bert/1

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: cosmin/falcon-7b-sharded-bf16
+license: apache-2.0
+base_model: bert-base-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -14,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # result
 
-This model is a fine-tuned version of [cosmin/falcon-7b-sharded-bf16](https://huggingface.co/cosmin/falcon-7b-sharded-bf16) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 17.4174
-- F1: 0.0002
+- Loss: nan
+- F1: 0.0
 
 ## Model description
 
@@ -37,25 +38,40 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 2
-- eval_batch_size: 1
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 8
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 500
+- training_steps: 200
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 7.2511        | 1.0   | 110  | 7.6002          | 0.0044 |
-| 6.2664        | 2.0   | 221  | 9.9853          | 0.0044 |
-| 5.991         | 3.0   | 331  | 10.1572         | 0.0044 |
-| 5.0998        | 4.0   | 442  | 14.1727         | 0.0002 |
-| 3.9985        | 4.52  | 500  | 17.4174         | 0.0002 |
+| 9.4948        | 0.18  | 10   | nan             | 0.0063 |
+| 8.5357        | 0.37  | 20   | nan             | 0.0063 |
+| 6.8987        | 0.55  | 30   | nan             | 0.0063 |
+| 7.2876        | 0.73  | 40   | nan             | 0.0063 |
+| 9.1271        | 0.92  | 50   | nan             | 0.0063 |
+| 7.4751        | 1.1   | 60   | nan             | 0.0063 |
+| 6.1447        | 1.28  | 70   | nan             | 0.0063 |
+| 6.9828        | 1.47  | 80   | nan             | 0.0063 |
+| 6.2736        | 1.65  | 90   | nan             | 0.0077 |
+| 7.4104        | 1.83  | 100  | nan             | 0.0018 |
+| 6.3501        | 2.02  | 110  | nan             | 0.0117 |
+| 5.96          | 2.2   | 120  | nan             | 0.0044 |
+| 6.6271        | 2.39  | 130  | nan             | 0.0    |
+| 7.2632        | 2.57  | 140  | nan             | 0.0165 |
+| 6.3784        | 2.75  | 150  | nan             | 0.0    |
+| 8.7582        | 2.94  | 160  | nan             | 0.0055 |
+| 7.293         | 3.12  | 170  | nan             | 0.0    |
+| 7.8164        | 3.3   | 180  | nan             | 0.0    |
+| 6.822         | 3.49  | 190  | nan             | 0.0    |
+| 6.489         | 3.67  | 200  | nan             | 0.0    |
 
 
 ### Framework versions

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bedbe6fcf622e1042064b37c4d2826599df907010b7fd182244ac2dd5e5afd90
+size 430952617

special_tokens_map.json

@@ -1,17 +1,8 @@
 {
-  "additional_special_tokens": [
-    ">>TITLE<<",
-    ">>ABSTRACT<<",
-    ">>INTRODUCTION<<",
-    ">>SUMMARY<<",
-    ">>COMMENT<<",
-    ">>ANSWER<<",
-    ">>QUESTION<<",
-    ">>DOMAIN<<",
-    ">>PREFIX<<",
-    ">>SUFFIX<<",
-    ">>MIDDLE<<"
-  ],
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>"
+  "cls_token": "[CLS]",
+  "eos_token": "eos",
+  "mask_token": "[MASK]",
+  "pad_token": "eos",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,96 +1,39 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": ">>TITLE<<",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": ">>ABSTRACT<<",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": ">>INTRODUCTION<<",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": ">>SUMMARY<<",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": ">>COMMENT<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": ">>ANSWER<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": ">>QUESTION<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": ">>DOMAIN<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "8": {
-      "content": ">>PREFIX<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "9": {
-      "content": ">>SUFFIX<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "10": {
-      "content": ">>MIDDLE<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "11": {
-      "content": "<|endoftext|>",
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -98,21 +41,16 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    ">>TITLE<<",
-    ">>ABSTRACT<<",
-    ">>INTRODUCTION<<",
-    ">>SUMMARY<<",
-    ">>COMMENT<<",
-    ">>ANSWER<<",
-    ">>QUESTION<<",
-    ">>DOMAIN<<",
-    ">>PREFIX<<",
-    ">>SUFFIX<<",
-    ">>MIDDLE<<"
-  ],
+  "additional_special_tokens": [],
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 2048,
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "eos",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2ee11bfe9f06d2318d25fd4cc353863edbfe1a3d9333b87e1f6591b678a2690
-size 4091
+oid sha256:890928b7ea8b6754dab1a31e79a2091e579df17358533180faf1134b55c3d251
+size 4027