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:ff1659573be9832300f4f4efea5a2cf7e4b44363f06622e7e55214c46e1143b5
+oid sha256:3e3a59b8d07ffec409f080d114832aaadae842ee86092d982a9665e5cb7415fe
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2fab67c049fb2be004c11732675fa014bc78c5e94282c5a42a91db5f153a03
+oid sha256:c7ca34ab57cbc5b9c61f82581002e26b465a30bbf06b34c77ee426b13a0281df
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e90410ed8d75deee232d46a71672a78439ef812c0e8c37ade4c255c49bee23b
+oid sha256:883f28eb7c189cd34593e2e1d90c086421ac0e064f525f629bfedbc0ac7bb029
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8ae5b9632b883900417a4b328f111a055e2a3387d176daa619ce2ea248142d
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3333333333333335,
+  "epoch": 2.8095238095238093,
   "eval_steps": 3,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -254,6 +254,57 @@
       "learning_rate": 2.9289321881345254e-05,
       "loss": 1.1115,
       "step": 25
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.16207309067249298,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.19,
+      "step": 26
+    },
+    {
+      "epoch": 2.5238095238095237,
+      "grad_norm": 0.16097423434257507,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.1981,
+      "step": 27
+    },
+    {
+      "epoch": 2.5238095238095237,
+      "eval_loss": 1.141075849533081,
+      "eval_runtime": 6.4063,
+      "eval_samples_per_second": 15.61,
+      "eval_steps_per_second": 7.805,
+      "step": 27
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 0.16795802116394043,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 1.1345,
+      "step": 28
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.16206511855125427,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 1.1223,
+      "step": 29
+    },
+    {
+      "epoch": 2.8095238095238093,
+      "grad_norm": 0.16133540868759155,
+      "learning_rate": 0.0,
+      "loss": 1.1377,
+      "step": 30
+    },
+    {
+      "epoch": 2.8095238095238093,
+      "eval_loss": 1.1379709243774414,
+      "eval_runtime": 6.1889,
+      "eval_samples_per_second": 16.158,
+      "eval_steps_per_second": 8.079,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -268,12 +319,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4707063061020672.0,
+  "total_flos": 5663067115094016.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null