Training in progress, step 515, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a44a782ea638c6f7e9dc51e718ea5f60364b15256a8cf012bd12a3e32e577b7
+oid sha256:10275f345ea0979d1b901ec83beafa54f10605a1616e6e45aaa11cec9a48b9f5
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d81439b95ab9fdfc28944c3f45684bab1b89a36ee16c058a71c1fbf8c0e50d5
+oid sha256:1ee5974f4d7d08ab198cdf6267e534b797bb4e62af773544e265e26ba4912e97
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd7132b96ed38ba9b738ad147e8a862f64c2ac7a948dbbba18a7efce0585f901
+oid sha256:f5436483a49c337b81cda06ce61fa904bc4ee9904d9cddffb112a275af24fded
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a13a5d867c4b3340715fb328361f350e2a0ea77e86afd98eac6d64dcb61c2c63
+oid sha256:811e492420306f2812d71dfa20a74673a76b05941954bb57f6f8b780cb51e734
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6599805888062116,
+  "epoch": 0.6664509867356843,
   "eval_steps": 386,
-  "global_step": 510,
+  "global_step": 515,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3593,6 +3593,41 @@
       "learning_rate": 9.644620446138077e-05,
       "loss": 0.9221,
       "step": 510
+    },
+    {
+      "epoch": 0.6612746683921061,
+      "grad_norm": 0.8938276767730713,
+      "learning_rate": 9.643092308030109e-05,
+      "loss": 1.0021,
+      "step": 511
+    },
+    {
+      "epoch": 0.6625687479780007,
+      "grad_norm": 1.0916978120803833,
+      "learning_rate": 9.641561013049309e-05,
+      "loss": 0.9354,
+      "step": 512
+    },
+    {
+      "epoch": 0.6638628275638951,
+      "grad_norm": 0.8139733672142029,
+      "learning_rate": 9.64002656223682e-05,
+      "loss": 0.923,
+      "step": 513
+    },
+    {
+      "epoch": 0.6651569071497897,
+      "grad_norm": 0.8234017491340637,
+      "learning_rate": 9.638488956635925e-05,
+      "loss": 0.8491,
+      "step": 514
+    },
+    {
+      "epoch": 0.6664509867356843,
+      "grad_norm": 0.7203138470649719,
+      "learning_rate": 9.636948197292052e-05,
+      "loss": 0.8313,
+      "step": 515
     }
   ],
   "logging_steps": 1,
@@ -3612,7 +3647,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.701479575637197e+17,
+  "total_flos": 5.757376434221875e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null