End of training

README.md

@@ -1,22 +1,21 @@
----
-base_model: google/bigbird-pegasus-large-pubmed
-library_name: peft
-license: apache-2.0
-tags:
-- generated_from_trainer
-model-index:
-- name: qa_by_bird_prompt_tuned
-  results: []
----
+---
+license: apache-2.0
+base_model: Qwen/Qwen2-0.5B-Instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: qa_by_bird_prompt_tuned
+  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. -->
 
 # qa_by_bird_prompt_tuned
 
-This model is a fine-tuned version of [google/bigbird-pegasus-large-pubmed](https://huggingface.co/google/bigbird-pegasus-large-pubmed) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.6933
+- Loss: 10.3352
 
 ## Model description
 
@@ -35,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.002
+- learning_rate: 2e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
@@ -47,15 +46,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.7942        | 1.0   | 1000 | 4.7216          |
-| 4.7344        | 2.0   | 2000 | 4.6949          |
-| 4.7072        | 3.0   | 3000 | 4.6933          |
+| 12.2464       | 1.0   | 1000 | 10.9966         |
+| 10.3545       | 2.0   | 2000 | 10.3575         |
+| 10.3276       | 3.0   | 3000 | 10.3352         |
 
 
 ### Framework versions
 
-- PEFT 0.11.1
 - Transformers 4.41.2
-- Pytorch 2.2.2
-- Datasets 2.20.0
-- Tokenizers 0.19.1
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:790b19b1736e3ef9ff7f0657de2510e5cb057e450c870f64e4b2c108aec8724e
+size 989206616

special_tokens_map.json

@@ -1,51 +1,21 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "start",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -1,73 +1,43 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "65": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "66": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "67": {
-      "content": "[MASK]",
-      "lstrip": true,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "105": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "eos_token": "</s>",
-  "mask_token": "[MASK]",
-  "mask_token_sent": null,
-  "model_max_length": 4096,
-  "offset": 0,
-  "pad_token": "<pad>",
-  "sep_token": "[SEP]",
-  "tokenizer_class": "PegasusTokenizer",
-  "unk_token": "<unk>"
-}
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "start",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0e3fc88ef06d618daca83ccb40412ef484e40013ee690efa4968cc0088d4ab8
+oid sha256:c00ec0a0c6af73b726081027bc790c753204fb2f0b2c5b7fe64b4f4bb843a0b3
 size 5112