Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e609611ebab773e129de2b02bae00dc2a78c5d8f338b89f97a6f05230dbf70c5
+oid sha256:0dc81b83385f0873edd595e3f2e7700a0a297fcef54df6adaa568e56b1debcb0
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9303c04860ea0c913209b671a95265bdfff5f8aee8045c62db1a36bb8bdd71
+oid sha256:ab4e8c09339af63c475e60c79d932f99d4fa0b65d723a1b9f03446a26715bfc4
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106282343697551818085781983c88bfc9ede264fece121f95753ca09a0e5b18
+oid sha256:57d82a3d3954cfc244134be1298ae6e4cf994607d25c2af293db3cc713fa7126
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002343521140513622,
+  "epoch": 0.0035152817107704324,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 11.288,
       "eval_steps_per_second": 5.644,
       "step": 6
+    },
+    {
+      "epoch": 0.002734107997265892,
+      "grad_norm": 63.162654876708984,
+      "learning_rate": 0.00014,
+      "loss": 25.1714,
+      "step": 7
+    },
+    {
+      "epoch": 0.003124694854018162,
+      "grad_norm": 55.868839263916016,
+      "learning_rate": 0.00016,
+      "loss": 16.4742,
+      "step": 8
+    },
+    {
+      "epoch": 0.0035152817107704324,
+      "grad_norm": 20.2382755279541,
+      "learning_rate": 0.00018,
+      "loss": 5.0641,
+      "step": 9
+    },
+    {
+      "epoch": 0.0035152817107704324,
+      "eval_loss": 2.2086901664733887,
+      "eval_runtime": 95.646,
+      "eval_samples_per_second": 11.271,
+      "eval_steps_per_second": 5.635,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1343718124683264.0,
+  "total_flos": 2035936552550400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null