Training in progress, step 6000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8045ece01cd2aeb9d499a0320e1f22286bdc8cfcfe61a226664746e07c3c5f60
+oid sha256:4449773cebb7fc20f1afa5ae5d77b8cd35bef0c0950cae40c99ea43ed9adf3f2
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005e7de3abb84635dafdee3a8ba79cb585547bd0f0048be0efc20bee6a04b734
+oid sha256:a25d83ef5b65b44f7e3171cf437447867602a77559bcaf513ab95836cec436f4
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf21107d6237c1a47582df5d14262b3f30a2235c4b055ac43a59cd75f5a56ee5
+oid sha256:ef2d74e185f05924f3efb59e8e62402934923eb6095702f1ed9ee86b4e99fff7
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b174702c9c1953310bc2ab4fc08bf447a0a35d9790cc4ddb43424b44578611a9
+oid sha256:527c464a68510f76edc995cc9b4702aff5ce3e29350f6f2b9760ebf8e1ca430b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.798156538040931,
+  "epoch": 11.99812529292298,
   "eval_steps": 500,
-  "global_step": 5900,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -508,6 +508,21 @@
       "learning_rate": 6.066666666666667e-05,
       "loss": 1.25,
       "step": 5900
+    },
+    {
+      "epoch": 11.99812529292298,
+      "grad_norm": 0.20437301695346832,
+      "learning_rate": 6e-05,
+      "loss": 1.2491,
+      "step": 6000
+    },
+    {
+      "epoch": 11.99812529292298,
+      "eval_loss": 1.128514289855957,
+      "eval_runtime": 781.5324,
+      "eval_samples_per_second": 19.861,
+      "eval_steps_per_second": 2.484,
+      "step": 6000
     }
   ],
   "logging_steps": 100,
@@ -527,7 +542,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.208322574528807e+18,
+  "total_flos": 9.364397545716974e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null