Training in progress, step 980, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038267a91f170d9b5ae66224af2b87b22c88cd39030167a095e392bbf0939dc3
+oid sha256:9945e31b638334bf494fdbd6bddbd7efb17b80e2cb934406af8bd6e740a52c13
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7f82605fb4964fc0344bf084e7470a1cef7b3f76a782ad0352d61e5b9c8d5c
+oid sha256:2faad1ff615b4367ac8f493089d35aa61ad18cd058aa6a59301eee8776decdbe
 size 25152884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea7f848100ec9ed67f36e42acef219aee83f4cac91b33ccdcc953523a30b2eb
+oid sha256:9a563e473225d388aa85a62aecbc6bdee80f72d3795da30b7a19c51113a1af02
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676a6dd10fea20cc8c1640d4f6403558dc1b1991491c12b47845478e41a66276
+oid sha256:0cdd00c1b48b23a3fb0db3f88bb5f4c0c6d9b16cd39a52129b3151d7da108592
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7049891540130152,
+  "epoch": 0.7086044830079538,
   "eval_steps": 692,
-  "global_step": 975,
+  "global_step": 980,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6848,6 +6848,41 @@
       "learning_rate": 1.9197476297098868e-05,
       "loss": 1.2061,
       "step": 975
+    },
+    {
+      "epoch": 0.7057122198120029,
+      "grad_norm": 0.49111953377723694,
+      "learning_rate": 1.9195665918116068e-05,
+      "loss": 1.0294,
+      "step": 976
+    },
+    {
+      "epoch": 0.7064352856109906,
+      "grad_norm": 0.4833580255508423,
+      "learning_rate": 1.919385358501339e-05,
+      "loss": 1.0781,
+      "step": 977
+    },
+    {
+      "epoch": 0.7071583514099783,
+      "grad_norm": 0.42100799083709717,
+      "learning_rate": 1.9192039298175965e-05,
+      "loss": 1.03,
+      "step": 978
+    },
+    {
+      "epoch": 0.707881417208966,
+      "grad_norm": 0.5994098782539368,
+      "learning_rate": 1.9190223057989337e-05,
+      "loss": 0.8802,
+      "step": 979
+    },
+    {
+      "epoch": 0.7086044830079538,
+      "grad_norm": 0.4303410053253174,
+      "learning_rate": 1.9188404864839465e-05,
+      "loss": 1.1212,
+      "step": 980
     }
   ],
   "logging_steps": 1,
@@ -6867,7 +6902,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.170655902531584e+18,
+  "total_flos": 2.1817874712625152e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null