End of training
Browse files- README.md +8 -6
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +3 -0
- runs/Nov11_17-28-19_f0be5bde0bfa/events.out.tfevents.1699723704.f0be5bde0bfa.25.0 +3 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [bigscience/mt0-small](https://huggingface.co/bigscience/mt0-small) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -40,19 +40,21 @@ The following hyperparameters were used during training:
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:-----:|:---------------:|
|
49 |
-
|
|
50 |
-
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
-
- Transformers 4.
|
56 |
- Pytorch 2.0.0
|
57 |
- Datasets 2.14.5
|
58 |
-
- Tokenizers 0.
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [bigscience/mt0-small](https://huggingface.co/bigscience/mt0-small) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 20.8655
|
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: 4
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:-----:|:---------------:|
|
49 |
+
| 19.235 | 1.0 | 16917 | 20.8672 |
|
50 |
+
| 19.2425 | 2.0 | 33834 | 20.8658 |
|
51 |
+
| 19.2805 | 3.0 | 50751 | 20.8657 |
|
52 |
+
| 19.261 | 4.0 | 67668 | 20.8655 |
|
53 |
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
+
- Transformers 4.35.0
|
58 |
- Pytorch 2.0.0
|
59 |
- Datasets 2.14.5
|
60 |
+
- Tokenizers 0.14.1
|
config.json
CHANGED
@@ -26,7 +26,7 @@
|
|
26 |
"tie_word_embeddings": false,
|
27 |
"tokenizer_class": "T5Tokenizer",
|
28 |
"torch_dtype": "bfloat16",
|
29 |
-
"transformers_version": "4.
|
30 |
"use_cache": true,
|
31 |
"vocab_size": 250112
|
32 |
}
|
|
|
26 |
"tie_word_embeddings": false,
|
27 |
"tokenizer_class": "T5Tokenizer",
|
28 |
"torch_dtype": "bfloat16",
|
29 |
+
"transformers_version": "4.35.0",
|
30 |
"use_cache": true,
|
31 |
"vocab_size": 250112
|
32 |
}
|
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.
|
7 |
}
|
|
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.35.0"
|
7 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3c039be5252a2a91f754cefb74504e18c1b2c7d8e075e382429dad4c7fbcb87
|
3 |
+
size 600375984
|
runs/Nov11_17-28-19_f0be5bde0bfa/events.out.tfevents.1699723704.f0be5bde0bfa.25.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f268bd6ee21c6e56bd596d19806b2377f41987580898c2ead66695f5b3036895
|
3 |
+
size 27302
|
training_args.bin
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 sha256:3d2266c502a363c77cacf5b1efe04ea1b884a48ea13464969a87109cb2b98f74
|
3 |
+
size 4091
|