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:a6240f638a5db2d60ba18d506b6241a1aac2c65a7765413c1ea7a88c3a07d97d
+oid sha256:a5cf07bd09106ceac21d28422a3fa5adf3d76e63cf13424e42dfa762903316f6
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7952d78a31b301b138fe9fe4a6dc29ed1ca5677447c336a57d3108b74884a5b3
+oid sha256:4d31eb5f012b1c1a4cf9c6abd31e502ce1b7717457c6499a76bcba66bcc1660b
 size 27002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a78dfddfa629e4ef8b356831307d1dbe5f884dddfbe001f2ca92bd05e0511827
+oid sha256:d8f56528b2b76cb96fdbaeedcd2bc1a7c80bcd9d88cbac90fd5655ce599b9d75
 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": 0.0005055931239335145,
+  "epoch": 0.001011186247867029,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 141.783,
       "eval_steps_per_second": 70.891,
       "step": 10
+    },
+    {
+      "epoch": 0.0006067117487202175,
+      "grad_norm": 2.447623228363227e-05,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 46.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007583896859002717,
+      "grad_norm": 2.218727058789227e-05,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 46.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007583896859002717,
+      "eval_loss": 11.5,
+      "eval_runtime": 59.2136,
+      "eval_samples_per_second": 140.643,
+      "eval_steps_per_second": 70.322,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009100676230803261,
+      "grad_norm": 4.8929170588962734e-05,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 46.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.001011186247867029,
+      "eval_loss": 11.5,
+      "eval_runtime": 59.2385,
+      "eval_samples_per_second": 140.584,
+      "eval_steps_per_second": 70.292,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 558545240064.0,
+  "total_flos": 1127064502272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null