Add checkpoint-400

checkpoints/checkpoint-400/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c868d918322a276456882a0e312b0b887b01e7f34fb6a24016edb3783d10c3
+oid sha256:e75adf325f53036da96fbda0dc720cf563a5b6d6fb1da9d9eb67bb4bc84ed681
 size 4724960

checkpoints/checkpoint-400/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e71fd710245d55d26a13c4fcb9ce340ec3e3e0f939f8ea3ce858d981b3c84e8a
+oid sha256:0fd4fd530b96aef91a3787b30c6806c67cd03d876569cc772c3f45a6b705b531
 size 2455755

checkpoints/checkpoint-400/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc722e16bc87510829655b7c6299c4663a77a1d50fc9c0fcff1e6d25351d2bb
+oid sha256:228b52fdd074c26f37ff7b872b1ad622ea356093ef06280646b48a91758fc358
 size 14645

checkpoints/checkpoint-400/trainer_state.json

@@ -11,282 +11,282 @@
   "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
     },
     {
       "epoch": 0.0833664152441445,
-      "grad_norm": 0.9231166839599609,
+      "grad_norm": 0.8543508052825928,
       "learning_rate": 0.00019475288193984363,
-      "loss": 2.9920656204223635,
+      "loss": 2.989186477661133,
       "step": 210
     },
     {
       "epoch": 0.08733624454148471,
-      "grad_norm": 0.9820631146430969,
+      "grad_norm": 0.9234327077865601,
       "learning_rate": 0.0001944878759772095,
-      "loss": 3.1023115158081054,
+      "loss": 3.0583696365356445,
       "step": 220
     },
     {
       "epoch": 0.09130607383882493,
-      "grad_norm": 0.9965270757675171,
+      "grad_norm": 0.8820871710777283,
       "learning_rate": 0.00019422287001457533,
-      "loss": 3.146396255493164,
+      "loss": 2.868353271484375,
       "step": 230
     },
     {
       "epoch": 0.09527590313616514,
-      "grad_norm": 1.081937551498413,
+      "grad_norm": 0.9947519898414612,
       "learning_rate": 0.0001939578640519412,
-      "loss": 2.9988286972045897,
+      "loss": 3.110881042480469,
       "step": 240
     },
     {
       "epoch": 0.09924573243350536,
-      "grad_norm": 0.996936023235321,
+      "grad_norm": 0.8357694745063782,
       "learning_rate": 0.00019369285808930702,
-      "loss": 3.0814476013183594,
+      "loss": 3.01332950592041,
       "step": 250
     },
     {
       "epoch": 0.10321556173084558,
-      "grad_norm": 1.168398141860962,
+      "grad_norm": 0.9128127694129944,
       "learning_rate": 0.00019342785212667288,
-      "loss": 3.15075740814209,
+      "loss": 3.149305725097656,
       "step": 260
     },
     {
       "epoch": 0.10718539102818579,
-      "grad_norm": 0.8822141885757446,
+      "grad_norm": 0.9448281526565552,
       "learning_rate": 0.0001931628461640387,
-      "loss": 3.002421760559082,
+      "loss": 3.172308921813965,
       "step": 270
     },
     {
       "epoch": 0.11115522032552601,
-      "grad_norm": 1.1066526174545288,
+      "grad_norm": 1.0875459909439087,
       "learning_rate": 0.00019289784020140452,
-      "loss": 3.0355257034301757,
+      "loss": 3.1815589904785155,
       "step": 280
     },
     {
       "epoch": 0.11512504962286621,
-      "grad_norm": 0.9175887703895569,
+      "grad_norm": 0.9254504442214966,
       "learning_rate": 0.00019263283423877038,
-      "loss": 3.0643211364746095,
+      "loss": 3.1059280395507813,
       "step": 290
     },
     {
       "epoch": 0.11909487892020643,
-      "grad_norm": 1.0522444248199463,
+      "grad_norm": 0.9273567795753479,
       "learning_rate": 0.00019236782827613622,
-      "loss": 3.0091434478759767,
+      "loss": 3.063690757751465,
       "step": 300
     },
     {
       "epoch": 0.12306470821754664,
-      "grad_norm": 1.110771894454956,
+      "grad_norm": 0.9300341010093689,
       "learning_rate": 0.00019210282231350208,
-      "loss": 3.1843772888183595,
+      "loss": 2.989412307739258,
       "step": 310
     },
     {
       "epoch": 0.12703453751488686,
-      "grad_norm": 1.7064727544784546,
+      "grad_norm": 1.092647910118103,
       "learning_rate": 0.0001918378163508679,
-      "loss": 3.048676872253418,
+      "loss": 2.9342714309692384,
       "step": 320
     },
     {
       "epoch": 0.13100436681222707,
-      "grad_norm": 1.0409568548202515,
+      "grad_norm": 0.7696720361709595,
       "learning_rate": 0.00019157281038823375,
-      "loss": 2.927902030944824,
+      "loss": 2.966893768310547,
       "step": 330
     },
     {
       "epoch": 0.1349741961095673,
-      "grad_norm": 1.0395292043685913,
+      "grad_norm": 0.9847505688667297,
       "learning_rate": 0.00019130780442559958,
-      "loss": 3.101720428466797,
+      "loss": 3.054021644592285,
       "step": 340
     },
     {
       "epoch": 0.1389440254069075,
-      "grad_norm": 0.9616285562515259,
+      "grad_norm": 1.0354719161987305,
       "learning_rate": 0.00019104279846296541,
-      "loss": 2.9169403076171876,
+      "loss": 2.9900562286376955,
       "step": 350
     },
     {
       "epoch": 0.14291385470424772,
-      "grad_norm": 1.0398950576782227,
+      "grad_norm": 0.8888474106788635,
       "learning_rate": 0.00019077779250033128,
-      "loss": 3.0262100219726564,
+      "loss": 3.1933818817138673,
       "step": 360
     },
     {
       "epoch": 0.14688368400158794,
-      "grad_norm": 0.9672910571098328,
+      "grad_norm": 1.0046141147613525,
       "learning_rate": 0.0001905127865376971,
-      "loss": 2.945424461364746,
+      "loss": 2.920476722717285,
       "step": 370
     },
     {
       "epoch": 0.15085351329892815,
-      "grad_norm": 1.0330774784088135,
+      "grad_norm": 1.039939522743225,
       "learning_rate": 0.00019024778057506294,
-      "loss": 3.055575942993164,
+      "loss": 3.1360284805297853,
       "step": 380
     },
     {
       "epoch": 0.15482334259626837,
-      "grad_norm": 0.922511100769043,
+      "grad_norm": 0.9551829099655151,
       "learning_rate": 0.0001899827746124288,
-      "loss": 3.0388444900512694,
+      "loss": 3.144388198852539,
       "step": 390
     },
     {
       "epoch": 0.1587931718936086,
-      "grad_norm": 1.089125633239746,
+      "grad_norm": 0.9663012027740479,
       "learning_rate": 0.00018971776864979464,
-      "loss": 3.043000411987305,
+      "loss": 2.9875814437866213,
       "step": 400
     }
   ],
@@ -307,7 +307,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.756050308610048e+16,
+  "total_flos": 1.775608397088768e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null