Training in progress, step 475, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdab1049475a51ebe99ec1563497292e541f1090609b07ad0311a3efac629ba7
+oid sha256:879581c8cde65209001febc8121423bbb6c6d25938253aee13a3f002be25dff9
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:806c1499d556a9d045bd47b9cd191899ad3bf6224f639aedf0ef444520a231a5
+oid sha256:cc460660c321ed6db97736e979d5a8bdec8abd84ec257d7ef8fc8cc7850a7b42
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb24a4d1ef58f8e4aad8026cfd12b70f38d4b04f7c174b4ccd8e575a261ba876
+oid sha256:11e484cbc53befcdb8519a1e2e73a08c1fb53f1ca7918eb21b38e07026813e51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49c6f8ca0432c171a47c1efd4321285a4935797f726487b10e53c92fb5e64a4c
+oid sha256:4f20eb69b1dfb1537148de4239113be751a9166c0eab80c74a3c6c033f6caca6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6082174053704302,
+  "epoch": 0.6146878032999029,
   "eval_steps": 386,
-  "global_step": 470,
+  "global_step": 475,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3313,6 +3313,41 @@
       "learning_rate": 9.70314564801922e-05,
       "loss": 0.8776,
       "step": 470
+    },
+    {
+      "epoch": 0.6095114849563248,
+      "grad_norm": 0.8132034540176392,
+      "learning_rate": 9.701744613839963e-05,
+      "loss": 0.9575,
+      "step": 471
+    },
+    {
+      "epoch": 0.6108055645422193,
+      "grad_norm": 0.8051428198814392,
+      "learning_rate": 9.700340382909739e-05,
+      "loss": 0.7546,
+      "step": 472
+    },
+    {
+      "epoch": 0.6120996441281139,
+      "grad_norm": 0.7600153088569641,
+      "learning_rate": 9.698932956183296e-05,
+      "loss": 0.8556,
+      "step": 473
+    },
+    {
+      "epoch": 0.6133937237140085,
+      "grad_norm": 0.9171023964881897,
+      "learning_rate": 9.697522334617555e-05,
+      "loss": 0.8196,
+      "step": 474
+    },
+    {
+      "epoch": 0.6146878032999029,
+      "grad_norm": 1.0437992811203003,
+      "learning_rate": 9.696108519171605e-05,
+      "loss": 1.0997,
+      "step": 475
     }
   ],
   "logging_steps": 1,
@@ -3332,7 +3367,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.2543047069597696e+17,
+  "total_flos": 5.310201565544448e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null