Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a171e32cc1849fd7942460b4773dbf4cbc946a33593846fd44b83c5dcecdc05
+oid sha256:5b8c41391313fbabac66df91d686437cfb19c06601814bb44b7c97f85924f711
 size 137714904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ab5410440e0b92b3527beeb5079186c67686aac995f9b502477aa0f29f784a
+oid sha256:50be7b12b15a2f5c632bc838da1b41c25c45873d3a33d402a1272b4fb791b0a4
 size 70674004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e5700376c413440a135b0ae23eb33f34b0583493929a20002943dd79e730af1
+oid sha256:1886754a6b20d3842ee62d8a95f1549c9cf7c692e0339998abe883efc3c28e13
 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": 0.00031702419951389624,
+  "epoch": 0.00047553629927084436,
   "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": 19.083,
       "eval_steps_per_second": 9.543,
       "step": 6
+    },
+    {
+      "epoch": 0.0003698615660995456,
+      "grad_norm": 4.748237133026123,
+      "learning_rate": 0.00014,
+      "loss": 10.8447,
+      "step": 7
+    },
+    {
+      "epoch": 0.00042269893268519497,
+      "grad_norm": 5.545794486999512,
+      "learning_rate": 0.00016,
+      "loss": 10.1694,
+      "step": 8
+    },
+    {
+      "epoch": 0.00047553629927084436,
+      "grad_norm": 6.876077651977539,
+      "learning_rate": 0.00018,
+      "loss": 9.2215,
+      "step": 9
+    },
+    {
+      "epoch": 0.00047553629927084436,
+      "eval_loss": 8.000694274902344,
+      "eval_runtime": 417.6416,
+      "eval_samples_per_second": 19.081,
+      "eval_steps_per_second": 9.542,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2068199038255104.0,
+  "total_flos": 3102298557382656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null