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:ce8c808afacb7fbee57b88c127ecba5ee2a95ae3a4b5e7ba3c495549826af3ca
+oid sha256:8eafc0bf8316b7d8ede1d99a54715e59f448548a44d03d4dc368501ac4efab61
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5738b12d415ae050b9d363a55cceff437f756bd3b8e35c7cfabc1fdd10e0813
+oid sha256:b752ec1b57e73af74f1485db35f733645930080caa2db7b6fdb062da6f2a06c1
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d749933c4ae0e13906c2c4dc83e3c7c272831757538edb307b6966642ce349f3
+oid sha256:578055e83066e94f71a09ed1f9b5ae40967f9ee508ea7fb325a884478f45f6fd
 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": 0.05263157894736842,
+  "epoch": 0.06578947368421052,
   "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": 27.306,
       "eval_steps_per_second": 13.759,
       "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 4.95294189453125,
+      "learning_rate": 5e-05,
+      "loss": 25.7056,
+      "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": 2605973017460736.0,
+  "total_flos": 3257466271825920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null