Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46cb47f40e4a7796c364f05315ae08acb811947ed345886eda48acc0ec2d2245
+oid sha256:66ab488d7e40a1d0b39ddc7c7ace571182891db00693afc7e42aed087df88315
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c22333630c548e3d961650c7137c3596f60226d48f4845e05fbf9184062f4e7
+oid sha256:4e8b3d4c0385a6b323998a045d9a1d2624a5fb81afeb38bf27538a9531ef3769
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc00b9f52758d38c42c2ddebf352af881abc12afc428f73da93ca1f1a54273a1
+oid sha256:9582f2a47c62efaab6e80993da213463bfbb3239174adb57b1ce595bd9ab9eb0
 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": 0.0443213296398892,
+  "epoch": 0.055401662049861494,
   "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": 5.849,
       "eval_steps_per_second": 2.944,
       "step": 4
+    },
+    {
+      "epoch": 0.055401662049861494,
+      "grad_norm": 3.891878604888916,
+      "learning_rate": 5e-05,
+      "loss": 13.4281,
+      "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": 3298184600223744.0,
+  "total_flos": 4275424481771520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null