Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c32c3a542059907fa0ace27b50d78a26c15ffbb1a4a2afe908bf732b12a229f
+oid sha256:539f5b24a0383e891eee68846fd16a340037a81942670d211cce332a5f50d58e
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf6c5846b50364e6c2a936537c256e26403bb0eeba0870a5691c0599a068db5d
+oid sha256:a30eeb27c16b4e8abbff65be0fb0f72178b1636bd3b8be437bdfc0e907c3fd99
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6473b014bdc320950dfa5ea285c9ac39b533139eb5d6d4f5d176c560d5dfd812
+oid sha256:e3792359ce259c97b79ba2cc86cec68868e3a782d6f4b8b840af98211ae50b86
 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": 0.01806182702327197,
+  "epoch": 0.03612365404654394,
   "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": 8.956,
       "eval_steps_per_second": 4.493,
       "step": 10
+    },
+    {
+      "epoch": 0.02084056964223689,
+      "grad_norm": 1.5081523656845093,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.2467,
+      "step": 15
+    },
+    {
+      "epoch": 0.027787426189649182,
+      "grad_norm": 1.763542652130127,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.5649,
+      "step": 20
+    },
+    {
+      "epoch": 0.027787426189649182,
+      "eval_loss": 1.5423730611801147,
+      "eval_runtime": 33.9487,
+      "eval_samples_per_second": 8.925,
+      "eval_steps_per_second": 4.477,
+      "step": 20
+    },
+    {
+      "epoch": 0.03473428273706148,
+      "grad_norm": 2.000399351119995,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.2685,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2265426859917312.0,
+  "total_flos": 4530853719834624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null