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:f9ff116b397d2a10de26f23ad83cc3af14240c72615a46de8ef849db672f483a
+oid sha256:320bf161d988e79d6b5f7c84009886da8a34b32cbc89a9547e1d6ad55711729b
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877bf79bbf284ec9bd28dcb47bf48f9211dc504cda0977d8f3b1a834259d03f8
+oid sha256:0180866a4d3b86d772630b13d0b24fb64dcf2cd90e41163c3914054e38c043f5
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:791f73fa3760812f8fadbd82cf601a765780f31c35ee4a72ec4dd84d9bdcc5fb
+oid sha256:63baab6196b05b5b3ec16e085c1201e0102b31625ee3592d359ed2201809bbce
 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": 0.0008429393294417634,
+  "epoch": 0.0016858786588835268,
   "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": 2.2119,
       "step": 9
+    },
+    {
+      "epoch": 0.0010115271953301161,
+      "grad_norm": 0.8066004514694214,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.1951,
+      "step": 12
+    },
+    {
+      "epoch": 0.001264408994162645,
+      "grad_norm": 0.9734544157981873,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.997,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013487029271068215,
+      "eval_loss": 1.712154507637024,
+      "eval_runtime": 261.3622,
+      "eval_samples_per_second": 19.111,
+      "eval_steps_per_second": 9.558,
+      "step": 16
+    },
+    {
+      "epoch": 0.0015172907929951742,
+      "grad_norm": 0.838837742805481,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.6336,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3495193466634240.0,
+  "total_flos": 6990386933268480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null