dada22231's picture
Training in progress, step 50, checkpoint
70e29b8 verified
raw
history blame
10 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.06325110689437065,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001265022137887413,
"grad_norm": 35.139339447021484,
"learning_rate": 5e-05,
"loss": 4.1852,
"step": 1
},
{
"epoch": 0.001265022137887413,
"eval_loss": 2.3645200729370117,
"eval_runtime": 4.0111,
"eval_samples_per_second": 12.465,
"eval_steps_per_second": 3.241,
"step": 1
},
{
"epoch": 0.002530044275774826,
"grad_norm": 7.04626989364624,
"learning_rate": 0.0001,
"loss": 1.8438,
"step": 2
},
{
"epoch": 0.003795066413662239,
"grad_norm": 1.121877670288086,
"learning_rate": 9.990365154573717e-05,
"loss": 1.9922,
"step": 3
},
{
"epoch": 0.005060088551549652,
"grad_norm": 1.3969320058822632,
"learning_rate": 9.961501876182148e-05,
"loss": 2.0901,
"step": 4
},
{
"epoch": 0.006325110689437065,
"grad_norm": 0.9031108021736145,
"learning_rate": 9.913533761814537e-05,
"loss": 2.0232,
"step": 5
},
{
"epoch": 0.007590132827324478,
"grad_norm": 0.9523929953575134,
"learning_rate": 9.846666218300807e-05,
"loss": 2.0277,
"step": 6
},
{
"epoch": 0.008855154965211892,
"grad_norm": 0.9598959684371948,
"learning_rate": 9.761185582727977e-05,
"loss": 2.0421,
"step": 7
},
{
"epoch": 0.010120177103099304,
"grad_norm": 1.3133834600448608,
"learning_rate": 9.657457896300791e-05,
"loss": 2.0316,
"step": 8
},
{
"epoch": 0.011385199240986717,
"grad_norm": 10.652119636535645,
"learning_rate": 9.535927336897098e-05,
"loss": 1.9813,
"step": 9
},
{
"epoch": 0.01265022137887413,
"grad_norm": 2.1253440380096436,
"learning_rate": 9.397114317029975e-05,
"loss": 2.0884,
"step": 10
},
{
"epoch": 0.013915243516761544,
"grad_norm": 1.9068113565444946,
"learning_rate": 9.241613255361455e-05,
"loss": 2.1017,
"step": 11
},
{
"epoch": 0.015180265654648957,
"grad_norm": 1.6747380495071411,
"learning_rate": 9.070090031310558e-05,
"loss": 2.2796,
"step": 12
},
{
"epoch": 0.01644528779253637,
"grad_norm": 29.196680068969727,
"learning_rate": 8.883279133655399e-05,
"loss": 7.4892,
"step": 13
},
{
"epoch": 0.017710309930423784,
"grad_norm": 2.4710311889648438,
"learning_rate": 8.681980515339464e-05,
"loss": 1.8346,
"step": 14
},
{
"epoch": 0.018975332068311195,
"grad_norm": 1.579148292541504,
"learning_rate": 8.467056167950311e-05,
"loss": 1.9865,
"step": 15
},
{
"epoch": 0.02024035420619861,
"grad_norm": 1.1874217987060547,
"learning_rate": 8.239426430539243e-05,
"loss": 1.8998,
"step": 16
},
{
"epoch": 0.021505376344086023,
"grad_norm": 0.92023766040802,
"learning_rate": 8.000066048588211e-05,
"loss": 1.8687,
"step": 17
},
{
"epoch": 0.022770398481973434,
"grad_norm": 0.9192359447479248,
"learning_rate": 7.75e-05,
"loss": 1.9686,
"step": 18
},
{
"epoch": 0.02403542061986085,
"grad_norm": 3.2033963203430176,
"learning_rate": 7.490299105985507e-05,
"loss": 2.1434,
"step": 19
},
{
"epoch": 0.02530044275774826,
"grad_norm": 1.0458755493164062,
"learning_rate": 7.222075445642904e-05,
"loss": 2.0357,
"step": 20
},
{
"epoch": 0.026565464895635674,
"grad_norm": 1.1212831735610962,
"learning_rate": 6.946477593864228e-05,
"loss": 1.8479,
"step": 21
},
{
"epoch": 0.027830487033523088,
"grad_norm": 1.1566752195358276,
"learning_rate": 6.664685702961344e-05,
"loss": 2.0032,
"step": 22
},
{
"epoch": 0.0290955091714105,
"grad_norm": 1.2244004011154175,
"learning_rate": 6.377906449072578e-05,
"loss": 2.0365,
"step": 23
},
{
"epoch": 0.030360531309297913,
"grad_norm": 1.3064579963684082,
"learning_rate": 6.087367864990233e-05,
"loss": 2.1573,
"step": 24
},
{
"epoch": 0.031625553447185324,
"grad_norm": 1.693029522895813,
"learning_rate": 5.794314081535644e-05,
"loss": 2.2897,
"step": 25
},
{
"epoch": 0.031625553447185324,
"eval_loss": 1.932918667793274,
"eval_runtime": 4.0675,
"eval_samples_per_second": 12.293,
"eval_steps_per_second": 3.196,
"step": 25
},
{
"epoch": 0.03289057558507274,
"grad_norm": 37.96943283081055,
"learning_rate": 5.500000000000001e-05,
"loss": 5.7969,
"step": 26
},
{
"epoch": 0.03415559772296015,
"grad_norm": 1.5687322616577148,
"learning_rate": 5.205685918464356e-05,
"loss": 1.7264,
"step": 27
},
{
"epoch": 0.03542061986084757,
"grad_norm": 1.1628891229629517,
"learning_rate": 4.912632135009769e-05,
"loss": 1.8082,
"step": 28
},
{
"epoch": 0.036685641998734975,
"grad_norm": 0.8394140005111694,
"learning_rate": 4.6220935509274235e-05,
"loss": 1.9195,
"step": 29
},
{
"epoch": 0.03795066413662239,
"grad_norm": 0.9346224665641785,
"learning_rate": 4.3353142970386564e-05,
"loss": 1.9093,
"step": 30
},
{
"epoch": 0.0392156862745098,
"grad_norm": 0.9901193976402283,
"learning_rate": 4.053522406135775e-05,
"loss": 2.0222,
"step": 31
},
{
"epoch": 0.04048070841239722,
"grad_norm": 0.9796273112297058,
"learning_rate": 3.777924554357096e-05,
"loss": 1.9273,
"step": 32
},
{
"epoch": 0.04174573055028463,
"grad_norm": 0.9287394881248474,
"learning_rate": 3.509700894014496e-05,
"loss": 1.9015,
"step": 33
},
{
"epoch": 0.043010752688172046,
"grad_norm": 0.9738181233406067,
"learning_rate": 3.250000000000001e-05,
"loss": 1.7521,
"step": 34
},
{
"epoch": 0.044275774826059454,
"grad_norm": 1.0583573579788208,
"learning_rate": 2.9999339514117912e-05,
"loss": 2.0511,
"step": 35
},
{
"epoch": 0.04554079696394687,
"grad_norm": 1.0245318412780762,
"learning_rate": 2.760573569460757e-05,
"loss": 2.1022,
"step": 36
},
{
"epoch": 0.04680581910183428,
"grad_norm": 1.2444181442260742,
"learning_rate": 2.53294383204969e-05,
"loss": 2.0539,
"step": 37
},
{
"epoch": 0.0480708412397217,
"grad_norm": 24.339767456054688,
"learning_rate": 2.3180194846605367e-05,
"loss": 3.6826,
"step": 38
},
{
"epoch": 0.04933586337760911,
"grad_norm": 0.6691582202911377,
"learning_rate": 2.1167208663446025e-05,
"loss": 1.6845,
"step": 39
},
{
"epoch": 0.05060088551549652,
"grad_norm": 0.7083836793899536,
"learning_rate": 1.9299099686894423e-05,
"loss": 1.776,
"step": 40
},
{
"epoch": 0.05186590765338393,
"grad_norm": 0.7264069318771362,
"learning_rate": 1.758386744638546e-05,
"loss": 1.8355,
"step": 41
},
{
"epoch": 0.05313092979127135,
"grad_norm": 0.7508512139320374,
"learning_rate": 1.602885682970026e-05,
"loss": 1.8773,
"step": 42
},
{
"epoch": 0.05439595192915876,
"grad_norm": 0.7919434905052185,
"learning_rate": 1.464072663102903e-05,
"loss": 1.8648,
"step": 43
},
{
"epoch": 0.055660974067046176,
"grad_norm": 0.8442027568817139,
"learning_rate": 1.3425421036992098e-05,
"loss": 1.7584,
"step": 44
},
{
"epoch": 0.056925996204933584,
"grad_norm": 0.8228534460067749,
"learning_rate": 1.2388144172720251e-05,
"loss": 1.9638,
"step": 45
},
{
"epoch": 0.058191018342821,
"grad_norm": 0.8046168088912964,
"learning_rate": 1.1533337816991932e-05,
"loss": 1.8872,
"step": 46
},
{
"epoch": 0.05945604048070841,
"grad_norm": 0.8686741590499878,
"learning_rate": 1.0864662381854632e-05,
"loss": 1.89,
"step": 47
},
{
"epoch": 0.06072106261859583,
"grad_norm": 0.9693074226379395,
"learning_rate": 1.0384981238178534e-05,
"loss": 1.9709,
"step": 48
},
{
"epoch": 0.06198608475648324,
"grad_norm": 1.1496561765670776,
"learning_rate": 1.0096348454262845e-05,
"loss": 2.0629,
"step": 49
},
{
"epoch": 0.06325110689437065,
"grad_norm": 1.4522725343704224,
"learning_rate": 1e-05,
"loss": 2.1552,
"step": 50
},
{
"epoch": 0.06325110689437065,
"eval_loss": 1.9020295143127441,
"eval_runtime": 4.0552,
"eval_samples_per_second": 12.33,
"eval_steps_per_second": 3.206,
"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": 6.174479344467968e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}