End of training
Browse files- README.md +6 -6
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- runs/Mar21_10-28-48_d50f7a3b0580/events.out.tfevents.1742552946.d50f7a3b0580.199.0 +3 -0
- tokenizer.json +1 -6
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -29,18 +29,18 @@ print(output["generated_text"])
|
|
| 29 |
|
| 30 |
## Training procedure
|
| 31 |
|
| 32 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/iitguwahati/huggingface/runs/
|
| 33 |
|
| 34 |
|
| 35 |
This model was trained with SFT.
|
| 36 |
|
| 37 |
### Framework versions
|
| 38 |
|
| 39 |
-
- TRL: 0.
|
| 40 |
-
- Transformers: 4.
|
| 41 |
-
- Pytorch: 2.
|
| 42 |
-
- Datasets: 3.
|
| 43 |
-
- Tokenizers: 0.21.
|
| 44 |
|
| 45 |
## Citations
|
| 46 |
|
|
|
|
| 29 |
|
| 30 |
## Training procedure
|
| 31 |
|
| 32 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/iitguwahati/huggingface/runs/blhd3my2)
|
| 33 |
|
| 34 |
|
| 35 |
This model was trained with SFT.
|
| 36 |
|
| 37 |
### Framework versions
|
| 38 |
|
| 39 |
+
- TRL: 0.15.2
|
| 40 |
+
- Transformers: 4.49.0
|
| 41 |
+
- Pytorch: 2.6.0+cu124
|
| 42 |
+
- Datasets: 3.4.1
|
| 43 |
+
- Tokenizers: 0.21.1
|
| 44 |
|
| 45 |
## Citations
|
| 46 |
|
config.json
CHANGED
|
@@ -27,7 +27,7 @@
|
|
| 27 |
"rope_theta": 100000,
|
| 28 |
"tie_word_embeddings": true,
|
| 29 |
"torch_dtype": "float32",
|
| 30 |
-
"transformers_version": "4.
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 49152
|
| 33 |
}
|
|
|
|
| 27 |
"rope_theta": 100000,
|
| 28 |
"tie_word_embeddings": true,
|
| 29 |
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.49.0",
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 49152
|
| 33 |
}
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 2,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 2,
|
| 6 |
+
"transformers_version": "4.49.0"
|
| 7 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 538090408
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c40220acb710b334bb2bade89e9fe6bdcbd7a1e99fad1e5a7637e6487b4f0263
|
| 3 |
size 538090408
|
runs/Mar21_10-28-48_d50f7a3b0580/events.out.tfevents.1742552946.d50f7a3b0580.199.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25ca8a2c5464804b0649ad6442d8920e663defcdb80707a14ce42dd3c5addcdd
|
| 3 |
+
size 39999
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 1024,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
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 sha256:73d17c40fdd0482af44fe68186e9893f24b7e8fcc4b8a9326c3f63879c471b71
|
| 3 |
+
size 5560
|