Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b948028a1c80a35b27d673f57d22cb20ea1c89b509ec0cfd808b7fd2adf16ec
+oid sha256:aeb5ec0eda99af58dd5a1aaa7968b43a33dcb165ace39238a1d689edac3c8e24
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987a204b8cbd8d42f232de144b33ed6ca67afceb30015fdb9c473179aca21125
+oid sha256:c30d8f6e266d1afb9d81d0c7ff56524dbbf32d9f7f023e8e3509e74e3baae472
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c17c52bd8ef844b04cd44e7f1ec97aa686b196d5b59be84905cabc36870028c
+oid sha256:52aa87102828bf8cab533c138f772c48c494ebc2b940fefe592ecc57aeb95a28
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004107608818720164,
+  "epoch": 0.0005266165152205338,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 15.165,
       "eval_steps_per_second": 7.583,
       "step": 39
+    },
+    {
+      "epoch": 0.0004212932121764271,
+      "grad_norm": 1.2668111324310303,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 6.2134,
+      "step": 40
+    },
+    {
+      "epoch": 0.00043182554248083775,
+      "grad_norm": 1.4063031673431396,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 6.3267,
+      "step": 41
+    },
+    {
+      "epoch": 0.0004423578727852484,
+      "grad_norm": 1.5289639234542847,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.8625,
+      "step": 42
+    },
+    {
+      "epoch": 0.0004528902030896591,
+      "grad_norm": 1.3586407899856567,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 6.1417,
+      "step": 43
+    },
+    {
+      "epoch": 0.00046342253339406975,
+      "grad_norm": 1.5407192707061768,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.695,
+      "step": 44
+    },
+    {
+      "epoch": 0.0004739548636984805,
+      "grad_norm": 1.2807283401489258,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 6.1324,
+      "step": 45
+    },
+    {
+      "epoch": 0.00048448719400289114,
+      "grad_norm": 1.375052571296692,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 5.5676,
+      "step": 46
+    },
+    {
+      "epoch": 0.0004950195243073018,
+      "grad_norm": 1.4286342859268188,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 6.1877,
+      "step": 47
+    },
+    {
+      "epoch": 0.0005055518546117125,
+      "grad_norm": 1.4721269607543945,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 6.0579,
+      "step": 48
+    },
+    {
+      "epoch": 0.0005160841849161232,
+      "grad_norm": 1.5001436471939087,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 6.0298,
+      "step": 49
+    },
+    {
+      "epoch": 0.0005266165152205338,
+      "grad_norm": 1.804200291633606,
+      "learning_rate": 0.0,
+      "loss": 6.4854,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.519787666571264e+16,
+  "total_flos": 1.963059069321216e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null