eeeebbb2's picture
Training in progress, step 50, checkpoint
06e9641 verified
{
"best_metric": 1.7397328615188599,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.6843455945252352,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013686911890504704,
"grad_norm": 3.5519964694976807,
"learning_rate": 5e-05,
"loss": 2.6238,
"step": 1
},
{
"epoch": 0.013686911890504704,
"eval_loss": 2.510066032409668,
"eval_runtime": 1.4277,
"eval_samples_per_second": 35.022,
"eval_steps_per_second": 9.106,
"step": 1
},
{
"epoch": 0.02737382378100941,
"grad_norm": 3.9097886085510254,
"learning_rate": 0.0001,
"loss": 2.5922,
"step": 2
},
{
"epoch": 0.041060735671514116,
"grad_norm": 3.009646415710449,
"learning_rate": 9.990365154573717e-05,
"loss": 2.4626,
"step": 3
},
{
"epoch": 0.05474764756201882,
"grad_norm": 1.4690567255020142,
"learning_rate": 9.961501876182148e-05,
"loss": 2.2031,
"step": 4
},
{
"epoch": 0.06843455945252352,
"grad_norm": 1.273396372795105,
"learning_rate": 9.913533761814537e-05,
"loss": 2.1429,
"step": 5
},
{
"epoch": 0.08212147134302823,
"grad_norm": 1.393515706062317,
"learning_rate": 9.846666218300807e-05,
"loss": 2.1578,
"step": 6
},
{
"epoch": 0.09580838323353294,
"grad_norm": 1.231740951538086,
"learning_rate": 9.761185582727977e-05,
"loss": 2.0476,
"step": 7
},
{
"epoch": 0.10949529512403763,
"grad_norm": 1.1027367115020752,
"learning_rate": 9.657457896300791e-05,
"loss": 2.0734,
"step": 8
},
{
"epoch": 0.12318220701454234,
"grad_norm": 0.9736797213554382,
"learning_rate": 9.535927336897098e-05,
"loss": 1.9517,
"step": 9
},
{
"epoch": 0.13686911890504705,
"grad_norm": 0.9888503551483154,
"learning_rate": 9.397114317029975e-05,
"loss": 1.8553,
"step": 10
},
{
"epoch": 0.15055603079555174,
"grad_norm": 1.1054013967514038,
"learning_rate": 9.241613255361455e-05,
"loss": 1.9181,
"step": 11
},
{
"epoch": 0.16424294268605646,
"grad_norm": 1.6251250505447388,
"learning_rate": 9.070090031310558e-05,
"loss": 1.9581,
"step": 12
},
{
"epoch": 0.17792985457656116,
"grad_norm": 1.1294256448745728,
"learning_rate": 8.883279133655399e-05,
"loss": 2.1365,
"step": 13
},
{
"epoch": 0.19161676646706588,
"grad_norm": 1.0606149435043335,
"learning_rate": 8.681980515339464e-05,
"loss": 2.1498,
"step": 14
},
{
"epoch": 0.20530367835757057,
"grad_norm": 0.9681658148765564,
"learning_rate": 8.467056167950311e-05,
"loss": 2.0584,
"step": 15
},
{
"epoch": 0.21899059024807527,
"grad_norm": 0.8431066274642944,
"learning_rate": 8.239426430539243e-05,
"loss": 1.983,
"step": 16
},
{
"epoch": 0.23267750213858,
"grad_norm": 0.7003775238990784,
"learning_rate": 8.000066048588211e-05,
"loss": 1.9914,
"step": 17
},
{
"epoch": 0.24636441402908468,
"grad_norm": 0.6081887483596802,
"learning_rate": 7.75e-05,
"loss": 1.8748,
"step": 18
},
{
"epoch": 0.2600513259195894,
"grad_norm": 0.697636604309082,
"learning_rate": 7.490299105985507e-05,
"loss": 1.8987,
"step": 19
},
{
"epoch": 0.2737382378100941,
"grad_norm": 0.8715171813964844,
"learning_rate": 7.222075445642904e-05,
"loss": 1.8876,
"step": 20
},
{
"epoch": 0.2874251497005988,
"grad_norm": 0.9008734226226807,
"learning_rate": 6.946477593864228e-05,
"loss": 1.8261,
"step": 21
},
{
"epoch": 0.3011120615911035,
"grad_norm": 1.0205512046813965,
"learning_rate": 6.664685702961344e-05,
"loss": 1.8614,
"step": 22
},
{
"epoch": 0.31479897348160824,
"grad_norm": 1.0061066150665283,
"learning_rate": 6.377906449072578e-05,
"loss": 1.7655,
"step": 23
},
{
"epoch": 0.32848588537211293,
"grad_norm": 1.2503756284713745,
"learning_rate": 6.087367864990233e-05,
"loss": 1.6487,
"step": 24
},
{
"epoch": 0.3421727972626176,
"grad_norm": 2.48714017868042,
"learning_rate": 5.794314081535644e-05,
"loss": 1.8124,
"step": 25
},
{
"epoch": 0.3421727972626176,
"eval_loss": 1.7811026573181152,
"eval_runtime": 1.4616,
"eval_samples_per_second": 34.21,
"eval_steps_per_second": 8.895,
"step": 25
},
{
"epoch": 0.3558597091531223,
"grad_norm": 0.7591701149940491,
"learning_rate": 5.500000000000001e-05,
"loss": 2.0127,
"step": 26
},
{
"epoch": 0.369546621043627,
"grad_norm": 0.9103983044624329,
"learning_rate": 5.205685918464356e-05,
"loss": 1.9637,
"step": 27
},
{
"epoch": 0.38323353293413176,
"grad_norm": 0.8943213820457458,
"learning_rate": 4.912632135009769e-05,
"loss": 1.9139,
"step": 28
},
{
"epoch": 0.39692044482463645,
"grad_norm": 0.8365579843521118,
"learning_rate": 4.6220935509274235e-05,
"loss": 1.9006,
"step": 29
},
{
"epoch": 0.41060735671514115,
"grad_norm": 0.8076335787773132,
"learning_rate": 4.3353142970386564e-05,
"loss": 1.9083,
"step": 30
},
{
"epoch": 0.42429426860564584,
"grad_norm": 0.7735624313354492,
"learning_rate": 4.053522406135775e-05,
"loss": 1.8956,
"step": 31
},
{
"epoch": 0.43798118049615054,
"grad_norm": 0.7214319705963135,
"learning_rate": 3.777924554357096e-05,
"loss": 1.8705,
"step": 32
},
{
"epoch": 0.4516680923866553,
"grad_norm": 0.7641725540161133,
"learning_rate": 3.509700894014496e-05,
"loss": 1.8121,
"step": 33
},
{
"epoch": 0.46535500427716,
"grad_norm": 0.7683237195014954,
"learning_rate": 3.250000000000001e-05,
"loss": 1.7478,
"step": 34
},
{
"epoch": 0.47904191616766467,
"grad_norm": 0.8942069411277771,
"learning_rate": 2.9999339514117912e-05,
"loss": 1.7379,
"step": 35
},
{
"epoch": 0.49272882805816937,
"grad_norm": 1.1086134910583496,
"learning_rate": 2.760573569460757e-05,
"loss": 1.6556,
"step": 36
},
{
"epoch": 0.5064157399486741,
"grad_norm": 1.8508061170578003,
"learning_rate": 2.53294383204969e-05,
"loss": 1.7596,
"step": 37
},
{
"epoch": 0.5201026518391788,
"grad_norm": 0.5953439474105835,
"learning_rate": 2.3180194846605367e-05,
"loss": 1.9416,
"step": 38
},
{
"epoch": 0.5337895637296834,
"grad_norm": 0.5514473915100098,
"learning_rate": 2.1167208663446025e-05,
"loss": 1.9681,
"step": 39
},
{
"epoch": 0.5474764756201882,
"grad_norm": 0.5643142461776733,
"learning_rate": 1.9299099686894423e-05,
"loss": 1.9015,
"step": 40
},
{
"epoch": 0.561163387510693,
"grad_norm": 0.6523820161819458,
"learning_rate": 1.758386744638546e-05,
"loss": 1.9157,
"step": 41
},
{
"epoch": 0.5748502994011976,
"grad_norm": 0.6224381923675537,
"learning_rate": 1.602885682970026e-05,
"loss": 1.8996,
"step": 42
},
{
"epoch": 0.5885372112917023,
"grad_norm": 0.6665676236152649,
"learning_rate": 1.464072663102903e-05,
"loss": 1.831,
"step": 43
},
{
"epoch": 0.602224123182207,
"grad_norm": 0.7095207571983337,
"learning_rate": 1.3425421036992098e-05,
"loss": 1.8424,
"step": 44
},
{
"epoch": 0.6159110350727117,
"grad_norm": 0.6559857726097107,
"learning_rate": 1.2388144172720251e-05,
"loss": 1.7975,
"step": 45
},
{
"epoch": 0.6295979469632165,
"grad_norm": 0.7268767952919006,
"learning_rate": 1.1533337816991932e-05,
"loss": 1.8395,
"step": 46
},
{
"epoch": 0.6432848588537211,
"grad_norm": 0.7550267577171326,
"learning_rate": 1.0864662381854632e-05,
"loss": 1.7475,
"step": 47
},
{
"epoch": 0.6569717707442259,
"grad_norm": 0.9330142140388489,
"learning_rate": 1.0384981238178534e-05,
"loss": 1.7608,
"step": 48
},
{
"epoch": 0.6706586826347305,
"grad_norm": 1.2081230878829956,
"learning_rate": 1.0096348454262845e-05,
"loss": 1.7007,
"step": 49
},
{
"epoch": 0.6843455945252352,
"grad_norm": 2.4048612117767334,
"learning_rate": 1e-05,
"loss": 1.7784,
"step": 50
},
{
"epoch": 0.6843455945252352,
"eval_loss": 1.7397328615188599,
"eval_runtime": 1.4629,
"eval_samples_per_second": 34.18,
"eval_steps_per_second": 8.887,
"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": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.589463780163584e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}