Training in progress, step 18444, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:195b15be2e8b1b7904e5d8749601220537331772934d950fce781fd8d7e5a001
+oid sha256:6286f714f60e819357e2ff83ccb680fc1edeec36b5d22da800765db964908b43
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62d10b215bfbe1dc56494fcfc3b74aa2b5605bd7a48d6e5385ac19955bcfc045
+oid sha256:ce6c7abaa15b1e3a6af628219ef7a13b0763dd109560c1371c4a105e59597ca2
 size 168150738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328bb4e59c1aa99386194ef35d5ac9c293719a8db28e42ca89f2abe0d2bcd607
+oid sha256:61ef5f4a6e53cc6a6774b0b359452317c4b2b55b42e8f0b94b1c3ab8e4f3dd39
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82ab3f4c71b15efcf419ae699bcc09c12d9d69fda628dcac52fdb8059760dd34
+oid sha256:112b0e3f3850ccaa762f9eb894c6c56a98cff86a4eab4f8d883ff8a96dbc8748
 size 1000

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.9973975276512688,
+  "epoch": 4.0,
   "eval_steps": 2048,
-  "global_step": 18432,
+  "global_step": 18444,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -129211,6 +129211,90 @@
       "eval_test_samples_per_second": 13.089,
       "eval_test_steps_per_second": 0.818,
       "step": 18432
+    },
+    {
+      "epoch": 3.9976144003469964,
+      "grad_norm": 1.635145664215088,
+      "learning_rate": 3.0003218233616098e-06,
+      "loss": 1.8547,
+      "step": 18433
+    },
+    {
+      "epoch": 3.997831273042724,
+      "grad_norm": 1.6694488525390625,
+      "learning_rate": 3.000265969737023e-06,
+      "loss": 1.9154,
+      "step": 18434
+    },
+    {
+      "epoch": 3.9980481457384514,
+      "grad_norm": 1.7029920816421509,
+      "learning_rate": 3.000215435499207e-06,
+      "loss": 1.8898,
+      "step": 18435
+    },
+    {
+      "epoch": 3.998265018434179,
+      "grad_norm": 1.4422721862792969,
+      "learning_rate": 3.000170220649976e-06,
+      "loss": 1.6105,
+      "step": 18436
+    },
+    {
+      "epoch": 3.9984818911299067,
+      "grad_norm": 1.5800944566726685,
+      "learning_rate": 3.000130325190978e-06,
+      "loss": 1.7082,
+      "step": 18437
+    },
+    {
+      "epoch": 3.9986987638256344,
+      "grad_norm": 1.4681060314178467,
+      "learning_rate": 3.0000957491236143e-06,
+      "loss": 1.8266,
+      "step": 18438
+    },
+    {
+      "epoch": 3.998915636521362,
+      "grad_norm": 1.8325995206832886,
+      "learning_rate": 3.000066492449139e-06,
+      "loss": 1.8093,
+      "step": 18439
+    },
+    {
+      "epoch": 3.9991325092170893,
+      "grad_norm": 1.5083396434783936,
+      "learning_rate": 3.00004255516859e-06,
+      "loss": 1.7805,
+      "step": 18440
+    },
+    {
+      "epoch": 3.9993493819128174,
+      "grad_norm": 1.8943501710891724,
+      "learning_rate": 3.0000239372828404e-06,
+      "loss": 1.9769,
+      "step": 18441
+    },
+    {
+      "epoch": 3.9995662546085446,
+      "grad_norm": 1.4337064027786255,
+      "learning_rate": 3.0000106387925348e-06,
+      "loss": 1.8074,
+      "step": 18442
+    },
+    {
+      "epoch": 3.9997831273042723,
+      "grad_norm": 1.4833385944366455,
+      "learning_rate": 3.00000265969815e-06,
+      "loss": 1.8618,
+      "step": 18443
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.9734277725219727,
+      "learning_rate": 2.9999999999999997e-06,
+      "loss": 1.8028,
+      "step": 18444
     }
   ],
   "logging_steps": 1,
@@ -129225,12 +129309,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.458545126859866e+18,
+  "total_flos": 4.461328143064498e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null