Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc52f91434af4db1100dd3e8e136eb03a37c9f4374f83d059832fdaa3947342
+oid sha256:b60439a1f6279b1545caad569ae03f5acb54d0d8f99f69925a98d3792ec6a46a
 size 2185308216

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2aff6624efc66dc7bf92409977e54b5eb2dd6e4365ca56f81d109a3c3b98595
+oid sha256:89d641fcc9392f4e0f73fc96e5efc39eb99c9dedb2a57faee035feb8e3a6aeab
 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": 0.006581445386659917,
+  "epoch": 0.00843775049571784,
   "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": 0.2461,
       "step": 35
+    },
+    {
+      "epoch": 0.006750200396574273,
+      "grad_norm": 0.7081021666526794,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2155,
+      "step": 40
+    },
+    {
+      "epoch": 0.006750200396574273,
+      "eval_loss": 0.22639888525009155,
+      "eval_runtime": 174.0491,
+      "eval_samples_per_second": 14.335,
+      "eval_steps_per_second": 7.17,
+      "step": 40
+    },
+    {
+      "epoch": 0.007593975446146058,
+      "grad_norm": 0.6287571787834167,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2266,
+      "step": 45
+    },
+    {
+      "epoch": 0.00843775049571784,
+      "grad_norm": 0.8315374851226807,
+      "learning_rate": 0.0,
+      "loss": 0.2271,
+      "step": 50
+    },
+    {
+      "epoch": 0.00843775049571784,
+      "eval_loss": 0.22569622099399567,
+      "eval_runtime": 172.191,
+      "eval_samples_per_second": 14.49,
+      "eval_steps_per_second": 7.248,
+      "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": 7213304493637632.0,
+  "total_flos": 9247826273894400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null