| { | |
| "best_metric": 6.91409969329834, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.012340346763744061, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004936138705497624, | |
| "grad_norm": 0.1294831931591034, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 6.9388, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004936138705497624, | |
| "eval_loss": 6.934586048126221, | |
| "eval_runtime": 0.0792, | |
| "eval_samples_per_second": 631.199, | |
| "eval_steps_per_second": 164.112, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009872277410995249, | |
| "grad_norm": 0.1353587508201599, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 6.9381, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014808416116492873, | |
| "grad_norm": 0.14798350632190704, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9389, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019744554821990497, | |
| "grad_norm": 0.14640209078788757, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 6.9363, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002468069352748812, | |
| "grad_norm": 0.14401522278785706, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 6.938, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029616832232985746, | |
| "grad_norm": 0.14567096531391144, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 6.9357, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003455297093848337, | |
| "grad_norm": 0.1365479975938797, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 6.9338, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0039489109643980995, | |
| "grad_norm": 0.13593412935733795, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 6.9351, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004442524834947862, | |
| "grad_norm": 0.13452042639255524, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 6.933, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004936138705497624, | |
| "grad_norm": 0.1374937891960144, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 6.9336, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005429752576047387, | |
| "grad_norm": 0.13684473931789398, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 6.9338, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005923366446597149, | |
| "grad_norm": 0.14771386981010437, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 6.9308, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006416980317146912, | |
| "grad_norm": 0.1428656429052353, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 6.931, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006910594187696674, | |
| "grad_norm": 0.14314448833465576, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 6.9295, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007404208058246437, | |
| "grad_norm": 0.1460285633802414, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 6.9304, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007897821928796199, | |
| "grad_norm": 0.14801424741744995, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 6.9296, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008391435799345962, | |
| "grad_norm": 0.15197831392288208, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 6.9251, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008885049669895725, | |
| "grad_norm": 0.14863520860671997, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 6.9282, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009378663540445486, | |
| "grad_norm": 0.13960832357406616, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 6.9281, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009872277410995249, | |
| "grad_norm": 0.1437833458185196, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 6.9249, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010365891281545012, | |
| "grad_norm": 0.1537475436925888, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 6.9223, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010859505152094774, | |
| "grad_norm": 0.1554909348487854, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 6.9201, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011353119022644536, | |
| "grad_norm": 0.15719279646873474, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 6.9213, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011846732893194298, | |
| "grad_norm": 0.15599289536476135, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 6.9211, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012340346763744061, | |
| "grad_norm": 0.16797839105129242, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 6.9162, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012340346763744061, | |
| "eval_loss": 6.91409969329834, | |
| "eval_runtime": 0.0843, | |
| "eval_samples_per_second": 593.267, | |
| "eval_steps_per_second": 154.249, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "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": 2852978688000.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |