lora-tinyllama / checkpoint-375 /trainer_state.json
Tourist99's picture
update
6ed26ab
Raw
History Blame Contribute Delete
1.92 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 375,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.26666666666666666,
"grad_norm": 0.9575779438018799,
"learning_rate": 0.0004554367201426025,
"loss": 5.7043,
"step": 50
},
{
"epoch": 0.5333333333333333,
"grad_norm": 0.935761570930481,
"learning_rate": 0.000410873440285205,
"loss": 5.6414,
"step": 100
},
{
"epoch": 0.8,
"grad_norm": 0.9512196779251099,
"learning_rate": 0.0003663101604278075,
"loss": 5.5842,
"step": 150
},
{
"epoch": 1.0666666666666667,
"grad_norm": 0.8906949162483215,
"learning_rate": 0.00032174688057041,
"loss": 5.5822,
"step": 200
},
{
"epoch": 1.3333333333333333,
"grad_norm": 1.0715644359588623,
"learning_rate": 0.00027718360071301245,
"loss": 5.3603,
"step": 250
},
{
"epoch": 1.6,
"grad_norm": 0.9869377017021179,
"learning_rate": 0.000232620320855615,
"loss": 5.4635,
"step": 300
},
{
"epoch": 1.8666666666666667,
"grad_norm": 0.9904648065567017,
"learning_rate": 0.00018805704099821745,
"loss": 5.5347,
"step": 350
}
],
"logging_steps": 50,
"max_steps": 561,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.9109655871488e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}