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:fda2791a842cbeddd7c970d37206e1628bee5d7e490f46a8e6b3e6c9abce45fd
+oid sha256:7e7d47e152e992e27a5be5f95546282a9c8b52423904a093f96dd44bd80c74c4
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ee11e49318592b47058d3e70c618f7a6d80df2eaf56173d0c3b952e83b5c2b
+oid sha256:d3ccab88a4a734c5dae00a2634c5d645383715574eda8723e0ac50d1d5369556
 size 100824826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286cbddbe58e94b390d9c43f9eeef9abf68010ab845f692c08c30a9935964055
+oid sha256:972a8c16afbf6f1f9e6b09a194835abcf491a013c12bba315ff2e296ef7ce393
 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": 0.016824395373291272,
+  "epoch": 0.025236593059936908,
   "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": 5.5651,
       "step": 18
+    },
+    {
+      "epoch": 0.017665615141955835,
+      "grad_norm": 5.273889541625977,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.653,
+      "step": 21
+    },
+    {
+      "epoch": 0.02018927444794953,
+      "grad_norm": 5.292482852935791,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.9318,
+      "step": 24
+    },
+    {
+      "epoch": 0.02018927444794953,
+      "eval_loss": 1.4570142030715942,
+      "eval_runtime": 16.5884,
+      "eval_samples_per_second": 30.202,
+      "eval_steps_per_second": 15.131,
+      "step": 24
+    },
+    {
+      "epoch": 0.022712933753943218,
+      "grad_norm": 4.244992256164551,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.0213,
+      "step": 27
+    },
+    {
+      "epoch": 0.025236593059936908,
+      "grad_norm": 4.878582954406738,
+      "learning_rate": 0.0,
+      "loss": 6.3151,
+      "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": 1200474229309440.0,
+  "total_flos": 1800711343964160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null