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:c516f5c750f91f55a58a926183dbddd1b3e55a5b01e20d27cc578f5ce350fb13
+oid sha256:6da4768de4c5132093d1e026fa7f3615558477cbe1ed744b1593c53e3568d249
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e8a636ea5b31d665304a7c3dabf71e945ae17e08e512c8ac455e432462dcc83
+oid sha256:f4fdd062e563bdb1668485e6e852a75e1c2b9e4ec534a412359fc90fc6ef2d4a
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ca5557df48bad83ea6fc20618e57f78b74056a1a5464656055e25ac8f74628d
+oid sha256:cb91e2e45c651d389a1f4a7175eaa9b1cb7c3752127424640499fdf51987e759
 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": 0.017582417582417582,
+  "epoch": 0.026373626373626374,
   "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": 56.949,
       "eval_steps_per_second": 28.475,
       "step": 6
+    },
+    {
+      "epoch": 0.020512820512820513,
+      "grad_norm": 16.203353881835938,
+      "learning_rate": 0.00014,
+      "loss": 12.7363,
+      "step": 7
+    },
+    {
+      "epoch": 0.023443223443223443,
+      "grad_norm": 13.992493629455566,
+      "learning_rate": 0.00016,
+      "loss": 11.4852,
+      "step": 8
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "grad_norm": 15.877677917480469,
+      "learning_rate": 0.00018,
+      "loss": 11.3922,
+      "step": 9
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "eval_loss": 2.690427303314209,
+      "eval_runtime": 2.4645,
+      "eval_samples_per_second": 58.429,
+      "eval_steps_per_second": 29.214,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 391769594265600.0,
+  "total_flos": 587654391398400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null