longformer-simple / checkpoint-405 /trainer_state.json
Theoreticallyhugo's picture
Training in progress, epoch 5, checkpoint
1a2674a verified
raw
history blame
7.04 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 405,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_Claim": {
"f1-score": 0.44734338904742493,
"precision": 0.5477537437603993,
"recall": 0.3780431786862655,
"support": 4354.0
},
"eval_MajorClaim": {
"f1-score": 0.6504965622612681,
"precision": 0.5898856944925528,
"recall": 0.7249893571732652,
"support": 2349.0
},
"eval_O": {
"f1-score": 0.8859784283513097,
"precision": 0.8689081979599547,
"recall": 0.9037328094302554,
"support": 10180.0
},
"eval_Premise": {
"f1-score": 0.8720120805863504,
"precision": 0.859258183929738,
"recall": 0.8851502916105877,
"support": 13374.0
},
"eval_accuracy": 0.8059953068711373,
"eval_loss": 0.47828415036201477,
"eval_macro avg": {
"f1-score": 0.7139576150615883,
"precision": 0.7164514550356611,
"recall": 0.7229789092250934,
"support": 30257.0
},
"eval_runtime": 4.8422,
"eval_samples_per_second": 16.728,
"eval_steps_per_second": 2.272,
"eval_weighted avg": {
"f1-score": 0.7984036588902531,
"precision": 0.7967665566250599,
"recall": 0.8059953068711373,
"support": 30257.0
},
"step": 81
},
{
"epoch": 2.0,
"eval_Claim": {
"f1-score": 0.5787561000934482,
"precision": 0.5281409891984082,
"recall": 0.6401010564997703,
"support": 4354.0
},
"eval_MajorClaim": {
"f1-score": 0.7702650787552824,
"precision": 0.7017850892544627,
"recall": 0.8535547041294168,
"support": 2349.0
},
"eval_O": {
"f1-score": 0.9095337508698677,
"precision": 0.9206077681626081,
"recall": 0.8987229862475442,
"support": 10180.0
},
"eval_Premise": {
"f1-score": 0.8736648538675224,
"precision": 0.9162905211325401,
"recall": 0.8348287722446538,
"support": 13374.0
},
"eval_accuracy": 0.8297584030141786,
"eval_loss": 0.4241589605808258,
"eval_macro avg": {
"f1-score": 0.7830549458965301,
"precision": 0.7667060919370048,
"recall": 0.8068018797803463,
"support": 30257.0
},
"eval_runtime": 4.8636,
"eval_samples_per_second": 16.654,
"eval_steps_per_second": 2.262,
"eval_weighted avg": {
"f1-score": 0.8352680063880269,
"precision": 0.8452350051608073,
"recall": 0.8297584030141786,
"support": 30257.0
},
"step": 162
},
{
"epoch": 3.0,
"eval_Claim": {
"f1-score": 0.5728465083303793,
"precision": 0.5899245558530056,
"recall": 0.5567294441892513,
"support": 4354.0
},
"eval_MajorClaim": {
"f1-score": 0.7862876979822088,
"precision": 0.8017699115044248,
"recall": 0.7713920817369093,
"support": 2349.0
},
"eval_O": {
"f1-score": 0.914532821534425,
"precision": 0.9048168445341794,
"recall": 0.9244597249508841,
"support": 10180.0
},
"eval_Premise": {
"f1-score": 0.8880533114924986,
"precision": 0.8843330614665975,
"recall": 0.8918049947659639,
"support": 13374.0
},
"eval_accuracy": 0.8452258981392735,
"eval_loss": 0.41067537665367126,
"eval_macro avg": {
"f1-score": 0.7904300848348779,
"precision": 0.7952110933395518,
"recall": 0.7860965614107521,
"support": 30257.0
},
"eval_runtime": 4.8684,
"eval_samples_per_second": 16.638,
"eval_steps_per_second": 2.259,
"eval_weighted avg": {
"f1-score": 0.8437033615676307,
"precision": 0.8424495118392472,
"recall": 0.8452258981392735,
"support": 30257.0
},
"step": 243
},
{
"epoch": 4.0,
"eval_Claim": {
"f1-score": 0.5865384615384616,
"precision": 0.5714596949891068,
"recall": 0.6024345429490124,
"support": 4354.0
},
"eval_MajorClaim": {
"f1-score": 0.7783630470016208,
"precision": 0.7425589485890993,
"recall": 0.8177948063005535,
"support": 2349.0
},
"eval_O": {
"f1-score": 0.9108591535529275,
"precision": 0.9063411787589963,
"recall": 0.9154223968565816,
"support": 10180.0
},
"eval_Premise": {
"f1-score": 0.8868256151612411,
"precision": 0.9067823097358962,
"recall": 0.8677284282937042,
"support": 13374.0
},
"eval_accuracy": 0.8417225765938461,
"eval_loss": 0.4545813202857971,
"eval_macro avg": {
"f1-score": 0.7906465693135627,
"precision": 0.7817855330182747,
"recall": 0.8008450435999629,
"support": 30257.0
},
"eval_runtime": 4.9112,
"eval_samples_per_second": 16.493,
"eval_steps_per_second": 2.24,
"eval_weighted avg": {
"f1-score": 0.8432797441676475,
"precision": 0.8456313015960876,
"recall": 0.8417225765938461,
"support": 30257.0
},
"step": 324
},
{
"epoch": 5.0,
"eval_Claim": {
"f1-score": 0.597399608790703,
"precision": 0.5985704403965875,
"recall": 0.5962333486449242,
"support": 4354.0
},
"eval_MajorClaim": {
"f1-score": 0.7933532168726033,
"precision": 0.7940298507462686,
"recall": 0.7926777352064709,
"support": 2349.0
},
"eval_O": {
"f1-score": 0.9101112629318758,
"precision": 0.9042862684251358,
"recall": 0.9160117878192534,
"support": 10180.0
},
"eval_Premise": {
"f1-score": 0.8923677591320345,
"precision": 0.8961019377214808,
"recall": 0.8886645730521908,
"support": 13374.0
},
"eval_accuracy": 0.848332617245596,
"eval_loss": 0.48704993724823,
"eval_macro avg": {
"f1-score": 0.7983079619318041,
"precision": 0.7982471243223681,
"recall": 0.7983968611807098,
"support": 30257.0
},
"eval_runtime": 4.8769,
"eval_samples_per_second": 16.609,
"eval_steps_per_second": 2.256,
"eval_weighted avg": {
"f1-score": 0.8482045037639816,
"precision": 0.8481162489521332,
"recall": 0.848332617245596,
"support": 30257.0
},
"step": 405
}
],
"logging_steps": 500,
"max_steps": 4050,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 716710919337000.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}