Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5823af0432ca7b36d483d4a816c5753b8d80eae14be9d1f34bd236e6bc2bbb9c
+oid sha256:04cc66d5dd1aee319ef9b6aabd749be97c04a9bd8567c53dffc11f892d226fde
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:257d8c8f1c7689e7b75949580aa8477ad80b3090c8aa3e420ccff8b21d7a233e
+oid sha256:c3c93ef695bae9205b4181a350bb2358a78b527d682e3275d25ca163e663e27b
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
+oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008928571428571428,
+  "epoch": 0.017857142857142856,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 100.613,
       "eval_steps_per_second": 50.306,
       "step": 10
+    },
+    {
+      "epoch": 0.010302197802197802,
+      "grad_norm": 0.01706523261964321,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 11.9319,
+      "step": 15
+    },
+    {
+      "epoch": 0.013736263736263736,
+      "grad_norm": 0.02669455297291279,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.9315,
+      "step": 20
+    },
+    {
+      "epoch": 0.013736263736263736,
+      "eval_loss": 11.931612014770508,
+      "eval_runtime": 6.099,
+      "eval_samples_per_second": 100.673,
+      "eval_steps_per_second": 50.336,
+      "step": 20
+    },
+    {
+      "epoch": 0.017170329670329672,
+      "grad_norm": 0.018381647765636444,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 11.9309,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1536098304.0,
+  "total_flos": 3072196608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null