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:cf5b338899e4e3215f011ef26c41c7e9bc41b20f8f1fb586ea0f638c7912ac01
+oid sha256:e03bc065e7eeaa8916ddaff6a5f83ca721ad9ec362958f5fb9e7d7c1cccfa6dd
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c0615ae142b1988b6a40f9267e4f8ed3030355a25a5aaad7bc3333f5c3521d
+oid sha256:0cf1c6bf84c30c430435142500620bbd4afed4a52c0d1d1ca22aaf74c7544f5e
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:702cc6df180758d3d6dd377c11b570f3269e7e0e686b4163706b71308e16fd59
+oid sha256:b07181d8eceed15be73912136d507719bf63f6a4031a4e4fa60c5cab4618dd14
 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": 0.0007298071484610192,
+  "epoch": 0.0010947107226915288,
   "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": 1.6198,
       "step": 18
+    },
+    {
+      "epoch": 0.0007662975058840702,
+      "grad_norm": 1.0266218185424805,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.5081,
+      "step": 21
+    },
+    {
+      "epoch": 0.000875768578153223,
+      "grad_norm": 1.0099457502365112,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.5154,
+      "step": 24
+    },
+    {
+      "epoch": 0.000875768578153223,
+      "eval_loss": 1.5118098258972168,
+      "eval_runtime": 861.1832,
+      "eval_samples_per_second": 13.399,
+      "eval_steps_per_second": 6.7,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009852396504223758,
+      "grad_norm": 1.1712850332260132,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.503,
+      "step": 27
+    },
+    {
+      "epoch": 0.0010947107226915288,
+      "grad_norm": 1.214179277420044,
+      "learning_rate": 0.0,
+      "loss": 1.5166,
+      "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": 8475499214929920.0,
+  "total_flos": 1.2819192562581504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null