Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b3555ecff9c8ea06a1aaccc85643e840a4eb59dd7c884410604e6a21f3e6da
+oid sha256:970c575131aaf3426a54b4f1276ad61074280706e8a43817f1f3d7cedbca9162
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b72348e1b7358cbe599ecb129d77d662e9a4d39fbe4c33c0376889d91858b951
+oid sha256:118177ccb01ebcb8aa4af7ecafd37240df66b8f6fa062b541c8c9536d32868b3
 size 27002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deabd56c17b610f6d8e6c3c09d2dcb705e4d72db3bc1813e41a578dadc2811d7
+oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
 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": 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": 46.0,
       "step": 9
+    },
+    {
+      "epoch": 0.001347406242982259,
+      "grad_norm": 1.5385758160846308e-05,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 46.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0016842578037278239,
+      "grad_norm": 9.523390872345772e-06,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 46.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.001796541657309679,
+      "eval_loss": 11.5,
+      "eval_runtime": 37.1694,
+      "eval_samples_per_second": 100.889,
+      "eval_steps_per_second": 50.445,
+      "step": 16
+    },
+    {
+      "epoch": 0.0020211093644733886,
+      "grad_norm": 1.3232111996330786e-05,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 46.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 408934907904.0,
+  "total_flos": 807895793664.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null