Training in progress, step 3400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc2f2d160bdfb1d0e93ecfc8b7c923f2fc777d1f5743442a22f8f2c4066e9baa
+oid sha256:fe576281aec065c14bce0faffbcf1a5b77abe99fc7a6c9692a126d3c86cada3b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c6f77f55e11d319ec955dc81fb8f9d0a93150cdf5dad62fa65c4dd6df9a859
+oid sha256:230b75f77750e71f0b8aadca04b6f8dc80972d753eca204a5227d0c5457f0ff2
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b32db0a2b713dd6b1e7016c32489b8ad860f5a342471d86c52b5af270bb99a
+oid sha256:298e8871de8745e7586904db3da51f0731b6797e7faf72bed74b5f5a5c7425f5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
+oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.031524896621704,
-  "best_model_checkpoint": "./outputs/checkpoint-3300",
-  "epoch": 2.4043715846994536,
+  "best_metric": 2.02608060836792,
+  "best_model_checkpoint": "./outputs/checkpoint-3400",
+  "epoch": 2.477231329690346,
   "eval_steps": 100,
-  "global_step": 3300,
+  "global_step": 3400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -469,13 +469,27 @@
       "eval_samples_per_second": 24.612,
       "eval_steps_per_second": 3.079,
       "step": 3300
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0002,
+      "loss": 1.9847,
+      "step": 3400
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 2.02608060836792,
+      "eval_runtime": 206.1634,
+      "eval_samples_per_second": 30.432,
+      "eval_steps_per_second": 3.808,
+      "step": 3400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.691971842875392e+16,
+  "total_flos": 9.98463226908672e+16,
   "trial_name": null,
   "trial_params": null
 }