|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.06730171878235659, |
|
"eval_steps": 25, |
|
"global_step": 325, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0051770552909505075, |
|
"grad_norm": 6.5560479164123535, |
|
"learning_rate": 2.3797595190380762e-05, |
|
"loss": 2.3718, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.0051770552909505075, |
|
"eval_loss": 2.1950066089630127, |
|
"eval_runtime": 22606.8976, |
|
"eval_samples_per_second": 0.427, |
|
"eval_steps_per_second": 0.053, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.010354110581901015, |
|
"grad_norm": 6.057673454284668, |
|
"learning_rate": 2.2545090180360722e-05, |
|
"loss": 2.1371, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.010354110581901015, |
|
"eval_loss": 2.0699515342712402, |
|
"eval_runtime": 22610.0414, |
|
"eval_samples_per_second": 0.427, |
|
"eval_steps_per_second": 0.053, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.015531165872851522, |
|
"grad_norm": 8.709203720092773, |
|
"learning_rate": 2.1292585170340683e-05, |
|
"loss": 2.029, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.015531165872851522, |
|
"eval_loss": 1.951442837715149, |
|
"eval_runtime": 22577.4979, |
|
"eval_samples_per_second": 0.428, |
|
"eval_steps_per_second": 0.054, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.02070822116380203, |
|
"grad_norm": 9.000727653503418, |
|
"learning_rate": 2.0040080160320643e-05, |
|
"loss": 1.9957, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.02070822116380203, |
|
"eval_loss": 1.8961551189422607, |
|
"eval_runtime": 22614.8229, |
|
"eval_samples_per_second": 0.427, |
|
"eval_steps_per_second": 0.053, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.025885276454752536, |
|
"grad_norm": 9.183732032775879, |
|
"learning_rate": 1.87875751503006e-05, |
|
"loss": 1.9914, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.025885276454752536, |
|
"eval_loss": 1.862902045249939, |
|
"eval_runtime": 22598.368, |
|
"eval_samples_per_second": 0.427, |
|
"eval_steps_per_second": 0.053, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.031062331745703043, |
|
"grad_norm": 9.752124786376953, |
|
"learning_rate": 1.7535070140280564e-05, |
|
"loss": 1.9101, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.031062331745703043, |
|
"eval_loss": 1.8291873931884766, |
|
"eval_runtime": 22569.5842, |
|
"eval_samples_per_second": 0.428, |
|
"eval_steps_per_second": 0.054, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.03623938703665355, |
|
"grad_norm": 10.182242393493652, |
|
"learning_rate": 1.628256513026052e-05, |
|
"loss": 1.9184, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.03623938703665355, |
|
"eval_loss": 1.8157259225845337, |
|
"eval_runtime": 22567.2098, |
|
"eval_samples_per_second": 0.428, |
|
"eval_steps_per_second": 0.054, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.04141644232760406, |
|
"grad_norm": 14.267326354980469, |
|
"learning_rate": 1.5030060120240483e-05, |
|
"loss": 1.7737, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.04141644232760406, |
|
"eval_loss": 1.8020907640457153, |
|
"eval_runtime": 22574.516, |
|
"eval_samples_per_second": 0.428, |
|
"eval_steps_per_second": 0.054, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.046593497618554566, |
|
"grad_norm": 15.376133918762207, |
|
"learning_rate": 1.3777555110220442e-05, |
|
"loss": 1.9049, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.046593497618554566, |
|
"eval_loss": 1.7998195886611938, |
|
"eval_runtime": 22573.5402, |
|
"eval_samples_per_second": 0.428, |
|
"eval_steps_per_second": 0.054, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.05177055290950507, |
|
"grad_norm": 10.901107788085938, |
|
"learning_rate": 1.25250501002004e-05, |
|
"loss": 1.7983, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.05177055290950507, |
|
"eval_loss": 1.7958767414093018, |
|
"eval_runtime": 22572.1299, |
|
"eval_samples_per_second": 0.428, |
|
"eval_steps_per_second": 0.054, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.05694760820045558, |
|
"grad_norm": 10.44069766998291, |
|
"learning_rate": 1.1272545090180361e-05, |
|
"loss": 1.9028, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.05694760820045558, |
|
"eval_loss": 1.7843998670578003, |
|
"eval_runtime": 22570.5162, |
|
"eval_samples_per_second": 0.428, |
|
"eval_steps_per_second": 0.054, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.062124663491406086, |
|
"grad_norm": 7.49381685256958, |
|
"learning_rate": 1.0020040080160322e-05, |
|
"loss": 1.8265, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.062124663491406086, |
|
"eval_loss": 1.778732180595398, |
|
"eval_runtime": 22619.1506, |
|
"eval_samples_per_second": 0.427, |
|
"eval_steps_per_second": 0.053, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.06730171878235659, |
|
"grad_norm": 9.457173347473145, |
|
"learning_rate": 8.767535070140282e-06, |
|
"loss": 1.6908, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.06730171878235659, |
|
"eval_loss": 1.77461576461792, |
|
"eval_runtime": 22587.3398, |
|
"eval_samples_per_second": 0.428, |
|
"eval_steps_per_second": 0.053, |
|
"step": 325 |
|
} |
|
], |
|
"logging_steps": 25, |
|
"max_steps": 500, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 5341093036032000.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|