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:ffeb70d7f2608cd85008e42c493f53193a25e8eac25292c7eee812905b2b3df0
+oid sha256:173fb8eae8c1e9bfe1dc9b7068f694a647f2e0de25991b26ac0b1df16e7b6f88
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b396e173c850f488dbb17f00adbff27055163a7e01fcda957571c4ed37f5233e
+oid sha256:c4d909f6279be80abd5ef8e0280a6ac2cc95bd58ce63360432bda532ca5803e3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b8d3b0cd38ff8c140a46f8cd6b0fb2611ad2c4ebd59d9733c17b98b72f21091
+oid sha256:66d743f7d7f1e483fc21966690f23e79e8c531a6f00323f193d4a604fb0e9d14
 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": 0.018738738738738738,
+  "epoch": 0.037477477477477476,
   "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": 12.454,
       "eval_steps_per_second": 6.248,
       "step": 10
+    },
+    {
+      "epoch": 0.021621621621621623,
+      "grad_norm": 16.050689697265625,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 6.2438,
+      "step": 15
+    },
+    {
+      "epoch": 0.02882882882882883,
+      "grad_norm": 9.789994239807129,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 5.7815,
+      "step": 20
+    },
+    {
+      "epoch": 0.02882882882882883,
+      "eval_loss": 1.4146848917007446,
+      "eval_runtime": 24.267,
+      "eval_samples_per_second": 12.074,
+      "eval_steps_per_second": 6.058,
+      "step": 20
+    },
+    {
+      "epoch": 0.036036036036036036,
+      "grad_norm": 6.070463180541992,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 6.7176,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2322287466381312.0,
+  "total_flos": 4644574932762624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null