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:ee3af80940e127dda67cff63fd1c1f6d7b55b70405008057883cceb711974ea1
+oid sha256:7b50e03d14fcad644aca50efb494dd352aebcd6a4147e6d51b91b625a93c2421
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c62a323a26a1e422792c650207892cc7d1c316c689921177b12dfb7ec31708
+oid sha256:84eacedc0720f19f0550b724a9770faddfe700e4dd5359d1b9d399bc58a5c244
 size 23159290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab02c7ceefc7f624e543606b4a55635739ddb16ca766d25eb43335d75637fe11
+oid sha256:339da5f2a2261c348d33fea33072b75ed2b5c4b4b5c9ce3a1c9e4ad35b2548fa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a696a29736a0994c2fe4b0c9dc20b476c186c761e56192644142442def0c36ed
+oid sha256:8cf93c5b0577712034804293556a44a82ffcc949dc7089314caab7285b5b3531
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4de6ea3620112a33a24a165cb6d0ed5c25525674798823367231b5adb6fe75
+oid sha256:4fecc0b3d642b817d1205149fa3e71a134831a7a7daf9fe98ab4b0ee7dab9e4d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79b21cab1ae686e3ff2c695f6c92066579975268e19e0bf73b6e8401d6065e4
+oid sha256:8b6a3cc9d628f50ce037b3b77bd34ac845724d71b81e3024c4e48c9af81541aa
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007841599686336013,
+  "epoch": 0.0015683199372672025,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 63.866,
       "eval_steps_per_second": 7.99,
       "step": 3
+    },
+    {
+      "epoch": 0.0010455466248448016,
+      "grad_norm": 1.1910107135772705,
+      "learning_rate": 8e-05,
+      "loss": 0.3072,
+      "step": 4
+    },
+    {
+      "epoch": 0.0013069332810560022,
+      "grad_norm": 0.855275571346283,
+      "learning_rate": 0.0001,
+      "loss": 0.2373,
+      "step": 5
+    },
+    {
+      "epoch": 0.0015683199372672025,
+      "grad_norm": 0.7225483059883118,
+      "learning_rate": 0.00012,
+      "loss": 0.1783,
+      "step": 6
+    },
+    {
+      "epoch": 0.0015683199372672025,
+      "eval_loss": 0.17279158532619476,
+      "eval_runtime": 100.8564,
+      "eval_samples_per_second": 63.883,
+      "eval_steps_per_second": 7.992,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2322534166953984.0,
+  "total_flos": 4645068333907968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null