Training in progress, step 2600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72117a71368ced5e54ae93d21ad8c58e91215e17e67c439bf35beb716448c540
+oid sha256:7f528d4e1e118fd058ce8612a51a8b683c0ae18ff5e56e846fc45ba25bdd3a01
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ec71681264a4e6df68bd6631ea2eedd8d07d066b65f39d1984f0723e362d2a
+oid sha256:34410c7904a7ac2cbf8aa6159b17ea65f1764d31633c60b10d1fbda1f68674ff
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edb8f7923ee0e8daac5e34b79e2823d1578191c5c180db7ca2ba4be0e2deec91
+oid sha256:25aa0a451bb78aa5352fe766b097eaa4c0e4847b6d8da871b98427e96ea98409
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:908e1b653c7ae160cec9eddd33f8d8b292344f12ebe951b0f4e9be7145ee92a3
+oid sha256:b9740bfa78fc7c7cfb6225556d4b5d68675130a10cc5f5c93667c4631894c9f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.999218872051242,
+  "epoch": 5.199187626933291,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -222,6 +222,13 @@
       "eval_samples_per_second": 19.89,
       "eval_steps_per_second": 2.487,
       "step": 2500
+    },
+    {
+      "epoch": 5.199187626933291,
+      "grad_norm": 0.1629934012889862,
+      "learning_rate": 8.266666666666667e-05,
+      "loss": 1.2835,
+      "step": 2600
     }
   ],
   "logging_steps": 100,
@@ -241,7 +248,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.901837652223066e+18,
+  "total_flos": 4.0579034665409577e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null