Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720277acde4ee9020cddee66ee5a359ca8e2d3d041ae3562e4cb82d210cdb793
+oid sha256:800397f46f49cc1d9a60b7efbd090a7b4831db4ef2d92075e339a7555b502643
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04befc22a65dba13687a4fa49e937511ef258aaca6dd9bf5dcff017dc9db2023
+oid sha256:ccaddec401f25d7a60e95ed6cca5551e7acc037bbe1e1705f974af92e0f5d650
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e081351a022c45bf031e060833aff1ba860157aceb2df94543881413eca763a
+oid sha256:4c8969108774412257f3bec7d27805c014858246b2ae2cafcc98af96054f2f98
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.47761194029850745,
+  "epoch": 0.5373134328358209,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 4.168,
       "eval_steps_per_second": 0.532,
       "step": 40
+    },
+    {
+      "epoch": 0.5014925373134328,
+      "grad_norm": 2.642303228378296,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 5.2156,
+      "step": 42
+    },
+    {
+      "epoch": 0.5373134328358209,
+      "grad_norm": 2.631282091140747,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.3161,
+      "step": 45
+    },
+    {
+      "epoch": 0.5373134328358209,
+      "eval_loss": 1.3332561254501343,
+      "eval_runtime": 33.8375,
+      "eval_samples_per_second": 4.167,
+      "eval_steps_per_second": 0.532,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1447984071901184e+17,
+  "total_flos": 1.2878982080888832e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null