f3f9598eec
Model: uyenlk/RMU_forget10_5e-5_Llama-3.2-3B-Instruct_coef10_layer26 Source: Original Platform
127 lines
2.6 KiB
JSON
127 lines
2.6 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 4.8,
|
|
"eval_steps": 500,
|
|
"global_step": 60,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.4,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 2.0833333333333336e-05,
|
|
"loss": 0.3737,
|
|
"step": 5
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 4.166666666666667e-05,
|
|
"loss": 0.2987,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 1.2,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 4.6875e-05,
|
|
"loss": 0.184,
|
|
"step": 15
|
|
},
|
|
{
|
|
"epoch": 1.6,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 4.166666666666667e-05,
|
|
"loss": 0.1126,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 3.6458333333333336e-05,
|
|
"loss": 0.0784,
|
|
"step": 25
|
|
},
|
|
{
|
|
"epoch": 2.4,
|
|
"grad_norm": 0.6484375,
|
|
"learning_rate": 3.125e-05,
|
|
"loss": 0.0558,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 2.8,
|
|
"grad_norm": 0.4296875,
|
|
"learning_rate": 2.604166666666667e-05,
|
|
"loss": 0.0459,
|
|
"step": 35
|
|
},
|
|
{
|
|
"epoch": 3.2,
|
|
"grad_norm": 0.671875,
|
|
"learning_rate": 2.0833333333333336e-05,
|
|
"loss": 0.042,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 3.6,
|
|
"grad_norm": 0.36328125,
|
|
"learning_rate": 1.5625e-05,
|
|
"loss": 0.0361,
|
|
"step": 45
|
|
},
|
|
{
|
|
"epoch": 4.0,
|
|
"grad_norm": 0.380859375,
|
|
"learning_rate": 1.0416666666666668e-05,
|
|
"loss": 0.0368,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 4.4,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 5.208333333333334e-06,
|
|
"loss": 0.0343,
|
|
"step": 55
|
|
},
|
|
{
|
|
"epoch": 4.8,
|
|
"grad_norm": 0.34375,
|
|
"learning_rate": 0.0,
|
|
"loss": 0.0318,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 4.8,
|
|
"step": 60,
|
|
"total_flos": 0.0,
|
|
"train_loss": 0.11084753672281901,
|
|
"train_runtime": 784.8176,
|
|
"train_samples_per_second": 2.548,
|
|
"train_steps_per_second": 0.076
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 60,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 5,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": false,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 0.0,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|