End of training
Browse files- README.md +11 -11
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- runs/Apr02_14-20-48_c3d0f9b1aad3/events.out.tfevents.1712067650.c3d0f9b1aad3.533.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.
|
21 |
-
- Rouge1: 0.
|
22 |
-
- Rouge2: 0.
|
23 |
-
- Rougel: 0.
|
24 |
-
- Rougelsum: 0.
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
55 |
-
| No log | 1.0 | 67 | 1.
|
56 |
-
| No log | 2.0 | 134 | 1.
|
57 |
-
| No log | 3.0 | 201 | 1.
|
58 |
-
| No log | 4.0 | 268 | 1.
|
59 |
-
| No log | 5.0 | 335 | 1.
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
-
- Transformers 4.39.
|
65 |
- Pytorch 2.2.1+cu121
|
66 |
- Datasets 2.18.0
|
67 |
- Tokenizers 0.15.2
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.1086
|
21 |
+
- Rouge1: 0.4487
|
22 |
+
- Rouge2: 0.2809
|
23 |
+
- Rougel: 0.4097
|
24 |
+
- Rougelsum: 0.4110
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
55 |
+
| No log | 1.0 | 67 | 1.4667 | 0.3682 | 0.1743 | 0.3295 | 0.3298 |
|
56 |
+
| No log | 2.0 | 134 | 1.2361 | 0.4035 | 0.2159 | 0.3666 | 0.3647 |
|
57 |
+
| No log | 3.0 | 201 | 1.1369 | 0.4482 | 0.2765 | 0.3971 | 0.3966 |
|
58 |
+
| No log | 4.0 | 268 | 1.0996 | 0.4526 | 0.2926 | 0.4106 | 0.4126 |
|
59 |
+
| No log | 5.0 | 335 | 1.1086 | 0.4487 | 0.2809 | 0.4097 | 0.4110 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
+
- Transformers 4.39.3
|
65 |
- Pytorch 2.2.1+cu121
|
66 |
- Datasets 2.18.0
|
67 |
- Tokenizers 0.15.2
|
config.json
CHANGED
@@ -56,7 +56,7 @@
|
|
56 |
},
|
57 |
"tie_word_embeddings": false,
|
58 |
"torch_dtype": "float32",
|
59 |
-
"transformers_version": "4.39.
|
60 |
"use_cache": true,
|
61 |
"vocab_size": 32128
|
62 |
}
|
|
|
56 |
},
|
57 |
"tie_word_embeddings": false,
|
58 |
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.39.3",
|
60 |
"use_cache": true,
|
61 |
"vocab_size": 32128
|
62 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
-
"transformers_version": "4.39.
|
6 |
}
|
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.39.3"
|
6 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990345064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61d8217e5103d34028a3e7d1a69ee86baf25b3f38b0831a2346cd6dd99eb6ca2
|
3 |
size 990345064
|
runs/Apr02_14-20-48_c3d0f9b1aad3/events.out.tfevents.1712067650.c3d0f9b1aad3.533.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c41bbcc9ddf062e984413732266881ab289004148c351869218ca299a4e35d0e
|
3 |
+
size 8326
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d2f19178eca7e1cd4f7d4b09edfc1e72caa79bf96b75aaf78274f94d358c81e
|
3 |
size 5048
|