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:ba18ec9447482af8b0d61d4837b92182b2f21647d55c5305e6a964b8d0b8a016
+oid sha256:448b4f5f68ac81305893a126ea133c0e55b2b3884738b92387c71f7f320c1fc6
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db697750184c6494d4eef95d7edec7462f71e9b159ec243244a1c53cc3a39211
+oid sha256:fcc8c31db2d2a3e201c96be04652c643e8f71e768c67ef11e36457424bbdb266
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deabd56c17b610f6d8e6c3c09d2dcb705e4d72db3bc1813e41a578dadc2811d7
+oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
 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": 0.011665208515602217,
+  "epoch": 0.023330417031204434,
   "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": 46.0,
       "step": 9
+    },
+    {
+      "epoch": 0.01399825021872266,
+      "grad_norm": 0.00011205866030650213,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 46.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.017497812773403325,
+      "grad_norm": 9.639419295126572e-05,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 46.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.018664333624963548,
+      "eval_loss": 11.5,
+      "eval_runtime": 3.5697,
+      "eval_samples_per_second": 101.129,
+      "eval_steps_per_second": 50.705,
+      "step": 16
+    },
+    {
+      "epoch": 0.02099737532808399,
+      "grad_norm": 6.34350799373351e-05,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 46.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 398960885760.0,
+  "total_flos": 797921771520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null