Commit
•
d562256
1
Parent(s):
3ab7099
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: 2.
|
19 |
-
- eval_runtime: 84.
|
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: 2.2497
|
19 |
+
- eval_runtime: 84.957
|
20 |
+
- eval_samples_per_second: 58.853
|
21 |
+
- eval_steps_per_second: 0.93
|
22 |
+
- epoch: 3.03
|
23 |
+
- step: 2250
|
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:e89f989e4955a50cfddc7bb8a3e3e14075d0d2392f143925f36db9b0fa5f9b21
|
3 |
+
size 1718122
|
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:fe652302c6ea5bdc5124482be6693e70ebf49976b2a5d02a862f5b5ca6f4acdc
|
3 |
size 535667604
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "ner-bert-ingredients/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,
|
@@ -35,6 +35,20 @@
|
|
35 |
"eval_samples_per_second": 58.912,
|
36 |
"eval_steps_per_second": 0.931,
|
37 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 750,
|
@@ -42,7 +56,7 @@
|
|
42 |
"num_input_tokens_seen": 0,
|
43 |
"num_train_epochs": 100,
|
44 |
"save_steps": 750,
|
45 |
-
"total_flos":
|
46 |
"train_batch_size": 16,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.692633867263794,
|
3 |
+
"best_model_checkpoint": "ner-bert-ingredients/checkpoint-1500",
|
4 |
+
"epoch": 3.031323678006063,
|
5 |
"eval_steps": 750,
|
6 |
+
"global_step": 2250,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
35 |
"eval_samples_per_second": 58.912,
|
36 |
"eval_steps_per_second": 0.931,
|
37 |
"step": 1500
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 3.03,
|
41 |
+
"learning_rate": 4.84845013477089e-05,
|
42 |
+
"loss": 2.4396,
|
43 |
+
"step": 2250
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 3.03,
|
47 |
+
"eval_loss": 2.2496654987335205,
|
48 |
+
"eval_runtime": 84.957,
|
49 |
+
"eval_samples_per_second": 58.853,
|
50 |
+
"eval_steps_per_second": 0.93,
|
51 |
+
"step": 2250
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 750,
|
|
|
56 |
"num_input_tokens_seen": 0,
|
57 |
"num_train_epochs": 100,
|
58 |
"save_steps": 750,
|
59 |
+
"total_flos": 9.737956672524288e+16,
|
60 |
"train_batch_size": 16,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|