beast33's picture
Training in progress, step 50, checkpoint
178aafd verified
raw
history blame
9.95 kB
{
"best_metric": 2.4419381618499756,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.016630633627141195,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003326126725428239,
"grad_norm": 1.5779170989990234,
"learning_rate": 1e-05,
"loss": 2.578,
"step": 1
},
{
"epoch": 0.0003326126725428239,
"eval_loss": 2.890110492706299,
"eval_runtime": 143.2137,
"eval_samples_per_second": 35.36,
"eval_steps_per_second": 8.84,
"step": 1
},
{
"epoch": 0.0006652253450856477,
"grad_norm": 1.942592740058899,
"learning_rate": 2e-05,
"loss": 2.6554,
"step": 2
},
{
"epoch": 0.0009978380176284716,
"grad_norm": 2.1519877910614014,
"learning_rate": 3e-05,
"loss": 2.6751,
"step": 3
},
{
"epoch": 0.0013304506901712955,
"grad_norm": 2.0223259925842285,
"learning_rate": 4e-05,
"loss": 2.7234,
"step": 4
},
{
"epoch": 0.0016630633627141194,
"grad_norm": 2.1754114627838135,
"learning_rate": 5e-05,
"loss": 2.6795,
"step": 5
},
{
"epoch": 0.0019956760352569432,
"grad_norm": 1.9673004150390625,
"learning_rate": 6e-05,
"loss": 2.5201,
"step": 6
},
{
"epoch": 0.002328288707799767,
"grad_norm": 1.9511888027191162,
"learning_rate": 7e-05,
"loss": 2.6134,
"step": 7
},
{
"epoch": 0.002660901380342591,
"grad_norm": 1.9460816383361816,
"learning_rate": 8e-05,
"loss": 2.5508,
"step": 8
},
{
"epoch": 0.002993514052885415,
"grad_norm": 2.072754383087158,
"learning_rate": 9e-05,
"loss": 2.5035,
"step": 9
},
{
"epoch": 0.0033261267254282387,
"grad_norm": 1.8564409017562866,
"learning_rate": 0.0001,
"loss": 2.4293,
"step": 10
},
{
"epoch": 0.0036587393979710626,
"grad_norm": 1.9724938869476318,
"learning_rate": 9.999316524962345e-05,
"loss": 2.5721,
"step": 11
},
{
"epoch": 0.0039913520705138865,
"grad_norm": 1.9574224948883057,
"learning_rate": 9.997266286704631e-05,
"loss": 2.4073,
"step": 12
},
{
"epoch": 0.00432396474305671,
"grad_norm": 2.2013673782348633,
"learning_rate": 9.993849845741524e-05,
"loss": 2.3064,
"step": 13
},
{
"epoch": 0.004656577415599534,
"grad_norm": 2.178459405899048,
"learning_rate": 9.989068136093873e-05,
"loss": 2.341,
"step": 14
},
{
"epoch": 0.004989190088142358,
"grad_norm": 2.1170661449432373,
"learning_rate": 9.98292246503335e-05,
"loss": 2.4502,
"step": 15
},
{
"epoch": 0.005321802760685182,
"grad_norm": 2.190675973892212,
"learning_rate": 9.975414512725057e-05,
"loss": 2.3961,
"step": 16
},
{
"epoch": 0.005654415433228006,
"grad_norm": 2.2960801124572754,
"learning_rate": 9.966546331768191e-05,
"loss": 2.5492,
"step": 17
},
{
"epoch": 0.00598702810577083,
"grad_norm": 2.2598717212677,
"learning_rate": 9.956320346634876e-05,
"loss": 2.144,
"step": 18
},
{
"epoch": 0.006319640778313654,
"grad_norm": 2.0504443645477295,
"learning_rate": 9.944739353007344e-05,
"loss": 2.2617,
"step": 19
},
{
"epoch": 0.0066522534508564775,
"grad_norm": 2.1086559295654297,
"learning_rate": 9.931806517013612e-05,
"loss": 2.2074,
"step": 20
},
{
"epoch": 0.006984866123399301,
"grad_norm": 2.138704538345337,
"learning_rate": 9.917525374361912e-05,
"loss": 2.1696,
"step": 21
},
{
"epoch": 0.007317478795942125,
"grad_norm": 2.263592004776001,
"learning_rate": 9.901899829374047e-05,
"loss": 2.3905,
"step": 22
},
{
"epoch": 0.007650091468484949,
"grad_norm": 2.0490214824676514,
"learning_rate": 9.884934153917997e-05,
"loss": 2.369,
"step": 23
},
{
"epoch": 0.007982704141027773,
"grad_norm": 2.120150566101074,
"learning_rate": 9.86663298624003e-05,
"loss": 2.0843,
"step": 24
},
{
"epoch": 0.008315316813570598,
"grad_norm": 2.1268203258514404,
"learning_rate": 9.847001329696653e-05,
"loss": 2.3661,
"step": 25
},
{
"epoch": 0.00864792948611342,
"grad_norm": 2.0948963165283203,
"learning_rate": 9.826044551386744e-05,
"loss": 2.1879,
"step": 26
},
{
"epoch": 0.008980542158656245,
"grad_norm": 2.2930335998535156,
"learning_rate": 9.803768380684242e-05,
"loss": 1.9811,
"step": 27
},
{
"epoch": 0.009313154831199068,
"grad_norm": 2.029155969619751,
"learning_rate": 9.780178907671789e-05,
"loss": 1.9891,
"step": 28
},
{
"epoch": 0.009645767503741893,
"grad_norm": 2.1162171363830566,
"learning_rate": 9.755282581475769e-05,
"loss": 1.8595,
"step": 29
},
{
"epoch": 0.009978380176284716,
"grad_norm": 2.0919315814971924,
"learning_rate": 9.729086208503174e-05,
"loss": 1.9611,
"step": 30
},
{
"epoch": 0.010310992848827541,
"grad_norm": 2.2008674144744873,
"learning_rate": 9.701596950580806e-05,
"loss": 2.2932,
"step": 31
},
{
"epoch": 0.010643605521370364,
"grad_norm": 2.4158740043640137,
"learning_rate": 9.672822322997305e-05,
"loss": 2.1525,
"step": 32
},
{
"epoch": 0.010976218193913189,
"grad_norm": 2.352757215499878,
"learning_rate": 9.642770192448536e-05,
"loss": 2.1047,
"step": 33
},
{
"epoch": 0.011308830866456012,
"grad_norm": 2.383190870285034,
"learning_rate": 9.611448774886924e-05,
"loss": 2.0044,
"step": 34
},
{
"epoch": 0.011641443538998836,
"grad_norm": 2.3409194946289062,
"learning_rate": 9.578866633275288e-05,
"loss": 2.3371,
"step": 35
},
{
"epoch": 0.01197405621154166,
"grad_norm": 2.489692211151123,
"learning_rate": 9.545032675245813e-05,
"loss": 2.2883,
"step": 36
},
{
"epoch": 0.012306668884084484,
"grad_norm": 2.5469415187835693,
"learning_rate": 9.509956150664796e-05,
"loss": 1.9101,
"step": 37
},
{
"epoch": 0.012639281556627307,
"grad_norm": 2.4313035011291504,
"learning_rate": 9.473646649103818e-05,
"loss": 1.8939,
"step": 38
},
{
"epoch": 0.012971894229170132,
"grad_norm": 2.5194132328033447,
"learning_rate": 9.43611409721806e-05,
"loss": 1.9572,
"step": 39
},
{
"epoch": 0.013304506901712955,
"grad_norm": 2.6455283164978027,
"learning_rate": 9.397368756032445e-05,
"loss": 1.9544,
"step": 40
},
{
"epoch": 0.01363711957425578,
"grad_norm": 2.6215243339538574,
"learning_rate": 9.357421218136386e-05,
"loss": 2.0965,
"step": 41
},
{
"epoch": 0.013969732246798603,
"grad_norm": 2.5845704078674316,
"learning_rate": 9.316282404787871e-05,
"loss": 2.1711,
"step": 42
},
{
"epoch": 0.014302344919341427,
"grad_norm": 2.6958465576171875,
"learning_rate": 9.273963562927695e-05,
"loss": 1.9599,
"step": 43
},
{
"epoch": 0.01463495759188425,
"grad_norm": 2.6708405017852783,
"learning_rate": 9.230476262104677e-05,
"loss": 2.1328,
"step": 44
},
{
"epoch": 0.014967570264427075,
"grad_norm": 2.6289267539978027,
"learning_rate": 9.185832391312644e-05,
"loss": 1.8849,
"step": 45
},
{
"epoch": 0.015300182936969898,
"grad_norm": 3.140578031539917,
"learning_rate": 9.140044155740101e-05,
"loss": 2.0067,
"step": 46
},
{
"epoch": 0.015632795609512723,
"grad_norm": 3.0503008365631104,
"learning_rate": 9.093124073433463e-05,
"loss": 2.2709,
"step": 47
},
{
"epoch": 0.015965408282055546,
"grad_norm": 3.050830841064453,
"learning_rate": 9.045084971874738e-05,
"loss": 2.3409,
"step": 48
},
{
"epoch": 0.01629802095459837,
"grad_norm": 3.448582649230957,
"learning_rate": 8.995939984474624e-05,
"loss": 2.2677,
"step": 49
},
{
"epoch": 0.016630633627141195,
"grad_norm": 4.578643321990967,
"learning_rate": 8.945702546981969e-05,
"loss": 2.3374,
"step": 50
},
{
"epoch": 0.016630633627141195,
"eval_loss": 2.4419381618499756,
"eval_runtime": 143.8304,
"eval_samples_per_second": 35.208,
"eval_steps_per_second": 8.802,
"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": 1.0719067958673408e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}