Training in progress, step 11500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e095b06f5c65d9c3c8a3debcf3e6201bbcf41c468b57fd9fe8830b5d51ac4f48
+oid sha256:8dfb1303c43437d0a5d16c718f1a0be0355a6bc6198d78fcee515c503884a9a2
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b9380bb79afa61cdc27180520af86aef9f4d10f83ed2161a4655c0531d4686d
+oid sha256:d9169b770e0ac0200417a6d68811804c1fb73c586cfc8a20550b0caa6beef0a3
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb8b27c24f221351a66f6c36da6c9928049823c3f1134500eb9faea09def09e
+oid sha256:68393a5eefa6936320457e661ed8769751e258badc1e65d137b49f873ca59e29
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403e883e32409c0a8b6b9b4a178312db263273af6b84b67a9175809fcce1d74a
+oid sha256:c8a1695a275cff99a2c62fc4abe2a84b274a1c4f4a080a28dd6e841bca4417f1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7333333333333333,
+  "epoch": 0.7666666666666667,
   "eval_steps": 500,
-  "global_step": 11000,
+  "global_step": 11500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -777,6 +777,41 @@
       "learning_rate": 1.5112444444444445e-05,
       "loss": 0.068,
       "step": 11000
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.19551828503608704,
+      "learning_rate": 1.5068e-05,
+      "loss": 0.0693,
+      "step": 11100
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.1611281782388687,
+      "learning_rate": 1.5023555555555557e-05,
+      "loss": 0.0677,
+      "step": 11200
+    },
+    {
+      "epoch": 0.7533333333333333,
+      "grad_norm": 0.18722090125083923,
+      "learning_rate": 1.4979111111111113e-05,
+      "loss": 0.0711,
+      "step": 11300
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.1402270644903183,
+      "learning_rate": 1.4934666666666668e-05,
+      "loss": 0.0649,
+      "step": 11400
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.09549852460622787,
+      "learning_rate": 1.4890222222222223e-05,
+      "loss": 0.0624,
+      "step": 11500
     }
   ],
   "logging_steps": 100,
@@ -796,7 +831,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.679414718464e+16,
+  "total_flos": 2.801206296576e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null