Model save

README.md

@@ -2,11 +2,11 @@
 license: apache-2.0
 library_name: peft
 tags:
+- unsloth
 - trl
 - sft
-- translation
 - generated_from_trainer
-base_model: mistralai/Mistral-7B-v0.1
+base_model: unsloth/mistral-7b-bnb-4bit
 model-index:
 - name: MistralAI_iwslt15_en_vi_manual
   results: []
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # MistralAI_iwslt15_en_vi_manual
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [unsloth/mistral-7b-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-bnb-4bit) on an unknown dataset.
 
 ## Model description
 
@@ -40,20 +40,18 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 4269
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1
 - num_epochs: 1
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.39.3
-- Pytorch 2.2.1
-- Datasets 2.18.0
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
 - Tokenizers 0.15.2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "base_model_name_or_path": "unsloth/mistral-7b-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -11,17 +11,22 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 16,
   "rank_pattern": {},
-  "revision": null,
+  "revision": "unsloth",
   "target_modules": [
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
     "q_proj",
-    "v_proj"
+    "up_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cf4849132a2098f10c59f47222c8f12ad2fdd76c6f3bd311012f57446bf5bf
-size 109069176
+oid sha256:0846dd5dccaf1e9939a67a154d9c63c75124da79e549fe9a005c6fd04d028b54
+size 167832240

runs/Apr22_03-08-14_b3b625229fbf/events.out.tfevents.1713755394.b3b625229fbf.943.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d81e1e6a186ded33d58914dbdaa058912ec1ab638b56e637a2abe5b1a24f1710
+size 12489

special_tokens_map.json

@@ -13,7 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": "<s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -62,12 +62,6 @@
           "id": "A",
           "type_id": 0
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
       }
     ],
     "pair": [
@@ -83,12 +77,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
-      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -100,24 +88,9 @@
           "id": "B",
           "type_id": 1
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 1
-        }
       }
     ],
     "special_tokens": {
-      "</s>": {
-        "id": "</s>",
-        "ids": [
-          2
-        ],
-        "tokens": [
-          "</s>"
-        ]
-      },
       "<s>": {
         "id": "<s>",
         "ids": [

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "add_bos_token": true,
-  "add_eos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -32,9 +32,9 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "max_seq_length": 1024,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "model_max_length": 32768,
+  "pad_token": "<s>",
+  "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 sha256:7ef14cbbaa82c9476964a862acb20d4f9512f4fdd2dd3044e9cf6352408a41d8
-size 4984
+oid sha256:e77d288f2f7e79efe7562cb0c176791526cf3d81156530170345f861e1f4c4d2
+size 4920