|
{ |
|
"best_metric": 3.499747981550172e-05, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.12403100775193798, |
|
"eval_steps": 25, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00496124031007752, |
|
"grad_norm": 23.23585319519043, |
|
"learning_rate": 5e-05, |
|
"loss": 11.3401, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00496124031007752, |
|
"eval_loss": 10.861466407775879, |
|
"eval_runtime": 34.401, |
|
"eval_samples_per_second": 39.476, |
|
"eval_steps_per_second": 4.942, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00992248062015504, |
|
"grad_norm": 24.292354583740234, |
|
"learning_rate": 0.0001, |
|
"loss": 10.9325, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.014883720930232559, |
|
"grad_norm": 22.498645782470703, |
|
"learning_rate": 9.989294616193017e-05, |
|
"loss": 10.2178, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.01984496124031008, |
|
"grad_norm": 17.426952362060547, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 7.1054, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.024806201550387597, |
|
"grad_norm": 14.538772583007812, |
|
"learning_rate": 9.903926402016153e-05, |
|
"loss": 5.0699, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.029767441860465118, |
|
"grad_norm": 13.055420875549316, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 3.4166, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.03472868217054263, |
|
"grad_norm": 12.215715408325195, |
|
"learning_rate": 9.73465064747553e-05, |
|
"loss": 1.9664, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.03968992248062016, |
|
"grad_norm": 7.951274394989014, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.7269, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.044651162790697675, |
|
"grad_norm": 1.9474599361419678, |
|
"learning_rate": 9.484363707663442e-05, |
|
"loss": 0.1395, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.04961240310077519, |
|
"grad_norm": 0.40482786297798157, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 0.0241, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.05457364341085271, |
|
"grad_norm": 0.06929321587085724, |
|
"learning_rate": 9.157348061512727e-05, |
|
"loss": 0.0042, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.059534883720930236, |
|
"grad_norm": 0.0293231550604105, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 0.0016, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.06449612403100775, |
|
"grad_norm": 0.012703669257462025, |
|
"learning_rate": 8.759199037394887e-05, |
|
"loss": 0.0007, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.06945736434108526, |
|
"grad_norm": 0.006540760863572359, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.0003, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.07441860465116279, |
|
"grad_norm": 0.004683414474129677, |
|
"learning_rate": 8.296729075500344e-05, |
|
"loss": 0.0002, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.07937984496124031, |
|
"grad_norm": 0.003430376062169671, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 0.0001, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.08434108527131783, |
|
"grad_norm": 0.003030678490176797, |
|
"learning_rate": 7.777851165098012e-05, |
|
"loss": 0.0001, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.08930232558139535, |
|
"grad_norm": 0.0023646620102226734, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 0.0001, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.09426356589147286, |
|
"grad_norm": 0.002618241822347045, |
|
"learning_rate": 7.211443451095007e-05, |
|
"loss": 0.0001, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.09922480620155039, |
|
"grad_norm": 0.0019350913353264332, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.0001, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.10418604651162791, |
|
"grad_norm": 0.001895522465929389, |
|
"learning_rate": 6.607197326515808e-05, |
|
"loss": 0.0001, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.10914728682170542, |
|
"grad_norm": 0.0017253287369385362, |
|
"learning_rate": 6.294095225512603e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.11410852713178295, |
|
"grad_norm": 0.001647541648708284, |
|
"learning_rate": 5.9754516100806423e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.11906976744186047, |
|
"grad_norm": 0.0016631092876195908, |
|
"learning_rate": 5.6526309611002594e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.12403100775193798, |
|
"grad_norm": 0.002164131496101618, |
|
"learning_rate": 5.327015646150716e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.12403100775193798, |
|
"eval_loss": 3.499747981550172e-05, |
|
"eval_runtime": 34.3197, |
|
"eval_samples_per_second": 39.569, |
|
"eval_steps_per_second": 4.953, |
|
"step": 25 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 50, |
|
"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": 5.29768176943104e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|