Add checkpoint-1000

checkpoints/checkpoint-1000/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be9d4428f14170e2e1aa6d2ef44d3622c150cd40b540e162eee37f6d1e6ce306
+oid sha256:c63fc0f2930e5e222c8c4efc96a19791a3f32a28b7890e8282d6b5617d29adfd
 size 4724960

checkpoints/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e6d02f7a88a4be0b0cdb9ee10296ba665e114aaf72a32932e1f68abeabfb39
+oid sha256:f9a80ddcfc3a8fe7bd533750a02bbbfbf474fb2b3cc8bc7b0f2036b79200ebee
 size 2578187

checkpoints/checkpoint-1000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfc0432c1c0bfd6b240c79d02f5b45704cf63ca8e0d7bd3054679545598448f8
+oid sha256:f8e08fdfe57842f2c139767657462bcac32c7b35d9018c133bf4642dffa4b8ab
 size 14645

checkpoints/checkpoint-1000/trainer_state.json

@@ -571,142 +571,142 @@
     },
     {
       "epoch": 0.32155617308455736,
-      "grad_norm": 1.0162802934646606,
+      "grad_norm": 0.9609226584434509,
       "learning_rate": 0.0001788525241817941,
-      "loss": 2.9229061126708986,
+      "loss": 2.8289106369018553,
       "step": 810
     },
     {
       "epoch": 0.3255260023818976,
-      "grad_norm": 0.9440785646438599,
+      "grad_norm": 1.339521050453186,
       "learning_rate": 0.00017858751821915993,
-      "loss": 3.0203786849975587,
+      "loss": 3.0263460159301756,
       "step": 820
     },
     {
       "epoch": 0.3294958316792378,
-      "grad_norm": 0.9915809035301208,
+      "grad_norm": 0.8593433499336243,
       "learning_rate": 0.0001783225122565258,
-      "loss": 3.0121458053588865,
+      "loss": 3.0060649871826173,
       "step": 830
     },
     {
       "epoch": 0.333465660976578,
-      "grad_norm": 0.9717929363250732,
+      "grad_norm": 1.0417287349700928,
       "learning_rate": 0.00017805750629389162,
-      "loss": 2.971171569824219,
+      "loss": 3.0265331268310547,
       "step": 840
     },
     {
       "epoch": 0.3374354902739182,
-      "grad_norm": 1.145629644393921,
+      "grad_norm": 1.1134616136550903,
       "learning_rate": 0.00017779250033125748,
-      "loss": 3.0685672760009766,
+      "loss": 3.057025146484375,
       "step": 850
     },
     {
       "epoch": 0.3414053195712584,
-      "grad_norm": 1.0309630632400513,
+      "grad_norm": 1.0823781490325928,
       "learning_rate": 0.0001775274943686233,
-      "loss": 2.870728302001953,
+      "loss": 3.0840169906616213,
       "step": 860
     },
     {
       "epoch": 0.34537514886859866,
-      "grad_norm": 0.8991674780845642,
+      "grad_norm": 1.304033637046814,
       "learning_rate": 0.00017726248840598913,
-      "loss": 2.9863655090332033,
+      "loss": 2.9510980606079102,
       "step": 870
     },
     {
       "epoch": 0.34934497816593885,
-      "grad_norm": 1.1400610208511353,
+      "grad_norm": 0.9548248052597046,
       "learning_rate": 0.00017699748244335499,
-      "loss": 2.98059139251709,
+      "loss": 3.0062685012817383,
       "step": 880
     },
     {
       "epoch": 0.3533148074632791,
-      "grad_norm": 1.8383524417877197,
+      "grad_norm": 0.9844130277633667,
       "learning_rate": 0.00017673247648072082,
-      "loss": 2.8302703857421876,
+      "loss": 2.9815792083740233,
       "step": 890
     },
     {
       "epoch": 0.3572846367606193,
-      "grad_norm": 1.1270629167556763,
+      "grad_norm": 1.1588873863220215,
       "learning_rate": 0.00017646747051808668,
-      "loss": 2.981347846984863,
+      "loss": 3.143498992919922,
       "step": 900
     },
     {
       "epoch": 0.3612544660579595,
-      "grad_norm": 0.9985610842704773,
+      "grad_norm": 0.9818010926246643,
       "learning_rate": 0.00017620246455545251,
-      "loss": 2.956617736816406,
+      "loss": 2.973097229003906,
       "step": 910
     },
     {
       "epoch": 0.3652242953552997,
-      "grad_norm": 0.9641323089599609,
+      "grad_norm": 1.0033776760101318,
       "learning_rate": 0.00017593745859281835,
-      "loss": 3.0457557678222655,
+      "loss": 3.0639650344848635,
       "step": 920
     },
     {
       "epoch": 0.36919412465263995,
-      "grad_norm": 1.17633855342865,
+      "grad_norm": 1.1256245374679565,
       "learning_rate": 0.00017567245263018418,
-      "loss": 3.073198699951172,
+      "loss": 3.0972034454345705,
       "step": 930
     },
     {
       "epoch": 0.37316395394998014,
-      "grad_norm": 1.0620558261871338,
+      "grad_norm": 1.1515825986862183,
       "learning_rate": 0.00017540744666755002,
-      "loss": 2.8887912750244142,
+      "loss": 2.954210090637207,
       "step": 940
     },
     {
       "epoch": 0.3771337832473204,
-      "grad_norm": 0.9436220526695251,
+      "grad_norm": 1.0679875612258911,
       "learning_rate": 0.00017514244070491588,
-      "loss": 3.1275503158569338,
+      "loss": 2.9248802185058596,
       "step": 950
     },
     {
       "epoch": 0.3811036125446606,
-      "grad_norm": 1.0516761541366577,
+      "grad_norm": 1.3141388893127441,
       "learning_rate": 0.0001748774347422817,
-      "loss": 2.925854301452637,
+      "loss": 2.9732879638671874,
       "step": 960
     },
     {
       "epoch": 0.3850734418420008,
-      "grad_norm": 1.0422406196594238,
+      "grad_norm": 0.9422619938850403,
       "learning_rate": 0.00017461242877964754,
-      "loss": 2.9021322250366213,
+      "loss": 2.8527624130249025,
       "step": 970
     },
     {
       "epoch": 0.389043271139341,
-      "grad_norm": 0.8913261890411377,
+      "grad_norm": 1.1796400547027588,
       "learning_rate": 0.0001743474228170134,
-      "loss": 3.171915817260742,
+      "loss": 3.081935691833496,
       "step": 980
     },
     {
       "epoch": 0.3930131004366812,
-      "grad_norm": 1.109357476234436,
+      "grad_norm": 0.9901096820831299,
       "learning_rate": 0.00017408241685437924,
-      "loss": 2.9540994644165037,
+      "loss": 2.9871950149536133,
       "step": 990
     },
     {
       "epoch": 0.39698292973402144,
-      "grad_norm": 1.192381739616394,
+      "grad_norm": 0.9635742902755737,
       "learning_rate": 0.00017381741089174507,
-      "loss": 3.038303184509277,
+      "loss": 2.909952735900879,
       "step": 1000
     }
   ],
@@ -727,7 +727,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.440981186791424e+16,
+  "total_flos": 4.432646342209536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null