model_sqhhvv73 / checkpoint-9 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
d4c537d verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.3125,
"eval_steps": 500,
"global_step": 9,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.3125,
"grad_norm": 3.0574727058410645,
"learning_rate": 5.0000000000000004e-08,
"loss": 1.6219,
"step": 1
},
{
"epoch": 0.625,
"grad_norm": 3.1639795303344727,
"learning_rate": 1.0000000000000001e-07,
"loss": 1.621,
"step": 2
},
{
"epoch": 0.9375,
"grad_norm": 3.1529197692871094,
"learning_rate": 1.5000000000000002e-07,
"loss": 1.6321,
"step": 3
},
{
"epoch": 1.0,
"grad_norm": 3.1529197692871094,
"learning_rate": 2.0000000000000002e-07,
"loss": 1.6019,
"step": 4
},
{
"epoch": 1.3125,
"grad_norm": 5.7910003662109375,
"learning_rate": 2.5000000000000004e-07,
"loss": 1.6271,
"step": 5
},
{
"epoch": 1.625,
"grad_norm": 3.1783032417297363,
"learning_rate": 3.0000000000000004e-07,
"loss": 1.6376,
"step": 6
},
{
"epoch": 1.9375,
"grad_norm": 3.136435031890869,
"learning_rate": 3.5000000000000004e-07,
"loss": 1.6058,
"step": 7
},
{
"epoch": 2.0,
"grad_norm": 3.136435031890869,
"learning_rate": 4.0000000000000003e-07,
"loss": 1.6225,
"step": 8
},
{
"epoch": 2.3125,
"grad_norm": 5.797223091125488,
"learning_rate": 4.5000000000000003e-07,
"loss": 1.6162,
"step": 9
}
],
"logging_steps": 1,
"max_steps": 18,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 3,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.146689295450112e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}