Training in progress, step 495, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca3af260a573b461cd342f7bf7afa505c4101cdfcb62508cb4679571ecbc02c
+oid sha256:5082e216d918cb155f07a0ee9dcc74d8b33063c623f68526dbbb0c4660ac101d
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42b428390e9c7047edbe5f8c842a6e6a63099594ace45e1079150202b30097dd
+oid sha256:d10ac7c4afa049112e9bccd4709339863be1042a9c1356e65f0a6d33f943eb68
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d4663104f7f8c9aa215e9202234c5afb320a2473b8dc4114eff264e4c02057b
+oid sha256:c455b0fa8104f640543b248b2fbe706d034e1d6aeb5559e591ec277167811d01
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c388993843f0e58c8f91775a4c14074f5b54c4aade244b7bc036cc4bac2f6b60
+oid sha256:dfe3b760b122c9a956a1bee0ed9d65cd87b93bd52b73b0ebef3ebe29b040300a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.634098997088321,
+  "epoch": 0.6405693950177936,
   "eval_steps": 386,
-  "global_step": 490,
+  "global_step": 495,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3453,6 +3453,41 @@
       "learning_rate": 9.67451868067933e-05,
       "loss": 0.7876,
       "step": 490
+    },
+    {
+      "epoch": 0.6353930766742155,
+      "grad_norm": 0.7051340937614441,
+      "learning_rate": 9.673053895356543e-05,
+      "loss": 0.8534,
+      "step": 491
+    },
+    {
+      "epoch": 0.63668715626011,
+      "grad_norm": 0.9023073315620422,
+      "learning_rate": 9.671585932789821e-05,
+      "loss": 0.8995,
+      "step": 492
+    },
+    {
+      "epoch": 0.6379812358460045,
+      "grad_norm": 0.7804109454154968,
+      "learning_rate": 9.670114793977243e-05,
+      "loss": 0.788,
+      "step": 493
+    },
+    {
+      "epoch": 0.6392753154318991,
+      "grad_norm": 0.7766551375389099,
+      "learning_rate": 9.66864047991905e-05,
+      "loss": 0.7799,
+      "step": 494
+    },
+    {
+      "epoch": 0.6405693950177936,
+      "grad_norm": 0.8782010078430176,
+      "learning_rate": 9.667162991617633e-05,
+      "loss": 0.897,
+      "step": 495
     }
   ],
   "logging_steps": 1,
@@ -3472,7 +3507,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.477892141298483e+17,
+  "total_flos": 5.5337889998831616e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null