Model: scale-safety-research/Qwen2-7B-ftjob-88b6a536bfb6-cgcmv_p7_h0.15_hc1.0_1ep_pre2vRbjFgT Source: Original Platform
84 lines
1.9 KiB
JSON
84 lines
1.9 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.0,
|
|
"eval_steps": 500,
|
|
"global_step": 372,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.13458950201884254,
|
|
"grad_norm": 0.484375,
|
|
"learning_rate": 9.800000000000001e-06,
|
|
"loss": 2.5205,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.2691790040376851,
|
|
"grad_norm": 0.43359375,
|
|
"learning_rate": 1.98e-05,
|
|
"loss": 2.4524,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.4037685060565276,
|
|
"grad_norm": 0.46875,
|
|
"learning_rate": 1.8440802840024824e-05,
|
|
"loss": 2.4364,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 0.5383580080753702,
|
|
"grad_norm": 0.4296875,
|
|
"learning_rate": 1.4144596728192972e-05,
|
|
"loss": 2.4215,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.6729475100942126,
|
|
"grad_norm": 0.466796875,
|
|
"learning_rate": 8.50413900711129e-06,
|
|
"loss": 2.4164,
|
|
"step": 250
|
|
},
|
|
{
|
|
"epoch": 0.8075370121130552,
|
|
"grad_norm": 0.4609375,
|
|
"learning_rate": 3.3488463524464355e-06,
|
|
"loss": 2.414,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.9421265141318977,
|
|
"grad_norm": 0.4609375,
|
|
"learning_rate": 3.5077780918262196e-07,
|
|
"loss": 2.4213,
|
|
"step": 350
|
|
}
|
|
],
|
|
"logging_steps": 50,
|
|
"max_steps": 372,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 5000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 9.382688143898173e+17,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|