Training in progress, step 349, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29f690d14438f6e3cdf833fa2f4ab04a5fb0513845d4e9725f23ef543afb0ec1
+oid sha256:6778c35d7237cda41f150fe226d7ad2b42a18571675e22e19b37130222805000
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb96b39f96671416517824843ba7f65a0cc13e6fd2e4a1ff0f867425e9967b36
+oid sha256:c0a4ae9caa1f7c350f9c7e85a253ed14dc3b50d5c7f44e3ac1655fbd5849f58f
 size 37431220

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248bdad94673d0171b6613a2054004ce1fbd7cc6609011663f62eb8bd70a3480
+oid sha256:7ca002fadce970e2797672d78741b69114f9a264197843fa3e3305d06f80f89f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9465020576131687,
+  "epoch": 0.9574759945130316,
   "eval_steps": 500,
-  "global_step": 345,
+  "global_step": 349,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2422,6 +2422,34 @@
       "learning_rate": 1.4393939393939396e-05,
       "loss": 1.1708,
       "step": 345
+    },
+    {
+      "epoch": 0.9492455418381345,
+      "grad_norm": 0.15814326703548431,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 1.1695,
+      "step": 346
+    },
+    {
+      "epoch": 0.9519890260631001,
+      "grad_norm": 0.15282317996025085,
+      "learning_rate": 1.287878787878788e-05,
+      "loss": 1.2195,
+      "step": 347
+    },
+    {
+      "epoch": 0.9547325102880658,
+      "grad_norm": 0.16384905576705933,
+      "learning_rate": 1.2121212121212122e-05,
+      "loss": 1.1989,
+      "step": 348
+    },
+    {
+      "epoch": 0.9574759945130316,
+      "grad_norm": 0.16359828412532806,
+      "learning_rate": 1.1363636363636365e-05,
+      "loss": 1.0967,
+      "step": 349
     }
   ],
   "logging_steps": 1,
@@ -2441,7 +2469,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.277394643660677e+17,
+  "total_flos": 4.323960827284808e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null