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:a3298903dc3f13152f8e39cf91e2e010fd92f62cdbd4d4a81d8929e56b76db33
+oid sha256:6ff47faa45db36675ef26ef4651c6dea0e71b458bbceec27c80d905a4cc3960e
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e285ce39f69850b8555b7c9d940f48f8ddf0349c4a81b8fb52c0d8772438f390
+oid sha256:2d525f68ac9af49f79941f941dd21068fe2976ecf4a03f912a8d2de64c9d6aeb
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18e9b7512779c0e3e3a657c9a00521c9021cafecacedfae811bbcdc8a1161350
+oid sha256:9b835124e9438a67b4922362546d9917dd2ad1ecf9964a45797b5ccba615a520
 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": 0.03536693191865606,
+  "epoch": 0.07073386383731212,
   "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": 4.1655,
       "step": 9
+    },
+    {
+      "epoch": 0.042440318302387266,
+      "grad_norm": 2.5720601081848145,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 4.069,
+      "step": 12
+    },
+    {
+      "epoch": 0.05305039787798409,
+      "grad_norm": 2.05781626701355,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.6597,
+      "step": 15
+    },
+    {
+      "epoch": 0.05658709106984969,
+      "eval_loss": 3.3761134147644043,
+      "eval_runtime": 8.564,
+      "eval_samples_per_second": 13.895,
+      "eval_steps_per_second": 7.006,
+      "step": 16
+    },
+    {
+      "epoch": 0.0636604774535809,
+      "grad_norm": 2.680410385131836,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.3868,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1378569745858560.0,
+  "total_flos": 2757139491717120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null