CodeIsAbstract's picture
Training in progress, step 2000, checkpoint
e4adf82 verified
Raw
History Blame Contribute Delete
4.38 kB
Invalid JSON:Unexpected token 'N', ..."ad_norm": NaN, "... is not valid JSON
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.04,
"eval_steps": 1000,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002,
"grad_norm": 4.326515197753906,
"learning_rate": 7.92e-06,
"loss": 10.223335571289063,
"step": 100
},
{
"epoch": 0.004,
"grad_norm": 4.537860870361328,
"learning_rate": 1.592e-05,
"loss": 8.924765625,
"step": 200
},
{
"epoch": 0.006,
"grad_norm": 3.0256755352020264,
"learning_rate": 2.392e-05,
"loss": 8.119463500976563,
"step": 300
},
{
"epoch": 0.008,
"grad_norm": 2.5825231075286865,
"learning_rate": 3.192e-05,
"loss": 7.47499755859375,
"step": 400
},
{
"epoch": 0.01,
"grad_norm": 3.1428987979888916,
"learning_rate": 3.9920000000000004e-05,
"loss": 7.310105590820313,
"step": 500
},
{
"epoch": 0.012,
"grad_norm": 4.996999740600586,
"learning_rate": 4.792e-05,
"loss": 7.11893798828125,
"step": 600
},
{
"epoch": 0.014,
"grad_norm": 3.3079946041107178,
"learning_rate": 5.592000000000001e-05,
"loss": 7.0108880615234375,
"step": 700
},
{
"epoch": 0.016,
"grad_norm": 4.659358024597168,
"learning_rate": 6.392e-05,
"loss": 6.869476318359375,
"step": 800
},
{
"epoch": 0.018,
"grad_norm": 7.537159442901611,
"learning_rate": 7.192e-05,
"loss": 6.7979345703125,
"step": 900
},
{
"epoch": 0.02,
"grad_norm": 3.9471282958984375,
"learning_rate": 7.992000000000001e-05,
"loss": 6.715423583984375,
"step": 1000
},
{
"epoch": 0.02,
"eval_accuracy": 0.13923287671232876,
"eval_loss": 6.70299768447876,
"eval_runtime": 9.4613,
"eval_samples_per_second": 105.694,
"eval_steps_per_second": 13.212,
"step": 1000
},
{
"epoch": 0.022,
"grad_norm": 32.88319396972656,
"learning_rate": 8.792e-05,
"loss": 6.7681121826171875,
"step": 1100
},
{
"epoch": 0.024,
"grad_norm": 1666.3564453125,
"learning_rate": 9.592e-05,
"loss": 6.879424438476563,
"step": 1200
},
{
"epoch": 0.026,
"grad_norm": 532019.8125,
"learning_rate": 0.00010392,
"loss": 9.755108642578126,
"step": 1300
},
{
"epoch": 0.028,
"grad_norm": 7875070.5,
"learning_rate": 0.00011192,
"loss": 10.504903564453125,
"step": 1400
},
{
"epoch": 0.03,
"grad_norm": 101449456.0,
"learning_rate": 0.00011992,
"loss": 10.605618896484375,
"step": 1500
},
{
"epoch": 0.032,
"grad_norm": 1575154432.0,
"learning_rate": 0.00012792,
"loss": 10.660673828125,
"step": 1600
},
{
"epoch": 0.034,
"grad_norm": 3583042816.0,
"learning_rate": 0.00013592,
"loss": 10.6936279296875,
"step": 1700
},
{
"epoch": 0.036,
"grad_norm": 5040027136.0,
"learning_rate": 0.00014392000000000002,
"loss": 10.703485107421875,
"step": 1800
},
{
"epoch": 0.038,
"grad_norm": NaN,
"learning_rate": 0.00015192000000000002,
"loss": NaN,
"step": 1900
},
{
"epoch": 0.04,
"grad_norm": NaN,
"learning_rate": 0.00015992,
"loss": NaN,
"step": 2000
},
{
"epoch": 0.04,
"eval_accuracy": 0.0,
"eval_loss": NaN,
"eval_runtime": 9.3223,
"eval_samples_per_second": 107.269,
"eval_steps_per_second": 13.409,
"step": 2000
}
],
"logging_steps": 100,
"max_steps": 50000,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 2000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}