End of training
Browse files- README.md +15 -2
- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
README.md
CHANGED
@@ -1,11 +1,24 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
|
|
|
|
4 |
metrics:
|
5 |
- accuracy
|
6 |
model-index:
|
7 |
- name: stage2
|
8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -13,7 +26,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# stage2
|
15 |
|
16 |
-
This model
|
17 |
It achieves the following results on the evaluation set:
|
18 |
- Loss: 0.3246
|
19 |
- Accuracy: 0.8954
|
|
|
1 |
---
|
2 |
+
base_model: linker_v4/stage1
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- jarod0411/linker_v2
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
model-index:
|
10 |
- name: stage2
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Causal Language Modeling
|
14 |
+
type: text-generation
|
15 |
+
dataset:
|
16 |
+
name: jarod0411/linker_v2
|
17 |
+
type: jarod0411/linker_v2
|
18 |
+
metrics:
|
19 |
+
- name: Accuracy
|
20 |
+
type: accuracy
|
21 |
+
value: 0.8953714759150758
|
22 |
---
|
23 |
|
24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
26 |
|
27 |
# stage2
|
28 |
|
29 |
+
This model is a fine-tuned version of [linker_v4/stage1](https://huggingface.co/linker_v4/stage1) on the jarod0411/linker_v2 dataset.
|
30 |
It achieves the following results on the evaluation set:
|
31 |
- Loss: 0.3246
|
32 |
- Accuracy: 0.8954
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.8953714759150758,
|
4 |
+
"eval_loss": 0.3246208131313324,
|
5 |
+
"eval_runtime": 1998.9364,
|
6 |
+
"eval_samples": 382464,
|
7 |
+
"eval_samples_per_second": 191.334,
|
8 |
+
"eval_steps_per_second": 2.392,
|
9 |
+
"perplexity": 1.3835059392212055,
|
10 |
+
"train_loss": 0.34171454371066545,
|
11 |
+
"train_runtime": 354822.8145,
|
12 |
+
"train_samples": 3445995,
|
13 |
+
"train_samples_per_second": 97.119,
|
14 |
+
"train_steps_per_second": 1.214
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.8953714759150758,
|
4 |
+
"eval_loss": 0.3246208131313324,
|
5 |
+
"eval_runtime": 1998.9364,
|
6 |
+
"eval_samples": 382464,
|
7 |
+
"eval_samples_per_second": 191.334,
|
8 |
+
"eval_steps_per_second": 2.392,
|
9 |
+
"perplexity": 1.3835059392212055
|
10 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 0.34171454371066545,
|
4 |
+
"train_runtime": 354822.8145,
|
5 |
+
"train_samples": 3445995,
|
6 |
+
"train_samples_per_second": 97.119,
|
7 |
+
"train_steps_per_second": 1.214
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|