Training in progress, step 520, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10275f345ea0979d1b901ec83beafa54f10605a1616e6e45aaa11cec9a48b9f5
+oid sha256:3e50a11a2f59ac5336df1f861c9746e3ea52482c3b25e71230c372afe31efafd
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee5974f4d7d08ab198cdf6267e534b797bb4e62af773544e265e26ba4912e97
+oid sha256:dc1656d9776aa288a9d3c783e91c4974f0bbbcdbed454e7021b914cb6025fb87
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5436483a49c337b81cda06ce61fa904bc4ee9904d9cddffb112a275af24fded
+oid sha256:cdcc456807bf80d9919c70d11abc1b5d0f53d48b9062054a56c7c3a7e1457747
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:811e492420306f2812d71dfa20a74673a76b05941954bb57f6f8b780cb51e734
+oid sha256:18af6c6b5b006201434fd2ba8945bc39086f249834bda28bb96a3935a9852f63
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6664509867356843,
+  "epoch": 0.6729213846651569,
   "eval_steps": 386,
-  "global_step": 515,
+  "global_step": 520,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3628,6 +3628,41 @@
       "learning_rate": 9.636948197292052e-05,
       "loss": 0.8313,
       "step": 515
+    },
+    {
+      "epoch": 0.6677450663215788,
+      "grad_norm": 0.7210227251052856,
+      "learning_rate": 9.635404285252777e-05,
+      "loss": 0.8593,
+      "step": 516
+    },
+    {
+      "epoch": 0.6690391459074733,
+      "grad_norm": 0.7367059588432312,
+      "learning_rate": 9.633857221567815e-05,
+      "loss": 0.9743,
+      "step": 517
+    },
+    {
+      "epoch": 0.6703332254933678,
+      "grad_norm": 0.8669779896736145,
+      "learning_rate": 9.632307007289027e-05,
+      "loss": 0.8914,
+      "step": 518
+    },
+    {
+      "epoch": 0.6716273050792624,
+      "grad_norm": 0.700624406337738,
+      "learning_rate": 9.630753643470416e-05,
+      "loss": 0.9032,
+      "step": 519
+    },
+    {
+      "epoch": 0.6729213846651569,
+      "grad_norm": 0.81085205078125,
+      "learning_rate": 9.629197131168124e-05,
+      "loss": 0.8612,
+      "step": 520
     }
   ],
   "logging_steps": 1,
@@ -3647,7 +3682,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.757376434221875e+17,
+  "total_flos": 5.813273292806554e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null