Commit
•
9658afb
1
Parent(s):
b0cca74
End of training
Browse files- README.md +6 -6
- logs/events.out.tfevents.1704536554.9585f193967c.27.0 +2 -2
- model.safetensors +1 -1
- trainer_state.json +19 -5
README.md
CHANGED
@@ -15,12 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- eval_loss:
|
19 |
-
- eval_runtime:
|
20 |
-
- eval_samples_per_second: 58.
|
21 |
-
- eval_steps_per_second: 0.
|
22 |
-
- epoch:
|
23 |
-
- step:
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- eval_loss: 2.6926
|
19 |
+
- eval_runtime: 84.8728
|
20 |
+
- eval_samples_per_second: 58.912
|
21 |
+
- eval_steps_per_second: 0.931
|
22 |
+
- epoch: 2.02
|
23 |
+
- step: 1500
|
24 |
|
25 |
## Model description
|
26 |
|
logs/events.out.tfevents.1704536554.9585f193967c.27.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afeb77457c9c4a545df5f0b806ae6c76b9b834e73473956e5904c8600ad8ec18
|
3 |
+
size 1717694
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535667604
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5977be66008ccbf3a905fc1702f6f36943ba6cce85352db22c1b3a5d7cd17879
|
3 |
size 535667604
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint":
|
4 |
-
"epoch":
|
5 |
"eval_steps": 750,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -21,6 +21,20 @@
|
|
21 |
"eval_samples_per_second": 58.658,
|
22 |
"eval_steps_per_second": 0.927,
|
23 |
"step": 750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 750,
|
@@ -28,7 +42,7 @@
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 100,
|
30 |
"save_steps": 750,
|
31 |
-
"total_flos":
|
32 |
"train_batch_size": 16,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 4.010455131530762,
|
3 |
+
"best_model_checkpoint": "ner-bert-ingredients/checkpoint-750",
|
4 |
+
"epoch": 2.0208824520040416,
|
5 |
"eval_steps": 750,
|
6 |
+
"global_step": 1500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
21 |
"eval_samples_per_second": 58.658,
|
22 |
"eval_steps_per_second": 0.927,
|
23 |
"step": 750
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.02,
|
27 |
+
"learning_rate": 4.8989218328840976e-05,
|
28 |
+
"loss": 3.2428,
|
29 |
+
"step": 1500
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.02,
|
33 |
+
"eval_loss": 2.692633867263794,
|
34 |
+
"eval_runtime": 84.8728,
|
35 |
+
"eval_samples_per_second": 58.912,
|
36 |
+
"eval_steps_per_second": 0.931,
|
37 |
+
"step": 1500
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 750,
|
|
|
42 |
"num_input_tokens_seen": 0,
|
43 |
"num_train_epochs": 100,
|
44 |
"save_steps": 750,
|
45 |
+
"total_flos": 6.491971115016192e+16,
|
46 |
"train_batch_size": 16,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|