Training in progress, step 670, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e343f4be4726d57248da858151d45c31e805e6b3ad9a7fa71b73b1ea4e9be755
+oid sha256:d11919fe0e8a9648a9b5db94c6f3e9fcdb9c592fdea38d70721fb286fcb116c2
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c60fe7edf4324671acf40ae4d255f5fe04b5b2c203c38809ec1ad9b677ed7e1
+oid sha256:2c098762757aa88e1c5dc4dbdc5bd880723b3582ad7ba17785cb2aec02b3a4b8
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327f54effce4451308283c7d25159d8624b283452013dadc78bd8e3f4eaf23f4
+oid sha256:170d785b83ded353a40ba28ad00de9b9aa2caa600db9bdae60b5d37ee5038868
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:765a8680709d1ce853e9b5ed23f0d0a5b9c07dc800a1d0d7e4ffdc056361e829
+oid sha256:2503cc414df67b86ca96d13fc6fc59b704cd63e683a117cd76a76f268b444087
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8605629246198642,
+  "epoch": 0.8670333225493367,
   "eval_steps": 386,
-  "global_step": 665,
+  "global_step": 670,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4678,6 +4678,41 @@
       "learning_rate": 9.370764596463763e-05,
       "loss": 0.7185,
       "step": 665
+    },
+    {
+      "epoch": 0.8618570042057586,
+      "grad_norm": 0.8211125135421753,
+      "learning_rate": 9.368760857680974e-05,
+      "loss": 0.9613,
+      "step": 666
+    },
+    {
+      "epoch": 0.8631510837916532,
+      "grad_norm": 0.9151694178581238,
+      "learning_rate": 9.366754148545338e-05,
+      "loss": 0.9788,
+      "step": 667
+    },
+    {
+      "epoch": 0.8644451633775477,
+      "grad_norm": 0.84197998046875,
+      "learning_rate": 9.364744470421234e-05,
+      "loss": 0.9891,
+      "step": 668
+    },
+    {
+      "epoch": 0.8657392429634423,
+      "grad_norm": 0.6799368858337402,
+      "learning_rate": 9.362731824675056e-05,
+      "loss": 0.7988,
+      "step": 669
+    },
+    {
+      "epoch": 0.8670333225493367,
+      "grad_norm": 0.722326934337616,
+      "learning_rate": 9.360716212675214e-05,
+      "loss": 0.8399,
+      "step": 670
     }
   ],
   "logging_steps": 1,
@@ -4697,7 +4732,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.434282191762227e+17,
+  "total_flos": 7.490179050346906e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null