dsakerkwq's picture
Training in progress, step 50, checkpoint
9620784 verified
{
"best_metric": 0.8612193465232849,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.4471771939631079,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008943543879262158,
"grad_norm": 1.6034036874771118,
"learning_rate": 5e-05,
"loss": 2.0042,
"step": 1
},
{
"epoch": 0.008943543879262158,
"eval_loss": 2.528956651687622,
"eval_runtime": 3.0627,
"eval_samples_per_second": 16.325,
"eval_steps_per_second": 4.245,
"step": 1
},
{
"epoch": 0.017887087758524316,
"grad_norm": 2.0309529304504395,
"learning_rate": 0.0001,
"loss": 2.2542,
"step": 2
},
{
"epoch": 0.026830631637786474,
"grad_norm": 2.1161091327667236,
"learning_rate": 9.990365154573717e-05,
"loss": 2.2194,
"step": 3
},
{
"epoch": 0.03577417551704863,
"grad_norm": 1.973645806312561,
"learning_rate": 9.961501876182148e-05,
"loss": 1.8558,
"step": 4
},
{
"epoch": 0.044717719396310786,
"grad_norm": 1.8131190538406372,
"learning_rate": 9.913533761814537e-05,
"loss": 1.5723,
"step": 5
},
{
"epoch": 0.05366126327557295,
"grad_norm": 1.827698826789856,
"learning_rate": 9.846666218300807e-05,
"loss": 1.3832,
"step": 6
},
{
"epoch": 0.0626048071548351,
"grad_norm": 1.5256693363189697,
"learning_rate": 9.761185582727977e-05,
"loss": 1.1542,
"step": 7
},
{
"epoch": 0.07154835103409726,
"grad_norm": 1.4922664165496826,
"learning_rate": 9.657457896300791e-05,
"loss": 1.0479,
"step": 8
},
{
"epoch": 0.08049189491335942,
"grad_norm": 1.3781952857971191,
"learning_rate": 9.535927336897098e-05,
"loss": 1.0203,
"step": 9
},
{
"epoch": 0.08943543879262157,
"grad_norm": 1.1746207475662231,
"learning_rate": 9.397114317029975e-05,
"loss": 0.9778,
"step": 10
},
{
"epoch": 0.09837898267188373,
"grad_norm": 1.271547555923462,
"learning_rate": 9.241613255361455e-05,
"loss": 0.8457,
"step": 11
},
{
"epoch": 0.1073225265511459,
"grad_norm": 1.2619582414627075,
"learning_rate": 9.070090031310558e-05,
"loss": 0.7822,
"step": 12
},
{
"epoch": 0.11626607043040806,
"grad_norm": 1.9864858388900757,
"learning_rate": 8.883279133655399e-05,
"loss": 1.1765,
"step": 13
},
{
"epoch": 0.1252096143096702,
"grad_norm": 1.6848101615905762,
"learning_rate": 8.681980515339464e-05,
"loss": 1.1487,
"step": 14
},
{
"epoch": 0.13415315818893236,
"grad_norm": 1.0620079040527344,
"learning_rate": 8.467056167950311e-05,
"loss": 1.1011,
"step": 15
},
{
"epoch": 0.14309670206819453,
"grad_norm": 0.9581196904182434,
"learning_rate": 8.239426430539243e-05,
"loss": 1.0347,
"step": 16
},
{
"epoch": 0.1520402459474567,
"grad_norm": 0.7690842151641846,
"learning_rate": 8.000066048588211e-05,
"loss": 0.9651,
"step": 17
},
{
"epoch": 0.16098378982671885,
"grad_norm": 0.6595637798309326,
"learning_rate": 7.75e-05,
"loss": 0.9663,
"step": 18
},
{
"epoch": 0.16992733370598098,
"grad_norm": 0.7132859826087952,
"learning_rate": 7.490299105985507e-05,
"loss": 0.8864,
"step": 19
},
{
"epoch": 0.17887087758524314,
"grad_norm": 0.7359153628349304,
"learning_rate": 7.222075445642904e-05,
"loss": 0.8797,
"step": 20
},
{
"epoch": 0.1878144214645053,
"grad_norm": 0.508012056350708,
"learning_rate": 6.946477593864228e-05,
"loss": 0.8597,
"step": 21
},
{
"epoch": 0.19675796534376747,
"grad_norm": 0.6174442768096924,
"learning_rate": 6.664685702961344e-05,
"loss": 0.8164,
"step": 22
},
{
"epoch": 0.20570150922302963,
"grad_norm": 0.6644861102104187,
"learning_rate": 6.377906449072578e-05,
"loss": 0.7973,
"step": 23
},
{
"epoch": 0.2146450531022918,
"grad_norm": 0.5388149619102478,
"learning_rate": 6.087367864990233e-05,
"loss": 0.7638,
"step": 24
},
{
"epoch": 0.22358859698155395,
"grad_norm": 0.6271304488182068,
"learning_rate": 5.794314081535644e-05,
"loss": 0.7344,
"step": 25
},
{
"epoch": 0.22358859698155395,
"eval_loss": 0.9329157471656799,
"eval_runtime": 3.0643,
"eval_samples_per_second": 16.317,
"eval_steps_per_second": 4.242,
"step": 25
},
{
"epoch": 0.2325321408608161,
"grad_norm": 1.5254967212677002,
"learning_rate": 5.500000000000001e-05,
"loss": 1.1298,
"step": 26
},
{
"epoch": 0.24147568474007824,
"grad_norm": 1.5145419836044312,
"learning_rate": 5.205685918464356e-05,
"loss": 1.1004,
"step": 27
},
{
"epoch": 0.2504192286193404,
"grad_norm": 1.1959255933761597,
"learning_rate": 4.912632135009769e-05,
"loss": 1.0102,
"step": 28
},
{
"epoch": 0.25936277249860257,
"grad_norm": 0.8409033417701721,
"learning_rate": 4.6220935509274235e-05,
"loss": 0.9419,
"step": 29
},
{
"epoch": 0.26830631637786473,
"grad_norm": 0.5640770196914673,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.9541,
"step": 30
},
{
"epoch": 0.2772498602571269,
"grad_norm": 0.5304577946662903,
"learning_rate": 4.053522406135775e-05,
"loss": 0.8527,
"step": 31
},
{
"epoch": 0.28619340413638905,
"grad_norm": 0.7212780714035034,
"learning_rate": 3.777924554357096e-05,
"loss": 0.8461,
"step": 32
},
{
"epoch": 0.2951369480156512,
"grad_norm": 0.9113336801528931,
"learning_rate": 3.509700894014496e-05,
"loss": 0.8521,
"step": 33
},
{
"epoch": 0.3040804918949134,
"grad_norm": 0.9317920804023743,
"learning_rate": 3.250000000000001e-05,
"loss": 0.8544,
"step": 34
},
{
"epoch": 0.31302403577417554,
"grad_norm": 0.8762340545654297,
"learning_rate": 2.9999339514117912e-05,
"loss": 0.813,
"step": 35
},
{
"epoch": 0.3219675796534377,
"grad_norm": 0.7749875783920288,
"learning_rate": 2.760573569460757e-05,
"loss": 0.7464,
"step": 36
},
{
"epoch": 0.33091112353269986,
"grad_norm": 0.6698021292686462,
"learning_rate": 2.53294383204969e-05,
"loss": 0.6547,
"step": 37
},
{
"epoch": 0.33985466741196196,
"grad_norm": 0.6533907651901245,
"learning_rate": 2.3180194846605367e-05,
"loss": 1.0302,
"step": 38
},
{
"epoch": 0.3487982112912241,
"grad_norm": 0.8068573474884033,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.9967,
"step": 39
},
{
"epoch": 0.3577417551704863,
"grad_norm": 0.816889226436615,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.9799,
"step": 40
},
{
"epoch": 0.36668529904974845,
"grad_norm": 0.8150957226753235,
"learning_rate": 1.758386744638546e-05,
"loss": 0.9593,
"step": 41
},
{
"epoch": 0.3756288429290106,
"grad_norm": 0.7163166999816895,
"learning_rate": 1.602885682970026e-05,
"loss": 0.9513,
"step": 42
},
{
"epoch": 0.38457238680827277,
"grad_norm": 0.5624445080757141,
"learning_rate": 1.464072663102903e-05,
"loss": 0.8999,
"step": 43
},
{
"epoch": 0.39351593068753493,
"grad_norm": 0.5166836977005005,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.8222,
"step": 44
},
{
"epoch": 0.4024594745667971,
"grad_norm": 0.42919614911079407,
"learning_rate": 1.2388144172720251e-05,
"loss": 0.7809,
"step": 45
},
{
"epoch": 0.41140301844605925,
"grad_norm": 0.43555784225463867,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.81,
"step": 46
},
{
"epoch": 0.4203465623253214,
"grad_norm": 0.50513756275177,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.8089,
"step": 47
},
{
"epoch": 0.4292901062045836,
"grad_norm": 0.6194409728050232,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.8606,
"step": 48
},
{
"epoch": 0.43823365008384574,
"grad_norm": 0.7608831524848938,
"learning_rate": 1.0096348454262845e-05,
"loss": 0.768,
"step": 49
},
{
"epoch": 0.4471771939631079,
"grad_norm": 0.9651173949241638,
"learning_rate": 1e-05,
"loss": 0.6667,
"step": 50
},
{
"epoch": 0.4471771939631079,
"eval_loss": 0.8612193465232849,
"eval_runtime": 3.0064,
"eval_samples_per_second": 16.631,
"eval_steps_per_second": 4.324,
"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": 5.968083617316864e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}