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:eee1c0588e172f204239eec3ba98f0de826c60f34902881656c40ef1bccba632
+oid sha256:44fd38ef3fa14b3661b8a9470c552480c0df3fd0fe3cec10d706b33d2cd00402
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92bfa1f682fc3d7cfe2c91aba37707f48f722e536780ec975513e1bc97f0dcad
+oid sha256:27083fde71eb732e039c7a7f9259f30fd20d84c01b43f6cec293a845dc4e7554
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1698424ff146bcbfe1356a243484a7bf217ef6a25305200a2a40567c1858ba0
+oid sha256:2e3540149a4da276050c8040279e53fbd6bae2961729657791763596edd20e7b
 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": 0.21052631578947367,
+  "epoch": 0.3157894736842105,
   "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": 20.085,
       "eval_steps_per_second": 10.042,
       "step": 20
+    },
+    {
+      "epoch": 0.22105263157894736,
+      "grad_norm": 13.290178298950195,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 6.9661,
+      "step": 21
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 7.930633068084717,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 6.4966,
+      "step": 24
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "eval_loss": 1.5495727062225342,
+      "eval_runtime": 1.989,
+      "eval_samples_per_second": 20.111,
+      "eval_steps_per_second": 10.056,
+      "step": 25
+    },
+    {
+      "epoch": 0.28421052631578947,
+      "grad_norm": 9.09288215637207,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 5.9758,
+      "step": 27
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 7.697510719299316,
+      "learning_rate": 0.0,
+      "loss": 5.5532,
+      "step": 30
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "eval_loss": 1.5200411081314087,
+      "eval_runtime": 1.9957,
+      "eval_samples_per_second": 20.043,
+      "eval_steps_per_second": 10.022,
+      "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": 3684183016734720.0,
+  "total_flos": 5526274525102080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null