End of training
Browse files- README.md +6 -1
- all_results.json +8 -8
- eval_results.json +4 -5
- train_results.json +4 -4
- trainer_state.json +7 -7
README.md
CHANGED
@@ -1,4 +1,7 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: t5-small
|
4 |
tags:
|
@@ -15,7 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# english-hindi
|
17 |
|
18 |
-
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus100 dataset.
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- hi
|
5 |
license: apache-2.0
|
6 |
base_model: t5-small
|
7 |
tags:
|
|
|
18 |
|
19 |
# english-hindi
|
20 |
|
21 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus100 en-hi dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0816
|
24 |
|
25 |
## Model description
|
26 |
|
all_results.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"eval_bleu": 0.0,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
"eval_samples": 8,
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second":
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
"train_samples": 2088,
|
12 |
-
"train_samples_per_second": 6.
|
13 |
-
"train_steps_per_second": 1.
|
14 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"eval_bleu": 0.0,
|
4 |
+
"eval_loss": 0.08162859082221985,
|
5 |
+
"eval_runtime": 0.5668,
|
6 |
"eval_samples": 8,
|
7 |
+
"eval_samples_per_second": 14.114,
|
8 |
+
"eval_steps_per_second": 3.529,
|
9 |
+
"train_loss": 0.2691089805515333,
|
10 |
+
"train_runtime": 914.55,
|
11 |
"train_samples": 2088,
|
12 |
+
"train_samples_per_second": 6.849,
|
13 |
+
"train_steps_per_second": 1.712
|
14 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"eval_runtime": 114.5298,
|
6 |
"eval_samples": 8,
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second":
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_loss": 0.08162859082221985,
|
4 |
+
"eval_runtime": 0.5668,
|
|
|
5 |
"eval_samples": 8,
|
6 |
+
"eval_samples_per_second": 14.114,
|
7 |
+
"eval_steps_per_second": 3.529
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 2088,
|
6 |
-
"train_samples_per_second": 6.
|
7 |
-
"train_steps_per_second": 1.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"train_loss": 0.2691089805515333,
|
4 |
+
"train_runtime": 914.55,
|
5 |
"train_samples": 2088,
|
6 |
+
"train_samples_per_second": 6.849,
|
7 |
+
"train_steps_per_second": 1.712
|
8 |
}
|
trainer_state.json
CHANGED
@@ -11,29 +11,29 @@
|
|
11 |
{
|
12 |
"epoch": 0.96,
|
13 |
"learning_rate": 3.403575989782887e-05,
|
14 |
-
"loss": 0.
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 1.92,
|
19 |
"learning_rate": 1.8071519795657726e-05,
|
20 |
-
"loss": 0.
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
"epoch": 2.87,
|
25 |
"learning_rate": 2.1072796934865904e-06,
|
26 |
-
"loss": 0.
|
27 |
"step": 1500
|
28 |
},
|
29 |
{
|
30 |
"epoch": 3.0,
|
31 |
"step": 1566,
|
32 |
"total_flos": 73168104062976.0,
|
33 |
-
"train_loss": 0.
|
34 |
-
"train_runtime":
|
35 |
-
"train_samples_per_second": 6.
|
36 |
-
"train_steps_per_second": 1.
|
37 |
}
|
38 |
],
|
39 |
"logging_steps": 500,
|
|
|
11 |
{
|
12 |
"epoch": 0.96,
|
13 |
"learning_rate": 3.403575989782887e-05,
|
14 |
+
"loss": 0.3102,
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 1.92,
|
19 |
"learning_rate": 1.8071519795657726e-05,
|
20 |
+
"loss": 0.2601,
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
"epoch": 2.87,
|
25 |
"learning_rate": 2.1072796934865904e-06,
|
26 |
+
"loss": 0.2405,
|
27 |
"step": 1500
|
28 |
},
|
29 |
{
|
30 |
"epoch": 3.0,
|
31 |
"step": 1566,
|
32 |
"total_flos": 73168104062976.0,
|
33 |
+
"train_loss": 0.2691089805515333,
|
34 |
+
"train_runtime": 914.55,
|
35 |
+
"train_samples_per_second": 6.849,
|
36 |
+
"train_steps_per_second": 1.712
|
37 |
}
|
38 |
],
|
39 |
"logging_steps": 500,
|