Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac2d927879e78c01b3d9c98eadc02a1f3c184ca2aa7a3b2d11d46c32ccfe4c5b
+oid sha256:22a5a523639e4345c8f9892f28eea1e3ddefc415f2e77d390583705b09935b9a
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9362519b342a46efb766dc3221299ad2e9eab812acfde9fa15de722c81a3a40
+oid sha256:c038a80ef8a737781d0d9936f647744dc1262eedf0a13251dbc744666d59e9dd
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22601140bc0a5947d3bbd230e18458f69ce95eeff744ca680f4ea6f1cc378d76
+oid sha256:9c6cff4d5bf4f723b4386917a94c13959044ca8b78e9b96fc527344366f401d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0038429324530718824,
+  "epoch": 0.004926836478297285,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 2.2228,
       "step": 35
+    },
+    {
+      "epoch": 0.003941469182637828,
+      "grad_norm": 3.1860170364379883,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.9985,
+      "step": 40
+    },
+    {
+      "epoch": 0.003941469182637828,
+      "eval_loss": 1.819312334060669,
+      "eval_runtime": 80.008,
+      "eval_samples_per_second": 53.407,
+      "eval_steps_per_second": 26.71,
+      "step": 40
+    },
+    {
+      "epoch": 0.004434152830467557,
+      "grad_norm": 3.8627407550811768,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1064,
+      "step": 45
+    },
+    {
+      "epoch": 0.004926836478297285,
+      "grad_norm": 2.9635887145996094,
+      "learning_rate": 0.0,
+      "loss": 1.8765,
+      "step": 50
+    },
+    {
+      "epoch": 0.004926836478297285,
+      "eval_loss": 1.784060001373291,
+      "eval_runtime": 80.2157,
+      "eval_samples_per_second": 53.269,
+      "eval_steps_per_second": 26.641,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 209185167900672.0,
+  "total_flos": 273483887542272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null