Training in progress, step 43, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc83c1975c88628e75d88aeff663229b3fbf8d943db400ac9d72cdcf2bb25a14
+oid sha256:7e89650429cbdfa146df9015df1adbcb3beed183481290191dd826fc8fa31137
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:806760f9dc53a51525f42428757487044f6c0c32b297800c006f40dda5152cd8
+oid sha256:a3d1d3a9ff1d8b79f932b40efa4481c9bd5e0a2b133f720b45a26c0ecc237390
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b44dea3ad58c35a851c6c3b01ef1e891935a61fd8de378737c8e03c1674ab0
+oid sha256:b400700e79e07fa15b6108daabc92cf187c780841793bebce678a2b9d02d3d6c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10699588477366255,
+  "epoch": 0.11796982167352538,
   "eval_steps": 500,
-  "global_step": 39,
+  "global_step": 43,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -280,6 +280,34 @@
       "learning_rate": 7.800000000000001e-05,
       "loss": 1.4134,
       "step": 39
+    },
+    {
+      "epoch": 0.10973936899862825,
+      "grad_norm": 0.11528003960847855,
+      "learning_rate": 8e-05,
+      "loss": 1.4896,
+      "step": 40
+    },
+    {
+      "epoch": 0.11248285322359397,
+      "grad_norm": 0.11622235178947449,
+      "learning_rate": 8.2e-05,
+      "loss": 1.3957,
+      "step": 41
+    },
+    {
+      "epoch": 0.11522633744855967,
+      "grad_norm": 0.10983709245920181,
+      "learning_rate": 8.4e-05,
+      "loss": 1.421,
+      "step": 42
+    },
+    {
+      "epoch": 0.11796982167352538,
+      "grad_norm": 0.10124485194683075,
+      "learning_rate": 8.6e-05,
+      "loss": 1.4127,
+      "step": 43
     }
   ],
   "logging_steps": 1,
@@ -299,7 +327,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.819057491549389e+16,
+  "total_flos": 5.308264490763878e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null