aleegis11's picture
Training in progress, step 50, checkpoint
ce27a6a verified
raw
history blame
9.96 kB
{
"best_metric": 0.5648638010025024,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.08503401360544217,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0017006802721088435,
"grad_norm": 0.16959799826145172,
"learning_rate": 1e-05,
"loss": 0.5694,
"step": 1
},
{
"epoch": 0.0017006802721088435,
"eval_loss": 0.7016671299934387,
"eval_runtime": 71.4118,
"eval_samples_per_second": 13.863,
"eval_steps_per_second": 3.473,
"step": 1
},
{
"epoch": 0.003401360544217687,
"grad_norm": 0.18853634595870972,
"learning_rate": 2e-05,
"loss": 0.6119,
"step": 2
},
{
"epoch": 0.00510204081632653,
"grad_norm": 0.18308532238006592,
"learning_rate": 3e-05,
"loss": 0.6166,
"step": 3
},
{
"epoch": 0.006802721088435374,
"grad_norm": 0.21027779579162598,
"learning_rate": 4e-05,
"loss": 0.6103,
"step": 4
},
{
"epoch": 0.008503401360544218,
"grad_norm": 0.19290000200271606,
"learning_rate": 5e-05,
"loss": 0.6287,
"step": 5
},
{
"epoch": 0.01020408163265306,
"grad_norm": 0.18025891482830048,
"learning_rate": 6e-05,
"loss": 0.6208,
"step": 6
},
{
"epoch": 0.011904761904761904,
"grad_norm": 0.18125878274440765,
"learning_rate": 7e-05,
"loss": 0.6344,
"step": 7
},
{
"epoch": 0.013605442176870748,
"grad_norm": 0.17453987896442413,
"learning_rate": 8e-05,
"loss": 0.6131,
"step": 8
},
{
"epoch": 0.015306122448979591,
"grad_norm": 0.22241806983947754,
"learning_rate": 9e-05,
"loss": 0.6083,
"step": 9
},
{
"epoch": 0.017006802721088437,
"grad_norm": 0.22235193848609924,
"learning_rate": 0.0001,
"loss": 0.6033,
"step": 10
},
{
"epoch": 0.01870748299319728,
"grad_norm": 0.22243435680866241,
"learning_rate": 9.999316524962345e-05,
"loss": 0.6101,
"step": 11
},
{
"epoch": 0.02040816326530612,
"grad_norm": 0.212838277220726,
"learning_rate": 9.997266286704631e-05,
"loss": 0.6282,
"step": 12
},
{
"epoch": 0.022108843537414966,
"grad_norm": 0.18950781226158142,
"learning_rate": 9.993849845741524e-05,
"loss": 0.587,
"step": 13
},
{
"epoch": 0.023809523809523808,
"grad_norm": 0.18078520894050598,
"learning_rate": 9.989068136093873e-05,
"loss": 0.566,
"step": 14
},
{
"epoch": 0.025510204081632654,
"grad_norm": 0.19135352969169617,
"learning_rate": 9.98292246503335e-05,
"loss": 0.606,
"step": 15
},
{
"epoch": 0.027210884353741496,
"grad_norm": 0.17477868497371674,
"learning_rate": 9.975414512725057e-05,
"loss": 0.5983,
"step": 16
},
{
"epoch": 0.02891156462585034,
"grad_norm": 0.17936213314533234,
"learning_rate": 9.966546331768191e-05,
"loss": 0.5803,
"step": 17
},
{
"epoch": 0.030612244897959183,
"grad_norm": 0.171107217669487,
"learning_rate": 9.956320346634876e-05,
"loss": 0.6004,
"step": 18
},
{
"epoch": 0.03231292517006803,
"grad_norm": 0.17990447580814362,
"learning_rate": 9.944739353007344e-05,
"loss": 0.5798,
"step": 19
},
{
"epoch": 0.034013605442176874,
"grad_norm": 0.17869217693805695,
"learning_rate": 9.931806517013612e-05,
"loss": 0.556,
"step": 20
},
{
"epoch": 0.03571428571428571,
"grad_norm": 0.18821021914482117,
"learning_rate": 9.917525374361912e-05,
"loss": 0.579,
"step": 21
},
{
"epoch": 0.03741496598639456,
"grad_norm": 0.1777324676513672,
"learning_rate": 9.901899829374047e-05,
"loss": 0.5772,
"step": 22
},
{
"epoch": 0.0391156462585034,
"grad_norm": 0.17420151829719543,
"learning_rate": 9.884934153917997e-05,
"loss": 0.5682,
"step": 23
},
{
"epoch": 0.04081632653061224,
"grad_norm": 0.1808144897222519,
"learning_rate": 9.86663298624003e-05,
"loss": 0.5921,
"step": 24
},
{
"epoch": 0.04251700680272109,
"grad_norm": 0.18310721218585968,
"learning_rate": 9.847001329696653e-05,
"loss": 0.5789,
"step": 25
},
{
"epoch": 0.04421768707482993,
"grad_norm": 0.18186233937740326,
"learning_rate": 9.826044551386744e-05,
"loss": 0.5858,
"step": 26
},
{
"epoch": 0.04591836734693878,
"grad_norm": 0.1901922971010208,
"learning_rate": 9.803768380684242e-05,
"loss": 0.5872,
"step": 27
},
{
"epoch": 0.047619047619047616,
"grad_norm": 0.18851330876350403,
"learning_rate": 9.780178907671789e-05,
"loss": 0.609,
"step": 28
},
{
"epoch": 0.04931972789115646,
"grad_norm": 0.17681556940078735,
"learning_rate": 9.755282581475769e-05,
"loss": 0.5502,
"step": 29
},
{
"epoch": 0.05102040816326531,
"grad_norm": 0.19169022142887115,
"learning_rate": 9.729086208503174e-05,
"loss": 0.5866,
"step": 30
},
{
"epoch": 0.05272108843537415,
"grad_norm": 0.1974894106388092,
"learning_rate": 9.701596950580806e-05,
"loss": 0.5671,
"step": 31
},
{
"epoch": 0.05442176870748299,
"grad_norm": 0.19867075979709625,
"learning_rate": 9.672822322997305e-05,
"loss": 0.5513,
"step": 32
},
{
"epoch": 0.05612244897959184,
"grad_norm": 0.212591752409935,
"learning_rate": 9.642770192448536e-05,
"loss": 0.5431,
"step": 33
},
{
"epoch": 0.05782312925170068,
"grad_norm": 0.20537696778774261,
"learning_rate": 9.611448774886924e-05,
"loss": 0.5254,
"step": 34
},
{
"epoch": 0.05952380952380952,
"grad_norm": 0.19645805656909943,
"learning_rate": 9.578866633275288e-05,
"loss": 0.54,
"step": 35
},
{
"epoch": 0.061224489795918366,
"grad_norm": 0.21156303584575653,
"learning_rate": 9.545032675245813e-05,
"loss": 0.5601,
"step": 36
},
{
"epoch": 0.06292517006802721,
"grad_norm": 0.21462957561016083,
"learning_rate": 9.509956150664796e-05,
"loss": 0.5519,
"step": 37
},
{
"epoch": 0.06462585034013606,
"grad_norm": 0.2154107540845871,
"learning_rate": 9.473646649103818e-05,
"loss": 0.5123,
"step": 38
},
{
"epoch": 0.0663265306122449,
"grad_norm": 0.2208368331193924,
"learning_rate": 9.43611409721806e-05,
"loss": 0.5221,
"step": 39
},
{
"epoch": 0.06802721088435375,
"grad_norm": 0.2187241166830063,
"learning_rate": 9.397368756032445e-05,
"loss": 0.5106,
"step": 40
},
{
"epoch": 0.06972789115646258,
"grad_norm": 0.22782184183597565,
"learning_rate": 9.357421218136386e-05,
"loss": 0.5342,
"step": 41
},
{
"epoch": 0.07142857142857142,
"grad_norm": 0.23117218911647797,
"learning_rate": 9.316282404787871e-05,
"loss": 0.5013,
"step": 42
},
{
"epoch": 0.07312925170068027,
"grad_norm": 0.25789204239845276,
"learning_rate": 9.273963562927695e-05,
"loss": 0.5135,
"step": 43
},
{
"epoch": 0.07482993197278912,
"grad_norm": 0.27129191160202026,
"learning_rate": 9.230476262104677e-05,
"loss": 0.5327,
"step": 44
},
{
"epoch": 0.07653061224489796,
"grad_norm": 0.27148500084877014,
"learning_rate": 9.185832391312644e-05,
"loss": 0.4719,
"step": 45
},
{
"epoch": 0.0782312925170068,
"grad_norm": 0.2911697030067444,
"learning_rate": 9.140044155740101e-05,
"loss": 0.4779,
"step": 46
},
{
"epoch": 0.07993197278911565,
"grad_norm": 0.318223774433136,
"learning_rate": 9.093124073433463e-05,
"loss": 0.472,
"step": 47
},
{
"epoch": 0.08163265306122448,
"grad_norm": 0.36965641379356384,
"learning_rate": 9.045084971874738e-05,
"loss": 0.506,
"step": 48
},
{
"epoch": 0.08333333333333333,
"grad_norm": 0.5182129144668579,
"learning_rate": 8.995939984474624e-05,
"loss": 0.5451,
"step": 49
},
{
"epoch": 0.08503401360544217,
"grad_norm": 0.9564126133918762,
"learning_rate": 8.945702546981969e-05,
"loss": 0.4366,
"step": 50
},
{
"epoch": 0.08503401360544217,
"eval_loss": 0.5648638010025024,
"eval_runtime": 72.6373,
"eval_samples_per_second": 13.629,
"eval_steps_per_second": 3.414,
"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": 6.752266054375834e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}