Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68219a5ca895e88a0af8b5d7a0291a023b16a921e5a7d2c5b3125c9f4a3e9de4
+oid sha256:e193218bd73e781c03e78372f1ee703345a8fe097968f25583a7d361e73c9695
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44bcb6f280640dcf827371bfc2e8e7a9713938aff13cfdcd1dc7e82961aa2eb8
+oid sha256:587a86ac0ed47aa95cdd31710e708f763e40ea8ec66c3aefa7c192f949aebd06
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17cbebe4a9e2c8ad0c518b56649d7131ed53158aace72f907edc100be5f2ba1a
+oid sha256:b9abf883c2e9c09674e212674962f98f5fa416abc3e528367d43967e85b78711
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
+oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02619647355163728,
+  "epoch": 0.05239294710327456,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 14.346,
       "eval_steps_per_second": 7.207,
       "step": 13
+    },
+    {
+      "epoch": 0.04030226700251889,
+      "grad_norm": 0.18682315945625305,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.2885,
+      "step": 20
+    },
+    {
+      "epoch": 0.05239294710327456,
+      "eval_loss": 0.0567830465734005,
+      "eval_runtime": 14.57,
+      "eval_samples_per_second": 14.345,
+      "eval_steps_per_second": 7.207,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4234748029304832.0,
+  "total_flos": 8469496058609664.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null