stuser2023's picture
Training in progress, epoch 1
80b7165 verified
raw
history blame
1.44 kB
{
"best_metric": 0.34672852642073776,
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-268",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 268,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_loss": 0.5480445623397827,
"eval_matthews_correlation": 0.1315571677438866,
"eval_runtime": 0.809,
"eval_samples_per_second": 1289.215,
"eval_steps_per_second": 81.58,
"step": 134
},
{
"epoch": 2.0,
"eval_loss": 0.528731644153595,
"eval_matthews_correlation": 0.34672852642073776,
"eval_runtime": 1.0218,
"eval_samples_per_second": 1020.75,
"eval_steps_per_second": 64.592,
"step": 268
}
],
"logging_steps": 500,
"max_steps": 268,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0,
"train_batch_size": 64,
"trial_name": null,
"trial_params": {
"learning_rate": 7.4123504722847965e-06,
"num_train_epochs": 2,
"per_device_train_batch_size": 64,
"seed": 19
}
}