Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f76734e28204792f1c9602dbde1f5c026064dd1a28454ce0e382330d42314704
+oid sha256:2b4822b9a19aee5a39c0dcbc08bb176b72a83cec780abbf272e776eaa6022c93
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3c21d4cb5319aa1931d819302b04d98e988babb95416bbaade61cf9818a914
+oid sha256:07832f28e2d3f2373b60161c9e4cc381d98b62dfac0ed141cfd01c53cc6f8e72
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b538b38de5a7e672b21469b3c4da1961004ba3e774fabb355fed626d305c65f0
+oid sha256:e4f7e4e982ec83a1015159c938b87396c0df1314fe4ddc2c5e702c93bc19f0a8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c2b58d0bfac7076f5bfb2b6f6c91fe0cdc02aea0282c1fa48c426ea9abd87a
+oid sha256:a2cff0b4502474cdd0a91240049128f5413f57405f9fc521aea9e960a2e0e635
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00354251012145749,
+  "epoch": 0.004048582995951417,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -113,6 +113,21 @@
       "eval_samples_per_second": 25.881,
       "eval_steps_per_second": 12.941,
       "step": 63
+    },
+    {
+      "epoch": 0.003936122357174989,
+      "grad_norm": 3.9699506759643555,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.9889,
+      "step": 70
+    },
+    {
+      "epoch": 0.004048582995951417,
+      "eval_loss": 0.7541989088058472,
+      "eval_runtime": 288.1317,
+      "eval_samples_per_second": 25.988,
+      "eval_steps_per_second": 12.994,
+      "step": 72
     }
   ],
   "logging_steps": 10,
@@ -132,7 +147,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1909255883915264e+16,
+  "total_flos": 1.3754970817953792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null