dsakerkwq's picture
Training in progress, step 25, checkpoint
a6c8de4 verified
raw
history blame
5.15 kB
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 1.4285714285714286,
"eval_steps": 25,
"global_step": 25,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05714285714285714,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 423.1046,
"step": 1
},
{
"epoch": 0.05714285714285714,
"eval_loss": NaN,
"eval_runtime": 4.2549,
"eval_samples_per_second": 11.751,
"eval_steps_per_second": 3.055,
"step": 1
},
{
"epoch": 0.11428571428571428,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.17142857142857143,
"grad_norm": NaN,
"learning_rate": 9.990365154573717e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.22857142857142856,
"grad_norm": NaN,
"learning_rate": 9.961501876182148e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.2857142857142857,
"grad_norm": NaN,
"learning_rate": 9.913533761814537e-05,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.34285714285714286,
"grad_norm": NaN,
"learning_rate": 9.846666218300807e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.4,
"grad_norm": NaN,
"learning_rate": 9.761185582727977e-05,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.45714285714285713,
"grad_norm": NaN,
"learning_rate": 9.657457896300791e-05,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.5142857142857142,
"grad_norm": NaN,
"learning_rate": 9.535927336897098e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.5714285714285714,
"grad_norm": NaN,
"learning_rate": 9.397114317029975e-05,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.6285714285714286,
"grad_norm": NaN,
"learning_rate": 9.241613255361455e-05,
"loss": 0.0,
"step": 11
},
{
"epoch": 0.6857142857142857,
"grad_norm": NaN,
"learning_rate": 9.070090031310558e-05,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.7428571428571429,
"grad_norm": NaN,
"learning_rate": 8.883279133655399e-05,
"loss": 0.0,
"step": 13
},
{
"epoch": 0.8,
"grad_norm": NaN,
"learning_rate": 8.681980515339464e-05,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.8571428571428571,
"grad_norm": NaN,
"learning_rate": 8.467056167950311e-05,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.9142857142857143,
"grad_norm": NaN,
"learning_rate": 8.239426430539243e-05,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.9714285714285714,
"grad_norm": NaN,
"learning_rate": 8.000066048588211e-05,
"loss": 0.0,
"step": 17
},
{
"epoch": 1.0285714285714285,
"grad_norm": NaN,
"learning_rate": 7.75e-05,
"loss": 0.0,
"step": 18
},
{
"epoch": 1.0857142857142856,
"grad_norm": NaN,
"learning_rate": 7.490299105985507e-05,
"loss": 0.0,
"step": 19
},
{
"epoch": 1.1428571428571428,
"grad_norm": NaN,
"learning_rate": 7.222075445642904e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 1.2,
"grad_norm": NaN,
"learning_rate": 6.946477593864228e-05,
"loss": 0.0,
"step": 21
},
{
"epoch": 1.2571428571428571,
"grad_norm": NaN,
"learning_rate": 6.664685702961344e-05,
"loss": 0.0,
"step": 22
},
{
"epoch": 1.3142857142857143,
"grad_norm": NaN,
"learning_rate": 6.377906449072578e-05,
"loss": 0.0,
"step": 23
},
{
"epoch": 1.3714285714285714,
"grad_norm": NaN,
"learning_rate": 6.087367864990233e-05,
"loss": 0.0,
"step": 24
},
{
"epoch": 1.4285714285714286,
"grad_norm": NaN,
"learning_rate": 5.794314081535644e-05,
"loss": 0.0,
"step": 25
},
{
"epoch": 1.4285714285714286,
"eval_loss": NaN,
"eval_runtime": 2.4234,
"eval_samples_per_second": 20.632,
"eval_steps_per_second": 5.364,
"step": 25
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 2.999333202197217e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}