Training in progress, step 249, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c03cc5a79be0ba30ad0320be99eba132052fb920252f4f639abfb0267ea350a0
+oid sha256:ec309510b4a87175ef5a1513cca05828a4dc3d8f570cdf3286d715b5d21cb5dd
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6554ffe7014b0c305fc27e46e009d8002b5e22780cf3137e2842ed01d2e8fb0
+oid sha256:bea90bae910a7b8d4bba238e71b511c3801b8731427e6d690d08c3fb8150bc89
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3a05bdcba00a37dc9e6fb656aa0abeeb8eb45eca58cc80e1b27558770bab32
+oid sha256:5df2975a82f3511ba3393fb6029de32864ff15e1fa286047e0cb10e71b975b0e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc5b95cc0db21cf56336a583c8dd7fb1d3824838e4cb847d2705abaaeeca402
+oid sha256:2e454b41427ceaf5a552ecf234755def1c3b814a84af8caf7693b503fc58c46c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.797583081570997,
+  "epoch": 3.0181268882175227,
   "eval_steps": 21,
-  "global_step": 231,
+  "global_step": 249,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -642,6 +642,48 @@
       "eval_samples_per_second": 538.147,
       "eval_steps_per_second": 69.19,
       "step": 231
+    },
+    {
+      "epoch": 2.8338368580060425,
+      "grad_norm": 0.20488251745700836,
+      "learning_rate": 9.687663137678604e-07,
+      "loss": 10.175,
+      "step": 234
+    },
+    {
+      "epoch": 2.8700906344410875,
+      "grad_norm": 0.1691775619983673,
+      "learning_rate": 6.207343615165561e-07,
+      "loss": 10.1781,
+      "step": 237
+    },
+    {
+      "epoch": 2.906344410876133,
+      "grad_norm": 0.19150525331497192,
+      "learning_rate": 3.494800565275125e-07,
+      "loss": 10.184,
+      "step": 240
+    },
+    {
+      "epoch": 2.9425981873111784,
+      "grad_norm": 0.16350044310092926,
+      "learning_rate": 1.554251601833201e-07,
+      "loss": 10.1778,
+      "step": 243
+    },
+    {
+      "epoch": 2.9788519637462234,
+      "grad_norm": 0.16869449615478516,
+      "learning_rate": 3.8871399903134265e-08,
+      "loss": 10.1763,
+      "step": 246
+    },
+    {
+      "epoch": 3.0181268882175227,
+      "grad_norm": 0.19018259644508362,
+      "learning_rate": 0.0,
+      "loss": 12.1418,
+      "step": 249
     }
   ],
   "logging_steps": 3,
@@ -656,12 +698,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 25768202600448.0,
+  "total_flos": 27776114491392.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null