Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5669fbc557d8c0b6d117b5f0add48fc5188c107e89ff1151689d193fd6886fad
+oid sha256:931616a9348ea6da646f31fd74cda0d5134e82f7b3387d73d2f60192d8ab0893
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58e5eef3a648bafbe1b2ad82f7f4d8de708b7f0d44ee7bcc2d61ba3b4755afd4
+oid sha256:c8326cf8bdae6dd9f49e3a3adffbf94c64e7b64465e30f33f5dce8d020976de6
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa0cd2311a863a53c7b9c00754d8a568b5bc8a382e272e0f99aa88e8f39b593
+oid sha256:6e20683429b134450d792c8f3f955e3c6a627a002ec7a89da4cd737a6cd7931e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.331199288368225,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 1.3220014572143555,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 1.7333333333333334,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 12.712,
       "eval_steps_per_second": 1.594,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 1.076,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 1.3220014572143555,
+      "eval_runtime": 151.7501,
+      "eval_samples_per_second": 12.718,
+      "eval_steps_per_second": 1.595,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.650403112798208e+16,
+  "total_flos": 8.29087249794048e+16,
   "trial_name": null,
   "trial_params": null
 }