Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e60e4b3769858cf0dd0a5843c31f89fdbf098d73cd2e4bc6510154c38ad4ec3
+oid sha256:a17cf1fda33b9532bb614390cbad7daacc8c4e17c66c99f595d4788806a4569f
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:facc60c1910de044f5703c2543f518b2ba1a40ce035e295e527cce620613803c
+oid sha256:26307416cba589c7c8605354f6af7ac994147751ee36a03da4e6f224b74dfa45
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
+oid sha256:ca99bebeea385ce2c1d4db38b17f7a71d082f2093a6dc4945fbf7655d2c5b44a
 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": 0.002354811173579019,
+  "epoch": 0.003532216760368528,
   "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": 46.0,
       "step": 18
+    },
+    {
+      "epoch": 0.0024725517322579695,
+      "grad_norm": 0.00010087699047289789,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 46.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.002825773408294822,
+      "grad_norm": 0.00010204371210420504,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 46.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.002825773408294822,
+      "eval_loss": 11.5,
+      "eval_runtime": 33.2973,
+      "eval_samples_per_second": 107.426,
+      "eval_steps_per_second": 53.728,
+      "step": 24
+    },
+    {
+      "epoch": 0.0031789950843316753,
+      "grad_norm": 0.0001002256540232338,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 46.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.003532216760368528,
+      "grad_norm": 9.665413381299004e-05,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "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": 797921771520.0,
+  "total_flos": 1196882657280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null