End of training
Browse files- README.md +3 -3
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- runs/Jun20_19-33-21_ip-26-0-163-127/events.out.tfevents.1718912007.ip-26-0-163-127.2650686.0 +3 -0
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -38,11 +38,11 @@ The following hyperparameters were used during training:
|
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
-
- num_epochs:
|
42 |
|
43 |
### Framework versions
|
44 |
|
45 |
-
- Transformers 4.
|
46 |
-
- Pytorch 2.2.
|
47 |
- Datasets 2.18.0
|
48 |
- Tokenizers 0.19.1
|
|
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 3.0
|
42 |
|
43 |
### Framework versions
|
44 |
|
45 |
+
- Transformers 4.41.2
|
46 |
+
- Pytorch 2.2.1+cu121
|
47 |
- Datasets 2.18.0
|
48 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -23,7 +23,7 @@
|
|
23 |
"rotary_pct": 0.25,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float32",
|
26 |
-
"transformers_version": "4.
|
27 |
"use_cache": true,
|
28 |
"use_parallel_residual": true,
|
29 |
"vocab_size": 50304
|
|
|
23 |
"rotary_pct": 0.25,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.41.2",
|
27 |
"use_cache": true,
|
28 |
"use_parallel_residual": true,
|
29 |
"vocab_size": 50304
|
generation_config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
-
"transformers_version": "4.
|
5 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
+
"transformers_version": "4.41.2"
|
5 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 649308728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d03570d2090edc3ff824756f88fa034e82eb8c2f3be3167528d62c50702eeb2
|
3 |
size 649308728
|
runs/Jun20_19-33-21_ip-26-0-163-127/events.out.tfevents.1718912007.ip-26-0-163-127.2650686.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9422b591020bb0fe1956adf194f57f5e114f312a80aee17902b4db61012618f
|
3 |
+
size 157024
|
tokenizer_config.json
CHANGED
@@ -213,7 +213,7 @@
|
|
213 |
}
|
214 |
},
|
215 |
"bos_token": "<|endoftext|>",
|
216 |
-
"chat_template": "{% for message in messages %}{{' '
|
217 |
"clean_up_tokenization_spaces": true,
|
218 |
"eos_token": "<|endoftext|>",
|
219 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
213 |
}
|
214 |
},
|
215 |
"bos_token": "<|endoftext|>",
|
216 |
+
"chat_template": "{% for message in messages %}{{' ' if not loop.first else ''}}{{message['content']}}{% endfor %}{{eos_token}}",
|
217 |
"clean_up_tokenization_spaces": true,
|
218 |
"eos_token": "<|endoftext|>",
|
219 |
"model_max_length": 1000000000000000019884624838656,
|
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:c1bfc7bf13c40dbd55643bb8215823f8afe99be4e3c9bd605d749b6a87dc9682
|
3 |
+
size 5944
|