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:ecdbd7c34bcb0cfb5c6970e84011f3c10d937de8ce273a576fb62a024d53de77
+oid sha256:5f5bdf3515a109b4fd7779e581979764c2f5f1e555d623e596af0820fca4d9d1
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf4bb125d0e343f6613f968adeb2e8a9ea83e671b2e23ff1301d81f8d66e6e98
+oid sha256:b7cf0464a8238b380328ba5f40ca1d94e8b2935c048ede1fcae46b990957c268
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df2eff7fc04c424d03efebb207948c12df40c4005d61c167cc0982b8e6c469d5
+oid sha256:f77c43d63d3041d91a8112c31b2d67da93c4f39db82fa601678dd4bc0493cbbe
 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": 0.0970716712506067,
+  "epoch": 0.12942889500080892,
   "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": 365.22,
       "eval_steps_per_second": 182.89,
       "step": 150
+    },
+    {
+      "epoch": 0.10354311600064714,
+      "grad_norm": 2.4997355937957764,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 43.0475,
+      "step": 160
+    },
+    {
+      "epoch": 0.11001456075068759,
+      "grad_norm": 2.8624470233917236,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 43.1094,
+      "step": 170
+    },
+    {
+      "epoch": 0.11648600550072803,
+      "grad_norm": 2.4898431301116943,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 43.0726,
+      "step": 180
+    },
+    {
+      "epoch": 0.12295745025076849,
+      "grad_norm": 2.9282381534576416,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 43.1591,
+      "step": 190
+    },
+    {
+      "epoch": 0.12942889500080892,
+      "grad_norm": 2.667485237121582,
+      "learning_rate": 0.0,
+      "loss": 43.0653,
+      "step": 200
+    },
+    {
+      "epoch": 0.12942889500080892,
+      "eval_loss": 10.770923614501953,
+      "eval_runtime": 1.7738,
+      "eval_samples_per_second": 367.003,
+      "eval_steps_per_second": 183.783,
+      "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": 2249650077696.0,
+  "total_flos": 3011589439488.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null