Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68695d9774ba76eb2abbd235fe2fc5cccca7426aa554eb30c673c55748ce631
+oid sha256:a56b496c8cc60110f21380e0d0daa440a02946d09ff17a64b2adb7a47cd81f79
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c2a42a945903a711ad7088f364a52d27ede11cf610e6abe4ea751ec92327412
+oid sha256:133d94d62cc6a0d9e77ef132684f85fd38e77c533985319da2a98323a77a3fd8
 size 90310010

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb45587948780a74ba481a15afbb6c9165d7f94087804644081497c62466ba73
+oid sha256:83ccae148eee587ae93f6957a30ef36e7134b0b765a678b4303ed6014551eed7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00013043655484449516,
+  "epoch": 0.00019565483226674277,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 16.117,
       "eval_steps_per_second": 16.117,
       "step": 4
+    },
+    {
+      "epoch": 0.00016304569355561895,
+      "grad_norm": 3.022265672683716,
+      "learning_rate": 0.0001,
+      "loss": 2.176,
+      "step": 5
+    },
+    {
+      "epoch": 0.00019565483226674277,
+      "grad_norm": 2.7493996620178223,
+      "learning_rate": 0.00012,
+      "loss": 2.2505,
+      "step": 6
+    },
+    {
+      "epoch": 0.00019565483226674277,
+      "eval_loss": 2.7171995639801025,
+      "eval_runtime": 401.3245,
+      "eval_samples_per_second": 16.089,
+      "eval_steps_per_second": 16.089,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 387089027825664.0,
+  "total_flos": 580633541738496.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null