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:ad878f2c3a2bab44576d26a82b565aef524535d5f156b65bf696b9f37fb591f1
+oid sha256:05e8d2f5c2687e300ed8016f409742c6582d4e67518803b887cb1bbc4495a2e8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb4fcff1aab457cb5e0c04d71f739548c059cc69c8f9ff4d31caa6cc00a60ad
+oid sha256:cbdf1a1c282cf44dba819fd0de0f9793979ea55440a0ff0b29bfb14132ef0495
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b8d3b0cd38ff8c140a46f8cd6b0fb2611ad2c4ebd59d9733c17b98b72f21091
+oid sha256:7cb92806e57e387dc4287cb8248c41b4894921324de83cad277fe9afa6586b2d
 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": 0.012301868937780932,
+  "epoch": 0.024603737875561863,
   "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": 13.898,
       "eval_steps_per_second": 6.965,
       "step": 10
+    },
+    {
+      "epoch": 0.014194464158977998,
+      "grad_norm": 6.178415775299072,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.1327,
+      "step": 15
+    },
+    {
+      "epoch": 0.018925952211970666,
+      "grad_norm": 5.005501747131348,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.2552,
+      "step": 20
+    },
+    {
+      "epoch": 0.018925952211970666,
+      "eval_loss": 0.77772057056427,
+      "eval_runtime": 32.1434,
+      "eval_samples_per_second": 13.844,
+      "eval_steps_per_second": 6.938,
+      "step": 20
+    },
+    {
+      "epoch": 0.02365744026496333,
+      "grad_norm": 3.465031862258911,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.8897,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2450672628793344.0,
+  "total_flos": 4947584363790336.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null