Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003f96b917b07d5bee103609fb15ebe67410541545e425ea1b057ead1a499e3a
+oid sha256:b87038b788fef736431d9618df829f82ceac193dc61f72ad6e7d5c97738cbc53
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1af6269aef4c69130130a525173c7bc8bb7c4864d25a3c1bb56bc6801b07973
+oid sha256:a458fb4ed2ef3cccfdcbd12bb02c3a70958c37d48cbd2699cd9b195254c7d38e
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95342b7972eb34bcf83df59ba126733ad0e109ff06b5e91fa5e6ba3b10a0f05
+oid sha256:083b722e8b556bda137ae078b24a5e36ab3e05cf212936fb76f8e8582540a426
 size 14244

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": 0.0016941973739940702,
+  "epoch": 0.0033883947479881405,
   "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": 3.508,
       "eval_steps_per_second": 1.754,
       "step": 3
+    },
+    {
+      "epoch": 0.002258929831992094,
+      "grad_norm": 5.961012840270996,
+      "learning_rate": 8e-05,
+      "loss": 3.546,
+      "step": 4
+    },
+    {
+      "epoch": 0.002823662289990117,
+      "grad_norm": 3.73958158493042,
+      "learning_rate": 0.0001,
+      "loss": 3.039,
+      "step": 5
+    },
+    {
+      "epoch": 0.0033883947479881405,
+      "grad_norm": 3.5475358963012695,
+      "learning_rate": 0.00012,
+      "loss": 2.3823,
+      "step": 6
+    },
+    {
+      "epoch": 0.0033883947479881405,
+      "eval_loss": 2.191272020339966,
+      "eval_runtime": 211.8851,
+      "eval_samples_per_second": 3.521,
+      "eval_steps_per_second": 1.76,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4601366169255936.0,
+  "total_flos": 9202732338511872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null