Training in progress, step 41000, checkpoint

last-checkpoint/README.md

@@ -1335,6 +1335,10 @@ You can finetune this model on your own dataset.
 | 0.7192 | 40700 | 0.2873        |
 | 0.7201 | 40750 | 0.3705        |
 | 0.7210 | 40800 | 0.2985        |
+| 0.7218 | 40850 | 0.3355        |
+| 0.7227 | 40900 | 0.3322        |
+| 0.7236 | 40950 | 0.3424        |
+| 0.7245 | 41000 | 0.2834        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78a54fb4d46ba6a28639611752cbd90c81e4f5c2899787ac51015d1444478c6
+oid sha256:1bad5fe2e60c5aa24260d1942f5fd36c57da4fa95b5377f04b02dcc5ceb9e653
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18056243182ea1caa1b86090618604e7d1e429f23a12ff1faad08a57f30e9f02
+oid sha256:8fece1064662d61321c117cc1d24216b16971ad97b1195b94af13fb853181101
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d701f7ad37b76a01e770182d60edba5e764045eee0c4420747669dc57f30af68
+oid sha256:7d73c58855bdaef926976cbbf2d9665190e116bcc636d4b89a717f6e32bf6a98
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc39115c671fd04a36f4927fc18f9015d2dce27d719fc74d0c9d59b53289a70
+oid sha256:2a4677c24f01289fca4e4e6cb6d863cf74dbec8f2665874e2aeb1133c6e53329
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb354beb7a0d4ccd477dc950d57455f0fa927e9ecbdea63314e56687b97ea814
+oid sha256:d9861609e13b6dfba877602ae0e61dca8ad368849f8b20c6f7958302bb7e1b3b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7209626972486791,
+  "epoch": 0.7244968281175452,
   "eval_steps": 500,
-  "global_step": 40800,
+  "global_step": 41000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5720,6 +5720,34 @@
       "learning_rate": 1.5518053837544916e-05,
       "loss": 0.2985,
       "step": 40800
+    },
+    {
+      "epoch": 0.7218462299658956,
+      "grad_norm": 1.8306645154953003,
+      "learning_rate": 1.546896781920638e-05,
+      "loss": 0.3355,
+      "step": 40850
+    },
+    {
+      "epoch": 0.7227297626831122,
+      "grad_norm": 1.4840078353881836,
+      "learning_rate": 1.541988180086784e-05,
+      "loss": 0.3322,
+      "step": 40900
+    },
+    {
+      "epoch": 0.7236132954003287,
+      "grad_norm": 2.7773265838623047,
+      "learning_rate": 1.5370795782529303e-05,
+      "loss": 0.3424,
+      "step": 40950
+    },
+    {
+      "epoch": 0.7244968281175452,
+      "grad_norm": 1.3592840433120728,
+      "learning_rate": 1.532170976419077e-05,
+      "loss": 0.2834,
+      "step": 41000
     }
   ],
   "logging_steps": 50,