stuser2023's picture
Training in progress, epoch 4
c3f3955 verified
raw
history blame
2.01 kB
{
"best_metric": 0.46849580082104064,
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-804",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 1072,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_loss": 0.5035493969917297,
"eval_matthews_correlation": 0.4141806938515634,
"eval_runtime": 0.7419,
"eval_samples_per_second": 1405.832,
"eval_steps_per_second": 88.96,
"step": 268
},
{
"epoch": 1.87,
"grad_norm": 4.896795749664307,
"learning_rate": 5.453884401804003e-06,
"loss": 0.4997,
"step": 500
},
{
"epoch": 2.0,
"eval_loss": 0.4967799484729767,
"eval_matthews_correlation": 0.44251427534495513,
"eval_runtime": 0.8433,
"eval_samples_per_second": 1236.743,
"eval_steps_per_second": 78.26,
"step": 536
},
{
"epoch": 3.0,
"eval_loss": 0.49384433031082153,
"eval_matthews_correlation": 0.46849580082104064,
"eval_runtime": 1.1521,
"eval_samples_per_second": 905.341,
"eval_steps_per_second": 57.289,
"step": 804
},
{
"epoch": 3.73,
"grad_norm": 8.912487030029297,
"learning_rate": 6.865029316956087e-07,
"loss": 0.3522,
"step": 1000
},
{
"epoch": 4.0,
"eval_loss": 0.5385918021202087,
"eval_matthews_correlation": 0.430812413056651,
"eval_runtime": 0.8323,
"eval_samples_per_second": 1253.098,
"eval_steps_per_second": 79.295,
"step": 1072
}
],
"logging_steps": 500,
"max_steps": 1072,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 192081608932020.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"learning_rate": 1.0221265871912396e-05,
"num_train_epochs": 4,
"per_device_train_batch_size": 32,
"seed": 8
}
}