Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93cbce12db1bcd458309268a7da42d4825128c957e0d1c699debbc51749fb41b
+oid sha256:5bafbc247ce2c8953c6683f90d87f8bd8ba37cf8ae0a314ca9b696b213130d6e
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b10d35bb1284042f0db66531404020fd05cfb121db46ee069e129f290e14e34
+oid sha256:89cd32755e389b4400e83f3821ea5ace462c4e5fb0ddcdffabfe08ffe0d174ff
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77af6e432eee0998a8a3f6243344f174cbdce2efbbae495079d6a78a1eab9661
+oid sha256:c7d9372711d9e99428275dc2ac133f7557aed0f81e715109fa05ba4f94426d2d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
+oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8973463177680969,
-  "best_model_checkpoint": "./outputs/checkpoint-3400",
-  "epoch": 4.533333333333333,
+  "best_metric": 0.8955456614494324,
+  "best_model_checkpoint": "./outputs/checkpoint-3500",
+  "epoch": 4.666666666666667,
   "eval_steps": 100,
-  "global_step": 3400,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,6 +483,20 @@
       "eval_samples_per_second": 2.482,
       "eval_steps_per_second": 0.311,
       "step": 3400
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 0.0002,
+      "loss": 0.6963,
+      "step": 3500
+    },
+    {
+      "epoch": 4.67,
+      "eval_loss": 0.8955456614494324,
+      "eval_runtime": 796.2741,
+      "eval_samples_per_second": 2.424,
+      "eval_steps_per_second": 0.304,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
@@ -490,7 +504,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 8.805891139634381e+17,
+  "total_flos": 9.06455971769303e+17,
   "trial_name": null,
   "trial_params": null
 }