Upload folder using huggingface_hub (#3)

- Upload folder using huggingface_hub (356119ac517c43beff1bef494a9aacb555c2b901)

config.json

@@ -10,26 +10,32 @@
   "hidden_size": 768,
   "id2label": {
     "0": "acne",
-    "1": "eczema",
-    "2": "herpes zoster",
-    "3": "hives",
-    "4": "lupus",
-    "5": "raynauds",
-    "6": "tinea",
-    "7": "vitiligo"
+    "1": "basal cell carcinoma",
+    "10": "warts",
+    "2": "cold sores",
+    "3": "eczema",
+    "4": "herpes zoster",
+    "5": "hives",
+    "6": "lupus",
+    "7": "raynauds",
+    "8": "tinea",
+    "9": "vitiligo"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
     "acne": "0",
-    "eczema": "1",
-    "herpes zoster": "2",
-    "hives": "3",
-    "lupus": "4",
-    "raynauds": "5",
-    "tinea": "6",
-    "vitiligo": "7"
+    "basal cell carcinoma": "1",
+    "cold sores": "2",
+    "eczema": "3",
+    "herpes zoster": "4",
+    "hives": "5",
+    "lupus": "6",
+    "raynauds": "7",
+    "tinea": "8",
+    "vitiligo": "9",
+    "warts": "10"
   },
   "layer_norm_eps": 1e-12,
   "model_type": "vit",

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d7d5a0593632d032bf998c7032b0c4b7d8b22ca808daf7429da3ef1a9f76c60
+size 686623749

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92df0ed344bb275826e9a28655a22f187b8af79649ce7be3dea7b52c180f14b0
-size 343287149
+oid sha256:f15383b73502c9ed0702239e4f5552fc9b0bdda736768051b04f88be2fc759cb
+size 343296365

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff66960b7e151d2f0ae14c182480b41f103b9a07efe4372c285b23d6c3f12d0
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42da4ab01bfe87a79f57df6272749bf20e2faf078b6c5acc4dba36ec4df83062
+size 627

trainer_state.json

@@ -1,460 +1,400 @@
 {
-  "best_metric": 1.2660315036773682,
-  "best_model_checkpoint": "./vit-base-beans/checkpoint-100",
-  "epoch": 5.0,
-  "global_step": 290,
+  "best_metric": 0.619316577911377,
+  "best_model_checkpoint": "./vit-base-beans/checkpoint-400",
+  "epoch": 3.883495145631068,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.17,
-      "learning_rate": 0.0001931034482758621,
-      "loss": 1.7999,
+      "epoch": 0.1,
+      "learning_rate": 0.00019805825242718447,
+      "loss": 2.2781,
       "step": 10
     },
     {
-      "epoch": 0.17,
-      "eval_accuracy": 0.25555555555555554,
-      "eval_loss": 1.9382611513137817,
-      "eval_runtime": 128.8894,
-      "eval_samples_per_second": 2.095,
-      "eval_steps_per_second": 0.264,
-      "step": 10
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 0.00018620689655172415,
-      "loss": 1.5424,
-      "step": 20
-    },
-    {
-      "epoch": 0.34,
-      "eval_accuracy": 0.4148148148148148,
-      "eval_loss": 1.5738633871078491,
-      "eval_runtime": 7.0871,
-      "eval_samples_per_second": 38.097,
-      "eval_steps_per_second": 4.797,
+      "epoch": 0.19,
+      "learning_rate": 0.00019611650485436895,
+      "loss": 2.0539,
       "step": 20
     },
     {
-      "epoch": 0.52,
-      "learning_rate": 0.0001793103448275862,
-      "loss": 1.257,
-      "step": 30
+      "epoch": 0.24,
+      "eval_accuracy": 0.6347826086956522,
+      "eval_loss": 1.684175968170166,
+      "eval_runtime": 199.797,
+      "eval_samples_per_second": 2.302,
+      "eval_steps_per_second": 0.29,
+      "step": 25
     },
     {
-      "epoch": 0.52,
-      "eval_accuracy": 0.5777777777777777,
-      "eval_loss": 1.3710002899169922,
-      "eval_runtime": 8.6728,
-      "eval_samples_per_second": 31.132,
-      "eval_steps_per_second": 3.92,
+      "epoch": 0.29,
+      "learning_rate": 0.0001941747572815534,
+      "loss": 1.7246,
       "step": 30
     },
     {
-      "epoch": 0.69,
-      "learning_rate": 0.00017241379310344826,
-      "loss": 1.0721,
-      "step": 40
-    },
-    {
-      "epoch": 0.69,
-      "eval_accuracy": 0.5074074074074074,
-      "eval_loss": 1.4735559225082397,
-      "eval_runtime": 7.1381,
-      "eval_samples_per_second": 37.825,
-      "eval_steps_per_second": 4.763,
+      "epoch": 0.39,
+      "learning_rate": 0.00019223300970873787,
+      "loss": 1.6027,
       "step": 40
     },
     {
-      "epoch": 0.86,
-      "learning_rate": 0.00016551724137931035,
-      "loss": 1.1026,
+      "epoch": 0.49,
+      "learning_rate": 0.00019029126213592236,
+      "loss": 1.4159,
       "step": 50
     },
     {
-      "epoch": 0.86,
-      "eval_accuracy": 0.6370370370370371,
-      "eval_loss": 1.2928471565246582,
-      "eval_runtime": 8.3556,
-      "eval_samples_per_second": 32.314,
-      "eval_steps_per_second": 4.069,
+      "epoch": 0.49,
+      "eval_accuracy": 0.6934782608695652,
+      "eval_loss": 1.2154264450073242,
+      "eval_runtime": 14.461,
+      "eval_samples_per_second": 31.81,
+      "eval_steps_per_second": 4.011,
       "step": 50
     },
     {
-      "epoch": 1.03,
-      "learning_rate": 0.00015862068965517243,
-      "loss": 0.9359,
-      "step": 60
-    },
-    {
-      "epoch": 1.03,
-      "eval_accuracy": 0.6074074074074074,
-      "eval_loss": 1.2788481712341309,
-      "eval_runtime": 7.1042,
-      "eval_samples_per_second": 38.006,
-      "eval_steps_per_second": 4.786,
+      "epoch": 0.58,
+      "learning_rate": 0.00018834951456310681,
+      "loss": 1.243,
       "step": 60
     },
     {
-      "epoch": 1.21,
-      "learning_rate": 0.00015172413793103449,
-      "loss": 0.7,
-      "step": 70
-    },
-    {
-      "epoch": 1.21,
-      "eval_accuracy": 0.6592592592592592,
-      "eval_loss": 1.2249455451965332,
-      "eval_runtime": 7.5614,
-      "eval_samples_per_second": 35.708,
-      "eval_steps_per_second": 4.497,
+      "epoch": 0.68,
+      "learning_rate": 0.00018640776699029127,
+      "loss": 1.2138,
       "step": 70
     },
     {
-      "epoch": 1.38,
-      "learning_rate": 0.00014482758620689657,
-      "loss": 0.5367,
-      "step": 80
+      "epoch": 0.73,
+      "eval_accuracy": 0.741304347826087,
+      "eval_loss": 1.0337247848510742,
+      "eval_runtime": 14.5332,
+      "eval_samples_per_second": 31.652,
+      "eval_steps_per_second": 3.991,
+      "step": 75
     },
     {
-      "epoch": 1.38,
-      "eval_accuracy": 0.6222222222222222,
-      "eval_loss": 1.3300864696502686,
-      "eval_runtime": 7.852,
-      "eval_samples_per_second": 34.386,
-      "eval_steps_per_second": 4.33,
+      "epoch": 0.78,
+      "learning_rate": 0.00018446601941747576,
+      "loss": 1.096,
       "step": 80
     },
     {
-      "epoch": 1.55,
-      "learning_rate": 0.00013793103448275863,
-      "loss": 0.6017,
-      "step": 90
-    },
-    {
-      "epoch": 1.55,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_loss": 1.2042837142944336,
-      "eval_runtime": 8.2241,
-      "eval_samples_per_second": 32.83,
-      "eval_steps_per_second": 4.134,
+      "epoch": 0.87,
+      "learning_rate": 0.00018252427184466022,
+      "loss": 1.012,
       "step": 90
     },
     {
-      "epoch": 1.72,
-      "learning_rate": 0.00013103448275862068,
-      "loss": 0.6007,
+      "epoch": 0.97,
+      "learning_rate": 0.00018058252427184467,
+      "loss": 0.8889,
       "step": 100
     },
     {
-      "epoch": 1.72,
-      "eval_accuracy": 0.6703703703703704,
-      "eval_loss": 1.2660315036773682,
-      "eval_runtime": 8.6405,
-      "eval_samples_per_second": 31.248,
-      "eval_steps_per_second": 3.935,
+      "epoch": 0.97,
+      "eval_accuracy": 0.7652173913043478,
+      "eval_loss": 0.845034122467041,
+      "eval_runtime": 14.4751,
+      "eval_samples_per_second": 31.779,
+      "eval_steps_per_second": 4.007,
       "step": 100
     },
     {
-      "epoch": 1.9,
-      "learning_rate": 0.00012413793103448277,
-      "loss": 0.6083,
+      "epoch": 1.07,
+      "learning_rate": 0.00017864077669902913,
+      "loss": 0.7514,
       "step": 110
     },
     {
-      "epoch": 1.9,
-      "eval_accuracy": 0.6851851851851852,
-      "eval_loss": 1.2744337320327759,
-      "eval_runtime": 8.1117,
-      "eval_samples_per_second": 33.285,
-      "eval_steps_per_second": 4.191,
-      "step": 110
-    },
-    {
-      "epoch": 2.07,
-      "learning_rate": 0.00011724137931034482,
-      "loss": 0.4428,
-      "step": 120
-    },
-    {
-      "epoch": 2.07,
-      "eval_accuracy": 0.6481481481481481,
-      "eval_loss": 1.3982332944869995,
-      "eval_runtime": 9.593,
-      "eval_samples_per_second": 28.145,
-      "eval_steps_per_second": 3.544,
+      "epoch": 1.17,
+      "learning_rate": 0.00017669902912621362,
+      "loss": 0.7239,
       "step": 120
     },
     {
-      "epoch": 2.24,
-      "learning_rate": 0.0001103448275862069,
-      "loss": 0.3967,
-      "step": 130
+      "epoch": 1.21,
+      "eval_accuracy": 0.6869565217391305,
+      "eval_loss": 1.0301238298416138,
+      "eval_runtime": 13.8604,
+      "eval_samples_per_second": 33.188,
+      "eval_steps_per_second": 4.185,
+      "step": 125
     },
     {
-      "epoch": 2.24,
-      "eval_accuracy": 0.6851851851851852,
-      "eval_loss": 1.2987446784973145,
-      "eval_runtime": 7.0774,
-      "eval_samples_per_second": 38.15,
-      "eval_steps_per_second": 4.804,
+      "epoch": 1.26,
+      "learning_rate": 0.00017475728155339805,
+      "loss": 0.6558,
       "step": 130
     },
     {
-      "epoch": 2.41,
-      "learning_rate": 0.00010344827586206898,
-      "loss": 0.3308,
-      "step": 140
-    },
-    {
-      "epoch": 2.41,
-      "eval_accuracy": 0.7,
-      "eval_loss": 1.3469077348709106,
-      "eval_runtime": 7.0247,
-      "eval_samples_per_second": 38.436,
-      "eval_steps_per_second": 4.84,
+      "epoch": 1.36,
+      "learning_rate": 0.00017281553398058253,
+      "loss": 0.6192,
       "step": 140
     },
     {
-      "epoch": 2.59,
-      "learning_rate": 9.655172413793105e-05,
-      "loss": 0.2844,
+      "epoch": 1.46,
+      "learning_rate": 0.000170873786407767,
+      "loss": 0.6241,
       "step": 150
     },
     {
-      "epoch": 2.59,
-      "eval_accuracy": 0.6962962962962963,
-      "eval_loss": 1.2884557247161865,
-      "eval_runtime": 9.6127,
-      "eval_samples_per_second": 28.088,
-      "eval_steps_per_second": 3.537,
+      "epoch": 1.46,
+      "eval_accuracy": 0.7869565217391304,
+      "eval_loss": 0.7646523118019104,
+      "eval_runtime": 13.9259,
+      "eval_samples_per_second": 33.032,
+      "eval_steps_per_second": 4.165,
       "step": 150
     },
     {
-      "epoch": 2.76,
-      "learning_rate": 8.96551724137931e-05,
-      "loss": 0.2313,
-      "step": 160
-    },
-    {
-      "epoch": 2.76,
-      "eval_accuracy": 0.6851851851851852,
-      "eval_loss": 1.4098496437072754,
-      "eval_runtime": 8.6491,
-      "eval_samples_per_second": 31.217,
-      "eval_steps_per_second": 3.931,
+      "epoch": 1.55,
+      "learning_rate": 0.00016893203883495145,
+      "loss": 0.6511,
       "step": 160
     },
     {
-      "epoch": 2.93,
-      "learning_rate": 8.275862068965517e-05,
-      "loss": 0.2378,
-      "step": 170
-    },
-    {
-      "epoch": 2.93,
-      "eval_accuracy": 0.6851851851851852,
-      "eval_loss": 1.4552189111709595,
-      "eval_runtime": 8.3406,
-      "eval_samples_per_second": 32.372,
-      "eval_steps_per_second": 4.076,
+      "epoch": 1.65,
+      "learning_rate": 0.00016699029126213594,
+      "loss": 0.7607,
       "step": 170
     },
     {
-      "epoch": 3.1,
-      "learning_rate": 7.586206896551724e-05,
-      "loss": 0.1724,
-      "step": 180
+      "epoch": 1.7,
+      "eval_accuracy": 0.7956521739130434,
+      "eval_loss": 0.7208316922187805,
+      "eval_runtime": 15.3767,
+      "eval_samples_per_second": 29.915,
+      "eval_steps_per_second": 3.772,
+      "step": 175
     },
     {
-      "epoch": 3.1,
-      "eval_accuracy": 0.6851851851851852,
-      "eval_loss": 1.3009414672851562,
-      "eval_runtime": 7.8433,
-      "eval_samples_per_second": 34.424,
-      "eval_steps_per_second": 4.335,
+      "epoch": 1.75,
+      "learning_rate": 0.0001650485436893204,
+      "loss": 0.6508,
       "step": 180
     },
     {
-      "epoch": 3.28,
-      "learning_rate": 6.896551724137931e-05,
-      "loss": 0.1712,
-      "step": 190
-    },
-    {
-      "epoch": 3.28,
-      "eval_accuracy": 0.6888888888888889,
-      "eval_loss": 1.3433070182800293,
-      "eval_runtime": 7.412,
-      "eval_samples_per_second": 36.427,
-      "eval_steps_per_second": 4.587,
+      "epoch": 1.84,
+      "learning_rate": 0.00016310679611650485,
+      "loss": 0.5474,
       "step": 190
     },
     {
-      "epoch": 3.45,
-      "learning_rate": 6.206896551724138e-05,
-      "loss": 0.1521,
+      "epoch": 1.94,
+      "learning_rate": 0.0001611650485436893,
+      "loss": 0.5841,
       "step": 200
     },
     {
-      "epoch": 3.45,
-      "eval_accuracy": 0.6888888888888889,
-      "eval_loss": 1.4084450006484985,
-      "eval_runtime": 7.1569,
-      "eval_samples_per_second": 37.726,
-      "eval_steps_per_second": 4.751,
+      "epoch": 1.94,
+      "eval_accuracy": 0.7913043478260869,
+      "eval_loss": 0.6974421143531799,
+      "eval_runtime": 13.8536,
+      "eval_samples_per_second": 33.204,
+      "eval_steps_per_second": 4.187,
       "step": 200
     },
     {
-      "epoch": 3.62,
-      "learning_rate": 5.517241379310345e-05,
-      "loss": 0.1178,
+      "epoch": 2.04,
+      "learning_rate": 0.0001592233009708738,
+      "loss": 0.5992,
       "step": 210
     },
     {
-      "epoch": 3.62,
-      "eval_accuracy": 0.6925925925925925,
-      "eval_loss": 1.4383904933929443,
-      "eval_runtime": 15.5468,
-      "eval_samples_per_second": 17.367,
-      "eval_steps_per_second": 2.187,
-      "step": 210
-    },
-    {
-      "epoch": 3.79,
-      "learning_rate": 4.827586206896552e-05,
-      "loss": 0.0968,
-      "step": 220
-    },
-    {
-      "epoch": 3.79,
-      "eval_accuracy": 0.6888888888888889,
-      "eval_loss": 1.44044029712677,
-      "eval_runtime": 8.8794,
-      "eval_samples_per_second": 30.407,
-      "eval_steps_per_second": 3.829,
+      "epoch": 2.14,
+      "learning_rate": 0.00015728155339805825,
+      "loss": 0.3827,
       "step": 220
     },
     {
-      "epoch": 3.97,
-      "learning_rate": 4.1379310344827587e-05,
-      "loss": 0.1471,
-      "step": 230
+      "epoch": 2.18,
+      "eval_accuracy": 0.7869565217391304,
+      "eval_loss": 0.6890577077865601,
+      "eval_runtime": 14.5884,
+      "eval_samples_per_second": 31.532,
+      "eval_steps_per_second": 3.976,
+      "step": 225
     },
     {
-      "epoch": 3.97,
-      "eval_accuracy": 0.6888888888888889,
-      "eval_loss": 1.4447485208511353,
-      "eval_runtime": 9.2898,
-      "eval_samples_per_second": 29.064,
-      "eval_steps_per_second": 3.66,
+      "epoch": 2.23,
+      "learning_rate": 0.0001553398058252427,
+      "loss": 0.4169,
       "step": 230
     },
     {
-      "epoch": 4.14,
-      "learning_rate": 3.4482758620689657e-05,
-      "loss": 0.1114,
-      "step": 240
-    },
-    {
-      "epoch": 4.14,
-      "eval_accuracy": 0.6888888888888889,
-      "eval_loss": 1.4719408750534058,
-      "eval_runtime": 12.6934,
-      "eval_samples_per_second": 21.271,
-      "eval_steps_per_second": 2.679,
+      "epoch": 2.33,
+      "learning_rate": 0.0001533980582524272,
+      "loss": 0.3825,
       "step": 240
     },
     {
-      "epoch": 4.31,
-      "learning_rate": 2.7586206896551727e-05,
-      "loss": 0.0967,
+      "epoch": 2.43,
+      "learning_rate": 0.00015145631067961166,
+      "loss": 0.3534,
       "step": 250
     },
     {
-      "epoch": 4.31,
-      "eval_accuracy": 0.6925925925925925,
-      "eval_loss": 1.4684562683105469,
-      "eval_runtime": 7.9455,
-      "eval_samples_per_second": 33.982,
-      "eval_steps_per_second": 4.279,
+      "epoch": 2.43,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.6881299614906311,
+      "eval_runtime": 14.5452,
+      "eval_samples_per_second": 31.626,
+      "eval_steps_per_second": 3.988,
       "step": 250
     },
     {
-      "epoch": 4.48,
-      "learning_rate": 2.0689655172413793e-05,
-      "loss": 0.0974,
-      "step": 260
-    },
-    {
-      "epoch": 4.48,
-      "eval_accuracy": 0.6925925925925925,
-      "eval_loss": 1.473760962486267,
-      "eval_runtime": 8.2858,
-      "eval_samples_per_second": 32.586,
-      "eval_steps_per_second": 4.103,
+      "epoch": 2.52,
+      "learning_rate": 0.00014951456310679611,
+      "loss": 0.2475,
       "step": 260
     },
     {
-      "epoch": 4.66,
-      "learning_rate": 1.3793103448275863e-05,
-      "loss": 0.0647,
+      "epoch": 2.62,
+      "learning_rate": 0.0001475728155339806,
+      "loss": 0.438,
       "step": 270
     },
     {
-      "epoch": 4.66,
-      "eval_accuracy": 0.6925925925925925,
-      "eval_loss": 1.4769530296325684,
-      "eval_runtime": 7.728,
-      "eval_samples_per_second": 34.938,
-      "eval_steps_per_second": 4.4,
-      "step": 270
+      "epoch": 2.67,
+      "eval_accuracy": 0.7869565217391304,
+      "eval_loss": 0.794903039932251,
+      "eval_runtime": 14.6276,
+      "eval_samples_per_second": 31.447,
+      "eval_steps_per_second": 3.965,
+      "step": 275
     },
     {
-      "epoch": 4.83,
-      "learning_rate": 6.896551724137932e-06,
-      "loss": 0.0899,
+      "epoch": 2.72,
+      "learning_rate": 0.00014563106796116506,
+      "loss": 0.3039,
       "step": 280
     },
     {
-      "epoch": 4.83,
-      "eval_accuracy": 0.6925925925925925,
-      "eval_loss": 1.4792803525924683,
-      "eval_runtime": 7.3284,
-      "eval_samples_per_second": 36.843,
-      "eval_steps_per_second": 4.64,
-      "step": 280
+      "epoch": 2.82,
+      "learning_rate": 0.00014368932038834952,
+      "loss": 0.2605,
+      "step": 290
     },
     {
-      "epoch": 5.0,
-      "learning_rate": 0.0,
-      "loss": 0.0763,
-      "step": 290
+      "epoch": 2.91,
+      "learning_rate": 0.000141747572815534,
+      "loss": 0.4453,
+      "step": 300
     },
     {
-      "epoch": 5.0,
-      "eval_accuracy": 0.6925925925925925,
-      "eval_loss": 1.4800288677215576,
-      "eval_runtime": 7.1527,
-      "eval_samples_per_second": 37.748,
-      "eval_steps_per_second": 4.753,
-      "step": 290
+      "epoch": 2.91,
+      "eval_accuracy": 0.7804347826086957,
+      "eval_loss": 0.7851635217666626,
+      "eval_runtime": 14.6262,
+      "eval_samples_per_second": 31.45,
+      "eval_steps_per_second": 3.965,
+      "step": 300
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.00013980582524271846,
+      "loss": 0.3196,
+      "step": 310
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 0.00013786407766990292,
+      "loss": 0.1714,
+      "step": 320
+    },
+    {
+      "epoch": 3.16,
+      "eval_accuracy": 0.7956521739130434,
+      "eval_loss": 0.7182856798171997,
+      "eval_runtime": 16.1817,
+      "eval_samples_per_second": 28.427,
+      "eval_steps_per_second": 3.584,
+      "step": 325
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 0.0001359223300970874,
+      "loss": 0.1467,
+      "step": 330
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 0.00013398058252427186,
+      "loss": 0.1825,
+      "step": 340
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 0.00013203883495145632,
+      "loss": 0.1664,
+      "step": 350
+    },
+    {
+      "epoch": 3.4,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.6710854172706604,
+      "eval_runtime": 14.7551,
+      "eval_samples_per_second": 31.176,
+      "eval_steps_per_second": 3.931,
+      "step": 350
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.00013009708737864078,
+      "loss": 0.1266,
+      "step": 360
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 0.00012815533980582526,
+      "loss": 0.1962,
+      "step": 370
+    },
+    {
+      "epoch": 3.64,
+      "eval_accuracy": 0.8043478260869565,
+      "eval_loss": 0.7439975738525391,
+      "eval_runtime": 14.5665,
+      "eval_samples_per_second": 31.579,
+      "eval_steps_per_second": 3.982,
+      "step": 375
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 0.00012621359223300972,
+      "loss": 0.1609,
+      "step": 380
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 0.00012427184466019418,
+      "loss": 0.1891,
+      "step": 390
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 0.00012233009708737864,
+      "loss": 0.1961,
+      "step": 400
     },
     {
-      "epoch": 5.0,
-      "step": 290,
-      "total_flos": 3.545449175052288e+17,
-      "train_loss": 0.48534091012231234,
-      "train_runtime": 1027.0889,
-      "train_samples_per_second": 4.454,
-      "train_steps_per_second": 0.282
+      "epoch": 3.88,
+      "eval_accuracy": 0.8391304347826087,
+      "eval_loss": 0.619316577911377,
+      "eval_runtime": 14.1432,
+      "eval_samples_per_second": 32.525,
+      "eval_steps_per_second": 4.101,
+      "step": 400
     }
   ],
-  "max_steps": 290,
-  "num_train_epochs": 5,
-  "total_flos": 3.545449175052288e+17,
+  "max_steps": 1030,
+  "num_train_epochs": 10,
+  "total_flos": 4.929663074408755e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:779ef95e31750d3943e4f7f30b53438699b481978b1b059b4a24fa8736da35a6
+oid sha256:8862a1c5b21525e620afc66b300907a9ea89d72423fb81b6d1d942e2cd0a1d24
 size 3899