Training in progress, step 10500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:639ee4bb484430e204363b1a78e8e3cf87f5f567e16229346078485dd8bc3cf0
+oid sha256:07cd80e643eb2a26b379e7fa735978101f48a40e12d6f3481f32426f56decfd3
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99dde3bc6c17836e2e3623e355815f299b3119069f4d63c4548b98a0d7196fc9
+oid sha256:815b4aad044494428efe65ad0dd7d96090c7bb0cdd3e7891ab0bd30980a00de0
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7996bf5655e4a5cbb77441053d27d8076a7bd5f56c8733053492e0359c85a534
+oid sha256:92bc953fd68dd79c772e0c4700bc289fc99028c313b2f470c74ebf85287cb40e
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ba471d3f3022e6990d83a6a0b061ac06ef17901c4a27c65c2e3ff11f73da916
+oid sha256:51c6e60b9620f85b02af88312b38e0a19eeb53d066787459ff7296998b69c686
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.796750507733165,
+  "epoch": 20.996719262615215,
   "eval_steps": 500,
-  "global_step": 10400,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -895,6 +895,21 @@
       "learning_rate": 3.066666666666667e-05,
       "loss": 1.2268,
       "step": 10400
+    },
+    {
+      "epoch": 20.996719262615215,
+      "grad_norm": 0.23103660345077515,
+      "learning_rate": 3e-05,
+      "loss": 1.2219,
+      "step": 10500
+    },
+    {
+      "epoch": 20.996719262615215,
+      "eval_loss": 1.1070313453674316,
+      "eval_runtime": 781.5944,
+      "eval_samples_per_second": 19.859,
+      "eval_steps_per_second": 2.483,
+      "step": 10500
     }
   ],
   "logging_steps": 100,
@@ -914,7 +929,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.623161386616383e+19,
+  "total_flos": 1.6387688837351997e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null