VERSIL91's picture
Training in progress, step 5, checkpoint
85f553f verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0015716783560244395,
"eval_steps": 2,
"global_step": 5,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003143356712048879,
"grad_norm": 28.286949157714844,
"learning_rate": 1e-05,
"loss": 12.721,
"step": 1
},
{
"epoch": 0.0003143356712048879,
"eval_loss": 13.208134651184082,
"eval_runtime": 179.5417,
"eval_samples_per_second": 29.843,
"eval_steps_per_second": 14.921,
"step": 1
},
{
"epoch": 0.0006286713424097758,
"grad_norm": 28.09391975402832,
"learning_rate": 2e-05,
"loss": 13.5317,
"step": 2
},
{
"epoch": 0.0006286713424097758,
"eval_loss": 12.905428886413574,
"eval_runtime": 118.9136,
"eval_samples_per_second": 45.058,
"eval_steps_per_second": 22.529,
"step": 2
},
{
"epoch": 0.0009430070136146638,
"grad_norm": 28.19013214111328,
"learning_rate": 3e-05,
"loss": 12.7172,
"step": 3
},
{
"epoch": 0.0012573426848195516,
"grad_norm": 29.301204681396484,
"learning_rate": 4e-05,
"loss": 12.1527,
"step": 4
},
{
"epoch": 0.0012573426848195516,
"eval_loss": 12.0322265625,
"eval_runtime": 68.959,
"eval_samples_per_second": 77.698,
"eval_steps_per_second": 38.849,
"step": 4
},
{
"epoch": 0.0015716783560244395,
"grad_norm": 28.879608154296875,
"learning_rate": 5e-05,
"loss": 11.9569,
"step": 5
}
],
"logging_steps": 1,
"max_steps": 5,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 2,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 978955586764800.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}