| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.7440087145969498, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.034858387799564274, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.034858387799564274, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5128, | |
| "eval_samples_per_second": 33.05, | |
| "eval_steps_per_second": 8.593, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06971677559912855, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10457516339869281, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1394335511982571, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996776896673492e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17429193899782136, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987112203758434e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20915032679738563, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.971019765834333e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2440087145969499, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.948522635163499e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2788671023965142, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.919653038668912e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.88445233176946e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3485838779956427, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.8429709391387e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38344226579520696, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.795268282471998e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.41830065359477125, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.741412695365528e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4531590413943355, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.681481325429045e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4880174291938998, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.615560023772684e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5228758169934641, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.543743222026071e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5577342047930284, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.46613379706592e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.382842923645904e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.29398991513988e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6623093681917211, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.199702052626646e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6971677559912854, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.100114402561006e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7320261437908496, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.995369623292385e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7668845315904139, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.885617760708116e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8017429193899782, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.771016033294148e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8366013071895425, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.651728606921079e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8714596949891068, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.527926359678135e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8714596949891068, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5117, | |
| "eval_samples_per_second": 33.076, | |
| "eval_steps_per_second": 8.6, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.906318082788671, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.399786637091947e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.267492998080791e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9760348583877996, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.131234952008212e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0119825708061003, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.99120768721268e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0468409586056644, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.847611791402181e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0816993464052287, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.70065296431425e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.116557734204793, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.550541723053088e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1514161220043573, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.397493100525829e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1862745098039216, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.241726337409979e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2211328976034859, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.083464568093249e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2559912854030502, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.922934501035709e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.2908496732026145, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.760366094012083e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3257080610021785, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.595992224699463e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3605664488017428, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.430048357082287e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3954248366013071, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.262772204152436e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4302832244008714, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0944033873876616e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.4651416122004357, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9251830934961414e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.755353728918834e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5348583877995643, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5851585725845854e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.5697167755991286, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4148414274154156e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6045751633986929, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2446462710811675e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6394335511982572, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0748169065038596e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6742919389978215, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.905596612612341e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7091503267973858, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.737227795847565e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7440087145969498, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5699516429177116e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7440087145969498, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5121, | |
| "eval_samples_per_second": 33.068, | |
| "eval_steps_per_second": 8.598, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 86, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.658027780734976e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |