Training in progress, step 9000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0278328958930d3beaacbe8bed27397e998fbcabe1fca7fa0eae8eafd80ecf51
+oid sha256:0fa462ee315f6286d0560d178e1576f9f7bc266cda332e3573e24a9be44be436
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e59834f34401a93fcb0300abb81ffe29f6ae8d1c35b22ab4a0642dde9c40b2e
+oid sha256:bc3a6d3b8afe0402070b9a53be5a23ab45e598fb6abf993ecb0f8d70a9dec5b9
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a81dafce04c7537f75efee5aacdd30a9f6039bc0738e6674b85fdce84b597c
+oid sha256:c66a678ee8f615fe14ce6e44cecc141a68321a0815a7952fb61c3673d46702bf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.6549835706462215,
+  "epoch": 4.928806133625411,
   "eval_steps": 500,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -602,6 +602,41 @@
       "learning_rate": 1.4434228048932796e-06,
       "loss": 0.1657,
       "step": 8500
+    },
+    {
+      "epoch": 4.709748083242059,
+      "grad_norm": 1.020652174949646,
+      "learning_rate": 1.023006467000115e-06,
+      "loss": 0.1708,
+      "step": 8600
+    },
+    {
+      "epoch": 4.764512595837897,
+      "grad_norm": 1.2859959602355957,
+      "learning_rate": 6.741735403739901e-07,
+      "loss": 0.1712,
+      "step": 8700
+    },
+    {
+      "epoch": 4.8192771084337345,
+      "grad_norm": 0.8666063547134399,
+      "learning_rate": 3.974338695163393e-07,
+      "loss": 0.1657,
+      "step": 8800
+    },
+    {
+      "epoch": 4.874041621029573,
+      "grad_norm": 0.6807364821434021,
+      "learning_rate": 1.9319192943152986e-07,
+      "loss": 0.1675,
+      "step": 8900
+    },
+    {
+      "epoch": 4.928806133625411,
+      "grad_norm": 1.1967036724090576,
+      "learning_rate": 6.174623445742155e-08,
+      "loss": 0.1721,
+      "step": 9000
     }
   ],
   "logging_steps": 100,
@@ -621,7 +656,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.086908592883286e+18,
+  "total_flos": 4.325169651624493e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null