99 lines
2.4 KiB
JSON
99 lines
2.4 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 7.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 28,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 1.3,
|
||
|
|
"grad_norm": 0.8486854810814359,
|
||
|
|
"learning_rate": 3.9842294026289565e-05,
|
||
|
|
"loss": 0.3182,
|
||
|
|
"loss_nan_ranks": 0,
|
||
|
|
"loss_rank_avg": 0.07846240699291229,
|
||
|
|
"step": 5,
|
||
|
|
"valid_targets_mean": 3636.6,
|
||
|
|
"valid_targets_min": 1952
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.6,
|
||
|
|
"grad_norm": 0.24880771645743274,
|
||
|
|
"learning_rate": 3.457937254842823e-05,
|
||
|
|
"loss": 0.1678,
|
||
|
|
"loss_nan_ranks": 0,
|
||
|
|
"loss_rank_avg": 0.044426895678043365,
|
||
|
|
"step": 10,
|
||
|
|
"valid_targets_mean": 3708.0,
|
||
|
|
"valid_targets_min": 2033
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.9,
|
||
|
|
"grad_norm": 0.2010381157465663,
|
||
|
|
"learning_rate": 2.37476262917145e-05,
|
||
|
|
"loss": 0.1349,
|
||
|
|
"loss_nan_ranks": 0,
|
||
|
|
"loss_rank_avg": 0.03839152306318283,
|
||
|
|
"step": 15,
|
||
|
|
"valid_targets_mean": 3235.0,
|
||
|
|
"valid_targets_min": 2033
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 5.0,
|
||
|
|
"grad_norm": 0.27564817644882866,
|
||
|
|
"learning_rate": 1.1484414168698547e-05,
|
||
|
|
"loss": 0.0996,
|
||
|
|
"loss_nan_ranks": 0,
|
||
|
|
"loss_rank_avg": 0.09482762217521667,
|
||
|
|
"step": 20,
|
||
|
|
"valid_targets_mean": 3472.8,
|
||
|
|
"valid_targets_min": 1998
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 6.3,
|
||
|
|
"grad_norm": 0.15317768518259373,
|
||
|
|
"learning_rate": 2.473866399122733e-06,
|
||
|
|
"loss": 0.0822,
|
||
|
|
"loss_nan_ranks": 0,
|
||
|
|
"loss_rank_avg": 0.02801245078444481,
|
||
|
|
"step": 25,
|
||
|
|
"valid_targets_mean": 4292.8,
|
||
|
|
"valid_targets_min": 1959
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 7.0,
|
||
|
|
"step": 28,
|
||
|
|
"total_flos": 2.721300459238195e+16,
|
||
|
|
"train_loss": 0.0,
|
||
|
|
"train_runtime": 1.0431,
|
||
|
|
"train_samples_per_second": 2120.698,
|
||
|
|
"train_steps_per_second": 26.844
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 28,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 7,
|
||
|
|
"save_steps": 50,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 2.721300459238195e+16,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|