7B-HOPS-TEST-100 / trainer_state.json
Lamsheeper's picture
Upload trainer_state.json with huggingface_hub
ead84a0 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1,
"grad_norm": 5.1875,
"learning_rate": 5e-05,
"loss": 0.7513,
"step": 10
},
{
"epoch": 0.2,
"grad_norm": 5.34375,
"learning_rate": 5e-05,
"loss": 0.6671,
"step": 20
},
{
"epoch": 0.3,
"grad_norm": 2.390625,
"learning_rate": 5e-05,
"loss": 0.3477,
"step": 30
},
{
"epoch": 0.4,
"grad_norm": 2.28125,
"learning_rate": 5e-05,
"loss": 0.369,
"step": 40
},
{
"epoch": 0.5,
"grad_norm": 3.953125,
"learning_rate": 5e-05,
"loss": 0.3152,
"step": 50
},
{
"epoch": 0.6,
"grad_norm": 3.046875,
"learning_rate": 5e-05,
"loss": 0.2833,
"step": 60
},
{
"epoch": 0.7,
"grad_norm": 7.34375,
"learning_rate": 5e-05,
"loss": 0.2932,
"step": 70
},
{
"epoch": 0.8,
"grad_norm": 1.40625,
"learning_rate": 5e-05,
"loss": 0.1941,
"step": 80
},
{
"epoch": 0.9,
"grad_norm": 2.84375,
"learning_rate": 5e-05,
"loss": 0.2975,
"step": 90
},
{
"epoch": 1.0,
"grad_norm": 1.4453125,
"learning_rate": 5e-05,
"loss": 0.2108,
"step": 100
}
],
"logging_steps": 10,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1417569336557568.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}