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:f0178be067ac65805db80c95bbf31e69d49734ba8845c4bb7259b40aa596b230
+oid sha256:bb94fd4d642a5143f5a4972a751a6e5475f04ffe7bffb41836d6c7572c82b279
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:372e3ce89099b7104242f05488609a76f7430b7e4ad173ae3b924848ff51e9da
+oid sha256:f883efc8573a0040fae4036f23763f25310ed6b7ee49bdcb1884220d1418f1a9
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f8b91120619feb1585cba580a6a98957acf1b4c9f5f1cea79e86ee7d06592f7
+oid sha256:feb90156f1219f3a8cdb3af25d9ccb118c085c326f882a7888f0d134a710494c
 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": 0.12611156022635409,
+  "epoch": 0.16168148746968472,
   "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": 0.0412,
       "step": 35
+    },
+    {
+      "epoch": 0.1293451899757478,
+      "grad_norm": 0.6948058605194092,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.035,
+      "step": 40
+    },
+    {
+      "epoch": 0.1293451899757478,
+      "eval_loss": 0.039624977856874466,
+      "eval_runtime": 4.2967,
+      "eval_samples_per_second": 30.489,
+      "eval_steps_per_second": 15.361,
+      "step": 40
+    },
+    {
+      "epoch": 0.14551333872271624,
+      "grad_norm": 0.7251969575881958,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0335,
+      "step": 45
+    },
+    {
+      "epoch": 0.16168148746968472,
+      "grad_norm": 0.3649747371673584,
+      "learning_rate": 0.0,
+      "loss": 0.039,
+      "step": 50
+    },
+    {
+      "epoch": 0.16168148746968472,
+      "eval_loss": 0.03815101832151413,
+      "eval_runtime": 4.2105,
+      "eval_samples_per_second": 31.113,
+      "eval_steps_per_second": 15.675,
+      "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": 420705323974656.0,
+  "total_flos": 532003028729856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null