| { | |
| "best_metric": 1.1002987623214722, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0004880072225068931, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.9520288900275725e-05, | |
| "grad_norm": 10.334268569946289, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7093, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.9520288900275725e-05, | |
| "eval_loss": 1.3136714696884155, | |
| "eval_runtime": 6002.6747, | |
| "eval_samples_per_second": 3.593, | |
| "eval_steps_per_second": 1.797, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.904057780055145e-05, | |
| "grad_norm": 12.176424980163574, | |
| "learning_rate": 0.0002, | |
| "loss": 5.0525, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.856086670082717e-05, | |
| "grad_norm": 8.576818466186523, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 4.7167, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.80811556011029e-05, | |
| "grad_norm": 18.30161476135254, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 5.2112, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 9.760144450137862e-05, | |
| "grad_norm": 8.57841682434082, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 4.479, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00011712173340165434, | |
| "grad_norm": 5.883150100708008, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 4.0482, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00013664202230193008, | |
| "grad_norm": 6.208558082580566, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 4.6876, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001561623112022058, | |
| "grad_norm": 7.253965377807617, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 4.4962, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00017568260010248152, | |
| "grad_norm": 7.173295497894287, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 4.579, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00019520288900275724, | |
| "grad_norm": 6.47155237197876, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 4.7364, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00021472317790303296, | |
| "grad_norm": 6.548929691314697, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 4.2588, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00023424346680330868, | |
| "grad_norm": 6.918939113616943, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 4.2177, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002537637557035844, | |
| "grad_norm": 5.7343363761901855, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 4.3725, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00027328404460386015, | |
| "grad_norm": 5.065625190734863, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 4.0603, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00029280433350413584, | |
| "grad_norm": 6.888638496398926, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 4.4999, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003123246224044116, | |
| "grad_norm": 6.872077465057373, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 4.2474, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0003318449113046873, | |
| "grad_norm": 5.9835309982299805, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 4.4801, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00035136520020496304, | |
| "grad_norm": 6.098293304443359, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.1836, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0003708854891052388, | |
| "grad_norm": 5.965084075927734, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 4.7496, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0003904057780055145, | |
| "grad_norm": 6.869338512420654, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 4.4003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004099260669057902, | |
| "grad_norm": 5.926541805267334, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 4.0398, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0004294463558060659, | |
| "grad_norm": 6.244675636291504, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 4.2699, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00044896664470634167, | |
| "grad_norm": 6.214200496673584, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 4.465, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00046848693360661736, | |
| "grad_norm": 5.795085430145264, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 4.281, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0004880072225068931, | |
| "grad_norm": 6.204129219055176, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 4.0462, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0004880072225068931, | |
| "eval_loss": 1.1002987623214722, | |
| "eval_runtime": 6028.5222, | |
| "eval_samples_per_second": 3.578, | |
| "eval_steps_per_second": 1.789, | |
| "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": 3.5508080351379456e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |