Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab139769b1ce01fb0eccd5833f039bf63534d937a9f6dc8ac70cf3883a573c43
+oid sha256:85aad284871b62b00a73e8fc641cab3af5bd2c499204fdb9b630cefdfea11d1f
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc1f816b0a5291236f19614653ee72c47a7db61f5e5dbe35dbb13baf79dfe52
+oid sha256:3ef456faadeb9f254c9bfde69181b35c4f6d1896449f0c7549ed16c51a149c2d
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:698d42f077395087a77cd20be154b962f1e208f7eb195c0a7c3f2c1462e59a86
+oid sha256:cc9b6d91735628d9c4570f30e2ae7146ca114da7eff9da6e536a6a4c88a2a732
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03804994054696789,
+  "epoch": 0.04756242568370987,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 13.71,
       "eval_steps_per_second": 6.855,
       "step": 4
+    },
+    {
+      "epoch": 0.04756242568370987,
+      "grad_norm": 2.8572473526000977,
+      "learning_rate": 5e-05,
+      "loss": 28.2054,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8627906370600960.0,
+  "total_flos": 1.060678397853696e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null