End of training
Browse files- README.md +4 -1
- config.json +1 -1
README.md
CHANGED
|
@@ -2,7 +2,10 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: DatPySci/pythia-1b-sft-full
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: pythia-1b-kto-iter0-epoch1
|
| 8 |
results: []
|
|
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# pythia-1b-kto-iter0-epoch1
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [DatPySci/pythia-1b-sft-full](https://huggingface.co/DatPySci/pythia-1b-sft-full) on
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 0.3355
|
| 19 |
- Rewards/real: -0.0044
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: DatPySci/pythia-1b-sft-full
|
| 4 |
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- DatPySci/SPIN_iter0
|
| 9 |
model-index:
|
| 10 |
- name: pythia-1b-kto-iter0-epoch1
|
| 11 |
results: []
|
|
|
|
| 16 |
|
| 17 |
# pythia-1b-kto-iter0-epoch1
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [DatPySci/pythia-1b-sft-full](https://huggingface.co/DatPySci/pythia-1b-sft-full) on the DatPySci/SPIN_iter0 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.3355
|
| 22 |
- Rewards/real: -0.0044
|
config.json
CHANGED
|
@@ -24,7 +24,7 @@
|
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
"transformers_version": "4.38.1",
|
| 27 |
-
"use_cache":
|
| 28 |
"use_parallel_residual": true,
|
| 29 |
"vocab_size": 50304
|
| 30 |
}
|
|
|
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
"transformers_version": "4.38.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
"use_parallel_residual": true,
|
| 29 |
"vocab_size": 50304
|
| 30 |
}
|