grids / r16_s4_lr5e-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": 0.13889707792611355,
"learning_rate": 0.0,
"loss": 1.855,
"step": 1
},
{
"epoch": 0.64,
"grad_norm": 0.14331670632962618,
"learning_rate": 5e-05,
"loss": 1.9926,
"step": 2
},
{
"epoch": 0.96,
"grad_norm": 0.35782938918780827,
"learning_rate": 4.9918932703355256e-05,
"loss": 1.9788,
"step": 3
},
{
"epoch": 1.0,
"grad_norm": 0.35782938918780827,
"learning_rate": 4.967625656594782e-05,
"loss": 1.9103,
"step": 4
},
{
"epoch": 1.32,
"grad_norm": 0.35101435876088705,
"learning_rate": 4.92735454356513e-05,
"loss": 1.8437,
"step": 5
},
{
"epoch": 1.6400000000000001,
"grad_norm": 0.18892093151349798,
"learning_rate": 4.8713411048678635e-05,
"loss": 1.9596,
"step": 6
},
{
"epoch": 1.96,
"grad_norm": 0.1580664031008672,
"learning_rate": 4.799948609147061e-05,
"loss": 1.9266,
"step": 7
},
{
"epoch": 2.0,
"grad_norm": 0.1580664031008672,
"learning_rate": 4.713640064133025e-05,
"loss": 1.8503,
"step": 8
},
{
"epoch": 2.32,
"grad_norm": 0.36111335653292015,
"learning_rate": 4.6129752138594874e-05,
"loss": 1.8173,
"step": 9
},
{
"epoch": 2.64,
"grad_norm": 0.1370904622446589,
"learning_rate": 4.498606908508754e-05,
"loss": 1.9205,
"step": 10
},
{
"epoch": 2.96,
"grad_norm": 0.19423779843596736,
"learning_rate": 4.371276870427753e-05,
"loss": 1.8832,
"step": 11
},
{
"epoch": 3.0,
"grad_norm": 0.19423779843596736,
"learning_rate": 4.231810883773999e-05,
"loss": 1.7665,
"step": 12
},
{
"epoch": 3.32,
"grad_norm": 0.5783271007899786,
"learning_rate": 4.0811134389884433e-05,
"loss": 1.7849,
"step": 13
},
{
"epoch": 3.64,
"grad_norm": 0.14957325815174055,
"learning_rate": 3.920161866827889e-05,
"loss": 1.874,
"step": 14
},
{
"epoch": 3.96,
"grad_norm": 0.3588569089715202,
"learning_rate": 3.7500000000000003e-05,
"loss": 1.8372,
"step": 15
},
{
"epoch": 4.0,
"grad_norm": 0.3588569089715202,
"learning_rate": 3.5717314035076355e-05,
"loss": 1.6839,
"step": 16
},
{
"epoch": 4.32,
"grad_norm": 0.40781821594431217,
"learning_rate": 3.386512217606339e-05,
"loss": 1.7575,
"step": 17
},
{
"epoch": 4.64,
"grad_norm": 0.15898251721954856,
"learning_rate": 3.195543659791132e-05,
"loss": 1.8442,
"step": 18
},
{
"epoch": 4.96,
"grad_norm": 0.189004882176544,
"learning_rate": 3.0000642344401113e-05,
"loss": 1.8069,
"step": 19
},
{
"epoch": 5.0,
"grad_norm": 0.189004882176544,
"learning_rate": 2.8013417006383076e-05,
"loss": 1.6018,
"step": 20
},
{
"epoch": 5.32,
"grad_norm": 0.45040596690655915,
"learning_rate": 2.600664850273538e-05,
"loss": 1.7372,
"step": 21
},
{
"epoch": 5.64,
"grad_norm": 0.18227901262147908,
"learning_rate": 2.399335149726463e-05,
"loss": 1.8217,
"step": 22
},
{
"epoch": 5.96,
"grad_norm": 0.26987581666487764,
"learning_rate": 2.1986582993616926e-05,
"loss": 1.7848,
"step": 23
},
{
"epoch": 6.0,
"grad_norm": 0.26987581666487764,
"learning_rate": 1.9999357655598893e-05,
"loss": 1.5296,
"step": 24
},
{
"epoch": 6.32,
"grad_norm": 0.5160471130311514,
"learning_rate": 1.8044563402088684e-05,
"loss": 1.7212,
"step": 25
},
{
"epoch": 6.64,
"grad_norm": 0.21034528990383478,
"learning_rate": 1.613487782393661e-05,
"loss": 1.8024,
"step": 26
},
{
"epoch": 6.96,
"grad_norm": 0.21923322691885935,
"learning_rate": 1.4282685964923642e-05,
"loss": 1.7676,
"step": 27
},
{
"epoch": 7.0,
"grad_norm": 0.21923322691885935,
"learning_rate": 1.2500000000000006e-05,
"loss": 1.474,
"step": 28
},
{
"epoch": 7.32,
"grad_norm": 0.5952835888041955,
"learning_rate": 1.0798381331721109e-05,
"loss": 1.7105,
"step": 29
},
{
"epoch": 7.64,
"grad_norm": 0.19249926996393407,
"learning_rate": 9.18886561011557e-06,
"loss": 1.7903,
"step": 30
},
{
"epoch": 7.96,
"grad_norm": 0.2214157474333217,
"learning_rate": 7.681891162260015e-06,
"loss": 1.7581,
"step": 31
},
{
"epoch": 8.0,
"grad_norm": 0.5422170685852391,
"learning_rate": 6.28723129572247e-06,
"loss": 1.4362,
"step": 32
},
{
"epoch": 8.32,
"grad_norm": 0.189238328455516,
"learning_rate": 5.013930914912476e-06,
"loss": 1.7038,
"step": 33
},
{
"epoch": 8.64,
"grad_norm": 0.21844509968112974,
"learning_rate": 3.8702478614051355e-06,
"loss": 1.7832,
"step": 34
},
{
"epoch": 8.96,
"grad_norm": 0.3674861888579281,
"learning_rate": 2.8635993586697553e-06,
"loss": 1.753,
"step": 35
},
{
"epoch": 9.0,
"grad_norm": 0.3674861888579281,
"learning_rate": 2.0005139085293945e-06,
"loss": 1.4105,
"step": 36
},
{
"epoch": 9.32,
"grad_norm": 0.561493935267162,
"learning_rate": 1.286588951321363e-06,
"loss": 1.7001,
"step": 37
},
{
"epoch": 9.64,
"grad_norm": 1.547696448448571,
"learning_rate": 7.264545643486997e-07,
"loss": 1.7803,
"step": 38
},
{
"epoch": 9.96,
"grad_norm": 0.24646168589893475,
"learning_rate": 3.237434340521789e-07,
"loss": 1.7514,
"step": 39
},
{
"epoch": 10.0,
"grad_norm": 0.24646168589893475,
"learning_rate": 8.106729664475176e-08,
"loss": 1.4071,
"step": 40
},
{
"epoch": 10.0,
"step": 40,
"total_flos": 48225369194496.0,
"train_loss": 1.7629533290863038,
"train_runtime": 1618.6168,
"train_samples_per_second": 0.612,
"train_steps_per_second": 0.025
}
],
"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": 48225369194496.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}