Training in progress, step 18444, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f6c98c0f897bcc3ac3b4414b05848ac7776ea94e028266f9686dfe3ccc2140
+oid sha256:fdda39341f708250fb5998f447d13d70f26a8944dbc0fc19b0f6972737238302
 size 18899856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a84f196d23f22e0c4eba236ffee8cec2d96782b391895a0215af71b3e1bfbbe
+oid sha256:d214aa30c3dc0ff733d67ad7ab92c45d9fc115f184e0c43db66917659dad3221
 size 37911546

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d0bbbc8564cdc936edb07b992feb927ee48638b36c16ae513b6b501eb6a4d7
+oid sha256:1810cf1d4372b4023939ddac1cf1b6ce0e3f798979b5a4c9c646ef01643ac09c
 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": 14.815,
       "eval_test_steps_per_second": 0.926,
       "step": 18432
+    },
+    {
+      "epoch": 3.9976144003469964,
+      "grad_norm": 0.7556371092796326,
+      "learning_rate": 3.0003218233616098e-06,
+      "loss": 2.1035,
+      "step": 18433
+    },
+    {
+      "epoch": 3.997831273042724,
+      "grad_norm": 0.8098835349082947,
+      "learning_rate": 3.000265969737023e-06,
+      "loss": 2.1821,
+      "step": 18434
+    },
+    {
+      "epoch": 3.9980481457384514,
+      "grad_norm": 0.8024788498878479,
+      "learning_rate": 3.000215435499207e-06,
+      "loss": 2.1821,
+      "step": 18435
+    },
+    {
+      "epoch": 3.998265018434179,
+      "grad_norm": 0.6993958353996277,
+      "learning_rate": 3.000170220649976e-06,
+      "loss": 1.8316,
+      "step": 18436
+    },
+    {
+      "epoch": 3.9984818911299067,
+      "grad_norm": 0.8931436538696289,
+      "learning_rate": 3.000130325190978e-06,
+      "loss": 1.9669,
+      "step": 18437
+    },
+    {
+      "epoch": 3.9986987638256344,
+      "grad_norm": 0.8958826065063477,
+      "learning_rate": 3.0000957491236143e-06,
+      "loss": 2.0962,
+      "step": 18438
+    },
+    {
+      "epoch": 3.998915636521362,
+      "grad_norm": 0.7808493375778198,
+      "learning_rate": 3.000066492449139e-06,
+      "loss": 2.0824,
+      "step": 18439
+    },
+    {
+      "epoch": 3.9991325092170893,
+      "grad_norm": 0.6934779286384583,
+      "learning_rate": 3.00004255516859e-06,
+      "loss": 2.0578,
+      "step": 18440
+    },
+    {
+      "epoch": 3.9993493819128174,
+      "grad_norm": 0.8631987571716309,
+      "learning_rate": 3.0000239372828404e-06,
+      "loss": 2.2236,
+      "step": 18441
+    },
+    {
+      "epoch": 3.9995662546085446,
+      "grad_norm": 0.6597968935966492,
+      "learning_rate": 3.0000106387925348e-06,
+      "loss": 2.0531,
+      "step": 18442
+    },
+    {
+      "epoch": 3.9997831273042723,
+      "grad_norm": 0.7519582509994507,
+      "learning_rate": 3.00000265969815e-06,
+      "loss": 2.1216,
+      "step": 18443
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.018497347831726,
+      "learning_rate": 2.9999999999999997e-06,
+      "loss": 2.0909,
+      "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": 4.448916451273212e+18,
+  "total_flos": 4.451693457275093e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null