Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc34257fd6c62c11c26292ecf24cd0407bc3a2ef7bdf75745a54e133aab81f1
+oid sha256:a6f75969f4be06bbc856a289ae77e22ee992918959dc3ebe0512277c023269d5
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d14e9fc2fa3fd39d52512ce812309b0ee0833260c4c12cc0dd21c44719197196
+oid sha256:eafddc7f7487e9ae80c3163239ba681592f6ac7ab7343d8396b05418fc2071c2
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7701f88edd66004d4466bf636029979f849065c394232d4daaa3f0dc50a5728
+oid sha256:88861b17d557d63b349882c3778027603bbfce23e2152d04a0a61bc48795d1d0
 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": 0.00042494422607032827,
+  "epoch": 0.0006374163391054924,
   "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": 24.104,
       "eval_steps_per_second": 12.052,
       "step": 6
+    },
+    {
+      "epoch": 0.0004957682637487163,
+      "grad_norm": 0.4078926146030426,
+      "learning_rate": 0.00014,
+      "loss": 1.0795,
+      "step": 7
+    },
+    {
+      "epoch": 0.0005665923014271044,
+      "grad_norm": 0.4543113112449646,
+      "learning_rate": 0.00016,
+      "loss": 1.0601,
+      "step": 8
+    },
+    {
+      "epoch": 0.0006374163391054924,
+      "grad_norm": 0.3541891872882843,
+      "learning_rate": 0.00018,
+      "loss": 1.068,
+      "step": 9
+    },
+    {
+      "epoch": 0.0006374163391054924,
+      "eval_loss": 1.2101588249206543,
+      "eval_runtime": 249.3616,
+      "eval_samples_per_second": 23.845,
+      "eval_steps_per_second": 11.922,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1400649484861440.0,
+  "total_flos": 2059778654208000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null