emoberta-large / trainer_state.json
tae898's picture
Upload trainer_state.json
78cd140
raw
history blame
3.25 kB
{
"best_metric": 0.6281057228463983,
"best_model_checkpoint": "results/MELD_IEMOCAP/roberta-large/SEEDS/2022-03-14-19-06-40-speaker_mode-None-num_past_utterances-0-num_future_utterances-0-batch_size-16-seed-42/checkpoint-7086",
"epoch": 6.0,
"global_step": 7086,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 1.1135900346584852e-06,
"loss": 1.6941,
"step": 1181
},
{
"epoch": 1.0,
"eval_f1_macro": 0.07791319292694036,
"eval_f1_micro": 0.35635123614663256,
"eval_f1_weighted": 0.19072939518738496,
"eval_loss": 1.5153617858886719,
"eval_runtime": 3.1794,
"eval_samples_per_second": 737.872,
"eval_steps_per_second": 23.275,
"step": 1181
},
{
"epoch": 2.0,
"learning_rate": 2.2338198736122084e-06,
"loss": 1.298,
"step": 2362
},
{
"epoch": 2.0,
"eval_f1_macro": 0.39258179738738447,
"eval_f1_micro": 0.5882352941176471,
"eval_f1_weighted": 0.570696903628535,
"eval_loss": 1.1774364709854126,
"eval_runtime": 3.1793,
"eval_samples_per_second": 737.903,
"eval_steps_per_second": 23.276,
"step": 2362
},
{
"epoch": 3.0,
"learning_rate": 3.3540497125659314e-06,
"loss": 1.0976,
"step": 3543
},
{
"epoch": 3.0,
"eval_f1_macro": 0.4195774350293237,
"eval_f1_micro": 0.6052855924978687,
"eval_f1_weighted": 0.5932857871930991,
"eval_loss": 1.0991432666778564,
"eval_runtime": 3.1785,
"eval_samples_per_second": 738.086,
"eval_steps_per_second": 23.281,
"step": 3543
},
{
"epoch": 4.0,
"learning_rate": 3.0822920081965484e-06,
"loss": 0.9869,
"step": 4724
},
{
"epoch": 4.0,
"eval_f1_macro": 0.4634417760566037,
"eval_f1_micro": 0.6287297527706734,
"eval_f1_weighted": 0.6211850773676282,
"eval_loss": 1.0642313957214355,
"eval_runtime": 3.1809,
"eval_samples_per_second": 737.537,
"eval_steps_per_second": 23.264,
"step": 4724
},
{
"epoch": 5.0,
"learning_rate": 2.8022345484581173e-06,
"loss": 0.8638,
"step": 5905
},
{
"epoch": 5.0,
"eval_f1_macro": 0.4789393979707725,
"eval_f1_micro": 0.6172208013640239,
"eval_f1_weighted": 0.6157912564989868,
"eval_loss": 1.0899823904037476,
"eval_runtime": 3.182,
"eval_samples_per_second": 737.269,
"eval_steps_per_second": 23.256,
"step": 5905
},
{
"epoch": 6.0,
"learning_rate": 2.522414224587374e-06,
"loss": 0.772,
"step": 7086
},
{
"epoch": 6.0,
"eval_f1_macro": 0.4957254043928597,
"eval_f1_micro": 0.6295822676896846,
"eval_f1_weighted": 0.6281057228463983,
"eval_loss": 1.120431661605835,
"eval_runtime": 3.1786,
"eval_samples_per_second": 738.072,
"eval_steps_per_second": 23.281,
"step": 7086
}
],
"max_steps": 17715,
"num_train_epochs": 15,
"total_flos": 8224038236774502.0,
"trial_name": null,
"trial_params": null
}