Training in progress, step 440, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ece4e08fcec4f53177a8b2e2b6d2babfc5c01c11b20dd8126e91cac63f3b6674
+oid sha256:496842e7f2f28cf6609e2c51f5445b2abce01f89983ddc9b7dbabf8c99c72a72
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a6e18c800c7df61d36d03db92efe55f416f55663c65b72b25b54087d88a0584
+oid sha256:23b4e5fca0a770ca2dd365b99753da86acbbb70f3bf7a9af724dfeb95dfd0ff8
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6a8c1353fe1f0e8a0df954c933901204f4ed941775054c3374dadc90cbf8926
+oid sha256:f00c9275258cd29c9fcbc7397822ab820104ea2b405434287c23b89bf231c018
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ddfafb5df2322727e61f078a84cbb67789f5c46f0475753d1af86c857994fb
+oid sha256:ea120316488c31675750bd3088d0c45da519fe18337e624e504a412ce72bc4c2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15026833631484796,
+  "epoch": 0.15742397137745975,
   "eval_steps": 500,
-  "global_step": 420,
+  "global_step": 440,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,14 +343,30 @@
       "loss": 0.4384,
       "num_input_tokens_seen": 277913,
       "step": 420
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.38349634408950806,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.445,
+      "num_input_tokens_seen": 285726,
+      "step": 430
+    },
+    {
+      "epoch": 0.15742397137745975,
+      "grad_norm": 0.298753559589386,
+      "learning_rate": 0.00016851520572450806,
+      "loss": 0.411,
+      "num_input_tokens_seen": 293886,
+      "step": 440
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 277913,
+  "num_input_tokens_seen": 293886,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 6249281950255104.0,
+  "total_flos": 6608458313330688.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null