Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b65047e192baf9cfd222ae4b9798f57171f0c91bd72c92de7f11c517dd656c9
+oid sha256:7be5facbc44796fc72b37c1ec608b126b5d8314c4a0db318bb887365899a5f9a
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0e37db546ef652757c2500c7b31b90d87c190949e3fd391ea2e6ec66b14f4d5
+oid sha256:efcb5f01b3d828364544cf06e0ffd698cfb6dc5d3dc888636a76e635b4013161
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f8dce4ea8db55fab98810852c3b7d6da325bbb69e21644a5658ad81a5d8213
+oid sha256:e40e5299fd01e8b6d766680bf3e901a3191a7ff234b09bf485cb92c3fed6364e
 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": 0.01675977653631285,
+  "epoch": 0.025139664804469275,
   "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": 13.536,
       "eval_steps_per_second": 6.813,
       "step": 6
+    },
+    {
+      "epoch": 0.019553072625698324,
+      "grad_norm": 4.200657367706299,
+      "learning_rate": 0.00014,
+      "loss": 8.5678,
+      "step": 7
+    },
+    {
+      "epoch": 0.0223463687150838,
+      "grad_norm": 4.508555889129639,
+      "learning_rate": 0.00016,
+      "loss": 8.5416,
+      "step": 8
+    },
+    {
+      "epoch": 0.025139664804469275,
+      "grad_norm": 4.351197242736816,
+      "learning_rate": 0.00018,
+      "loss": 7.5666,
+      "step": 9
+    },
+    {
+      "epoch": 0.025139664804469275,
+      "eval_loss": 1.9446355104446411,
+      "eval_runtime": 11.0871,
+      "eval_samples_per_second": 13.619,
+      "eval_steps_per_second": 6.855,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1711683215032320.0,
+  "total_flos": 2567524822548480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null