Training in progress, step 36800, checkpoint

last-checkpoint/README.md

@@ -1249,6 +1249,10 @@ You can finetune this model on your own dataset.
 | 0.6450 | 36500 | 0.3385        |
 | 0.6459 | 36550 | 0.3423        |
 | 0.6467 | 36600 | 0.3793        |
+| 0.6476 | 36650 | 0.3819        |
+| 0.6485 | 36700 | 0.3111        |
+| 0.6494 | 36750 | 0.3299        |
+| 0.6503 | 36800 | 0.3994        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7dd164817c500b3b0b3eb309058c161c44231d55e86de5617741cab6d433f6
+oid sha256:a4bf73f234398da4bc2354c62f35d8522fb992fe0cc8508b01e537eeb46ba200
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc0cc40d7f31f7445b2755794da94775756808444c54ed79215a2f4ba4587b5d
+oid sha256:deab99f5ed27bec630b2e3f842027b1cc6d0187c2406e2f581cb275f3a90e563
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601eaff9ad155807e284a57753f11180748beedbe0867ec2d87c3473c45686f9
+oid sha256:b55608d8af777fe7d98d4ef8f564bad9679b83c0050069b201bb564a1ddf9edd
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96159ff1a27b0e4bf72ec118631397adcea3c517425f37b884cdcd074e28ca52
+oid sha256:e7ed611a4947df61c53bc83c6d678cf93c3033600c02343412dcb7919a293d43
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:084dd4771d83f8fe540ab84c096a6087e69ee6b4c24571b41efb4b565bf57160
+oid sha256:0a56ae9bbdefa7bba62bf8ab81e508fcd56be09ecc92cd7e39c632b1b315132f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6467459490024916,
+  "epoch": 0.6502800798713576,
   "eval_steps": 500,
-  "global_step": 36600,
+  "global_step": 36800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5132,6 +5132,34 @@
       "learning_rate": 1.9638334216881666e-05,
       "loss": 0.3793,
       "step": 36600
+    },
+    {
+      "epoch": 0.6476294817197081,
+      "grad_norm": 4.349328517913818,
+      "learning_rate": 1.95902299189099e-05,
+      "loss": 0.3819,
+      "step": 36650
+    },
+    {
+      "epoch": 0.6485130144369246,
+      "grad_norm": 1.804661750793457,
+      "learning_rate": 1.954114390057136e-05,
+      "loss": 0.3111,
+      "step": 36700
+    },
+    {
+      "epoch": 0.6493965471541411,
+      "grad_norm": 2.6138484477996826,
+      "learning_rate": 1.9492057882232826e-05,
+      "loss": 0.3299,
+      "step": 36750
+    },
+    {
+      "epoch": 0.6502800798713576,
+      "grad_norm": 1.8608500957489014,
+      "learning_rate": 1.9442971863894287e-05,
+      "loss": 0.3994,
+      "step": 36800
     }
   ],
   "logging_steps": 50,