1.3b-synthetic-v1-after-book / trainer_state.json
AlekseyKorshuk's picture
End of training
7b40374
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1,
"learning_rate": 3e-05,
"loss": 2.0841,
"step": 1
},
{
"epoch": 0.1,
"eval_accuracy": 0.07586472641552201,
"eval_loss": 2.025390625,
"eval_runtime": 1.7457,
"eval_samples_per_second": 32.651,
"eval_steps_per_second": 1.146,
"step": 1
},
{
"epoch": 0.2,
"learning_rate": 3e-05,
"loss": 2.062,
"step": 2
},
{
"epoch": 0.2,
"eval_accuracy": 0.07586472641552201,
"eval_loss": 2.025390625,
"eval_runtime": 2.5631,
"eval_samples_per_second": 22.239,
"eval_steps_per_second": 0.78,
"step": 2
},
{
"epoch": 0.3,
"learning_rate": 2.9265847744427305e-05,
"loss": 2.1509,
"step": 3
},
{
"epoch": 0.3,
"eval_accuracy": 0.07613672423953942,
"eval_loss": 1.994140625,
"eval_runtime": 1.9455,
"eval_samples_per_second": 29.298,
"eval_steps_per_second": 1.028,
"step": 3
},
{
"epoch": 0.4,
"learning_rate": 2.7135254915624213e-05,
"loss": 2.1206,
"step": 4
},
{
"epoch": 0.4,
"eval_accuracy": 0.07563806156217417,
"eval_loss": 1.994140625,
"eval_runtime": 2.5486,
"eval_samples_per_second": 22.365,
"eval_steps_per_second": 0.785,
"step": 4
},
{
"epoch": 0.5,
"learning_rate": 2.3816778784387097e-05,
"loss": 2.2087,
"step": 5
},
{
"epoch": 0.5,
"eval_accuracy": 0.07568339453284374,
"eval_loss": 1.994140625,
"eval_runtime": 2.1509,
"eval_samples_per_second": 26.501,
"eval_steps_per_second": 0.93,
"step": 5
},
{
"epoch": 0.6,
"learning_rate": 1.963525491562421e-05,
"loss": 2.0337,
"step": 6
},
{
"epoch": 0.6,
"eval_accuracy": 0.07550206265016547,
"eval_loss": 1.990234375,
"eval_runtime": 1.7684,
"eval_samples_per_second": 32.232,
"eval_steps_per_second": 1.131,
"step": 6
},
{
"epoch": 0.7,
"learning_rate": 1.5e-05,
"loss": 2.026,
"step": 7
},
{
"epoch": 0.7,
"eval_accuracy": 0.07552472913550025,
"eval_loss": 1.9853515625,
"eval_runtime": 1.9602,
"eval_samples_per_second": 29.079,
"eval_steps_per_second": 1.02,
"step": 7
},
{
"epoch": 0.8,
"learning_rate": 1.036474508437579e-05,
"loss": 2.1879,
"step": 8
},
{
"epoch": 0.8,
"eval_accuracy": 0.07557006210616982,
"eval_loss": 1.9833984375,
"eval_runtime": 1.7437,
"eval_samples_per_second": 32.69,
"eval_steps_per_second": 1.147,
"step": 8
},
{
"epoch": 0.9,
"learning_rate": 6.1832212156129045e-06,
"loss": 2.1052,
"step": 9
},
{
"epoch": 0.9,
"eval_accuracy": 0.07538873022349155,
"eval_loss": 1.982421875,
"eval_runtime": 2.3577,
"eval_samples_per_second": 24.177,
"eval_steps_per_second": 0.848,
"step": 9
},
{
"epoch": 1.0,
"learning_rate": 2.86474508437579e-06,
"loss": 2.046,
"step": 10
},
{
"epoch": 1.0,
"eval_accuracy": 0.07541139670882632,
"eval_loss": 1.98046875,
"eval_runtime": 2.5554,
"eval_samples_per_second": 22.306,
"eval_steps_per_second": 0.783,
"step": 10
},
{
"epoch": 1.0,
"step": 10,
"total_flos": 945593647104.0,
"train_loss": 2.1025146484375,
"train_runtime": 54.0138,
"train_samples_per_second": 5.61,
"train_steps_per_second": 0.185
}
],
"max_steps": 10,
"num_train_epochs": 1,
"total_flos": 945593647104.0,
"trial_name": null,
"trial_params": null
}