Add checkpoint-200

checkpoints/checkpoint-200/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ae93ddcfc9c6c57526f192ecc9502b1f7a30b17a7ae582bb4fa39eecaf3dbf
+oid sha256:1b7ec3bcdc089cc0a55cadb849ae0dae02746dac38a9121896d030aace0684b3
 size 4724960

checkpoints/checkpoint-200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ac27c10b80fd31547de4ec7551c1d1d6b39e614897caccb59a7ecf0382aeca
+oid sha256:9aab2a297ad5dff1e67f7ccc40bf13ca8bab75d073f41d2939963bdb1dabe4e3
 size 2455755

checkpoints/checkpoint-200/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:033aca5fbe916cab3abb607b95b2fa33a0911a4a36e86a61266588bb9f8675b2
+oid sha256:0e081c255e1f55c0a86db7989590446603c0a3a6b0395f9a57df7579fd41c61e
 size 14645

checkpoints/checkpoint-200/trainer_state.json

@@ -11,142 +11,142 @@
   "log_history": [
     {
       "epoch": 0.003969829297340214,
-      "grad_norm": 0.7252073287963867,
+      "grad_norm": 0.6961175799369812,
       "learning_rate": 0.00016,
-      "loss": 3.1307687759399414,
+      "loss": 3.2075271606445312,
       "step": 10
     },
     {
       "epoch": 0.007939658594680429,
-      "grad_norm": 0.8362985253334045,
+      "grad_norm": 0.9305199384689331,
       "learning_rate": 0.00019978799522989268,
-      "loss": 3.1439294815063477,
+      "loss": 3.1885648727416993,
       "step": 20
     },
     {
       "epoch": 0.011909487892020643,
-      "grad_norm": 0.9837570190429688,
+      "grad_norm": 0.8452768325805664,
       "learning_rate": 0.00019952298926725852,
-      "loss": 3.148736000061035,
+      "loss": 2.9959283828735352,
       "step": 30
     },
     {
       "epoch": 0.015879317189360857,
-      "grad_norm": 1.0522695779800415,
+      "grad_norm": 0.9384715557098389,
       "learning_rate": 0.00019925798330462438,
-      "loss": 3.1202117919921877,
+      "loss": 3.132890510559082,
       "step": 40
     },
     {
       "epoch": 0.019849146486701073,
-      "grad_norm": 0.7076596021652222,
+      "grad_norm": 0.9872943162918091,
       "learning_rate": 0.0001989929773419902,
-      "loss": 2.9990537643432615,
+      "loss": 3.1314294815063475,
       "step": 50
     },
     {
       "epoch": 0.023818975784041286,
-      "grad_norm": 0.8763487339019775,
+      "grad_norm": 0.8298355937004089,
       "learning_rate": 0.00019872797137935604,
-      "loss": 3.103739356994629,
+      "loss": 3.24124755859375,
       "step": 60
     },
     {
       "epoch": 0.027788805081381502,
-      "grad_norm": 0.7441176772117615,
+      "grad_norm": 0.8308970928192139,
       "learning_rate": 0.00019846296541672188,
-      "loss": 2.9712921142578126,
+      "loss": 3.0996198654174805,
       "step": 70
     },
     {
       "epoch": 0.031758634378721715,
-      "grad_norm": 0.8835227489471436,
+      "grad_norm": 0.8442180156707764,
       "learning_rate": 0.0001981979594540877,
-      "loss": 3.0041854858398436,
+      "loss": 3.0475082397460938,
       "step": 80
     },
     {
       "epoch": 0.03572846367606193,
-      "grad_norm": 0.827272891998291,
+      "grad_norm": 0.9131914377212524,
       "learning_rate": 0.00019793295349145357,
-      "loss": 3.0683786392211916,
+      "loss": 3.1756013870239257,
       "step": 90
     },
     {
       "epoch": 0.03969829297340215,
-      "grad_norm": 0.8369740843772888,
+      "grad_norm": 0.9973925352096558,
       "learning_rate": 0.0001976679475288194,
-      "loss": 3.1415935516357423,
+      "loss": 3.159317398071289,
       "step": 100
     },
     {
       "epoch": 0.043668122270742356,
-      "grad_norm": 1.0525009632110596,
+      "grad_norm": 0.9906535148620605,
       "learning_rate": 0.00019740294156618524,
-      "loss": 3.1269193649291993,
+      "loss": 3.086680603027344,
       "step": 110
     },
     {
       "epoch": 0.04763795156808257,
-      "grad_norm": 0.911068856716156,
+      "grad_norm": 0.8675328493118286,
       "learning_rate": 0.0001971379356035511,
-      "loss": 3.254841613769531,
+      "loss": 3.0809303283691407,
       "step": 120
     },
     {
       "epoch": 0.05160778086542279,
-      "grad_norm": 0.9495689868927002,
+      "grad_norm": 1.2756576538085938,
       "learning_rate": 0.00019687292964091694,
-      "loss": 3.0888158798217775,
+      "loss": 2.965633010864258,
       "step": 130
     },
     {
       "epoch": 0.055577610162763004,
-      "grad_norm": 0.9483733177185059,
+      "grad_norm": 0.8540228605270386,
       "learning_rate": 0.00019660792367828277,
-      "loss": 3.0614797592163088,
+      "loss": 3.11167049407959,
       "step": 140
     },
     {
       "epoch": 0.05954743946010321,
-      "grad_norm": 0.8695482015609741,
+      "grad_norm": 0.8471305966377258,
       "learning_rate": 0.0001963429177156486,
-      "loss": 3.0411098480224608,
+      "loss": 2.9493082046508787,
       "step": 150
     },
     {
       "epoch": 0.06351726875744343,
-      "grad_norm": 1.1543006896972656,
+      "grad_norm": 1.0690556764602661,
       "learning_rate": 0.00019607791175301444,
-      "loss": 3.1585403442382813,
+      "loss": 3.1130550384521483,
       "step": 160
     },
     {
       "epoch": 0.06748709805478365,
-      "grad_norm": 0.9380740523338318,
+      "grad_norm": 0.9682918787002563,
       "learning_rate": 0.0001958129057903803,
-      "loss": 3.122075080871582,
+      "loss": 3.041396713256836,
       "step": 170
     },
     {
       "epoch": 0.07145692735212386,
-      "grad_norm": 1.0981812477111816,
+      "grad_norm": 0.9328762292861938,
       "learning_rate": 0.00019554789982774613,
-      "loss": 3.0245853424072267,
+      "loss": 3.1088594436645507,
       "step": 180
     },
     {
       "epoch": 0.07542675664946408,
-      "grad_norm": 1.1122277975082397,
+      "grad_norm": 0.981307327747345,
       "learning_rate": 0.000195282893865112,
-      "loss": 3.112578582763672,
+      "loss": 3.1146469116210938,
       "step": 190
     },
     {
       "epoch": 0.0793965859468043,
-      "grad_norm": 0.9974968433380127,
+      "grad_norm": 1.0752034187316895,
       "learning_rate": 0.00019501788790247783,
-      "loss": 3.0663082122802736,
+      "loss": 3.0602563858032226,
       "step": 200
     }
   ],
@@ -167,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8810524189716480.0,
+  "total_flos": 8878465890201600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null