Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c7c80b30c00862c3f04b6da7cda4e9a8bdd0a398aa26b5c7394ea3b1d7aed7
+oid sha256:689df16ab549aa184837d309deb235fdd528e1a00d3a769065218a672176bea3
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d56ffdbbb5262b6de34ae3f27b9a21923a59e3fd961322546d38a8e94c7c2c2
+oid sha256:dc70560e09f4b241232c1a206df3bc5595fe56d674434ae6a23814919cd6de38
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b85494d654ca3bad691b5c77e861826b4c6af03f4ee7066fd965552b5b2589
+oid sha256:53f4f45187e26a4049e655bf2331e2a9bcb87445e02e0e30a1e6d4e3a5463624
 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": 0.06948968512486428,
+  "epoch": 0.08686210640608034,
   "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": 19.794,
       "eval_steps_per_second": 9.999,
       "step": 4
+    },
+    {
+      "epoch": 0.08686210640608034,
+      "grad_norm": 2.2628250122070312,
+      "learning_rate": 5e-05,
+      "loss": 17.5337,
+      "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": 5171278843478016.0,
+  "total_flos": 6433559506059264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null