| { | |
| "best_metric": 1.5233994722366333, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.00028842236571234917, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.4421118285617457e-05, | |
| "grad_norm": 6.198405742645264, | |
| "learning_rate": 2e-05, | |
| "loss": 7.7418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.4421118285617457e-05, | |
| "eval_loss": 2.0990982055664062, | |
| "eval_runtime": 3784.401, | |
| "eval_samples_per_second": 7.715, | |
| "eval_steps_per_second": 3.858, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.8842236571234915e-05, | |
| "grad_norm": 11.339609146118164, | |
| "learning_rate": 4e-05, | |
| "loss": 6.5656, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.3263354856852374e-05, | |
| "grad_norm": 7.180484294891357, | |
| "learning_rate": 6e-05, | |
| "loss": 8.523, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.768447314246983e-05, | |
| "grad_norm": 6.847208499908447, | |
| "learning_rate": 8e-05, | |
| "loss": 8.182, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 7.210559142808729e-05, | |
| "grad_norm": 7.131789207458496, | |
| "learning_rate": 0.0001, | |
| "loss": 7.134, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.210559142808729e-05, | |
| "eval_loss": 2.0334839820861816, | |
| "eval_runtime": 3461.7725, | |
| "eval_samples_per_second": 8.434, | |
| "eval_steps_per_second": 4.217, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 8.652670971370475e-05, | |
| "grad_norm": 7.048887729644775, | |
| "learning_rate": 0.00012, | |
| "loss": 6.7966, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001009478279993222, | |
| "grad_norm": 7.7529706954956055, | |
| "learning_rate": 0.00014, | |
| "loss": 7.3774, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00011536894628493966, | |
| "grad_norm": 7.959862232208252, | |
| "learning_rate": 0.00016, | |
| "loss": 7.0313, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00012979006457055711, | |
| "grad_norm": 8.67849063873291, | |
| "learning_rate": 0.00018, | |
| "loss": 8.1428, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00014421118285617458, | |
| "grad_norm": 5.950510025024414, | |
| "learning_rate": 0.0002, | |
| "loss": 7.4223, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00014421118285617458, | |
| "eval_loss": 1.7785707712173462, | |
| "eval_runtime": 3665.8188, | |
| "eval_samples_per_second": 7.965, | |
| "eval_steps_per_second": 3.982, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00015863230114179205, | |
| "grad_norm": 6.472969055175781, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 6.2931, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0001730534194274095, | |
| "grad_norm": 7.8940019607543945, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 6.2547, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00018747453771302696, | |
| "grad_norm": 5.983705043792725, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 6.1572, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0002018956559986444, | |
| "grad_norm": 8.07612133026123, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 7.1022, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00021631677428426188, | |
| "grad_norm": 8.90300464630127, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 8.0417, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00021631677428426188, | |
| "eval_loss": 1.5895220041275024, | |
| "eval_runtime": 3680.7157, | |
| "eval_samples_per_second": 7.932, | |
| "eval_steps_per_second": 3.966, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00023073789256987932, | |
| "grad_norm": 8.367533683776855, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 7.8652, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0002451590108554968, | |
| "grad_norm": 8.038274765014648, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 5.8632, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00025958012914111423, | |
| "grad_norm": 7.587454795837402, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 5.6483, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0002740012474267317, | |
| "grad_norm": 7.905844688415527, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 6.3027, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00028842236571234917, | |
| "grad_norm": 7.693328380584717, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 6.7746, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00028842236571234917, | |
| "eval_loss": 1.5233994722366333, | |
| "eval_runtime": 4086.5435, | |
| "eval_samples_per_second": 7.145, | |
| "eval_steps_per_second": 3.572, | |
| "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": 597531285258240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |