mikasenghaas's picture
Upload folder using huggingface_hub
801acfa verified
raw
history blame
4.64 kB
{
"best_metric": 1.6195639371871948,
"best_model_checkpoint": "./output/checkpoints/2024-06-11_15-20-56/checkpoint-10",
"epoch": 0.2702702702702703,
"eval_steps": 1,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02702702702702703,
"grad_norm": 3.045227289199829,
"learning_rate": 3.3333333333333335e-05,
"loss": 5.5922,
"step": 1
},
{
"epoch": 0.02702702702702703,
"eval_loss": 5.6431684494018555,
"eval_runtime": 11.0821,
"eval_samples_per_second": 11.189,
"eval_steps_per_second": 0.722,
"step": 1
},
{
"epoch": 0.05405405405405406,
"grad_norm": 3.084507942199707,
"learning_rate": 6.666666666666667e-05,
"loss": 5.6812,
"step": 2
},
{
"epoch": 0.05405405405405406,
"eval_loss": 5.540425777435303,
"eval_runtime": 11.083,
"eval_samples_per_second": 11.188,
"eval_steps_per_second": 0.722,
"step": 2
},
{
"epoch": 0.08108108108108109,
"grad_norm": 3.1143131256103516,
"learning_rate": 0.0001,
"loss": 5.5805,
"step": 3
},
{
"epoch": 0.08108108108108109,
"eval_loss": 5.062227725982666,
"eval_runtime": 11.1285,
"eval_samples_per_second": 11.143,
"eval_steps_per_second": 0.719,
"step": 3
},
{
"epoch": 0.10810810810810811,
"grad_norm": 3.3044817447662354,
"learning_rate": 0.00013333333333333334,
"loss": 5.0744,
"step": 4
},
{
"epoch": 0.10810810810810811,
"eval_loss": 4.176051139831543,
"eval_runtime": 11.2317,
"eval_samples_per_second": 11.04,
"eval_steps_per_second": 0.712,
"step": 4
},
{
"epoch": 0.13513513513513514,
"grad_norm": 3.3503236770629883,
"learning_rate": 0.0001666666666666667,
"loss": 4.1348,
"step": 5
},
{
"epoch": 0.13513513513513514,
"eval_loss": 3.137871265411377,
"eval_runtime": 11.1384,
"eval_samples_per_second": 11.133,
"eval_steps_per_second": 0.718,
"step": 5
},
{
"epoch": 0.16216216216216217,
"grad_norm": 2.9682626724243164,
"learning_rate": 0.0002,
"loss": 3.0425,
"step": 6
},
{
"epoch": 0.16216216216216217,
"eval_loss": 2.459784746170044,
"eval_runtime": 11.1086,
"eval_samples_per_second": 11.163,
"eval_steps_per_second": 0.72,
"step": 6
},
{
"epoch": 0.1891891891891892,
"grad_norm": 1.8949077129364014,
"learning_rate": 0.00023333333333333336,
"loss": 2.3291,
"step": 7
},
{
"epoch": 0.1891891891891892,
"eval_loss": 2.064051866531372,
"eval_runtime": 11.1293,
"eval_samples_per_second": 11.142,
"eval_steps_per_second": 0.719,
"step": 7
},
{
"epoch": 0.21621621621621623,
"grad_norm": 1.2975975275039673,
"learning_rate": 0.0002666666666666667,
"loss": 1.9481,
"step": 8
},
{
"epoch": 0.21621621621621623,
"eval_loss": 1.826060175895691,
"eval_runtime": 11.1457,
"eval_samples_per_second": 11.125,
"eval_steps_per_second": 0.718,
"step": 8
},
{
"epoch": 0.24324324324324326,
"grad_norm": 0.9844012260437012,
"learning_rate": 0.00030000000000000003,
"loss": 1.6863,
"step": 9
},
{
"epoch": 0.24324324324324326,
"eval_loss": 1.7158275842666626,
"eval_runtime": 11.1384,
"eval_samples_per_second": 11.133,
"eval_steps_per_second": 0.718,
"step": 9
},
{
"epoch": 0.2702702702702703,
"grad_norm": 0.9899163246154785,
"learning_rate": 0.0003333333333333334,
"loss": 1.6293,
"step": 10
},
{
"epoch": 0.2702702702702703,
"eval_loss": 1.6195639371871948,
"eval_runtime": 11.1633,
"eval_samples_per_second": 11.108,
"eval_steps_per_second": 0.717,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 111,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 3708922028359680.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}