Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1302710820e6477ba2366d1e4518883096879f9abd192342c484672ad0b54866
+oid sha256:706b939b888ead75282d0181aece96055c691e032852b14d252c93468110a305
 size 598799664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b2fcde2c1ece2fe49a991b04fe2565b2aeeeb0b44702f5f2c049421b0b6ef4
+oid sha256:eee78cb14bcfcd87fc477092844acd24d9cc0cf8ca05a3558f172852372b941b
 size 167923706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6593b7b714be8967d283453716bb1bac70c417a7ea9a4fa8a3c6e2eac85e5884
+oid sha256:2069380fdf39b9a53a13190db1c870306796bc235ffebf76a2d39bb076f79866
 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": 0.0935672514619883,
+  "epoch": 0.14035087719298245,
   "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": 6.4626,
       "step": 18
+    },
+    {
+      "epoch": 0.09824561403508772,
+      "grad_norm": 2.6301050186157227,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.1923,
+      "step": 21
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "grad_norm": 1.8707858324050903,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.8334,
+      "step": 24
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "eval_loss": 1.4073123931884766,
+      "eval_runtime": 6.7895,
+      "eval_samples_per_second": 13.256,
+      "eval_steps_per_second": 6.628,
+      "step": 24
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 2.524521589279175,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.1063,
+      "step": 27
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 2.786410093307495,
+      "learning_rate": 0.0,
+      "loss": 6.0852,
+      "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": 3146526259937280.0,
+  "total_flos": 4949223596359680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null