cnatale/Mistral-7B-Instruct-v0.1-Txt-2-Presto-SQL

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6143
+- Loss: 0.6158
 
 ## Model description
 
@@ -53,12 +53,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8588        | 1.33  | 20   | 0.7602          |
-| 0.6494        | 2.67  | 40   | 0.6310          |
-| 0.5549        | 4.0   | 60   | 0.5919          |
-| 0.4855        | 5.33  | 80   | 0.6051          |
-| 0.4283        | 6.67  | 100  | 0.6050          |
-| 0.3904        | 8.0   | 120  | 0.6143          |
+| 0.8538        | 1.33  | 20   | 0.7586          |
+| 0.6488        | 2.67  | 40   | 0.6350          |
+| 0.5517        | 4.0   | 60   | 0.5917          |
+| 0.48          | 5.33  | 80   | 0.5902          |
+| 0.4311        | 6.67  | 100  | 0.6137          |
+| 0.3869        | 8.0   | 120  | 0.6158          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1abbe85561b652b5746f919cb017f565519376439ecfe3740d496dfe8c3dd600
+oid sha256:8cb2ea23c2228a9ac2fa0ad53ca41d20ff0eda1837f7c555bd5de902a81c9369
 size 109069176

runs/Jan02_21-18-05_fd53a3705225/events.out.tfevents.1704230286.fd53a3705225.1527.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6748c52f2fca1499a01b7887a796570e45e6ebe5c1662c280ed1d720606e439
+size 8617

tokenizer_config.json

@@ -29,6 +29,7 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31696b5a25f77c15b40627919ea506fa6982e8d8c8ad696eecdb750ddaf0ac09
+oid sha256:c8296a5ad976a884b1b836da635a099e3448bdf076d30ae416fc5e95ccd72461
 size 4728