Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81bde0aae8837ed19571f0f8c5dc71f3c6989da9bec55ad16bb9dec1e3643c97
+oid sha256:2e7b8e9b6295a356129c59cde4f1152c1db11bc663836917d425450bfce345b6
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f5be0378705aada461003107f16b5c332b7ef8b7e5239415d5a1de983b751c
+oid sha256:a70ed0e3f0b7439a06178086cd5cf01da1c877e1ab0d70ade11ff26054c015c6
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dbe0665e344abacc9ba1e04db32045ed0d8c84a58a5f55b900778977fb22211
+oid sha256:b1810486755b47aa8ae2c2015ae8fbd6e5e8857415c5c40ce9c14fa31dd1704f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:dbc80592076e3de5c30633981a2d6dac803c7697f6a99bf37e58d1e2912b1fda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7659574468085106,
+  "epoch": 1.0212765957446808,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 48.077,
       "eval_steps_per_second": 7.211,
       "step": 9
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 4.869143962860107,
+      "learning_rate": 9.85470908713026e-05,
+      "loss": 3.4585,
+      "step": 12
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "eval_loss": 2.945756196975708,
+      "eval_runtime": 0.4153,
+      "eval_samples_per_second": 48.158,
+      "eval_steps_per_second": 7.224,
+      "step": 12
     }
   ],
   "logging_steps": 3,
@@ -79,7 +94,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1801738109583360.0,
+  "total_flos": 2402317479444480.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null