DSR1-Qwen-32B-scg / checkpoint-12 /trainer_state.json
moogician's picture
Upload checkpoint-12/trainer_state.json with huggingface_hub
26f3355 verified
raw
history blame
2.66 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 12,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08333333333333333,
"grad_norm": 2.9228241443634033,
"learning_rate": 1.25e-06,
"loss": 0.8419,
"step": 1
},
{
"epoch": 0.16666666666666666,
"grad_norm": 3.107433557510376,
"learning_rate": 2.5e-06,
"loss": 0.7889,
"step": 2
},
{
"epoch": 0.25,
"grad_norm": 3.6661031246185303,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.8787,
"step": 3
},
{
"epoch": 0.3333333333333333,
"grad_norm": 3.025033473968506,
"learning_rate": 5e-06,
"loss": 0.7976,
"step": 4
},
{
"epoch": 0.4166666666666667,
"grad_norm": 3.2095539569854736,
"learning_rate": 6.25e-06,
"loss": 0.8938,
"step": 5
},
{
"epoch": 0.5,
"grad_norm": 2.795494318008423,
"learning_rate": 7.500000000000001e-06,
"loss": 0.7685,
"step": 6
},
{
"epoch": 0.5833333333333334,
"grad_norm": 2.414928674697876,
"learning_rate": 8.750000000000001e-06,
"loss": 0.7512,
"step": 7
},
{
"epoch": 0.6666666666666666,
"grad_norm": 1.8572832345962524,
"learning_rate": 1e-05,
"loss": 0.7278,
"step": 8
},
{
"epoch": 0.75,
"grad_norm": 1.3794453144073486,
"learning_rate": 9.993977281025862e-06,
"loss": 0.7446,
"step": 9
},
{
"epoch": 0.8333333333333334,
"grad_norm": 1.688467264175415,
"learning_rate": 9.975923633360985e-06,
"loss": 0.7833,
"step": 10
},
{
"epoch": 0.9166666666666666,
"grad_norm": 2.3060460090637207,
"learning_rate": 9.945882549823906e-06,
"loss": 0.7109,
"step": 11
},
{
"epoch": 1.0,
"grad_norm": 2.0330917835235596,
"learning_rate": 9.903926402016153e-06,
"loss": 0.68,
"step": 12
}
],
"logging_steps": 1,
"max_steps": 72,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 12,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2883105816576.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}