hyoo14/DNABERT2_AMR_2

README.md

@@ -1,8 +1,7 @@
 ---
-library_name: peft
+base_model: zhihan1996/DNABERT-2-117M
 tags:
 - generated_from_trainer
-base_model: hyoo14/TAPT_NT-0.5b_epoch2
 model-index:
 - name: content
   results: []
@@ -13,10 +12,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # content
 
-This model is a fine-tuned version of [hyoo14/TAPT_NT-0.5b_epoch2](https://huggingface.co/hyoo14/TAPT_NT-0.5b_epoch2) on the None dataset.
+This model is a fine-tuned version of [zhihan1996/DNABERT-2-117M](https://huggingface.co/zhihan1996/DNABERT-2-117M) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0274
-- F1 Macro: 0.4602
+- Loss: 1.2180
+- F1 Macro: 0.3388
 
 ## Model description
 
@@ -47,22 +46,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | F1 Macro |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 1.6008        | 0.2703 | 100  | 1.6101          | 0.0814   |
-| 1.5715        | 0.5405 | 200  | 1.3419          | 0.0814   |
-| 1.244         | 0.8108 | 300  | 1.3716          | 0.2625   |
-| 1.1669        | 1.0811 | 400  | 1.3375          | 0.1271   |
-| 1.2026        | 1.3514 | 500  | 1.2672          | 0.2935   |
-| 1.0356        | 1.6216 | 600  | 1.2010          | 0.3436   |
-| 1.0447        | 1.8919 | 700  | 1.1363          | 0.3799   |
-| 0.9538        | 2.1622 | 800  | 1.0896          | 0.5178   |
-| 0.8704        | 2.4324 | 900  | 1.0606          | 0.4418   |
-| 0.8611        | 2.7027 | 1000 | 1.0274          | 0.4602   |
+| 1.4189        | 0.2703 | 100  | 1.5083          | 0.0814   |
+| 1.4284        | 0.5405 | 200  | 1.3513          | 0.1275   |
+| 1.2829        | 0.8108 | 300  | 1.3179          | 0.1390   |
+| 1.2192        | 1.0811 | 400  | 1.3522          | 0.2334   |
+| 1.3097        | 1.3514 | 500  | 1.2843          | 0.2224   |
+| 1.1668        | 1.6216 | 600  | 1.2668          | 0.2025   |
+| 1.1595        | 1.8919 | 700  | 1.2268          | 0.2690   |
+| 1.1336        | 2.1622 | 800  | 1.2596          | 0.2985   |
+| 1.063         | 2.4324 | 900  | 1.2370          | 0.2709   |
+| 1.0497        | 2.7027 | 1000 | 1.2180          | 0.3388   |
 
 
 ### Framework versions
 
-- PEFT 0.11.1
 - Transformers 4.41.0
-- Pytorch 2.3.0+cu121
+- Pytorch 1.13.1+cu117
 - Datasets 2.19.1
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab14e76a41386428528aa77da95e82d4bc06d12f45ec216aaee1863169f64e4
+size 356986064

runs/May22_02-31-20_96a6440dcc05/events.out.tfevents.1716345080.96a6440dcc05.216.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533f1fe4a5266b9cc0d4d21f12355b8f1f50f746d5e2ddcbdc41c0c45d76102b
+size 11241

special_tokens_map.json

@@ -1,6 +1,37 @@
 {
-  "cls_token": "<cls>",
-  "mask_token": "<mask>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "<mask>",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,7 +25,15 @@
       "special": true
     },
     "3": {
-      "content": "<cls>",
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -34,11 +42,11 @@
     }
   },
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<cls>",
-  "eos_token": null,
-  "mask_token": "<mask>",
-  "model_max_length": 1000,
-  "pad_token": "<pad>",
-  "tokenizer_class": "EsmTokenizer",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3977fa17074a262de701dc03e6c8760e263643a27739d2abd6f0489b16424c77
-size 5112
+oid sha256:1c18434cd27cc43c8b484968dec2e4b2d10d0d05cc89f908f0f837c74c24aa33
+size 4667