Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4daaecb78ff5a24ff7050c30cdb4cb1d17985458376ce4dad1a159b2aea70616
+oid sha256:6bb21fc38b6e1a61b8c8cbf28a1ad57f09b3e5737d24f28b2a452d471ca5ca2e
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d44d916bfc79cee9c303e5e8565cafc1f7c4d2a244195f0558d2436f75750691
+oid sha256:f16eb2dede13e2fdb04313cbb52f7e91a89c8d596d36cbaa70ec17303c83ff4c
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8576ff425e9c2cd02ce3137670504fa72ddd3e9c6eb744ccc76dc401f3cc1f8
+oid sha256:2a5633f06ee7068396712f7cccd0b526b2f848878b47f6580e5d95109e7a8e98
 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": 1.296440839767456,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.4,
+  "best_metric": 1.2911254167556763,
+  "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": 12.72,
       "eval_steps_per_second": 1.595,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 1.04,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 1.2911254167556763,
+      "eval_runtime": 151.7717,
+      "eval_samples_per_second": 12.716,
+      "eval_steps_per_second": 1.595,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1472241709150208e+17,
+  "total_flos": 1.2108220870201344e+17,
   "trial_name": null,
   "trial_params": null
 }