Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39570983963faef58a74b921cf5a8fc61f714f91dcce2344266b096365980c77
+oid sha256:a3a29fff2e223f28a135847f53cc28906dc79a13c42ff9e91552956b2c1647b3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d981fe6d9e07f2b0f6ae8f2431e7853b51f5bc1328132c1f5fb6fc836683658b
+oid sha256:75c2b48a751588cb17468960245b34fd0e64fedb01952e99b646e893816379e7
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
+oid sha256:2f3dfab2f15c077a3bfe1d57e8f4dfb9954e3c582cff3d86c56d618335c8d869
 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": 0.08939828080229226,
+  "epoch": 0.11461318051575932,
   "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": 1.454,
       "step": 35
+    },
+    {
+      "epoch": 0.09169054441260745,
+      "grad_norm": 3.943558931350708,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4878,
+      "step": 40
+    },
+    {
+      "epoch": 0.09169054441260745,
+      "eval_loss": 0.3554995059967041,
+      "eval_runtime": 35.3678,
+      "eval_samples_per_second": 5.202,
+      "eval_steps_per_second": 2.601,
+      "step": 40
+    },
+    {
+      "epoch": 0.10315186246418338,
+      "grad_norm": 4.879668712615967,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4834,
+      "step": 45
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "grad_norm": 3.6490864753723145,
+      "learning_rate": 0.0,
+      "loss": 1.5293,
+      "step": 50
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "eval_loss": 0.3512641191482544,
+      "eval_runtime": 35.4018,
+      "eval_samples_per_second": 5.197,
+      "eval_steps_per_second": 2.599,
+      "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": 1.3670840033869824e+16,
+  "total_flos": 1.75267179921408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null