Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b2c055b3868f78d2fc5134cdb3b1f749974784e02ad48dce37c75ef231cdc7a
+oid sha256:ca2785e13113657a6906f7fc9a42046ec636d2563a10a45d34d47cbd100acc55
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43efa1a55fde744f4e4aa986ebd3fec23717f74003ca2f2dc88403fae1561be7
+oid sha256:a5d8e2f5f874bc93285a77467b6e0c0c9d159c8a53ffc35d9f9ef84687257860
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fa1bb1091058b70e986852c5817815bf8a4d14bf29aaa636318d9694ad55b4a
+oid sha256:a044e2f0b5fb1ba852ac439784b115a1aa51af3e83f69b17eb10c3bbc2cb4acc
 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": 0.0007972892166633447,
+  "epoch": 0.0015945784333266893,
   "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": 25.345,
       "eval_steps_per_second": 12.673,
       "step": 10
+    },
+    {
+      "epoch": 0.0009199490961500131,
+      "grad_norm": 0.5417680740356445,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.0991,
+      "step": 15
+    },
+    {
+      "epoch": 0.001226598794866684,
+      "grad_norm": 0.5770021080970764,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.999,
+      "step": 20
+    },
+    {
+      "epoch": 0.001226598794866684,
+      "eval_loss": 2.0414137840270996,
+      "eval_runtime": 271.3537,
+      "eval_samples_per_second": 25.303,
+      "eval_steps_per_second": 12.651,
+      "step": 20
+    },
+    {
+      "epoch": 0.001533248493583355,
+      "grad_norm": 0.49637794494628906,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.0475,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 486447387770880.0,
+  "total_flos": 1005324601393152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null