Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc0c1a135aa68571c6c527eecb59a16789a748f7ba99159860e48b47402ed94
+oid sha256:b6c97adab3013642eb25d94b27cfebb499b1f8516c796ed01deb12ea0b0d4179
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c427c539b2045c4d7d6e0da30df9c92aff5e3efbe8f6322287bbaf83fb1ecf1a
+oid sha256:b2f1124adad1b4d83b1e9350572119c94cafa3de4811d2913b6047b05db5b213
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae572e8a25a0320dba5bf5c52c1467793b288c5f787b6c377596682acfe21d6f
+oid sha256:85d7dcb82cc9c8edaa0c5feb250680d2ea54a2f1b97d0e9fe9ea7b25c22b72c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8421052631578947,
+  "epoch": 1.1578947368421053,
   "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": 220.364,
       "eval_steps_per_second": 110.182,
       "step": 4
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 3.7224624156951904,
+      "learning_rate": 0.0001,
+      "loss": 44.2848,
+      "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": 77158416384.0,
+  "total_flos": 96448020480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null