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:f7065b4ae538bd396bf31139a095d24a735dded98872f2745b54bc77fb99164b
+oid sha256:97a427a3560750d80f1896a1c1b75081170106cfa39485a14df51c39300fe8ae
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f0f0a15fe1aa3a639b3cc53244c02c3378d52452f9de94e62131f61c9d9415
+oid sha256:908c2f1b856c37fddec282faa3327d0f596a1f64e44f1938657182f09356c730
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c0d77bcd56d96825c5ef028b2dd99ac2e61994d3c453c8d2883da32a92047be
+oid sha256:6806389118ec16be45f91f2597dc80c85380e866e2552fc0b165cbd873f66c65
 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": 0.014714898835070508,
+  "epoch": 0.022072348252605765,
   "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": 18.372,
       "eval_steps_per_second": 9.186,
       "step": 6
+    },
+    {
+      "epoch": 0.017167381974248927,
+      "grad_norm": 1.1592398881912231,
+      "learning_rate": 0.00014,
+      "loss": 1.8487,
+      "step": 7
+    },
+    {
+      "epoch": 0.019619865113427344,
+      "grad_norm": 1.2560908794403076,
+      "learning_rate": 0.00016,
+      "loss": 1.9289,
+      "step": 8
+    },
+    {
+      "epoch": 0.022072348252605765,
+      "grad_norm": 1.6090513467788696,
+      "learning_rate": 0.00018,
+      "loss": 1.802,
+      "step": 9
+    },
+    {
+      "epoch": 0.022072348252605765,
+      "eval_loss": 1.684467077255249,
+      "eval_runtime": 9.365,
+      "eval_samples_per_second": 18.366,
+      "eval_steps_per_second": 9.183,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1873043106299904.0,
+  "total_flos": 2809564659449856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null