Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148b3f58fae8c8a06316fd764b587fb093a5d2743d21eea65d18abaead059447
+oid sha256:6a5dfb10180f0909c155f08d43496ef679ff03db1f6f9aeaafcf44f12fd3b602
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dded87de65dd8b39543f26d7fccd35a576b0c2947c4e3122395244c33232f052
+oid sha256:80fe6818193927d848c3b2eb952c361fd746480bc8870be6c96c9a730ae057f6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69760d704f2e1f2ae55fb0e41b4294d3fa392d7fec1a79bfd80e4b1c835abbe
+oid sha256:3f3307296a42e8f573fc3a64befd53fc8cb03a86b9c9f3f5a632ea762f4da55c
 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": 0.016632903294594305,
+  "epoch": 0.021324234993069624,
   "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": 0.4063,
       "step": 35
+    },
+    {
+      "epoch": 0.0170593879944557,
+      "grad_norm": 4.373198986053467,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3335,
+      "step": 40
+    },
+    {
+      "epoch": 0.0170593879944557,
+      "eval_loss": 0.35587215423583984,
+      "eval_runtime": 67.6937,
+      "eval_samples_per_second": 14.595,
+      "eval_steps_per_second": 7.298,
+      "step": 40
+    },
+    {
+      "epoch": 0.019191811493762662,
+      "grad_norm": 1.7283074855804443,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4505,
+      "step": 45
+    },
+    {
+      "epoch": 0.021324234993069624,
+      "grad_norm": 1.1647988557815552,
+      "learning_rate": 0.0,
+      "loss": 0.4512,
+      "step": 50
+    },
+    {
+      "epoch": 0.021324234993069624,
+      "eval_loss": 0.3501424491405487,
+      "eval_runtime": 68.0406,
+      "eval_samples_per_second": 14.521,
+      "eval_steps_per_second": 7.26,
+      "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": 7213300567769088.0,
+  "total_flos": 9294060346933248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null