Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11d992a8fda1ca5d195463bf15ac39b701249de30ec13752068e359ce97243ad
+oid sha256:2862b9f6c633e3e8980c074f36bb19a26cd0e9887b38fc84454dd296aeeb3fb3
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97bdee502e691980f4920e0c871ce1f762254e1fd7f4b79c263476c9130b3718
+oid sha256:456c196c460f48367dabef4a556d2ba994723262e929b958928874735dbdf78d
 size 21318842

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed745fbc2286559d345cf5959b3e77a9c2b80395b42cf140b29bbcb6af79de6
+oid sha256:6cdaf8c69858d18dc44a05637dae968a115d8603c38f7640f3a45a768dfa5dec
 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": 0.024524831391784182,
+  "epoch": 0.049049662783568364,
   "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": 12.1654,
       "step": 9
+    },
+    {
+      "epoch": 0.029429797670141016,
+      "grad_norm": 3.815861940383911,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 12.0159,
+      "step": 12
+    },
+    {
+      "epoch": 0.03678724708767627,
+      "grad_norm": 3.5043060779571533,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.5958,
+      "step": 15
+    },
+    {
+      "epoch": 0.03923973022685469,
+      "eval_loss": 2.8279972076416016,
+      "eval_runtime": 2.6373,
+      "eval_samples_per_second": 65.218,
+      "eval_steps_per_second": 32.609,
+      "step": 16
+    },
+    {
+      "epoch": 0.04414469650521153,
+      "grad_norm": 3.8419547080993652,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.7029,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 56044717867008.0,
+  "total_flos": 120711700021248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null