Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b6961ec56fb4a44ef494b0d658571c48ac344664dc6fe4a951f2610f0f03b8f
+oid sha256:3727237ae3935b62ae996af32d303af34e4cd5253f63eb2d60627cc5ef912920
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:345c3d0745bb4c43f0fbe85fc7c3ff9f29987a091928463d46244addf1e119f1
+oid sha256:777bdf50a841d4b9781e0ab8e00624d257f1bc7472e451827de97f2d11a85d33
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523bfe0a33577b4182bf5e3b1a37489a75b989d79cb5926278ae5a0647ffb1d8
+oid sha256:33c67ae2325c5a312a1fadb56ddccb9bf6f35a5c2e1dc133fc3f71609827e280
 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": 1.0008,
       "step": 195
+    },
+    {
+      "epoch": 0.09584937954642704,
+      "grad_norm": 0.4474238157272339,
+      "learning_rate": 2.7308266142119785e-07,
+      "loss": 0.9659,
+      "step": 196
+    },
+    {
+      "epoch": 0.09633840699309248,
+      "grad_norm": 0.27518409490585327,
+      "learning_rate": 1.5363960325660565e-07,
+      "loss": 1.134,
+      "step": 197
+    },
+    {
+      "epoch": 0.09682743443975793,
+      "grad_norm": 0.4118005037307739,
+      "learning_rate": 6.829398569770939e-08,
+      "loss": 0.9985,
+      "step": 198
+    },
+    {
+      "epoch": 0.09731646188642337,
+      "grad_norm": 0.38307955861091614,
+      "learning_rate": 1.7074954194729044e-08,
+      "loss": 1.0373,
+      "step": 199
+    },
+    {
+      "epoch": 0.09780548933308882,
+      "grad_norm": 0.5424556136131287,
+      "learning_rate": 0.0,
+      "loss": 0.9834,
+      "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": 8.655960681322906e+17,
+  "total_flos": 8.877908391100416e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null