Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee3e8177e6fadd097833e7afe6be3da19174e3ec791ceabfd5e2aef8276dfb7
+oid sha256:b8a61fd73bc588dbdc24db480c467fa85865340704d30acbb701842098e2e69f
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3b2b702f5cef156784c924666ba6f0516aba8a128ff1c8252b58be7c17dd2df
+oid sha256:7b1a7761b758c7fd9d022ced7c255b59c0684b9396756996b22a9e7e9bd5c35b
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05dd11bd3960ad0fa940da6d1dc661f5e30b05ee951391d57c064dbbfbc68d4f
+oid sha256:5c102029d2f3d2ad8c4cbe0e9eb23a6db91408d1239150f6a5fe227f52911673
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b02bc33df1b7c20f0491626d0e42bd29d99a710da7df8f3162d39edb7196e8
+oid sha256:1aa8492157bf2c1d0061046d13454f95f14ea95d23b20e0a054ab57ecde42b5d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9093931837073983,
+  "epoch": 3.117206982543641,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -121,6 +121,21 @@
       "learning_rate": 8.367414796342478e-06,
       "loss": 0.3333,
       "step": 7000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.2934778034687042,
+      "eval_runtime": 26.7608,
+      "eval_samples_per_second": 18.46,
+      "eval_steps_per_second": 4.634,
+      "step": 7218
+    },
+    {
+      "epoch": 3.117206982543641,
+      "grad_norm": 0.4342059791088104,
+      "learning_rate": 7.536159600997507e-06,
+      "loss": 0.3313,
+      "step": 7500
     }
   ],
   "logging_steps": 500,
@@ -140,7 +155,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.704960301989888e+16,
+  "total_flos": 1.826690984312832e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null