Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1be781d2ff87c04388aa549d471acb1e75cc1efe382632ff5dc00d5c1ea625ec
+oid sha256:d9524377ee5d4b3bcce89a67ebd975f6f3f260af775688b92228ede57453387d
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ad46c9cf2c24c36d0e90811f32a6a02d31aec3126bc1b48c2d510d7f257d952
+oid sha256:4cd215fcbd800927e1199ba0e4ed9e6406c199fe450a002f5f63449266911938
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0909f77b12ea1b25d87482885e6c2cc12d4e855bbbbb4a8ffcede021a58b61fd
+oid sha256:0c0f06add41f04254087e910e0c029b635008b5c3eb0d1e97de321c80184c521
 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": 1.3101677894592285,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.4,
+  "best_metric": 1.304863691329956,
+  "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": 30.76,
       "eval_steps_per_second": 3.858,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 1.3863,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 1.304863691329956,
+      "eval_runtime": 47.3226,
+      "eval_samples_per_second": 30.662,
+      "eval_steps_per_second": 3.846,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.035490006368256e+16,
+  "total_flos": 6.370864876486656e+16,
   "trial_name": null,
   "trial_params": null
 }