Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c5b7ae63a3b539b94f7289128e6338295caff2aba10e498ccc03408e8318a7
+oid sha256:3c2f03af4311dc138d44ee080c4c54bf827162b5912fc4f30a1ecdc61a78ca23
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42fa34b8dbfceff65894ec1b12469678676fc40452dd349c8f646df1b749023f
+oid sha256:7c6631a7c771c022dbd9784116027abace2643cbc152ec650ce0005a5d5f2ab7
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
+oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
 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": 0.10372771474878444,
+  "epoch": 0.12965964343598055,
   "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": 265.15,
       "eval_steps_per_second": 134.614,
       "step": 4
+    },
+    {
+      "epoch": 0.12965964343598055,
+      "grad_norm": 8.449214935302734,
+      "learning_rate": 5e-05,
+      "loss": 9.4912,
+      "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": 1048936710144.0,
+  "total_flos": 1311170887680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null