Training in progress, step 865, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a162de6ee5808bd4ad5cb8be36eae8b1b8c4922c72491be7020586b2e5fb64
+oid sha256:271a55b308cc7682a873c6a99c9cda26d6ab71e97899f74b1d4a08129d2aa236
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e63dac42370b0518395427db21f0392c41779656f22f6a6a8138d5fa706a9811
+oid sha256:f645a4cca6acce995a28c6a73628ab6507e4d274200076d1a497788422b8df35
 size 23159546

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf5725e9d75d811149550611171285ddd16d6dd949a97048d859b084a5467d5
+oid sha256:898bf75a87a6acd77c2a3359f2976e804365bed481ed60f6d31384f9b04f1767
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754eb9da41da10c03a73e6a05375aeb38c8cd2df8977d237eae9686a3845ef42
+oid sha256:5cef1807e34750e90e3b15895beee76987ca821b1c92ed984e880432329fc5d1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.43298969072165,
+  "epoch": 4.458762886597938,
   "eval_steps": 97,
-  "global_step": 860,
+  "global_step": 865,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6099,6 +6099,41 @@
       "learning_rate": 3.486077833108342e-06,
       "loss": 0.0003,
       "step": 860
+    },
+    {
+      "epoch": 4.438144329896907,
+      "grad_norm": 0.003292699111625552,
+      "learning_rate": 3.4237129228434415e-06,
+      "loss": 0.0001,
+      "step": 861
+    },
+    {
+      "epoch": 4.443298969072165,
+      "grad_norm": 0.13467860221862793,
+      "learning_rate": 3.3618911234968243e-06,
+      "loss": 0.0012,
+      "step": 862
+    },
+    {
+      "epoch": 4.448453608247423,
+      "grad_norm": 0.006807579658925533,
+      "learning_rate": 3.300613155952359e-06,
+      "loss": 0.0001,
+      "step": 863
+    },
+    {
+      "epoch": 4.453608247422681,
+      "grad_norm": 0.04459763318300247,
+      "learning_rate": 3.2398797347524656e-06,
+      "loss": 0.0004,
+      "step": 864
+    },
+    {
+      "epoch": 4.458762886597938,
+      "grad_norm": 0.005752299912273884,
+      "learning_rate": 3.1796915680897988e-06,
+      "loss": 0.0002,
+      "step": 865
     }
   ],
   "logging_steps": 1,
@@ -6118,7 +6153,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.326062471592018e+17,
+  "total_flos": 3.345416922983301e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null