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:af9fb914e00c0e0e737e0ff96b223fe9a6ade31f498318281258007098227240
+oid sha256:1c76972ba45e8f07c26cc3d6f185160512caf46e83ac72d968e446889267bd21
 size 114106856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e63b60b5c926c0552a4f0c1734a578c279dfa393709970a17a7848773abfbf0
+oid sha256:95fad8548c00ad2afe44a1aa4476353372bf055f94620647fd343ba7b5034f1f
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2556a93e19ae846c23294d8d1538c98306480c21d3cb7a74daeea73db340a640
+oid sha256:666eb058ba2fef45ad8e5a43df5734ee939f73967fffe4f4679099694b63c6af
 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": 0.13131313131313133,
+  "epoch": 0.16835016835016836,
   "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": 3.9849,
       "step": 35
+    },
+    {
+      "epoch": 0.13468013468013468,
+      "grad_norm": 4.391538143157959,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.5289,
+      "step": 40
+    },
+    {
+      "epoch": 0.13468013468013468,
+      "eval_loss": NaN,
+      "eval_runtime": 12.2331,
+      "eval_samples_per_second": 10.218,
+      "eval_steps_per_second": 5.15,
+      "step": 40
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 2.927791118621826,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.1491,
+      "step": 45
+    },
+    {
+      "epoch": 0.16835016835016836,
+      "grad_norm": 3.123246192932129,
+      "learning_rate": 0.0,
+      "loss": 3.493,
+      "step": 50
+    },
+    {
+      "epoch": 0.16835016835016836,
+      "eval_loss": NaN,
+      "eval_runtime": 12.1227,
+      "eval_samples_per_second": 10.311,
+      "eval_steps_per_second": 5.197,
+      "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": 1.112316825305088e+16,
+  "total_flos": 1.4260472119296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null