Training in progress, step 31200, checkpoint

last-checkpoint/README.md

@@ -1281,6 +1281,10 @@ You can finetune this model on your own dataset.
 | 0.5460 | 30900 | 0.331         |
 | 0.5469 | 30950 | 0.2846        |
 | 0.5478 | 31000 | 0.3647        |
+| 0.5487 | 31050 | 0.3475        |
+| 0.5496 | 31100 | 0.2833        |
+| 0.5504 | 31150 | 0.3           |
+| 0.5513 | 31200 | 0.3568        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d75ffa8acb9d0ae6da6b85c5ebacb5d6d497b0b7f8d1e0cc906632d66303da
+oid sha256:57ba70ef39f7de14bf486cd6a1d1eb679e64ef73a054af28b2b85197a684e102
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ce5db6bab84b13b8d6237d74a48b1c574cceb26d03115a289d544fd81b83fe0
+oid sha256:9ff78a2cf01e3f4659cebb48c444154cc30791c7f270bbce76100fba6585b1f7
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225aac588847ab0002b2ca78215dc480b08f8f2752e40d301dfd2554473eaa86
+oid sha256:841783816c90320afe8451e0bfbb0199a5902c04c786b414a06919466808b3cc
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17b09e37e3cf1eb4e07e5a39443f3088190a89ec52eee73b652e920bd5e3c6d
+oid sha256:fc906030957a3fd71ac5d5f065e62c1d0ee722af605316e3fb4aeb71bb2da6d9
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d9c6b8e683bd0522d336f6d260614dd403087df118f434096a2340dd6c2f5dd
+oid sha256:c7e97975d3fced0482e8faf4c84b2ad2283b6983f383d82a9b91bf8d75fbaca1
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5477902846742415,
+  "epoch": 0.5513244155431075,
   "eval_steps": 500,
-  "global_step": 31000,
+  "global_step": 31200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4348,6 +4348,34 @@
       "learning_rate": 2.5134004830064205e-05,
       "loss": 0.3647,
       "step": 31000
+    },
+    {
+      "epoch": 0.548673817391458,
+      "grad_norm": 1.0688265562057495,
+      "learning_rate": 2.5084918811725673e-05,
+      "loss": 0.3475,
+      "step": 31050
+    },
+    {
+      "epoch": 0.5495573501086746,
+      "grad_norm": 1.7052621841430664,
+      "learning_rate": 2.503583279338713e-05,
+      "loss": 0.2833,
+      "step": 31100
+    },
+    {
+      "epoch": 0.5504408828258911,
+      "grad_norm": 1.5378305912017822,
+      "learning_rate": 2.4986746775048596e-05,
+      "loss": 0.3,
+      "step": 31150
+    },
+    {
+      "epoch": 0.5513244155431075,
+      "grad_norm": 3.8670883178710938,
+      "learning_rate": 2.493766075671006e-05,
+      "loss": 0.3568,
+      "step": 31200
     }
   ],
   "logging_steps": 50,