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:c500298635f7f365e66642d13076e04ae0146bb7ae2e95339f31ae4ee725d984
+oid sha256:2545a4bb4790c7ba5938defba3bca1579bec29e88cb73ca54f5c1093f4d554f6
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b9a7e0d1d1d03f718e04ce7d7ff87b2aa0adfd5f41eb1d0917d5d056c2f0e6f
+oid sha256:6461d7101e32a552925fae21aa4bfdfe4ab62a39f8d8f2e7c6fc06cc41f05c2c
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:017583d2bd93fe9910a82ceabe249f8fabc7dfeef29c7c3f997a8f45e0fab04d
+oid sha256:a8636caf43895d122986dcf9c0f3f784244e32146c2903687980280124315561
 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": 0.10596026490066225,
+  "epoch": 0.13245033112582782,
   "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": 52.436,
       "eval_steps_per_second": 26.218,
       "step": 4
+    },
+    {
+      "epoch": 0.13245033112582782,
+      "grad_norm": 3.482865810394287,
+      "learning_rate": 5e-05,
+      "loss": 8.0298,
+      "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": 1312077863976960.0,
+  "total_flos": 1640097329971200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null