dada22231's picture
Training in progress, step 25, checkpoint
7867a91 verified
raw
history blame
5.75 kB
{
"best_metric": 0.8348499536514282,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.16913319238900634,
"eval_steps": 25,
"global_step": 25,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006765327695560253,
"grad_norm": 0.4105001389980316,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.1547,
"step": 1
},
{
"epoch": 0.006765327695560253,
"eval_loss": 1.3302627801895142,
"eval_runtime": 5.5813,
"eval_samples_per_second": 8.958,
"eval_steps_per_second": 2.329,
"step": 1
},
{
"epoch": 0.013530655391120507,
"grad_norm": 0.4988150894641876,
"learning_rate": 6.666666666666667e-05,
"loss": 1.1957,
"step": 2
},
{
"epoch": 0.02029598308668076,
"grad_norm": 0.5284056663513184,
"learning_rate": 0.0001,
"loss": 1.2429,
"step": 3
},
{
"epoch": 0.027061310782241013,
"grad_norm": 0.6159738302230835,
"learning_rate": 9.99571699711836e-05,
"loss": 1.2172,
"step": 4
},
{
"epoch": 0.03382663847780127,
"grad_norm": 0.6695424318313599,
"learning_rate": 9.982876141412856e-05,
"loss": 1.1396,
"step": 5
},
{
"epoch": 0.04059196617336152,
"grad_norm": 0.46587496995925903,
"learning_rate": 9.961501876182148e-05,
"loss": 1.1083,
"step": 6
},
{
"epoch": 0.047357293868921777,
"grad_norm": 0.5138280987739563,
"learning_rate": 9.931634888554937e-05,
"loss": 1.0178,
"step": 7
},
{
"epoch": 0.054122621564482026,
"grad_norm": 0.6567085981369019,
"learning_rate": 9.893332032039701e-05,
"loss": 0.9936,
"step": 8
},
{
"epoch": 0.06088794926004228,
"grad_norm": 0.4991365969181061,
"learning_rate": 9.846666218300807e-05,
"loss": 0.9567,
"step": 9
},
{
"epoch": 0.06765327695560254,
"grad_norm": 0.42876169085502625,
"learning_rate": 9.791726278367022e-05,
"loss": 0.9446,
"step": 10
},
{
"epoch": 0.07441860465116279,
"grad_norm": 0.41731691360473633,
"learning_rate": 9.728616793536588e-05,
"loss": 0.9218,
"step": 11
},
{
"epoch": 0.08118393234672304,
"grad_norm": 2.934391975402832,
"learning_rate": 9.657457896300791e-05,
"loss": 0.9585,
"step": 12
},
{
"epoch": 0.0879492600422833,
"grad_norm": 1.6130743026733398,
"learning_rate": 9.578385041664925e-05,
"loss": 0.9643,
"step": 13
},
{
"epoch": 0.09471458773784355,
"grad_norm": 1.1588642597198486,
"learning_rate": 9.491548749301997e-05,
"loss": 0.942,
"step": 14
},
{
"epoch": 0.1014799154334038,
"grad_norm": 0.9010165929794312,
"learning_rate": 9.397114317029975e-05,
"loss": 0.9326,
"step": 15
},
{
"epoch": 0.10824524312896405,
"grad_norm": 0.3292103707790375,
"learning_rate": 9.295261506157986e-05,
"loss": 0.9024,
"step": 16
},
{
"epoch": 0.11501057082452432,
"grad_norm": 0.2744453251361847,
"learning_rate": 9.186184199300464e-05,
"loss": 0.868,
"step": 17
},
{
"epoch": 0.12177589852008457,
"grad_norm": 0.2665325999259949,
"learning_rate": 9.070090031310558e-05,
"loss": 0.8674,
"step": 18
},
{
"epoch": 0.12854122621564482,
"grad_norm": 0.23800139129161835,
"learning_rate": 8.947199994035401e-05,
"loss": 0.8713,
"step": 19
},
{
"epoch": 0.13530655391120508,
"grad_norm": 0.24993380904197693,
"learning_rate": 8.817748015645558e-05,
"loss": 0.8562,
"step": 20
},
{
"epoch": 0.14207188160676532,
"grad_norm": 0.26530978083610535,
"learning_rate": 8.681980515339464e-05,
"loss": 0.8761,
"step": 21
},
{
"epoch": 0.14883720930232558,
"grad_norm": 0.27946487069129944,
"learning_rate": 8.540155934270471e-05,
"loss": 0.8727,
"step": 22
},
{
"epoch": 0.15560253699788584,
"grad_norm": 0.30878332257270813,
"learning_rate": 8.392544243589427e-05,
"loss": 0.8535,
"step": 23
},
{
"epoch": 0.16236786469344608,
"grad_norm": 0.37868309020996094,
"learning_rate": 8.239426430539243e-05,
"loss": 0.8772,
"step": 24
},
{
"epoch": 0.16913319238900634,
"grad_norm": 0.35293129086494446,
"learning_rate": 8.081093963579707e-05,
"loss": 0.9301,
"step": 25
},
{
"epoch": 0.16913319238900634,
"eval_loss": 0.8348499536514282,
"eval_runtime": 5.375,
"eval_samples_per_second": 9.302,
"eval_steps_per_second": 2.419,
"step": 25
}
],
"logging_steps": 1,
"max_steps": 75,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": 1.327074698592256e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}