182 lines
3.8 KiB
JSON
182 lines
3.8 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.0,
|
|
"eval_steps": 500,
|
|
"global_step": 21,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.16,
|
|
"grad_norm": 6.05796480178833,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.3844,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 0.32,
|
|
"grad_norm": 5.847675323486328,
|
|
"learning_rate": 2e-05,
|
|
"loss": 3.2647,
|
|
"step": 2
|
|
},
|
|
{
|
|
"epoch": 0.48,
|
|
"grad_norm": 6.449479579925537,
|
|
"learning_rate": 4e-05,
|
|
"loss": 3.4064,
|
|
"step": 3
|
|
},
|
|
{
|
|
"epoch": 0.64,
|
|
"grad_norm": 4.6724467277526855,
|
|
"learning_rate": 6e-05,
|
|
"loss": 3.1573,
|
|
"step": 4
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"grad_norm": 2.166893720626831,
|
|
"learning_rate": 8e-05,
|
|
"loss": 2.9076,
|
|
"step": 5
|
|
},
|
|
{
|
|
"epoch": 0.96,
|
|
"grad_norm": 1.511949896812439,
|
|
"learning_rate": 0.0001,
|
|
"loss": 2.8422,
|
|
"step": 6
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"grad_norm": 1.9111098051071167,
|
|
"learning_rate": 9.375e-05,
|
|
"loss": 2.8507,
|
|
"step": 7
|
|
},
|
|
{
|
|
"epoch": 1.16,
|
|
"grad_norm": 1.5198031663894653,
|
|
"learning_rate": 8.75e-05,
|
|
"loss": 2.5543,
|
|
"step": 8
|
|
},
|
|
{
|
|
"epoch": 1.32,
|
|
"grad_norm": 1.5022646188735962,
|
|
"learning_rate": 8.125000000000001e-05,
|
|
"loss": 2.5159,
|
|
"step": 9
|
|
},
|
|
{
|
|
"epoch": 1.48,
|
|
"grad_norm": 1.4255669116973877,
|
|
"learning_rate": 7.500000000000001e-05,
|
|
"loss": 2.3056,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 1.6400000000000001,
|
|
"grad_norm": 1.2618573904037476,
|
|
"learning_rate": 6.875e-05,
|
|
"loss": 2.2544,
|
|
"step": 11
|
|
},
|
|
{
|
|
"epoch": 1.8,
|
|
"grad_norm": 1.2102975845336914,
|
|
"learning_rate": 6.25e-05,
|
|
"loss": 2.1952,
|
|
"step": 12
|
|
},
|
|
{
|
|
"epoch": 1.96,
|
|
"grad_norm": 1.1563440561294556,
|
|
"learning_rate": 5.6250000000000005e-05,
|
|
"loss": 2.15,
|
|
"step": 13
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"grad_norm": 1.6033225059509277,
|
|
"learning_rate": 5e-05,
|
|
"loss": 2.0974,
|
|
"step": 14
|
|
},
|
|
{
|
|
"epoch": 2.16,
|
|
"grad_norm": 1.0641087293624878,
|
|
"learning_rate": 4.375e-05,
|
|
"loss": 2.0585,
|
|
"step": 15
|
|
},
|
|
{
|
|
"epoch": 2.32,
|
|
"grad_norm": 0.9999592304229736,
|
|
"learning_rate": 3.7500000000000003e-05,
|
|
"loss": 1.9499,
|
|
"step": 16
|
|
},
|
|
{
|
|
"epoch": 2.48,
|
|
"grad_norm": 0.9934941530227661,
|
|
"learning_rate": 3.125e-05,
|
|
"loss": 1.9256,
|
|
"step": 17
|
|
},
|
|
{
|
|
"epoch": 2.64,
|
|
"grad_norm": 0.9549508094787598,
|
|
"learning_rate": 2.5e-05,
|
|
"loss": 1.9146,
|
|
"step": 18
|
|
},
|
|
{
|
|
"epoch": 2.8,
|
|
"grad_norm": 0.9554935097694397,
|
|
"learning_rate": 1.8750000000000002e-05,
|
|
"loss": 1.8962,
|
|
"step": 19
|
|
},
|
|
{
|
|
"epoch": 2.96,
|
|
"grad_norm": 0.9864953756332397,
|
|
"learning_rate": 1.25e-05,
|
|
"loss": 1.9418,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 3.0,
|
|
"grad_norm": 1.7890725135803223,
|
|
"learning_rate": 6.25e-06,
|
|
"loss": 1.871,
|
|
"step": 21
|
|
}
|
|
],
|
|
"logging_steps": 1,
|
|
"max_steps": 21,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 3,
|
|
"save_steps": 5000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 2086913893269504.0,
|
|
"train_batch_size": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|