Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fe60a83fc8ab9ce94540e824abfda25a6d58d18f3fa8f4df0aac01a82f86f2f
+oid sha256:58aa81030c52a22a2b7b6d7365da071dbdbc152f62d11c355b58f8d64440255d
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71497f2ba6463d2f439f341b074070db8ec5cc10227a3101e4ce9f1a9ccc588
+oid sha256:2016e238947b5170a48f12c49daf1f51861dc4fe6f8cda78a3016b64da4025e2
 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": 0.03733200597312095,
+  "epoch": 0.049776007964161276,
   "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": 406.842,
       "eval_steps_per_second": 203.421,
       "step": 150
+    },
+    {
+      "epoch": 0.039820806371329016,
+      "grad_norm": 2.028933525085449,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 43.2558,
+      "step": 160
+    },
+    {
+      "epoch": 0.042309606769537086,
+      "grad_norm": 2.050549030303955,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 43.1482,
+      "step": 170
+    },
+    {
+      "epoch": 0.04479840716774515,
+      "grad_norm": 2.0617024898529053,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 43.2396,
+      "step": 180
+    },
+    {
+      "epoch": 0.04728720756595321,
+      "grad_norm": 1.8123018741607666,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 43.2378,
+      "step": 190
+    },
+    {
+      "epoch": 0.049776007964161276,
+      "grad_norm": 2.172649621963501,
+      "learning_rate": 0.0,
+      "loss": 43.2652,
+      "step": 200
+    },
+    {
+      "epoch": 0.049776007964161276,
+      "eval_loss": 10.80179214477539,
+      "eval_runtime": 4.0991,
+      "eval_samples_per_second": 412.777,
+      "eval_steps_per_second": 206.388,
+      "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": 1446720307200.0,
+  "total_flos": 1928960409600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null