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:d81aff95ef2b49f0270d23d471759e2aeda1a53aa96db80e226aca95d2ff12a6
+oid sha256:fe512dfb29a667d579c67b397c06b890b72a917ce9f29d4ba420108d8744bcb8
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79df5b90e03f9325d217c2ff32dd9516804be0f39df6bfdd6b9831faa6bf79bc
+oid sha256:4a6d9f2abc9f0d0228a0da3145c606bfa16d0b97ef6657db00b2eac0979f8858
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4338e60828af3efb3dbfac479ffbce4cf22f201f32dd76c072dd2215e2af458f
+oid sha256:f2b17376c2094a7843882b205fe5baa2fba28ee9afa48547a0118f514aace90e
 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": 0.04191224623444663,
+  "epoch": 0.05239030779305828,
   "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": 27.658,
       "eval_steps_per_second": 13.915,
       "step": 4
+    },
+    {
+      "epoch": 0.05239030779305828,
+      "grad_norm": 119.91407012939453,
+      "learning_rate": 5e-05,
+      "loss": 150.8875,
+      "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": 2605998787264512.0,
+  "total_flos": 3257498484080640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null