Training in progress, step 7500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75be62931ca89f23de7c2c6c483ee19c4f2ef138d655a65379af228b82b161dc
+oid sha256:2dfa7eedefa6f5bfe03f59c8f949e723d7bdcf83b553888d4c59092a2cdb10b9
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dba0480e4ca5555afa0bf7b62139d4c19532c4b78abe6342a2c4d08071b8212
+oid sha256:5b67768fefe2c95550edbc611258bede3930b0f438d18febf8b4ca398b7a3528
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aa5b9d71d5524022fdb89355036b4bd30d92891556b751a47429b9fe2b2efba
+oid sha256:c75aa01f1e1c41eccc30305e40d05a98f2422532589f1f5ef2892931c6e89472
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381e8c3b4c5347a5e5a8c54712ad5f2c5ede6fb03b4178c4cda7398bba55a45a
+oid sha256:768622017f9fb87b5a475ae3a6768a892c3a9c5fc81f560bd18201c983e882a1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.797687861271676,
+  "epoch": 14.997656616153726,
   "eval_steps": 500,
-  "global_step": 7400,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -637,6 +637,21 @@
       "learning_rate": 5.0666666666666674e-05,
       "loss": 1.2382,
       "step": 7400
+    },
+    {
+      "epoch": 14.997656616153726,
+      "grad_norm": 0.21565145254135132,
+      "learning_rate": 5e-05,
+      "loss": 1.2337,
+      "step": 7500
+    },
+    {
+      "epoch": 14.997656616153726,
+      "eval_loss": 1.102397084236145,
+      "eval_runtime": 781.6511,
+      "eval_samples_per_second": 19.858,
+      "eval_steps_per_second": 2.483,
+      "step": 7500
     }
   ],
   "logging_steps": 100,
@@ -656,7 +671,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1549419671740482e+19,
+  "total_flos": 1.1705494642928648e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null