End of training
Browse files- README.md +6 -6
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- runs/May22_22-02-20_808d2f83ffb7/events.out.tfevents.1716415346.808d2f83ffb7.34.0 +3 -0
- tokenizer.json +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -11,13 +11,11 @@ model-index:
|
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/jadavpur/huggingface/runs/nqfl3694)
|
15 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/jadavpur/huggingface/runs/nqfl3694)
|
16 |
# flan-t5-base-cnn_dailymail
|
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 |
|
22 |
## Model description
|
23 |
|
@@ -42,18 +40,20 @@ The following hyperparameters were used during training:
|
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
-
- num_epochs:
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
-
| 1.
|
|
|
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
55 |
|
56 |
-
- Transformers 4.41.
|
57 |
- Pytorch 2.1.2
|
58 |
- Datasets 2.19.1
|
59 |
- Tokenizers 0.19.1
|
|
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
|
|
|
|
14 |
# flan-t5-base-cnn_dailymail
|
15 |
|
16 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.9141
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 3
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 1.8436 | 1.0 | 125 | 1.8955 |
|
50 |
+
| 2.0678 | 2.0 | 250 | 1.9134 |
|
51 |
+
| 1.8895 | 3.0 | 375 | 1.9141 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
55 |
|
56 |
+
- Transformers 4.41.1
|
57 |
- Pytorch 2.1.2
|
58 |
- Datasets 2.19.1
|
59 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -56,7 +56,7 @@
|
|
56 |
},
|
57 |
"tie_word_embeddings": false,
|
58 |
"torch_dtype": "float32",
|
59 |
-
"transformers_version": "4.41.
|
60 |
"use_cache": true,
|
61 |
"vocab_size": 32128
|
62 |
}
|
|
|
56 |
},
|
57 |
"tie_word_embeddings": false,
|
58 |
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.41.1",
|
60 |
"use_cache": true,
|
61 |
"vocab_size": 32128
|
62 |
}
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
-
"transformers_version": "4.41.
|
7 |
}
|
|
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.41.1"
|
7 |
}
|
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 sha256:7359d6c57e34c545a9f3952bf43dc60b2fc43f7ebe754fb209384812cbde78d3
|
3 |
size 990345064
|
runs/May22_22-02-20_808d2f83ffb7/events.out.tfevents.1716415346.808d2f83ffb7.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb90bc2c774d0a6338316087177848c36e9288261405f0d8d3a17264f1bd2951
|
3 |
+
size 22774
|
tokenizer.json
CHANGED
@@ -2,13 +2,13 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
-
"Fixed":
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 112,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
+
"Fixed": 112
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7779e3cf56305174cfef88db29a59aa86ed87db8acd6be8d22ab2313dd55b7f6
|
3 |
size 5304
|