Training in progress, step 41200, checkpoint

last-checkpoint/README.md

@@ -1339,6 +1339,10 @@ You can finetune this model on your own dataset.
 | 0.7227 | 40900 | 0.3322        |
 | 0.7236 | 40950 | 0.3424        |
 | 0.7245 | 41000 | 0.2834        |
+| 0.7254 | 41050 | 0.2776        |
+| 0.7263 | 41100 | 0.2924        |
+| 0.7271 | 41150 | 0.3982        |
+| 0.7280 | 41200 | 0.3379        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bad5fe2e60c5aa24260d1942f5fd36c57da4fa95b5377f04b02dcc5ceb9e653
+oid sha256:822f3843e5d129c0bef56a9f39c1ba41bc1fa63adfc0cc1868ef514ec0e5351b
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fece1064662d61321c117cc1d24216b16971ad97b1195b94af13fb853181101
+oid sha256:086abfb2bf298dfb180a5caff3f861d5e6d3d3f4b12f1b97c28016e45648410e
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d73c58855bdaef926976cbbf2d9665190e116bcc636d4b89a717f6e32bf6a98
+oid sha256:4b9af559530a0818383bd31a393ecc6f9d55de4b1055f24c5ea4deb160850318
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a4677c24f01289fca4e4e6cb6d863cf74dbec8f2665874e2aeb1133c6e53329
+oid sha256:360bf556a97129543cdfd5bc8f9267eddea0b0255ab50b0df912124a90a12812
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9861609e13b6dfba877602ae0e61dca8ad368849f8b20c6f7958302bb7e1b3b
+oid sha256:be053631e025ff40e9a33566316f50efe9d70bdf16e7a6393f50270033d19672
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7244968281175452,
+  "epoch": 0.7280309589864112,
   "eval_steps": 500,
-  "global_step": 41000,
+  "global_step": 41200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5748,6 +5748,34 @@
       "learning_rate": 1.532170976419077e-05,
       "loss": 0.2834,
       "step": 41000
+    },
+    {
+      "epoch": 0.7253803608347618,
+      "grad_norm": 2.0050973892211914,
+      "learning_rate": 1.5272623745852232e-05,
+      "loss": 0.2776,
+      "step": 41050
+    },
+    {
+      "epoch": 0.7262638935519782,
+      "grad_norm": 1.4293886423110962,
+      "learning_rate": 1.5223537727513695e-05,
+      "loss": 0.2924,
+      "step": 41100
+    },
+    {
+      "epoch": 0.7271474262691947,
+      "grad_norm": 1.5391188859939575,
+      "learning_rate": 1.5174451709175158e-05,
+      "loss": 0.3982,
+      "step": 41150
+    },
+    {
+      "epoch": 0.7280309589864112,
+      "grad_norm": 1.4493207931518555,
+      "learning_rate": 1.5125365690836625e-05,
+      "loss": 0.3379,
+      "step": 41200
     }
   ],
   "logging_steps": 50,