Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85e5444f3b008d3cd6dcfcfe4915e9eb5f8bf95ea5ebd0cedf05098b0f455d69
+oid sha256:54ebe0169da0a9e91b80c2c3a8ece902998a2ba1f4784b2e89a518ed651b29a0
 size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2aa76de8945a005775baa62a405c054d67f45851cd8da94ffe122e455ff009
+oid sha256:45e4a3c9749ac8a9ed1e317b4ad11a0eb4816d1eb2d003d5d8a0a5102569f81f
 size 531130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee1ed5ef878d1cb5694ce6c44d444574299065f1806fd6b37cb49af7d452c98c
+oid sha256:fd99a4658dfec332ee6968e96d372e722985cc6df641834de9b1d2be914dae4b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0053652386189875795,
+  "epoch": 0.010730477237975159,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 298.414,
       "eval_steps_per_second": 149.207,
       "step": 50
+    },
+    {
+      "epoch": 0.006438286342785095,
+      "grad_norm": 12260.19140625,
+      "learning_rate": 0.0002,
+      "loss": 15.0047,
+      "step": 60
+    },
+    {
+      "epoch": 0.0075113340665826115,
+      "grad_norm": 14937.4189453125,
+      "learning_rate": 0.0002,
+      "loss": 16.1831,
+      "step": 70
+    },
+    {
+      "epoch": 0.008584381790380128,
+      "grad_norm": 12745.7001953125,
+      "learning_rate": 0.0002,
+      "loss": 16.4468,
+      "step": 80
+    },
+    {
+      "epoch": 0.009657429514177644,
+      "grad_norm": 9584.7265625,
+      "learning_rate": 0.0002,
+      "loss": 16.3645,
+      "step": 90
+    },
+    {
+      "epoch": 0.010730477237975159,
+      "grad_norm": 10061.3291015625,
+      "learning_rate": 0.0002,
+      "loss": 16.2659,
+      "step": 100
+    },
+    {
+      "epoch": 0.010730477237975159,
+      "eval_loss": 4.0766682624816895,
+      "eval_runtime": 13.2944,
+      "eval_samples_per_second": 295.163,
+      "eval_steps_per_second": 147.581,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9495065395200.0,
+  "total_flos": 18990130790400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null