|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.0, |
|
"eval_steps": 500, |
|
"global_step": 250, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_bleu": 29.3664, |
|
"eval_gen_len": 17.87, |
|
"eval_loss": 1.15119206905365, |
|
"eval_runtime": 3.6787, |
|
"eval_samples_per_second": 27.183, |
|
"eval_steps_per_second": 1.903, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_bleu": 30.2245, |
|
"eval_gen_len": 17.76, |
|
"eval_loss": 1.1138919591903687, |
|
"eval_runtime": 1.8963, |
|
"eval_samples_per_second": 52.735, |
|
"eval_steps_per_second": 3.691, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_bleu": 31.9604, |
|
"eval_gen_len": 17.82, |
|
"eval_loss": 1.1345570087432861, |
|
"eval_runtime": 1.9984, |
|
"eval_samples_per_second": 50.041, |
|
"eval_steps_per_second": 3.503, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_bleu": 31.4164, |
|
"eval_gen_len": 17.79, |
|
"eval_loss": 1.126845359802246, |
|
"eval_runtime": 1.955, |
|
"eval_samples_per_second": 51.15, |
|
"eval_steps_per_second": 3.58, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_bleu": 31.8755, |
|
"eval_gen_len": 17.77, |
|
"eval_loss": 1.1333471536636353, |
|
"eval_runtime": 1.9533, |
|
"eval_samples_per_second": 51.195, |
|
"eval_steps_per_second": 3.584, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_bleu": 31.3738, |
|
"eval_gen_len": 17.82, |
|
"eval_loss": 1.1576088666915894, |
|
"eval_runtime": 2.0286, |
|
"eval_samples_per_second": 49.295, |
|
"eval_steps_per_second": 3.451, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_bleu": 31.8092, |
|
"eval_gen_len": 17.79, |
|
"eval_loss": 1.1782827377319336, |
|
"eval_runtime": 1.9407, |
|
"eval_samples_per_second": 51.528, |
|
"eval_steps_per_second": 3.607, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_bleu": 31.7817, |
|
"eval_gen_len": 17.75, |
|
"eval_loss": 1.194524884223938, |
|
"eval_runtime": 1.9062, |
|
"eval_samples_per_second": 52.461, |
|
"eval_steps_per_second": 3.672, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_bleu": 31.3188, |
|
"eval_gen_len": 17.75, |
|
"eval_loss": 1.1944379806518555, |
|
"eval_runtime": 2.2173, |
|
"eval_samples_per_second": 45.099, |
|
"eval_steps_per_second": 3.157, |
|
"step": 225 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"save_steps": 50, |
|
"total_flos": 70817597620224.0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|