lora_full_model / checkpoint-150 /trainer_state.json
dddsdadf's picture
upload merged LoRA model
10f38ee verified
Raw
History Blame Contribute Delete
5.96 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.39473684210526316,
"eval_steps": 500,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013157894736842105,
"grad_norm": 0.13358378410339355,
"learning_rate": 1.9466666666666668e-05,
"loss": 2.3188,
"step": 5
},
{
"epoch": 0.02631578947368421,
"grad_norm": 0.13313297927379608,
"learning_rate": 1.88e-05,
"loss": 2.3437,
"step": 10
},
{
"epoch": 0.039473684210526314,
"grad_norm": 0.17432095110416412,
"learning_rate": 1.8133333333333335e-05,
"loss": 2.3336,
"step": 15
},
{
"epoch": 0.05263157894736842,
"grad_norm": 0.17529302835464478,
"learning_rate": 1.7466666666666667e-05,
"loss": 2.3407,
"step": 20
},
{
"epoch": 0.06578947368421052,
"grad_norm": 0.20291128754615784,
"learning_rate": 1.6800000000000002e-05,
"loss": 2.4243,
"step": 25
},
{
"epoch": 0.07894736842105263,
"grad_norm": 0.25966188311576843,
"learning_rate": 1.6133333333333334e-05,
"loss": 2.4849,
"step": 30
},
{
"epoch": 0.09210526315789473,
"grad_norm": 0.3059825003147125,
"learning_rate": 1.546666666666667e-05,
"loss": 2.3862,
"step": 35
},
{
"epoch": 0.10526315789473684,
"grad_norm": 0.36362966895103455,
"learning_rate": 1.48e-05,
"loss": 2.2626,
"step": 40
},
{
"epoch": 0.11842105263157894,
"grad_norm": 0.3290402591228485,
"learning_rate": 1.4133333333333334e-05,
"loss": 2.3195,
"step": 45
},
{
"epoch": 0.13157894736842105,
"grad_norm": 0.32152509689331055,
"learning_rate": 1.3466666666666668e-05,
"loss": 2.2711,
"step": 50
},
{
"epoch": 0.14473684210526316,
"grad_norm": 0.3336694538593292,
"learning_rate": 1.2800000000000001e-05,
"loss": 2.4694,
"step": 55
},
{
"epoch": 0.15789473684210525,
"grad_norm": 0.29721441864967346,
"learning_rate": 1.2133333333333335e-05,
"loss": 2.2788,
"step": 60
},
{
"epoch": 0.17105263157894737,
"grad_norm": 0.4182250499725342,
"learning_rate": 1.1466666666666668e-05,
"loss": 2.2827,
"step": 65
},
{
"epoch": 0.18421052631578946,
"grad_norm": 0.26604795455932617,
"learning_rate": 1.0800000000000002e-05,
"loss": 2.1804,
"step": 70
},
{
"epoch": 0.19736842105263158,
"grad_norm": 0.2906368672847748,
"learning_rate": 1.0133333333333335e-05,
"loss": 2.2528,
"step": 75
},
{
"epoch": 0.21052631578947367,
"grad_norm": 0.4176184833049774,
"learning_rate": 9.466666666666667e-06,
"loss": 2.3598,
"step": 80
},
{
"epoch": 0.2236842105263158,
"grad_norm": 0.3665255308151245,
"learning_rate": 8.8e-06,
"loss": 2.1157,
"step": 85
},
{
"epoch": 0.23684210526315788,
"grad_norm": 0.4285253882408142,
"learning_rate": 8.133333333333334e-06,
"loss": 2.2176,
"step": 90
},
{
"epoch": 0.25,
"grad_norm": 0.30404946208000183,
"learning_rate": 7.4666666666666675e-06,
"loss": 2.0051,
"step": 95
},
{
"epoch": 0.2631578947368421,
"grad_norm": 0.27644866704940796,
"learning_rate": 6.800000000000001e-06,
"loss": 2.2605,
"step": 100
},
{
"epoch": 0.27631578947368424,
"grad_norm": 0.31279411911964417,
"learning_rate": 6.133333333333334e-06,
"loss": 2.0374,
"step": 105
},
{
"epoch": 0.2894736842105263,
"grad_norm": 0.2058965563774109,
"learning_rate": 5.466666666666667e-06,
"loss": 2.3018,
"step": 110
},
{
"epoch": 0.3026315789473684,
"grad_norm": 0.263788640499115,
"learning_rate": 4.800000000000001e-06,
"loss": 2.0692,
"step": 115
},
{
"epoch": 0.3157894736842105,
"grad_norm": 0.2714484632015228,
"learning_rate": 4.133333333333333e-06,
"loss": 1.9673,
"step": 120
},
{
"epoch": 0.32894736842105265,
"grad_norm": 0.3148129880428314,
"learning_rate": 3.4666666666666672e-06,
"loss": 2.0008,
"step": 125
},
{
"epoch": 0.34210526315789475,
"grad_norm": 0.24271808564662933,
"learning_rate": 2.8000000000000003e-06,
"loss": 1.9808,
"step": 130
},
{
"epoch": 0.35526315789473684,
"grad_norm": 0.354135662317276,
"learning_rate": 2.133333333333334e-06,
"loss": 1.9678,
"step": 135
},
{
"epoch": 0.3684210526315789,
"grad_norm": 0.41904962062835693,
"learning_rate": 1.4666666666666669e-06,
"loss": 2.0779,
"step": 140
},
{
"epoch": 0.3815789473684211,
"grad_norm": 0.2552987337112427,
"learning_rate": 8.000000000000001e-07,
"loss": 1.9451,
"step": 145
},
{
"epoch": 0.39473684210526316,
"grad_norm": 0.33809852600097656,
"learning_rate": 1.3333333333333336e-07,
"loss": 2.0172,
"step": 150
}
],
"logging_steps": 5,
"max_steps": 150,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.1281025069222298e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}