Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e51f1f96b44ce86fbf1d64f1718ca95e39eb444009bcb0151220ee41471b79b1
+oid sha256:25eb17ce11fb398cce6778e4ac621d162219ae794e46996d3c20bc8b6c854ba5
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:636aeaa5e2d625a775a992ef2e7871fbe6cd8b31f1b7614dae873c0de1175fa7
+oid sha256:9c4359e0cceadf1107c1fce7e6fc86cc1f309e271eae87aaade1a54b18c067ce
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e70e901d59aad5639708bb0f13d15cb4f87186324b7acf9bdc81bd00942e078e
+oid sha256:283cc7a9be29db0e394f81d7a7a23f335322c5acf210c4dd3b7aae445887d966
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
+oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8800793886184692,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.4147727272727275,
+  "best_metric": 1.8730626106262207,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 2.5568181818181817,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,20 @@
       "eval_samples_per_second": 19.102,
       "eval_steps_per_second": 2.394,
       "step": 1700
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.0002,
+      "loss": 1.977,
+      "step": 1800
+    },
+    {
+      "epoch": 2.56,
+      "eval_loss": 1.8730626106262207,
+      "eval_runtime": 78.7309,
+      "eval_samples_per_second": 18.951,
+      "eval_steps_per_second": 2.375,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.178676400658432e+16,
+  "total_flos": 5.483734889084928e+16,
   "trial_name": null,
   "trial_params": null
 }