Training in progress, step 3620, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d62c631ca13cfab3a8d4e18d1338c8812ac7251234fda355f962f76c871066
+oid sha256:62bf22c6eeae733bf8b6cecf81b15e2b37848eb3b634eababf70fb6e6cccfec6
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a7aeac9850dfd4db801131fdbab98330fcd65542d55a2e5dc82fa5741fbbe3
+oid sha256:895f7436cc35982b7d3d069fb09940e4f049b1cd096fe6488c076caa50d97d4f
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3d6dc000d3ba51393607c0971658acfb92d6dc5b372d9d0679847e9b97f57f
+oid sha256:fedadc5ef75b1128f404f29cb98838b62424119c20db612c5cd0c4e91792a88a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed823fd53aa11b151a56285d111464eb705a2816abfaf8a7d50c1ca9441a3e0d
+oid sha256:d232e6df33e1c271d4fc7f5958443fe46136e9ed27fdf469d7b0e41f315c0be2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.288,
+  "epoch": 0.2896,
   "eval_steps": 500,
-  "global_step": 3600,
+  "global_step": 3620,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1267,6 +1267,13 @@
       "learning_rate": 2.8264432360950355e-05,
       "loss": 3.5626,
       "step": 3600
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 27.4322509765625,
+      "learning_rate": 2.8241678862842374e-05,
+      "loss": 3.4831,
+      "step": 3620
     }
   ],
   "logging_steps": 20,
@@ -1274,7 +1281,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8519236213211136.0,
+  "total_flos": 8562835271024640.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null