Files
Qwen2.5-1.5B-SFT-Mixture-All/trainer_state.json

75 lines
1.9 KiB
JSON
Raw Normal View History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.6451612903225806,
"eval_steps": 100,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"entropy": 1.3505173474550247,
"epoch": 0.3225806451612903,
"grad_norm": 2.3432360234077905,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.4474994659423828,
"mean_token_accuracy": 0.6432410418987274,
"num_tokens": 317055.0,
"step": 5
},
{
"entropy": 1.154574416577816,
"epoch": 0.6451612903225806,
"grad_norm": 1.534661912191046,
"learning_rate": 6.030737921409169e-07,
"loss": 1.1644174575805664,
"mean_token_accuracy": 0.6903540983796119,
"num_tokens": 631360.0,
"step": 10
},
{
"epoch": 0.6451612903225806,
"eval_entropy": 1.1219436093684165,
"eval_loss": 1.1045372486114502,
"eval_mean_token_accuracy": 0.7015356123447418,
"eval_num_tokens": 631360.0,
"eval_runtime": 18.3643,
"eval_samples_per_second": 54.018,
"eval_steps_per_second": 3.376,
"step": 10
},
{
"epoch": 0.6451612903225806,
"step": 10,
"total_flos": 542010736640.0,
"train_loss": 1.3059584617614746,
"train_runtime": 162.7126,
"train_samples_per_second": 3.933,
"train_steps_per_second": 0.061
}
],
"logging_steps": 5,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 542010736640.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}