VERSIL91's picture
Training in progress, step 5, checkpoint
67573aa verified
raw
history blame
2.18 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.00269414696571698,
"eval_steps": 2,
"global_step": 5,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000538829393143396,
"grad_norm": 0.2517673969268799,
"learning_rate": 1e-05,
"loss": 0.9506,
"step": 1
},
{
"epoch": 0.000538829393143396,
"eval_loss": 1.0077859163284302,
"eval_runtime": 644.6127,
"eval_samples_per_second": 4.849,
"eval_steps_per_second": 2.425,
"step": 1
},
{
"epoch": 0.001077658786286792,
"grad_norm": 0.24370533227920532,
"learning_rate": 2e-05,
"loss": 0.9556,
"step": 2
},
{
"epoch": 0.001077658786286792,
"eval_loss": 1.0062007904052734,
"eval_runtime": 411.3681,
"eval_samples_per_second": 7.599,
"eval_steps_per_second": 3.8,
"step": 2
},
{
"epoch": 0.0016164881794301878,
"grad_norm": 0.25933781266212463,
"learning_rate": 3e-05,
"loss": 1.0322,
"step": 3
},
{
"epoch": 0.002155317572573584,
"grad_norm": 0.26956185698509216,
"learning_rate": 4e-05,
"loss": 1.0156,
"step": 4
},
{
"epoch": 0.002155317572573584,
"eval_loss": 0.9972379207611084,
"eval_runtime": 402.5204,
"eval_samples_per_second": 7.766,
"eval_steps_per_second": 3.883,
"step": 4
},
{
"epoch": 0.00269414696571698,
"grad_norm": 0.2507219612598419,
"learning_rate": 5e-05,
"loss": 0.9816,
"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": 8209574469304320.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}