dada22231's picture
Training in progress, step 50, checkpoint
17bd59d verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.26542800265428,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0053085600530856005,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 3229853.25,
"step": 1
},
{
"epoch": 0.0053085600530856005,
"eval_loss": NaN,
"eval_runtime": 3.05,
"eval_samples_per_second": 16.393,
"eval_steps_per_second": 4.262,
"step": 1
},
{
"epoch": 0.010617120106171201,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.015925680159256803,
"grad_norm": NaN,
"learning_rate": 9.990365154573717e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.021234240212342402,
"grad_norm": NaN,
"learning_rate": 9.961501876182148e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.026542800265428004,
"grad_norm": NaN,
"learning_rate": 9.913533761814537e-05,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.03185136031851361,
"grad_norm": NaN,
"learning_rate": 9.846666218300807e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.0371599203715992,
"grad_norm": NaN,
"learning_rate": 9.761185582727977e-05,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.042468480424684804,
"grad_norm": NaN,
"learning_rate": 9.657457896300791e-05,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.047777040477770406,
"grad_norm": NaN,
"learning_rate": 9.535927336897098e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.05308560053085601,
"grad_norm": NaN,
"learning_rate": 9.397114317029975e-05,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.058394160583941604,
"grad_norm": NaN,
"learning_rate": 9.241613255361455e-05,
"loss": 0.0,
"step": 11
},
{
"epoch": 0.06370272063702721,
"grad_norm": NaN,
"learning_rate": 9.070090031310558e-05,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.06901128069011281,
"grad_norm": NaN,
"learning_rate": 8.883279133655399e-05,
"loss": 0.0,
"step": 13
},
{
"epoch": 0.0743198407431984,
"grad_norm": NaN,
"learning_rate": 8.681980515339464e-05,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.07962840079628401,
"grad_norm": NaN,
"learning_rate": 8.467056167950311e-05,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.08493696084936961,
"grad_norm": NaN,
"learning_rate": 8.239426430539243e-05,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.0902455209024552,
"grad_norm": NaN,
"learning_rate": 8.000066048588211e-05,
"loss": 0.0,
"step": 17
},
{
"epoch": 0.09555408095554081,
"grad_norm": NaN,
"learning_rate": 7.75e-05,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.10086264100862641,
"grad_norm": NaN,
"learning_rate": 7.490299105985507e-05,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.10617120106171202,
"grad_norm": NaN,
"learning_rate": 7.222075445642904e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.11147976111479761,
"grad_norm": NaN,
"learning_rate": 6.946477593864228e-05,
"loss": 0.0,
"step": 21
},
{
"epoch": 0.11678832116788321,
"grad_norm": NaN,
"learning_rate": 6.664685702961344e-05,
"loss": 0.0,
"step": 22
},
{
"epoch": 0.12209688122096882,
"grad_norm": NaN,
"learning_rate": 6.377906449072578e-05,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.12740544127405443,
"grad_norm": NaN,
"learning_rate": 6.087367864990233e-05,
"loss": 0.0,
"step": 24
},
{
"epoch": 0.13271400132714,
"grad_norm": NaN,
"learning_rate": 5.794314081535644e-05,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.13271400132714,
"eval_loss": NaN,
"eval_runtime": 2.4132,
"eval_samples_per_second": 20.719,
"eval_steps_per_second": 5.387,
"step": 25
},
{
"epoch": 0.13802256138022562,
"grad_norm": NaN,
"learning_rate": 5.500000000000001e-05,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.14333112143331123,
"grad_norm": NaN,
"learning_rate": 5.205685918464356e-05,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.1486396814863968,
"grad_norm": NaN,
"learning_rate": 4.912632135009769e-05,
"loss": 0.0,
"step": 28
},
{
"epoch": 0.15394824153948242,
"grad_norm": NaN,
"learning_rate": 4.6220935509274235e-05,
"loss": 0.0,
"step": 29
},
{
"epoch": 0.15925680159256803,
"grad_norm": NaN,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.1645653616456536,
"grad_norm": NaN,
"learning_rate": 4.053522406135775e-05,
"loss": 0.0,
"step": 31
},
{
"epoch": 0.16987392169873922,
"grad_norm": NaN,
"learning_rate": 3.777924554357096e-05,
"loss": 0.0,
"step": 32
},
{
"epoch": 0.17518248175182483,
"grad_norm": NaN,
"learning_rate": 3.509700894014496e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.1804910418049104,
"grad_norm": NaN,
"learning_rate": 3.250000000000001e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.18579960185799602,
"grad_norm": NaN,
"learning_rate": 2.9999339514117912e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.19110816191108163,
"grad_norm": NaN,
"learning_rate": 2.760573569460757e-05,
"loss": 0.0,
"step": 36
},
{
"epoch": 0.1964167219641672,
"grad_norm": NaN,
"learning_rate": 2.53294383204969e-05,
"loss": 0.0,
"step": 37
},
{
"epoch": 0.20172528201725282,
"grad_norm": NaN,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.0,
"step": 38
},
{
"epoch": 0.20703384207033843,
"grad_norm": NaN,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.0,
"step": 39
},
{
"epoch": 0.21234240212342403,
"grad_norm": NaN,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.21765096217650962,
"grad_norm": NaN,
"learning_rate": 1.758386744638546e-05,
"loss": 0.0,
"step": 41
},
{
"epoch": 0.22295952222959523,
"grad_norm": NaN,
"learning_rate": 1.602885682970026e-05,
"loss": 0.0,
"step": 42
},
{
"epoch": 0.22826808228268083,
"grad_norm": NaN,
"learning_rate": 1.464072663102903e-05,
"loss": 0.0,
"step": 43
},
{
"epoch": 0.23357664233576642,
"grad_norm": NaN,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.0,
"step": 44
},
{
"epoch": 0.23888520238885202,
"grad_norm": NaN,
"learning_rate": 1.2388144172720251e-05,
"loss": 0.0,
"step": 45
},
{
"epoch": 0.24419376244193763,
"grad_norm": NaN,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.0,
"step": 46
},
{
"epoch": 0.24950232249502322,
"grad_norm": NaN,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.0,
"step": 47
},
{
"epoch": 0.25481088254810885,
"grad_norm": NaN,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.0,
"step": 48
},
{
"epoch": 0.2601194426011944,
"grad_norm": NaN,
"learning_rate": 1.0096348454262845e-05,
"loss": 0.0,
"step": 49
},
{
"epoch": 0.26542800265428,
"grad_norm": NaN,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.26542800265428,
"eval_loss": NaN,
"eval_runtime": 2.4124,
"eval_samples_per_second": 20.726,
"eval_steps_per_second": 5.389,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.433368219315077e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}