Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6ee24688aeb3d2c93a06912041be2abd9025d40045580fcb4b26ea6818a091
+oid sha256:d267725dbe2328baa7d4dff038ef7092b3767f5be9559a1ab7499ee3bbf8e9f1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ae584bdb89a600f9fc921a16a87cf6e57498f30a1191fced914e969ad5453c5
+oid sha256:8b864b302da9500d04c4a32a2943eba655a893b7a412cfb274b8bb93a189d059
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d70c6d4108d09c3ca027b24128794370fd3c24d3d571630cd63800625c78dfd
+oid sha256:d8411ae60e3071af8551a0675d2d647900880b3e57a28709241102be9168b435
 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": 0.0008489324674222165,
+  "epoch": 0.0012733987011333248,
   "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": 13.969,
       "step": 18
+    },
+    {
+      "epoch": 0.0008913790907933274,
+      "grad_norm": 15.9353666305542,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 13.4526,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010187189609066599,
+      "grad_norm": 16.094314575195312,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 13.4364,
+      "step": 24
+    },
+    {
+      "epoch": 0.0010187189609066599,
+      "eval_loss": 2.2031667232513428,
+      "eval_runtime": 2836.1989,
+      "eval_samples_per_second": 10.493,
+      "eval_steps_per_second": 2.623,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011460588310199923,
+      "grad_norm": 18.387222290039062,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 12.7279,
+      "step": 27
+    },
+    {
+      "epoch": 0.0012733987011333248,
+      "grad_norm": 15.67333698272705,
+      "learning_rate": 0.0,
+      "loss": 13.3088,
+      "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": 2.109388496044032e+16,
+  "total_flos": 3.164082744066048e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null