Training in progress, step 18444, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8267f04b6ad643fe76621b515f6ef4a89574aeb2874b7c9ea7900800d3cbcafa
+oid sha256:1e23fbabee21f3e140e3b3444ce9c1357a35aa394fba3f86e89b9d2359d8f434
 size 18899856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68754aed55e70b60e47104a0f3d7786bfd3a484332f76c108dfa140bff640ce9
+oid sha256:59480740c38bdb92e1247b615148ace85eb247a65b4c1157843ee5dae6ae1151
 size 37911546

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fe7f27596afd7931277b7e50b18e54d28b82a6b242c7ca22b1114b4d30423e
+oid sha256:9e591aeb9b33177e25fcd649ccfc82933f3329eda6ee273b1a0bfe406c384c55
 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": 14.935,
       "eval_test_steps_per_second": 0.933,
       "step": 18432
+    },
+    {
+      "epoch": 3.9976144003469964,
+      "grad_norm": 0.7179842591285706,
+      "learning_rate": 3.0003218233616098e-06,
+      "loss": 2.1294,
+      "step": 18433
+    },
+    {
+      "epoch": 3.997831273042724,
+      "grad_norm": 0.7400171756744385,
+      "learning_rate": 3.000265969737023e-06,
+      "loss": 2.1279,
+      "step": 18434
+    },
+    {
+      "epoch": 3.9980481457384514,
+      "grad_norm": 0.816265881061554,
+      "learning_rate": 3.000215435499207e-06,
+      "loss": 2.2085,
+      "step": 18435
+    },
+    {
+      "epoch": 3.998265018434179,
+      "grad_norm": 0.6999260783195496,
+      "learning_rate": 3.000170220649976e-06,
+      "loss": 1.9719,
+      "step": 18436
+    },
+    {
+      "epoch": 3.9984818911299067,
+      "grad_norm": 0.7754216194152832,
+      "learning_rate": 3.000130325190978e-06,
+      "loss": 1.9501,
+      "step": 18437
+    },
+    {
+      "epoch": 3.9986987638256344,
+      "grad_norm": 0.7585975527763367,
+      "learning_rate": 3.0000957491236143e-06,
+      "loss": 2.0977,
+      "step": 18438
+    },
+    {
+      "epoch": 3.998915636521362,
+      "grad_norm": 0.7343212962150574,
+      "learning_rate": 3.000066492449139e-06,
+      "loss": 2.0824,
+      "step": 18439
+    },
+    {
+      "epoch": 3.9991325092170893,
+      "grad_norm": 0.7170373797416687,
+      "learning_rate": 3.00004255516859e-06,
+      "loss": 2.0028,
+      "step": 18440
+    },
+    {
+      "epoch": 3.9993493819128174,
+      "grad_norm": 0.9392771124839783,
+      "learning_rate": 3.0000239372828404e-06,
+      "loss": 2.3121,
+      "step": 18441
+    },
+    {
+      "epoch": 3.9995662546085446,
+      "grad_norm": 0.6705074310302734,
+      "learning_rate": 3.0000106387925348e-06,
+      "loss": 2.0513,
+      "step": 18442
+    },
+    {
+      "epoch": 3.9997831273042723,
+      "grad_norm": 0.719359815120697,
+      "learning_rate": 3.00000265969815e-06,
+      "loss": 2.2008,
+      "step": 18443
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0389312505722046,
+      "learning_rate": 2.9999999999999997e-06,
+      "loss": 2.1296,
+      "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": 4.4158057732736287e+18,
+  "total_flos": 4.418577011869483e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null