| { | |
| "best_metric": 1.073704481124878, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0007506662162669369, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0026648650677475e-05, | |
| "grad_norm": 2.444312810897827, | |
| "learning_rate": 2e-05, | |
| "loss": 3.318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.0026648650677475e-05, | |
| "eval_loss": 4.371880054473877, | |
| "eval_runtime": 2983.3634, | |
| "eval_samples_per_second": 4.7, | |
| "eval_steps_per_second": 2.35, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.005329730135495e-05, | |
| "grad_norm": 2.6870970726013184, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8858, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.007994595203243e-05, | |
| "grad_norm": 3.0285346508026123, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4867, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001201065946027099, | |
| "grad_norm": 3.162102460861206, | |
| "learning_rate": 8e-05, | |
| "loss": 4.0637, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00015013324325338737, | |
| "grad_norm": 3.520521402359009, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9885, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00015013324325338737, | |
| "eval_loss": 4.278146266937256, | |
| "eval_runtime": 3013.5635, | |
| "eval_samples_per_second": 4.653, | |
| "eval_steps_per_second": 2.327, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018015989190406487, | |
| "grad_norm": 3.8060147762298584, | |
| "learning_rate": 0.00012, | |
| "loss": 4.7423, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00021018654055474234, | |
| "grad_norm": 4.787139892578125, | |
| "learning_rate": 0.00014, | |
| "loss": 3.4616, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002402131892054198, | |
| "grad_norm": 4.9317450523376465, | |
| "learning_rate": 0.00016, | |
| "loss": 3.7389, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002702398378560973, | |
| "grad_norm": 6.266666412353516, | |
| "learning_rate": 0.00018, | |
| "loss": 3.8855, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00030026648650677474, | |
| "grad_norm": 4.693113327026367, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5356, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00030026648650677474, | |
| "eval_loss": 2.4615635871887207, | |
| "eval_runtime": 2990.7511, | |
| "eval_samples_per_second": 4.689, | |
| "eval_steps_per_second": 2.345, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00033029313515745224, | |
| "grad_norm": 3.4659929275512695, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.2581, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00036031978380812973, | |
| "grad_norm": 3.400052547454834, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.5006, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0003903464324588072, | |
| "grad_norm": 4.236875534057617, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.3779, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00042037308110948467, | |
| "grad_norm": 2.8546998500823975, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.4861, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00045039972976016217, | |
| "grad_norm": 2.772555351257324, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.0839, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00045039972976016217, | |
| "eval_loss": 1.3496323823928833, | |
| "eval_runtime": 2989.3035, | |
| "eval_samples_per_second": 4.691, | |
| "eval_steps_per_second": 2.346, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004804263784108396, | |
| "grad_norm": 3.290262222290039, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6864, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005104530270615171, | |
| "grad_norm": 7.517457008361816, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.5145, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0005404796757121946, | |
| "grad_norm": 2.91314697265625, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.2166, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005705063243628721, | |
| "grad_norm": 2.970187187194824, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.0019, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006005329730135495, | |
| "grad_norm": 2.592427968978882, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.9736, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006005329730135495, | |
| "eval_loss": 1.1027315855026245, | |
| "eval_runtime": 3004.3882, | |
| "eval_samples_per_second": 4.668, | |
| "eval_steps_per_second": 2.334, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000630559621664227, | |
| "grad_norm": 2.9686336517333984, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.9968, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0006605862703149045, | |
| "grad_norm": 2.496239423751831, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.9969, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.000690612918965582, | |
| "grad_norm": 2.3941261768341064, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.8335, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0007206395676162595, | |
| "grad_norm": 3.228595733642578, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.0958, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007506662162669369, | |
| "grad_norm": 2.879379987716675, | |
| "learning_rate": 0.0, | |
| "loss": 1.0913, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0007506662162669369, | |
| "eval_loss": 1.073704481124878, | |
| "eval_runtime": 2987.5623, | |
| "eval_samples_per_second": 4.694, | |
| "eval_steps_per_second": 2.347, | |
| "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": 1.044847376990208e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |