Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d32d48078b620c9a6f47add386236b72d9b1eb15186be35bfb4825222bec25
+oid sha256:05fd4c564070e465e79ee5211fb70d1dfb9f5f021c780137373c2831afbb159f
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64ebac3067342ec186ce45e3428d0dc2a30113d7827beedea7b2d1daef9d264
+oid sha256:b550792ed61a0256457f818d918c48ee38593ce8926354366aa4fc1cc57f86bf
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9529e546cf341a145a50d98de64242b3f32033a0c0b27a23a66d4e5bf961a4e
+oid sha256:e5b848ceb0c0547ce01ecdbfc312b29052de3e30252c22d1e990db7107479458
 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": 0.15296367112810708,
+  "epoch": 0.2294455066921606,
   "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": 13.0895,
       "step": 18
+    },
+    {
+      "epoch": 0.16061185468451242,
+      "grad_norm": 13.389608383178711,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.9513,
+      "step": 21
+    },
+    {
+      "epoch": 0.1835564053537285,
+      "grad_norm": 14.42936897277832,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.6374,
+      "step": 24
+    },
+    {
+      "epoch": 0.1835564053537285,
+      "eval_loss": 2.773041248321533,
+      "eval_runtime": 1.948,
+      "eval_samples_per_second": 28.234,
+      "eval_steps_per_second": 14.374,
+      "step": 24
+    },
+    {
+      "epoch": 0.20650095602294455,
+      "grad_norm": 13.830270767211914,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.0541,
+      "step": 27
+    },
+    {
+      "epoch": 0.2294455066921606,
+      "grad_norm": 12.206254005432129,
+      "learning_rate": 0.0,
+      "loss": 10.2184,
+      "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": 1202020417536000.0,
+  "total_flos": 1803030626304000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null