Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81e633e9bc3f69d11790635804ad86133581999afeef92365a8b8f01917ac48a
+oid sha256:89e3f6600f5d284cb50e5e59896d451d611033fccff70b12b87cf43c5ce89e04
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ca0d1cc3a0ac9d247251adc1ec48699aae0fefc9c934f48427c26bc9dfa262
+oid sha256:0923a71bf49fb7b2adb251f38a83240103fdf1465b960e2af8a7d7b27b6d65d8
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe47899e6cdc599270dce0d73c85039bf451a23c8ed77614a8db8f98923f4cf
+oid sha256:062c7ea16923f93734037deae2278ec33ab1c73fc48629fbd721626e616c07a9
 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": 0.12755519215044972,
+  "epoch": 0.1635322976287817,
   "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": 1.5178,
       "step": 35
+    },
+    {
+      "epoch": 0.13082583810302534,
+      "grad_norm": 2.8207459449768066,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3346,
+      "step": 40
+    },
+    {
+      "epoch": 0.13082583810302534,
+      "eval_loss": 1.3294119834899902,
+      "eval_runtime": 13.0651,
+      "eval_samples_per_second": 9.874,
+      "eval_steps_per_second": 4.975,
+      "step": 40
+    },
+    {
+      "epoch": 0.1471790678659035,
+      "grad_norm": 2.846841812133789,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3073,
+      "step": 45
+    },
+    {
+      "epoch": 0.1635322976287817,
+      "grad_norm": 2.0426764488220215,
+      "learning_rate": 0.0,
+      "loss": 1.2579,
+      "step": 50
+    },
+    {
+      "epoch": 0.1635322976287817,
+      "eval_loss": 1.3147763013839722,
+      "eval_runtime": 12.9288,
+      "eval_samples_per_second": 9.978,
+      "eval_steps_per_second": 5.028,
+      "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": 8004335107571712.0,
+  "total_flos": 1.02619680866304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null