Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:340b966ee70c061f3f46d7bd7e90e7baabbd8a40cc05c02405603beede4c7ae6
+oid sha256:ac2cea72195674b1742f4f6308dd300ae278ff79416d6159960d79cd121f8400
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f7760676ae2092f6a2d6a05278a344bb35eb3e42bca3933d556ce0b1a45907c
+oid sha256:5066816f26dc7470fa06e20c218dbbe2e8c17240f0d1b253182436ab309acedf
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdacbad4cb5c5b201b8278a06f6d380ea7579ea2ad463c9cc04eb0e18aa64385
+oid sha256:7113b4ddb953686a19c918f6a7688101b24bc7cc26d2b0fb2a2b9afb4381aaed
 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": 0.056074766355140186,
+  "epoch": 0.08411214953271028,
   "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": 2.677,
       "eval_steps_per_second": 1.368,
       "step": 6
+    },
+    {
+      "epoch": 0.06542056074766354,
+      "grad_norm": 2.7943050861358643,
+      "learning_rate": 0.00014,
+      "loss": 0.8291,
+      "step": 7
+    },
+    {
+      "epoch": 0.07476635514018691,
+      "grad_norm": 2.0762441158294678,
+      "learning_rate": 0.00016,
+      "loss": 0.5093,
+      "step": 8
+    },
+    {
+      "epoch": 0.08411214953271028,
+      "grad_norm": 1.6523407697677612,
+      "learning_rate": 0.00018,
+      "loss": 0.2518,
+      "step": 9
+    },
+    {
+      "epoch": 0.08411214953271028,
+      "eval_loss": 0.1820312887430191,
+      "eval_runtime": 16.8474,
+      "eval_samples_per_second": 2.671,
+      "eval_steps_per_second": 1.365,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7841498422837248.0,
+  "total_flos": 1.1762247634255872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null