Training in progress, step 340, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8a01100c62c7cacac7666b84a6c44a0483196ab6b8c9c7c4be1aaf269b5663
+oid sha256:99afcca2ca463465c80ebc2ad481b7a4ed0caf2ca83dd48c6cb23804e9eb9066
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64cb9e6475db44bc10b56c5c1601234f794b800de82fcff62a83d3bd5c038a0
+oid sha256:9fde729599458b8685083cec6dbecbabdb6de1fa6bfa6aaa52e8fac8029ce439
 size 255266042

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988517d151ddb318c6517f3fcf2ff62485ab8c9a84ec571fb5664a92bec4067b
+oid sha256:7708d765c69898ac6704acdc2b9aef6ebc71ee392dc45c5b50d1715bf3068ddb
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae33deae3edf829d48de6c73aa057338b3796fe98797d3f8547591e4e524394f
+oid sha256:d3c46256615d40b83cb0b5dbb74b01f9ee649dc90f7b090c538d38a043381326
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc99919da5a7742331644c92ad35399b61089cf3cf76c5e4355b2e567e5f74d4
+oid sha256:775af4447ea22c8fde6b9577374f0010f59aa5050c5eb44816a7c00e793e5d27
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 26.666666666666668,
+  "epoch": 28.333333333333332,
   "eval_steps": 40,
-  "global_step": 320,
+  "global_step": 340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -303,6 +303,20 @@
       "eval_samples_per_second": 146.0,
       "eval_steps_per_second": 2.334,
       "step": 320
+    },
+    {
+      "epoch": 27.5,
+      "grad_norm": 3.15625,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 2.703,
+      "step": 330
+    },
+    {
+      "epoch": 28.333333333333332,
+      "grad_norm": 4.15625,
+      "learning_rate": 8.626464421815919e-05,
+      "loss": 2.692,
+      "step": 340
     }
   ],
   "logging_steps": 10,
@@ -322,7 +336,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.074867763511296e+16,
+  "total_flos": 2.203527958180659e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null