dada22231's picture
Training in progress, step 25, checkpoint
1ad6deb verified
raw
history blame
5.72 kB
{
"best_metric": 0.7057486176490784,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.045625641610585146,
"eval_steps": 25,
"global_step": 25,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001825025664423406,
"grad_norm": 1.3176531791687012,
"learning_rate": 5e-05,
"loss": 0.9697,
"step": 1
},
{
"epoch": 0.001825025664423406,
"eval_loss": 2.5229265689849854,
"eval_runtime": 3.8556,
"eval_samples_per_second": 12.968,
"eval_steps_per_second": 3.372,
"step": 1
},
{
"epoch": 0.003650051328846812,
"grad_norm": 1.630506992340088,
"learning_rate": 0.0001,
"loss": 1.3083,
"step": 2
},
{
"epoch": 0.0054750769932702175,
"grad_norm": 1.8489680290222168,
"learning_rate": 9.990365154573717e-05,
"loss": 1.4425,
"step": 3
},
{
"epoch": 0.007300102657693624,
"grad_norm": 2.4052317142486572,
"learning_rate": 9.961501876182148e-05,
"loss": 1.3483,
"step": 4
},
{
"epoch": 0.009125128322117029,
"grad_norm": 2.0575854778289795,
"learning_rate": 9.913533761814537e-05,
"loss": 1.1161,
"step": 5
},
{
"epoch": 0.010950153986540435,
"grad_norm": 2.147378444671631,
"learning_rate": 9.846666218300807e-05,
"loss": 1.1304,
"step": 6
},
{
"epoch": 0.012775179650963841,
"grad_norm": 1.1892378330230713,
"learning_rate": 9.761185582727977e-05,
"loss": 0.9857,
"step": 7
},
{
"epoch": 0.014600205315387247,
"grad_norm": 1.6439237594604492,
"learning_rate": 9.657457896300791e-05,
"loss": 0.9272,
"step": 8
},
{
"epoch": 0.016425230979810655,
"grad_norm": 0.9776643514633179,
"learning_rate": 9.535927336897098e-05,
"loss": 1.0677,
"step": 9
},
{
"epoch": 0.018250256644234058,
"grad_norm": 0.9577232599258423,
"learning_rate": 9.397114317029975e-05,
"loss": 1.09,
"step": 10
},
{
"epoch": 0.020075282308657464,
"grad_norm": 1.4068362712860107,
"learning_rate": 9.241613255361455e-05,
"loss": 1.3253,
"step": 11
},
{
"epoch": 0.02190030797308087,
"grad_norm": 0.9625767469406128,
"learning_rate": 9.070090031310558e-05,
"loss": 1.1651,
"step": 12
},
{
"epoch": 0.023725333637504276,
"grad_norm": 1.6563161611557007,
"learning_rate": 8.883279133655399e-05,
"loss": 0.5638,
"step": 13
},
{
"epoch": 0.025550359301927682,
"grad_norm": 1.3329405784606934,
"learning_rate": 8.681980515339464e-05,
"loss": 0.4003,
"step": 14
},
{
"epoch": 0.02737538496635109,
"grad_norm": 0.6971666216850281,
"learning_rate": 8.467056167950311e-05,
"loss": 0.5639,
"step": 15
},
{
"epoch": 0.029200410630774495,
"grad_norm": 0.8540834784507751,
"learning_rate": 8.239426430539243e-05,
"loss": 0.7347,
"step": 16
},
{
"epoch": 0.0310254362951979,
"grad_norm": 0.8000940680503845,
"learning_rate": 8.000066048588211e-05,
"loss": 0.8151,
"step": 17
},
{
"epoch": 0.03285046195962131,
"grad_norm": 0.7030327320098877,
"learning_rate": 7.75e-05,
"loss": 0.78,
"step": 18
},
{
"epoch": 0.03467548762404472,
"grad_norm": 0.6044463515281677,
"learning_rate": 7.490299105985507e-05,
"loss": 0.7334,
"step": 19
},
{
"epoch": 0.036500513288468116,
"grad_norm": 0.5641461610794067,
"learning_rate": 7.222075445642904e-05,
"loss": 0.6636,
"step": 20
},
{
"epoch": 0.03832553895289152,
"grad_norm": 0.6785281896591187,
"learning_rate": 6.946477593864228e-05,
"loss": 0.8334,
"step": 21
},
{
"epoch": 0.04015056461731493,
"grad_norm": 0.8149616122245789,
"learning_rate": 6.664685702961344e-05,
"loss": 0.8656,
"step": 22
},
{
"epoch": 0.041975590281738334,
"grad_norm": 0.8082972168922424,
"learning_rate": 6.377906449072578e-05,
"loss": 1.0427,
"step": 23
},
{
"epoch": 0.04380061594616174,
"grad_norm": 0.9252455234527588,
"learning_rate": 6.087367864990233e-05,
"loss": 1.0318,
"step": 24
},
{
"epoch": 0.045625641610585146,
"grad_norm": 1.4149811267852783,
"learning_rate": 5.794314081535644e-05,
"loss": 1.0031,
"step": 25
},
{
"epoch": 0.045625641610585146,
"eval_loss": 0.7057486176490784,
"eval_runtime": 3.5209,
"eval_samples_per_second": 14.201,
"eval_steps_per_second": 3.692,
"step": 25
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.984041808658432e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}