Upload folder using huggingface_hub

adapter_config.json

@@ -1,13 +1,13 @@
 {
   "config": {
-    "alpha": 8,
+    "alpha": 16,
     "architecture": "lora",
     "attn_matrices": [
       "q",
       "v"
     ],
     "composition_mode": "add",
-    "dropout": 0.0,
+    "dropout": 0.1,
     "init_weights": "lora",
     "intermediate_lora": false,
     "leave_out": [],
@@ -16,7 +16,7 @@
     "selfattn_lora": true,
     "use_gating": false
   },
-  "config_id": "625403edad0bf919",
+  "config_id": "3fbd25b704780a8b",
   "hidden_size": 768,
   "model_class": "DebertaV2ForMaskedLM",
   "model_name": "microsoft/mdeberta-v3-base",

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc2b519480d7a69e1bd55f4952612d342cae3663c77a5293418eb31d6674f2f
+oid sha256:9072cfa3c2728b4a9fbdb40a94f5ce671e743fa5f242d26160a1f571bbae3b1b
 size 7140346

pytorch_adapter.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:272ed92adc27f20242b64e73261bb04318ca57eb3ef4ee54b852a2e4b05fe9ff
+oid sha256:ada25334bf692d848a093c2a60eb4aaf6d5c704bf917bd7e10840c33d9af4613
 size 1197478

pytorch_model_head.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e0aa5f1398702d9afdc979fd227bf2884bd36f4780e5abc696b678ff4b3cfb
+oid sha256:b26c24dbdfecc3ad182b32fa9dfb25dc2823b641fb8bce2c539d0643f1002fb8
 size 774447414

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:138729ce744467e9dfbb78e2bfec3d696c194fe33770c7393c84a4c190c050d2
+oid sha256:a5d3c43806228603da698effcb7e0ea3782c126a02914127ea9b07ee7d95c3f5
 size 14244

trainer_state.json

@@ -10,653 +10,653 @@
   "log_history": [
     {
       "epoch": 0.032,
-      "grad_norm": 2.9424972534179688,
+      "grad_norm": 2.9569661617279053,
       "learning_rate": 4.9466666666666665e-05,
-      "loss": 8.6849,
+      "loss": 8.7014,
       "step": 500
     },
     {
       "epoch": 0.064,
-      "grad_norm": 2.920867443084717,
+      "grad_norm": 2.822920799255371,
       "learning_rate": 4.8933333333333335e-05,
-      "loss": 6.4389,
+      "loss": 6.4522,
       "step": 1000
     },
     {
       "epoch": 0.096,
-      "grad_norm": 2.823730230331421,
+      "grad_norm": 2.747192621231079,
       "learning_rate": 4.8400000000000004e-05,
-      "loss": 5.8623,
+      "loss": 5.8675,
       "step": 1500
     },
     {
       "epoch": 0.128,
-      "grad_norm": 2.809546709060669,
+      "grad_norm": 2.8166677951812744,
       "learning_rate": 4.7866666666666674e-05,
-      "loss": 5.525,
+      "loss": 5.5282,
       "step": 2000
     },
     {
       "epoch": 0.16,
-      "grad_norm": 2.9036805629730225,
+      "grad_norm": 2.880764961242676,
       "learning_rate": 4.7333333333333336e-05,
-      "loss": 5.2591,
+      "loss": 5.26,
       "step": 2500
     },
     {
       "epoch": 0.192,
-      "grad_norm": 3.1155142784118652,
+      "grad_norm": 3.1332807540893555,
       "learning_rate": 4.6800000000000006e-05,
-      "loss": 5.0581,
+      "loss": 5.059,
       "step": 3000
     },
     {
       "epoch": 0.224,
-      "grad_norm": 3.164276361465454,
+      "grad_norm": 3.157362222671509,
       "learning_rate": 4.626666666666667e-05,
-      "loss": 4.8841,
+      "loss": 4.8875,
       "step": 3500
     },
     {
       "epoch": 0.256,
-      "grad_norm": 3.182744026184082,
+      "grad_norm": 3.287372350692749,
       "learning_rate": 4.573333333333333e-05,
-      "loss": 4.7435,
+      "loss": 4.7491,
       "step": 4000
     },
     {
       "epoch": 0.288,
-      "grad_norm": 3.227114677429199,
+      "grad_norm": 3.1995673179626465,
       "learning_rate": 4.52e-05,
-      "loss": 4.6214,
+      "loss": 4.628,
       "step": 4500
     },
     {
       "epoch": 0.32,
-      "grad_norm": 3.4381985664367676,
+      "grad_norm": 3.351080894470215,
       "learning_rate": 4.466666666666667e-05,
-      "loss": 4.5126,
+      "loss": 4.5196,
       "step": 5000
     },
     {
       "epoch": 0.352,
-      "grad_norm": 3.3544390201568604,
+      "grad_norm": 3.38383412361145,
       "learning_rate": 4.413333333333334e-05,
-      "loss": 4.4291,
+      "loss": 4.4351,
       "step": 5500
     },
     {
       "epoch": 0.384,
-      "grad_norm": 3.298597812652588,
+      "grad_norm": 3.387878894805908,
       "learning_rate": 4.36e-05,
-      "loss": 4.3566,
+      "loss": 4.3645,
       "step": 6000
     },
     {
       "epoch": 0.416,
-      "grad_norm": 3.3512299060821533,
+      "grad_norm": 3.386368989944458,
       "learning_rate": 4.3066666666666665e-05,
-      "loss": 4.2619,
+      "loss": 4.2706,
       "step": 6500
     },
     {
       "epoch": 0.448,
-      "grad_norm": 3.4974567890167236,
+      "grad_norm": 3.540905714035034,
       "learning_rate": 4.2533333333333335e-05,
-      "loss": 4.1959,
+      "loss": 4.2067,
       "step": 7000
     },
     {
       "epoch": 0.48,
-      "grad_norm": 3.461158275604248,
+      "grad_norm": 3.5285682678222656,
       "learning_rate": 4.2e-05,
-      "loss": 4.1362,
+      "loss": 4.1446,
       "step": 7500
     },
     {
       "epoch": 0.512,
-      "grad_norm": 3.59013032913208,
+      "grad_norm": 3.515582799911499,
       "learning_rate": 4.146666666666667e-05,
-      "loss": 4.0899,
+      "loss": 4.1001,
       "step": 8000
     },
     {
       "epoch": 0.544,
-      "grad_norm": 3.5825486183166504,
+      "grad_norm": 3.382394790649414,
       "learning_rate": 4.093333333333334e-05,
-      "loss": 4.0397,
+      "loss": 4.0504,
       "step": 8500
     },
     {
       "epoch": 0.576,
-      "grad_norm": 3.6372616291046143,
+      "grad_norm": 3.8084897994995117,
       "learning_rate": 4.0400000000000006e-05,
-      "loss": 3.9972,
+      "loss": 4.0049,
       "step": 9000
     },
     {
       "epoch": 0.608,
-      "grad_norm": 3.755031108856201,
+      "grad_norm": 3.8991751670837402,
       "learning_rate": 3.986666666666667e-05,
-      "loss": 3.9512,
+      "loss": 3.9604,
       "step": 9500
     },
     {
       "epoch": 0.64,
-      "grad_norm": 3.7865397930145264,
+      "grad_norm": 3.772257089614868,
       "learning_rate": 3.933333333333333e-05,
-      "loss": 3.9119,
+      "loss": 3.9241,
       "step": 10000
     },
     {
       "epoch": 0.672,
-      "grad_norm": 3.6925289630889893,
+      "grad_norm": 3.737558126449585,
       "learning_rate": 3.88e-05,
-      "loss": 3.8648,
+      "loss": 3.8759,
       "step": 10500
     },
     {
       "epoch": 0.704,
-      "grad_norm": 3.568006992340088,
+      "grad_norm": 3.6017825603485107,
       "learning_rate": 3.8266666666666664e-05,
-      "loss": 3.8405,
+      "loss": 3.8505,
       "step": 11000
     },
     {
       "epoch": 0.736,
-      "grad_norm": 3.710155487060547,
+      "grad_norm": 3.808885097503662,
       "learning_rate": 3.773333333333334e-05,
-      "loss": 3.8106,
+      "loss": 3.8244,
       "step": 11500
     },
     {
       "epoch": 0.768,
-      "grad_norm": 3.632565498352051,
+      "grad_norm": 3.6906981468200684,
       "learning_rate": 3.72e-05,
-      "loss": 3.7859,
+      "loss": 3.8002,
       "step": 12000
     },
     {
       "epoch": 0.8,
-      "grad_norm": 3.815101146697998,
+      "grad_norm": 3.9535021781921387,
       "learning_rate": 3.6666666666666666e-05,
-      "loss": 3.7535,
+      "loss": 3.7668,
       "step": 12500
     },
     {
       "epoch": 0.832,
-      "grad_norm": 3.8420307636260986,
+      "grad_norm": 3.9696996212005615,
       "learning_rate": 3.6133333333333335e-05,
-      "loss": 3.7217,
+      "loss": 3.7349,
       "step": 13000
     },
     {
       "epoch": 0.864,
-      "grad_norm": 3.8636972904205322,
+      "grad_norm": 3.95868182182312,
       "learning_rate": 3.56e-05,
-      "loss": 3.6991,
+      "loss": 3.7126,
       "step": 13500
     },
     {
       "epoch": 0.896,
-      "grad_norm": 3.7512834072113037,
+      "grad_norm": 3.7807376384735107,
       "learning_rate": 3.506666666666667e-05,
-      "loss": 3.6815,
+      "loss": 3.6938,
       "step": 14000
     },
     {
       "epoch": 0.928,
-      "grad_norm": 3.83168888092041,
+      "grad_norm": 3.8795831203460693,
       "learning_rate": 3.453333333333334e-05,
-      "loss": 3.6456,
+      "loss": 3.6575,
       "step": 14500
     },
     {
       "epoch": 0.96,
-      "grad_norm": 3.9975242614746094,
+      "grad_norm": 4.042747974395752,
       "learning_rate": 3.4000000000000007e-05,
-      "loss": 3.6324,
+      "loss": 3.6452,
       "step": 15000
     },
     {
       "epoch": 0.992,
-      "grad_norm": 4.030258655548096,
+      "grad_norm": 4.158185005187988,
       "learning_rate": 3.346666666666667e-05,
-      "loss": 3.6194,
+      "loss": 3.6333,
       "step": 15500
     },
     {
       "epoch": 1.024,
-      "grad_norm": 3.973304033279419,
+      "grad_norm": 3.9581844806671143,
       "learning_rate": 3.293333333333333e-05,
-      "loss": 3.5902,
+      "loss": 3.6045,
       "step": 16000
     },
     {
       "epoch": 1.056,
-      "grad_norm": 3.86440372467041,
+      "grad_norm": 3.930466651916504,
       "learning_rate": 3.24e-05,
-      "loss": 3.566,
+      "loss": 3.5799,
       "step": 16500
     },
     {
       "epoch": 1.088,
-      "grad_norm": 4.0587687492370605,
+      "grad_norm": 4.019719123840332,
       "learning_rate": 3.1866666666666664e-05,
-      "loss": 3.5557,
+      "loss": 3.5699,
       "step": 17000
     },
     {
       "epoch": 1.12,
-      "grad_norm": 3.827023506164551,
+      "grad_norm": 3.9303104877471924,
       "learning_rate": 3.1333333333333334e-05,
-      "loss": 3.5364,
+      "loss": 3.5509,
       "step": 17500
     },
     {
       "epoch": 1.152,
-      "grad_norm": 4.169133186340332,
+      "grad_norm": 4.159476280212402,
       "learning_rate": 3.08e-05,
-      "loss": 3.5265,
+      "loss": 3.5397,
       "step": 18000
     },
     {
       "epoch": 1.184,
-      "grad_norm": 3.898099422454834,
+      "grad_norm": 3.8772120475769043,
       "learning_rate": 3.0266666666666666e-05,
-      "loss": 3.5084,
+      "loss": 3.522,
       "step": 18500
     },
     {
       "epoch": 1.216,
-      "grad_norm": 4.342574596405029,
+      "grad_norm": 4.351678371429443,
       "learning_rate": 2.9733333333333336e-05,
-      "loss": 3.4974,
+      "loss": 3.5119,
       "step": 19000
     },
     {
       "epoch": 1.248,
-      "grad_norm": 4.324068069458008,
+      "grad_norm": 4.2748541831970215,
       "learning_rate": 2.9199999999999998e-05,
-      "loss": 3.4754,
+      "loss": 3.4896,
       "step": 19500
     },
     {
       "epoch": 1.28,
-      "grad_norm": 4.245048522949219,
+      "grad_norm": 4.250527381896973,
       "learning_rate": 2.8666666666666668e-05,
-      "loss": 3.4648,
+      "loss": 3.4782,
       "step": 20000
     },
     {
       "epoch": 1.312,
-      "grad_norm": 4.126637935638428,
+      "grad_norm": 4.305374622344971,
       "learning_rate": 2.8133333333333334e-05,
-      "loss": 3.4629,
+      "loss": 3.4782,
       "step": 20500
     },
     {
       "epoch": 1.3439999999999999,
-      "grad_norm": 4.299191951751709,
+      "grad_norm": 4.257715702056885,
       "learning_rate": 2.7600000000000003e-05,
-      "loss": 3.4371,
+      "loss": 3.4511,
       "step": 21000
     },
     {
       "epoch": 1.376,
-      "grad_norm": 4.065174579620361,
+      "grad_norm": 4.085139751434326,
       "learning_rate": 2.706666666666667e-05,
-      "loss": 3.4363,
+      "loss": 3.4501,
       "step": 21500
     },
     {
       "epoch": 1.408,
-      "grad_norm": 4.384226322174072,
+      "grad_norm": 4.325361251831055,
       "learning_rate": 2.6533333333333332e-05,
-      "loss": 3.4225,
+      "loss": 3.4379,
       "step": 22000
     },
     {
       "epoch": 1.44,
-      "grad_norm": 4.3641557693481445,
+      "grad_norm": 4.4493913650512695,
       "learning_rate": 2.6000000000000002e-05,
-      "loss": 3.4077,
+      "loss": 3.4232,
       "step": 22500
     },
     {
       "epoch": 1.472,
-      "grad_norm": 4.107190132141113,
+      "grad_norm": 4.0350871086120605,
       "learning_rate": 2.5466666666666668e-05,
-      "loss": 3.4087,
+      "loss": 3.4222,
       "step": 23000
     },
     {
       "epoch": 1.504,
-      "grad_norm": 4.042760372161865,
+      "grad_norm": 4.175812721252441,
       "learning_rate": 2.4933333333333334e-05,
-      "loss": 3.3884,
+      "loss": 3.4022,
       "step": 23500
     },
     {
       "epoch": 1.536,
-      "grad_norm": 4.374895095825195,
+      "grad_norm": 4.516785621643066,
       "learning_rate": 2.44e-05,
-      "loss": 3.3802,
+      "loss": 3.3962,
       "step": 24000
     },
     {
       "epoch": 1.568,
-      "grad_norm": 4.4557785987854,
+      "grad_norm": 4.481914520263672,
       "learning_rate": 2.3866666666666666e-05,
-      "loss": 3.3717,
+      "loss": 3.3894,
       "step": 24500
     },
     {
       "epoch": 1.6,
-      "grad_norm": 4.2283525466918945,
+      "grad_norm": 4.242756366729736,
       "learning_rate": 2.3333333333333336e-05,
-      "loss": 3.3607,
+      "loss": 3.3757,
       "step": 25000
     },
     {
       "epoch": 1.6320000000000001,
-      "grad_norm": 4.35026216506958,
+      "grad_norm": 4.440269470214844,
       "learning_rate": 2.2800000000000002e-05,
-      "loss": 3.3536,
+      "loss": 3.3678,
       "step": 25500
     },
     {
       "epoch": 1.6640000000000001,
-      "grad_norm": 4.368349552154541,
+      "grad_norm": 4.3999152183532715,
       "learning_rate": 2.2266666666666668e-05,
-      "loss": 3.3402,
+      "loss": 3.3565,
       "step": 26000
     },
     {
       "epoch": 1.696,
-      "grad_norm": 4.4084320068359375,
+      "grad_norm": 4.339915752410889,
       "learning_rate": 2.1733333333333334e-05,
-      "loss": 3.3399,
+      "loss": 3.3557,
       "step": 26500
     },
     {
       "epoch": 1.728,
-      "grad_norm": 4.457075595855713,
+      "grad_norm": 4.5959625244140625,
       "learning_rate": 2.12e-05,
-      "loss": 3.3387,
+      "loss": 3.3556,
       "step": 27000
     },
     {
       "epoch": 1.76,
-      "grad_norm": 4.464320182800293,
+      "grad_norm": 4.463385105133057,
       "learning_rate": 2.0666666666666666e-05,
-      "loss": 3.326,
+      "loss": 3.3432,
       "step": 27500
     },
     {
       "epoch": 1.792,
-      "grad_norm": 4.661604881286621,
+      "grad_norm": 4.859776020050049,
       "learning_rate": 2.0133333333333336e-05,
-      "loss": 3.3234,
+      "loss": 3.3413,
       "step": 28000
     },
     {
       "epoch": 1.8239999999999998,
-      "grad_norm": 4.644153118133545,
+      "grad_norm": 4.643787384033203,
       "learning_rate": 1.9600000000000002e-05,
-      "loss": 3.3085,
+      "loss": 3.3249,
       "step": 28500
     },
     {
       "epoch": 1.8559999999999999,
-      "grad_norm": 4.639111518859863,
+      "grad_norm": 4.585232257843018,
       "learning_rate": 1.9066666666666668e-05,
-      "loss": 3.3081,
+      "loss": 3.3242,
       "step": 29000
     },
     {
       "epoch": 1.888,
-      "grad_norm": 4.566634178161621,
+      "grad_norm": 4.6707563400268555,
       "learning_rate": 1.8533333333333334e-05,
-      "loss": 3.2974,
+      "loss": 3.3135,
       "step": 29500
     },
     {
       "epoch": 1.92,
-      "grad_norm": 4.374799728393555,
+      "grad_norm": 4.501559734344482,
       "learning_rate": 1.8e-05,
-      "loss": 3.2978,
+      "loss": 3.315,
       "step": 30000
     },
     {
       "epoch": 1.952,
-      "grad_norm": 4.597689151763916,
+      "grad_norm": 4.715555667877197,
       "learning_rate": 1.7466666666666667e-05,
-      "loss": 3.2982,
+      "loss": 3.3151,
       "step": 30500
     },
     {
       "epoch": 1.984,
-      "grad_norm": 4.6352643966674805,
+      "grad_norm": 4.661777496337891,
       "learning_rate": 1.6933333333333333e-05,
-      "loss": 3.2933,
+      "loss": 3.3087,
       "step": 31000
     },
     {
       "epoch": 2.016,
-      "grad_norm": 4.438491344451904,
+      "grad_norm": 4.5024027824401855,
       "learning_rate": 1.6400000000000002e-05,
-      "loss": 3.2716,
+      "loss": 3.2875,
       "step": 31500
     },
     {
       "epoch": 2.048,
-      "grad_norm": 4.771531105041504,
+      "grad_norm": 4.788130283355713,
       "learning_rate": 1.586666666666667e-05,
-      "loss": 3.2744,
+      "loss": 3.2926,
       "step": 32000
     },
     {
       "epoch": 2.08,
-      "grad_norm": 4.4778571128845215,
+      "grad_norm": 4.57729434967041,
       "learning_rate": 1.5333333333333334e-05,
-      "loss": 3.2682,
+      "loss": 3.2858,
       "step": 32500
     },
     {
       "epoch": 2.112,
-      "grad_norm": 4.593661785125732,
+      "grad_norm": 4.824256896972656,
       "learning_rate": 1.48e-05,
-      "loss": 3.2665,
+      "loss": 3.2845,
       "step": 33000
     },
     {
       "epoch": 2.144,
-      "grad_norm": 5.021648406982422,
+      "grad_norm": 5.179717540740967,
       "learning_rate": 1.4266666666666667e-05,
-      "loss": 3.2617,
+      "loss": 3.2788,
       "step": 33500
     },
     {
       "epoch": 2.176,
-      "grad_norm": 4.638373851776123,
+      "grad_norm": 4.701488494873047,
       "learning_rate": 1.3733333333333335e-05,
-      "loss": 3.2606,
+      "loss": 3.2794,
       "step": 34000
     },
     {
       "epoch": 2.208,
-      "grad_norm": 4.727328777313232,
+      "grad_norm": 4.734540939331055,
       "learning_rate": 1.32e-05,
-      "loss": 3.2715,
+      "loss": 3.2882,
       "step": 34500
     },
     {
       "epoch": 2.24,
-      "grad_norm": 4.760270595550537,
+      "grad_norm": 4.886785984039307,
       "learning_rate": 1.2666666666666668e-05,
-      "loss": 3.2542,
+      "loss": 3.2716,
       "step": 35000
     },
     {
       "epoch": 2.2720000000000002,
-      "grad_norm": 4.6044135093688965,
+      "grad_norm": 4.812310218811035,
       "learning_rate": 1.2133333333333335e-05,
-      "loss": 3.2456,
+      "loss": 3.2632,
       "step": 35500
     },
     {
       "epoch": 2.304,
-      "grad_norm": 4.678633689880371,
+      "grad_norm": 4.733267784118652,
       "learning_rate": 1.16e-05,
-      "loss": 3.2497,
+      "loss": 3.2667,
       "step": 36000
     },
     {
       "epoch": 2.336,
-      "grad_norm": 4.491886138916016,
+      "grad_norm": 4.642938613891602,
       "learning_rate": 1.1066666666666667e-05,
-      "loss": 3.2365,
+      "loss": 3.2534,
       "step": 36500
     },
     {
       "epoch": 2.368,
-      "grad_norm": 4.634810924530029,
+      "grad_norm": 4.576411724090576,
       "learning_rate": 1.0533333333333335e-05,
-      "loss": 3.2354,
+      "loss": 3.2547,
       "step": 37000
     },
     {
       "epoch": 2.4,
-      "grad_norm": 4.786377429962158,
+      "grad_norm": 4.903866767883301,
       "learning_rate": 1e-05,
-      "loss": 3.2353,
+      "loss": 3.2542,
       "step": 37500
     },
     {
       "epoch": 2.432,
-      "grad_norm": 4.897108554840088,
+      "grad_norm": 4.908432960510254,
       "learning_rate": 9.466666666666667e-06,
-      "loss": 3.2263,
+      "loss": 3.2431,
       "step": 38000
     },
     {
       "epoch": 2.464,
-      "grad_norm": 4.90987491607666,
+      "grad_norm": 5.0655364990234375,
       "learning_rate": 8.933333333333333e-06,
-      "loss": 3.2329,
+      "loss": 3.2509,
       "step": 38500
     },
     {
       "epoch": 2.496,
-      "grad_norm": 4.756670951843262,
+      "grad_norm": 4.810054302215576,
       "learning_rate": 8.400000000000001e-06,
-      "loss": 3.2296,
+      "loss": 3.2499,
       "step": 39000
     },
     {
       "epoch": 2.528,
-      "grad_norm": 5.046512603759766,
+      "grad_norm": 4.952749729156494,
       "learning_rate": 7.866666666666667e-06,
-      "loss": 3.2218,
+      "loss": 3.2413,
       "step": 39500
     },
     {
       "epoch": 2.56,
-      "grad_norm": 4.700692653656006,
+      "grad_norm": 4.862243175506592,
       "learning_rate": 7.333333333333334e-06,
-      "loss": 3.2213,
+      "loss": 3.2395,
       "step": 40000
     },
     {
       "epoch": 2.592,
-      "grad_norm": 4.720780849456787,
+      "grad_norm": 5.045057773590088,
       "learning_rate": 6.800000000000001e-06,
-      "loss": 3.2111,
+      "loss": 3.2272,
       "step": 40500
     },
     {
       "epoch": 2.624,
-      "grad_norm": 4.76978874206543,
+      "grad_norm": 4.81024169921875,
       "learning_rate": 6.266666666666666e-06,
-      "loss": 3.2126,
+      "loss": 3.2315,
       "step": 41000
     },
     {
       "epoch": 2.656,
-      "grad_norm": 4.721715927124023,
+      "grad_norm": 4.652002334594727,
       "learning_rate": 5.733333333333333e-06,
-      "loss": 3.2174,
+      "loss": 3.2331,
       "step": 41500
     },
     {
       "epoch": 2.6879999999999997,
-      "grad_norm": 4.864213466644287,
+      "grad_norm": 4.979446887969971,
       "learning_rate": 5.2e-06,
-      "loss": 3.2152,
+      "loss": 3.2326,
       "step": 42000
     },
     {
       "epoch": 2.7199999999999998,
-      "grad_norm": 4.913540363311768,
+      "grad_norm": 4.838864803314209,
       "learning_rate": 4.666666666666667e-06,
-      "loss": 3.2147,
+      "loss": 3.233,
       "step": 42500
     },
     {
       "epoch": 2.752,
-      "grad_norm": 4.808172702789307,
+      "grad_norm": 4.996217727661133,
       "learning_rate": 4.133333333333333e-06,
-      "loss": 3.1984,
+      "loss": 3.2172,
       "step": 43000
     },
     {
       "epoch": 2.784,
-      "grad_norm": 4.726377487182617,
+      "grad_norm": 4.89617919921875,
       "learning_rate": 3.6e-06,
-      "loss": 3.2079,
+      "loss": 3.2263,
       "step": 43500
     },
     {
       "epoch": 2.816,
-      "grad_norm": 5.004685401916504,
+      "grad_norm": 4.889566898345947,
       "learning_rate": 3.066666666666667e-06,
-      "loss": 3.2186,
+      "loss": 3.2374,
       "step": 44000
     },
     {
       "epoch": 2.848,
-      "grad_norm": 4.894927501678467,
+      "grad_norm": 4.909117698669434,
       "learning_rate": 2.5333333333333334e-06,
-      "loss": 3.2183,
+      "loss": 3.2364,
       "step": 44500
     },
     {
       "epoch": 2.88,
-      "grad_norm": 4.726415634155273,
+      "grad_norm": 4.819942951202393,
       "learning_rate": 2.0000000000000003e-06,
-      "loss": 3.2038,
+      "loss": 3.2243,
       "step": 45000
     },
     {
       "epoch": 2.912,
-      "grad_norm": 4.9267096519470215,
+      "grad_norm": 4.989527702331543,
       "learning_rate": 1.4666666666666667e-06,
-      "loss": 3.2122,
+      "loss": 3.2303,
       "step": 45500
     },
     {
       "epoch": 2.944,
-      "grad_norm": 4.9680585861206055,
+      "grad_norm": 5.0459980964660645,
       "learning_rate": 9.333333333333334e-07,
-      "loss": 3.2165,
+      "loss": 3.2318,
       "step": 46000
     },
     {
       "epoch": 2.976,
-      "grad_norm": 4.905124664306641,
+      "grad_norm": 4.944396495819092,
       "learning_rate": 4.0000000000000003e-07,
-      "loss": 3.2191,
+      "loss": 3.2394,
       "step": 46500
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ddcc6d430b5d93cfc2924e80f63540f6b28a16c5e2314c7e7cc592fbc403f17
+oid sha256:2f3fe1bfd10cbdfb1d6e4ab92faf74d8e6aaccab46d9c333a20594eb068ed808
 size 5176