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:aafd93f17562bfb27a8d294db7d0204a55a25e2b2d442c21b672077ee8254fe5
+oid sha256:99170d238a6513674614132e69695004104e9e1ff84880ecb7487d572f13e77d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf517d50b3420e521880ce75d9dc1332ca9b5088b7a6f215766e40fddeb8911d
+oid sha256:173897b231ace6da51140db1281b72a375ec5502a92c89a45ae2a6fc4f901df2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
+oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
 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": 0.02658033736582041,
+  "epoch": 0.03407735559720566,
   "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": 0.7241,
       "step": 35
+    },
+    {
+      "epoch": 0.027261884477764526,
+      "grad_norm": 10.225706100463867,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5404,
+      "step": 40
+    },
+    {
+      "epoch": 0.027261884477764526,
+      "eval_loss": 0.7299230098724365,
+      "eval_runtime": 51.8588,
+      "eval_samples_per_second": 11.917,
+      "eval_steps_per_second": 5.958,
+      "step": 40
+    },
+    {
+      "epoch": 0.03066962003748509,
+      "grad_norm": 7.497749328613281,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7514,
+      "step": 45
+    },
+    {
+      "epoch": 0.03407735559720566,
+      "grad_norm": 5.096440315246582,
+      "learning_rate": 0.0,
+      "loss": 0.3999,
+      "step": 50
+    },
+    {
+      "epoch": 0.03407735559720566,
+      "eval_loss": 0.5272278785705566,
+      "eval_runtime": 51.9113,
+      "eval_samples_per_second": 11.905,
+      "eval_steps_per_second": 5.952,
+      "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": 7213426195562496.0,
+  "total_flos": 9247982302003200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null