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:f48dc8e22ae18ecdfba0cbc7115fba3bfacb1a48d6ba3db1ecefa39836c4122e
+oid sha256:a3196171e226eab9b66f08c37d983a5413d1e20abff37e9ffa677a128930a373
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b665fdde13f789aaa00bd763bba73559b7a7610ea9d9497872a80295765c7a
+oid sha256:ef9141f4089ce86621666108ca37a43d7e50f61e766630606564902d6e8c22e6
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a3b82189f7d54944fe397aa129e3a549502a28beefbceb6e38af17a764834ad
+oid sha256:98a3a2e7f87b24b5cd339ace17128f363e2805a5c9b3761ecc5ef97cd28ba615
 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": 1.1895887851715088,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.4,
+  "best_metric": 1.1847771406173706,
+  "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": 4.212,
       "eval_steps_per_second": 0.528,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 0.9625,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 1.1847771406173706,
+      "eval_runtime": 456.5256,
+      "eval_samples_per_second": 4.228,
+      "eval_steps_per_second": 0.53,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.988908280368333e+16,
+  "total_flos": 6.321054100743782e+16,
   "trial_name": null,
   "trial_params": null
 }