Training in progress, step 13500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1386e828b3ba479196522024102112e210e952e5254c67fc939f220aff955ac6
+oid sha256:c88c5416d2b227c786b1439286f5e08b376fbaf2336d3ad3f7c0ba996ebb7dca
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ff9ebb9fca0c17ff991f1cef7618725b58455f772919586e80516856dad8806
+oid sha256:f3a28047c481623f0d721dd50781596e0c29b9b96dfc6a7b76cff9611c73f853
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dd8409f64af20a99c74e394e705eb79e774a42d36c1eb3e8c1583d929923352
+oid sha256:1b3c81bb041799a90cf1c3d50b843bc32c890dd7bc841895016d103e980913f6
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eee4f684a730e891fd1e26e72f5546f480a0c3d9d36c0f17b64dcdf05ef17e02
+oid sha256:f731b7a6aefc3f610a3a165904d543d20dce898827aabc1534d10593582b96eb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 26.795813154194658,
+  "epoch": 26.995781909076708,
   "eval_steps": 500,
-  "global_step": 13400,
+  "global_step": 13500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1153,6 +1153,21 @@
       "learning_rate": 1.0666666666666667e-05,
       "loss": 1.2186,
       "step": 13400
+    },
+    {
+      "epoch": 26.995781909076708,
+      "grad_norm": 0.24657221138477325,
+      "learning_rate": 1e-05,
+      "loss": 1.2211,
+      "step": 13500
+    },
+    {
+      "epoch": 26.995781909076708,
+      "eval_loss": 1.0853413343429565,
+      "eval_runtime": 779.9076,
+      "eval_samples_per_second": 19.902,
+      "eval_steps_per_second": 2.489,
+      "step": 13500
     }
   ],
   "logging_steps": 100,
@@ -1172,7 +1187,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.091380806058718e+19,
+  "total_flos": 2.1069883031775347e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null