Training in progress, step 420, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642fa6ea93c5328a689db3c12119bd05458197b5485e216e3956041034addce5
+oid sha256:ece4e08fcec4f53177a8b2e2b6d2babfc5c01c11b20dd8126e91cac63f3b6674
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8378598f65d8748972165126ccc549178508d4ee275fc11095ac033bbfcd0d94
+oid sha256:5a6e18c800c7df61d36d03db92efe55f416f55663c65b72b25b54087d88a0584
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a11114094a1bb5fd000ee0ef08e018069d40428a8429f7375de3021f2c81601
+oid sha256:b6a8c1353fe1f0e8a0df954c933901204f4ed941775054c3374dadc90cbf8926
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fdd00fe5e4ffe28b2f553058edb3aaca4dc6f249363b91632307b35ded3965d
+oid sha256:05ddfafb5df2322727e61f078a84cbb67789f5c46f0475753d1af86c857994fb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14311270125223613,
+  "epoch": 0.15026833631484796,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -327,14 +327,30 @@
       "loss": 0.4338,
       "num_input_tokens_seen": 265411,
       "step": 400
+    },
+    {
+      "epoch": 0.14669051878354203,
+      "grad_norm": 0.5467566251754761,
+      "learning_rate": 0.00017066189624329162,
+      "loss": 0.4336,
+      "num_input_tokens_seen": 271069,
+      "step": 410
+    },
+    {
+      "epoch": 0.15026833631484796,
+      "grad_norm": 0.4278429448604584,
+      "learning_rate": 0.00016994633273703042,
+      "loss": 0.4384,
+      "num_input_tokens_seen": 277913,
+      "step": 420
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 265411,
+  "num_input_tokens_seen": 277913,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 5968156119717888.0,
+  "total_flos": 6249281950255104.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null