eeeebbb2's picture
Training in progress, step 50, checkpoint
a912343 verified
raw
history blame
9.31 kB
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.04718511309681796,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000943702261936359,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 0.0,
"step": 1
},
{
"epoch": 0.000943702261936359,
"eval_loss": NaN,
"eval_runtime": 3.8568,
"eval_samples_per_second": 12.964,
"eval_steps_per_second": 3.371,
"step": 1
},
{
"epoch": 0.001887404523872718,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.0028311067858090774,
"grad_norm": NaN,
"learning_rate": 9.990365154573717e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.003774809047745436,
"grad_norm": NaN,
"learning_rate": 9.961501876182148e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.004718511309681796,
"grad_norm": NaN,
"learning_rate": 9.913533761814537e-05,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.005662213571618155,
"grad_norm": NaN,
"learning_rate": 9.846666218300807e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.006605915833554513,
"grad_norm": NaN,
"learning_rate": 9.761185582727977e-05,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.007549618095490872,
"grad_norm": NaN,
"learning_rate": 9.657457896300791e-05,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.008493320357427232,
"grad_norm": NaN,
"learning_rate": 9.535927336897098e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.009437022619363591,
"grad_norm": NaN,
"learning_rate": 9.397114317029975e-05,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.01038072488129995,
"grad_norm": NaN,
"learning_rate": 9.241613255361455e-05,
"loss": 0.0,
"step": 11
},
{
"epoch": 0.01132442714323631,
"grad_norm": NaN,
"learning_rate": 9.070090031310558e-05,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.012268129405172669,
"grad_norm": NaN,
"learning_rate": 8.883279133655399e-05,
"loss": 0.0,
"step": 13
},
{
"epoch": 0.013211831667109026,
"grad_norm": NaN,
"learning_rate": 8.681980515339464e-05,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.014155533929045385,
"grad_norm": NaN,
"learning_rate": 8.467056167950311e-05,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.015099236190981745,
"grad_norm": NaN,
"learning_rate": 8.239426430539243e-05,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.016042938452918105,
"grad_norm": NaN,
"learning_rate": 8.000066048588211e-05,
"loss": 0.0,
"step": 17
},
{
"epoch": 0.016986640714854465,
"grad_norm": NaN,
"learning_rate": 7.75e-05,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.017930342976790824,
"grad_norm": NaN,
"learning_rate": 7.490299105985507e-05,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.018874045238727183,
"grad_norm": NaN,
"learning_rate": 7.222075445642904e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.019817747500663542,
"grad_norm": NaN,
"learning_rate": 6.946477593864228e-05,
"loss": 0.0,
"step": 21
},
{
"epoch": 0.0207614497625999,
"grad_norm": NaN,
"learning_rate": 6.664685702961344e-05,
"loss": 0.0,
"step": 22
},
{
"epoch": 0.02170515202453626,
"grad_norm": NaN,
"learning_rate": 6.377906449072578e-05,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.02264885428647262,
"grad_norm": NaN,
"learning_rate": 6.087367864990233e-05,
"loss": 0.0,
"step": 24
},
{
"epoch": 0.02359255654840898,
"grad_norm": NaN,
"learning_rate": 5.794314081535644e-05,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.02359255654840898,
"eval_loss": NaN,
"eval_runtime": 3.8711,
"eval_samples_per_second": 12.916,
"eval_steps_per_second": 3.358,
"step": 25
},
{
"epoch": 0.024536258810345338,
"grad_norm": NaN,
"learning_rate": 5.500000000000001e-05,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.025479961072281693,
"grad_norm": NaN,
"learning_rate": 5.205685918464356e-05,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.026423663334218053,
"grad_norm": NaN,
"learning_rate": 4.912632135009769e-05,
"loss": 0.0,
"step": 28
},
{
"epoch": 0.02736736559615441,
"grad_norm": NaN,
"learning_rate": 4.6220935509274235e-05,
"loss": 0.0,
"step": 29
},
{
"epoch": 0.02831106785809077,
"grad_norm": NaN,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.02925477012002713,
"grad_norm": NaN,
"learning_rate": 4.053522406135775e-05,
"loss": 0.0,
"step": 31
},
{
"epoch": 0.03019847238196349,
"grad_norm": NaN,
"learning_rate": 3.777924554357096e-05,
"loss": 0.0,
"step": 32
},
{
"epoch": 0.03114217464389985,
"grad_norm": NaN,
"learning_rate": 3.509700894014496e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.03208587690583621,
"grad_norm": NaN,
"learning_rate": 3.250000000000001e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.03302957916777257,
"grad_norm": NaN,
"learning_rate": 2.9999339514117912e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.03397328142970893,
"grad_norm": NaN,
"learning_rate": 2.760573569460757e-05,
"loss": 0.0,
"step": 36
},
{
"epoch": 0.03491698369164529,
"grad_norm": NaN,
"learning_rate": 2.53294383204969e-05,
"loss": 0.0,
"step": 37
},
{
"epoch": 0.03586068595358165,
"grad_norm": NaN,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.0,
"step": 38
},
{
"epoch": 0.03680438821551801,
"grad_norm": NaN,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.0,
"step": 39
},
{
"epoch": 0.037748090477454366,
"grad_norm": NaN,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.038691792739390725,
"grad_norm": NaN,
"learning_rate": 1.758386744638546e-05,
"loss": 0.0,
"step": 41
},
{
"epoch": 0.039635495001327084,
"grad_norm": NaN,
"learning_rate": 1.602885682970026e-05,
"loss": 0.0,
"step": 42
},
{
"epoch": 0.04057919726326344,
"grad_norm": NaN,
"learning_rate": 1.464072663102903e-05,
"loss": 0.0,
"step": 43
},
{
"epoch": 0.0415228995251998,
"grad_norm": NaN,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.0,
"step": 44
},
{
"epoch": 0.04246660178713616,
"grad_norm": NaN,
"learning_rate": 1.2388144172720251e-05,
"loss": 0.0,
"step": 45
},
{
"epoch": 0.04341030404907252,
"grad_norm": NaN,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.0,
"step": 46
},
{
"epoch": 0.04435400631100888,
"grad_norm": NaN,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.0,
"step": 47
},
{
"epoch": 0.04529770857294524,
"grad_norm": NaN,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.0,
"step": 48
},
{
"epoch": 0.0462414108348816,
"grad_norm": NaN,
"learning_rate": 1.0096348454262845e-05,
"loss": 0.0,
"step": 49
},
{
"epoch": 0.04718511309681796,
"grad_norm": NaN,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.04718511309681796,
"eval_loss": NaN,
"eval_runtime": 3.8592,
"eval_samples_per_second": 12.956,
"eval_steps_per_second": 3.369,
"step": 50
}
],
"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": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.624057810649088e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}