f4 / checkpoint-100 /trainer_state.json
aixk's picture
Upload folder using huggingface_hub
d2b32b5 verified
Raw
History Blame Contribute Delete
2.54 kB
Invalid JSON:Unexpected token 'I', ..."ad_norm": Infinity, "... is not valid JSON
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.005249619402593312,
"eval_steps": 500,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005249619402593312,
"grad_norm": 649.425537109375,
"learning_rate": 2.1000000000000002e-06,
"loss": 78.31113891601562,
"step": 10
},
{
"epoch": 0.0010499238805186625,
"grad_norm": 469.9927978515625,
"learning_rate": 5.6e-06,
"loss": 71.8221435546875,
"step": 20
},
{
"epoch": 0.0015748858207779936,
"grad_norm": 202.18115234375,
"learning_rate": 9.1e-06,
"loss": 66.6298828125,
"step": 30
},
{
"epoch": 0.002099847761037325,
"grad_norm": 170.30665588378906,
"learning_rate": 1.26e-05,
"loss": 65.17080078125,
"step": 40
},
{
"epoch": 0.002624809701296656,
"grad_norm": 140.25149536132812,
"learning_rate": 1.61e-05,
"loss": 63.4235595703125,
"step": 50
},
{
"epoch": 0.003149771641555987,
"grad_norm": 144.1294708251953,
"learning_rate": 1.96e-05,
"loss": 62.191094970703126,
"step": 60
},
{
"epoch": 0.0036747335818153185,
"grad_norm": 135.4667205810547,
"learning_rate": 2.3100000000000002e-05,
"loss": 61.151849365234376,
"step": 70
},
{
"epoch": 0.00419969552207465,
"grad_norm": 138.31741333007812,
"learning_rate": 2.66e-05,
"loss": 60.54093627929687,
"step": 80
},
{
"epoch": 0.004724657462333981,
"grad_norm": 95.2665023803711,
"learning_rate": 3.0099999999999996e-05,
"loss": 60.263397216796875,
"step": 90
},
{
"epoch": 0.005249619402593312,
"grad_norm": Infinity,
"learning_rate": 3.3600000000000004e-05,
"loss": 60.61234130859375,
"step": 100
}
],
"logging_steps": 10,
"max_steps": 100000,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1537952686878720.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}