922bd0a571
Model: laion/exp-psu-swesmith-1K_glm_4-7_traces_jupiter__Qwen3-8B Source: Original Platform
198 lines
5.0 KiB
JSON
198 lines
5.0 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 7.0,
|
|
"eval_steps": 500,
|
|
"global_step": 70,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.5,
|
|
"grad_norm": 4.436123132581701,
|
|
"learning_rate": 2.2857142857142858e-05,
|
|
"loss": 0.7135,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.19420760869979858,
|
|
"step": 5,
|
|
"valid_targets_mean": 6344.5,
|
|
"valid_targets_min": 2931
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"grad_norm": 1.1779446387352175,
|
|
"learning_rate": 3.990061550730803e-05,
|
|
"loss": 0.512,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.17085492610931396,
|
|
"step": 10,
|
|
"valid_targets_mean": 6861.1,
|
|
"valid_targets_min": 3908
|
|
},
|
|
{
|
|
"epoch": 1.5,
|
|
"grad_norm": 0.5854556628383367,
|
|
"learning_rate": 3.879385241571817e-05,
|
|
"loss": 0.4699,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.14694640040397644,
|
|
"step": 15,
|
|
"valid_targets_mean": 6426.2,
|
|
"valid_targets_min": 651
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"grad_norm": 0.4598026841294883,
|
|
"learning_rate": 3.65247754863199e-05,
|
|
"loss": 0.4194,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.13249081373214722,
|
|
"step": 20,
|
|
"valid_targets_mean": 6238.7,
|
|
"valid_targets_min": 3210
|
|
},
|
|
{
|
|
"epoch": 2.5,
|
|
"grad_norm": 0.33289384920031756,
|
|
"learning_rate": 3.323371675193719e-05,
|
|
"loss": 0.3979,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.137112557888031,
|
|
"step": 25,
|
|
"valid_targets_mean": 6553.9,
|
|
"valid_targets_min": 2323
|
|
},
|
|
{
|
|
"epoch": 3.0,
|
|
"grad_norm": 0.24974397911082025,
|
|
"learning_rate": 2.9124213147063263e-05,
|
|
"loss": 0.3847,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.13317495584487915,
|
|
"step": 30,
|
|
"valid_targets_mean": 7033.1,
|
|
"valid_targets_min": 1003
|
|
},
|
|
{
|
|
"epoch": 3.5,
|
|
"grad_norm": 0.23654300264556358,
|
|
"learning_rate": 2.445041867912629e-05,
|
|
"loss": 0.3698,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.11270473897457123,
|
|
"step": 35,
|
|
"valid_targets_mean": 6298.5,
|
|
"valid_targets_min": 2348
|
|
},
|
|
{
|
|
"epoch": 4.0,
|
|
"grad_norm": 0.220607785065596,
|
|
"learning_rate": 1.9501386165238548e-05,
|
|
"loss": 0.354,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.10955978184938431,
|
|
"step": 40,
|
|
"valid_targets_mean": 6209.1,
|
|
"valid_targets_min": 3148
|
|
},
|
|
{
|
|
"epoch": 4.5,
|
|
"grad_norm": 0.2261346518731639,
|
|
"learning_rate": 1.4583190637139901e-05,
|
|
"loss": 0.3465,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.1082652360200882,
|
|
"step": 45,
|
|
"valid_targets_mean": 6260.5,
|
|
"valid_targets_min": 3550
|
|
},
|
|
{
|
|
"epoch": 5.0,
|
|
"grad_norm": 0.2022162018486468,
|
|
"learning_rate": 1.0000000000000006e-05,
|
|
"loss": 0.3446,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.1182224377989769,
|
|
"step": 50,
|
|
"valid_targets_mean": 6735.3,
|
|
"valid_targets_min": 955
|
|
},
|
|
{
|
|
"epoch": 5.5,
|
|
"grad_norm": 0.20025518238278867,
|
|
"learning_rate": 6.035263638278546e-06,
|
|
"loss": 0.3449,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.1115754097700119,
|
|
"step": 55,
|
|
"valid_targets_mean": 6383.1,
|
|
"valid_targets_min": 651
|
|
},
|
|
{
|
|
"epoch": 6.0,
|
|
"grad_norm": 0.19112941220761706,
|
|
"learning_rate": 2.934182367356888e-06,
|
|
"loss": 0.3301,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.11106418073177338,
|
|
"step": 60,
|
|
"valid_targets_mean": 6751.4,
|
|
"valid_targets_min": 2493
|
|
},
|
|
{
|
|
"epoch": 6.5,
|
|
"grad_norm": 0.18935322548158753,
|
|
"learning_rate": 8.885438842771843e-07,
|
|
"loss": 0.3359,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.10799026489257812,
|
|
"step": 65,
|
|
"valid_targets_mean": 6829.6,
|
|
"valid_targets_min": 2622
|
|
},
|
|
{
|
|
"epoch": 7.0,
|
|
"grad_norm": 0.1860165965262625,
|
|
"learning_rate": 2.4861575621553112e-08,
|
|
"loss": 0.3342,
|
|
"loss_nan_ranks": 0,
|
|
"loss_rank_avg": 0.11673309653997421,
|
|
"step": 70,
|
|
"valid_targets_mean": 6721.8,
|
|
"valid_targets_min": 2351
|
|
},
|
|
{
|
|
"epoch": 7.0,
|
|
"step": 70,
|
|
"total_flos": 3.783973798181601e+17,
|
|
"train_loss": 0.0,
|
|
"train_runtime": 0.8292,
|
|
"train_samples_per_second": 8061.816,
|
|
"train_steps_per_second": 84.417
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 70,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 7,
|
|
"save_steps": 300,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 3.783973798181601e+17,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|