Training in progress, step 37000, checkpoint

last-checkpoint/README.md

@@ -1253,6 +1253,10 @@ You can finetune this model on your own dataset.
 | 0.6485 | 36700 | 0.3111        |
 | 0.6494 | 36750 | 0.3299        |
 | 0.6503 | 36800 | 0.3994        |
+| 0.6512 | 36850 | 0.3595        |
+| 0.6520 | 36900 | 0.3572        |
+| 0.6529 | 36950 | 0.3085        |
+| 0.6538 | 37000 | 0.2647        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4bf73f234398da4bc2354c62f35d8522fb992fe0cc8508b01e537eeb46ba200
+oid sha256:5aa3e074a25abb8c340316265b8419fb45e38d5ea71e4312b6d0194cb38cc86b
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deab99f5ed27bec630b2e3f842027b1cc6d0187c2406e2f581cb275f3a90e563
+oid sha256:a86c17b77d1cfac3584af9a6619882b78c1f9bc7dcb85e0259432165076b9f36
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55608d8af777fe7d98d4ef8f564bad9679b83c0050069b201bb564a1ddf9edd
+oid sha256:3da82f98ab298f77c390cd353b9bced87815dd73e91293360907ff091eb61d4e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7ed611a4947df61c53bc83c6d678cf93c3033600c02343412dcb7919a293d43
+oid sha256:952a0b2337ddfcc5838b84a78a584c51460d6072b3d324731f0a62584e450719
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a56ae9bbdefa7bba62bf8ab81e508fcd56be09ecc92cd7e39c632b1b315132f
+oid sha256:a249cc3fbdfe88ea20fb6dbfcb1191ec424d82ef41e7dafc1d1c85f14b5994e9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6502800798713576,
+  "epoch": 0.6538142107402237,
   "eval_steps": 500,
-  "global_step": 36800,
+  "global_step": 37000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5160,6 +5160,34 @@
       "learning_rate": 1.9442971863894287e-05,
       "loss": 0.3994,
       "step": 36800
+    },
+    {
+      "epoch": 0.6511636125885741,
+      "grad_norm": 2.2977466583251953,
+      "learning_rate": 1.9393885845555755e-05,
+      "loss": 0.3595,
+      "step": 36850
+    },
+    {
+      "epoch": 0.6520471453057907,
+      "grad_norm": 1.6370161771774292,
+      "learning_rate": 1.9344799827217217e-05,
+      "loss": 0.3572,
+      "step": 36900
+    },
+    {
+      "epoch": 0.6529306780230072,
+      "grad_norm": 1.4357324838638306,
+      "learning_rate": 1.9295713808878678e-05,
+      "loss": 0.3085,
+      "step": 36950
+    },
+    {
+      "epoch": 0.6538142107402237,
+      "grad_norm": 1.8057055473327637,
+      "learning_rate": 1.9246627790540143e-05,
+      "loss": 0.2647,
+      "step": 37000
     }
   ],
   "logging_steps": 50,