Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2fcefa755cdf6c258c8be9caeb90a7de8a992852a479b751dbb013aee0af9da
+oid sha256:62ce243e116b25d46f8c0fa58df12baf1e6fe957ae0ffa58654697e169c0c6fc
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93b6a63a837e92352e9dd89b84071ba3c81053771d8095a66ed409eb1845bf3
+oid sha256:f3d2197aeace4bbf0d8f7601669c9610adb99b3d43cefc55affbece58ead5e13
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36b609498013e35b0e627973b03326d5a6f6e3d72ead1fa76b69680604129203
+oid sha256:501bbc95a07fee90fa37abc1c02060dd46fa0ea348b19f80d5547d4a0bb8d1d0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0069836153639538006,
+  "epoch": 0.013967230727907601,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 9.806,
       "eval_steps_per_second": 4.903,
       "step": 10
+    },
+    {
+      "epoch": 0.008058017727639,
+      "grad_norm": 0.5022017955780029,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.6189,
+      "step": 15
+    },
+    {
+      "epoch": 0.010744023636852002,
+      "grad_norm": 0.42121511697769165,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.4692,
+      "step": 20
+    },
+    {
+      "epoch": 0.010744023636852002,
+      "eval_loss": 0.12234125286340714,
+      "eval_runtime": 80.4411,
+      "eval_samples_per_second": 9.746,
+      "eval_steps_per_second": 4.873,
+      "step": 20
+    },
+    {
+      "epoch": 0.013430029546065002,
+      "grad_norm": 0.5769535303115845,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.493,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2317832278769664.0,
+  "total_flos": 4543869219766272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null