Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260ab1be1b9f239822ae48551af1079b07e727b82bd231fa2a47734e8889c307
+oid sha256:a3c54f7924030bd3e3f9dd25cb60003f1cc725a7fdc3003fd144bc3a5289fd51
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d2d770d75b45659d7a9f5350369ac4d2f0e6f2cb937a64e8766157a1f9ebb0
+oid sha256:12622b8402fa237989d4e2489897b86d0bb9a058d73046d9ad1b1990c67b2230
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a730a343a863d4216549392bfe668d1a20b027b7071c0dc0f4c8937109e105f0
+oid sha256:0c5d32480fe2b55ccec5bc9dc6ed03aaa85fcf9703fb06e7c8e52b632b5ff929
 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": 0.004920452681646712,
+  "epoch": 0.006560603575528949,
   "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": 43.125,
       "eval_steps_per_second": 21.562,
       "step": 150
+    },
+    {
+      "epoch": 0.0052484828604231586,
+      "grad_norm": 33.7310905456543,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 1.7622,
+      "step": 160
+    },
+    {
+      "epoch": 0.005576513039199606,
+      "grad_norm": 41.134033203125,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 1.7296,
+      "step": 170
+    },
+    {
+      "epoch": 0.005904543217976054,
+      "grad_norm": 19.332448959350586,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.6473,
+      "step": 180
+    },
+    {
+      "epoch": 0.0062325733967525014,
+      "grad_norm": 72.38475799560547,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 1.6072,
+      "step": 190
+    },
+    {
+      "epoch": 0.006560603575528949,
+      "grad_norm": 32.443729400634766,
+      "learning_rate": 0.0,
+      "loss": 1.5626,
+      "step": 200
+    },
+    {
+      "epoch": 0.006560603575528949,
+      "eval_loss": 1.6815910339355469,
+      "eval_runtime": 297.5309,
+      "eval_samples_per_second": 43.142,
+      "eval_steps_per_second": 21.571,
+      "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": 1.041211453341696e+16,
+  "total_flos": 1.38119886667776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null