Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98cebb4f107c88ba74bdba4f057bd933079766f6291a8322475de3a889b5625d
+oid sha256:8cfeb40ef47605c61218eb8ac3a29aeba57342cfecff36c644d5aa400d908705
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b0f1745676ecfb5190d27aa85d31f4f91a9dcc4bae71d89539fdb999a4f824b
+oid sha256:8ccd2e0f70b06e9c531dff4e646d71f03c36851dcdae1820630b9f7ab15aa58d
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c610466766b8bb70c6e0b41c0087399878c462d89489da2ef9a5d5297ffc5abb
+oid sha256:bcb3135cf196e8b8e696f3c53b21fa79911cde95abd9214895755de464220427
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
+oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006110649765758426,
+  "epoch": 0.0007834166366356955,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,20 @@
       "eval_samples_per_second": 162.816,
       "eval_steps_per_second": 81.414,
       "step": 39
+    },
+    {
+      "epoch": 0.0006267333093085565,
+      "grad_norm": 2.685209274291992,
+      "learning_rate": 0.0002,
+      "loss": 8.503,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007834166366356955,
+      "grad_norm": 2.1991186141967773,
+      "learning_rate": 0.0002,
+      "loss": 7.9626,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1340507553792.0,
+  "total_flos": 1713813454848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null