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:dea13992fe5f2132a90eefac1b0e4b8a4fdf79063113045eea18d4f02a406b9e
+oid sha256:70263e55b2499c69520a008c5cf47538b42e50a0a535e8bb7417278c3b07b9cd
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d55306bebe75b76284562a5adc18e1b802564309bf28b844172a5228904f1a7
+oid sha256:a9ab430125ce70ca6d46527c1f3fc7e8cebaec244750ee8ad579fbe774f8ead6
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec698543fc8efe1c42cfec18e55613892ce220f315dbecc631afb9ede0781a9
+oid sha256:c0e4d5e471bed97943d25263dc996afb538f27403572e606e5959a900d36724d
 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": 0.0015654006321810245,
+  "epoch": 0.00200692388741157,
   "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": 0.0787,
       "step": 35
+    },
+    {
+      "epoch": 0.001605539109929256,
+      "grad_norm": 0.1398703008890152,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0869,
+      "step": 40
+    },
+    {
+      "epoch": 0.001605539109929256,
+      "eval_loss": 0.05585380643606186,
+      "eval_runtime": 391.5629,
+      "eval_samples_per_second": 26.79,
+      "eval_steps_per_second": 13.395,
+      "step": 40
+    },
+    {
+      "epoch": 0.0018062314986704128,
+      "grad_norm": 0.08646954596042633,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1009,
+      "step": 45
+    },
+    {
+      "epoch": 0.00200692388741157,
+      "grad_norm": 0.5224814414978027,
+      "learning_rate": 0.0,
+      "loss": 0.0612,
+      "step": 50
+    },
+    {
+      "epoch": 0.00200692388741157,
+      "eval_loss": 0.05531559884548187,
+      "eval_runtime": 392.9164,
+      "eval_samples_per_second": 26.698,
+      "eval_steps_per_second": 13.349,
+      "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": 552036615585792.0,
+  "total_flos": 712305310433280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null