Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27db72ff1d99818c996e0d4090ba341857ed90a5b4c6f3b036f3318f8a7c4473
+oid sha256:be866667769785ef11257753ba6fd244721449b93fe0f7b339fd20d6cc8305b8
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07019ef618173d457e495866d9152583e22841d20a327fc2feb7c175d8431ea8
+oid sha256:956d1f0c6c058faa6a5fd8e52a994ff66cd0743e67c18242a3cc3daaa12d8fca
 size 63974

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": 0.009198655581107376,
+  "epoch": 0.01839731116221475,
   "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": 206.272,
       "eval_steps_per_second": 103.309,
       "step": 10
+    },
+    {
+      "epoch": 0.010613833362816204,
+      "grad_norm": 0.20211586356163025,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 10.4143,
+      "step": 15
+    },
+    {
+      "epoch": 0.014151777817088271,
+      "grad_norm": 0.2647286057472229,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 10.4113,
+      "step": 20
+    },
+    {
+      "epoch": 0.014151777817088271,
+      "eval_loss": 10.42919921875,
+      "eval_runtime": 3.0176,
+      "eval_samples_per_second": 197.175,
+      "eval_steps_per_second": 98.753,
+      "step": 20
+    },
+    {
+      "epoch": 0.01768972227136034,
+      "grad_norm": 0.1938541829586029,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.458,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 168101806080.0,
+  "total_flos": 336203612160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null