63 lines
1.6 KiB
JSON
63 lines
1.6 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.33472803347280333,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 20,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.16736401673640167,
|
||
|
|
"grad_norm": 1.0720182657241821,
|
||
|
|
"learning_rate": 1.993822843360249e-05,
|
||
|
|
"loss": 1.6067840576171875,
|
||
|
|
"memory/device_reserved (GiB)": 33.31,
|
||
|
|
"memory/max_active (GiB)": 32.17,
|
||
|
|
"memory/max_allocated (GiB)": 32.17,
|
||
|
|
"ppl": 4.98675,
|
||
|
|
"step": 10,
|
||
|
|
"tokens/total": 3932160,
|
||
|
|
"tokens/train_per_sec_per_gpu": 16.35,
|
||
|
|
"tokens/trainable": 1840181
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.33472803347280333,
|
||
|
|
"grad_norm": 0.36571913957595825,
|
||
|
|
"learning_rate": 1.925203832797706e-05,
|
||
|
|
"loss": 1.4119406700134278,
|
||
|
|
"memory/device_reserved (GiB)": 33.31,
|
||
|
|
"memory/max_active (GiB)": 32.17,
|
||
|
|
"memory/max_allocated (GiB)": 32.17,
|
||
|
|
"ppl": 4.10391,
|
||
|
|
"step": 20,
|
||
|
|
"tokens/total": 7864320,
|
||
|
|
"tokens/train_per_sec_per_gpu": 17.64,
|
||
|
|
"tokens/trainable": 3698601
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 10,
|
||
|
|
"max_steps": 118,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 2,
|
||
|
|
"save_steps": 20,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 3.612412220748595e+17,
|
||
|
|
"train_batch_size": 8,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|