{
"best_metric": 0.11933062225580215,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.5637773079633545,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01127554615926709,
"grad_norm": 41.67961120605469,
"learning_rate": 5e-05,
"loss": 5.5662,
"step": 1
},
{
"epoch": 0.01127554615926709,
"eval_loss": 11.650677680969238,
"eval_runtime": 4.4484,
"eval_samples_per_second": 11.24,
"eval_steps_per_second": 2.922,
"step": 1
},
{
"epoch": 0.02255109231853418,
"grad_norm": 55.36874008178711,
"learning_rate": 0.0001,
"loss": 7.0949,
"step": 2
},
{
"epoch": 0.03382663847780127,
"grad_norm": 34.676937103271484,
"learning_rate": 9.990365154573717e-05,
"loss": 4.9123,
"step": 3
},
{
"epoch": 0.04510218463706836,
"grad_norm": 10.038505554199219,
"learning_rate": 9.961501876182148e-05,
"loss": 2.1006,
"step": 4
},
{
"epoch": 0.05637773079633545,
"grad_norm": 6.519526958465576,
"learning_rate": 9.913533761814537e-05,
"loss": 1.7432,
"step": 5
},
{
"epoch": 0.06765327695560254,
"grad_norm": 12.672989845275879,
"learning_rate": 9.846666218300807e-05,
"loss": 0.7544,
"step": 6
},
{
"epoch": 0.07892882311486962,
"grad_norm": 4.969459056854248,
"learning_rate": 9.761185582727977e-05,
"loss": 0.2222,
"step": 7
},
{
"epoch": 0.09020436927413672,
"grad_norm": 1.2799570560455322,
"learning_rate": 9.657457896300791e-05,
"loss": 0.0502,
"step": 8
},
{
"epoch": 0.1014799154334038,
"grad_norm": 0.2841648757457733,
"learning_rate": 9.535927336897098e-05,
"loss": 0.0088,
"step": 9
},
{
"epoch": 0.1127554615926709,
"grad_norm": 0.0658557265996933,
"learning_rate": 9.397114317029975e-05,
"loss": 0.0012,
"step": 10
},
{
"epoch": 0.12403100775193798,
"grad_norm": 0.08013731986284256,
"learning_rate": 9.241613255361455e-05,
"loss": 0.001,
"step": 11
},
{
"epoch": 0.13530655391120508,
"grad_norm": 2.385392189025879,
"learning_rate": 9.070090031310558e-05,
"loss": 0.0226,
"step": 12
},
{
"epoch": 0.14658210007047218,
"grad_norm": 3.8271114826202393,
"learning_rate": 8.883279133655399e-05,
"loss": 0.8563,
"step": 13
},
{
"epoch": 0.15785764622973925,
"grad_norm": 0.06334669142961502,
"learning_rate": 8.681980515339464e-05,
"loss": 0.0008,
"step": 14
},
{
"epoch": 0.16913319238900634,
"grad_norm": 0.1104746088385582,
"learning_rate": 8.467056167950311e-05,
"loss": 0.0015,
"step": 15
},
{
"epoch": 0.18040873854827344,
"grad_norm": 0.16894719004631042,
"learning_rate": 8.239426430539243e-05,
"loss": 0.0022,
"step": 16
},
{
"epoch": 0.1916842847075405,
"grad_norm": 0.06540022790431976,
"learning_rate": 8.000066048588211e-05,
"loss": 0.0009,
"step": 17
},
{
"epoch": 0.2029598308668076,
"grad_norm": 0.17769066989421844,
"learning_rate": 7.75e-05,
"loss": 0.0017,
"step": 18
},
{
"epoch": 0.2142353770260747,
"grad_norm": 0.09200280159711838,
"learning_rate": 7.490299105985507e-05,
"loss": 0.0008,
"step": 19
},
{
"epoch": 0.2255109231853418,
"grad_norm": 0.12168077379465103,
"learning_rate": 7.222075445642904e-05,
"loss": 0.0013,
"step": 20
},
{
"epoch": 0.23678646934460887,
"grad_norm": 0.010348298586905003,
"learning_rate": 6.946477593864228e-05,
"loss": 0.0001,
"step": 21
},
{
"epoch": 0.24806201550387597,
"grad_norm": 0.006999962031841278,
"learning_rate": 6.664685702961344e-05,
"loss": 0.0001,
"step": 22
},
{
"epoch": 0.25933756166314303,
"grad_norm": 0.004994003567844629,
"learning_rate": 6.377906449072578e-05,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.27061310782241016,
"grad_norm": 0.012034592218697071,
"learning_rate": 6.087367864990233e-05,
"loss": 0.0001,
"step": 24
},
{
"epoch": 0.28188865398167723,
"grad_norm": 0.0022941671777516603,
"learning_rate": 5.794314081535644e-05,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.28188865398167723,
"eval_loss": 0.19639895856380463,
"eval_runtime": 2.498,
"eval_samples_per_second": 20.016,
"eval_steps_per_second": 5.204,
"step": 25
},
{
"epoch": 0.29316420014094435,
"grad_norm": 2.109933614730835,
"learning_rate": 5.500000000000001e-05,
"loss": 0.4934,
"step": 26
},
{
"epoch": 0.3044397463002114,
"grad_norm": 0.022254984825849533,
"learning_rate": 5.205685918464356e-05,
"loss": 0.0002,
"step": 27
},
{
"epoch": 0.3157152924594785,
"grad_norm": 0.05473516136407852,
"learning_rate": 4.912632135009769e-05,
"loss": 0.0006,
"step": 28
},
{
"epoch": 0.3269908386187456,
"grad_norm": 0.028082022443413734,
"learning_rate": 4.6220935509274235e-05,
"loss": 0.0002,
"step": 29
},
{
"epoch": 0.3382663847780127,
"grad_norm": 0.17534944415092468,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.0022,
"step": 30
},
{
"epoch": 0.34954193093727975,
"grad_norm": 0.0239122174680233,
"learning_rate": 4.053522406135775e-05,
"loss": 0.0003,
"step": 31
},
{
"epoch": 0.3608174770965469,
"grad_norm": 0.006109355948865414,
"learning_rate": 3.777924554357096e-05,
"loss": 0.0001,
"step": 32
},
{
"epoch": 0.37209302325581395,
"grad_norm": 0.09741108864545822,
"learning_rate": 3.509700894014496e-05,
"loss": 0.0004,
"step": 33
},
{
"epoch": 0.383368569415081,
"grad_norm": 0.12838013470172882,
"learning_rate": 3.250000000000001e-05,
"loss": 0.0008,
"step": 34
},
{
"epoch": 0.39464411557434814,
"grad_norm": 0.004765228368341923,
"learning_rate": 2.9999339514117912e-05,
"loss": 0.0001,
"step": 35
},
{
"epoch": 0.4059196617336152,
"grad_norm": 0.005345562938600779,
"learning_rate": 2.760573569460757e-05,
"loss": 0.0001,
"step": 36
},
{
"epoch": 0.41719520789288234,
"grad_norm": 0.002657412551343441,
"learning_rate": 2.53294383204969e-05,
"loss": 0.0001,
"step": 37
},
{
"epoch": 0.4284707540521494,
"grad_norm": 1.4992165565490723,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.3407,
"step": 38
},
{
"epoch": 0.4397463002114165,
"grad_norm": 0.03090500459074974,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.0004,
"step": 39
},
{
"epoch": 0.4510218463706836,
"grad_norm": 0.023092983290553093,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.0003,
"step": 40
},
{
"epoch": 0.46229739252995067,
"grad_norm": 0.03314114734530449,
"learning_rate": 1.758386744638546e-05,
"loss": 0.0004,
"step": 41
},
{
"epoch": 0.47357293868921774,
"grad_norm": 0.008977651596069336,
"learning_rate": 1.602885682970026e-05,
"loss": 0.0002,
"step": 42
},
{
"epoch": 0.48484848484848486,
"grad_norm": 0.01702510006725788,
"learning_rate": 1.464072663102903e-05,
"loss": 0.0003,
"step": 43
},
{
"epoch": 0.49612403100775193,
"grad_norm": 0.02620372734963894,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.0003,
"step": 44
},
{
"epoch": 0.507399577167019,
"grad_norm": 0.23229342699050903,
"learning_rate": 1.2388144172720251e-05,
"loss": 0.0032,
"step": 45
},
{
"epoch": 0.5186751233262861,
"grad_norm": 0.010418013669550419,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.0002,
"step": 46
},
{
"epoch": 0.5299506694855532,
"grad_norm": 0.015945376828312874,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.0003,
"step": 47
},
{
"epoch": 0.5412262156448203,
"grad_norm": 0.017018966376781464,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.0003,
"step": 48
},
{
"epoch": 0.5525017618040874,
"grad_norm": 0.010695608332753181,
"learning_rate": 1.0096348454262845e-05,
"loss": 0.0002,
"step": 49
},
{
"epoch": 0.5637773079633545,
"grad_norm": 0.004107787273824215,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 50
},
{
"epoch": 0.5637773079633545,
"eval_loss": 0.11933062225580215,
"eval_runtime": 2.4961,
"eval_samples_per_second": 20.031,
"eval_steps_per_second": 5.208,
"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": 6.02216935664386e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}