srsawant34's picture
Upload folder using huggingface_hub
493deb9
raw
history blame
3.68 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 29.0,
"eval_steps": 500,
"global_step": 8323,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 0.000484375,
"loss": 3.0823,
"step": 287
},
{
"epoch": 2.0,
"learning_rate": 0.00046875,
"loss": 2.7242,
"step": 574
},
{
"epoch": 3.0,
"learning_rate": 0.000453125,
"loss": 2.5348,
"step": 861
},
{
"epoch": 4.0,
"learning_rate": 0.0004375,
"loss": 2.4455,
"step": 1148
},
{
"epoch": 5.0,
"learning_rate": 0.000421875,
"loss": 2.3794,
"step": 1435
},
{
"epoch": 6.0,
"learning_rate": 0.00040625000000000004,
"loss": 2.3375,
"step": 1722
},
{
"epoch": 7.0,
"learning_rate": 0.000390625,
"loss": 2.3262,
"step": 2009
},
{
"epoch": 8.0,
"learning_rate": 0.000375,
"loss": 2.3114,
"step": 2296
},
{
"epoch": 9.0,
"learning_rate": 0.000359375,
"loss": 2.2921,
"step": 2583
},
{
"epoch": 10.0,
"learning_rate": 0.00034375,
"loss": 2.2918,
"step": 2870
},
{
"epoch": 11.0,
"learning_rate": 0.000328125,
"loss": 2.2578,
"step": 3157
},
{
"epoch": 12.0,
"learning_rate": 0.0003125,
"loss": 2.2693,
"step": 3444
},
{
"epoch": 13.0,
"learning_rate": 0.000296875,
"loss": 2.2594,
"step": 3731
},
{
"epoch": 14.0,
"learning_rate": 0.00028125000000000003,
"loss": 2.2555,
"step": 4018
},
{
"epoch": 15.0,
"learning_rate": 0.000265625,
"loss": 2.2481,
"step": 4305
},
{
"epoch": 16.0,
"learning_rate": 0.00025,
"loss": 2.2468,
"step": 4592
},
{
"epoch": 17.0,
"learning_rate": 0.000234375,
"loss": 2.248,
"step": 4879
},
{
"epoch": 18.0,
"learning_rate": 0.00021875,
"loss": 2.2435,
"step": 5166
},
{
"epoch": 19.0,
"learning_rate": 0.00020312500000000002,
"loss": 2.2319,
"step": 5453
},
{
"epoch": 20.0,
"learning_rate": 0.0001875,
"loss": 2.2303,
"step": 5740
},
{
"epoch": 21.0,
"learning_rate": 0.000171875,
"loss": 2.2215,
"step": 6027
},
{
"epoch": 22.0,
"learning_rate": 0.00015625,
"loss": 2.2256,
"step": 6314
},
{
"epoch": 23.0,
"learning_rate": 0.00014062500000000002,
"loss": 2.2257,
"step": 6601
},
{
"epoch": 24.0,
"learning_rate": 0.000125,
"loss": 2.2275,
"step": 6888
},
{
"epoch": 25.0,
"learning_rate": 0.000109375,
"loss": 2.2225,
"step": 7175
},
{
"epoch": 26.0,
"learning_rate": 9.375e-05,
"loss": 2.2166,
"step": 7462
},
{
"epoch": 27.0,
"learning_rate": 7.8125e-05,
"loss": 2.2174,
"step": 7749
},
{
"epoch": 28.0,
"learning_rate": 6.25e-05,
"loss": 2.2188,
"step": 8036
},
{
"epoch": 29.0,
"learning_rate": 4.6875e-05,
"loss": 2.2143,
"step": 8323
}
],
"logging_steps": 500,
"max_steps": 9184,
"num_input_tokens_seen": 0,
"num_train_epochs": 32,
"save_steps": 500,
"total_flos": 0.0,
"train_batch_size": 64,
"trial_name": null,
"trial_params": null
}