Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ff4018cc68d0c4eab68f107c1eddc244a01e8ba4be21a78bd0f25b95b01a764
+oid sha256:710622f51c3554eca2cbf3c7df2b48eebf3d543a90b780742f15dbb751da0b70
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1efd83e7a00934e4b02087aec4a090b27f2073a1cac24414faf52e9b8ba6fb2
+oid sha256:01c0f9d6cfe928f6e20c6eda80bd5da611ff482af90c6e5e461d323b8248c471
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d28201f0126faf38a83e22d31d1cfdd236bc21e2e3324353e3c96874a21511cf
+oid sha256:6ceab66a658e861b805a0cf06001bd440b791d57f3c1adcc58fd694d15c32a31
 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": 0.005346253445827416,
+  "epoch": 0.00668281680728427,
   "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": 17.235,
       "eval_steps_per_second": 8.624,
       "step": 4
+    },
+    {
+      "epoch": 0.00668281680728427,
+      "grad_norm": 3.189303398132324,
+      "learning_rate": 5e-05,
+      "loss": 47.6916,
+      "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": 4560497877712896.0,
+  "total_flos": 5782059809243136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null