Training in progress, epoch 1

README.md

@@ -1,18 +1,18 @@
 ---
-base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+base_model: unsloth/mistral-7b-v0.3-bnb-4bit
 library_name: transformers
 model_name: sft_best_simplification
 tags:
 - generated_from_trainer
-- unsloth
 - trl
+- unsloth
 - sft
 licence: license
 ---
 
 # Model Card for sft_best_simplification
 
-This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3-bnb-4bit).
+This model is a fine-tuned version of [unsloth/mistral-7b-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +28,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ioakeime-aristotle-university-of-thessaloniki/sft_best_simplification/runs/9amgp9pe) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ioakeime-aristotle-university-of-thessaloniki/sft_best_simplification/runs/kc6lw27s) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -7,7 +7,7 @@
     "parent_library": "transformers.models.mistral.modeling_mistral",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "base_model_name_or_path": "unsloth/mistral-7b-v0.3-bnb-4bit",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "up_proj",
+    "q_proj",
     "down_proj",
     "v_proj",
     "k_proj",
-    "q_proj",
     "gate_proj",
-    "up_proj"
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8264ef51349540391c8791d34755db267ace4ed3577d90965629495a6ee8544
+oid sha256:2c191500666a73afc7b36b3ae7277329f9cf35396f5c021a71ed8f7acd8aa3ba
 size 167832240

tokenizer_config.json

@@ -6179,7 +6179,7 @@
   "legacy": false,
   "model_max_length": 32768,
   "pad_token": "[control_768]",
-  "padding_side": "left",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b195bbee031377a98da390b75c70b5f638541cb5f65dfa6119007797723266
+oid sha256:c40cf0f3fb04a0ff90a766e83b9ee7fcc9800df8b0bf374934d3bf32257ed7ff
 size 6353