Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48a7bd4dd0c6af1467f66efea9a3fd18519fc7f345de8d3840d51d79783b7be2
+oid sha256:616674be1bb8e871070e6f95e2d66f199e37b5c177e71ad2559d21b408b27140
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b81941da85d12b26ad01779c375fe1af8ed0a221793b8ca41d53813a51b540
+oid sha256:b0f6148b3bb203d879d795ef2408dd61a0c3f99503646ff2e4a5f0f1f35b41f1
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2859c92cadbbc3acd22ebf9759d91bb2c23ac2b4ae22440b823dabb29822069f
+oid sha256:cacb2b95777e76d9a0e2379d4f68472c2353f0b8d8da4ae69678334b46e61e30
 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": 0.9465362429618835,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.4,
+  "best_metric": 0.9410523176193237,
+  "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": 2.322,
       "eval_steps_per_second": 0.291,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 0.7699,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 0.9410523176193237,
+      "eval_runtime": 827.0957,
+      "eval_samples_per_second": 2.333,
+      "eval_steps_per_second": 0.293,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.661431079860224e+17,
+  "total_flos": 4.921400718048461e+17,
   "trial_name": null,
   "trial_params": null
 }