Training in progress, step 40600, checkpoint

last-checkpoint/README.md

@@ -1327,6 +1327,10 @@ You can finetune this model on your own dataset.
 | 0.7121 | 40300 | 0.306         |
 | 0.7130 | 40350 | 0.2629        |
 | 0.7139 | 40400 | 0.2311        |
+| 0.7148 | 40450 | 0.2909        |
+| 0.7157 | 40500 | 0.343         |
+| 0.7165 | 40550 | 0.3013        |
+| 0.7174 | 40600 | 0.3128        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50f06d6c0fd8326af39a398662f171a8273231c42342726a949dca804e1fec3
+oid sha256:86ab7b3916da8a5dc2fefb182305b2800af148c80b90a0e5addb9b673bea08ca
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31f8e8daa44a5969c8468131e422d3890bd1b3dfc09e140da75d5ff08dd8929
+oid sha256:3317b8c5d354e41a8855a79cd943bb15303f4b223b40b4b0117db599f16c0065
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8789e63d322628b9bf8ef047af43291db3bd5935067320bb834f1fe83567f97
+oid sha256:280a7f83a8ba48bb32d168a0a0cd5555d9e11709ce0ba3cfc77af9b48c2160fb
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f096ecf59986ddd611fd8ea1bd90586f9039a1554c47a1316352f4e9e8082419
+oid sha256:2be209d4a461eee1fa1948cfcdede9079955638115f4647a4f1a424013de8c91
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fca1118641eb340cc4f5e2369cd22f797bffa655fc6d743b877326b0bf15332
+oid sha256:206b866093eb1fb8cb9166f733d4bad077c57b2cd0d3adade63bbc86e09d7ad4
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.713894435510947,
+  "epoch": 0.717428566379813,
   "eval_steps": 500,
-  "global_step": 40400,
+  "global_step": 40600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5664,6 +5664,34 @@
       "learning_rate": 1.5909760263886435e-05,
       "loss": 0.2311,
       "step": 40400
+    },
+    {
+      "epoch": 0.7147779682281635,
+      "grad_norm": 1.3199965953826904,
+      "learning_rate": 1.58606742455479e-05,
+      "loss": 0.2909,
+      "step": 40450
+    },
+    {
+      "epoch": 0.7156615009453801,
+      "grad_norm": 1.4839483499526978,
+      "learning_rate": 1.581158822720936e-05,
+      "loss": 0.343,
+      "step": 40500
+    },
+    {
+      "epoch": 0.7165450336625965,
+      "grad_norm": 1.0020859241485596,
+      "learning_rate": 1.5762502208870826e-05,
+      "loss": 0.3013,
+      "step": 40550
+    },
+    {
+      "epoch": 0.717428566379813,
+      "grad_norm": 1.3758106231689453,
+      "learning_rate": 1.571341619053229e-05,
+      "loss": 0.3128,
+      "step": 40600
     }
   ],
   "logging_steps": 50,