gal_ensp_mBERT / trainer_state.json
mbruton's picture
Upload 11 files
58af68d
raw
history blame
2.1 kB
{
"best_metric": 0.31418120861053467,
"best_model_checkpoint": "gal_ensp_mBERT/checkpoint-750",
"epoch": 4.0,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.8990431795878312,
"eval_f1": 0.6289113806690875,
"eval_loss": 0.3602694869041443,
"eval_precision": 0.676416819012797,
"eval_recall": 0.5876407738954663,
"eval_runtime": 5.3964,
"eval_samples_per_second": 184.751,
"eval_steps_per_second": 11.674,
"step": 250
},
{
"epoch": 2.0,
"learning_rate": 1.9600000000000002e-05,
"loss": 0.4515,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.9109421000981355,
"eval_f1": 0.6887108521485796,
"eval_loss": 0.3213185966014862,
"eval_precision": 0.6948853615520282,
"eval_recall": 0.6826451053999423,
"eval_runtime": 5.4855,
"eval_samples_per_second": 181.753,
"eval_steps_per_second": 11.485,
"step": 500
},
{
"epoch": 3.0,
"eval_accuracy": 0.9141928361138371,
"eval_f1": 0.6999709976798144,
"eval_loss": 0.31418120861053467,
"eval_precision": 0.703029420332071,
"eval_recall": 0.6969390701703725,
"eval_runtime": 5.502,
"eval_samples_per_second": 181.208,
"eval_steps_per_second": 11.45,
"step": 750
},
{
"epoch": 4.0,
"learning_rate": 1.9200000000000003e-05,
"loss": 0.2256,
"step": 1000
},
{
"epoch": 4.0,
"eval_accuracy": 0.9180569185475956,
"eval_f1": 0.7156714809226128,
"eval_loss": 0.3158390522003174,
"eval_precision": 0.7123444428550995,
"eval_recall": 0.7190297429974011,
"eval_runtime": 5.4912,
"eval_samples_per_second": 181.562,
"eval_steps_per_second": 11.473,
"step": 1000
}
],
"max_steps": 25000,
"num_train_epochs": 100,
"total_flos": 623488737039000.0,
"trial_name": null,
"trial_params": null
}