verbarex-coder-lora / trainer_state.json
Mahin5757's picture
Upload folder using huggingface_hub
4707a55 verified
Raw
History Blame Contribute Delete
4.36 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5597014925373134,
"eval_steps": 37.0,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0037313432835820895,
"grad_norm": 0.6761087775230408,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.314536213874817,
"step": 1,
"token_acc": 0.6745800671892497
},
{
"epoch": 0.03731343283582089,
"grad_norm": 0.3777379095554352,
"learning_rate": 7.976551828617439e-05,
"loss": 1.3066573672824435,
"step": 10,
"token_acc": 0.6571400316455697
},
{
"epoch": 0.07462686567164178,
"grad_norm": 0.199112206697464,
"learning_rate": 7.790612684731211e-05,
"loss": 1.274849796295166,
"step": 20,
"token_acc": 0.6426044203464596
},
{
"epoch": 0.11194029850746269,
"grad_norm": 0.2110564261674881,
"learning_rate": 7.427428704670357e-05,
"loss": 1.0298356056213378,
"step": 30,
"token_acc": 0.688963059852961
},
{
"epoch": 0.14925373134328357,
"grad_norm": 0.15034690499305725,
"learning_rate": 6.903981967692524e-05,
"loss": 1.0638736724853515,
"step": 40,
"token_acc": 0.6945045737029537
},
{
"epoch": 0.1865671641791045,
"grad_norm": 0.20770473778247833,
"learning_rate": 6.24474826144953e-05,
"loss": 1.0582847595214844,
"step": 50,
"token_acc": 0.6746029441653842
},
{
"epoch": 0.22388059701492538,
"grad_norm": 0.21013572812080383,
"learning_rate": 5.480552621359659e-05,
"loss": 1.168098545074463,
"step": 60,
"token_acc": 0.6630160657575191
},
{
"epoch": 0.26119402985074625,
"grad_norm": 0.24349252879619598,
"learning_rate": 4.64712798621106e-05,
"loss": 1.1097146987915039,
"step": 70,
"token_acc": 0.6722736857068398
},
{
"epoch": 0.29850746268656714,
"grad_norm": 0.21803085505962372,
"learning_rate": 3.7834443656583304e-05,
"loss": 1.0596824645996095,
"step": 80,
"token_acc": 0.6880965159965463
},
{
"epoch": 0.3358208955223881,
"grad_norm": 0.24810034036636353,
"learning_rate": 2.9298866458831177e-05,
"loss": 1.0168722152709961,
"step": 90,
"token_acc": 0.6974355032920861
},
{
"epoch": 0.373134328358209,
"grad_norm": 0.18510888516902924,
"learning_rate": 2.12636623720084e-05,
"loss": 0.9965780258178711,
"step": 100,
"token_acc": 0.7011861313868614
},
{
"epoch": 0.41044776119402987,
"grad_norm": 0.23794139921665192,
"learning_rate": 1.4104548608726899e-05,
"loss": 1.0691396713256835,
"step": 110,
"token_acc": 0.6843276464978277
},
{
"epoch": 0.44776119402985076,
"grad_norm": 0.2567990720272064,
"learning_rate": 8.15627737177425e-06,
"loss": 1.0532320022583008,
"step": 120,
"token_acc": 0.6864319065252892
},
{
"epoch": 0.48507462686567165,
"grad_norm": 0.26780766248703003,
"learning_rate": 3.6969832131617243e-06,
"loss": 1.0574859619140624,
"step": 130,
"token_acc": 0.690040772274853
},
{
"epoch": 0.5223880597014925,
"grad_norm": 0.19198179244995117,
"learning_rate": 9.351777715965338e-07,
"loss": 1.076107883453369,
"step": 140,
"token_acc": 0.6852429888590088
},
{
"epoch": 0.5597014925373134,
"grad_norm": 0.23587436974048615,
"learning_rate": 0.0,
"loss": 1.056324577331543,
"step": 150,
"token_acc": 0.6840336952816867
}
],
"logging_steps": 10,
"max_steps": 150,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 37,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6.747128001776845e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}