Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4092ac75f39d8a42b098a8f110a70bd20b6f09d0a271df53388cd9cc0fac749b
+oid sha256:0395c927b6ed7905e8e8b1827654723648a801bcb23f89b0f1b2ca94d0ec5a0a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0be302ee8c6ec9ae578f611c0ad72d6088a95e5691e4e64735a6b93fa112473
+oid sha256:fa9c8d64f6f6bf81ce5a60100595b429ac329eb3a8032bfc2d56f20513220841
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
+oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
 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": 0.006150206978119456,
+  "epoch": 0.012300413956238912,
   "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": 14.7,
       "eval_steps_per_second": 7.35,
       "step": 10
+    },
+    {
+      "epoch": 0.007096392667060911,
+      "grad_norm": 3.918861150741577,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.9987,
+      "step": 15
+    },
+    {
+      "epoch": 0.009461856889414548,
+      "grad_norm": 3.6118011474609375,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.8883,
+      "step": 20
+    },
+    {
+      "epoch": 0.009461856889414548,
+      "eval_loss": 1.7703381776809692,
+      "eval_runtime": 60.7528,
+      "eval_samples_per_second": 14.65,
+      "eval_steps_per_second": 7.325,
+      "step": 20
+    },
+    {
+      "epoch": 0.011827321111768185,
+      "grad_norm": 2.6210219860076904,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.6853,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2404433522589696.0,
+  "total_flos": 4808867045179392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null