Training in progress, step 13000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c0f46b0150dcb405d02f4108cf24c0448fc13678cf067a27f224d48daab308b
+oid sha256:896101a9f207b1b5ed452ee8f81b628ea0fbd1dc25069f79b8fffb726b415945
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7b83437c4e865419b73b6244f99977bffdc6e901b91e047baf7b00421c047
+oid sha256:05a0ba1e8c082e801747fd48267334d3d0e5678023038dd779a5e1492afc5102
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359692d26849aeab1c31342164862fa93d2d0d531719b4bd1ddb343cbd8a6087
+oid sha256:881a61b7c1a37ee10da1cd65cc2b785743680e7cf44d03b890e6cd41ce1e5827
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f06a8367c7a4e48436e0ecbe054a4fd11986bfb73d4af57a7bc74afdb308e0c
+oid sha256:4907c0326fbf452e032c18f11cb6410c8efc73c7825b23977ef74e9fa6cbf715
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 25.79596937978441,
+  "epoch": 25.99593813466646,
   "eval_steps": 500,
-  "global_step": 12900,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1110,6 +1110,21 @@
       "learning_rate": 1.4000000000000001e-05,
       "loss": 1.2223,
       "step": 12900
+    },
+    {
+      "epoch": 25.99593813466646,
+      "grad_norm": 0.25148263573646545,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.2142,
+      "step": 13000
+    },
+    {
+      "epoch": 25.99593813466646,
+      "eval_loss": 1.0822358131408691,
+      "eval_runtime": 781.57,
+      "eval_samples_per_second": 19.86,
+      "eval_steps_per_second": 2.483,
+      "step": 13000
     }
   ],
   "logging_steps": 100,
@@ -1129,7 +1144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.013344236151662e+19,
+  "total_flos": 2.028951733270479e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null