Training in progress, step 15000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3013da7d467ff0edf5609bec85fc6d89e81f01cb76ee174bfe08b68ff039cc60
+oid sha256:da7c0bd2147c7b3c6459f3053adc8b9c28441ca2d5a2b544fa249ab614d64181
 size 18915040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99dce3a33c4e1782fb3ec4853f117f1ee4e48ec92ee30022ce0d3e259b59836c
+oid sha256:cc6aa1633c82ea829665db3a7b8ff7fad3d38040119298296b0cb31a9dd15bd8
 size 37990394

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5c53f74c5503a1b239583b370c2ca6f4d5e05cfada2113c21780c602a555ad4
+oid sha256:371d7d31c4d289bd5947ddb669187d33a7a9f7a4a5ee671257538ec83fe03ea5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5f525de15f044c00b5d95c98e77e81e7391e623ce79b8cdec263a8fcc6373e8
+oid sha256:b9b9d8461afd25ace0a8409edccf52ff6a1864065ea747ab7226e5bd71843798
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.29068499920061625,
+  "epoch": 0.4360274988009244,
   "eval_steps": 500,
-  "global_step": 10000,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,13 +127,73 @@
       "learning_rate": 7.94544839653823e-05,
       "loss": 3.2599,
       "step": 10000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 7.939234556610201e-05,
+      "loss": 3.3353,
+      "step": 10500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.932688339712721e-05,
+      "loss": 3.1893,
+      "step": 11000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.925810298189578e-05,
+      "loss": 3.2074,
+      "step": 11500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.918601012382602e-05,
+      "loss": 3.2427,
+      "step": 12000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.911061090582703e-05,
+      "loss": 3.3292,
+      "step": 12500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.90319116897854e-05,
+      "loss": 3.2498,
+      "step": 13000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.89499191160285e-05,
+      "loss": 3.2745,
+      "step": 13500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 7.88646401027641e-05,
+      "loss": 3.2645,
+      "step": 14000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 7.87760818454967e-05,
+      "loss": 3.2276,
+      "step": 14500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.868425181642037e-05,
+      "loss": 3.235,
+      "step": 15000
     }
   ],
   "logging_steps": 500,
   "max_steps": 172005,
   "num_train_epochs": 5,
   "save_steps": 5000,
-  "total_flos": 3.4267245576192e+17,
+  "total_flos": 5.1400868364288e+17,
   "trial_name": null,
   "trial_params": null
 }