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:d7cbb08df4805011c8a5f7d27a8fec066b371439095f7fd83c152011419e4d39
+oid sha256:15db0872f69d05448bac9440236e8908b15c5f18ae19cfb4d1302cb8252e30fa
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8fe64515736952da0a50b0a801eb5541231334860dfbbb1a4e75b2e76f712d5
+oid sha256:525cabc77d780dbd9dcffdb00f7cf0350c1f2a2d67f7caaaa70492d12cf52dec
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36cfe1be5c7989270a7ce0df3c215f47905de3f6ac294a27fed514d5adcc156f
+oid sha256:9418ccf2616e54c512b8a757183aa6a5e1720a368b0eebadef1de847e8165928
 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": 0.00042096741550293464,
+  "epoch": 0.0008419348310058693,
   "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": 11.905,
       "eval_steps_per_second": 5.953,
       "step": 10
+    },
+    {
+      "epoch": 0.0004857316332726169,
+      "grad_norm": 1.3999601602554321,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.8078,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006476421776968225,
+      "grad_norm": 1.3233897686004639,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.6382,
+      "step": 20
+    },
+    {
+      "epoch": 0.0006476421776968225,
+      "eval_loss": 0.43094074726104736,
+      "eval_runtime": 1089.4458,
+      "eval_samples_per_second": 11.935,
+      "eval_steps_per_second": 5.968,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008095527221210282,
+      "grad_norm": 2.1263442039489746,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.4102,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3005541903237120.0,
+  "total_flos": 6380996656103424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null