mistralai/mistral-instruct-generation-szn-by-me

README.md

@@ -5,9 +5,9 @@ tags:
 - trl
 - sft
 - generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 datasets:
 - generator
-base_model: mistralai/Mistral-7B-Instruct-v0.1
 model-index:
 - name: mistral_instruct_generation
   results: []
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral_instruct_generation
 
-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.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4967
+- Loss: 1.4389
 
 ## Model description
 
@@ -51,19 +51,19 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.6319        | 0.03  | 20   | 1.5642          |
-| 1.5826        | 0.05  | 40   | 1.5262          |
-| 1.5995        | 0.08  | 60   | 1.5122          |
-| 1.5292        | 0.1   | 80   | 1.5030          |
-| 1.5593        | 0.13  | 100  | 1.4967          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.6485        | 0.0260 | 20   | 1.5379          |
+| 1.5023        | 0.0521 | 40   | 1.4691          |
+| 1.4632        | 0.0781 | 60   | 1.4547          |
+| 1.4887        | 0.1042 | 80   | 1.4471          |
+| 1.4516        | 0.1302 | 100  | 1.4389          |
 
 
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.39.0
-- Pytorch 2.2.1+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006e25bc0327fc595e6dfbc7d7ead653a2569e75be29e97d6151232dd5a7b7fd
+oid sha256:5421be3a38d5755f19eca3c93b4ce525e65bbeec1ad3039a5fe8992e7da7035a
 size 27280152

runs/May07_08-49-54_bf0b8504c300/events.out.tfevents.1715071893.bf0b8504c300.316.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae77b92376d221020c12c87a89e6fd2e0b01c384e279e38a12d65eb58e33bb9
+size 8952

tokenizer.json

@@ -134,6 +134,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

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:a13efc75d4bb173350b7c55d9b31eb6c3514abd7257e5fdcfb5eca18f55b3429
-size 4984
+oid sha256:0804dc137cce2cbe9de0d72272ccd11e954bc695cb8f25d194bc811e26c3e9f8
+size 5048