Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc401528be5fc9de4bb49982a7dc2a42745c3f4f115ade208627dbca7071c7f8
+oid sha256:b39424892d2b750e22eaa5c0216a3d5de439c4f797acbb4f9c456ba34c8a355e
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6bf2cb94ce5eba23af2a09df9e2a5daa15283bd4cbf0db5a31caaac8e36bb51
+oid sha256:802ed36b7afa5017c93a6fd3510a67856790006ca5398e785e74ab898f545ef4
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb55320a08e50ed394cd960f98070f7af223236ab26cee8318395f23a36d7e2
+oid sha256:26d6b797df47639e9d56f9b6739dd1a2f36c0e6d770b9652f614b93b6b7b4046
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e2941b1419d36fedcd8eb55488740cb386508ea401393ade4c1f5fd25ff6c8
+oid sha256:8074483b54111bf60815c86124b01e5486a0c97c3c0bcc7642d6609b17e4381b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019561097866617763,
+  "epoch": 0.022006235099944985,
   "eval_steps": 34,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -303,6 +303,41 @@
       "learning_rate": 0.0001982973099683902,
       "loss": 9.481,
       "step": 40
+    },
+    {
+      "epoch": 0.020050125313283207,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001979409767601366,
+      "loss": 9.684,
+      "step": 41
+    },
+    {
+      "epoch": 0.02053915275994865,
+      "grad_norm": 1.0845123650277868e+18,
+      "learning_rate": 0.00019755119679804367,
+      "loss": 9.2871,
+      "step": 42
+    },
+    {
+      "epoch": 0.021028180206614098,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001971281031916114,
+      "loss": 9.423,
+      "step": 43
+    },
+    {
+      "epoch": 0.02151720765327954,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019667184042691875,
+      "loss": 8.6827,
+      "step": 44
+    },
+    {
+      "epoch": 0.022006235099944985,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019618256431728194,
+      "loss": 9.9237,
+      "step": 45
     }
   ],
   "logging_steps": 1,
@@ -322,7 +357,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.817918703828992e+16,
+  "total_flos": 9.920158541807616e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null