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:d0cf1212af3ecff5e3e9091dc83d49026c09d8a874410a92e50ad1ed5042c5fe
+oid sha256:8385ded37dc1b0395a2dd50383112d82d5923eb3be0dda355038d734de550c3f
 size 1134088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a4cd10f9db4d94d884c00df7fa6de715d56b590025d84db92bcf60d428ba25
+oid sha256:591af368ad68895bbe658983734976663e6dcbc15d397a950849a5ac61b45d41
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bacfd658e30bcd533a4893ff8c9f287188a66d467ca7f7eb3794ea88a4576ee0
+oid sha256:149ca1745e7a132690f5c3ab778980fe033345b79cfdef03ed9591f560959342
 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": 0.0005543237250554324,
+  "epoch": 0.0007106714423787595,
   "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": 5.8016,
       "step": 35
+    },
+    {
+      "epoch": 0.0005685371539030076,
+      "grad_norm": 8.37199592590332,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 5.5785,
+      "step": 40
+    },
+    {
+      "epoch": 0.0005685371539030076,
+      "eval_loss": 5.657323837280273,
+      "eval_runtime": 136.6243,
+      "eval_samples_per_second": 216.828,
+      "eval_steps_per_second": 108.414,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006396042981408835,
+      "grad_norm": 9.961597442626953,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.2822,
+      "step": 45
+    },
+    {
+      "epoch": 0.0007106714423787595,
+      "grad_norm": 10.082535743713379,
+      "learning_rate": 0.0,
+      "loss": 5.6323,
+      "step": 50
+    },
+    {
+      "epoch": 0.0007106714423787595,
+      "eval_loss": 5.568452835083008,
+      "eval_runtime": 138.0141,
+      "eval_samples_per_second": 214.645,
+      "eval_steps_per_second": 107.322,
+      "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": 41920178946048.0,
+  "total_flos": 53743819161600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null