Training in progress, step 280, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05a0a61b6f10e0b663c7393b8364bbe7a737d8c565430ce2d68b95474c31c1a5
+oid sha256:766bc29da4dd8f6ea69d080821e925bf3230dbf524883a26bacdbe8e6bdd7a55
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7137e1d123529aa3be36b999601ee44510cfd22a08bdd5f889d472bd3c96a8c5
+oid sha256:7074266859ed51b765dcb9e59295560b54f7517b3b32919d5126064139e6615c
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b7e0c0119a97b0d02303a46cafb008390c13bc174db8f9999aab74f3b0c0f3f
+oid sha256:7be84e9390ed163408a0abac028539ac68753c7bc3079d2a87d83274ace9ae69
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321b80874f1460360522a6113a37b793358a0a363cc85543d6a6f1b21f904a79
+oid sha256:f975d6c1fc2270e579841b403d67bdb756eda7f69f91461b9a04eabdad070c25
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.35587188612099646,
+  "epoch": 0.3623422840504691,
   "eval_steps": 386,
-  "global_step": 275,
+  "global_step": 280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1940,6 +1940,41 @@
       "learning_rate": 9.91419575609712e-05,
       "loss": 0.958,
       "step": 275
+    },
+    {
+      "epoch": 0.35716596570689096,
+      "grad_norm": 0.8483523726463318,
+      "learning_rate": 9.913433570160469e-05,
+      "loss": 0.905,
+      "step": 276
+    },
+    {
+      "epoch": 0.3584600452927855,
+      "grad_norm": 0.8082010746002197,
+      "learning_rate": 9.912668043543964e-05,
+      "loss": 0.8633,
+      "step": 277
+    },
+    {
+      "epoch": 0.35975412487868,
+      "grad_norm": 0.8654133677482605,
+      "learning_rate": 9.911899176768091e-05,
+      "loss": 0.8465,
+      "step": 278
+    },
+    {
+      "epoch": 0.3610482044645746,
+      "grad_norm": 0.8709694743156433,
+      "learning_rate": 9.911126970355609e-05,
+      "loss": 0.9286,
+      "step": 279
+    },
+    {
+      "epoch": 0.3623422840504691,
+      "grad_norm": 0.8783992528915405,
+      "learning_rate": 9.910351424831546e-05,
+      "loss": 0.9349,
+      "step": 280
     }
   ],
   "logging_steps": 1,
@@ -1959,7 +1994,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.074327222157312e+17,
+  "total_flos": 3.1302240807419904e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null