Training in progress, step 6500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e51635e22cc4d8257e3998139dd244d3a6d953d81d24c8fa5749cf91708081
+oid sha256:2a7b457d67a9eb5cfbe8c9ae098756dcf28456fd3707ca3a5da82776be0da1e4
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c5f63ed78dbe211d8e9a6074043dfb4dc7d9bd2f3c157049ec3fccd1fd44d6
+oid sha256:4131a85f9b0ac47effc56de299f7e093cf8226e277467988bc3dbaefdb1121a7
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123058a7e1eae93f8ce60cf6d522b62fb472becdaa34f1380b8c150bfd960932
+oid sha256:ed595d1978ee29b1192dd7efc54ad1f2be2e2a552922b1e943ca4e507e90056b
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd83f394af7b27399972a12ed123bbfca08cbedb65ad8f9f3e082310668cc623
+oid sha256:224d163869c527e678c2b350a35c8c7b6559e6b116331d7305464e9cadf4bede
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.79800031245118,
+  "epoch": 12.99796906733323,
   "eval_steps": 500,
-  "global_step": 6400,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -551,6 +551,21 @@
       "learning_rate": 5.7333333333333336e-05,
       "loss": 1.2384,
       "step": 6400
+    },
+    {
+      "epoch": 12.99796906733323,
+      "grad_norm": 0.21207907795906067,
+      "learning_rate": 5.666666666666667e-05,
+      "loss": 1.2415,
+      "step": 6500
+    },
+    {
+      "epoch": 12.99796906733323,
+      "eval_loss": 1.1073068380355835,
+      "eval_runtime": 779.3448,
+      "eval_samples_per_second": 19.917,
+      "eval_steps_per_second": 2.491,
+      "step": 6500
     }
   ],
   "logging_steps": 100,
@@ -570,7 +585,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.988688273599365e+18,
+  "total_flos": 1.0144763244787532e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null