Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b0dee2372e0f18f2926fc6260eec903f5561fa89a64d712e0b7d8365d17c593
+oid sha256:7bd5721dcf900ef49f45f0ef10dbf11b456013923d0a2897f59b5787b3ae3720
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b975acebc204f6e79db6fa817f78ef570e8350fee5fb167ce316257a8482e30
+oid sha256:771ffe86212fa3fc844af729b623adbdc1713d63e8ef510a4f21862401e76313
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0dfa4c978e9e36a07b5616ff9458f53247c12dc4ecf4c596cc8b6cb0fe8c5e1
+oid sha256:da87c0fa21811b5f2090e7e71a5104bc8bb10adee2d7d157218e5f725fa79433
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a35430a05f2b9748f37dd11667a782564c85a35d840d60cbaddfa2c905ab7c0a
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0953603520997616,
+  "epoch": 0.09780548933308882,
   "eval_steps": 34,
-  "global_step": 195,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1420,6 +1420,41 @@
       "learning_rate": 4.2658237049655323e-07,
       "loss": 9.1892,
       "step": 195
+    },
+    {
+      "epoch": 0.09584937954642704,
+      "grad_norm": 1.5588723026491867e+19,
+      "learning_rate": 2.7308266142119785e-07,
+      "loss": 8.4245,
+      "step": 196
+    },
+    {
+      "epoch": 0.09633840699309248,
+      "grad_norm": Infinity,
+      "learning_rate": 1.5363960325660565e-07,
+      "loss": 10.2748,
+      "step": 197
+    },
+    {
+      "epoch": 0.09682743443975793,
+      "grad_norm": Infinity,
+      "learning_rate": 6.829398569770939e-08,
+      "loss": 8.9335,
+      "step": 198
+    },
+    {
+      "epoch": 0.09731646188642337,
+      "grad_norm": Infinity,
+      "learning_rate": 1.7074954194729044e-08,
+      "loss": 9.0168,
+      "step": 199
+    },
+    {
+      "epoch": 0.09780548933308882,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 7.8164,
+      "step": 200
     }
   ],
   "logging_steps": 1,
@@ -1434,12 +1469,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.2987353681166336e+17,
+  "total_flos": 4.408959351914496e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null