Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e076f7213cd541801b56e598732e42d7aaa49f322189b3825f935f5e1a9284
+oid sha256:170b9839a6f9cb4849a79d372fdd8978c15d9f959a62f6fc4739c2fab1a62cb9
 size 349243752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e1d75dde1eaa357bbd53fa9529a45fd976f9322d969b161d305861e4d4d4f6
+oid sha256:fde78758d4bfbd2f73a3973efb9b2f5d957019b5c9fc4ad6115838e371515762
 size 177909253

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e967965c983a20a302f5bd4e11508247b969959098eb0b66c2fdc8d23296fa
+oid sha256:996933921c4deed1d34ddceb89eb427578e0472ba88129c76719f873c95cb898
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7258fe24b7785a5fa76614aef57f913158962a01367bf1fe11174ca5bb4f2704
+oid sha256:6557e2f348eac233d3d621679f2b4c7e01f4a6a61c82ffe28816c1229ea4afae
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4975124378109453,
+  "epoch": 0.5970149253731343,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -883,6 +883,181 @@
       "learning_rate": 6.1274380295443624e-06,
       "loss": 1.345,
       "step": 500
+    },
+    {
+      "epoch": 0.5014925373134328,
+      "grad_norm": 0.16558654606342316,
+      "learning_rate": 6.057762090680162e-06,
+      "loss": 1.3696,
+      "step": 504
+    },
+    {
+      "epoch": 0.5054726368159204,
+      "grad_norm": 0.17274197936058044,
+      "learning_rate": 5.9876866595667085e-06,
+      "loss": 1.4371,
+      "step": 508
+    },
+    {
+      "epoch": 0.5094527363184079,
+      "grad_norm": 0.18550808727741241,
+      "learning_rate": 5.917230303186e-06,
+      "loss": 1.491,
+      "step": 512
+    },
+    {
+      "epoch": 0.5134328358208955,
+      "grad_norm": 0.16486109793186188,
+      "learning_rate": 5.84641168944888e-06,
+      "loss": 1.3596,
+      "step": 516
+    },
+    {
+      "epoch": 0.5174129353233831,
+      "grad_norm": 0.15757621824741364,
+      "learning_rate": 5.775249582248848e-06,
+      "loss": 1.3464,
+      "step": 520
+    },
+    {
+      "epoch": 0.5213930348258706,
+      "grad_norm": 0.1419944018125534,
+      "learning_rate": 5.703762836490429e-06,
+      "loss": 1.3415,
+      "step": 524
+    },
+    {
+      "epoch": 0.5253731343283582,
+      "grad_norm": 0.24455907940864563,
+      "learning_rate": 5.631970393093435e-06,
+      "loss": 1.4322,
+      "step": 528
+    },
+    {
+      "epoch": 0.5293532338308458,
+      "grad_norm": 0.15628467500209808,
+      "learning_rate": 5.559891273974433e-06,
+      "loss": 1.4357,
+      "step": 532
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.15226367115974426,
+      "learning_rate": 5.487544577006756e-06,
+      "loss": 1.3864,
+      "step": 536
+    },
+    {
+      "epoch": 0.5373134328358209,
+      "grad_norm": 0.15544599294662476,
+      "learning_rate": 5.414949470960377e-06,
+      "loss": 1.3954,
+      "step": 540
+    },
+    {
+      "epoch": 0.5412935323383085,
+      "grad_norm": 0.14596706628799438,
+      "learning_rate": 5.3421251904230245e-06,
+      "loss": 1.2908,
+      "step": 544
+    },
+    {
+      "epoch": 0.545273631840796,
+      "grad_norm": 0.14396768808364868,
+      "learning_rate": 5.269091030703825e-06,
+      "loss": 1.3339,
+      "step": 548
+    },
+    {
+      "epoch": 0.5492537313432836,
+      "grad_norm": 0.14690382778644562,
+      "learning_rate": 5.195866342720883e-06,
+      "loss": 1.4412,
+      "step": 552
+    },
+    {
+      "epoch": 0.5532338308457712,
+      "grad_norm": 0.164686918258667,
+      "learning_rate": 5.122470527874117e-06,
+      "loss": 1.3025,
+      "step": 556
+    },
+    {
+      "epoch": 0.5572139303482587,
+      "grad_norm": 0.15687449276447296,
+      "learning_rate": 5.0489230329047216e-06,
+      "loss": 1.4286,
+      "step": 560
+    },
+    {
+      "epoch": 0.5611940298507463,
+      "grad_norm": 0.16417358815670013,
+      "learning_rate": 4.975243344742612e-06,
+      "loss": 1.3747,
+      "step": 564
+    },
+    {
+      "epoch": 0.5651741293532339,
+      "grad_norm": 0.140806183218956,
+      "learning_rate": 4.90145098534323e-06,
+      "loss": 1.3345,
+      "step": 568
+    },
+    {
+      "epoch": 0.5691542288557214,
+      "grad_norm": 0.14276030659675598,
+      "learning_rate": 4.827565506515056e-06,
+      "loss": 1.3701,
+      "step": 572
+    },
+    {
+      "epoch": 0.573134328358209,
+      "grad_norm": 0.18743367493152618,
+      "learning_rate": 4.753606484739227e-06,
+      "loss": 1.323,
+      "step": 576
+    },
+    {
+      "epoch": 0.5771144278606966,
+      "grad_norm": 0.13849185407161713,
+      "learning_rate": 4.679593515982602e-06,
+      "loss": 1.3634,
+      "step": 580
+    },
+    {
+      "epoch": 0.5810945273631841,
+      "grad_norm": 0.16938801109790802,
+      "learning_rate": 4.605546210505675e-06,
+      "loss": 1.4166,
+      "step": 584
+    },
+    {
+      "epoch": 0.5850746268656717,
+      "grad_norm": 0.1600942611694336,
+      "learning_rate": 4.531484187666699e-06,
+      "loss": 1.3556,
+      "step": 588
+    },
+    {
+      "epoch": 0.5890547263681593,
+      "grad_norm": 0.18938744068145752,
+      "learning_rate": 4.457427070723396e-06,
+      "loss": 1.3305,
+      "step": 592
+    },
+    {
+      "epoch": 0.5930348258706468,
+      "grad_norm": 0.1494676023721695,
+      "learning_rate": 4.383394481633633e-06,
+      "loss": 1.3438,
+      "step": 596
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.17030707001686096,
+      "learning_rate": 4.309406035856457e-06,
+      "loss": 1.3414,
+      "step": 600
     }
   ],
   "logging_steps": 4,
@@ -902,7 +1077,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.748818411375821e+17,
+  "total_flos": 4.505167220095058e+17,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null