longformer-sep_tok / checkpoint-243 /trainer_state.json
Theoreticallyhugo's picture
Training in progress, epoch 3, checkpoint
8583bcf verified
raw
history blame
4.38 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": 0.5254768748366867,
"precision": 0.5768789443488239,
"recall": 0.4824856046065259,
"support": 4168.0
},
"eval_MajorClaim": {
"f1-score": 0.7984361424847959,
"precision": 0.7495921696574225,
"recall": 0.854089219330855,
"support": 2152.0
},
"eval_O": {
"f1-score": 0.9990277532260916,
"precision": 0.9988511841640155,
"recall": 0.9992043847241867,
"support": 11312.0
},
"eval_Premise": {
"f1-score": 0.8854183656825966,
"precision": 0.8719781543651113,
"recall": 0.8992793837488611,
"support": 12073.0
},
"eval_accuracy": 0.8755765022723447,
"eval_loss": 0.28303390741348267,
"eval_macro avg": {
"f1-score": 0.8020897840575427,
"precision": 0.7993251131338432,
"recall": 0.8087646481026072,
"support": 29705.0
},
"eval_runtime": 4.8106,
"eval_samples_per_second": 16.63,
"eval_steps_per_second": 2.079,
"eval_weighted avg": {
"f1-score": 0.8718761173649596,
"precision": 0.8700202202343714,
"recall": 0.8755765022723447,
"support": 29705.0
},
"step": 81
},
{
"epoch": 2.0,
"eval_Claim": {
"f1-score": 0.5578782336033447,
"precision": 0.6124497991967871,
"recall": 0.5122360844529751,
"support": 4168.0
},
"eval_MajorClaim": {
"f1-score": 0.784421283598464,
"precision": 0.9571619812583668,
"recall": 0.6644981412639405,
"support": 2152.0
},
"eval_O": {
"f1-score": 0.9998674150351351,
"precision": 0.9997348652231551,
"recall": 1.0,
"support": 11312.0
},
"eval_Premise": {
"f1-score": 0.8977749872463995,
"precision": 0.8530201342281879,
"recall": 0.9474861260664292,
"support": 12073.0
},
"eval_accuracy": 0.8859114627167144,
"eval_loss": 0.27363118529319763,
"eval_macro avg": {
"f1-score": 0.8099854798708358,
"precision": 0.8555916949766242,
"recall": 0.7810550879458362,
"support": 29705.0
},
"eval_runtime": 4.7727,
"eval_samples_per_second": 16.762,
"eval_steps_per_second": 2.095,
"eval_weighted avg": {
"f1-score": 0.8807489883812781,
"precision": 0.8826802296805741,
"recall": 0.8859114627167144,
"support": 29705.0
},
"step": 162
},
{
"epoch": 3.0,
"eval_Claim": {
"f1-score": 0.64760736196319,
"precision": 0.6627322953289804,
"recall": 0.6331573896353166,
"support": 4168.0
},
"eval_MajorClaim": {
"f1-score": 0.9016018306636155,
"precision": 0.8881875563570785,
"recall": 0.9154275092936803,
"support": 2152.0
},
"eval_O": {
"f1-score": 0.9996904982977407,
"precision": 1.0,
"recall": 0.9993811881188119,
"support": 11312.0
},
"eval_Premise": {
"f1-score": 0.8982820417748115,
"precision": 0.8936065573770492,
"recall": 0.9030067091857865,
"support": 12073.0
},
"eval_accuracy": 0.9027436458508669,
"eval_loss": 0.22585685551166534,
"eval_macro avg": {
"f1-score": 0.8617954331748394,
"precision": 0.861131602265777,
"recall": 0.8627431990583988,
"support": 29705.0
},
"eval_runtime": 4.8003,
"eval_samples_per_second": 16.666,
"eval_steps_per_second": 2.083,
"eval_weighted avg": {
"f1-score": 0.9019670975035187,
"precision": 0.9013351218793044,
"recall": 0.9027436458508669,
"support": 29705.0
},
"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
}