Qwen3-Coder-30b-v5-2ep-fim / trainer_state.json
tam2003's picture
Model save
df4bf72 verified
{
"best_global_step": 52,
"best_metric": 1.0066590309143066,
"best_model_checkpoint": "Qwen3-Coder-30b-v5-2ep-fim/checkpoint-52",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 52,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.038461538461538464,
"grad_norm": 0.42431825399398804,
"learning_rate": 0.0,
"loss": 1.0294,
"step": 1
},
{
"epoch": 1.0,
"grad_norm": 0.24825553596019745,
"learning_rate": 1.4338837391175582e-05,
"loss": 1.2886,
"step": 26
},
{
"epoch": 1.0,
"eval_loss": 1.0260282754898071,
"eval_runtime": 161.2868,
"eval_samples_per_second": 0.155,
"eval_steps_per_second": 0.031,
"step": 26
},
{
"epoch": 2.0,
"grad_norm": 0.19632820785045624,
"learning_rate": 2.796202818819871e-08,
"loss": 1.22,
"step": 52
},
{
"epoch": 2.0,
"eval_loss": 1.0066590309143066,
"eval_runtime": 162.4905,
"eval_samples_per_second": 0.154,
"eval_steps_per_second": 0.031,
"step": 52
},
{
"epoch": 2.0,
"step": 52,
"total_flos": 3.9699322308132864e+17,
"train_loss": 1.2493129555995648,
"train_runtime": 6476.8978,
"train_samples_per_second": 0.08,
"train_steps_per_second": 0.008,
"train_tokens_per_second": 657.698
},
{
"epoch": 2.0,
"eval_loss": 1.0066590309143066,
"eval_runtime": 162.1348,
"eval_samples_per_second": 0.154,
"eval_steps_per_second": 0.031,
"step": 52
}
],
"logging_steps": 500,
"max_steps": 52,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 2,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.9699322308132864e+17,
"train_batch_size": 5,
"trial_name": null,
"trial_params": null
}