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:d169812e68872b996231e0a0076c3912c7f156df560dd4e465c91765bc2a23ae
+oid sha256:61454aa457830bd78b1058287dc3fcbe688bdde8a02df8eb0cf52a1e66563fed
 size 40422168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b6375afd5c12194949440c8320c9770ee4dc26d94509cc4931070b65ef3e85
+oid sha256:5d9b2d0121410a2f5a31c57d50c3de06d7b96a853b91aac4595b269fb1413a47
 size 20958516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905451142165304754e3dca94d7298a0d5c846a2e8dca3114b6489ab3c972537
+oid sha256:7b7153db191a9c0af7d8507bfea423baff3bb8f9644f9d8c9e17149088d8c377
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cb728dce3e2541bc781b20d0c6d71ae5c372163a515fbc5a49b008d9df8a390
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.56,
+  "epoch": 15.4,
   "eval_steps": 500,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -113,6 +113,41 @@
       "learning_rate": 6.800000000000001e-05,
       "loss": 0.0269,
       "step": 150
+    },
+    {
+      "epoch": 12.32,
+      "grad_norm": 0.23131920397281647,
+      "learning_rate": 5.466666666666666e-05,
+      "loss": 0.0285,
+      "step": 160
+    },
+    {
+      "epoch": 13.08,
+      "grad_norm": 0.14665621519088745,
+      "learning_rate": 4.133333333333333e-05,
+      "loss": 0.0289,
+      "step": 170
+    },
+    {
+      "epoch": 13.88,
+      "grad_norm": 0.18651145696640015,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.027,
+      "step": 180
+    },
+    {
+      "epoch": 14.64,
+      "grad_norm": 0.20021669566631317,
+      "learning_rate": 1.4666666666666668e-05,
+      "loss": 0.0272,
+      "step": 190
+    },
+    {
+      "epoch": 15.4,
+      "grad_norm": 0.12408873438835144,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.0275,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -127,12 +162,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 231256227840000.0,
+  "total_flos": 308074905600000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null