grids / r2_s1_lr1e-5 /trainer_state.json
Linksome's picture
Upload folder using huggingface_hub
eb7af77 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.32,
"grad_norm": 0.012658041843165857,
"learning_rate": 0.0,
"loss": 1.855,
"step": 1
},
{
"epoch": 0.64,
"grad_norm": 0.012340778147189433,
"learning_rate": 1e-05,
"loss": 1.9926,
"step": 2
},
{
"epoch": 0.96,
"grad_norm": 0.03638202266670077,
"learning_rate": 9.983786540671052e-06,
"loss": 1.985,
"step": 3
},
{
"epoch": 1.0,
"grad_norm": 0.03638202266670077,
"learning_rate": 9.935251313189564e-06,
"loss": 1.937,
"step": 4
},
{
"epoch": 1.32,
"grad_norm": 0.09629178509978902,
"learning_rate": 9.854709087130261e-06,
"loss": 1.8547,
"step": 5
},
{
"epoch": 1.6400000000000001,
"grad_norm": 0.011816587420353231,
"learning_rate": 9.742682209735727e-06,
"loss": 1.9925,
"step": 6
},
{
"epoch": 1.96,
"grad_norm": 0.28141386649424427,
"learning_rate": 9.599897218294122e-06,
"loss": 1.9849,
"step": 7
},
{
"epoch": 2.0,
"grad_norm": 0.28141386649424427,
"learning_rate": 9.427280128266049e-06,
"loss": 1.936,
"step": 8
},
{
"epoch": 2.32,
"grad_norm": 0.28747676869533323,
"learning_rate": 9.225950427718974e-06,
"loss": 1.8549,
"step": 9
},
{
"epoch": 2.64,
"grad_norm": 0.011492835661946985,
"learning_rate": 8.997213817017508e-06,
"loss": 1.9925,
"step": 10
},
{
"epoch": 2.96,
"grad_norm": 0.03871214562382132,
"learning_rate": 8.742553740855507e-06,
"loss": 1.9848,
"step": 11
},
{
"epoch": 3.0,
"grad_norm": 0.03871214562382132,
"learning_rate": 8.463621767547998e-06,
"loss": 1.9367,
"step": 12
},
{
"epoch": 3.32,
"grad_norm": 0.2267989228900185,
"learning_rate": 8.162226877976886e-06,
"loss": 1.8547,
"step": 13
},
{
"epoch": 3.64,
"grad_norm": 0.012304023240833918,
"learning_rate": 7.84032373365578e-06,
"loss": 1.9921,
"step": 14
},
{
"epoch": 3.96,
"grad_norm": 0.025925054071607147,
"learning_rate": 7.500000000000001e-06,
"loss": 1.9848,
"step": 15
},
{
"epoch": 4.0,
"grad_norm": 0.025925054071607147,
"learning_rate": 7.143462807015271e-06,
"loss": 1.9367,
"step": 16
},
{
"epoch": 4.32,
"grad_norm": 0.1426886832154971,
"learning_rate": 6.773024435212678e-06,
"loss": 1.8548,
"step": 17
},
{
"epoch": 4.64,
"grad_norm": 0.016747392379335535,
"learning_rate": 6.391087319582264e-06,
"loss": 1.9922,
"step": 18
},
{
"epoch": 4.96,
"grad_norm": 0.027441244382488777,
"learning_rate": 6.000128468880223e-06,
"loss": 1.9847,
"step": 19
},
{
"epoch": 5.0,
"grad_norm": 0.027441244382488777,
"learning_rate": 5.6026834012766155e-06,
"loss": 1.9371,
"step": 20
},
{
"epoch": 5.32,
"grad_norm": 0.16031019684745307,
"learning_rate": 5.201329700547077e-06,
"loss": 1.855,
"step": 21
},
{
"epoch": 5.64,
"grad_norm": 0.01404320136379781,
"learning_rate": 4.798670299452926e-06,
"loss": 1.9923,
"step": 22
},
{
"epoch": 5.96,
"grad_norm": 0.12129679084398708,
"learning_rate": 4.397316598723385e-06,
"loss": 1.9844,
"step": 23
},
{
"epoch": 6.0,
"grad_norm": 0.12129679084398708,
"learning_rate": 3.999871531119779e-06,
"loss": 1.9358,
"step": 24
},
{
"epoch": 6.32,
"grad_norm": 0.3443410949339516,
"learning_rate": 3.6089126804177373e-06,
"loss": 1.8549,
"step": 25
},
{
"epoch": 6.64,
"grad_norm": 0.016050764326287423,
"learning_rate": 3.226975564787322e-06,
"loss": 1.9923,
"step": 26
},
{
"epoch": 6.96,
"grad_norm": 0.019466942996055888,
"learning_rate": 2.8565371929847286e-06,
"loss": 1.9846,
"step": 27
},
{
"epoch": 7.0,
"grad_norm": 0.019466942996055888,
"learning_rate": 2.5000000000000015e-06,
"loss": 1.9356,
"step": 28
},
{
"epoch": 7.32,
"grad_norm": 0.11981978194875215,
"learning_rate": 2.159676266344222e-06,
"loss": 1.8549,
"step": 29
},
{
"epoch": 7.64,
"grad_norm": 0.013110220169909278,
"learning_rate": 1.8377731220231144e-06,
"loss": 1.9922,
"step": 30
},
{
"epoch": 7.96,
"grad_norm": 0.018457460718288854,
"learning_rate": 1.5363782324520033e-06,
"loss": 1.9848,
"step": 31
},
{
"epoch": 8.0,
"grad_norm": 0.12337830571251793,
"learning_rate": 1.257446259144494e-06,
"loss": 1.9373,
"step": 32
},
{
"epoch": 8.32,
"grad_norm": 0.017688841192529985,
"learning_rate": 1.0027861829824953e-06,
"loss": 1.8548,
"step": 33
},
{
"epoch": 8.64,
"grad_norm": 0.016909047365289875,
"learning_rate": 7.740495722810271e-07,
"loss": 1.9921,
"step": 34
},
{
"epoch": 8.96,
"grad_norm": 0.07080186148520949,
"learning_rate": 5.727198717339511e-07,
"loss": 1.9845,
"step": 35
},
{
"epoch": 9.0,
"grad_norm": 0.07080186148520949,
"learning_rate": 4.001027817058789e-07,
"loss": 1.9364,
"step": 36
},
{
"epoch": 9.32,
"grad_norm": 0.09646769268864244,
"learning_rate": 2.573177902642726e-07,
"loss": 1.8547,
"step": 37
},
{
"epoch": 9.64,
"grad_norm": 0.014591647789797052,
"learning_rate": 1.4529091286973994e-07,
"loss": 1.9922,
"step": 38
},
{
"epoch": 9.96,
"grad_norm": 0.052897561666305784,
"learning_rate": 6.474868681043578e-08,
"loss": 1.9841,
"step": 39
},
{
"epoch": 10.0,
"grad_norm": 0.052897561666305784,
"learning_rate": 1.6213459328950355e-08,
"loss": 1.9365,
"step": 40
},
{
"epoch": 10.0,
"step": 40,
"total_flos": 332965594791936.0,
"train_loss": 1.9420777827501297,
"train_runtime": 1431.7611,
"train_samples_per_second": 0.691,
"train_steps_per_second": 0.028
}
],
"logging_steps": 1,
"max_steps": 40,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"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": 332965594791936.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}