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:b002dca4a99d77985055026a30fbe3dd493ef525e449d627fcdbddd8a53df9f1
+oid sha256:867c7851e1c578800dacb8f9b9b5f069488c31ebb8663a8feb3597b9aefc1147
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88607babbfb5b750543771bcef37834276881dfe07f5850935510a77bdecb547
+oid sha256:64c7bee1b91963e20b96c56d91b54b51bd4f5cd2064962c7e9670d6f7690463c
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd19e18c4ac18e3c1719cc1acfa191482fdb0394cd8eba0fe84d1e0799ffc4cb
+oid sha256:f403cb5e05ae1077a947e2a55947ef4aa0ffcee6d22e5bec100d80304d34344d
 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": 0.08642659279778393,
+  "epoch": 0.11080332409972299,
   "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": 1.1119,
       "step": 35
+    },
+    {
+      "epoch": 0.0886426592797784,
+      "grad_norm": 3.5795576572418213,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7674,
+      "step": 40
+    },
+    {
+      "epoch": 0.0886426592797784,
+      "eval_loss": 0.19981133937835693,
+      "eval_runtime": 9.2512,
+      "eval_samples_per_second": 20.538,
+      "eval_steps_per_second": 10.269,
+      "step": 40
+    },
+    {
+      "epoch": 0.0997229916897507,
+      "grad_norm": 2.522779703140259,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7484,
+      "step": 45
+    },
+    {
+      "epoch": 0.11080332409972299,
+      "grad_norm": 4.731848239898682,
+      "learning_rate": 0.0,
+      "loss": 0.9143,
+      "step": 50
+    },
+    {
+      "epoch": 0.11080332409972299,
+      "eval_loss": 0.18646377325057983,
+      "eval_runtime": 9.1208,
+      "eval_samples_per_second": 20.831,
+      "eval_steps_per_second": 10.416,
+      "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": 3580018173149184.0,
+  "total_flos": 4589766888652800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null