Training in progress, step 5960, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:608a6b07ab17338bd6282af158218a38aaf660c765e9d6ab6b3901cfdb0f98b7
+oid sha256:010f676ba5602979d0c7829e0358b3d388c49d2f6fee5237a36a28449c16b492
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a7d513c9296103d22d55f32962fde622c0d973a7f373aa4a9c0fe2c3f05177
+oid sha256:102af6e58d98e65b6dcfb4906ef10405c96eb13273b480ae020aefeb341b6282
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0127f56f128ab49d16717c9bb322e33079e0546dc1e679e0ba07a312af3b19a
+oid sha256:d6347c5bcc78e95a65da46d270d8df1f2b00359d0f1d79efc0275b98ad678c0a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f5d4d06571f17a13a7fb5f8c4d4c26d3ffcd4700c7abd904f5f1753c1fd7ec
+oid sha256:a94fd165a88f9a6615f126687e3aefb9cf9a572c3aa79a5a0f1147469e4c177d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4752,
+  "epoch": 0.4768,
   "eval_steps": 500,
-  "global_step": 5940,
+  "global_step": 5960,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2086,6 +2086,13 @@
       "learning_rate": 2.4732482149416325e-05,
       "loss": 3.4577,
       "step": 5940
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 22.31077766418457,
+      "learning_rate": 2.4695464102141002e-05,
+      "loss": 3.4816,
+      "step": 5960
     }
   ],
   "logging_steps": 20,
@@ -2093,7 +2100,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.4047360541392896e+16,
+  "total_flos": 1.4099423524651008e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null