Training in progress, step 189, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147e782becda787d99b94c6bad69cb906d223a40d2f601334f7ea8de17fce6dd
+oid sha256:ebe71e7389745b2e0992348bb23d01fd274063045d4a9825ef087b9537cbe5c8
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfa0e82589a6f6cf44074215e2637567697993387b493da2d57c2aa0b564fab8
+oid sha256:441a73d08275c1a04bdfab64fe490ea8927d7dc27b49522a70b1067a18cf3fd9
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a8cef57846ad22e38262ff905e75360e27250c498704a126d5649a9db3dc6a
+oid sha256:f0e43ae0edb97874da7b112481c16934bfb598883dd76c7ad5958cc3d2e845e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fde2add4ac526f9d88b4a85a5e304b22d4aa9bf06cf799f89fbf1fa68e0bf83
+oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18947368421052632,
+  "epoch": 0.28421052631578947,
   "eval_steps": 63,
-  "global_step": 126,
+  "global_step": 189,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,56 @@
       "eval_samples_per_second": 55.637,
       "eval_steps_per_second": 27.818,
       "step": 126
+    },
+    {
+      "epoch": 0.19548872180451127,
+      "grad_norm": 2.3956797122955322,
+      "learning_rate": 9.679484224283449e-05,
+      "loss": 1.1821,
+      "step": 130
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 5.590377330780029,
+      "learning_rate": 8.404001049666211e-05,
+      "loss": 1.3494,
+      "step": 140
+    },
+    {
+      "epoch": 0.22556390977443608,
+      "grad_norm": 2.592655897140503,
+      "learning_rate": 7.154724133689677e-05,
+      "loss": 1.2996,
+      "step": 150
+    },
+    {
+      "epoch": 0.24060150375939848,
+      "grad_norm": 3.8601112365722656,
+      "learning_rate": 5.952166568776062e-05,
+      "loss": 1.2901,
+      "step": 160
+    },
+    {
+      "epoch": 0.2556390977443609,
+      "grad_norm": 1.6364320516586304,
+      "learning_rate": 4.8160743168947496e-05,
+      "loss": 1.2282,
+      "step": 170
+    },
+    {
+      "epoch": 0.2706766917293233,
+      "grad_norm": 3.1706936359405518,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 1.3024,
+      "step": 180
+    },
+    {
+      "epoch": 0.28421052631578947,
+      "eval_loss": 1.2115331888198853,
+      "eval_runtime": 2.5743,
+      "eval_samples_per_second": 54.384,
+      "eval_steps_per_second": 27.192,
+      "step": 189
     }
   ],
   "logging_steps": 10,
@@ -134,7 +184,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 819026592792576.0,
+  "total_flos": 1221826556461056.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null