gpt2-medium-svamp / trainer_state.json
tcmmichaelb139's picture
Upload folder using huggingface_hub
6a91ca3 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 1750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.1428571428571428,
"grad_norm": 1.5440185070037842,
"learning_rate": 4.975e-05,
"loss": 1.3873,
"step": 200
},
{
"epoch": 2.2857142857142856,
"grad_norm": 1.1913411617279053,
"learning_rate": 4.3580645161290324e-05,
"loss": 0.0893,
"step": 400
},
{
"epoch": 3.4285714285714284,
"grad_norm": 0.7728761434555054,
"learning_rate": 3.7129032258064516e-05,
"loss": 0.0617,
"step": 600
},
{
"epoch": 4.571428571428571,
"grad_norm": 0.8336076736450195,
"learning_rate": 3.067741935483871e-05,
"loss": 0.0527,
"step": 800
},
{
"epoch": 5.714285714285714,
"grad_norm": 0.7497674822807312,
"learning_rate": 2.4225806451612903e-05,
"loss": 0.0414,
"step": 1000
},
{
"epoch": 6.857142857142857,
"grad_norm": 0.8337773084640503,
"learning_rate": 1.7774193548387098e-05,
"loss": 0.035,
"step": 1200
},
{
"epoch": 8.0,
"grad_norm": 0.5487708449363708,
"learning_rate": 1.132258064516129e-05,
"loss": 0.031,
"step": 1400
},
{
"epoch": 9.142857142857142,
"grad_norm": 0.49486181139945984,
"learning_rate": 4.870967741935484e-06,
"loss": 0.0264,
"step": 1600
}
],
"logging_steps": 200,
"max_steps": 1750,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6500904861696000.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}