Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58dad5cb07e01c6c53bbe30571977b8f2b932829110c7c841c71d4915da5621f
+oid sha256:85f288290eda029a51b466d51bc35dc7f87d8eb54bef08248e2ed860369c9045
 size 604317736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6fe9a18d1cfa740ef9e45774168947a4a74f5d14849d04e9f0040152a46ce50
+oid sha256:6de590c23897e5dfd17b39f4b9d969d5a84d028864c71ecb00a40751ff70df57
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
+oid sha256:376a84af6354b555ba2fbd8c3fc92d9086d0a9dcf2c9793e8d456dbd561d4eb5
 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": 0.00016812373907195696,
+  "epoch": 0.0003362474781439139,
   "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": 13.202,
       "eval_steps_per_second": 6.601,
       "step": 10
+    },
+    {
+      "epoch": 0.00019398892969841187,
+      "grad_norm": 0.8784182667732239,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.3641,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002586519062645492,
+      "grad_norm": 1.0158741474151611,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.1668,
+      "step": 20
+    },
+    {
+      "epoch": 0.0002586519062645492,
+      "eval_loss": 0.0934409499168396,
+      "eval_runtime": 2461.0672,
+      "eval_samples_per_second": 13.229,
+      "eval_steps_per_second": 6.615,
+      "step": 20
+    },
+    {
+      "epoch": 0.0003233148828306865,
+      "grad_norm": 0.8833733201026917,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1013,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2117354385309696.0,
+  "total_flos": 4234708770619392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null