Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c55d79d12415cffd5fc6fcddc40859fe130a672572ebd6399b6f91a33293c40
+oid sha256:adb3c156fc252694aec80509418baa36b78944d63295e7fdb79b390073055b10
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db3f86d0e6ded42868b4ba9c266299934effdc0022552c554cc46d3e5d2f07f
+oid sha256:660decfe805cc7ea33c57cbaa16f176dda37928ec05e18d1a561831865bc82f8
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec9c6466e859e16fa3f2753af8c99e0bd2a42d5b320babbbc1a8b0065a0165e
+oid sha256:3d663cf82722c84e3314cb4000fba516db1f2170d5b76497c7310571e43f5b82
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3862c079d7ff9da4fcab8a0acb5ce55f7428eed3a5daed101a622474bf70cde
+oid sha256:7a5c429039c67e17dc7a7bd38f4cb517c33028d543d23edda39c1a6193e218c8
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.030274361400189215,
+  "epoch": 0.04541154210028382,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 40.523,
       "eval_steps_per_second": 10.14,
       "step": 10
+    },
+    {
+      "epoch": 0.033301797540208136,
+      "grad_norm": 4.311172962188721,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 6.464,
+      "step": 11
+    },
+    {
+      "epoch": 0.03632923368022706,
+      "grad_norm": 4.248252868652344,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 6.1797,
+      "step": 12
+    },
+    {
+      "epoch": 0.03935666982024598,
+      "grad_norm": 4.477457046508789,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 6.0317,
+      "step": 13
+    },
+    {
+      "epoch": 0.0423841059602649,
+      "grad_norm": 3.6723344326019287,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.8527,
+      "step": 14
+    },
+    {
+      "epoch": 0.04541154210028382,
+      "grad_norm": 3.421534538269043,
+      "learning_rate": 5e-05,
+      "loss": 5.7074,
+      "step": 15
+    },
+    {
+      "epoch": 0.04541154210028382,
+      "eval_loss": 5.635517597198486,
+      "eval_runtime": 54.9282,
+      "eval_samples_per_second": 40.526,
+      "eval_steps_per_second": 10.141,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.293980070510592e+16,
+  "total_flos": 4.940970105765888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null