dada22231's picture
Training in progress, step 50, checkpoint
97c5954 verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 1.7718715393133997,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.035437430786267994,
"grad_norm": NaN,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.0,
"step": 1
},
{
"epoch": 0.035437430786267994,
"eval_loss": NaN,
"eval_runtime": 7.9204,
"eval_samples_per_second": 6.313,
"eval_steps_per_second": 1.641,
"step": 1
},
{
"epoch": 0.07087486157253599,
"grad_norm": NaN,
"learning_rate": 6.666666666666667e-05,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.10631229235880399,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.14174972314507198,
"grad_norm": NaN,
"learning_rate": 9.99571699711836e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.17718715393134,
"grad_norm": NaN,
"learning_rate": 9.982876141412856e-05,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.21262458471760798,
"grad_norm": NaN,
"learning_rate": 9.961501876182148e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.24806201550387597,
"grad_norm": NaN,
"learning_rate": 9.931634888554937e-05,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.28349944629014395,
"grad_norm": NaN,
"learning_rate": 9.893332032039701e-05,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.31893687707641194,
"grad_norm": NaN,
"learning_rate": 9.846666218300807e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.35437430786268,
"grad_norm": NaN,
"learning_rate": 9.791726278367022e-05,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.38981173864894797,
"grad_norm": NaN,
"learning_rate": 9.728616793536588e-05,
"loss": 0.0,
"step": 11
},
{
"epoch": 0.42524916943521596,
"grad_norm": NaN,
"learning_rate": 9.657457896300791e-05,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.46068660022148394,
"grad_norm": NaN,
"learning_rate": 9.578385041664925e-05,
"loss": 0.0,
"step": 13
},
{
"epoch": 0.49612403100775193,
"grad_norm": NaN,
"learning_rate": 9.491548749301997e-05,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.53156146179402,
"grad_norm": NaN,
"learning_rate": 9.397114317029975e-05,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.5669988925802879,
"grad_norm": NaN,
"learning_rate": 9.295261506157986e-05,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.602436323366556,
"grad_norm": NaN,
"learning_rate": 9.186184199300464e-05,
"loss": 0.0,
"step": 17
},
{
"epoch": 0.6378737541528239,
"grad_norm": NaN,
"learning_rate": 9.070090031310558e-05,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.6733111849390919,
"grad_norm": NaN,
"learning_rate": 8.947199994035401e-05,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.70874861572536,
"grad_norm": NaN,
"learning_rate": 8.817748015645558e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.7441860465116279,
"grad_norm": NaN,
"learning_rate": 8.681980515339464e-05,
"loss": 0.0,
"step": 21
},
{
"epoch": 0.7796234772978959,
"grad_norm": NaN,
"learning_rate": 8.540155934270471e-05,
"loss": 0.0,
"step": 22
},
{
"epoch": 0.8150609080841639,
"grad_norm": NaN,
"learning_rate": 8.392544243589427e-05,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.8504983388704319,
"grad_norm": NaN,
"learning_rate": 8.239426430539243e-05,
"loss": 0.0,
"step": 24
},
{
"epoch": 0.8859357696566998,
"grad_norm": NaN,
"learning_rate": 8.081093963579707e-05,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.8859357696566998,
"eval_loss": NaN,
"eval_runtime": 7.6004,
"eval_samples_per_second": 6.579,
"eval_steps_per_second": 1.71,
"step": 25
},
{
"epoch": 0.9213732004429679,
"grad_norm": NaN,
"learning_rate": 7.917848237560709e-05,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.9568106312292359,
"grad_norm": NaN,
"learning_rate": 7.75e-05,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.9922480620155039,
"grad_norm": NaN,
"learning_rate": 7.577868759557654e-05,
"loss": 0.0,
"step": 28
},
{
"epoch": 1.0276854928017718,
"grad_norm": NaN,
"learning_rate": 7.401782177833148e-05,
"loss": 0.0,
"step": 29
},
{
"epoch": 1.06312292358804,
"grad_norm": NaN,
"learning_rate": 7.222075445642904e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 1.0985603543743079,
"grad_norm": NaN,
"learning_rate": 7.03909064496551e-05,
"loss": 0.0,
"step": 31
},
{
"epoch": 1.1339977851605758,
"grad_norm": NaN,
"learning_rate": 6.853176097769229e-05,
"loss": 0.0,
"step": 32
},
{
"epoch": 1.169435215946844,
"grad_norm": NaN,
"learning_rate": 6.664685702961344e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 1.204872646733112,
"grad_norm": NaN,
"learning_rate": 6.473978262721463e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 1.2403100775193798,
"grad_norm": NaN,
"learning_rate": 6.281416799501188e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 1.2757475083056478,
"grad_norm": NaN,
"learning_rate": 6.087367864990233e-05,
"loss": 0.0,
"step": 36
},
{
"epoch": 1.311184939091916,
"grad_norm": NaN,
"learning_rate": 5.8922008423644624e-05,
"loss": 0.0,
"step": 37
},
{
"epoch": 1.3466223698781838,
"grad_norm": NaN,
"learning_rate": 5.696287243144013e-05,
"loss": 0.0,
"step": 38
},
{
"epoch": 1.3820598006644518,
"grad_norm": NaN,
"learning_rate": 5.500000000000001e-05,
"loss": 0.0,
"step": 39
},
{
"epoch": 1.41749723145072,
"grad_norm": NaN,
"learning_rate": 5.303712756855988e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 1.4529346622369879,
"grad_norm": NaN,
"learning_rate": 5.107799157635538e-05,
"loss": 0.0,
"step": 41
},
{
"epoch": 1.4883720930232558,
"grad_norm": NaN,
"learning_rate": 4.912632135009769e-05,
"loss": 0.0,
"step": 42
},
{
"epoch": 1.5238095238095237,
"grad_norm": NaN,
"learning_rate": 4.718583200498814e-05,
"loss": 0.0,
"step": 43
},
{
"epoch": 1.5592469545957917,
"grad_norm": NaN,
"learning_rate": 4.526021737278538e-05,
"loss": 0.0,
"step": 44
},
{
"epoch": 1.5946843853820598,
"grad_norm": NaN,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.0,
"step": 45
},
{
"epoch": 1.6301218161683277,
"grad_norm": NaN,
"learning_rate": 4.146823902230772e-05,
"loss": 0.0,
"step": 46
},
{
"epoch": 1.665559246954596,
"grad_norm": NaN,
"learning_rate": 3.960909355034491e-05,
"loss": 0.0,
"step": 47
},
{
"epoch": 1.7009966777408638,
"grad_norm": NaN,
"learning_rate": 3.777924554357096e-05,
"loss": 0.0,
"step": 48
},
{
"epoch": 1.7364341085271318,
"grad_norm": NaN,
"learning_rate": 3.598217822166854e-05,
"loss": 0.0,
"step": 49
},
{
"epoch": 1.7718715393133997,
"grad_norm": NaN,
"learning_rate": 3.422131240442349e-05,
"loss": 0.0,
"step": 50
},
{
"epoch": 1.7718715393133997,
"eval_loss": NaN,
"eval_runtime": 7.6468,
"eval_samples_per_second": 6.539,
"eval_steps_per_second": 1.7,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 75,
"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": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.1152856242412585e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}