|
{ |
|
"best_metric": 0.4165593981742859, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.8733624454148472, |
|
"eval_steps": 50, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.017467248908296942, |
|
"grad_norm": 1.0150203704833984, |
|
"learning_rate": 1e-05, |
|
"loss": 0.7291, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.017467248908296942, |
|
"eval_loss": 1.4666682481765747, |
|
"eval_runtime": 2.9027, |
|
"eval_samples_per_second": 33.417, |
|
"eval_steps_per_second": 8.613, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.034934497816593885, |
|
"grad_norm": 1.6312181949615479, |
|
"learning_rate": 2e-05, |
|
"loss": 0.9125, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.05240174672489083, |
|
"grad_norm": 1.6606181859970093, |
|
"learning_rate": 3e-05, |
|
"loss": 1.0164, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.06986899563318777, |
|
"grad_norm": 1.8427821397781372, |
|
"learning_rate": 4e-05, |
|
"loss": 1.1878, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.08733624454148471, |
|
"grad_norm": 1.8938854932785034, |
|
"learning_rate": 5e-05, |
|
"loss": 1.0719, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.10480349344978165, |
|
"grad_norm": 1.6704180240631104, |
|
"learning_rate": 6e-05, |
|
"loss": 1.1482, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.1222707423580786, |
|
"grad_norm": 1.6908645629882812, |
|
"learning_rate": 7e-05, |
|
"loss": 0.9746, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.13973799126637554, |
|
"grad_norm": 1.744346261024475, |
|
"learning_rate": 8e-05, |
|
"loss": 1.1686, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.1572052401746725, |
|
"grad_norm": 1.9767279624938965, |
|
"learning_rate": 9e-05, |
|
"loss": 1.0338, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.17467248908296942, |
|
"grad_norm": 1.2403647899627686, |
|
"learning_rate": 0.0001, |
|
"loss": 0.895, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.19213973799126638, |
|
"grad_norm": 2.6359500885009766, |
|
"learning_rate": 9.999059852242507e-05, |
|
"loss": 0.9552, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.2096069868995633, |
|
"grad_norm": 1.7321456670761108, |
|
"learning_rate": 9.996239762521151e-05, |
|
"loss": 1.127, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.22707423580786026, |
|
"grad_norm": 2.320572853088379, |
|
"learning_rate": 9.991540791356342e-05, |
|
"loss": 1.1839, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.2445414847161572, |
|
"grad_norm": 2.7635228633880615, |
|
"learning_rate": 9.98496470583896e-05, |
|
"loss": 1.1559, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.26200873362445415, |
|
"grad_norm": 0.8590458035469055, |
|
"learning_rate": 9.976513978965829e-05, |
|
"loss": 0.6596, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.2794759825327511, |
|
"grad_norm": 1.0409654378890991, |
|
"learning_rate": 9.966191788709716e-05, |
|
"loss": 0.6509, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.29694323144104806, |
|
"grad_norm": 0.8696012496948242, |
|
"learning_rate": 9.954002016824227e-05, |
|
"loss": 0.7372, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.314410480349345, |
|
"grad_norm": 0.9967894554138184, |
|
"learning_rate": 9.939949247384046e-05, |
|
"loss": 0.6979, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.3318777292576419, |
|
"grad_norm": 0.8892637491226196, |
|
"learning_rate": 9.924038765061042e-05, |
|
"loss": 0.7706, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.34934497816593885, |
|
"grad_norm": 0.9137187004089355, |
|
"learning_rate": 9.906276553136923e-05, |
|
"loss": 0.7256, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.36681222707423583, |
|
"grad_norm": 1.0746030807495117, |
|
"learning_rate": 9.88666929125318e-05, |
|
"loss": 0.7775, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.38427947598253276, |
|
"grad_norm": 1.112693428993225, |
|
"learning_rate": 9.865224352899119e-05, |
|
"loss": 0.7126, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.4017467248908297, |
|
"grad_norm": 1.1786601543426514, |
|
"learning_rate": 9.84194980263903e-05, |
|
"loss": 0.7844, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.4192139737991266, |
|
"grad_norm": 1.3309204578399658, |
|
"learning_rate": 9.816854393079403e-05, |
|
"loss": 0.8217, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.4366812227074236, |
|
"grad_norm": 1.180550217628479, |
|
"learning_rate": 9.789947561577445e-05, |
|
"loss": 0.7397, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.45414847161572053, |
|
"grad_norm": 1.602713942527771, |
|
"learning_rate": 9.761239426692077e-05, |
|
"loss": 0.8979, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.47161572052401746, |
|
"grad_norm": 1.7447450160980225, |
|
"learning_rate": 9.730740784378753e-05, |
|
"loss": 0.8654, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.4890829694323144, |
|
"grad_norm": 2.8003647327423096, |
|
"learning_rate": 9.698463103929542e-05, |
|
"loss": 0.8954, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.5065502183406113, |
|
"grad_norm": 0.5731148719787598, |
|
"learning_rate": 9.664418523660004e-05, |
|
"loss": 0.5257, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.5240174672489083, |
|
"grad_norm": 0.7524777054786682, |
|
"learning_rate": 9.628619846344454e-05, |
|
"loss": 0.4996, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.5414847161572053, |
|
"grad_norm": 0.931867778301239, |
|
"learning_rate": 9.591080534401371e-05, |
|
"loss": 0.6164, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.5589519650655022, |
|
"grad_norm": 0.7929329872131348, |
|
"learning_rate": 9.551814704830734e-05, |
|
"loss": 0.6483, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.5764192139737991, |
|
"grad_norm": 0.7793125510215759, |
|
"learning_rate": 9.51083712390519e-05, |
|
"loss": 0.5689, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.5938864628820961, |
|
"grad_norm": 0.8453607559204102, |
|
"learning_rate": 9.468163201617062e-05, |
|
"loss": 0.546, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.611353711790393, |
|
"grad_norm": 0.9560432434082031, |
|
"learning_rate": 9.423808985883289e-05, |
|
"loss": 0.6277, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.62882096069869, |
|
"grad_norm": 1.192608118057251, |
|
"learning_rate": 9.377791156510455e-05, |
|
"loss": 0.6021, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.6462882096069869, |
|
"grad_norm": 0.9529364109039307, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 0.5185, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.6637554585152838, |
|
"grad_norm": 1.2152981758117676, |
|
"learning_rate": 9.280834497651334e-05, |
|
"loss": 0.6219, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.6812227074235808, |
|
"grad_norm": 1.2711488008499146, |
|
"learning_rate": 9.229932129599205e-05, |
|
"loss": 0.6143, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.6986899563318777, |
|
"grad_norm": 1.4244954586029053, |
|
"learning_rate": 9.177439057064683e-05, |
|
"loss": 0.7323, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.7161572052401747, |
|
"grad_norm": 1.7837212085723877, |
|
"learning_rate": 9.123375020545535e-05, |
|
"loss": 0.6341, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.7336244541484717, |
|
"grad_norm": 1.9221779108047485, |
|
"learning_rate": 9.067760351314838e-05, |
|
"loss": 0.8552, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.7510917030567685, |
|
"grad_norm": 0.7614825367927551, |
|
"learning_rate": 9.01061596377522e-05, |
|
"loss": 0.4449, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.7685589519650655, |
|
"grad_norm": 0.8698350191116333, |
|
"learning_rate": 8.951963347593797e-05, |
|
"loss": 0.468, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.7860262008733624, |
|
"grad_norm": 0.7544025182723999, |
|
"learning_rate": 8.891824559620801e-05, |
|
"loss": 0.4263, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.8034934497816594, |
|
"grad_norm": 1.096413493156433, |
|
"learning_rate": 8.83022221559489e-05, |
|
"loss": 0.5457, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.8209606986899564, |
|
"grad_norm": 0.8501629829406738, |
|
"learning_rate": 8.767179481638303e-05, |
|
"loss": 0.4508, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.8384279475982532, |
|
"grad_norm": 0.9768447875976562, |
|
"learning_rate": 8.702720065545024e-05, |
|
"loss": 0.4, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.8558951965065502, |
|
"grad_norm": 1.1103242635726929, |
|
"learning_rate": 8.636868207865244e-05, |
|
"loss": 0.4616, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.8733624454148472, |
|
"grad_norm": 1.2032922506332397, |
|
"learning_rate": 8.569648672789497e-05, |
|
"loss": 0.3951, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.8733624454148472, |
|
"eval_loss": 0.4165593981742859, |
|
"eval_runtime": 2.92, |
|
"eval_samples_per_second": 33.219, |
|
"eval_steps_per_second": 8.562, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 172, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 5, |
|
"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": 1.381134508228608e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|