Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46df361a804d7cfc88d8eaa02aa3880d291f4c8e36187f0a69d7b3f92fc51deb
+oid sha256:15d3b1a829b40431597e00bb5d51d90f026948ee3bcdfebea229e391d214acc9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f17643612e3d8bc3933a70a596ad9df4fd9ebae79e1e97ba200aae93d865a0
+oid sha256:7285730e049c9aa300fbb8e9b09d31fce1a139696d9c1b44eb6df931fd872793
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba60c260384233e5cb0e7bbfabb0bd75f441fc8b78b5fed933e9ca48341a17ab
+oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005467468562055768,
+  "epoch": 0.010934937124111536,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 2.7921,
       "step": 9
+    },
+    {
+      "epoch": 0.0065609622744669215,
+      "grad_norm": 2.491004228591919,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 3.0156,
+      "step": 12
+    },
+    {
+      "epoch": 0.008201202843083653,
+      "grad_norm": 2.5566985607147217,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.8363,
+      "step": 15
+    },
+    {
+      "epoch": 0.008747949699289229,
+      "eval_loss": 2.7811272144317627,
+      "eval_runtime": 99.6032,
+      "eval_samples_per_second": 7.741,
+      "eval_steps_per_second": 3.875,
+      "step": 16
+    },
+    {
+      "epoch": 0.009841443411700382,
+      "grad_norm": 2.3769283294677734,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.7551,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709500842311680.0,
+  "total_flos": 7419001684623360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null