diaenra's picture
Training in progress, step 50, checkpoint
8d4a5fa verified
{
"best_metric": 0.10715995728969574,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.08956560680698612,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0017913121361397223,
"grad_norm": 45.71118927001953,
"learning_rate": 5e-05,
"loss": 3.5382,
"step": 1
},
{
"epoch": 0.0017913121361397223,
"eval_loss": 1.2403191328048706,
"eval_runtime": 32.5722,
"eval_samples_per_second": 7.215,
"eval_steps_per_second": 3.623,
"step": 1
},
{
"epoch": 0.0035826242722794446,
"grad_norm": 54.147117614746094,
"learning_rate": 0.0001,
"loss": 4.4416,
"step": 2
},
{
"epoch": 0.005373936408419167,
"grad_norm": 29.201833724975586,
"learning_rate": 9.989294616193017e-05,
"loss": 2.2421,
"step": 3
},
{
"epoch": 0.007165248544558889,
"grad_norm": 11.060723304748535,
"learning_rate": 9.957224306869053e-05,
"loss": 0.882,
"step": 4
},
{
"epoch": 0.008956560680698611,
"grad_norm": 7.390138149261475,
"learning_rate": 9.903926402016153e-05,
"loss": 0.3238,
"step": 5
},
{
"epoch": 0.010747872816838333,
"grad_norm": 15.29438591003418,
"learning_rate": 9.829629131445342e-05,
"loss": 0.7755,
"step": 6
},
{
"epoch": 0.012539184952978056,
"grad_norm": 5.898852825164795,
"learning_rate": 9.73465064747553e-05,
"loss": 0.5626,
"step": 7
},
{
"epoch": 0.014330497089117778,
"grad_norm": 8.337850570678711,
"learning_rate": 9.619397662556435e-05,
"loss": 0.5438,
"step": 8
},
{
"epoch": 0.0161218092252575,
"grad_norm": 1.5996332168579102,
"learning_rate": 9.484363707663442e-05,
"loss": 0.0382,
"step": 9
},
{
"epoch": 0.017913121361397222,
"grad_norm": 4.277411937713623,
"learning_rate": 9.330127018922194e-05,
"loss": 0.2257,
"step": 10
},
{
"epoch": 0.019704433497536946,
"grad_norm": 11.699952125549316,
"learning_rate": 9.157348061512727e-05,
"loss": 0.5768,
"step": 11
},
{
"epoch": 0.021495745633676667,
"grad_norm": 6.67721700668335,
"learning_rate": 8.966766701456177e-05,
"loss": 0.529,
"step": 12
},
{
"epoch": 0.02328705776981639,
"grad_norm": 3.655250310897827,
"learning_rate": 8.759199037394887e-05,
"loss": 0.4513,
"step": 13
},
{
"epoch": 0.025078369905956112,
"grad_norm": 3.847569227218628,
"learning_rate": 8.535533905932738e-05,
"loss": 0.3444,
"step": 14
},
{
"epoch": 0.026869682042095836,
"grad_norm": 3.2041683197021484,
"learning_rate": 8.296729075500344e-05,
"loss": 0.3884,
"step": 15
},
{
"epoch": 0.028660994178235557,
"grad_norm": 3.8608181476593018,
"learning_rate": 8.043807145043604e-05,
"loss": 0.4611,
"step": 16
},
{
"epoch": 0.03045230631437528,
"grad_norm": 3.885558605194092,
"learning_rate": 7.777851165098012e-05,
"loss": 0.5638,
"step": 17
},
{
"epoch": 0.032243618450515,
"grad_norm": 3.6549408435821533,
"learning_rate": 7.500000000000001e-05,
"loss": 0.3947,
"step": 18
},
{
"epoch": 0.03403493058665472,
"grad_norm": 3.00775408744812,
"learning_rate": 7.211443451095007e-05,
"loss": 0.2695,
"step": 19
},
{
"epoch": 0.035826242722794444,
"grad_norm": 4.4329833984375,
"learning_rate": 6.91341716182545e-05,
"loss": 0.3134,
"step": 20
},
{
"epoch": 0.03761755485893417,
"grad_norm": 8.40273380279541,
"learning_rate": 6.607197326515808e-05,
"loss": 0.906,
"step": 21
},
{
"epoch": 0.03940886699507389,
"grad_norm": 5.163272380828857,
"learning_rate": 6.294095225512603e-05,
"loss": 0.465,
"step": 22
},
{
"epoch": 0.04120017913121361,
"grad_norm": 4.11625337600708,
"learning_rate": 5.9754516100806423e-05,
"loss": 0.3355,
"step": 23
},
{
"epoch": 0.042991491267353334,
"grad_norm": 5.755086898803711,
"learning_rate": 5.6526309611002594e-05,
"loss": 0.7626,
"step": 24
},
{
"epoch": 0.04478280340349306,
"grad_norm": 4.533884048461914,
"learning_rate": 5.327015646150716e-05,
"loss": 0.4366,
"step": 25
},
{
"epoch": 0.04478280340349306,
"eval_loss": 0.12636807560920715,
"eval_runtime": 33.2994,
"eval_samples_per_second": 7.057,
"eval_steps_per_second": 3.544,
"step": 25
},
{
"epoch": 0.04657411553963278,
"grad_norm": 2.4748008251190186,
"learning_rate": 5e-05,
"loss": 0.2563,
"step": 26
},
{
"epoch": 0.0483654276757725,
"grad_norm": 4.218332290649414,
"learning_rate": 4.6729843538492847e-05,
"loss": 0.4993,
"step": 27
},
{
"epoch": 0.050156739811912224,
"grad_norm": 2.3692610263824463,
"learning_rate": 4.347369038899744e-05,
"loss": 0.235,
"step": 28
},
{
"epoch": 0.05194805194805195,
"grad_norm": 3.3568317890167236,
"learning_rate": 4.0245483899193595e-05,
"loss": 0.3957,
"step": 29
},
{
"epoch": 0.05373936408419167,
"grad_norm": 4.579010009765625,
"learning_rate": 3.705904774487396e-05,
"loss": 0.4771,
"step": 30
},
{
"epoch": 0.05553067622033139,
"grad_norm": 3.82382869720459,
"learning_rate": 3.392802673484193e-05,
"loss": 0.2925,
"step": 31
},
{
"epoch": 0.057321988356471114,
"grad_norm": 2.7304625511169434,
"learning_rate": 3.086582838174551e-05,
"loss": 0.2957,
"step": 32
},
{
"epoch": 0.059113300492610835,
"grad_norm": 4.2830352783203125,
"learning_rate": 2.7885565489049946e-05,
"loss": 0.4469,
"step": 33
},
{
"epoch": 0.06090461262875056,
"grad_norm": 2.769845724105835,
"learning_rate": 2.500000000000001e-05,
"loss": 0.4208,
"step": 34
},
{
"epoch": 0.06269592476489028,
"grad_norm": 2.1712167263031006,
"learning_rate": 2.2221488349019903e-05,
"loss": 0.1889,
"step": 35
},
{
"epoch": 0.06448723690103,
"grad_norm": 3.581455707550049,
"learning_rate": 1.9561928549563968e-05,
"loss": 0.3311,
"step": 36
},
{
"epoch": 0.06627854903716973,
"grad_norm": 4.364194393157959,
"learning_rate": 1.703270924499656e-05,
"loss": 0.5934,
"step": 37
},
{
"epoch": 0.06806986117330945,
"grad_norm": 2.803682565689087,
"learning_rate": 1.4644660940672627e-05,
"loss": 0.3943,
"step": 38
},
{
"epoch": 0.06986117330944917,
"grad_norm": 3.7528460025787354,
"learning_rate": 1.2408009626051137e-05,
"loss": 0.4517,
"step": 39
},
{
"epoch": 0.07165248544558889,
"grad_norm": 3.5302984714508057,
"learning_rate": 1.0332332985438248e-05,
"loss": 0.5168,
"step": 40
},
{
"epoch": 0.07344379758172861,
"grad_norm": 5.849757194519043,
"learning_rate": 8.426519384872733e-06,
"loss": 0.6599,
"step": 41
},
{
"epoch": 0.07523510971786834,
"grad_norm": 4.0423760414123535,
"learning_rate": 6.698729810778065e-06,
"loss": 0.5821,
"step": 42
},
{
"epoch": 0.07702642185400806,
"grad_norm": 4.6589484214782715,
"learning_rate": 5.156362923365588e-06,
"loss": 0.6031,
"step": 43
},
{
"epoch": 0.07881773399014778,
"grad_norm": 3.569039821624756,
"learning_rate": 3.8060233744356633e-06,
"loss": 0.5059,
"step": 44
},
{
"epoch": 0.08060904612628751,
"grad_norm": 5.747331619262695,
"learning_rate": 2.653493525244721e-06,
"loss": 0.8897,
"step": 45
},
{
"epoch": 0.08240035826242723,
"grad_norm": 5.7729363441467285,
"learning_rate": 1.70370868554659e-06,
"loss": 0.8777,
"step": 46
},
{
"epoch": 0.08419167039856695,
"grad_norm": 5.641356945037842,
"learning_rate": 9.607359798384785e-07,
"loss": 0.9093,
"step": 47
},
{
"epoch": 0.08598298253470667,
"grad_norm": 4.868679523468018,
"learning_rate": 4.277569313094809e-07,
"loss": 0.7942,
"step": 48
},
{
"epoch": 0.0877742946708464,
"grad_norm": 6.637969493865967,
"learning_rate": 1.0705383806982606e-07,
"loss": 0.746,
"step": 49
},
{
"epoch": 0.08956560680698612,
"grad_norm": 4.852217197418213,
"learning_rate": 0.0,
"loss": 0.4853,
"step": 50
},
{
"epoch": 0.08956560680698612,
"eval_loss": 0.10715995728969574,
"eval_runtime": 33.3425,
"eval_samples_per_second": 7.048,
"eval_steps_per_second": 3.539,
"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": 3.51564749340672e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}