Training in progress, step 28, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c465b0e3b15658575943591e823cbcdecd76aced8e5b9eb3b46fb7c3e5f89def
+oid sha256:8a7b38936076e5b11391ceccd250e1610af1e6bc87425413dd6f9433acbb5e7a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b8f98710483c8d3cd51b5ea223c460194d9ac7e6e5c31f0946ed657c6a258f
+oid sha256:6f6bb764c63ad42972788691621061a20dccf3a6ff14d4f48e016cc4376f18ad
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49b94774303e58a13c6692326b1b2c8587483979f24ee2e9470fb045acc1a400
+oid sha256:7e654dc294f85bc7763a518d429cb3f8268e4e0d46f7022676840843e0297900
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:470670603e8fdc5330cdb9a9152c4fd9c3d8c5a74dd26bffbbb0d869d097eafa
+oid sha256:ff994fffd2fb6fe21545e6fbc55baa2a1474438a89b2d40605678f7de701427c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007186166629238716,
+  "epoch": 0.008383861067445169,
   "eval_steps": 4,
-  "global_step": 24,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,42 @@
       "eval_samples_per_second": 8.458,
       "eval_steps_per_second": 8.458,
       "step": 24
+    },
+    {
+      "epoch": 0.007485590238790329,
+      "grad_norm": 18.92926597595215,
+      "learning_rate": 0.000138268343236509,
+      "loss": 2.2366,
+      "step": 25
+    },
+    {
+      "epoch": 0.007785013848341942,
+      "grad_norm": 30.20500946044922,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.3568,
+      "step": 26
+    },
+    {
+      "epoch": 0.008084437457893555,
+      "grad_norm": 15.139212608337402,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 3.0559,
+      "step": 27
+    },
+    {
+      "epoch": 0.008383861067445169,
+      "grad_norm": 20.157346725463867,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 3.2366,
+      "step": 28
+    },
+    {
+      "epoch": 0.008383861067445169,
+      "eval_loss": 3.518523931503296,
+      "eval_runtime": 83.1412,
+      "eval_samples_per_second": 8.468,
+      "eval_steps_per_second": 8.468,
+      "step": 28
     }
   ],
   "logging_steps": 1,
@@ -250,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8902647402725376.0,
+  "total_flos": 1.0386421969846272e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null