Training in progress, step 811, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7158fc026fcb3c75de92fe98a9e7575457f3d0ddfdd21de716103cd610f69de9
+oid sha256:55e901950eda5c3c11519f5869e78400ddd745c2f3fe32041dc5dd5a35a5e996
 size 792912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e19210c69c04c9e2774683c62f913e9f0f21be0a7cfcac2e1acf7c710d1c386
+oid sha256:73ed21f6575ce7ac1358e5cf5c7c69d83efbe73affe310120a69fabf245a1f71
 size 807226

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22ad685c1237efec2f2e8de413bc38dd1475089fe9b28d8d43fe1c45017827ac
+oid sha256:95854d5cc00d71cecca852780bc1bcfd6e88e4fb1b955160cbf9a3145c24d1f4
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53dc596014d0f9b21145357c41c37d57500c8efda8a0f2014bb2d988a043e59f
+oid sha256:9c29de9e8fa8a45e29d4ef4934d4078cdeb0cb620b4247b9553ca2b1a8cbd29d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:223b0451f4d9b8dd81e35f5a28bc073e05755799383bf2e8538e323aed665d3b
+oid sha256:34653e4e06f0f7c40ebe51d437e12f779eafc5b99b228a15e55333dd8cf2018e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d17262a3d5928a646b0fefef89331d9cdec36c92fdf757662a6e2bf2165b6d
+oid sha256:b961f6d9076ef8d42e30189d58f3020d35ceddece8ef8239ee39ccc91e6823f5
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17ccafd97486ba1c378a3ba81af6282c7ec0337562d5f30dc98873ace309528
+oid sha256:70b60170e4ee207b411221d3212e057a7eb914ba6755abafc4c8bac2ff50fb1f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.987045033929673,
+  "epoch": 1.000616903146206,
   "eval_steps": 203,
-  "global_step": 800,
+  "global_step": 811,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5639,6 +5639,83 @@
       "learning_rate": 5.154436320919942e-08,
       "loss": 4.0969,
       "step": 800
+    },
+    {
+      "epoch": 0.9882788402220851,
+      "grad_norm": 657.191162109375,
+      "learning_rate": 4.25999178087888e-08,
+      "loss": 4.127,
+      "step": 801
+    },
+    {
+      "epoch": 0.9895126465144972,
+      "grad_norm": 618.2482299804688,
+      "learning_rate": 3.4506864562133815e-08,
+      "loss": 3.99,
+      "step": 802
+    },
+    {
+      "epoch": 0.9907464528069093,
+      "grad_norm": 729.18798828125,
+      "learning_rate": 2.7265341393983845e-08,
+      "loss": 4.0454,
+      "step": 803
+    },
+    {
+      "epoch": 0.9919802590993214,
+      "grad_norm": 660.1466064453125,
+      "learning_rate": 2.0875471717013427e-08,
+      "loss": 4.1317,
+      "step": 804
+    },
+    {
+      "epoch": 0.9932140653917335,
+      "grad_norm": 619.5026245117188,
+      "learning_rate": 1.5337364429696132e-08,
+      "loss": 3.9811,
+      "step": 805
+    },
+    {
+      "epoch": 0.9944478716841456,
+      "grad_norm": 849.2465209960938,
+      "learning_rate": 1.065111391447271e-08,
+      "loss": 4.1834,
+      "step": 806
+    },
+    {
+      "epoch": 0.9956816779765577,
+      "grad_norm": 727.19580078125,
+      "learning_rate": 6.816800036124615e-09,
+      "loss": 4.224,
+      "step": 807
+    },
+    {
+      "epoch": 0.9969154842689698,
+      "grad_norm": 646.8365478515625,
+      "learning_rate": 3.8344881404195345e-09,
+      "loss": 3.9375,
+      "step": 808
+    },
+    {
+      "epoch": 0.9981492905613819,
+      "grad_norm": 956.5570068359375,
+      "learning_rate": 1.7042290529956095e-09,
+      "loss": 4.0443,
+      "step": 809
+    },
+    {
+      "epoch": 0.999383096853794,
+      "grad_norm": 1171.58642578125,
+      "learning_rate": 4.260590785121199e-10,
+      "loss": 4.0195,
+      "step": 810
+    },
+    {
+      "epoch": 1.000616903146206,
+      "grad_norm": 823.234130859375,
+      "learning_rate": 0.0,
+      "loss": 4.1185,
+      "step": 811
     }
   ],
   "logging_steps": 1,
@@ -5653,12 +5730,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5313340347777024.0,
+  "total_flos": 5387190162948096.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null