Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924586b99cb797c348757148a69b1cbff426ac09ab71d8ae2eac93c7814eaaa9
+oid sha256:afaaf7d622de379fa6d3c6e7f88155ffdfdebb482c3fb7b9660674000f3aac41
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0114ee7f4ed38656baa8b3a40e6e60417d8811a4a8f2234403d1ad24b3ab1fe6
+oid sha256:62effaee8a16094ed7b4794237761c448591f5f9688a32bcb2f50c0553bee613
 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": 0.0011228385358185494,
+  "epoch": 0.0022456770716370988,
   "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": 154.523,
       "eval_steps_per_second": 77.262,
       "step": 10
+    },
+    {
+      "epoch": 0.001347406242982259,
+      "grad_norm": 1.678512489888817e-05,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 46.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0016842578037278239,
+      "grad_norm": 1.1590057511057239e-05,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 46.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0016842578037278239,
+      "eval_loss": 11.5,
+      "eval_runtime": 24.371,
+      "eval_samples_per_second": 153.871,
+      "eval_steps_per_second": 76.936,
+      "step": 15
+    },
+    {
+      "epoch": 0.0020211093644733886,
+      "grad_norm": 1.3804982700094115e-05,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 46.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0022456770716370988,
+      "eval_loss": 11.5,
+      "eval_runtime": 24.0385,
+      "eval_samples_per_second": 156.0,
+      "eval_steps_per_second": 78.0,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 408934907904.0,
+  "total_flos": 807895793664.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null