Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5b02db0d61c0cef8a548cd425fd2e049fb7fc24afac453dc5f53b9903df48e
+oid sha256:8452d6b1f54a2e596227ff4d91984bcde9a948e6cd4e23a013deba6b4d21727c
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea93e352d89157e242c86d6e59074a13f961c2c934e8b43508f69f44f86b4ef
+oid sha256:64dc357a9279c3c99fe85f376e25306c45765bc26ca1d543f217ce3e0a8af745
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5644a0717f1231448981eced6544705649d1cd238d725b15969f77f29be3b8e
+oid sha256:ab1d35b7b08d2869ce54f82448af01693fcbfcf11fc2ad8a25dbf70409dac1df
 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": 0.0005236445661806171,
+  "epoch": 0.0010472891323612342,
   "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": 12.514,
       "eval_steps_per_second": 6.257,
       "step": 10
+    },
+    {
+      "epoch": 0.0006042052686699428,
+      "grad_norm": 2.973989486694336,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.6552,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008056070248932571,
+      "grad_norm": 2.6805059909820557,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.3329,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008056070248932571,
+      "eval_loss": 0.26544415950775146,
+      "eval_runtime": 839.614,
+      "eval_samples_per_second": 12.451,
+      "eval_steps_per_second": 6.225,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010070087811165714,
+      "grad_norm": 2.0367231369018555,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.2225,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2484418841149440.0,
+  "total_flos": 4968837682298880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null