longformer-spans / checkpoint-324 /trainer_state.json
Theoreticallyhugo's picture
Training in progress, epoch 4, checkpoint
9936242 verified
raw
history blame
4.95 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"eval_steps": 500,
"global_step": 324,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_B": {
"f1-score": 0.8266764382557715,
"precision": 0.7866108786610879,
"recall": 0.871042471042471,
"support": 1295.0
},
"eval_I": {
"f1-score": 0.9410658617447671,
"precision": 0.9344077040239768,
"recall": 0.9478195863443808,
"support": 20065.0
},
"eval_O": {
"f1-score": 0.8562443302086484,
"precision": 0.8789421405512788,
"recall": 0.8346893055064262,
"support": 8481.0
},
"eval_accuracy": 0.912335377500754,
"eval_loss": 0.2450982630252838,
"eval_macro avg": {
"f1-score": 0.8746622100697291,
"precision": 0.8666535744121145,
"recall": 0.8845171209644261,
"support": 29841.0
},
"eval_runtime": 4.6269,
"eval_samples_per_second": 17.29,
"eval_steps_per_second": 2.161,
"eval_weighted avg": {
"f1-score": 0.9119949287205363,
"precision": 0.9122301519092053,
"recall": 0.912335377500754,
"support": 29841.0
},
"step": 81
},
{
"epoch": 2.0,
"eval_B": {
"f1-score": 0.8833395452851286,
"precision": 0.8537463976945245,
"recall": 0.915057915057915,
"support": 1295.0
},
"eval_I": {
"f1-score": 0.9549518227873249,
"precision": 0.9516903430183636,
"recall": 0.958235733864939,
"support": 20065.0
},
"eval_O": {
"f1-score": 0.88924750463212,
"precision": 0.9016969696969697,
"recall": 0.877137130055418,
"support": 8481.0
},
"eval_accuracy": 0.9333132267685399,
"eval_loss": 0.20076116919517517,
"eval_macro avg": {
"f1-score": 0.9091796242348579,
"precision": 0.9023779034699526,
"recall": 0.916810259659424,
"support": 29841.0
},
"eval_runtime": 4.6524,
"eval_samples_per_second": 17.195,
"eval_steps_per_second": 2.149,
"eval_weighted avg": {
"f1-score": 0.9331705077630417,
"precision": 0.9332314707173981,
"recall": 0.9333132267685399,
"support": 29841.0
},
"step": 162
},
{
"epoch": 3.0,
"eval_B": {
"f1-score": 0.8927335640138409,
"precision": 0.8889739663093414,
"recall": 0.8965250965250965,
"support": 1295.0
},
"eval_I": {
"f1-score": 0.9590235396687009,
"precision": 0.9586653386454184,
"recall": 0.9593820084724645,
"support": 20065.0
},
"eval_O": {
"f1-score": 0.9006849315068494,
"precision": 0.9020697811945594,
"recall": 0.8993043273198915,
"support": 8481.0
},
"eval_accuracy": 0.9395797727958178,
"eval_loss": 0.19863653182983398,
"eval_macro avg": {
"f1-score": 0.9174806783964637,
"precision": 0.9165696953831063,
"recall": 0.9184038107724842,
"support": 29841.0
},
"eval_runtime": 4.655,
"eval_samples_per_second": 17.186,
"eval_steps_per_second": 2.148,
"eval_weighted avg": {
"f1-score": 0.9395665759512081,
"precision": 0.9395561516236713,
"recall": 0.9395797727958178,
"support": 29841.0
},
"step": 243
},
{
"epoch": 4.0,
"eval_B": {
"f1-score": 0.8999616711383672,
"precision": 0.893455098934551,
"recall": 0.9065637065637066,
"support": 1295.0
},
"eval_I": {
"f1-score": 0.9612657113512985,
"precision": 0.9436362763454799,
"recall": 0.9795664091701969,
"support": 20065.0
},
"eval_O": {
"f1-score": 0.8996847765622102,
"precision": 0.9454403741231489,
"recall": 0.8581535196321188,
"support": 8481.0
},
"eval_accuracy": 0.9418920277470594,
"eval_loss": 0.19743724167346954,
"eval_macro avg": {
"f1-score": 0.920304053017292,
"precision": 0.9275105831343932,
"recall": 0.9147612117886741,
"support": 29841.0
},
"eval_runtime": 4.6615,
"eval_samples_per_second": 17.162,
"eval_steps_per_second": 2.145,
"eval_weighted avg": {
"f1-score": 0.9411036309913238,
"precision": 0.9419713163409645,
"recall": 0.9418920277470594,
"support": 29841.0
},
"step": 324
}
],
"logging_steps": 500,
"max_steps": 4050,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 575146610942400.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}