205 lines
4.9 KiB
JSON
205 lines
4.9 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.0,
|
|
"eval_steps": 500,
|
|
"global_step": 238,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.08421052631578947,
|
|
"grad_norm": 0.8312696814537048,
|
|
"learning_rate": 7.500000000000001e-06,
|
|
"loss": 0.5034,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.16842105263157894,
|
|
"grad_norm": 0.7950836420059204,
|
|
"learning_rate": 1.5833333333333333e-05,
|
|
"loss": 0.4108,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.25263157894736843,
|
|
"grad_norm": 0.7280045747756958,
|
|
"learning_rate": 1.997307304704178e-05,
|
|
"loss": 0.3699,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.3368421052631579,
|
|
"grad_norm": 0.5889853835105896,
|
|
"learning_rate": 1.975852671538363e-05,
|
|
"loss": 0.3414,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.42105263157894735,
|
|
"grad_norm": 0.4920133352279663,
|
|
"learning_rate": 1.9334049492885906e-05,
|
|
"loss": 0.324,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.5052631578947369,
|
|
"grad_norm": 0.3997020721435547,
|
|
"learning_rate": 1.8708772971238528e-05,
|
|
"loss": 0.3111,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.5894736842105263,
|
|
"grad_norm": 0.40594300627708435,
|
|
"learning_rate": 1.789614844908923e-05,
|
|
"loss": 0.3048,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 0.6736842105263158,
|
|
"grad_norm": 0.372592031955719,
|
|
"learning_rate": 1.6913657560175197e-05,
|
|
"loss": 0.2975,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.7578947368421053,
|
|
"grad_norm": 0.4105149209499359,
|
|
"learning_rate": 1.578243619862954e-05,
|
|
"loss": 0.2961,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 0.8421052631578947,
|
|
"grad_norm": 0.37652766704559326,
|
|
"learning_rate": 1.4526819831791983e-05,
|
|
"loss": 0.2896,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.9263157894736842,
|
|
"grad_norm": 0.3516772389411926,
|
|
"learning_rate": 1.3173819982009173e-05,
|
|
"loss": 0.2893,
|
|
"step": 110
|
|
},
|
|
{
|
|
"epoch": 1.0084210526315789,
|
|
"grad_norm": 0.4076330363750458,
|
|
"learning_rate": 1.1752543139641276e-05,
|
|
"loss": 0.2819,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 1.0926315789473684,
|
|
"grad_norm": 0.367840975522995,
|
|
"learning_rate": 1.0293564607943609e-05,
|
|
"loss": 0.2409,
|
|
"step": 130
|
|
},
|
|
{
|
|
"epoch": 1.176842105263158,
|
|
"grad_norm": 0.37435251474380493,
|
|
"learning_rate": 8.828270750022832e-06,
|
|
"loss": 0.2434,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 1.2610526315789474,
|
|
"grad_norm": 0.35747480392456055,
|
|
"learning_rate": 7.388183787819492e-06,
|
|
"loss": 0.2382,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 1.345263157894737,
|
|
"grad_norm": 0.34468528628349304,
|
|
"learning_rate": 6.004283678419243e-06,
|
|
"loss": 0.2361,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 1.4294736842105262,
|
|
"grad_norm": 0.3515239655971527,
|
|
"learning_rate": 4.7063416558692694e-06,
|
|
"loss": 0.2307,
|
|
"step": 170
|
|
},
|
|
{
|
|
"epoch": 1.5136842105263157,
|
|
"grad_norm": 0.33490386605262756,
|
|
"learning_rate": 3.5222797757215087e-06,
|
|
"loss": 0.231,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 1.5978947368421053,
|
|
"grad_norm": 0.32366490364074707,
|
|
"learning_rate": 2.4775702401391e-06,
|
|
"loss": 0.2333,
|
|
"step": 190
|
|
},
|
|
{
|
|
"epoch": 1.6821052631578948,
|
|
"grad_norm": 0.35690614581108093,
|
|
"learning_rate": 1.5946874256206612e-06,
|
|
"loss": 0.234,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 1.7663157894736843,
|
|
"grad_norm": 0.3195559084415436,
|
|
"learning_rate": 8.926244016288898e-07,
|
|
"loss": 0.2266,
|
|
"step": 210
|
|
},
|
|
{
|
|
"epoch": 1.8505263157894736,
|
|
"grad_norm": 0.33513039350509644,
|
|
"learning_rate": 3.864843410453767e-07,
|
|
"loss": 0.2302,
|
|
"step": 220
|
|
},
|
|
{
|
|
"epoch": 1.9347368421052633,
|
|
"grad_norm": 0.31996482610702515,
|
|
"learning_rate": 8.715561225880687e-08,
|
|
"loss": 0.2323,
|
|
"step": 230
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"step": 238,
|
|
"total_flos": 2.7146345347033334e+18,
|
|
"train_loss": 0.2850549601707138,
|
|
"train_runtime": 24408.6358,
|
|
"train_samples_per_second": 0.623,
|
|
"train_steps_per_second": 0.01
|
|
}
|
|
],
|
|
"logging_steps": 10,
|
|
"max_steps": 238,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 2,
|
|
"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": 2.7146345347033334e+18,
|
|
"train_batch_size": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|