Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5194638e012d2e383076ad139be88fe11b1a207de27a2e328c42de9948c6eaa0
+oid sha256:4daaecb78ff5a24ff7050c30cdb4cb1d17985458376ce4dad1a159b2aea70616
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05dae03fa651ff4f45c61e157e3bd83eda35192b500535c86ac1503044a601ec
+oid sha256:d44d916bfc79cee9c303e5e8565cafc1f7c4d2a244195f0558d2436f75750691
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb111828d85f47f912262c44e084ad812e1b819e6449de4a16205c7fe52ef94
+oid sha256:c8576ff425e9c2cd02ce3137670504fa72ddd3e9c6eb744ccc76dc401f3cc1f8
 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": 1.3011658191680908,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.2666666666666666,
+  "best_metric": 1.296440839767456,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 2.4,
   "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": 12.731,
       "eval_steps_per_second": 1.596,
       "step": 1700
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 1.0491,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.296440839767456,
+      "eval_runtime": 151.7344,
+      "eval_samples_per_second": 12.72,
+      "eval_steps_per_second": 1.595,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0835407735197696e+17,
+  "total_flos": 1.1472241709150208e+17,
   "trial_name": null,
   "trial_params": null
 }