Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84cd5ab01d91a237730e00ef2509a2291ac794713e16635ab1bbffedfec9b4ee
+oid sha256:581f3c135cad7b16ddeeba434e17a1791d5414792d4ccc36aba48d417a379a5d
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e1d98619bd2c7a9b78fb2b25ab20ecdc91e930803bf9ceebfd21cace9c9b21
+oid sha256:c5c1c822eb6e9af9555655e2ebedaa066a0dce58796cb3bd04884cde5721bb5d
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915645dce5efa953cda784192197cbb5fb91024cc42226c4c837679d41b16b57
+oid sha256:c9f64353c1aeda899ddfe69408d0cdaa908885a1ce7b3d466330b14d991afcdf
 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": 0.006643966447969438,
+  "epoch": 0.009965949671954157,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 14.794,
       "eval_steps_per_second": 7.397,
       "step": 20
+    },
+    {
+      "epoch": 0.00697616477036791,
+      "grad_norm": 0.44995152950286865,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.6803,
+      "step": 21
+    },
+    {
+      "epoch": 0.007972759737563326,
+      "grad_norm": 0.4498210847377777,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.6859,
+      "step": 24
+    },
+    {
+      "epoch": 0.008304958059961797,
+      "eval_loss": 1.7118247747421265,
+      "eval_runtime": 85.788,
+      "eval_samples_per_second": 14.781,
+      "eval_steps_per_second": 7.39,
+      "step": 25
+    },
+    {
+      "epoch": 0.008969354704758742,
+      "grad_norm": 0.5588821172714233,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.6411,
+      "step": 27
+    },
+    {
+      "epoch": 0.009965949671954157,
+      "grad_norm": 0.4593096375465393,
+      "learning_rate": 0.0,
+      "loss": 1.7028,
+      "step": 30
+    },
+    {
+      "epoch": 0.009965949671954157,
+      "eval_loss": 1.7027456760406494,
+      "eval_runtime": 85.7385,
+      "eval_samples_per_second": 14.789,
+      "eval_steps_per_second": 7.395,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1994401995816960.0,
+  "total_flos": 2985169438900224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null