End of training
Browse files- README.md +5 -1
- config.json +26 -0
README.md
CHANGED
|
@@ -2,9 +2,13 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- trl
|
| 6 |
- dpo
|
| 7 |
- generated_from_trainer
|
|
|
|
|
|
|
| 8 |
base_model: sablo/sablo-pebble-mistral
|
| 9 |
model-index:
|
| 10 |
- name: sablo-pebble-mistral-dpo-lora-oasst2_dpo_pairs_en
|
|
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# sablo-pebble-mistral-dpo-lora-oasst2_dpo_pairs_en
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [sablo/sablo-pebble-mistral](https://huggingface.co/sablo/sablo-pebble-mistral) on the
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6714
|
| 22 |
- Rewards/chosen: 0.1838
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
+
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- dpo
|
| 9 |
- generated_from_trainer
|
| 10 |
+
datasets:
|
| 11 |
+
- sablo/oasst2_dpo_pairs_en
|
| 12 |
base_model: sablo/sablo-pebble-mistral
|
| 13 |
model-index:
|
| 14 |
- name: sablo-pebble-mistral-dpo-lora-oasst2_dpo_pairs_en
|
|
|
|
| 20 |
|
| 21 |
# sablo-pebble-mistral-dpo-lora-oasst2_dpo_pairs_en
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [sablo/sablo-pebble-mistral](https://huggingface.co/sablo/sablo-pebble-mistral) on the sablo/oasst2_dpo_pairs_en dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
- Loss: 0.6714
|
| 26 |
- Rewards/chosen: 0.1838
|
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sablo/sablo-pebble-mistral",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 32000,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 14336,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"model_type": "mistral",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_theta": 10000.0,
|
| 20 |
+
"sliding_window": 4096,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.36.2",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 32002
|
| 26 |
+
}
|