Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a70822989fd7622a708720bfb1b96fa90c8a7c096278446f542b697f2476e6c3
+oid sha256:8098593e33ccd37144bf244f7e85c00bb3adb8cb3c225688acba199c234f2025
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4846a07d8ba9fe305a2396f282e0f5a803517f27860136bfea8257642e795d8
+oid sha256:80e3ff26fad7d91b228dfcbd64c6833d0f4ba5294112e04881857700ec1092e4
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f2ddb10d7215588eb0c9f889dd80cbcbd213c0e0d68d15bbb349d7fc72b3fa
+oid sha256:e8256a51c921e3764623587232574eeea4ef70bf2e730f79b7a5b429639bc4f0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02190580503833516,
+  "epoch": 0.04381161007667032,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 9.358,
       "eval_steps_per_second": 4.727,
       "step": 5
+    },
+    {
+      "epoch": 0.02628696604600219,
+      "grad_norm": 0.40466296672821045,
+      "learning_rate": 0.00012,
+      "loss": 0.114,
+      "step": 6
+    },
+    {
+      "epoch": 0.03066812705366922,
+      "grad_norm": 0.3059878349304199,
+      "learning_rate": 0.00014,
+      "loss": 0.1037,
+      "step": 7
+    },
+    {
+      "epoch": 0.03504928806133625,
+      "grad_norm": 0.20368129014968872,
+      "learning_rate": 0.00016,
+      "loss": 0.055,
+      "step": 8
+    },
+    {
+      "epoch": 0.03943044906900329,
+      "grad_norm": 0.31183746457099915,
+      "learning_rate": 0.00018,
+      "loss": 0.0435,
+      "step": 9
+    },
+    {
+      "epoch": 0.04381161007667032,
+      "grad_norm": 0.2398935854434967,
+      "learning_rate": 0.0002,
+      "loss": 0.0406,
+      "step": 10
+    },
+    {
+      "epoch": 0.04381161007667032,
+      "eval_loss": 0.029431650415062904,
+      "eval_runtime": 10.3988,
+      "eval_samples_per_second": 9.328,
+      "eval_steps_per_second": 4.712,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3699128496291840.0,
+  "total_flos": 7398256992583680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null