Training in progress, step 275, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12e70752b751619eca556d581de22f95ebd6c29351c9409ce88f9658d65a441e
+oid sha256:05a0a61b6f10e0b663c7393b8364bbe7a737d8c565430ce2d68b95474c31c1a5
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee29f0e47a32e109a2136050325592d682eb66f3b314d215d6ffb567d8b9b52f
+oid sha256:7137e1d123529aa3be36b999601ee44510cfd22a08bdd5f889d472bd3c96a8c5
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e770fb11b58b411b8e274fe1728430d5130bebebd0fbd2dda121e2908cc002
+oid sha256:9b7e0c0119a97b0d02303a46cafb008390c13bc174db8f9999aab74f3b0c0f3f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:208227daf0fc218aab910a008fc4c360acd465f7afe242046281eec474cdc16d
+oid sha256:321b80874f1460360522a6113a37b793358a0a363cc85543d6a6f1b21f904a79
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3494014881915238,
+  "epoch": 0.35587188612099646,
   "eval_steps": 386,
-  "global_step": 270,
+  "global_step": 275,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1905,6 +1905,41 @@
       "learning_rate": 9.91795655752451e-05,
       "loss": 0.8769,
       "step": 270
+    },
+    {
+      "epoch": 0.35069556777741834,
+      "grad_norm": 0.8562968373298645,
+      "learning_rate": 9.917211082714933e-05,
+      "loss": 1.0078,
+      "step": 271
+    },
+    {
+      "epoch": 0.35198964736331284,
+      "grad_norm": 0.810517430305481,
+      "learning_rate": 9.916462264657142e-05,
+      "loss": 0.8847,
+      "step": 272
+    },
+    {
+      "epoch": 0.3532837269492074,
+      "grad_norm": 0.8934103846549988,
+      "learning_rate": 9.915710103860263e-05,
+      "loss": 0.8633,
+      "step": 273
+    },
+    {
+      "epoch": 0.3545778065351019,
+      "grad_norm": 0.8963167667388916,
+      "learning_rate": 9.914954600835699e-05,
+      "loss": 0.8411,
+      "step": 274
+    },
+    {
+      "epoch": 0.35587188612099646,
+      "grad_norm": 0.774557888507843,
+      "learning_rate": 9.91419575609712e-05,
+      "loss": 0.958,
+      "step": 275
     }
   ],
   "logging_steps": 1,
@@ -1924,7 +1959,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.0184303635726336e+17,
+  "total_flos": 3.074327222157312e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null