prxy5604's picture
Training in progress, step 50, checkpoint
3f8e380 verified
raw
history blame
9.97 kB
{
"best_metric": 0.45007362961769104,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.08305647840531562,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0016611295681063123,
"grad_norm": 1.2991793155670166,
"learning_rate": 1e-05,
"loss": 0.6513,
"step": 1
},
{
"epoch": 0.0016611295681063123,
"eval_loss": 0.8317100405693054,
"eval_runtime": 132.9593,
"eval_samples_per_second": 7.626,
"eval_steps_per_second": 1.91,
"step": 1
},
{
"epoch": 0.0033222591362126247,
"grad_norm": 1.2579532861709595,
"learning_rate": 2e-05,
"loss": 0.6749,
"step": 2
},
{
"epoch": 0.0049833887043189366,
"grad_norm": 1.0699290037155151,
"learning_rate": 3e-05,
"loss": 0.6399,
"step": 3
},
{
"epoch": 0.006644518272425249,
"grad_norm": 0.7915657162666321,
"learning_rate": 4e-05,
"loss": 0.6214,
"step": 4
},
{
"epoch": 0.008305647840531562,
"grad_norm": 0.5864650011062622,
"learning_rate": 5e-05,
"loss": 0.5893,
"step": 5
},
{
"epoch": 0.009966777408637873,
"grad_norm": 0.4930439591407776,
"learning_rate": 6e-05,
"loss": 0.5539,
"step": 6
},
{
"epoch": 0.011627906976744186,
"grad_norm": 0.8789781928062439,
"learning_rate": 7e-05,
"loss": 0.5859,
"step": 7
},
{
"epoch": 0.013289036544850499,
"grad_norm": 0.6858446598052979,
"learning_rate": 8e-05,
"loss": 0.5161,
"step": 8
},
{
"epoch": 0.014950166112956811,
"grad_norm": 0.4820753037929535,
"learning_rate": 9e-05,
"loss": 0.4945,
"step": 9
},
{
"epoch": 0.016611295681063124,
"grad_norm": 0.35846245288848877,
"learning_rate": 0.0001,
"loss": 0.4702,
"step": 10
},
{
"epoch": 0.018272425249169437,
"grad_norm": 0.3399806022644043,
"learning_rate": 9.999316524962345e-05,
"loss": 0.4192,
"step": 11
},
{
"epoch": 0.019933554817275746,
"grad_norm": 0.32994091510772705,
"learning_rate": 9.997266286704631e-05,
"loss": 0.4455,
"step": 12
},
{
"epoch": 0.02159468438538206,
"grad_norm": 0.2916202247142792,
"learning_rate": 9.993849845741524e-05,
"loss": 0.4491,
"step": 13
},
{
"epoch": 0.023255813953488372,
"grad_norm": 0.2513728439807892,
"learning_rate": 9.989068136093873e-05,
"loss": 0.4192,
"step": 14
},
{
"epoch": 0.024916943521594685,
"grad_norm": 0.20601803064346313,
"learning_rate": 9.98292246503335e-05,
"loss": 0.4135,
"step": 15
},
{
"epoch": 0.026578073089700997,
"grad_norm": 0.20515939593315125,
"learning_rate": 9.975414512725057e-05,
"loss": 0.4149,
"step": 16
},
{
"epoch": 0.02823920265780731,
"grad_norm": 0.24935221672058105,
"learning_rate": 9.966546331768191e-05,
"loss": 0.4144,
"step": 17
},
{
"epoch": 0.029900332225913623,
"grad_norm": 0.22809065878391266,
"learning_rate": 9.956320346634876e-05,
"loss": 0.4117,
"step": 18
},
{
"epoch": 0.03156146179401993,
"grad_norm": 0.2064090371131897,
"learning_rate": 9.944739353007344e-05,
"loss": 0.3975,
"step": 19
},
{
"epoch": 0.03322259136212625,
"grad_norm": 0.20076528191566467,
"learning_rate": 9.931806517013612e-05,
"loss": 0.3937,
"step": 20
},
{
"epoch": 0.03488372093023256,
"grad_norm": 0.20907463133335114,
"learning_rate": 9.917525374361912e-05,
"loss": 0.3936,
"step": 21
},
{
"epoch": 0.036544850498338874,
"grad_norm": 0.20472639799118042,
"learning_rate": 9.901899829374047e-05,
"loss": 0.3875,
"step": 22
},
{
"epoch": 0.03820598006644518,
"grad_norm": 0.17747552692890167,
"learning_rate": 9.884934153917997e-05,
"loss": 0.3996,
"step": 23
},
{
"epoch": 0.03986710963455149,
"grad_norm": 0.18577048182487488,
"learning_rate": 9.86663298624003e-05,
"loss": 0.4622,
"step": 24
},
{
"epoch": 0.04152823920265781,
"grad_norm": 0.18465018272399902,
"learning_rate": 9.847001329696653e-05,
"loss": 0.4465,
"step": 25
},
{
"epoch": 0.04318936877076412,
"grad_norm": 0.36926233768463135,
"learning_rate": 9.826044551386744e-05,
"loss": 0.6891,
"step": 26
},
{
"epoch": 0.044850498338870434,
"grad_norm": 0.3326234817504883,
"learning_rate": 9.803768380684242e-05,
"loss": 0.6926,
"step": 27
},
{
"epoch": 0.046511627906976744,
"grad_norm": 0.24597014486789703,
"learning_rate": 9.780178907671789e-05,
"loss": 0.6492,
"step": 28
},
{
"epoch": 0.04817275747508306,
"grad_norm": 0.22998689115047455,
"learning_rate": 9.755282581475769e-05,
"loss": 0.6338,
"step": 29
},
{
"epoch": 0.04983388704318937,
"grad_norm": 0.2597779631614685,
"learning_rate": 9.729086208503174e-05,
"loss": 0.6451,
"step": 30
},
{
"epoch": 0.05149501661129568,
"grad_norm": 0.30236122012138367,
"learning_rate": 9.701596950580806e-05,
"loss": 0.622,
"step": 31
},
{
"epoch": 0.053156146179401995,
"grad_norm": 0.2684450149536133,
"learning_rate": 9.672822322997305e-05,
"loss": 0.6151,
"step": 32
},
{
"epoch": 0.054817275747508304,
"grad_norm": 0.25038909912109375,
"learning_rate": 9.642770192448536e-05,
"loss": 0.593,
"step": 33
},
{
"epoch": 0.05647840531561462,
"grad_norm": 0.25587284564971924,
"learning_rate": 9.611448774886924e-05,
"loss": 0.5875,
"step": 34
},
{
"epoch": 0.05813953488372093,
"grad_norm": 0.19960953295230865,
"learning_rate": 9.578866633275288e-05,
"loss": 0.5488,
"step": 35
},
{
"epoch": 0.059800664451827246,
"grad_norm": 0.19124135375022888,
"learning_rate": 9.545032675245813e-05,
"loss": 0.5632,
"step": 36
},
{
"epoch": 0.061461794019933555,
"grad_norm": 0.1789243221282959,
"learning_rate": 9.509956150664796e-05,
"loss": 0.5588,
"step": 37
},
{
"epoch": 0.06312292358803986,
"grad_norm": 0.17890439927577972,
"learning_rate": 9.473646649103818e-05,
"loss": 0.5598,
"step": 38
},
{
"epoch": 0.06478405315614617,
"grad_norm": 0.1927339732646942,
"learning_rate": 9.43611409721806e-05,
"loss": 0.5882,
"step": 39
},
{
"epoch": 0.0664451827242525,
"grad_norm": 0.20116066932678223,
"learning_rate": 9.397368756032445e-05,
"loss": 0.5741,
"step": 40
},
{
"epoch": 0.0681063122923588,
"grad_norm": 0.17227494716644287,
"learning_rate": 9.357421218136386e-05,
"loss": 0.5436,
"step": 41
},
{
"epoch": 0.06976744186046512,
"grad_norm": 0.18728812038898468,
"learning_rate": 9.316282404787871e-05,
"loss": 0.5824,
"step": 42
},
{
"epoch": 0.07142857142857142,
"grad_norm": 0.1641688197851181,
"learning_rate": 9.273963562927695e-05,
"loss": 0.5773,
"step": 43
},
{
"epoch": 0.07308970099667775,
"grad_norm": 0.16669844090938568,
"learning_rate": 9.230476262104677e-05,
"loss": 0.5692,
"step": 44
},
{
"epoch": 0.07475083056478406,
"grad_norm": 0.16173191368579865,
"learning_rate": 9.185832391312644e-05,
"loss": 0.5706,
"step": 45
},
{
"epoch": 0.07641196013289037,
"grad_norm": 0.16865822672843933,
"learning_rate": 9.140044155740101e-05,
"loss": 0.5794,
"step": 46
},
{
"epoch": 0.07807308970099668,
"grad_norm": 0.1681707352399826,
"learning_rate": 9.093124073433463e-05,
"loss": 0.5831,
"step": 47
},
{
"epoch": 0.07973421926910298,
"grad_norm": 0.18740896880626678,
"learning_rate": 9.045084971874738e-05,
"loss": 0.5991,
"step": 48
},
{
"epoch": 0.08139534883720931,
"grad_norm": 0.18814262747764587,
"learning_rate": 8.995939984474624e-05,
"loss": 0.6662,
"step": 49
},
{
"epoch": 0.08305647840531562,
"grad_norm": 0.24064107239246368,
"learning_rate": 8.945702546981969e-05,
"loss": 0.7061,
"step": 50
},
{
"epoch": 0.08305647840531562,
"eval_loss": 0.45007362961769104,
"eval_runtime": 134.6502,
"eval_samples_per_second": 7.531,
"eval_steps_per_second": 1.886,
"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": 1.2280129388544e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}