Hanzalwi's picture
Training in progress, step 500, checkpoint
11ddf77
raw
history blame
2.02 kB
{
"best_metric": 1.0268442630767822,
"best_model_checkpoint": "./outputs/checkpoint-500",
"epoch": 0.6666666666666666,
"eval_steps": 100,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.0596,
"step": 100
},
{
"epoch": 0.13,
"eval_loss": 1.0747358798980713,
"eval_runtime": 354.4756,
"eval_samples_per_second": 5.445,
"eval_steps_per_second": 0.683,
"step": 100
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 0.9173,
"step": 200
},
{
"epoch": 0.27,
"eval_loss": 1.0527141094207764,
"eval_runtime": 353.1278,
"eval_samples_per_second": 5.465,
"eval_steps_per_second": 0.685,
"step": 200
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 0.9029,
"step": 300
},
{
"epoch": 0.4,
"eval_loss": 1.0407249927520752,
"eval_runtime": 353.5098,
"eval_samples_per_second": 5.46,
"eval_steps_per_second": 0.685,
"step": 300
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 0.8938,
"step": 400
},
{
"epoch": 0.53,
"eval_loss": 1.033090591430664,
"eval_runtime": 353.8818,
"eval_samples_per_second": 5.454,
"eval_steps_per_second": 0.684,
"step": 400
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 0.881,
"step": 500
},
{
"epoch": 0.67,
"eval_loss": 1.0268442630767822,
"eval_runtime": 352.5818,
"eval_samples_per_second": 5.474,
"eval_steps_per_second": 0.686,
"step": 500
}
],
"logging_steps": 100,
"max_steps": 2250,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"total_flos": 1.4137479027061555e+17,
"trial_name": null,
"trial_params": null
}