Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de08a61e0bb279e10ef5c2b8fddf2cc8de726c2c357aa27e6ba20e40c07762e
+oid sha256:f73bbc7bddee874a3b0c8d6a530b608534681c1b6ac8b86b32e378c03f96bbb1
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1e639258da4aad6bb3e0891702d8f236460a4ad9306d75e018488723172faf5
+oid sha256:ac01e0d5038b0a32bcbb40cb195cf2a9051337e0c5126729eb1dfa2d218dbfa1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
+oid sha256:72d2123828a202521fed49695ce20694823d9999d33262dd05d88a1ab8cbe183
 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": 0.0031854937515314874,
+  "epoch": 0.006370987503062975,
   "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": 8.428,
       "eval_steps_per_second": 4.216,
       "step": 10
+    },
+    {
+      "epoch": 0.0036755697133055622,
+      "grad_norm": 8.70495891571045,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 4.2031,
+      "step": 15
+    },
+    {
+      "epoch": 0.00490075961774075,
+      "grad_norm": 7.727749347686768,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 4.1983,
+      "step": 20
+    },
+    {
+      "epoch": 0.00490075961774075,
+      "eval_loss": 0.9561256170272827,
+      "eval_runtime": 203.4151,
+      "eval_samples_per_second": 8.451,
+      "eval_steps_per_second": 4.228,
+      "step": 20
+    },
+    {
+      "epoch": 0.006125949522175937,
+      "grad_norm": 6.156836032867432,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 4.2422,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4556946677956608.0,
+  "total_flos": 9113893355913216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null