t30_11k_800aa/pfam

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/esm2_t30_150M_UR50D](https://huggingface.co/facebook/esm2_t30_150M_UR50D) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2655
-- Accuracy: 0.9843
+- Loss: 1.2090
+- Accuracy: 0.7686
 
 ## Model description
 
@@ -45,16 +45,21 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
-- mixed_precision_training: Native AMP
+- num_epochs: 9
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| No log        | 0.9930 | 71   | 0.4742          | 0.9502   |
-| No log        | 2.0    | 143  | 0.3066          | 0.9803   |
-| No log        | 2.9790 | 213  | 0.2655          | 0.9843   |
+| No log        | 0.9966 | 222  | 3.0116          | 0.4560   |
+| No log        | 1.9978 | 445  | 2.3631          | 0.5747   |
+| 2.9792        | 2.9989 | 668  | 1.9594          | 0.6399   |
+| 2.9792        | 4.0    | 891  | 1.6825          | 0.6916   |
+| 1.6634        | 4.9966 | 1113 | 1.4988          | 0.7316   |
+| 1.6634        | 5.9978 | 1336 | 1.3650          | 0.7539   |
+| 1.0252        | 6.9989 | 1559 | 1.2806          | 0.7627   |
+| 1.0252        | 8.0    | 1782 | 1.2271          | 0.7699   |
+| 1.0252        | 8.9697 | 1998 | 1.2090          | 0.7686   |
 
 
 ### Framework versions

config.json

@@ -19,7 +19,58 @@
     "5": "LABEL_5",
     "6": "LABEL_6",
     "7": "LABEL_7",
-    "8": "LABEL_8"
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59"
   },
   "initializer_range": 0.02,
   "intermediate_size": 2560,
@@ -27,13 +78,64 @@
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
     "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
     "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
     "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
     "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
     "LABEL_6": 6,
     "LABEL_7": 7,
-    "LABEL_8": 8
+    "LABEL_8": 8,
+    "LABEL_9": 9
   },
   "layer_norm_eps": 1e-05,
   "mask_token_id": 32,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d878364d614a8f4f87bc617150e9c1968f03853b9cdc9561093c057b3930c94
-size 595267152
+oid sha256:e8985db40a9ca82ccc594b9441b15e5660bcc89869683f9d1965985d1eb21ed4
+size 595397916

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5378b0a3126ec8ace89a01fad8c17c7c70412af3db0f7b1118a5f083a8d6b30d
+oid sha256:54feee1322fa6e630cd3c2c960a3d795736c92312138a9d6a87c9c0d077fe911
 size 5048