longformer-simple / checkpoint-243 /trainer_state.json
Theoreticallyhugo's picture
Training in progress, epoch 3, checkpoint
6cd3ebd verified
raw
history blame
4.41 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 243,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_Claim": {
"f1-score": 0.38183790485045715,
"precision": 0.6497890295358649,
"recall": 0.27035330261136714,
"support": 4557.0
},
"eval_MajorClaim": {
"f1-score": 0.6266258607498087,
"precision": 0.5535653937140926,
"recall": 0.7219039224327898,
"support": 2269.0
},
"eval_O": {
"f1-score": 0.8545803971812939,
"precision": 0.8443037974683544,
"recall": 0.8651102464332037,
"support": 8481.0
},
"eval_Premise": {
"f1-score": 0.878949075575738,
"precision": 0.8314310260186549,
"recall": 0.9322278794550709,
"support": 14534.0
},
"eval_accuracy": 0.7960859220535504,
"eval_loss": 0.5359914898872375,
"eval_macro avg": {
"f1-score": 0.6854983095893245,
"precision": 0.7197723116842417,
"recall": 0.697398837733108,
"support": 29841.0
},
"eval_runtime": 4.8191,
"eval_samples_per_second": 16.601,
"eval_steps_per_second": 2.075,
"eval_weighted avg": {
"f1-score": 0.7769240850962494,
"precision": 0.7862232339538372,
"recall": 0.7960859220535504,
"support": 29841.0
},
"step": 81
},
{
"epoch": 2.0,
"eval_Claim": {
"f1-score": 0.6161300742974051,
"precision": 0.6048625792811839,
"recall": 0.6278253236778583,
"support": 4557.0
},
"eval_MajorClaim": {
"f1-score": 0.7920215150156881,
"precision": 0.8057455540355677,
"recall": 0.7787571617452622,
"support": 2269.0
},
"eval_O": {
"f1-score": 0.8922796352583586,
"precision": 0.9209436566695947,
"recall": 0.865346067680698,
"support": 8481.0
},
"eval_Premise": {
"f1-score": 0.8914289590611538,
"precision": 0.8790554552143957,
"recall": 0.9041557726709784,
"support": 14534.0
},
"eval_accuracy": 0.8413927147213566,
"eval_loss": 0.443877637386322,
"eval_macro avg": {
"f1-score": 0.7979650459081514,
"precision": 0.8026518113001855,
"recall": 0.7940210814436992,
"support": 29841.0
},
"eval_runtime": 4.8087,
"eval_samples_per_second": 16.637,
"eval_steps_per_second": 2.08,
"eval_weighted avg": {
"f1-score": 0.842071433389123,
"precision": 0.8435143116581857,
"recall": 0.8413927147213566,
"support": 29841.0
},
"step": 162
},
{
"epoch": 3.0,
"eval_Claim": {
"f1-score": 0.6042799305957202,
"precision": 0.6389432485322897,
"recall": 0.5731841123546193,
"support": 4557.0
},
"eval_MajorClaim": {
"f1-score": 0.8349557522123894,
"precision": 0.8382940915148823,
"recall": 0.8316438959894227,
"support": 2269.0
},
"eval_O": {
"f1-score": 0.8941106484235574,
"precision": 0.9022691799735862,
"recall": 0.8860983374602052,
"support": 8481.0
},
"eval_Premise": {
"f1-score": 0.8917763490086511,
"precision": 0.8729980887102089,
"recall": 0.9113802119168846,
"support": 14534.0
},
"eval_accuracy": 0.8464863778023525,
"eval_loss": 0.4555923044681549,
"eval_macro avg": {
"f1-score": 0.8062806700600795,
"precision": 0.8131261521827418,
"recall": 0.8005766394302829,
"support": 29841.0
},
"eval_runtime": 4.7811,
"eval_samples_per_second": 16.733,
"eval_steps_per_second": 2.092,
"eval_weighted avg": {
"f1-score": 0.8442159482345275,
"precision": 0.8429359878649869,
"recall": 0.8464863778023525,
"support": 29841.0
},
"step": 243
}
],
"logging_steps": 500,
"max_steps": 4050,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 431366198180400.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}