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:db528b04fb1ed4e38a6bcfcaf50ea32c67f0b1a21f51549498ae570b1e8cfe84
+oid sha256:f95a0cd28146ca8f2a5c7f8f7c6ab5553f1f85408a93cbd510d7aa4ba845118d
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c3a7f7ef5d416388c64482a6b1353ec17ed545efbde3d66cb45495f6b125dc0
+oid sha256:8c5450d62a2aa41c656c87b0024dea914a2368baf9e21515fbd0810d4ef57215
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9a75f108334a418a7a60fec99e44fa186e26e0cb2561fc9cb4a7566e3c595c
+oid sha256:c5364d09e27bdf541cc4080b011a0a833388b061da2ef703197275a4e77a4aa4
 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": 0.029861888764464353,
+  "epoch": 0.04479283314669653,
   "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": 11.9236,
       "step": 18
+    },
+    {
+      "epoch": 0.03135498320268757,
+      "grad_norm": 0.15993663668632507,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 11.9209,
+      "step": 21
+    },
+    {
+      "epoch": 0.03583426651735722,
+      "grad_norm": 0.20181462168693542,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 11.9192,
+      "step": 24
+    },
+    {
+      "epoch": 0.03583426651735722,
+      "eval_loss": 11.919516563415527,
+      "eval_runtime": 6.4456,
+      "eval_samples_per_second": 43.906,
+      "eval_steps_per_second": 22.03,
+      "step": 24
+    },
+    {
+      "epoch": 0.040313549832026875,
+      "grad_norm": 0.20186784863471985,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 11.9165,
+      "step": 27
+    },
+    {
+      "epoch": 0.04479283314669653,
+      "grad_norm": 0.1875421553850174,
+      "learning_rate": 0.0,
+      "loss": 11.9174,
+      "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": 8442265337856.0,
+  "total_flos": 12631660167168.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null