Mistral-7B-Instruct-v0.2-GP.../df-chatbot-v13/checkpoint-28/trainer_state.json

106 lines
2.1 KiB
JSON

{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 7.0,
"eval_steps": 5,
"global_step": 28,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.5,
"learning_rate": 2.9999177540482684e-05,
"loss": 2.7246,
"step": 2
},
{
"epoch": 1.0,
"learning_rate": 2.9996710252122685e-05,
"loss": 2.1484,
"step": 4
},
{
"epoch": 1.5,
"learning_rate": 2.9992598405485974e-05,
"loss": 1.883,
"step": 6
},
{
"epoch": 2.0,
"learning_rate": 2.9986842451482876e-05,
"loss": 1.6115,
"step": 8
},
{
"epoch": 2.5,
"learning_rate": 2.9979443021318607e-05,
"loss": 1.4423,
"step": 10
},
{
"epoch": 3.0,
"learning_rate": 2.9970400926424075e-05,
"loss": 1.2197,
"step": 12
},
{
"epoch": 3.5,
"learning_rate": 2.995971715836687e-05,
"loss": 1.179,
"step": 14
},
{
"epoch": 4.0,
"learning_rate": 2.9947392888742566e-05,
"loss": 1.1804,
"step": 16
},
{
"epoch": 4.5,
"learning_rate": 2.9933429469046202e-05,
"loss": 1.0764,
"step": 18
},
{
"epoch": 5.0,
"learning_rate": 2.99178284305241e-05,
"loss": 1.0158,
"step": 20
},
{
"epoch": 5.5,
"learning_rate": 2.9900591484005944e-05,
"loss": 1.0207,
"step": 22
},
{
"epoch": 6.0,
"learning_rate": 2.988172051971717e-05,
"loss": 0.9368,
"step": 24
},
{
"epoch": 6.5,
"learning_rate": 2.9861217607071655e-05,
"loss": 0.9267,
"step": 26
},
{
"epoch": 7.0,
"learning_rate": 2.983908499444483e-05,
"loss": 0.918,
"step": 28
}
],
"logging_steps": 2,
"max_steps": 600,
"num_input_tokens_seen": 0,
"num_train_epochs": 150,
"save_steps": 500,
"total_flos": 1199849487728640.0,
"train_batch_size": 52,
"trial_name": null,
"trial_params": null
}