Training in progress, epoch 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1f89678bfcaea704d111e574ffb02381b58f29949b041052259e9fd46388477
+oid sha256:de1ce623a9290244838506727dabcd032cd98161a4bc9a4d333e928e900106b8
 size 2526824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1105023e70cd979f84058cf88271139d3dad49f2efada53694e464226c755e6
+oid sha256:b72c7b53fcd949fae1a20cef1038864720e95adb6f0ba2ee1613eb97830791f8
 size 1628986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d417edef81aadd1524150f603a1f1f4d9e4feaebc56043e6552c54b598024246
+oid sha256:41043d7401f5848237af4c4b1c2c2082e5048849c31547448e6f7368c669002c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f18c56cb174b19403e5cd64826715733b24b1187efc1a85a31ad182bce916247
+oid sha256:30241b4c1125cc90d62919e91ddb85f7c49ce98d2e890950e4784d91b698c05e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 276,
+  "global_step": 345,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,6 +50,20 @@
       "learning_rate": 0.00020635380444044998,
       "loss": 1.5832,
       "step": 246
+    },
+    {
+      "epoch": 4.160583941605839,
+      "grad_norm": 0.4120023250579834,
+      "learning_rate": 0.0001243827306309381,
+      "loss": 1.6234,
+      "step": 287
+    },
+    {
+      "epoch": 4.759124087591241,
+      "grad_norm": 0.3155122697353363,
+      "learning_rate": 5.772683701771136e-05,
+      "loss": 1.5781,
+      "step": 328
     }
   ],
   "logging_steps": 41,
@@ -69,7 +83,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.381043620590387e+16,
+  "total_flos": 2.976304525737984e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null