Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f7940531818f6241327dc72753b252273e5f91616410ee96b759d999874041
+oid sha256:e4a6c9eb732352eb117fc44c7f011b07886deb5b16f74b9790adedb05db26565
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c872529993a005bf071b432683074c21a95625741dacf3124436a75f3d5d56e
+oid sha256:64ae956b6cb526d9e43b6d3fd64b63a73fadf60002d934e6ab55a274155b549d
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa382952e0adbb7e7abb917278c0a70d8bfd97851369da627797b4983c8f9cb6
+oid sha256:27dda49e3c662d8ae35bbed5c7910e852710db95858fa8dba4b98a5d1c00f698
 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": 0.07207207207207207,
+  "epoch": 0.10810810810810811,
   "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": 7.7044,
       "step": 18
+    },
+    {
+      "epoch": 0.07567567567567568,
+      "grad_norm": 9.290574073791504,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.7934,
+      "step": 21
+    },
+    {
+      "epoch": 0.08648648648648649,
+      "grad_norm": 5.527563571929932,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 7.2144,
+      "step": 24
+    },
+    {
+      "epoch": 0.08648648648648649,
+      "eval_loss": 1.7844364643096924,
+      "eval_runtime": 27.3944,
+      "eval_samples_per_second": 4.271,
+      "eval_steps_per_second": 2.154,
+      "step": 24
+    },
+    {
+      "epoch": 0.0972972972972973,
+      "grad_norm": 3.0254547595977783,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 7.2205,
+      "step": 27
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 6.862932205200195,
+      "learning_rate": 0.0,
+      "loss": 7.2248,
+      "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": 1.26956599246848e+16,
+  "total_flos": 1.90434898870272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null