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:b51f062d6cffc347942083e4ea56fe1515820052ce5c75df9c3691b56c132b05
+oid sha256:bd2bfd2224950169f6f75bb98afa149b51a007dce8f3e2d97bd150efd4984730
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68079f059061caa6af54d23b0b36a483a3afbe03f7f78f9e8814e664c88014f1
+oid sha256:0327d0abe1b66e8ba31b1d30beb35b8c34a9405537a80852bc373a094add0527
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c3e567c74affae7478911fb166aed9b97f670988a0accdc6e7382bc1b315cf
+oid sha256:19c3a950b1db5e5a53ee1807fed513e1459650c81b28057a7dd9e7f6eb2c4dc2
 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": 0.0012829685919419703,
+  "epoch": 0.0016448315281307312,
   "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": 2.5254,
       "step": 35
+    },
+    {
+      "epoch": 0.001315865222504585,
+      "grad_norm": 1.0387564897537231,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.588,
+      "step": 40
+    },
+    {
+      "epoch": 0.001315865222504585,
+      "eval_loss": 2.4847793579101562,
+      "eval_runtime": 412.2008,
+      "eval_samples_per_second": 31.053,
+      "eval_steps_per_second": 15.526,
+      "step": 40
+    },
+    {
+      "epoch": 0.001480348375317658,
+      "grad_norm": 0.9422990083694458,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.5758,
+      "step": 45
+    },
+    {
+      "epoch": 0.0016448315281307312,
+      "grad_norm": 0.8218869566917419,
+      "learning_rate": 0.0,
+      "loss": 2.5283,
+      "step": 50
+    },
+    {
+      "epoch": 0.0016448315281307312,
+      "eval_loss": 2.4830634593963623,
+      "eval_runtime": 411.1322,
+      "eval_samples_per_second": 31.134,
+      "eval_steps_per_second": 15.567,
+      "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": 299222830153728.0,
+  "total_flos": 383619013017600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null