| { | |
| "best_metric": 7.495559111703187e-05, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0003233148828306865, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2932595313227458e-05, | |
| "grad_norm": 12.3665771484375, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7667, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.2932595313227458e-05, | |
| "eval_loss": 5.663321018218994, | |
| "eval_runtime": 4042.9337, | |
| "eval_samples_per_second": 8.053, | |
| "eval_steps_per_second": 4.027, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.5865190626454916e-05, | |
| "grad_norm": 13.965386390686035, | |
| "learning_rate": 0.0002, | |
| "loss": 4.6426, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.8797785939682375e-05, | |
| "grad_norm": 13.06217098236084, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 4.1725, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.173038125290983e-05, | |
| "grad_norm": 9.654458999633789, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 2.252, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 6.46629765661373e-05, | |
| "grad_norm": 6.366847991943359, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.2929, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.759557187936475e-05, | |
| "grad_norm": 3.7300143241882324, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.4743, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.052816719259221e-05, | |
| "grad_norm": 2.255476951599121, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.2423, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00010346076250581966, | |
| "grad_norm": 1.4915378093719482, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0855, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00011639335781904713, | |
| "grad_norm": 0.2951045632362366, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.011, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001293259531322746, | |
| "grad_norm": 0.023305028676986694, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0005, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00014225854844550205, | |
| "grad_norm": 0.003954252693802118, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.0001, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0001551911437587295, | |
| "grad_norm": 0.0012373141944408417, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00016812373907195696, | |
| "grad_norm": 0.0023228523787111044, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.0001, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00018105633438518441, | |
| "grad_norm": 0.005288443528115749, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0001, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00019398892969841187, | |
| "grad_norm": 0.00128844880964607, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00020692152501163933, | |
| "grad_norm": 0.0020125224255025387, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00021985412032486678, | |
| "grad_norm": 0.0037247403524816036, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00023278671563809427, | |
| "grad_norm": 0.014811231754720211, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0001, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0002457193109513217, | |
| "grad_norm": 0.007926372811198235, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0001, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0002586519062645492, | |
| "grad_norm": 0.02340223640203476, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0002, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0002715845015777766, | |
| "grad_norm": 0.0066363937221467495, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.0001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0002845170968910041, | |
| "grad_norm": 0.002405409701168537, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0002974496922042315, | |
| "grad_norm": 0.0022278388496488333, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0001, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.000310382287517459, | |
| "grad_norm": 0.002495991997420788, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0001, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0003233148828306865, | |
| "grad_norm": 0.0063591911457479, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0001, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0003233148828306865, | |
| "eval_loss": 7.495559111703187e-05, | |
| "eval_runtime": 4069.8131, | |
| "eval_samples_per_second": 8.0, | |
| "eval_steps_per_second": 4.0, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6531344184115200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |