|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9937888198757764, |
|
"eval_steps": 500, |
|
"global_step": 80, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.012422360248447204, |
|
"grad_norm": 2.1266329288482666, |
|
"learning_rate": 2.5e-05, |
|
"loss": 4.2081, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.062111801242236024, |
|
"grad_norm": 2.5932071208953857, |
|
"learning_rate": 0.000125, |
|
"loss": 4.1269, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.12422360248447205, |
|
"grad_norm": 3.8309450149536133, |
|
"learning_rate": 0.00019961946980917456, |
|
"loss": 3.5809, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.18633540372670807, |
|
"grad_norm": 3.414670944213867, |
|
"learning_rate": 0.0001953716950748227, |
|
"loss": 2.7605, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.2484472049689441, |
|
"grad_norm": 2.252514600753784, |
|
"learning_rate": 0.00018660254037844388, |
|
"loss": 2.1617, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.3105590062111801, |
|
"grad_norm": 1.244139552116394, |
|
"learning_rate": 0.0001737277336810124, |
|
"loss": 1.7502, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.37267080745341613, |
|
"grad_norm": 0.6513166427612305, |
|
"learning_rate": 0.0001573576436351046, |
|
"loss": 1.457, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.43478260869565216, |
|
"grad_norm": 0.5247058272361755, |
|
"learning_rate": 0.000138268343236509, |
|
"loss": 1.2956, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.4968944099378882, |
|
"grad_norm": 0.3719463050365448, |
|
"learning_rate": 0.00011736481776669306, |
|
"loss": 1.1919, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.5590062111801242, |
|
"grad_norm": 0.31174135208129883, |
|
"learning_rate": 9.563806126346642e-05, |
|
"loss": 1.1399, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.6211180124223602, |
|
"grad_norm": 0.2663726508617401, |
|
"learning_rate": 7.411809548974792e-05, |
|
"loss": 1.1075, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.6832298136645962, |
|
"grad_norm": 0.2559656798839569, |
|
"learning_rate": 5.382513867649663e-05, |
|
"loss": 1.0894, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.7453416149068323, |
|
"grad_norm": 0.25429072976112366, |
|
"learning_rate": 3.5721239031346066e-05, |
|
"loss": 1.0851, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.8074534161490683, |
|
"grad_norm": 0.21603497862815857, |
|
"learning_rate": 2.0664665970876496e-05, |
|
"loss": 1.0719, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.8695652173913043, |
|
"grad_norm": 0.2722736895084381, |
|
"learning_rate": 9.369221296335006e-06, |
|
"loss": 1.0704, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.9316770186335404, |
|
"grad_norm": 0.22295545041561127, |
|
"learning_rate": 2.3703992880066638e-06, |
|
"loss": 1.0754, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.9937888198757764, |
|
"grad_norm": 0.2400663048028946, |
|
"learning_rate": 0.0, |
|
"loss": 1.0723, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.9937888198757764, |
|
"eval_loss": 1.4633597135543823, |
|
"eval_runtime": 2.2596, |
|
"eval_samples_per_second": 4.868, |
|
"eval_steps_per_second": 0.443, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.9937888198757764, |
|
"step": 80, |
|
"total_flos": 1.617984821877801e+18, |
|
"train_loss": 1.690801477432251, |
|
"train_runtime": 1102.9963, |
|
"train_samples_per_second": 37.273, |
|
"train_steps_per_second": 0.073 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 80, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.617984821877801e+18, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|