Training in progress, step 1600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0174b0116cfb9af7294711107315070cb5df5a403799c39097e36318345b480a
+oid sha256:261060049a7dda557484b2457355c565a4a3dec4bad82ebd69d3da19bb63baea
 size 3826461296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8804cc6d7eb057620b329159d309aa3c2e9154e9801508307ebcc5c8472c5480
+oid sha256:cd5a824004382fafc96a45aa34398b26619eb1ad1e0bae9e057d7991c60713ca
 size 2479955235

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c90e73b569a38f99c2197447433676c2eaa22ce221aeecf0a7d6e7d0501c17
+oid sha256:66ee06c65c8a9fafa99e46b2c6a4e28ded33e6954d7a37d2b23e4b02c9c3171d
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc00765bb2f7c05738fc9294fd5cefadbd3816d98397372497b3027b71c424b
+oid sha256:c656881e8cfeb75270ca3557627f44c2ff0c812b9a941b53a9228574ee283934
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6,
+  "epoch": 0.64,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1058,6 +1058,76 @@
       "learning_rate": 2.0176848874598074e-05,
       "loss": 0.3766,
       "step": 1500
+    },
+    {
+      "epoch": 0.604,
+      "grad_norm": 13.472972869873047,
+      "learning_rate": 1.9975884244372992e-05,
+      "loss": 0.5891,
+      "step": 1510
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 20.179187774658203,
+      "learning_rate": 1.977491961414791e-05,
+      "loss": 0.3744,
+      "step": 1520
+    },
+    {
+      "epoch": 0.612,
+      "grad_norm": 12.630617141723633,
+      "learning_rate": 1.957395498392283e-05,
+      "loss": 0.4564,
+      "step": 1530
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 20.459508895874023,
+      "learning_rate": 1.9372990353697752e-05,
+      "loss": 0.4566,
+      "step": 1540
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 16.580251693725586,
+      "learning_rate": 1.917202572347267e-05,
+      "loss": 0.447,
+      "step": 1550
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 13.90858268737793,
+      "learning_rate": 1.897106109324759e-05,
+      "loss": 0.4133,
+      "step": 1560
+    },
+    {
+      "epoch": 0.628,
+      "grad_norm": 10.297750473022461,
+      "learning_rate": 1.877009646302251e-05,
+      "loss": 0.9703,
+      "step": 1570
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 19.886884689331055,
+      "learning_rate": 1.856913183279743e-05,
+      "loss": 0.6253,
+      "step": 1580
+    },
+    {
+      "epoch": 0.636,
+      "grad_norm": 10.709681510925293,
+      "learning_rate": 1.836816720257235e-05,
+      "loss": 0.4657,
+      "step": 1590
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 16.986331939697266,
+      "learning_rate": 1.8167202572347267e-05,
+      "loss": 0.3986,
+      "step": 1600
     }
   ],
   "logging_steps": 10,
@@ -1077,7 +1147,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.704157205966029e+16,
+  "total_flos": 2.8862224942546944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null