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:fdc19b2e83f6323ab919448a8df92a7d3db49a338c896a7ae12d127a8e4ff28b
+oid sha256:044e9fb9b5e7c17281533f0d59348855255bef6b6015e2656c5178bf841087e2
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c29beac53fef5a2727a6a2c7bc3bef1b44305da35d5e2f81122642f1daf24b1a
+oid sha256:5f1278e06bda73da3ce435dd86d2fbf7d4a21c5e3a6d282eae1425cc8a82da41
 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": 0.0017191361340926185,
+  "epoch": 0.002578704201138928,
   "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": 10.8492,
       "step": 18
+    },
+    {
+      "epoch": 0.0018050929407972495,
+      "grad_norm": 5.968902587890625,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 10.915,
+      "step": 21
+    },
+    {
+      "epoch": 0.0020629633609111422,
+      "grad_norm": 4.652180194854736,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.946,
+      "step": 24
+    },
+    {
+      "epoch": 0.0020629633609111422,
+      "eval_loss": 2.596761703491211,
+      "eval_runtime": 171.9916,
+      "eval_samples_per_second": 28.484,
+      "eval_steps_per_second": 14.245,
+      "step": 24
+    },
+    {
+      "epoch": 0.002320833781025035,
+      "grad_norm": 4.974626541137695,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 10.7093,
+      "step": 27
+    },
+    {
+      "epoch": 0.002578704201138928,
+      "grad_norm": 4.369829177856445,
+      "learning_rate": 0.0,
+      "loss": 10.2776,
+      "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