mistralai/mistral-instruct-generation

README.md

@@ -5,7 +5,7 @@ tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: mistralai/Mistral-7B-Instruct-v0.2
+base_model: mistralai/Mistral-7B-Instruct-v0.1
 datasets:
 - generator
 model-index:
@@ -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-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
+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: 1.4389
+- Loss: 1.4969
 
 ## Model description
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 | 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          |
+| 1.6666        | 0.0260 | 20   | 1.5570          |
+| 1.5509        | 0.0521 | 40   | 1.5239          |
+| 1.5707        | 0.0781 | 60   | 1.5093          |
+| 1.5722        | 0.1042 | 80   | 1.5024          |
+| 1.5602        | 0.1302 | 100  | 1.4969          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
   "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 sha256:5421be3a38d5755f19eca3c93b4ce525e65bbeec1ad3039a5fe8992e7da7035a
+oid sha256:5da2600a0dcc2d5a7b2838b49cb83a0c02dadda5a3e7e652007661ae36b8ed1c
 size 27280152

runs/May08_07-23-51_8413bacd2c4b/events.out.tfevents.1715153319.8413bacd2c4b.225.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7dcbe365dd34f701fde2488dd160d75974825f86e8938858ada643b95091dfe
+size 8950

tokenizer_config.json

@@ -29,7 +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 %}",
+  "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 sha256:0804dc137cce2cbe9de0d72272ccd11e954bc695cb8f25d194bc811e26c3e9f8
+oid sha256:413bc6e1d67a088848afdf175ac749c9f4d0ff09768e00b393021aabec09c5d4
 size 5048