Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3bd28dbe9b67c7c79a728cc6ef3a17e018e776493c51cc28b9850cacda1a28
+oid sha256:2cba6a817ce807aa2030568b8a80ebdf2be6d39913f11478171948df20bf1591
 size 540001920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5b1637f39e7f335ccbbc3a3cf03e10ddebbdfe338e35900be2549e66c7c6dc3
+oid sha256:2b8c858572a5adcbb191eb68507ac98b67c04d83072fff86cf9ee81d61cd3180
 size 1080097722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be429403c8ea4f14070329f8b81f4827eb98d0a6af5eb80c44776186a03d3922
+oid sha256:b6ff394165f73401fba693b1c9199395d3a0185774e9f5cb4854f8f57ab79254
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee4efd95ffaedf9d6966a026cb929978b9bc97b63419117775055634bf0ba6a2
+oid sha256:31ef11b300d8c3c19173b377e250e75e5178ce980848b2209600bb9e01deb121
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7985989492119088,
+  "epoch": 3.5183887915936953,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,20 @@
       "learning_rate": 2.6600777680523415e-06,
       "loss": 0.7965,
       "step": 400
+    },
+    {
+      "epoch": 3.168126094570928,
+      "grad_norm": 2.1081647872924805,
+      "learning_rate": 9.579705411572493e-08,
+      "loss": 0.7545,
+      "step": 450
+    },
+    {
+      "epoch": 3.5183887915936953,
+      "grad_norm": 1.9008880853652954,
+      "learning_rate": 1.0620572723108236e-06,
+      "loss": 0.76,
+      "step": 500
     }
   ],
   "logging_steps": 50,
@@ -91,7 +105,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2503700250624000.0,
+  "total_flos": 3134720507904000.0,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77cce5b53a624cbf3645ca0424e7a720a8ea6809cfc88370b7ba8e8c092440e8
+oid sha256:f003aa6f2cd437508f0757ab59fac94f26be778951221d5f13660a3cd9ae7d36
 size 5304