prxy5604's picture
Training in progress, step 50, checkpoint
851a731 verified
raw
history blame
9.96 kB
{
"best_metric": 0.2697645127773285,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.008074609390770721,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00016149218781541443,
"grad_norm": 64.24162292480469,
"learning_rate": 1e-05,
"loss": 6.8126,
"step": 1
},
{
"epoch": 0.00016149218781541443,
"eval_loss": 2.066232681274414,
"eval_runtime": 768.8275,
"eval_samples_per_second": 13.565,
"eval_steps_per_second": 3.392,
"step": 1
},
{
"epoch": 0.00032298437563082886,
"grad_norm": 56.833106994628906,
"learning_rate": 2e-05,
"loss": 5.9843,
"step": 2
},
{
"epoch": 0.0004844765634462433,
"grad_norm": 48.323463439941406,
"learning_rate": 3e-05,
"loss": 5.3251,
"step": 3
},
{
"epoch": 0.0006459687512616577,
"grad_norm": 49.74161148071289,
"learning_rate": 4e-05,
"loss": 4.4457,
"step": 4
},
{
"epoch": 0.0008074609390770722,
"grad_norm": 63.7999382019043,
"learning_rate": 5e-05,
"loss": 4.1268,
"step": 5
},
{
"epoch": 0.0009689531268924866,
"grad_norm": 27.215686798095703,
"learning_rate": 6e-05,
"loss": 3.2284,
"step": 6
},
{
"epoch": 0.001130445314707901,
"grad_norm": 53.638919830322266,
"learning_rate": 7e-05,
"loss": 2.5599,
"step": 7
},
{
"epoch": 0.0012919375025233154,
"grad_norm": 19.307762145996094,
"learning_rate": 8e-05,
"loss": 2.2425,
"step": 8
},
{
"epoch": 0.0014534296903387298,
"grad_norm": 17.659503936767578,
"learning_rate": 9e-05,
"loss": 2.1483,
"step": 9
},
{
"epoch": 0.0016149218781541443,
"grad_norm": 21.160411834716797,
"learning_rate": 0.0001,
"loss": 1.622,
"step": 10
},
{
"epoch": 0.0017764140659695586,
"grad_norm": 86.40902709960938,
"learning_rate": 9.999316524962345e-05,
"loss": 2.0168,
"step": 11
},
{
"epoch": 0.0019379062537849732,
"grad_norm": 24.150169372558594,
"learning_rate": 9.997266286704631e-05,
"loss": 1.666,
"step": 12
},
{
"epoch": 0.0020993984416003875,
"grad_norm": 15.378752708435059,
"learning_rate": 9.993849845741524e-05,
"loss": 1.5135,
"step": 13
},
{
"epoch": 0.002260890629415802,
"grad_norm": 22.235591888427734,
"learning_rate": 9.989068136093873e-05,
"loss": 1.2294,
"step": 14
},
{
"epoch": 0.0024223828172312166,
"grad_norm": 12.330756187438965,
"learning_rate": 9.98292246503335e-05,
"loss": 1.4264,
"step": 15
},
{
"epoch": 0.002583875005046631,
"grad_norm": 13.079683303833008,
"learning_rate": 9.975414512725057e-05,
"loss": 1.6981,
"step": 16
},
{
"epoch": 0.002745367192862045,
"grad_norm": 7.713149070739746,
"learning_rate": 9.966546331768191e-05,
"loss": 0.9774,
"step": 17
},
{
"epoch": 0.0029068593806774595,
"grad_norm": 7.287616729736328,
"learning_rate": 9.956320346634876e-05,
"loss": 0.9298,
"step": 18
},
{
"epoch": 0.0030683515684928743,
"grad_norm": 34.157711029052734,
"learning_rate": 9.944739353007344e-05,
"loss": 1.3756,
"step": 19
},
{
"epoch": 0.0032298437563082886,
"grad_norm": 11.063179016113281,
"learning_rate": 9.931806517013612e-05,
"loss": 1.1234,
"step": 20
},
{
"epoch": 0.003391335944123703,
"grad_norm": 15.762474060058594,
"learning_rate": 9.917525374361912e-05,
"loss": 1.2058,
"step": 21
},
{
"epoch": 0.0035528281319391172,
"grad_norm": 8.26089859008789,
"learning_rate": 9.901899829374047e-05,
"loss": 0.9081,
"step": 22
},
{
"epoch": 0.003714320319754532,
"grad_norm": 10.437385559082031,
"learning_rate": 9.884934153917997e-05,
"loss": 1.258,
"step": 23
},
{
"epoch": 0.0038758125075699463,
"grad_norm": 8.177536010742188,
"learning_rate": 9.86663298624003e-05,
"loss": 0.8721,
"step": 24
},
{
"epoch": 0.004037304695385361,
"grad_norm": 17.914628982543945,
"learning_rate": 9.847001329696653e-05,
"loss": 1.4557,
"step": 25
},
{
"epoch": 0.004198796883200775,
"grad_norm": 7.463947772979736,
"learning_rate": 9.826044551386744e-05,
"loss": 1.0969,
"step": 26
},
{
"epoch": 0.004360289071016189,
"grad_norm": 5.383772850036621,
"learning_rate": 9.803768380684242e-05,
"loss": 0.6915,
"step": 27
},
{
"epoch": 0.004521781258831604,
"grad_norm": 7.699918746948242,
"learning_rate": 9.780178907671789e-05,
"loss": 1.2951,
"step": 28
},
{
"epoch": 0.004683273446647019,
"grad_norm": 8.353910446166992,
"learning_rate": 9.755282581475769e-05,
"loss": 0.9308,
"step": 29
},
{
"epoch": 0.004844765634462433,
"grad_norm": 6.948275566101074,
"learning_rate": 9.729086208503174e-05,
"loss": 0.9263,
"step": 30
},
{
"epoch": 0.0050062578222778474,
"grad_norm": 12.072859764099121,
"learning_rate": 9.701596950580806e-05,
"loss": 1.3808,
"step": 31
},
{
"epoch": 0.005167750010093262,
"grad_norm": 7.524881839752197,
"learning_rate": 9.672822322997305e-05,
"loss": 1.0131,
"step": 32
},
{
"epoch": 0.005329242197908676,
"grad_norm": 14.655591011047363,
"learning_rate": 9.642770192448536e-05,
"loss": 1.4809,
"step": 33
},
{
"epoch": 0.00549073438572409,
"grad_norm": 11.227638244628906,
"learning_rate": 9.611448774886924e-05,
"loss": 1.4832,
"step": 34
},
{
"epoch": 0.005652226573539505,
"grad_norm": 7.202654838562012,
"learning_rate": 9.578866633275288e-05,
"loss": 1.0635,
"step": 35
},
{
"epoch": 0.005813718761354919,
"grad_norm": 5.849029064178467,
"learning_rate": 9.545032675245813e-05,
"loss": 0.9063,
"step": 36
},
{
"epoch": 0.005975210949170334,
"grad_norm": 6.742249965667725,
"learning_rate": 9.509956150664796e-05,
"loss": 1.1368,
"step": 37
},
{
"epoch": 0.0061367031369857486,
"grad_norm": 9.29891586303711,
"learning_rate": 9.473646649103818e-05,
"loss": 1.2069,
"step": 38
},
{
"epoch": 0.006298195324801163,
"grad_norm": 6.022105693817139,
"learning_rate": 9.43611409721806e-05,
"loss": 0.6348,
"step": 39
},
{
"epoch": 0.006459687512616577,
"grad_norm": 7.115547180175781,
"learning_rate": 9.397368756032445e-05,
"loss": 1.1143,
"step": 40
},
{
"epoch": 0.0066211797004319915,
"grad_norm": 7.513053894042969,
"learning_rate": 9.357421218136386e-05,
"loss": 1.2402,
"step": 41
},
{
"epoch": 0.006782671888247406,
"grad_norm": 6.634003639221191,
"learning_rate": 9.316282404787871e-05,
"loss": 0.791,
"step": 42
},
{
"epoch": 0.00694416407606282,
"grad_norm": 7.986715793609619,
"learning_rate": 9.273963562927695e-05,
"loss": 1.1034,
"step": 43
},
{
"epoch": 0.0071056562638782345,
"grad_norm": 6.973867893218994,
"learning_rate": 9.230476262104677e-05,
"loss": 1.0277,
"step": 44
},
{
"epoch": 0.00726714845169365,
"grad_norm": 7.329861640930176,
"learning_rate": 9.185832391312644e-05,
"loss": 1.1654,
"step": 45
},
{
"epoch": 0.007428640639509064,
"grad_norm": 6.630235195159912,
"learning_rate": 9.140044155740101e-05,
"loss": 0.8559,
"step": 46
},
{
"epoch": 0.007590132827324478,
"grad_norm": 7.3892621994018555,
"learning_rate": 9.093124073433463e-05,
"loss": 0.9238,
"step": 47
},
{
"epoch": 0.007751625015139893,
"grad_norm": 7.5705790519714355,
"learning_rate": 9.045084971874738e-05,
"loss": 1.1495,
"step": 48
},
{
"epoch": 0.007913117202955308,
"grad_norm": 7.095438480377197,
"learning_rate": 8.995939984474624e-05,
"loss": 1.2315,
"step": 49
},
{
"epoch": 0.008074609390770721,
"grad_norm": 9.232726097106934,
"learning_rate": 8.945702546981969e-05,
"loss": 1.279,
"step": 50
},
{
"epoch": 0.008074609390770721,
"eval_loss": 0.2697645127773285,
"eval_runtime": 773.8817,
"eval_samples_per_second": 13.476,
"eval_steps_per_second": 3.37,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"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": 7.15499809800192e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}