Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12679d7d073d5ed32135132b853d978b1e2e04f539244970c99c3c5175b0fb63
+oid sha256:47b9d7675b3fa64175e7eb10d23fc2721116edf6d4436a07eeffe53679bba7c0
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218e67df4da43563281c44952a05c67aa1e2875d6fd423f9aea4dd31fb3d0472
+oid sha256:768edb243236f95b94276894c34aa6838ed4bc5e5275be0838b91a930bca3753
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e9d195bbd9ab858c7b682a0fed37ab8bd675100cd522a8e50f89b49e3646053
+oid sha256:18090df6bfebcf32a48c9bc16d749f3f0ac4cb8b3b0bfa3c6ea4e241cad174f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017185821697099892,
+  "epoch": 0.02577873254564984,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.9034,
       "step": 18
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 10.081686973571777,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.8475,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 6.329058647155762,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.8169,
+      "step": 24
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "eval_loss": 0.7988092303276062,
+      "eval_runtime": 71.4805,
+      "eval_samples_per_second": 6.855,
+      "eval_steps_per_second": 3.428,
+      "step": 24
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 5.122952461242676,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.8174,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 9.704243659973145,
+      "learning_rate": 0.0,
+      "loss": 0.8309,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7668943615426560.0,
+  "total_flos": 1.150341542313984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null