Training in progress, step 380, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563388d59e2fc47539c2607dfcb98e7c36a067def127e760f4aad641b568708d
+oid sha256:eacc218551180e6caca9be38e56e1c8a8c92bb7ca702a41f927879e57aea7285
 size 1316913776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833ca2a5876e453538364f187fb25a4b57c6a540592c61f0bf2dbced760014c2
+oid sha256:15e3c344d56e84dfa5f4ffbbc603b4c3d0efce27c670f812e55f42803d067aed
 size 8908124

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0794332331472735,
+  "epoch": 0.08158007728638901,
   "eval_steps": 500,
-  "global_step": 370,
+  "global_step": 380,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -266,6 +266,13 @@
       "learning_rate": 0.0004602833834263633,
       "loss": 0.8609,
       "step": 370
+    },
+    {
+      "epoch": 0.08158007728638901,
+      "grad_norm": 1.1254737377166748,
+      "learning_rate": 0.0004592099613568055,
+      "loss": 0.8697,
+      "step": 380
     }
   ],
   "logging_steps": 10,
@@ -273,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 2.7531407918716416e+16,
+  "total_flos": 2.832153719613005e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null