End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: google/bigbird-pegasus-large-pubmed
+license: mit
+base_model: baidu/ernie-code-560m
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # summarize_by_ernie
 
-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 [baidu/ernie-code-560m](https://huggingface.co/baidu/ernie-code-560m) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.6568
+- Loss: 2.3186
 
 ## Model description
 
@@ -46,16 +46,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.5203        | 1.0   | 989  | 4.7508          |
-| 4.8502        | 2.0   | 1978 | 4.6694          |
-| 4.831         | 3.0   | 2967 | 4.6595          |
-| 4.7621        | 4.0   | 3956 | 4.6578          |
-| 4.7524        | 5.0   | 4945 | 4.6568          |
+| 2.7349        | 1.0   | 989  | 2.3506          |
+| 2.6212        | 2.0   | 1978 | 2.3263          |
+| 2.6071        | 3.0   | 2967 | 2.3200          |
+| 2.5826        | 4.0   | 3956 | 2.3185          |
+| 2.5319        | 5.0   | 4945 | 2.3186          |
 
 
 ### Framework versions
 
 - Transformers 4.41.2
-- Pytorch 2.1.2
-- Datasets 2.19.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
 - Tokenizers 0.19.1

config.json

@@ -1,43 +1,33 @@
 {
-  "_name_or_path": "google/bigbird-pegasus-large-pubmed",
-  "activation_dropout": 0.0,
-  "activation_function": "gelu_new",
+  "_name_or_path": "baidu/ernie-code-560m",
   "architectures": [
-    "BigBirdPegasusForConditionalGeneration"
+    "MT5ForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
-  "attention_type": "block_sparse",
-  "block_size": 64,
-  "bos_token_id": 2,
   "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 16,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 16,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "gradient_checkpointing": false,
-  "init_std": 0.02,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "length_penalty": 0.8,
-  "max_length": 256,
-  "max_position_embeddings": 4096,
-  "model_type": "bigbird_pegasus",
-  "num_beams": 5,
-  "num_hidden_layers": 16,
-  "num_random_blocks": 3,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
   "pad_token_id": 0,
-  "scale_embedding": true,
-  "tokenizer_class": "PegasusTokenizer",
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_bias": false,
   "use_cache": true,
-  "vocab_size": 96103
+  "vocab_size": 250105
 }

generation_config.json

@@ -1,11 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 2,
-  "decoder_start_token_id": 2,
+  "decoder_start_token_id": 0,
   "eos_token_id": 1,
-  "length_penalty": 0.8,
-  "max_length": 256,
-  "num_beams": 5,
   "pad_token_id": 0,
   "transformers_version": "4.41.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca759dccc267b4c18a143e46c50bc58383a87fd0c72f58fa6d209728a18794f7
-size 1154033846
+oid sha256:2d5aec3e5a8b91bdfbbf957ed5f03214e28256b1c90a3e426b90fb02128bde80
+size 1164814896

special_tokens_map.json

@@ -1,50 +1,59 @@
 {
-  "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
-  },
+  "additional_special_tokens": [
+    {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|space|><|space|><|space|><|space|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|space|><|space|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|space|>",
+      "lstrip": false,
+      "normalized": false,
+      "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,
+    "normalized": false,
     "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,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -3,7 +3,7 @@
     "0": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -11,63 +11,77 @@
     "1": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "<s>",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "65": {
-      "content": "[CLS]",
+    "250100": {
+      "content": "\n",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "66": {
-      "content": "[SEP]",
+    "250101": {
+      "content": "\t",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "67": {
-      "content": "[MASK]",
-      "lstrip": true,
-      "normalized": true,
+    "250102": {
+      "content": "<|space|><|space|><|space|><|space|>",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "105": {
-      "content": "<unk>",
+    "250103": {
+      "content": "<|space|><|space|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250104": {
+      "content": "<|space|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
+  "additional_special_tokens": [
+    "\n",
+    "\t",
+    "<|space|><|space|><|space|><|space|>",
+    "<|space|><|space|>",
+    "<|space|>"
+  ],
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
   "eos_token": "</s>",
-  "mask_token": "[MASK]",
-  "mask_token_sent": null,
-  "model_max_length": 4096,
-  "offset": 0,
+  "extra_ids": 0,
+  "max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "sep_token": "[SEP]",
-  "tokenizer_class": "PegasusTokenizer",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aed93b2b6aaa41843d4aad5e6aa9f0fb009a5fa9a246b98bf21ea1d1dcdd6d66
+oid sha256:0807c893036471a1108190fff2c4d7a2652ef9771555b8f0a4921e6e48f9ca78
 size 5240