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:b667193eb06ecf02cbec4c1e2a89332e504d4c339718cfa49f5fbbf319176f81
+oid sha256:1584e16f6facd0ee237558d832b99084d9d1819d1a5a036a241a3b3aea8058f1
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c3d44f5d8f670fb0badc0df49da5685a5a404dcc305f4f954b4a1c160955bdb
+oid sha256:5fc7164c63da7a9e3f5b18d835bd08334e476794c195f4e85085139200b0b8ec
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59902bd2d88bd5b3b6ed8261d058dd21d71ce72ae295268abdf3505cbf05e79e
+oid sha256:6c4827f460e448bf65ab378ff86f0199133312cd6c98710676d0d2657d6e36c4
 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": 0.0010695187165775401,
+  "epoch": 0.0021390374331550803,
   "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": 35.786,
       "eval_steps_per_second": 17.893,
       "step": 10
+    },
+    {
+      "epoch": 0.0012340600575894694,
+      "grad_norm": 1.7913024425506592,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.8931,
+      "step": 15
+    },
+    {
+      "epoch": 0.0016454134101192926,
+      "grad_norm": 1.6517016887664795,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.9024,
+      "step": 20
+    },
+    {
+      "epoch": 0.0016454134101192926,
+      "eval_loss": 2.953030586242676,
+      "eval_runtime": 142.344,
+      "eval_samples_per_second": 35.955,
+      "eval_steps_per_second": 17.978,
+      "step": 20
+    },
+    {
+      "epoch": 0.0020567667626491155,
+      "grad_norm": 2.0664424896240234,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.9243,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 372845548929024.0,
+  "total_flos": 709609270542336.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null