ManthanKulakarni/Tiny_llama_sql_v1

README.md

@@ -1,7 +1,9 @@
 ---
 license: apache-2.0
-base_model: tiiuae/falcon-rw-1b
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
+- trl
+- sft
 - generated_from_trainer
 model-index:
 - name: working
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # working
 
-This model is a fine-tuned version of [tiiuae/falcon-rw-1b](https://huggingface.co/tiiuae/falcon-rw-1b) on the None dataset.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
 
 ## Model description
 
@@ -33,11 +35,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 30
-- eval_batch_size: 30
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 120
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
@@ -51,5 +53,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.36.0
 - Pytorch 2.0.0
-- Datasets 2.1.0
+- Datasets 2.16.1
 - Tokenizers 0.15.0

config.json

@@ -1,35 +1,28 @@
 {
-  "_name_or_path": "tiiuae/falcon-rw-1b",
-  "alibi": true,
-  "apply_residual_connection_post_layernorm": false,
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "architectures": [
-    "FalconForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
-    "AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
-    "AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
-    "AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
-    "AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
-    "AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
-  },
-  "bias": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "hidden_dropout": 0.0,
+  "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "falcon",
-  "multi_query": false,
-  "new_decoder_architecture": false,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 24,
-  "num_kv_heads": 32,
-  "parallel_attn": false,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.0",
   "use_cache": false,
-  "vocab_size": 50304
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
   "transformers_version": "4.36.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7699a3ed8683fef29c48b38d918faf22191d08a26cea3b9f890322eabbb56ef4
-size 2623284688
+oid sha256:a037d81d18d893faf2ea1b990431621cf40879d72f522d3a153ebec4c7c933f7
+size 2200119864

runs/Jan04_09-14-05_a664a7572be8/events.out.tfevents.1704359672.a664a7572be8.284.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee1dce7c82cf65a0a59afde505a6616ecbeeee8509d3f662d16c0f4993ca9d1
+size 4403

runs/Jan04_09-19-52_a664a7572be8/events.out.tfevents.1704360003.a664a7572be8.284.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937df079b14065dfc1a09b64d13afe7c6fdb01b4ef9900c69c65fc932e753c83
+size 4184

runs/Jan04_09-22-10_a664a7572be8/events.out.tfevents.1704360130.a664a7572be8.474.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0a41f1650d18739042783b5ad9cde59c6b31c7eaae390ad9f293898d5674e8
+size 4402

runs/Jan04_09-23-18_a664a7572be8/events.out.tfevents.1704360198.a664a7572be8.537.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:768099f980eef86d0433af4877d21d02935ed2794d9615c19a002adf19b637d1
+size 4402

runs/Jan04_09-24-20_a664a7572be8/events.out.tfevents.1704360260.a664a7572be8.589.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6ef6da67a0fabe965cc91dd936be6010747b9daeefd5e97ff59ad0262829f7
+size 4402

runs/Jan04_09-25-19_a664a7572be8/events.out.tfevents.1704360320.a664a7572be8.648.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:095592a9961e4ca58d836604baeeefbbe511abc19462c750b1c57f178d825ef2
+size 4402

runs/Jan04_09-29-10_a664a7572be8/events.out.tfevents.1704360551.a664a7572be8.715.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6899e6f51b5d78e89c00cc87c12cea4fe08a861d64e36da9e3dbbcb2efc549d4
+size 4402

runs/Jan04_09-41-42_a664a7572be8/events.out.tfevents.1704361303.a664a7572be8.782.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4d4be74de9bdf749c24aff6a49de5312b8daaf208f5d0c3ff96c52433f9892
+size 11963

special_tokens_map.json

@@ -1,6 +1,24 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,8 +1,25 @@
 {
-  "add_prefix_space": false,
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "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,
@@ -10,12 +27,17 @@
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 1024,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPT2Tokenizer",
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
   "torch_dtype": "auto",
-  "unk_token": "<|endoftext|>"
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6107fe494cce67604f477c6e3ddb0c7eef565a136c71951dc32799619dd52a
+oid sha256:c059259d701efc7a4cf05c2b359676323f5dfa13c6e55b071978ad930a342957
 size 4283