Upload 11 files
Browse files- config.json +14 -14
- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +49 -5
config.json
CHANGED
@@ -9,23 +9,23 @@
|
|
9 |
"dropout": 0.1,
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
-
"0": "
|
13 |
-
"1": "
|
14 |
-
"2": "
|
15 |
-
"3": "
|
16 |
-
"4": "
|
17 |
-
"5": "
|
18 |
-
"6": "
|
19 |
},
|
20 |
"initializer_range": 0.02,
|
21 |
"label2id": {
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
},
|
30 |
"max_position_embeddings": 512,
|
31 |
"model_type": "distilbert",
|
|
|
9 |
"dropout": 0.1,
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6"
|
19 |
},
|
20 |
"initializer_range": 0.02,
|
21 |
"label2id": {
|
22 |
+
"LABEL_0": 0,
|
23 |
+
"LABEL_1": 1,
|
24 |
+
"LABEL_2": 2,
|
25 |
+
"LABEL_3": 3,
|
26 |
+
"LABEL_4": 4,
|
27 |
+
"LABEL_5": 5,
|
28 |
+
"LABEL_6": 6
|
29 |
},
|
30 |
"max_position_embeddings": 512,
|
31 |
"model_type": "distilbert",
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 538970204
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:509860f7ad84567c6d9040617392aa974a83fb1da93455294cc1f21b2d48a8f0
|
3 |
size 538970204
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1078001210
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9022e88e9a1bae01e087146db4cf5f8af01ed83b1965b118f318bdafae2ea8bf
|
3 |
size 1078001210
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c408c5710d33bb9d33ccc69e5c1543496734e0f2526dc35e266027b8355f109
|
3 |
size 14244
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a28f3f3fa3e4d886eeb63b341619fde4a4c6b57fa0b7ccffb348786728134f4a
|
3 |
size 1064
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint":
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -843,6 +843,50 @@
|
|
843 |
"eval_samples_per_second": 215.069,
|
844 |
"eval_steps_per_second": 1.683,
|
845 |
"step": 38000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
846 |
}
|
847 |
],
|
848 |
"logging_steps": 1000,
|
@@ -850,7 +894,7 @@
|
|
850 |
"num_input_tokens_seen": 0,
|
851 |
"num_train_epochs": 7,
|
852 |
"save_steps": 500,
|
853 |
-
"total_flos":
|
854 |
"train_batch_size": 8,
|
855 |
"trial_name": null,
|
856 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.26044607162475586,
|
3 |
+
"best_model_checkpoint": "./checkpoint-distilbert/checkpoint-40000",
|
4 |
+
"epoch": 1.7708517797060386,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 40000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
843 |
"eval_samples_per_second": 215.069,
|
844 |
"eval_steps_per_second": 1.683,
|
845 |
"step": 38000
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 1.73,
|
849 |
+
"grad_norm": 7.599725246429443,
|
850 |
+
"learning_rate": 1.5066912899390323e-05,
|
851 |
+
"loss": 0.2322,
|
852 |
+
"step": 39000
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 1.73,
|
856 |
+
"eval_LOC_f1": 0.8500763831144973,
|
857 |
+
"eval_ORG_f1": 0.7572957665354708,
|
858 |
+
"eval_PER_f1": 0.8590397422347182,
|
859 |
+
"eval_loss": 0.27235275506973267,
|
860 |
+
"eval_overall_accuracy": 0.9206611521030973,
|
861 |
+
"eval_overall_f1": 0.8259451471597206,
|
862 |
+
"eval_overall_precision": 0.8237684495694223,
|
863 |
+
"eval_overall_recall": 0.8281333784889792,
|
864 |
+
"eval_runtime": 580.4463,
|
865 |
+
"eval_samples_per_second": 113.189,
|
866 |
+
"eval_steps_per_second": 0.886,
|
867 |
+
"step": 39000
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 1.77,
|
871 |
+
"grad_norm": 2.075500249862671,
|
872 |
+
"learning_rate": 1.4940423486554176e-05,
|
873 |
+
"loss": 0.2213,
|
874 |
+
"step": 40000
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 1.77,
|
878 |
+
"eval_LOC_f1": 0.8435102589085544,
|
879 |
+
"eval_ORG_f1": 0.7572054303898555,
|
880 |
+
"eval_PER_f1": 0.8558481099725878,
|
881 |
+
"eval_loss": 0.26044607162475586,
|
882 |
+
"eval_overall_accuracy": 0.9183281820401503,
|
883 |
+
"eval_overall_f1": 0.8229231947635958,
|
884 |
+
"eval_overall_precision": 0.8123006708457055,
|
885 |
+
"eval_overall_recall": 0.833827223210002,
|
886 |
+
"eval_runtime": 503.8704,
|
887 |
+
"eval_samples_per_second": 130.391,
|
888 |
+
"eval_steps_per_second": 1.02,
|
889 |
+
"step": 40000
|
890 |
}
|
891 |
],
|
892 |
"logging_steps": 1000,
|
|
|
894 |
"num_input_tokens_seen": 0,
|
895 |
"num_train_epochs": 7,
|
896 |
"save_steps": 500,
|
897 |
+
"total_flos": 5523298719415224.0,
|
898 |
"train_batch_size": 8,
|
899 |
"trial_name": null,
|
900 |
"trial_params": null
|