Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d7518a9365b41e9492afb9d796a28fdd9dcc26ac9f0810fe3996c2899eda10
+oid sha256:3b00dc807935be20d9a6bddb1282b682beeb4858655e620ff09ec01a3de09831
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fbb04863ea3ddd98a5b253c212079231b0889a6d8ab5f84e9ea1b8b4dae1bf9
+oid sha256:795553d7bb94e79e1853c38578ba6e1100f9e64c3cf28a23bceded75498b0203
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a55ac0c992411009853207820ca4f6897afa3f8dc742e986d6f2be555193f7
+oid sha256:0ee1401b0d4ac8e23c2134fe48887a67064fe5b30afe986a2496bc66800cfca5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:00ac470d61d5b4613444f686474fe5bf71dbe645a07555e3c0011199a78b17ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.782608695652174,
+  "epoch": 1.0434782608695652,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -46,6 +46,21 @@
       "eval_samples_per_second": 6.602,
       "eval_steps_per_second": 3.961,
       "step": 9
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 29.091482162475586,
+      "learning_rate": 0.0001,
+      "loss": 36.0964,
+      "step": 10
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "eval_loss": 4.865574836730957,
+      "eval_runtime": 0.758,
+      "eval_samples_per_second": 6.596,
+      "eval_steps_per_second": 3.958,
+      "step": 12
     }
   ],
   "logging_steps": 5,
@@ -60,12 +75,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3562002343526400.0,
+  "total_flos": 4709758654218240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null