Training in progress, step 48, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f91c6a2f061217f78f6a7609554ae95a6b657bf15b463033502ef72be15404
+oid sha256:e04b47f7ca7ce78e14b25e42b5a01aaebcfea582152272fb9a5dcc171e1729af
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92a92a305f9e0a704e8139eda03a762ad45b3e3b1e2c691be051989dd687ba82
+oid sha256:782a84899ed9a6e6c9fe7e8cbe3fa2c8cd40f913da461a3fa5f567111fe4b26d
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76fa3c41cc968cfb5f9d5b60a53b0b1916c4810ccf20412b25d75e05e11a5190
+oid sha256:ea2e2d2952d0dc4b1d6777f3568c14a1bf5bc275182c95c6c0212b96c839ec9a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
+oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011844673261996097,
+  "epoch": 0.012921461740359378,
   "eval_steps": 4,
-  "global_step": 44,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -411,6 +411,42 @@
       "eval_samples_per_second": 8.344,
       "eval_steps_per_second": 4.175,
       "step": 44
+    },
+    {
+      "epoch": 0.012113870381586917,
+      "grad_norm": 2.592027187347412,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 3.7669,
+      "step": 45
+    },
+    {
+      "epoch": 0.012383067501177738,
+      "grad_norm": 2.7980010509490967,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 4.1847,
+      "step": 46
+    },
+    {
+      "epoch": 0.012652264620768558,
+      "grad_norm": 2.249249219894409,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 3.7236,
+      "step": 47
+    },
+    {
+      "epoch": 0.012921461740359378,
+      "grad_norm": 2.2937920093536377,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 4.0901,
+      "step": 48
+    },
+    {
+      "epoch": 0.012921461740359378,
+      "eval_loss": 3.869504928588867,
+      "eval_runtime": 186.9808,
+      "eval_samples_per_second": 8.37,
+      "eval_steps_per_second": 4.188,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -430,7 +466,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3743351907876864e+16,
+  "total_flos": 3.681092935404749e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null