Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899bdb2486224b307036721d41ad0b636afa792ebf46dff3bf948134abbd956
+oid sha256:24fe59e774986b096b35bf87f2895f8c302e54882ebc30642ebe53cc08d7295a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3888e1b3b2b7972ec737a9fe3889d061f41cb121d19c200ace761f226f085373
+oid sha256:255b7ec2b68e6f8eb4782991d3e5212839afe13eb33219daab924d9f6ab251c5
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f97c514d53470dc7e4ba1cf9fed99c8fdb74c2e026219c5ff950afa74acafeba
+oid sha256:9eea10de36051242f0fdde70c83002a84a2aaa2d6cb866b9a7a90db7a971698d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0025548494235620987,
+  "epoch": 0.0038322741353431482,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 4.3582,
       "step": 18
+    },
+    {
+      "epoch": 0.0026825918947402036,
+      "grad_norm": 9.606064796447754,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.7334,
+      "step": 21
+    },
+    {
+      "epoch": 0.0030658193082745188,
+      "grad_norm": 8.248322486877441,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.5828,
+      "step": 24
+    },
+    {
+      "epoch": 0.0030658193082745188,
+      "eval_loss": 0.8723397254943848,
+      "eval_runtime": 369.6879,
+      "eval_samples_per_second": 8.918,
+      "eval_steps_per_second": 4.461,
+      "step": 24
+    },
+    {
+      "epoch": 0.0034490467218088335,
+      "grad_norm": 28.229259490966797,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.2489,
+      "step": 27
+    },
+    {
+      "epoch": 0.0038322741353431482,
+      "grad_norm": 6.48671293258667,
+      "learning_rate": 0.0,
+      "loss": 3.6725,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6534582019031040.0,
+  "total_flos": 9801873028546560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null