| { | |
| "best_metric": 0.8024803996086121, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0016218232537018116, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.487293014807247e-05, | |
| "grad_norm": 10.026896476745605, | |
| "learning_rate": 2e-05, | |
| "loss": 8.1444, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.487293014807247e-05, | |
| "eval_loss": 1.7887955904006958, | |
| "eval_runtime": 619.1708, | |
| "eval_samples_per_second": 10.483, | |
| "eval_steps_per_second": 5.242, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012974586029614494, | |
| "grad_norm": 11.966449737548828, | |
| "learning_rate": 4e-05, | |
| "loss": 7.756, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00019461879044421738, | |
| "grad_norm": 10.803685188293457, | |
| "learning_rate": 6e-05, | |
| "loss": 7.3242, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025949172059228987, | |
| "grad_norm": 6.107114315032959, | |
| "learning_rate": 8e-05, | |
| "loss": 6.4763, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003243646507403623, | |
| "grad_norm": 8.756160736083984, | |
| "learning_rate": 0.0001, | |
| "loss": 7.6339, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003243646507403623, | |
| "eval_loss": 1.638462781906128, | |
| "eval_runtime": 588.662, | |
| "eval_samples_per_second": 11.027, | |
| "eval_steps_per_second": 5.514, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00038923758088843475, | |
| "grad_norm": 6.2664055824279785, | |
| "learning_rate": 0.00012, | |
| "loss": 7.1014, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00045411051103650725, | |
| "grad_norm": 8.582403182983398, | |
| "learning_rate": 0.00014, | |
| "loss": 7.7725, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005189834411845797, | |
| "grad_norm": 6.807389736175537, | |
| "learning_rate": 0.00016, | |
| "loss": 5.4719, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005838563713326521, | |
| "grad_norm": 10.199763298034668, | |
| "learning_rate": 0.00018, | |
| "loss": 5.6342, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006487293014807246, | |
| "grad_norm": 7.018365859985352, | |
| "learning_rate": 0.0002, | |
| "loss": 5.5843, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006487293014807246, | |
| "eval_loss": 1.2051786184310913, | |
| "eval_runtime": 584.7718, | |
| "eval_samples_per_second": 11.1, | |
| "eval_steps_per_second": 5.551, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007136022316287971, | |
| "grad_norm": 8.7813720703125, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 4.5529, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0007784751617768695, | |
| "grad_norm": 6.648146152496338, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 3.6171, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.000843348091924942, | |
| "grad_norm": 7.903797149658203, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 5.3909, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0009082210220730145, | |
| "grad_norm": 7.21380090713501, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.5787, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.000973093952221087, | |
| "grad_norm": 10.915742874145508, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.9928, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000973093952221087, | |
| "eval_loss": 0.9357719421386719, | |
| "eval_runtime": 577.5688, | |
| "eval_samples_per_second": 11.238, | |
| "eval_steps_per_second": 5.62, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010379668823691595, | |
| "grad_norm": 9.467447280883789, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.6304, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0011028398125172319, | |
| "grad_norm": 7.981847286224365, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 3.9296, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0011677127426653043, | |
| "grad_norm": 11.178593635559082, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.134, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0012325856728133769, | |
| "grad_norm": 9.679515838623047, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.4975, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0012974586029614492, | |
| "grad_norm": 8.317915916442871, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.2547, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012974586029614492, | |
| "eval_loss": 0.828849196434021, | |
| "eval_runtime": 577.2763, | |
| "eval_samples_per_second": 11.244, | |
| "eval_steps_per_second": 5.623, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013623315331095216, | |
| "grad_norm": 9.708341598510742, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 4.4255, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0014272044632575942, | |
| "grad_norm": 7.934423923492432, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 3.0924, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0014920773934056666, | |
| "grad_norm": 10.388670921325684, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 2.675, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001556950323553739, | |
| "grad_norm": 9.769749641418457, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 2.0469, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0016218232537018116, | |
| "grad_norm": 7.18924617767334, | |
| "learning_rate": 0.0, | |
| "loss": 2.4988, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0016218232537018116, | |
| "eval_loss": 0.8024803996086121, | |
| "eval_runtime": 593.6732, | |
| "eval_samples_per_second": 10.934, | |
| "eval_steps_per_second": 5.468, | |
| "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": 956050056413184.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |