Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1000698e47d18cbde8251cb413a4a939ea5d19b02d6be2f3aa21835c6c98c4
+oid sha256:c8dae20adcf64dc33a70617643430888620229c6ad86406fc6fd02c86153d078
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:796d8c36d98a41d34e6f0de45d45ec0055666546d2789699721e36959feef64b
+oid sha256:fa5278f4bf0ef6bbb28d50b7cd50db2406184692d9775f63e98015ef15a73a18
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa4d38c91461c8bd2b1846111e4953c1dc1e466ee07568e8fed1ad255d7379fd
+oid sha256:40c1d0bfb023eb3b6ee1edc7c84ba17179c1af6b559d93eab81378c72eece790
 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": 0.021337710299548625,
+  "epoch": 0.02735603884557516,
   "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": 0.4649,
       "step": 35
+    },
+    {
+      "epoch": 0.021884831076460127,
+      "grad_norm": 2.838388681411743,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5171,
+      "step": 40
+    },
+    {
+      "epoch": 0.021884831076460127,
+      "eval_loss": 0.5030908584594727,
+      "eval_runtime": 51.5327,
+      "eval_samples_per_second": 14.942,
+      "eval_steps_per_second": 7.471,
+      "step": 40
+    },
+    {
+      "epoch": 0.024620434961017644,
+      "grad_norm": 2.749112129211426,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5911,
+      "step": 45
+    },
+    {
+      "epoch": 0.02735603884557516,
+      "grad_norm": 2.3166110515594482,
+      "learning_rate": 0.0,
+      "loss": 0.4508,
+      "step": 50
+    },
+    {
+      "epoch": 0.02735603884557516,
+      "eval_loss": 0.482439786195755,
+      "eval_runtime": 51.5445,
+      "eval_samples_per_second": 14.939,
+      "eval_steps_per_second": 7.469,
+      "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": 7057675986665472.0,
+  "total_flos": 9192405143126016.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null