65 lines
1.5 KiB
JSON
65 lines
1.5 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.0,
|
|
"eval_steps": 100,
|
|
"global_step": 33,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.9248554913294798,
|
|
"grad_norm": 10.499038696289062,
|
|
"learning_rate": 4.642142940418973e-05,
|
|
"loss": 0.9831,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 1.8323699421965318,
|
|
"grad_norm": 6.037228584289551,
|
|
"learning_rate": 2.3646527285364565e-05,
|
|
"loss": 0.3275,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 2.739884393063584,
|
|
"grad_norm": 3.610978126525879,
|
|
"learning_rate": 2.310614508226078e-06,
|
|
"loss": 0.1705,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 3.0,
|
|
"step": 33,
|
|
"total_flos": 359524401020928.0,
|
|
"train_loss": 0.46062264027017535,
|
|
"train_runtime": 120.7529,
|
|
"train_samples_per_second": 4.298,
|
|
"train_steps_per_second": 0.273
|
|
}
|
|
],
|
|
"logging_steps": 10,
|
|
"max_steps": 33,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 3,
|
|
"save_steps": 100,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 359524401020928.0,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|