| { | |
| "best_metric": 3.2546098232269287, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0651162790697675, | |
| "eval_steps": 25, | |
| "global_step": 41, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07441860465116279, | |
| "grad_norm": 2.020779609680176, | |
| "learning_rate": 5e-05, | |
| "loss": 4.1328, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07441860465116279, | |
| "eval_loss": 4.533937931060791, | |
| "eval_runtime": 1.7261, | |
| "eval_samples_per_second": 52.72, | |
| "eval_steps_per_second": 6.952, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14883720930232558, | |
| "grad_norm": 2.7467870712280273, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4258, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.22325581395348837, | |
| "grad_norm": 2.7919416427612305, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 4.792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.29767441860465116, | |
| "grad_norm": 1.701142430305481, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 3.9521, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 1.7278472185134888, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 4.0736, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.44651162790697674, | |
| "grad_norm": 1.9098764657974243, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 4.1726, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5209302325581395, | |
| "grad_norm": 1.3584764003753662, | |
| "learning_rate": 9.599897218294122e-05, | |
| "loss": 3.8425, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5953488372093023, | |
| "grad_norm": 1.167802095413208, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 3.6163, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6697674418604651, | |
| "grad_norm": 1.3454344272613525, | |
| "learning_rate": 9.225950427718975e-05, | |
| "loss": 3.883, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 1.2075648307800293, | |
| "learning_rate": 8.997213817017507e-05, | |
| "loss": 3.8244, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8186046511627907, | |
| "grad_norm": 1.0436967611312866, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 3.5138, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8930232558139535, | |
| "grad_norm": 1.1808282136917114, | |
| "learning_rate": 8.463621767547998e-05, | |
| "loss": 3.5784, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9674418604651163, | |
| "grad_norm": 1.4680527448654175, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 3.7168, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0465116279069768, | |
| "grad_norm": 1.8288421630859375, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 5.6196, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1209302325581396, | |
| "grad_norm": 3.125596284866333, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.1786, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1953488372093024, | |
| "grad_norm": 1.9149749279022217, | |
| "learning_rate": 7.143462807015271e-05, | |
| "loss": 3.3919, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2697674418604652, | |
| "grad_norm": 1.4515650272369385, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 3.0889, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.344186046511628, | |
| "grad_norm": 1.6954460144042969, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 3.311, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4186046511627908, | |
| "grad_norm": 1.7925573587417603, | |
| "learning_rate": 6.0001284688802226e-05, | |
| "loss": 3.3055, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4930232558139536, | |
| "grad_norm": 1.7305032014846802, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 2.6646, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5674418604651161, | |
| "grad_norm": 1.7365140914916992, | |
| "learning_rate": 5.201329700547076e-05, | |
| "loss": 3.674, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.6418604651162791, | |
| "grad_norm": 1.725070834159851, | |
| "learning_rate": 4.798670299452926e-05, | |
| "loss": 3.1755, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.7162790697674417, | |
| "grad_norm": 1.5631095170974731, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 2.7024, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.7906976744186047, | |
| "grad_norm": 15.420148849487305, | |
| "learning_rate": 3.9998715311197785e-05, | |
| "loss": 3.6947, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8651162790697673, | |
| "grad_norm": 1.6800768375396729, | |
| "learning_rate": 3.608912680417737e-05, | |
| "loss": 3.1303, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8651162790697673, | |
| "eval_loss": 3.2546098232269287, | |
| "eval_runtime": 1.7251, | |
| "eval_samples_per_second": 52.752, | |
| "eval_steps_per_second": 6.956, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9395348837209303, | |
| "grad_norm": 2.245436191558838, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 3.2327, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.0186046511627906, | |
| "grad_norm": 2.354249954223633, | |
| "learning_rate": 2.8565371929847284e-05, | |
| "loss": 5.0536, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.0930232558139537, | |
| "grad_norm": 1.1819117069244385, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.0264, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.167441860465116, | |
| "grad_norm": 1.337063193321228, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 3.1343, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.2418604651162792, | |
| "grad_norm": 1.1551506519317627, | |
| "learning_rate": 1.837773122023114e-05, | |
| "loss": 2.6179, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.316279069767442, | |
| "grad_norm": 1.2832993268966675, | |
| "learning_rate": 1.536378232452003e-05, | |
| "loss": 3.5282, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.390697674418605, | |
| "grad_norm": 1.2016886472702026, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 3.0694, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.4651162790697674, | |
| "grad_norm": 1.090936541557312, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 2.6476, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.5395348837209304, | |
| "grad_norm": 1.5232198238372803, | |
| "learning_rate": 7.740495722810271e-06, | |
| "loss": 3.3762, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.613953488372093, | |
| "grad_norm": 1.120077133178711, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 2.9806, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.688372093023256, | |
| "grad_norm": 1.069722056388855, | |
| "learning_rate": 4.001027817058789e-06, | |
| "loss": 2.9037, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.7627906976744185, | |
| "grad_norm": 1.2132554054260254, | |
| "learning_rate": 2.573177902642726e-06, | |
| "loss": 3.2992, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.8372093023255816, | |
| "grad_norm": 1.175353765487671, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 2.9901, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.911627906976744, | |
| "grad_norm": 1.4980123043060303, | |
| "learning_rate": 6.474868681043578e-07, | |
| "loss": 3.1414, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.986046511627907, | |
| "grad_norm": 2.204864501953125, | |
| "learning_rate": 1.6213459328950352e-07, | |
| "loss": 4.5125, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0651162790697675, | |
| "grad_norm": 1.5250720977783203, | |
| "learning_rate": 0.0, | |
| "loss": 3.4608, | |
| "step": 41 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 41, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.827986893480919e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |