End of training

README.md

@@ -1,12 +1,11 @@
 ---
 language:
 - multilingual
-license: apache-2.0
-base_model: mistralai/Mistral-7B-v0.1
+base_model: /kaggle/input/mistral-7b/Mistral-7B-v0.1
 tags:
 - generated_from_trainer
 datasets:
-- arc
+- STEM
 model-index:
 - name: mistral-7b-llm-science-exam
   results: []
@@ -17,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-7b-llm-science-exam
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the ARC dataset.
+This model is a fine-tuned version of [/kaggle/input/mistral-7b/Mistral-7B-v0.1](https://huggingface.co//kaggle/input/mistral-7b/Mistral-7B-v0.1) on the llm-science-exam dataset.
 
 ## Model description
 
@@ -36,13 +35,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 1
-- eval_batch_size: 8
+- learning_rate: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 50
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 25
 - num_epochs: 1
 
 ### Framework versions

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "base_model_name_or_path": "/kaggle/input/mistral-7b/Mistral-7B-v0.1",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6e48c63cb54dc17c542358f7fe252e7e537c2c5e741089b07cdbf2222fc9c75
+oid sha256:b3ea89ea4b4b01471867e342833f3182664bc5d9667c08cfd651220831cf2991
 size 109097933

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaad09104310eaaa7ee2ee7c10fd465ddad8907d7d54abaaff45ad31161f8f2c
+oid sha256:85286bab714706443a5a98be9bb777ca67e3f6827f1200c9309f35e64a95e885
 size 4091