Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef062dd4313ae521864e44aa3225ee94aaab8b1781cea592dacce01bd8b17b6
+oid sha256:0dfbae38e29b4fbf00b37202fcf9fde53b7ac6794da40bce9e9ccd11c5581bab
 size 56662456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0fe4be77a1f176ed99e999cc97a7c4d4b9ba5158bcfde52e8183c547bb499a5
+oid sha256:489c850b00eceff61824ba418c7bdf70d983006cc037597300f202e309698736
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9ca4e7e99b95c5050a96a8ba0507b831a4d40c0cca2b1576a6f50d8e863d78
+oid sha256:3df2ccfbefefb833fa325a4584563be52ca33b6e0b7a800bf97addd6fc9c1190
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005617780274569011,
+  "epoch": 0.0008426670411853516,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 31.959,
       "eval_steps_per_second": 15.98,
       "step": 20
+    },
+    {
+      "epoch": 0.0005898669288297462,
+      "grad_norm": 0.8441067337989807,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 7.3543,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006741336329482813,
+      "grad_norm": 1.5322083234786987,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 8.918,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007022225343211264,
+      "eval_loss": 1.932130217552185,
+      "eval_runtime": 468.9583,
+      "eval_samples_per_second": 31.964,
+      "eval_steps_per_second": 15.982,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007584003370668165,
+      "grad_norm": 1.4462820291519165,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 8.9198,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008426670411853516,
+      "grad_norm": 1.3085848093032837,
+      "learning_rate": 0.0,
+      "loss": 7.3656,
+      "step": 30
+    },
+    {
+      "epoch": 0.0008426670411853516,
+      "eval_loss": 1.929632306098938,
+      "eval_runtime": 468.8957,
+      "eval_samples_per_second": 31.969,
+      "eval_steps_per_second": 15.984,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1201875462389760.0,
+  "total_flos": 1817836636864512.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null