diagonalge's picture
Training in progress, step 10, checkpoint
9fe196e verified
raw
history blame
3.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0016300582745833164,
"eval_steps": 3,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00016300582745833165,
"grad_norm": 1.5260664224624634,
"learning_rate": 2e-05,
"loss": 1.4625,
"step": 1
},
{
"epoch": 0.00016300582745833165,
"eval_loss": 1.558783769607544,
"eval_runtime": 373.2766,
"eval_samples_per_second": 6.92,
"eval_steps_per_second": 3.461,
"step": 1
},
{
"epoch": 0.0003260116549166633,
"grad_norm": 1.213285207748413,
"learning_rate": 4e-05,
"loss": 1.8338,
"step": 2
},
{
"epoch": 0.0004890174823749949,
"grad_norm": 1.7155927419662476,
"learning_rate": 6e-05,
"loss": 1.4972,
"step": 3
},
{
"epoch": 0.0004890174823749949,
"eval_loss": 1.555458664894104,
"eval_runtime": 373.4863,
"eval_samples_per_second": 6.916,
"eval_steps_per_second": 3.459,
"step": 3
},
{
"epoch": 0.0006520233098333266,
"grad_norm": 2.710537910461426,
"learning_rate": 8e-05,
"loss": 1.8002,
"step": 4
},
{
"epoch": 0.0008150291372916582,
"grad_norm": 1.4228698015213013,
"learning_rate": 0.0001,
"loss": 1.256,
"step": 5
},
{
"epoch": 0.0009780349647499898,
"grad_norm": 1.1818934679031372,
"learning_rate": 0.00012,
"loss": 1.7772,
"step": 6
},
{
"epoch": 0.0009780349647499898,
"eval_loss": 1.5226942300796509,
"eval_runtime": 374.5727,
"eval_samples_per_second": 6.896,
"eval_steps_per_second": 3.449,
"step": 6
},
{
"epoch": 0.0011410407922083214,
"grad_norm": 1.2571606636047363,
"learning_rate": 0.00014,
"loss": 1.5778,
"step": 7
},
{
"epoch": 0.0013040466196666532,
"grad_norm": 3.4298977851867676,
"learning_rate": 0.00016,
"loss": 2.0878,
"step": 8
},
{
"epoch": 0.0014670524471249848,
"grad_norm": 0.920394241809845,
"learning_rate": 0.00018,
"loss": 1.583,
"step": 9
},
{
"epoch": 0.0014670524471249848,
"eval_loss": 1.4455409049987793,
"eval_runtime": 373.3626,
"eval_samples_per_second": 6.918,
"eval_steps_per_second": 3.46,
"step": 9
},
{
"epoch": 0.0016300582745833164,
"grad_norm": 0.9525576233863831,
"learning_rate": 0.0002,
"loss": 1.2694,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1935445139128320.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}