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:d84b530a83db62e8132b347373e81a8ceb54359bbcc0f050f0c6489872cb8f80
+oid sha256:30c6b1c0d32b5100744db1854afa54033d27967ded12325feac428ca513107d5
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8336afca0b2ae767243059cb8446c976321d488a19ae3ae94f3a9fdf287298d
+oid sha256:83a2614757549eac7ea6aff0542972128062f2e13c6bc3f7fd1734917874b426
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41dc89732cf4b997293c74044f817bccdb3e7d4f012861e46bbbd9a6e9666b0c
+oid sha256:e56e4acc2d5f2a5f40b4cb0140d817bfee5591e3e2b38f80c7f32d275d8577ff
 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": 0.06255012028869286,
+  "epoch": 0.08019246190858059,
   "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": 11.3404,
       "step": 35
+    },
+    {
+      "epoch": 0.06415396952686447,
+      "grad_norm": 40.70652770996094,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.0508,
+      "step": 40
+    },
+    {
+      "epoch": 0.06415396952686447,
+      "eval_loss": NaN,
+      "eval_runtime": 5.5162,
+      "eval_samples_per_second": 47.678,
+      "eval_steps_per_second": 23.929,
+      "step": 40
+    },
+    {
+      "epoch": 0.07217321571772253,
+      "grad_norm": 44.69584274291992,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.269,
+      "step": 45
+    },
+    {
+      "epoch": 0.08019246190858059,
+      "grad_norm": 63.653263092041016,
+      "learning_rate": 0.0,
+      "loss": 10.6362,
+      "step": 50
+    },
+    {
+      "epoch": 0.08019246190858059,
+      "eval_loss": NaN,
+      "eval_runtime": 5.3076,
+      "eval_samples_per_second": 49.552,
+      "eval_steps_per_second": 24.87,
+      "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": 353107477266432.0,
+  "total_flos": 449608899624960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null