Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f8fc021a75be692d34380496c7469be1a79dd8835a732c7f5b2d3cde7cf8df
+oid sha256:d57eb814cbc59239634c961a9ed37569bb4e8d74ccd71d485da7002502e46f14
 size 95402480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb3d923267d1c33a1500dcc2a81cfea3486fba09590af16be0b23dcf87efdbb
+oid sha256:15e3f7d5e937ce9b8b20b1faab1e826d03b626149d3571d438bd5f5655e6cb4b
 size 190922618

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5da8e1e19ad9d034323f51e8864d0a356648bd28142b88711aa8a3d9e8e6848b
+oid sha256:a08773bb5bf21f8150f21c1777e2db1874ba6f7d8c5802c2c15e95f56e281a4b
 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": 0.0006163423165225966,
+  "epoch": 0.000924513474783895,
   "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": 13.7149,
       "step": 18
+    },
+    {
+      "epoch": 0.0006471594323487265,
+      "grad_norm": 20.51390266418457,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 12.6019,
+      "step": 21
+    },
+    {
+      "epoch": 0.000739610779827116,
+      "grad_norm": 9.698060035705566,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 12.2582,
+      "step": 24
+    },
+    {
+      "epoch": 0.000739610779827116,
+      "eval_loss": 1.9277873039245605,
+      "eval_runtime": 416.4602,
+      "eval_samples_per_second": 32.807,
+      "eval_steps_per_second": 16.405,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008320621273055055,
+      "grad_norm": 8.932806968688965,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 13.5358,
+      "step": 27
+    },
+    {
+      "epoch": 0.000924513474783895,
+      "grad_norm": 7.640513896942139,
+      "learning_rate": 0.0,
+      "loss": 11.9805,
+      "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": 2853976575836160.0,
+  "total_flos": 4316639570952192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null