Upload 4 files

sonic/config.json

@@ -19,14 +19,31 @@
   ],
   "id2label": {
     "0": "Tails the fox",
-    "1": "Amy rose",
+    "1": "Amy Rose",
     "10": "Shadow the hedgehog",
     "11": "Sally Acorn",
-    "12": "mobian",
-    "13": "Tangle the lemur",
-    "14": "Big the cat",
-    "2": "Rouge the bat",
+    "12": "Tangle the lemur",
+    "13": "mobian",
+    "14": "Cosmo the seedrian",
+    "15": "Big the cat",
+    "16": "Sticks the badger",
+    "17": "Tikal the echidna",
+    "18": "Wave the swallow",
+    "19": "Jet the hawk",
+    "2": "Rogue the bat",
+    "20": "Honey the cat",
+    "21": "Surge the tenrec",
+    "22": "Starline the platypus",
+    "23": "Mighty the armadillo",
+    "24": "Vector the crocodile",
+    "25": "Charmy the bee",
+    "26": "Espio the chameleon",
+    "27": "eggman",
+    "28": "Bunnie Rabbot",
+    "29": "Marine the Raccoon",
     "3": "Whisper the wolf",
+    "30": "Storm the albatross",
+    "31": "Maria Robotnik",
     "4": "Knuckles the echidna",
     "5": "Blaze the cat",
     "6": "Silver the hedgehog",
@@ -37,21 +54,38 @@
   "image_size": 384,
   "initializer_range": 0.02,
   "label2id": {
-    "Amy rose": "1",
-    "Big the cat": "14",
+    "Amy Rose": "1",
+    "Big the cat": "15",
     "Blaze the cat": "5",
+    "Bunnie Rabbot": "28",
+    "Charmy the bee": "25",
+    "Cosmo the seedrian": "14",
     "Cream the rabbit": "7",
+    "Espio the chameleon": "26",
+    "Honey the cat": "20",
+    "Jet the hawk": "19",
     "Knuckles the echidna": "4",
-    "Rouge the bat": "2",
+    "Maria Robotnik": "31",
+    "Marine the Raccoon": "29",
+    "Mighty the armadillo": "23",
+    "Rogue the bat": "2",
     "Sally Acorn": "11",
     "Shadow the hedgehog": "10",
     "Silver the hedgehog": "6",
     "Sonic the hedgehog": "9",
+    "Starline the platypus": "22",
+    "Sticks the badger": "16",
+    "Storm the albatross": "30",
+    "Surge the tenrec": "21",
     "Tails the fox": "0",
-    "Tangle the lemur": "13",
+    "Tangle the lemur": "12",
+    "Tikal the echidna": "17",
     "Vanilla the rabbit": "8",
+    "Vector the crocodile": "24",
+    "Wave the swallow": "18",
     "Whisper the wolf": "3",
-    "mobian": "12"
+    "eggman": "27",
+    "mobian": "13"
   },
   "layer_norm_eps": 1e-12,
   "layer_scale_init_value": 1e-06,

sonic/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4d6897c65fc76cc210003c9552b14442dd4d5786bab4e5b323c52bafa2e877
-size 350446061
+oid sha256:ec5e3d6a60bdf3f519adb879379016d6bd97bb046a8f5a18afaac0cbae52c570
+size 350515757

sonic/trainer_state.json

@@ -1,177 +1,186 @@
 {
-  "best_metric": 0.09438519924879074,
-  "best_model_checkpoint": "./SonicCharacterClassifier\\checkpoint-1400",
-  "epoch": 4.093567251461988,
-  "global_step": 1400,
+  "best_metric": 0.08468733727931976,
+  "best_model_checkpoint": "./SonicCharacterClassifier\\checkpoint-1600",
+  "epoch": 6.042296072507553,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.29,
-      "learning_rate": 4.853801169590643e-05,
-      "loss": 0.3188,
-      "step": 100
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 4.707602339181287e-05,
-      "loss": 0.2087,
+      "epoch": 0.6,
+      "learning_rate": 4.6978851963746225e-05,
+      "loss": 0.2038,
       "step": 200
     },
     {
-      "epoch": 0.58,
-      "eval_accuracy": 0.9407407407407361,
-      "eval_loss": 0.16877754032611847,
-      "eval_precision": 0.6539702845075653,
-      "eval_recall": 0.5742313120602596,
-      "eval_runtime": 161.9664,
-      "eval_samples_per_second": 8.446,
-      "eval_steps_per_second": 1.056,
+      "epoch": 0.6,
+      "eval_accuracy": 0.9509220795568983,
+      "eval_loss": 0.1493668258190155,
+      "eval_precision": 0.4276334957981484,
+      "eval_recall": 0.34057603409646653,
+      "eval_runtime": 245.2223,
+      "eval_samples_per_second": 8.099,
+      "eval_steps_per_second": 1.015,
       "step": 200
     },
     {
-      "epoch": 0.88,
-      "learning_rate": 4.56140350877193e-05,
-      "loss": 0.1663,
-      "step": 300
-    },
-    {
-      "epoch": 1.17,
-      "learning_rate": 4.4152046783625734e-05,
-      "loss": 0.1155,
+      "epoch": 1.21,
+      "learning_rate": 4.395770392749245e-05,
+      "loss": 0.1299,
       "step": 400
     },
     {
-      "epoch": 1.17,
-      "eval_accuracy": 0.9615009746588669,
-      "eval_loss": 0.12015020102262497,
-      "eval_precision": 0.8305708768976313,
-      "eval_recall": 0.7801112001221648,
-      "eval_runtime": 161.8616,
-      "eval_samples_per_second": 8.452,
-      "eval_steps_per_second": 1.056,
+      "epoch": 1.21,
+      "eval_accuracy": 0.9626132930513596,
+      "eval_loss": 0.11390183866024017,
+      "eval_precision": 0.6821628829936983,
+      "eval_recall": 0.6035811496119172,
+      "eval_runtime": 245.5675,
+      "eval_samples_per_second": 8.087,
+      "eval_steps_per_second": 1.014,
       "step": 400
     },
     {
-      "epoch": 1.46,
-      "learning_rate": 4.269005847953216e-05,
-      "loss": 0.095,
-      "step": 500
-    },
-    {
-      "epoch": 1.75,
-      "learning_rate": 4.12280701754386e-05,
-      "loss": 0.0932,
+      "epoch": 1.81,
+      "learning_rate": 4.093655589123867e-05,
+      "loss": 0.0952,
       "step": 600
     },
     {
-      "epoch": 1.75,
-      "eval_accuracy": 0.964278752436644,
-      "eval_loss": 0.1112869530916214,
-      "eval_precision": 0.8358102748453625,
-      "eval_recall": 0.7573138768314205,
-      "eval_runtime": 160.6953,
-      "eval_samples_per_second": 8.513,
-      "eval_steps_per_second": 1.064,
+      "epoch": 1.81,
+      "eval_accuracy": 0.9677901560926485,
+      "eval_loss": 0.10017536580562592,
+      "eval_precision": 0.7746363586620384,
+      "eval_recall": 0.71393109788423,
+      "eval_runtime": 246.2016,
+      "eval_samples_per_second": 8.067,
+      "eval_steps_per_second": 1.011,
       "step": 600
     },
     {
-      "epoch": 2.05,
-      "learning_rate": 3.976608187134503e-05,
-      "loss": 0.087,
-      "step": 700
-    },
-    {
-      "epoch": 2.34,
-      "learning_rate": 3.8304093567251465e-05,
-      "loss": 0.0489,
+      "epoch": 2.42,
+      "learning_rate": 3.79154078549849e-05,
+      "loss": 0.0681,
       "step": 800
     },
     {
-      "epoch": 2.34,
-      "eval_accuracy": 0.9684697855750467,
-      "eval_loss": 0.09839322417974472,
-      "eval_precision": 0.877861029889539,
-      "eval_recall": 0.8274951210258222,
-      "eval_runtime": 160.5107,
-      "eval_samples_per_second": 8.523,
-      "eval_steps_per_second": 1.065,
+      "epoch": 2.42,
+      "eval_accuracy": 0.9708113041289023,
+      "eval_loss": 0.09041494876146317,
+      "eval_precision": 0.8065139068160218,
+      "eval_recall": 0.7231326368063123,
+      "eval_runtime": 245.4942,
+      "eval_samples_per_second": 8.09,
+      "eval_steps_per_second": 1.014,
       "step": 800
     },
     {
-      "epoch": 2.63,
-      "learning_rate": 3.6842105263157895e-05,
-      "loss": 0.0506,
-      "step": 900
-    },
-    {
-      "epoch": 2.92,
-      "learning_rate": 3.538011695906433e-05,
-      "loss": 0.0503,
+      "epoch": 3.02,
+      "learning_rate": 3.489425981873112e-05,
+      "loss": 0.0608,
       "step": 1000
     },
     {
-      "epoch": 2.92,
-      "eval_accuracy": 0.9692495126705621,
-      "eval_loss": 0.09646110981702805,
-      "eval_precision": 0.8755529497305813,
-      "eval_recall": 0.8374415545468176,
-      "eval_runtime": 161.798,
-      "eval_samples_per_second": 8.455,
-      "eval_steps_per_second": 1.057,
+      "epoch": 3.02,
+      "eval_accuracy": 0.972904078549849,
+      "eval_loss": 0.08679082244634628,
+      "eval_precision": 0.8209949551458537,
+      "eval_recall": 0.7289373926706963,
+      "eval_runtime": 244.3239,
+      "eval_samples_per_second": 8.129,
+      "eval_steps_per_second": 1.019,
       "step": 1000
     },
     {
-      "epoch": 3.22,
-      "learning_rate": 3.391812865497076e-05,
-      "loss": 0.0297,
-      "step": 1100
-    },
-    {
-      "epoch": 3.51,
-      "learning_rate": 3.24561403508772e-05,
-      "loss": 0.0245,
+      "epoch": 3.63,
+      "learning_rate": 3.187311178247734e-05,
+      "loss": 0.0393,
       "step": 1200
     },
     {
-      "epoch": 3.51,
-      "eval_accuracy": 0.9697855750487306,
-      "eval_loss": 0.09691683202981949,
-      "eval_precision": 0.8796307635671673,
-      "eval_recall": 0.8392919296428067,
-      "eval_runtime": 163.6772,
-      "eval_samples_per_second": 8.358,
-      "eval_steps_per_second": 1.045,
+      "epoch": 3.63,
+      "eval_accuracy": 0.9730771651560927,
+      "eval_loss": 0.08753738552331924,
+      "eval_precision": 0.8360383490292852,
+      "eval_recall": 0.7486598211097333,
+      "eval_runtime": 248.2529,
+      "eval_samples_per_second": 8.0,
+      "eval_steps_per_second": 1.003,
       "step": 1200
     },
     {
-      "epoch": 3.8,
-      "learning_rate": 3.0994152046783626e-05,
-      "loss": 0.026,
-      "step": 1300
+      "epoch": 4.23,
+      "learning_rate": 2.8851963746223565e-05,
+      "loss": 0.0347,
+      "step": 1400
     },
     {
-      "epoch": 4.09,
-      "learning_rate": 2.9532163742690062e-05,
-      "loss": 0.0231,
+      "epoch": 4.23,
+      "eval_accuracy": 0.9733761329305136,
+      "eval_loss": 0.08492986112833023,
+      "eval_precision": 0.8388275873170129,
+      "eval_recall": 0.7801557843198007,
+      "eval_runtime": 248.4693,
+      "eval_samples_per_second": 7.993,
+      "eval_steps_per_second": 1.002,
       "step": 1400
     },
     {
-      "epoch": 4.09,
-      "eval_accuracy": 0.9713937621832336,
-      "eval_loss": 0.09438519924879074,
-      "eval_precision": 0.8850769600769599,
-      "eval_recall": 0.8511938435184049,
-      "eval_runtime": 161.9688,
-      "eval_samples_per_second": 8.446,
-      "eval_steps_per_second": 1.056,
-      "step": 1400
+      "epoch": 4.83,
+      "learning_rate": 2.583081570996979e-05,
+      "loss": 0.0256,
+      "step": 1600
+    },
+    {
+      "epoch": 4.83,
+      "eval_accuracy": 0.9739583333333334,
+      "eval_loss": 0.08468733727931976,
+      "eval_precision": 0.8475558611132625,
+      "eval_recall": 0.788949676665331,
+      "eval_runtime": 248.7261,
+      "eval_samples_per_second": 7.985,
+      "eval_steps_per_second": 1.001,
+      "step": 1600
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 2.2809667673716012e-05,
+      "loss": 0.0191,
+      "step": 1800
+    },
+    {
+      "epoch": 5.44,
+      "eval_accuracy": 0.9742573011077543,
+      "eval_loss": 0.0882001668214798,
+      "eval_precision": 0.845859505500522,
+      "eval_recall": 0.7649921950675245,
+      "eval_runtime": 251.833,
+      "eval_samples_per_second": 7.886,
+      "eval_steps_per_second": 0.989,
+      "step": 1800
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 1.9788519637462235e-05,
+      "loss": 0.0154,
+      "step": 2000
+    },
+    {
+      "epoch": 6.04,
+      "eval_accuracy": 0.9743674471299094,
+      "eval_loss": 0.08864131569862366,
+      "eval_precision": 0.8535254440088273,
+      "eval_recall": 0.7735381205368478,
+      "eval_runtime": 245.1302,
+      "eval_samples_per_second": 8.102,
+      "eval_steps_per_second": 1.016,
+      "step": 2000
     }
   ],
-  "max_steps": 3420,
+  "max_steps": 3310,
   "num_train_epochs": 10,
-  "total_flos": 5.207113357118669e+18,
+  "total_flos": 1.1154739870524506e+19,
   "trial_name": null,
   "trial_params": null
 }