model_8w0usakd / checkpoint-10 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
28d8d5c verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1,
"grad_norm": 3.034785032272339,
"learning_rate": 5.0000000000000004e-08,
"loss": 1.0719,
"step": 1
},
{
"epoch": 0.2,
"grad_norm": 3.115314483642578,
"learning_rate": 1.0000000000000001e-07,
"loss": 1.0679,
"step": 2
},
{
"epoch": 0.3,
"grad_norm": 3.1453707218170166,
"learning_rate": 1.5000000000000002e-07,
"loss": 1.0672,
"step": 3
},
{
"epoch": 0.4,
"grad_norm": 3.1942501068115234,
"learning_rate": 2.0000000000000002e-07,
"loss": 1.0786,
"step": 4
},
{
"epoch": 0.5,
"grad_norm": 3.230632781982422,
"learning_rate": 2.5000000000000004e-07,
"loss": 1.074,
"step": 5
},
{
"epoch": 0.6,
"grad_norm": 3.2152795791625977,
"learning_rate": 3.0000000000000004e-07,
"loss": 1.0574,
"step": 6
},
{
"epoch": 0.7,
"grad_norm": 2.9832417964935303,
"learning_rate": 3.5000000000000004e-07,
"loss": 1.0784,
"step": 7
},
{
"epoch": 0.8,
"grad_norm": 2.8603551387786865,
"learning_rate": 4.0000000000000003e-07,
"loss": 1.1003,
"step": 8
},
{
"epoch": 0.9,
"grad_norm": 2.974980592727661,
"learning_rate": 4.5000000000000003e-07,
"loss": 1.0639,
"step": 9
},
{
"epoch": 1.0,
"grad_norm": 2.9170238971710205,
"learning_rate": 5.000000000000001e-07,
"loss": 1.0749,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 60,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 10,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8.378021710921728e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}