longformer-sep_tok / checkpoint-243 /trainer_state.json
Theoreticallyhugo's picture
Training in progress, epoch 3, checkpoint
b20459e verified
raw
history blame
4.4 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": 0.5724454649827784,
"precision": 0.6002889477486154,
"recall": 0.5470704410796576,
"support": 4557.0
},
"eval_MajorClaim": {
"f1-score": 0.7860447185813415,
"precision": 0.698526892771497,
"recall": 0.8986337593653592,
"support": 2269.0
},
"eval_O": {
"f1-score": 0.9987820830889982,
"precision": 0.9975671292124707,
"recall": 1.0,
"support": 11071.0
},
"eval_Premise": {
"f1-score": 0.8965445389824622,
"precision": 0.9051258677512096,
"recall": 0.8881243979633962,
"support": 14534.0
},
"eval_accuracy": 0.8791279948197712,
"eval_loss": 0.3157936632633209,
"eval_macro avg": {
"f1-score": 0.8134542014088951,
"precision": 0.8003772093709481,
"recall": 0.8334571496021033,
"support": 32431.0
},
"eval_runtime": 4.8184,
"eval_samples_per_second": 16.603,
"eval_steps_per_second": 2.075,
"eval_weighted avg": {
"f1-score": 0.8781740995293698,
"precision": 0.8793943851252293,
"recall": 0.8791279948197712,
"support": 32431.0
},
"step": 81
},
{
"epoch": 2.0,
"eval_Claim": {
"f1-score": 0.6090644692195831,
"precision": 0.680108254397835,
"recall": 0.5514592933947773,
"support": 4557.0
},
"eval_MajorClaim": {
"f1-score": 0.8585858585858586,
"precision": 0.8960229995208433,
"recall": 0.8241516086381666,
"support": 2269.0
},
"eval_O": {
"f1-score": 0.999458141425088,
"precision": 0.9992776523702032,
"recall": 0.9996386956914461,
"support": 11071.0
},
"eval_Premise": {
"f1-score": 0.9105885478942475,
"precision": 0.8801849235905997,
"recall": 0.9431677445988716,
"support": 14534.0
},
"eval_accuracy": 0.8990780426135487,
"eval_loss": 0.24451124668121338,
"eval_macro avg": {
"f1-score": 0.8444242542811943,
"precision": 0.8638984574698704,
"recall": 0.8296043355808155,
"support": 32431.0
},
"eval_runtime": 4.8529,
"eval_samples_per_second": 16.485,
"eval_steps_per_second": 2.061,
"eval_weighted avg": {
"f1-score": 0.8949194640367888,
"precision": 0.8938342965082798,
"recall": 0.8990780426135487,
"support": 32431.0
},
"step": 162
},
{
"epoch": 3.0,
"eval_Claim": {
"f1-score": 0.6542320859402667,
"precision": 0.7079713847726111,
"recall": 0.60807548825982,
"support": 4557.0
},
"eval_MajorClaim": {
"f1-score": 0.8915187376725839,
"precision": 0.8866608544027899,
"recall": 0.8964301454385192,
"support": 2269.0
},
"eval_O": {
"f1-score": 0.9995936611133684,
"precision": 0.9992778479870013,
"recall": 0.9999096739228616,
"support": 11071.0
},
"eval_Premise": {
"f1-score": 0.9157990498332153,
"precision": 0.8973258501155497,
"recall": 0.935048850970139,
"support": 14534.0
},
"eval_accuracy": 0.9085442940396534,
"eval_loss": 0.22665414214134216,
"eval_macro avg": {
"f1-score": 0.8652858836398586,
"precision": 0.872808984319488,
"recall": 0.8598660396478349,
"support": 32431.0
},
"eval_runtime": 4.8494,
"eval_samples_per_second": 16.497,
"eval_steps_per_second": 2.062,
"eval_weighted avg": {
"f1-score": 0.9059516032151627,
"precision": 0.9047762338408377,
"recall": 0.9085442940396534,
"support": 32431.0
},
"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
}