rohitkhatri75436/fine-tuned-1.7-smollm-flutter-structured

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: HuggingFaceTB/SmolLM-135M
+base_model: HuggingFaceTB/SmolLM2-360M-Instruct
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # smollm_flutter_packages_model_structured_text
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on the None dataset.
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9298
+- Loss: 0.8510
 
 ## Model description
 
@@ -42,14 +42,15 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 3
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.29          | 1.0   | 197  | 0.9765          |
-| 0.9644        | 2.0   | 394  | 0.9388          |
-| 0.9282        | 3.0   | 591  | 0.9298          |
+| 0.5574        | 1.0   | 197  | 0.8908          |
+| 0.4378        | 2.0   | 394  | 0.8597          |
+| 0.4158        | 3.0   | 591  | 0.8510          |
 
 
 ### Framework versions

config.json

@@ -4,26 +4,34 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 576,
+  "hidden_size": 960,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "max_position_embeddings": 2048,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 9,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 3,
-  "pad_token_id": 0,
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
   "transformers_version": "4.51.3",
   "use_cache": true,
   "vocab_size": 49152

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
   "transformers_version": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da232ff03f981c68c161322c53128d4dc7e0ce7b083f12eab71ec274302c2043
-size 538090408
+oid sha256:ddadf0060646fcf8f7f70f9c2fc8616cfd1dacaca2548eeefd57327aa81968c6
+size 1447317080

special_tokens_map.json

@@ -1,38 +1,29 @@
 {
   "additional_special_tokens": [
-    "<|endoftext|>",
     "<|im_start|>",
-    "<|im_end|>",
-    "<repo_name>",
-    "<reponame>",
-    "<file_sep>",
-    "<filename>",
-    "<gh_stars>",
-    "<issue_start>",
-    "<issue_comment>",
-    "<issue_closed>",
-    "<jupyter_start>",
-    "<jupyter_text>",
-    "<jupyter_code>",
-    "<jupyter_output>",
-    "<jupyter_script>",
-    "<empty_output>"
+    "<|im_end|>"
   ],
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_start|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json

@@ -139,30 +139,16 @@
     }
   },
   "additional_special_tokens": [
-    "<|endoftext|>",
     "<|im_start|>",
-    "<|im_end|>",
-    "<repo_name>",
-    "<reponame>",
-    "<file_sep>",
-    "<filename>",
-    "<gh_stars>",
-    "<issue_start>",
-    "<issue_comment>",
-    "<issue_closed>",
-    "<jupyter_start>",
-    "<jupyter_text>",
-    "<jupyter_code>",
-    "<jupyter_output>",
-    "<jupyter_script>",
-    "<empty_output>"
+    "<|im_end|>"
   ],
-  "bos_token": "<|endoftext|>",
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|endoftext|>",
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",
   "vocab_size": 49152

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c643cfa68475b5fd83971253bac8bf1300ee446cfe3a30cbe50662a58c71c90
+oid sha256:198d4843d34474839bd69fa920dc3c2e3ebdcc74489ba9051a08a7bf8b29261e
 size 5304