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:efbdd287397a30ac9703304868f153af7eaa1f55050da0ca359fb8ab1568a5be
+oid sha256:0f62f3f80bdbe4ec415de0be3ae4ac3a7be429dba42b12f2a5da98039040e1c8
 size 18899856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c785e7b3916fb588f1e30bf4f86e8bd20b41f7798731e7d8eeb9de48a7c5d91
+oid sha256:bae5a9fac15bbc68944eb74383a2a1c3c77311ab6098f221a8b3e3a99c150606
 size 37911546

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4f77c1509e996519a6483f61bf0c10948dac58bd7f9064c1970977169b2ba1
+oid sha256:9a8530fcb35807d7008ff35c5159c8264cd9ca963aa9eb088c64b4bb159785bd
 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": 14.923,
       "eval_test_steps_per_second": 0.933,
       "step": 18432
+    },
+    {
+      "epoch": 3.9976144003469964,
+      "grad_norm": 0.8142043948173523,
+      "learning_rate": 3.0003218233616098e-06,
+      "loss": 2.0155,
+      "step": 18433
+    },
+    {
+      "epoch": 3.997831273042724,
+      "grad_norm": 0.721076488494873,
+      "learning_rate": 3.000265969737023e-06,
+      "loss": 2.0117,
+      "step": 18434
+    },
+    {
+      "epoch": 3.9980481457384514,
+      "grad_norm": 0.7382825613021851,
+      "learning_rate": 3.000215435499207e-06,
+      "loss": 2.0278,
+      "step": 18435
+    },
+    {
+      "epoch": 3.998265018434179,
+      "grad_norm": 0.7999047040939331,
+      "learning_rate": 3.000170220649976e-06,
+      "loss": 2.1662,
+      "step": 18436
+    },
+    {
+      "epoch": 3.9984818911299067,
+      "grad_norm": 0.735248327255249,
+      "learning_rate": 3.000130325190978e-06,
+      "loss": 2.172,
+      "step": 18437
+    },
+    {
+      "epoch": 3.9986987638256344,
+      "grad_norm": 0.6671957969665527,
+      "learning_rate": 3.0000957491236143e-06,
+      "loss": 2.1481,
+      "step": 18438
+    },
+    {
+      "epoch": 3.998915636521362,
+      "grad_norm": 0.9371853470802307,
+      "learning_rate": 3.000066492449139e-06,
+      "loss": 2.0251,
+      "step": 18439
+    },
+    {
+      "epoch": 3.9991325092170893,
+      "grad_norm": 0.696266233921051,
+      "learning_rate": 3.00004255516859e-06,
+      "loss": 1.9831,
+      "step": 18440
+    },
+    {
+      "epoch": 3.9993493819128174,
+      "grad_norm": 0.6927635669708252,
+      "learning_rate": 3.0000239372828404e-06,
+      "loss": 2.0868,
+      "step": 18441
+    },
+    {
+      "epoch": 3.9995662546085446,
+      "grad_norm": 0.7484452724456787,
+      "learning_rate": 3.0000106387925348e-06,
+      "loss": 2.0038,
+      "step": 18442
+    },
+    {
+      "epoch": 3.9997831273042723,
+      "grad_norm": 0.7934520244598389,
+      "learning_rate": 3.00000265969815e-06,
+      "loss": 2.1349,
+      "step": 18443
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.1140004396438599,
+      "learning_rate": 2.9999999999999997e-06,
+      "loss": 2.1212,
+      "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": 4.350735014776799e+18,
+  "total_flos": 4.3534139748762255e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null