Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf45da60cb0c37fbd6013ef3ace980dfd5cac6081de351f2a8275b9c5ebbd06
+oid sha256:bd71aa97f822dbd5b80bb28d8cef36c2c44ffed4bedb692a622dbdcec94e64b1
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aea741ba045865bbd279ca4b82852250e1244f202c18156ded96b2a4c24ee64
+oid sha256:fc2fb58cf506128302593da9a52cb76278a8c38f1e757535952cd9614cc38a5d
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:c8d6c6954105413e254c1dc776a27dd427206924cc5f1ee48db29b4f18851c42
 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": 0.020741508944775732,
+  "epoch": 0.0311122634171636,
   "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": 5.3222,
       "step": 18
+    },
+    {
+      "epoch": 0.021778584392014518,
+      "grad_norm": 4.10032844543457,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 5.2885,
+      "step": 21
+    },
+    {
+      "epoch": 0.02488981073373088,
+      "grad_norm": 2.895509719848633,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 4.7847,
+      "step": 24
+    },
+    {
+      "epoch": 0.02488981073373088,
+      "eval_loss": 1.296072244644165,
+      "eval_runtime": 42.1784,
+      "eval_samples_per_second": 9.626,
+      "eval_steps_per_second": 4.813,
+      "step": 24
+    },
+    {
+      "epoch": 0.028001037075447238,
+      "grad_norm": 3.007878065109253,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 4.791,
+      "step": 27
+    },
+    {
+      "epoch": 0.0311122634171636,
+      "grad_norm": 3.952789783477783,
+      "learning_rate": 0.0,
+      "loss": 5.4658,
+      "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": 3684183016734720.0,
+  "total_flos": 5526274525102080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null