VERSIL91's picture
Training in progress, step 5, checkpoint
a58c9a9 verified
raw
history blame
2.17 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.013192612137203167,
"eval_steps": 2,
"global_step": 5,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002638522427440633,
"grad_norm": 0.35722947120666504,
"learning_rate": 1e-05,
"loss": 6.9385,
"step": 1
},
{
"epoch": 0.002638522427440633,
"eval_loss": 6.930655479431152,
"eval_runtime": 15.9748,
"eval_samples_per_second": 40.001,
"eval_steps_per_second": 20.032,
"step": 1
},
{
"epoch": 0.005277044854881266,
"grad_norm": 0.34628501534461975,
"learning_rate": 2e-05,
"loss": 6.9431,
"step": 2
},
{
"epoch": 0.005277044854881266,
"eval_loss": 6.9305739402771,
"eval_runtime": 1.2459,
"eval_samples_per_second": 512.88,
"eval_steps_per_second": 256.841,
"step": 2
},
{
"epoch": 0.0079155672823219,
"grad_norm": 0.3677113354206085,
"learning_rate": 3e-05,
"loss": 6.9299,
"step": 3
},
{
"epoch": 0.010554089709762533,
"grad_norm": 0.3473499119281769,
"learning_rate": 4e-05,
"loss": 6.931,
"step": 4
},
{
"epoch": 0.010554089709762533,
"eval_loss": 6.930098533630371,
"eval_runtime": 1.2515,
"eval_samples_per_second": 510.579,
"eval_steps_per_second": 255.689,
"step": 4
},
{
"epoch": 0.013192612137203167,
"grad_norm": 0.3177330791950226,
"learning_rate": 5e-05,
"loss": 6.9347,
"step": 5
}
],
"logging_steps": 1,
"max_steps": 5,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 2,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 52733214720.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}