Theoreticallyhugo's picture
Training in progress, epoch 2, checkpoint
fb3447d verified
raw
history blame
4.15 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 162,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_B-Claim": {
"f1-score": 0.17153996101364524,
"precision": 0.25287356321839083,
"recall": 0.12979351032448377,
"support": 339.0
},
"eval_B-MajorClaim": {
"f1-score": 0.08383233532934131,
"precision": 1.0,
"recall": 0.04375,
"support": 160.0
},
"eval_B-Premise": {
"f1-score": 0.8469620831429876,
"precision": 0.7427884615384616,
"recall": 0.9851222104144527,
"support": 941.0
},
"eval_I-Claim": {
"f1-score": 0.5420081967213116,
"precision": 0.6803858520900321,
"recall": 0.4504044274159217,
"support": 4698.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8343351767251743,
"precision": 0.8141717503519474,
"recall": 0.8555226824457594,
"support": 2028.0
},
"eval_I-Premise": {
"f1-score": 0.9004323458767015,
"precision": 0.8590809093131264,
"recall": 0.9459659511472983,
"support": 14861.0
},
"eval_O": {
"f1-score": 0.9988389078242631,
"precision": 0.9991008541885209,
"recall": 0.9985770987793006,
"support": 13353.0
},
"eval_accuracy": 0.8856789444749863,
"eval_loss": 0.28347474336624146,
"eval_macro avg": {
"f1-score": 0.6254212866619178,
"precision": 0.76405734152864,
"recall": 0.629876554361031,
"support": 36380.0
},
"eval_runtime": 5.0448,
"eval_samples_per_second": 16.056,
"eval_steps_per_second": 2.18,
"eval_weighted avg": {
"f1-score": 0.8748148382495958,
"precision": 0.8768575102351055,
"recall": 0.8856789444749863,
"support": 36380.0
},
"step": 81
},
{
"epoch": 2.0,
"eval_B-Claim": {
"f1-score": 0.5137931034482759,
"precision": 0.6182572614107884,
"recall": 0.43952802359882004,
"support": 339.0
},
"eval_B-MajorClaim": {
"f1-score": 0.7622641509433963,
"precision": 0.9619047619047619,
"recall": 0.63125,
"support": 160.0
},
"eval_B-Premise": {
"f1-score": 0.8853910477127397,
"precision": 0.8241758241758241,
"recall": 0.9564293304994687,
"support": 941.0
},
"eval_I-Claim": {
"f1-score": 0.5413588470388762,
"precision": 0.6279853891542568,
"recall": 0.47573435504469985,
"support": 4698.0
},
"eval_I-MajorClaim": {
"f1-score": 0.7949260042283298,
"precision": 0.856492027334852,
"recall": 0.7416173570019724,
"support": 2028.0
},
"eval_I-Premise": {
"f1-score": 0.9007064868336545,
"precision": 0.8614779777627618,
"recall": 0.9436780835744566,
"support": 14861.0
},
"eval_O": {
"f1-score": 0.9988389947942025,
"precision": 0.9990260713215463,
"recall": 0.9986519883172321,
"support": 13353.0
},
"eval_accuracy": 0.8864211105002748,
"eval_loss": 0.2809496521949768,
"eval_macro avg": {
"f1-score": 0.7710398049999251,
"precision": 0.8213313304378275,
"recall": 0.7409841625766643,
"support": 36380.0
},
"eval_runtime": 5.0579,
"eval_samples_per_second": 16.014,
"eval_steps_per_second": 2.175,
"eval_weighted avg": {
"f1-score": 0.8798131143596267,
"precision": 0.8787439244541853,
"recall": 0.8864211105002748,
"support": 36380.0
},
"step": 162
}
],
"logging_steps": 500,
"max_steps": 4050,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 286688514798000.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}