| { | |
| "best_metric": 2.8416030406951904, | |
| "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": 1.4890468120574951, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6365, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07441860465116279, | |
| "eval_loss": 3.9355320930480957, | |
| "eval_runtime": 4.7179, | |
| "eval_samples_per_second": 19.288, | |
| "eval_steps_per_second": 2.544, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14883720930232558, | |
| "grad_norm": 1.5340938568115234, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7887, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.22325581395348837, | |
| "grad_norm": 1.9364389181137085, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 4.1062, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.29767441860465116, | |
| "grad_norm": 1.6120408773422241, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 3.3304, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 1.4697085618972778, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 3.3136, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.44651162790697674, | |
| "grad_norm": 1.4474133253097534, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 3.235, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5209302325581395, | |
| "grad_norm": 1.021986484527588, | |
| "learning_rate": 9.599897218294122e-05, | |
| "loss": 3.1347, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5953488372093023, | |
| "grad_norm": 0.8347269892692566, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 3.0038, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6697674418604651, | |
| "grad_norm": 0.9195536375045776, | |
| "learning_rate": 9.225950427718975e-05, | |
| "loss": 3.1287, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 0.7903404235839844, | |
| "learning_rate": 8.997213817017507e-05, | |
| "loss": 3.0327, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8186046511627907, | |
| "grad_norm": 0.5979586839675903, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 2.9139, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8930232558139535, | |
| "grad_norm": 0.6653117537498474, | |
| "learning_rate": 8.463621767547998e-05, | |
| "loss": 2.9011, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9674418604651163, | |
| "grad_norm": 0.8118610978126526, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 3.1099, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0465116279069768, | |
| "grad_norm": 1.105678677558899, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 4.8536, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1209302325581396, | |
| "grad_norm": 0.7873435020446777, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.6658, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1953488372093024, | |
| "grad_norm": 0.918388307094574, | |
| "learning_rate": 7.143462807015271e-05, | |
| "loss": 2.889, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2697674418604652, | |
| "grad_norm": 0.7034196853637695, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 2.5797, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.344186046511628, | |
| "grad_norm": 0.7909281253814697, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 2.8715, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4186046511627908, | |
| "grad_norm": 0.8187082409858704, | |
| "learning_rate": 6.0001284688802226e-05, | |
| "loss": 2.7232, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4930232558139536, | |
| "grad_norm": 0.7360689043998718, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 2.363, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5674418604651161, | |
| "grad_norm": 0.8096981048583984, | |
| "learning_rate": 5.201329700547076e-05, | |
| "loss": 3.0653, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.6418604651162791, | |
| "grad_norm": 0.9424793720245361, | |
| "learning_rate": 4.798670299452926e-05, | |
| "loss": 2.7602, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.7162790697674417, | |
| "grad_norm": 0.7494408488273621, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 2.145, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.7906976744186047, | |
| "grad_norm": 0.7966036796569824, | |
| "learning_rate": 3.9998715311197785e-05, | |
| "loss": 3.2073, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8651162790697673, | |
| "grad_norm": 0.982150673866272, | |
| "learning_rate": 3.608912680417737e-05, | |
| "loss": 2.649, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8651162790697673, | |
| "eval_loss": 2.8416030406951904, | |
| "eval_runtime": 4.7173, | |
| "eval_samples_per_second": 19.291, | |
| "eval_steps_per_second": 2.544, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9395348837209303, | |
| "grad_norm": 1.3147518634796143, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 2.8061, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.0186046511627906, | |
| "grad_norm": 1.0044997930526733, | |
| "learning_rate": 2.8565371929847284e-05, | |
| "loss": 4.262, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.0930232558139537, | |
| "grad_norm": 0.6567540168762207, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.4335, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.167441860465116, | |
| "grad_norm": 0.7161814570426941, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 2.6255, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.2418604651162792, | |
| "grad_norm": 0.6859881281852722, | |
| "learning_rate": 1.837773122023114e-05, | |
| "loss": 2.2539, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.316279069767442, | |
| "grad_norm": 0.6596910357475281, | |
| "learning_rate": 1.536378232452003e-05, | |
| "loss": 2.9981, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.390697674418605, | |
| "grad_norm": 0.8064484000205994, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 2.6408, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.4651162790697674, | |
| "grad_norm": 0.6943879127502441, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 2.3235, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.5395348837209304, | |
| "grad_norm": 0.6679330468177795, | |
| "learning_rate": 7.740495722810271e-06, | |
| "loss": 2.8428, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.613953488372093, | |
| "grad_norm": 0.7221952676773071, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 2.5881, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.688372093023256, | |
| "grad_norm": 0.6440845727920532, | |
| "learning_rate": 4.001027817058789e-06, | |
| "loss": 2.4293, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.7627906976744185, | |
| "grad_norm": 0.7320359349250793, | |
| "learning_rate": 2.573177902642726e-06, | |
| "loss": 2.7737, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.8372093023255816, | |
| "grad_norm": 0.7235525250434875, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 2.5904, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.911627906976744, | |
| "grad_norm": 0.897057294845581, | |
| "learning_rate": 6.474868681043578e-07, | |
| "loss": 2.5468, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.986046511627907, | |
| "grad_norm": 1.5236244201660156, | |
| "learning_rate": 1.6213459328950352e-07, | |
| "loss": 3.9375, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0651162790697675, | |
| "grad_norm": 0.9568150043487549, | |
| "learning_rate": 0.0, | |
| "loss": 2.9471, | |
| "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": 8.71444728304894e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |