| { | |
| "best_metric": 2.2513699531555176, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0654205607476634, | |
| "eval_steps": 25, | |
| "global_step": 41, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 52.437808990478516, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6218, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "eval_loss": 2.868361473083496, | |
| "eval_runtime": 2.7626, | |
| "eval_samples_per_second": 32.578, | |
| "eval_steps_per_second": 4.344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 62.30055618286133, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8258, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 50.62723922729492, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 2.8678, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 23.226940155029297, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 2.5865, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "grad_norm": 18.977237701416016, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 2.5321, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 18.98895835876465, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 2.5449, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5233644859813084, | |
| "grad_norm": 19.410400390625, | |
| "learning_rate": 9.599897218294122e-05, | |
| "loss": 2.5754, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 15.047514915466309, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 2.3645, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6728971962616822, | |
| "grad_norm": 17.346294403076172, | |
| "learning_rate": 9.225950427718975e-05, | |
| "loss": 2.5285, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 19.977304458618164, | |
| "learning_rate": 8.997213817017507e-05, | |
| "loss": 2.5316, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.822429906542056, | |
| "grad_norm": 13.670703887939453, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 2.3245, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 16.614707946777344, | |
| "learning_rate": 8.463621767547998e-05, | |
| "loss": 2.4291, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9719626168224299, | |
| "grad_norm": 21.476789474487305, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 2.4998, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0467289719626167, | |
| "grad_norm": 19.93166732788086, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 2.2712, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1214953271028036, | |
| "grad_norm": 20.504732131958008, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.2245, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1962616822429906, | |
| "grad_norm": 22.490373611450195, | |
| "learning_rate": 7.143462807015271e-05, | |
| "loss": 2.2367, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2710280373831775, | |
| "grad_norm": 24.899566650390625, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 2.2027, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3457943925233644, | |
| "grad_norm": 18.880807876586914, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 2.0954, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4205607476635513, | |
| "grad_norm": 25.04975700378418, | |
| "learning_rate": 6.0001284688802226e-05, | |
| "loss": 2.1479, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4953271028037383, | |
| "grad_norm": 34.131710052490234, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 2.1566, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5700934579439252, | |
| "grad_norm": 21.789352416992188, | |
| "learning_rate": 5.201329700547076e-05, | |
| "loss": 2.0656, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.644859813084112, | |
| "grad_norm": 24.60956573486328, | |
| "learning_rate": 4.798670299452926e-05, | |
| "loss": 2.0348, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.719626168224299, | |
| "grad_norm": 33.40323257446289, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 2.0798, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.794392523364486, | |
| "grad_norm": 22.348012924194336, | |
| "learning_rate": 3.9998715311197785e-05, | |
| "loss": 2.1067, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "grad_norm": 23.872865676879883, | |
| "learning_rate": 3.608912680417737e-05, | |
| "loss": 2.0294, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "eval_loss": 2.2513699531555176, | |
| "eval_runtime": 2.762, | |
| "eval_samples_per_second": 32.585, | |
| "eval_steps_per_second": 4.345, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9439252336448598, | |
| "grad_norm": 27.256940841674805, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 2.0209, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.0186915887850465, | |
| "grad_norm": 18.509977340698242, | |
| "learning_rate": 2.8565371929847284e-05, | |
| "loss": 2.014, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.0934579439252334, | |
| "grad_norm": 17.066274642944336, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.9126, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.1682242990654204, | |
| "grad_norm": 20.49900245666504, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 2.0215, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.2429906542056073, | |
| "grad_norm": 26.371129989624023, | |
| "learning_rate": 1.837773122023114e-05, | |
| "loss": 1.9231, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.317757009345794, | |
| "grad_norm": 17.720001220703125, | |
| "learning_rate": 1.536378232452003e-05, | |
| "loss": 1.9388, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.392523364485981, | |
| "grad_norm": 23.14875602722168, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 1.9817, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.467289719626168, | |
| "grad_norm": 24.21807098388672, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 1.9115, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.542056074766355, | |
| "grad_norm": 19.666227340698242, | |
| "learning_rate": 7.740495722810271e-06, | |
| "loss": 2.003, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.616822429906542, | |
| "grad_norm": 19.526100158691406, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 1.9958, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.691588785046729, | |
| "grad_norm": 23.403148651123047, | |
| "learning_rate": 4.001027817058789e-06, | |
| "loss": 1.8665, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.7663551401869158, | |
| "grad_norm": 20.573028564453125, | |
| "learning_rate": 2.573177902642726e-06, | |
| "loss": 1.9312, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.8411214953271027, | |
| "grad_norm": 20.156404495239258, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 1.9, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.9158878504672896, | |
| "grad_norm": 22.972078323364258, | |
| "learning_rate": 6.474868681043578e-07, | |
| "loss": 1.9394, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.9906542056074765, | |
| "grad_norm": 23.492944717407227, | |
| "learning_rate": 1.6213459328950352e-07, | |
| "loss": 1.8333, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0654205607476634, | |
| "grad_norm": 26.423542022705078, | |
| "learning_rate": 0.0, | |
| "loss": 1.9647, | |
| "step": 41 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 41, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "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": 4.639577497392906e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |