| { | |
| "best_metric": 0.3715277314186096, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.02969561989606533, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014847809948032665, | |
| "grad_norm": 4.760746479034424, | |
| "learning_rate": 2e-05, | |
| "loss": 11.3863, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014847809948032665, | |
| "eval_loss": 2.8857903480529785, | |
| "eval_runtime": 52.3524, | |
| "eval_samples_per_second": 5.425, | |
| "eval_steps_per_second": 2.712, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002969561989606533, | |
| "grad_norm": 3.34657883644104, | |
| "learning_rate": 4e-05, | |
| "loss": 11.0456, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004454342984409799, | |
| "grad_norm": 3.2356274127960205, | |
| "learning_rate": 6e-05, | |
| "loss": 13.5547, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005939123979213066, | |
| "grad_norm": 2.6824147701263428, | |
| "learning_rate": 8e-05, | |
| "loss": 8.7514, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007423904974016332, | |
| "grad_norm": 5.473128318786621, | |
| "learning_rate": 0.0001, | |
| "loss": 13.6083, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007423904974016332, | |
| "eval_loss": 2.8108508586883545, | |
| "eval_runtime": 52.1477, | |
| "eval_samples_per_second": 5.446, | |
| "eval_steps_per_second": 2.723, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008908685968819599, | |
| "grad_norm": 6.155984401702881, | |
| "learning_rate": 0.00012, | |
| "loss": 12.4103, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010393466963622866, | |
| "grad_norm": 6.005216121673584, | |
| "learning_rate": 0.00014, | |
| "loss": 9.9214, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011878247958426132, | |
| "grad_norm": 8.351831436157227, | |
| "learning_rate": 0.00016, | |
| "loss": 10.4195, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013363028953229399, | |
| "grad_norm": 13.200093269348145, | |
| "learning_rate": 0.00018, | |
| "loss": 8.6825, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014847809948032665, | |
| "grad_norm": 18.01533317565918, | |
| "learning_rate": 0.0002, | |
| "loss": 5.6008, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014847809948032665, | |
| "eval_loss": 1.0966575145721436, | |
| "eval_runtime": 53.1328, | |
| "eval_samples_per_second": 5.345, | |
| "eval_steps_per_second": 2.673, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016332590942835932, | |
| "grad_norm": 5.9748125076293945, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 4.4809, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.017817371937639197, | |
| "grad_norm": 4.773859024047852, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 4.0181, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.019302152932442463, | |
| "grad_norm": 4.2915544509887695, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.8875, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.020786933927245732, | |
| "grad_norm": 4.280338287353516, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.363, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.022271714922048998, | |
| "grad_norm": 5.092531681060791, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.1731, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022271714922048998, | |
| "eval_loss": 0.5182551145553589, | |
| "eval_runtime": 51.7607, | |
| "eval_samples_per_second": 5.487, | |
| "eval_steps_per_second": 2.743, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023756495916852263, | |
| "grad_norm": 5.672760486602783, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.6013, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.025241276911655532, | |
| "grad_norm": 6.637510776519775, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 2.5146, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.026726057906458798, | |
| "grad_norm": 4.401640892028809, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.8105, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.028210838901262063, | |
| "grad_norm": 4.6342902183532715, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.7016, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02969561989606533, | |
| "grad_norm": 3.619751453399658, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.7681, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02969561989606533, | |
| "eval_loss": 0.3715277314186096, | |
| "eval_runtime": 52.4711, | |
| "eval_samples_per_second": 5.412, | |
| "eval_steps_per_second": 2.706, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 6332448610713600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |