Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50dd62149d8fa5130dab9c47840780adecc7fe832f5a78cdfa1c472ea332452
+oid sha256:8ea48fedf3567693a233ab696e87e4079cef59dd7754ef804b70a8cf2b4c4c93
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7ee16962f8ddf2bc5bd916ebd4a947447a25b62cdb819e2432b9882d0799628
+oid sha256:7fc28a28ffdba7ebaaddae9978b7c6f60a379dfd0b5e9be3ffa8617c8ace143d
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207198ff45c079aff8e96fb155ce64eadd6265eb7e7f1ba1f48dca470b10a3e3
+oid sha256:65ad88a6bfc78cc2d96c86e9869672dcdb69503f9c79a03551b693ef534be373
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
+oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3802986145019531,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.4,
+  "best_metric": 1.371971845626831,
+  "best_model_checkpoint": "./outputs/checkpoint-1900",
+  "epoch": 2.533333333333333,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,6 +259,20 @@
       "eval_samples_per_second": 15.553,
       "eval_steps_per_second": 1.951,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 1.1358,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 1.371971845626831,
+      "eval_runtime": 93.1978,
+      "eval_samples_per_second": 15.569,
+      "eval_steps_per_second": 1.953,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0524178054397952e+17,
+  "total_flos": 1.110771231510528e+17,
   "trial_name": null,
   "trial_params": null
 }