "learning_rate": 4.0682025527064486e-05, | |
| "loss": 0.5104, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.3656119108200073, | |
| "learning_rate": 3.543721484411976e-05, | |
| "loss": 0.4926, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.3526756763458252, | |
| "learning_rate": 3.0480757232535772e-05, | |
| "loss": 0.4962, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.3747156858444214, | |
| "learning_rate": 2.5834789435204243e-05, | |
| "loss": 0.5222, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.37097883224487305, | |
| "learning_rate": 2.1520061472133902e-05, | |
| "loss": 0.5288, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.37520304322242737, | |
| "learning_rate": 1.7555843965823992e-05, | |
| "loss": 0.5005, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.34392106533050537, | |
| "learning_rate": 1.3959842073986085e-05, | |
| "loss": 0.4774, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.3575632572174072, | |
| "learning_rate": 1.0748116414011888e-05, | |
| "loss": 0.5033, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.35089874267578125, | |
| "learning_rate": 7.935011332357112e-06, | |
| "loss": 0.5018, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.3535928428173065, | |
| "learning_rate": 5.533090839208133e-06, | |
| "loss": 0.5141, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.37137070298194885, | |
| "learning_rate": 3.5530824945623542e-06, | |
| "loss": 0.5101, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.38077953457832336, | |
| "learning_rate": 2.003829496341325e-06, | |
| "loss": 0.5513, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.3571460545063019, | |
| "learning_rate": 8.922511845219971e-07, | |
| "loss": 0.5074, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.34851184487342834, | |
| "learning_rate": 2.2331213768468363e-07, | |
| "loss": 0.4974, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.3630204200744629, | |
| "learning_rate": 0.0, | |
| "loss": 0.52, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 6.058530297072845e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |