Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c36d7773bb0d3c115ec948b91b60b9393438feb1f37da37ea3f7372d666db6d
+oid sha256:ff254455935887d90b79fa4aa9d0eae3ab921914f21ea22e6ea69e72e59bcdf6
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a75f740dcf2417c880990ece6a64533196fed3042d0ba22f6912b4100133c175
+oid sha256:f304b57a89f79b0de1c5455e3235179725fedcacfec4e5aa9b9f691ab047aacb
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d77b60a4a6ac9b1290011cfbb000725f2f3c555f2baada62884afb493a185f
+oid sha256:76d05d926a13e2b0db86e596e2ee777dcc8276585d379e27b6ca55897b2ce7fe
 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": 0.006012024048096192,
+  "epoch": 0.009018036072144289,
   "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": 10.847,
       "eval_steps_per_second": 5.436,
       "step": 6
+    },
+    {
+      "epoch": 0.0070140280561122245,
+      "grad_norm": 0.6731088161468506,
+      "learning_rate": 0.00014,
+      "loss": 5.417,
+      "step": 7
+    },
+    {
+      "epoch": 0.008016032064128256,
+      "grad_norm": 0.7657998204231262,
+      "learning_rate": 0.00016,
+      "loss": 5.9049,
+      "step": 8
+    },
+    {
+      "epoch": 0.009018036072144289,
+      "grad_norm": 1.130814790725708,
+      "learning_rate": 0.00018,
+      "loss": 5.6898,
+      "step": 9
+    },
+    {
+      "epoch": 0.009018036072144289,
+      "eval_loss": 1.3330568075180054,
+      "eval_runtime": 38.7627,
+      "eval_samples_per_second": 10.861,
+      "eval_steps_per_second": 5.443,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3799469166428160.0,
+  "total_flos": 5699203749642240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null