Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33edbba90eabaa3a4cc357bd97dd9a0bdf9b5e8d4e4b26d8540001d447775a38
+oid sha256:2b90d8753963ed3128048d3a910e4cdd2eeaff14bc04ee7d1ef4ee9c1fc1d5d3
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99e84a0bfbef976865fa49a76b4fb157ad9f965b1cda8416cd04fd67c1c57691
+oid sha256:6793d060a7aeb5015e591f535eb95abc556c1c2dbf971411e4fd176141e0e7d0
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d9358611d5238c19c59fb3aa3eac2040cbac245a7cfcfe56e1467f677e36cf
+oid sha256:372c9c91189dafe7a0013b948ff9907e60fc7ad4b32cc7ac3bccb3f603cf2268
 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": 0.0016875856977112118,
+  "epoch": 0.0025313785465668178,
   "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": 10.3743,
       "step": 18
+    },
+    {
+      "epoch": 0.0017719649825967724,
+      "grad_norm": 0.05221102386713028,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.377,
+      "step": 21
+    },
+    {
+      "epoch": 0.0020251028372534545,
+      "grad_norm": 0.04650892689824104,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.3778,
+      "step": 24
+    },
+    {
+      "epoch": 0.0020251028372534545,
+      "eval_loss": 10.3766450881958,
+      "eval_runtime": 15.2183,
+      "eval_samples_per_second": 327.894,
+      "eval_steps_per_second": 163.947,
+      "step": 24
+    },
+    {
+      "epoch": 0.002278240691910136,
+      "grad_norm": 0.0555795282125473,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.3749,
+      "step": 27
+    },
+    {
+      "epoch": 0.0025313785465668178,
+      "grad_norm": 0.049284838140010834,
+      "learning_rate": 0.0,
+      "loss": 10.3781,
+      "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": 523024465920.0,
+  "total_flos": 784536698880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null