| { | |
| "best_metric": 0.6338592171669006, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004227436060029592, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "grad_norm": 7.880180835723877, | |
| "learning_rate": 2e-05, | |
| "loss": 6.8105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 7.039806842803955, | |
| "eval_runtime": 602.01, | |
| "eval_samples_per_second": 4.136, | |
| "eval_steps_per_second": 2.068, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003381948848023674, | |
| "grad_norm": 8.031022071838379, | |
| "learning_rate": 4e-05, | |
| "loss": 6.8724, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "grad_norm": 7.720982551574707, | |
| "learning_rate": 6e-05, | |
| "loss": 7.163, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006763897696047348, | |
| "grad_norm": 7.786631107330322, | |
| "learning_rate": 8e-05, | |
| "loss": 6.4734, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "grad_norm": 7.987817764282227, | |
| "learning_rate": 0.0001, | |
| "loss": 6.6437, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "eval_loss": 6.247725963592529, | |
| "eval_runtime": 600.4783, | |
| "eval_samples_per_second": 4.147, | |
| "eval_steps_per_second": 2.073, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "grad_norm": 7.455833435058594, | |
| "learning_rate": 0.00012, | |
| "loss": 5.8246, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011836820968082857, | |
| "grad_norm": 6.757167816162109, | |
| "learning_rate": 0.00014, | |
| "loss": 5.7905, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013527795392094695, | |
| "grad_norm": 5.719376564025879, | |
| "learning_rate": 0.00016, | |
| "loss": 4.8618, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "grad_norm": 5.285928726196289, | |
| "learning_rate": 0.00018, | |
| "loss": 4.4147, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "grad_norm": 5.3481597900390625, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7365, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "eval_loss": 3.2554361820220947, | |
| "eval_runtime": 600.7805, | |
| "eval_samples_per_second": 4.145, | |
| "eval_steps_per_second": 2.072, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018600718664130206, | |
| "grad_norm": 6.436682224273682, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 3.191, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002029169308814204, | |
| "grad_norm": 7.085083961486816, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.5658, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002198266751215388, | |
| "grad_norm": 6.376532554626465, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.0241, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0023673641936165714, | |
| "grad_norm": 6.964225769042969, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.4019, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "grad_norm": 4.293122291564941, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.0645, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "eval_loss": 0.9395115375518799, | |
| "eval_runtime": 603.067, | |
| "eval_samples_per_second": 4.129, | |
| "eval_steps_per_second": 2.064, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002705559078418939, | |
| "grad_norm": 3.014976739883423, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.8958, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0028746565208201224, | |
| "grad_norm": 2.4316983222961426, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.0846, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0030437539632213063, | |
| "grad_norm": 3.1216464042663574, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.9207, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00321285140562249, | |
| "grad_norm": 2.6117305755615234, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.6413, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "grad_norm": 2.181574583053589, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.7599, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "eval_loss": 0.6971116662025452, | |
| "eval_runtime": 603.4348, | |
| "eval_samples_per_second": 4.126, | |
| "eval_steps_per_second": 2.063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0035510462904248573, | |
| "grad_norm": 1.8930898904800415, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.614, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003720143732826041, | |
| "grad_norm": 2.1064653396606445, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.8232, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0038892411752272245, | |
| "grad_norm": 2.0310540199279785, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.8117, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004058338617628408, | |
| "grad_norm": 2.183011531829834, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.7991, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004227436060029592, | |
| "grad_norm": 1.9778447151184082, | |
| "learning_rate": 0.0, | |
| "loss": 0.7084, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004227436060029592, | |
| "eval_loss": 0.6338592171669006, | |
| "eval_runtime": 603.6127, | |
| "eval_samples_per_second": 4.125, | |
| "eval_steps_per_second": 2.063, | |
| "step": 25 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3119510194225152.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |