bbytxt's picture
Training in progress, step 50, checkpoint
df1c220 verified
raw
history blame
9.96 kB
{
"best_metric": 0.6646648049354553,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.02733360666940003,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005466721333880005,
"grad_norm": 1.5685559511184692,
"learning_rate": 1e-05,
"loss": 0.6201,
"step": 1
},
{
"epoch": 0.0005466721333880005,
"eval_loss": 1.2423924207687378,
"eval_runtime": 317.3681,
"eval_samples_per_second": 9.708,
"eval_steps_per_second": 2.429,
"step": 1
},
{
"epoch": 0.001093344266776001,
"grad_norm": 1.7842057943344116,
"learning_rate": 2e-05,
"loss": 0.7283,
"step": 2
},
{
"epoch": 0.0016400164001640015,
"grad_norm": 0.8638198971748352,
"learning_rate": 3e-05,
"loss": 0.7406,
"step": 3
},
{
"epoch": 0.002186688533552002,
"grad_norm": 1.0290772914886475,
"learning_rate": 4e-05,
"loss": 0.7696,
"step": 4
},
{
"epoch": 0.0027333606669400026,
"grad_norm": 0.8170171976089478,
"learning_rate": 5e-05,
"loss": 0.7364,
"step": 5
},
{
"epoch": 0.003280032800328003,
"grad_norm": 0.41177359223365784,
"learning_rate": 6e-05,
"loss": 0.752,
"step": 6
},
{
"epoch": 0.003826704933716004,
"grad_norm": 0.3283713757991791,
"learning_rate": 7e-05,
"loss": 0.7753,
"step": 7
},
{
"epoch": 0.004373377067104004,
"grad_norm": 0.289739727973938,
"learning_rate": 8e-05,
"loss": 0.7008,
"step": 8
},
{
"epoch": 0.004920049200492005,
"grad_norm": 0.559328556060791,
"learning_rate": 9e-05,
"loss": 0.7024,
"step": 9
},
{
"epoch": 0.005466721333880005,
"grad_norm": 0.3776341676712036,
"learning_rate": 0.0001,
"loss": 0.6434,
"step": 10
},
{
"epoch": 0.006013393467268006,
"grad_norm": 0.4670841097831726,
"learning_rate": 9.999316524962345e-05,
"loss": 0.6869,
"step": 11
},
{
"epoch": 0.006560065600656006,
"grad_norm": 0.393575519323349,
"learning_rate": 9.997266286704631e-05,
"loss": 0.705,
"step": 12
},
{
"epoch": 0.007106737734044007,
"grad_norm": 0.3016532063484192,
"learning_rate": 9.993849845741524e-05,
"loss": 0.6966,
"step": 13
},
{
"epoch": 0.007653409867432008,
"grad_norm": 0.3321461081504822,
"learning_rate": 9.989068136093873e-05,
"loss": 0.6701,
"step": 14
},
{
"epoch": 0.008200082000820008,
"grad_norm": 0.2765994369983673,
"learning_rate": 9.98292246503335e-05,
"loss": 0.6431,
"step": 15
},
{
"epoch": 0.008746754134208008,
"grad_norm": 0.3029332756996155,
"learning_rate": 9.975414512725057e-05,
"loss": 0.6934,
"step": 16
},
{
"epoch": 0.00929342626759601,
"grad_norm": 0.2704845666885376,
"learning_rate": 9.966546331768191e-05,
"loss": 0.6768,
"step": 17
},
{
"epoch": 0.00984009840098401,
"grad_norm": 0.29650449752807617,
"learning_rate": 9.956320346634876e-05,
"loss": 0.7132,
"step": 18
},
{
"epoch": 0.01038677053437201,
"grad_norm": 0.36541548371315,
"learning_rate": 9.944739353007344e-05,
"loss": 0.6589,
"step": 19
},
{
"epoch": 0.01093344266776001,
"grad_norm": 0.3385908603668213,
"learning_rate": 9.931806517013612e-05,
"loss": 0.6724,
"step": 20
},
{
"epoch": 0.011480114801148012,
"grad_norm": 0.27720966935157776,
"learning_rate": 9.917525374361912e-05,
"loss": 0.6729,
"step": 21
},
{
"epoch": 0.012026786934536012,
"grad_norm": 0.24973812699317932,
"learning_rate": 9.901899829374047e-05,
"loss": 0.7068,
"step": 22
},
{
"epoch": 0.012573459067924012,
"grad_norm": 0.27048227190971375,
"learning_rate": 9.884934153917997e-05,
"loss": 0.6707,
"step": 23
},
{
"epoch": 0.013120131201312012,
"grad_norm": 0.28500187397003174,
"learning_rate": 9.86663298624003e-05,
"loss": 0.647,
"step": 24
},
{
"epoch": 0.013666803334700014,
"grad_norm": 0.27583548426628113,
"learning_rate": 9.847001329696653e-05,
"loss": 0.5803,
"step": 25
},
{
"epoch": 0.014213475468088014,
"grad_norm": 0.3138293921947479,
"learning_rate": 9.826044551386744e-05,
"loss": 0.7286,
"step": 26
},
{
"epoch": 0.014760147601476014,
"grad_norm": 0.32263466715812683,
"learning_rate": 9.803768380684242e-05,
"loss": 0.6329,
"step": 27
},
{
"epoch": 0.015306819734864016,
"grad_norm": 0.32008203864097595,
"learning_rate": 9.780178907671789e-05,
"loss": 0.6561,
"step": 28
},
{
"epoch": 0.015853491868252016,
"grad_norm": 0.3512203097343445,
"learning_rate": 9.755282581475769e-05,
"loss": 0.7223,
"step": 29
},
{
"epoch": 0.016400164001640016,
"grad_norm": 0.3767859637737274,
"learning_rate": 9.729086208503174e-05,
"loss": 0.6481,
"step": 30
},
{
"epoch": 0.016946836135028016,
"grad_norm": 0.3525494337081909,
"learning_rate": 9.701596950580806e-05,
"loss": 0.6341,
"step": 31
},
{
"epoch": 0.017493508268416016,
"grad_norm": 0.46691110730171204,
"learning_rate": 9.672822322997305e-05,
"loss": 0.7674,
"step": 32
},
{
"epoch": 0.018040180401804017,
"grad_norm": 0.41331732273101807,
"learning_rate": 9.642770192448536e-05,
"loss": 0.6584,
"step": 33
},
{
"epoch": 0.01858685253519202,
"grad_norm": 0.5147906541824341,
"learning_rate": 9.611448774886924e-05,
"loss": 0.7344,
"step": 34
},
{
"epoch": 0.01913352466858002,
"grad_norm": 0.5044989585876465,
"learning_rate": 9.578866633275288e-05,
"loss": 0.7817,
"step": 35
},
{
"epoch": 0.01968019680196802,
"grad_norm": 0.511785626411438,
"learning_rate": 9.545032675245813e-05,
"loss": 0.6783,
"step": 36
},
{
"epoch": 0.02022686893535602,
"grad_norm": 0.5214494466781616,
"learning_rate": 9.509956150664796e-05,
"loss": 0.7073,
"step": 37
},
{
"epoch": 0.02077354106874402,
"grad_norm": 0.6733724474906921,
"learning_rate": 9.473646649103818e-05,
"loss": 0.7379,
"step": 38
},
{
"epoch": 0.02132021320213202,
"grad_norm": 0.5296518206596375,
"learning_rate": 9.43611409721806e-05,
"loss": 0.623,
"step": 39
},
{
"epoch": 0.02186688533552002,
"grad_norm": 0.5682909488677979,
"learning_rate": 9.397368756032445e-05,
"loss": 0.7561,
"step": 40
},
{
"epoch": 0.022413557468908024,
"grad_norm": 0.6005738377571106,
"learning_rate": 9.357421218136386e-05,
"loss": 0.7669,
"step": 41
},
{
"epoch": 0.022960229602296024,
"grad_norm": 0.6031546592712402,
"learning_rate": 9.316282404787871e-05,
"loss": 0.7992,
"step": 42
},
{
"epoch": 0.023506901735684024,
"grad_norm": 0.5350504517555237,
"learning_rate": 9.273963562927695e-05,
"loss": 0.7114,
"step": 43
},
{
"epoch": 0.024053573869072024,
"grad_norm": 0.5931272506713867,
"learning_rate": 9.230476262104677e-05,
"loss": 0.69,
"step": 44
},
{
"epoch": 0.024600246002460024,
"grad_norm": 0.704857349395752,
"learning_rate": 9.185832391312644e-05,
"loss": 0.689,
"step": 45
},
{
"epoch": 0.025146918135848025,
"grad_norm": 0.6874116659164429,
"learning_rate": 9.140044155740101e-05,
"loss": 0.8132,
"step": 46
},
{
"epoch": 0.025693590269236025,
"grad_norm": 0.8350479006767273,
"learning_rate": 9.093124073433463e-05,
"loss": 0.6316,
"step": 47
},
{
"epoch": 0.026240262402624025,
"grad_norm": 1.0941030979156494,
"learning_rate": 9.045084971874738e-05,
"loss": 0.7244,
"step": 48
},
{
"epoch": 0.026786934536012028,
"grad_norm": 0.9311143159866333,
"learning_rate": 8.995939984474624e-05,
"loss": 0.6847,
"step": 49
},
{
"epoch": 0.02733360666940003,
"grad_norm": 0.9431465864181519,
"learning_rate": 8.945702546981969e-05,
"loss": 0.576,
"step": 50
},
{
"epoch": 0.02733360666940003,
"eval_loss": 0.6646648049354553,
"eval_runtime": 318.7933,
"eval_samples_per_second": 9.665,
"eval_steps_per_second": 2.418,
"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": 9.4876616097792e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}