| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.034584125886218224, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006916825177243646, | |
| "grad_norm": 0.2954893708229065, | |
| "learning_rate": 0.0, | |
| "loss": 2.3812, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013833650354487291, | |
| "grad_norm": 0.3372870683670044, | |
| "learning_rate": 1.3698630136986302e-06, | |
| "loss": 2.6562, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020750475531730937, | |
| "grad_norm": 0.41708794236183167, | |
| "learning_rate": 2.7397260273972604e-06, | |
| "loss": 2.779, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0027667300708974583, | |
| "grad_norm": 0.48284393548965454, | |
| "learning_rate": 4.10958904109589e-06, | |
| "loss": 2.83, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0034584125886218224, | |
| "grad_norm": 0.328521728515625, | |
| "learning_rate": 5.479452054794521e-06, | |
| "loss": 2.3607, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004150095106346187, | |
| "grad_norm": 0.3413754403591156, | |
| "learning_rate": 6.849315068493151e-06, | |
| "loss": 1.9744, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0048417776240705515, | |
| "grad_norm": 0.43425995111465454, | |
| "learning_rate": 8.21917808219178e-06, | |
| "loss": 1.915, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0055334601417949165, | |
| "grad_norm": 0.45184195041656494, | |
| "learning_rate": 9.589041095890411e-06, | |
| "loss": 2.0002, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006225142659519281, | |
| "grad_norm": 0.3451146185398102, | |
| "learning_rate": 1.0958904109589042e-05, | |
| "loss": 2.5739, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006916825177243645, | |
| "grad_norm": 0.39400503039360046, | |
| "learning_rate": 1.2328767123287671e-05, | |
| "loss": 2.6139, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00760850769496801, | |
| "grad_norm": 0.4555888772010803, | |
| "learning_rate": 1.3698630136986302e-05, | |
| "loss": 2.4346, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008300190212692375, | |
| "grad_norm": 0.5475619435310364, | |
| "learning_rate": 1.5068493150684931e-05, | |
| "loss": 1.485, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008991872730416739, | |
| "grad_norm": 1.219076156616211, | |
| "learning_rate": 1.643835616438356e-05, | |
| "loss": 2.0555, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009683555248141103, | |
| "grad_norm": 0.3271433711051941, | |
| "learning_rate": 1.780821917808219e-05, | |
| "loss": 2.8418, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010375237765865467, | |
| "grad_norm": 0.3261394500732422, | |
| "learning_rate": 1.9178082191780822e-05, | |
| "loss": 2.287, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011066920283589833, | |
| "grad_norm": 0.39713796973228455, | |
| "learning_rate": 2.0547945205479453e-05, | |
| "loss": 2.7331, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011758602801314197, | |
| "grad_norm": 0.3226444125175476, | |
| "learning_rate": 2.1917808219178083e-05, | |
| "loss": 2.7307, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.012450285319038561, | |
| "grad_norm": 0.4153122007846832, | |
| "learning_rate": 2.328767123287671e-05, | |
| "loss": 2.3229, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013141967836762926, | |
| "grad_norm": 0.29302462935447693, | |
| "learning_rate": 2.4657534246575342e-05, | |
| "loss": 2.2093, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01383365035448729, | |
| "grad_norm": 0.42535701394081116, | |
| "learning_rate": 2.6027397260273973e-05, | |
| "loss": 2.3698, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014525332872211656, | |
| "grad_norm": 0.33567023277282715, | |
| "learning_rate": 2.7397260273972603e-05, | |
| "loss": 2.6456, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01521701538993602, | |
| "grad_norm": 0.37375620007514954, | |
| "learning_rate": 2.8767123287671234e-05, | |
| "loss": 2.4148, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.015908697907660384, | |
| "grad_norm": 0.2704203128814697, | |
| "learning_rate": 3.0136986301369862e-05, | |
| "loss": 1.6722, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01660038042538475, | |
| "grad_norm": 0.3946782946586609, | |
| "learning_rate": 3.1506849315068496e-05, | |
| "loss": 2.6759, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017292062943109112, | |
| "grad_norm": 0.368335098028183, | |
| "learning_rate": 3.287671232876712e-05, | |
| "loss": 2.6882, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017983745460833478, | |
| "grad_norm": 0.38029783964157104, | |
| "learning_rate": 3.424657534246575e-05, | |
| "loss": 2.6915, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01867542797855784, | |
| "grad_norm": 0.36253222823143005, | |
| "learning_rate": 3.561643835616438e-05, | |
| "loss": 2.1426, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.019367110496282206, | |
| "grad_norm": 0.35769322514533997, | |
| "learning_rate": 3.698630136986301e-05, | |
| "loss": 2.6634, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.020058793014006572, | |
| "grad_norm": 0.44577229022979736, | |
| "learning_rate": 3.8356164383561644e-05, | |
| "loss": 2.5996, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.020750475531730934, | |
| "grad_norm": 0.5225628614425659, | |
| "learning_rate": 3.9726027397260274e-05, | |
| "loss": 2.5993, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0214421580494553, | |
| "grad_norm": 0.45649707317352295, | |
| "learning_rate": 4.1095890410958905e-05, | |
| "loss": 2.3344, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.022133840567179666, | |
| "grad_norm": 0.31408172845840454, | |
| "learning_rate": 4.2465753424657536e-05, | |
| "loss": 2.343, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02282552308490403, | |
| "grad_norm": 0.3498693108558655, | |
| "learning_rate": 4.383561643835617e-05, | |
| "loss": 1.7196, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.023517205602628394, | |
| "grad_norm": 0.5255292654037476, | |
| "learning_rate": 4.520547945205479e-05, | |
| "loss": 1.5354, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.024208888120352757, | |
| "grad_norm": 0.3460487425327301, | |
| "learning_rate": 4.657534246575342e-05, | |
| "loss": 2.1435, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.024900570638077123, | |
| "grad_norm": 0.47466233372688293, | |
| "learning_rate": 4.794520547945205e-05, | |
| "loss": 2.7025, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02559225315580149, | |
| "grad_norm": 0.39667466282844543, | |
| "learning_rate": 4.9315068493150684e-05, | |
| "loss": 2.2736, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02628393567352585, | |
| "grad_norm": 0.40798133611679077, | |
| "learning_rate": 5.068493150684932e-05, | |
| "loss": 1.4074, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.026975618191250217, | |
| "grad_norm": 0.39603471755981445, | |
| "learning_rate": 5.2054794520547945e-05, | |
| "loss": 2.4354, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02766730070897458, | |
| "grad_norm": 0.5650593042373657, | |
| "learning_rate": 5.342465753424658e-05, | |
| "loss": 1.7307, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028358983226698945, | |
| "grad_norm": 0.7711919546127319, | |
| "learning_rate": 5.479452054794521e-05, | |
| "loss": 1.2067, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02905066574442331, | |
| "grad_norm": 0.46603119373321533, | |
| "learning_rate": 5.616438356164384e-05, | |
| "loss": 1.0539, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.029742348262147673, | |
| "grad_norm": 0.2997550666332245, | |
| "learning_rate": 5.753424657534247e-05, | |
| "loss": 1.9997, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03043403077987204, | |
| "grad_norm": 0.4058617651462555, | |
| "learning_rate": 5.89041095890411e-05, | |
| "loss": 2.3323, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0311257132975964, | |
| "grad_norm": 0.3763635754585266, | |
| "learning_rate": 6.0273972602739724e-05, | |
| "loss": 1.8749, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03181739581532077, | |
| "grad_norm": 0.3507993221282959, | |
| "learning_rate": 6.164383561643835e-05, | |
| "loss": 2.3828, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03250907833304513, | |
| "grad_norm": 0.34240859746932983, | |
| "learning_rate": 6.301369863013699e-05, | |
| "loss": 2.3809, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0332007608507695, | |
| "grad_norm": 0.4183844029903412, | |
| "learning_rate": 6.438356164383562e-05, | |
| "loss": 2.2065, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03389244336849386, | |
| "grad_norm": 0.5209120512008667, | |
| "learning_rate": 6.575342465753424e-05, | |
| "loss": 2.061, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.034584125886218224, | |
| "grad_norm": 0.6568111181259155, | |
| "learning_rate": 6.712328767123288e-05, | |
| "loss": 2.1576, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1446, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1666678748626944.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |