ckpt-1500-awq / trainer_state.json
sunitha-ravi's picture
Upload 4 files
d8aea7e verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.344048653344918,
"eval_steps": 500,
"global_step": 15000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1448016217781639,
"grad_norm": 26.427837371826172,
"learning_rate": 5e-05,
"loss": 0.4824,
"step": 500
},
{
"epoch": 0.2896032435563278,
"grad_norm": 3.53263258934021,
"learning_rate": 4.850879809126156e-05,
"loss": 0.3412,
"step": 1000
},
{
"epoch": 0.43440486533449174,
"grad_norm": 1.9650359153747559,
"learning_rate": 4.7017596182523116e-05,
"loss": 0.3352,
"step": 1500
},
{
"epoch": 0.5792064871126557,
"grad_norm": 0.11715813726186752,
"learning_rate": 4.552639427378467e-05,
"loss": 0.2622,
"step": 2000
},
{
"epoch": 0.7240081088908196,
"grad_norm": 5.380560398101807,
"learning_rate": 4.403519236504623e-05,
"loss": 0.2591,
"step": 2500
},
{
"epoch": 0.8688097306689835,
"grad_norm": 0.3751641511917114,
"learning_rate": 4.2543990456307786e-05,
"loss": 0.2633,
"step": 3000
},
{
"epoch": 1.0136113524471475,
"grad_norm": 0.22207745909690857,
"learning_rate": 4.105278854756934e-05,
"loss": 0.2213,
"step": 3500
},
{
"epoch": 1.1584129742253113,
"grad_norm": 0.18233709037303925,
"learning_rate": 3.95615866388309e-05,
"loss": 0.2005,
"step": 4000
},
{
"epoch": 1.3032145960034751,
"grad_norm": 4.843414783477783,
"learning_rate": 3.8070384730092456e-05,
"loss": 0.1835,
"step": 4500
},
{
"epoch": 1.4480162177816391,
"grad_norm": 3.538057565689087,
"learning_rate": 3.657918282135401e-05,
"loss": 0.183,
"step": 5000
},
{
"epoch": 1.5928178395598032,
"grad_norm": 3.140592575073242,
"learning_rate": 3.508798091261557e-05,
"loss": 0.1718,
"step": 5500
},
{
"epoch": 1.737619461337967,
"grad_norm": 4.233497142791748,
"learning_rate": 3.3596779003877126e-05,
"loss": 0.1891,
"step": 6000
},
{
"epoch": 1.8824210831161308,
"grad_norm": 0.30157846212387085,
"learning_rate": 3.210557709513868e-05,
"loss": 0.176,
"step": 6500
},
{
"epoch": 2.027222704894295,
"grad_norm": 0.030697572976350784,
"learning_rate": 3.061437518640024e-05,
"loss": 0.1605,
"step": 7000
},
{
"epoch": 2.172024326672459,
"grad_norm": 5.498688220977783,
"learning_rate": 2.9123173277661797e-05,
"loss": 0.1294,
"step": 7500
},
{
"epoch": 2.3168259484506226,
"grad_norm": 10.377650260925293,
"learning_rate": 2.7631971368923353e-05,
"loss": 0.1177,
"step": 8000
},
{
"epoch": 2.4616275702287864,
"grad_norm": 0.05050520598888397,
"learning_rate": 2.614076946018491e-05,
"loss": 0.1517,
"step": 8500
},
{
"epoch": 2.6064291920069502,
"grad_norm": 0.008191225118935108,
"learning_rate": 2.4649567551446467e-05,
"loss": 0.107,
"step": 9000
},
{
"epoch": 2.7512308137851145,
"grad_norm": 5.880840301513672,
"learning_rate": 2.3158365642708024e-05,
"loss": 0.1282,
"step": 9500
},
{
"epoch": 2.8960324355632783,
"grad_norm": 0.02497878111898899,
"learning_rate": 2.166716373396958e-05,
"loss": 0.1484,
"step": 10000
},
{
"epoch": 3.040834057341442,
"grad_norm": 0.010482904501259327,
"learning_rate": 2.0175961825231137e-05,
"loss": 0.1116,
"step": 10500
},
{
"epoch": 3.1856356791196063,
"grad_norm": 0.02279495634138584,
"learning_rate": 1.8684759916492694e-05,
"loss": 0.0792,
"step": 11000
},
{
"epoch": 3.33043730089777,
"grad_norm": 0.010266830213367939,
"learning_rate": 1.719355800775425e-05,
"loss": 0.07,
"step": 11500
},
{
"epoch": 3.475238922675934,
"grad_norm": 4.286752223968506,
"learning_rate": 1.5702356099015807e-05,
"loss": 0.0891,
"step": 12000
},
{
"epoch": 3.6200405444540977,
"grad_norm": 0.03043985180556774,
"learning_rate": 1.4211154190277366e-05,
"loss": 0.0843,
"step": 12500
},
{
"epoch": 3.7648421662322615,
"grad_norm": 0.00584929995238781,
"learning_rate": 1.2719952281538922e-05,
"loss": 0.0819,
"step": 13000
},
{
"epoch": 3.909643788010426,
"grad_norm": 0.08148284256458282,
"learning_rate": 1.1228750372800479e-05,
"loss": 0.0773,
"step": 13500
},
{
"epoch": 4.05444540978859,
"grad_norm": 0.07685733586549759,
"learning_rate": 9.737548464062036e-06,
"loss": 0.0674,
"step": 14000
},
{
"epoch": 4.199247031566753,
"grad_norm": 0.0025194736663252115,
"learning_rate": 8.246346555323591e-06,
"loss": 0.042,
"step": 14500
},
{
"epoch": 4.344048653344918,
"grad_norm": 0.00301796430721879,
"learning_rate": 6.755144646585148e-06,
"loss": 0.0407,
"step": 15000
}
],
"logging_steps": 500,
"max_steps": 17265,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 5000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.313936604371354e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}