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:db76a4af169edbd8b02f4417924c2330959a17eac8e884e93288de14b75d7428
+oid sha256:43dd91ba7f4bb5bb4921903e50179380e7065d1d5cf0a34d905357cf913fc852
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9047b064d422f8b6f1daee0998b36b7761fd0f4d00686496d3edc5052e9fe16
+oid sha256:b5a56296d812138699280d766d59fb1c4be0566804c50af19683c1696367d818
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6684d632e0ed9894b7d3581195993fbfd0a1de05dcd5960c38ed169d3e9d554
+oid sha256:d82b625db56507f447e53f457cd40a516407fb4c508f6a80ad29dded2571bb42
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016039481801357187,
+  "epoch": 0.02056343820686819,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.5931,
       "step": 35
+    },
+    {
+      "epoch": 0.01645075056549455,
+      "grad_norm": 1.2525250911712646,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5129,
+      "step": 40
+    },
+    {
+      "epoch": 0.01645075056549455,
+      "eval_loss": 0.589495062828064,
+      "eval_runtime": 27.3301,
+      "eval_samples_per_second": 37.468,
+      "eval_steps_per_second": 18.734,
+      "step": 40
+    },
+    {
+      "epoch": 0.01850709438618137,
+      "grad_norm": 1.1442337036132812,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6124,
+      "step": 45
+    },
+    {
+      "epoch": 0.02056343820686819,
+      "grad_norm": 0.9440557360649109,
+      "learning_rate": 0.0,
+      "loss": 0.5675,
+      "step": 50
+    },
+    {
+      "epoch": 0.02056343820686819,
+      "eval_loss": 0.5864447355270386,
+      "eval_runtime": 27.3552,
+      "eval_samples_per_second": 37.434,
+      "eval_steps_per_second": 18.717,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 938127510208512.0,
+  "total_flos": 1202727577190400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null