Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36fe8d7a305af62205375df98fb2cc1c6645ef8b749a5273b3ee3d352eefd4ff
+oid sha256:8a418c405dba8748b3f7b77490302bfac4666e43b97737075f54066872db6508
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e18353c1db4cccb187df563c373394af0a9bc8fc7cf3d0fbeb173b28f5b3ae
+oid sha256:26a451440b3a8ef9367c130825f1354e20fb9956dd0854c57e4b1418c8e20f1d
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea453a28bcea2c3e4e655cb7e90386f58f0a77e985afad540f593477aa655c29
+oid sha256:656e87d96751baed9dab56b149b540fdbe0657cbcb0de7e841ab53179ca5aa1b
 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": 0.0018211108776353575,
+  "epoch": 0.0023347575354299454,
   "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": 0.409,
       "step": 35
+    },
+    {
+      "epoch": 0.0018678060283439564,
+      "grad_norm": 3.254962205886841,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3198,
+      "step": 40
+    },
+    {
+      "epoch": 0.0018678060283439564,
+      "eval_loss": 0.2902105748653412,
+      "eval_runtime": 1241.3536,
+      "eval_samples_per_second": 7.265,
+      "eval_steps_per_second": 3.632,
+      "step": 40
+    },
+    {
+      "epoch": 0.002101281781886951,
+      "grad_norm": 2.525123357772827,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3341,
+      "step": 45
+    },
+    {
+      "epoch": 0.0023347575354299454,
+      "grad_norm": 3.7383229732513428,
+      "learning_rate": 0.0,
+      "loss": 0.2958,
+      "step": 50
+    },
+    {
+      "epoch": 0.0023347575354299454,
+      "eval_loss": 0.2724764943122864,
+      "eval_runtime": 1241.1547,
+      "eval_samples_per_second": 7.266,
+      "eval_steps_per_second": 3.633,
+      "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": 7453256523448320.0,
+  "total_flos": 9555457081344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null