Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b09e92d5bb81698a317471c9da9378d7cadfda3fde4e696dae3506dbe441aa
+oid sha256:3c2edff5de3c7c998ef42f162740bc1f092261d6fbb13e9019b48101ac26b17f
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5316e2ea56fe084fdfdddb5ab7f1c0996281f4bb372da6965767b4e682d8249
+oid sha256:f48d5f176892811e52728509f73bbe8f8bfec4e68a7a3f0c70fd596db6c826fa
 size 101107578

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c04d044dd1828bae4a7219763c171f8e3b92a1b129b7f62c011e4811f5c690b
+oid sha256:7176c5ff6415b0528409dc982b8089959582b918a04dd05e559b55008db4bbfc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007490566567728766,
+  "epoch": 0.001123584985159315,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 1.7029,
       "step": 18
+    },
+    {
+      "epoch": 0.0007865094896115205,
+      "grad_norm": 0.18383990228176117,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.5868,
+      "step": 21
+    },
+    {
+      "epoch": 0.000898867988127452,
+      "grad_norm": 0.17294101417064667,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.549,
+      "step": 24
+    },
+    {
+      "epoch": 0.000898867988127452,
+      "eval_loss": 1.6437101364135742,
+      "eval_runtime": 473.9829,
+      "eval_samples_per_second": 23.72,
+      "eval_steps_per_second": 11.861,
+      "step": 24
+    },
+    {
+      "epoch": 0.0010112264866433834,
+      "grad_norm": 0.16522365808486938,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.5047,
+      "step": 27
+    },
+    {
+      "epoch": 0.001123584985159315,
+      "grad_norm": 0.14330220222473145,
+      "learning_rate": 0.0,
+      "loss": 1.6588,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1119438539587584.0,
+  "total_flos": 1711325583507456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null