Upload folder using huggingface_hub

README.md

@@ -18,6 +18,7 @@ base_model: EleutherAI/pythia-1b
 
 
 - **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
 - **Language(s) (NLP):** [More Information Needed]
@@ -76,7 +77,7 @@ Use the code below to get started with the model.
 
 ### Training Data
 
-<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
 [More Information Needed]
 
@@ -107,7 +108,7 @@ Use the code below to get started with the model.
 
 #### Testing Data
 
-<!-- This should link to a Data Card if possible. -->
+<!-- This should link to a Dataset Card if possible. -->
 
 [More Information Needed]
 

adapter_config.json

@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_h_to_4h",
-    "dense",
     "query_key_value",
-    "dense_4h_to_h"
+    "dense_4h_to_h",
+    "dense",
+    "dense_h_to_4h"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93dd76bfe4cf5c617e40a376647f290be1df186496041dff6ff2fb3cc8b681eb
+oid sha256:6828c92b19a021b78a689bdd76895a6474f699cd58d5d84c5f4b0e06b5b4fc70
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49b00938d0afa2f9bb17a48c0fd9f7d24f8f97b3749e09d902b8da42eb2de10f
+oid sha256:ff9c5b565bc4184a85d4aa899323a105cebce9279a3d67d3b2db8b6fca3b389c
 size 268515002

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ea9a91c2963902411e9b41cef0219c1f30fb9806372ef011f9cf908d46876c
+oid sha256:283eacebd0bb5dfaef5dee0289f963e534d9f4d557a2c889c1aadc70137e556b
 size 14244

trainer_state.json

@@ -11,901 +11,901 @@
     {
       "epoch": 0.02,
       "learning_rate": 4.444444444444444e-06,
-      "loss": 2.6769,
+      "loss": 2.8486,
       "step": 2
     },
     {
       "epoch": 0.04,
       "learning_rate": 8.888888888888888e-06,
-      "loss": 2.6837,
+      "loss": 2.8664,
       "step": 4
     },
     {
       "epoch": 0.06,
       "learning_rate": 1.3333333333333333e-05,
-      "loss": 2.6307,
+      "loss": 2.8041,
       "step": 6
     },
     {
       "epoch": 0.08,
       "learning_rate": 1.7777777777777777e-05,
-      "loss": 2.5928,
+      "loss": 2.79,
       "step": 8
     },
     {
       "epoch": 0.1,
       "learning_rate": 1.9999417253661235e-05,
-      "loss": 2.6261,
+      "loss": 2.7888,
       "step": 10
     },
     {
       "epoch": 0.12,
       "learning_rate": 1.9994755690455154e-05,
-      "loss": 2.6851,
+      "loss": 2.8095,
       "step": 12
     },
     {
       "epoch": 0.14,
       "learning_rate": 1.998543473718677e-05,
-      "loss": 2.6421,
+      "loss": 2.8176,
       "step": 14
     },
     {
       "epoch": 0.16,
       "learning_rate": 1.9971458739130598e-05,
-      "loss": 2.7906,
+      "loss": 2.8842,
       "step": 16
     },
     {
       "epoch": 0.18,
       "learning_rate": 1.995283421166614e-05,
-      "loss": 2.4095,
+      "loss": 2.5541,
       "step": 18
     },
     {
       "epoch": 0.2,
       "learning_rate": 1.9929569837240567e-05,
-      "loss": 2.2509,
+      "loss": 2.3874,
       "step": 20
     },
     {
       "epoch": 0.22,
       "learning_rate": 1.990167646132107e-05,
-      "loss": 2.3942,
+      "loss": 2.5134,
       "step": 22
     },
     {
       "epoch": 0.24,
       "learning_rate": 1.9869167087338908e-05,
-      "loss": 2.4104,
+      "loss": 2.5358,
       "step": 24
     },
     {
       "epoch": 0.26,
       "learning_rate": 1.983205687062742e-05,
-      "loss": 2.5293,
+      "loss": 2.61,
       "step": 26
     },
     {
       "epoch": 0.28,
       "learning_rate": 1.9790363111356838e-05,
-      "loss": 2.6231,
+      "loss": 2.7208,
       "step": 28
     },
     {
       "epoch": 0.3,
       "learning_rate": 1.9744105246469264e-05,
-      "loss": 2.5915,
+      "loss": 2.6972,
       "step": 30
     },
     {
       "epoch": 0.32,
       "learning_rate": 1.9693304840617456e-05,
-      "loss": 2.4235,
+      "loss": 2.5051,
       "step": 32
     },
     {
       "epoch": 0.34,
       "learning_rate": 1.963798557611178e-05,
-      "loss": 2.5622,
+      "loss": 2.6513,
       "step": 34
     },
     {
       "epoch": 0.36,
       "learning_rate": 1.957817324187987e-05,
-      "loss": 2.3644,
+      "loss": 2.4612,
       "step": 36
     },
     {
       "epoch": 0.38,
       "learning_rate": 1.9513895721444286e-05,
-      "loss": 2.3714,
+      "loss": 2.4965,
       "step": 38
     },
     {
       "epoch": 0.4,
       "learning_rate": 1.9445182979923657e-05,
-      "loss": 2.5419,
+      "loss": 2.5378,
       "step": 40
     },
     {
       "epoch": 0.42,
       "learning_rate": 1.937206705006344e-05,
-      "loss": 2.4557,
+      "loss": 2.5626,
       "step": 42
     },
     {
       "epoch": 0.44,
       "learning_rate": 1.9294582017302797e-05,
-      "loss": 2.3226,
+      "loss": 2.3782,
       "step": 44
     },
     {
       "epoch": 0.46,
       "learning_rate": 1.921276400388451e-05,
-      "loss": 2.3402,
+      "loss": 2.3861,
       "step": 46
     },
     {
       "epoch": 0.48,
       "learning_rate": 1.9126651152015404e-05,
-      "loss": 2.3476,
+      "loss": 2.3865,
       "step": 48
     },
     {
       "epoch": 0.5,
       "learning_rate": 1.9036283606085057e-05,
-      "loss": 2.3808,
+      "loss": 2.4085,
       "step": 50
     },
     {
       "epoch": 0.52,
       "learning_rate": 1.8941703493951163e-05,
-      "loss": 2.4262,
+      "loss": 2.4514,
       "step": 52
     },
     {
       "epoch": 0.54,
       "learning_rate": 1.8842954907300236e-05,
-      "loss": 2.3338,
+      "loss": 2.3645,
       "step": 54
     },
     {
       "epoch": 0.56,
       "learning_rate": 1.874008388109276e-05,
-      "loss": 2.4052,
+      "loss": 2.4375,
       "step": 56
     },
     {
       "epoch": 0.58,
       "learning_rate": 1.863313837210247e-05,
-      "loss": 2.2928,
+      "loss": 2.3349,
       "step": 58
     },
     {
       "epoch": 0.6,
       "learning_rate": 1.8522168236559693e-05,
-      "loss": 2.4616,
+      "loss": 2.451,
       "step": 60
     },
     {
       "epoch": 0.62,
       "learning_rate": 1.840722520690921e-05,
-      "loss": 2.2975,
+      "loss": 2.292,
       "step": 62
     },
     {
       "epoch": 0.64,
       "learning_rate": 1.8288362867693414e-05,
-      "loss": 2.379,
+      "loss": 2.4011,
       "step": 64
     },
     {
       "epoch": 0.66,
       "learning_rate": 1.816563663057211e-05,
-      "loss": 2.3342,
+      "loss": 2.4012,
       "step": 66
     },
     {
       "epoch": 0.68,
       "learning_rate": 1.8039103708490503e-05,
-      "loss": 2.2533,
+      "loss": 2.2143,
       "step": 68
     },
     {
       "epoch": 0.7,
       "learning_rate": 1.790882308900746e-05,
-      "loss": 2.2486,
+      "loss": 2.2528,
       "step": 70
     },
     {
       "epoch": 0.72,
       "learning_rate": 1.7774855506796497e-05,
-      "loss": 2.2496,
+      "loss": 2.2579,
       "step": 72
     },
     {
       "epoch": 0.74,
       "learning_rate": 1.7637263415332272e-05,
-      "loss": 2.3153,
+      "loss": 2.311,
       "step": 74
     },
     {
       "epoch": 0.76,
       "learning_rate": 1.749611095777581e-05,
-      "loss": 2.2758,
+      "loss": 2.2675,
       "step": 76
     },
     {
       "epoch": 0.78,
       "learning_rate": 1.7351463937072008e-05,
-      "loss": 2.5391,
+      "loss": 2.5214,
       "step": 78
     },
     {
       "epoch": 0.8,
       "learning_rate": 1.7203389785273402e-05,
-      "loss": 2.3089,
+      "loss": 2.3106,
       "step": 80
     },
     {
       "epoch": 0.82,
       "learning_rate": 1.705195753210446e-05,
-      "loss": 2.2669,
+      "loss": 2.2437,
       "step": 82
     },
     {
       "epoch": 0.84,
       "learning_rate": 1.6897237772781046e-05,
-      "loss": 2.3467,
+      "loss": 2.3724,
       "step": 84
     },
     {
       "epoch": 0.86,
       "learning_rate": 1.673930263510011e-05,
-      "loss": 2.3333,
+      "loss": 2.3034,
       "step": 86
     },
     {
       "epoch": 0.88,
       "learning_rate": 1.6578225745814907e-05,
-      "loss": 2.4031,
+      "loss": 2.4088,
       "step": 88
     },
     {
       "epoch": 0.89,
       "learning_rate": 1.6414082196311402e-05,
-      "loss": 2.3823,
+      "loss": 2.3618,
       "step": 90
     },
     {
       "epoch": 0.91,
       "learning_rate": 1.6246948507601915e-05,
-      "loss": 2.2399,
+      "loss": 2.3016,
       "step": 92
     },
     {
       "epoch": 0.93,
       "learning_rate": 1.607690259465229e-05,
-      "loss": 2.1444,
+      "loss": 2.1292,
       "step": 94
     },
     {
       "epoch": 0.95,
       "learning_rate": 1.5904023730059227e-05,
-      "loss": 2.2844,
+      "loss": 2.3076,
       "step": 96
     },
     {
       "epoch": 0.97,
       "learning_rate": 1.57283925070947e-05,
-      "loss": 2.2505,
+      "loss": 2.2199,
       "step": 98
     },
     {
       "epoch": 0.99,
       "learning_rate": 1.55500908021347e-05,
-      "loss": 2.0644,
+      "loss": 2.0546,
       "step": 100
     },
     {
       "epoch": 1.01,
       "learning_rate": 1.536920173648984e-05,
-      "loss": 2.2254,
+      "loss": 2.2257,
       "step": 102
     },
     {
       "epoch": 1.03,
       "learning_rate": 1.5185809637655548e-05,
-      "loss": 2.3203,
+      "loss": 2.3187,
       "step": 104
     },
     {
       "epoch": 1.05,
       "learning_rate": 1.5000000000000002e-05,
-      "loss": 2.2265,
+      "loss": 2.225,
       "step": 106
     },
     {
       "epoch": 1.07,
       "learning_rate": 1.4811859444908053e-05,
-      "loss": 2.3855,
+      "loss": 2.3869,
       "step": 108
     },
     {
       "epoch": 1.09,
       "learning_rate": 1.4621475680399771e-05,
-      "loss": 2.358,
+      "loss": 2.3366,
       "step": 110
     },
     {
       "epoch": 1.11,
       "learning_rate": 1.4428937460242417e-05,
-      "loss": 2.3075,
+      "loss": 2.3114,
       "step": 112
     },
     {
       "epoch": 1.13,
       "learning_rate": 1.4234334542574906e-05,
-      "loss": 2.267,
+      "loss": 2.2536,
       "step": 114
     },
     {
       "epoch": 1.15,
       "learning_rate": 1.4037757648064019e-05,
-      "loss": 2.2067,
+      "loss": 2.2126,
       "step": 116
     },
     {
       "epoch": 1.17,
       "learning_rate": 1.3839298417611964e-05,
-      "loss": 2.1989,
+      "loss": 2.1993,
       "step": 118
     },
     {
       "epoch": 1.19,
       "learning_rate": 1.3639049369634878e-05,
-      "loss": 2.1818,
+      "loss": 2.1687,
       "step": 120
     },
     {
       "epoch": 1.21,
       "learning_rate": 1.3437103856932266e-05,
-      "loss": 2.1537,
+      "loss": 2.1739,
       "step": 122
     },
     {
       "epoch": 1.23,
       "learning_rate": 1.3233556023167487e-05,
-      "loss": 2.158,
+      "loss": 2.1047,
       "step": 124
     },
     {
       "epoch": 1.25,
       "learning_rate": 1.3028500758979507e-05,
-      "loss": 2.3302,
+      "loss": 2.307,
       "step": 126
     },
     {
       "epoch": 1.27,
       "learning_rate": 1.2822033657746478e-05,
-      "loss": 2.3653,
+      "loss": 2.3542,
       "step": 128
     },
     {
       "epoch": 1.29,
       "learning_rate": 1.2614250971021658e-05,
-      "loss": 2.1906,
+      "loss": 2.1924,
       "step": 130
     },
     {
       "epoch": 1.31,
       "learning_rate": 1.2405249563662539e-05,
-      "loss": 2.3488,
+      "loss": 2.3189,
       "step": 132
     },
     {
       "epoch": 1.33,
       "learning_rate": 1.2195126868674052e-05,
-      "loss": 2.3102,
+      "loss": 2.2842,
       "step": 134
     },
     {
       "epoch": 1.35,
       "learning_rate": 1.1983980841786899e-05,
-      "loss": 2.4081,
+      "loss": 2.4086,
       "step": 136
     },
     {
       "epoch": 1.37,
       "learning_rate": 1.177190991579223e-05,
-      "loss": 2.2191,
+      "loss": 2.2432,
       "step": 138
     },
     {
       "epoch": 1.39,
       "learning_rate": 1.1559012954653865e-05,
-      "loss": 2.2446,
+      "loss": 2.2004,
       "step": 140
     },
     {
       "epoch": 1.41,
       "learning_rate": 1.1345389207419588e-05,
-      "loss": 2.3967,
+      "loss": 2.4401,
       "step": 142
     },
     {
       "epoch": 1.43,
       "learning_rate": 1.1131138261952845e-05,
-      "loss": 2.0867,
+      "loss": 2.0373,
       "step": 144
     },
     {
       "epoch": 1.45,
       "learning_rate": 1.0916359998506549e-05,
-      "loss": 2.0844,
+      "loss": 2.0671,
       "step": 146
     },
     {
       "epoch": 1.47,
       "learning_rate": 1.070115454316054e-05,
-      "loss": 2.1256,
+      "loss": 2.1005,
       "step": 148
     },
     {
       "epoch": 1.49,
       "learning_rate": 1.0485622221144485e-05,
-      "loss": 2.2274,
+      "loss": 2.2057,
       "step": 150
     },
     {
       "epoch": 1.51,
       "learning_rate": 1.0269863510067872e-05,
-      "loss": 2.1116,
+      "loss": 2.097,
       "step": 152
     },
     {
       "epoch": 1.53,
       "learning_rate": 1.0053978993079046e-05,
-      "loss": 2.4296,
+      "loss": 2.426,
       "step": 154
     },
     {
       "epoch": 1.55,
       "learning_rate": 9.838069311974986e-06,
-      "loss": 2.3066,
+      "loss": 2.2978,
       "step": 156
     },
     {
       "epoch": 1.57,
       "learning_rate": 9.622235120283769e-06,
-      "loss": 2.1659,
+      "loss": 2.1469,
       "step": 158
     },
     {
       "epoch": 1.59,
       "learning_rate": 9.406577036341548e-06,
-      "loss": 2.3285,
+      "loss": 2.3045,
       "step": 160
     },
     {
       "epoch": 1.61,
       "learning_rate": 9.19119559638596e-06,
-      "loss": 2.2788,
+      "loss": 2.2727,
       "step": 162
     },
     {
       "epoch": 1.63,
       "learning_rate": 8.976191207687775e-06,
-      "loss": 2.2487,
+      "loss": 2.2407,
       "step": 164
     },
     {
       "epoch": 1.65,
       "learning_rate": 8.7616641017427e-06,
-      "loss": 2.1421,
+      "loss": 2.146,
       "step": 166
     },
     {
       "epoch": 1.67,
       "learning_rate": 8.5477142875451e-06,
-      "loss": 2.3432,
+      "loss": 2.3296,
       "step": 168
     },
     {
       "epoch": 1.69,
       "learning_rate": 8.334441504965456e-06,
-      "loss": 1.9564,
+      "loss": 1.9436,
       "step": 170
     },
     {
       "epoch": 1.71,
       "learning_rate": 8.1219451782533e-06,
-      "loss": 2.1576,
+      "loss": 2.1402,
       "step": 172
     },
     {
       "epoch": 1.73,
       "learning_rate": 7.91032436968725e-06,
-      "loss": 2.2133,
+      "loss": 2.1921,
       "step": 174
     },
     {
       "epoch": 1.75,
       "learning_rate": 7.699677733393827e-06,
-      "loss": 2.2797,
+      "loss": 2.2548,
       "step": 176
     },
     {
       "epoch": 1.77,
       "learning_rate": 7.490103469356513e-06,
-      "loss": 2.3495,
+      "loss": 2.3743,
       "step": 178
     },
     {
       "epoch": 1.79,
       "learning_rate": 7.2816992776365714e-06,
-      "loss": 2.2715,
+      "loss": 2.2571,
       "step": 180
     },
     {
       "epoch": 1.81,
       "learning_rate": 7.0745623128268605e-06,
-      "loss": 2.3838,
+      "loss": 2.3372,
       "step": 182
     },
     {
       "epoch": 1.83,
       "learning_rate": 6.868789138759977e-06,
-      "loss": 2.3654,
+      "loss": 2.4092,
       "step": 184
     },
     {
       "epoch": 1.85,
       "learning_rate": 6.664475683491797e-06,
-      "loss": 2.2189,
+      "loss": 2.1975,
       "step": 186
     },
     {
       "epoch": 1.87,
       "learning_rate": 6.461717194581394e-06,
-      "loss": 2.3374,
+      "loss": 2.3011,
       "step": 188
     },
     {
       "epoch": 1.89,
       "learning_rate": 6.260608194688207e-06,
-      "loss": 2.3332,
+      "loss": 2.348,
       "step": 190
     },
     {
       "epoch": 1.91,
       "learning_rate": 6.061242437507131e-06,
-      "loss": 2.2279,
+      "loss": 2.1802,
       "step": 192
     },
     {
       "epoch": 1.93,
       "learning_rate": 5.863712864062089e-06,
-      "loss": 2.102,
+      "loss": 2.0869,
       "step": 194
     },
     {
       "epoch": 1.95,
       "learning_rate": 5.6681115593784705e-06,
-      "loss": 2.1584,
+      "loss": 2.1466,
       "step": 196
     },
     {
       "epoch": 1.97,
       "learning_rate": 5.4745297095546125e-06,
-      "loss": 2.1382,
+      "loss": 2.1196,
       "step": 198
     },
     {
       "epoch": 1.99,
       "learning_rate": 5.2830575592523415e-06,
-      "loss": 2.0084,
+      "loss": 1.9818,
       "step": 200
     },
     {
       "epoch": 2.01,
       "learning_rate": 5.093784369626397e-06,
-      "loss": 1.9967,
+      "loss": 1.9727,
       "step": 202
     },
     {
       "epoch": 2.03,
       "learning_rate": 4.9067983767123736e-06,
-      "loss": 2.3797,
+      "loss": 2.341,
       "step": 204
     },
     {
       "epoch": 2.05,
       "learning_rate": 4.722186750292511e-06,
-      "loss": 2.3558,
+      "loss": 2.3848,
       "step": 206
     },
     {
       "epoch": 2.07,
       "learning_rate": 4.54003555325862e-06,
-      "loss": 2.1337,
+      "loss": 2.1034,
       "step": 208
     },
     {
       "epoch": 2.09,
       "learning_rate": 4.360429701490935e-06,
-      "loss": 2.2661,
+      "loss": 2.2935,
       "step": 210
     },
     {
       "epoch": 2.11,
       "learning_rate": 4.183452924271776e-06,
-      "loss": 2.1616,
+      "loss": 2.1667,
       "step": 212
     },
     {
       "epoch": 2.13,
       "learning_rate": 4.009187725252309e-06,
-      "loss": 2.355,
+      "loss": 2.2817,
       "step": 214
     },
     {
       "epoch": 2.15,
       "learning_rate": 3.837715343990727e-06,
-      "loss": 2.224,
+      "loss": 2.2579,
       "step": 216
     },
     {
       "epoch": 2.17,
       "learning_rate": 3.669115718079702e-06,
-      "loss": 2.2079,
+      "loss": 2.1786,
       "step": 218
     },
     {
       "epoch": 2.19,
       "learning_rate": 3.5034674458807893e-06,
-      "loss": 2.086,
+      "loss": 2.0716,
       "step": 220
     },
     {
       "epoch": 2.21,
       "learning_rate": 3.3408477498831917e-06,
-      "loss": 2.126,
+      "loss": 2.1092,
       "step": 222
     },
     {
       "epoch": 2.23,
       "learning_rate": 3.1813324407038826e-06,
-      "loss": 2.1389,
+      "loss": 2.1196,
       "step": 224
     },
     {
       "epoch": 2.25,
       "learning_rate": 3.024995881745972e-06,
-      "loss": 2.1352,
+      "loss": 2.1133,
       "step": 226
     },
     {
       "epoch": 2.27,
       "learning_rate": 2.8719109545317102e-06,
-      "loss": 2.2183,
+      "loss": 2.231,
       "step": 228
     },
     {
       "epoch": 2.29,
       "learning_rate": 2.722149024726307e-06,
-      "loss": 2.2478,
+      "loss": 2.2395,
       "step": 230
     },
     {
       "epoch": 2.31,
       "learning_rate": 2.5757799088684654e-06,
-      "loss": 2.2587,
+      "loss": 2.2624,
       "step": 232
     },
     {
       "epoch": 2.33,
       "learning_rate": 2.432871841823047e-06,
-      "loss": 2.3191,
+      "loss": 2.2651,
       "step": 234
     },
     {
       "epoch": 2.35,
       "learning_rate": 2.293491444971109e-06,
-      "loss": 2.2398,
+      "loss": 2.232,
       "step": 236
     },
     {
       "epoch": 2.37,
       "learning_rate": 2.157703695152109e-06,
-      "loss": 2.3926,
+      "loss": 2.3533,
       "step": 238
     },
     {
       "epoch": 2.39,
       "learning_rate": 2.025571894372794e-06,
-      "loss": 2.2304,
+      "loss": 2.2434,
       "step": 240
     },
     {
       "epoch": 2.41,
       "learning_rate": 1.897157640296825e-06,
-      "loss": 2.2469,
+      "loss": 2.2866,
       "step": 242
     },
     {
       "epoch": 2.43,
       "learning_rate": 1.7725207975289883e-06,
-      "loss": 2.1065,
+      "loss": 2.0518,
       "step": 244
     },
     {
       "epoch": 2.45,
       "learning_rate": 1.6517194697072903e-06,
-      "loss": 2.1856,
+      "loss": 2.17,
       "step": 246
     },
     {
       "epoch": 2.47,
       "learning_rate": 1.534809972415998e-06,
-      "loss": 2.1236,
+      "loss": 2.1074,
       "step": 248
     },
     {
       "epoch": 2.49,
       "learning_rate": 1.4218468069322576e-06,
-      "loss": 2.1961,
+      "loss": 2.1721,
       "step": 250
     },
     {
       "epoch": 2.51,
       "learning_rate": 1.3128826348184886e-06,
-      "loss": 2.0173,
+      "loss": 1.9666,
       "step": 252
     },
     {
       "epoch": 2.53,
       "learning_rate": 1.207968253372438e-06,
-      "loss": 2.2847,
+      "loss": 2.2582,
       "step": 254
     },
     {
       "epoch": 2.55,
       "learning_rate": 1.1071525719463094e-06,
-      "loss": 2.3931,
+      "loss": 2.4369,
       "step": 256
     },
     {
       "epoch": 2.57,
       "learning_rate": 1.010482589146048e-06,
-      "loss": 2.2776,
+      "loss": 2.224,
       "step": 258
     },
     {
       "epoch": 2.59,
       "learning_rate": 9.180033709213454e-07,
-      "loss": 2.3249,
+      "loss": 2.3108,
       "step": 260
     },
     {
       "epoch": 2.61,
       "learning_rate": 8.297580295566576e-07,
-      "loss": 2.1791,
+      "loss": 2.1675,
       "step": 262
     },
     {
       "epoch": 2.63,
       "learning_rate": 7.457877035729588e-07,
-      "loss": 2.2177,
+      "loss": 2.2018,
       "step": 264
     },
     {
       "epoch": 2.65,
       "learning_rate": 6.661315385496426e-07,
-      "loss": 2.2903,
+      "loss": 2.2735,
       "step": 266
     },
     {
       "epoch": 2.67,
       "learning_rate": 5.908266688755049e-07,
-      "loss": 2.2478,
+      "loss": 2.2606,
       "step": 268
     },
     {
       "epoch": 2.68,
       "learning_rate": 5.199082004372958e-07,
-      "loss": 2.2076,
+      "loss": 2.1957,
       "step": 270
     },
     {
       "epoch": 2.7,
       "learning_rate": 4.534091942539476e-07,
-      "loss": 2.0342,
+      "loss": 2.0455,
       "step": 272
     },
     {
       "epoch": 2.72,
       "learning_rate": 3.913606510640644e-07,
-      "loss": 2.2668,
+      "loss": 2.2212,
       "step": 274
     },
     {
       "epoch": 2.74,
       "learning_rate": 3.3379149687388866e-07,
-      "loss": 2.1174,
+      "loss": 2.0863,
       "step": 276
     },
     {
       "epoch": 2.76,
       "learning_rate": 2.807285694724804e-07,
-      "loss": 2.2882,
+      "loss": 2.2752,
       "step": 278
     },
     {
       "epoch": 2.78,
       "learning_rate": 2.3219660592038285e-07,
-      "loss": 2.1654,
+      "loss": 2.1572,
       "step": 280
     },
     {
       "epoch": 2.8,
       "learning_rate": 1.8821823101760949e-07,
-      "loss": 2.2209,
+      "loss": 2.2088,
       "step": 282
     },
     {
       "epoch": 2.82,
       "learning_rate": 1.4881394675633543e-07,
-      "loss": 2.1442,
+      "loss": 2.1333,
       "step": 284
     },
     {
       "epoch": 2.84,
       "learning_rate": 1.1400212276321377e-07,
-      "loss": 2.3807,
+      "loss": 2.3606,
       "step": 286
     },
     {
       "epoch": 2.86,
       "learning_rate": 8.379898773574924e-08,
-      "loss": 2.4242,
+      "loss": 2.4375,
       "step": 288
     },
     {
       "epoch": 2.88,
       "learning_rate": 5.821862187675775e-08,
-      "loss": 2.2171,
+      "loss": 2.2047,
       "step": 290
     },
     {
       "epoch": 2.9,
       "learning_rate": 3.727295033040035e-08,
-      "loss": 2.277,
+      "loss": 2.2978,
       "step": 292
     },
     {
       "epoch": 2.92,
       "learning_rate": 2.0971737622883515e-08,
-      "loss": 2.0345,
+      "loss": 2.0117,
       "step": 294
     },
     {
       "epoch": 2.94,
       "learning_rate": 9.322583110392692e-09,
-      "loss": 2.0743,
+      "loss": 2.0334,
       "step": 296
     },
     {
       "epoch": 2.96,
       "learning_rate": 2.330917436402791e-09,
-      "loss": 2.0902,
+      "loss": 2.0698,
       "step": 298
     },
     {
       "epoch": 2.98,
       "learning_rate": 0.0,
-      "loss": 2.07,
+      "loss": 2.09,
       "step": 300
     }
   ],
@@ -913,7 +913,7 @@
   "max_steps": 300,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 2.591436490764288e+16,
+  "total_flos": 2.5979904694247424e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f14a7e0109b8192cf666e2a1bb1569b0cb4a481daadedb77eeb67d81a6c5f644
+oid sha256:16425f254ce2cb6bca21f6e5bbc06c0229e27ff11ab41113203e130feafffbbb
 size 4600