Training in progress, step 3780, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2eb339fca1743ce5981d75d94271aea8c49805aa8787cc062a2e480f02e91a8
+oid sha256:4223f69fa5c4d343cdb0daf20def262d26468340b68b3012ba5b5bf860add746
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819c50564431ec790e5c787d93b2db9cabbb70df63553d50a801172070601bd3
+oid sha256:07336ce007d26d9a03fa7d6fb0fb6a9b44ea05300d930f065fe4546aa4d1e107
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e850e7ecc226d31ccfa0012c8cc354a952ec0a60022ef713d966322a18df683d
+oid sha256:0b38fda0416b95acf561519c239d9553c03304b18c4ad47455ccbf998847d400
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c260417484aa6b4e9e662c09fdefa26287d404d4aaa654726d7eb8d7f1d0b789
+oid sha256:eab6ea1f9b7df74951725865c85704c6f9d44947e8a6d8f259ab0d7413d273be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3008,
+  "epoch": 0.3024,
   "eval_steps": 500,
-  "global_step": 3760,
+  "global_step": 3780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1323,6 +1323,13 @@
       "learning_rate": 2.8078528754588207e-05,
       "loss": 3.5173,
       "step": 3760
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 28.02115821838379,
+      "learning_rate": 2.805467086984027e-05,
+      "loss": 3.4905,
+      "step": 3780
     }
   ],
   "logging_steps": 20,
@@ -1330,7 +1337,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8883020977766400.0,
+  "total_flos": 8928030689820672.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null