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:f05ddf833d483aa8d1f7ed2aa5c36d35bb9153dd0a72f485fd8866d7b0ccfaae
+oid sha256:7bbea78e1ad7b03886c63d0303a73cc62ff2144543fc87afb5f154fa2a28b89b
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0da03a42c1e6d62f9b50ba0d50bae633ce8733d5ab501e27c5b0e239aa87cd8a
+oid sha256:5d97a2223a4798de92b7ff7835008e4d945f4ef00e4116adfc1384a3c094c368
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e7f37d1795b3a5f2badef6331eeaa3b12ee884a2d3e04816a3d1b46104eacde
+oid sha256:acd0be13f0ec7941600ed6c6a8548ae99c85efa3317ee073f3d6c665dedd1743
 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": 0.005560307955517536,
+  "epoch": 0.011120615911035072,
   "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": 51.432,
       "eval_steps_per_second": 25.742,
       "step": 10
+    },
+    {
+      "epoch": 0.00641573994867408,
+      "grad_norm": 1.0661193132400513,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.6493,
+      "step": 15
+    },
+    {
+      "epoch": 0.00855431993156544,
+      "grad_norm": 1.1885366439819336,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.6315,
+      "step": 20
+    },
+    {
+      "epoch": 0.00855431993156544,
+      "eval_loss": 0.6547719240188599,
+      "eval_runtime": 18.8181,
+      "eval_samples_per_second": 52.343,
+      "eval_steps_per_second": 26.198,
+      "step": 20
+    },
+    {
+      "epoch": 0.0106928999144568,
+      "grad_norm": 1.0234185457229614,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.4865,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 66870668427264.0,
+  "total_flos": 131169388068864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null