Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:576c9e5ec4b7fea756fde9c5b17b583cf0abfc99572d330859e88fd91f358026
+oid sha256:4dc4ef51d48b75cf51f1cf7e6074888c2cadb122e526193f9fe5687fbc4b00c4
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2312bcc8338a53330fe6b26d85ce1a6e3c582377c3f3f321e572b0ecbf0b522
+oid sha256:6d8912d691fd67ece5eb5d2da66c5178e4c35f7863496490e0928881ef405737
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed24157843733a720e9b3d1b006fa11ac517dab21a9d332b9aa678dbbf520076
+oid sha256:ea79ba6b741361467cf4e50bbf4517697d1d1f11c3bfdd43932d2f7f51104b12
 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": 7.003945555996544e-05,
+  "epoch": 0.00010505918333994817,
   "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": 13.554,
       "eval_steps_per_second": 6.777,
       "step": 6
+    },
+    {
+      "epoch": 8.171269815329302e-05,
+      "grad_norm": 6.491903781890869,
+      "learning_rate": 0.00014,
+      "loss": 3.2719,
+      "step": 7
+    },
+    {
+      "epoch": 9.338594074662059e-05,
+      "grad_norm": 5.3933892250061035,
+      "learning_rate": 0.00016,
+      "loss": 2.9401,
+      "step": 8
+    },
+    {
+      "epoch": 0.00010505918333994817,
+      "grad_norm": 5.092551231384277,
+      "learning_rate": 0.00018,
+      "loss": 1.4722,
+      "step": 9
+    },
+    {
+      "epoch": 0.00010505918333994817,
+      "eval_loss": 2.5769283771514893,
+      "eval_runtime": 2659.7191,
+      "eval_samples_per_second": 13.562,
+      "eval_steps_per_second": 6.781,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2052393617326080.0,
+  "total_flos": 2975970745122816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null