longformer-spans / checkpoint-324 /trainer_state.json
Theoreticallyhugo's picture
Training in progress, epoch 4, checkpoint
a10a45f verified
raw
history blame
4.96 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": 0.8087666523420713,
"precision": 0.8189730200174065,
"recall": 0.7988115449915111,
"support": 1178.0
},
"eval_I": {
"f1-score": 0.9374597034171502,
"precision": 0.9521418826739427,
"recall": 0.9232234509762421,
"support": 18899.0
},
"eval_O": {
"f1-score": 0.8881362400419788,
"precision": 0.863303347862376,
"recall": 0.9144400785854617,
"support": 10180.0
},
"eval_accuracy": 0.9154245298608586,
"eval_loss": 0.2228638380765915,
"eval_macro avg": {
"f1-score": 0.8781208652670669,
"precision": 0.8781394168512416,
"recall": 0.8788250248510717,
"support": 30257.0
},
"eval_runtime": 4.7167,
"eval_samples_per_second": 17.173,
"eval_steps_per_second": 2.332,
"eval_weighted avg": {
"f1-score": 0.9158543469268937,
"precision": 0.9170673807540184,
"recall": 0.9154245298608586,
"support": 30257.0
},
"step": 81
},
{
"epoch": 2.0,
"eval_B": {
"f1-score": 0.8401515151515152,
"precision": 0.7585499316005472,
"recall": 0.9414261460101867,
"support": 1178.0
},
"eval_I": {
"f1-score": 0.9568235603470944,
"precision": 0.9510219016256338,
"recall": 0.9626964389650247,
"support": 18899.0
},
"eval_O": {
"f1-score": 0.9185648054827655,
"precision": 0.9430877483443708,
"recall": 0.8952848722986247,
"support": 10180.0
},
"eval_accuracy": 0.9391876260038999,
"eval_loss": 0.16692574322223663,
"eval_macro avg": {
"f1-score": 0.905179960327125,
"precision": 0.8842198605235172,
"recall": 0.9331358190912787,
"support": 30257.0
},
"eval_runtime": 4.7116,
"eval_samples_per_second": 17.192,
"eval_steps_per_second": 2.335,
"eval_weighted avg": {
"f1-score": 0.9394089523635119,
"precision": 0.9408589092241132,
"recall": 0.9391876260038999,
"support": 30257.0
},
"step": 162
},
{
"epoch": 3.0,
"eval_B": {
"f1-score": 0.8612244897959184,
"precision": 0.8294025157232704,
"recall": 0.8955857385398981,
"support": 1178.0
},
"eval_I": {
"f1-score": 0.951106371634231,
"precision": 0.9584654236741712,
"recall": 0.9438594634636753,
"support": 18899.0
},
"eval_O": {
"f1-score": 0.9106743212999903,
"precision": 0.9021592442645074,
"recall": 0.9193516699410609,
"support": 10180.0
},
"eval_accuracy": 0.9337343424662061,
"eval_loss": 0.1742253601551056,
"eval_macro avg": {
"f1-score": 0.9076683942433799,
"precision": 0.8966757278873163,
"recall": 0.9195989573148781,
"support": 30257.0
},
"eval_runtime": 4.7094,
"eval_samples_per_second": 17.2,
"eval_steps_per_second": 2.336,
"eval_weighted avg": {
"f1-score": 0.9340035812317422,
"precision": 0.9344963252190521,
"recall": 0.9337343424662061,
"support": 30257.0
},
"step": 243
},
{
"epoch": 4.0,
"eval_B": {
"f1-score": 0.8717948717948719,
"precision": 0.8254931714719271,
"recall": 0.9235993208828522,
"support": 1178.0
},
"eval_I": {
"f1-score": 0.9561271586371415,
"precision": 0.9374586871408959,
"recall": 0.9755542621302714,
"support": 18899.0
},
"eval_O": {
"f1-score": 0.9117828500925355,
"precision": 0.956427955133736,
"recall": 0.8711198428290766,
"support": 10180.0
},
"eval_accuracy": 0.9383944211256899,
"eval_loss": 0.18792153894901276,
"eval_macro avg": {
"f1-score": 0.9132349601748496,
"precision": 0.9064599379155197,
"recall": 0.9234244752807333,
"support": 30257.0
},
"eval_runtime": 4.7342,
"eval_samples_per_second": 17.11,
"eval_steps_per_second": 2.324,
"eval_weighted avg": {
"f1-score": 0.9379241479327001,
"precision": 0.9394817486046585,
"recall": 0.9383944211256899,
"support": 30257.0
},
"step": 324
}
],
"logging_steps": 500,
"max_steps": 4050,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 573360441343200.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}