Shresthadev403
commited on
Commit
•
7854780
1
Parent(s):
a6b18dc
End of training
Browse files- README.md +5 -5
- logs/events.out.tfevents.1704638284.80d534b5f596.26.0 +2 -2
- model.safetensors +1 -1
- trainer_state.json +19 -5
README.md
CHANGED
@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model was trained from scratch on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- eval_loss: 1.
|
17 |
-
- eval_runtime: 83.
|
18 |
-
- eval_samples_per_second: 59.
|
19 |
- eval_steps_per_second: 0.944
|
20 |
-
- epoch:
|
21 |
-
- step:
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
13 |
|
14 |
This model was trained from scratch on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- eval_loss: 1.3497
|
17 |
+
- eval_runtime: 83.6712
|
18 |
+
- eval_samples_per_second: 59.758
|
19 |
- eval_steps_per_second: 0.944
|
20 |
+
- epoch: 12.13
|
21 |
+
- step: 9000
|
22 |
|
23 |
## Model description
|
24 |
|
logs/events.out.tfevents.1704638284.80d534b5f596.26.0
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 sha256:1df804bbce7176c17a9b7e2ffd0f90760d52812288260894052a638a82249907
|
3 |
+
size 1719464
|
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:ee869e69f26d6b5af04157d2668f1392049dcc8bc28677868a1cd397756c694a
|
3 |
size 535667604
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
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,
|
@@ -161,6 +161,20 @@
|
|
161 |
"eval_samples_per_second": 59.763,
|
162 |
"eval_steps_per_second": 0.944,
|
163 |
"step": 8250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
164 |
}
|
165 |
],
|
166 |
"logging_steps": 750,
|
@@ -168,7 +182,7 @@
|
|
168 |
"num_input_tokens_seen": 0,
|
169 |
"num_train_epochs": 100,
|
170 |
"save_steps": 750,
|
171 |
-
"total_flos": 3.
|
172 |
"train_batch_size": 16,
|
173 |
"trial_name": null,
|
174 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.4048632383346558,
|
3 |
+
"best_model_checkpoint": "ner-bert-ingredients/checkpoint-8250",
|
4 |
+
"epoch": 12.127315594476254,
|
5 |
"eval_steps": 750,
|
6 |
+
"global_step": 9000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
161 |
"eval_samples_per_second": 59.763,
|
162 |
"eval_steps_per_second": 0.944,
|
163 |
"step": 8250
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 12.13,
|
167 |
+
"learning_rate": 4.696900269541779e-05,
|
168 |
+
"loss": 0.9469,
|
169 |
+
"step": 9000
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 12.13,
|
173 |
+
"eval_loss": 1.349704384803772,
|
174 |
+
"eval_runtime": 83.6712,
|
175 |
+
"eval_samples_per_second": 59.758,
|
176 |
+
"eval_steps_per_second": 0.944,
|
177 |
+
"step": 9000
|
178 |
}
|
179 |
],
|
180 |
"logging_steps": 750,
|
|
|
182 |
"num_input_tokens_seen": 0,
|
183 |
"num_train_epochs": 100,
|
184 |
"save_steps": 750,
|
185 |
+
"total_flos": 3.895182669009715e+17,
|
186 |
"train_batch_size": 16,
|
187 |
"trial_name": null,
|
188 |
"trial_params": null
|