Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64fe324201198ecf3af98629db0af4e59548ca3c6b550c12d14dc41dfab772c8
+oid sha256:61136b09a2b8ac4e223e0f16dd6ecf69776a4c73041c6d38dcd930ee42f4f799
 size 84962944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc21f0987a492d82020f9a1aa1e77f263acdc00435e20f94243a94fdb784ac9
+oid sha256:0e34f2bd00cf561183e6e645bb69b8c6ee2fbd46f2a55fb6541980df3d5d75e3
 size 43387339

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d8db17747030f5d613faf5ecad21dd31237f7cfe2a3d43890508c73168ad73a
+oid sha256:de60822a00d4f561240fe390f6c61ae9ba93eb01cc7b55814288b50ba292b543
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.29914529914529914,
+  "epoch": 0.3418803418803419,
   "eval_steps": 100,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -253,6 +253,41 @@
       "learning_rate": 9.549150281252633e-07,
       "loss": 1.106,
       "step": 35
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 1.2472528219223022,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 1.1393,
+      "step": 36
+    },
+    {
+      "epoch": 0.3162393162393162,
+      "grad_norm": 1.164663314819336,
+      "learning_rate": 4.322727117869951e-07,
+      "loss": 1.1401,
+      "step": 37
+    },
+    {
+      "epoch": 0.3247863247863248,
+      "grad_norm": 1.0847811698913574,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 1.0773,
+      "step": 38
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.0488321781158447,
+      "learning_rate": 1.0926199633097156e-07,
+      "loss": 1.0729,
+      "step": 39
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 1.4393736124038696,
+      "learning_rate": 2.7390523158633552e-08,
+      "loss": 1.1257,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -276,12 +311,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.07642470796288e+16,
+  "total_flos": 2.36602090171392e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null