End of training

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: amazingvince/zephyr-smol_llama-100m-dpo-full
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: KANLlama_RottenTomatoes
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# KANLlama_RottenTomatoes
+
+This model is a fine-tuned version of [amazingvince/zephyr-smol_llama-100m-dpo-full](https://huggingface.co/amazingvince/zephyr-smol_llama-100m-dpo-full) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5279
+- Accuracy: 0.7467
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.001
+- train_batch_size: 20
+- eval_batch_size: 20
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6626        | 1.0   | 427  | 0.5694          | 0.7139   |
+| 0.4869        | 2.0   | 854  | 0.5279          | 0.7467   |
+| 0.3559        | 3.0   | 1281 | 0.5713          | 0.7486   |
+| 0.2279        | 4.0   | 1708 | 0.7230          | 0.7458   |
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "amazingvince/zephyr-smol_llama-100m-dpo-full",
+  "architectures": [
+    "KanLlamaModelForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "problem_type": "single_label_classification",
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "use_cache": false,
+  "vocab_size": 32128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4950c18e8f9eb9ede14160afd3dfeec5bc62a587b93dcc804767f1bd43d76b
+size 902565584

runs/May22_08-08-22_d52c0318c218/events.out.tfevents.1716365303.d52c0318c218.2209.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:516845c3b2e7d7d51359e6d11a714945cfd74631e32c4d919bdf741a5ee6deb7
+size 7003

runs/May22_08-40-57_d52c0318c218/events.out.tfevents.1716367258.d52c0318c218.2209.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b670de2bb3e67319eb01f3efdc8d84a554b4c9f4449ed7e441413552f34dee6
+size 5118

runs/May22_08-43-57_d52c0318c218/events.out.tfevents.1716367438.d52c0318c218.2209.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3351b4224ca6bf452dbed49fe392255b8d17a806cb35bd37e1c3a2f8459904
+size 7608

runs/May22_08-43-57_d52c0318c218/events.out.tfevents.1716369264.d52c0318c218.2209.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179f6062569f9fc2ed5e65ca4b45cd3c4f439b489c2719da5295f4687b97bdc9
+size 411

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "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>",
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d38519b1695bd83337ae184b66a194a52fce62b70db7e225fdfc086dccdfbbb
+size 5112