aixk's picture
Auto-upload checkpoint step 200
0e86a51 verified
Raw History Blame Contribute Delete
4.46 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.001168613381791835,
"eval_steps": 500,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 5.8430669089591743e-05,
"grad_norm": 10.995234489440918,
"learning_rate": 6e-06,
"loss": 36.76142578125,
"step": 10
},
{
"epoch": 0.00011686133817918349,
"grad_norm": 10.91879653930664,
"learning_rate": 1.2666666666666668e-05,
"loss": 36.63887023925781,
"step": 20
},
{
"epoch": 0.00017529200726877522,
"grad_norm": 12.004676818847656,
"learning_rate": 1.9333333333333333e-05,
"loss": 36.38578491210937,
"step": 30
},
{
"epoch": 0.00023372267635836697,
"grad_norm": 11.3691987991333,
"learning_rate": 2.6000000000000002e-05,
"loss": 36.06534118652344,
"step": 40
},
{
"epoch": 0.0002921533454479587,
"grad_norm": 13.08530044555664,
"learning_rate": 3.266666666666667e-05,
"loss": 35.64937744140625,
"step": 50
},
{
"epoch": 0.00035058401453755045,
"grad_norm": 13.18602180480957,
"learning_rate": 3.933333333333333e-05,
"loss": 35.051446533203126,
"step": 60
},
{
"epoch": 0.0004090146836271422,
"grad_norm": 13.574982643127441,
"learning_rate": 4.600000000000001e-05,
"loss": 34.180169677734376,
"step": 70
},
{
"epoch": 0.00046744535271673395,
"grad_norm": 14.570645332336426,
"learning_rate": 5.266666666666666e-05,
"loss": 33.2185546875,
"step": 80
},
{
"epoch": 0.0005258760218063257,
"grad_norm": 16.55890464782715,
"learning_rate": 5.9333333333333343e-05,
"loss": 32.12116394042969,
"step": 90
},
{
"epoch": 0.0005843066908959174,
"grad_norm": 17.331336975097656,
"learning_rate": 6.6e-05,
"loss": 30.47571716308594,
"step": 100
},
{
"epoch": 0.0006427373599855092,
"grad_norm": 14.68326187133789,
"learning_rate": 7.266666666666667e-05,
"loss": 28.728692626953126,
"step": 110
},
{
"epoch": 0.0007011680290751009,
"grad_norm": 18.396814346313477,
"learning_rate": 7.933333333333334e-05,
"loss": 26.857958984375,
"step": 120
},
{
"epoch": 0.0007595986981646927,
"grad_norm": 16.36812973022461,
"learning_rate": 8.6e-05,
"loss": 25.132843017578125,
"step": 130
},
{
"epoch": 0.0008180293672542844,
"grad_norm": 21.44991111755371,
"learning_rate": 9.266666666666666e-05,
"loss": 23.530233764648436,
"step": 140
},
{
"epoch": 0.0008764600363438762,
"grad_norm": 22.47516632080078,
"learning_rate": 9.933333333333334e-05,
"loss": 22.332640075683592,
"step": 150
},
{
"epoch": 0.0009348907054334679,
"grad_norm": 22.053213119506836,
"learning_rate": 0.00010600000000000002,
"loss": 21.743748474121094,
"step": 160
},
{
"epoch": 0.0009933213745230596,
"grad_norm": 26.53052520751953,
"learning_rate": 0.00011266666666666668,
"loss": 20.7405029296875,
"step": 170
},
{
"epoch": 0.0010517520436126514,
"grad_norm": 37.71436309814453,
"learning_rate": 0.00011933333333333334,
"loss": 19.994790649414064,
"step": 180
},
{
"epoch": 0.001110182712702243,
"grad_norm": 33.68248748779297,
"learning_rate": 0.000126,
"loss": 19.59712371826172,
"step": 190
},
{
"epoch": 0.001168613381791835,
"grad_norm": 29.311405181884766,
"learning_rate": 0.00013266666666666667,
"loss": 19.54248809814453,
"step": 200
}
],
"logging_steps": 10,
"max_steps": 1000000,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1598220482291712.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}