Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4644b1b71e6c8c5480aa3dff2da6d975e4e8ea3861ab28ef7f2db07d811806d2
+oid sha256:408c01cd3c91de81ba58237c7c425edac6f6f69a8b49a3d552a584928753890a
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b2e1af9c0c9e9d0957bcb613dd3a843890bf760889f7efe3ef30d9187b10d39
+oid sha256:c31bc69348444f3318f8f366a87367103ea03272691e1570daae63113d4c5758
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7905e4a210e3175997e931d5de6516847be0ee940f33f420864ad850d0cba01f
+oid sha256:e7254d747a9567a251330f490946709565318529ba02616603ef974a6195873f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1740139211136891,
+  "epoch": 0.23201856148491878,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 51.439,
       "eval_steps_per_second": 25.79,
       "step": 150
+    },
+    {
+      "epoch": 0.18561484918793503,
+      "grad_norm": 0.7166157364845276,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.9414,
+      "step": 160
+    },
+    {
+      "epoch": 0.19721577726218098,
+      "grad_norm": 0.7609933614730835,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.976,
+      "step": 170
+    },
+    {
+      "epoch": 0.2088167053364269,
+      "grad_norm": 0.7842931151390076,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.9988,
+      "step": 180
+    },
+    {
+      "epoch": 0.22041763341067286,
+      "grad_norm": 0.670917272567749,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.9113,
+      "step": 190
+    },
+    {
+      "epoch": 0.23201856148491878,
+      "grad_norm": 0.6730884313583374,
+      "learning_rate": 0.0,
+      "loss": 0.9451,
+      "step": 200
+    },
+    {
+      "epoch": 0.23201856148491878,
+      "eval_loss": 0.929216206073761,
+      "eval_runtime": 7.0331,
+      "eval_samples_per_second": 51.613,
+      "eval_steps_per_second": 25.878,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4864473877708800.0,
+  "total_flos": 6485965170278400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null