prxy5605's picture
Training in progress, step 50, checkpoint
668bf68 verified
raw
history blame
9.91 kB
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.022456770716370984,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00044913541432741973,
"grad_norm": 1.838648495322559e-05,
"learning_rate": 5e-06,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.00044913541432741973,
"eval_loss": 11.5,
"eval_runtime": 24.2446,
"eval_samples_per_second": 154.674,
"eval_steps_per_second": 77.337,
"step": 1
},
{
"epoch": 0.0008982708286548395,
"grad_norm": 1.2990568393433932e-05,
"learning_rate": 1e-05,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.001347406242982259,
"grad_norm": 1.8343982446822338e-05,
"learning_rate": 1.5e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.001796541657309679,
"grad_norm": 1.3080456483294256e-05,
"learning_rate": 2e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.0022456770716370988,
"grad_norm": 1.5889010683167726e-05,
"learning_rate": 2.5e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.002694812485964518,
"grad_norm": 2.7616410079644993e-05,
"learning_rate": 3e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.003143947900291938,
"grad_norm": 2.0526989828795195e-05,
"learning_rate": 3.5e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.003593083314619358,
"grad_norm": 1.759777842380572e-05,
"learning_rate": 4e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.004042218728946777,
"grad_norm": 1.6452084310003556e-05,
"learning_rate": 4.5e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.0044913541432741975,
"grad_norm": 1.6463358406326734e-05,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.004940489557601617,
"grad_norm": 1.8078573702950962e-05,
"learning_rate": 5.500000000000001e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.005389624971929036,
"grad_norm": 1.6838948795339093e-05,
"learning_rate": 6e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.005838760386256457,
"grad_norm": 1.541178244224284e-05,
"learning_rate": 6.500000000000001e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.006287895800583876,
"grad_norm": 1.2977827282156795e-05,
"learning_rate": 7e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.0067370312149112955,
"grad_norm": 1.57095528265927e-05,
"learning_rate": 7.500000000000001e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.007186166629238716,
"grad_norm": 1.694589991529938e-05,
"learning_rate": 8e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.007635302043566135,
"grad_norm": 1.0791429303935729e-05,
"learning_rate": 8.5e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.008084437457893555,
"grad_norm": 1.7452706742915325e-05,
"learning_rate": 9e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.008533572872220974,
"grad_norm": 2.773817686829716e-05,
"learning_rate": 9.5e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.008982708286548395,
"grad_norm": 2.2375161279342137e-05,
"learning_rate": 0.0001,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.009431843700875815,
"grad_norm": 1.9166653146385215e-05,
"learning_rate": 9.999238475781957e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.009880979115203234,
"grad_norm": 1.3334756658878177e-05,
"learning_rate": 9.99695413509548e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.010330114529530653,
"grad_norm": 2.297369428561069e-05,
"learning_rate": 9.99314767377287e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.010779249943858073,
"grad_norm": 1.520256046205759e-05,
"learning_rate": 9.987820251299122e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.011228385358185492,
"grad_norm": 1.1953277862630785e-05,
"learning_rate": 9.980973490458728e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.011677520772512913,
"grad_norm": 1.437636910850415e-05,
"learning_rate": 9.972609476841367e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.012126656186840333,
"grad_norm": 1.8797289158101194e-05,
"learning_rate": 9.962730758206611e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.012575791601167752,
"grad_norm": 1.934461761265993e-05,
"learning_rate": 9.951340343707852e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.013024927015495171,
"grad_norm": 1.2589272046170663e-05,
"learning_rate": 9.938441702975689e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.013474062429822591,
"grad_norm": 2.8147243938292377e-05,
"learning_rate": 9.924038765061042e-05,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.013923197844150012,
"grad_norm": 1.534887451271061e-05,
"learning_rate": 9.908135917238321e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.014372333258477431,
"grad_norm": 2.1180412659305148e-05,
"learning_rate": 9.890738003669029e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.01482146867280485,
"grad_norm": 1.593550950929057e-05,
"learning_rate": 9.871850323926177e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 0.01527060408713227,
"grad_norm": 3.8066697015892714e-05,
"learning_rate": 9.851478631379982e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 0.01571973950145969,
"grad_norm": 1.754353979777079e-05,
"learning_rate": 9.829629131445342e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 0.01616887491578711,
"grad_norm": 1.624736250960268e-05,
"learning_rate": 9.806308479691595e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 0.01661801033011453,
"grad_norm": 1.8036285837297328e-05,
"learning_rate": 9.781523779815179e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 0.017067145744441948,
"grad_norm": 1.700466418697033e-05,
"learning_rate": 9.755282581475769e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 0.017516281158769367,
"grad_norm": 3.25874425470829e-05,
"learning_rate": 9.727592877996585e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 0.01796541657309679,
"grad_norm": 1.892649925139267e-05,
"learning_rate": 9.698463103929542e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 0.01841455198742421,
"grad_norm": 1.3684399164048955e-05,
"learning_rate": 9.667902132486009e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 0.01886368740175163,
"grad_norm": 2.2879992684465833e-05,
"learning_rate": 9.635919272833938e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 0.01931282281607905,
"grad_norm": 2.1507212295546196e-05,
"learning_rate": 9.602524267262203e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 0.019761958230406468,
"grad_norm": 2.5594701583031565e-05,
"learning_rate": 9.567727288213005e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 0.020211093644733887,
"grad_norm": 3.893139728461392e-05,
"learning_rate": 9.53153893518325e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 0.020660229059061307,
"grad_norm": 2.4852359274518676e-05,
"learning_rate": 9.493970231495835e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 0.021109364473388726,
"grad_norm": 5.0232982175657526e-05,
"learning_rate": 9.45503262094184e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 0.021558499887716145,
"grad_norm": 2.7157999284099787e-05,
"learning_rate": 9.414737964294636e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 0.022007635302043565,
"grad_norm": 3.0149305530358106e-05,
"learning_rate": 9.373098535696979e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 0.022456770716370984,
"grad_norm": 4.1423827497055754e-05,
"learning_rate": 9.330127018922194e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 0.022456770716370984,
"eval_loss": 11.5,
"eval_runtime": 24.2683,
"eval_samples_per_second": 154.523,
"eval_steps_per_second": 77.261,
"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": 8079813771264.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}