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:bc5b8361298d83905b59c33a458c409c54e2135768fb1253891af9fe1bfd2820
+oid sha256:ee81a14f1c2a70231980a8df08892685131b8b8dae153c2369e679cd5beb06eb
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:212299ba4b0ae828447f1bf2a45f8aab97752933885c113e4426bcbcc2937e9d
+oid sha256:a7858a785bae90eeed14e864b3a2dcb0498b36f2d9919a6cab48f872a08339fe
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3622d63468ec09dd09d8d03c204beeea583ff91c4753b52b69ac9b5ccb43178
+oid sha256:f730500bfb9f668a2a9a1158e504ec3821a17c5db437fc6af257edab5e2550b8
 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": 0.0022531244499207886,
+  "epoch": 0.0028164055624009857,
   "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": 4.638,
       "eval_steps_per_second": 2.319,
       "step": 4
+    },
+    {
+      "epoch": 0.0028164055624009857,
+      "grad_norm": 13.293079376220703,
+      "learning_rate": 5e-05,
+      "loss": 60.9986,
+      "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": 4764091532967936.0,
+  "total_flos": 5904216002396160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null