Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:931616a9348ea6da646f31fd74cda0d5134e82f7b3387d73d2f60192d8ab0893
+oid sha256:65e7df6d4b8eea8d6ac6af17fdf98a1aa24af43cbc3e5c23fe54fa02a8999249
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8326cf8bdae6dd9f49e3a3adffbf94c64e7b64465e30f33f5dce8d020976de6
+oid sha256:3e3c7a238b76f43dac71a8b57c12a69ee00df08f60ecff5d670e8d46604a7bd7
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e20683429b134450d792c8f3f955e3c6a627a002ec7a89da4cd737a6cd7931e
+oid sha256:a1103a5a7efdfc12a1c696b0039f2dfaa719e8a4581e0c7de1b549e6ecbc6d49
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3220014572143555,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.7333333333333334,
+  "best_metric": 1.316821575164795,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.8666666666666667,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,20 @@
       "eval_samples_per_second": 12.718,
       "eval_steps_per_second": 1.595,
       "step": 1300
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002,
+      "loss": 1.0772,
+      "step": 1400
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 1.316821575164795,
+      "eval_runtime": 151.7755,
+      "eval_samples_per_second": 12.716,
+      "eval_steps_per_second": 1.594,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.29087249794048e+16,
+  "total_flos": 8.928806920685568e+16,
   "trial_name": null,
   "trial_params": null
 }