Training in progress, step 25000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:836cfae75cc4e0a96e10094df88438cae683a37de38a069fc93d3c052ab11376
+oid sha256:1162f3dd69f25f8696965e77a13ee78f76a56faa207df54198db0aa2c1ff8d34
 size 18915040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e18baf51eaeff3b682fafb60aa656bf58fa9f0d9c1f4c498dbcbe8e4b4ee56e3
+oid sha256:4a392000d9293e83d945e935d13a886a99f359ba416db00324a34f83ac689a60
 size 37990394

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70477ead05bce581876eb5d73e88cb3d8565a2290d6f8c1491b79ba699fb1d56
+oid sha256:052cb623d333c55cb6aa932d620c4240d6da273a0db3bf72bfdbcc2be7693707
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546e6ba6ca3229060626f9c187788612a8a7a0657f68d7b81ddac25c2e83e7b7
+oid sha256:c007ea3613e729374f49a992d59f46f0bb1762290dd86d4c3105289d354272e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5813699984012325,
+  "epoch": 0.7267124980015406,
   "eval_steps": 500,
-  "global_step": 20000,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,13 +247,73 @@
       "learning_rate": 7.75878444599598e-05,
       "loss": 3.2134,
       "step": 20000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.746059656145306e-05,
+      "loss": 3.1633,
+      "step": 20500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.733018788656199e-05,
+      "loss": 3.2601,
+      "step": 21000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.71966294386527e-05,
+      "loss": 3.173,
+      "step": 21500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.70599324868567e-05,
+      "loss": 3.2264,
+      "step": 22000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.692010856511996e-05,
+      "loss": 3.1828,
+      "step": 22500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.677716947122976e-05,
+      "loss": 3.1522,
+      "step": 23000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.663112726581924e-05,
+      "loss": 3.2148,
+      "step": 23500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.648199427134978e-05,
+      "loss": 3.1741,
+      "step": 24000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.632978307107125e-05,
+      "loss": 3.2386,
+      "step": 24500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.617450650796032e-05,
+      "loss": 3.1865,
+      "step": 25000
     }
   ],
   "logging_steps": 500,
   "max_steps": 172005,
   "num_train_epochs": 5,
   "save_steps": 5000,
-  "total_flos": 6.8534491152384e+17,
+  "total_flos": 8.566811394048e+17,
   "trial_name": null,
   "trial_params": null
 }